feat(telemetry): add 7-day validation agreement window to ValidationTracker

Add window7d_ deque, agreementPct7d(), agreements7d(), missed7d() to
match the external xrpl-validator-dashboard's 7-day agreement tracking.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.clang-format

@@ -37,7 +37,7 @@ BinPackParameters: false
 BreakBeforeBinaryOperators: false
 BreakBeforeTernaryOperators: true
 BreakConstructorInitializersBeforeComma: true
-ColumnLimit: 80
+ColumnLimit: 100
 CommentPragmas: "^ IWYU pragma:"
 ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ConstructorInitializerIndentWidth: 4

.clang-tidy

@@ -0,0 +1,199 @@
+---
+Checks: "-*,
+  bugprone-argument-comment,
+  bugprone-assert-side-effect,
+  bugprone-bad-signal-to-kill-thread,
+  bugprone-bool-pointer-implicit-conversion,
+  bugprone-casting-through-void,
+  bugprone-chained-comparison,
+  bugprone-compare-pointer-to-member-virtual-function,
+  bugprone-copy-constructor-init,
+  bugprone-crtp-constructor-accessibility,
+  bugprone-dangling-handle,
+  bugprone-dynamic-static-initializers,
+  bugprone-empty-catch,
+  bugprone-fold-init-type,
+  bugprone-forward-declaration-namespace,
+  bugprone-inaccurate-erase,
+  bugprone-inc-dec-in-conditions,
+  bugprone-incorrect-enable-if,
+  bugprone-incorrect-roundings,
+  bugprone-infinite-loop,
+  bugprone-integer-division,
+  bugprone-lambda-function-name,
+  bugprone-macro-parentheses,
+  bugprone-macro-repeated-side-effects,
+  bugprone-misplaced-operator-in-strlen-in-alloc,
+  bugprone-misplaced-pointer-arithmetic-in-alloc,
+  bugprone-misplaced-widening-cast,
+  bugprone-move-forwarding-reference,
+  bugprone-multi-level-implicit-pointer-conversion,
+  bugprone-multiple-new-in-one-expression,
+  bugprone-multiple-statement-macro,
+  bugprone-no-escape,
+  bugprone-non-zero-enum-to-bool-conversion,
+  bugprone-optional-value-conversion,
+  bugprone-parent-virtual-call,
+  bugprone-pointer-arithmetic-on-polymorphic-object,
+  bugprone-posix-return,
+  bugprone-redundant-branch-condition,
+  bugprone-reserved-identifier,
+  bugprone-return-const-ref-from-parameter,
+  bugprone-shared-ptr-array-mismatch,
+  bugprone-signal-handler,
+  bugprone-signed-char-misuse,
+  bugprone-sizeof-container,
+  bugprone-sizeof-expression,
+  bugprone-spuriously-wake-up-functions,
+  bugprone-standalone-empty,
+  bugprone-string-constructor,
+  bugprone-string-integer-assignment,
+  bugprone-string-literal-with-embedded-nul,
+  bugprone-stringview-nullptr,
+  bugprone-suspicious-enum-usage,
+  bugprone-suspicious-include,
+  bugprone-suspicious-memory-comparison,
+  bugprone-suspicious-memset-usage,
+  bugprone-suspicious-missing-comma,
+  bugprone-suspicious-realloc-usage,
+  bugprone-suspicious-semicolon,
+  bugprone-suspicious-string-compare,
+  bugprone-suspicious-stringview-data-usage,
+  bugprone-swapped-arguments,
+  bugprone-switch-missing-default-case,
+  bugprone-terminating-continue,
+  bugprone-throw-keyword-missing,
+  bugprone-too-small-loop-variable,
+  # bugprone-unchecked-optional-access, # see https://github.com/XRPLF/rippled/pull/6502
+  bugprone-undefined-memory-manipulation,
+  bugprone-undelegated-constructor,
+  bugprone-unhandled-exception-at-new,
+  bugprone-unhandled-self-assignment,
+  bugprone-unique-ptr-array-mismatch,
+  bugprone-unsafe-functions,
+  bugprone-use-after-move,
+  bugprone-unused-raii,
+  bugprone-unused-return-value,
+  bugprone-unused-local-non-trivial-variable,
+  bugprone-virtual-near-miss,
+  cppcoreguidelines-init-variables,
+  cppcoreguidelines-misleading-capture-default-by-value,
+  cppcoreguidelines-no-suspend-with-lock,
+  cppcoreguidelines-pro-type-member-init,
+  cppcoreguidelines-pro-type-static-cast-downcast,
+  cppcoreguidelines-rvalue-reference-param-not-moved,
+  cppcoreguidelines-use-default-member-init,
+  cppcoreguidelines-virtual-class-destructor,
+  hicpp-ignored-remove-result,
+  misc-definitions-in-headers,
+  misc-header-include-cycle,
+  misc-misplaced-const,
+  misc-static-assert,
+  misc-throw-by-value-catch-by-reference,
+  misc-unused-alias-decls,
+  misc-unused-using-decls,
+  modernize-deprecated-headers,
+  modernize-make-shared,
+  modernize-make-unique,
+  performance-implicit-conversion-in-loop,
+  performance-move-constructor-init,
+  performance-trivially-destructible,
+  readability-avoid-nested-conditional-operator,
+  readability-avoid-return-with-void-value,
+  readability-braces-around-statements,
+  readability-const-return-type,
+  readability-container-contains,
+  readability-container-size-empty,
+  readability-convert-member-functions-to-static,
+  readability-duplicate-include,
+  readability-else-after-return,
+  readability-enum-initial-value,
+  readability-implicit-bool-conversion,
+  readability-make-member-function-const,
+  readability-math-missing-parentheses,
+  readability-misleading-indentation,
+  readability-non-const-parameter,
+  readability-redundant-casting,
+  readability-redundant-declaration,
+  readability-redundant-inline-specifier,
+  readability-redundant-member-init,
+  readability-redundant-string-init,
+  readability-reference-to-constructed-temporary,
+  readability-simplify-boolean-expr,
+  readability-static-definition-in-anonymous-namespace,
+  readability-suspicious-call-argument,
+  readability-use-std-min-max
+  "
+# ---
+# checks that have some issues that need to be resolved:
+#
+# llvm-namespace-comment,
+# misc-const-correctness,
+# misc-include-cleaner,
+# misc-redundant-expression,
+#
+# readability-inconsistent-declaration-parameter-name, # in this codebase this check will break a lot of arg names
+# readability-static-accessed-through-instance,        # this check is probably unnecessary. it makes the code less readable
+# readability-identifier-naming,
+#
+# modernize-concat-nested-namespaces,
+# modernize-pass-by-value,
+# modernize-type-traits,
+# modernize-use-designated-initializers,
+# modernize-use-emplace,
+# modernize-use-equals-default,
+# modernize-use-equals-delete,
+# modernize-use-override,
+# modernize-use-ranges,
+# modernize-use-starts-ends-with,
+# modernize-use-std-numbers,
+# modernize-use-using,
+#
+# performance-faster-string-find,
+# performance-for-range-copy,
+# performance-inefficient-vector-operation,
+# performance-move-const-arg,
+# performance-no-automatic-move,
+# ---
+#
+CheckOptions:
+  readability-braces-around-statements.ShortStatementLines: 2
+  #   readability-identifier-naming.MacroDefinitionCase: UPPER_CASE
+  #   readability-identifier-naming.ClassCase: CamelCase
+  #   readability-identifier-naming.StructCase: CamelCase
+  #   readability-identifier-naming.UnionCase: CamelCase
+  #   readability-identifier-naming.EnumCase: CamelCase
+  #   readability-identifier-naming.EnumConstantCase: CamelCase
+  #   readability-identifier-naming.ScopedEnumConstantCase: CamelCase
+  #   readability-identifier-naming.GlobalConstantCase: UPPER_CASE
+  #   readability-identifier-naming.GlobalConstantPrefix: "k"
+  #   readability-identifier-naming.GlobalVariableCase: CamelCase
+  #   readability-identifier-naming.GlobalVariablePrefix: "g"
+  #   readability-identifier-naming.ConstexprFunctionCase: camelBack
+  #   readability-identifier-naming.ConstexprMethodCase: camelBack
+  #   readability-identifier-naming.ClassMethodCase: camelBack
+  #   readability-identifier-naming.ClassMemberCase: camelBack
+  #   readability-identifier-naming.ClassConstantCase: UPPER_CASE
+  #   readability-identifier-naming.ClassConstantPrefix: "k"
+  #   readability-identifier-naming.StaticConstantCase: UPPER_CASE
+  #   readability-identifier-naming.StaticConstantPrefix: "k"
+  #   readability-identifier-naming.StaticVariableCase: UPPER_CASE
+  #   readability-identifier-naming.StaticVariablePrefix: "k"
+  #   readability-identifier-naming.ConstexprVariableCase: UPPER_CASE
+  #   readability-identifier-naming.ConstexprVariablePrefix: "k"
+  #   readability-identifier-naming.LocalConstantCase: camelBack
+  #   readability-identifier-naming.LocalVariableCase: camelBack
+  #   readability-identifier-naming.TemplateParameterCase: CamelCase
+  #   readability-identifier-naming.ParameterCase: camelBack
+  #   readability-identifier-naming.FunctionCase: camelBack
+  #   readability-identifier-naming.MemberCase: camelBack
+  #   readability-identifier-naming.PrivateMemberSuffix: _
+  #   readability-identifier-naming.ProtectedMemberSuffix: _
+  #   readability-identifier-naming.PublicMemberSuffix: ""
+  #   readability-identifier-naming.FunctionIgnoredRegexp: ".*tag_invoke.*"
+  bugprone-unsafe-functions.ReportMoreUnsafeFunctions: true
+  bugprone-unused-return-value.CheckedReturnTypes: ::std::error_code;::std::error_condition;::std::errc
+#   misc-include-cleaner.IgnoreHeaders: '.*/(detail|impl)/.*;.*(expected|unexpected).*;.*ranges_lower_bound\.h;time.h;stdlib.h;__chrono/.*;fmt/chrono.h;boost/uuid/uuid_hash.hpp'
+#
+# HeaderFilterRegex: '^.*/(src|tests)/.*\.(h|hpp)$'
+WarningsAsErrors: "*"

.codecov.yml

@@ -36,3 +36,8 @@ ignore:
   - "src/tests/"
   - "include/xrpl/beast/test/"
   - "include/xrpl/beast/unit_test/"
+  # Telemetry modules — conditionally compiled behind XRPL_ENABLE_TELEMETRY,
+  # which is not enabled in coverage builds.
+  - "src/xrpld/telemetry/"
+  - "src/libxrpl/beast/insight/OTelCollector.cpp"
+  - "include/xrpl/beast/insight/OTelCollector.h"

.gersemi/definitions.cmake

@@ -0,0 +1,101 @@
+# Custom CMake command definitions for gersemi formatting.
+# These stubs teach gersemi the signatures of project-specific commands
+# so it can format their invocations correctly.
+
+function(git_branch branch_val)
+endfunction()
+
+function(isolate_headers target A B scope)
+endfunction()
+
+function(create_symbolic_link target link)
+endfunction()
+
+function(xrpl_add_test name)
+endfunction()
+
+macro(exclude_from_default target_)
+endmacro()
+
+macro(exclude_if_included target_)
+endmacro()
+
+function(target_protobuf_sources target prefix)
+    set(options APPEND_PATH DESCRIPTORS)
+    set(oneValueArgs
+        LANGUAGE
+        OUT_VAR
+        EXPORT_MACRO
+        TARGET
+        PROTOC_OUT_DIR
+        PLUGIN
+        PLUGIN_OPTIONS
+        PROTOC_EXE
+    )
+    set(multiValueArgs
+        PROTOS
+        IMPORT_DIRS
+        GENERATE_EXTENSIONS
+        PROTOC_OPTIONS
+        DEPENDENCIES
+    )
+    cmake_parse_arguments(
+        THIS_FUNCTION_PREFIX
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
+endfunction()
+
+function(add_module parent name)
+endfunction()
+
+function(setup_protocol_autogen)
+endfunction()
+
+function(target_link_modules parent scope)
+endfunction()
+
+function(setup_target_for_coverage_gcovr)
+    set(options NONE)
+    set(oneValueArgs BASE_DIRECTORY NAME FORMAT)
+    set(multiValueArgs EXCLUDE EXECUTABLE EXECUTABLE_ARGS DEPENDENCIES)
+    cmake_parse_arguments(
+        THIS_FUNCTION_PREFIX
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
+endfunction()
+
+function(add_code_coverage_to_target name scope)
+endfunction()
+
+function(verbose_find_path variable name)
+    set(options
+        NO_CACHE
+        REQUIRED
+        OPTIONAL
+        NO_DEFAULT_PATH
+        NO_PACKAGE_ROOT_PATH
+        NO_CMAKE_PATH
+        NO_CMAKE_ENVIRONMENT_PATH
+        NO_SYSTEM_ENVIRONMENT_PATH
+        NO_CMAKE_SYSTEM_PATH
+        NO_CMAKE_INSTALL_PREFIX
+        CMAKE_FIND_ROOT_PATH_BOTH
+        ONLY_CMAKE_FIND_ROOT_PATH
+        NO_CMAKE_FIND_ROOT_PATH
+    )
+    set(oneValueArgs REGISTRY_VIEW VALIDATOR DOC)
+    set(multiValueArgs NAMES HINTS PATHS PATH_SUFFIXES)
+    cmake_parse_arguments(
+        THIS_FUNCTION_PREFIX
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
+endfunction()

.gersemirc

@@ -0,0 +1 @@
+definitions: [.gersemi]

.git-blame-ignore-revs

@@ -1,16 +1,79 @@
 # This feature requires Git >= 2.24
 # To use it by default in git blame:
 # git config blame.ignoreRevsFile .git-blame-ignore-revs
-50760c693510894ca368e90369b0cc2dabfd07f3
-e2384885f5f630c8f0ffe4bf21a169b433a16858
-241b9ddde9e11beb7480600fd5ed90e1ef109b21
-760f16f56835663d9286bd29294d074de26a7ba6
-0eebe6a5f4246fced516d52b83ec4e7f47373edd
-2189cc950c0cebb89e4e2fa3b2d8817205bf7cef
-b9d007813378ad0ff45660dc07285b823c7e9855
-fe9a5365b8a52d4acc42eb27369247e6f238a4f9
-9a93577314e6a8d4b4a8368cc9d2b15a5d8303e8
-552377c76f55b403a1c876df873a23d780fcc81c
-97f0747e103f13e26e45b731731059b32f7679ac
-b13370ac0d207217354f1fc1c29aef87769fb8a1
+
+# This file is sorted in reverse chronological order, with the most recent commits at the top.
+# The commits listed here are ignored by git blame, which is useful for formatting-only commits that would otherwise obscure the history of changes to a file.
+
+# refactor: Enable remaining clang-tidy `cppcoreguidelines` checks (#6538)
+72f4cb097f626b08b02fc3efcb4aa11cb2e7adb8
+# refactor: Rename system name from 'ripple' to 'xrpld' (#6347)
+ffea3977f0b771fe8e43a8f74e4d393d63a7afd8
+# refactor: Update transaction folder structure (#6483)
+5865bd017f777491b4a956f9210be0c4161f5442
+# chore: Use gersemi instead of ancient cmake-format (#6486)
+0c74270b055133a57a497b5c9fc5a75f7647b1f4
+# chore: Apply clang-format width 100 (#6387)
+2c1fad102353e11293e3edde1c043224e7d3e983
+# chore: Set clang-format width to 100 in config file (#6387)
+25cca465538a56cce501477f9e5e2c1c7ea2d84c
+# chore: Set cmake-format width to 100 (#6386)
+469ce9f291a4480c38d4ee3baca5136b2f053cd0
+# refactor: Modularize app/tx (#6228)
+0976b2b68b64972af8e6e7c497900b5bce9fe22f
+# chore: Update clang-format to 21.1.8 (#6352)
+958d8f375453d80bb1aa4c293b5102c045a3e4b4
+# refactor: Replace include guards by '#pragma once' (#6322)
+34ef577604782ca8d6e1c17df8bd7470990a52ff
+# chore: Format all cmake files without comments (#6294)
+fe9c8d568fcf6ac21483024e01f58962dd5c8260
+# chore: Add cmake-format pre-commit hook (#6279)
+a0e09187b9370805d027c611a7e9ff5a0125282a
+# chore: Set ColumnLimit to 120 in clang-format (#6288)
+5f638f55536def0d88b970d1018a465a238e55f4
+# refactor: Fix typos in comments, configure cspell (#6164)
+3c9f5b62525cb1d6ca1153eeb10433db7d7379fd
+# refactor: Rename `rippled.cfg` to `xrpld.cfg` (#6098)
+3d1b3a49b3601a0a7037fa0b19d5df7b5e0e2fc1
+# refactor: Rename `ripple` namespace to `xrpl` (#5982)
+1eb0fdac6543706b4b9ddca57fd4102928a1f871
+# refactor: Rename `rippled` binary to `xrpld` (#5983)
+9eb84a561ef8bb066d89f098bd9b4ac71baed67c
+# refactor: Replaces secp256k1 source by Conan package (#6089)
+813bc4d9491b078bb950f8255f93b02f71320478
+# refactor: Remove unnecessary copyright notices already covered by LICENSE.md (#5929)
+1d42c4f6de6bf01d1286fc7459b17a37a5189e88
+# refactor: Rename `RIPPLE_` and `RIPPLED_` definitions to `XRPL_` (#5821)
+ada83564d894829424b0f4d922b0e737e07abbf7
+# refactor: Modularize shamap and nodestore (#5668)
+8eb233c2ea8ad5a159be73b77f0f5e1496d547ac
+# refactor: Modularise ledger (#5493)
+dc8b37a52448b005153c13a7f046ad494128cf94
+# chore: Update clang-format and prettier with pre-commit (#5709)
+c14ce956adeabe476ad73c18d73103f347c9c613
+# chore: Fix file formatting (#5718)
 896b8c3b54a22b0497cb0d1ce95e1095f9a227ce
+# chore: Reverts formatting changes to external files, adds formatting changes to proto files (#5711)
+b13370ac0d207217354f1fc1c29aef87769fb8a1
+# chore: Run prettier on all files (#5657)
+97f0747e103f13e26e45b731731059b32f7679ac
+# Reformat code with clang-format-18
+552377c76f55b403a1c876df873a23d780fcc81c
+# Recompute loops (#4997)
+d028005aa6319338b0adae1aebf8abe113162960
+# Rewrite includes (#4997)
+1d23148e6dd53957fcb6205c07a5c6cd7b64d50c
+# Rearrange sources (#4997)
+e416ee72ca26fa0c09d2aee1b68bdfb2b7046eed
+# Move CMake directory (#4997)
+2e902dee53aab2a8f27f32971047bb81e022f94f
+# Rewrite includes
+0eebe6a5f4246fced516d52b83ec4e7f47373edd
+# Format formerly .hpp files
+760f16f56835663d9286bd29294d074de26a7ba6
+# Rename .hpp to .h
+241b9ddde9e11beb7480600fd5ed90e1ef109b21
+# Consolidate external libraries
+e2384885f5f630c8f0ffe4bf21a169b433a16858
+# Format first-party source according to .clang-format
+50760c693510894ca368e90369b0cc2dabfd07f3

.github/CODEOWNERS

@@ -1,8 +0,0 @@
-# Allow anyone to review any change by default.
-*
-
-# Require the rpc-reviewers team to review changes to the rpc code.
-include/xrpl/protocol/ @xrplf/rpc-reviewers
-src/libxrpl/protocol/ @xrplf/rpc-reviewers
-src/xrpld/rpc/ @xrplf/rpc-reviewers
-src/xrpld/app/misc/ @xrplf/rpc-reviewers

.github/actions/generate-version/action.yml

@@ -11,16 +11,18 @@ runs:
   steps:
     # When a tag is pushed, the version is used as-is.
     - name: Generate version for tag event
-      if: ${{ github.event_name == 'tag' }}
+      if: ${{ startsWith(github.ref, 'refs/tags/') }}
       shell: bash
       env:
         VERSION: ${{ github.ref_name }}
       run: echo "VERSION=${VERSION}" >> "${GITHUB_ENV}"
 
-    # When a tag is not pushed, then the version is extracted from the
-    # BuildInfo.cpp file and the shortened commit hash appended to it.
+    # When a tag is not pushed, then the version (e.g. 1.2.3-b0) is extracted
+    # from the BuildInfo.cpp file and the shortened commit hash appended to it.
+    # We use a plus sign instead of a hyphen because Conan recipe versions do
+    # not support two hyphens.
     - name: Generate version for non-tag event
-      if: ${{ github.event_name != 'tag' }}
+      if: ${{ !startsWith(github.ref, 'refs/tags/') }}
       shell: bash
       run: |
         echo 'Extracting version from BuildInfo.cpp.'
@@ -32,7 +34,7 @@ runs:
 
         echo 'Appending shortened commit hash to version.'
         SHA='${{ github.sha }}'
-        VERSION="${VERSION}-${SHA:0:7}"
+        VERSION="${VERSION}+${SHA:0:7}"
 
         echo "VERSION=${VERSION}" >> "${GITHUB_ENV}"
 

.github/actions/setup-conan/action.yml

@@ -31,7 +31,7 @@ runs:
         conan config install conan/profiles/ -tf $(conan config home)/profiles/
 
         echo 'Conan profile:'
-        conan profile show
+        conan profile show --profile ci
 
     - name: Set up Conan remote
       shell: bash

.github/dependabot.yml

@@ -0,0 +1,56 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+      day: monday
+      time: "04:00"
+      timezone: Etc/GMT
+    commit-message:
+      prefix: "ci: [DEPENDABOT] "
+    target-branch: develop
+
+  - package-ecosystem: github-actions
+    directory: .github/actions/build-deps/
+    schedule:
+      interval: weekly
+      day: monday
+      time: "04:00"
+      timezone: Etc/GMT
+    commit-message:
+      prefix: "ci: [DEPENDABOT] "
+    target-branch: develop
+
+  - package-ecosystem: github-actions
+    directory: .github/actions/generate-version/
+    schedule:
+      interval: weekly
+      day: monday
+      time: "04:00"
+      timezone: Etc/GMT
+    commit-message:
+      prefix: "ci: [DEPENDABOT] "
+    target-branch: develop
+
+  - package-ecosystem: github-actions
+    directory: .github/actions/print-env/
+    schedule:
+      interval: weekly
+      day: monday
+      time: "04:00"
+      timezone: Etc/GMT
+    commit-message:
+      prefix: "ci: [DEPENDABOT] "
+    target-branch: develop
+
+  - package-ecosystem: github-actions
+    directory: .github/actions/setup-conan/
+    schedule:
+      interval: weekly
+      day: monday
+      time: "04:00"
+      timezone: Etc/GMT
+    commit-message:
+      prefix: "ci: [DEPENDABOT] "
+    target-branch: develop

.github/pull_request_template.md

@@ -29,22 +29,6 @@ If a refactor, how is this better than the previous implementation?
 If there is a spec or design document for this feature, please link it here.
 -->
 
-### Type of Change
-
-<!--
-Please check [x] relevant options, delete irrelevant ones.
--->
-
-- [ ] Bug fix (non-breaking change which fixes an issue)
-- [ ] New feature (non-breaking change which adds functionality)
-- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
-- [ ] Refactor (non-breaking change that only restructures code)
-- [ ] Performance (increase or change in throughput and/or latency)
-- [ ] Tests (you added tests for code that already exists, or your new feature included in this PR)
-- [ ] Documentation update
-- [ ] Chore (no impact to binary, e.g. `.gitignore`, formatting, dropping support for older tooling)
-- [ ] Release
-
 ### API Impact
 
 <!--

.github/scripts/levelization/README.md

@@ -70,7 +70,7 @@ that `test` code should _never_ be included in `xrpl` or `xrpld` code.)
 
 ## Validation
 
-The [levelization](generate.sh) script takes no parameters,
+The [levelization](generate.py) script takes no parameters,
 reads no environment variables, and can be run from any directory,
 as long as it is in the expected location in the rippled repo.
 It can be run at any time from within a checked out repo, and will
@@ -104,7 +104,7 @@ It generates many files of [results](results):
   Github Actions workflow to test that levelization loops haven't
   changed. Unfortunately, if changes are detected, it can't tell if
   they are improvements or not, so if you have resolved any issues or
-  done anything else to improve levelization, run `levelization.sh`,
+  done anything else to improve levelization, run `generate.py`,
   and commit the updated results.
 
 The `loops.txt` and `ordering.txt` files relate the modules
@@ -128,7 +128,7 @@ The committed files hide the detailed values intentionally, to
 prevent false alarms and merging issues, and because it's easy to
 get those details locally.
 
-1. Run `levelization.sh`
+1. Run `generate.py`
 2. Grep the modules in `paths.txt`.
    - For example, if a cycle is found `A ~= B`, simply `grep -w
 A .github/scripts/levelization/results/paths.txt | grep -w B`

.github/scripts/levelization/generate.py

@@ -0,0 +1,335 @@
+#!/usr/bin/env python3
+
+"""
+Usage: generate.py
+This script takes no parameters, and can be called from any directory in the file system.
+"""
+
+import os
+import re
+import subprocess
+import sys
+from collections import defaultdict
+from pathlib import Path
+from typing import Dict, List, Tuple, Set, Optional
+
+# Compile regex patterns once at module level
+INCLUDE_PATTERN = re.compile(r"^\s*#include.*/.*\.h")
+INCLUDE_PATH_PATTERN = re.compile(r'[<"]([^>"]+)[>"]')
+
+
+def dictionary_sort_key(s: str) -> str:
+    """
+    Create a sort key that mimics 'sort -d' (dictionary order).
+    Dictionary order only considers blanks and alphanumeric characters.
+    This means punctuation like '.' is ignored during sorting.
+    """
+    # Keep only alphanumeric characters and spaces
+    return "".join(c for c in s if c.isalnum() or c.isspace())
+
+
+def get_level(file_path: str) -> str:
+    """
+    Extract the level from a file path (second and third directory components).
+    Equivalent to bash: cut -d/ -f 2,3
+
+    Examples:
+        src/xrpld/app/main.cpp -> xrpld.app
+        src/libxrpl/protocol/STObject.cpp -> libxrpl.protocol
+        include/xrpl/basics/base_uint.h -> xrpl.basics
+    """
+    parts = file_path.split("/")
+
+    # Get fields 2 and 3 (indices 1 and 2 in 0-based indexing)
+    if len(parts) >= 3:
+        level = f"{parts[1]}/{parts[2]}"
+    elif len(parts) >= 2:
+        level = f"{parts[1]}/toplevel"
+    else:
+        level = file_path
+
+    # If the "level" indicates a file, cut off the filename
+    if "." in level.split("/")[-1]:  # Avoid Path object creation
+        # Use the "toplevel" label as a workaround for `sort`
+        # inconsistencies between different utility versions
+        level = level.rsplit("/", 1)[0] + "/toplevel"
+
+    return level.replace("/", ".")
+
+
+def extract_include_level(include_line: str) -> Optional[str]:
+    """
+    Extract the include path from an #include directive.
+    Gets the first two directory components from the include path.
+    Equivalent to bash: cut -d/ -f 1,2
+
+    Examples:
+        #include <xrpl/basics/base_uint.h> -> xrpl.basics
+        #include "xrpld/app/main/Application.h" -> xrpld.app
+    """
+    # Remove everything before the quote or angle bracket
+    match = INCLUDE_PATH_PATTERN.search(include_line)
+    if not match:
+        return None
+
+    include_path = match.group(1)
+    parts = include_path.split("/")
+
+    # Get first two fields (indices 0 and 1)
+    if len(parts) >= 2:
+        include_level = f"{parts[0]}/{parts[1]}"
+    else:
+        include_level = include_path
+
+    # If the "includelevel" indicates a file, cut off the filename
+    if "." in include_level.split("/")[-1]:  # Avoid Path object creation
+        include_level = include_level.rsplit("/", 1)[0] + "/toplevel"
+
+    return include_level.replace("/", ".")
+
+
+def find_repository_directories(
+    start_path: Path, depth_limit: int = 10
+) -> Tuple[Path, List[Path]]:
+    """
+    Find the repository root by looking for src or include folders.
+    Walks up the directory tree from the start path.
+    """
+    current = start_path.resolve()
+
+    # Walk up the directory tree
+    for _ in range(depth_limit):  # Limit search depth to prevent infinite loops
+        src_path = current / "src"
+        include_path = current / "include"
+        # Check if this directory has src or include folders
+        has_src = src_path.exists()
+        has_include = include_path.exists()
+
+        if has_src or has_include:
+            return current, [src_path, include_path]
+
+        # Move up one level
+        parent = current.parent
+        if parent == current:  # Reached filesystem root
+            break
+        current = parent
+
+    # If we couldn't find it, raise an error
+    raise RuntimeError(
+        "Could not find repository root. "
+        "Expected to find a directory containing 'src' and/or 'include' folders."
+    )
+
+
+def main():
+    # Change to the script's directory
+    script_dir = Path(__file__).parent.resolve()
+    os.chdir(script_dir)
+
+    # Clean up and create results directory.
+    results_dir = script_dir / "results"
+    if results_dir.exists():
+        import shutil
+
+        shutil.rmtree(results_dir)
+    results_dir.mkdir()
+
+    # Find the repository root by searching for src and include directories.
+    try:
+        repo_root, scan_dirs = find_repository_directories(script_dir)
+
+        print(f"Found repository root: {repo_root}")
+        print(f"Scanning directories:")
+        for scan_dir in scan_dirs:
+            print(f"  - {scan_dir.relative_to(repo_root)}")
+    except RuntimeError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    print("\nScanning for raw includes...")
+    # Find all #include directives
+    raw_includes: List[Tuple[str, str]] = []
+    rawincludes_file = results_dir / "rawincludes.txt"
+
+    # Write to file as we go to avoid storing everything in memory.
+    with open(rawincludes_file, "w", buffering=8192) as raw_f:
+        for dir_path in scan_dirs:
+            print(f"  Scanning {dir_path.relative_to(repo_root)}...")
+
+            for file_path in dir_path.rglob("*"):
+                if not file_path.is_file():
+                    continue
+
+                try:
+                    rel_path_str = str(file_path.relative_to(repo_root))
+
+                    # Read file with a large buffer for performance.
+                    with open(
+                        file_path,
+                        "r",
+                        encoding="utf-8",
+                        errors="ignore",
+                        buffering=8192,
+                    ) as f:
+                        for line in f:
+                            # Quick check before regex
+                            if "#include" not in line or "boost" in line:
+                                continue
+
+                            if INCLUDE_PATTERN.match(line):
+                                line_stripped = line.strip()
+                                entry = f"{rel_path_str}:{line_stripped}\n"
+                                print(entry, end="")
+                                raw_f.write(entry)
+                                raw_includes.append((rel_path_str, line_stripped))
+                except Exception as e:
+                    print(f"Error reading {file_path}: {e}", file=sys.stderr)
+
+    # Build levelization paths and count directly (no need to sort first).
+    print("Build levelization paths")
+    path_counts: Dict[Tuple[str, str], int] = defaultdict(int)
+
+    for file_path, include_line in raw_includes:
+        include_level = extract_include_level(include_line)
+        if not include_level:
+            continue
+
+        level = get_level(file_path)
+        if level != include_level:
+            path_counts[(level, include_level)] += 1
+
+    # Sort and deduplicate paths (using dictionary order like bash 'sort -d').
+    print("Sort and deduplicate paths")
+
+    paths_file = results_dir / "paths.txt"
+    with open(paths_file, "w") as f:
+        # Sort using dictionary order: only alphanumeric and spaces matter
+        sorted_items = sorted(
+            path_counts.items(),
+            key=lambda x: (dictionary_sort_key(x[0][0]), dictionary_sort_key(x[0][1])),
+        )
+        for (level, include_level), count in sorted_items:
+            line = f"{count:7} {level} {include_level}\n"
+            print(line.rstrip())
+            f.write(line)
+
+    # Split into flat-file database
+    print("Split into flat-file database")
+    includes_dir = results_dir / "includes"
+    included_by_dir = results_dir / "included_by"
+    includes_dir.mkdir()
+    included_by_dir.mkdir()
+
+    # Batch writes by grouping data first to avoid repeated file opens.
+    includes_data: Dict[str, List[Tuple[str, int]]] = defaultdict(list)
+    included_by_data: Dict[str, List[Tuple[str, int]]] = defaultdict(list)
+
+    # Process in sorted order to match bash script behaviour (dictionary order).
+    sorted_items = sorted(
+        path_counts.items(),
+        key=lambda x: (dictionary_sort_key(x[0][0]), dictionary_sort_key(x[0][1])),
+    )
+    for (level, include_level), count in sorted_items:
+        includes_data[level].append((include_level, count))
+        included_by_data[include_level].append((level, count))
+
+    # Write all includes files in sorted order (dictionary order).
+    for level in sorted(includes_data.keys(), key=dictionary_sort_key):
+        entries = includes_data[level]
+        with open(includes_dir / level, "w") as f:
+            for include_level, count in entries:
+                line = f"{include_level} {count}\n"
+                print(line.rstrip())
+                f.write(line)
+
+    # Write all included_by files in sorted order (dictionary order).
+    for include_level in sorted(included_by_data.keys(), key=dictionary_sort_key):
+        entries = included_by_data[include_level]
+        with open(included_by_dir / include_level, "w") as f:
+            for level, count in entries:
+                line = f"{level} {count}\n"
+                print(line.rstrip())
+                f.write(line)
+
+    # Search for loops
+    print("Search for loops")
+    loops_file = results_dir / "loops.txt"
+    ordering_file = results_dir / "ordering.txt"
+
+    loops_found: Set[Tuple[str, str]] = set()
+
+    # Pre-load all include files into memory to avoid repeated I/O.
+    # This is the biggest optimisation - we were reading files repeatedly in nested loops.
+    # Use list of tuples to preserve file order.
+    includes_cache: Dict[str, List[Tuple[str, int]]] = {}
+    includes_lookup: Dict[str, Dict[str, int]] = {}  # For fast lookup
+
+    # Note: bash script uses 'for source in *' which uses standard glob sorting,
+    # NOT dictionary order. So we use standard sorted() here, not dictionary_sort_key.
+    for include_file in sorted(includes_dir.iterdir(), key=lambda p: p.name):
+        if not include_file.is_file():
+            continue
+
+        includes_cache[include_file.name] = []
+        includes_lookup[include_file.name] = {}
+        with open(include_file, "r") as f:
+            for line in f:
+                parts = line.strip().split()
+                if len(parts) >= 2:
+                    include_name = parts[0]
+                    include_count = int(parts[1])
+                    includes_cache[include_file.name].append(
+                        (include_name, include_count)
+                    )
+                    includes_lookup[include_file.name][include_name] = include_count
+
+    with open(loops_file, "w", buffering=8192) as loops_f, open(
+        ordering_file, "w", buffering=8192
+    ) as ordering_f:
+
+        # Use standard sorting to match bash glob expansion 'for source in *'.
+        for source in sorted(includes_cache.keys()):
+            source_includes = includes_cache[source]
+
+            for include, include_freq in source_includes:
+                # Check if include file exists and references source
+                if include not in includes_lookup:
+                    continue
+
+                source_freq = includes_lookup[include].get(source)
+
+                if source_freq is not None:
+                    # Found a loop
+                    loop_key = tuple(sorted([source, include]))
+                    if loop_key in loops_found:
+                        continue
+                    loops_found.add(loop_key)
+
+                    loops_f.write(f"Loop: {source} {include}\n")
+
+                    # If the counts are close, indicate that the two modules are
+                    # on the same level, though they shouldn't be.
+                    diff = include_freq - source_freq
+                    if diff > 3:
+                        loops_f.write(f"  {source} > {include}\n\n")
+                    elif diff < -3:
+                        loops_f.write(f"  {include} > {source}\n\n")
+                    elif source_freq == include_freq:
+                        loops_f.write(f"  {include} == {source}\n\n")
+                    else:
+                        loops_f.write(f"  {include} ~= {source}\n\n")
+                else:
+                    ordering_f.write(f"{source} > {include}\n")
+
+    # Print results
+    print("\nOrdering:")
+    with open(ordering_file, "r") as f:
+        print(f.read(), end="")
+
+    print("\nLoops:")
+    with open(loops_file, "r") as f:
+        print(f.read(), end="")
+
+
+if __name__ == "__main__":
+    main()

.github/scripts/levelization/generate.sh

@@ -1,130 +0,0 @@
-#!/bin/bash
-
-# Usage: generate.sh
-# This script takes no parameters, reads no environment variables,
-# and can be run from any directory, as long as it is in the expected
-# location in the repo.
-
-pushd $( dirname $0 )
-
-if [ -v PS1 ]
-then
-  # if the shell is interactive, clean up any flotsam before analyzing
-  git clean -ix
-fi
-
-# Ensure all sorting is ASCII-order consistently across platforms.
-export LANG=C
-
-rm -rfv results
-mkdir results
-includes="$( pwd )/results/rawincludes.txt"
-pushd ../../..
-echo Raw includes:
-grep -r '^[ ]*#include.*/.*\.h' include src | \
-    grep -v boost | tee ${includes}
-popd
-pushd results
-
-oldifs=${IFS}
-IFS=:
-mkdir includes
-mkdir included_by
-echo Build levelization paths
-exec 3< ${includes} # open rawincludes.txt for input
-while read -r -u 3 file include
-do
-    level=$( echo ${file} | cut -d/ -f 2,3 )
-    # If the "level" indicates a file, cut off the filename
-    if [[ "${level##*.}" != "${level}" ]]
-    then
-        # Use the "toplevel" label as a workaround for `sort`
-        # inconsistencies between different utility versions
-        level="$( dirname ${level} )/toplevel"
-    fi
-    level=$( echo ${level} | tr '/' '.' )
-
-    includelevel=$( echo ${include} | sed 's/.*["<]//; s/[">].*//' | \
-        cut -d/ -f 1,2 )
-    if [[ "${includelevel##*.}" != "${includelevel}" ]]
-    then
-        # Use the "toplevel" label as a workaround for `sort`
-        # inconsistencies between different utility versions
-        includelevel="$( dirname ${includelevel} )/toplevel"
-    fi
-    includelevel=$( echo ${includelevel} | tr '/' '.' )
-
-    if [[ "$level" != "$includelevel" ]]
-    then
-        echo $level $includelevel | tee -a paths.txt
-    fi
-done
-echo Sort and deduplicate paths
-sort -ds paths.txt | uniq -c | tee sortedpaths.txt
-mv sortedpaths.txt paths.txt
-exec 3>&- #close fd 3
-IFS=${oldifs}
-unset oldifs
-
-echo Split into flat-file database
-exec 4<paths.txt # open paths.txt for input
-while read -r -u 4 count level include
-do
-    echo ${include} ${count} | tee -a includes/${level}
-    echo ${level} ${count} | tee -a included_by/${include}
-done
-exec 4>&- #close fd 4
-
-loops="$( pwd )/loops.txt"
-ordering="$( pwd )/ordering.txt"
-pushd includes
-echo Search for loops
-# Redirect stdout to a file
-exec 4>&1
-exec 1>"${loops}"
-for source in *
-do
-  if [[ -f "$source" ]]
-  then
-    exec 5<"${source}" # open for input
-    while read -r -u 5 include includefreq
-    do
-      if [[ -f $include ]]
-      then
-        if grep -q -w $source $include
-        then
-          if grep -q -w "Loop: $include $source" "${loops}"
-          then
-            continue
-          fi
-          sourcefreq=$( grep -w $source $include | cut -d\  -f2 )
-          echo "Loop: $source $include"
-          # If the counts are close, indicate that the two modules are
-          # on the same level, though they shouldn't be
-          if [[ $(( $includefreq - $sourcefreq )) -gt 3 ]]
-          then
-              echo -e "  $source > $include\n"
-          elif [[ $(( $sourcefreq - $includefreq )) -gt 3 ]]
-          then
-              echo -e "  $include > $source\n"
-          elif [[ $sourcefreq -eq $includefreq ]]
-          then
-              echo -e "  $include == $source\n"
-          else
-              echo -e "  $include ~= $source\n"
-          fi
-        else
-          echo "$source > $include" >> "${ordering}"
-        fi
-      fi
-    done
-    exec 5>&- #close fd 5
-  fi
-done
-exec 1>&4 #close fd 1
-exec 4>&- #close fd 4
-cat "${ordering}"
-cat "${loops}"
-popd
-popd
-popd

.github/scripts/levelization/results/loops.txt

@@ -4,14 +4,11 @@ Loop: test.jtx test.toplevel
 Loop: test.jtx test.unit_test
   test.unit_test == test.jtx
 
-Loop: xrpld.app xrpld.core
-  xrpld.app > xrpld.core
-
 Loop: xrpld.app xrpld.overlay
-  xrpld.overlay > xrpld.app
+  xrpld.overlay ~= xrpld.app
 
 Loop: xrpld.app xrpld.peerfinder
-  xrpld.peerfinder ~= xrpld.app
+  xrpld.peerfinder == xrpld.app
 
 Loop: xrpld.app xrpld.rpc
   xrpld.rpc > xrpld.app

.github/scripts/levelization/results/ordering.txt

@@ -1,4 +1,6 @@
 libxrpl.basics > xrpl.basics
+libxrpl.conditions > xrpl.basics
+libxrpl.conditions > xrpl.conditions
 libxrpl.core > xrpl.basics
 libxrpl.core > xrpl.core
 libxrpl.crypto > xrpl.basics
@@ -17,16 +19,31 @@ libxrpl.nodestore > xrpl.protocol
 libxrpl.protocol > xrpl.basics
 libxrpl.protocol > xrpl.json
 libxrpl.protocol > xrpl.protocol
+libxrpl.protocol_autogen > xrpl.protocol_autogen
+libxrpl.rdb > xrpl.basics
+libxrpl.rdb > xrpl.core
+libxrpl.rdb > xrpl.rdb
 libxrpl.resource > xrpl.basics
 libxrpl.resource > xrpl.json
 libxrpl.resource > xrpl.resource
 libxrpl.server > xrpl.basics
 libxrpl.server > xrpl.json
 libxrpl.server > xrpl.protocol
+libxrpl.server > xrpl.rdb
 libxrpl.server > xrpl.server
 libxrpl.shamap > xrpl.basics
 libxrpl.shamap > xrpl.protocol
 libxrpl.shamap > xrpl.shamap
+libxrpl.telemetry > xrpl.basics
+libxrpl.telemetry > xrpl.telemetry
+libxrpl.tx > xrpl.basics
+libxrpl.tx > xrpl.conditions
+libxrpl.tx > xrpl.core
+libxrpl.tx > xrpl.json
+libxrpl.tx > xrpl.ledger
+libxrpl.tx > xrpl.protocol
+libxrpl.tx > xrpl.server
+libxrpl.tx > xrpl.tx
 test.app > test.jtx
 test.app > test.rpc
 test.app > test.toplevel
@@ -41,7 +58,10 @@ test.app > xrpl.json
 test.app > xrpl.ledger
 test.app > xrpl.nodestore
 test.app > xrpl.protocol
+test.app > xrpl.rdb
 test.app > xrpl.resource
+test.app > xrpl.server
+test.app > xrpl.tx
 test.basics > test.jtx
 test.basics > test.unit_test
 test.basics > xrpl.basics
@@ -51,7 +71,7 @@ test.basics > xrpl.json
 test.basics > xrpl.protocol
 test.beast > xrpl.basics
 test.conditions > xrpl.basics
-test.conditions > xrpld.conditions
+test.conditions > xrpl.conditions
 test.consensus > test.csf
 test.consensus > test.toplevel
 test.consensus > test.unit_test
@@ -60,6 +80,7 @@ test.consensus > xrpld.app
 test.consensus > xrpld.consensus
 test.consensus > xrpl.json
 test.consensus > xrpl.ledger
+test.consensus > xrpl.tx
 test.core > test.jtx
 test.core > test.toplevel
 test.core > test.unit_test
@@ -67,14 +88,18 @@ test.core > xrpl.basics
 test.core > xrpl.core
 test.core > xrpld.core
 test.core > xrpl.json
+test.core > xrpl.rdb
 test.core > xrpl.server
 test.csf > xrpl.basics
 test.csf > xrpld.consensus
 test.csf > xrpl.json
+test.csf > xrpl.ledger
 test.csf > xrpl.protocol
+test.csf > xrpl.telemetry
 test.json > test.jtx
 test.json > xrpl.json
 test.jtx > xrpl.basics
+test.jtx > xrpl.core
 test.jtx > xrpld.app
 test.jtx > xrpld.core
 test.jtx > xrpld.rpc
@@ -84,10 +109,10 @@ test.jtx > xrpl.net
 test.jtx > xrpl.protocol
 test.jtx > xrpl.resource
 test.jtx > xrpl.server
+test.jtx > xrpl.tx
 test.ledger > test.jtx
 test.ledger > test.toplevel
 test.ledger > xrpl.basics
-test.ledger > xrpld.app
 test.ledger > xrpld.core
 test.ledger > xrpl.ledger
 test.ledger > xrpl.protocol
@@ -95,8 +120,8 @@ test.nodestore > test.jtx
 test.nodestore > test.toplevel
 test.nodestore > test.unit_test
 test.nodestore > xrpl.basics
-test.nodestore > xrpld.core
 test.nodestore > xrpl.nodestore
+test.nodestore > xrpl.rdb
 test.overlay > test.jtx
 test.overlay > test.toplevel
 test.overlay > test.unit_test
@@ -104,6 +129,7 @@ test.overlay > xrpl.basics
 test.overlay > xrpld.app
 test.overlay > xrpld.overlay
 test.overlay > xrpld.peerfinder
+test.overlay > xrpl.ledger
 test.overlay > xrpl.nodestore
 test.overlay > xrpl.protocol
 test.overlay > xrpl.shamap
@@ -114,6 +140,7 @@ test.peerfinder > xrpld.core
 test.peerfinder > xrpld.peerfinder
 test.peerfinder > xrpl.protocol
 test.protocol > test.toplevel
+test.protocol > test.unit_test
 test.protocol > xrpl.basics
 test.protocol > xrpl.json
 test.protocol > xrpl.protocol
@@ -129,8 +156,11 @@ test.rpc > xrpld.core
 test.rpc > xrpld.overlay
 test.rpc > xrpld.rpc
 test.rpc > xrpl.json
+test.rpc > xrpl.ledger
 test.rpc > xrpl.protocol
 test.rpc > xrpl.resource
+test.rpc > xrpl.server
+test.rpc > xrpl.tx
 test.server > test.jtx
 test.server > test.toplevel
 test.server > test.unit_test
@@ -148,61 +178,96 @@ test.shamap > xrpl.shamap
 test.toplevel > test.csf
 test.toplevel > xrpl.json
 test.unit_test > xrpl.basics
+test.unit_test > xrpl.protocol
 tests.libxrpl > xrpl.basics
+tests.libxrpl > xrpld.telemetry
 tests.libxrpl > xrpl.json
 tests.libxrpl > xrpl.net
+tests.libxrpl > xrpl.protocol
+tests.libxrpl > xrpl.protocol_autogen
+tests.libxrpl > xrpl.telemetry
+xrpl.conditions > xrpl.basics
+xrpl.conditions > xrpl.protocol
 xrpl.core > xrpl.basics
 xrpl.core > xrpl.json
+xrpl.core > xrpl.protocol
 xrpl.json > xrpl.basics
 xrpl.ledger > xrpl.basics
 xrpl.ledger > xrpl.protocol
+xrpl.ledger > xrpl.server
+xrpl.ledger > xrpl.shamap
 xrpl.net > xrpl.basics
 xrpl.nodestore > xrpl.basics
 xrpl.nodestore > xrpl.protocol
 xrpl.protocol > xrpl.basics
 xrpl.protocol > xrpl.json
+xrpl.protocol_autogen > xrpl.json
+xrpl.protocol_autogen > xrpl.protocol
+xrpl.rdb > xrpl.basics
+xrpl.rdb > xrpl.core
+xrpl.rdb > xrpl.protocol
 xrpl.resource > xrpl.basics
 xrpl.resource > xrpl.json
 xrpl.resource > xrpl.protocol
 xrpl.server > xrpl.basics
+xrpl.server > xrpl.core
 xrpl.server > xrpl.json
 xrpl.server > xrpl.protocol
+xrpl.server > xrpl.rdb
+xrpl.server > xrpl.resource
+xrpl.server > xrpl.shamap
 xrpl.shamap > xrpl.basics
 xrpl.shamap > xrpl.nodestore
 xrpl.shamap > xrpl.protocol
+xrpl.telemetry > xrpl.basics
+xrpl.tx > xrpl.basics
+xrpl.tx > xrpl.core
+xrpl.tx > xrpl.ledger
+xrpl.tx > xrpl.protocol
 xrpld.app > test.unit_test
 xrpld.app > xrpl.basics
 xrpld.app > xrpl.core
-xrpld.app > xrpld.conditions
 xrpld.app > xrpld.consensus
+xrpld.app > xrpld.core
+xrpld.app > xrpld.telemetry
 xrpld.app > xrpl.json
 xrpld.app > xrpl.ledger
 xrpld.app > xrpl.net
 xrpld.app > xrpl.nodestore
 xrpld.app > xrpl.protocol
+xrpld.app > xrpl.rdb
 xrpld.app > xrpl.resource
+xrpld.app > xrpl.server
 xrpld.app > xrpl.shamap
-xrpld.conditions > xrpl.basics
-xrpld.conditions > xrpl.protocol
+xrpld.app > xrpl.telemetry
+xrpld.app > xrpl.tx
 xrpld.consensus > xrpl.basics
+xrpld.consensus > xrpld.telemetry
 xrpld.consensus > xrpl.json
+xrpld.consensus > xrpl.ledger
 xrpld.consensus > xrpl.protocol
+xrpld.consensus > xrpl.telemetry
 xrpld.core > xrpl.basics
 xrpld.core > xrpl.core
 xrpld.core > xrpl.json
 xrpld.core > xrpl.net
 xrpld.core > xrpl.protocol
+xrpld.core > xrpl.rdb
 xrpld.overlay > xrpl.basics
 xrpld.overlay > xrpl.core
 xrpld.overlay > xrpld.core
 xrpld.overlay > xrpld.peerfinder
+xrpld.overlay > xrpld.telemetry
 xrpld.overlay > xrpl.json
 xrpld.overlay > xrpl.protocol
+xrpld.overlay > xrpl.rdb
 xrpld.overlay > xrpl.resource
 xrpld.overlay > xrpl.server
+xrpld.overlay > xrpl.tx
 xrpld.peerfinder > xrpl.basics
 xrpld.peerfinder > xrpld.core
 xrpld.peerfinder > xrpl.protocol
+xrpld.peerfinder > xrpl.rdb
 xrpld.perflog > xrpl.basics
 xrpld.perflog > xrpl.core
 xrpld.perflog > xrpld.rpc
@@ -210,11 +275,15 @@ xrpld.perflog > xrpl.json
 xrpld.rpc > xrpl.basics
 xrpld.rpc > xrpl.core
 xrpld.rpc > xrpld.core
+xrpld.rpc > xrpld.telemetry
 xrpld.rpc > xrpl.json
 xrpld.rpc > xrpl.ledger
 xrpld.rpc > xrpl.net
 xrpld.rpc > xrpl.nodestore
 xrpld.rpc > xrpl.protocol
+xrpld.rpc > xrpl.rdb
 xrpld.rpc > xrpl.resource
 xrpld.rpc > xrpl.server
+xrpld.rpc > xrpl.tx
 xrpld.shamap > xrpl.shamap
+xrpld.telemetry > xrpl.telemetry

.github/scripts/rename/include.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+# Exit the script as soon as an error occurs.
+set -e
+
+# This script checks whether there are no new include guards introduced by a new
+# PR, as header files should use "#pragma once" instead. The script assumes any
+# include guards will use "XRPL_" as prefix.
+# Usage: .github/scripts/rename/include.sh <repository directory>
+
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 <repository directory>"
+    exit 1
+fi
+
+DIRECTORY=$1
+echo "Processing directory: ${DIRECTORY}"
+if [ ! -d "${DIRECTORY}" ]; then
+    echo "Error: Directory '${DIRECTORY}' does not exist."
+    exit 1
+fi
+
+find "${DIRECTORY}" -type f \( -name "*.h" -o -name "*.hpp" -o -name "*.ipp" \) | while read -r FILE; do
+    echo "Processing file: ${FILE}"
+    if grep -q "#ifndef XRPL_" "${FILE}"; then
+      echo "Please replace all include guards by #pragma once."
+      exit 1
+    fi
+done
+echo "Checking complete."

.github/scripts/strategy-matrix/generate.py

@@ -51,22 +51,20 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
         # Only generate a subset of configurations in PRs.
         if not all:
             # Debian:
-            # - Bookworm using GCC 13: Release and Unity on linux/amd64, set
-            #   the reference fee to 500.
-            # - Bookworm using GCC 15: Debug and no Unity on linux/amd64, enable
-            #   code coverage (which will be done below).
-            # - Bookworm using Clang 16: Debug and no Unity on linux/arm64,
-            #   enable voidstar.
-            # - Bookworm using Clang 17: Release and no Unity on linux/amd64,
-            #   set the reference fee to 1000.
-            # - Bookworm using Clang 20: Debug and Unity on linux/amd64.
+            # - Bookworm using GCC 13: Release on linux/amd64, set the reference
+            #   fee to 500.
+            # - Bookworm using GCC 15: Debug on linux/amd64, enable code
+            #   coverage (which will be done below).
+            # - Bookworm using Clang 16: Debug on linux/amd64, enable voidstar.
+            # - Bookworm using Clang 17: Release on linux/amd64, set the
+            #   reference fee to 1000.
+            # - Bookworm using Clang 20: Debug on linux/amd64.
             if os["distro_name"] == "debian":
                 skip = True
                 if os["distro_version"] == "bookworm":
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-13"
                         and build_type == "Release"
-                        and "-Dunity=ON" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         cmake_args = f"-DUNIT_TEST_REFERENCE_FEE=500 {cmake_args}"
@@ -74,22 +72,19 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-15"
                         and build_type == "Debug"
-                        and "-Dunity=OFF" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         skip = False
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "clang-16"
                         and build_type == "Debug"
-                        and "-Dunity=OFF" in cmake_args
-                        and architecture["platform"] == "linux/arm64"
+                        and architecture["platform"] == "linux/amd64"
                     ):
                         cmake_args = f"-Dvoidstar=ON {cmake_args}"
                         skip = False
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "clang-17"
                         and build_type == "Release"
-                        and "-Dunity=ON" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         cmake_args = f"-DUNIT_TEST_REFERENCE_FEE=1000 {cmake_args}"
@@ -97,7 +92,6 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "clang-20"
                         and build_type == "Debug"
-                        and "-Dunity=ON" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         skip = False
@@ -105,15 +99,14 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     continue
 
             # RHEL:
-            # - 9 using GCC 12: Debug and Unity on linux/amd64.
-            # - 10 using Clang: Release and no Unity on linux/amd64.
+            # - 9 using GCC 12: Debug on linux/amd64.
+            # - 10 using Clang: Release on linux/amd64.
             if os["distro_name"] == "rhel":
                 skip = True
                 if os["distro_version"] == "9":
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-12"
                         and build_type == "Debug"
-                        and "-Dunity=ON" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         skip = False
@@ -121,7 +114,6 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "clang-any"
                         and build_type == "Release"
-                        and "-Dunity=OFF" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         skip = False
@@ -129,17 +121,16 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     continue
 
             # Ubuntu:
-            # - Jammy using GCC 12: Debug and no Unity on linux/arm64.
-            # - Noble using GCC 14: Release and Unity on linux/amd64.
-            # - Noble using Clang 18: Debug and no Unity on linux/amd64.
-            # - Noble using Clang 19: Release and Unity on linux/arm64.
+            # - Jammy using GCC 12: Debug on linux/arm64.
+            # - Noble using GCC 14: Release on linux/amd64.
+            # - Noble using Clang 18: Debug on linux/amd64.
+            # - Noble using Clang 19: Release on linux/arm64.
             if os["distro_name"] == "ubuntu":
                 skip = True
                 if os["distro_version"] == "jammy":
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-12"
                         and build_type == "Debug"
-                        and "-Dunity=OFF" in cmake_args
                         and architecture["platform"] == "linux/arm64"
                     ):
                         skip = False
@@ -147,21 +138,18 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-14"
                         and build_type == "Release"
-                        and "-Dunity=ON" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         skip = False
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "clang-18"
                         and build_type == "Debug"
-                        and "-Dunity=OFF" in cmake_args
                         and architecture["platform"] == "linux/amd64"
                     ):
                         skip = False
                     if (
                         f"{os['compiler_name']}-{os['compiler_version']}" == "clang-19"
                         and build_type == "Release"
-                        and "-Dunity=ON" in cmake_args
                         and architecture["platform"] == "linux/arm64"
                     ):
                         skip = False
@@ -169,20 +157,16 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
                     continue
 
             # MacOS:
-            # - Debug and no Unity on macos/arm64.
+            # - Debug on macos/arm64.
             if os["distro_name"] == "macos" and not (
-                build_type == "Debug"
-                and "-Dunity=OFF" in cmake_args
-                and architecture["platform"] == "macos/arm64"
+                build_type == "Debug" and architecture["platform"] == "macos/arm64"
             ):
                 continue
 
             # Windows:
-            # - Release and Unity on windows/amd64.
+            # - Release on windows/amd64.
             if os["distro_name"] == "windows" and not (
-                build_type == "Release"
-                and "-Dunity=ON" in cmake_args
-                and architecture["platform"] == "windows/amd64"
+                build_type == "Release" and architecture["platform"] == "windows/amd64"
             ):
                 continue
 
@@ -209,18 +193,28 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
         ):
             continue
 
-        # Enable code coverage for Debian Bookworm using GCC 15 in Debug and no
-        # Unity on linux/amd64
+        # Enable code coverage for Debian Bookworm using GCC 15 in Debug on
+        # linux/amd64
         if (
-            f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-15"
+            f"{os['distro_name']}-{os['distro_version']}" == "debian-bookworm"
+            and f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-15"
             and build_type == "Debug"
-            and "-Dunity=OFF" in cmake_args
             and architecture["platform"] == "linux/amd64"
         ):
-            cmake_args = f"-Dcoverage=ON -Dcoverage_format=xml -DCODE_COVERAGE_VERBOSE=ON -DCMAKE_C_FLAGS=-O0 -DCMAKE_CXX_FLAGS=-O0 {cmake_args}"
+            cmake_args = f"{cmake_args} -Dcoverage=ON -Dcoverage_format=xml -DCODE_COVERAGE_VERBOSE=ON -DCMAKE_C_FLAGS=-O0 -DCMAKE_CXX_FLAGS=-O0"
+
+        # Enable unity build for Ubuntu Jammy using GCC 12 in Debug on
+        # linux/amd64.
+        if (
+            f"{os['distro_name']}-{os['distro_version']}" == "ubuntu-jammy"
+            and f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-12"
+            and build_type == "Debug"
+            and architecture["platform"] == "linux/amd64"
+        ):
+            cmake_args = f"{cmake_args} -Dunity=ON"
 
         # Generate a unique name for the configuration, e.g. macos-arm64-debug
-        # or debian-bookworm-gcc-12-amd64-release-unity.
+        # or debian-bookworm-gcc-12-amd64-release.
         config_name = os["distro_name"]
         if (n := os["distro_version"]) != "":
             config_name += f"-{n}"

.github/scripts/strategy-matrix/linux.json

@@ -208,5 +208,5 @@
     }
   ],
   "build_type": ["Debug", "Release"],
-  "cmake_args": ["-Dunity=OFF", "-Dunity=ON"]
+  "cmake_args": [""]
 }

.github/scripts/strategy-matrix/macos.json

@@ -15,8 +15,5 @@
     }
   ],
   "build_type": ["Debug", "Release"],
-  "cmake_args": [
-    "-Dunity=OFF -DCMAKE_POLICY_VERSION_MINIMUM=3.5",
-    "-Dunity=ON -DCMAKE_POLICY_VERSION_MINIMUM=3.5"
-  ]
+  "cmake_args": ["-DCMAKE_POLICY_VERSION_MINIMUM=3.5"]
 }

.github/scripts/strategy-matrix/windows.json

@@ -15,5 +15,5 @@
     }
   ],
   "build_type": ["Debug", "Release"],
-  "cmake_args": ["-Dunity=OFF", "-Dunity=ON"]
+  "cmake_args": [""]
 }

.github/workflows/check-pr-commits.yml

@@ -0,0 +1,13 @@
+name: Check PR commits
+
+on:
+  pull_request:
+
+# The action needs to have write permissions to post comments on the PR.
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  check_commits:
+    uses: XRPLF/actions/.github/workflows/check-pr-commits.yml@481048b78b94ac3343d1292b4ef125a813879f2b

.github/workflows/check-pr-title.yml

@@ -0,0 +1,14 @@
+name: Check PR title
+
+on:
+  merge_group:
+    types:
+      - checks_requested
+  pull_request:
+    types: [opened, edited, reopened, synchronize, ready_for_review]
+    branches: [develop]
+
+jobs:
+  check_title:
+    if: ${{ github.event.pull_request.draft != true }}
+    uses: XRPLF/actions/.github/workflows/check-pr-title.yml@e2c7f400d1e85ae65dad552fd425169fbacca4a3

.github/workflows/conflicting-pr.yml

@@ -0,0 +1,25 @@
+name: Label PRs with merge conflicts
+
+on:
+  # So that PRs touching the same files as the push are updated.
+  push:
+  # So that the `dirtyLabel` is removed if conflicts are resolved.
+  # We recommend `pull_request_target` so that github secrets are available.
+  # In `pull_request` we wouldn't be able to change labels of fork PRs.
+  pull_request_target:
+    types: [synchronize]
+
+permissions:
+  pull-requests: write
+
+jobs:
+  main:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check if PRs are dirty
+        uses: eps1lon/actions-label-merge-conflict@1df065ebe6e3310545d4f4c4e862e43bdca146f0 # v3.0.3
+        with:
+          dirtyLabel: "PR: has conflicts"
+          repoToken: "${{ secrets.GITHUB_TOKEN }}"
+          commentOnDirty: "This PR has conflicts, please resolve them in order for the PR to be reviewed."
+          commentOnClean: "All conflicts have been resolved. Assigned reviewers can now start or resume their review."

.github/workflows/on-pr.yml

@@ -33,7 +33,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
       - name: Determine changed files
         # This step checks whether any files have changed that should
         # cause the next jobs to run. We do it this way rather than
@@ -46,7 +46,7 @@ jobs:
         # that Github considers any skipped jobs to have passed, and in
         # turn the required checks as well.
         id: changes
-        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             # These paths are unique to `on-pr.yml`.
@@ -59,14 +59,18 @@ jobs:
             # Keep the paths below in sync with those in `on-trigger.yml`.
             .github/actions/build-deps/**
             .github/actions/build-test/**
+            .github/actions/generate-version/**
             .github/actions/setup-conan/**
             .github/scripts/strategy-matrix/**
             .github/workflows/reusable-build.yml
             .github/workflows/reusable-build-test-config.yml
             .github/workflows/reusable-build-test.yml
+            .github/workflows/reusable-clang-tidy.yml
+            .github/workflows/reusable-clang-tidy-files.yml
             .github/workflows/reusable-strategy-matrix.yml
             .github/workflows/reusable-test.yml
             .github/workflows/reusable-upload-recipe.yml
+            .clang-tidy
             .codecov.yml
             cmake/**
             conan/**
@@ -106,6 +110,17 @@ jobs:
     if: ${{ needs.should-run.outputs.go == 'true' }}
     uses: ./.github/workflows/reusable-check-rename.yml
 
+  clang-tidy:
+    needs: should-run
+    if: ${{ needs.should-run.outputs.go == 'true' }}
+    uses: ./.github/workflows/reusable-clang-tidy.yml
+    permissions:
+      issues: write
+      contents: read
+    with:
+      check_only_changed: true
+      create_issue_on_failure: false
+
   build-test:
     needs: should-run
     if: ${{ needs.should-run.outputs.go == 'true' }}
@@ -126,9 +141,8 @@ jobs:
     needs:
       - should-run
       - build-test
-    # Only run when committing to a PR that targets a release branch in the
-    # XRPLF repository.
-    if: ${{ github.repository_owner == 'XRPLF' && needs.should-run.outputs.go == 'true' && startsWith(github.ref, 'refs/heads/release') }}
+    # Only run when committing to a PR that targets a release branch.
+    if: ${{ github.repository == 'XRPLF/rippled' && needs.should-run.outputs.go == 'true' && github.event_name == 'pull_request' && startsWith(github.event.pull_request.base.ref, 'release') }}
     uses: ./.github/workflows/reusable-upload-recipe.yml
     secrets:
       remote_username: ${{ secrets.CONAN_REMOTE_USERNAME }}
@@ -155,6 +169,7 @@ jobs:
     needs:
       - check-levelization
       - check-rename
+      - clang-tidy
       - build-test
       - upload-recipe
       - notify-clio

.github/workflows/on-tag.yml

@@ -5,7 +5,7 @@ name: Tag
 on:
   push:
     tags:
-      - "v*"
+      - "[0-9]+.[0-9]+.[0-9]*"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -17,8 +17,7 @@ defaults:
 
 jobs:
   upload-recipe:
-    # Only run when a tag is pushed to the XRPLF repository.
-    if: ${{ github.repository_owner == 'XRPLF' }}
+    if: ${{ github.repository == 'XRPLF/rippled' }}
     uses: ./.github/workflows/reusable-upload-recipe.yml
     secrets:
       remote_username: ${{ secrets.CONAN_REMOTE_USERNAME }}

.github/workflows/on-trigger.yml

@@ -16,14 +16,18 @@ on:
       # Keep the paths below in sync with those in `on-pr.yml`.
       - ".github/actions/build-deps/**"
       - ".github/actions/build-test/**"
+      - ".github/actions/generate-version/**"
       - ".github/actions/setup-conan/**"
       - ".github/scripts/strategy-matrix/**"
       - ".github/workflows/reusable-build.yml"
       - ".github/workflows/reusable-build-test-config.yml"
       - ".github/workflows/reusable-build-test.yml"
+      - ".github/workflows/reusable-clang-tidy.yml"
+      - ".github/workflows/reusable-clang-tidy-files.yml"
       - ".github/workflows/reusable-strategy-matrix.yml"
       - ".github/workflows/reusable-test.yml"
       - ".github/workflows/reusable-upload-recipe.yml"
+      - ".clang-tidy"
       - ".codecov.yml"
       - "cmake/**"
       - "conan/**"
@@ -59,6 +63,15 @@ defaults:
     shell: bash
 
 jobs:
+  clang-tidy:
+    uses: ./.github/workflows/reusable-clang-tidy.yml
+    permissions:
+      issues: write
+      contents: read
+    with:
+      check_only_changed: false
+      create_issue_on_failure: ${{ github.event_name == 'schedule' }}
+
   build-test:
     uses: ./.github/workflows/reusable-build-test.yml
     strategy:
@@ -79,8 +92,8 @@ jobs:
 
   upload-recipe:
     needs: build-test
-    # Only run when pushing to the develop branch in the XRPLF repository.
-    if: ${{ github.repository_owner == 'XRPLF' && github.event_name == 'push' && github.ref == 'refs/heads/develop' }}
+    # Only run when pushing to the develop branch.
+    if: ${{ github.repository == 'XRPLF/rippled' && github.event_name == 'push' && github.ref == 'refs/heads/develop' }}
     uses: ./.github/workflows/reusable-upload-recipe.yml
     secrets:
       remote_username: ${{ secrets.CONAN_REMOTE_USERNAME }}

.github/workflows/pre-commit.yml

@@ -1,6 +1,9 @@
 name: Run pre-commit hooks
 
 on:
+  merge_group:
+    types:
+      - checks_requested
   pull_request:
   push:
     branches:
@@ -11,7 +14,7 @@ on:
 jobs:
   # Call the workflow in the XRPLF/actions repo that runs the pre-commit hooks.
   run-hooks:
-    uses: XRPLF/actions/.github/workflows/pre-commit.yml@282890f46d6921249d5659dd38babcb0bd8aef48
+    uses: XRPLF/actions/.github/workflows/pre-commit.yml@e7896f15cc60d0da1a272c77ee5c4026b424f9c7
     with:
       runs_on: ubuntu-latest
-      container: '{ "image": "ghcr.io/xrplf/ci/tools-rippled-pre-commit:sha-ab4d1f0" }'
+      container: '{ "image": "ghcr.io/xrplf/ci/tools-rippled-pre-commit:sha-41ec7c1" }'

.github/workflows/publish-docs.yml

@@ -4,6 +4,17 @@ name: Build and publish documentation
 
 on:
   push:
+    branches:
+      - "develop"
+    paths:
+      - ".github/workflows/publish-docs.yml"
+      - "*.md"
+      - "**/*.md"
+      - "docs/**"
+      - "include/**"
+      - "src/libxrpl/**"
+      - "src/xrpld/**"
+  pull_request:
     paths:
       - ".github/workflows/publish-docs.yml"
       - "*.md"
@@ -23,20 +34,25 @@ defaults:
 
 env:
   BUILD_DIR: build
-  NPROC_SUBTRACT: 2
+  # ubuntu-latest has only 2 CPUs for private repositories
+  # https://docs.github.com/en/actions/reference/runners/github-hosted-runners#standard-github-hosted-runners-for--private-repositories
+  NPROC_SUBTRACT: ${{ github.event.repository.private && '1' || '2' }}
 
 jobs:
-  publish:
+  build:
     runs-on: ubuntu-latest
     container: ghcr.io/xrplf/ci/tools-rippled-documentation:sha-a8c7be1
-    permissions:
-      contents: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@2bbc2dc1abeec7bfaa886804ab86871ac201764e
+        with:
+          enable_ccache: false
 
       - name: Get number of processors
-        uses: XRPLF/actions/get-nproc@2ece4ec6ab7de266859a6f053571425b2bd684b6
+        uses: XRPLF/actions/get-nproc@cf0433aa74563aead044a1e395610c96d65a37cf
         id: nproc
         with:
           subtract: ${{ env.NPROC_SUBTRACT }}
@@ -64,9 +80,23 @@ jobs:
           cmake -Donly_docs=ON ..
           cmake --build . --target docs --parallel ${BUILD_NPROC}
 
-      - name: Publish documentation
-        if: ${{ github.ref_type == 'branch' && github.ref_name == github.event.repository.default_branch }}
-        uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0
+      - name: Create documentation artifact
+        if: ${{ github.event_name == 'push' }}
+        uses: actions/upload-pages-artifact@7b1f4a764d45c48632c6b24a0339c27f5614fb0b # v4.0.0
         with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          publish_dir: ${{ env.BUILD_DIR }}/docs/html
+          path: ${{ env.BUILD_DIR }}/docs/html
+
+  deploy:
+    if: ${{ github.event_name == 'push' }}
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deploy.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deploy
+        uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128 # v5.0.0

.github/workflows/reusable-build-test-config.yml

@@ -76,7 +76,7 @@ jobs:
     name: ${{ inputs.config_name }}
     runs-on: ${{ fromJSON(inputs.runs_on) }}
     container: ${{ inputs.image != '' && inputs.image || null }}
-    timeout-minutes: 60
+    timeout-minutes: ${{ inputs.sanitizers != '' && 360 || 60 }}
     env:
       # Use a namespace to keep the objects separate for each configuration.
       CCACHE_NAMESPACE: ${{ inputs.config_name }}
@@ -101,13 +101,13 @@ jobs:
     steps:
       - name: Cleanup workspace (macOS and Windows)
         if: ${{ runner.os == 'macOS' || runner.os == 'Windows' }}
-        uses: XRPLF/actions/cleanup-workspace@2ece4ec6ab7de266859a6f053571425b2bd684b6
+        uses: XRPLF/actions/cleanup-workspace@cf0433aa74563aead044a1e395610c96d65a37cf
 
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@f05cab7b8541eee6473aa42beb9d2fe35608a190
+        uses: XRPLF/actions/prepare-runner@2bbc2dc1abeec7bfaa886804ab86871ac201764e
         with:
           enable_ccache: ${{ inputs.ccache_enabled }}
 
@@ -119,12 +119,14 @@ jobs:
         uses: ./.github/actions/print-env
 
       - name: Get number of processors
-        uses: XRPLF/actions/get-nproc@2ece4ec6ab7de266859a6f053571425b2bd684b6
+        uses: XRPLF/actions/get-nproc@cf0433aa74563aead044a1e395610c96d65a37cf
         id: nproc
         with:
           subtract: ${{ inputs.nproc_subtract }}
 
       - name: Setup Conan
+        env:
+          SANITIZERS: ${{ inputs.sanitizers }}
         uses: ./.github/actions/setup-conan
 
       - name: Build dependencies
@@ -164,6 +166,29 @@ jobs:
             --parallel "${BUILD_NPROC}" \
             --target "${CMAKE_TARGET}"
 
+      - name: Check protocol autogen files are up-to-date
+        env:
+          MESSAGE: |
+
+            The generated protocol wrapper classes are out of date.
+
+            This typically happens when your branch is behind develop and
+            the macro files or generator scripts have changed.
+
+            To fix this:
+              1. Update your branch from develop (merge or rebase)
+              2. Build with code generation enabled (XRPL_NO_CODEGEN=OFF)
+              3. Commit and push the regenerated files
+        run: |
+          set -e
+          DIFF=$(git status --porcelain -- include/xrpl/protocol_autogen src/tests/libxrpl/protocol_autogen)
+          if [ -n "${DIFF}" ]; then
+            echo "::error::Generated protocol files are out of date"
+            git diff -- include/xrpl/protocol_autogen src/tests/libxrpl/protocol_autogen
+            echo "${MESSAGE}"
+            exit 1
+          fi
+
       - name: Show ccache statistics
         if: ${{ inputs.ccache_enabled }}
         run: |
@@ -174,8 +199,8 @@ jobs:
           fi
 
       - name: Upload the binary (Linux)
-        if: ${{ github.repository_owner == 'XRPLF' && runner.os == 'Linux' }}
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
+        if: ${{ github.event.repository.visibility == 'public' && runner.os == 'Linux' }}
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
         with:
           name: xrpld-${{ inputs.config_name }}
           path: ${{ env.BUILD_DIR }}/xrpld
@@ -202,11 +227,17 @@ jobs:
 
       - name: Set sanitizer options
         if: ${{ !inputs.build_only && env.SANITIZERS_ENABLED == 'true' }}
+        env:
+          CONFIG_NAME: ${{ inputs.config_name }}
         run: |
-          echo "ASAN_OPTIONS=print_stacktrace=1:detect_container_overflow=0:suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/asan.supp" >> ${GITHUB_ENV}
-          echo "TSAN_OPTIONS=second_deadlock_stack=1:halt_on_error=0:suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/tsan.supp" >> ${GITHUB_ENV}
-          echo "UBSAN_OPTIONS=suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/ubsan.supp" >> ${GITHUB_ENV}
-          echo "LSAN_OPTIONS=suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/lsan.supp" >> ${GITHUB_ENV}
+          ASAN_OPTS="include=${GITHUB_WORKSPACE}/sanitizers/suppressions/runtime-asan-options.txt:suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/asan.supp"
+          if [[ "${CONFIG_NAME}" == *gcc* ]]; then
+            ASAN_OPTS="${ASAN_OPTS}:alloc_dealloc_mismatch=0"
+          fi
+          echo "ASAN_OPTIONS=${ASAN_OPTS}" >> ${GITHUB_ENV}
+          echo "TSAN_OPTIONS=include=${GITHUB_WORKSPACE}/sanitizers/suppressions/runtime-tsan-options.txt:suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/tsan.supp" >> ${GITHUB_ENV}
+          echo "UBSAN_OPTIONS=include=${GITHUB_WORKSPACE}/sanitizers/suppressions/runtime-ubsan-options.txt:suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/ubsan.supp" >> ${GITHUB_ENV}
+          echo "LSAN_OPTIONS=include=${GITHUB_WORKSPACE}/sanitizers/suppressions/runtime-lsan-options.txt:suppressions=${GITHUB_WORKSPACE}/sanitizers/suppressions/lsan.supp" >> ${GITHUB_ENV}
 
       - name: Run the separate tests
         if: ${{ !inputs.build_only }}
@@ -227,7 +258,10 @@ jobs:
         env:
           BUILD_NPROC: ${{ steps.nproc.outputs.nproc }}
         run: |
-          ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}"
+          set -o pipefail
+          # Coverage builds are slower due to instrumentation; use fewer parallel jobs to avoid flakiness
+          [ "$COVERAGE_ENABLED" = "true" ] && BUILD_NPROC=$(( BUILD_NPROC - 2 ))
+          ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}" 2>&1 | tee unittest.log
 
       - name: Debug failure (Linux)
         if: ${{ failure() && runner.os == 'Linux' && !inputs.build_only }}
@@ -251,8 +285,8 @@ jobs:
             --target coverage
 
       - name: Upload coverage report
-        if: ${{ github.repository_owner == 'XRPLF' && !inputs.build_only && env.COVERAGE_ENABLED == 'true' }}
-        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
+        if: ${{ github.repository == 'XRPLF/rippled' && !inputs.build_only && env.COVERAGE_ENABLED == 'true' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
         with:
           disable_search: true
           disable_telem: true

.github/workflows/reusable-check-levelization.yml

@@ -18,9 +18,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
       - name: Check levelization
-        run: .github/scripts/levelization/generate.sh
+        run: python .github/scripts/levelization/generate.py
       - name: Check for differences
         env:
           MESSAGE: |
@@ -32,7 +32,7 @@ jobs:
             removed from loops.txt, it's probably an improvement, while if
             something was added, it's probably a regression.
 
-            Run '.github/scripts/levelization/generate.sh' in your repo, commit
+            Run '.github/scripts/levelization/generate.py' in your repo, commit
             and push the changes. See .github/scripts/levelization/README.md for
             more info.
         run: |

.github/workflows/reusable-check-rename.yml

@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
       - name: Check definitions
         run: .github/scripts/rename/definitions.sh .
       - name: Check copyright notices
@@ -31,6 +31,8 @@ jobs:
         run: .github/scripts/rename/namespace.sh .
       - name: Check config name
         run: .github/scripts/rename/config.sh .
+      - name: Check include guards
+        run: .github/scripts/rename/include.sh .
       - name: Check for differences
         env:
           MESSAGE: |

.github/workflows/reusable-clang-tidy-files.yml

@@ -0,0 +1,162 @@
+name: Run clang-tidy on files
+
+on:
+  workflow_call:
+    inputs:
+      files:
+        description: "List of files to check (empty means check all files)"
+        type: string
+        default: ""
+      create_issue_on_failure:
+        description: "Whether to create an issue if the check failed"
+        type: boolean
+        default: false
+
+defaults:
+  run:
+    shell: bash
+
+env:
+  # Conan installs the generators in the build/generators directory, see the
+  # layout() method in conanfile.py. We then run CMake from the build directory.
+  BUILD_DIR: build
+  BUILD_TYPE: Release
+
+jobs:
+  run-clang-tidy:
+    name: Run clang tidy
+    runs-on: ["self-hosted", "Linux", "X64", "heavy"]
+    container: "ghcr.io/xrplf/ci/debian-trixie:clang-21-sha-53033a2"
+    permissions:
+      issues: write
+      contents: read
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@2bbc2dc1abeec7bfaa886804ab86871ac201764e
+        with:
+          enable_ccache: false
+
+      - name: Print build environment
+        uses: ./.github/actions/print-env
+
+      - name: Get number of processors
+        uses: XRPLF/actions/get-nproc@cf0433aa74563aead044a1e395610c96d65a37cf
+        id: nproc
+
+      - name: Setup Conan
+        uses: ./.github/actions/setup-conan
+
+      - name: Build dependencies
+        uses: ./.github/actions/build-deps
+        with:
+          build_nproc: ${{ steps.nproc.outputs.nproc }}
+          build_type: ${{ env.BUILD_TYPE }}
+          log_verbosity: verbose
+
+      - name: Configure CMake
+        working-directory: ${{ env.BUILD_DIR }}
+        run: |
+          cmake \
+            -G 'Ninja' \
+            -DCMAKE_TOOLCHAIN_FILE:FILEPATH=build/generators/conan_toolchain.cmake \
+            -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
+            -Dtests=ON \
+            -Dwerr=ON \
+            -Dxrpld=ON \
+            ..
+
+      # clang-tidy needs headers generated from proto files
+      - name: Build libxrpl.libpb
+        working-directory: ${{ env.BUILD_DIR }}
+        run: |
+          ninja -j ${{ steps.nproc.outputs.nproc }} xrpl.libpb
+
+      - name: Run clang tidy
+        id: run_clang_tidy
+        continue-on-error: true
+        env:
+          FILES: ${{ inputs.files }}
+        run: |
+          run-clang-tidy -j ${{ steps.nproc.outputs.nproc }} -p "$BUILD_DIR" $FILES 2>&1 | tee clang-tidy-output.txt
+
+      - name: Upload clang-tidy output
+        if: ${{ github.event.repository.visibility == 'public' && steps.run_clang_tidy.outcome != 'success' }}
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        with:
+          name: clang-tidy-results
+          path: clang-tidy-output.txt
+          retention-days: 30
+
+      - name: Create an issue
+        if: steps.run_clang_tidy.outcome != 'success' && inputs.create_issue_on_failure
+        id: create_issue
+        shell: bash
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          # Prepare issue body with clang-tidy output
+          cat > issue.md <<EOF
+          ## Clang-tidy Check Failed
+
+          **Workflow:** ${{ github.workflow }}
+          **Run ID:** ${{ github.run_id }}
+          **Commit:** ${{ github.sha }}
+          **Branch/Ref:** ${{ github.ref }}
+          **Triggered by:** ${{ github.actor }}
+
+          ### Clang-tidy Output:
+          \`\`\`
+          EOF
+
+          # Append clang-tidy output (filter for errors and warnings)
+          if [ -f clang-tidy-output.txt ]; then
+            # Extract lines containing 'error:', 'warning:', or 'note:'
+            grep -E '(error:|warning:|note:)' clang-tidy-output.txt > filtered-output.txt || true
+
+            # If filtered output is empty, use original (might be a different error format)
+            if [ ! -s filtered-output.txt ]; then
+              cp clang-tidy-output.txt filtered-output.txt
+            fi
+
+            # Truncate if too large
+            head -c 60000 filtered-output.txt >> issue.md
+            if [ "$(wc -c < filtered-output.txt)" -gt 60000 ]; then
+              echo "" >> issue.md
+              echo "... (output truncated, see artifacts for full output)" >> issue.md
+            fi
+
+            rm filtered-output.txt
+          else
+            echo "No output file found" >> issue.md
+          fi
+
+          cat >> issue.md <<EOF
+          \`\`\`
+
+          **Workflow run:** ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+
+          ---
+          *This issue was automatically created by the clang-tidy workflow.*
+          EOF
+
+          # Create the issue
+          gh issue create \
+            --label "Bug,Clang-tidy" \
+            --title "Clang-tidy check failed" \
+            --body-file ./issue.md \
+            > create_issue.log
+
+          created_issue="$(sed 's|.*/||' create_issue.log)"
+          echo "created_issue=$created_issue" >> $GITHUB_OUTPUT
+          echo "Created issue #$created_issue"
+
+          rm -f create_issue.log issue.md clang-tidy-output.txt
+
+      - name: Fail the workflow if clang-tidy failed
+        if: steps.run_clang_tidy.outcome != 'success'
+        run: |
+          echo "Clang-tidy check failed!"
+          exit 1

.github/workflows/reusable-clang-tidy.yml

@@ -0,0 +1,55 @@
+name: Clang-tidy check
+
+on:
+  workflow_call:
+    inputs:
+      check_only_changed:
+        description: "Check only changed files in PR. If false, checks all files in the repository."
+        type: boolean
+        default: false
+      create_issue_on_failure:
+        description: "Whether to create an issue if the check failed"
+        type: boolean
+        default: false
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  determine-files:
+    name: Determine files to check
+    if: ${{ inputs.check_only_changed }}
+    runs-on: ubuntu-latest
+    outputs:
+      clang_tidy_config_changed: ${{ steps.changed_clang_tidy.outputs.any_changed }}
+      any_cpp_changed: ${{ steps.changed_files.outputs.any_changed }}
+      all_changed_files: ${{ steps.changed_files.outputs.all_changed_files }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - name: Get changed C++ files
+        id: changed_files
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        with:
+          files: |
+            **/*.cpp
+            **/*.h
+            **/*.ipp
+          separator: " "
+
+      - name: Get changed clang-tidy configuration
+        id: changed_clang_tidy
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        with:
+          files: |
+            .clang-tidy
+
+  run-clang-tidy:
+    needs: [determine-files]
+    if: ${{ always() && !cancelled() && (!inputs.check_only_changed || needs.determine-files.outputs.any_cpp_changed == 'true' || needs.determine-files.outputs.clang_tidy_config_changed == 'true') }}
+    uses: ./.github/workflows/reusable-clang-tidy-files.yml
+    with:
+      files: ${{ (needs.determine-files.outputs.clang_tidy_config_changed != 'true' && inputs.check_only_changed) && needs.determine-files.outputs.all_changed_files || '' }}
+      create_issue_on_failure: ${{ inputs.create_issue_on_failure }}

.github/workflows/reusable-strategy-matrix.yml

@@ -29,10 +29,10 @@ jobs:
       matrix: ${{ steps.generate.outputs.matrix }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Set up Python
-        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: 3.13
 

.github/workflows/reusable-upload-recipe.yml

@@ -43,16 +43,12 @@ jobs:
     container: ghcr.io/xrplf/ci/ubuntu-noble:gcc-13-sha-5dd7158
     steps:
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Generate build version number
         id: version
         uses: ./.github/actions/generate-version
 
-      - name: Determine recipe reference
-        id: ref
-        run: echo "ref=xrpl/${{ steps.version.outputs.version }}" >> "${GITHUB_OUTPUT}"
-
       - name: Set up Conan
         uses: ./.github/actions/setup-conan
         with:
@@ -62,17 +58,46 @@ jobs:
       - name: Log into Conan remote
         env:
           REMOTE_NAME: ${{ inputs.remote_name }}
-          REMOTE_USERNAME: ${{ inputs.remote_username }}
-          REMOTE_PASSWORD: ${{ inputs.remote_password }}
+          REMOTE_USERNAME: ${{ secrets.remote_username }}
+          REMOTE_PASSWORD: ${{ secrets.remote_password }}
         run: conan remote login "${REMOTE_NAME}" "${REMOTE_USERNAME}" --password "${REMOTE_PASSWORD}"
 
-      - name: Upload Conan recipe
+      - name: Upload Conan recipe (version)
         env:
-          RECIPE_REF: ${{ steps.ref.outputs.ref }}
           REMOTE_NAME: ${{ inputs.remote_name }}
         run: |
-          conan export .
-          conan upload --confirm --check --remote="${REMOTE_NAME}" ${RECIPE_REF}
+          conan export . --version=${{ steps.version.outputs.version }}
+          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/${{ steps.version.outputs.version }}
+
+      # When this workflow is triggered by a push event, it will always be when merging into the
+      # 'develop' branch, see on-trigger.yml.
+      - name: Upload Conan recipe (develop)
+        if: ${{ github.event_name == 'push' }}
+        env:
+          REMOTE_NAME: ${{ inputs.remote_name }}
+        run: |
+          conan export . --version=develop
+          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/develop
+
+      # When this workflow is triggered by a pull request event, it will always be when merging into
+      # one of the 'release' branches, see on-pr.yml.
+      - name: Upload Conan recipe (rc)
+        if: ${{ github.event_name == 'pull_request' }}
+        env:
+          REMOTE_NAME: ${{ inputs.remote_name }}
+        run: |
+          conan export . --version=rc
+          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/rc
+
+      # When this workflow is triggered by a push event, it will always be when tagging a final
+      # release, see on-tag.yml.
+      - name: Upload Conan recipe (release)
+        if: ${{ startsWith(github.ref, 'refs/tags/') }}
+        env:
+          REMOTE_NAME: ${{ inputs.remote_name }}
+        run: |
+          conan export . --version=release
+          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/release
 
     outputs:
-      ref: ${{ steps.ref.outputs.ref }}
+      ref: xrpl/${{ steps.version.outputs.version }}

.github/workflows/upload-conan-deps.yml

@@ -64,13 +64,13 @@ jobs:
     steps:
       - name: Cleanup workspace (macOS and Windows)
         if: ${{ runner.os == 'macOS' || runner.os == 'Windows' }}
-        uses: XRPLF/actions/cleanup-workspace@2ece4ec6ab7de266859a6f053571425b2bd684b6
+        uses: XRPLF/actions/cleanup-workspace@cf0433aa74563aead044a1e395610c96d65a37cf
 
       - name: Checkout repository
-        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@f05cab7b8541eee6473aa42beb9d2fe35608a190
+        uses: XRPLF/actions/prepare-runner@2bbc2dc1abeec7bfaa886804ab86871ac201764e
         with:
           enable_ccache: false
 
@@ -78,12 +78,14 @@ jobs:
         uses: ./.github/actions/print-env
 
       - name: Get number of processors
-        uses: XRPLF/actions/get-nproc@2ece4ec6ab7de266859a6f053571425b2bd684b6
+        uses: XRPLF/actions/get-nproc@cf0433aa74563aead044a1e395610c96d65a37cf
         id: nproc
         with:
           subtract: ${{ env.NPROC_SUBTRACT }}
 
       - name: Setup Conan
+        env:
+          SANITIZERS: ${{ matrix.sanitizers }}
         uses: ./.github/actions/setup-conan
         with:
           remote_name: ${{ env.CONAN_REMOTE_NAME }}
@@ -98,13 +100,14 @@ jobs:
           # Set the verbosity to "quiet" for Windows to avoid an excessive
           # amount of logs. For other OSes, the "verbose" logs are more useful.
           log_verbosity: ${{ runner.os == 'Windows' && 'quiet' || 'verbose' }}
+          sanitizers: ${{ matrix.sanitizers }}
 
       - name: Log into Conan remote
-        if: ${{ github.repository_owner == 'XRPLF' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') }}
+        if: ${{ github.repository == 'XRPLF/rippled' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') }}
         run: conan remote login "${CONAN_REMOTE_NAME}" "${{ secrets.CONAN_REMOTE_USERNAME }}" --password "${{ secrets.CONAN_REMOTE_PASSWORD }}"
 
       - name: Upload Conan packages
-        if: ${{ github.repository_owner == 'XRPLF' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') }}
+        if: ${{ github.repository == 'XRPLF/rippled' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') }}
         env:
           FORCE_OPTION: ${{ github.event.inputs.force_upload == 'true' && '--force' || '' }}
         run: conan upload "*" --remote="${CONAN_REMOTE_NAME}" --confirm ${FORCE_OPTION}

.gitignore

@@ -42,6 +42,9 @@ gmon.out
 # Locally patched Conan recipes
 external/conan-center-index/
 
+# Local conan directory
+.conan
+
 # XCode IDE.
 *.pbxuser
 !default.pbxuser
@@ -64,7 +67,21 @@ DerivedData
 /.vs/
 /.vscode/
 
+# zed IDE.
+/.zed/
+
 # AI tools.
+/.agent
+/.agents
 /.augment
 /.claude
 /CLAUDE.md
+
+# Python
+__pycache__
+
+# Direnv's directory
+/.direnv
+
+# clangd cache
+/.cache

.pre-commit-config.yaml

@@ -13,6 +13,8 @@ repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: 3e8a8703264a2f4a69428a0aa4dcb512790b2c8c # frozen: v6.0.0
     hooks:
+      - id: check-added-large-files
+        args: [--maxkb=400, --enforce-all]
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: mixed-line-ending
@@ -20,27 +22,33 @@ repos:
         args: [--assume-in-merge]
 
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: 7d85583be209cb547946c82fbe51f4bc5dd1d017 # frozen: v18.1.8
+    rev: cd481d7b0bfb5c7b3090c21846317f9a8262e891 # frozen: v22.1.0
     hooks:
       - id: clang-format
         args: [--style=file]
         "types_or": [c++, c, proto]
+        exclude: ^include/xrpl/protocol_autogen/(transactions|ledger_entries)/
+
+  - repo: https://github.com/BlankSpruce/gersemi
+    rev: 0.26.0
+    hooks:
+      - id: gersemi
 
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: 5ba47274f9b181bce26a5150a725577f3c336011 # frozen: v3.6.2
+    rev: c2bc67fe8f8f549cc489e00ba8b45aa18ee713b1 # frozen: v3.8.1
     hooks:
       - id: prettier
 
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 831207fd435b47aeffdf6af853097e64322b4d44 # frozen: v25.12.0
+    rev: ea488cebbfd88a5f50b8bd95d5c829d0bb76feb8 # frozen: 26.1.0
     hooks:
       - id: black
 
   - repo: https://github.com/streetsidesoftware/cspell-cli
-    rev: 1cfa010f078c354f3ffb8413616280cc28f5ba21 # frozen: v9.4.0
+    rev: a42085ade523f591dca134379a595e7859986445 # frozen: v9.7.0
     hooks:
       - id: cspell # Spell check changed files
-        exclude: .config/cspell.config.yaml
+        exclude: (.config/cspell.config.yaml|^include/xrpl/protocol_autogen/(transactions|ledger_entries)/)
       - id: cspell # Spell check the commit message
         name: check commit message spelling
         args:
@@ -51,8 +59,27 @@ repos:
           - .git/COMMIT_EDITMSG
         stages: [commit-msg]
 
+  - repo: local
+    hooks:
+      - id: nix-fmt
+        name: Format Nix files
+        entry: |
+          bash -c '
+            if command -v nix &> /dev/null || [ "$GITHUB_ACTIONS" = "true" ]; then
+              nix --extra-experimental-features "nix-command flakes" fmt "$@"
+            else
+              echo "Skipping nix-fmt: nix not installed and not in GitHub Actions"
+              exit 0
+            fi
+          ' --
+        language: system
+        types:
+          - nix
+        pass_filenames: true
+
 exclude: |
   (?x)^(
       external/.*|
-      .github/scripts/levelization/results/.*\.txt
+      .github/scripts/levelization/results/.*\.txt|
+      src/tests/libxrpl/protocol_autogen/(transactions|ledger_entries)/.*
   )$

API-CHANGELOG.md

@@ -6,90 +6,102 @@ For info about how [API versioning](https://xrpl.org/request-formatting.html#api
 
 The API version controls the API behavior you see. This includes what properties you see in responses, what parameters you're permitted to send in requests, and so on. You specify the API version in each of your requests. When a breaking change is introduced to the `rippled` API, a new version is released. To avoid breaking your code, you should set (or increase) your version when you're ready to upgrade.
 
+The [commandline](https://xrpl.org/docs/references/http-websocket-apis/api-conventions/request-formatting/#commandline-format) always uses the latest API version. The command line is intended for ad-hoc usage by humans, not programs or automated scripts. The command line is not meant for use in production code.
+
 For a log of breaking changes, see the **API Version [number]** headings. In general, breaking changes are associated with a particular API Version number. For non-breaking changes, scroll to the **XRP Ledger version [x.y.z]** headings. Non-breaking changes are associated with a particular XRP Ledger (`rippled`) release.
 
+## API Version 3 (Beta)
+
+API version 3 is currently a beta API. It requires enabling `[beta_rpc_api]` in the rippled configuration to use. See [API-VERSION-3.md](API-VERSION-3.md) for the full list of changes in API version 3.
+
 ## API Version 2
 
-API version 2 is available in `rippled` version 2.0.0 and later. To use this API, clients specify `"api_version" : 2` in each request.
-
-#### Removed methods
-
-In API version 2, the following deprecated methods are no longer available: (https://github.com/XRPLF/rippled/pull/4759)
-
-- `tx_history` - Instead, use other methods such as `account_tx` or `ledger` with the `transactions` field set to `true`.
-- `ledger_header` - Instead, use the `ledger` method.
-
-#### Modifications to JSON transaction element in V2
-
-In API version 2, JSON elements for transaction output have been changed and made consistent for all methods which output transactions. (https://github.com/XRPLF/rippled/pull/4775)
-This helps to unify the JSON serialization format of transactions. (https://github.com/XRPLF/clio/issues/722, https://github.com/XRPLF/rippled/issues/4727)
-
-- JSON transaction element is named `tx_json`
-- Binary transaction element is named `tx_blob`
-- JSON transaction metadata element is named `meta`
-- Binary transaction metadata element is named `meta_blob`
-
-Additionally, these elements are now consistently available next to `tx_json` (i.e. sibling elements), where possible:
-
-- `hash` - Transaction ID. This data was stored inside transaction output in API version 1, but in API version 2 is a sibling element.
-- `ledger_index` - Ledger index (only set on validated ledgers)
-- `ledger_hash` - Ledger hash (only set on closed or validated ledgers)
-- `close_time_iso` - Ledger close time expressed in ISO 8601 time format (only set on validated ledgers)
-- `validated` - Bool element set to `true` if the transaction is in a validated ledger, otherwise `false`
-
-This change affects the following methods:
-
-- `tx` - Transaction data moved into element `tx_json` (was inline inside `result`) or, if binary output was requested, moved from `tx` to `tx_blob`. Renamed binary transaction metadata element (if it was requested) from `meta` to `meta_blob`. Changed location of `hash` and added new elements
-- `account_tx` - Renamed transaction element from `tx` to `tx_json`. Renamed binary transaction metadata element (if it was requested) from `meta` to `meta_blob`. Changed location of `hash` and added new elements
-- `transaction_entry` - Renamed transaction metadata element from `metadata` to `meta`. Changed location of `hash` and added new elements
-- `subscribe` - Renamed transaction element from `transaction` to `tx_json`. Changed location of `hash` and added new elements
-- `sign`, `sign_for`, `submit` and `submit_multisigned` - Changed location of `hash` element.
-
-#### Modification to `Payment` transaction JSON schema
-
-When reading Payments, the `Amount` field should generally **not** be used. Instead, use [delivered_amount](https://xrpl.org/partial-payments.html#the-delivered_amount-field) to see the amount that the Payment delivered. To clarify its meaning, the `Amount` field is being renamed to `DeliverMax`. (https://github.com/XRPLF/rippled/pull/4733)
-
-- In `Payment` transaction type, JSON RPC field `Amount` is renamed to `DeliverMax`. To enable smooth client transition, `Amount` is still handled, as described below: (https://github.com/XRPLF/rippled/pull/4733)
-  - On JSON RPC input (e.g. `submit_multisigned` etc. methods), `Amount` is recognized as an alias to `DeliverMax` for both API version 1 and version 2 clients.
-  - On JSON RPC input, submitting both `Amount` and `DeliverMax` fields is allowed _only_ if they are identical; otherwise such input is rejected with `rpcINVALID_PARAMS` error.
-  - On JSON RPC output (e.g. `subscribe`, `account_tx` etc. methods), `DeliverMax` is present in both API version 1 and version 2.
-  - On JSON RPC output, `Amount` is only present in API version 1 and _not_ in version 2.
-
-#### Modifications to account_info response
-
-- `signer_lists` is returned in the root of the response. (In API version 1, it was nested under `account_data`.) (https://github.com/XRPLF/rippled/pull/3770)
-- When using an invalid `signer_lists` value, the API now returns an "invalidParams" error. (https://github.com/XRPLF/rippled/pull/4585)
-  - (`signer_lists` must be a boolean. In API version 1, strings were accepted and may return a normal response - i.e. as if `signer_lists` were `true`.)
-
-#### Modifications to [account_tx](https://xrpl.org/account_tx.html#account_tx) response
-
-- Using `ledger_index_min`, `ledger_index_max`, and `ledger_index` returns `invalidParams` because if you use `ledger_index_min` or `ledger_index_max`, then it does not make sense to also specify `ledger_index`. In API version 1, no error was returned. (https://github.com/XRPLF/rippled/pull/4571)
-  - The same applies for `ledger_index_min`, `ledger_index_max`, and `ledger_hash`. (https://github.com/XRPLF/rippled/issues/4545#issuecomment-1565065579)
-- Using a `ledger_index_min` or `ledger_index_max` beyond the range of ledgers that the server has:
-  - returns `lgrIdxMalformed` in API version 2. Previously, in API version 1, no error was returned. (https://github.com/XRPLF/rippled/issues/4288)
-- Attempting to use a non-boolean value (such as a string) for the `binary` or `forward` parameters returns `invalidParams` (`rpcINVALID_PARAMS`). Previously, in API version 1, no error was returned. (https://github.com/XRPLF/rippled/pull/4620)
-
-#### Modifications to [noripple_check](https://xrpl.org/noripple_check.html#noripple_check) response
-
-- Attempting to use a non-boolean value (such as a string) for the `transactions` parameter returns `invalidParams` (`rpcINVALID_PARAMS`). Previously, in API version 1, no error was returned. (https://github.com/XRPLF/rippled/pull/4620)
+API version 2 is available in `rippled` version 2.0.0 and later. See [API-VERSION-2.md](API-VERSION-2.md) for the full list of changes in API version 2.
 
 ## API Version 1
 
 This version is supported by all `rippled` versions. For WebSocket and HTTP JSON-RPC requests, it is currently the default API version used when no `api_version` is specified.
 
-The [commandline](https://xrpl.org/docs/references/http-websocket-apis/api-conventions/request-formatting/#commandline-format) always uses the latest API version. The command line is intended for ad-hoc usage by humans, not programs or automated scripts. The command line is not meant for use in production code.
+## Unreleased
 
-### Inconsistency: server_info - network_id
+This section contains changes targeting a future version.
 
-The `network_id` field was added in the `server_info` response in version 1.5.0 (2019), but it is not returned in [reporting mode](https://xrpl.org/rippled-server-modes.html#reporting-mode). However, use of reporting mode is now discouraged, in favor of using [Clio](https://github.com/XRPLF/clio) instead.
+### Additions
+
+- `server_definitions`: Added the following new sections to the response ([#6321](https://github.com/XRPLF/rippled/pull/6321)):
+  - `TRANSACTION_FORMATS`: Describes the fields and their optionality for each transaction type, including common fields shared across all transactions.
+  - `LEDGER_ENTRY_FORMATS`: Describes the fields and their optionality for each ledger entry type, including common fields shared across all ledger entries.
+  - `TRANSACTION_FLAGS`: Maps transaction type names to their supported flags and flag values.
+  - `LEDGER_ENTRY_FLAGS`: Maps ledger entry type names to their flags and flag values.
+  - `ACCOUNT_SET_FLAGS`: Maps AccountSet flag names (asf flags) to their numeric values.
+
+### Bugfixes
+
+- Peer Crawler: The `port` field in `overlay.active[]` now consistently returns an integer instead of a string for outbound peers. [#6318](https://github.com/XRPLF/rippled/pull/6318)
+
+## XRP Ledger server version 3.1.0
+
+[Version 3.1.0](https://github.com/XRPLF/rippled/releases/tag/3.1.0) was released on Jan 27, 2026.
+
+### Additions in 3.1.0
+
+- `vault_info`: New RPC method to retrieve information about a specific vault (part of XLS-66 Lending Protocol). ([#6156](https://github.com/XRPLF/rippled/pull/6156))
+
+## XRP Ledger server version 3.0.0
+
+[Version 3.0.0](https://github.com/XRPLF/rippled/releases/tag/3.0.0) was released on Dec 9, 2025.
+
+### Additions in 3.0.0
+
+- `ledger_entry`: Supports all ledger entry types with dedicated parsers. ([#5237](https://github.com/XRPLF/rippled/pull/5237))
+- `ledger_entry`: New error codes `entryNotFound` and `unexpectedLedgerType` for more specific error handling. ([#5237](https://github.com/XRPLF/rippled/pull/5237))
+- `ledger_entry`: Improved error messages with more context (e.g., specifying which field is invalid or missing). ([#5237](https://github.com/XRPLF/rippled/pull/5237))
+- `ledger_entry`: Assorted bug fixes in RPC processing. ([#5237](https://github.com/XRPLF/rippled/pull/5237))
+- `simulate`: Supports additional metadata in the response. ([#5754](https://github.com/XRPLF/rippled/pull/5754))
+
+## XRP Ledger server version 2.6.2
+
+[Version 2.6.2](https://github.com/XRPLF/rippled/releases/tag/2.6.2) was released on Nov 19, 2025.
+
+This release contains bug fixes only and no API changes.
+
+## XRP Ledger server version 2.6.1
+
+[Version 2.6.1](https://github.com/XRPLF/rippled/releases/tag/2.6.1) was released on Sep 30, 2025.
+
+This release contains bug fixes only and no API changes.
+
+## XRP Ledger server version 2.6.0
+
+[Version 2.6.0](https://github.com/XRPLF/rippled/releases/tag/2.6.0) was released on Aug 27, 2025.
+
+### Additions in 2.6.0
+
+- `account_info`: Added `allowTrustLineLocking` flag in response. ([#5525](https://github.com/XRPLF/rippled/pull/5525))
+- `ledger`: Removed the type filter from the RPC command. ([#4934](https://github.com/XRPLF/rippled/pull/4934))
+- `subscribe` (`validations` stream): `network_id` is now included. ([#5579](https://github.com/XRPLF/rippled/pull/5579))
+- `subscribe` (`transactions` stream): `nftoken_id`, `nftoken_ids`, and `offer_id` are now included in transaction metadata. ([#5230](https://github.com/XRPLF/rippled/pull/5230))
+
+## XRP Ledger server version 2.5.1
+
+[Version 2.5.1](https://github.com/XRPLF/rippled/releases/tag/2.5.1) was released on Sep 17, 2025.
+
+This release contains bug fixes only and no API changes.
 
 ## XRP Ledger server version 2.5.0
 
-As of 2025-04-04, version 2.5.0 is in development. You can use a pre-release version by building from source or [using the `nightly` package](https://xrpl.org/docs/infrastructure/installation/install-rippled-on-ubuntu).
+[Version 2.5.0](https://github.com/XRPLF/rippled/releases/tag/2.5.0) was released on Jun 24, 2025.
 
 ### Additions and bugfixes in 2.5.0
 
-- `channel_authorize`: If `signing_support` is not enabled in the config, the RPC is disabled.
+- `tx`: Added `ctid` field to the response and improved error handling. ([#4738](https://github.com/XRPLF/rippled/pull/4738))
+- `ledger_entry`: Improved error messages in `permissioned_domain`. ([#5344](https://github.com/XRPLF/rippled/pull/5344))
+- `simulate`: Improved multi-sign usage. ([#5479](https://github.com/XRPLF/rippled/pull/5479))
+- `channel_authorize`: If `signing_support` is not enabled in the config, the RPC is disabled. ([#5385](https://github.com/XRPLF/rippled/pull/5385))
+- `subscribe` (admin): Removed webhook queue limit to prevent dropping notifications; reduced HTTP timeout from 10 minutes to 30 seconds. ([#5163](https://github.com/XRPLF/rippled/pull/5163))
+- `ledger_data` (gRPC): Fixed crashing issue with some invalid markers. ([#5137](https://github.com/XRPLF/rippled/pull/5137))
+- `account_lines`: Fixed error with `no_ripple` and `no_ripple_peer` sometimes showing up incorrectly. ([#5345](https://github.com/XRPLF/rippled/pull/5345))
+- `account_tx`: Fixed issue with incorrect CTIDs. ([#5408](https://github.com/XRPLF/rippled/pull/5408))
 
 ## XRP Ledger server version 2.4.0
 
@@ -97,11 +109,19 @@ As of 2025-04-04, version 2.5.0 is in development. You can use a pre-release ver
 
 ### Additions and bugfixes in 2.4.0
 
-- `ledger_entry`: `state` is added an alias for `ripple_state`.
-- `ledger_entry`: Enables case-insensitive filtering by canonical name in addition to case-sensitive filtering by RPC name.
-- `validators`: Added new field `validator_list_threshold` in response.
-- `simulate`: A new RPC that executes a [dry run of a transaction submission](https://github.com/XRPLF/XRPL-Standards/tree/master/XLS-0069d-simulate#2-rpc-simulate)
-- Signing methods autofill fees better and properly handle transactions that don't have a base fee, and will also autofill the `NetworkID` field.
+- `simulate`: A new RPC that executes a [dry run of a transaction submission](https://github.com/XRPLF/XRPL-Standards/tree/master/XLS-0069d-simulate#2-rpc-simulate). ([#5069](https://github.com/XRPLF/rippled/pull/5069))
+- Signing methods (`sign`, `sign_for`, `submit`): Autofill fees better, properly handle transactions without a base fee, and autofill the `NetworkID` field. ([#5069](https://github.com/XRPLF/rippled/pull/5069))
+- `ledger_entry`: `state` is added as an alias for `ripple_state`. ([#5199](https://github.com/XRPLF/rippled/pull/5199))
+- `ledger`, `ledger_data`, `account_objects`: Support filtering ledger entry types by their canonical names (case-insensitive). ([#5271](https://github.com/XRPLF/rippled/pull/5271))
+- `validators`: Added new field `validator_list_threshold` in response. ([#5112](https://github.com/XRPLF/rippled/pull/5112))
+- `server_info`: Added git commit hash info on admin connection. ([#5225](https://github.com/XRPLF/rippled/pull/5225))
+- `server_definitions`: Changed larger `UInt` serialized types to `Hash`. ([#5231](https://github.com/XRPLF/rippled/pull/5231))
+
+## XRP Ledger server version 2.3.1
+
+[Version 2.3.1](https://github.com/XRPLF/rippled/releases/tag/2.3.1) was released on Jan 29, 2025.
+
+This release contains bug fixes only and no API changes.
 
 ## XRP Ledger server version 2.3.0
 
@@ -109,19 +129,30 @@ As of 2025-04-04, version 2.5.0 is in development. You can use a pre-release ver
 
 ### Breaking changes in 2.3.0
 
-- `book_changes`: If the requested ledger version is not available on this node, a `ledgerNotFound` error is returned and the node does not attempt to acquire the ledger from the p2p network (as with other non-admin RPCs).
-
-Admins can still attempt to retrieve old ledgers with the `ledger_request` RPC.
+- `book_changes`: If the requested ledger version is not available on this node, a `ledgerNotFound` error is returned and the node does not attempt to acquire the ledger from the p2p network (as with other non-admin RPCs). Admins can still attempt to retrieve old ledgers with the `ledger_request` RPC.
 
 ### Additions and bugfixes in 2.3.0
 
-- `book_changes`: Returns a `validated` field in its response, which was missing in prior versions.
+- `book_changes`: Returns a `validated` field in its response. ([#5096](https://github.com/XRPLF/rippled/pull/5096))
+- `book_changes`: Accepts shortcut strings (`current`, `closed`, `validated`) for the `ledger_index` parameter. ([#5096](https://github.com/XRPLF/rippled/pull/5096))
+- `server_definitions`: Include `index` in response. ([#5190](https://github.com/XRPLF/rippled/pull/5190))
+- `account_nfts`: Fix issue where unassociated marker would return incorrect results. ([#5045](https://github.com/XRPLF/rippled/pull/5045))
+- `account_objects`: Fix issue where invalid marker would not return an error. ([#5046](https://github.com/XRPLF/rippled/pull/5046))
+- `account_objects`: Disallow filtering by ledger entry types that an account cannot hold. ([#5056](https://github.com/XRPLF/rippled/pull/5056))
+- `tx`: Allow lowercase CTID. ([#5049](https://github.com/XRPLF/rippled/pull/5049))
+- `feature`: Better error handling for invalid values of `feature`. ([#5063](https://github.com/XRPLF/rippled/pull/5063))
 
 ## XRP Ledger server version 2.2.0
 
 [Version 2.2.0](https://github.com/XRPLF/rippled/releases/tag/2.2.0) was released on Jun 5, 2024. The following additions are non-breaking (because they are purely additive):
 
-- The `feature` method now has a non-admin mode for users. (It was previously only available to admin connections.) The method returns an updated list of amendments, including their names and other information. ([#4781](https://github.com/XRPLF/rippled/pull/4781))
+- `feature`: Add a non-admin mode for users. (It was previously only available to admin connections.) The method returns an updated list of amendments, including their names and other information. ([#4781](https://github.com/XRPLF/rippled/pull/4781))
+
+## XRP Ledger server version 2.0.1
+
+[Version 2.0.1](https://github.com/XRPLF/rippled/releases/tag/2.0.1) was released on Jan 29, 2024. The following additions are non-breaking:
+
+- `path_find`: Fixes unbounded memory growth. ([#4822](https://github.com/XRPLF/rippled/pull/4822))
 
 ## XRP Ledger server version 2.0.0
 
@@ -129,24 +160,18 @@ Admins can still attempt to retrieve old ledgers with the `ledger_request` RPC.
 
 - `server_definitions`: A new RPC that generates a `definitions.json`-like output that can be used in XRPL libraries.
 - In `Payment` transactions, `DeliverMax` has been added. This is a replacement for the `Amount` field, which should not be used. Typically, the `delivered_amount` (in transaction metadata) should be used. To ease the transition, `DeliverMax` is present regardless of API version, since adding a field is non-breaking.
-- API version 2 has been moved from beta to supported, meaning that it is generally available (regardless of the `beta_rpc_api` setting).
-
-## XRP Ledger server version 2.2.0
-
-The following is a non-breaking addition to the API.
-
-- The `feature` method now has a non-admin mode for users. (It was previously only available to admin connections.) The method returns an updated list of amendments, including their names and other information. ([#4781](https://github.com/XRPLF/rippled/pull/4781))
+- API version 2 has been moved from beta to supported, meaning that it is generally available (regardless of the `beta_rpc_api` setting). The full list of changes is in [API-VERSION-2.md](API-VERSION-2.md).
 
 ## XRP Ledger server version 1.12.0
 
-[Version 1.12.0](https://github.com/XRPLF/rippled/releases/tag/1.12.0) was released on Sep 6, 2023. The following additions are non-breaking (because they are purely additive).
+[Version 1.12.0](https://github.com/XRPLF/rippled/releases/tag/1.12.0) was released on Sep 6, 2023. The following additions are non-breaking (because they are purely additive):
 
-- `server_info`: Added `ports`, an array which advertises the RPC and WebSocket ports. This information is also included in the `/crawl` endpoint (which calls `server_info` internally). `grpc` and `peer` ports are also included. (https://github.com/XRPLF/rippled/pull/4427)
+- `server_info`: Added `ports`, an array which advertises the RPC and WebSocket ports. This information is also included in the `/crawl` endpoint (which calls `server_info` internally). `grpc` and `peer` ports are also included. ([#4427](https://github.com/XRPLF/rippled/pull/4427))
   - `ports` contains objects, each containing a `port` for the listening port (a number string), and a `protocol` array listing the supported protocols on that port.
   - This allows crawlers to build a more detailed topology without needing to port-scan nodes.
   - (For peers and other non-admin clients, the info about admin ports is excluded.)
-- Clawback: The following additions are gated by the Clawback amendment (`featureClawback`). (https://github.com/XRPLF/rippled/pull/4553)
-  - Adds an [AccountRoot flag](https://xrpl.org/accountroot.html#accountroot-flags) called `lsfAllowTrustLineClawback` (https://github.com/XRPLF/rippled/pull/4617)
+- Clawback: The following additions are gated by the Clawback amendment (`featureClawback`). ([#4553](https://github.com/XRPLF/rippled/pull/4553))
+  - Adds an [AccountRoot flag](https://xrpl.org/accountroot.html#accountroot-flags) called `lsfAllowTrustLineClawback`. ([#4617](https://github.com/XRPLF/rippled/pull/4617))
     - Adds the corresponding `asfAllowTrustLineClawback` [AccountSet Flag](https://xrpl.org/accountset.html#accountset-flags) as well.
     - Clawback is disabled by default, so if an issuer desires the ability to claw back funds, they must use an `AccountSet` transaction to set the AllowTrustLineClawback flag. They must do this before creating any trust lines, offers, escrows, payment channels, or checks.
   - Adds the [Clawback transaction type](https://github.com/XRPLF/XRPL-Standards/blob/master/XLS-39d-clawback/README.md#331-clawback-transaction), containing these fields:
@@ -181,16 +206,16 @@ The following is a non-breaking addition to the API.
 
 ### Breaking changes in 1.11
 
-- Added the ability to mark amendments as obsolete. For the `feature` admin API, there is a new possible value for the `vetoed` field. (https://github.com/XRPLF/rippled/pull/4291)
+- Added the ability to mark amendments as obsolete. For the `feature` admin API, there is a new possible value for the `vetoed` field. ([#4291](https://github.com/XRPLF/rippled/pull/4291))
   - The value of `vetoed` can now be `true`, `false`, or `"Obsolete"`.
-- Removed the acceptance of seeds or public keys in place of account addresses. (https://github.com/XRPLF/rippled/pull/4404)
+- Removed the acceptance of seeds or public keys in place of account addresses. ([#4404](https://github.com/XRPLF/rippled/pull/4404))
   - This simplifies the API and encourages better security practices (i.e. seeds should never be sent over the network).
-- For the `ledger_data` method, when all entries are filtered out, the `state` field of the response is now an empty list (in other words, an empty array, `[]`). (Previously, it would return `null`.) While this is technically a breaking change, the new behavior is consistent with the documentation, so this is considered only a bug fix. (https://github.com/XRPLF/rippled/pull/4398)
+- For the `ledger_data` method, when all entries are filtered out, the `state` field of the response is now an empty list (in other words, an empty array, `[]`). (Previously, it would return `null`.) While this is technically a breaking change, the new behavior is consistent with the documentation, so this is considered only a bug fix. ([#4398](https://github.com/XRPLF/rippled/pull/4398))
 - If and when the `fixNFTokenRemint` amendment activates, there will be a new AccountRoot field, `FirstNFTSequence`. This field is set to the current account sequence when the account issues their first NFT. If an account has not issued any NFTs, then the field is not set. ([#4406](https://github.com/XRPLF/rippled/pull/4406))
   - There is a new account deletion restriction: an account can only be deleted if `FirstNFTSequence` + `MintedNFTokens` + `256` is less than the current ledger sequence.
   - This is potentially a breaking change if clients have logic for determining whether an account can be deleted.
 - NetworkID
-  - For sidechains and networks with a network ID greater than 1024, there is a new [transaction common field](https://xrpl.org/transaction-common-fields.html), `NetworkID`. (https://github.com/XRPLF/rippled/pull/4370)
+  - For sidechains and networks with a network ID greater than 1024, there is a new [transaction common field](https://xrpl.org/transaction-common-fields.html), `NetworkID`. ([#4370](https://github.com/XRPLF/rippled/pull/4370))
     - This field helps to prevent replay attacks and is now required for chains whose network ID is 1025 or higher.
     - The field must be omitted for Mainnet, so there is no change for Mainnet users.
   - There are three new local error codes:
@@ -200,10 +225,10 @@ The following is a non-breaking addition to the API.
 
 ### Additions and bug fixes in 1.11
 
-- Added `nftoken_id`, `nftoken_ids` and `offer_id` meta fields into NFT `tx` and `account_tx` responses. (https://github.com/XRPLF/rippled/pull/4447)
-- Added an `account_flags` object to the `account_info` method response. (https://github.com/XRPLF/rippled/pull/4459)
-- Added `NFTokenPages` to the `account_objects` RPC. (https://github.com/XRPLF/rippled/pull/4352)
-- Fixed: `marker` returned from the `account_lines` command would not work on subsequent commands. (https://github.com/XRPLF/rippled/pull/4361)
+- Added `nftoken_id`, `nftoken_ids` and `offer_id` meta fields into NFT `tx` and `account_tx` responses. ([#4447](https://github.com/XRPLF/rippled/pull/4447))
+- Added an `account_flags` object to the `account_info` method response. ([#4459](https://github.com/XRPLF/rippled/pull/4459))
+- Added `NFTokenPages` to the `account_objects` RPC. ([#4352](https://github.com/XRPLF/rippled/pull/4352))
+- Fixed: `marker` returned from the `account_lines` command would not work on subsequent commands. ([#4361](https://github.com/XRPLF/rippled/pull/4361))
 
 ## XRP Ledger server version 1.10.0
 

API-VERSION-2.md

@@ -0,0 +1,66 @@
+# API Version 2
+
+API version 2 is available in `rippled` version 2.0.0 and later. To use this API, clients specify `"api_version" : 2` in each request.
+
+For info about how [API versioning](https://xrpl.org/request-formatting.html#api-versioning) works, including examples, please view the [XLS-22d spec](https://github.com/XRPLF/XRPL-Standards/discussions/54). For details about the implementation of API versioning, view the [implementation PR](https://github.com/XRPLF/rippled/pull/3155). API versioning ensures existing integrations and users continue to receive existing behavior, while those that request a higher API version will experience new behavior.
+
+## Removed methods
+
+In API version 2, the following deprecated methods are no longer available: ([#4759](https://github.com/XRPLF/rippled/pull/4759))
+
+- `tx_history` - Instead, use other methods such as `account_tx` or `ledger` with the `transactions` field set to `true`.
+- `ledger_header` - Instead, use the `ledger` method.
+
+## Modifications to JSON transaction element in API version 2
+
+In API version 2, JSON elements for transaction output have been changed and made consistent for all methods which output transactions. ([#4775](https://github.com/XRPLF/rippled/pull/4775))
+This helps to unify the JSON serialization format of transactions. ([clio#722](https://github.com/XRPLF/clio/issues/722), [#4727](https://github.com/XRPLF/rippled/issues/4727))
+
+- JSON transaction element is named `tx_json`
+- Binary transaction element is named `tx_blob`
+- JSON transaction metadata element is named `meta`
+- Binary transaction metadata element is named `meta_blob`
+
+Additionally, these elements are now consistently available next to `tx_json` (i.e. sibling elements), where possible:
+
+- `hash` - Transaction ID. This data was stored inside transaction output in API version 1, but in API version 2 is a sibling element.
+- `ledger_index` - Ledger index (only set on validated ledgers)
+- `ledger_hash` - Ledger hash (only set on closed or validated ledgers)
+- `close_time_iso` - Ledger close time expressed in ISO 8601 time format (only set on validated ledgers)
+- `validated` - Bool element set to `true` if the transaction is in a validated ledger, otherwise `false`
+
+This change affects the following methods:
+
+- `tx` - Transaction data moved into element `tx_json` (was inline inside `result`) or, if binary output was requested, moved from `tx` to `tx_blob`. Renamed binary transaction metadata element (if it was requested) from `meta` to `meta_blob`. Changed location of `hash` and added new elements
+- `account_tx` - Renamed transaction element from `tx` to `tx_json`. Renamed binary transaction metadata element (if it was requested) from `meta` to `meta_blob`. Changed location of `hash` and added new elements
+- `transaction_entry` - Renamed transaction metadata element from `metadata` to `meta`. Changed location of `hash` and added new elements
+- `subscribe` - Renamed transaction element from `transaction` to `tx_json`. Changed location of `hash` and added new elements
+- `sign`, `sign_for`, `submit` and `submit_multisigned` - Changed location of `hash` element.
+
+## Modifications to `Payment` transaction JSON schema
+
+When reading Payments, the `Amount` field should generally **not** be used. Instead, use [delivered_amount](https://xrpl.org/partial-payments.html#the-delivered_amount-field) to see the amount that the Payment delivered. To clarify its meaning, the `Amount` field is being renamed to `DeliverMax`. ([#4733](https://github.com/XRPLF/rippled/pull/4733))
+
+- In `Payment` transaction type, JSON RPC field `Amount` is renamed to `DeliverMax`. To enable smooth client transition, `Amount` is still handled, as described below: ([#4733](https://github.com/XRPLF/rippled/pull/4733))
+  - On JSON RPC input (e.g. `submit_multisigned` etc. methods), `Amount` is recognized as an alias to `DeliverMax` for both API version 1 and version 2 clients.
+  - On JSON RPC input, submitting both `Amount` and `DeliverMax` fields is allowed _only_ if they are identical; otherwise such input is rejected with `rpcINVALID_PARAMS` error.
+  - On JSON RPC output (e.g. `subscribe`, `account_tx` etc. methods), `DeliverMax` is present in both API version 1 and version 2.
+  - On JSON RPC output, `Amount` is only present in API version 1 and _not_ in version 2.
+
+## Modifications to account_info response
+
+- `signer_lists` is returned in the root of the response. (In API version 1, it was nested under `account_data`.) ([#3770](https://github.com/XRPLF/rippled/pull/3770))
+- When using an invalid `signer_lists` value, the API now returns an "invalidParams" error. ([#4585](https://github.com/XRPLF/rippled/pull/4585))
+  - (`signer_lists` must be a boolean. In API version 1, strings were accepted and may return a normal response - i.e. as if `signer_lists` were `true`.)
+
+## Modifications to [account_tx](https://xrpl.org/account_tx.html#account_tx) response
+
+- Using `ledger_index_min`, `ledger_index_max`, and `ledger_index` returns `invalidParams` because if you use `ledger_index_min` or `ledger_index_max`, then it does not make sense to also specify `ledger_index`. In API version 1, no error was returned. ([#4571](https://github.com/XRPLF/rippled/pull/4571))
+  - The same applies for `ledger_index_min`, `ledger_index_max`, and `ledger_hash`. ([#4545](https://github.com/XRPLF/rippled/issues/4545#issuecomment-1565065579))
+- Using a `ledger_index_min` or `ledger_index_max` beyond the range of ledgers that the server has:
+  - returns `lgrIdxMalformed` in API version 2. Previously, in API version 1, no error was returned. ([#4288](https://github.com/XRPLF/rippled/issues/4288))
+- Attempting to use a non-boolean value (such as a string) for the `binary` or `forward` parameters returns `invalidParams` (`rpcINVALID_PARAMS`). Previously, in API version 1, no error was returned. ([#4620](https://github.com/XRPLF/rippled/pull/4620))
+
+## Modifications to [noripple_check](https://xrpl.org/noripple_check.html#noripple_check) response
+
+- Attempting to use a non-boolean value (such as a string) for the `transactions` parameter returns `invalidParams` (`rpcINVALID_PARAMS`). Previously, in API version 1, no error was returned. ([#4620](https://github.com/XRPLF/rippled/pull/4620))

API-VERSION-3.md

@@ -0,0 +1,27 @@
+# API Version 3
+
+API version 3 is currently a **beta API**. It requires enabling `[beta_rpc_api]` in the rippled configuration to use. To use this API, clients specify `"api_version" : 3` in each request.
+
+For info about how [API versioning](https://xrpl.org/request-formatting.html#api-versioning) works, including examples, please view the [XLS-22d spec](https://github.com/XRPLF/XRPL-Standards/discussions/54). For details about the implementation of API versioning, view the [implementation PR](https://github.com/XRPLF/rippled/pull/3155). API versioning ensures existing integrations and users continue to receive existing behavior, while those that request a higher API version will experience new behavior.
+
+## Breaking Changes
+
+### Modifications to `amm_info`
+
+The order of error checks has been changed to provide more specific error messages. ([#4924](https://github.com/XRPLF/rippled/pull/4924))
+
+- **Before (API v2)**: When sending an invalid account or asset to `amm_info` while other parameters are not set as expected, the method returns a generic `rpcINVALID_PARAMS` error.
+- **After (API v3)**: The same scenario returns a more specific error: `rpcISSUE_MALFORMED` for malformed assets or `rpcACT_MALFORMED` for malformed accounts.
+
+### Modifications to `ledger_entry`
+
+Added support for string shortcuts to look up fixed-location ledger entries using the `"index"` parameter. ([#5644](https://github.com/XRPLF/rippled/pull/5644))
+
+In API version 3, the following string values can be used with the `"index"` parameter:
+
+- `"index": "amendments"` - Returns the `Amendments` ledger entry
+- `"index": "fee"` - Returns the `FeeSettings` ledger entry
+- `"index": "nunl"` - Returns the `NegativeUNL` ledger entry
+- `"index": "hashes"` - Returns the "short" `LedgerHashes` ledger entry (recent ledger hashes)
+
+These shortcuts are only available in API version 3 and later. In API versions 1 and 2, these string values would result in an error.

BUILD.md

@@ -125,9 +125,9 @@ default profile.
 
 ### Patched recipes
 
-The recipes in Conan Center occasionally need to be patched for compatibility
-with the latest version of `xrpld`. We maintain a fork of the Conan Center
-[here](https://github.com/XRPLF/conan-center-index/) containing the patches.
+Occasionally, we need patched recipes or recipes not present in Conan Center.
+We maintain a fork of the Conan Center Index
+[here](https://github.com/XRPLF/conan-center-index/) containing the modified and newly added recipes.
 
 To ensure our patched recipes are used, you must add our Conan remote at a
 higher index than the default Conan Center remote, so it is consulted first. You
@@ -137,19 +137,11 @@ can do this by running:
 conan remote add --index 0 xrplf https://conan.ripplex.io
 ```
 
-Alternatively, you can pull the patched recipes into the repository and use them
-locally:
+Alternatively, you can pull our recipes from the repository and export them locally:
 
 ```bash
-# Extract the version number from the lockfile.
-function extract_version {
-  version=$(cat conan.lock | sed -nE "s@.+${1}/(.+)#.+@\1@p" | head -n1)
-  echo ${version}
-}
-
 # Define which recipes to export.
-recipes=('ed25519' 'grpc' 'openssl' 'secp256k1' 'snappy' 'soci')
-folders=('all'     'all'  '3.x.x'   'all'       'all'    'all')
+recipes=('abseil' 'ed25519' 'grpc' 'm4' 'mpt-crypto' 'nudb' 'openssl' 'secp256k1' 'snappy' 'soci' 'wasm-xrplf' 'wasmi')
 
 # Selectively check out the recipes from our CCI fork.
 cd external
@@ -158,29 +150,19 @@ cd conan-center-index
 git init
 git remote add origin git@github.com:XRPLF/conan-center-index.git
 git sparse-checkout init
-for ((index = 1; index <= ${#recipes[@]}; index++)); do
-  recipe=${recipes[index]}
-  folder=${folders[index]}
-  echo "Checking out recipe '${recipe}' from folder '${folder}'..."
-  git sparse-checkout add recipes/${recipe}/${folder}
+for recipe in "${recipes[@]}"; do
+  echo "Checking out recipe '${recipe}'..."
+  git sparse-checkout add recipes/${recipe}
 done
 git fetch origin master
 git checkout master
-cd ../..
 
-# Export the recipes into the local cache.
-for ((index = 1; index <= ${#recipes[@]}; index++)); do
-  recipe=${recipes[index]}
-  folder=${folders[index]}
-  version=$(extract_version ${recipe})
-  echo "Exporting '${recipe}/${version}' from '${recipe}/${folder}'..."
-  conan export --version $(extract_version ${recipe}) \
-    external/conan-center-index/recipes/${recipe}/${folder}
-done
+./export_all.sh
+cd ../../
 ```
 
 In the case we switch to a newer version of a dependency that still requires a
-patch, it will be necessary for you to pull in the changes and re-export the
+patch or add a new dependency, it will be necessary for you to pull in the changes and re-export the
 updated dependencies with the newer version. However, if we switch to a newer
 version that no longer requires a patch, no action is required on your part, as
 the new recipe will be automatically pulled from the official Conan Center.
@@ -189,6 +171,8 @@ the new recipe will be automatically pulled from the official Conan Center.
 > You might need to add `--lockfile=""` to your `conan install` command
 > to avoid automatic use of the existing `conan.lock` file when you run
 > `conan export` manually on your machine
+>
+> This is not recommended though, as you might end up using different revisions of recipes.
 
 ### Conan profile tweaks
 
@@ -204,39 +188,14 @@ Possible values are ['5.0', '5.1', '6.0', '6.1', '7.0', '7.3', '8.0', '8.1',
 Read "http://docs.conan.io/2/knowledge/faq.html#error-invalid-setting"
 ```
 
-you need to amend the list of compiler versions in
-`$(conan config home)/settings.yml`, by appending the required version number(s)
+you need to add your compiler to the list of compiler versions in
+`$(conan config home)/settings_user.yml`, by adding the required version number(s)
 to the `version` array specific for your compiler. For example:
 
 ```yaml
-apple-clang:
-  version:
-    [
-      "5.0",
-      "5.1",
-      "6.0",
-      "6.1",
-      "7.0",
-      "7.3",
-      "8.0",
-      "8.1",
-      "9.0",
-      "9.1",
-      "10.0",
-      "11.0",
-      "12.0",
-      "13",
-      "13.0",
-      "13.1",
-      "14",
-      "14.0",
-      "15",
-      "15.0",
-      "16",
-      "16.0",
-      "17",
-      "17.0",
-    ]
+compiler:
+  apple-clang:
+    version: ["17.0"]
 ```
 
 #### Multiple compilers
@@ -368,6 +327,36 @@ The workaround for this error is to add two lines to your profile:
 tools.build:cxxflags=['-DBOOST_ASIO_DISABLE_CONCEPTS']
 ```
 
+### Set Up Ccache
+
+To speed up repeated compilations, we recommend that you install
+[ccache](https://ccache.dev), a tool that wraps your compiler so that it can
+cache build objects locally.
+
+#### Linux
+
+You can install it using the package manager, e.g. `sudo apt install ccache`
+(Ubuntu) or `sudo dnf install ccache` (RHEL).
+
+#### macOS
+
+You can install it using Homebrew, i.e. `brew install ccache`.
+
+#### Windows
+
+You can install it using Chocolatey, i.e. `choco install ccache`. If you already
+have Ccache installed, then `choco upgrade ccache` will update it to the latest
+version. However, if you see an error such as:
+
+```
+terminate called after throwing an instance of 'std::bad_alloc'
+      what():  std::bad_alloc
+C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\Microsoft.CppCommon.targets(617,5): error MSB6006: "cl.exe" exited with code 3.
+```
+
+then please install a specific version of Ccache that we know works, via: `choco
+install ccache --version 4.11.3 --allow-downgrade`.
+
 ### Build and Test
 
 1. Create a build directory and move into it.
@@ -550,10 +539,10 @@ See [Sanitizers docs](./docs/build/sanitizers.md) for more details.
 | `werr`     | OFF           | Treat compilation warnings as errors                           |
 | `wextra`   | OFF           | Enable additional compilation warnings                         |
 
-[Unity builds][5] may be faster for the first build
-(at the cost of much more memory) since they concatenate sources into fewer
-translation units. Non-unity builds may be faster for incremental builds,
-and can be helpful for detecting `#include` omissions.
+[Unity builds][5] may be faster for the first build (at the cost of much more
+memory) since they concatenate sources into fewer translation units. Non-unity
+builds may be faster for incremental builds, and can be helpful for detecting
+`#include` omissions.
 
 ## Troubleshooting
 

CMakeLists.txt

@@ -1,20 +1,23 @@
 cmake_minimum_required(VERSION 3.16)
 
 if(POLICY CMP0074)
-  cmake_policy(SET CMP0074 NEW)
+    cmake_policy(SET CMP0074 NEW)
 endif()
 if(POLICY CMP0077)
-  cmake_policy(SET CMP0077 NEW)
+    cmake_policy(SET CMP0077 NEW)
 endif()
 
 # Fix "unrecognized escape" issues when passing CMAKE_MODULE_PATH on Windows.
-file(TO_CMAKE_PATH "${CMAKE_MODULE_PATH}" CMAKE_MODULE_PATH)
+if(DEFINED CMAKE_MODULE_PATH)
+    file(TO_CMAKE_PATH "${CMAKE_MODULE_PATH}" CMAKE_MODULE_PATH)
+endif()
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
 
 project(xrpl)
 set(CMAKE_CXX_EXTENSIONS OFF)
 set(CMAKE_CXX_STANDARD 20)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
 include(CompilationEnv)
 
@@ -33,51 +36,40 @@ endif()
 # Enable ccache to speed up builds.
 include(Ccache)
 
-# make GIT_COMMIT_HASH define available to all sources
-find_package(Git)
-if(Git_FOUND)
-    execute_process(COMMAND ${GIT_EXECUTABLE} --git-dir=${CMAKE_CURRENT_SOURCE_DIR}/.git rev-parse HEAD
-        OUTPUT_STRIP_TRAILING_WHITESPACE OUTPUT_VARIABLE gch)
-    if(gch)
-        set(GIT_COMMIT_HASH "${gch}")
-        message(STATUS gch: ${GIT_COMMIT_HASH})
-        add_definitions(-DGIT_COMMIT_HASH="${GIT_COMMIT_HASH}")
-    endif()
-
-    execute_process(COMMAND ${GIT_EXECUTABLE} --git-dir=${CMAKE_CURRENT_SOURCE_DIR}/.git rev-parse --abbrev-ref HEAD
-        OUTPUT_STRIP_TRAILING_WHITESPACE OUTPUT_VARIABLE gb)
-    if(gb)
-        set(GIT_BRANCH "${gb}")
-        message(STATUS gb: ${GIT_BRANCH})
-        add_definitions(-DGIT_BRANCH="${GIT_BRANCH}")
-    endif()
-endif() #git
-
 if(thread_safety_analysis)
-  add_compile_options(-Wthread-safety -D_LIBCPP_ENABLE_THREAD_SAFETY_ANNOTATIONS -DXRPL_ENABLE_THREAD_SAFETY_ANNOTATIONS)
-  add_compile_options("-stdlib=libc++")
-  add_link_options("-stdlib=libc++")
+    add_compile_options(
+        -Wthread-safety
+        -D_LIBCPP_ENABLE_THREAD_SAFETY_ANNOTATIONS
+        -DXRPL_ENABLE_THREAD_SAFETY_ANNOTATIONS
+    )
+    add_compile_options("-stdlib=libc++")
+    add_link_options("-stdlib=libc++")
 endif()
 
-include (CheckCXXCompilerFlag)
-include (FetchContent)
-include (ExternalProject)
-include (CMakeFuncs) # must come *after* ExternalProject b/c it overrides one function in EP
-if (target)
-  message (FATAL_ERROR "The target option has been removed - use native cmake options to control build")
-endif ()
+include(CheckCXXCompilerFlag)
+include(FetchContent)
+include(ExternalProject)
+include(CMakeFuncs) # must come *after* ExternalProject b/c it overrides one function in EP
+if(target)
+    message(
+        FATAL_ERROR
+        "The target option has been removed - use native cmake options to control build"
+    )
+endif()
 
 include(XrplSanity)
 include(XrplVersion)
 include(XrplSettings)
-# this check has to remain in the top-level cmake
-# because of the early return statement
-if (packages_only)
-  if (NOT TARGET rpm)
-    message (FATAL_ERROR "packages_only requested, but targets were not created - is docker installed?")
-  endif()
-  return ()
-endif ()
+# this check has to remain in the top-level cmake because of the early return statement
+if(packages_only)
+    if(NOT TARGET rpm)
+        message(
+            FATAL_ERROR
+            "packages_only requested, but targets were not created - is docker installed?"
+        )
+    endif()
+    return()
+endif()
 include(XrplCompiler)
 include(XrplSanitizers)
 include(XrplInterface)
@@ -85,11 +77,9 @@ include(XrplInterface)
 option(only_docs "Include only the docs target?" FALSE)
 include(XrplDocs)
 if(only_docs)
-  return()
+    return()
 endif()
 
-###
-
 include(deps/Boost)
 
 add_subdirectory(external/antithesis-sdk)
@@ -105,45 +95,59 @@ find_package(SOCI REQUIRED)
 find_package(SQLite3 REQUIRED)
 find_package(xxHash REQUIRED)
 
-target_link_libraries(xrpl_libs INTERFACE
-  ed25519::ed25519
-  lz4::lz4
-  OpenSSL::Crypto
-  OpenSSL::SSL
-  secp256k1::secp256k1
-  soci::soci
-  SQLite::SQLite3
+target_link_libraries(
+    xrpl_libs
+    INTERFACE
+        ed25519::ed25519
+        lz4::lz4
+        OpenSSL::Crypto
+        OpenSSL::SSL
+        secp256k1::secp256k1
+        soci::soci
+        SQLite::SQLite3
 )
 
 option(rocksdb "Enable RocksDB" ON)
 if(rocksdb)
     find_package(RocksDB REQUIRED)
-    set_target_properties(RocksDB::rocksdb PROPERTIES
-            INTERFACE_COMPILE_DEFINITIONS XRPL_ROCKSDB_AVAILABLE=1
+    set_target_properties(
+        RocksDB::rocksdb
+        PROPERTIES INTERFACE_COMPILE_DEFINITIONS XRPL_ROCKSDB_AVAILABLE=1
     )
     target_link_libraries(xrpl_libs INTERFACE RocksDB::rocksdb)
 endif()
 
+# OpenTelemetry distributed tracing (optional).
+# When ON, links against opentelemetry-cpp and defines XRPL_ENABLE_TELEMETRY
+# so that tracing macros in TracingInstrumentation.h are compiled in.
+# When OFF (default), all tracing code compiles to no-ops with zero overhead.
+# Enable via: conan install -o telemetry=True, or cmake -Dtelemetry=ON.
+option(telemetry "Enable OpenTelemetry tracing" OFF)
+if(telemetry)
+    find_package(opentelemetry-cpp CONFIG REQUIRED)
+    add_compile_definitions(XRPL_ENABLE_TELEMETRY)
+    message(STATUS "OpenTelemetry tracing enabled")
+endif()
+
 # Work around changes to Conan recipe for now.
 if(TARGET nudb::core)
-  set(nudb nudb::core)
+    set(nudb nudb::core)
 elseif(TARGET NuDB::nudb)
-  set(nudb NuDB::nudb)
+    set(nudb NuDB::nudb)
 else()
-  message(FATAL_ERROR "unknown nudb target")
+    message(FATAL_ERROR "unknown nudb target")
 endif()
 target_link_libraries(xrpl_libs INTERFACE ${nudb})
 
 if(coverage)
-  include(XrplCov)
+    include(XrplCov)
 endif()
 
-set(PROJECT_EXPORT_SET XrplExports)
 include(XrplCore)
 include(XrplInstall)
 include(XrplValidatorKeys)
 
 if(tests)
-  include(CTest)
-  add_subdirectory(src/tests/libxrpl)
+    include(CTest)
+    add_subdirectory(src/tests/libxrpl)
 endif()

CONTRIBUTING.md

@@ -127,26 +127,6 @@ tl;dr
 > 6. Wrap the body at 72 characters.
 > 7. Use the body to explain what and why vs. how.
 
-In addition to those guidelines, please add one of the following
-prefixes to the subject line if appropriate.
-
-- `fix:` - The primary purpose is to fix an existing bug.
-- `perf:` - The primary purpose is performance improvements.
-- `refactor:` - The changes refactor code without affecting
-  functionality.
-- `test:` - The changes _only_ affect unit tests.
-- `docs:` - The changes _only_ affect documentation. This can
-  include code comments in addition to `.md` files like this one.
-- `build:` - The changes _only_ affect the build process,
-  including CMake and/or Conan settings.
-- `chore:` - Other tasks that don't affect the binary, but don't fit
-  any of the other cases. e.g. formatting, git settings, updating
-  Github Actions jobs.
-
-Whenever possible, when updating commits after the PR is open, please
-add the PR number to the end of the subject line. e.g. `test: Add
-unit tests for Feature X (#1234)`.
-
 ## Pull requests
 
 In general, pull requests use `develop` as the base branch.
@@ -180,6 +160,23 @@ credibility of the existing approvals is insufficient.
 Pull requests must be merged by [squash-and-merge][squash]
 to preserve a linear history for the `develop` branch.
 
+### Type of Change
+
+In addition to those guidelines, please start your PR title with one of the following:
+
+- `build:` - The changes _only_ affect the build process, including CMake and/or Conan settings.
+- `feat`: New feature (change which adds functionality).
+- `fix:` - The primary purpose is to fix an existing bug.
+- `docs:` - The changes _only_ affect documentation.
+- `test:` - The changes _only_ affect unit tests.
+- `ci`: Continuous Integration (changes to our CI configuration files and scripts).
+- `style`: Code style (formatting).
+- `refactor:` - The changes refactor code without affecting functionality.
+- `perf:` - The primary purpose is performance improvements.
+- `chore:` - Other tasks that don't affect the binary, but don't fit any of the other cases. e.g. `git` settings, `clang-tidy`, removing dead code, dropping support for older tooling.
+
+First letter after the type prefix should be capitalized, and the type prefix should be followed by a colon and a space. e.g. `feat: Add support for Borrowing Protocol`.
+
 ### "Ready to merge"
 
 A pull request should only have the "Ready to merge" label added when it
@@ -219,7 +216,7 @@ coherent rather than a set of _thou shalt not_ commandments.
 
 ## Formatting
 
-All code must conform to `clang-format` version 18,
+All code must conform to `clang-format` version 21,
 according to the settings in [`.clang-format`](./.clang-format),
 unless the result would be unreasonably difficult to read or maintain.
 To demarcate lines that should be left as-is, surround them with comments like
@@ -251,6 +248,38 @@ pip3 install pre-commit
 pre-commit install
 ```
 
+## Clang-tidy
+
+All code must pass `clang-tidy` checks according to the settings in [`.clang-tidy`](./.clang-tidy).
+
+There is a Continuous Integration job that runs clang-tidy on pull requests. The CI will check:
+
+- All changed C++ files (`.cpp`, `.h`, `.ipp`) when only code files are modified
+- **All files in the repository** when the `.clang-tidy` configuration file is changed
+
+This ensures that configuration changes don't introduce new warnings across the codebase.
+
+### Installing clang-tidy
+
+See the [environment setup guide](./docs/build/environment.md#clang-tidy) for platform-specific installation instructions.
+
+### Running clang-tidy locally
+
+Before running clang-tidy, you must build the project to generate required files (particularly protobuf headers). Refer to [`BUILD.md`](./BUILD.md) for build instructions.
+
+Then run clang-tidy on your local changes:
+
+```
+run-clang-tidy -p build src include tests
+```
+
+This will check all source files in the `src`, `include` and `tests` directories using the compile commands from your `build` directory.
+If you wish to automatically fix whatever clang-tidy finds _and_ is capable of fixing, add `-fix` to the above command:
+
+```
+run-clang-tidy -p build -fix src include tests
+```
+
 ## Contracts and instrumentation
 
 We are using [Antithesis](https://antithesis.com/) for continuous fuzzing,
@@ -872,7 +901,8 @@ git push --delete upstream-push master-next
 11. [Create a new release on
     Github](https://github.com/XRPLF/rippled/releases). Be sure that
     "Set as the latest release" is checked.
-12. Finally [reverse merge the release into `develop`](#follow-up-reverse-merge).
+12. Open a PR to update the [API-CHANGELOG](API-CHANGELOG.md) and `API-VERSION-[n].md` with the changes for this release (if any are missing).
+13. Finally, [reverse merge the release into `develop`](#follow-up-reverse-merge).
 
 #### Special cases: point releases, hotfixes, etc.
 

LICENSE.md

@@ -1,7 +1,7 @@
 ISC License
 
 Copyright (c) 2011, Arthur Britto, David Schwartz, Jed McCaleb, Vinnie Falco, Bob Way, Eric Lombrozo, Nikolaos D. Bougalis, Howard Hinnant.
-Copyright (c) 2012-2025, the XRP Ledger developers.
+Copyright (c) 2012-present, the XRP Ledger developers.
 
 Permission to use, copy, modify, and distribute this software for any
 purpose with or without fee is hereby granted, provided that the above

OpenTelemetryPlan/00-tracing-fundamentals.md

@@ -0,0 +1,567 @@
+# Distributed Tracing Fundamentals
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Next**: [Architecture Analysis](./01-architecture-analysis.md)
+
+---
+
+## What is Distributed Tracing?
+
+Distributed tracing is a method for tracking data objects as they flow through distributed systems. In a network like XRP Ledger, a single transaction touches multiple independent nodes—each with no shared memory or logging. Distributed tracing connects these dots.
+
+**Without tracing:** You see isolated logs on each node with no way to correlate them.
+
+**With tracing:** You see the complete journey of a transaction or an event across all nodes it touched.
+
+---
+
+## Actors and Actions at a Glance
+
+### Actors
+
+| Who (Plain English)                            | Technical Term  |
+| ---------------------------------------------- | --------------- |
+| A single unit of work being tracked            | Span            |
+| The complete journey of a request              | Trace           |
+| Data that links spans across services          | Trace Context   |
+| Code that creates spans and propagates context | Instrumentation |
+| Service that receives and processes traces     | Collector       |
+| Storage and visualization system               | Backend (Tempo) |
+| Decision logic for which traces to keep        | Sampler         |
+
+### Actions
+
+| What Happens (Plain English)            | Technical Term          |
+| --------------------------------------- | ----------------------- |
+| Start tracking a new operation          | Create a Span           |
+| Connect a child operation to its parent | Set `parent_span_id`    |
+| Group all related operations together   | Share a `trace_id`      |
+| Pass tracking data between services     | Context Propagation     |
+| Decide whether to record a trace        | Sampling (Head or Tail) |
+| Send completed traces to storage        | Export (OTLP)           |
+
+---
+
+## Core Concepts
+
+### 1. Trace
+
+A **trace** represents the entire journey of a request through the system. It has a unique `trace_id` that stays constant across all nodes.
+
+```
+Trace ID: abc123
+├── Node A: received transaction
+├── Node B: relayed transaction
+├── Node C: included in consensus
+└── Node D: applied to ledger
+```
+
+### 2. Span
+
+A **span** represents a single unit of work within a trace. Each span has:
+
+| Attribute        | Description                      | Example                    |
+| ---------------- | -------------------------------- | -------------------------- |
+| `trace_id`       | Identifies the trace             | `event123`                 |
+| `span_id`        | Unique identifier                | `span456`                  |
+| `parent_span_id` | Parent span (if any)             | `p_span123`                |
+| `name`           | Operation name                   | `rpc.submit`               |
+| `start_time`     | When work began (local time)     | `2024-01-15T10:30:00Z`     |
+| `end_time`       | When work completed (local time) | `2024-01-15T10:30:00.050Z` |
+| `attributes`     | Key-value metadata               | `tx.hash=ABC...`           |
+| `status`         | OK, ERROR MSG                    | `OK`                       |
+
+### 3. Trace Context
+
+**Trace context** is the data that propagates between services to link spans together. It contains:
+
+- `trace_id` - The trace this span belongs to
+- `span_id` - The current span (becomes parent for child spans)
+- `trace_flags` - Sampling decisions
+
+---
+
+## How Spans Form a Trace
+
+Spans have parent-child relationships forming a tree structure:
+
+```mermaid
+flowchart TB
+    subgraph trace["Trace: abc123"]
+        A["tx.submit<br/>span_id: 001<br/>50ms"] --> B["tx.validate<br/>span_id: 002<br/>5ms"]
+        A --> C["tx.relay<br/>span_id: 003<br/>10ms"]
+        A --> D["tx.apply<br/>span_id: 004<br/>30ms"]
+        D --> E["ledger.update<br/>span_id: 005<br/>20ms"]
+    end
+
+    style A fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style B fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style D fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style E fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **tx.submit (blue, root)**: The top-level span representing the entire transaction submission; all other spans are its descendants.
+- **tx.validate, tx.relay, tx.apply (green)**: Direct children of tx.submit, representing the three main stages -- validation, relay to peers, and application to the ledger.
+- **ledger.update (red)**: A grandchild span nested under tx.apply, representing the actual ledger state mutation triggered by applying the transaction.
+- **Arrows (parent to child)**: Each arrow indicates a parent-child span relationship where the parent's completion depends on the child finishing.
+
+The same trace visualized as a **timeline (Gantt chart)**:
+
+```
+Time →   0ms    10ms    20ms    30ms    40ms    50ms
+         ├───────────────────────────────────────────┤
+tx.submit│▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+         ├─────┤
+tx.valid │▓▓▓▓▓│
+         │     ├──────────┤
+tx.relay │     │▓▓▓▓▓▓▓▓▓▓│
+         │               ├────────────────────────────┤
+tx.apply │               │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+         │                         ├──────────────────┤
+ledger   │                         │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+```
+
+---
+
+## Span Relationships
+
+Spans don't always form simple parent-child trees. Distributed tracing defines several relationship types to capture different causal patterns:
+
+### 1. Parent-Child (ChildOf)
+
+The default relationship. The parent span **depends on** or **contains** the child span. The child runs within the scope of the parent.
+
+```
+tx.submit (parent)
+├── tx.validate (child)     ← parent waits for this
+├── tx.relay (child)        ← parent waits for this
+└── tx.apply (child)        ← parent waits for this
+```
+
+**When to use:** Synchronous calls, nested operations, any case where the parent's completion depends on the child.
+
+### 2. Follows-From
+
+A causal relationship where the first span **triggers** the second, but does **not wait** for it. The originator fires and moves on.
+
+```
+Time →
+
+tx.receive [=======]
+                     ↓ triggers (follows-from)
+              tx.relay   [===========]   ← runs independently
+```
+
+**When to use:** Asynchronous jobs, queued work, fire-and-forget patterns. For example, a node receives a transaction and queues it for relay — the relay span _follows from_ the receive span but the receiver doesn't wait for relaying to complete.
+
+> **OpenTracing** defined `FollowsFrom` as a first-class reference type alongside `ChildOf`.
+> **OpenTelemetry** represents this using **Span Links** with descriptive attributes instead (see below).
+
+### 3. Span Links (Cross-Trace and Non-Hierarchical)
+
+Links connect spans that are **causally related but not in a parent-child hierarchy**. Unlike parent-child, links can cross trace boundaries.
+
+```
+Trace A                          Trace B
+──────                           ──────
+batch.schedule                   batch.execute
+├─ item.enqueue (span X)    ┌──► process.item
+├─ item.enqueue (span Y) ───┤    (links to X, Y, Z)
+├─ item.enqueue (span Z)    └──►
+```
+
+**Use cases:**
+
+| Pattern              | Description                                                                 |
+| -------------------- | --------------------------------------------------------------------------- |
+| **Batch processing** | A batch span links back to all individual spans that contributed to it      |
+| **Fan-in**           | An aggregation span links to the multiple producer spans it merges          |
+| **Fan-out**          | Multiple downstream spans link back to the single span that triggered them  |
+| **Async handoff**    | A deferred job links back to the request that queued it (follows-from)      |
+| **Cross-trace**      | Correlating spans across independent traces (e.g., retries, related events) |
+
+**Link structure:** Each link carries the target span's context plus optional attributes:
+
+```
+Link {
+    trace_id:   <target trace>
+    span_id:    <target span>
+    attributes: { "link.description": "triggered by batch scheduler" }
+}
+```
+
+### Relationship Summary
+
+```mermaid
+flowchart LR
+    subgraph parent_child["Parent-Child"]
+        direction TB
+        P["Parent"] --> C["Child"]
+    end
+
+    subgraph follows_from["Follows-From"]
+        direction TB
+        A["Span A"] -.->|triggers| B["Span B"]
+    end
+
+    subgraph links["Span Links"]
+        direction TB
+        X["Span X\n(Trace 1)"] -.-|link| Y["Span Y\n(Trace 2)"]
+    end
+
+    parent_child ~~~ follows_from ~~~ links
+
+    style P fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style C fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style A fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style B fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style X fill:#4a148c,stroke:#38006b,color:#ffffff
+    style Y fill:#4a148c,stroke:#38006b,color:#ffffff
+```
+
+| Relationship     | Same Trace? | Dependency?                | OTel Mechanism    |
+| ---------------- | ----------- | -------------------------- | ----------------- |
+| **Parent-Child** | Yes         | Parent depends on child    | `parent_span_id`  |
+| **Follows-From** | Usually     | Causal but no dependency   | Link + attributes |
+| **Span Link**    | Either      | Correlation, no dependency | Link + attributes |
+
+---
+
+## Trace ID Generation
+
+A `trace_id` is a 128-bit (16-byte) identifier that groups all spans belonging to one logical operation. How it's generated determines how easily you can find and correlate traces later.
+
+### General Approaches
+
+#### 1. Random (W3C Default)
+
+Generate a random 128-bit ID when a trace starts. Standard approach for most services.
+
+```
+trace_id = random_128_bits()
+```
+
+| Pros                        | Cons                                          |
+| --------------------------- | --------------------------------------------- |
+| Simple, standard            | No natural correlation to domain events       |
+| Guaranteed unique per trace | If propagation is lost, trace is broken       |
+| Works with all OTel tooling | "Find trace for TX abc" requires index lookup |
+
+#### 2. Deterministic (Derived from Domain Data)
+
+Compute the trace_id from a hash of a natural identifier. Every node independently derives the **same** trace_id for the same event.
+
+```
+trace_id = SHA-256(domain_identifier)[0:16]   // truncate to 128 bits
+```
+
+| Pros                                                | Cons                                                       |
+| --------------------------------------------------- | ---------------------------------------------------------- |
+| Propagation-resilient — same ID computed everywhere | Same event processed twice (retry) shares trace_id         |
+| Natural search — domain ID maps directly to trace   | Non-standard (tooling assumes random)                      |
+| No coordination needed between nodes                | 256→128 bit truncation (collision risk negligible at ~2⁶⁴) |
+
+#### 3. Hybrid (Deterministic Prefix + Random Suffix)
+
+First 8 bytes derived from domain data, last 8 bytes random.
+
+```
+trace_id = SHA-256(domain_identifier)[0:8] || random_64_bits()
+```
+
+| Pros                                        | Cons                                     |
+| ------------------------------------------- | ---------------------------------------- |
+| Prefix search: "find all traces for TX abc" | Must propagate to maintain full trace_id |
+| Unique per processing instance              | More complex generation logic            |
+| Retries get distinct trace_ids              | Partial correlation only (prefix match)  |
+
+### XRPL Workflow Analysis
+
+XRPL has a unique advantage: its core workflows produce **globally unique 256-bit hashes** that are known on every node. This makes deterministic trace_id generation practical in ways most systems can't achieve.
+
+#### Natural Identifiers by Workflow
+
+| Workflow            | Natural Identifier                | Size       | Known at Start?               | Same on All Nodes?               |
+| ------------------- | --------------------------------- | ---------- | ----------------------------- | -------------------------------- |
+| **Transaction**     | Transaction hash (`tid_`)         | 256-bit    | Yes — computed before signing | Yes — hash of canonical tx data  |
+| **Consensus round** | Previous ledger hash + ledger seq | 256+32 bit | Yes — known when round opens  | Yes — all validators agree       |
+| **Validation**      | Ledger hash being validated       | 256-bit    | Yes — from consensus result   | Yes — same closed ledger         |
+| **Ledger catch-up** | Target ledger hash                | 256-bit    | Yes — we know what to fetch   | Yes — identifies ledger globally |
+
+#### Where These Identifiers Live in Code
+
+```
+Transaction:     STTx::getTransactionID()     → uint256 tid_
+                 TMTransaction::rawTransaction → recompute hash from bytes
+
+Consensus:       ConsensusProposal::prevLedger_ → uint256 (previous ledger hash)
+                 ConsensusProposal::position_   → uint256 (TxSet hash)
+                 LedgerHeader::seq              → uint32_t (ledger sequence)
+
+Validation:      STValidation::getLedgerHash()  → uint256
+                 STValidation::getNodeID()      → NodeID (160-bit)
+
+Ledger fetch:    InboundLedger constructor      → uint256 hash, uint32_t seq
+                 TMGetLedger::ledgerHash        → bytes (uint256)
+```
+
+### Recommended Strategy: Workflow-Scoped Deterministic
+
+Each workflow type derives its trace_id from its natural domain identifier:
+
+```
+Transaction trace:   trace_id = SHA-256("tx"    || tx_hash)[0:16]
+Consensus trace:     trace_id = SHA-256("cons"  || prev_ledger_hash || ledger_seq)[0:16]
+Ledger catch-up:     trace_id = SHA-256("fetch" || target_ledger_hash)[0:16]
+```
+
+The string prefix (`"tx"`, `"cons"`, `"fetch"`) prevents collisions between workflows that might share underlying hashes.
+
+**Why this works for XRPL:**
+
+1. **Propagation-resilient** — Even if a P2P message drops trace context, every node independently computes the same trace_id from the same tx_hash or ledger_hash. Spans still correlate.
+
+2. **Zero-cost search** — "Show me the trace for transaction ABC" becomes a direct lookup: compute `SHA-256("tx" || ABC)[0:16]` and query. No secondary index needed.
+
+3. **Cross-workflow linking via Span Links** — A consensus trace links to individual transaction traces. A validation span links to the consensus trace. This connects the full picture without forcing everything into one giant trace.
+
+### Cross-Workflow Correlation
+
+Each workflow gets its own trace. Span Links tie them together:
+
+```mermaid
+flowchart TB
+    subgraph tx_trace["Transaction Trace"]
+        direction LR
+        Tn["trace_id = f(tx_hash)"]:::note --> T1["tx.receive"] --> T2["tx.validate"] --> T3["tx.relay"]
+    end
+
+    subgraph cons_trace["Consensus Trace"]
+        direction LR
+        Cn["trace_id = f(prev_ledger, seq)"]:::note --> C1["cons.open"] --> C2["cons.propose"] --> C3["cons.accept"]
+    end
+
+    subgraph val_trace["Validation"]
+        direction LR
+        Vn["spans within consensus trace"]:::note --> V1["val.create"] --> V2["val.broadcast"]
+    end
+
+    subgraph fetch_trace["Catch-Up Trace"]
+        direction LR
+        Fn["trace_id = f(ledger_hash)"]:::note --> F1["fetch.request"] --> F2["fetch.receive"] --> F3["fetch.apply"]
+    end
+
+    C1 -.-|"span link\n(tx traces)"| T3
+    C3 --> V1
+    F1 -.-|"span link\n(target ledger)"| C3
+
+    classDef note fill:none,stroke:#888,stroke-dasharray:5 5,color:#333,font-style:italic
+    style T1 fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style T2 fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style T3 fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style C1 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C2 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C3 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style V1 fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style V2 fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style F1 fill:#4a148c,stroke:#38006b,color:#ffffff
+    style F2 fill:#4a148c,stroke:#38006b,color:#ffffff
+    style F3 fill:#4a148c,stroke:#38006b,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **Transaction Trace (blue)**: An independent trace whose `trace_id` is deterministically derived from the transaction hash. Contains receive, validate, and relay spans.
+- **Consensus Trace (green)**: An independent trace whose `trace_id` is derived from the previous ledger hash and sequence number. Covers the open, propose, and accept phases.
+- **Validation (red)**: Validation spans live within the consensus trace (not a separate trace). They are created after the accept phase completes.
+- **Catch-Up Trace (purple)**: An independent trace for ledger acquisition, derived from the target ledger hash. Used when a node is behind and fetching missing ledgers.
+- **Dotted arrows (span links)**: Cross-trace correlations. Consensus links to transaction traces it included; catch-up links to the consensus trace that produced the target ledger.
+- **Solid arrow (C3 to V1)**: A parent-child relationship -- validation spans are direct children of the consensus accept span within the same trace.
+
+**How a query flows:**
+
+```
+"Why was TX abc slow?"
+  1. Compute trace_id = SHA-256("tx" || abc)[0:16]
+  2. Find transaction trace → see it was included in consensus round N
+  3. Follow span link → consensus trace for round N
+  4. See which phase was slow (propose? accept?)
+  5. If a node was catching up, follow link → catch-up trace
+```
+
+### Trade-offs to Consider
+
+| Concern                       | Mitigation                                                                                                                    |
+| ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
+| **Retries get same trace_id** | Add `attempt` attribute to root span; spans have unique span_ids and timestamps                                               |
+| **256→128 bit truncation**    | Birthday-bound collision at ~2⁶⁴ operations — negligible for XRPL's throughput                                                |
+| **Non-standard generation**   | OTel spec allows any 16-byte non-zero value; tooling works on the hex string                                                  |
+| **Hash computation cost**     | SHA-256 is ~0.3μs per call; XRPL already computes these hashes for other purposes                                             |
+| **Late-binding identifiers**  | Ledger hash isn't known until after consensus — validation spans use ledger_seq as fallback, then link to the consensus trace |
+
+---
+
+## Distributed Traces Across Nodes
+
+In distributed systems like rippled, traces span **multiple independent nodes**. The trace context must be propagated in network messages:
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant NodeA as Node A
+    participant NodeB as Node B
+    participant NodeC as Node C
+
+    Client->>NodeA: Submit TX<br/>(no trace context)
+
+    Note over NodeA: Creates new trace<br/>trace_id: abc123<br/>span: tx.receive
+
+    NodeA->>NodeB: Relay TX<br/>(trace_id: abc123, parent: 001)
+
+    Note over NodeB: Creates child span<br/>span: tx.relay<br/>parent_span_id: 001
+
+    NodeA->>NodeC: Relay TX<br/>(trace_id: abc123, parent: 001)
+
+    Note over NodeC: Creates child span<br/>span: tx.relay<br/>parent_span_id: 001
+
+    Note over NodeA,NodeC: All spans share trace_id: abc123<br/>enabling correlation across nodes
+```
+
+**Reading the diagram:**
+
+- **Client**: The external entity that submits a transaction. It does not carry trace context -- the trace originates at the first node.
+- **Node A**: The entry point that creates a new trace (trace_id: abc123) and the root span `tx.receive`. It relays the transaction to peers with trace context attached.
+- **Node B and Node C**: Peer nodes that receive the relayed transaction along with the propagated trace context. Each creates a child span under Node A's span, preserving the same `trace_id`.
+- **Arrows with trace context**: The relay messages carry `trace_id` and `parent_span_id`, allowing each downstream node to link its spans back to the originating span on Node A.
+
+---
+
+## Context Propagation
+
+For traces to work across nodes, **trace context must be propagated** in messages.
+
+### What's in the Context (~26 bytes)
+
+| Field         | Size     | Description                                             |
+| ------------- | -------- | ------------------------------------------------------- |
+| `trace_id`    | 16 bytes | Identifies the entire trace (constant across all nodes) |
+| `span_id`     | 8 bytes  | The sender's current span (becomes parent on receiver)  |
+| `trace_flags` | 1 byte   | Sampling decision (bit 0 = sampled; bits 1-7 reserved)  |
+| `trace_state` | variable | Optional vendor-specific data (typically omitted)       |
+
+### How span_id Changes at Each Hop
+
+Only **one** `span_id` travels in the context - the sender's current span. Each node:
+
+1. Extracts the received `span_id` and uses it as the `parent_span_id`
+2. Creates a **new** `span_id` for its own span
+3. Sends its own `span_id` as the parent when forwarding
+
+```
+Node A                      Node B                      Node C
+──────                      ──────                      ──────
+
+Span AAA                    Span BBB                    Span CCC
+   │                           │                           │
+   ▼                           ▼                           ▼
+Context out:                Context out:                Context out:
+├─ trace_id: abc123         ├─ trace_id: abc123         ├─ trace_id: abc123
+├─ span_id: AAA ──────────► ├─ span_id: BBB ──────────► ├─ span_id: CCC ──────►
+└─ flags: 01                └─ flags: 01                └─ flags: 01
+                               │                           │
+                          parent = AAA               parent = BBB
+```
+
+The `trace_id` stays constant, but `span_id` **changes at every hop** to maintain the parent-child chain.
+
+### Propagation Formats
+
+There are two patterns:
+
+### HTTP/RPC Headers (W3C Trace Context)
+
+```
+traceparent: 00-4bf92f3577b34da6a3ce929d0e0e4736-00f067aa0ba902b7-01
+             │  │                                │                │
+             │  │                                │                └── Flags (sampled)
+             │  │                                └── Parent span ID (16 hex)
+             │  └── Trace ID (32 hex)
+             └── Version
+```
+
+### Protocol Buffers (rippled P2P messages)
+
+```protobuf
+message TMTransaction {
+    bytes rawTransaction = 1;
+    // ... existing fields ...
+
+    // Trace context extension
+    bytes trace_parent = 100;  // W3C traceparent
+    bytes trace_state = 101;   // W3C tracestate
+}
+```
+
+---
+
+## Sampling
+
+Not every trace needs to be recorded. **Sampling** reduces overhead:
+
+### Head Sampling (at trace start)
+
+```
+Request arrives → Random 10% chance → Record or skip entire trace
+```
+
+- ✅ Low overhead
+- ❌ May miss interesting traces
+
+### Tail Sampling (after trace completes)
+
+```
+Trace completes → Collector evaluates:
+                  - Error? → KEEP
+                  - Slow? → KEEP
+                  - Normal? → Sample 10%
+```
+
+- ✅ Never loses important traces
+- ❌ Higher memory usage at collector
+
+---
+
+## Key Benefits for rippled
+
+| Challenge                          | How Tracing Helps                        |
+| ---------------------------------- | ---------------------------------------- |
+| "Where is my transaction?"         | Follow trace across all nodes it touched |
+| "Why was consensus slow?"          | See timing breakdown of each phase       |
+| "Which node is the bottleneck?"    | Compare span durations across nodes      |
+| "What happened during the outage?" | Correlate errors across the network      |
+
+---
+
+## Glossary
+
+| Term                 | Definition                                                          |
+| -------------------- | ------------------------------------------------------------------- |
+| **Trace**            | Complete journey of a request, identified by `trace_id`             |
+| **Span**             | Single operation within a trace                                     |
+| **Parent-Child**     | Span relationship where the parent depends on the child             |
+| **Follows-From**     | Causal relationship where originator doesn't wait for the result    |
+| **Span Link**        | Non-hierarchical connection between spans, possibly across traces   |
+| **Deterministic ID** | Trace ID derived from domain data (e.g., tx_hash) instead of random |
+| **Context**          | Data propagated between services (`trace_id`, `span_id`, flags)     |
+| **Instrumentation**  | Code that creates spans and propagates context                      |
+| **Collector**        | Service that receives, processes, and exports traces                |
+| **Backend**          | Storage/visualization system (Tempo)                                |
+| **Head Sampling**    | Sampling decision at trace start                                    |
+| **Tail Sampling**    | Sampling decision after trace completes                             |
+
+---
+
+_Next: [Architecture Analysis](./01-architecture-analysis.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/01-architecture-analysis.md

@@ -0,0 +1,467 @@
+# Architecture Analysis
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Design Decisions](./02-design-decisions.md) | [Implementation Strategy](./03-implementation-strategy.md)
+
+---
+
+## 1.1 Current rippled Architecture Overview
+
+> **WS** = WebSocket | **UNL** = Unique Node List | **TxQ** = Transaction Queue | **StatsD** = Statistics Daemon
+
+The rippled node software consists of several interconnected components that need instrumentation for distributed tracing:
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Node"]
+        subgraph services["Core Services"]
+            RPC["RPC Server<br/>(HTTP/WS/gRPC)"]
+            Overlay["Overlay<br/>(P2P Network)"]
+            Consensus["Consensus<br/>(RCLConsensus)"]
+            ValidatorList["ValidatorList<br/>(UNL Mgmt)"]
+        end
+
+        JobQueue["JobQueue<br/>(Thread Pool)"]
+
+        subgraph processing["Processing Layer"]
+            NetworkOPs["NetworkOPs<br/>(Tx Processing)"]
+            LedgerMaster["LedgerMaster<br/>(Ledger Mgmt)"]
+            NodeStore["NodeStore<br/>(Database)"]
+            InboundLedgers["InboundLedgers<br/>(Ledger Sync)"]
+        end
+
+        subgraph appservices["Application Services"]
+            PathFind["PathFinding<br/>(Payment Paths)"]
+            TxQ["TxQ<br/>(Fee Escalation)"]
+            LoadMgr["LoadManager<br/>(Fee/Load)"]
+        end
+
+        subgraph observability["Existing Observability"]
+            PerfLog["PerfLog<br/>(JSON)"]
+            Insight["Insight<br/>(StatsD)"]
+            Logging["Logging<br/>(Journal)"]
+        end
+
+        services --> JobQueue
+        JobQueue --> processing
+        JobQueue --> appservices
+    end
+
+    style rippled fill:#424242,stroke:#212121,color:#ffffff
+    style services fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style processing fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style appservices fill:#6a1b9a,stroke:#4a148c,color:#ffffff
+    style observability fill:#e65100,stroke:#bf360c,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **Core Services (blue)**: The entry points into rippled -- RPC Server handles client requests, Overlay manages peer-to-peer networking, Consensus drives agreement, and ValidatorList manages trusted validators.
+- **JobQueue (center)**: The asynchronous thread pool that decouples Core Services from the Processing and Application layers. All work flows through it.
+- **Processing Layer (green)**: Core business logic -- NetworkOPs processes transactions, LedgerMaster manages ledger state, NodeStore handles persistence, and InboundLedgers synchronizes missing data.
+- **Application Services (purple)**: Higher-level features -- PathFinding computes payment routes, TxQ manages fee-based queuing, and LoadManager tracks server load.
+- **Existing Observability (orange)**: The current monitoring stack (PerfLog, Insight, Journal logging) that OpenTelemetry will complement, not replace.
+- **Arrows (Services to JobQueue to layers)**: Work originates at Core Services, is enqueued onto the JobQueue, and dispatched to Processing or Application layers for execution.
+
+---
+
+## 1.1.1 Actors and Actions
+
+### Actors
+
+| Who (Plain English)                       | Technical Term             |
+| ----------------------------------------- | -------------------------- |
+| Network node running XRPL software        | rippled node               |
+| External client submitting requests       | RPC Client                 |
+| Network neighbor sharing data             | Peer (PeerImp)             |
+| Request handler for client queries        | RPC Server (ServerHandler) |
+| Command executor for specific RPC methods | RPCHandler                 |
+| Agreement process between nodes           | Consensus (RCLConsensus)   |
+| Transaction processing coordinator        | NetworkOPs                 |
+| Background task scheduler                 | JobQueue                   |
+| Ledger state manager                      | LedgerMaster               |
+| Payment route calculator                  | PathFinding (Pathfinder)   |
+| Transaction waiting room                  | TxQ (Transaction Queue)    |
+| Fee adjustment system                     | LoadManager                |
+| Trusted validator list manager            | ValidatorList              |
+| Protocol upgrade tracker                  | AmendmentTable             |
+| Ledger state hash tree                    | SHAMap                     |
+| Persistent key-value storage              | NodeStore                  |
+
+### Actions
+
+| What Happens (Plain English)                   | Technical Term         |
+| ---------------------------------------------- | ---------------------- |
+| Client sends a request to a node               | `rpc.request`          |
+| Node executes a specific RPC command           | `rpc.command.*`        |
+| Node receives a transaction from a peer        | `tx.receive`           |
+| Node checks if a transaction is valid          | `tx.validate`          |
+| Node forwards a transaction to neighbors       | `tx.relay`             |
+| Nodes agree on which transactions to include   | `consensus.round`      |
+| Consensus progresses through phases            | `consensus.phase.*`    |
+| Node builds a new confirmed ledger             | `ledger.build`         |
+| Node fetches missing ledger data from peers    | `ledger.acquire`       |
+| Node computes payment routes                   | `pathfind.compute`     |
+| Node queues a transaction for later processing | `txq.enqueue`          |
+| Node increases fees due to high load           | `fee.escalate`         |
+| Node fetches the latest trusted validator list | `validator.list.fetch` |
+| Node votes on a protocol amendment             | `amendment.vote`       |
+| Node synchronizes state tree data              | `shamap.sync`          |
+
+---
+
+## 1.2 Key Components for Instrumentation
+
+> **TxQ** = Transaction Queue | **UNL** = Unique Node List
+
+| Component          | Location                                   | Purpose                  | Trace Value                      |
+| ------------------ | ------------------------------------------ | ------------------------ | -------------------------------- |
+| **Overlay**        | `src/xrpld/overlay/`                       | P2P communication        | Message propagation timing       |
+| **PeerImp**        | `src/xrpld/overlay/detail/PeerImp.cpp`     | Individual peer handling | Per-peer latency                 |
+| **RCLConsensus**   | `src/xrpld/app/consensus/RCLConsensus.cpp` | Consensus algorithm      | Round timing, phase analysis     |
+| **NetworkOPs**     | `src/xrpld/app/misc/NetworkOPs.cpp`        | Transaction processing   | Tx lifecycle tracking            |
+| **ServerHandler**  | `src/xrpld/rpc/detail/ServerHandler.cpp`   | RPC entry point          | Request latency                  |
+| **RPCHandler**     | `src/xrpld/rpc/detail/RPCHandler.cpp`      | Command execution        | Per-command timing               |
+| **JobQueue**       | `src/xrpl/core/JobQueue.h`                 | Async task execution     | Queue wait times                 |
+| **PathFinding**    | `src/xrpld/app/paths/`                     | Payment path computation | Path latency, cache hits         |
+| **TxQ**            | `src/xrpld/app/misc/TxQ.cpp`               | Transaction queue/fees   | Queue depth, eviction rates      |
+| **LoadManager**    | `src/xrpld/app/main/LoadManager.cpp`       | Fee escalation/load      | Fee levels, load factors         |
+| **InboundLedgers** | `src/xrpld/app/ledger/InboundLedgers.cpp`  | Ledger acquisition       | Sync time, peer reliability      |
+| **ValidatorList**  | `src/xrpld/app/misc/ValidatorList.cpp`     | UNL management           | List freshness, fetch failures   |
+| **AmendmentTable** | `src/xrpld/app/misc/AmendmentTable.cpp`    | Protocol amendments      | Voting status, activation events |
+| **SHAMap**         | `src/xrpld/shamap/`                        | State hash tree          | Sync speed, missing nodes        |
+
+---
+
+## 1.3 Transaction Flow Diagram
+
+Transaction flow spans multiple nodes in the network. Each node creates linked spans to form a distributed trace:
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant PeerA as Peer A (Receive)
+    participant PeerB as Peer B (Relay)
+    participant PeerC as Peer C (Validate)
+
+    Client->>PeerA: 1. Submit TX
+
+    rect rgb(230, 245, 255)
+        Note over PeerA: tx.receive SPAN START
+        PeerA->>PeerA: HashRouter Deduplication
+        PeerA->>PeerA: tx.validate (child span)
+    end
+
+    PeerA->>PeerB: 2. Relay TX (with trace ctx)
+
+    rect rgb(230, 245, 255)
+        Note over PeerB: tx.receive (linked span)
+    end
+
+    PeerB->>PeerC: 3. Relay TX
+
+    rect rgb(230, 245, 255)
+        Note over PeerC: tx.receive (linked span)
+        PeerC->>PeerC: tx.process
+    end
+
+    Note over Client,PeerC: DISTRIBUTED TRACE (same trace_id: abc123)
+```
+
+**Reading the diagram:**
+
+- **Client**: The external entity that submits a transaction to Peer A. It has no trace context -- the trace starts at the first node.
+- **Peer A (Receive)**: The entry node that creates the root span `tx.receive`, runs HashRouter deduplication to avoid processing duplicates, and creates a child `tx.validate` span.
+- **Peer A to Peer B arrow**: The relay message carries trace context (trace_id + parent span_id), enabling Peer B to create a linked span under the same trace.
+- **Peer B (Relay)**: Receives the transaction and trace context, creates a `tx.receive` span linked to Peer A's trace, then relays onward.
+- **Peer C (Validate)**: Final hop in this example. Creates a linked `tx.receive` span and runs `tx.process` to fully process the transaction.
+- **Blue rectangles**: Highlight the span boundaries on each node, showing where instrumentation creates and closes spans.
+
+### Trace Structure
+
+```
+trace_id: abc123
+├── span: tx.receive (Peer A)
+│   ├── span: tx.validate
+│   └── span: tx.relay
+├── span: tx.receive (Peer B) [parent: Peer A]
+│   └── span: tx.relay
+└── span: tx.receive (Peer C) [parent: Peer B]
+    └── span: tx.process
+```
+
+---
+
+## 1.4 Consensus Round Flow
+
+Consensus rounds are multi-phase operations that benefit significantly from tracing:
+
+```mermaid
+flowchart TB
+    subgraph round["consensus.round (root span)"]
+        attrs["Attributes:<br/>xrpl.consensus.ledger.seq = 12345678<br/>xrpl.consensus.mode = proposing<br/>xrpl.consensus.proposers = 35"]
+
+        subgraph open["consensus.phase.open"]
+            open_desc["Duration: ~3s<br/>Waiting for transactions"]
+        end
+
+        subgraph establish["consensus.phase.establish"]
+            est_attrs["proposals_received = 28<br/>disputes_resolved = 3"]
+            est_children["├── consensus.proposal.receive (×28)<br/>├── consensus.proposal.send (×1)<br/>└── consensus.dispute.resolve (×3)"]
+        end
+
+        subgraph accept["consensus.phase.accept"]
+            acc_attrs["transactions_applied = 150<br/>ledger.hash = DEF456..."]
+            acc_children["├── ledger.build<br/>└── ledger.validate"]
+        end
+
+        attrs --> open
+        open --> establish
+        establish --> accept
+    end
+
+    style round fill:#f57f17,stroke:#e65100,color:#ffffff
+    style open fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style establish fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style accept fill:#c2185b,stroke:#880e4f,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **consensus.round (orange, root span)**: The top-level span encompassing the entire consensus round, with attributes like ledger sequence, mode, and proposer count.
+- **consensus.phase.open (blue)**: The first phase where the node waits (~3s) to collect incoming transactions before proposing.
+- **consensus.phase.establish (green)**: The negotiation phase where validators exchange proposals, resolve disputes, and converge on a transaction set. Child spans track each proposal received/sent and each dispute resolved.
+- **consensus.phase.accept (pink)**: The final phase where the agreed transaction set is applied, a new ledger is built, and the ledger is validated. Child spans cover `ledger.build` and `ledger.validate`.
+- **Arrows (open to establish to accept)**: The sequential flow through the three consensus phases. Each phase must complete before the next begins.
+
+---
+
+## 1.5 RPC Request Flow
+
+> **WS** = WebSocket
+
+RPC requests support W3C Trace Context headers for distributed tracing across services:
+
+```mermaid
+flowchart TB
+    subgraph request["rpc.request (root span)"]
+        http["HTTP Request — POST /<br/>traceparent:<br/>00-abc123...-def456...-01"]
+
+        attrs["Attributes:<br/>http.method = POST<br/>net.peer.ip = 192.168.1.100<br/>xrpl.rpc.command = submit"]
+
+        subgraph enqueue["jobqueue.enqueue"]
+            job_attr["xrpl.job.type = jtCLIENT_RPC"]
+        end
+
+        subgraph command["rpc.command.submit"]
+            cmd_attrs["xrpl.rpc.version = 2<br/>xrpl.rpc.role = user"]
+            cmd_children["├── tx.deserialize<br/>├── tx.validate_local<br/>└── tx.submit_to_network"]
+        end
+
+        response["Response: 200 OK<br/>Duration: 45ms"]
+
+        http --> attrs
+        attrs --> enqueue
+        enqueue --> command
+        command --> response
+    end
+
+    style request fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style enqueue fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style command fill:#e65100,stroke:#bf360c,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **rpc.request (green, root span)**: The outermost span representing the full RPC request lifecycle, from HTTP receipt to response. Carries the W3C `traceparent` header for distributed tracing.
+- **HTTP Request node**: Shows the incoming POST request with its `traceparent` header and extracted attributes (method, peer IP, command name).
+- **jobqueue.enqueue (blue)**: The span covering the asynchronous handoff from the RPC thread to the JobQueue worker thread. The trace context is preserved across this async boundary.
+- **rpc.command.submit (orange)**: The span for the actual command execution, with child spans for deserialization, local validation, and network submission.
+- **Response node**: The final output with HTTP status and total duration, marking the end of the root span.
+- **Arrows (top to bottom)**: The sequential processing pipeline -- receive request, extract attributes, enqueue job, execute command, return response.
+
+---
+
+## 1.6 Key Trace Points
+
+> **TxQ** = Transaction Queue
+
+The following table identifies priority instrumentation points across the codebase:
+
+| Category        | Span Name              | File                   | Method                  | Priority |
+| --------------- | ---------------------- | ---------------------- | ----------------------- | -------- |
+| **Transaction** | `tx.receive`           | `PeerImp.cpp`          | `handleTransaction()`   | High     |
+| **Transaction** | `tx.validate`          | `NetworkOPs.cpp`       | `processTransaction()`  | High     |
+| **Transaction** | `tx.process`           | `NetworkOPs.cpp`       | `doTransactionSync()`   | High     |
+| **Transaction** | `tx.relay`             | `OverlayImpl.cpp`      | `relay()`               | Medium   |
+| **Consensus**   | `consensus.round`      | `RCLConsensus.cpp`     | `startRound()`          | High     |
+| **Consensus**   | `consensus.phase.*`    | `Consensus.h`          | `timerEntry()`          | High     |
+| **Consensus**   | `consensus.proposal.*` | `RCLConsensus.cpp`     | `peerProposal()`        | Medium   |
+| **RPC**         | `rpc.request`          | `ServerHandler.cpp`    | `onRequest()`           | High     |
+| **RPC**         | `rpc.command.*`        | `RPCHandler.cpp`       | `doCommand()`           | High     |
+| **Peer**        | `peer.connect`         | `OverlayImpl.cpp`      | `onHandoff()`           | Low      |
+| **Peer**        | `peer.message.*`       | `PeerImp.cpp`          | `onMessage()`           | Low      |
+| **Ledger**      | `ledger.acquire`       | `InboundLedgers.cpp`   | `acquire()`             | Medium   |
+| **Ledger**      | `ledger.build`         | `RCLConsensus.cpp`     | `buildLCL()`            | High     |
+| **PathFinding** | `pathfind.request`     | `PathRequest.cpp`      | `doUpdate()`            | High     |
+| **PathFinding** | `pathfind.compute`     | `Pathfinder.cpp`       | `findPaths()`           | High     |
+| **TxQ**         | `txq.enqueue`          | `TxQ.cpp`              | `apply()`               | High     |
+| **TxQ**         | `txq.apply`            | `TxQ.cpp`              | `processClosedLedger()` | High     |
+| **Fee**         | `fee.escalate`         | `LoadManager.cpp`      | `raiseLocalFee()`       | Medium   |
+| **Ledger**      | `ledger.replay`        | `LedgerReplayer.h`     | `replay()`              | Medium   |
+| **Ledger**      | `ledger.delta`         | `LedgerDeltaAcquire.h` | `processData()`         | Medium   |
+| **Validator**   | `validator.list.fetch` | `ValidatorList.cpp`    | `verify()`              | Medium   |
+| **Validator**   | `validator.manifest`   | `Manifest.cpp`         | `applyManifest()`       | Low      |
+| **Amendment**   | `amendment.vote`       | `AmendmentTable.cpp`   | `doVoting()`            | Low      |
+| **SHAMap**      | `shamap.sync`          | `SHAMap.cpp`           | `fetchRoot()`           | Medium   |
+
+---
+
+## 1.7 Instrumentation Priority
+
+> **TxQ** = Transaction Queue
+
+```mermaid
+quadrantChart
+    title Instrumentation Priority Matrix
+    x-axis Low Complexity --> High Complexity
+    y-axis Low Value --> High Value
+    quadrant-1 Implement First
+    quadrant-2 Plan Carefully
+    quadrant-3 Quick Wins
+    quadrant-4 Consider Later
+
+    RPC Tracing: [0.2, 0.92]
+    Transaction Tracing: [0.55, 0.88]
+    Consensus Tracing: [0.78, 0.82]
+    PathFinding: [0.38, 0.75]
+    TxQ and Fees: [0.25, 0.65]
+    Ledger Sync: [0.62, 0.58]
+    Peer Message Tracing: [0.35, 0.25]
+    JobQueue Tracing: [0.2, 0.48]
+    Validator Mgmt: [0.48, 0.42]
+    Amendment Tracking: [0.15, 0.32]
+    SHAMap Operations: [0.72, 0.45]
+```
+
+---
+
+## 1.8 Observable Outcomes
+
+> **TxQ** = Transaction Queue | **UNL** = Unique Node List
+
+After implementing OpenTelemetry, operators and developers will gain visibility into the following:
+
+### 1.8.1 What You Will See: Traces
+
+| Trace Type                 | Description                                                                                 | Example Query in Grafana/Tempo                         |
+| -------------------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| **Transaction Lifecycle**  | Full journey from RPC submission through validation, relay, consensus, and ledger inclusion | `{service.name="rippled" && xrpl.tx.hash="ABC123..."}` |
+| **Cross-Node Propagation** | Transaction path across multiple rippled nodes with timing                                  | `{xrpl.tx.relay_count > 0}`                            |
+| **Consensus Rounds**       | Complete round with all phases (open, establish, accept)                                    | `{span.name=~"consensus.round.*"}`                     |
+| **RPC Request Processing** | Individual command execution with timing breakdown                                          | `{xrpl.rpc.command="account_info"}`                    |
+| **Ledger Acquisition**     | Peer-to-peer ledger data requests and responses                                             | `{span.name="ledger.acquire"}`                         |
+| **PathFinding Latency**    | Path computation time and cache effectiveness for payment RPCs                              | `{span.name="pathfind.compute"}`                       |
+| **TxQ Behavior**           | Queue depth, eviction patterns, fee escalation during congestion                            | `{span.name=~"txq.*"}`                                 |
+| **Ledger Sync**            | Full acquisition timeline including delta and transaction fetches                           | `{span.name=~"ledger.acquire.*"}`                      |
+| **Validator Health**       | UNL fetch success, manifest updates, stale list detection                                   | `{span.name=~"validator.*"}`                           |
+
+### 1.8.2 What You Will See: Metrics (Derived from Traces)
+
+| Metric                        | Description                             | Dashboard Panel             |
+| ----------------------------- | --------------------------------------- | --------------------------- |
+| **RPC Latency (p50/p95/p99)** | Response time distribution per command  | Heatmap by command          |
+| **Transaction Throughput**    | Transactions processed per second       | Time series graph           |
+| **Consensus Round Duration**  | Time to complete consensus phases       | Histogram                   |
+| **Cross-Node Latency**        | Time for transaction to reach N nodes   | Line chart with percentiles |
+| **Error Rate**                | Failed transactions/RPC calls by type   | Stacked bar chart           |
+| **PathFinding Latency**       | Path computation time per currency pair | Heatmap by currency         |
+| **TxQ Depth**                 | Queued transactions over time           | Time series with thresholds |
+| **Fee Escalation Level**      | Current fee multiplier                  | Gauge with alert thresholds |
+| **Ledger Sync Duration**      | Time to acquire missing ledgers         | Histogram                   |
+
+### 1.8.3 Concrete Dashboard Examples
+
+**Transaction Trace View (Tempo):**
+
+```
+┌────────────────────────────────────────────────────────────────────────────────┐
+│ Trace: abc123... (Transaction Submission)                    Duration: 847ms   │
+├────────────────────────────────────────────────────────────────────────────────┤
+│ ├── rpc.request [ServerHandler]                              ████░░░░░░  45ms  │
+│ │   └── rpc.command.submit [RPCHandler]                      ████░░░░░░  42ms  │
+│ │       └── tx.receive [NetworkOPs]                          ███░░░░░░░  35ms  │
+│ │           ├── tx.validate [TxQ]                            █░░░░░░░░░   8ms  │
+│ │           └── tx.relay [Overlay]                           ██░░░░░░░░  15ms  │
+│ │               ├── tx.receive [Node-B]                      █████░░░░░  52ms  │
+│ │               │   └── tx.relay [Node-B]                    ██░░░░░░░░  18ms  │
+│ │               └── tx.receive [Node-C]                      ██████░░░░  65ms  │
+│ └── consensus.round [RCLConsensus]                           ████████░░ 720ms  │
+│     ├── consensus.phase.open                                 ██░░░░░░░░ 180ms  │
+│     ├── consensus.phase.establish                            █████░░░░░ 480ms  │
+│     └── consensus.phase.accept                               █░░░░░░░░░  60ms  │
+└────────────────────────────────────────────────────────────────────────────────┘
+```
+
+**RPC Performance Dashboard Panel:**
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│ RPC Command Latency (Last 1 Hour)                           │
+├─────────────────────────────────────────────────────────────┤
+│ Command          │ p50    │ p95    │ p99    │ Errors │ Rate │
+│──────────────────┼────────┼────────┼────────┼────────┼──────│
+│ account_info     │  12ms  │  45ms  │  89ms  │  0.1%  │ 150/s│
+│ submit           │  35ms  │ 120ms  │ 250ms  │  2.3%  │  45/s│
+│ ledger           │   8ms  │  25ms  │  55ms  │  0.0%  │  80/s│
+│ tx               │  15ms  │  50ms  │ 100ms  │  0.5%  │  60/s│
+│ server_info      │   5ms  │  12ms  │  20ms  │  0.0%  │ 200/s│
+└─────────────────────────────────────────────────────────────┘
+```
+
+**Consensus Health Dashboard Panel:**
+
+```mermaid
+---
+config:
+    xyChart:
+        width: 1200
+        height: 400
+        plotReservedSpacePercent: 50
+        chartOrientation: vertical
+    themeVariables:
+        xyChart:
+            plotColorPalette: "#3498db"
+---
+xychart-beta
+    title "Consensus Round Duration (Last 24 Hours)"
+    x-axis "Time of Day (Hours)" [0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24]
+    y-axis "Duration (seconds)" 1 --> 5
+    line [2.1, 2.4, 2.8, 3.2, 3.8, 4.3, 4.5, 5.0, 4.7, 4.0, 3.2, 2.6, 2.0]
+```
+
+### 1.8.4 Operator Actionable Insights
+
+| Scenario                  | What You'll See                                                              | Action                                           |
+| ------------------------- | ---------------------------------------------------------------------------- | ------------------------------------------------ |
+| **Slow RPC**              | Span showing which phase is slow (parsing, execution, serialization)         | Optimize specific code path                      |
+| **Transaction Stuck**     | Trace stops at validation; error attribute shows reason                      | Fix transaction parameters                       |
+| **Consensus Delay**       | Phase.establish taking too long; proposer attribute shows missing validators | Investigate network connectivity                 |
+| **Memory Spike**          | Large batch of spans correlating with memory increase                        | Tune batch_size or sampling                      |
+| **Network Partition**     | Traces missing cross-node links for specific peer                            | Check peer connectivity                          |
+| **Path Computation Slow** | pathfind.compute span shows high latency; cache miss rate in attributes      | Warm the RippleLineCache, check order book depth |
+| **TxQ Full**              | txq.enqueue spans show evictions; fee.escalate spans increasing              | Monitor fee levels, alert operators              |
+| **Ledger Sync Stalled**   | ledger.acquire spans timing out; peer reliability attributes show issues     | Check peer connectivity, add trusted peers       |
+| **UNL Stale**             | validator.list.fetch spans failing; last_update attribute aging              | Verify validator site URLs, check DNS            |
+
+### 1.8.5 Developer Debugging Workflow
+
+1. **Find Transaction**: Query by `xrpl.tx.hash` to get full trace
+2. **Identify Bottleneck**: Look at span durations to find slowest component
+3. **Check Attributes**: Review `xrpl.tx.validity`, `xrpl.rpc.status` for errors
+4. **Correlate Logs**: Use `trace_id` to find related PerfLog entries
+5. **Compare Nodes**: Filter by `service.instance.id` to compare behavior across nodes
+
+---
+
+_Next: [Design Decisions](./02-design-decisions.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/02-design-decisions.md

@@ -0,0 +1,631 @@
+# Design Decisions
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Architecture Analysis](./01-architecture-analysis.md) | [Code Samples](./04-code-samples.md)
+
+---
+
+## 2.1 OpenTelemetry Components
+
+> **OTLP** = OpenTelemetry Protocol
+
+### 2.1.1 SDK Selection
+
+**Primary Choice**: OpenTelemetry C++ SDK (`opentelemetry-cpp`)
+
+| Component                               | Purpose                | Required    |
+| --------------------------------------- | ---------------------- | ----------- |
+| `opentelemetry-cpp::api`                | Tracing API headers    | Yes         |
+| `opentelemetry-cpp::sdk`                | SDK implementation     | Yes         |
+| `opentelemetry-cpp::ext`                | Extensions (exporters) | Yes         |
+| `opentelemetry-cpp::otlp_grpc_exporter` | OTLP/gRPC export       | Recommended |
+| `opentelemetry-cpp::otlp_http_exporter` | OTLP/HTTP export       | Alternative |
+
+### 2.1.2 Instrumentation Strategy
+
+**Manual Instrumentation** (recommended):
+
+| Approach   | Pros                                                              | Cons                                                    |
+| ---------- | ----------------------------------------------------------------- | ------------------------------------------------------- |
+| **Manual** | Precise control, optimized placement, rippled-specific attributes | More development effort                                 |
+| **Auto**   | Less code, automatic coverage                                     | Less control, potential overhead, limited customization |
+
+---
+
+## 2.2 Exporter Configuration
+
+> **OTLP** = OpenTelemetry Protocol
+
+```mermaid
+flowchart TB
+    subgraph nodes["rippled Nodes"]
+        node1["rippled<br/>Node 1"]
+        node2["rippled<br/>Node 2"]
+        node3["rippled<br/>Node 3"]
+    end
+
+    collector["OpenTelemetry<br/>Collector<br/>(sidecar or standalone)"]
+
+    subgraph backends["Observability Backends"]
+        tempo["Tempo"]
+        elastic["Elastic<br/>APM"]
+    end
+
+    node1 -->|"OTLP/gRPC<br/>:4317"| collector
+    node2 -->|"OTLP/gRPC<br/>:4317"| collector
+    node3 -->|"OTLP/gRPC<br/>:4317"| collector
+
+    collector --> tempo
+    collector --> elastic
+
+    style nodes fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style backends fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style collector fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **rippled Nodes (blue)**: The source of telemetry data. Each rippled node exports spans via OTLP/gRPC on port 4317.
+- **OpenTelemetry Collector (red)**: The central aggregation point that receives spans from all nodes. Can run as a sidecar (per-node) or standalone (shared). Handles batching, filtering, and routing.
+- **Observability Backends (green)**: The storage and visualization destinations. Tempo is the recommended backend for both development and production, and Elastic APM is an alternative. The Collector routes to one or more backends.
+- **Arrows (nodes to collector to backends)**: The data pipeline -- spans flow from nodes to the Collector over gRPC, then the Collector fans out to the configured backends.
+
+### 2.2.1 OTLP/gRPC (Recommended)
+
+```cpp
+// Configuration for OTLP over gRPC
+namespace otlp = opentelemetry::exporter::otlp;
+
+otlp::OtlpGrpcExporterOptions opts;
+opts.endpoint = "localhost:4317";
+opts.useTls = true;
+opts.sslCaCertPath = "/path/to/ca.crt";
+```
+
+### 2.2.2 OTLP/HTTP (Alternative)
+
+```cpp
+// Configuration for OTLP over HTTP
+namespace otlp = opentelemetry::exporter::otlp;
+
+otlp::OtlpHttpExporterOptions opts;
+opts.url = "http://localhost:4318/v1/traces";
+opts.content_type = otlp::HttpRequestContentType::kJson;  // or kBinary
+```
+
+---
+
+## 2.3 Span Naming Conventions
+
+> **TxQ** = Transaction Queue | **UNL** = Unique Node List | **WS** = WebSocket
+
+### 2.3.1 Naming Schema
+
+```
+<component>.<operation>[.<sub-operation>]
+```
+
+**Examples**:
+
+- `tx.receive` - Transaction received from peer
+- `consensus.phase.establish` - Consensus establish phase
+- `rpc.command.server_info` - server_info RPC command
+
+### 2.3.2 Complete Span Catalog
+
+```yaml
+# Transaction Spans
+tx:
+  receive: "Transaction received from network"
+  validate: "Transaction signature/format validation"
+  process: "Full transaction processing"
+  relay: "Transaction relay to peers"
+  apply: "Apply transaction to ledger"
+
+# Consensus Spans
+consensus:
+  round: "Complete consensus round"
+  phase:
+    open: "Open phase - collecting transactions"
+    establish: "Establish phase - reaching agreement"
+    accept: "Accept phase - applying consensus"
+  proposal:
+    receive: "Receive peer proposal"
+    send: "Send our proposal"
+  validation:
+    receive: "Receive peer validation"
+    send: "Send our validation"
+
+# RPC Spans
+rpc:
+  request: "HTTP/WebSocket request handling"
+  command:
+    "*": "Specific RPC command (dynamic)"
+
+# Peer Spans
+peer:
+  connect: "Peer connection establishment"
+  disconnect: "Peer disconnection"
+  message:
+    send: "Send protocol message"
+    receive: "Receive protocol message"
+
+# Ledger Spans
+ledger:
+  acquire: "Ledger acquisition from network"
+  build: "Build new ledger"
+  validate: "Ledger validation"
+  close: "Close ledger"
+  replay: "Ledger replay executed"
+  delta: "Delta-based ledger acquired"
+
+# PathFinding Spans
+pathfind:
+  request: "Path request initiated"
+  compute: "Path computation executed"
+
+# TxQ Spans
+txq:
+  enqueue: "Transaction queued"
+  apply: "Queued transaction applied"
+
+# Fee/Load Spans
+fee:
+  escalate: "Fee escalation triggered"
+
+# Validator Spans
+validator:
+  list:
+    fetch: "UNL list fetched"
+  manifest: "Manifest update processed"
+
+# Amendment Spans
+amendment:
+  vote: "Amendment voting executed"
+
+# SHAMap Spans
+shamap:
+  sync: "State tree synchronization"
+
+# Job Spans
+job:
+  enqueue: "Job added to queue"
+  execute: "Job execution"
+```
+
+---
+
+## 2.4 Attribute Schema
+
+> **TxQ** = Transaction Queue | **UNL** = Unique Node List | **OTLP** = OpenTelemetry Protocol
+
+### 2.4.1 Resource Attributes (Set Once at Startup)
+
+```cpp
+// Standard OpenTelemetry semantic conventions
+resource::SemanticConventions::SERVICE_NAME        = "rippled"
+resource::SemanticConventions::SERVICE_VERSION     = BuildInfo::getVersionString()
+resource::SemanticConventions::SERVICE_INSTANCE_ID = <node_public_key_base58>
+
+// Custom rippled attributes
+"xrpl.network.id"      = <network_id>           // e.g., 0 for mainnet
+"xrpl.network.type"    = "mainnet" | "testnet" | "devnet" | "standalone"
+"xrpl.node.type"       = "validator" | "stock" | "reporting"
+"xrpl.node.cluster"    = <cluster_name>         // If clustered
+```
+
+### 2.4.2 Span Attributes by Category
+
+#### Transaction Attributes
+
+```cpp
+"xrpl.tx.hash"         = string   // Transaction hash (hex)
+"xrpl.tx.type"         = string   // "Payment", "OfferCreate", etc.
+"xrpl.tx.account"      = string   // Source account (redacted in prod)
+"xrpl.tx.sequence"     = int64    // Account sequence number
+"xrpl.tx.fee"          = int64    // Fee in drops
+"xrpl.tx.result"       = string   // "tesSUCCESS", "tecPATH_DRY", etc.
+"xrpl.tx.ledger_index" = int64    // Ledger containing transaction
+```
+
+#### Consensus Attributes
+
+```cpp
+"xrpl.consensus.round"          = int64    // Round number
+"xrpl.consensus.phase"          = string   // "open", "establish", "accept"
+"xrpl.consensus.mode"           = string   // "proposing", "observing", etc.
+"xrpl.consensus.proposers"      = int64    // Number of proposers
+"xrpl.consensus.ledger.prev"    = string   // Previous ledger hash
+"xrpl.consensus.ledger.seq"     = int64    // Ledger sequence
+"xrpl.consensus.tx_count"       = int64    // Transactions in consensus set
+"xrpl.consensus.duration_ms"    = float64  // Round duration
+
+// Phase 4a: Establish-phase gap fill & cross-node correlation
+"xrpl.consensus.round_id"          = int64    // Consensus round number
+"xrpl.consensus.ledger_id"         = string   // previousLedger.id() — shared across nodes
+"xrpl.consensus.trace_strategy"    = string   // "deterministic" or "attribute"
+"xrpl.consensus.converge_percent"  = int64    // Convergence % (0-100+)
+"xrpl.consensus.establish_count"   = int64    // Number of establish iterations
+"xrpl.consensus.disputes_count"    = int64    // Active disputed transactions
+"xrpl.consensus.proposers_agreed"  = int64    // Peers agreeing with our position
+"xrpl.consensus.proposers_total"   = int64    // Total peer positions
+"xrpl.consensus.agree_count"       = int64    // Peers that agree (haveConsensus)
+"xrpl.consensus.disagree_count"    = int64    // Peers that disagree
+"xrpl.consensus.threshold_percent" = int64    // Current threshold (50/65/70/95)
+"xrpl.consensus.result"            = string   // "yes", "no", "moved_on"
+"xrpl.consensus.mode.old"          = string   // Previous consensus mode
+"xrpl.consensus.mode.new"          = string   // New consensus mode
+```
+
+#### RPC Attributes
+
+```cpp
+"xrpl.rpc.command"     = string   // Command name
+"xrpl.rpc.version"     = int64    // API version
+"xrpl.rpc.role"        = string   // "admin" or "user"
+"xrpl.rpc.params"      = string   // Sanitized parameters (optional)
+```
+
+#### Peer & Message Attributes
+
+```cpp
+"xrpl.peer.id"            = string   // Peer public key (base58)
+"xrpl.peer.address"       = string   // IP:port
+"xrpl.peer.latency_ms"    = float64  // Measured latency
+"xrpl.peer.cluster"       = string   // Cluster name if clustered
+"xrpl.message.type"       = string   // Protocol message type name
+"xrpl.message.size_bytes" = int64    // Message size
+"xrpl.message.compressed" = bool     // Whether compressed
+```
+
+#### Ledger & Job Attributes
+
+```cpp
+"xrpl.ledger.hash"       = string   // Ledger hash
+"xrpl.ledger.index"      = int64    // Ledger sequence/index
+"xrpl.ledger.close_time" = int64    // Close time (epoch)
+"xrpl.ledger.tx_count"   = int64    // Transaction count
+"xrpl.job.type"          = string   // Job type name
+"xrpl.job.queue_ms"      = float64  // Time spent in queue
+"xrpl.job.worker"        = int64    // Worker thread ID
+```
+
+#### PathFinding Attributes
+
+```cpp
+"xrpl.pathfind.source_currency"  = string   // Source currency code
+"xrpl.pathfind.dest_currency"    = string   // Destination currency code
+"xrpl.pathfind.path_count"       = int64    // Number of paths found
+"xrpl.pathfind.cache_hit"        = bool     // RippleLineCache hit
+```
+
+#### TxQ Attributes
+
+```cpp
+"xrpl.txq.queue_depth"      = int64    // Current queue depth
+"xrpl.txq.fee_level"        = int64    // Fee level of transaction
+"xrpl.txq.eviction_reason"  = string   // Why transaction was evicted
+```
+
+#### Fee Attributes
+
+```cpp
+"xrpl.fee.load_factor"      = int64    // Current load factor
+"xrpl.fee.escalation_level" = int64    // Fee escalation multiplier
+```
+
+#### Validator Attributes
+
+```cpp
+"xrpl.validator.list_size"    = int64    // UNL size
+"xrpl.validator.list_age_sec" = int64    // Seconds since last update
+```
+
+#### Amendment Attributes
+
+```cpp
+"xrpl.amendment.name"         = string   // Amendment name
+"xrpl.amendment.status"       = string   // "enabled", "vetoed", "supported"
+```
+
+#### SHAMap Attributes
+
+```cpp
+"xrpl.shamap.type"            = string   // "transaction", "state", "account_state"
+"xrpl.shamap.missing_nodes"   = int64    // Number of missing nodes during sync
+"xrpl.shamap.duration_ms"     = float64  // Sync duration
+```
+
+### 2.4.3 Data Collection Summary
+
+The following table summarizes what data is collected by category:
+
+| Category        | Attributes Collected                                                   | Purpose                      |
+| --------------- | ---------------------------------------------------------------------- | ---------------------------- |
+| **Transaction** | `tx.hash`, `tx.type`, `tx.result`, `tx.fee`, `ledger_index`            | Trace transaction lifecycle  |
+| **Consensus**   | `round`, `phase`, `mode`, `proposers` (public keys), `duration_ms`     | Analyze consensus timing     |
+| **RPC**         | `command`, `version`, `status`, `duration_ms`                          | Monitor RPC performance      |
+| **Peer**        | `peer.id` (public key), `latency_ms`, `message.type`, `message.size`   | Network topology analysis    |
+| **Ledger**      | `ledger.hash`, `ledger.index`, `close_time`, `tx_count`                | Ledger progression tracking  |
+| **Job**         | `job.type`, `queue_ms`, `worker`                                       | JobQueue performance         |
+| **PathFinding** | `pathfind.source_currency`, `dest_currency`, `path_count`, `cache_hit` | Payment path analysis        |
+| **TxQ**         | `txq.queue_depth`, `fee_level`, `eviction_reason`                      | Queue depth and fee tracking |
+| **Fee**         | `fee.load_factor`, `escalation_level`                                  | Fee escalation monitoring    |
+| **Validator**   | `validator.list_size`, `list_age_sec`                                  | UNL health monitoring        |
+| **Amendment**   | `amendment.name`, `status`                                             | Protocol upgrade tracking    |
+| **SHAMap**      | `shamap.type`, `missing_nodes`, `duration_ms`                          | State tree sync performance  |
+
+### 2.4.4 Privacy & Sensitive Data Policy
+
+> **PII** = Personally Identifiable Information
+
+OpenTelemetry instrumentation is designed to collect **operational metadata only**, never sensitive content.
+
+#### Data NOT Collected
+
+The following data is explicitly **excluded** from telemetry collection:
+
+| Excluded Data           | Reason                                    |
+| ----------------------- | ----------------------------------------- |
+| **Private Keys**        | Never exposed; not relevant to tracing    |
+| **Account Balances**    | Financial data; privacy sensitive         |
+| **Transaction Amounts** | Financial data; privacy sensitive         |
+| **Raw TX Payloads**     | May contain sensitive memo/data fields    |
+| **Personal Data**       | No PII collected                          |
+| **IP Addresses**        | Configurable; excluded by default in prod |
+
+#### Privacy Protection Mechanisms
+
+| Mechanism                     | Description                                                               |
+| ----------------------------- | ------------------------------------------------------------------------- |
+| **Account Hashing**           | `xrpl.tx.account` is hashed at collector level before storage             |
+| **Configurable Redaction**    | Sensitive fields can be excluded via `[telemetry]` config section         |
+| **Sampling**                  | Only 10% of traces recorded by default, reducing data exposure            |
+| **Local Control**             | Node operators have full control over what gets exported                  |
+| **No Raw Payloads**           | Transaction content is never recorded, only metadata (hash, type, result) |
+| **Collector-Level Filtering** | Additional redaction/hashing can be configured at OTel Collector          |
+
+#### Collector-Level Data Protection
+
+The OpenTelemetry Collector can be configured to hash or redact sensitive attributes before export:
+
+```yaml
+processors:
+  attributes:
+    actions:
+      # Hash account addresses before storage
+      - key: xrpl.tx.account
+        action: hash
+      # Remove IP addresses entirely
+      - key: xrpl.peer.address
+        action: delete
+      # Redact specific fields
+      - key: xrpl.rpc.params
+        action: delete
+```
+
+#### Configuration Options for Privacy
+
+In `rippled.cfg`, operators can control data collection granularity:
+
+```ini
+[telemetry]
+enabled=1
+
+# Disable collection of specific components
+trace_transactions=1
+trace_consensus=1
+trace_rpc=1
+trace_peer=0          # Disable peer tracing (high volume, includes addresses)
+
+# Redact specific attributes
+redact_account=1      # Hash account addresses before export
+redact_peer_address=1 # Remove peer IP addresses
+```
+
+> **Note**: The `redact_account` configuration in `rippled.cfg` controls SDK-level redaction before export, while collector-level filtering (see [Collector-Level Data Protection](#collector-level-data-protection) above) provides an additional defense-in-depth layer. Both can operate independently.
+
+> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes) — never **sensitive content** (keys, balances, amounts, raw payloads).
+
+---
+
+## 2.5 Context Propagation Design
+
+> **WS** = WebSocket
+
+### 2.5.1 Propagation Boundaries
+
+```mermaid
+flowchart TB
+    subgraph http["HTTP/WebSocket (RPC)"]
+        w3c["W3C Trace Context Headers:<br/>traceparent:<br/>00-trace_id-span_id-flags<br/>tracestate: rippled=..."]
+    end
+
+    subgraph protobuf["Protocol Buffers (P2P)"]
+        proto["message TraceContext {<br/>  bytes trace_id = 1;  // 16 bytes<br/>  bytes span_id = 2;   // 8 bytes<br/>  uint32 trace_flags = 3;<br/>  string trace_state = 4;<br/>}"]
+    end
+
+    subgraph jobqueue["JobQueue (Internal Async)"]
+        job["Context captured at job creation,<br/>restored at execution<br/><br/>class Job {<br/>  otel::context::Context<br/>    traceContext_;<br/>};"]
+    end
+
+    style http fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style protobuf fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style jobqueue fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **HTTP/WebSocket - RPC (blue)**: For client-facing RPC requests, trace context is propagated using the W3C `traceparent` header. This is the standard approach and works with any OTel-compatible client.
+- **Protocol Buffers - P2P (green)**: For peer-to-peer messages between rippled nodes, trace context is embedded as a protobuf `TraceContext` message carrying trace_id, span_id, flags, and optional trace_state.
+- **JobQueue - Internal Async (red)**: For asynchronous work within a single node, the OTel context is captured when a job is created and restored when the job executes on a worker thread. This bridges the async gap so spans remain linked.
+
+---
+
+## 2.6 Integration with Existing Observability
+
+> **OTLP** = OpenTelemetry Protocol | **WS** = WebSocket
+
+### 2.6.1 Existing Frameworks Comparison
+
+rippled already has two observability mechanisms. OpenTelemetry complements (not replaces) them:
+
+| Aspect                | PerfLog                       | Beast Insight (StatsD)       | OpenTelemetry             |
+| --------------------- | ----------------------------- | ---------------------------- | ------------------------- |
+| **Type**              | Logging                       | Metrics                      | Distributed Tracing       |
+| **Data**              | JSON log entries              | Counters, gauges, histograms | Spans with context        |
+| **Scope**             | Single node                   | Single node                  | **Cross-node**            |
+| **Output**            | `perf.log` file               | StatsD server                | OTLP Collector            |
+| **Question answered** | "What happened on this node?" | "How many? How fast?"        | "What was the journey?"   |
+| **Correlation**       | By timestamp                  | By metric name               | By `trace_id`             |
+| **Overhead**          | Low (file I/O)                | Low (UDP packets)            | Low-Medium (configurable) |
+
+### 2.6.2 What Each Framework Does Best
+
+#### PerfLog
+
+- **Purpose**: Detailed local event logging for RPC and job execution
+- **Strengths**:
+  - Rich JSON output with timing data
+  - Already integrated in RPC handlers
+  - File-based, no external dependencies
+- **Limitations**:
+  - Single-node only (no cross-node correlation)
+  - No parent-child relationships between events
+  - Manual log parsing required
+
+```json
+// Example PerfLog entry
+{
+  "time": "2024-01-15T10:30:00.123Z",
+  "method": "submit",
+  "duration_us": 1523,
+  "result": "tesSUCCESS"
+}
+```
+
+#### Beast Insight (StatsD)
+
+- **Purpose**: Real-time metrics for monitoring dashboards
+- **Strengths**:
+  - Aggregated metrics (counters, gauges, histograms)
+  - Low overhead (UDP, fire-and-forget)
+  - Good for alerting thresholds
+- **Limitations**:
+  - No request-level detail
+  - No causal relationships
+  - Single-node perspective
+
+```cpp
+// Example StatsD usage in rippled
+insight.increment("rpc.submit.count");
+insight.gauge("ledger.age", age);
+insight.timing("consensus.round", duration);
+```
+
+#### OpenTelemetry (NEW)
+
+- **Purpose**: Distributed request tracing across nodes
+- **Strengths**:
+  - **Cross-node correlation** via `trace_id`
+  - Parent-child span relationships
+  - Rich attributes per span
+  - Industry standard (CNCF)
+- **Limitations**:
+  - Requires collector infrastructure
+  - Higher complexity than logging
+
+```cpp
+// Example OpenTelemetry span
+auto span = telemetry.startSpan("tx.relay");
+span->SetAttribute("tx.hash", hash);
+span->SetAttribute("peer.id", peerId);
+// Span automatically linked to parent via context
+```
+
+### 2.6.3 When to Use Each
+
+| Scenario                                | PerfLog    | StatsD | OpenTelemetry |
+| --------------------------------------- | ---------- | ------ | ------------- |
+| "How many TXs per second?"              | ❌         | ✅     | ✅            |
+| "What's the p99 RPC latency?"           | ❌         | ✅     | ✅            |
+| "Why was this specific TX slow?"        | ⚠️ partial | ❌     | ✅            |
+| "Which node delayed consensus?"         | ❌         | ❌     | ✅            |
+| "What happened on node X at time T?"    | ✅         | ❌     | ✅            |
+| "Show me the TX journey across 5 nodes" | ❌         | ❌     | ✅            |
+
+### 2.6.4 Coexistence Strategy
+
+> **Note**: Phase 7 replaces the StatsD bridge with native OTel Metrics SDK export. The diagram below shows the Phase 6 intermediate state. See [Phase7_taskList.md](./Phase7_taskList.md) for the migration design where Beast Insight emits via OTLP instead of StatsD.
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Process"]
+        perflog["PerfLog<br/>(JSON to file)"]
+        insight["Beast Insight<br/>(StatsD)"]
+        otel["OpenTelemetry<br/>(Tracing)"]
+    end
+
+    perflog --> perffile["perf.log"]
+    insight --> statsd["StatsD Server"]
+    otel --> collector["OTLP Collector"]
+
+    perffile --> grafana["Grafana<br/>(Unified UI)"]
+    statsd --> grafana
+    collector --> grafana
+
+    style rippled fill:#212121,stroke:#0a0a0a,color:#ffffff
+    style grafana fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **rippled Process (dark gray)**: The single rippled node running all three observability frameworks side by side. Each framework operates independently with no interference.
+- **PerfLog to perf.log**: PerfLog writes JSON-formatted event logs to a local file. Grafana can ingest these via Loki or a file-based datasource.
+- **Beast Insight to StatsD Server**: Insight sends aggregated metrics (counters, gauges) over UDP to a StatsD server. Grafana reads from StatsD-compatible backends like Graphite or Prometheus (via StatsD exporter).
+- **OpenTelemetry to OTLP Collector**: OTel exports spans over OTLP/gRPC to a Collector, which then forwards to a trace backend (Tempo).
+- **Grafana (red, unified UI)**: All three data streams converge in Grafana, enabling operators to correlate logs, metrics, and traces in a single dashboard.
+
+**Phase 7 target state**: Beast Insight routes to `OTelCollector` (new `Collector` implementation) which exports via OTLP/HTTP to the same collector endpoint as traces. StatsD UDP path becomes a deprecated fallback (`[insight] server=statsd`). See [06-implementation-phases.md §6.8](./06-implementation-phases.md) and [Phase7_taskList.md](./Phase7_taskList.md) for details.
+
+### 2.6.5 Correlation with PerfLog
+
+Trace IDs can be correlated with existing PerfLog entries for comprehensive debugging:
+
+```cpp
+// In RPCHandler.cpp - correlate trace with PerfLog
+Status doCommand(RPC::JsonContext& context, Json::Value& result)
+{
+    // Start OpenTelemetry span
+    auto span = context.app.getTelemetry().startSpan(
+        "rpc.command." + context.method);
+
+    // Get trace ID for correlation
+    auto traceId = span->GetContext().trace_id().IsValid()
+        ? toHex(span->GetContext().trace_id())
+        : "";
+
+    // Use existing PerfLog with trace correlation
+    auto const curId = context.app.getPerfLog().currentId();
+    context.app.getPerfLog().rpcStart(context.method, curId);
+
+    // Future: Add trace ID to PerfLog entry
+    // context.app.getPerfLog().setTraceId(curId, traceId);
+
+    try {
+        auto ret = handler(context, result);
+        context.app.getPerfLog().rpcFinish(context.method, curId);
+        span->SetStatus(opentelemetry::trace::StatusCode::kOk);
+        return ret;
+    } catch (std::exception const& e) {
+        context.app.getPerfLog().rpcError(context.method, curId);
+        span->RecordException(e);
+        span->SetStatus(opentelemetry::trace::StatusCode::kError, e.what());
+        throw;
+    }
+}
+```
+
+---
+
+_Previous: [Architecture Analysis](./01-architecture-analysis.md)_ | _Next: [Implementation Strategy](./03-implementation-strategy.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/03-implementation-strategy.md

@@ -0,0 +1,528 @@
+# Implementation Strategy
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Code Samples](./04-code-samples.md) | [Configuration Reference](./05-configuration-reference.md)
+
+---
+
+## 3.1 Directory Structure
+
+The telemetry implementation follows rippled's existing code organization pattern:
+
+```
+include/xrpl/
+├── telemetry/
+│   ├── Telemetry.h              # Main telemetry interface
+│   ├── TelemetryConfig.h        # Configuration structures
+│   ├── TraceContext.h           # Context propagation utilities
+│   ├── SpanGuard.h              # RAII span management
+│   └── SpanAttributes.h         # Attribute helper functions
+
+src/libxrpl/
+├── telemetry/
+│   ├── Telemetry.cpp            # Implementation
+│   ├── TelemetryConfig.cpp      # Config parsing
+│   ├── TraceContext.cpp         # Context serialization
+│   └── NullTelemetry.cpp        # No-op implementation
+
+src/xrpld/
+├── telemetry/
+│   ├── TracingInstrumentation.h # Instrumentation macros
+│   └── TracingInstrumentation.cpp
+```
+
+---
+
+## 3.2 Implementation Approach
+
+<div align="center">
+
+```mermaid
+%%{init: {'flowchart': {'nodeSpacing': 20, 'rankSpacing': 30}}}%%
+flowchart TB
+    subgraph phase1["Phase 1: Core"]
+        direction LR
+        sdk["SDK Integration"] ~~~ interface["Telemetry Interface"] ~~~ config["Configuration"]
+    end
+
+    subgraph phase2["Phase 2: RPC"]
+        direction LR
+        http["HTTP Context"] ~~~ rpc["RPC Handlers"]
+    end
+
+    subgraph phase3["Phase 3: P2P"]
+        direction LR
+        proto["Protobuf Context"] ~~~ tx["Transaction Relay"]
+    end
+
+    subgraph phase4["Phase 4: Consensus"]
+        direction LR
+        consensus["Consensus Rounds"] ~~~ proposals["Proposals"]
+    end
+
+    phase1 --> phase2 --> phase3 --> phase4
+
+    style phase1 fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style phase2 fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style phase3 fill:#e65100,stroke:#bf360c,color:#ffffff
+    style phase4 fill:#c2185b,stroke:#880e4f,color:#ffffff
+```
+
+</div>
+
+### Key Principles
+
+1. **Minimal Intrusion**: Instrumentation should not alter existing control flow
+2. **Zero-Cost When Disabled**: Use compile-time flags and no-op implementations
+3. **Backward Compatibility**: Protocol Buffer extensions use high field numbers
+4. **Graceful Degradation**: Tracing failures must not affect node operation
+
+---
+
+## 3.3 Performance Overhead Summary
+
+> **OTLP** = OpenTelemetry Protocol
+
+| Metric        | Overhead   | Notes                                            |
+| ------------- | ---------- | ------------------------------------------------ |
+| CPU           | 1-3%       | Of per-transaction CPU cost (~200μs baseline)    |
+| Memory        | ~10 MB     | SDK statics + batch buffer + worker thread stack |
+| Network       | 10-50 KB/s | Compressed OTLP export to collector              |
+| Latency (p99) | <2%        | With proper sampling configuration               |
+
+---
+
+## 3.4 Detailed CPU Overhead Analysis
+
+### 3.4.1 Per-Operation Costs
+
+> **Note on hardware assumptions**: The costs below are based on the official OTel C++ SDK CI benchmarks
+> (969 runs on GitHub Actions 2-core shared runners). On production server hardware (3+ GHz Xeon),
+> expect costs at the **lower end** of each range (~30-50% improvement over CI hardware).
+
+| Operation             | Time (ns) | Frequency              | Impact     |
+| --------------------- | --------- | ---------------------- | ---------- |
+| Span creation         | 500-1000  | Every traced operation | Low        |
+| Span end              | 100-200   | Every traced operation | Low        |
+| SetAttribute (string) | 80-120    | 3-5 per span           | Low        |
+| SetAttribute (int)    | 40-60     | 2-3 per span           | Negligible |
+| AddEvent              | 100-200   | 0-2 per span           | Low        |
+| Context injection     | 150-250   | Per outgoing message   | Low        |
+| Context extraction    | 100-180   | Per incoming message   | Low        |
+| GetCurrent context    | 10-20     | Thread-local access    | Negligible |
+
+**Source**: Span creation based on OTel C++ SDK `BM_SpanCreation` benchmark (AlwaysOnSampler +
+SimpleSpanProcessor + InMemoryExporter), median ~1,000 ns on CI hardware. AddEvent includes
+timestamp read + string copy + vector push + mutex acquisition. Context injection/extraction
+confirmed by `BM_SpanCreationWithScope` benchmark delta (~160 ns).
+
+### 3.4.2 Transaction Processing Overhead
+
+<div align="center">
+
+```mermaid
+%%{init: {'pie': {'textPosition': 0.75}}}%%
+pie showData
+    "tx.receive (1400ns)" : 1400
+    "tx.validate (1200ns)" : 1200
+    "tx.relay (1200ns)" : 1200
+    "Context inject (200ns)" : 200
+```
+
+**Transaction Tracing Overhead (~4.0μs total)**
+
+</div>
+
+**Overhead percentage**: 4.0 μs / 200 μs (avg tx processing) = **~2.0%**
+
+> **Breakdown**: Each span (tx.receive, tx.validate, tx.relay) costs ~1,000 ns for creation plus
+> ~200-400 ns for 3-5 attribute sets. Context injection is ~200 ns (confirmed by benchmarks).
+> On production hardware, expect ~2.6 μs total (~1.3% overhead) due to faster span creation (~500-600 ns).
+
+### 3.4.3 Consensus Round Overhead
+
+| Operation              | Count | Cost (ns) | Total      |
+| ---------------------- | ----- | --------- | ---------- |
+| consensus.round span   | 1     | ~1200     | ~1.2 μs    |
+| consensus.phase spans  | 3     | ~1100     | ~3.3 μs    |
+| proposal.receive spans | ~20   | ~1100     | ~22 μs     |
+| proposal.send spans    | ~3    | ~1100     | ~3.3 μs    |
+| Context operations     | ~30   | ~200      | ~6 μs      |
+| **TOTAL**              |       |           | **~36 μs** |
+
+> **Why higher**: Each span costs ~1,000 ns creation + ~100-200 ns for 1-2 attributes, totaling ~1,100-1,200 ns.
+> Context operations remain ~200 ns (confirmed by benchmarks). On production hardware, expect ~24 μs total.
+
+**Overhead percentage**: 36 μs / 3s (typical round) = **~0.001%** (negligible)
+
+### 3.4.4 RPC Request Overhead
+
+| Operation        | Cost (ns)    |
+| ---------------- | ------------ |
+| rpc.request span | ~1200        |
+| rpc.command span | ~1100        |
+| Context extract  | ~250         |
+| Context inject   | ~200         |
+| **TOTAL**        | **~2.75 μs** |
+
+> **Why higher**: Each span costs ~1,000 ns creation + ~100-200 ns for attributes (command name,
+> version, role). Context extract/inject costs are confirmed by OTel C++ benchmarks.
+
+- Fast RPC (1ms): 2.75 μs / 1ms = **~0.275%**
+- Slow RPC (100ms): 2.75 μs / 100ms = **~0.003%**
+
+---
+
+## 3.5 Memory Overhead Analysis
+
+> **OTLP** = OpenTelemetry Protocol
+
+### 3.5.1 Static Memory
+
+| Component                            | Size        | Allocated  |
+| ------------------------------------ | ----------- | ---------- |
+| TracerProvider singleton             | ~64 KB      | At startup |
+| BatchSpanProcessor (circular buffer) | ~16 KB      | At startup |
+| BatchSpanProcessor (worker thread)   | ~8 MB       | At startup |
+| OTLP exporter (gRPC channel init)    | ~256 KB     | At startup |
+| Propagator registry                  | ~8 KB       | At startup |
+| **Total static**                     | **~8.3 MB** |            |
+
+> **Why higher than earlier estimate**: The BatchSpanProcessor's circular buffer itself is only ~16 KB
+> (2049 x 8-byte `AtomicUniquePtr` entries), but it spawns a dedicated worker thread whose default
+> stack size on Linux is ~8 MB. The OTLP gRPC exporter allocates memory for channel stubs and TLS
+> initialization. The worker thread stack dominates the static footprint.
+
+### 3.5.2 Dynamic Memory
+
+| Component            | Size per unit  | Max units  | Peak            |
+| -------------------- | -------------- | ---------- | --------------- |
+| Active span          | ~500-800 bytes | 1000       | ~500-800 KB     |
+| Queued span (export) | ~500 bytes     | 2048       | ~1 MB           |
+| Attribute storage    | ~80 bytes      | 5 per span | Included        |
+| Context storage      | ~64 bytes      | Per thread | ~6.4 KB         |
+| **Total dynamic**    |                |            | **~1.5-1.8 MB** |
+
+> **Why active spans are larger**: An active `Span` object includes the wrapper (~88 bytes: shared_ptr,
+> mutex, unique_ptr to Recordable) plus `SpanData` (~250 bytes: SpanContext, timestamps, name, status,
+> empty containers) plus attribute storage (~200-500 bytes for 3-5 string attributes in a `std::map`).
+> Source: `sdk/src/trace/span.h` and `sdk/include/opentelemetry/sdk/trace/span_data.h`.
+> Queued spans release the wrapper, keeping only `SpanData` + attributes (~500 bytes).
+
+### 3.5.3 Memory Growth Characteristics
+
+```mermaid
+---
+config:
+    xyChart:
+        width: 700
+        height: 400
+---
+xychart-beta
+    title "Memory Usage vs Span Rate (bounded by queue limit)"
+    x-axis "Spans/second" [0, 200, 400, 600, 800, 1000]
+    y-axis "Memory (MB)" 0 --> 12
+    line [8.5, 9.2, 9.6, 9.9, 10.0, 10.0]
+```
+
+**Notes**:
+
+- Memory increases with span rate but **plateaus at queue capacity** (default 2048 spans)
+- Batch export prevents unbounded growth
+- At queue limit, oldest spans are dropped (not blocked)
+- Maximum memory is bounded: ~8.3 MB static (dominated by worker thread stack) + 2048 queued spans x ~500 bytes (~1 MB) + active spans (~0.8 MB) ≈ **~10 MB ceiling**
+- The worker thread stack (~8 MB) is virtual memory; actual RSS depends on stack usage (typically much less)
+
+### 3.5.4 Performance Data Sources
+
+The overhead estimates in Sections 3.3-3.5 are derived from the following sources:
+
+| Source                                           | What it covers                                        | URL                                                                                                                                        |
+| ------------------------------------------------ | ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| OTel C++ SDK CI benchmarks (969 runs)            | Span creation, context activation, sampler overhead   | [Benchmark Dashboard](https://open-telemetry.github.io/opentelemetry-cpp/benchmarks/)                                                      |
+| `api/test/trace/span_benchmark.cc`               | API-level span creation (~22 ns no-op)                | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/api/test/trace/span_benchmark.cc)                                   |
+| `sdk/test/trace/sampler_benchmark.cc`            | SDK span creation with samplers (~1,000 ns AlwaysOn)  | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/test/trace/sampler_benchmark.cc)                                |
+| `sdk/include/.../span_data.h`                    | SpanData memory layout (~250 bytes base)              | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/include/opentelemetry/sdk/trace/span_data.h)                    |
+| `sdk/src/trace/span.h`                           | Span wrapper memory layout (~88 bytes)                | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/src/trace/span.h)                                               |
+| `sdk/include/.../batch_span_processor_options.h` | Default queue size (2048), batch size (512)           | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/include/opentelemetry/sdk/trace/batch_span_processor_options.h) |
+| `sdk/include/.../circular_buffer.h`              | CircularBuffer implementation (AtomicUniquePtr array) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/include/opentelemetry/sdk/common/circular_buffer.h)             |
+| OTLP proto definition                            | Serialized span size estimation                       | [Proto](https://github.com/open-telemetry/opentelemetry-proto/blob/main/opentelemetry/proto/trace/v1/trace.proto)                          |
+
+---
+
+## 3.6 Network Overhead Analysis
+
+### 3.6.1 Export Bandwidth
+
+> **Bytes per span**: Estimates use ~500 bytes/span (conservative upper bound). OTLP protobuf analysis
+> shows a typical span with 3-5 string attributes serializes to ~200-300 bytes raw; with gzip
+> compression (~60-70% of raw) and batching (amortized headers), ~350 bytes/span is more realistic.
+> The table uses the conservative estimate for capacity planning.
+
+| Sampling Rate | Spans/sec | Bandwidth | Notes            |
+| ------------- | --------- | --------- | ---------------- |
+| 100%          | ~500      | ~250 KB/s | Development only |
+| 10%           | ~50       | ~25 KB/s  | Staging          |
+| 1%            | ~5        | ~2.5 KB/s | Production       |
+| Error-only    | ~1        | ~0.5 KB/s | Minimal overhead |
+
+### 3.6.2 Trace Context Propagation
+
+| Message Type           | Context Size | Messages/sec | Overhead    |
+| ---------------------- | ------------ | ------------ | ----------- |
+| TMTransaction          | 25 bytes     | ~100         | ~2.5 KB/s   |
+| TMProposeSet           | 25 bytes     | ~10          | ~250 B/s    |
+| TMValidation           | 25 bytes     | ~50          | ~1.25 KB/s  |
+| **Total P2P overhead** |              |              | **~4 KB/s** |
+
+---
+
+## 3.7 Optimization Strategies
+
+### 3.7.1 Sampling Strategies
+
+#### Tail Sampling
+
+```mermaid
+flowchart TD
+    trace["New Trace"]
+
+    trace --> errors{"Is Error?"}
+    errors -->|Yes| sample["SAMPLE"]
+    errors -->|No| consensus{"Is Consensus?"}
+
+    consensus -->|Yes| sample
+    consensus -->|No| slow{"Is Slow?"}
+
+    slow -->|Yes| sample
+    slow -->|No| prob{"Random < 10%?"}
+
+    prob -->|Yes| sample
+    prob -->|No| drop["DROP"]
+
+    style sample fill:#4caf50,stroke:#388e3c,color:#fff
+    style drop fill:#f44336,stroke:#c62828,color:#fff
+```
+
+### 3.7.2 Batch Tuning Recommendations
+
+| Environment        | Batch Size | Batch Delay | Max Queue |
+| ------------------ | ---------- | ----------- | --------- |
+| Low-latency        | 128        | 1000ms      | 512       |
+| High-throughput    | 1024       | 10000ms     | 8192      |
+| Memory-constrained | 256        | 2000ms      | 512       |
+
+### 3.7.3 Conditional Instrumentation
+
+```cpp
+// Compile-time feature flag
+#ifndef XRPL_ENABLE_TELEMETRY
+// Zero-cost when disabled
+#define XRPL_TRACE_SPAN(t, n) ((void)0)
+#endif
+
+// Runtime component filtering
+if (telemetry.shouldTracePeer())
+{
+    XRPL_TRACE_SPAN(telemetry, "peer.message.receive");
+    // ... instrumentation
+}
+// No overhead when component tracing disabled
+```
+
+---
+
+## 3.8 Links to Detailed Documentation
+
+- **[Code Samples](./04-code-samples.md)**: Complete implementation code for all components
+- **[Configuration Reference](./05-configuration-reference.md)**: Configuration options and collector setup
+- **[Implementation Phases](./06-implementation-phases.md)**: Detailed timeline and milestones
+
+---
+
+## 3.9 Code Intrusiveness Assessment
+
+> **TxQ** = Transaction Queue
+
+This section provides a detailed assessment of how intrusive the OpenTelemetry integration is to the existing rippled codebase.
+
+### 3.9.1 Files Modified Summary
+
+| Component             | Files Modified | Lines Added | Lines Changed | Architectural Impact |
+| --------------------- | -------------- | ----------- | ------------- | -------------------- |
+| **Core Telemetry**    | 5 new files    | ~800        | 0             | None (new module)    |
+| **Application Init**  | 2 files        | ~30         | ~5            | Minimal              |
+| **RPC Layer**         | 3 files        | ~80         | ~20           | Minimal              |
+| **Transaction Relay** | 4 files        | ~120        | ~40           | Low                  |
+| **Consensus**         | 3 files        | ~100        | ~30           | Low-Medium           |
+| **Protocol Buffers**  | 1 file         | ~25         | 0             | Low                  |
+| **CMake/Build**       | 3 files        | ~50         | ~10           | Minimal              |
+| **PathFinding**       | 2              | ~80         | ~5            | Minimal              |
+| **TxQ/Fee**           | 2              | ~60         | ~5            | Minimal              |
+| **Validator/Amend**   | 3              | ~40         | ~5            | Minimal              |
+| **Total**             | **~28 files**  | **~1,490**  | **~120**      | **Low**              |
+
+### 3.9.2 Detailed File Impact
+
+```mermaid
+pie title Code Changes by Component
+    "New Telemetry Module" : 800
+    "Transaction Relay" : 160
+    "Consensus" : 130
+    "RPC Layer" : 100
+    "PathFinding" : 80
+    "TxQ/Fee" : 60
+    "Validator/Amendment" : 40
+    "Application Init" : 35
+    "Protocol Buffers" : 25
+    "Build System" : 60
+```
+
+#### New Files (No Impact on Existing Code)
+
+| File                                           | Lines | Purpose              |
+| ---------------------------------------------- | ----- | -------------------- |
+| `include/xrpl/telemetry/Telemetry.h`           | ~160  | Main interface       |
+| `include/xrpl/telemetry/SpanGuard.h`           | ~120  | RAII wrapper         |
+| `include/xrpl/telemetry/TraceContext.h`        | ~80   | Context propagation  |
+| `src/xrpld/telemetry/TracingInstrumentation.h` | ~60   | Macros               |
+| `src/libxrpl/telemetry/Telemetry.cpp`          | ~200  | Implementation       |
+| `src/libxrpl/telemetry/TelemetryConfig.cpp`    | ~60   | Config parsing       |
+| `src/libxrpl/telemetry/NullTelemetry.cpp`      | ~40   | No-op implementation |
+
+#### Modified Files (Existing Rippled Code)
+
+| File                                              | Lines Added | Lines Changed | Risk Level |
+| ------------------------------------------------- | ----------- | ------------- | ---------- |
+| `src/xrpld/app/main/Application.cpp`              | ~15         | ~3            | Low        |
+| `include/xrpl/app/main/Application.h`             | ~5          | ~2            | Low        |
+| `src/xrpld/rpc/detail/ServerHandler.cpp`          | ~40         | ~10           | Low        |
+| `src/xrpld/rpc/handlers/*.cpp`                    | ~30         | ~8            | Low        |
+| `src/xrpld/overlay/detail/PeerImp.cpp`            | ~60         | ~15           | Medium     |
+| `src/xrpld/overlay/detail/OverlayImpl.cpp`        | ~30         | ~10           | Medium     |
+| `src/xrpld/app/consensus/RCLConsensus.cpp`        | ~50         | ~15           | Medium     |
+| `src/xrpld/app/consensus/RCLConsensusAdaptor.cpp` | ~40         | ~12           | Medium     |
+| `src/xrpld/core/JobQueue.cpp`                     | ~20         | ~5            | Low        |
+| `src/xrpld/app/paths/PathRequest.cpp`             | ~40         | ~3            | Low        |
+| `src/xrpld/app/paths/Pathfinder.cpp`              | ~40         | ~2            | Low        |
+| `src/xrpld/app/misc/TxQ.cpp`                      | ~40         | ~3            | Low        |
+| `src/xrpld/app/main/LoadManager.cpp`              | ~20         | ~2            | Low        |
+| `src/xrpld/app/misc/ValidatorList.cpp`            | ~20         | ~2            | Low        |
+| `src/xrpld/app/misc/AmendmentTable.cpp`           | ~10         | ~2            | Low        |
+| `src/xrpld/app/misc/Manifest.cpp`                 | ~10         | ~1            | Low        |
+| `src/xrpld/shamap/SHAMap.cpp`                     | ~20         | ~3            | Low        |
+| `src/xrpld/overlay/detail/ripple.proto`           | ~25         | 0             | Low        |
+| `CMakeLists.txt`                                  | ~40         | ~8            | Low        |
+| `cmake/FindOpenTelemetry.cmake`                   | ~50         | 0             | None (new) |
+
+### 3.9.3 Risk Assessment by Component
+
+<div align="center">
+
+**Do First** ↖ ↗ **Plan Carefully**
+
+```mermaid
+quadrantChart
+    title Code Intrusiveness Risk Matrix
+    x-axis Low Risk --> High Risk
+    y-axis Low Value --> High Value
+
+    RPC Tracing: [0.2, 0.55]
+    Transaction Relay: [0.55, 0.85]
+    Consensus Tracing: [0.75, 0.92]
+    Peer Message Tracing: [0.85, 0.35]
+    JobQueue Context: [0.3, 0.42]
+    Ledger Acquisition: [0.48, 0.65]
+    PathFinding: [0.38, 0.72]
+    TxQ and Fees: [0.25, 0.62]
+    Validator Mgmt: [0.15, 0.35]
+```
+
+**Optional** ↙ ↘ **Avoid**
+
+</div>
+
+#### Risk Level Definitions
+
+| Risk Level | Definition                                                       | Mitigation                         |
+| ---------- | ---------------------------------------------------------------- | ---------------------------------- |
+| **Low**    | Additive changes only; no modification to existing logic         | Standard code review               |
+| **Medium** | Minor modifications to existing functions; clear boundaries      | Comprehensive unit tests           |
+| **High**   | Changes to core logic or data structures; potential side effects | Integration tests + staged rollout |
+
+### 3.9.4 Architectural Impact Assessment
+
+| Aspect               | Impact  | Justification                                                                    |
+| -------------------- | ------- | -------------------------------------------------------------------------------- |
+| **Data Flow**        | Minimal | Read-only instrumentation; no modification to consensus or transaction data flow |
+| **Threading Model**  | Minimal | Context propagation uses thread-local storage (standard OTel pattern)            |
+| **Memory Model**     | Low     | Bounded queues prevent unbounded growth; RAII ensures cleanup                    |
+| **Network Protocol** | Low     | Optional fields in protobuf (high field numbers); backward compatible            |
+| **Configuration**    | None    | New config section; existing configs unaffected                                  |
+| **Build System**     | Low     | Optional CMake flag; builds work without OpenTelemetry                           |
+| **Dependencies**     | Low     | OpenTelemetry SDK is optional; null implementation when disabled                 |
+
+### 3.9.5 Backward Compatibility
+
+| Compatibility   | Status  | Notes                                                 |
+| --------------- | ------- | ----------------------------------------------------- |
+| **Config File** | ✅ Full | New `[telemetry]` section is optional                 |
+| **Protocol**    | ✅ Full | Optional protobuf fields with high field numbers      |
+| **Build**       | ✅ Full | `XRPL_ENABLE_TELEMETRY=OFF` produces identical binary |
+| **Runtime**     | ✅ Full | `enabled=0` produces zero overhead                    |
+| **API**         | ✅ Full | No changes to public RPC or P2P APIs                  |
+
+### 3.9.6 Rollback Strategy
+
+If issues are discovered after deployment:
+
+1. **Immediate**: Set `enabled=0` in config and restart (zero code change)
+2. **Quick**: Rebuild with `XRPL_ENABLE_TELEMETRY=OFF`
+3. **Complete**: Revert telemetry commits (clean separation makes this easy)
+
+### 3.9.7 Code Change Examples
+
+**Minimal RPC Instrumentation (Low Intrusiveness):**
+
+```cpp
+// Before
+void ServerHandler::onRequest(...) {
+    auto result = processRequest(req);
+    send(result);
+}
+
+// After (only ~10 lines added)
+void ServerHandler::onRequest(...) {
+    XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.request");  // +1 line
+    XRPL_TRACE_SET_ATTR("xrpl.rpc.command", command);     // +1 line
+
+    auto result = processRequest(req);
+
+    XRPL_TRACE_SET_ATTR("xrpl.rpc.status", status);       // +1 line
+    send(result);
+}
+```
+
+**Consensus Instrumentation (Medium Intrusiveness):**
+
+```cpp
+// Before
+void RCLConsensusAdaptor::startRound(...) {
+    // ... existing logic
+}
+
+// After (context storage required)
+void RCLConsensusAdaptor::startRound(...) {
+    XRPL_TRACE_CONSENSUS(app_.getTelemetry(), "consensus.round");
+    XRPL_TRACE_SET_ATTR("xrpl.consensus.ledger.seq", seq);
+
+    // Store context for child spans in phase transitions
+    currentRoundContext_ = _xrpl_guard_->context();  // New member variable
+
+    // ... existing logic unchanged
+}
+```
+
+---
+
+_Previous: [Design Decisions](./02-design-decisions.md)_ | _Next: [Code Samples](./04-code-samples.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/05-configuration-reference.md

@@ -0,0 +1,976 @@
+# Configuration Reference
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Code Samples](./04-code-samples.md) | [Implementation Phases](./06-implementation-phases.md)
+
+---
+
+## 5.1 rippled Configuration
+
+> **OTLP** = OpenTelemetry Protocol | **TxQ** = Transaction Queue
+
+### 5.1.1 Configuration File Section
+
+Add to `cfg/xrpld-example.cfg`:
+
+```ini
+# ═══════════════════════════════════════════════════════════════════════════════
+# TELEMETRY (OpenTelemetry Distributed Tracing)
+# ═══════════════════════════════════════════════════════════════════════════════
+#
+# Enables distributed tracing for transaction flow, consensus, and RPC calls.
+# Traces are exported to an OpenTelemetry Collector using OTLP protocol.
+#
+# [telemetry]
+#
+# # Enable/disable telemetry (default: 0 = disabled)
+# enabled=1
+#
+# # Exporter type: "otlp_grpc" (default), "otlp_http", or "none"
+# exporter=otlp_grpc
+#
+# # OTLP endpoint (default: localhost:4317 for gRPC, localhost:4318 for HTTP)
+# endpoint=localhost:4317
+#
+# # Use TLS for exporter connection (default: 0)
+# use_tls=0
+#
+# # Path to CA certificate for TLS (optional)
+# # tls_ca_cert=/path/to/ca.crt
+#
+# # Sampling ratio: 0.0-1.0 (default: 1.0 = 100% sampling)
+# # Use lower values in production to reduce overhead
+# # Default: 1.0 (all traces). For production deployments with high
+# # throughput, 0.1 (10%) is recommended to reduce overhead.
+# # See Section 7.4.2 for sampling strategy details.
+# sampling_ratio=0.1
+#
+# # Batch processor settings
+# batch_size=512           # Spans per batch (default: 512)
+# batch_delay_ms=5000      # Max delay before sending batch (default: 5000)
+# max_queue_size=2048      # Max queued spans (default: 2048)
+#
+# # Component-specific tracing (default: all enabled except peer)
+# trace_transactions=1     # Transaction relay and processing
+# trace_consensus=1        # Consensus rounds and proposals
+# trace_rpc=1              # RPC request handling
+# trace_peer=0             # Peer messages (high volume, disabled by default)
+# trace_ledger=1           # Ledger acquisition and building
+# trace_pathfind=1         # Path computation (can be expensive)
+# trace_txq=1              # Transaction queue and fee escalation
+# trace_validator=0        # Validator list and manifest updates (low volume)
+# trace_amendment=0        # Amendment voting (very low volume)
+#
+# # Service identification (automatically detected if not specified)
+# # service_name=rippled
+# # service_instance_id=<node_public_key>
+
+[telemetry]
+enabled=0
+```
+
+### 5.1.2 Configuration Options Summary
+
+| Option                | Type   | Default          | Description                               |
+| --------------------- | ------ | ---------------- | ----------------------------------------- |
+| `enabled`             | bool   | `false`          | Enable/disable telemetry                  |
+| `exporter`            | string | `"otlp_grpc"`    | Exporter type: otlp_grpc, otlp_http, none |
+| `endpoint`            | string | `localhost:4317` | OTLP collector endpoint                   |
+| `use_tls`             | bool   | `false`          | Enable TLS for exporter connection        |
+| `tls_ca_cert`         | string | `""`             | Path to CA certificate file               |
+| `sampling_ratio`      | float  | `1.0`            | Sampling ratio (0.0-1.0)                  |
+| `batch_size`          | uint   | `512`            | Spans per export batch                    |
+| `batch_delay_ms`      | uint   | `5000`           | Max delay before sending batch (ms)       |
+| `max_queue_size`      | uint   | `2048`           | Maximum queued spans                      |
+| `trace_transactions`  | bool   | `true`           | Enable transaction tracing                |
+| `trace_consensus`     | bool   | `true`           | Enable consensus tracing                  |
+| `trace_rpc`           | bool   | `true`           | Enable RPC tracing                        |
+| `trace_peer`          | bool   | `false`          | Enable peer message tracing (high volume) |
+| `trace_ledger`        | bool   | `true`           | Enable ledger tracing                     |
+| `trace_pathfind`      | bool   | `true`           | Enable path computation tracing           |
+| `trace_txq`           | bool   | `true`           | Enable transaction queue tracing          |
+| `trace_validator`     | bool   | `false`          | Enable validator list/manifest tracing    |
+| `trace_amendment`     | bool   | `false`          | Enable amendment voting tracing           |
+| `service_name`        | string | `"rippled"`      | Service name for traces                   |
+| `service_instance_id` | string | `<node_pubkey>`  | Instance identifier                       |
+
+---
+
+## 5.2 Configuration Parser
+
+> **TxQ** = Transaction Queue
+
+```cpp
+// src/libxrpl/telemetry/TelemetryConfig.cpp
+
+#include <xrpl/telemetry/Telemetry.h>
+#include <xrpl/basics/Log.h>
+
+namespace xrpl {
+namespace telemetry {
+
+Telemetry::Setup
+setup_Telemetry(
+    Section const& section,
+    std::string const& nodePublicKey,
+    std::string const& version)
+{
+    Telemetry::Setup setup;
+
+    // Basic settings
+    setup.enabled = section.value_or("enabled", false);
+    setup.serviceName = section.value_or("service_name", "rippled");
+    setup.serviceVersion = version;
+    setup.serviceInstanceId = section.value_or(
+        "service_instance_id", nodePublicKey);
+
+    // Exporter settings
+    setup.exporterType = section.value_or("exporter", "otlp_grpc");
+
+    if (setup.exporterType == "otlp_grpc")
+        setup.exporterEndpoint = section.value_or("endpoint", "localhost:4317");
+    else if (setup.exporterType == "otlp_http")
+        setup.exporterEndpoint = section.value_or("endpoint", "localhost:4318");
+
+    setup.useTls = section.value_or("use_tls", false);
+    setup.tlsCertPath = section.value_or("tls_ca_cert", "");
+
+    // Sampling
+    setup.samplingRatio = section.value_or("sampling_ratio", 1.0);
+    if (setup.samplingRatio < 0.0 || setup.samplingRatio > 1.0)
+    {
+        Throw<std::runtime_error>(
+            "telemetry.sampling_ratio must be between 0.0 and 1.0");
+    }
+
+    // Batch processor
+    setup.batchSize = section.value_or("batch_size", 512u);
+    setup.batchDelay = std::chrono::milliseconds{
+        section.value_or("batch_delay_ms", 5000u)};
+    setup.maxQueueSize = section.value_or("max_queue_size", 2048u);
+
+    // Component filtering
+    setup.traceTransactions = section.value_or("trace_transactions", true);
+    setup.traceConsensus = section.value_or("trace_consensus", true);
+    setup.traceRpc = section.value_or("trace_rpc", true);
+    setup.tracePeer = section.value_or("trace_peer", false);
+    setup.traceLedger = section.value_or("trace_ledger", true);
+    setup.tracePathfind = section.value_or("trace_pathfind", true);
+    setup.traceTxQ = section.value_or("trace_txq", true);
+    setup.traceValidator = section.value_or("trace_validator", false);
+    setup.traceAmendment = section.value_or("trace_amendment", false);
+
+    return setup;
+}
+
+} // namespace telemetry
+} // namespace xrpl
+```
+
+---
+
+## 5.3 Application Integration
+
+### 5.3.1 ApplicationImp Changes
+
+```cpp
+// src/xrpld/app/main/Application.cpp (modified)
+
+#include <xrpl/telemetry/Telemetry.h>
+
+class ApplicationImp : public Application
+{
+    // ... existing members ...
+
+    // Telemetry (must be constructed early, destroyed late)
+    std::unique_ptr<telemetry::Telemetry> telemetry_;
+
+public:
+    ApplicationImp(...)
+    {
+        // Initialize telemetry early (before other components)
+        auto telemetrySection = config_->section("telemetry");
+        auto telemetrySetup = telemetry::setup_Telemetry(
+            telemetrySection,
+            toBase58(TokenType::NodePublic, nodeIdentity_.publicKey()),
+            BuildInfo::getVersionString());
+
+        // Set network attributes
+        telemetrySetup.networkId = config_->NETWORK_ID;
+        telemetrySetup.networkType = [&]() {
+            if (config_->NETWORK_ID == 0) return "mainnet";
+            if (config_->NETWORK_ID == 1) return "testnet";
+            if (config_->NETWORK_ID == 2) return "devnet";
+            return "custom";
+        }();
+
+        telemetry_ = telemetry::make_Telemetry(
+            telemetrySetup,
+            logs_->journal("Telemetry"));
+
+        // ... rest of initialization ...
+    }
+
+    void start() override
+    {
+        // Start telemetry first
+        if (telemetry_)
+            telemetry_->start();
+
+        // ... existing start code ...
+    }
+
+    void stop() override
+    {
+        // ... existing stop code ...
+
+        // Stop telemetry last (to capture shutdown spans)
+        if (telemetry_)
+            telemetry_->stop();
+    }
+
+    telemetry::Telemetry& getTelemetry() override
+    {
+        assert(telemetry_);
+        return *telemetry_;
+    }
+};
+```
+
+### 5.3.2 Application Interface Addition
+
+```cpp
+// include/xrpl/app/main/Application.h (modified)
+
+namespace telemetry { class Telemetry; }
+
+class Application
+{
+public:
+    // ... existing virtual methods ...
+
+    /** Get the telemetry system for distributed tracing */
+    virtual telemetry::Telemetry& getTelemetry() = 0;
+};
+```
+
+---
+
+## 5.4 CMake Integration
+
+> **OTLP** = OpenTelemetry Protocol
+
+### 5.4.1 Find OpenTelemetry Module
+
+```cmake
+# cmake/FindOpenTelemetry.cmake
+
+# Find OpenTelemetry C++ SDK
+#
+# This module defines:
+#   OpenTelemetry_FOUND - System has OpenTelemetry
+#   OpenTelemetry::api - API library target
+#   OpenTelemetry::sdk - SDK library target
+#   OpenTelemetry::otlp_grpc_exporter - OTLP gRPC exporter target
+#   OpenTelemetry::otlp_http_exporter - OTLP HTTP exporter target
+
+find_package(opentelemetry-cpp CONFIG QUIET)
+
+if(opentelemetry-cpp_FOUND)
+    set(OpenTelemetry_FOUND TRUE)
+
+    # Create imported targets if not already created by config
+    if(NOT TARGET OpenTelemetry::api)
+        add_library(OpenTelemetry::api ALIAS opentelemetry-cpp::api)
+    endif()
+    if(NOT TARGET OpenTelemetry::sdk)
+        add_library(OpenTelemetry::sdk ALIAS opentelemetry-cpp::sdk)
+    endif()
+    if(NOT TARGET OpenTelemetry::otlp_grpc_exporter)
+        add_library(OpenTelemetry::otlp_grpc_exporter ALIAS
+            opentelemetry-cpp::otlp_grpc_exporter)
+    endif()
+else()
+    # Try pkg-config fallback
+    find_package(PkgConfig QUIET)
+    if(PKG_CONFIG_FOUND)
+        pkg_check_modules(OTEL opentelemetry-cpp QUIET)
+        if(OTEL_FOUND)
+            set(OpenTelemetry_FOUND TRUE)
+            # Create imported targets from pkg-config
+            add_library(OpenTelemetry::api INTERFACE IMPORTED)
+            target_include_directories(OpenTelemetry::api INTERFACE
+                ${OTEL_INCLUDE_DIRS})
+        endif()
+    endif()
+endif()
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(OpenTelemetry
+    REQUIRED_VARS OpenTelemetry_FOUND)
+```
+
+### 5.4.2 CMakeLists.txt Changes
+
+```cmake
+# CMakeLists.txt (additions)
+
+# ═══════════════════════════════════════════════════════════════════════════════
+# TELEMETRY OPTIONS
+# ═══════════════════════════════════════════════════════════════════════════════
+
+option(XRPL_ENABLE_TELEMETRY
+    "Enable OpenTelemetry distributed tracing support" OFF)
+
+if(XRPL_ENABLE_TELEMETRY)
+    find_package(OpenTelemetry REQUIRED)
+
+    # Define compile-time flag
+    add_compile_definitions(XRPL_ENABLE_TELEMETRY)
+
+    message(STATUS "OpenTelemetry tracing: ENABLED")
+else()
+    message(STATUS "OpenTelemetry tracing: DISABLED")
+endif()
+
+# ═══════════════════════════════════════════════════════════════════════════════
+# TELEMETRY LIBRARY
+# ═══════════════════════════════════════════════════════════════════════════════
+
+if(XRPL_ENABLE_TELEMETRY)
+    add_library(xrpl_telemetry
+        src/libxrpl/telemetry/Telemetry.cpp
+        src/libxrpl/telemetry/TelemetryConfig.cpp
+        src/libxrpl/telemetry/TraceContext.cpp
+    )
+
+    target_include_directories(xrpl_telemetry
+        PUBLIC
+            ${CMAKE_CURRENT_SOURCE_DIR}/include
+    )
+
+    target_link_libraries(xrpl_telemetry
+        PUBLIC
+            OpenTelemetry::api
+            OpenTelemetry::sdk
+            OpenTelemetry::otlp_grpc_exporter
+        PRIVATE
+            xrpl_basics
+    )
+
+    # Add to main library dependencies
+    target_link_libraries(xrpld PRIVATE xrpl_telemetry)
+else()
+    # Create null implementation library
+    add_library(xrpl_telemetry
+        src/libxrpl/telemetry/NullTelemetry.cpp
+    )
+    target_include_directories(xrpl_telemetry
+        PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include
+    )
+endif()
+```
+
+---
+
+## 5.5 OpenTelemetry Collector Configuration
+
+> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring
+
+### 5.5.1 Development Configuration
+
+```yaml
+# otel-collector-dev.yaml
+# Minimal configuration for local development
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 100
+
+exporters:
+  # Console output for debugging
+  logging:
+    verbosity: detailed
+    sampling_initial: 5
+    sampling_thereafter: 200
+
+  # Tempo for trace visualization
+  otlp/tempo:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+
+  # Grafana Tempo for trace storage
+  otlp/tempo:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [logging, jaeger, otlp/tempo]
+```
+
+### 5.5.2 Production Configuration
+
+```yaml
+# otel-collector-prod.yaml
+# Production configuration with filtering, sampling, and multiple backends
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+        tls:
+          cert_file: /etc/otel/server.crt
+          key_file: /etc/otel/server.key
+          ca_file: /etc/otel/ca.crt
+
+processors:
+  # Memory limiter to prevent OOM
+  memory_limiter:
+    check_interval: 1s
+    limit_mib: 1000
+    spike_limit_mib: 200
+
+  # Batch processing for efficiency
+  batch:
+    timeout: 5s
+    send_batch_size: 512
+    send_batch_max_size: 1024
+
+  # Tail-based sampling (keep errors and slow traces)
+  tail_sampling:
+    decision_wait: 10s
+    num_traces: 100000
+    expected_new_traces_per_sec: 1000
+    policies:
+      # Always keep error traces
+      - name: errors
+        type: status_code
+        status_code:
+          status_codes: [ERROR]
+      # Keep slow consensus rounds (>5s)
+      - name: slow-consensus
+        type: latency
+        latency:
+          threshold_ms: 5000
+      # Keep slow RPC requests (>1s)
+      - name: slow-rpc
+        type: and
+        and:
+          and_sub_policy:
+            - name: rpc-spans
+              type: string_attribute
+              string_attribute:
+                key: xrpl.rpc.command
+                values: [".*"]
+                enabled_regex_matching: true
+            - name: latency
+              type: latency
+              latency:
+                threshold_ms: 1000
+      # Probabilistic sampling for the rest
+      - name: probabilistic
+        type: probabilistic
+        probabilistic:
+          sampling_percentage: 10
+
+  # Attribute processing
+  attributes:
+    actions:
+      # Hash sensitive data
+      - key: xrpl.tx.account
+        action: hash
+      # Add deployment info
+      - key: deployment.environment
+        value: production
+        action: upsert
+
+exporters:
+  # Grafana Tempo for long-term storage
+  otlp/tempo:
+    endpoint: tempo.monitoring:4317
+    tls:
+      insecure: false
+      ca_file: /etc/otel/tempo-ca.crt
+
+  # Elastic APM for correlation with logs
+  otlp/elastic:
+    endpoint: apm.elastic:8200
+    headers:
+      Authorization: "Bearer ${ELASTIC_APM_TOKEN}"
+
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+  zpages:
+    endpoint: 0.0.0.0:55679
+
+service:
+  extensions: [health_check, zpages]
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [memory_limiter, tail_sampling, attributes, batch]
+      exporters: [otlp/tempo, otlp/elastic]
+```
+
+---
+
+## 5.6 Docker Compose Development Environment
+
+> **OTLP** = OpenTelemetry Protocol
+
+```yaml
+# docker-compose-telemetry.yaml
+version: "3.8"
+
+services:
+  # OpenTelemetry Collector
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:0.92.0
+    container_name: otel-collector
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    volumes:
+      - ./otel-collector-dev.yaml:/etc/otel-collector-config.yaml:ro
+    ports:
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP
+      - "13133:13133" # Health check
+    depends_on:
+      - tempo
+
+  # Tempo for trace visualization
+  tempo:
+    image: grafana/tempo:2.6.1
+    container_name: tempo
+    ports:
+      - "3200:3200" # Tempo HTTP API
+      - "4317" # OTLP gRPC (internal)
+
+  # Grafana Tempo for trace storage (recommended for production)
+  tempo:
+    image: grafana/tempo:2.7.2
+    container_name: tempo
+    command: ["-config.file=/etc/tempo.yaml"]
+    volumes:
+      - ./tempo.yaml:/etc/tempo.yaml:ro
+      - tempo-data:/var/tempo
+    ports:
+      - "3200:3200" # HTTP API
+
+  # Grafana for dashboards
+  grafana:
+    image: grafana/grafana:10.2.3
+    container_name: grafana
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+    ports:
+      - "3000:3000"
+    depends_on:
+      - jaeger
+      - tempo
+
+  # Prometheus for metrics (optional, for correlation)
+  prometheus:
+    image: prom/prometheus:v2.48.1
+    container_name: prometheus
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus/prometheus.yml:ro
+    ports:
+      - "9090:9090"
+
+networks:
+  default:
+    name: rippled-telemetry
+```
+
+---
+
+## 5.7 Configuration Architecture
+
+> **OTLP** = OpenTelemetry Protocol
+
+```mermaid
+flowchart TB
+    subgraph config["Configuration Sources"]
+        cfgFile["xrpld.cfg<br/>[telemetry] section"]
+        cmake["CMake<br/>XRPL_ENABLE_TELEMETRY"]
+    end
+
+    subgraph init["Initialization"]
+        parse["setup_Telemetry()"]
+        factory["make_Telemetry()"]
+    end
+
+    subgraph runtime["Runtime Components"]
+        tracer["TracerProvider"]
+        exporter["OTLP Exporter"]
+        processor["BatchProcessor"]
+    end
+
+    subgraph collector["Collector Pipeline"]
+        recv["Receivers"]
+        proc["Processors"]
+        exp["Exporters"]
+    end
+
+    cfgFile --> parse
+    cmake -->|"compile flag"| parse
+    parse --> factory
+    factory --> tracer
+    tracer --> processor
+    processor --> exporter
+    exporter -->|"OTLP"| recv
+    recv --> proc
+    proc --> exp
+
+    style config fill:#e3f2fd,stroke:#1976d2
+    style runtime fill:#e8f5e9,stroke:#388e3c
+    style collector fill:#fff3e0,stroke:#ff9800
+```
+
+**Reading the diagram:**
+
+- **Configuration Sources**: `xrpld.cfg` provides runtime settings (endpoint, sampling) while the CMake flag controls whether telemetry is compiled in at all.
+- **Initialization**: `setup_Telemetry()` parses config values, then `make_Telemetry()` constructs the provider, processor, and exporter objects.
+- **Runtime Components**: The `TracerProvider` creates spans, the `BatchProcessor` buffers them, and the `OTLP Exporter` serializes and sends them over the wire.
+- **OTLP arrow to Collector**: Trace data leaves the rippled process via OTLP (gRPC or HTTP) and enters the external Collector pipeline.
+- **Collector Pipeline**: `Receivers` ingest OTLP data, `Processors` apply sampling/filtering/enrichment, and `Exporters` forward traces to storage backends (Tempo, etc.).
+
+---
+
+## 5.8 Grafana Integration
+
+> **APM** = Application Performance Monitoring
+
+Step-by-step instructions for integrating rippled traces with Grafana.
+
+### 5.8.1 Data Source Configuration
+
+#### Tempo (Recommended)
+
+```yaml
+# grafana/provisioning/datasources/tempo.yaml
+apiVersion: 1
+
+datasources:
+  - name: Tempo
+    type: tempo
+    access: proxy
+    url: http://tempo:3200
+    jsonData:
+      httpMethod: GET
+      tracesToLogs:
+        datasourceUid: loki
+        tags: ["service.name", "xrpl.tx.hash"]
+        mappedTags: [{ key: "trace_id", value: "traceID" }]
+        mapTagNamesEnabled: true
+        filterByTraceID: true
+      serviceMap:
+        datasourceUid: prometheus
+      nodeGraph:
+        enabled: true
+      search:
+        hide: false
+      lokiSearch:
+        datasourceUid: loki
+```
+
+#### Elastic APM
+
+```yaml
+# grafana/provisioning/datasources/elastic-apm.yaml
+apiVersion: 1
+
+datasources:
+  - name: Elasticsearch-APM
+    type: elasticsearch
+    access: proxy
+    url: http://elasticsearch:9200
+    database: "apm-*"
+    jsonData:
+      esVersion: "8.0.0"
+      timeField: "@timestamp"
+      logMessageField: message
+      logLevelField: log.level
+```
+
+### 5.8.2 Dashboard Provisioning
+
+```yaml
+# grafana/provisioning/dashboards/dashboards.yaml
+apiVersion: 1
+
+providers:
+  - name: "rippled-dashboards"
+    orgId: 1
+    folder: "rippled"
+    folderUid: "rippled"
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 30
+    options:
+      path: /var/lib/grafana/dashboards/rippled
+```
+
+### 5.8.3 Example Dashboard: RPC Performance
+
+```json
+{
+  "title": "rippled RPC Performance",
+  "uid": "rippled-rpc-performance",
+  "panels": [
+    {
+      "title": "RPC Latency by Command",
+      "type": "heatmap",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && span.xrpl.rpc.command != \"\"} | histogram_over_time(duration) by (span.xrpl.rpc.command)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }
+    },
+    {
+      "title": "RPC Error Rate",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && status.code=error} | rate() by (span.xrpl.rpc.command)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }
+    },
+    {
+      "title": "Top 10 Slowest RPC Commands",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && span.xrpl.rpc.command != \"\"} | avg(duration) by (span.xrpl.rpc.command) | topk(10)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 8 }
+    },
+    {
+      "title": "Recent Traces",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\"}"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 16 }
+    }
+  ]
+}
+```
+
+### 5.8.4 Example Dashboard: Transaction Tracing
+
+```json
+{
+  "title": "rippled Transaction Tracing",
+  "uid": "rippled-tx-tracing",
+  "panels": [
+    {
+      "title": "Transaction Throughput",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.receive\"} | rate()"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Cross-Node Relay Count",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.relay\"} | avg(span.xrpl.tx.relay_count)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 }
+    },
+    {
+      "title": "Transaction Validation Errors",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.validate\" && status.code=error}"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 }
+    }
+  ]
+}
+```
+
+### 5.8.5 TraceQL Query Examples
+
+Common queries for rippled traces:
+
+```
+# Find all traces for a specific transaction hash
+{resource.service.name="rippled" && span.xrpl.tx.hash="ABC123..."}
+
+# Find slow RPC commands (>100ms)
+{resource.service.name="rippled" && name=~"rpc.command.*"} | duration > 100ms
+
+# Find consensus rounds taking >5 seconds
+{resource.service.name="rippled" && name="consensus.round"} | duration > 5s
+
+# Find failed transactions with error details
+{resource.service.name="rippled" && name="tx.validate" && status.code=error}
+
+# Find transactions relayed to many peers
+{resource.service.name="rippled" && name="tx.relay"} | span.xrpl.tx.relay_count > 10
+
+# Compare latency across nodes
+{resource.service.name="rippled" && name="rpc.command.account_info"} | avg(duration) by (resource.service.instance.id)
+```
+
+### 5.8.6 Correlation with PerfLog
+
+To correlate OpenTelemetry traces with existing PerfLog data:
+
+**Step 1: Configure Loki to ingest PerfLog**
+
+```yaml
+# promtail-config.yaml
+scrape_configs:
+  - job_name: rippled-perflog
+    static_configs:
+      - targets:
+          - localhost
+        labels:
+          job: rippled
+          __path__: /var/log/rippled/perf*.log
+    pipeline_stages:
+      - json:
+          expressions:
+            trace_id: trace_id
+            ledger_seq: ledger_seq
+            tx_hash: tx_hash
+      - labels:
+          trace_id:
+          ledger_seq:
+          tx_hash:
+```
+
+**Step 2: Add trace_id to PerfLog entries**
+
+Modify PerfLog to include trace_id when available:
+
+```cpp
+// In PerfLog output, add trace_id from current span context
+void logPerf(Json::Value& entry) {
+    auto span = opentelemetry::trace::GetSpan(
+        opentelemetry::context::RuntimeContext::GetCurrent());
+    if (span && span->GetContext().IsValid()) {
+        char traceIdHex[33];
+        span->GetContext().trace_id().ToLowerBase16(traceIdHex);
+        entry["trace_id"] = std::string(traceIdHex, 32);
+    }
+    // ... existing logging
+}
+```
+
+**Step 3: Configure Grafana trace-to-logs link**
+
+In Tempo data source configuration, set up the derived field:
+
+```yaml
+jsonData:
+  tracesToLogs:
+    datasourceUid: loki
+    tags: ["trace_id", "xrpl.tx.hash"]
+    filterByTraceID: true
+    filterBySpanID: false
+```
+
+### 5.8.7 Correlation with Insight/OTel System Metrics
+
+To correlate traces with Beast Insight system metrics:
+
+**Step 1: Export Insight metrics to Prometheus**
+
+Beast Insight metrics are exported natively via OTLP to the OTel Collector,
+which exposes them on the Prometheus endpoint alongside spanmetrics. No
+separate StatsD exporter is needed when using `server=otel`.
+
+```ini
+# xrpld.cfg — native OTel metrics (recommended)
+[insight]
+server=otel
+endpoint=http://localhost:4318/v1/metrics
+prefix=rippled
+```
+
+**Step 2: Add exemplars to metrics**
+
+OpenTelemetry SDK automatically adds exemplars (trace IDs) to metrics when using the Prometheus exporter. This links metrics spikes to specific traces.
+
+**Step 3: Configure Grafana metric-to-trace link**
+
+```yaml
+# In Prometheus data source
+jsonData:
+  exemplarTraceIdDestinations:
+    - name: trace_id
+      datasourceUid: tempo
+```
+
+**Step 4: Dashboard panel with exemplars**
+
+```json
+{
+  "title": "RPC Latency with Trace Links",
+  "type": "timeseries",
+  "datasource": "Prometheus",
+  "targets": [
+    {
+      "expr": "histogram_quantile(0.99, rate(rippled_rpc_duration_seconds_bucket[5m]))",
+      "exemplar": true
+    }
+  ]
+}
+```
+
+This allows clicking on metric data points to jump directly to the related trace.
+
+---
+
+_Previous: [Code Samples](./04-code-samples.md)_ | _Next: [Implementation Phases](./06-implementation-phases.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/06-implementation-phases.md

@@ -0,0 +1,913 @@
+# Implementation Phases
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Configuration Reference](./05-configuration-reference.md) | [Observability Backends](./07-observability-backends.md)
+
+---
+
+## 6.1 Phase Overview
+
+> **TxQ** = Transaction Queue
+
+```mermaid
+gantt
+    title OpenTelemetry Implementation Timeline
+    dateFormat  YYYY-MM-DD
+    axisFormat  Week %W
+
+    section Phase 1
+    Core Infrastructure        :p1, 2024-01-01, 2w
+    SDK Integration           :p1a, 2024-01-01, 4d
+    Telemetry Interface       :p1b, after p1a, 3d
+    Configuration & CMake     :p1c, after p1b, 3d
+    Unit Tests                :p1d, after p1c, 2d
+    Buffer & Integration      :p1e, after p1d, 2d
+
+    section Phase 2
+    RPC Tracing               :p2, after p1, 2w
+    HTTP Context Extraction   :p2a, after p1, 2d
+    RPC Handler Instrumentation :p2b, after p2a, 4d
+    PathFinding Instrumentation :p2f, after p2b, 2d
+    TxQ Instrumentation       :p2g, after p2f, 2d
+    WebSocket Support         :p2c, after p2g, 2d
+    Integration Tests         :p2d, after p2c, 2d
+    Buffer & Review           :p2e, after p2d, 4d
+
+    section Phase 3
+    Transaction Tracing       :p3, after p2, 2w
+    Protocol Buffer Extension :p3a, after p2, 2d
+    PeerImp Instrumentation   :p3b, after p3a, 3d
+    Fee Escalation Instrumentation :p3f, after p3b, 2d
+    Relay Context Propagation :p3c, after p3f, 3d
+    Multi-node Tests          :p3d, after p3c, 2d
+    Buffer & Review           :p3e, after p3d, 4d
+
+    section Phase 4
+    Consensus Tracing         :p4, after p3, 2w
+    Consensus Round Spans     :p4a, after p3, 3d
+    Proposal Handling         :p4b, after p4a, 3d
+    Validator List & Manifest Tracing :p4f, after p4b, 2d
+    Amendment Voting Tracing  :p4g, after p4f, 2d
+    SHAMap Sync Tracing       :p4h, after p4g, 2d
+    Validation Tests          :p4c, after p4h, 4d
+    Buffer & Review           :p4e, after p4c, 4d
+
+    section Phase 5
+    Documentation & Deploy    :p5, after p4, 1w
+```
+
+---
+
+## 6.2 Phase 1: Core Infrastructure (Weeks 1-2)
+
+**Objective**: Establish foundational telemetry infrastructure
+
+### Tasks
+
+| Task | Description                                           |
+| ---- | ----------------------------------------------------- |
+| 1.1  | Add OpenTelemetry C++ SDK to Conan/CMake              |
+| 1.2  | Implement `Telemetry` interface and factory           |
+| 1.3  | Implement `SpanGuard` RAII wrapper                    |
+| 1.4  | Implement configuration parser                        |
+| 1.5  | Integrate into `ApplicationImp`                       |
+| 1.6  | Add conditional compilation (`XRPL_ENABLE_TELEMETRY`) |
+| 1.7  | Create `NullTelemetry` no-op implementation           |
+| 1.8  | Unit tests for core infrastructure                    |
+
+### Exit Criteria
+
+- [ ] OpenTelemetry SDK compiles and links
+- [ ] Telemetry can be enabled/disabled via config
+- [ ] Basic span creation works
+- [ ] No performance regression when disabled
+- [ ] Unit tests passing
+
+---
+
+## 6.3 Phase 2: RPC Tracing (Weeks 3-4)
+
+> **TxQ** = Transaction Queue
+
+**Objective**: Complete tracing for all RPC operations
+
+### Tasks
+
+| Task | Description                                                                |
+| ---- | -------------------------------------------------------------------------- |
+| 2.1  | Implement W3C Trace Context HTTP header extraction                         |
+| 2.2  | Instrument `ServerHandler::onRequest()`                                    |
+| 2.3  | Instrument `RPCHandler::doCommand()`                                       |
+| 2.4  | Add RPC-specific attributes                                                |
+| 2.5  | Instrument WebSocket handler                                               |
+| 2.6  | PathFinding instrumentation (`pathfind.request`, `pathfind.compute` spans) |
+| 2.7  | TxQ instrumentation (`txq.enqueue`, `txq.apply` spans)                     |
+| 2.8  | Integration tests for RPC tracing                                          |
+| 2.9  | Performance benchmarks                                                     |
+| 2.10 | Documentation                                                              |
+
+### Exit Criteria
+
+- [ ] All RPC commands traced
+- [ ] Trace context propagates from HTTP headers
+- [ ] WebSocket and HTTP both instrumented
+- [ ] <1ms overhead per RPC call
+- [ ] Integration tests passing
+
+---
+
+## 6.4 Phase 3: Transaction Tracing (Weeks 5-6)
+
+**Objective**: Trace transaction lifecycle across network
+
+### Tasks
+
+| Task | Description                                          |
+| ---- | ---------------------------------------------------- |
+| 3.1  | Define `TraceContext` Protocol Buffer message        |
+| 3.2  | Implement protobuf context serialization             |
+| 3.3  | Instrument `PeerImp::handleTransaction()`            |
+| 3.4  | Instrument `NetworkOPs::submitTransaction()`         |
+| 3.5  | Instrument HashRouter integration                    |
+| 3.6  | Fee escalation instrumentation (`fee.escalate` span) |
+| 3.7  | Implement relay context propagation                  |
+| 3.8  | Integration tests (multi-node)                       |
+| 3.9  | Performance benchmarks                               |
+
+### Exit Criteria
+
+- [ ] Transaction traces span across nodes
+- [ ] Trace context in Protocol Buffer messages
+- [ ] HashRouter deduplication visible in traces
+- [ ] Multi-node integration tests passing
+- [ ] <5% overhead on transaction throughput
+
+---
+
+## 6.5 Phase 4: Consensus Tracing (Weeks 7-8)
+
+**Objective**: Full observability into consensus rounds
+
+### Tasks
+
+| Task | Description                                    |
+| ---- | ---------------------------------------------- |
+| 4.1  | Instrument `RCLConsensusAdaptor::startRound()` |
+| 4.2  | Instrument phase transitions                   |
+| 4.3  | Instrument proposal handling                   |
+| 4.4  | Instrument validation handling                 |
+| 4.5  | Add consensus-specific attributes              |
+| 4.6  | Correlate with transaction traces              |
+| 4.7  | Validator list and manifest tracing            |
+| 4.8  | Amendment voting tracing                       |
+| 4.9  | SHAMap sync tracing                            |
+| 4.10 | Multi-validator integration tests              |
+| 4.11 | Performance validation                         |
+
+### Spans Produced
+
+| Span Name                   | Location               | Attributes                                                                                                                                                                                                            |
+| --------------------------- | ---------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `consensus.proposal.send`   | `RCLConsensus.cpp:177` | `xrpl.consensus.round`                                                                                                                                                                                                |
+| `consensus.ledger_close`    | `RCLConsensus.cpp:282` | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode`                                                                                                                                                                    |
+| `consensus.accept`          | `RCLConsensus.cpp:395` | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms`                                                                                                                                                            |
+| `consensus.accept.apply`    | `RCLConsensus.cpp:521` | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state`, `proposing`, `round_time_ms`, `ledger.seq`, `parent_close_time`, `close_time_self`, `close_time_vote_bins`, `resolution_direction` |
+| `consensus.validation.send` | `RCLConsensus.cpp:753` | `xrpl.consensus.proposing`                                                                                                                                                                                            |
+
+### Exit Criteria
+
+- [x] Complete consensus round traces
+- [x] Phase transitions visible
+- [x] Proposals and validations traced
+- [x] Close time agreement tracked (per `avCT_CONSENSUS_PCT`)
+- [x] No impact on consensus timing
+- [ ] Multi-validator test network validated
+
+### Implementation Status — Phase 4a Complete
+
+Phase 4a (establish-phase gap fill & cross-node correlation) adds:
+
+- **Deterministic trace ID** derived from `previousLedger.id()` so all validators
+  in the same round share the same `trace_id` (switchable via
+  `consensus_trace_strategy` config: `"deterministic"` or `"attribute"`).
+  See [Configuration Reference](./05-configuration-reference.md) for full
+  configuration options. The `consensus_trace_strategy` option will be
+  documented in the configuration reference as part of Phase 4a implementation.
+- **Round lifecycle spans**: `consensus.round` with round-to-round span links.
+- **Establish phase**: `consensus.establish`, `consensus.update_positions` (with
+  `dispute.resolve` events), `consensus.check` (with threshold tracking).
+- **Mode changes**: `consensus.mode_change` spans.
+- **Validation**: `consensus.validation.send` with span link to round span
+  (thread-safe cross-thread access via `roundSpanContext_` snapshot).
+- **Separation of concerns**: telemetry extracted to private helpers
+  (`startRoundTracing`, `createValidationSpan`, `startEstablishTracing`,
+  `updateEstablishTracing`, `endEstablishTracing`).
+
+See [Phase4_taskList.md](./Phase4_taskList.md) for the full spec and implementation notes.
+
+---
+
+## 6.5a Phase 4a: Establish-Phase Gap Fill & Cross-Node Correlation
+
+**Objective**: Fill tracing gaps in the establish phase and establish cross-node
+correlation using deterministic trace IDs derived from `previousLedger.id()`.
+
+**Approach**: Direct instrumentation in `Consensus.h`. Long-lived spans use
+direct SpanGuard members; short-lived scoped spans use `XRPL_TRACE_*` macros.
+
+### Tasks
+
+| Task | Description                                      | Effort | Risk   |
+| ---- | ------------------------------------------------ | ------ | ------ |
+| 4a.0 | Prerequisites: extend SpanGuard & Telemetry APIs | 1d     | Medium |
+| 4a.1 | Adaptor `getTelemetry()` method                  | 0.5d   | Low    |
+| 4a.2 | Switchable round span with deterministic traceID | 2d     | High   |
+| 4a.3 | Span members in `Consensus.h`                    | 0.5d   | Medium |
+| 4a.4 | Instrument `phaseEstablish()`                    | 1d     | Medium |
+| 4a.5 | Instrument `updateOurPositions()`                | 1d     | Medium |
+| 4a.6 | Instrument `haveConsensus()` (thresholds)        | 1d     | Medium |
+| 4a.7 | Instrument mode changes                          | 0.5d   | Low    |
+| 4a.8 | Reparent existing spans under round              | 0.5d   | Low    |
+| 4a.9 | Build verification and testing                   | 1d     | Low    |
+
+**Total Effort**: 9 days
+
+### Spans Produced
+
+| Span Name                    | Location           | Key Attributes                                                   |
+| ---------------------------- | ------------------ | ---------------------------------------------------------------- |
+| `consensus.round`            | `RCLConsensus.cpp` | `round_id`, `ledger_id`, `ledger.seq`, `mode`; link → prev round |
+| `consensus.establish`        | `Consensus.h`      | `converge_percent`, `establish_count`, `proposers`               |
+| `consensus.update_positions` | `Consensus.h`      | `disputes_count`, `converge_percent`, `proposers_agreed/total`   |
+| `consensus.check`            | `Consensus.h`      | `agree/disagree_count`, `threshold_percent`, `result`            |
+| `consensus.mode_change`      | `RCLConsensus.cpp` | `mode.old`, `mode.new`                                           |
+
+### Exit Criteria
+
+- [ ] Establish phase internals fully traced (disputes, convergence, thresholds)
+- [ ] Cross-node correlation works via deterministic trace_id
+- [ ] Strategy switchable via config (`deterministic` / `attribute`)
+- [ ] Consecutive rounds linked via follows-from spans
+- [ ] Build passes with telemetry ON and OFF
+- [ ] No impact on consensus timing
+
+See [Phase4_taskList.md](./Phase4_taskList.md) for full task details.
+
+---
+
+## 6.5b Phase 4b: Cross-Node Propagation (Future)
+
+**Objective**: Wire `TraceContextPropagator` for P2P messages (proposals,
+validations) to enable true distributed tracing between nodes.
+
+**Status**: Design documented, NOT implemented. Protobuf fields (field 1001)
+and `TraceContextPropagator` class exist. Wiring deferred until Phase 4a is
+validated in a multi-node environment.
+
+**Prerequisites**: Phase 4a complete and validated.
+
+See [Phase4_taskList.md § Phase 4b](./Phase4_taskList.md) for full design.
+
+---
+
+## 6.6 Phase 5: Documentation & Deployment (Week 9)
+
+**Objective**: Production readiness
+
+### Tasks
+
+| Task | Description                   |
+| ---- | ----------------------------- |
+| 5.1  | Operator runbook              |
+| 5.2  | Grafana dashboards            |
+| 5.3  | Alert definitions             |
+| 5.4  | Collector deployment examples |
+| 5.5  | Developer documentation       |
+| 5.6  | Training materials            |
+| 5.7  | Final integration testing     |
+
+---
+
+## 6.7 Phase 6: StatsD Metrics Integration (Week 10)
+
+**Objective**: Bridge rippled's existing `beast::insight` StatsD metrics into the OpenTelemetry collection pipeline, exposing 300+ pre-existing metrics alongside span-derived RED metrics in Prometheus/Grafana.
+
+### Background
+
+rippled has a mature metrics framework (`beast::insight`) that emits StatsD-format metrics over UDP. These metrics cover node health, peer networking, RPC performance, job queue, and overlay traffic — data that **does not** overlap with the span-based instrumentation from Phases 1-5. By adding a StatsD receiver to the OTel Collector, both metric sources converge in Prometheus.
+
+### Metric Inventory
+
+| Category        | Group              | Type          | Count      | Key Metrics                                            |
+| --------------- | ------------------ | ------------- | ---------- | ------------------------------------------------------ |
+| Node State      | `State_Accounting` | Gauge         | 10         | `*_duration`, `*_transitions` per operating mode       |
+| Ledger          | `LedgerMaster`     | Gauge         | 2          | `Validated_Ledger_Age`, `Published_Ledger_Age`         |
+| Ledger Fetch    | —                  | Counter       | 1          | `ledger_fetches`                                       |
+| Ledger History  | `ledger.history`   | Counter       | 1          | `mismatch`                                             |
+| RPC             | `rpc`              | Counter+Event | 3          | `requests`, `time` (histogram), `size` (histogram)     |
+| Job Queue       | —                  | Gauge+Event   | 1 + 2×N    | `job_count`, per-job `{name}` and `{name}_q`           |
+| Peer Finder     | `Peer_Finder`      | Gauge         | 2          | `Active_Inbound_Peers`, `Active_Outbound_Peers`        |
+| Overlay         | `Overlay`          | Gauge         | 1          | `Peer_Disconnects`                                     |
+| Overlay Traffic | per-category       | Gauge         | 4×57 = 228 | `Bytes_In/Out`, `Messages_In/Out` per traffic category |
+| Pathfinding     | —                  | Event         | 2          | `pathfind_fast`, `pathfind_full` (histograms)          |
+| I/O             | —                  | Event         | 1          | `ios_latency` (histogram)                              |
+| Resource Mgr    | —                  | Meter         | 2          | `warn`, `drop` (rate counters)                         |
+| Caches          | per-cache          | Gauge         | 2×N        | `{cache}.size`, `{cache}.hit_rate`                     |
+
+**Total**: ~255+ unique metrics (plus dynamic job-type and cache metrics)
+
+### Tasks
+
+| Task | Description                                                                                                     |
+| ---- | --------------------------------------------------------------------------------------------------------------- |
+| 6.1  | **DEFERRED** Fix Meter wire format (`\|m` → `\|c`) in StatsDCollector.cpp — breaking change, tracked separately |
+| 6.2  | Add `statsd` receiver to OTel Collector config                                                                  |
+| 6.3  | Expose UDP port 8125 in docker-compose.yml                                                                      |
+| 6.4  | Add `[insight]` config to integration test node configs                                                         |
+| 6.5  | Create "Node Health" Grafana dashboard (8 panels)                                                               |
+| 6.6  | Create "Network Traffic" Grafana dashboard (8 panels)                                                           |
+| 6.7  | Create "RPC & Pathfinding (StatsD)" Grafana dashboard (8 panels)                                                |
+| 6.8  | Update integration test to verify StatsD metrics in Prometheus                                                  |
+| 6.9  | Update TESTING.md and telemetry-runbook.md                                                                      |
+
+### Wire Format Fix (Task 6.1) — DEFERRED
+
+The `StatsDMeterImpl` in `StatsDCollector.cpp:706` sends metrics with `|m` suffix, which is non-standard StatsD. The OTel StatsD receiver silently drops these. Fix: change `|m` to `|c` (counter), which is semantically correct since meters are increment-only counters. Only 2 metrics are affected (`warn`, `drop` in Resource Manager).
+
+**Status**: Deferred as a separate change — this is a breaking change for any StatsD backend that previously consumed the custom `|m` type. The Resource Warnings and Resource Drops dashboard panels will show no data until this fix is applied.
+
+### New Grafana Dashboards
+
+**Node Health** (`statsd-node-health.json`, uid: `rippled-statsd-node-health`):
+
+- Validated/Published Ledger Age, Operating Mode Duration/Transitions, I/O Latency, Job Queue Depth, Ledger Fetch Rate, Ledger History Mismatches
+
+**Network Traffic** (`statsd-network-traffic.json`, uid: `rippled-statsd-network`):
+
+- Active Inbound/Outbound Peers, Peer Disconnects, Total Bytes/Messages In/Out, Transaction/Proposal/Validation Traffic, Top Traffic Categories
+
+**RPC & Pathfinding (StatsD)** (`statsd-rpc-pathfinding.json`, uid: `rippled-statsd-rpc`):
+
+- RPC Request Rate, Response Time p95/p50, Response Size p95/p50, Pathfinding Fast/Full Duration, Resource Warnings/Drops, Response Time Heatmap
+
+### Exit Criteria
+
+- [ ] StatsD metrics visible in Prometheus (`curl localhost:9090/api/v1/query?query=rippled_LedgerMaster_Validated_Ledger_Age`)
+- [ ] All 3 new Grafana dashboards load without errors
+- [ ] Integration test verifies at least core StatsD metrics (ledger age, peer counts, RPC requests)
+- [ ] ~~Meter metrics (`warn`, `drop`) flow correctly after `|m` → `|c` fix~~ — DEFERRED (breaking change, tracked separately; resolved by Phase 7's OTel Counter mapping)
+
+---
+
+## 6.8 Phase 7: Native OTel Metrics Migration (Weeks 11-12)
+
+**Objective**: Replace `StatsDCollector` with a native OpenTelemetry Metrics SDK implementation behind the existing `beast::insight::Collector` interface, eliminating the StatsD UDP dependency and unifying traces and metrics into a single OTLP pipeline.
+
+### Motivation: Why Migrate from StatsD to Native OTel Metrics
+
+The Phase 6 StatsD bridge was a pragmatic first step, but it retains inherent limitations that native OTel export resolves.
+
+#### What We Gain
+
+1. **Unified telemetry pipeline** — Traces and metrics export via the same OTLP/HTTP endpoint to the same OTel Collector. One protocol, one endpoint, one config. Eliminates the split-brain architecture of "OTLP for traces, StatsD UDP for metrics."
+
+2. **Eliminates StatsD UDP limitations** — StatsD is fire-and-forget over UDP with no delivery guarantees, no backpressure, 1472-byte MTU packet fragmentation, and text-based encoding overhead. OTLP uses HTTP/gRPC with retries, binary protobuf encoding, and connection-level flow control.
+
+3. **Fixes the `|m` wire format issue** — The `StatsDMeterImpl` uses non-standard `|m` StatsD type that the OTel StatsD receiver silently drops. Native OTel counters eliminate this problem entirely (Phase 6 Task 6.1 — DEFERRED becomes resolved).
+
+4. **Richer metric semantics** — OTel Metrics SDK supports explicit histogram bucket boundaries, exemplars (linking metrics to traces), resource attributes, and metric views. StatsD has no concept of these.
+
+5. **Removes infrastructure dependency** — No more StatsD receiver needed in the OTel Collector. One less receiver to configure, monitor, and debug. Simplifies the collector YAML.
+
+6. **Metric-to-trace correlation** — OTel metrics and traces share the same resource attributes (service.name, service.instance.id). Grafana can link from a metric spike directly to the traces that caused it — impossible with StatsD-sourced metrics.
+
+7. **Production-grade export** — OTel's `PeriodicMetricReader` provides configurable export intervals, batch sizes, timeout handling, and graceful shutdown — all built into the SDK rather than hand-rolled in `StatsDCollectorImp`.
+
+#### What We Lose
+
+1. **StatsD ecosystem compatibility** — Operators using external StatsD-compatible backends (Datadog Agent, Graphite, Telegraph) will need to switch to OTLP-compatible backends or keep `server=statsd` as a fallback.
+
+2. **Simplicity of UDP** — StatsD's UDP fire-and-forget model is dead simple and has zero connection management. OTLP/HTTP requires a TCP connection, TLS negotiation (in production), and retry logic. The OTel SDK handles this, but it's more moving parts.
+
+3. **Slightly higher memory** — OTel SDK maintains internal aggregation state for metrics before export. StatsD just formats and sends strings. Expected overhead: ~1-2 MB additional for metric state.
+
+4. **Dependency on OTel C++ Metrics SDK stability** — The Metrics SDK is GA since 1.0 and on version 1.18.0, but it's less battle-tested than the tracing SDK in the C++ ecosystem.
+
+#### Decision
+
+The gains (unified pipeline, delivery guarantees, metric-trace correlation, simpler collector config) significantly outweigh the losses. `StatsDCollector` is retained as a fallback via `server=statsd` for operators who need StatsD ecosystem compatibility during the transition period.
+
+### Architecture
+
+#### Class Hierarchy (after Phase 7)
+
+```
+beast::insight::Collector (abstract interface — unchanged)
+    |
+    +-- StatsDCollector        (existing — retained as fallback, deprecated)
+    |     +-- StatsDCounterImpl    -> StatsD |c over UDP
+    |     +-- StatsDGaugeImpl      -> StatsD |g over UDP
+    |     +-- StatsDMeterImpl      -> StatsD |m over UDP (non-standard)
+    |     +-- StatsDEventImpl      -> StatsD |ms over UDP
+    |     +-- StatsDHookImpl       -> 1s periodic callback
+    |
+    +-- NullCollector          (existing — unchanged, used when disabled)
+    |     +-- NullCounterImpl      -> no-op
+    |     +-- NullGaugeImpl        -> no-op
+    |     +-- NullMeterImpl        -> no-op
+    |     +-- NullEventImpl        -> no-op
+    |     +-- NullHookImpl         -> no-op
+    |
+    +-- OTelCollector          (NEW — Phase 7)
+          +-- OTelCounterImpl      -> otel::Counter<int64_t>
+          +-- OTelGaugeImpl        -> otel::ObservableGauge<uint64_t>
+          +-- OTelMeterImpl        -> otel::Counter<uint64_t>
+          +-- OTelEventImpl        -> otel::Histogram<double>
+          +-- OTelHookImpl         -> 1s periodic callback (same pattern)
+```
+
+#### Data Flow (after Phase 7)
+
+```mermaid
+graph LR
+    subgraph rippledNode["rippled Node"]
+        A["Trace Macros<br/>XRPL_TRACE_SPAN"]
+        B["beast::insight<br/>OTelCollector"]
+    end
+
+    subgraph collector["OTel Collector  :4317 / :4318"]
+        direction TB
+        R1["OTLP Receiver<br/>:4317 gRPC  |  :4318 HTTP"]
+        BP["Batch Processor"]
+        SM["SpanMetrics Connector"]
+
+        R1 --> BP
+        BP --> SM
+    end
+
+    subgraph backends["Trace Backends"]
+        D["Jaeger / Tempo"]
+    end
+
+    subgraph metrics["Metrics Stack"]
+        E["Prometheus  :9090<br/>scrapes :8889<br/>span-derived + native OTel metrics"]
+    end
+
+    subgraph viz["Visualization"]
+        F["Grafana  :3000"]
+    end
+
+    A -->|"OTLP/HTTP :4318<br/>(traces)"| R1
+    B -->|"OTLP/HTTP :4318<br/>(metrics)"| R1
+
+    BP -->|"OTLP/gRPC"| D
+    SM -->|"RED metrics"| E
+    R1 -->|"rippled_* metrics<br/>(native OTLP)"| E
+
+    E --> F
+    D --> F
+
+    style A fill:#4a90d9,color:#fff,stroke:#2a6db5
+    style B fill:#d9534f,color:#fff,stroke:#b52d2d
+    style R1 fill:#5cb85c,color:#fff,stroke:#3d8b3d
+    style BP fill:#449d44,color:#fff,stroke:#2d6e2d
+    style SM fill:#449d44,color:#fff,stroke:#2d6e2d
+    style D fill:#f0ad4e,color:#000,stroke:#c78c2e
+    style E fill:#f0ad4e,color:#000,stroke:#c78c2e
+    style F fill:#5bc0de,color:#000,stroke:#3aa8c1
+    style rippledNode fill:#1a2633,color:#ccc,stroke:#4a90d9
+    style collector fill:#1a3320,color:#ccc,stroke:#5cb85c
+    style backends fill:#332a1a,color:#ccc,stroke:#f0ad4e
+    style metrics fill:#332a1a,color:#ccc,stroke:#f0ad4e
+    style viz fill:#1a2d33,color:#ccc,stroke:#5bc0de
+```
+
+**Key change**: StatsD receiver removed from collector. Both traces and metrics enter via OTLP receiver on the same port.
+
+#### Configuration
+
+```ini
+# [insight] section — new "otel" server option
+[insight]
+server=otel              # NEW: uses OTel OTLP metrics exporter
+prefix=rippled           # metric name prefix (preserved)
+
+# Endpoint and auth inherited from [telemetry] section:
+[telemetry]
+enabled=1
+endpoint=http://localhost:4318/v1/traces
+```
+
+The `OTelCollector` reads the OTLP endpoint from `[telemetry]` config (replacing `/v1/traces` with `/v1/metrics` for the metrics exporter). No additional config keys needed.
+
+**Backward compatibility**: `server=statsd` continues to work exactly as before.
+
+See [Phase7_taskList.md](./Phase7_taskList.md) for detailed per-task breakdown.
+
+### Instrument Type Mapping
+
+| beast::insight         | OTel Metrics SDK                 | Rationale                                                        |
+| ---------------------- | -------------------------------- | ---------------------------------------------------------------- |
+| Counter (int64, `\|c`) | `Counter<int64_t>`               | Direct 1:1 mapping                                               |
+| Gauge (uint64, `\|g`)  | `ObservableGauge<uint64_t>`      | Async callback matches existing Hook polling pattern             |
+| Meter (uint64, `\|m`)  | `Counter<uint64_t>`              | Fixes non-standard wire format; meters are semantically counters |
+| Event (ms, `\|ms`)     | `Histogram<double>`              | Duration distributions with explicit bucket boundaries           |
+| Hook (1s callback)     | `PeriodicMetricReader` alignment | Same 1s collection interval                                      |
+
+### Tasks
+
+| Task | Description                                                               |
+| ---- | ------------------------------------------------------------------------- |
+| 7.1  | Add OTel Metrics SDK to build deps (conan/cmake)                          |
+| 7.2  | Implement `OTelCollector` class (~400-500 lines)                          |
+| 7.3  | Update `CollectorManager` — add `server=otel`                             |
+| 7.4  | Update OTel Collector YAML (add metrics pipeline, remove StatsD receiver) |
+| 7.5  | Preserve metric names in Prometheus (naming strategy)                     |
+| 7.6  | Update Grafana dashboards (if names change)                               |
+| 7.7  | Update integration tests                                                  |
+| 7.8  | Update documentation (runbook, reference docs)                            |
+
+### Exit Criteria
+
+- [ ] All 255+ metrics visible in Prometheus via OTLP pipeline (no StatsD receiver)
+- [ ] `server=otel` is the default in development docker-compose
+- [ ] `server=statsd` still works as a fallback
+- [ ] Existing Grafana dashboards display data correctly
+- [ ] Integration test passes with OTLP-only metrics pipeline
+- [ ] No performance regression vs StatsD baseline (< 1% CPU overhead)
+- [ ] Deferred Task 6.1 (`|m` wire format) no longer relevant
+
+---
+
+## 6.9 Risk Assessment
+
+```mermaid
+quadrantChart
+    title Risk Assessment Matrix
+    x-axis Low Impact --> High Impact
+    y-axis Low Likelihood --> High Likelihood
+    quadrant-1 Mitigate Immediately
+    quadrant-2 Plan Mitigation
+    quadrant-3 Accept Risk
+    quadrant-4 Monitor Closely
+
+    SDK Compat: [0.2, 0.18]
+    Protocol Chg: [0.75, 0.72]
+    Perf Overhead: [0.58, 0.42]
+    Context Prop: [0.4, 0.55]
+    Memory Leaks: [0.85, 0.25]
+```
+
+### Risk Details
+
+| Risk                                 | Likelihood | Impact | Mitigation                              |
+| ------------------------------------ | ---------- | ------ | --------------------------------------- |
+| Protocol changes break compatibility | Medium     | High   | Use high field numbers, optional fields |
+| Performance overhead unacceptable    | Medium     | Medium | Sampling, conditional compilation       |
+| Context propagation complexity       | Medium     | Medium | Phased rollout, extensive testing       |
+| SDK compatibility issues             | Low        | Medium | Pin SDK version, fallback to no-op      |
+| Memory leaks in long-running nodes   | Low        | High   | Memory profiling, bounded queues        |
+
+---
+
+## 6.10 Success Metrics
+
+| Metric                   | Target                                                         | Measurement           |
+| ------------------------ | -------------------------------------------------------------- | --------------------- |
+| Trace coverage           | >95% of transaction code paths (independent of sampling ratio) | Sampling verification |
+| CPU overhead             | <3%                                                            | Benchmark tests       |
+| Memory overhead          | <10 MB                                                         | Memory profiling      |
+| Latency impact (p99)     | <2%                                                            | Performance tests     |
+| Trace completeness       | >99% spans with required attrs                                 | Validation script     |
+| Cross-node trace linkage | >90% of multi-hop transactions                                 | Integration tests     |
+
+---
+
+## 6.9 Quick Wins and Crawl-Walk-Run Strategy
+
+> **TxQ** = Transaction Queue
+
+This section outlines a prioritized approach to maximize ROI with minimal initial investment.
+
+### 6.9.1 Crawl-Walk-Run Overview
+
+<div align="center">
+
+```mermaid
+flowchart TB
+    subgraph crawl["🐢 CRAWL (Week 1-2)"]
+        direction LR
+        c1[Core SDK Setup] ~~~ c2[RPC Tracing Only] ~~~ c3[PathFinding + TxQ Tracing] ~~~ c4[Single Node]
+    end
+
+    subgraph walk["🚶 WALK (Week 3-5)"]
+        direction LR
+        w1[Transaction Tracing] ~~~ w2[Fee Escalation Tracing] ~~~ w3[Cross-Node Context] ~~~ w4[Basic Dashboards]
+    end
+
+    subgraph run["🏃 RUN (Week 6-9)"]
+        direction LR
+        r1[Consensus Tracing] ~~~ r2[Validator, Amendment,<br/>SHAMap Tracing] ~~~ r3[Full Correlation] ~~~ r4[Production Deploy]
+    end
+
+    crawl --> walk --> run
+
+    style crawl fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style walk fill:#bf360c,stroke:#8c2809,color:#fff
+    style run fill:#0d47a1,stroke:#082f6a,color:#fff
+    style c1 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style c2 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style c3 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style c4 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style w1 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style w2 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style w3 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style w4 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style r1 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style r2 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style r3 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style r4 fill:#0d47a1,stroke:#082f6a,color:#fff
+```
+
+</div>
+
+**Reading the diagram:**
+
+- **CRAWL (Weeks 1-2)**: Minimal investment -- set up the SDK, instrument RPC and PathFinding/TxQ handlers, and verify on a single node. Delivers immediate latency visibility.
+- **WALK (Weeks 3-5)**: Expand to transaction lifecycle tracing, fee escalation, cross-node context propagation, and basic Grafana dashboards. This is where distributed tracing starts working.
+- **RUN (Weeks 6-9)**: Full consensus instrumentation, validator/amendment/SHAMap tracing, end-to-end correlation, and production deployment with sampling and alerting.
+- **Arrows (crawl → walk → run)**: Each phase builds on the prior one; you cannot skip ahead because later phases depend on infrastructure established earlier.
+
+### 6.9.2 Quick Wins (Immediate Value)
+
+| Quick Win                      | Value  | When to Deploy |
+| ------------------------------ | ------ | -------------- |
+| **RPC Command Tracing**        | High   | Week 2         |
+| **RPC Latency Histograms**     | High   | Week 2         |
+| **Error Rate Dashboard**       | Medium | Week 2         |
+| **Transaction Submit Tracing** | High   | Week 3         |
+| **Consensus Round Duration**   | Medium | Week 6         |
+
+### 6.9.3 CRAWL Phase (Weeks 1-2)
+
+**Goal**: Get basic tracing working with minimal code changes.
+
+**What You Get**:
+
+- RPC request/response traces for all commands
+- Latency breakdown per RPC command
+- PathFinding and TxQ tracing (directly impacts RPC latency)
+- Error visibility with stack traces
+- Basic Grafana dashboard
+
+**Code Changes**: ~15 lines in `ServerHandler.cpp`, ~40 lines in new telemetry module
+
+**Why Start Here**:
+
+- RPC is the lowest-risk, highest-visibility component
+- PathFinding and TxQ are RPC-adjacent and directly affect latency
+- Immediate value for debugging client issues
+- No cross-node complexity
+- Single file modification to existing code
+
+### 6.9.4 WALK Phase (Weeks 3-5)
+
+**Goal**: Add transaction lifecycle tracing across nodes.
+
+**What You Get**:
+
+- End-to-end transaction traces from submit to relay
+- Fee escalation tracing within the transaction pipeline
+- Cross-node correlation (see transaction path)
+- HashRouter deduplication visibility
+- Relay latency metrics
+
+**Code Changes**: ~120 lines across 4 files, plus protobuf extension
+
+**Why Do This Second**:
+
+- Builds on RPC tracing (transactions submitted via RPC)
+- Fee escalation is integral to the transaction processing pipeline
+- Moderate complexity (requires context propagation)
+- High value for debugging transaction issues
+
+### 6.9.5 RUN Phase (Weeks 6-9)
+
+**Goal**: Full observability including consensus.
+
+**What You Get**:
+
+- Complete consensus round visibility
+- Phase transition timing
+- Validator proposal tracking
+- Validator list and manifest tracing
+- Amendment voting tracing
+- SHAMap sync tracing
+- Full end-to-end traces (client → RPC → TX → consensus → ledger)
+
+**Code Changes**: ~100 lines across 3 consensus files, plus validator/amendment/SHAMap modules
+
+**Why Do This Last**:
+
+- Highest complexity (consensus is critical path)
+- Validator, amendment, and SHAMap components are lower priority
+- Requires thorough testing
+- Lower relative value (consensus issues are rarer)
+
+### 6.9.6 ROI Prioritization Matrix
+
+```mermaid
+quadrantChart
+    title Implementation ROI Matrix
+    x-axis Low Effort --> High Effort
+    y-axis Low Value --> High Value
+    quadrant-1 Quick Wins - Do First
+    quadrant-2 Major Projects - Plan Carefully
+    quadrant-3 Nice to Have - Optional
+    quadrant-4 Time Sinks - Avoid
+
+    RPC Tracing: [0.15, 0.92]
+    TX Submit Trace: [0.3, 0.78]
+    TX Relay Trace: [0.5, 0.88]
+    Consensus Trace: [0.72, 0.72]
+    Peer Msg Trace: [0.85, 0.3]
+    Ledger Acquire: [0.55, 0.52]
+```
+
+---
+
+
+## 6.13 Definition of Done
+
+> **TxQ** = Transaction Queue | **HA** = High Availability
+
+Clear, measurable criteria for each phase.
+
+### 6.13.1 Phase 1: Core Infrastructure
+
+
+| Criterion       | Measurement                                                | Target                       |
+| --------------- | ---------------------------------------------------------- | ---------------------------- |
+| SDK Integration | `cmake --build` succeeds with `-DXRPL_ENABLE_TELEMETRY=ON` | ✅ Compiles                  |
+| Runtime Toggle  | `enabled=0` produces zero overhead                         | <0.1% CPU difference         |
+| Span Creation   | Unit test creates and exports span                         | Span appears in Tempo        |
+| Configuration   | All config options parsed correctly                        | Config validation tests pass |
+| Documentation   | Developer guide exists                                     | PR approved                  |
+
+**Definition of Done**: All criteria met, PR merged, no regressions in CI.
+
+
+### 6.13.2 Phase 2: RPC Tracing
+
+
+| Criterion          | Measurement                        | Target                     |
+| ------------------ | ---------------------------------- | -------------------------- |
+| Coverage           | All RPC commands instrumented      | 100% of commands           |
+| Context Extraction | traceparent header propagates      | Integration test passes    |
+| Attributes         | Command, status, duration recorded | Validation script confirms |
+| Performance        | RPC latency overhead               | <1ms p99                   |
+| Dashboard          | Grafana dashboard deployed         | Screenshot in docs         |
+
+**Definition of Done**: RPC traces visible in Tempo for all commands, dashboard shows latency distribution.
+
+
+### 6.13.3 Phase 3: Transaction Tracing
+
+
+| Criterion        | Measurement                     | Target                             |
+| ---------------- | ------------------------------- | ---------------------------------- |
+| Local Trace      | Submit → validate → TxQ traced  | Single-node test passes            |
+| Cross-Node       | Context propagates via protobuf | Multi-node test passes             |
+| Relay Visibility | relay_count attribute correct   | Spot check 100 txs                 |
+| HashRouter       | Deduplication visible in trace  | Duplicate txs show suppressed=true |
+| Performance      | TX throughput overhead          | <5% degradation                    |
+
+**Definition of Done**: Transaction traces span 3+ nodes in test network, performance within bounds.
+
+
+### 6.13.4 Phase 4: Consensus Tracing
+
+
+| Criterion            | Measurement                   | Target                    |
+| -------------------- | ----------------------------- | ------------------------- |
+| Round Tracing        | startRound creates root span  | Unit test passes          |
+| Phase Visibility     | All phases have child spans   | Integration test confirms |
+| Proposer Attribution | Proposer ID in attributes     | Spot check 50 rounds      |
+| Timing Accuracy      | Phase durations match PerfLog | <5% variance              |
+| No Consensus Impact  | Round timing unchanged        | Performance test passes   |
+
+**Definition of Done**: Consensus rounds fully traceable, no impact on consensus timing.
+
+
+### 6.13.5 Phase 5: Production Deployment
+
+
+| Criterion    | Measurement                  | Target                     |
+| ------------ | ---------------------------- | -------------------------- |
+| Collector HA | Multiple collectors deployed | No single point of failure |
+| Sampling     | Tail sampling configured     | 10% base + errors + slow   |
+| Retention    | Data retained per policy     | 7 days hot, 30 days warm   |
+| Alerting     | Alerts configured            | Error spike, high latency  |
+| Runbook      | Operator documentation       | Approved by ops team       |
+| Training     | Team trained                 | Session completed          |
+
+**Definition of Done**: Telemetry running in production, operators trained, alerts active.
+
+
+### 6.13.6 Success Metrics Summary
+
+| Phase   | Primary Metric               | Secondary Metric            | Deadline       |
+| ------- | ---------------------------- | --------------------------- | -------------- |
+| Phase 1 | SDK compiles and runs        | Zero overhead when disabled | End of Week 2  |
+| Phase 2 | 100% RPC coverage            | <1ms latency overhead       | End of Week 4  |
+| Phase 3 | Cross-node traces work       | <5% throughput impact       | End of Week 6  |
+| Phase 4 | Consensus fully traced       | No consensus timing impact  | End of Week 8  |
+| Phase 5 | Production deployment        | Operators trained           | End of Week 9  |
+| Phase 6 | StatsD metrics in Prometheus | 3 dashboards operational    | End of Week 10 |
+| Phase 7 | All metrics via OTLP         | No StatsD dependency        | End of Week 12 |
+
+---
+
+## 6.14 Recommended Implementation Order
+
+Based on ROI analysis, implement in this exact order:
+
+```mermaid
+flowchart TB
+    subgraph week1["Week 1"]
+        t1[1. OpenTelemetry SDK<br/>Conan/CMake integration]
+        t2[2. Telemetry interface<br/>SpanGuard, config]
+    end
+
+    subgraph week2["Week 2"]
+        t3[3. RPC ServerHandler<br/>instrumentation]
+        t4[4. Basic Tempo setup<br/>for testing]
+    end
+
+    subgraph week3["Week 3"]
+        t5[5. Transaction submit<br/>tracing]
+        t6[6. Grafana dashboard<br/>v1]
+    end
+
+    subgraph week4["Week 4"]
+        t7[7. Protobuf context<br/>extension]
+        t8[8. PeerImp tx.relay<br/>instrumentation]
+    end
+
+    subgraph week5["Week 5"]
+        t9[9. Multi-node<br/>integration tests]
+        t10[10. Performance<br/>benchmarks]
+    end
+
+    subgraph week6_8["Weeks 6-8"]
+        t11[11. Consensus<br/>instrumentation]
+        t12[12. Full integration<br/>testing]
+    end
+
+    subgraph week9["Week 9"]
+        t13[13. Production<br/>deployment]
+        t14[14. Documentation<br/>& training]
+    end
+
+    t1 --> t2 --> t3 --> t4
+    t4 --> t5 --> t6
+    t6 --> t7 --> t8
+    t8 --> t9 --> t10
+    t10 --> t11 --> t12
+    t12 --> t13 --> t14
+
+    style week1 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style week2 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style week3 fill:#bf360c,stroke:#8c2809,color:#fff
+    style week4 fill:#bf360c,stroke:#8c2809,color:#fff
+    style week5 fill:#bf360c,stroke:#8c2809,color:#fff
+    style week6_8 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style week9 fill:#4a148c,stroke:#2e0d57,color:#fff
+    style t1 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style t2 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style t3 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style t4 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style t5 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style t6 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style t7 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style t8 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style t9 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style t10 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style t11 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style t12 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style t13 fill:#4a148c,stroke:#2e0d57,color:#fff
+    style t14 fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+**Reading the diagram:**
+
+- **Week 1 (tasks 1-2)**: Foundation work -- integrate the OpenTelemetry SDK via Conan/CMake and build the `Telemetry` interface with `SpanGuard` and config parsing.
+- **Week 2 (tasks 3-4)**: First observable output -- instrument `ServerHandler` for RPC tracing and stand up Tempo so developers can see traces immediately.
+- **Weeks 3-5 (tasks 5-10)**: Transaction lifecycle -- add submit tracing, build the first Grafana dashboard, extend protobuf for cross-node context, instrument `PeerImp` relay, then validate with multi-node integration tests and performance benchmarks.
+- **Weeks 6-8 (tasks 11-12)**: Consensus deep-dive -- instrument consensus rounds and phases, then run full integration testing across all instrumented paths.
+- **Week 9 (tasks 13-14)**: Go-live -- deploy to production with sampling/alerting configured, and deliver documentation and operator training.
+- **Arrow chain (t1 → ... → t14)**: Strict sequential dependency; each task's output is a prerequisite for the next.
+
+---
+
+_Previous: [Configuration Reference](./05-configuration-reference.md)_ | _Next: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/07-observability-backends.md

@@ -0,0 +1,641 @@
+# Observability Backend Recommendations
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Implementation Phases](./06-implementation-phases.md) | [Appendix](./08-appendix.md)
+
+---
+
+## 7.1 Development/Testing Backends
+
+> **OTLP** = OpenTelemetry Protocol
+
+| Backend    | Pros                                | Cons                   | Use Case            |
+| ---------- | ----------------------------------- | ---------------------- | ------------------- |
+| **Tempo**  | Cost-effective, Grafana integration | Requires Grafana stack | Local dev, CI, Prod |
+| **Zipkin** | Simple, lightweight                 | Basic features         | Quick prototyping   |
+
+### Quick Start with Tempo
+
+```bash
+# Start Tempo with OTLP support
+docker run -d --name tempo \
+  -p 3200:3200 \
+  -p 4317:4317 \
+  -p 4318:4318 \
+  grafana/tempo:2.6.1
+```
+
+---
+
+## 7.2 Production Backends
+
+> **APM** = Application Performance Monitoring
+
+| Backend           | Pros                                      | Cons                   | Use Case                    |
+| ----------------- | ----------------------------------------- | ---------------------- | --------------------------- |
+| **Grafana Tempo** | Cost-effective, Grafana integration       | Requires Grafana stack | Most production deployments |
+| **Elastic APM**   | Full observability stack, log correlation | Resource intensive     | Existing Elastic users      |
+| **Honeycomb**     | Excellent query, high cardinality         | SaaS cost              | Deep debugging needs        |
+| **Datadog APM**   | Full platform, easy setup                 | SaaS cost              | Enterprise with budget      |
+
+### Backend Selection Flowchart
+
+```mermaid
+flowchart TD
+    start[Select Backend] --> budget{Budget<br/>Constraints?}
+
+    budget -->|Yes| oss[Open Source]
+    budget -->|No| saas{Prefer<br/>SaaS?}
+
+    oss --> existing{Existing<br/>Stack?}
+    existing -->|Grafana| tempo[Grafana Tempo]
+    existing -->|Elastic| elastic[Elastic APM]
+    existing -->|None| tempo
+
+    saas -->|Yes| enterprise{Enterprise<br/>Support?}
+    saas -->|No| oss
+
+    enterprise -->|Yes| datadog[Datadog APM]
+    enterprise -->|No| honeycomb[Honeycomb]
+
+    tempo --> final[Configure Collector]
+    elastic --> final
+    honeycomb --> final
+    datadog --> final
+
+    style start fill:#0f172a,stroke:#020617,color:#fff
+    style budget fill:#334155,stroke:#1e293b,color:#fff
+    style oss fill:#1e293b,stroke:#0f172a,color:#fff
+    style existing fill:#334155,stroke:#1e293b,color:#fff
+    style saas fill:#334155,stroke:#1e293b,color:#fff
+    style enterprise fill:#334155,stroke:#1e293b,color:#fff
+    style final fill:#0f172a,stroke:#020617,color:#fff
+    style tempo fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style elastic fill:#bf360c,stroke:#8c2809,color:#fff
+    style honeycomb fill:#0d47a1,stroke:#082f6a,color:#fff
+    style datadog fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+**Reading the diagram:**
+
+- **Budget Constraints? (Yes)**: Leads to open-source options. If you already run Grafana or Elastic, pick the matching backend; otherwise default to Grafana Tempo.
+- **Budget Constraints? (No) → Prefer SaaS?**: If you want a managed service, choose between Datadog (enterprise support) and Honeycomb (developer-focused). If not, fall back to open-source.
+- **Terminal nodes (Tempo / Elastic / Honeycomb / Datadog)**: Each represents a concrete backend choice, all of which feed into the same final step.
+- **Configure Collector**: Regardless of backend, you always finish by configuring the OTel Collector to export to your chosen destination.
+
+---
+
+## 7.3 Recommended Production Architecture
+
+> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring | **HA** = High Availability
+
+```mermaid
+flowchart TB
+    subgraph validators["Validator Nodes"]
+        v1[rippled<br/>Validator 1]
+        v2[rippled<br/>Validator 2]
+    end
+
+    subgraph stock["Stock Nodes"]
+        s1[rippled<br/>Stock 1]
+        s2[rippled<br/>Stock 2]
+    end
+
+    subgraph collector["OTel Collector Cluster"]
+        c1[Collector<br/>DC1]
+        c2[Collector<br/>DC2]
+    end
+
+    subgraph backends["Storage Backends"]
+        tempo[(Grafana<br/>Tempo)]
+        elastic[(Elastic<br/>APM)]
+        archive[(S3/GCS<br/>Archive)]
+    end
+
+    subgraph ui["Visualization"]
+        grafana[Grafana<br/>Dashboards]
+    end
+
+    v1 -->|OTLP| c1
+    v2 -->|OTLP| c1
+    s1 -->|OTLP| c2
+    s2 -->|OTLP| c2
+
+    c1 --> tempo
+    c1 --> elastic
+    c2 --> tempo
+    c2 --> archive
+
+    tempo --> grafana
+    elastic --> grafana
+
+    %% Note: simplified single-collector-per-DC topology shown for clarity
+
+    style validators fill:#b71c1c,stroke:#7f1d1d,color:#ffffff
+    style stock fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style collector fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style backends fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style ui fill:#4a148c,stroke:#2e0d57,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **Validator / Stock Nodes**: All rippled nodes emit trace data via OTLP. Validators and stock nodes are grouped separately because they may reside in different network zones.
+- **Collector Cluster (DC1, DC2)**: Regional collectors receive OTLP from nodes in their datacenter, apply processing (sampling, enrichment), and fan out to multiple backends.
+- **Storage Backends**: Tempo and Elastic provide queryable trace storage; S3/GCS Archive provides long-term cold storage for compliance or post-incident analysis.
+- **Grafana Dashboards**: The single visualization layer that queries both Tempo and Elastic, giving operators a unified view of all traces.
+- **Data flow direction**: Nodes → Collectors → Storage → Grafana. Each arrow represents a network hop; minimizing collector-to-backend hops reduces latency.
+
+> **Note**: Production deployments should use multiple collector instances behind a load balancer for high availability. The diagram shows a simplified single-collector topology for clarity.
+
+---
+
+## 7.4 Architecture Considerations
+
+### 7.4.1 Collector Placement
+
+| Strategy      | Description          | Pros                     | Cons                    |
+| ------------- | -------------------- | ------------------------ | ----------------------- |
+| **Sidecar**   | Collector per node   | Isolation, simple config | Resource overhead       |
+| **DaemonSet** | Collector per host   | Shared resources         | Complexity              |
+| **Gateway**   | Central collector(s) | Centralized processing   | Single point of failure |
+
+**Recommendation**: Use **Gateway** pattern with regional collectors for rippled networks:
+
+- One collector cluster per datacenter/region
+- Tail-based sampling at collector level
+- Multiple export destinations for redundancy
+
+### 7.4.2 Sampling Strategy
+
+```mermaid
+flowchart LR
+    subgraph head["Head Sampling (Node)"]
+        hs[Node-level head sampling<br/>configurable, default: 100%<br/>recommended production: 10%]
+    end
+
+    subgraph tail["Tail Sampling (Collector)"]
+        ts1[Keep all errors]
+        ts2[Keep slow >5s]
+        ts3[Keep 10% rest]
+    end
+
+    head --> tail
+
+    ts1 --> final[Final Traces]
+    ts2 --> final
+    ts3 --> final
+
+    style head fill:#0d47a1,stroke:#082f6a,color:#fff
+    style tail fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style hs fill:#0d47a1,stroke:#082f6a,color:#fff
+    style ts1 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style ts2 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style ts3 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style final fill:#bf360c,stroke:#8c2809,color:#fff
+```
+
+**Reading the diagram:**
+
+- **Head Sampling (Node)**: The first filter -- each rippled node decides whether to sample a trace at creation time (default 100%, recommended 10% in production). This controls the volume leaving the node.
+- **Tail Sampling (Collector)**: The second filter -- the collector inspects completed traces and applies rules: keep all errors, keep anything slower than 5 seconds, and keep 10% of the remainder.
+- **Arrow head → tail**: All head-sampled traces flow to the collector, where tail sampling further reduces volume while preserving the most valuable data.
+- **Final Traces**: The output after both sampling stages; this is what gets stored and queried. The two-stage approach balances cost with debuggability.
+
+### 7.4.3 Data Retention
+
+| Environment | Hot Storage | Warm Storage | Cold Archive |
+| ----------- | ----------- | ------------ | ------------ |
+| Development | 24 hours    | N/A          | N/A          |
+| Staging     | 7 days      | N/A          | N/A          |
+| Production  | 7 days      | 30 days      | many years   |
+
+---
+
+## 7.5 Integration Checklist
+
+- [ ] Choose primary backend (Tempo recommended for cost/features)
+- [ ] Deploy collector cluster with high availability
+- [ ] Configure tail-based sampling for error/latency traces
+- [ ] Set up Grafana dashboards for trace visualization
+- [ ] Configure alerts for trace anomalies
+- [ ] Establish data retention policies
+- [ ] Test trace correlation with logs and metrics
+
+---
+
+## 7.6 Grafana Dashboard Examples
+
+Pre-built dashboards for rippled observability.
+
+### 7.6.1 Consensus Health Dashboard
+
+```json
+{
+  "title": "rippled Consensus Health",
+  "uid": "rippled-consensus-health",
+  "tags": ["rippled", "consensus", "tracing"],
+  "panels": [
+    {
+      "title": "Consensus Round Duration",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"consensus.round\"} | avg(duration) by (resource.service.instance.id)"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 4000 },
+              { "color": "red", "value": 5000 }
+            ]
+          }
+        }
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Phase Duration Breakdown",
+      "type": "barchart",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=~\"consensus.phase.*\"} | avg(duration) by (name)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }
+    },
+    {
+      "title": "Proposers per Round",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"consensus.round\"} | avg(span.xrpl.consensus.proposers)"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 8 }
+    },
+    {
+      "title": "Recent Slow Rounds (>5s)",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"consensus.round\"} | duration > 5s"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 12 }
+    }
+  ]
+}
+```
+
+### 7.6.2 Node Overview Dashboard
+
+```json
+{
+  "title": "rippled Node Overview",
+  "uid": "rippled-node-overview",
+  "panels": [
+    {
+      "title": "Active Nodes",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\"} | count_over_time() by (resource.service.instance.id) | count()"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Total Transactions (1h)",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.receive\"} | count()"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 0 }
+    },
+    {
+      "title": "Error Rate",
+      "type": "gauge",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && status.code=error} | rate() / {resource.service.name=\"rippled\"} | rate() * 100"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent",
+          "max": 10,
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 1 },
+              { "color": "red", "value": 5 }
+            ]
+          }
+        }
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 0 }
+    },
+    {
+      "title": "Service Map",
+      "type": "nodeGraph",
+      "datasource": "Tempo",
+      "gridPos": { "h": 12, "w": 12, "x": 12, "y": 0 }
+    }
+  ]
+}
+```
+
+### 7.6.3 Alert Rules
+
+```yaml
+# grafana/provisioning/alerting/rippled-alerts.yaml
+apiVersion: 1
+
+groups:
+  - name: rippled-tracing-alerts
+    folder: rippled
+    interval: 1m
+    rules:
+      - uid: consensus-slow
+        title: Consensus Round Slow
+        condition: A
+        data:
+          - refId: A
+            datasourceUid: tempo
+            model:
+              queryType: traceql
+              query: '{resource.service.name="rippled" && name="consensus.round"} | avg(duration) > 5s'
+              # Note: Verify TraceQL aggregate queries are supported by your
+              # Tempo version. Aggregate alerting (e.g., avg(duration)) requires
+              # Tempo 2.3+ with TraceQL metrics enabled.
+        for: 5m
+        annotations:
+          summary: Consensus rounds taking >5 seconds
+          description: "Consensus duration: {{ $value }}ms"
+        labels:
+          severity: warning
+
+      - uid: rpc-error-spike
+        title: RPC Error Rate Spike
+        condition: B
+        data:
+          - refId: B
+            datasourceUid: tempo
+            model:
+              queryType: traceql
+              query: '{resource.service.name="rippled" && name=~"rpc.command.*" && status.code=error} | rate() > 0.05'
+              # Note: Verify TraceQL aggregate queries are supported by your
+              # Tempo version. Aggregate alerting (e.g., rate()) requires
+              # Tempo 2.3+ with TraceQL metrics enabled.
+        for: 2m
+        annotations:
+          summary: RPC error rate >5%
+        labels:
+          severity: critical
+
+      - uid: tx-throughput-drop
+        title: Transaction Throughput Drop
+        condition: C
+        data:
+          - refId: C
+            datasourceUid: tempo
+            model:
+              queryType: traceql
+              query: '{resource.service.name="rippled" && name="tx.receive"} | rate() < 10'
+        for: 10m
+        annotations:
+          summary: Transaction throughput below threshold
+        labels:
+          severity: warning
+```
+
+---
+
+## 7.7 PerfLog and Insight Correlation
+
+> **OTLP** = OpenTelemetry Protocol
+
+How to correlate OpenTelemetry traces with existing rippled observability.
+
+### 7.7.1 Correlation Architecture
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Node"]
+        otel[OpenTelemetry<br/>Spans]
+        perflog[PerfLog<br/>JSON Logs]
+        insight[Beast Insight<br/>StatsD Metrics]
+    end
+
+    subgraph collectors["Data Collection"]
+        otelc[OTel Collector]
+        promtail[Promtail/Fluentd]
+        statsd[StatsD Exporter]
+    end
+
+    subgraph storage["Storage"]
+        tempo[(Tempo)]
+        loki[(Loki)]
+        prom[(Prometheus)]
+    end
+
+    subgraph grafana["Grafana"]
+        traces[Trace View]
+        logs[Log View]
+        metrics[Metrics View]
+        corr[Correlation<br/>Panel]
+    end
+
+    otel -->|OTLP| otelc --> tempo
+    perflog -->|JSON| promtail --> loki
+    insight -->|StatsD| statsd --> prom
+
+    tempo --> traces
+    loki --> logs
+    prom --> metrics
+
+    traces --> corr
+    logs --> corr
+    metrics --> corr
+
+    style rippled fill:#0d47a1,stroke:#082f6a,color:#fff
+    style collectors fill:#bf360c,stroke:#8c2809,color:#fff
+    style storage fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style grafana fill:#4a148c,stroke:#2e0d57,color:#fff
+    style otel fill:#0d47a1,stroke:#082f6a,color:#fff
+    style perflog fill:#0d47a1,stroke:#082f6a,color:#fff
+    style insight fill:#0d47a1,stroke:#082f6a,color:#fff
+    style otelc fill:#bf360c,stroke:#8c2809,color:#fff
+    style promtail fill:#bf360c,stroke:#8c2809,color:#fff
+    style statsd fill:#bf360c,stroke:#8c2809,color:#fff
+    style tempo fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style loki fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style prom fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style traces fill:#4a148c,stroke:#2e0d57,color:#fff
+    style logs fill:#4a148c,stroke:#2e0d57,color:#fff
+    style metrics fill:#4a148c,stroke:#2e0d57,color:#fff
+    style corr fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+**Reading the diagram:**
+
+- **rippled Node (three sources)**: A single node emits three independent data streams -- OpenTelemetry spans, PerfLog JSON logs, and Beast Insight StatsD metrics.
+- **Data Collection layer**: Each stream has its own collector -- OTel Collector for spans, Promtail/Fluentd for logs, and a StatsD exporter for metrics. They operate independently.
+- **Storage layer (Tempo, Loki, Prometheus)**: Each data type lands in a purpose-built store optimized for its query patterns (trace search, log grep, metric aggregation).
+- **Grafana Correlation Panel**: The key integration point -- Grafana queries all three stores and links them via shared fields (`trace_id`, `xrpl.tx.hash`, `ledger_seq`), enabling a single-pane debugging experience.
+
+### 7.7.2 Correlation Fields
+
+| Source      | Field                       | Link To       | Purpose                    |
+| ----------- | --------------------------- | ------------- | -------------------------- |
+| **Trace**   | `trace_id`                  | Logs          | Find log entries for trace |
+| **Trace**   | `xrpl.tx.hash`              | Logs, Metrics | Find TX-related data       |
+| **Trace**   | `xrpl.consensus.ledger.seq` | Logs          | Find ledger-related logs   |
+| **PerfLog** | `trace_id` (new)            | Traces        | Jump to trace from log     |
+| **PerfLog** | `ledger_seq`                | Traces        | Find consensus trace       |
+| **Insight** | `exemplar.trace_id`         | Traces        | Jump from metric spike     |
+
+### 7.7.3 Example: Debugging a Slow Transaction
+
+**Step 1: Find the trace**
+
+```
+# In Grafana Explore with Tempo
+{resource.service.name="rippled" && span.xrpl.tx.hash="ABC123..."}
+```
+
+**Step 2: Get the trace_id from the trace view**
+
+```
+Trace ID: 4bf92f3577b34da6a3ce929d0e0e4736
+```
+
+**Step 3: Find related PerfLog entries**
+
+```
+# In Grafana Explore with Loki
+{job="rippled"} |= "4bf92f3577b34da6a3ce929d0e0e4736"
+```
+
+**Step 4: Check Insight metrics for the time window**
+
+```
+# In Grafana with Prometheus
+rate(rippled_tx_applied_total[1m])
+  @ timestamp_from_trace
+```
+
+### 7.7.4 Unified Dashboard Example
+
+```json
+{
+  "title": "rippled Unified Observability",
+  "uid": "rippled-unified",
+  "panels": [
+    {
+      "title": "Transaction Latency (Traces)",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.receive\"} | histogram_over_time(duration)"
+        }
+      ],
+      "gridPos": { "h": 6, "w": 8, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Transaction Rate (Metrics)",
+      "type": "timeseries",
+      "datasource": "Prometheus",
+      "targets": [
+        {
+          "expr": "rate(rippled_tx_received_total[5m])",
+          "legendFormat": "{{ instance }}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "links": [
+            {
+              "title": "View traces",
+              "url": "/explore?left={\"datasource\":\"Tempo\",\"query\":\"{resource.service.name=\\\"rippled\\\" && name=\\\"tx.receive\\\"}\"}"
+            }
+          ]
+        }
+      },
+      "gridPos": { "h": 6, "w": 8, "x": 8, "y": 0 }
+    },
+    {
+      "title": "Recent Logs",
+      "type": "logs",
+      "datasource": "Loki",
+      "targets": [
+        {
+          "expr": "{job=\"rippled\"} | json"
+        }
+      ],
+      "gridPos": { "h": 6, "w": 8, "x": 16, "y": 0 }
+    },
+    {
+      "title": "Trace Search",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\"}"
+        }
+      ],
+      "fieldConfig": {
+        "overrides": [
+          {
+            "matcher": { "id": "byName", "options": "traceID" },
+            "properties": [
+              {
+                "id": "links",
+                "value": [
+                  {
+                    "title": "View trace",
+                    "url": "/explore?left={\"datasource\":\"Tempo\",\"query\":\"${__value.raw}\"}"
+                  },
+                  {
+                    "title": "View logs",
+                    "url": "/explore?left={\"datasource\":\"Loki\",\"query\":\"{job=\\\"rippled\\\"} |= \\\"${__value.raw}\\\"\"}"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": { "h": 12, "w": 24, "x": 0, "y": 6 }
+    }
+  ]
+}
+```
+
+---
+
+_Previous: [Implementation Phases](./06-implementation-phases.md)_ | _Next: [Appendix](./08-appendix.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/08-appendix.md

@@ -0,0 +1,203 @@
+# Appendix
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Observability Backends](./07-observability-backends.md)
+
+---
+
+## 8.1 Glossary
+
+> **OTLP** = OpenTelemetry Protocol | **TxQ** = Transaction Queue
+
+| Term                  | Definition                                                 |
+| --------------------- | ---------------------------------------------------------- |
+| **Span**              | A unit of work with start/end time, name, and attributes   |
+| **Trace**             | A collection of spans representing a complete request flow |
+| **Trace ID**          | 128-bit unique identifier for a trace                      |
+| **Span ID**           | 64-bit unique identifier for a span within a trace         |
+| **Context**           | Carrier for trace/span IDs across boundaries               |
+| **Propagator**        | Component that injects/extracts context                    |
+| **Sampler**           | Decides which traces to record                             |
+| **Exporter**          | Sends spans to backend                                     |
+| **Collector**         | Receives, processes, and forwards telemetry                |
+| **OTLP**              | OpenTelemetry Protocol (wire format)                       |
+| **W3C Trace Context** | Standard HTTP headers for trace propagation                |
+| **Baggage**           | Key-value pairs propagated across service boundaries       |
+| **Resource**          | Entity producing telemetry (service, host, etc.)           |
+| **Instrumentation**   | Code that creates telemetry data                           |
+
+### rippled-Specific Terms
+
+| Term              | Definition                                                    |
+| ----------------- | ------------------------------------------------------------- |
+| **Overlay**       | P2P network layer managing peer connections                   |
+| **Consensus**     | XRP Ledger consensus algorithm (RCL)                          |
+| **Proposal**      | Validator's suggested transaction set for a ledger            |
+| **Validation**    | Validator's signature on a closed ledger                      |
+| **HashRouter**    | Component for transaction deduplication                       |
+| **JobQueue**      | Thread pool for asynchronous task execution                   |
+| **PerfLog**       | Existing performance logging system in rippled                |
+| **Beast Insight** | Existing metrics framework in rippled                         |
+| **PathFinding**   | Payment path computation engine for cross-currency payments   |
+| **TxQ**           | Transaction queue managing fee-based prioritization           |
+| **LoadManager**   | Dynamic fee escalation based on network load                  |
+| **SHAMap**        | SHA-256 hash-based map (Merkle trie variant) for ledger state |
+
+---
+
+## 8.2 Span Hierarchy Visualization
+
+> **TxQ** = Transaction Queue
+
+```mermaid
+flowchart TB
+    subgraph trace["Trace: Transaction Lifecycle"]
+        rpc["rpc.request<br/>(entry point)"]
+        validate["tx.validate"]
+        relay["tx.relay<br/>(parent span)"]
+
+        subgraph peers["Peer Spans"]
+            p1["peer.send<br/>Peer A"]
+            p2["peer.send<br/>Peer B"]
+            p3["peer.send<br/>Peer C"]
+        end
+
+        subgraph pathfinding["PathFinding Spans"]
+            pathfind["pathfind.request"]
+            pathcomp["pathfind.compute"]
+        end
+
+        consensus["consensus.round"]
+        apply["tx.apply"]
+
+        subgraph txqueue["TxQ Spans"]
+            txq["txq.enqueue"]
+            txqApply["txq.apply"]
+        end
+
+        feeCalc["fee.escalate"]
+    end
+
+    subgraph validators["Validator Spans"]
+        valFetch["validator.list.fetch"]
+        valManifest["validator.manifest"]
+    end
+
+    rpc --> validate
+    rpc --> pathfind
+    pathfind --> pathcomp
+    validate --> relay
+    relay --> p1
+    relay --> p2
+    relay --> p3
+    p1 -.->|"context propagation"| consensus
+    consensus --> apply
+    apply --> txq
+    txq --> txqApply
+    txq --> feeCalc
+
+    style trace fill:#0f172a,stroke:#020617,color:#fff
+    style peers fill:#1e3a8a,stroke:#172554,color:#fff
+    style pathfinding fill:#134e4a,stroke:#0f766e,color:#fff
+    style txqueue fill:#064e3b,stroke:#047857,color:#fff
+    style validators fill:#4c1d95,stroke:#6d28d9,color:#fff
+    style rpc fill:#1d4ed8,stroke:#1e40af,color:#fff
+    style validate fill:#047857,stroke:#064e3b,color:#fff
+    style relay fill:#047857,stroke:#064e3b,color:#fff
+    style p1 fill:#0e7490,stroke:#155e75,color:#fff
+    style p2 fill:#0e7490,stroke:#155e75,color:#fff
+    style p3 fill:#0e7490,stroke:#155e75,color:#fff
+    style consensus fill:#fef3c7,stroke:#fde68a,color:#1e293b
+    style apply fill:#047857,stroke:#064e3b,color:#fff
+    style pathfind fill:#0e7490,stroke:#155e75,color:#fff
+    style pathcomp fill:#0e7490,stroke:#155e75,color:#fff
+    style txq fill:#047857,stroke:#064e3b,color:#fff
+    style txqApply fill:#047857,stroke:#064e3b,color:#fff
+    style feeCalc fill:#047857,stroke:#064e3b,color:#fff
+    style valFetch fill:#6d28d9,stroke:#4c1d95,color:#fff
+    style valManifest fill:#6d28d9,stroke:#4c1d95,color:#fff
+```
+
+**Reading the diagram:**
+
+- **rpc.request (blue, top)**: The entry point — every traced transaction starts as an RPC call; this root span is the parent of all downstream work.
+- **tx.validate and pathfind.request (green/teal, first fork)**: The RPC request fans out into transaction validation and, for cross-currency payments, a PathFinding branch (`pathfind.request` -> `pathfind.compute`).
+- **tx.relay -> Peer Spans (teal, middle)**: After validation, the transaction is relayed to peers A, B, and C in parallel; each `peer.send` is a sibling child span showing fan-out across the network.
+- **context propagation (dashed arrow)**: The dotted line from `peer.send Peer A` to `consensus.round` represents the trace context crossing a node boundary — the receiving validator picks up the same `trace_id` and continues the trace.
+- **consensus.round -> tx.apply -> TxQ Spans (green, lower)**: Once consensus accepts the transaction, it is applied to the ledger; the TxQ spans (`txq.enqueue`, `txq.apply`, `fee.escalate`) capture queue depth and fee escalation behavior.
+- **Validator Spans (purple, detached)**: `validator.list.fetch` and `validator.manifest` are independent workflows for UNL management — they run on their own traces and are linked to consensus via Span Links, not parent-child relationships.
+
+---
+
+## 8.3 References
+
+> **OTLP** = OpenTelemetry Protocol
+
+### OpenTelemetry Resources
+
+1. [OpenTelemetry C++ SDK](https://github.com/open-telemetry/opentelemetry-cpp)
+2. [OpenTelemetry Specification](https://opentelemetry.io/docs/specs/otel/)
+3. [OpenTelemetry Collector](https://opentelemetry.io/docs/collector/)
+4. [OTLP Protocol Specification](https://opentelemetry.io/docs/specs/otlp/)
+
+### Standards
+
+5. [W3C Trace Context](https://www.w3.org/TR/trace-context/)
+6. [W3C Baggage](https://www.w3.org/TR/baggage/)
+7. [Protocol Buffers](https://protobuf.dev/)
+
+### rippled Resources
+
+8. [rippled Source Code](https://github.com/XRPLF/rippled)
+9. [XRP Ledger Documentation](https://xrpl.org/docs/)
+10. [rippled Overlay README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/README.md)
+11. [rippled RPC README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/README.md)
+12. [rippled Consensus README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/README.md)
+
+---
+
+## 8.4 Version History
+
+| Version | Date       | Author | Changes                                                        |
+| ------- | ---------- | ------ | -------------------------------------------------------------- |
+| 1.0     | 2026-02-12 | -      | Initial implementation plan                                    |
+| 1.1     | 2026-02-13 | -      | Refactored into modular documents                              |
+| 1.2     | 2026-03-24 | -      | Review fixes: accuracy corrections, cross-document consistency |
+
+---
+
+## 8.5 Document Index
+
+### Plan Documents
+
+| Document                                                             | Description                                  |
+| -------------------------------------------------------------------- | -------------------------------------------- |
+| [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)                       | Master overview and executive summary        |
+| [00-tracing-fundamentals.md](./00-tracing-fundamentals.md)           | Distributed tracing concepts and OTel primer |
+| [01-architecture-analysis.md](./01-architecture-analysis.md)         | rippled architecture and trace points        |
+| [02-design-decisions.md](./02-design-decisions.md)                   | SDK selection, exporters, span conventions   |
+| [03-implementation-strategy.md](./03-implementation-strategy.md)     | Directory structure, performance analysis    |
+| [04-code-samples.md](./04-code-samples.md)                           | C++ code examples for all components         |
+| [05-configuration-reference.md](./05-configuration-reference.md)     | rippled config, CMake, Collector configs     |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Timeline, tasks, risks, success metrics      |
+| [07-observability-backends.md](./07-observability-backends.md)       | Backend selection and architecture           |
+| [08-appendix.md](./08-appendix.md)                                   | Glossary, references, version history        |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Span/metric/dashboard inventory              |
+| [presentation.md](./presentation.md)                                 | Slide deck for OTel plan overview            |
+
+### Task Lists
+
+| Document                                                                   | Description                                         |
+| -------------------------------------------------------------------------- | --------------------------------------------------- |
+| [POC_taskList.md](./POC_taskList.md)                                       | Proof-of-concept telemetry integration              |
+| [Phase2_taskList.md](./Phase2_taskList.md)                                 | RPC layer trace instrumentation                     |
+| [Phase3_taskList.md](./Phase3_taskList.md)                                 | Peer overlay & consensus tracing                    |
+| [Phase4_taskList.md](./Phase4_taskList.md)                                 | Transaction lifecycle tracing                       |
+| [Phase5_taskList.md](./Phase5_taskList.md)                                 | Ledger processing & advanced tracing                |
+| [Phase5_IntegrationTest_taskList.md](./Phase5_IntegrationTest_taskList.md) | Observability stack integration tests               |
+| [Phase7_taskList.md](./Phase7_taskList.md)                                 | Native OTel metrics migration                       |
+| [presentation.md](./presentation.md)                                       | Presentation slides for OpenTelemetry plan overview |
+
+---
+
+_Previous: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/09-data-collection-reference.md

@@ -0,0 +1,559 @@
+# Observability Data Collection Reference
+
+> **Audience**: Developers and operators. This is the single source of truth for all telemetry data collected by rippled's observability stack.
+>
+> **Related docs**: [docs/telemetry-runbook.md](../docs/telemetry-runbook.md) (operator runbook with alerting and troubleshooting) | [03-implementation-strategy.md](./03-implementation-strategy.md) (code structure and performance optimization) | [04-code-samples.md](./04-code-samples.md) (C++ instrumentation examples)
+
+## Data Flow Overview
+
+```mermaid
+graph LR
+    subgraph rippledNode["rippled Node"]
+        A["Trace Macros<br/>XRPL_TRACE_SPAN<br/>(OTLP/HTTP exporter)"]
+        B["beast::insight<br/>OTel native metrics<br/>(OTLP/HTTP exporter)"]
+    end
+
+    subgraph collector["OTel Collector  :4317 / :4318"]
+        direction TB
+        R1["OTLP Receiver<br/>:4317 gRPC  |  :4318 HTTP<br/>(traces + metrics)"]
+        BP["Batch Processor<br/>timeout 1s, batch 100"]
+        SM["SpanMetrics Connector<br/>derives RED metrics<br/>from trace spans"]
+
+        R1 --> BP
+        BP --> SM
+    end
+
+    subgraph backends["Trace Backend"]
+        D["Grafana Tempo  :3200<br/>TraceQL search &<br/>S3/GCS long-term storage"]
+    end
+
+    subgraph metrics["Metrics Stack"]
+        E["Prometheus  :9090<br/>scrapes :8889<br/>span-derived + system metrics"]
+    end
+
+    subgraph viz["Visualization"]
+        F["Grafana  :3000<br/>10 dashboards"]
+    end
+
+    A -->|"OTLP/HTTP :4318<br/>(traces + attributes)"| R1
+    B -->|"OTLP/HTTP :4318<br/>(gauges, counters, histograms)"| R1
+
+    BP -->|"OTLP/gRPC :4317"| D
+
+    SM -->|"span_calls_total<br/>span_duration_ms<br/>(6 dimension labels)"| E
+    R1 -->|"rippled_* gauges<br/>rippled_* counters<br/>rippled_* histograms"| E
+
+    E -->|"Prometheus<br/>data source"| F
+    D -->|"Tempo<br/>data source"| F
+
+    style A fill:#4a90d9,color:#fff,stroke:#2a6db5
+    style B fill:#4a90d9,color:#fff,stroke:#2a6db5
+    style R1 fill:#5cb85c,color:#fff,stroke:#3d8b3d
+    style BP fill:#449d44,color:#fff,stroke:#2d6e2d
+    style SM fill:#449d44,color:#fff,stroke:#2d6e2d
+    style D fill:#f0ad4e,color:#000,stroke:#c78c2e
+    style E fill:#f0ad4e,color:#000,stroke:#c78c2e
+    style F fill:#5bc0de,color:#000,stroke:#3aa8c1
+    style rippledNode fill:#1a2633,color:#ccc,stroke:#4a90d9
+    style collector fill:#1a3320,color:#ccc,stroke:#5cb85c
+    style backends fill:#332a1a,color:#ccc,stroke:#f0ad4e
+    style metrics fill:#332a1a,color:#ccc,stroke:#f0ad4e
+    style viz fill:#1a2d33,color:#ccc,stroke:#5bc0de
+```
+
+There are two independent telemetry pipelines entering a single **OTel Collector** via the same OTLP receiver:
+
+1. **OpenTelemetry Traces** — Distributed spans with attributes, exported via OTLP/HTTP (:4318) to the collector's **OTLP Receiver**. The **Batch Processor** groups spans (1s timeout, batch size 100) before forwarding to trace backends. The **SpanMetrics Connector** derives RED metrics (rate, errors, duration) from every span and feeds them into the metrics pipeline.
+2. **beast::insight OTel Metrics** — System-level gauges, counters, and histograms exported natively via OTLP/HTTP (:4318) to the same **OTLP Receiver**. These are batched and exported to Prometheus alongside span-derived metrics. The StatsD UDP transport has been replaced by native OTLP; `server=statsd` remains available as a fallback.
+
+**Trace backend** — The collector exports traces via OTLP/gRPC to:
+
+- **Grafana Tempo** — Preferred trace backend. Supports TraceQL queries at `:3200`, S3/GCS object storage for cost-effective long-term trace retention, and integrates natively with Grafana.
+
+> **Further reading**: [00-tracing-fundamentals.md](./00-tracing-fundamentals.md) for core OpenTelemetry concepts (traces, spans, context propagation, sampling). [07-observability-backends.md](./07-observability-backends.md) for production backend selection, collector placement, and sampling strategies.
+
+---
+
+## 1. OpenTelemetry Spans
+
+### 1.1 Complete Span Inventory (16 spans)
+
+> **See also**: [02-design-decisions.md §2.3](./02-design-decisions.md#23-span-naming-conventions) for naming conventions and the full span catalog with rationale. [04-code-samples.md §4.6](./04-code-samples.md#46-span-flow-visualization) for span flow diagrams.
+
+#### RPC Spans
+
+Controlled by `trace_rpc=1` in `[telemetry]` config.
+
+| Span Name            | Parent        | Source File       | Description                                                              |
+| -------------------- | ------------- | ----------------- | ------------------------------------------------------------------------ |
+| `rpc.request`        | —             | ServerHandler.cpp | Top-level HTTP RPC request entry point                                   |
+| `rpc.process`        | `rpc.request` | ServerHandler.cpp | RPC processing pipeline                                                  |
+| `rpc.ws_message`     | —             | ServerHandler.cpp | WebSocket message handling                                               |
+| `rpc.command.<name>` | `rpc.process` | RPCHandler.cpp    | Per-command span (e.g., `rpc.command.server_info`, `rpc.command.ledger`) |
+
+**Where to find**: Tempo → TraceQL: `{resource.service.name="rippled" && name=~"rpc.request|rpc.command.*"}`
+
+**Grafana dashboard**: _RPC Performance_ (`rippled-rpc-perf`)
+
+#### Transaction Spans
+
+Controlled by `trace_transactions=1` in `[telemetry]` config.
+
+| Span Name    | Parent         | Source File     | Description                                                       |
+| ------------ | -------------- | --------------- | ----------------------------------------------------------------- |
+| `tx.process` | —              | NetworkOPs.cpp  | Transaction submission entry point (local or peer-relayed)        |
+| `tx.receive` | —              | PeerImp.cpp     | Raw transaction received from peer overlay (before deduplication) |
+| `tx.apply`   | `ledger.build` | BuildLedger.cpp | Transaction set applied to new ledger during consensus            |
+
+**Where to find**: Tempo → TraceQL: `{resource.service.name="rippled" && name=~"tx.process|tx.receive"}`
+
+**Grafana dashboard**: _Transaction Overview_ (`rippled-transactions`)
+
+#### Consensus Spans
+
+Controlled by `trace_consensus=1` in `[telemetry]` config.
+
+| Span Name                   | Parent | Source File      | Description                                   |
+| --------------------------- | ------ | ---------------- | --------------------------------------------- |
+| `consensus.proposal.send`   | —      | RCLConsensus.cpp | Node broadcasts its transaction set proposal  |
+| `consensus.ledger_close`    | —      | RCLConsensus.cpp | Ledger close event triggered by consensus     |
+| `consensus.accept`          | —      | RCLConsensus.cpp | Consensus accepts a ledger (round complete)   |
+| `consensus.validation.send` | —      | RCLConsensus.cpp | Validation message sent after ledger accepted |
+| `consensus.accept.apply`    | —      | RCLConsensus.cpp | Ledger application with close time details    |
+
+**Where to find**: Tempo → TraceQL: `{resource.service.name="rippled" && name=~"consensus.*"}`
+
+**Grafana dashboard**: _Consensus Health_ (`rippled-consensus`)
+
+#### Ledger Spans
+
+Controlled by `trace_ledger=1` in `[telemetry]` config.
+
+| Span Name         | Parent | Source File      | Description                                    |
+| ----------------- | ------ | ---------------- | ---------------------------------------------- |
+| `ledger.build`    | —      | BuildLedger.cpp  | Build new ledger from accepted transaction set |
+| `ledger.validate` | —      | LedgerMaster.cpp | Ledger promoted to validated status            |
+| `ledger.store`    | —      | LedgerMaster.cpp | Ledger stored to database/history              |
+
+**Where to find**: Tempo → TraceQL: `{resource.service.name="rippled" && name=~"ledger.*"}`
+
+**Grafana dashboard**: _Ledger Operations_ (`rippled-ledger-ops`)
+
+#### Peer Spans
+
+Controlled by `trace_peer=1` in `[telemetry]` config. **Disabled by default** (high volume).
+
+| Span Name                 | Parent | Source File | Description                           |
+| ------------------------- | ------ | ----------- | ------------------------------------- |
+| `peer.proposal.receive`   | —      | PeerImp.cpp | Consensus proposal received from peer |
+| `peer.validation.receive` | —      | PeerImp.cpp | Validation message received from peer |
+
+**Where to find**: Tempo → TraceQL: `{resource.service.name="rippled" && name=~"peer.*"}`
+
+**Grafana dashboard**: _Peer Network_ (`rippled-peer-net`)
+
+---
+
+### 1.2 Complete Attribute Inventory (22 attributes)
+
+> **See also**: [02-design-decisions.md §2.4.2](./02-design-decisions.md#242-span-attributes-by-category) for attribute design rationale and privacy considerations.
+
+Every span can carry key-value attributes that provide context for filtering and aggregation.
+
+#### RPC Attributes
+
+| Attribute                | Type   | Set On          | Description                                      |
+| ------------------------ | ------ | --------------- | ------------------------------------------------ |
+| `xrpl.rpc.command`       | string | `rpc.command.*` | RPC command name (e.g., `server_info`, `ledger`) |
+| `xrpl.rpc.version`       | int64  | `rpc.command.*` | API version number                               |
+| `xrpl.rpc.role`          | string | `rpc.command.*` | Caller role: `"admin"` or `"user"`               |
+| `xrpl.rpc.status`        | string | `rpc.command.*` | Result: `"success"` or `"error"`                 |
+| `xrpl.rpc.duration_ms`   | int64  | `rpc.command.*` | Command execution time in milliseconds           |
+| `xrpl.rpc.error_message` | string | `rpc.command.*` | Error details (only set on failure)              |
+
+**Tempo query**: `{span.xrpl.rpc.command="server_info"}` to find all `server_info` calls.
+
+**Prometheus label**: `xrpl_rpc_command` (dots converted to underscores by SpanMetrics).
+
+#### Transaction Attributes
+
+| Attribute            | Type    | Set On                     | Description                                          |
+| -------------------- | ------- | -------------------------- | ---------------------------------------------------- |
+| `xrpl.tx.hash`       | string  | `tx.process`, `tx.receive` | Transaction hash (hex-encoded)                       |
+| `xrpl.tx.local`      | boolean | `tx.process`               | `true` if locally submitted, `false` if peer-relayed |
+| `xrpl.tx.path`       | string  | `tx.process`               | Submission path: `"sync"` or `"async"`               |
+| `xrpl.tx.suppressed` | boolean | `tx.receive`               | `true` if transaction was suppressed (duplicate)     |
+| `xrpl.tx.status`     | string  | `tx.receive`               | Transaction status (e.g., `"known_bad"`)             |
+
+**Tempo query**: `{span.xrpl.tx.hash="<hash>"}` to trace a specific transaction across nodes.
+
+**Prometheus label**: `xrpl_tx_local` (used as SpanMetrics dimension).
+
+#### Consensus Attributes
+
+| Attribute                            | Type    | Set On                                                                                              | Description                                                   |
+| ------------------------------------ | ------- | --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------- |
+| `xrpl.consensus.round`               | int64   | `consensus.proposal.send`                                                                           | Consensus round number                                        |
+| `xrpl.consensus.mode`                | string  | `consensus.proposal.send`, `consensus.ledger_close`                                                 | Node mode: `"syncing"`, `"tracking"`, `"full"`, `"proposing"` |
+| `xrpl.consensus.proposers`           | int64   | `consensus.proposal.send`, `consensus.accept`                                                       | Number of proposers in the round                              |
+| `xrpl.consensus.proposing`           | boolean | `consensus.validation.send`                                                                         | Whether this node was a proposer                              |
+| `xrpl.consensus.ledger.seq`          | int64   | `consensus.ledger_close`, `consensus.accept`, `consensus.validation.send`, `consensus.accept.apply` | Ledger sequence number                                        |
+| `xrpl.consensus.close_time`          | int64   | `consensus.accept.apply`                                                                            | Agreed-upon ledger close time (epoch seconds)                 |
+| `xrpl.consensus.close_time_correct`  | boolean | `consensus.accept.apply`                                                                            | Whether validators reached agreement on close time            |
+| `xrpl.consensus.close_resolution_ms` | int64   | `consensus.accept.apply`                                                                            | Close time rounding granularity in milliseconds               |
+| `xrpl.consensus.state`               | string  | `consensus.accept.apply`                                                                            | Consensus outcome: `"finished"` or `"moved_on"`               |
+| `xrpl.consensus.round_time_ms`       | int64   | `consensus.accept.apply`                                                                            | Total consensus round duration in milliseconds                |
+
+**Tempo query**: `{span.xrpl.consensus.mode="proposing"}` to find rounds where node was proposing.
+
+**Prometheus label**: `xrpl_consensus_mode` (used as SpanMetrics dimension).
+
+#### Ledger Attributes
+
+| Attribute                 | Type  | Set On                                                        | Description                                    |
+| ------------------------- | ----- | ------------------------------------------------------------- | ---------------------------------------------- |
+| `xrpl.ledger.seq`         | int64 | `ledger.build`, `ledger.validate`, `ledger.store`, `tx.apply` | Ledger sequence number                         |
+| `xrpl.ledger.validations` | int64 | `ledger.validate`                                             | Number of validations received for this ledger |
+| `xrpl.ledger.tx_count`    | int64 | `ledger.build`, `tx.apply`                                    | Transactions in the ledger                     |
+| `xrpl.ledger.tx_failed`   | int64 | `ledger.build`, `tx.apply`                                    | Failed transactions in the ledger              |
+
+**Tempo query**: `{span.xrpl.ledger.seq=12345}` to find all spans for a specific ledger.
+
+#### Peer Attributes
+
+| Attribute                      | Type    | Set On                                                           | Description                                          |
+| ------------------------------ | ------- | ---------------------------------------------------------------- | ---------------------------------------------------- |
+| `xrpl.peer.id`                 | int64   | `tx.receive`, `peer.proposal.receive`, `peer.validation.receive` | Peer identifier                                      |
+| `xrpl.peer.proposal.trusted`   | boolean | `peer.proposal.receive`                                          | Whether the proposal came from a trusted validator   |
+| `xrpl.peer.validation.trusted` | boolean | `peer.validation.receive`                                        | Whether the validation came from a trusted validator |
+
+**Prometheus labels**: `xrpl_peer_proposal_trusted`, `xrpl_peer_validation_trusted` (SpanMetrics dimensions).
+
+---
+
+### 1.3 SpanMetrics — Derived Prometheus Metrics
+
+> **See also**: [01-architecture-analysis.md](./01-architecture-analysis.md) §1.8.2 for how span-derived metrics map to operational insights.
+
+The OTel Collector's SpanMetrics connector automatically generates RED (Rate, Errors, Duration) metrics from every span. No custom metrics code in rippled is needed.
+
+| Prometheus Metric                                  | Type      | Description                                                                    |
+| -------------------------------------------------- | --------- | ------------------------------------------------------------------------------ |
+| `traces_span_metrics_calls_total`                  | Counter   | Total span invocations                                                         |
+| `traces_span_metrics_duration_milliseconds_bucket` | Histogram | Latency distribution (buckets: 1, 5, 10, 25, 50, 100, 250, 500, 1000, 5000 ms) |
+| `traces_span_metrics_duration_milliseconds_count`  | Histogram | Observation count                                                              |
+| `traces_span_metrics_duration_milliseconds_sum`    | Histogram | Cumulative latency                                                             |
+
+**Standard labels on every metric**: `span_name`, `status_code`, `service_name`, `span_kind`
+
+**Additional dimension labels** (configured in `otel-collector-config.yaml`):
+
+| Span Attribute                 | Prometheus Label               | Applies To                |
+| ------------------------------ | ------------------------------ | ------------------------- |
+| `xrpl.rpc.command`             | `xrpl_rpc_command`             | `rpc.command.*`           |
+| `xrpl.rpc.status`              | `xrpl_rpc_status`              | `rpc.command.*`           |
+| `xrpl.consensus.mode`          | `xrpl_consensus_mode`          | `consensus.ledger_close`  |
+| `xrpl.tx.local`                | `xrpl_tx_local`                | `tx.process`              |
+| `xrpl.peer.proposal.trusted`   | `xrpl_peer_proposal_trusted`   | `peer.proposal.receive`   |
+| `xrpl.peer.validation.trusted` | `xrpl_peer_validation_trusted` | `peer.validation.receive` |
+
+**Where to query**: Prometheus → `traces_span_metrics_calls_total{span_name="rpc.command.server_info"}`
+
+---
+
+## 2. System Metrics (beast::insight — OTel native)
+
+> **See also**: [02-design-decisions.md](./02-design-decisions.md) for the beast::insight coexistence design. [06-implementation-phases.md](./06-implementation-phases.md) for the Phase 6/7 metric inventory.
+>
+> **Migration complete**: Phase 7 replaced the StatsD UDP transport with native OTel Metrics SDK export via OTLP/HTTP. The `beast::insight::Collector` interface and all metric names are preserved — only the wire protocol changed. `[insight] server=statsd` remains as a fallback.
+
+These are system-level metrics emitted by rippled's `beast::insight` framework via OTel OTLP/HTTP. They cover operational data that doesn't map to individual trace spans.
+
+### Configuration
+
+```ini
+# Recommended: native OTel metrics via OTLP/HTTP
+[insight]
+server=otel
+endpoint=http://localhost:4318/v1/metrics
+prefix=rippled
+```
+
+Fallback (StatsD):
+
+```ini
+[insight]
+server=statsd
+address=127.0.0.1:8125
+prefix=rippled
+```
+
+### 2.1 Gauges
+
+| Prometheus Metric                                   | Source File           | Description                               | Typical Range                   |
+| --------------------------------------------------- | --------------------- | ----------------------------------------- | ------------------------------- |
+| `rippled_LedgerMaster_Validated_Ledger_Age`         | LedgerMaster.h        | Seconds since last validated ledger       | 0–10 (healthy), >30 (stale)     |
+| `rippled_LedgerMaster_Published_Ledger_Age`         | LedgerMaster.h        | Seconds since last published ledger       | 0–10 (healthy)                  |
+| `rippled_State_Accounting_Disconnected_duration`    | NetworkOPs.cpp        | Cumulative seconds in Disconnected state  | Monotonic                       |
+| `rippled_State_Accounting_Connected_duration`       | NetworkOPs.cpp        | Cumulative seconds in Connected state     | Monotonic                       |
+| `rippled_State_Accounting_Syncing_duration`         | NetworkOPs.cpp        | Cumulative seconds in Syncing state       | Monotonic                       |
+| `rippled_State_Accounting_Tracking_duration`        | NetworkOPs.cpp        | Cumulative seconds in Tracking state      | Monotonic                       |
+| `rippled_State_Accounting_Full_duration`            | NetworkOPs.cpp        | Cumulative seconds in Full state          | Monotonic (should dominate)     |
+| `rippled_State_Accounting_Disconnected_transitions` | NetworkOPs.cpp        | Count of transitions to Disconnected      | Low                             |
+| `rippled_State_Accounting_Connected_transitions`    | NetworkOPs.cpp        | Count of transitions to Connected         | Low                             |
+| `rippled_State_Accounting_Syncing_transitions`      | NetworkOPs.cpp        | Count of transitions to Syncing           | Low                             |
+| `rippled_State_Accounting_Tracking_transitions`     | NetworkOPs.cpp        | Count of transitions to Tracking          | Low                             |
+| `rippled_State_Accounting_Full_transitions`         | NetworkOPs.cpp        | Count of transitions to Full              | Low (should be 1 after startup) |
+| `rippled_Peer_Finder_Active_Inbound_Peers`          | PeerfinderManager.cpp | Active inbound peer connections           | 0–85                            |
+| `rippled_Peer_Finder_Active_Outbound_Peers`         | PeerfinderManager.cpp | Active outbound peer connections          | 10–21                           |
+| `rippled_Overlay_Peer_Disconnects`                  | OverlayImpl.cpp       | Cumulative peer disconnection count       | Low growth                      |
+| `rippled_Overlay_Peer_Disconnects_Charges`          | OverlayImpl.cpp       | Disconnects due to resource limit charges | Low growth (subset of above)    |
+| `rippled_job_count`                                 | JobQueue.cpp          | Current job queue depth                   | 0–100 (healthy)                 |
+
+**Grafana dashboard**: _Node Health (System Metrics)_ (`rippled-system-node-health`)
+
+### 2.2 Counters
+
+| Prometheus Metric                 | Source File        | Description                                   |
+| --------------------------------- | ------------------ | --------------------------------------------- |
+| `rippled_rpc_requests`            | ServerHandler.cpp  | Total RPC requests received                   |
+| `rippled_ledger_fetches`          | InboundLedgers.cpp | Inbound ledger fetch attempts                 |
+| `rippled_ledger_history_mismatch` | LedgerHistory.cpp  | Ledger hash mismatches detected               |
+| `rippled_warn`                    | Logic.h            | Resource manager warnings issued              |
+| `rippled_drop`                    | Logic.h            | Resource manager drops (connections rejected) |
+
+**Note**: With `server=otel`, `rippled_warn` and `rippled_drop` are properly exported as OTel Counter instruments. The previous StatsD `|m` type limitation no longer applies.
+
+**Grafana dashboard**: _RPC & Pathfinding (System Metrics)_ (`rippled-system-rpc`)
+
+### 2.3 Histograms (Event timers)
+
+| Prometheus Metric       | Source File       | Unit  | Description                    |
+| ----------------------- | ----------------- | ----- | ------------------------------ |
+| `rippled_rpc_time`      | ServerHandler.cpp | ms    | RPC response time distribution |
+| `rippled_rpc_size`      | ServerHandler.cpp | bytes | RPC response size distribution |
+| `rippled_ios_latency`   | Application.cpp   | ms    | I/O service loop latency       |
+| `rippled_pathfind_fast` | PathRequests.h    | ms    | Fast pathfinding duration      |
+| `rippled_pathfind_full` | PathRequests.h    | ms    | Full pathfinding duration      |
+
+Quantiles collected: 0th, 50th, 90th, 95th, 99th, 100th percentile.
+
+**Grafana dashboards**: _Node Health_ (`ios_latency`), _RPC & Pathfinding_ (`rpc_time`, `rpc_size`, `pathfind_*`)
+
+### 2.4 Overlay Traffic Metrics
+
+For each of the 45+ overlay traffic categories (defined in `TrafficCount.h`), four gauges are emitted:
+
+- `rippled_{category}_Bytes_In`
+- `rippled_{category}_Bytes_Out`
+- `rippled_{category}_Messages_In`
+- `rippled_{category}_Messages_Out`
+
+**Key categories**:
+
+| Category                                                          | Description                |
+| ----------------------------------------------------------------- | -------------------------- |
+| `total`                                                           | All traffic aggregated     |
+| `overhead` / `overhead_overlay`                                   | Protocol overhead          |
+| `transactions` / `transactions_duplicate`                         | Transaction relay          |
+| `proposals` / `proposals_untrusted` / `proposals_duplicate`       | Consensus proposals        |
+| `validations` / `validations_untrusted` / `validations_duplicate` | Consensus validations      |
+| `ledger_data_get` / `ledger_data_share`                           | Ledger data exchange       |
+| `ledger_data_Transaction_Node_get/share`                          | Transaction node data      |
+| `ledger_data_Account_State_Node_get/share`                        | Account state node data    |
+| `ledger_data_Transaction_Set_candidate_get/share`                 | Transaction set candidates |
+| `getObject` / `haveTxSet` / `ledgerData`                          | Object requests            |
+| `ping` / `status`                                                 | Keepalive and status       |
+| `set_get`                                                         | Set requests               |
+
+**Grafana dashboards**: _Network Traffic_ (`rippled-system-network`), _Overlay Traffic Detail_ (`rippled-system-overlay-detail`), _Ledger Data & Sync_ (`rippled-system-ledger-sync`)
+
+---
+
+## 3. Grafana Dashboard Reference
+
+> **See also**: [05-configuration-reference.md](./05-configuration-reference.md) §5.8 for Grafana data source provisioning (Tempo, Prometheus) and TraceQL query examples.
+
+### 3.1 Span-Derived Dashboards (5)
+
+| Dashboard            | UID                    | Data Source              | Key Panels                                                                         |
+| -------------------- | ---------------------- | ------------------------ | ---------------------------------------------------------------------------------- |
+| RPC Performance      | `rippled-rpc-perf`     | Prometheus (SpanMetrics) | Request rate by command, p95 latency by command, error rate, heatmap, top commands |
+| Transaction Overview | `rippled-transactions` | Prometheus (SpanMetrics) | Processing rate, latency p95/p50, local vs relay split, apply duration, heatmap    |
+| Consensus Health     | `rippled-consensus`    | Prometheus (SpanMetrics) | Round duration p95/p50, proposals rate, close duration, mode timeline, heatmap     |
+| Ledger Operations    | `rippled-ledger-ops`   | Prometheus (SpanMetrics) | Build rate, build duration, validation rate, store rate, build vs close comparison |
+| Peer Network         | `rippled-peer-net`     | Prometheus (SpanMetrics) | Proposal receive rate, validation receive rate, trusted vs untrusted breakdown     |
+
+### 3.2 System Metrics Dashboards (5)
+
+| Dashboard              | UID                             | Data Source       | Key Panels                                                                        |
+| ---------------------- | ------------------------------- | ----------------- | --------------------------------------------------------------------------------- |
+| Node Health            | `rippled-system-node-health`    | Prometheus (OTLP) | Ledger age, operating mode, I/O latency, job queue, fetch rate                    |
+| Network Traffic        | `rippled-system-network`        | Prometheus (OTLP) | Active peers, disconnects, bytes in/out, messages in/out, traffic by category     |
+| RPC & Pathfinding      | `rippled-system-rpc`            | Prometheus (OTLP) | RPC rate, response time/size, pathfinding duration, resource warnings/drops       |
+| Overlay Traffic Detail | `rippled-system-overlay-detail` | Prometheus (OTLP) | Squelch, overhead, validator lists, set get/share, have/requested tx, proof paths |
+| Ledger Data & Sync     | `rippled-system-ledger-sync`    | Prometheus (OTLP) | Ledger data exchange, legacy ledger share/get, getobject by type, traffic heatmap |
+
+### 3.3 Accessing the Dashboards
+
+1. Open Grafana at **http://localhost:3000**
+2. Navigate to **Dashboards → rippled** folder
+3. All 10 dashboards are auto-provisioned from `docker/telemetry/grafana/dashboards/`
+
+---
+
+## 4. Tempo Trace Search Guide
+
+> **See also**: [08-appendix.md](./08-appendix.md) §8.2 for span hierarchy visualizations. [05-configuration-reference.md](./05-configuration-reference.md) §5.8.5 for TraceQL query examples.
+
+### Finding Traces by Type
+
+| What to Find             | Tempo TraceQL Query                                                              |
+| ------------------------ | -------------------------------------------------------------------------------- |
+| All RPC calls            | `{resource.service.name="rippled" && name="rpc.request"}`                        |
+| Specific RPC command     | `{resource.service.name="rippled" && name="rpc.command.server_info"}`            |
+| Slow RPC calls           | `{resource.service.name="rippled" && name=~"rpc.command.*"} \| duration > 100ms` |
+| Failed RPC calls         | `{span.xrpl.rpc.status="error"}`                                                 |
+| Specific transaction     | `{span.xrpl.tx.hash="<hex_hash>"}`                                               |
+| Local transactions only  | `{span.xrpl.tx.local=true}`                                                      |
+| Consensus rounds         | `{resource.service.name="rippled" && name="consensus.accept"}`                   |
+| Rounds by mode           | `{span.xrpl.consensus.mode="proposing"}`                                         |
+| Specific ledger          | `{span.xrpl.ledger.seq=12345}`                                                   |
+| Peer proposals (trusted) | `{span.xrpl.peer.proposal.trusted=true}`                                         |
+
+### Trace Structure
+
+A typical RPC trace shows the span hierarchy:
+
+```
+rpc.request (ServerHandler)
+  └── rpc.process (ServerHandler)
+       └── rpc.command.server_info (RPCHandler)
+```
+
+A consensus round produces independent spans (not parent-child):
+
+```
+consensus.ledger_close        (close event)
+consensus.proposal.send       (broadcast proposal)
+ledger.build                  (build new ledger)
+  └── tx.apply                (apply transaction set)
+consensus.accept              (accept result)
+consensus.validation.send     (send validation)
+ledger.validate               (promote to validated)
+ledger.store                  (persist to DB)
+```
+
+---
+
+## 5. Prometheus Query Examples
+
+> **See also**: [05-configuration-reference.md](./05-configuration-reference.md) §5.8.7 for correlating Prometheus system metrics with trace-derived metrics.
+
+### Span-Derived Metrics
+
+```promql
+# RPC request rate by command (last 5 minutes)
+sum by (xrpl_rpc_command) (rate(traces_span_metrics_calls_total{span_name=~"rpc.command.*"}[5m]))
+
+# RPC p95 latency by command
+histogram_quantile(0.95, sum by (le, xrpl_rpc_command) (rate(traces_span_metrics_duration_milliseconds_bucket{span_name=~"rpc.command.*"}[5m])))
+
+# Consensus round duration p95
+histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{span_name="consensus.accept"}[5m])))
+
+# Transaction processing rate (local vs relay)
+sum by (xrpl_tx_local) (rate(traces_span_metrics_calls_total{span_name="tx.process"}[5m]))
+
+# Trusted vs untrusted proposal rate
+sum by (xrpl_peer_proposal_trusted) (rate(traces_span_metrics_calls_total{span_name="peer.proposal.receive"}[5m]))
+```
+
+### StatsD Metrics
+
+```promql
+# Validated ledger age (should be < 10s)
+rippled_LedgerMaster_Validated_Ledger_Age
+
+# Active peer count
+rippled_Peer_Finder_Active_Inbound_Peers + rippled_Peer_Finder_Active_Outbound_Peers
+
+# RPC response time p95
+histogram_quantile(0.95, rippled_rpc_time_bucket)
+
+# Total network bytes in (rate)
+rate(rippled_total_Bytes_In[5m])
+
+# Operating mode (should be "Full" after startup)
+rippled_State_Accounting_Full_duration
+```
+
+---
+
+## 6. Known Issues
+
+| Issue                                                              | Impact                                           | Status                                                               |
+| ------------------------------------------------------------------ | ------------------------------------------------ | -------------------------------------------------------------------- |
+| `warn` and `drop` metrics use non-standard StatsD `\|m` meter type | Metrics silently dropped by OTel StatsD receiver | Phase 6 Task 6.1 — needs `\|m` → `\|c` change in StatsDCollector.cpp |
+| `rippled_job_count` may not emit in standalone mode                | Missing from Prometheus in some test configs     | Requires active job queue activity                                   |
+| `rippled_rpc_requests` depends on `[insight]` config               | Zero series if StatsD not configured             | Requires `[insight] server=statsd` in xrpld.cfg                      |
+| Peer tracing disabled by default                                   | No `peer.*` spans unless `trace_peer=1`          | Intentional — high volume on mainnet                                 |
+
+---
+
+## 7. Privacy and Data Collection
+
+The telemetry system is designed with privacy in mind:
+
+- **No private keys** are ever included in spans or metrics
+- **No account balances** or financial data is traced
+- **Transaction hashes** are included (public on-ledger data) but not transaction contents
+- **Peer IDs** are internal identifiers, not IP addresses
+- **All telemetry is opt-in** — disabled by default at build time (`-Dtelemetry=OFF`)
+- **Sampling** reduces data volume — `sampling_ratio=0.01` recommended for production
+- **Data stays local** — the default stack sends data to `localhost` only
+
+---
+
+## 8. Configuration Quick Reference
+
+> **Full reference**: [05-configuration-reference.md](./05-configuration-reference.md) §5.1 for all `[telemetry]` options with defaults, the config parser implementation, and collector YAML configurations (dev and production).
+
+### Minimal Setup (development)
+
+```ini
+[telemetry]
+enabled=1
+
+[insight]
+server=statsd
+address=127.0.0.1:8125
+prefix=rippled
+```
+
+### Production Setup
+
+```ini
+[telemetry]
+enabled=1
+endpoint=http://otel-collector:4318/v1/traces
+sampling_ratio=0.01
+trace_peer=0
+batch_size=1024
+max_queue_size=4096
+
+[insight]
+server=statsd
+address=otel-collector:8125
+prefix=rippled
+```
+
+### Trace Category Toggle
+
+| Config Key           | Default | Controls                     |
+| -------------------- | ------- | ---------------------------- |
+| `trace_rpc`          | `1`     | `rpc.*` spans                |
+| `trace_transactions` | `1`     | `tx.*` spans                 |
+| `trace_consensus`    | `1`     | `consensus.*` spans          |
+| `trace_ledger`       | `1`     | `ledger.*` spans             |
+| `trace_peer`         | `0`     | `peer.*` spans (high volume) |

OpenTelemetryPlan/OpenTelemetryPlan.md

@@ -0,0 +1,244 @@
+# [OpenTelemetry](00-tracing-fundamentals.md) Distributed Tracing Implementation Plan for rippled (xrpld)
+
+## Executive Summary
+
+> **OTLP** = OpenTelemetry Protocol
+
+This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the rippled XRP Ledger node software. The plan addresses the unique challenges of a decentralized peer-to-peer system where trace context must propagate across network boundaries between independent nodes.
+
+### Key Benefits
+
+- **End-to-end transaction visibility**: Track transactions from submission through consensus to ledger inclusion
+- **Consensus round analysis**: Understand timing and behavior of consensus phases across validators
+- **RPC performance insights**: Identify slow handlers and optimize response times
+- **Network topology understanding**: Visualize message propagation patterns between peers
+- **Incident debugging**: Correlate events across distributed nodes during issues
+
+### Estimated Performance Overhead
+
+| Metric        | Overhead   | Notes                               |
+| ------------- | ---------- | ----------------------------------- |
+| CPU           | 1-3%       | Span creation and attribute setting |
+| Memory        | 2-5 MB     | Batch buffer for pending spans      |
+| Network       | 10-50 KB/s | Compressed OTLP export to collector |
+| Latency (p99) | <2%        | With proper sampling configuration  |
+
+---
+
+## Document Structure
+
+This implementation plan is organized into modular documents for easier navigation:
+
+<div align="center">
+
+```mermaid
+flowchart TB
+    overview["📋 OpenTelemetryPlan.md<br/>(This Document)"]
+
+    subgraph fundamentals["Fundamentals"]
+        fund["00-tracing-fundamentals.md"]
+    end
+
+    subgraph analysis["Analysis & Design"]
+        arch["01-architecture-analysis.md"]
+        design["02-design-decisions.md"]
+    end
+
+    subgraph impl["Implementation"]
+        strategy["03-implementation-strategy.md"]
+        code["04-code-samples.md"]
+        config["05-configuration-reference.md"]
+    end
+
+    subgraph deploy["Deployment & Planning"]
+        phases["06-implementation-phases.md"]
+        backends["07-observability-backends.md"]
+        appendix["08-appendix.md"]
+        poc["POC_taskList.md"]
+        dataref["09-data-collection-reference.md"]
+    end
+
+    overview --> fundamentals
+    overview --> analysis
+    overview --> impl
+    overview --> deploy
+
+    fund --> arch
+    arch --> design
+    design --> strategy
+    strategy --> code
+    code --> config
+    config --> phases
+    phases --> backends
+    backends --> appendix
+    phases --> poc
+    appendix --> dataref
+
+    style overview fill:#1b5e20,stroke:#0d3d14,color:#fff,stroke-width:2px
+    style fundamentals fill:#00695c,stroke:#004d40,color:#fff
+    style fund fill:#00695c,stroke:#004d40,color:#fff
+    style analysis fill:#0d47a1,stroke:#082f6a,color:#fff
+    style impl fill:#bf360c,stroke:#8c2809,color:#fff
+    style deploy fill:#4a148c,stroke:#2e0d57,color:#fff
+    style arch fill:#0d47a1,stroke:#082f6a,color:#fff
+    style design fill:#0d47a1,stroke:#082f6a,color:#fff
+    style strategy fill:#bf360c,stroke:#8c2809,color:#fff
+    style code fill:#bf360c,stroke:#8c2809,color:#fff
+    style config fill:#bf360c,stroke:#8c2809,color:#fff
+    style phases fill:#4a148c,stroke:#2e0d57,color:#fff
+    style backends fill:#4a148c,stroke:#2e0d57,color:#fff
+    style appendix fill:#4a148c,stroke:#2e0d57,color:#fff
+    style poc fill:#4a148c,stroke:#2e0d57,color:#fff
+    style dataref fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+</div>
+
+---
+
+## Table of Contents
+
+| Section | Document                                                       | Description                                                            |
+| ------- | -------------------------------------------------------------- | ---------------------------------------------------------------------- |
+| **0**   | [Tracing Fundamentals](./00-tracing-fundamentals.md)           | Distributed tracing concepts, span relationships, context propagation  |
+| **1**   | [Architecture Analysis](./01-architecture-analysis.md)         | rippled component analysis, trace points, instrumentation priorities   |
+| **2**   | [Design Decisions](./02-design-decisions.md)                   | SDK selection, exporters, span naming, attributes, context propagation |
+| **3**   | [Implementation Strategy](./03-implementation-strategy.md)     | Directory structure, key principles, performance optimization          |
+| **4**   | [Code Samples](./04-code-samples.md)                           | C++ implementation examples for core infrastructure and key modules    |
+| **5**   | [Configuration Reference](./05-configuration-reference.md)     | rippled config, CMake integration, Collector configurations            |
+| **6**   | [Implementation Phases](./06-implementation-phases.md)         | 5-phase timeline, tasks, risks, success metrics                        |
+| **7**   | [Observability Backends](./07-observability-backends.md)       | Backend selection guide and production architecture                    |
+| **8**   | [Appendix](./08-appendix.md)                                   | Glossary, references, version history                                  |
+| **9**   | [Data Collection Reference](./09-data-collection-reference.md) | Complete inventory of spans, attributes, metrics, and dashboards       |
+| **POC** | [POC Task List](./POC_taskList.md)                             | Proof of concept tasks for RPC tracing end-to-end demo                 |
+
+---
+
+## 0. Tracing Fundamentals
+
+This document introduces distributed tracing concepts for readers unfamiliar with the domain. It covers what traces and spans are, how parent-child and follows-from relationships model causality, how context propagates across service boundaries, and how sampling controls data volume. It also maps these concepts to rippled-specific scenarios like transaction relay and consensus.
+
+➡️ **[Read Tracing Fundamentals](./00-tracing-fundamentals.md)**
+
+---
+
+## 1. Architecture Analysis
+
+> **WS** = WebSocket | **TxQ** = Transaction Queue
+
+The rippled node consists of several key components that require instrumentation for comprehensive distributed tracing. The main areas include the RPC server (HTTP/WebSocket), Overlay P2P network, Consensus mechanism (RCLConsensus), JobQueue for async task execution, PathFinding, Transaction Queue (TxQ), fee escalation (LoadManager), ledger acquisition, validator management, and existing observability infrastructure (PerfLog, Insight/StatsD, Journal logging).
+
+Key trace points span across transaction submission via RPC, peer-to-peer message propagation, consensus round execution, ledger building, path computation, transaction queue behavior, fee escalation, and validator health. The implementation prioritizes high-value, low-risk components first: RPC handlers provide immediate value with minimal risk, while consensus tracing requires careful implementation to avoid timing impacts.
+
+➡️ **[Read full Architecture Analysis](./01-architecture-analysis.md)**
+
+---
+
+## 2. Design Decisions
+
+> **OTLP** = OpenTelemetry Protocol | **CNCF** = Cloud Native Computing Foundation
+
+The OpenTelemetry C++ SDK is selected for its CNCF backing, active development, and native performance characteristics. Traces are exported via OTLP/gRPC (primary) or OTLP/HTTP (fallback) to an OpenTelemetry Collector, which provides flexible routing and sampling.
+
+Span naming follows a hierarchical `<component>.<operation>` convention (e.g., `rpc.submit`, `tx.relay`, `consensus.round`). Context propagation uses W3C Trace Context headers for HTTP and embedded Protocol Buffer fields for P2P messages. The implementation coexists with existing PerfLog and Insight observability systems through correlation IDs.
+
+**Data Collection & Privacy**: Telemetry collects only operational metadata (timing, counts, hashes) — never sensitive content (private keys, balances, amounts, raw payloads). Privacy protection includes account hashing, configurable redaction, sampling, and collector-level filtering. Node operators retain full control over telemetry configuration.
+
+➡️ **[Read full Design Decisions](./02-design-decisions.md)**
+
+---
+
+## 3. Implementation Strategy
+
+The telemetry code is organized under `include/xrpl/telemetry/` for headers and `src/libxrpl/telemetry/` for implementation. Key principles include RAII-based span management via `SpanGuard`, conditional compilation with `XRPL_ENABLE_TELEMETRY`, and minimal runtime overhead through batch processing and efficient sampling.
+
+Performance optimization strategies include probabilistic head sampling (10% default), tail-based sampling at the collector for errors and slow traces, batch export to reduce network overhead, and conditional instrumentation that compiles to no-ops when disabled.
+
+➡️ **[Read full Implementation Strategy](./03-implementation-strategy.md)**
+
+---
+
+## 4. Code Samples
+
+C++ implementation examples are provided for the core telemetry infrastructure and key modules:
+
+- `Telemetry.h` - Core interface for tracer access and span creation
+- `SpanGuard.h` - RAII wrapper for automatic span lifecycle management
+- `TracingInstrumentation.h` - Macros for conditional instrumentation
+- Protocol Buffer extensions for trace context propagation
+- Module-specific instrumentation (RPC, Consensus, P2P, JobQueue)
+- Remaining modules (PathFinding, TxQ, Validator, etc.) follow the same patterns
+
+➡️ **[View all Code Samples](./04-code-samples.md)**
+
+---
+
+## 5. Configuration Reference
+
+> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring
+
+Configuration is handled through the `[telemetry]` section in `xrpld.cfg` with options for enabling/disabling, exporter selection, endpoint configuration, sampling ratios, and component-level filtering. CMake integration includes a `XRPL_ENABLE_TELEMETRY` option for compile-time control.
+
+OpenTelemetry Collector configurations are provided for development and production (with tail-based sampling, Tempo, and Elastic APM). Docker Compose examples enable quick local development environment setup.
+
+➡️ **[View full Configuration Reference](./05-configuration-reference.md)**
+
+---
+
+## 6. Implementation Phases
+
+The implementation spans 12 weeks across 7 phases:
+
+| Phase | Duration    | Focus                 | Key Deliverables                                            |
+| ----- | ----------- | --------------------- | ----------------------------------------------------------- |
+| 1     | Weeks 1-2   | Core Infrastructure   | SDK integration, Telemetry interface, Configuration         |
+| 2     | Weeks 3-4   | RPC Tracing           | HTTP context extraction, Handler instrumentation            |
+| 3     | Weeks 5-6   | Transaction Tracing   | Protocol Buffer context, Relay propagation                  |
+| 4     | Weeks 7-8   | Consensus Tracing     | Round spans, Proposal/validation tracing                    |
+| 5     | Week 9      | Documentation         | Runbook, Dashboards, Training                               |
+| 6     | Week 10     | StatsD Metrics Bridge | OTel Collector StatsD receiver, 3 Grafana dashboards        |
+| 7     | Weeks 11-12 | Native OTel Metrics   | OTelCollector impl, OTLP metrics export, StatsD deprecation |
+
+**Total Effort**: 60.6 developer-days with 2 developers
+
+➡️ **[View full Implementation Phases](./06-implementation-phases.md)**
+
+---
+
+## 7. Observability Backends
+
+> **APM** = Application Performance Monitoring | **GCS** = Google Cloud Storage
+
+Grafana Tempo is recommended for all environments due to its cost-effectiveness and Grafana integration, while Elastic APM is ideal for organizations with existing Elastic infrastructure.
+
+The recommended production architecture uses a gateway collector pattern with regional collectors performing tail-based sampling, routing traces to multiple backends (Tempo for primary storage, Elastic for log correlation, S3/GCS for long-term archive).
+
+➡️ **[View Observability Backend Recommendations](./07-observability-backends.md)**
+
+---
+
+## 8. Appendix
+
+The appendix contains a glossary of OpenTelemetry and rippled-specific terms, references to external documentation and specifications, version history for this implementation plan, and a complete document index.
+
+➡️ **[View Appendix](./08-appendix.md)**
+
+---
+
+## 9. Data Collection Reference
+
+A single-source-of-truth reference documenting every piece of telemetry data collected by rippled. Covers all 16 OpenTelemetry spans with their 22 attributes, all StatsD metrics (gauges, counters, histograms, overlay traffic), SpanMetrics-derived Prometheus metrics, and all 8 Grafana dashboards. Includes Jaeger search guides and Prometheus query examples.
+
+➡️ **[View Data Collection Reference](./09-data-collection-reference.md)**
+
+---
+
+## POC Task List
+
+A step-by-step task list for building a minimal end-to-end proof of concept that demonstrates distributed tracing in rippled. The POC scope is limited to RPC tracing — showing request traces flowing from rippled through an OpenTelemetry Collector into Tempo, viewable in Grafana.
+
+➡️ **[View POC Task List](./POC_taskList.md)**
+
+---
+
+_This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the rippled XRP Ledger node software. For detailed information on any section, follow the links to the corresponding sub-documents._

OpenTelemetryPlan/POC_taskList.md

@@ -0,0 +1,620 @@
+# OpenTelemetry POC Task List
+
+> **Goal**: Build a minimal end-to-end proof of concept that demonstrates distributed tracing in rippled. A successful POC will show RPC request traces flowing from rippled through an OTel Collector into Tempo, viewable in Grafana.
+>
+> **Scope**: RPC tracing only (highest value, lowest risk per the [CRAWL phase](./06-implementation-phases.md#6102-quick-wins-immediate-value) in the implementation phases). No cross-node P2P context propagation or consensus tracing in the POC.
+
+### Related Plan Documents
+
+| Document                                                         | Relevance to POC                                                                                                                                          |
+| ---------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [00-tracing-fundamentals.md](./00-tracing-fundamentals.md)       | Core concepts: traces, spans, context propagation, sampling                                                                                               |
+| [01-architecture-analysis.md](./01-architecture-analysis.md)     | RPC request flow (§1.5), key trace points (§1.6), instrumentation priority (§1.7)                                                                         |
+| [02-design-decisions.md](./02-design-decisions.md)               | SDK selection (§2.1), exporter config (§2.2), span naming (§2.3), attribute schema (§2.4), coexistence with PerfLog/Insight (§2.6)                        |
+| [03-implementation-strategy.md](./03-implementation-strategy.md) | Directory structure (§3.1), key principles (§3.2), performance overhead (§3.3-3.6), conditional compilation (§3.7.3), code intrusiveness (§3.9)           |
+| [04-code-samples.md](./04-code-samples.md)                       | Telemetry interface (§4.1), SpanGuard (§4.2), macros (§4.3), RPC instrumentation (§4.5.3)                                                                 |
+| [05-configuration-reference.md](./05-configuration-reference.md) | rippled config (§5.1), config parser (§5.2), Application integration (§5.3), CMake (§5.4), Collector config (§5.5), Docker Compose (§5.6), Grafana (§5.8) |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 1 core tasks (§6.2), Phase 2 RPC tasks (§6.3), quick wins (§6.10), definition of done (§6.11)                                                       |
+| [07-observability-backends.md](./07-observability-backends.md)   | Tempo dev setup (§7.1), Grafana dashboards (§7.6), alert rules (§7.6.3)                                                                                   |
+
+---
+
+## Task 0: Docker Observability Stack Setup
+
+> **OTLP** = OpenTelemetry Protocol
+
+**Objective**: Stand up the backend infrastructure to receive, store, and display traces.
+
+**What to do**:
+
+- Create `docker/telemetry/docker-compose.yml` in the repo with three services:
+  1. **OpenTelemetry Collector** (`otel/opentelemetry-collector-contrib:0.92.0`)
+     - Expose ports `4317` (OTLP gRPC) and `4318` (OTLP HTTP)
+     - Expose port `13133` (health check)
+     - Mount a config file `docker/telemetry/otel-collector-config.yaml`
+  2. **Tempo** (`grafana/tempo:2.6.1`)
+     - Expose port `3200` (HTTP API) and `4317` (OTLP gRPC, internal)
+  3. **Grafana** (`grafana/grafana:latest`) — optional but useful
+     - Expose port `3000`
+     - Enable anonymous admin access for local dev (`GF_AUTH_ANONYMOUS_ENABLED=true`, `GF_AUTH_ANONYMOUS_ORG_ROLE=Admin`)
+     - Provision Tempo as a data source via `docker/telemetry/grafana/provisioning/datasources/tempo.yaml`
+
+- Create `docker/telemetry/otel-collector-config.yaml`:
+
+  ```yaml
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+        http:
+          endpoint: 0.0.0.0:4318
+
+  processors:
+    batch:
+      timeout: 1s
+      send_batch_size: 100
+
+  exporters:
+    logging:
+      verbosity: detailed
+    otlp/tempo:
+      endpoint: tempo:4317
+      tls:
+        insecure: true
+
+  service:
+    pipelines:
+      traces:
+        receivers: [otlp]
+        processors: [batch]
+        exporters: [logging, otlp/tempo]
+  ```
+
+- Create Grafana Tempo datasource provisioning file at `docker/telemetry/grafana/provisioning/datasources/tempo.yaml`:
+  ```yaml
+  apiVersion: 1
+  datasources:
+    - name: Tempo
+      type: tempo
+      access: proxy
+      url: http://tempo:3200
+  ```
+
+**Verification**: Run `docker compose -f docker/telemetry/docker-compose.yml up -d`, then:
+
+- `curl http://localhost:13133` returns healthy (Collector)
+- `http://localhost:3000` opens Grafana (Tempo datasource available, no traces yet)
+
+**Reference**:
+
+- [05-configuration-reference.md §5.5](./05-configuration-reference.md) — Collector config (dev YAML with Tempo exporter)
+- [05-configuration-reference.md §5.6](./05-configuration-reference.md) — Docker Compose development environment
+- [07-observability-backends.md §7.1](./07-observability-backends.md) — Tempo quick start and backend selection
+- [05-configuration-reference.md §5.8](./05-configuration-reference.md) — Grafana datasource provisioning and dashboards
+
+---
+
+## Task 1: Add OpenTelemetry C++ SDK Dependency
+
+**Objective**: Make `opentelemetry-cpp` available to the build system.
+
+**What to do**:
+
+- Edit `conanfile.py` to add `opentelemetry-cpp` as an **optional** dependency. The gRPC otel plugin flag (`"grpc/*:otel_plugin": False`) in the existing conanfile may need to remain false — we pull the OTel SDK separately.
+  - Add a Conan option: `with_telemetry = [True, False]` defaulting to `False`
+  - When `with_telemetry` is `True`, add `opentelemetry-cpp` to `self.requires()`
+  - Required OTel Conan components: `opentelemetry-cpp` (which bundles api, sdk, and exporters). If the package isn't in Conan Center, consider using `FetchContent` in CMake or building from source as a fallback.
+- Edit `CMakeLists.txt`:
+  - Add option: `option(XRPL_ENABLE_TELEMETRY "Enable OpenTelemetry tracing" OFF)`
+  - When ON, `find_package(opentelemetry-cpp CONFIG REQUIRED)` and add compile definition `XRPL_ENABLE_TELEMETRY`
+  - When OFF, do nothing (zero build impact)
+- Verify the build succeeds with `-DXRPL_ENABLE_TELEMETRY=OFF` (no regressions) and with `-DXRPL_ENABLE_TELEMETRY=ON` (SDK links successfully).
+
+**Key files**:
+
+- `conanfile.py`
+- `CMakeLists.txt`
+
+**Reference**:
+
+- [05-configuration-reference.md §5.4](./05-configuration-reference.md) — CMake integration, `FindOpenTelemetry.cmake`, `XRPL_ENABLE_TELEMETRY` option
+- [03-implementation-strategy.md §3.2](./03-implementation-strategy.md) — Key principle: zero-cost when disabled via compile-time flags
+- [02-design-decisions.md §2.1](./02-design-decisions.md) — SDK selection rationale and required OTel components
+
+---
+
+## Task 2: Create Core Telemetry Interface and NullTelemetry
+
+**Objective**: Define the `Telemetry` abstract interface and a no-op implementation so the rest of the codebase can reference telemetry without hard-depending on the OTel SDK.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/Telemetry.h`:
+  - Define `namespace xrpl::telemetry`
+  - Define `struct Telemetry::Setup` holding: `enabled`, `exporterEndpoint`, `samplingRatio`, `serviceName`, `serviceVersion`, `serviceInstanceId`, `traceRpc`, `traceTransactions`, `traceConsensus`, `tracePeer`
+  - Define abstract `class Telemetry` with:
+    - `virtual void start() = 0;`
+    - `virtual void stop() = 0;`
+    - `virtual bool isEnabled() const = 0;`
+    - `virtual nostd::shared_ptr<Tracer> getTracer(string_view name = "rippled") = 0;`
+    - `virtual nostd::shared_ptr<Span> startSpan(string_view name, SpanKind kind = kInternal) = 0;`
+    - `virtual nostd::shared_ptr<Span> startSpan(string_view name, Context const& parentContext, SpanKind kind = kInternal) = 0;`
+    - `virtual bool shouldTraceRpc() const = 0;`
+    - `virtual bool shouldTraceTransactions() const = 0;`
+    - `virtual bool shouldTraceConsensus() const = 0;`
+  - Factory: `std::unique_ptr<Telemetry> make_Telemetry(Setup const&, beast::Journal);`
+  - Config parser: `Telemetry::Setup setup_Telemetry(Section const&, std::string const& nodePublicKey, std::string const& version);`
+
+- Create `include/xrpl/telemetry/SpanGuard.h`:
+  - RAII guard that takes an `nostd::shared_ptr<Span>`, creates a `Scope`, and calls `span->End()` in destructor.
+  - Convenience: `setAttribute()`, `setOk()`, `setStatus()`, `addEvent()`, `recordException()`, `context()`
+  - See [04-code-samples.md](./04-code-samples.md) §4.2 for the full implementation.
+
+- Create `src/libxrpl/telemetry/NullTelemetry.cpp`:
+  - Implements `Telemetry` with all no-ops.
+  - `isEnabled()` returns `false`, `startSpan()` returns a noop span.
+  - This is used when `XRPL_ENABLE_TELEMETRY` is OFF or `enabled=0` in config.
+
+- Guard all OTel SDK headers behind `#ifdef XRPL_ENABLE_TELEMETRY`. The `NullTelemetry` implementation should compile without the OTel SDK present.
+
+**Key new files**:
+
+- `include/xrpl/telemetry/Telemetry.h`
+- `include/xrpl/telemetry/SpanGuard.h`
+- `src/libxrpl/telemetry/NullTelemetry.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.1](./04-code-samples.md) — Full `Telemetry` interface with `Setup` struct, lifecycle, tracer access, span creation, and component filtering methods
+- [04-code-samples.md §4.2](./04-code-samples.md) — Full `SpanGuard` RAII implementation and `NullSpanGuard` no-op class
+- [03-implementation-strategy.md §3.1](./03-implementation-strategy.md) — Directory structure: `include/xrpl/telemetry/` for headers, `src/libxrpl/telemetry/` for implementation
+- [03-implementation-strategy.md §3.7.3](./03-implementation-strategy.md) — Conditional instrumentation and zero-cost compile-time disabled pattern
+
+---
+
+## Task 3: Implement OTel-Backed Telemetry
+
+> **OTLP** = OpenTelemetry Protocol
+
+**Objective**: Implement the real `Telemetry` class that initializes the OTel SDK, configures the OTLP exporter and batch processor, and creates tracers/spans.
+
+**What to do**:
+
+- Create `src/libxrpl/telemetry/Telemetry.cpp` (compiled only when `XRPL_ENABLE_TELEMETRY=ON`):
+  - `class TelemetryImpl : public Telemetry` that:
+    - In `start()`: creates a `TracerProvider` with:
+      - Resource attributes: `service.name`, `service.version`, `service.instance.id`
+      - An `OtlpHttpExporter` pointed at `setup.exporterEndpoint` (default `localhost:4318`)
+      - A `BatchSpanProcessor` with configurable batch size and delay
+      - A `TraceIdRatioBasedSampler` using `setup.samplingRatio`
+    - Sets the global `TracerProvider`
+    - In `stop()`: calls `ForceFlush()` then shuts down the provider
+    - In `startSpan()`: delegates to `getTracer()->StartSpan(name, ...)`
+    - `shouldTraceRpc()` etc. read from `Setup` fields
+
+- Create `src/libxrpl/telemetry/TelemetryConfig.cpp`:
+  - `setup_Telemetry()` parses the `[telemetry]` config section from `xrpld.cfg`
+  - Maps config keys: `enabled`, `exporter`, `endpoint`, `sampling_ratio`, `trace_rpc`, `trace_transactions`, `trace_consensus`, `trace_peer`
+
+- Wire `make_Telemetry()` factory:
+  - If `setup.enabled` is true AND `XRPL_ENABLE_TELEMETRY` is defined: return `TelemetryImpl`
+  - Otherwise: return `NullTelemetry`
+
+- Add telemetry source files to CMake. When `XRPL_ENABLE_TELEMETRY=ON`, compile `Telemetry.cpp` and `TelemetryConfig.cpp` and link against `opentelemetry-cpp::api`, `opentelemetry-cpp::sdk`, `opentelemetry-cpp::otlp_grpc_exporter`. When OFF, compile only `NullTelemetry.cpp`.
+
+**Key new files**:
+
+- `src/libxrpl/telemetry/Telemetry.cpp`
+- `src/libxrpl/telemetry/TelemetryConfig.cpp`
+
+**Key modified files**:
+
+- `CMakeLists.txt` (add telemetry library target)
+
+**Reference**:
+
+- [04-code-samples.md §4.1](./04-code-samples.md) — `Telemetry` interface that `TelemetryImpl` must implement
+- [05-configuration-reference.md §5.2](./05-configuration-reference.md) — `setup_Telemetry()` config parser implementation
+- [02-design-decisions.md §2.2](./02-design-decisions.md) — OTLP/gRPC exporter config (endpoint, TLS options)
+- [02-design-decisions.md §2.4.1](./02-design-decisions.md) — Resource attributes: `service.name`, `service.version`, `service.instance.id`, `xrpl.network.id`
+- [03-implementation-strategy.md §3.4](./03-implementation-strategy.md) — Per-operation CPU costs and overhead budget for span creation
+- [03-implementation-strategy.md §3.5](./03-implementation-strategy.md) — Memory overhead: static (~456 KB) and dynamic (~1.2 MB) budgets
+
+---
+
+## Task 4: Integrate Telemetry into Application Lifecycle
+
+**Objective**: Wire the `Telemetry` object into `Application` so all components can access it.
+
+**What to do**:
+
+- Edit `src/xrpld/app/main/Application.h`:
+  - Forward-declare `namespace xrpl::telemetry { class Telemetry; }`
+  - Add pure virtual method: `virtual telemetry::Telemetry& getTelemetry() = 0;`
+
+- Edit `src/xrpld/app/main/Application.cpp` (the `ApplicationImp` class):
+  - Add member: `std::unique_ptr<telemetry::Telemetry> telemetry_;`
+  - In the constructor, after config is loaded and node identity is known:
+    ```cpp
+    auto const telemetrySection = config_->section("telemetry");
+    auto telemetrySetup = telemetry::setup_Telemetry(
+        telemetrySection,
+        toBase58(TokenType::NodePublic, nodeIdentity_.publicKey()),
+        BuildInfo::getVersionString());
+    telemetry_ = telemetry::make_Telemetry(telemetrySetup, logs_->journal("Telemetry"));
+    ```
+  - In `start()`: call `telemetry_->start()` early
+  - In `stop()` or destructor: call `telemetry_->stop()` late (to flush pending spans)
+  - Implement `getTelemetry()` override: return `*telemetry_`
+
+- Add `[telemetry]` section to the example config `cfg/rippled-example.cfg`:
+  ```ini
+  # [telemetry]
+  # enabled=1
+  # endpoint=localhost:4317
+  # sampling_ratio=1.0
+  # trace_rpc=1
+  ```
+
+**Key modified files**:
+
+- `src/xrpld/app/main/Application.h`
+- `src/xrpld/app/main/Application.cpp`
+- `cfg/rippled-example.cfg` (or equivalent example config)
+
+**Reference**:
+
+- [05-configuration-reference.md §5.3](./05-configuration-reference.md) — `ApplicationImp` changes: member declaration, constructor init, `start()`/`stop()` wiring, `getTelemetry()` override
+- [05-configuration-reference.md §5.1](./05-configuration-reference.md) — `[telemetry]` config section format and all option defaults
+- [03-implementation-strategy.md §3.9.2](./03-implementation-strategy.md) — File impact assessment: `Application.cpp` ~15 lines added, ~3 changed (Low risk)
+
+---
+
+## Task 5: Create Instrumentation Macros
+
+**Objective**: Define convenience macros that make instrumenting code one-liners, and that compile to zero-cost no-ops when telemetry is disabled.
+
+**What to do**:
+
+- Create `src/xrpld/telemetry/TracingInstrumentation.h`:
+  - When `XRPL_ENABLE_TELEMETRY` is defined:
+
+    ```cpp
+    #define XRPL_TRACE_SPAN(telemetry, name) \
+        auto _xrpl_span_ = (telemetry).startSpan(name); \
+        ::xrpl::telemetry::SpanGuard _xrpl_guard_(_xrpl_span_)
+
+    #define XRPL_TRACE_RPC(telemetry, name) \
+        std::optional<::xrpl::telemetry::SpanGuard> _xrpl_guard_; \
+        if ((telemetry).shouldTraceRpc()) { \
+            _xrpl_guard_.emplace((telemetry).startSpan(name)); \
+        }
+
+    #define XRPL_TRACE_SET_ATTR(key, value) \
+        if (_xrpl_guard_.has_value()) { \
+            _xrpl_guard_->setAttribute(key, value); \
+        }
+
+    #define XRPL_TRACE_EXCEPTION(e) \
+        if (_xrpl_guard_.has_value()) { \
+            _xrpl_guard_->recordException(e); \
+        }
+    ```
+
+  - When `XRPL_ENABLE_TELEMETRY` is NOT defined, all macros expand to `((void)0)`
+
+**Key new file**:
+
+- `src/xrpld/telemetry/TracingInstrumentation.h`
+
+**Reference**:
+
+- [04-code-samples.md §4.3](./04-code-samples.md) — Full macro definitions for `XRPL_TRACE_SPAN`, `XRPL_TRACE_RPC`, `XRPL_TRACE_CONSENSUS`, `XRPL_TRACE_SET_ATTR`, `XRPL_TRACE_EXCEPTION` with both enabled and disabled branches
+- [03-implementation-strategy.md §3.7.3](./03-implementation-strategy.md) — Conditional instrumentation pattern: compile-time `#ifndef` and runtime `shouldTrace*()` checks
+- [03-implementation-strategy.md §3.9.7](./03-implementation-strategy.md) — Before/after code examples showing minimal intrusiveness (~1-3 lines per instrumentation point)
+
+---
+
+## Task 6: Instrument RPC ServerHandler
+
+> **WS** = WebSocket
+
+**Objective**: Add tracing to the HTTP RPC entry point so every incoming RPC request creates a span.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/ServerHandler.cpp`:
+  - `#include` the `TracingInstrumentation.h` header
+  - In `ServerHandler::onRequest(Session& session)`:
+    - At the top of the method, add: `XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.request");`
+    - After the RPC command name is extracted, set attribute: `XRPL_TRACE_SET_ATTR("xrpl.rpc.command", command);`
+    - After the response status is known, set: `XRPL_TRACE_SET_ATTR("http.status_code", static_cast<int64_t>(statusCode));`
+    - Wrap error paths with: `XRPL_TRACE_EXCEPTION(e);`
+  - In `ServerHandler::processRequest(...)`:
+    - Add a child span: `XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.process");`
+    - Set method attribute: `XRPL_TRACE_SET_ATTR("xrpl.rpc.method", request_method);`
+  - In `ServerHandler::onWSMessage(...)` (WebSocket path):
+    - Add: `XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.ws.message");`
+
+- The goal is to see spans like:
+  ```
+  rpc.request
+    └── rpc.process
+  ```
+  in Tempo/Grafana for every HTTP RPC call.
+
+**Key modified file**:
+
+- `src/xrpld/rpc/detail/ServerHandler.cpp` (~15-25 lines added)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.3](./04-code-samples.md) — Complete `ServerHandler::onRequest()` instrumented code sample with W3C header extraction, span creation, attribute setting, and error handling
+- [01-architecture-analysis.md §1.5](./01-architecture-analysis.md) — RPC request flow diagram: HTTP request -> attributes -> jobqueue.enqueue -> rpc.command -> response
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — Key trace points table: `rpc.request` in `ServerHandler.cpp::onRequest()` (Priority: High)
+- [02-design-decisions.md §2.3](./02-design-decisions.md) — Span naming convention: `rpc.request`, `rpc.command.*`
+- [02-design-decisions.md §2.4.2](./02-design-decisions.md) — RPC span attributes: `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role`, `xrpl.rpc.params`
+- [03-implementation-strategy.md §3.9.2](./03-implementation-strategy.md) — File impact: `ServerHandler.cpp` ~40 lines added, ~10 changed (Low risk)
+
+---
+
+## Task 7: Instrument RPC Command Execution
+
+**Objective**: Add per-command tracing inside the RPC handler so each command (e.g., `submit`, `account_info`, `server_info`) gets its own child span.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/RPCHandler.cpp`:
+  - `#include` the `TracingInstrumentation.h` header
+  - In `doCommand(RPC::JsonContext& context, Json::Value& result)`:
+    - At the top: `XRPL_TRACE_RPC(context.app.getTelemetry(), "rpc.command." + context.method);`
+    - Set attributes:
+      - `XRPL_TRACE_SET_ATTR("xrpl.rpc.command", context.method);`
+      - `XRPL_TRACE_SET_ATTR("xrpl.rpc.version", static_cast<int64_t>(context.apiVersion));`
+      - `XRPL_TRACE_SET_ATTR("xrpl.rpc.role", (context.role == Role::ADMIN) ? "admin" : "user");`
+    - On success: `XRPL_TRACE_SET_ATTR("xrpl.rpc.status", "success");`
+    - On error: `XRPL_TRACE_SET_ATTR("xrpl.rpc.status", "error");` and set the error message
+
+- After this, traces in Tempo/Grafana should look like:
+  ```
+  rpc.request  (xrpl.rpc.command=account_info)
+    └── rpc.process
+          └── rpc.command.account_info  (xrpl.rpc.version=2, xrpl.rpc.role=user, xrpl.rpc.status=success)
+  ```
+
+**Key modified file**:
+
+- `src/xrpld/rpc/detail/RPCHandler.cpp` (~15-20 lines added)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.3](./04-code-samples.md) — `ServerHandler::onRequest()` code sample (includes child span pattern for `rpc.command.*`)
+- [02-design-decisions.md §2.3](./02-design-decisions.md) — Span naming: `rpc.command.*` pattern with dynamic command name (e.g., `rpc.command.server_info`)
+- [02-design-decisions.md §2.4.2](./02-design-decisions.md) — RPC attribute schema: `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role`, `xrpl.rpc.status`
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — Key trace points table: `rpc.command.*` in `RPCHandler.cpp::doCommand()` (Priority: High)
+- [02-design-decisions.md §2.6.5](./02-design-decisions.md) — Correlation with PerfLog: how `doCommand()` can link trace_id with existing PerfLog entries
+- [03-implementation-strategy.md §3.4.4](./03-implementation-strategy.md) — RPC request overhead budget: ~1.75 μs total per request
+
+---
+
+## Task 8: Build, Run, and Verify End-to-End
+
+> **OTLP** = OpenTelemetry Protocol
+
+**Objective**: Prove the full pipeline works: rippled emits traces -> OTel Collector receives them -> Tempo stores them for Grafana visualization.
+
+**What to do**:
+
+1. **Start the Docker stack**:
+
+   ```bash
+   docker compose -f docker/telemetry/docker-compose.yml up -d
+   ```
+
+   Verify Collector health: `curl http://localhost:13133`
+
+2. **Build rippled with telemetry**:
+
+   ```bash
+   # Adjust for your actual build workflow
+   conan install . --build=missing -o with_telemetry=True
+   cmake --preset default -DXRPL_ENABLE_TELEMETRY=ON
+   cmake --build --preset default
+   ```
+
+3. **Configure rippled**:
+   Add to `rippled.cfg` (or your local test config):
+
+   ```ini
+   [telemetry]
+   enabled=1
+   endpoint=localhost:4317
+   sampling_ratio=1.0
+   trace_rpc=1
+   ```
+
+4. **Start rippled** in standalone mode:
+
+   ```bash
+   ./rippled --conf rippled.cfg -a --start
+   ```
+
+5. **Generate RPC traffic**:
+
+   ```bash
+   # server_info
+   curl -s -X POST http://localhost:5005 \
+     -H "Content-Type: application/json" \
+     -d '{"method":"server_info","params":[{}]}'
+
+   # ledger
+   curl -s -X POST http://localhost:5005 \
+     -H "Content-Type: application/json" \
+     -d '{"method":"ledger","params":[{"ledger_index":"current"}]}'
+
+   # account_info (will error in standalone, that's fine — we trace errors too)
+   curl -s -X POST http://localhost:5005 \
+     -H "Content-Type: application/json" \
+     -d '{"method":"account_info","params":[{"account":"rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}]}'
+   ```
+
+6. **Verify in Grafana (Tempo)**:
+   - Open `http://localhost:3000`
+   - Navigate to Explore → select Tempo datasource
+   - Search for service `rippled`
+   - Confirm you see traces with spans: `rpc.request` -> `rpc.process` -> `rpc.command.server_info`
+   - Click into a trace and verify attributes: `xrpl.rpc.command`, `xrpl.rpc.status`, `xrpl.rpc.version`
+
+7. **Verify zero-overhead when disabled**:
+   - Rebuild with `XRPL_ENABLE_TELEMETRY=OFF`, or set `enabled=0` in config
+   - Run the same RPC calls
+   - Confirm no new traces appear and no errors in rippled logs
+
+**Verification Checklist**:
+
+- [ ] Docker stack starts without errors
+- [ ] rippled builds with `-DXRPL_ENABLE_TELEMETRY=ON`
+- [ ] rippled starts and connects to OTel Collector (check rippled logs for telemetry messages)
+- [ ] Traces appear in Grafana/Tempo under service "rippled"
+- [ ] Span hierarchy is correct (parent-child relationships)
+- [ ] Span attributes are populated (`xrpl.rpc.command`, `xrpl.rpc.status`, etc.)
+- [ ] Error spans show error status and message
+- [ ] Building with `XRPL_ENABLE_TELEMETRY=OFF` produces no regressions
+- [ ] Setting `enabled=0` at runtime produces no traces and no errors
+
+**Reference**:
+
+- [06-implementation-phases.md §6.11.1](./06-implementation-phases.md) — Phase 1 definition of done: SDK compiles, runtime toggle works, span creation verified in Tempo, config validation passes
+- [06-implementation-phases.md §6.11.2](./06-implementation-phases.md#6112-phase-2-rpc-tracing) — Phase 2 definition of done: 100% RPC coverage, traceparent propagation, <1ms p99 overhead, dashboard deployed
+- [06-implementation-phases.md §6.8](./06-implementation-phases.md) — Success metrics: trace coverage >95%, CPU overhead <3%, memory <5 MB, latency impact <2%
+- [03-implementation-strategy.md §3.9.5](./03-implementation-strategy.md) — Backward compatibility: config optional, protocol unchanged, `XRPL_ENABLE_TELEMETRY=OFF` produces identical binary
+- [01-architecture-analysis.md §1.8](./01-architecture-analysis.md) — Observable outcomes: what traces, metrics, and dashboards to expect
+
+---
+
+## Task 9: Document POC Results and Next Steps
+
+> **OTLP** = OpenTelemetry Protocol | **WS** = WebSocket
+
+**Objective**: Capture findings, screenshots, and remaining work for the team.
+
+**What to do**:
+
+- Take screenshots of Grafana/Tempo showing:
+  - The service list with "rippled"
+  - A trace with the full span tree
+  - Span detail view showing attributes
+- Document any issues encountered (build issues, SDK quirks, missing attributes)
+- Note performance observations (build time impact, any noticeable runtime overhead)
+- Write a short summary of what the POC proves and what it doesn't cover yet:
+  - **Proves**: OTel SDK integrates with rippled, OTLP export works, RPC traces visible
+  - **Doesn't cover**: Cross-node P2P context propagation, consensus tracing, protobuf trace context, W3C traceparent header extraction, tail-based sampling, production deployment
+- Outline next steps (mapping to the full plan phases):
+  - [Phase 2](./06-implementation-phases.md) completion: [W3C header extraction](./02-design-decisions.md) (§2.5), WebSocket tracing, all [RPC handlers](./01-architecture-analysis.md) (§1.6)
+  - [Phase 3](./06-implementation-phases.md): [Protobuf `TraceContext` message](./04-code-samples.md) (§4.4), [transaction relay tracing](./04-code-samples.md) (§4.5.1) across nodes
+  - [Phase 4](./06-implementation-phases.md): [Consensus round and phase tracing](./04-code-samples.md) (§4.5.2)
+  - [Phase 5](./06-implementation-phases.md): [Production collector config](./05-configuration-reference.md) (§5.5.2), [Grafana dashboards](./07-observability-backends.md) (§7.6), [alerting](./07-observability-backends.md) (§7.6.3)
+
+**Reference**:
+
+- [06-implementation-phases.md §6.1](./06-implementation-phases.md) — Full 5-phase timeline overview and Gantt chart
+- [06-implementation-phases.md §6.10](./06-implementation-phases.md) — Crawl-Walk-Run strategy: POC is the CRAWL phase, next steps are WALK and RUN
+- [06-implementation-phases.md §6.12](./06-implementation-phases.md) — Recommended implementation order (14 steps across 9 weeks)
+- [03-implementation-strategy.md §3.9](./03-implementation-strategy.md) — Code intrusiveness assessment and risk matrix for each remaining component
+- [07-observability-backends.md §7.2](./07-observability-backends.md) — Production backend selection (Tempo, Elastic APM, Honeycomb, Datadog)
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — Context propagation design: W3C HTTP headers, protobuf P2P, JobQueue internal
+- [00-tracing-fundamentals.md](./00-tracing-fundamentals.md) — Reference for team onboarding on distributed tracing concepts
+
+---
+
+## Summary
+
+| Task | Description                          | New Files | Modified Files | Depends On |
+| ---- | ------------------------------------ | --------- | -------------- | ---------- |
+| 0    | Docker observability stack           | 4         | 0              | —          |
+| 1    | OTel C++ SDK dependency              | 0         | 2              | —          |
+| 2    | Core Telemetry interface + NullImpl  | 3         | 0              | 1          |
+| 3    | OTel-backed Telemetry implementation | 2         | 1              | 1, 2       |
+| 4    | Application lifecycle integration    | 0         | 3              | 2, 3       |
+| 5    | Instrumentation macros               | 1         | 0              | 2          |
+| 6    | Instrument RPC ServerHandler         | 0         | 1              | 4, 5       |
+| 7    | Instrument RPC command execution     | 0         | 1              | 4, 5       |
+| 8    | End-to-end verification              | 0         | 0              | 0-7        |
+| 9    | Document results and next steps      | 1         | 0              | 8          |
+
+**Parallel work**: Tasks 0 and 1 can run in parallel. Tasks 2 and 5 have no dependency on each other. Tasks 6 and 7 can be done in parallel once Tasks 4 and 5 are complete.
+
+---
+
+## Next Steps (Post-POC)
+
+> **OTLP** = OpenTelemetry Protocol | **WS** = WebSocket
+
+### Metrics Pipeline for Grafana Dashboards
+
+The current POC exports **traces only**. Grafana's Explore view can query Tempo for individual traces, but time-series charts (latency histograms, request throughput, error rates) require a **metrics pipeline**. To enable this:
+
+1. **Add a `spanmetrics` connector** to the OTel Collector config that derives RED metrics (Rate, Errors, Duration) from trace spans automatically:
+
+   ```yaml
+   connectors:
+     spanmetrics:
+       histogram:
+         explicit:
+           buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
+       dimensions:
+         - name: xrpl.rpc.command
+         - name: xrpl.rpc.status
+
+   exporters:
+     prometheus:
+       endpoint: 0.0.0.0:8889
+
+   service:
+     pipelines:
+       traces:
+         receivers: [otlp]
+         processors: [batch]
+         exporters: [debug, otlp/tempo, spanmetrics]
+       metrics:
+         receivers: [spanmetrics]
+         exporters: [prometheus]
+   ```
+
+2. **Add Prometheus** to the Docker Compose stack to scrape the collector's metrics endpoint.
+
+3. **Add Prometheus as a Grafana datasource** and build dashboards for:
+   - RPC request latency (p50/p95/p99) by command
+   - RPC throughput (requests/sec) by command
+   - Error rate by command
+   - Span duration distribution
+
+### Additional Instrumentation
+
+- **W3C `traceparent` header extraction** in `ServerHandler` to support cross-service context propagation from external callers
+- **WebSocket RPC tracing** in `ServerHandler::onWSMessage()`
+- **Transaction relay tracing** across nodes using protobuf `TraceContext` messages
+- **Consensus round and phase tracing** for validator coordination visibility
+- **Ledger close tracing** to measure close-to-validated latency
+
+### Production Hardening
+
+- **Tail-based sampling** in the OTel Collector to reduce volume while retaining error/slow traces
+- **TLS configuration** for the OTLP exporter in production deployments
+- **Resource limits** on the batch processor queue to prevent unbounded memory growth
+- **Health monitoring** for the telemetry pipeline itself (collector lag, export failures)
+
+### POC Lessons Learned
+
+Issues encountered during POC implementation that inform future work:
+
+| Issue                                                                                              | Resolution                                                                    | Impact on Future Work                                            |
+| -------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ---------------------------------------------------------------- |
+| Conan lockfile rejected `opentelemetry-cpp/1.18.0`                                                 | Used `--lockfile=""` to bypass                                                | Lockfile must be regenerated when adding new dependencies        |
+| Conan package only builds OTLP HTTP exporter, not gRPC                                             | Switched from gRPC to HTTP exporter (`localhost:4318/v1/traces`)              | HTTP exporter is the default; gRPC requires custom Conan profile |
+| CMake target `opentelemetry-cpp::api` etc. don't exist in Conan package                            | Use umbrella target `opentelemetry-cpp::opentelemetry-cpp`                    | Conan targets differ from upstream CMake targets                 |
+| OTel Collector `logging` exporter deprecated                                                       | Renamed to `debug` exporter                                                   | Use `debug` in all collector configs going forward               |
+| Macro parameter `telemetry` collided with `::xrpl::telemetry::` namespace                          | Renamed macro params to `_tel_obj_`, `_span_name_`                            | Avoid common words as macro parameter names                      |
+| `opentelemetry::trace::Scope` creates new context on move                                          | Store scope as member, create once in constructor                             | SpanGuard move semantics need care with Scope lifecycle          |
+| `TracerProviderFactory::Create` returns `unique_ptr<sdk::TracerProvider>`, not `nostd::shared_ptr` | Use `std::shared_ptr` member, wrap in `nostd::shared_ptr` for global provider | OTel SDK factory return types don't match API provider types     |

OpenTelemetryPlan/Phase2_taskList.md

@@ -0,0 +1,263 @@
+# Phase 2: RPC Tracing Completion Task List
+
+> **Goal**: Complete full RPC tracing coverage with W3C Trace Context propagation, unit tests, and performance validation. Build on the POC foundation to achieve production-quality RPC observability.
+>
+> **Scope**: W3C header extraction, TraceContext propagation utilities, unit tests for core telemetry, integration tests for RPC tracing, and performance benchmarks.
+>
+> **Branch**: `pratik/otel-phase2-rpc-tracing` (from `pratik/OpenTelemetry_and_DistributedTracing_planning`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                     |
+| ------------------------------------------------------------ | ------------------------------------------------------------- |
+| [04-code-samples.md](./04-code-samples.md)                   | TraceContextPropagator (§4.4.2), RPC instrumentation (§4.5.3) |
+| [02-design-decisions.md](./02-design-decisions.md)           | W3C Trace Context (§2.5), span attributes (§2.4.2)            |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 2 tasks (§6.3), definition of done (§6.11.2)            |
+
+---
+
+## Task 2.1: Implement W3C Trace Context HTTP Header Extraction
+
+**Objective**: Extract `traceparent` and `tracestate` headers from incoming HTTP RPC requests so external callers can propagate their trace context into rippled.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/TraceContextPropagator.h`:
+  - `extractFromHeaders(headerGetter)` - extract W3C traceparent/tracestate from HTTP headers
+  - `injectToHeaders(ctx, headerSetter)` - inject trace context into response headers
+  - Use OTel's `TextMapPropagator` with `W3CTraceContextPropagator` for standards compliance
+  - Only compiled when `XRPL_ENABLE_TELEMETRY` is defined
+
+- Create `src/libxrpl/telemetry/TraceContextPropagator.cpp`:
+  - Implement a simple `TextMapCarrier` adapter for HTTP headers
+  - Use `opentelemetry::context::propagation::GlobalTextMapPropagator` for extraction/injection
+  - Register the W3C propagator in `TelemetryImpl::start()`
+
+- Modify `src/xrpld/rpc/detail/ServerHandler.cpp`:
+  - In the HTTP request handler, extract parent context from headers before creating span
+  - Pass extracted context to `startSpan()` as parent
+  - Inject trace context into response headers
+
+**Key new files**:
+
+- `include/xrpl/telemetry/TraceContextPropagator.h`
+- `src/libxrpl/telemetry/TraceContextPropagator.cpp`
+
+**Key modified files**:
+
+- `src/xrpld/rpc/detail/ServerHandler.cpp`
+- `src/libxrpl/telemetry/Telemetry.cpp` (register W3C propagator)
+
+**Reference**:
+
+- [04-code-samples.md §4.4.2](./04-code-samples.md) — TraceContextPropagator with extractFromHeaders/injectToHeaders
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — W3C Trace Context propagation design
+
+---
+
+## Task 2.2: Add XRPL_TRACE_PEER Macro
+
+**Objective**: Add the missing peer-tracing macro for future Phase 3 use and ensure macro completeness.
+
+**What to do**:
+
+- Edit `src/xrpld/telemetry/TracingInstrumentation.h`:
+  - Add `XRPL_TRACE_PEER(_tel_obj_, _span_name_)` macro that checks `shouldTracePeer()`
+  - Add `XRPL_TRACE_LEDGER(_tel_obj_, _span_name_)` macro (for future ledger tracing)
+  - Ensure disabled variants expand to `((void)0)`
+
+**Key modified file**:
+
+- `src/xrpld/telemetry/TracingInstrumentation.h`
+
+---
+
+## Task 2.3: Add shouldTraceLedger() to Telemetry Interface
+
+**Objective**: The `Setup` struct has a `traceLedger` field but there's no corresponding virtual method. Add it for interface completeness.
+
+**What to do**:
+
+- Edit `include/xrpl/telemetry/Telemetry.h`:
+  - Add `virtual bool shouldTraceLedger() const = 0;`
+
+- Update all implementations:
+  - `src/libxrpl/telemetry/Telemetry.cpp` (TelemetryImpl, NullTelemetryOtel)
+  - `src/libxrpl/telemetry/NullTelemetry.cpp` (NullTelemetry)
+
+**Key modified files**:
+
+- `include/xrpl/telemetry/Telemetry.h`
+- `src/libxrpl/telemetry/Telemetry.cpp`
+- `src/libxrpl/telemetry/NullTelemetry.cpp`
+
+---
+
+## Task 2.4: Unit Tests for Core Telemetry Infrastructure
+
+**Objective**: Add unit tests for the core telemetry abstractions to validate correctness and catch regressions.
+
+**What to do**:
+
+- Create `src/test/telemetry/Telemetry_test.cpp`:
+  - Test NullTelemetry: verify all methods return expected no-op values
+  - Test Setup defaults: verify all Setup fields have correct defaults
+  - Test setup_Telemetry config parser: verify parsing of [telemetry] section
+  - Test enabled/disabled factory paths
+  - Test shouldTrace\* methods respect config flags
+
+- Create `src/test/telemetry/SpanGuard_test.cpp`:
+  - Test SpanGuard RAII lifecycle (span ends on destruction)
+  - Test move constructor works correctly
+  - Test setAttribute, setOk, setStatus, addEvent, recordException
+  - Test context() returns valid context
+
+- Add test files to CMake build
+
+**Key new files**:
+
+- `src/test/telemetry/Telemetry_test.cpp`
+- `src/test/telemetry/SpanGuard_test.cpp`
+
+**Reference**:
+
+- [06-implementation-phases.md §6.11.1](./06-implementation-phases.md) — Phase 1 exit criteria (unit tests passing)
+
+---
+
+## Task 2.5: Enhance RPC Span Attributes
+
+**Objective**: Add additional attributes to RPC spans per the semantic conventions defined in the plan.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/ServerHandler.cpp`:
+  - Add `http.method` attribute for HTTP requests
+  - Add `http.status_code` attribute for responses
+  - Add `net.peer.ip` attribute for client IP (if available)
+
+- Edit `src/xrpld/rpc/detail/RPCHandler.cpp`:
+  - Add `xrpl.rpc.duration_ms` attribute on completion
+  - Add error message attribute on failure: `xrpl.rpc.error_message`
+
+**Key modified files**:
+
+- `src/xrpld/rpc/detail/ServerHandler.cpp`
+- `src/xrpld/rpc/detail/RPCHandler.cpp`
+
+**Reference**:
+
+- [02-design-decisions.md §2.4.2](./02-design-decisions.md) — RPC attribute schema
+
+---
+
+## Task 2.6: Build Verification and Performance Baseline
+
+**Objective**: Verify the build succeeds with and without telemetry, and establish a performance baseline.
+
+**What to do**:
+
+1. Build with `telemetry=ON` and verify no compilation errors
+2. Build with `telemetry=OFF` and verify no regressions
+3. Run existing unit tests to verify no breakage
+4. Document any build issues in lessons.md
+
+**Verification Checklist**:
+
+- [ ] `conan install . --build=missing -o telemetry=True` succeeds
+- [ ] `cmake --preset default -Dtelemetry=ON` configures correctly
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass with telemetry ON
+- [ ] Existing tests pass with telemetry OFF
+
+---
+
+## Task 2.8: RPC Span Attribute Enrichment — Node Health Context
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md) — adds node-level health context inspired by the community [xrpl-validator-dashboard](https://github.com/realgrapedrop/xrpl-validator-dashboard).
+>
+> **Downstream**: Phase 7 (MetricsRegistry uses these attributes for alerting context), Phase 10 (validation checks for these attributes).
+
+**Objective**: Add node-level health state to every `rpc.command.*` span so operators can correlate RPC behavior with node state in Tempo.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/RPCHandler.cpp`:
+  - In the `rpc.command.*` span creation block (after existing `setAttribute` calls for `xrpl.rpc.command`, `xrpl.rpc.version`, etc.):
+    - Add `xrpl.node.amendment_blocked` (bool) — from `context.app.getOPs().isAmendmentBlocked()`
+    - Add `xrpl.node.server_state` (string) — from `context.app.getOPs().strOperatingMode()`
+
+**New span attributes**:
+
+| Attribute                     | Type   | Source                                      | Example  |
+| ----------------------------- | ------ | ------------------------------------------- | -------- |
+| `xrpl.node.amendment_blocked` | bool   | `context.app.getOPs().isAmendmentBlocked()` | `true`   |
+| `xrpl.node.server_state`      | string | `context.app.getOPs().strOperatingMode()`   | `"full"` |
+
+**Rationale**: When a node is amendment-blocked or in a degraded state, every RPC response is suspect. Tagging spans with this state enables Tempo TraceQL queries like:
+
+```
+{name=~"rpc.command.*"} | xrpl.node.amendment_blocked = true
+```
+
+This surfaces all RPCs served during a blocked period — critical for post-incident analysis.
+
+**Key modified files**:
+
+- `src/xrpld/rpc/detail/RPCHandler.cpp`
+
+**Exit Criteria**:
+
+- [ ] `rpc.command.server_info` spans carry `xrpl.node.amendment_blocked` and `xrpl.node.server_state` attributes
+- [ ] No measurable latency impact (attribute values are cached atomics, not computed per-call)
+- [ ] Attributes appear in Tempo trace detail view
+
+---
+
+## Summary
+
+| Task | Description                                 | New Files | Modified Files | Depends On |
+| ---- | ------------------------------------------- | --------- | -------------- | ---------- |
+| 2.1  | W3C Trace Context header extraction         | 2         | 2              | POC        |
+| 2.2  | Add XRPL_TRACE_PEER/LEDGER macros           | 0         | 1              | POC        |
+| 2.3  | Add shouldTraceLedger() interface method    | 0         | 3              | POC        |
+| 2.4  | Unit tests for core telemetry               | 2         | 1              | POC        |
+| 2.5  | Enhanced RPC span attributes                | 0         | 2              | POC        |
+| 2.6  | Build verification and performance baseline | 0         | 0              | 2.1-2.5    |
+| 2.8  | RPC span attribute enrichment (node health) | 0         | 1              | 2.5        |
+
+**Parallel work**: Tasks 2.1, 2.2, 2.3 can run in parallel. Task 2.4 depends on 2.3. Task 2.5 can run in parallel with 2.4. Task 2.6 depends on all others. Task 2.8 depends on 2.5 (existing span creation must be in place).
+
+---
+
+## Known Issues / Future Work
+
+### Thread safety of TelemetryImpl::stop() vs startSpan()
+
+`TelemetryImpl::stop()` resets `sdkProvider_` (a `std::shared_ptr`) without
+synchronization. `getTracer()` reads the same member from RPC handler threads.
+This is a data race if any thread calls `startSpan()` concurrently with `stop()`.
+
+**Current mitigation**: `Application::stop()` shuts down `serverHandler_`,
+`overlay_`, and `jobQueue_` before calling `telemetry_->stop()`, so no callers
+remain. See comments in `Telemetry.cpp:stop()` and `Application.cpp`.
+
+**TODO**: Add an `std::atomic<bool> stopped_` flag checked in `getTracer()` to
+make this robust against future shutdown order changes.
+
+### Macro incompatibility: XRPL_TRACE_SPAN vs XRPL_TRACE_SET_ATTR
+
+`XRPL_TRACE_SPAN` and `XRPL_TRACE_SPAN_KIND` declare `_xrpl_guard_` as a bare
+`SpanGuard`, but `XRPL_TRACE_SET_ATTR` and `XRPL_TRACE_EXCEPTION` call
+`_xrpl_guard_.has_value()` which requires `std::optional<SpanGuard>`. Using
+`XRPL_TRACE_SPAN` followed by `XRPL_TRACE_SET_ATTR` in the same scope would
+fail to compile.
+
+**Current mitigation**: No call site currently uses `XRPL_TRACE_SPAN` — all
+production code uses the conditional macros (`XRPL_TRACE_RPC`, `XRPL_TRACE_TX`,
+etc.) which correctly wrap the guard in `std::optional`.
+
+**TODO**: Either make `XRPL_TRACE_SPAN`/`XRPL_TRACE_SPAN_KIND` also wrap in
+`std::optional`, or document that `XRPL_TRACE_SET_ATTR` is only compatible with
+the conditional macros.

OpenTelemetryPlan/Phase3_taskList.md

@@ -0,0 +1,300 @@
+# Phase 3: Transaction Tracing Task List
+
+> **Goal**: Trace the full transaction lifecycle from RPC submission through peer relay, including cross-node context propagation via Protocol Buffer extensions. This is the WALK phase that demonstrates true distributed tracing.
+>
+> **Scope**: Protocol Buffer `TraceContext` message, context serialization, PeerImp transaction instrumentation, NetworkOPs processing instrumentation, HashRouter visibility, and multi-node relay context propagation.
+>
+> **Branch**: `pratik/otel-phase3-tx-tracing` (from `pratik/otel-phase2-rpc-tracing`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                                                        |
+| ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
+| [04-code-samples.md](./04-code-samples.md)                   | TraceContext protobuf (§4.4.1), PeerImp instrumentation (§4.5.1), context serialization (§4.4.2) |
+| [01-architecture-analysis.md](./01-architecture-analysis.md) | Transaction flow (§1.3), key trace points (§1.6)                                                 |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 3 tasks (§6.4), definition of done (§6.11.3)                                               |
+| [02-design-decisions.md](./02-design-decisions.md)           | Context propagation design (§2.5), attribute schema (§2.4.3)                                     |
+
+---
+
+## Task 3.1: Define TraceContext Protocol Buffer Message
+
+**Objective**: Add trace context fields to the P2P protocol messages so trace IDs can propagate across nodes.
+
+**What to do**:
+
+- Edit `include/xrpl/proto/xrpl.proto` (or `src/ripple/proto/ripple.proto`, wherever the proto is):
+  - Add `TraceContext` message definition:
+    ```protobuf
+    message TraceContext {
+        bytes trace_id = 1;      // 16-byte trace identifier
+        bytes span_id = 2;       // 8-byte span identifier
+        uint32 trace_flags = 3;  // bit 0 = sampled
+        string trace_state = 4;  // W3C tracestate value
+    }
+    ```
+  - Add `optional TraceContext trace_context = 1001;` to:
+    - `TMTransaction`
+    - `TMProposeSet` (for Phase 4 use)
+    - `TMValidation` (for Phase 4 use)
+  - Use high field numbers (1001+) to avoid conflicts with existing fields
+
+- Regenerate protobuf C++ code
+
+**Key modified files**:
+
+- `include/xrpl/proto/xrpl.proto` (or equivalent)
+
+**Reference**:
+
+- [04-code-samples.md §4.4.1](./04-code-samples.md) — TraceContext message definition
+- [02-design-decisions.md §2.5.2](./02-design-decisions.md) — Protocol buffer context propagation design
+
+---
+
+## Task 3.2: Implement Protobuf Context Serialization
+
+**Objective**: Create utilities to serialize/deserialize OTel trace context to/from protobuf `TraceContext` messages.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/TraceContextPropagator.h` (extend from Phase 2 if exists, or add protobuf methods):
+  - Add protobuf-specific methods:
+    - `static Context extractFromProtobuf(protocol::TraceContext const& proto)` — reconstruct OTel context from protobuf fields
+    - `static void injectToProtobuf(Context const& ctx, protocol::TraceContext& proto)` — serialize current span context into protobuf fields
+  - Both methods guard behind `#ifdef XRPL_ENABLE_TELEMETRY`
+
+- Create/extend `src/libxrpl/telemetry/TraceContextPropagator.cpp`:
+  - Implement extraction: read trace_id (16 bytes), span_id (8 bytes), trace_flags from protobuf, construct `SpanContext`, wrap in `Context`
+  - Implement injection: get current span from context, serialize its TraceId, SpanId, and TraceFlags into protobuf fields
+
+**Key new/modified files**:
+
+- `include/xrpl/telemetry/TraceContextPropagator.h`
+- `src/libxrpl/telemetry/TraceContextPropagator.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.4.2](./04-code-samples.md) — Full extract/inject implementation
+
+---
+
+## Task 3.3: Instrument PeerImp Transaction Handling
+
+**Objective**: Add trace spans to the peer-level transaction receive and relay path.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - In `onMessage(TMTransaction)` / `handleTransaction()`:
+    - Extract parent trace context from incoming `TMTransaction::trace_context` field (if present)
+    - Create `tx.receive` span as child of extracted context (or new root if none)
+    - Set attributes: `xrpl.tx.hash`, `xrpl.peer.id`, `xrpl.tx.status`
+    - On HashRouter suppression (duplicate): set `xrpl.tx.suppressed=true`, add `tx.duplicate` event
+    - Wrap validation call with child span `tx.validate`
+    - Wrap relay with `tx.relay` span
+  - When relaying to peers:
+    - Inject current trace context into outgoing `TMTransaction::trace_context`
+    - Set `xrpl.tx.relay_count` attribute
+
+- Include `TracingInstrumentation.h` and use `XRPL_TRACE_TX` macro
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Full PeerImp instrumentation example
+- [01-architecture-analysis.md §1.3](./01-architecture-analysis.md) — Transaction flow diagram
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.receive trace point
+
+---
+
+## Task 3.4: Instrument NetworkOPs Transaction Processing
+
+**Objective**: Trace the transaction processing pipeline in NetworkOPs, covering both sync and async paths.
+
+**What to do**:
+
+- Edit `src/xrpld/app/misc/NetworkOPs.cpp`:
+  - In `processTransaction()`:
+    - Create `tx.process` span
+    - Set attributes: `xrpl.tx.hash`, `xrpl.tx.type`, `xrpl.tx.local` (whether from RPC or peer)
+    - Record whether sync or async path is taken
+
+  - In `doTransactionAsync()`:
+    - Capture parent context before queuing
+    - Create `tx.queue` span with queue depth attribute
+    - Add event when transaction is dequeued for processing
+
+  - In `doTransactionSync()`:
+    - Create `tx.process_sync` span
+    - Record result (applied, queued, rejected)
+
+**Key modified files**:
+
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+**Reference**:
+
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.validate and tx.process trace points
+- [02-design-decisions.md §2.4.3](./02-design-decisions.md) — Transaction attribute schema
+
+---
+
+## Task 3.5: Instrument HashRouter for Dedup Visibility
+
+**Objective**: Make transaction deduplication visible in traces by recording HashRouter decisions as span attributes/events.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp` (in handleTransaction):
+  - After calling `HashRouter::shouldProcess()` or `addSuppressionPeer()`:
+    - Record `xrpl.tx.suppressed` attribute (true/false)
+    - Record `xrpl.tx.flags` showing current HashRouter state (SAVED, TRUSTED, etc.)
+    - Add `tx.first_seen` or `tx.duplicate` event
+
+- This is NOT a modification to HashRouter itself — just recording its decisions as span attributes in the existing PeerImp instrumentation from Task 3.3.
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp` (same changes as 3.3, logically grouped)
+
+---
+
+## Task 3.6: Context Propagation in Transaction Relay
+
+**Objective**: Ensure trace context flows correctly when transactions are relayed between peers, creating linked spans across nodes.
+
+**What to do**:
+
+- Verify the relay path injects trace context:
+  - When `PeerImp` relays a transaction, the `TMTransaction` message should carry `trace_context`
+  - When a remote peer receives it, the context is extracted and used as parent
+
+- Test context propagation:
+  - Manually verify with 2+ node setup that trace IDs match across nodes
+  - Confirm parent-child span relationships are correct in Tempo
+
+- Handle edge cases:
+  - Missing trace context (older peers): create new root span
+  - Corrupted trace context: log warning, create new root span
+  - Sampled-out traces: respect trace flags
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+- `src/xrpld/overlay/detail/OverlayImpl.cpp` (if relay method needs context param)
+
+**Reference**:
+
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — Context propagation design
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Relay context injection pattern
+
+---
+
+## Task 3.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 3 changes compile and work correctly.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions
+3. Run existing unit tests
+4. Verify protobuf regeneration produces correct C++ code
+5. Document any issues encountered
+
+**Verification Checklist**:
+
+- [ ] Protobuf changes generate valid C++
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass
+- [ ] No undefined symbols from new telemetry calls
+
+---
+
+## Task 3.8: Transaction Span Peer Version Attribute
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md) — adds peer version context inspired by the community [xrpl-validator-dashboard](https://github.com/realgrapedrop/xrpl-validator-dashboard).
+>
+> **Upstream**: Phase 2 (RPC span infrastructure must exist).
+> **Downstream**: Phase 10 (validation checks for this attribute).
+
+**Objective**: Add the relaying peer's rippled version to `tx.receive` spans so operators can correlate transaction issues with peer version mismatches during network upgrades.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - In the `tx.receive` span block (after existing `xrpl.peer.id` setAttribute call):
+    - Add `xrpl.peer.version` (string) — from `this->getVersion()`
+    - Only set if `getVersion()` returns a non-empty string (avoid empty-string attributes)
+
+**New span attribute**:
+
+| Attribute           | Type   | Source               | Example           |
+| ------------------- | ------ | -------------------- | ----------------- |
+| `xrpl.peer.version` | string | `peer->getVersion()` | `"rippled-2.4.0"` |
+
+**Rationale**: Transaction relay is where version mismatches cause subtle serialization or validation bugs. Tracing "this tx came from a v2.3.0 peer" helps diagnose compatibility issues. The community dashboard tracks peer versions externally; this brings version awareness into the trace itself.
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Exit Criteria**:
+
+- [ ] `tx.receive` spans carry `xrpl.peer.version` attribute with a non-empty version string
+- [ ] Attribute is omitted (not set to empty string) when `getVersion()` returns empty
+- [ ] Attribute visible in Jaeger span detail view
+
+---
+
+## Summary
+
+| Task | Description                         | New Files | Modified Files | Depends On |
+| ---- | ----------------------------------- | --------- | -------------- | ---------- |
+| 3.1  | TraceContext protobuf message       | 0         | 1              | Phase 2    |
+| 3.2  | Protobuf context serialization      | 1-2       | 0              | 3.1        |
+| 3.3  | PeerImp transaction instrumentation | 0         | 1              | 3.2        |
+| 3.4  | NetworkOPs transaction processing   | 0         | 1              | Phase 2    |
+| 3.5  | HashRouter dedup visibility         | 0         | 1              | 3.3        |
+| 3.6  | Relay context propagation           | 0         | 1-2            | 3.3, 3.5   |
+| 3.7  | Build verification and testing      | 0         | 0              | 3.1-3.6    |
+| 3.8  | TX span peer version attribute      | 0         | 1              | 3.3        |
+
+**Parallel work**: Tasks 3.1 and 3.4 can start in parallel. Task 3.2 depends on 3.1. Tasks 3.3 and 3.5 depend on 3.2. Task 3.6 depends on 3.3 and 3.5. Task 3.8 depends on 3.3 (span must exist).
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.3](./06-implementation-phases.md)):
+
+- [ ] Transaction traces span across nodes
+- [ ] Trace context in Protocol Buffer messages
+- [ ] HashRouter deduplication visible in traces
+- [ ] <5% overhead on transaction throughput
+
+---
+
+## Known Issues / Future Work
+
+### Propagation utilities not yet wired into P2P flow
+
+`extractFromProtobuf()` and `injectToProtobuf()` in `TraceContextPropagator.h`
+are implemented and tested but not called from production code. To enable
+cross-node distributed traces:
+
+- Call `injectToProtobuf()` in `PeerImp` when sending `TMTransaction` /
+  `TMProposeSet` messages
+- Call `extractFromProtobuf()` in the corresponding message handlers to
+  reconstruct the parent span context, then pass it to `startSpan()` as the
+  parent
+
+This was deferred to validate single-node tracing performance first.
+
+### Unused trace_state proto field
+
+The `TraceContext.trace_state` field (field 4) in `xrpl.proto` is reserved for
+W3C `tracestate` vendor-specific key-value pairs but is not read or written by
+`TraceContextPropagator`. Wire it when cross-vendor trace propagation is needed.
+No wire cost since proto `optional` fields are zero-cost when absent.

OpenTelemetryPlan/Phase4_taskList.md

@@ -0,0 +1,896 @@
+# Phase 4: Consensus Tracing Task List
+
+> **Goal**: Full observability into consensus rounds — track round lifecycle, phase transitions, proposal handling, and validation. This is the RUN phase that completes the distributed tracing story.
+>
+> **Scope**: RCLConsensus instrumentation for round starts, phase transitions (open/establish/accept), proposal send/receive, validation handling, and correlation with transaction traces from Phase 3.
+>
+> **Branch**: `pratik/otel-phase4-consensus-tracing` (from `pratik/otel-phase3-tx-tracing`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                   |
+| ------------------------------------------------------------ | ----------------------------------------------------------- |
+| [04-code-samples.md](./04-code-samples.md)                   | Consensus instrumentation (§4.5.2), consensus span patterns |
+| [01-architecture-analysis.md](./01-architecture-analysis.md) | Consensus round flow (§1.4), key trace points (§1.6)        |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 4 tasks (§6.5), definition of done (§6.11.4)          |
+| [02-design-decisions.md](./02-design-decisions.md)           | Consensus attribute schema (§2.4.4)                         |
+
+---
+
+## Task 4.1: Instrument Consensus Round Start
+
+**Objective**: Create a root span for each consensus round that captures the round's key parameters.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - In `RCLConsensus::startRound()` (or the Adaptor's startRound):
+    - Create `consensus.round` span using `XRPL_TRACE_CONSENSUS` macro
+    - Set attributes:
+      - `xrpl.consensus.ledger.prev` — previous ledger hash
+      - `xrpl.consensus.ledger.seq` — target ledger sequence
+      - `xrpl.consensus.proposers` — number of trusted proposers
+      - `xrpl.consensus.mode` — "proposing" or "observing"
+    - Store the span context for use by child spans in phase transitions
+
+- Add a member to hold current round trace context:
+  - `opentelemetry::context::Context currentRoundContext_` (guarded by `#ifdef`)
+  - Updated at round start, used by phase transition spans
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/consensus/RCLConsensus.h` (add context member)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — startRound instrumentation example
+- [01-architecture-analysis.md §1.4](./01-architecture-analysis.md) — Consensus round flow
+
+---
+
+## Task 4.2: Instrument Phase Transitions
+
+**Objective**: Create child spans for each consensus phase (open, establish, accept) to show timing breakdown.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - Identify where phase transitions occur (the `Consensus<Adaptor>` template drives this)
+  - For each phase entry:
+    - Create span as child of `currentRoundContext_`: `consensus.phase.open`, `consensus.phase.establish`, `consensus.phase.accept`
+    - Set `xrpl.consensus.phase` attribute
+    - Add `phase.enter` event at start, `phase.exit` event at end
+    - Record phase duration in milliseconds
+
+  - In the `onClose` adaptor method:
+    - Create `consensus.ledger_close` span
+    - Set attributes: close_time, mode, transaction count in initial position
+
+  - Note: The Consensus template class in `src/xrpld/consensus/Consensus.h` drives phase transitions — Phase 4a instruments directly in the template
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- Possibly `include/xrpl/consensus/Consensus.h` (for template-level phase tracking)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — phaseTransition instrumentation
+
+---
+
+## Task 4.3: Instrument Proposal Handling
+
+**Objective**: Trace proposal send and receive to show validator coordination.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - In `Adaptor::propose()`:
+    - Create `consensus.proposal.send` span
+    - Set attributes: `xrpl.consensus.round` (proposal sequence), proposal hash
+    - Inject trace context into outgoing `TMProposeSet::trace_context` (from Phase 3 protobuf)
+
+  - In `Adaptor::peerProposal()` (or wherever peer proposals are received):
+    - Extract trace context from incoming `TMProposeSet::trace_context`
+    - Create `consensus.proposal.receive` span as child of extracted context
+    - Set attributes: `xrpl.consensus.proposer` (node ID), `xrpl.consensus.round`
+
+  - In `Adaptor::share(RCLCxPeerPos)`:
+    - Create `consensus.proposal.relay` span for relaying peer proposals
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — peerProposal instrumentation
+- [02-design-decisions.md §2.4.4](./02-design-decisions.md) — Consensus attribute schema
+
+---
+
+## Task 4.4: Instrument Validation Handling
+
+**Objective**: Trace validation send and receive to show ledger validation flow.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp` (or the validation handler):
+  - When sending our validation:
+    - Create `consensus.validation.send` span
+    - Set attributes: validated ledger hash, sequence, signing time
+
+  - When receiving a peer validation:
+    - Extract trace context from `TMValidation::trace_context` (if present)
+    - Create `consensus.validation.receive` span
+    - Set attributes: `xrpl.consensus.validator` (node ID), ledger hash
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp` (if validation handling is here)
+
+---
+
+## Task 4.5: Add Consensus-Specific Attributes
+
+**Objective**: Enrich consensus spans with detailed attributes for debugging and analysis.
+
+**What to do**:
+
+- Review all consensus spans and ensure they include:
+  - `xrpl.consensus.ledger.seq` — target ledger sequence number
+  - `xrpl.consensus.round` — consensus round number
+  - `xrpl.consensus.mode` — proposing/observing/wrongLedger
+  - `xrpl.consensus.phase` — current phase name
+  - `xrpl.consensus.phase_duration_ms` — time spent in phase
+  - `xrpl.consensus.proposers` — number of trusted proposers
+  - `xrpl.consensus.tx_count` — transactions in proposed set
+  - `xrpl.consensus.disputes` — number of disputed transactions
+  - `xrpl.consensus.converge_percent` — convergence percentage
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Task 4.6: Correlate Transaction and Consensus Traces
+
+**Objective**: Link transaction traces from Phase 3 with consensus traces so you can follow a transaction from submission through consensus into the ledger.
+
+**What to do**:
+
+- In `onClose()` or `onAccept()`:
+  - When building the consensus position, link the round span to individual transaction spans using span links (if OTel SDK supports it) or events
+  - At minimum, record the transaction hashes included in the consensus set as span events: `tx.included` with `xrpl.tx.hash` attribute
+
+- In `processTransactionSet()` (NetworkOPs):
+  - If the consensus round span context is available, create child spans for each transaction applied to the ledger
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+---
+
+## Task 4.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 4 changes compile and don't affect consensus timing.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions (critical for consensus code)
+3. Run existing consensus-related unit tests
+4. Verify that all macros expand to no-ops when disabled
+5. Check that no consensus-critical code paths are affected by instrumentation overhead
+
+**Verification Checklist**:
+
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing consensus tests pass
+- [ ] No new includes in consensus headers when telemetry is OFF
+- [ ] Phase timing instrumentation doesn't use blocking operations
+
+---
+
+## Task 4.8: Consensus Validation Span Enrichment — External Dashboard Parity
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md) — adds validation agreement context inspired by the community [xrpl-validator-dashboard](https://github.com/realgrapedrop/xrpl-validator-dashboard).
+>
+> **Upstream**: Phase 4 tasks 4.1-4.4 (span creation must exist).
+> **Downstream**: Phase 7 (ValidationTracker reads these attributes), Phase 10 (validation checks).
+
+**Objective**: Add ledger hash, validation type, and quorum data to consensus validation spans on both send and receive paths. This enables trace-level validation agreement analysis — filter by ledger hash to see which validators agreed for a given ledger.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - On the `consensus.validation.send` span (in `validate()` / `doAccept()`):
+    - Add `xrpl.validation.ledger_hash` (string) — the ledger hash being validated
+    - Add `xrpl.validation.full` (bool) — whether this is a full validation (not partial)
+  - On the `consensus.accept` span (in `onAccept()`):
+    - Add `xrpl.consensus.validation_quorum` (int64) — from `app_.validators().quorum()`
+    - Add `xrpl.consensus.proposers_validated` (int64) — from `result.proposers`
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - On the `peer.validation.receive` span:
+    - Add `xrpl.peer.validation.ledger_hash` (string) — from deserialized `STValidation` object
+    - Add `xrpl.peer.validation.full` (bool) — from `STValidation` flags
+
+**New span attributes**:
+
+| Span                        | Attribute                            | Type   | Source                            |
+| --------------------------- | ------------------------------------ | ------ | --------------------------------- |
+| `consensus.validation.send` | `xrpl.validation.ledger_hash`        | string | Ledger hash from validate() args  |
+| `consensus.validation.send` | `xrpl.validation.full`               | bool   | Full vs partial validation        |
+| `peer.validation.receive`   | `xrpl.peer.validation.ledger_hash`   | string | From STValidation deserialization |
+| `peer.validation.receive`   | `xrpl.peer.validation.full`          | bool   | From STValidation flags           |
+| `consensus.accept`          | `xrpl.consensus.validation_quorum`   | int64  | `app_.validators().quorum()`      |
+| `consensus.accept`          | `xrpl.consensus.proposers_validated` | int64  | `result.proposers`                |
+
+**Rationale**: The external dashboard's most valuable feature is validation agreement tracking. By recording the ledger hash on both outgoing and incoming validation spans, we create the raw data for agreement analysis at the trace level. Example Tempo query:
+
+```
+{name="consensus.validation.send"} | xrpl.validation.ledger_hash = "A1B2C3..."
+```
+
+Phase 7's `ValidationTracker` builds metric-level aggregation (1h/24h agreement %) on top of this data.
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Exit Criteria**:
+
+- [ ] `consensus.validation.send` spans carry `xrpl.validation.ledger_hash` and `xrpl.validation.full`
+- [ ] `peer.validation.receive` spans carry `xrpl.peer.validation.ledger_hash` and `xrpl.peer.validation.full`
+- [ ] `consensus.accept` spans carry `xrpl.consensus.validation_quorum` and `xrpl.consensus.proposers_validated`
+- [ ] Ledger hash attributes match between send and receive for the same ledger
+- [ ] No impact on consensus performance
+
+---
+
+## Summary
+
+| Task | Description                                 | New Files | Modified Files | Depends On    |
+| ---- | ------------------------------------------- | --------- | -------------- | ------------- |
+| 4.1  | Consensus round start instrumentation       | 0         | 2              | Phase 3       |
+| 4.2  | Phase transition instrumentation            | 0         | 1-2            | 4.1           |
+| 4.3  | Proposal handling instrumentation           | 0         | 1              | 4.1           |
+| 4.4  | Validation handling instrumentation         | 0         | 1-2            | 4.1           |
+| 4.5  | Consensus-specific attributes               | 0         | 1              | 4.2, 4.3, 4.4 |
+| 4.6  | Transaction-consensus correlation           | 0         | 2              | 4.2, Phase 3  |
+| 4.7  | Build verification and testing              | 0         | 0              | 4.1-4.6       |
+| 4.8  | Validation span enrichment (ext. dashboard) | 0         | 2              | 4.4           |
+
+**Parallel work**: Tasks 4.2, 4.3, and 4.4 can run in parallel after 4.1 is complete. Task 4.5 depends on all three. Task 4.6 depends on 4.2 and Phase 3. Task 4.8 depends on 4.4 (validation spans must exist).
+
+### Implemented Spans
+
+| Span Name                   | Method                             | Key Attributes                                                                                                                                                                                                        |
+| --------------------------- | ---------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `consensus.proposal.send`   | `Adaptor::propose`                 | `xrpl.consensus.round`                                                                                                                                                                                                |
+| `consensus.ledger_close`    | `Adaptor::onClose`                 | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode`                                                                                                                                                                    |
+| `consensus.accept`          | `Adaptor::onAccept`                | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms`                                                                                                                                                            |
+| `consensus.accept.apply`    | `Adaptor::doAccept`                | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state`, `proposing`, `round_time_ms`, `ledger.seq`, `parent_close_time`, `close_time_self`, `close_time_vote_bins`, `resolution_direction` |
+| `consensus.validation.send` | `Adaptor::onAccept` (via validate) | `xrpl.consensus.proposing`                                                                                                                                                                                            |
+
+#### Close Time Attributes (consensus.accept.apply)
+
+The `consensus.accept.apply` span captures ledger close time agreement details
+driven by `avCT_CONSENSUS_PCT` (75% validator agreement threshold):
+
+- **`xrpl.consensus.close_time`** — Agreed-upon ledger close time (epoch seconds). When validators disagree (`consensusCloseTime == epoch`), this is synthetically set to `prevCloseTime + 1s`.
+- **`xrpl.consensus.close_time_correct`** — `true` if validators reached agreement, `false` if they "agreed to disagree" (close time forced to prev+1s).
+- **`xrpl.consensus.close_resolution_ms`** — Rounding granularity for close time (starts at 30s, decreases as ledger interval stabilizes).
+- **`xrpl.consensus.state`** — `"finished"` (normal) or `"moved_on"` (consensus failed, adopted best available).
+- **`xrpl.consensus.proposing`** — Whether this node was proposing.
+- **`xrpl.consensus.round_time_ms`** — Total consensus round duration.
+- **`xrpl.consensus.parent_close_time`** — Previous ledger's close time (epoch seconds). Enables computing close-time deltas across consecutive rounds without correlating separate spans.
+- **`xrpl.consensus.close_time_self`** — This node's own proposed close time before consensus voting.
+- **`xrpl.consensus.close_time_vote_bins`** — Number of distinct close-time vote bins from peer proposals. Higher values indicate less agreement among validators.
+- **`xrpl.consensus.resolution_direction`** — Whether close-time resolution `"increased"` (coarser), `"decreased"` (finer), or stayed `"unchanged"` relative to the previous ledger.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.4](./06-implementation-phases.md)):
+
+- [x] Complete consensus round traces
+- [x] Phase transitions visible
+- [x] Proposals and validations traced
+- [x] Close time agreement tracked (per `avCT_CONSENSUS_PCT`)
+- [x] No impact on consensus timing
+
+---
+
+# Phase 4a: Establish-Phase Gap Fill & Cross-Node Correlation
+
+> **Goal**: Fill tracing gaps in the consensus establish phase (disputes, convergence,
+> threshold escalation, mode changes) and establish cross-node correlation using a
+> deterministic shared trace ID derived from `previousLedger.id()`.
+>
+> **Approach**: Direct instrumentation in `Consensus.h` — the generic consensus
+> template has full access to internal state (`convergePercent_`, `result_->disputes`,
+> `mode_`, threshold logic). Telemetry access comes via a single new adaptor
+> method `getTelemetry()`. Long-lived spans (round, establish) are stored as
+> class members using `SpanGuard` directly — NOT the `XRPL_TRACE_*` convenience
+> macros (which create local variables named `_xrpl_guard_`). Short-lived
+> scoped spans (update_positions, check) can use the macros. All code compiles
+> to no-ops when `XRPL_ENABLE_TELEMETRY` is not defined.
+>
+> **Branch**: `pratik/otel-phase4-consensus-tracing`
+
+## Design: Switchable Correlation Strategy
+
+Two strategies for cross-node trace correlation, switchable via config:
+
+### Strategy A — Deterministic Trace ID (Default)
+
+Derive `trace_id = SHA256(previousLedger.id())[0:16]` so all nodes in the same
+consensus round share the same trace_id without P2P context propagation.
+
+- **Pros**: All nodes appear in the same trace in Tempo/Jaeger automatically.
+  No collector-side post-processing needed.
+- **Cons**: Overrides OTel's random trace_id generation; requires custom
+  `IdGenerator` or manual span context construction.
+
+### Strategy B — Attribute-Based Correlation
+
+Use normal random trace_id but attach `xrpl.consensus.ledger_id` as an attribute
+on every consensus span. Correlation happens at query time via Tempo/Grafana
+`by attribute` queries.
+
+- **Pros**: Standard OTel trace_id semantics; no SDK customization.
+- **Cons**: Cross-node correlation requires query-time joins, not automatic.
+
+### Config
+
+```ini
+[telemetry]
+# "deterministic" (default) or "attribute"
+consensus_trace_strategy=deterministic
+```
+
+### Implementation
+
+In `RCLConsensus::Adaptor::startRound()`:
+
+- If `deterministic`:
+  1. Compute `trace_id_bytes = SHA256(prevLedgerID)[0:16]`
+  2. Construct `opentelemetry::trace::TraceId(trace_id_bytes)`
+  3. Create a synthetic `SpanContext` with this trace_id and a random span_id:
+     ```cpp
+     auto traceId = opentelemetry::trace::TraceId(trace_id_bytes);
+     auto spanId  = opentelemetry::trace::SpanId(random_8_bytes);
+     auto syntheticCtx = opentelemetry::trace::SpanContext(
+         traceId, spanId, opentelemetry::trace::TraceFlags(1), false);
+     ```
+  4. Wrap in `opentelemetry::context::Context` via
+     `opentelemetry::trace::SetSpan(context, syntheticSpan)`
+  5. Call `startSpan("consensus.round", parentContext)` so the new span
+     inherits the deterministic trace_id.
+- If `attribute`: start a normal `consensus.round` span, set
+  `xrpl.consensus.ledger_id = previousLedger.id()` as attribute.
+
+Both strategies always set `xrpl.consensus.round_id` (round number) and
+`xrpl.consensus.ledger_id` (previous ledger hash) as attributes.
+
+---
+
+## Design: Span Hierarchy
+
+```
+consensus.round  (root — created in RCLConsensus::startRound, closed at accept)
+│   link → previous round's SpanContext (follows-from)
+│
+├── consensus.establish  (phaseEstablish → acceptance, in Consensus.h)
+│   ├── consensus.update_positions  (each updateOurPositions call)
+│   │   └── consensus.dispute.resolve  (per-tx dispute resolution event)
+│   ├── consensus.check  (each haveConsensus call)
+│   └── consensus.mode_change  (short-lived span in adaptor on mode transition)
+│
+├── consensus.accept  (existing onAccept span — reparented under round)
+│
+└── consensus.validation.send  (existing — reparented, follows-from link to round)
+```
+
+### Span Links (follows-from relationships)
+
+| Link Source                               | Link Target                | Rationale                                                                      |
+| ----------------------------------------- | -------------------------- | ------------------------------------------------------------------------------ |
+| `consensus.round` (N+1)                   | `consensus.round` (N)      | Causal chain: round N+1 exists because round N accepted                        |
+| `consensus.validation.send`               | `consensus.round`          | Validation follows from the round that produced it; may outlive the round span |
+| _(Phase 4b)_ Received proposal processing | Sender's `consensus.round` | Cross-node causal link via P2P context propagation                             |
+
+---
+
+## Task 4a.0: Prerequisites — Extend SpanGuard and Telemetry APIs
+
+**Objective**: Add missing API surface needed by later tasks.
+
+**What to do**:
+
+1. **Add `SpanGuard::addEvent()` with attributes** (needed by Task 4a.5):
+   The current `addEvent(string_view name)` only accepts a name. Add an
+   overload that accepts key-value attributes:
+
+   ```cpp
+   void addEvent(std::string_view name,
+       std::initializer_list<
+           std::pair<opentelemetry::nostd::string_view,
+                     opentelemetry::common::AttributeValue>> attributes)
+   {
+       span_->AddEvent(std::string(name), attributes);
+   }
+   ```
+
+2. **Add a `Telemetry::startSpan()` overload that accepts span links** (needed by Tasks 4a.2, 4a.8):
+   The current `startSpan()` has no span link support. Add an overload that
+   accepts a vector of `SpanContext` links for follows-from relationships:
+
+   ```cpp
+   virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+   startSpan(
+       std::string_view name,
+       opentelemetry::context::Context const& parentContext,
+       std::vector<opentelemetry::trace::SpanContext> const& links,
+       opentelemetry::trace::SpanKind kind = opentelemetry::trace::SpanKind::kInternal) = 0;
+   ```
+
+3. **Add `XRPL_TRACE_ADD_EVENT` macro** (needed by Task 4a.5):
+   Add to `TracingInstrumentation.h` to expose `addEvent(name, attrs)` through
+   the macro interface (consistent with `XRPL_TRACE_SET_ATTR` pattern):
+   ```cpp
+   #ifdef XRPL_ENABLE_TELEMETRY
+   #define XRPL_TRACE_ADD_EVENT(name, ...)               \
+       if (_xrpl_guard_.has_value())                     \
+       {                                                 \
+           _xrpl_guard_->addEvent(name, __VA_ARGS__);   \
+       }
+   #else
+   #define XRPL_TRACE_ADD_EVENT(name, ...) ((void)0)
+   #endif
+   ```
+
+**Key modified files**:
+
+- `include/xrpl/telemetry/SpanGuard.h` — add `addEvent()` overload
+- `include/xrpl/telemetry/Telemetry.h` — add `startSpan()` with links
+- `src/xrpld/telemetry/Telemetry.cpp` — implement new overload
+- `src/xrpld/telemetry/NullTelemetry.cpp` — no-op implementation
+- `src/xrpld/telemetry/TracingInstrumentation.h` — add `XRPL_TRACE_ADD_EVENT` macro
+
+---
+
+## Task 4a.1: Adaptor `getTelemetry()` Method
+
+**Objective**: Give `Consensus.h` access to the telemetry subsystem without
+coupling the generic template to OTel headers.
+
+**What to do**:
+
+- Add `getTelemetry()` method to the Adaptor concept (returns
+  `xrpl::telemetry::Telemetry&`). The return type is already forward-declared
+  behind `#ifdef XRPL_ENABLE_TELEMETRY`.
+- Implement in `RCLConsensus::Adaptor` — delegates to `app_.getTelemetry()`.
+- In `Consensus.h`, the `XRPL_TRACE_*` macros call
+  `adaptor_.getTelemetry()` — when telemetry is disabled, the macros expand to
+  `((void)0)` and the method is never called.
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.h` — declare `getTelemetry()`
+- `src/xrpld/app/consensus/RCLConsensus.cpp` — implement `getTelemetry()`
+
+---
+
+## Task 4a.2: Switchable Round Span with Deterministic Trace ID
+
+**Objective**: Create a `consensus.round` root span in `startRound()` that uses
+the switchable correlation strategy. Store span context as a member for child
+spans in `Consensus.h`.
+
+**What to do**:
+
+- In `RCLConsensus::Adaptor::startRound()` (or a new helper):
+  - Read `consensus_trace_strategy` from config.
+  - **Deterministic**: compute `trace_id = SHA256(prevLedgerID)[0:16]`.
+    Construct a `SpanContext` with this trace_id, then start
+    `consensus.round` span as child of that context.
+  - **Attribute**: start normal `consensus.round` span.
+  - Set attributes on both: `xrpl.consensus.round_id`,
+    `xrpl.consensus.ledger_id`, `xrpl.consensus.ledger.seq`,
+    `xrpl.consensus.mode`.
+  - Store the round span in `Consensus` as a member (see Task 4a.3).
+  - If a previous round's span context is available, add a **span link**
+    (follows-from) to establish the round chain.
+
+- Add `createDeterministicTraceId(hash)` utility to
+  `include/xrpl/telemetry/Telemetry.h` (returns 16-byte trace ID from a
+  256-bit hash by truncation).
+
+- Add `consensus_trace_strategy` to `Telemetry::Setup` and
+  `TelemetryConfig.cpp` parser:
+  ```cpp
+  /** Cross-node correlation strategy: "deterministic" or "attribute". */
+  std::string consensusTraceStrategy = "deterministic";
+  ```
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `include/xrpl/telemetry/Telemetry.h` — `createDeterministicTraceId()`
+- `src/xrpld/telemetry/TelemetryConfig.cpp` — parse new config option
+
+---
+
+## Task 4a.3: Span Members in `Consensus.h`
+
+**Objective**: Add span storage to the `Consensus` class so that spans created
+in `startRound()` (adaptor) are accessible from `phaseEstablish()`,
+`updateOurPositions()`, and `haveConsensus()` (template methods).
+
+**What to do**:
+
+- Add to `Consensus` private members (guarded by `#ifdef XRPL_ENABLE_TELEMETRY`):
+  ```cpp
+  #ifdef XRPL_ENABLE_TELEMETRY
+  std::optional<xrpl::telemetry::SpanGuard> roundSpan_;
+  std::optional<xrpl::telemetry::SpanGuard> establishSpan_;
+  opentelemetry::context::Context prevRoundContext_;
+  #endif
+  ```
+- `roundSpan_` is created in `startRound()` via the adaptor and stored.
+  Its `SpanGuard::Scope` member keeps the span active on the thread context
+  for the entire round lifetime.
+- `establishSpan_` is created when entering phaseEstablish and cleared on accept.
+  It becomes a child of `roundSpan_` via OTel's thread-local context propagation.
+- `prevRoundContext_` stores the previous round's context for follows-from links.
+
+**Threading assumption**: `startRound()`, `phaseEstablish()`, `updateOurPositions()`,
+and `haveConsensus()` all run on the same thread (the consensus job queue thread).
+This is required for the `SpanGuard::Scope`-based parent-child hierarchy to work.
+The `Consensus` class documentation confirms it is NOT thread-safe and calls are
+serialized by the application.
+
+- Add conditional include at top of `Consensus.h`:
+  ```cpp
+  #ifdef XRPL_ENABLE_TELEMETRY
+  #include <xrpl/telemetry/SpanGuard.h>
+  #include <xrpld/telemetry/TracingInstrumentation.h>
+  #endif
+  ```
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h`
+
+---
+
+## Task 4a.4: Instrument `phaseEstablish()`
+
+**Objective**: Create `consensus.establish` span wrapping the establish phase,
+with attributes for convergence progress.
+
+**What to do**:
+
+- At the start of `phaseEstablish()` (line 1298), if `establishSpan_` is not
+  yet created, create it as child of `roundSpan_` using the **direct API**
+  (NOT the `XRPL_TRACE_CONSENSUS` macro, which creates a local variable):
+
+  ```cpp
+  #ifdef XRPL_ENABLE_TELEMETRY
+  if (!establishSpan_ && adaptor_.getTelemetry().shouldTraceConsensus())
+  {
+      establishSpan_.emplace(
+          adaptor_.getTelemetry().startSpan("consensus.establish"));
+  }
+  #endif
+  ```
+
+- Set attributes on each call:
+  - `xrpl.consensus.converge_percent` — `convergePercent_`
+  - `xrpl.consensus.establish_count` — `establishCounter_`
+  - `xrpl.consensus.proposers` — `currPeerPositions_.size()`
+
+- On phase exit (transition to accept), close the establish span and record
+  final duration.
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h` — `phaseEstablish()` method
+
+---
+
+## Task 4a.5: Instrument `updateOurPositions()`
+
+**Objective**: Trace each position update cycle including dispute resolution
+details.
+
+**What to do**:
+
+- At the start of `updateOurPositions()` (line 1418), create a scoped child
+  span. This method is called and returns within a single `phaseEstablish()`
+  call, so the `XRPL_TRACE_CONSENSUS` macro works here (scoped local):
+
+  ```cpp
+  XRPL_TRACE_CONSENSUS(adaptor_.getTelemetry(), "consensus.update_positions");
+  ```
+
+- Set attributes:
+  - `xrpl.consensus.disputes_count` — `result_->disputes.size()`
+  - `xrpl.consensus.converge_percent` — current convergence
+  - `xrpl.consensus.proposers_agreed` — count of peers with same position
+  - `xrpl.consensus.proposers_total` — total peer positions
+
+- Inside the dispute resolution loop, for each dispute that changes our vote,
+  add an **event** with attributes using `XRPL_TRACE_ADD_EVENT` (from Task 4a.0):
+  ```cpp
+  XRPL_TRACE_ADD_EVENT("dispute.resolve", {
+      {"xrpl.tx.id", std::string(tx_id)},
+      {"xrpl.dispute.our_vote", our_vote},
+      {"xrpl.dispute.yays", static_cast<int64_t>(yays)},
+      {"xrpl.dispute.nays", static_cast<int64_t>(nays)}
+  });
+  ```
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h` — `updateOurPositions()` method
+
+---
+
+## Task 4a.6: Instrument `haveConsensus()` (Threshold & Convergence)
+
+**Objective**: Trace consensus checking including threshold escalation
+(`ConsensusParms::AvalancheState::{init, mid, late, stuck}`).
+
+**What to do**:
+
+- At the start of `haveConsensus()` (line 1598), create a scoped child span:
+
+  ```cpp
+  XRPL_TRACE_CONSENSUS(adaptor_.getTelemetry(), "consensus.check");
+  ```
+
+- Set attributes:
+  - `xrpl.consensus.agree_count` — peers that agree with our position
+  - `xrpl.consensus.disagree_count` — peers that disagree
+  - `xrpl.consensus.converge_percent` — convergence percentage
+  - `xrpl.consensus.result` — ConsensusState result (Yes/No/MovedOn)
+
+- The free function `checkConsensus()` in `Consensus.cpp` (line 151) determines
+  thresholds based on `currentAgreeTime`. Threshold values come from
+  `ConsensusParms::avalancheCutoffs` (defined in `ConsensusParms.h`).
+  The escalation states are `ConsensusParms::AvalancheState::{init, mid, late, stuck}`.
+  Record the effective threshold as an attribute on the span:
+  - `xrpl.consensus.threshold_percent` — current threshold from `avalancheCutoffs`
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h` — `haveConsensus()` method
+
+---
+
+## Task 4a.7: Instrument Mode Changes
+
+**Objective**: Trace consensus mode transitions (proposing ↔ observing,
+wrongLedger, switchedLedger).
+
+**What to do**:
+
+Mode changes are rare (typically 0-1 per round), so a **standalone short-lived
+span** is appropriate (not an event). This captures timing of the mode change
+itself.
+
+- In `RCLConsensus::Adaptor::onModeChange()`, create a scoped span:
+
+  ```cpp
+  XRPL_TRACE_CONSENSUS(app_.getTelemetry(), "consensus.mode_change");
+  XRPL_TRACE_SET_ATTR("xrpl.consensus.mode.old", to_string(before).c_str());
+  XRPL_TRACE_SET_ATTR("xrpl.consensus.mode.new", to_string(after).c_str());
+  ```
+
+- Note: `MonitoredMode::set()` (line 304 in `Consensus.h`) calls
+  `adaptor_.onModeChange(before, after)` — so the span is created in the
+  adaptor, which already has telemetry access. No instrumentation needed
+  in `Consensus.h` for this task.
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp` — `onModeChange()`
+
+---
+
+## Task 4a.8: Reparent Existing Spans Under Round
+
+**Objective**: Make existing consensus spans (`consensus.accept`,
+`consensus.accept.apply`, `consensus.validation.send`) children of the
+`consensus.round` root span instead of being standalone.
+
+**What to do**:
+
+- The existing spans in `onAccept()`, `doAccept()`, and `validate()` use
+  `XRPL_TRACE_CONSENSUS(app_.getTelemetry(), ...)` which creates standalone
+  spans on the current thread's context.
+- After Task 4a.2 creates the round span and stores it, these methods run on
+  the same thread within the round span's scope, so they automatically become
+  children. Verify this works correctly.
+- For `consensus.validation.send`: add a **span link** (follows-from) to the
+  round span context, since the validation may be processed after the round
+  completes.
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp` — verify parent-child hierarchy
+
+---
+
+## Task 4a.9: Build Verification and Testing
+
+**Objective**: Verify all Phase 4a changes compile cleanly with telemetry ON
+and OFF, and don't affect consensus timing.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify macros expand to no-ops, no new includes
+   leak into `Consensus.h` when disabled
+3. Run existing consensus unit tests
+4. Verify `#ifdef XRPL_ENABLE_TELEMETRY` guards on all new members in
+   `Consensus.h`
+5. Run `pccl` pre-commit checks
+
+**Verification Checklist**:
+
+- [x] Build succeeds with telemetry ON
+- [x] Build succeeds with telemetry OFF
+- [x] Existing consensus tests pass
+- [x] `Consensus.h` has zero OTel includes when telemetry is OFF
+- [x] No new virtual calls in hot consensus paths
+- [x] `pccl` passes
+
+---
+
+## Phase 4a Summary
+
+| Task | Description                                      | New Files | Modified Files | Depends On |
+| ---- | ------------------------------------------------ | --------- | -------------- | ---------- |
+| 4a.0 | Prerequisites: extend SpanGuard & Telemetry APIs | 0         | 4              | Phase 4    |
+| 4a.1 | Adaptor `getTelemetry()` method                  | 0         | 2              | Phase 4    |
+| 4a.2 | Switchable round span with deterministic traceID | 0         | 3              | 4a.0, 4a.1 |
+| 4a.3 | Span members in `Consensus.h`                    | 0         | 1              | 4a.1       |
+| 4a.4 | Instrument `phaseEstablish()`                    | 0         | 1              | 4a.3       |
+| 4a.5 | Instrument `updateOurPositions()`                | 0         | 1              | 4a.0, 4a.3 |
+| 4a.6 | Instrument `haveConsensus()` (thresholds)        | 0         | 1              | 4a.3       |
+| 4a.7 | Instrument mode changes                          | 0         | 1              | 4a.1       |
+| 4a.8 | Reparent existing spans under round              | 0         | 1              | 4a.0, 4a.2 |
+| 4a.9 | Build verification and testing                   | 0         | 0              | 4a.0-4a.8  |
+
+**Parallel work**: Tasks 4a.0 and 4a.1 can run in parallel. Tasks 4a.4, 4a.5, 4a.6, and 4a.7 can run in parallel after 4a.3 (and 4a.0 for 4a.5).
+
+### New Spans (Phase 4a)
+
+| Span Name                    | Location           | Key Attributes                                                                     |
+| ---------------------------- | ------------------ | ---------------------------------------------------------------------------------- |
+| `consensus.round`            | `RCLConsensus.cpp` | `round_id`, `ledger_id`, `ledger.seq`, `mode`; link → prev round                   |
+| `consensus.establish`        | `Consensus.h`      | `converge_percent`, `establish_count`, `proposers`                                 |
+| `consensus.update_positions` | `Consensus.h`      | `disputes_count`, `converge_percent`, `proposers_agreed`, `proposers_total`        |
+| `consensus.check`            | `Consensus.h`      | `agree_count`, `disagree_count`, `converge_percent`, `result`, `threshold_percent` |
+| `consensus.mode_change`      | `RCLConsensus.cpp` | `mode.old`, `mode.new`                                                             |
+
+### New Events (Phase 4a)
+
+| Event Name        | Parent Span                  | Attributes                          |
+| ----------------- | ---------------------------- | ----------------------------------- |
+| `dispute.resolve` | `consensus.update_positions` | `tx_id`, `our_vote`, `yays`, `nays` |
+
+### New Attributes (Phase 4a)
+
+```cpp
+// Round-level (on consensus.round)
+"xrpl.consensus.round_id"              = int64    // Consensus round number
+"xrpl.consensus.ledger_id"             = string   // previousLedger.id() hash
+"xrpl.consensus.trace_strategy"        = string   // "deterministic" or "attribute"
+
+// Establish-level
+"xrpl.consensus.converge_percent"      = int64    // Convergence % (0-100+)
+"xrpl.consensus.establish_count"       = int64    // Number of establish iterations
+"xrpl.consensus.disputes_count"        = int64    // Active disputes
+"xrpl.consensus.proposers_agreed"      = int64    // Peers agreeing with us
+"xrpl.consensus.proposers_total"       = int64    // Total peer positions
+"xrpl.consensus.agree_count"           = int64    // Peers that agree (haveConsensus)
+"xrpl.consensus.disagree_count"        = int64    // Peers that disagree
+"xrpl.consensus.threshold_percent"     = int64    // Current threshold (50/65/70/95)
+"xrpl.consensus.result"                = string   // "yes", "no", "moved_on"
+
+// Mode change
+"xrpl.consensus.mode.old"              = string   // Previous mode
+"xrpl.consensus.mode.new"              = string   // New mode
+```
+
+### Implementation Notes
+
+- **Separation of concerns**: All non-trivial telemetry code extracted to private
+  helpers (`startRoundTracing`, `createValidationSpan`, `startEstablishTracing`,
+  `updateEstablishTracing`, `endEstablishTracing`). Business logic methods contain
+  only single-line `#ifdef` blocks calling these helpers.
+- **Thread safety**: `createValidationSpan()` runs on the jtACCEPT worker thread.
+  Instead of accessing `roundSpan_` across threads, a `roundSpanContext_` snapshot
+  (lightweight `SpanContext` value type) is captured on the consensus thread in
+  `startRoundTracing()` and read by `createValidationSpan()`. The job queue
+  provides the happens-before guarantee.
+- **Macro safety**: `XRPL_TRACE_ADD_EVENT` uses `do { } while (0)` to prevent
+  dangling-else issues.
+- **Config validation**: `consensus_trace_strategy` is validated to be either
+  `"deterministic"` or `"attribute"`, falling back to `"deterministic"` for
+  unrecognised values.
+- **Plan deviation**: `roundSpan_` is stored in `RCLConsensus::Adaptor` (not
+  `Consensus.h`) because the adaptor has access to telemetry config and can
+  implement the deterministic trace ID strategy. `establishSpan_` is correctly
+  in `Consensus.h` as planned.
+
+---
+
+# Phase 4b: Cross-Node Propagation (Future — Documentation Only)
+
+> **Goal**: Wire `TraceContextPropagator` for P2P messages so that proposals
+> and validations carry trace context between nodes. This enables true
+> distributed tracing where a proposal sent by Node A creates a child span
+> on Node B.
+>
+> **Status**: NOT IMPLEMENTED. The protobuf fields and propagator class exist
+> but are not wired. This section documents the design for future work.
+
+## Architecture
+
+```
+Node A (proposing)                         Node B (receiving)
+─────────────────                         ──────────────────
+consensus.round                           consensus.round
+├── propose()                             ├── peerProposal()
+│   └── TraceContextPropagator            │   └── TraceContextPropagator
+│       ::injectToProtobuf(               │       ::extractFromProtobuf(
+│           TMProposeSet.trace_context)   │           TMProposeSet.trace_context)
+│                                         │   └── span link → Node A's context
+└── validate()                            └── onValidation()
+    └── inject into TMValidation              └── extract from TMValidation
+```
+
+## Wiring Points
+
+| Message         | Inject Location                    | Extract Location                    | Protobuf Field             |
+| --------------- | ---------------------------------- | ----------------------------------- | -------------------------- |
+| `TMProposeSet`  | `Adaptor::propose()`               | `PeerImp::onMessage(TMProposeSet)`  | field 1001: `TraceContext` |
+| `TMValidation`  | `Adaptor::validate()`              | `PeerImp::onMessage(TMValidation)`  | field 1001: `TraceContext` |
+| `TMTransaction` | `NetworkOPs::processTransaction()` | `PeerImp::onMessage(TMTransaction)` | field 1001: `TraceContext` |
+
+## Span Link Semantics
+
+Received messages use **span links** (follows-from), NOT parent-child:
+
+- The receiver's processing span links to the sender's context
+- This preserves each node's independent trace tree
+- Cross-node correlation visible via linked traces in Tempo/Jaeger
+
+## Interaction with Deterministic Trace ID (Strategy A)
+
+When using deterministic trace_id (Phase 4a default), cross-node spans already
+share the same trace_id. P2P propagation adds **span-level** linking:
+
+- Without propagation: spans from different nodes appear in the same trace
+  (same trace_id) but without parent-child or follows-from relationships.
+- With propagation: spans have explicit links showing which proposal/validation
+  from Node A caused processing on Node B.
+
+## Prerequisites
+
+- Phase 4a (this task list) — establish phase tracing must be in place
+- `TraceContextPropagator` class (already exists in
+  `include/xrpl/telemetry/TraceContextPropagator.h`)
+- Protobuf `TraceContext` message (already exists, field 1001)

OpenTelemetryPlan/Phase5_IntegrationTest_taskList.md

@@ -0,0 +1,221 @@
+# Phase 5: Integration Test Task List
+
+> **Goal**: End-to-end verification of the complete telemetry pipeline using a
+> 6-node consensus network. Proves that RPC, transaction, and consensus spans
+> flow through the observability stack (otel-collector, Tempo, Prometheus,
+> Grafana) under realistic conditions.
+>
+> **Scope**: Integration test script, manual testing plan, 6-node local network
+> setup, Tempo/Prometheus/Grafana verification.
+>
+> **Branch**: `pratik/otel-phase5-docs-deployment`
+
+### Related Plan Documents
+
+| Document                                                         | Relevance                                  |
+| ---------------------------------------------------------------- | ------------------------------------------ |
+| [07-observability-backends.md](./07-observability-backends.md)   | Tempo, Grafana, Prometheus setup           |
+| [05-configuration-reference.md](./05-configuration-reference.md) | Collector config, Docker Compose           |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 5 tasks, definition of done          |
+| [Phase5_taskList.md](./Phase5_taskList.md)                       | Phase 5 main task list (5.6 = integration) |
+
+---
+
+## Task IT.1: Create Integration Test Script
+
+**Objective**: Automated bash script that stands up a 6-node xrpld network
+with telemetry, exercises all span categories, and verifies data in
+Tempo/Prometheus.
+
+**What to do**:
+
+- Create `docker/telemetry/integration-test.sh`:
+  - Prerequisites check (docker, xrpld binary, curl, jq)
+  - Start observability stack via `docker compose`
+  - Generate 6 validator key pairs via temp standalone xrpld
+  - Generate 6 node configs + shared `validators.txt`
+  - Start 6 xrpld nodes in consensus mode (`--start`, no `-a`)
+  - Wait for all nodes to reach `"proposing"` state (120s timeout)
+
+**Key new file**: `docker/telemetry/integration-test.sh`
+
+**Verification**:
+
+- [ ] Script starts without errors
+- [ ] All 6 nodes reach "proposing" state
+- [ ] Observability stack is healthy (otel-collector, Tempo, Prometheus, Grafana)
+
+---
+
+## Task IT.2: RPC Span Verification (Phase 2)
+
+**Objective**: Verify RPC spans flow through the telemetry pipeline.
+
+**What to do**:
+
+- Send `server_info`, `server_state`, `ledger` RPCs to node1 (port 5005)
+- Wait for batch export (5s)
+- Query Tempo API for:
+  - `rpc.request` spans (ServerHandler::onRequest)
+  - `rpc.process` spans (ServerHandler::processRequest)
+  - `rpc.command.server_info` spans (callMethod)
+  - `rpc.command.server_state` spans (callMethod)
+  - `rpc.command.ledger` spans (callMethod)
+- Verify `xrpl.rpc.command` attribute present on `rpc.command.*` spans
+
+**Verification**:
+
+- [ ] Tempo shows `rpc.request` traces
+- [ ] Tempo shows `rpc.process` traces
+- [ ] Tempo shows `rpc.command.*` traces with correct attributes
+
+---
+
+## Task IT.3: Transaction Span Verification (Phase 3)
+
+**Objective**: Verify transaction spans flow through the telemetry pipeline.
+
+**What to do**:
+
+- Get genesis account sequence via `account_info` RPC
+- Submit Payment transaction using genesis seed (`snoPBrXtMeMyMHUVTgbuqAfg1SUTb`)
+- Wait for consensus inclusion (10s)
+- Query Tempo API for:
+  - `tx.process` spans (NetworkOPsImp::processTransaction) on submitting node
+  - `tx.receive` spans (PeerImp::handleTransaction) on peer nodes
+- Verify `xrpl.tx.hash` attribute on `tx.process` spans
+- Verify `xrpl.peer.id` attribute on `tx.receive` spans
+
+**Verification**:
+
+- [ ] Tempo shows `tx.process` traces with `xrpl.tx.hash`
+- [ ] Tempo shows `tx.receive` traces with `xrpl.peer.id`
+
+---
+
+## Task IT.4: Consensus Span Verification (Phase 4)
+
+**Objective**: Verify consensus spans flow through the telemetry pipeline.
+
+**What to do**:
+
+- Consensus runs automatically in 6-node network
+- Query Tempo API for:
+  - `consensus.proposal.send` (Adaptor::propose)
+  - `consensus.ledger_close` (Adaptor::onClose)
+  - `consensus.accept` (Adaptor::onAccept)
+  - `consensus.validation.send` (Adaptor::validate)
+- Verify attributes:
+  - `xrpl.consensus.mode` on `consensus.ledger_close`
+  - `xrpl.consensus.proposers` on `consensus.accept`
+  - `xrpl.consensus.ledger.seq` on `consensus.validation.send`
+
+**Verification**:
+
+- [ ] Tempo shows `consensus.ledger_close` traces with `xrpl.consensus.mode`
+- [ ] Tempo shows `consensus.accept` traces with `xrpl.consensus.proposers`
+- [ ] Tempo shows `consensus.proposal.send` traces
+- [ ] Tempo shows `consensus.validation.send` traces
+
+---
+
+## Task IT.5: Spanmetrics Verification (Phase 5)
+
+**Objective**: Verify spanmetrics connector derives RED metrics from spans.
+
+**What to do**:
+
+- Query Prometheus for `traces_span_metrics_calls_total`
+- Query Prometheus for `traces_span_metrics_duration_milliseconds_count`
+- Verify Grafana loads at `http://localhost:3000`
+
+**Verification**:
+
+- [ ] Prometheus returns non-empty results for `traces_span_metrics_calls_total`
+- [ ] Prometheus returns non-empty results for duration histogram
+- [ ] Grafana UI accessible with dashboards visible
+
+---
+
+## Task IT.6: Manual Testing Plan
+
+**Objective**: Document how to run tests manually for future reference.
+
+**What to do**:
+
+- Create `docker/telemetry/TESTING.md` with:
+  - Prerequisites section
+  - Single-node standalone test (quick verification)
+  - 6-node consensus test (full verification)
+  - Expected span catalog (all 12 span names with attributes)
+  - Verification queries (Tempo API, Prometheus API)
+  - Troubleshooting guide
+
+**Key new file**: `docker/telemetry/TESTING.md`
+
+**Verification**:
+
+- [ ] Document covers both single-node and multi-node testing
+- [ ] All 12 span names documented with source file and attributes
+- [ ] Troubleshooting section covers common failure modes
+
+---
+
+## Task IT.7: Run and Verify
+
+**Objective**: Execute the integration test and validate results.
+
+**What to do**:
+
+- Run `docker/telemetry/integration-test.sh` locally
+- Debug any failures
+- Leave stack running for manual verification
+- Share URLs:
+  - Tempo: `http://localhost:3200`
+  - Grafana: `http://localhost:3000`
+  - Prometheus: `http://localhost:9090`
+
+**Verification**:
+
+- [ ] Script completes with all checks passing
+- [ ] Tempo UI shows rippled service with all expected span names
+- [ ] Grafana dashboards load and show data
+
+---
+
+## Task IT.8: Commit
+
+**Objective**: Commit all new files to Phase 5 branch.
+
+**What to do**:
+
+- Run `pcc` (pre-commit checks)
+- Commit 3 new files to `pratik/otel-phase5-docs-deployment`
+
+**Verification**:
+
+- [ ] `pcc` passes
+- [ ] Commit created on Phase 5 branch
+
+---
+
+## Summary
+
+| Task | Description                   | New Files | Depends On |
+| ---- | ----------------------------- | --------- | ---------- |
+| IT.1 | Integration test script       | 1         | Phase 5    |
+| IT.2 | RPC span verification         | 0         | IT.1       |
+| IT.3 | Transaction span verification | 0         | IT.1       |
+| IT.4 | Consensus span verification   | 0         | IT.1       |
+| IT.5 | Spanmetrics verification      | 0         | IT.1       |
+| IT.6 | Manual testing plan           | 1         | --         |
+| IT.7 | Run and verify                | 0         | IT.1-IT.6  |
+| IT.8 | Commit                        | 0         | IT.7       |
+
+**Exit Criteria**:
+
+- [ ] All 6 xrpld nodes reach "proposing" state
+- [ ] All 11 expected span names visible in Tempo
+- [ ] Spanmetrics available in Prometheus
+- [ ] Grafana dashboards show data
+- [ ] Manual testing plan document complete

OpenTelemetryPlan/Phase5_taskList.md

@@ -0,0 +1,241 @@
+# Phase 5: Documentation & Deployment Task List
+
+> **Goal**: Production readiness — Grafana dashboards, spanmetrics pipeline, operator runbook, alert definitions, and final integration testing. This phase ensures the telemetry system is useful and maintainable in production.
+>
+> **Scope**: Grafana dashboard definitions, OTel Collector spanmetrics connector, Prometheus integration, alert rules, operator documentation, and production-ready Docker Compose stack.
+>
+> **Branch**: `pratik/otel-phase5-docs-deployment` (from `pratik/otel-phase4-consensus-tracing`)
+
+### Related Plan Documents
+
+| Document                                                         | Relevance                                                                  |
+| ---------------------------------------------------------------- | -------------------------------------------------------------------------- |
+| [07-observability-backends.md](./07-observability-backends.md)   | Tempo setup (§7.1), Grafana dashboards (§7.6), alerts (§7.6.3)             |
+| [05-configuration-reference.md](./05-configuration-reference.md) | Collector config (§5.5), production config (§5.5.2), Docker Compose (§5.6) |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 5 tasks (§6.6), definition of done (§6.11.5)                         |
+
+---
+
+## Task 5.1: Add Spanmetrics Connector to OTel Collector
+
+**Objective**: Derive RED metrics (Rate, Errors, Duration) from trace spans automatically, enabling Grafana time-series dashboards.
+
+**What to do**:
+
+- Edit `docker/telemetry/otel-collector-config.yaml`:
+  - Add `spanmetrics` connector:
+    ```yaml
+    connectors:
+      spanmetrics:
+        histogram:
+          explicit:
+            buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
+        dimensions:
+          - name: xrpl.rpc.command
+          - name: xrpl.rpc.status
+          - name: xrpl.consensus.phase
+          - name: xrpl.tx.type
+    ```
+  - Add `prometheus` exporter:
+    ```yaml
+    exporters:
+      prometheus:
+        endpoint: 0.0.0.0:8889
+    ```
+  - Wire the pipeline:
+    ```yaml
+    service:
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [debug, otlp/tempo, spanmetrics]
+        metrics:
+          receivers: [spanmetrics]
+          exporters: [prometheus]
+    ```
+
+- Edit `docker/telemetry/docker-compose.yml`:
+  - Expose port `8889` on the collector for Prometheus scraping
+  - Add Prometheus service
+  - Add Prometheus as Grafana datasource
+
+**Key modified files**:
+
+- `docker/telemetry/otel-collector-config.yaml`
+- `docker/telemetry/docker-compose.yml`
+
+**Key new files**:
+
+- `docker/telemetry/prometheus.yml` (Prometheus scrape config)
+- `docker/telemetry/grafana/provisioning/datasources/prometheus.yaml`
+
+**Reference**:
+
+- [POC_taskList.md §Next Steps](./POC_taskList.md) — Metrics pipeline for Grafana dashboards
+
+---
+
+## Task 5.2: Create Grafana Dashboards
+
+**Objective**: Provide pre-built Grafana dashboards for RPC performance, transaction lifecycle, and consensus health.
+
+**What to do**:
+
+- Create `docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml` (provisioning config)
+- Create dashboard JSON files:
+  1. **RPC Performance Dashboard** (`rpc-performance.json`):
+     - RPC request latency (p50/p95/p99) by command — histogram panel
+     - RPC throughput (requests/sec) by command — time series
+     - RPC error rate by command — bar gauge
+     - Top slowest RPC commands — table
+
+  2. **Transaction Overview Dashboard** (`transaction-overview.json`):
+     - Transaction processing rate — time series
+     - Transaction latency distribution — histogram
+     - Suppression rate (duplicates) — stat panel
+     - Transaction processing path (sync vs async) — pie chart
+
+  3. **Consensus Health Dashboard** (`consensus-health.json`):
+     - Consensus round duration — time series
+     - Phase duration breakdown (open/establish/accept) — stacked bar
+     - Proposals sent/received per round — stat panel
+     - Consensus mode distribution (proposing/observing) — pie chart
+
+- Store dashboards in `docker/telemetry/grafana/dashboards/`
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml`
+- `docker/telemetry/grafana/dashboards/rpc-performance.json`
+- `docker/telemetry/grafana/dashboards/transaction-overview.json`
+- `docker/telemetry/grafana/dashboards/consensus-health.json`
+
+**Reference**:
+
+- [07-observability-backends.md §7.6](./07-observability-backends.md) — Grafana dashboard specifications
+- [01-architecture-analysis.md §1.8.3](./01-architecture-analysis.md) — Dashboard panel examples
+
+---
+
+## Task 5.3: Define Alert Rules
+
+**Objective**: Create alert definitions for key telemetry anomalies.
+
+**What to do**:
+
+- Create `docker/telemetry/grafana/provisioning/alerting/alerts.yaml`:
+  - **RPC Latency Alert**: p99 latency > 1s for any command over 5 minutes
+  - **RPC Error Rate Alert**: Error rate > 5% for any command over 5 minutes
+  - **Consensus Duration Alert**: Round duration > 10s (warn), > 30s (critical)
+  - **Transaction Processing Alert**: Processing rate drops below threshold
+  - **Telemetry Pipeline Health**: No spans received for > 2 minutes
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/alerting/alerts.yaml`
+
+**Reference**:
+
+- [07-observability-backends.md §7.6.3](./07-observability-backends.md) — Alert rule definitions
+
+---
+
+## Task 5.4: Production Collector Configuration
+
+**Objective**: Create a production-ready OTel Collector configuration with tail-based sampling and resource limits.
+
+**What to do**:
+
+- Create `docker/telemetry/otel-collector-config-production.yaml`:
+  - Tail-based sampling policy:
+    - Always sample errors and slow traces
+    - 10% base sampling rate for normal traces
+    - Always sample first trace for each unique RPC command
+  - Resource limits:
+    - Memory limiter processor (80% of available memory)
+    - Queued retry for export failures
+  - TLS configuration for production endpoints
+  - Health check endpoint
+
+**Key new files**:
+
+- `docker/telemetry/otel-collector-config-production.yaml`
+
+**Reference**:
+
+- [05-configuration-reference.md §5.5.2](./05-configuration-reference.md) — Production collector config
+
+---
+
+## Task 5.5: Operator Runbook
+
+**Objective**: Create operator documentation for managing the telemetry system in production.
+
+**What to do**:
+
+- Create `docs/telemetry-runbook.md`:
+  - **Setup**: How to enable telemetry in rippled
+  - **Configuration**: All config options with descriptions
+  - **Collector Deployment**: Docker Compose vs. Kubernetes vs. bare metal
+  - **Troubleshooting**: Common issues and resolutions
+    - No traces appearing
+    - High memory usage from telemetry
+    - Collector connection failures
+    - Sampling configuration tuning
+  - **Performance Tuning**: Batch size, queue size, sampling ratio guidelines
+  - **Upgrading**: How to upgrade OTel SDK and Collector versions
+
+**Key new files**:
+
+- `docs/telemetry-runbook.md`
+
+---
+
+## Task 5.6: Final Integration Testing
+
+**Objective**: Validate the complete telemetry stack end-to-end.
+
+**What to do**:
+
+1. Start full Docker stack (Collector, Tempo, Grafana, Prometheus)
+2. Build rippled with `telemetry=ON`
+3. Run in standalone mode with telemetry enabled
+4. Generate RPC traffic and verify traces in Tempo
+5. Verify dashboards populate in Grafana
+6. Verify alerts trigger correctly
+7. Test telemetry OFF path (no regressions)
+8. Run full test suite
+
+**Verification Checklist**:
+
+- [ ] Docker stack starts without errors
+- [ ] Traces appear in Tempo with correct hierarchy
+- [ ] Grafana dashboards show metrics derived from spans
+- [ ] Prometheus scrapes spanmetrics successfully
+- [ ] Alerts can be triggered by simulated conditions
+- [ ] Build succeeds with telemetry ON and OFF
+- [ ] Full test suite passes
+
+---
+
+## Summary
+
+| Task | Description                        | New Files | Modified Files | Depends On |
+| ---- | ---------------------------------- | --------- | -------------- | ---------- |
+| 5.1  | Spanmetrics connector + Prometheus | 2         | 2              | Phase 4    |
+| 5.2  | Grafana dashboards                 | 4         | 0              | 5.1        |
+| 5.3  | Alert definitions                  | 1         | 0              | 5.1        |
+| 5.4  | Production collector config        | 1         | 0              | Phase 4    |
+| 5.5  | Operator runbook                   | 1         | 0              | Phase 4    |
+| 5.6  | Final integration testing          | 0         | 0              | 5.1-5.5    |
+
+**Parallel work**: Tasks 5.1, 5.4, and 5.5 can run in parallel. Tasks 5.2 and 5.3 depend on 5.1. Task 5.6 depends on all others.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.5](./06-implementation-phases.md)):
+
+- [ ] Dashboards deployed and showing data
+- [ ] Alerts configured and tested
+- [ ] Operator documentation complete
+- [ ] Production collector config ready
+- [ ] Full test suite passes

OpenTelemetryPlan/Phase7_taskList.md

@@ -0,0 +1,536 @@
+# Phase 7: Native OTel Metrics Migration — Task List
+
+> **Goal**: Replace `StatsDCollector` with a native OpenTelemetry Metrics SDK implementation behind the existing `beast::insight::Collector` interface, eliminating the StatsD UDP dependency.
+>
+> **Scope**: New `OTelCollectorImpl` class, `CollectorManager` config change, OTel Collector pipeline update, Grafana dashboard metric name migration, integration tests.
+>
+> **Branch**: `pratik/otel-phase7-native-metrics` (from `pratik/otel-phase6-statsd`)
+
+### Related Plan Documents
+
+| Document                                                             | Relevance                                                       |
+| -------------------------------------------------------------------- | --------------------------------------------------------------- |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Phase 7 plan: motivation, architecture, exit criteria (§6.8)    |
+| [02-design-decisions.md](./02-design-decisions.md)                   | Collector interface design, beast::insight coexistence strategy |
+| [05-configuration-reference.md](./05-configuration-reference.md)     | `[insight]` and `[telemetry]` config sections                   |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Complete metric inventory that must be preserved                |
+
+---
+
+## Task 7.1: Add OTel Metrics SDK to Build Dependencies
+
+**Objective**: Enable the OTel C++ Metrics SDK components in the build system.
+
+**What to do**:
+
+- Edit `conanfile.py`:
+  - Add OTel metrics SDK components to the dependency list when `telemetry=True`
+  - Components needed: `opentelemetry-cpp::metrics`, `opentelemetry-cpp::otlp_http_metric_exporter`
+
+- Edit `CMakeLists.txt` (telemetry section):
+  - Link `opentelemetry::metrics` and `opentelemetry::otlp_http_metric_exporter` targets
+
+**Key modified files**:
+
+- `conanfile.py`
+- `CMakeLists.txt` (or the relevant telemetry cmake target)
+
+**Reference**: [05-configuration-reference.md §5.3](./05-configuration-reference.md) — CMake integration
+
+---
+
+## Task 7.2: Implement OTelCollector Class
+
+**Objective**: Create the core `OTelCollector` implementation that maps beast::insight instruments to OTel Metrics SDK instruments.
+
+**What to do**:
+
+- Create `include/xrpl/beast/insight/OTelCollector.h`:
+  - Public factory: `static std::shared_ptr<OTelCollector> New(std::string const& endpoint, std::string const& prefix, beast::Journal journal)`
+  - Derives from `StatsDCollector` (or directly from `Collector` — TBD based on shared code)
+
+- Create `src/libxrpl/beast/insight/OTelCollector.cpp` (~400-500 lines):
+  - **OTelCounterImpl**: Wraps `opentelemetry::metrics::Counter<int64_t>`. `increment(amount)` calls `counter->Add(amount)`.
+  - **OTelGaugeImpl**: Uses `opentelemetry::metrics::ObservableGauge<uint64_t>` with an async callback. `set(value)` stores value atomically; callback reads it during collection.
+  - **OTelMeterImpl**: Wraps `opentelemetry::metrics::Counter<uint64_t>`. `increment(amount)` calls `counter->Add(amount)`. Semantically identical to Counter but unsigned.
+  - **OTelEventImpl**: Wraps `opentelemetry::metrics::Histogram<double>`. `notify(duration)` calls `histogram->Record(duration.count())`. Uses explicit bucket boundaries matching SpanMetrics: [1, 5, 10, 25, 50, 100, 250, 500, 1000, 5000] ms.
+  - **OTelHookImpl**: Stores handler function. Called during periodic metric collection (same 1s pattern via PeriodicMetricReader).
+  - **OTelCollectorImp**: Main class.
+    - Creates `MeterProvider` with `PeriodicMetricReader` (1s export interval)
+    - Creates `OtlpHttpMetricExporter` pointing to `[telemetry]` endpoint
+    - Sets resource attributes (service.name, service.instance.id) matching trace exporter
+    - Implements all `make_*()` factory methods
+    - Prefixes metric names with `[insight] prefix=` value
+
+- Guard all OTel SDK includes with `#ifdef XRPL_ENABLE_TELEMETRY` to compile to `NullCollector` equivalents when telemetry disabled.
+
+**Key new files**:
+
+- `include/xrpl/beast/insight/OTelCollector.h`
+- `src/libxrpl/beast/insight/OTelCollector.cpp`
+
+**Key patterns to follow**:
+
+- Match `StatsDCollector.cpp` structure: private impl classes, intrusive list for metrics, strand-based thread safety
+- Match existing telemetry code style from `src/libxrpl/telemetry/Telemetry.cpp`
+- Use RAII for MeterProvider lifecycle (shutdown on destructor)
+
+**Reference**: [04-code-samples.md](./04-code-samples.md) — code style and patterns
+
+---
+
+## Task 7.3: Update CollectorManager
+
+**Objective**: Add `server=otel` config option to route metric creation to the new OTel backend.
+
+**What to do**:
+
+- Edit `src/xrpld/app/main/CollectorManager.cpp`:
+  - In the constructor, add a third branch after `server == "statsd"`:
+    ```cpp
+    else if (server == "otel")
+    {
+        // Read endpoint from [telemetry] section
+        auto const endpoint = get(telemetryParams, "endpoint",
+            "http://localhost:4318/v1/metrics");
+        std::string const& prefix(get(params, "prefix"));
+        m_collector = beast::insight::OTelCollector::New(
+            endpoint, prefix, journal);
+    }
+    ```
+  - This requires access to the `[telemetry]` config section — may need to pass it as a parameter or read from Application config.
+
+- Edit `src/xrpld/app/main/CollectorManager.h`:
+  - Add `#include <xrpl/beast/insight/OTelCollector.h>`
+
+**Key modified files**:
+
+- `src/xrpld/app/main/CollectorManager.cpp`
+- `src/xrpld/app/main/CollectorManager.h`
+
+---
+
+## Task 7.4: Update OTel Collector Configuration
+
+**Objective**: Add a metrics pipeline to the OTLP receiver and remove the StatsD receiver dependency.
+
+**What to do**:
+
+- Edit `docker/telemetry/otel-collector-config.yaml`:
+  - Remove `statsd` receiver (no longer needed when `server=otel`)
+  - Add metrics pipeline under `service.pipelines`:
+    ```yaml
+    metrics:
+      receivers: [otlp, spanmetrics]
+      processors: [batch]
+      exporters: [prometheus]
+    ```
+  - The OTLP receiver already listens on :4318 — it just needs to be added to the metrics pipeline receivers.
+  - Keep `spanmetrics` connector in the metrics pipeline so span-derived RED metrics continue working.
+
+- Edit `docker/telemetry/docker-compose.yml`:
+  - Remove UDP :8125 port mapping from otel-collector service
+  - Update rippled service config: change `[insight] server=statsd` to `server=otel`
+
+**Key modified files**:
+
+- `docker/telemetry/otel-collector-config.yaml`
+- `docker/telemetry/docker-compose.yml`
+
+**Note**: Keep a commented-out `statsd` receiver block for operators who need backward compatibility.
+
+---
+
+## Task 7.5: Preserve Metric Names in Prometheus
+
+**Objective**: Ensure existing Grafana dashboards continue working with identical metric names.
+
+**What to do**:
+
+- In `OTelCollector.cpp`, construct OTel instrument names to match existing Prometheus metric names:
+  - beast::insight `make_gauge("LedgerMaster", "Validated_Ledger_Age")` → OTel instrument name: `rippled_LedgerMaster_Validated_Ledger_Age`
+  - The prefix + group + name concatenation must produce the same string as `StatsDCollector`'s format
+  - Use underscores as separators (matching StatsD convention)
+
+- Verify in integration test that key Prometheus queries still return data:
+  - `rippled_LedgerMaster_Validated_Ledger_Age`
+  - `rippled_Peer_Finder_Active_Inbound_Peers`
+  - `rippled_rpc_requests`
+
+**Key consideration**: OTel Prometheus exporter may normalize metric names differently than StatsD receiver. Test this early (Task 7.2) and adjust naming strategy if needed. The OTel SDK's Prometheus exporter adds `_total` suffix to counters and converts dots to underscores — match existing conventions.
+
+---
+
+## Task 7.6: Update Grafana Dashboards
+
+**Objective**: Update the 3 StatsD dashboards if any metric names change due to OTLP export format differences.
+
+**What to do**:
+
+- If Task 7.5 confirms metric names are preserved exactly, no dashboard changes needed.
+- If OTLP export produces different names (e.g., `_total` suffix on counters), update:
+  - `docker/telemetry/grafana/dashboards/statsd-node-health.json`
+  - `docker/telemetry/grafana/dashboards/statsd-network-traffic.json`
+  - `docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json`
+- Rename dashboard titles from "StatsD" to "System Metrics" or similar (since they're no longer StatsD-sourced).
+
+**Key modified files**:
+
+- `docker/telemetry/grafana/dashboards/statsd-*.json` (3 files, conditionally)
+
+---
+
+## Task 7.7: Update Integration Tests
+
+**Objective**: Verify the full OTLP metrics pipeline end-to-end.
+
+**What to do**:
+
+- Edit `docker/telemetry/integration-test.sh`:
+  - Update test config to use `[insight] server=otel`
+  - Verify metrics arrive in Prometheus via OTLP (not StatsD)
+  - Add check that StatsD receiver is no longer required
+  - Preserve all existing metric presence checks
+
+**Key modified files**:
+
+- `docker/telemetry/integration-test.sh`
+
+---
+
+## Task 7.8: Update Documentation
+
+**Objective**: Update all plan docs, runbook, and reference docs to reflect the migration.
+
+**What to do**:
+
+- Edit `docs/telemetry-runbook.md`:
+  - Update `[insight]` config examples to show `server=otel`
+  - Update troubleshooting section (no more StatsD UDP debugging)
+
+- Edit `OpenTelemetryPlan/09-data-collection-reference.md`:
+  - Update Data Flow Overview diagram (remove StatsD receiver)
+  - Update Section 2 header from "StatsD Metrics" to "System Metrics (OTel native)"
+  - Update config examples
+
+- Edit `OpenTelemetryPlan/05-configuration-reference.md`:
+  - Add `server=otel` option to `[insight]` section docs
+
+- Edit `docker/telemetry/TESTING.md`:
+  - Update setup instructions to use `server=otel`
+
+**Key modified files**:
+
+- `docs/telemetry-runbook.md`
+- `OpenTelemetryPlan/09-data-collection-reference.md`
+- `OpenTelemetryPlan/05-configuration-reference.md`
+- `docker/telemetry/TESTING.md`
+
+---
+
+## Task 7.9: ValidationTracker — Validation Agreement Computation
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md) — the most valuable metric from the community [xrpl-validator-dashboard](https://github.com/realgrapedrop/xrpl-validator-dashboard).
+>
+> **Upstream**: Phase 4 Task 4.8 (validation span attributes provide ledger hash context).
+> **Downstream**: Phase 9 (Validator Health dashboard), Phase 10 (validation checks), Phase 11 (agreement alert rules).
+
+**Objective**: Implement a stateful class that tracks whether our validator's validations agree with network consensus, maintaining rolling 1h and 24h windows with an 8-second grace period and 5-minute late repair window.
+
+**Architecture**:
+
+```
+consensus.validation.send ────> ValidationTracker ────> MetricsRegistry
+(records our validation         (reconciles after       (exports agreement
+ for ledger X)                   8s grace period)        gauges every 10s)
+
+ledger.validate ──────────────> ValidationTracker
+(records which ledger           (marks ledger X as
+ network validated)              agreed or missed)
+```
+
+**What to do**:
+
+- Create `src/xrpld/telemetry/ValidationTracker.h`:
+  - `recordOurValidation(ledgerHash, ledgerSeq)` — called when we send a validation
+  - `recordNetworkValidation(ledgerHash, seq)` — called when a ledger is fully validated
+  - `reconcile()` — called periodically; reconciles pending ledger events after 8s grace period
+  - Getters: `agreementPct1h()`, `agreementPct24h()`, `agreements1h()`, `missed1h()`, `agreements24h()`, `missed24h()`, `totalAgreements()`, `totalMissed()`, `totalValidationsSent()`, `totalValidationsChecked()`
+  - Thread-safety: atomics for counters, mutex for window deques
+
+- Create `src/xrpld/telemetry/detail/ValidationTracker.cpp`:
+  - Reconciliation logic: after 8s grace period, check if `weValidated && networkValidated && sameHash` → agreement; else missed
+  - Late repair: if a late validation arrives within 5 minutes, correct a false-positive miss
+  - Sliding window: `std::deque<WindowEvent>` evicts entries older than 1h/24h on each reconciliation pass
+  - Ring buffer of 1000 `LedgerEvent` structs for pending reconciliation
+
+- Add recording hooks (modifying Phase 4 code from Phase 7 branch):
+  - `RCLConsensus.cpp` `validate()`: call `tracker.recordOurValidation()`
+  - `LedgerMaster.cpp` fully-validated path: call `tracker.recordNetworkValidation()`
+
+**Key data structures**:
+
+```cpp
+struct LedgerEvent {
+    uint256 ledgerHash;
+    LedgerIndex seq;
+    TimePoint closeTime;
+    bool weValidated = false;
+    bool networkValidated = false;
+    bool reconciled = false;
+    bool agreed = false;
+};
+
+struct WindowEvent {
+    TimePoint time;
+    bool agreed;
+};
+```
+
+**Key new files**:
+
+- `src/xrpld/telemetry/ValidationTracker.h`
+- `src/xrpld/telemetry/detail/ValidationTracker.cpp`
+
+**Key modified files**:
+
+- `src/xrpld/telemetry/MetricsRegistry.h` (add ValidationTracker member)
+- `src/xrpld/telemetry/MetricsRegistry.cpp` (add gauge callback reading from tracker)
+- `src/xrpld/app/consensus/RCLConsensus.cpp` (add recording hooks)
+- `src/xrpld/app/ledger/detail/LedgerMaster.cpp` (add recording hook)
+
+**Exit Criteria**:
+
+- [ ] ValidationTracker correctly tracks agreement with 8s grace period
+- [ ] 5-minute late repair corrects false-positive misses
+- [ ] Thread-safe (atomics + mutex for window deques)
+- [ ] Rolling windows correctly evict stale entries
+- [ ] Unit tests: normal agreement, missed validation, late repair, window eviction
+
+---
+
+## Task 7.10: Validator Health Observable Gauges
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Export amendment blocked, UNL health, and quorum data as a native OTel observable gauge.
+
+**What to do**:
+
+- In `MetricsRegistry.cpp` `registerAsyncGauges()`, add:
+
+```cpp
+validatorHealthGauge_ = meter_->CreateDoubleObservableGauge(
+    "rippled_validator_health", "Validator health indicators");
+```
+
+**Gauge label values**:
+
+| Label `metric=`     | Type   | Source                                            |
+| ------------------- | ------ | ------------------------------------------------- |
+| `amendment_blocked` | int64  | `app_.getOPs().isAmendmentBlocked()` → 0/1        |
+| `unl_blocked`       | int64  | `app_.getOPs().isUNLBlocked()` → 0/1              |
+| `unl_expiry_days`   | double | `app_.validators().expires()` → days until expiry |
+| `validation_quorum` | int64  | `app_.validators().quorum()`                      |
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.h/.cpp`
+
+**Exit Criteria**:
+
+- [ ] All 4 label values emitted every 10s
+- [ ] `unl_expiry_days` is negative when expired, positive when active
+- [ ] Values visible in Prometheus
+
+---
+
+## Task 7.11: Peer Quality Observable Gauges
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Export peer health aggregates (latency P90, insane peers, version awareness) as a native OTel observable gauge.
+
+**What to do**:
+
+- In `MetricsRegistry.cpp` `registerAsyncGauges()`, add a callback that iterates `app_.overlay().foreach(...)` to:
+  - Collect per-peer latency values, sort, compute P90
+  - Count peers with `tracking_ == diverged` (insane)
+  - Compare peer `getVersion()` to own version for upgrade awareness
+
+**Gauge label values**:
+
+| Label `metric=`            | Type   | Source                                |
+| -------------------------- | ------ | ------------------------------------- |
+| `peer_latency_p90_ms`      | double | P90 from sorted peer latencies        |
+| `peers_insane_count`       | int64  | Peers with diverged tracking status   |
+| `peers_higher_version_pct` | double | % of peers on newer rippled version   |
+| `upgrade_recommended`      | int64  | 1 if `peers_higher_version_pct > 60%` |
+
+**Implementation note**: The callback runs every 10s on the metrics reader thread. Iterating ~50-200 peers is acceptable overhead.
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.h/.cpp`
+
+**Exit Criteria**:
+
+- [ ] P90 latency computed correctly
+- [ ] Insane count matches `peers` RPC output
+- [ ] Version comparison handles format variations (e.g., "rippled-2.4.0-rc1")
+
+---
+
+## Task 7.12: Ledger Economy Observable Gauges
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Export fee, reserve, ledger age, and transaction rate as a native OTel observable gauge.
+
+**Gauge label values**:
+
+| Label `metric=`      | Type   | Source                                              |
+| -------------------- | ------ | --------------------------------------------------- |
+| `base_fee_xrp`       | double | Base fee from validated ledger fee settings (drops) |
+| `reserve_base_xrp`   | double | Account reserve from validated ledger (drops)       |
+| `reserve_inc_xrp`    | double | Owner reserve increment (drops)                     |
+| `ledger_age_seconds` | double | `now - lastValidatedCloseTime`                      |
+| `transaction_rate`   | double | Derived: tx count delta / time delta (smoothed)     |
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.h/.cpp`
+
+**Exit Criteria**:
+
+- [ ] Fee values match `server_info` RPC output
+- [ ] `ledger_age_seconds` increases monotonically between ledger closes
+- [ ] `transaction_rate` is smoothed (rolling average)
+
+---
+
+## Task 7.13: State Tracking Observable Gauges
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Export extended state value (0-6 encoding combining OperatingMode + ConsensusMode) and time-in-current-state.
+
+**Gauge label values**:
+
+| Label `metric=`                 | Type   | Source                                          |
+| ------------------------------- | ------ | ----------------------------------------------- |
+| `state_value`                   | int64  | 0-6 encoding (see spec for mapping)             |
+| `time_in_current_state_seconds` | double | `now - lastModeChangeTime` from StateAccounting |
+
+**State value encoding**: 0=disconnected, 1=connected, 2=syncing, 3=tracking, 4=full, 5=validating (full + validating), 6=proposing (full + proposing).
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.h/.cpp`
+
+**Exit Criteria**:
+
+- [ ] `state_value` correctly combines OperatingMode and ConsensusMode
+- [ ] `time_in_current_state_seconds` resets on mode change
+
+---
+
+## Task 7.14: Storage Detail and Sync Info Gauges
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Export NuDB-specific storage size and initial sync duration.
+
+**Gauge label values**:
+
+| Gauge Name               | Label `metric=`                 | Type   | Source                        |
+| ------------------------ | ------------------------------- | ------ | ----------------------------- |
+| `rippled_storage_detail` | `nudb_bytes`                    | int64  | NuDB backend file size        |
+| `rippled_sync_info`      | `initial_sync_duration_seconds` | double | Time from start to first FULL |
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.h/.cpp`
+
+**Exit Criteria**:
+
+- [ ] NuDB file size reported in bytes (0 if NuDB not configured)
+- [ ] Sync duration captured once and remains stable after reaching FULL
+
+---
+
+## Task 7.15: New Synchronous Counters
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Add 7 new event counters incremented at their respective instrumentation sites.
+
+| Counter Name                          | Increment Site                   | Source File           |
+| ------------------------------------- | -------------------------------- | --------------------- |
+| `rippled_ledgers_closed_total`        | `onAccept()` in consensus        | RCLConsensus.cpp      |
+| `rippled_validations_sent_total`      | `validate()` in consensus        | RCLConsensus.cpp      |
+| `rippled_validations_checked_total`   | Network validation received      | LedgerMaster.cpp      |
+| `rippled_validation_agreements_total` | ValidationTracker reconciliation | ValidationTracker.cpp |
+| `rippled_validation_missed_total`     | ValidationTracker reconciliation | ValidationTracker.cpp |
+| `rippled_state_changes_total`         | `setMode()` in NetworkOPs        | NetworkOPs.cpp        |
+| `rippled_jq_trans_overflow_total`     | Job queue overflow path          | JobQueue.cpp          |
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.h/.cpp` (declarations), plus recording sites in RCLConsensus.cpp, LedgerMaster.cpp, NetworkOPs.cpp, JobQueue.cpp
+
+**Exit Criteria**:
+
+- [ ] All 7 counters monotonically increase during normal operation
+- [ ] Counter values match expected rates (e.g., ledgers_closed ≈ 1 per 3-5s)
+
+---
+
+## Task 7.16: Validation Agreement Observable Gauge
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md)
+
+**Objective**: Export rolling window agreement stats from `ValidationTracker` (Task 7.9).
+
+**Gauge label values**:
+
+| Gauge Name                     | Label `metric=`     | Type   | Source                      |
+| ------------------------------ | ------------------- | ------ | --------------------------- |
+| `rippled_validation_agreement` | `agreement_pct_1h`  | double | `tracker.agreementPct1h()`  |
+|                                | `agreements_1h`     | int64  | `tracker.agreements1h()`    |
+|                                | `missed_1h`         | int64  | `tracker.missed1h()`        |
+|                                | `agreement_pct_24h` | double | `tracker.agreementPct24h()` |
+|                                | `agreements_24h`    | int64  | `tracker.agreements24h()`   |
+|                                | `missed_24h`        | int64  | `tracker.missed24h()`       |
+
+**Key modified files**: `src/xrpld/telemetry/MetricsRegistry.cpp`
+
+**Exit Criteria**:
+
+- [ ] Agreement percentages in range [0.0, 100.0]
+- [ ] Window stats stabilize after 1h/24h of operation
+
+---
+
+## Summary Table
+
+| Task | Description                            | New Files | Modified Files | Depends On |
+| ---- | -------------------------------------- | --------- | -------------- | ---------- |
+| 7.1  | Add OTel Metrics SDK to build deps     | 0         | 2              | —          |
+| 7.2  | Implement OTelCollector class          | 2         | 0              | 7.1        |
+| 7.3  | Update CollectorManager config routing | 0         | 2              | 7.2        |
+| 7.4  | Update OTel Collector YAML and Docker  | 0         | 2              | 7.3        |
+| 7.5  | Preserve metric names in Prometheus    | 0         | 1              | 7.2        |
+| 7.6  | Update Grafana dashboards (if needed)  | 0         | 3              | 7.5        |
+| 7.7  | Update integration tests               | 0         | 1              | 7.4        |
+| 7.8  | Update documentation                   | 0         | 4              | 7.6        |
+| 7.9  | ValidationTracker (agreement tracking) | 2         | 4              | 7.2, P4.8  |
+| 7.10 | Validator health observable gauges     | 0         | 2              | 7.2        |
+| 7.11 | Peer quality observable gauges         | 0         | 2              | 7.2        |
+| 7.12 | Ledger economy observable gauges       | 0         | 2              | 7.2        |
+| 7.13 | State tracking observable gauges       | 0         | 2              | 7.2        |
+| 7.14 | Storage detail and sync info gauges    | 0         | 2              | 7.2        |
+| 7.15 | New synchronous counters               | 0         | 6              | 7.2        |
+| 7.16 | Validation agreement observable gauge  | 0         | 1              | 7.9        |
+
+**Parallel work**: Tasks 7.4 and 7.5 can run in parallel after 7.2/7.3 complete. Task 7.6 depends on 7.5's findings. Tasks 7.7 and 7.8 can run in parallel after 7.6. Tasks 7.10-7.14 can all run in parallel after 7.2. Task 7.15 depends on 7.2. Task 7.16 depends on 7.9. Task 7.9 depends on 7.2 and Phase 4 Task 4.8.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.8](./06-implementation-phases.md)):
+
+- [ ] All 255+ metrics visible in Prometheus via OTLP pipeline (no StatsD receiver)
+- [ ] `server=otel` is the default in development docker-compose
+- [ ] `server=statsd` still works as a fallback
+- [ ] Existing Grafana dashboards display data correctly
+- [ ] Integration test passes with OTLP-only metrics pipeline
+- [ ] No performance regression vs StatsD baseline (< 1% CPU overhead)
+- [ ] Deferred Task 6.1 (`|m` wire format) no longer relevant — Meter mapped to OTel Counter
+- [ ] ValidationTracker agreement % stabilizes after 1h under normal consensus
+- [ ] All new gauges and counters visible in Prometheus with non-zero values

OpenTelemetryPlan/presentation.md

@@ -0,0 +1,673 @@
+# OpenTelemetry Distributed Tracing for rippled
+
+---
+
+## Slide 1: Introduction
+
+> **CNCF** = Cloud Native Computing Foundation
+
+### What is OpenTelemetry?
+
+OpenTelemetry is an open-source, CNCF-backed observability framework for distributed tracing, metrics, and logs.
+
+### Why OpenTelemetry for rippled?
+
+- **End-to-End Transaction Visibility**: Track transactions from submission → consensus → ledger inclusion
+- **Cross-Node Correlation**: Follow requests across multiple independent nodes using a unique `trace_id`
+- **Consensus Round Analysis**: Understand timing and behavior across validators
+- **Incident Debugging**: Correlate events across distributed nodes during issues
+
+```mermaid
+flowchart LR
+    A["Node A<br/>tx.receive<br/>trace_id: abc123"] --> B["Node B<br/>tx.relay<br/>trace_id: abc123"] --> C["Node C<br/>tx.validate<br/>trace_id: abc123"] --> D["Node D<br/>ledger.apply<br/>trace_id: abc123"]
+
+    style A fill:#1565c0,stroke:#0d47a1,color:#fff
+    style B fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style C fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style D fill:#e65100,stroke:#bf360c,color:#fff
+```
+
+**Reading the diagram:**
+
+- **Node A (blue, leftmost)**: The originating node that first receives the transaction and assigns a new `trace_id: abc123`; this ID becomes the correlation key for the entire distributed trace.
+- **Node B and Node C (green, middle)**: Relay and validation nodes — each creates its own span but carries the same `trace_id`, so their work is linked to the original submission without any central coordinator.
+- **Node D (orange, rightmost)**: The final node that applies the transaction to the ledger; the trace now spans the full lifecycle from submission to ledger inclusion.
+- **Left-to-right flow**: The horizontal progression shows the real-world message path — a transaction hops from node to node, and the shared `trace_id` stitches all hops into a single queryable trace.
+
+> **Trace ID: abc123** — All nodes share the same trace, enabling cross-node correlation.
+
+---
+
+## Slide 2: OpenTelemetry vs Open Source Alternatives
+
+> **CNCF** = Cloud Native Computing Foundation
+
+| Feature             | OpenTelemetry    | Jaeger           | Zipkin             | SkyWalking | Pinpoint   | Prometheus |
+| ------------------- | ---------------- | ---------------- | ------------------ | ---------- | ---------- | ---------- |
+| **Tracing**         | YES              | YES              | YES                | YES        | YES        | NO         |
+| **Metrics**         | YES              | NO               | NO                 | YES        | YES        | YES        |
+| **Logs**            | YES              | NO               | NO                 | YES        | NO         | NO         |
+| **C++ SDK**         | YES Official     | YES (Deprecated) | YES (Unmaintained) | NO         | NO         | YES        |
+| **Vendor Neutral**  | YES Primary goal | NO               | NO                 | NO         | NO         | NO         |
+| **Instrumentation** | Manual + Auto    | Manual           | Manual             | Auto-first | Auto-first | Manual     |
+| **Backend**         | Any (exporters)  | Self             | Self               | Self       | Self       | Self       |
+| **CNCF Status**     | Incubating       | Graduated        | NO                 | Incubating | NO         | Graduated  |
+
+> **Why OpenTelemetry?** It's the only actively maintained, full-featured C++ option with vendor neutrality — allowing export to Tempo, Prometheus, Grafana, or any commercial backend without changing instrumentation.
+
+---
+
+## Slide 3: Adoption Scope — Traces Only (Current Plan)
+
+OpenTelemetry supports three signal types: **Traces**, **Metrics**, and **Logs**. rippled already captures metrics (StatsD via Beast Insight) and logs (Journal/PerfLog). The question is: how much of OTel do we adopt?
+
+> **Scenario A**: Add distributed tracing. Keep StatsD for metrics and Journal for logs.
+
+```mermaid
+flowchart LR
+    subgraph rippled["rippled Process"]
+        direction TB
+        OTel["OTel SDK<br/>(Traces)"]
+        Insight["Beast Insight<br/>(StatsD Metrics)"]
+        Journal["Journal + PerfLog<br/>(Logging)"]
+    end
+
+    OTel -->|"OTLP"| Collector["OTel Collector"]
+    Insight -->|"UDP"| StatsD["StatsD Server"]
+    Journal -->|"File I/O"| LogFile["perf.log / debug.log"]
+
+    Collector --> Tempo["Tempo"]
+    StatsD --> Graphite["Graphite / Grafana"]
+    LogFile --> Loki["Loki (optional)"]
+
+    style rippled fill:#424242,stroke:#212121,color:#fff
+    style OTel fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style Insight fill:#1565c0,stroke:#0d47a1,color:#fff
+    style Journal fill:#e65100,stroke:#bf360c,color:#fff
+    style Collector fill:#2e7d32,stroke:#1b5e20,color:#fff
+```
+
+| Aspect                         | Details                                                                                                         |
+| ------------------------------ | --------------------------------------------------------------------------------------------------------------- |
+| **What changes for operators** | Deploy OTel Collector + trace backend. Existing StatsD and log pipelines stay as-is.                            |
+| **Codebase impact**            | New `Telemetry` module (~1500 LOC). Beast Insight and Journal untouched.                                        |
+| **New capabilities**           | Cross-node trace correlation, span-based debugging, request lifecycle visibility.                               |
+| **What we still can't do**     | Correlate metrics with specific traces natively. StatsD metrics remain fire-and-forget with no trace exemplars. |
+| **Maintenance burden**         | Three separate observability systems to maintain (OTel + StatsD + Journal).                                     |
+| **Risk**                       | Lowest — additive change, no existing systems disturbed.                                                        |
+
+---
+
+## Slide 4: Future Adoption — Metrics & Logs via OTel
+
+### Scenario B: + OTel Metrics (Replace StatsD)
+
+> Migrate StatsD to OTel Metrics API, exposing Prometheus-compatible metrics. Remove Beast Insight.
+
+```mermaid
+flowchart LR
+    subgraph rippled["rippled Process"]
+        direction TB
+        OTel["OTel SDK<br/>(Traces + Metrics)"]
+        Journal["Journal + PerfLog<br/>(Logging)"]
+    end
+
+    OTel -->|"OTLP"| Collector["OTel Collector"]
+    Journal -->|"File I/O"| LogFile["perf.log / debug.log"]
+
+    Collector --> Tempo["Tempo<br/>(Traces)"]
+    Collector --> Prom["Prometheus<br/>(Metrics)"]
+    LogFile --> Loki["Loki (optional)"]
+
+    style rippled fill:#424242,stroke:#212121,color:#fff
+    style OTel fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style Journal fill:#e65100,stroke:#bf360c,color:#fff
+    style Collector fill:#2e7d32,stroke:#1b5e20,color:#fff
+```
+
+- **Better metrics?** Yes — Prometheus gives native histograms (p50/p95/p99), multi-dimensional labels, and exemplars linking metric spikes to traces.
+- **Codebase**: Remove `Beast::Insight` + `StatsDCollector` (~2000 LOC). Single SDK for traces and metrics.
+- **Operator effort**: Rewrite dashboards from StatsD/Graphite queries to PromQL. Run both in parallel during transition.
+- **Risk**: Medium — operators must migrate monitoring infrastructure.
+
+### Scenario C: + OTel Logs (Full Stack)
+
+> Also replace Journal logging with OTel Logs API. Single SDK for everything.
+
+```mermaid
+flowchart LR
+    subgraph rippled["rippled Process"]
+        OTel["OTel SDK<br/>(Traces + Metrics + Logs)"]
+    end
+
+    OTel -->|"OTLP"| Collector["OTel Collector"]
+
+    Collector --> Tempo["Tempo<br/>(Traces)"]
+    Collector --> Prom["Prometheus<br/>(Metrics)"]
+    Collector --> Loki["Loki / Elastic<br/>(Logs)"]
+
+    style rippled fill:#424242,stroke:#212121,color:#fff
+    style OTel fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style Collector fill:#2e7d32,stroke:#1b5e20,color:#fff
+```
+
+- **Structured logging**: OTel Logs API outputs structured records with `trace_id`, `span_id`, severity, and attributes by design.
+- **Full correlation**: Every log line carries `trace_id`. Click trace → see logs. Click metric spike → see trace → see logs.
+- **Codebase**: Remove Beast Insight (~2000 LOC) + simplify Journal/PerfLog (~3000 LOC). One dependency instead of three.
+- **Risk**: Highest — `beast::Journal` is deeply embedded in every component. Large refactor. OTel C++ Logs API is newer (stable since v1.11, less battle-tested).
+
+### Recommendation
+
+```mermaid
+flowchart LR
+    A["Phase 1<br/><b>Traces Only</b><br/>(Current Plan)"] --> B["Phase 2<br/><b>+ Metrics</b><br/>(Replace StatsD)"] --> C["Phase 3<br/><b>+ Logs</b><br/>(Full OTel)"]
+
+    style A fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style B fill:#1565c0,stroke:#0d47a1,color:#fff
+    style C fill:#e65100,stroke:#bf360c,color:#fff
+```
+
+| Phase                | Signal    | Strategy                                                       | Risk   |
+| -------------------- | --------- | -------------------------------------------------------------- | ------ |
+| **Phase 1** (now)    | Traces    | Add OTel traces. Keep StatsD and Journal. Prove value.         | Low    |
+| **Phase 2** (future) | + Metrics | Migrate StatsD → Prometheus via OTel. Remove Beast Insight.    | Medium |
+| **Phase 3** (future) | + Logs    | Adopt OTel Logs API. Align with structured logging initiative. | High   |
+
+> **Key Takeaway**: Start with traces (unique value, lowest risk), then incrementally adopt metrics and logs as the OTel infrastructure proves itself.
+
+---
+
+## Slide 5: Comparison with rippled's Existing Solutions
+
+### Current Observability Stack
+
+| Aspect                | PerfLog (JSON)        | StatsD (Metrics)      | OpenTelemetry (NEW)         |
+| --------------------- | --------------------- | --------------------- | --------------------------- |
+| **Type**              | Logging               | Metrics               | Distributed Tracing         |
+| **Scope**             | Single node           | Single node           | **Cross-node**              |
+| **Data**              | JSON log entries      | Counters, gauges      | Spans with context          |
+| **Correlation**       | By timestamp          | By metric name        | By `trace_id`               |
+| **Overhead**          | Low (file I/O)        | Low (UDP)             | Low-Medium (configurable)   |
+| **Question Answered** | "What happened here?" | "How many? How fast?" | **"What was the journey?"** |
+
+### Use Case Matrix
+
+| Scenario                         | PerfLog | StatsD | OpenTelemetry |
+| -------------------------------- | ------- | ------ | ------------- |
+| "How many TXs per second?"       | ❌      | ✅     | ❌            |
+| "Why was this specific TX slow?" | ⚠️      | ❌     | ✅            |
+| "Which node delayed consensus?"  | ❌      | ❌     | ✅            |
+| "Show TX journey across 5 nodes" | ❌      | ❌     | ✅            |
+
+> **Key Insight**: In the **traces-only** approach (Phase 1), OpenTelemetry **complements** existing systems. In future phases, OTel metrics and logs could **replace** StatsD and Journal respectively — see Slides 3-4 for the full adoption roadmap.
+
+---
+
+## Slide 6: Architecture
+
+> **OTLP** = OpenTelemetry Protocol | **WS** = WebSocket
+
+### High-Level Integration Architecture
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Node"]
+        subgraph services["Core Services"]
+            direction LR
+            RPC["RPC Server<br/>(HTTP/WS)"] ~~~ Overlay["Overlay<br/>(P2P Network)"] ~~~ Consensus["Consensus<br/>(RCLConsensus)"]
+        end
+
+        Telemetry["Telemetry Module<br/>(OpenTelemetry SDK)"]
+
+        services --> Telemetry
+    end
+
+    Telemetry -->|OTLP/gRPC| Collector["OTel Collector"]
+
+    Collector --> Tempo["Grafana Tempo"]
+    Collector --> Elastic["Elastic APM"]
+
+    style rippled fill:#424242,stroke:#212121,color:#fff
+    style services fill:#1565c0,stroke:#0d47a1,color:#fff
+    style Telemetry fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style Collector fill:#e65100,stroke:#bf360c,color:#fff
+```
+
+**Reading the diagram:**
+
+- **Core Services (blue, top)**: RPC Server, Overlay, and Consensus are the three primary components that generate trace data — they represent the entry points for client requests, peer messages, and consensus rounds respectively.
+- **Telemetry Module (green, middle)**: The OpenTelemetry SDK sits below the core services and receives span data from all three; it acts as a single collection point within the rippled process.
+- **OTel Collector (orange, center)**: An external process that receives spans over OTLP/gRPC from the Telemetry Module; it decouples rippled from backend choices and handles batching, sampling, and routing.
+- **Backends (bottom row)**: Tempo and Elastic APM are interchangeable — the Collector fans out to any combination, so operators can switch backends without modifying rippled code.
+- **Top-to-bottom flow**: Data flows from instrumented code down through the SDK, out over the network to the Collector, and finally into storage/visualization backends.
+
+### Context Propagation
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant NodeA as Node A
+    participant NodeB as Node B
+
+    Client->>NodeA: Submit TX (no context)
+    Note over NodeA: Creates trace_id: abc123<br/>span: tx.receive
+    NodeA->>NodeB: Relay TX<br/>(traceparent: abc123)
+    Note over NodeB: Links to trace_id: abc123<br/>span: tx.relay
+```
+
+- **HTTP/RPC**: W3C Trace Context headers (`traceparent`)
+- **P2P Messages**: Protocol Buffer extension fields
+
+---
+
+## Slide 7: Implementation Plan
+
+### 5-Phase Rollout (9 Weeks)
+
+> **Note**: Dates shown are relative to project start, not calendar dates.
+
+```mermaid
+gantt
+    title Implementation Timeline
+    dateFormat  YYYY-MM-DD
+    axisFormat  Week %W
+
+    section Phase 1
+    Core Infrastructure    :p1, 2024-01-01, 2w
+
+    section Phase 2
+    RPC Tracing           :p2, after p1, 2w
+
+    section Phase 3
+    Transaction Tracing   :p3, after p2, 2w
+
+    section Phase 4
+    Consensus Tracing     :p4, after p3, 2w
+
+    section Phase 5
+    Documentation         :p5, after p4, 1w
+```
+
+### Phase Details
+
+| Phase | Focus               | Key Deliverables                             | Effort  |
+| ----- | ------------------- | -------------------------------------------- | ------- |
+| 1     | Core Infrastructure | SDK integration, Telemetry interface, Config | 10 days |
+| 2     | RPC Tracing         | HTTP context extraction, Handler spans       | 10 days |
+| 3     | Transaction Tracing | Protobuf context, P2P relay propagation      | 10 days |
+| 4     | Consensus Tracing   | Round spans, Proposal/validation tracing     | 10 days |
+| 5     | Documentation       | Runbook, Dashboards, Training                | 7 days  |
+
+**Total Effort**: ~47 developer-days (2 developers)
+
+> **Future Phases** (not in current scope): After traces are stable, OTel metrics can replace StatsD (~3 weeks), and OTel logs can replace Journal (~4 weeks, aligned with structured logging initiative). See Slides 3-4 for the full adoption roadmap.
+
+---
+
+## Slide 8: Performance Overhead
+
+> **OTLP** = OpenTelemetry Protocol
+
+### Estimated System Impact
+
+| Metric            | Overhead   | Notes                                            |
+| ----------------- | ---------- | ------------------------------------------------ |
+| **CPU**           | 1-3%       | Span creation and attribute setting              |
+| **Memory**        | ~10 MB     | SDK statics + batch buffer + worker thread stack |
+| **Network**       | 10-50 KB/s | Compressed OTLP export to collector              |
+| **Latency (p99)** | <2%        | With proper sampling configuration               |
+
+#### How We Arrived at These Numbers
+
+**Assumptions (XRPL mainnet baseline)**:
+
+| Parameter                 | Value                  | Source                                                                                              |
+| ------------------------- | ---------------------- | --------------------------------------------------------------------------------------------------- |
+| Transaction throughput    | ~25 TPS (peaks to ~50) | Mainnet average                                                                                     |
+| Default peers per node    | 21                     | `peerfinder/detail/Tuning.h` (`defaultMaxPeers`)                                                    |
+| Consensus round frequency | ~1 round / 3-4 seconds | `ConsensusParms.h` (`ledgerMIN_CONSENSUS=1950ms`)                                                   |
+| Proposers per round       | ~20-35                 | Mainnet UNL size                                                                                    |
+| P2P message rate          | ~160 msgs/sec          | See message breakdown below                                                                         |
+| Avg TX processing time    | ~200 μs                | Profiled baseline                                                                                   |
+| Single span creation cost | 500-1000 ns            | OTel C++ SDK benchmarks (see [3.5.4](./03-implementation-strategy.md#354-performance-data-sources)) |
+
+**P2P message breakdown** (per node, mainnet):
+
+| Message Type  | Rate         | Derivation                                                            |
+| ------------- | ------------ | --------------------------------------------------------------------- |
+| TMTransaction | ~100/sec     | ~25 TPS × ~4 relay hops per TX, deduplicated by HashRouter            |
+| TMValidation  | ~50/sec      | ~35 validators × ~1 validation/3s round ≈ ~12/sec, plus relay fan-out |
+| TMProposeSet  | ~10/sec      | ~35 proposers / 3s round ≈ ~12/round, clustered in establish phase    |
+| **Total**     | **~160/sec** | **Only traced message types counted**                                 |
+
+**CPU (1-3%) — Calculation**:
+
+Per-transaction tracing cost breakdown:
+
+| Operation                                       | Cost        | Notes                                      |
+| ----------------------------------------------- | ----------- | ------------------------------------------ |
+| `tx.receive` span (create + end + 4 attributes) | ~1400 ns    | ~1000ns create + ~200ns end + 4×50ns attrs |
+| `tx.validate` span                              | ~1200 ns    | ~1000ns create + ~200ns for 2 attributes   |
+| `tx.relay` span                                 | ~1200 ns    | ~1000ns create + ~200ns for 2 attributes   |
+| Context injection into P2P message              | ~200 ns     | Serialize trace_id + span_id into protobuf |
+| **Total per TX**                                | **~4.0 μs** |                                            |
+
+> **CPU overhead**: 4.0 μs / 200 μs baseline = **~2.0% per transaction**. Under high load with consensus + RPC spans overlapping, reaches ~3%. Consensus itself adds only ~36 μs per 3-second round (~0.001%), so the TX path dominates. On production server hardware (3+ GHz Xeon), span creation drops to ~500-600 ns, bringing per-TX cost to ~2.6 μs (~1.3%). See [Section 3.5.4](./03-implementation-strategy.md#354-performance-data-sources) for benchmark sources.
+
+**Memory (~10 MB) — Calculation**:
+
+| Component                                     | Size               | Notes                                 |
+| --------------------------------------------- | ------------------ | ------------------------------------- |
+| TracerProvider + Exporter (gRPC channel init) | ~320 KB            | Allocated once at startup             |
+| BatchSpanProcessor (circular buffer)          | ~16 KB             | 2049 × 8-byte AtomicUniquePtr entries |
+| BatchSpanProcessor (worker thread stack)      | ~8 MB              | Default Linux thread stack size       |
+| Active spans (in-flight, max ~1000)           | ~500-800 KB        | ~500-800 bytes/span × 1000 concurrent |
+| Export queue (batch buffer, max 2048 spans)   | ~1 MB              | ~500 bytes/span × 2048 queue depth    |
+| Thread-local context storage (~100 threads)   | ~6.4 KB            | ~64 bytes/thread                      |
+| **Total**                                     | **~10 MB ceiling** |                                       |
+
+> Memory plateaus once the export queue fills — the `max_queue_size=2048` config bounds growth.
+> The worker thread stack (~8 MB) dominates the static footprint but is virtual memory; actual RSS
+> depends on stack usage (typically much less). Active spans are larger than originally estimated
+> (~500-800 bytes) because the OTel SDK `Span` object includes a mutex (~40 bytes), `SpanData`
+> recordable (~250 bytes base), and `std::map`-based attribute storage (~200-500 bytes for 3-5
+> string attributes). See [Section 3.5.4](./03-implementation-strategy.md#354-performance-data-sources) for source references.
+
+**Network (10-50 KB/s) — Calculation**:
+
+Two sources of network overhead:
+
+**(A) OTLP span export to Collector:**
+
+| Sampling Rate              | Effective Spans/sec | Avg Span Size (compressed) | Bandwidth    |
+| -------------------------- | ------------------- | -------------------------- | ------------ |
+| 100% (dev only)            | ~500                | ~500 bytes                 | ~250 KB/s    |
+| **10% (recommended prod)** | **~50**             | **~500 bytes**             | **~25 KB/s** |
+| 1% (minimal)               | ~5                  | ~500 bytes                 | ~2.5 KB/s    |
+
+> The ~500 spans/sec at 100% comes from: ~100 TX spans + ~160 P2P context spans + ~23 consensus spans/round + ~50 RPC spans = ~500/sec. OTLP protobuf with gzip compression yields ~500 bytes/span average.
+
+**(B) P2P trace context overhead** (added to existing messages, always-on regardless of sampling):
+
+| Message Type  | Rate     | Context Size | Bandwidth     |
+| ------------- | -------- | ------------ | ------------- |
+| TMTransaction | ~100/sec | 29 bytes     | ~2.9 KB/s     |
+| TMValidation  | ~50/sec  | 29 bytes     | ~1.5 KB/s     |
+| TMProposeSet  | ~10/sec  | 29 bytes     | ~0.3 KB/s     |
+| **Total P2P** |          |              | **~4.7 KB/s** |
+
+> **Combined**: 25 KB/s (OTLP export at 10%) + 5 KB/s (P2P context) ≈ **~30 KB/s typical**. The 10-50 KB/s range covers 10-20% sampling under normal to peak mainnet load.
+
+**Latency (<2%) — Calculation**:
+
+| Path                           | Tracing Cost | Baseline | Overhead |
+| ------------------------------ | ------------ | -------- | -------- |
+| Fast RPC (e.g., `server_info`) | 2.75 μs      | ~1 ms    | 0.275%   |
+| Slow RPC (e.g., `path_find`)   | 2.75 μs      | ~100 ms  | 0.003%   |
+| Transaction processing         | 4.0 μs       | ~200 μs  | 2.0%     |
+| Consensus round                | 36 μs        | ~3 sec   | 0.001%   |
+
+> At p99, even the worst case (TX processing at 2.0%) is within the 1-3% range. RPC and consensus overhead are negligible. On production hardware, TX overhead drops to ~1.3%.
+
+### Per-Message Overhead (Context Propagation)
+
+Each P2P message carries trace context with the following overhead:
+
+| Field         | Size          | Description                               |
+| ------------- | ------------- | ----------------------------------------- |
+| `trace_id`    | 16 bytes      | Unique identifier for the entire trace    |
+| `span_id`     | 8 bytes       | Current span (becomes parent on receiver) |
+| `trace_flags` | 1 byte        | Sampling decision flags                   |
+| `trace_state` | 0-4 bytes     | Optional vendor-specific data             |
+| **Total**     | **~29 bytes** | **Added per traced P2P message**          |
+
+```mermaid
+flowchart LR
+    subgraph msg["P2P Message with Trace Context"]
+        A["Original Message<br/>(variable size)"] --> B["+ TraceContext<br/>(~29 bytes)"]
+    end
+
+    subgraph breakdown["Context Breakdown"]
+        C["trace_id<br/>16 bytes"]
+        D["span_id<br/>8 bytes"]
+        E["flags<br/>1 byte"]
+        F["state<br/>0-4 bytes"]
+    end
+
+    B --> breakdown
+
+    style A fill:#424242,stroke:#212121,color:#fff
+    style B fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style C fill:#1565c0,stroke:#0d47a1,color:#fff
+    style D fill:#1565c0,stroke:#0d47a1,color:#fff
+    style E fill:#e65100,stroke:#bf360c,color:#fff
+    style F fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+**Reading the diagram:**
+
+- **Original Message (gray, left)**: The existing P2P message payload of variable size — this is unchanged; trace context is appended, never modifying the original data.
+- **+ TraceContext (green, right of message)**: The additional 29-byte context block attached to each traced message; the arrow from the original message shows it is a pure addition.
+- **Context Breakdown (right subgraph)**: The four fields — `trace_id` (16 bytes), `span_id` (8 bytes), `flags` (1 byte), and `state` (0-4 bytes) — show exactly what is added and their individual sizes.
+- **Color coding**: Blue fields (`trace_id`, `span_id`) are the core identifiers required for trace correlation; orange (`flags`) controls sampling decisions; purple (`state`) is optional vendor data typically omitted.
+
+> **Note**: 29 bytes represents ~1-6% overhead depending on message size (500B simple TX to 5KB proposal), which is acceptable for the observability benefits provided.
+
+### Mitigation Strategies
+
+```mermaid
+flowchart LR
+    A["Head Sampling<br/>10% default"] --> B["Tail Sampling<br/>Keep errors/slow"] --> C["Batch Export<br/>Reduce I/O"] --> D["Conditional Compile<br/>XRPL_ENABLE_TELEMETRY"]
+
+    style A fill:#1565c0,stroke:#0d47a1,color:#fff
+    style B fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style C fill:#e65100,stroke:#bf360c,color:#fff
+    style D fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+> For a detailed explanation of head vs. tail sampling, see Slide 9.
+
+### Kill Switches (Rollback Options)
+
+1. **Config Disable**: Set `enabled=0` in config → instant disable, no restart needed for sampling
+2. **Rebuild**: Compile with `XRPL_ENABLE_TELEMETRY=OFF` → zero overhead (no-op)
+3. **Full Revert**: Clean separation allows easy commit reversion
+
+---
+
+## Slide 9: Sampling Strategies — Head vs. Tail
+
+> Sampling controls **which traces are recorded and exported**. Without sampling, every operation generates a trace — at 500+ spans/sec, this overwhelms storage and network. Sampling lets you keep the signal, discard the noise.
+
+### Head Sampling (Decision at Start)
+
+The sampling decision is made **when a trace begins**, before any work is done. A random number is generated; if it falls within the configured ratio, the entire trace is recorded. Otherwise, the trace is silently dropped.
+
+```mermaid
+flowchart LR
+    A["New Request<br/>Arrives"] --> B{"Random < 10%?"}
+    B -->|"Yes (1 in 10)"| C["Record Entire Trace<br/>(all spans)"]
+    B -->|"No (9 in 10)"| D["Drop Entire Trace<br/>(zero overhead)"]
+
+    style C fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style D fill:#c62828,stroke:#8c2809,color:#fff
+    style B fill:#1565c0,stroke:#0d47a1,color:#fff
+```
+
+| Aspect                        | Details                                                                                                                                                                                                  |
+| ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Where it runs**             | Inside rippled (SDK-level). Configured via `sampling_ratio` in `rippled.cfg`.                                                                                                                            |
+| **When the decision happens** | At trace creation time — before the first span is even populated.                                                                                                                                        |
+| **How it works**              | `sampling_ratio=0.1` means each trace has a 10% probability of being recorded. Dropped traces incur near-zero overhead (no spans created, no attributes set, no export).                                 |
+| **Propagation**               | Once a trace is sampled, the `trace_flags` field (1 byte in the context header) tells downstream nodes to also sample it. Unsampled traces propagate `trace_flags=0`, so downstream nodes skip them too. |
+| **Pros**                      | Lowest overhead. Simple to configure. Predictable resource usage.                                                                                                                                        |
+| **Cons**                      | **Blind** — it doesn't know if the trace will be interesting. A rare error or slow consensus round has only a 10% chance of being captured.                                                              |
+| **Best for**                  | High-volume, steady-state traffic where most traces look similar (e.g., routine RPC requests).                                                                                                           |
+
+**rippled configuration**:
+
+```ini
+[telemetry]
+# Record 10% of traces (recommended for production)
+sampling_ratio=0.1
+```
+
+### Tail Sampling (Decision at End)
+
+The sampling decision is made **after the trace completes**, based on its actual content — was it slow? Did it error? Was it a consensus round? This requires buffering complete traces before deciding.
+
+```mermaid
+flowchart TB
+    A["All Traces<br/>Buffered (100%)"] --> B["OTel Collector<br/>Evaluates Rules"]
+
+    B --> C{"Error?"}
+    C -->|Yes| K["KEEP"]
+
+    C -->|No| D{"Slow?<br/>(>5s consensus,<br/>>1s RPC)"}
+    D -->|Yes| K
+
+    D -->|No| E{"Random < 10%?"}
+    E -->|Yes| K
+    E -->|No| F["DROP"]
+
+    style K fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style F fill:#c62828,stroke:#8c2809,color:#fff
+    style B fill:#1565c0,stroke:#0d47a1,color:#fff
+    style C fill:#e65100,stroke:#bf360c,color:#fff
+    style D fill:#e65100,stroke:#bf360c,color:#fff
+    style E fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+| Aspect                        | Details                                                                                                                                                                                                   |
+| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Where it runs**             | In the **OTel Collector** (external process), not inside rippled. rippled exports 100% of traces; the Collector decides what to keep.                                                                     |
+| **When the decision happens** | After the Collector has received all spans for a trace (waits `decision_wait=10s` for stragglers).                                                                                                        |
+| **How it works**              | Policy rules evaluate the completed trace: keep all errors, keep slow operations above a threshold, keep all consensus rounds, then probabilistically sample the rest at 10%.                             |
+| **Pros**                      | **Never misses important traces**. Errors, slow requests, and consensus anomalies are always captured regardless of probability.                                                                          |
+| **Cons**                      | Higher resource usage — rippled must export 100% of spans to the Collector, which buffers them in memory before deciding. The Collector needs more RAM (configured via `num_traces` and `decision_wait`). |
+| **Best for**                  | Production troubleshooting where you can't afford to miss errors or anomalies.                                                                                                                            |
+
+**Collector configuration** (tail sampling rules for rippled):
+
+```yaml
+processors:
+  tail_sampling:
+    decision_wait: 10s # Wait for all spans in a trace
+    num_traces: 100000 # Buffer up to 100K concurrent traces
+    policies:
+      - name: errors # Always keep error traces
+        type: status_code
+        status_code: { status_codes: [ERROR] }
+
+      - name: slow-consensus # Keep consensus rounds >5s
+        type: latency
+        latency: { threshold_ms: 5000 }
+
+      - name: slow-rpc # Keep slow RPC requests >1s
+        type: latency
+        latency: { threshold_ms: 1000 }
+
+      - name: probabilistic # Sample 10% of everything else
+        type: probabilistic
+        probabilistic: { sampling_percentage: 10 }
+```
+
+### Head vs. Tail — Side-by-Side
+
+|                               | Head Sampling                            | Tail Sampling                                    |
+| ----------------------------- | ---------------------------------------- | ------------------------------------------------ |
+| **Decision point**            | Trace start (inside rippled)             | Trace end (in OTel Collector)                    |
+| **Knows trace content?**      | No (random coin flip)                    | Yes (evaluates completed trace)                  |
+| **Overhead on rippled**       | Lowest (dropped traces = no-op)          | Higher (must export 100% to Collector)           |
+| **Collector resource usage**  | Low (receives only sampled traces)       | Higher (buffers all traces before deciding)      |
+| **Captures all errors?**      | No (only if trace was randomly selected) | **Yes** (error policy catches them)              |
+| **Captures slow operations?** | No (random)                              | **Yes** (latency policy catches them)            |
+| **Configuration**             | `rippled.cfg`: `sampling_ratio=0.1`      | `otel-collector.yaml`: `tail_sampling` processor |
+| **Best for**                  | High-throughput steady-state             | Troubleshooting & anomaly detection              |
+
+### Recommended Strategy for rippled
+
+Use **both** in a layered approach:
+
+```mermaid
+flowchart LR
+    subgraph rippled["rippled (Head Sampling)"]
+        HS["sampling_ratio=1.0<br/>(export everything)"]
+    end
+
+    subgraph collector["OTel Collector (Tail Sampling)"]
+        TS["Keep: errors + slow + 10% random<br/>Drop: routine traces"]
+    end
+
+    subgraph storage["Backend Storage"]
+        ST["Only interesting traces<br/>stored long-term"]
+    end
+
+    rippled -->|"100% of spans"| collector -->|"~15-20% kept"| storage
+
+    style rippled fill:#424242,stroke:#212121,color:#fff
+    style collector fill:#1565c0,stroke:#0d47a1,color:#fff
+    style storage fill:#2e7d32,stroke:#1b5e20,color:#fff
+```
+
+> **Why this works**: rippled exports everything (no blind drops), the Collector applies intelligent filtering (keep errors/slow/anomalies, sample the rest), and only ~15-20% of traces reach storage. If Collector resource usage becomes a concern, add head sampling at `sampling_ratio=0.5` to halve the export volume while still giving the Collector enough data for good tail-sampling decisions.
+
+---
+
+## Slide 10: Data Collection & Privacy
+
+### What Data is Collected
+
+| Category        | Attributes Collected                                                                 | Purpose                     |
+| --------------- | ------------------------------------------------------------------------------------ | --------------------------- |
+| **Transaction** | `tx.hash`, `tx.type`, `tx.result`, `tx.fee`, `ledger_index`                          | Trace transaction lifecycle |
+| **Consensus**   | `round`, `phase`, `mode`, `proposers` (count of proposing validators), `duration_ms` | Analyze consensus timing    |
+| **RPC**         | `command`, `version`, `status`, `duration_ms`                                        | Monitor RPC performance     |
+| **Peer**        | `peer.id`(public key), `latency_ms`, `message.type`, `message.size`                  | Network topology analysis   |
+| **Ledger**      | `ledger.hash`, `ledger.index`, `close_time`, `tx_count`                              | Ledger progression tracking |
+| **Job**         | `job.type`, `queue_ms`, `worker`                                                     | JobQueue performance        |
+
+### What is NOT Collected (Privacy Guarantees)
+
+```mermaid
+flowchart LR
+    subgraph notCollected["❌ NOT Collected"]
+        direction LR
+        A["Private Keys"] ~~~ B["Account Balances"] ~~~ C["Transaction Amounts"]
+    end
+
+    subgraph alsoNot["❌ Also Excluded"]
+        direction LR
+        D["IP Addresses<br/>(configurable)"] ~~~ E["Personal Data"] ~~~ F["Raw TX Payloads"]
+    end
+
+    style A fill:#c62828,stroke:#8c2809,color:#fff
+    style B fill:#c62828,stroke:#8c2809,color:#fff
+    style C fill:#c62828,stroke:#8c2809,color:#fff
+    style D fill:#c62828,stroke:#8c2809,color:#fff
+    style E fill:#c62828,stroke:#8c2809,color:#fff
+    style F fill:#c62828,stroke:#8c2809,color:#fff
+```
+
+**Reading the diagram:**
+
+- **NOT Collected (top row, red)**: Private Keys, Account Balances, and Transaction Amounts are explicitly excluded — these are financial/security-sensitive fields that telemetry never touches.
+- **Also Excluded (bottom row, red)**: IP Addresses (configurable per deployment), Personal Data, and Raw TX Payloads are also excluded — these protect operator and user privacy.
+- **All-red styling**: Every box is styled in red to visually reinforce that these are hard exclusions, not optional — the telemetry system has no code path to collect any of these fields.
+- **Two-row layout**: The split between "NOT Collected" and "Also Excluded" distinguishes between financial data (top) and operational/personal data (bottom), making the privacy boundaries clear to auditors.
+
+### Privacy Protection Mechanisms
+
+| Mechanism                  | Description                                                   |
+| -------------------------- | ------------------------------------------------------------- |
+| **Account Hashing**        | `xrpl.tx.account` is hashed at collector level before storage |
+| **Configurable Redaction** | Sensitive fields can be excluded via config                   |
+| **Sampling**               | Only 10% of traces recorded by default (reduces exposure)     |
+| **Local Control**          | Node operators control what gets exported                     |
+| **No Raw Payloads**        | Transaction content is never recorded, only metadata          |
+
+> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes) — never **sensitive content** (keys, balances, amounts).
+
+---
+
+_End of Presentation_

cfg/xrpld-example.cfg

@@ -940,23 +940,7 @@
 #
 #       path                Location to store the database
 #
-#   Optional keys
-#
-#       cache_size          Size of cache for database records. Default is 16384.
-#                           Setting this value to 0 will use the default value.
-#
-#       cache_age           Length of time in minutes to keep database records
-#                           cached. Default is 5 minutes. Setting this value to
-#                           0 will use the default value.
-#
-#                           Note: if neither cache_size nor cache_age is
-#                           specified, the cache for database records will not
-#                           be created. If only one of cache_size or cache_age
-#                           is specified, the cache will be created using the
-#                           default value for the unspecified parameter.
-#
-#                           Note: the cache will not be created if online_delete
-#                           is specified.
+#   Optional keys for NuDB and RocksDB:
 #
 #       fast_load           Boolean. If set, load the last persisted ledger
 #                           from disk upon process start before syncing to
@@ -964,8 +948,6 @@
 #                           if sufficient IOPS capacity is available.
 #                           Default 0.
 #
-#   Optional keys for NuDB or RocksDB:
-#
 #       earliest_seq        The default is 32570 to match the XRP ledger
 #                           network's earliest allowed sequence. Alternate
 #                           networks may set this value. Minimum value of 1.
@@ -1547,3 +1529,46 @@ validators.txt
 # set to ssl_verify to 0.
 [ssl_verify]
 1
+#-------------------------------------------------------------------------------
+#
+# 11. Telemetry (OpenTelemetry Tracing)
+#
+#-------------------------------------------------------------------------------
+#
+# Enables distributed tracing via OpenTelemetry. Requires building with
+# -DXRPL_ENABLE_TELEMETRY=ON (telemetry Conan option).
+#
+# [telemetry]
+#
+# enabled=0
+#
+#   Enable or disable telemetry at runtime. Default: 0 (disabled).
+#
+# endpoint=http://localhost:4318/v1/traces
+#
+#   The OpenTelemetry Collector endpoint (OTLP/HTTP). Default: http://localhost:4318/v1/traces.
+#
+# exporter=otlp_http
+#
+#   Exporter type: otlp_http. Default: otlp_http.
+#
+# sampling_ratio=1.0
+#
+#   Fraction of traces to sample (0.0 to 1.0). Default: 1.0 (all traces).
+#
+# trace_rpc=1
+#
+#   Enable RPC request tracing. Default: 1.
+#
+# trace_transactions=1
+#
+#   Enable transaction lifecycle tracing. Default: 1.
+#
+# trace_consensus=1
+#
+#   Enable consensus round tracing. Default: 1.
+#
+# trace_peer=0
+#
+#   Enable peer message tracing (high volume). Default: 0.
+#

cmake/CMakeFuncs.cmake

@@ -1,30 +1,32 @@
-macro (exclude_from_default target_)
-  set_target_properties (${target_} PROPERTIES EXCLUDE_FROM_ALL ON)
-  set_target_properties (${target_} PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD ON)
-endmacro ()
+macro(exclude_from_default target_)
+    set_target_properties(${target_} PROPERTIES EXCLUDE_FROM_ALL ON)
+    set_target_properties(${target_} PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD ON)
+endmacro()
 
-macro (exclude_if_included target_)
-  get_directory_property(has_parent PARENT_DIRECTORY)
-  if (has_parent)
-    exclude_from_default (${target_})
-  endif ()
-endmacro ()
+macro(exclude_if_included target_)
+    get_directory_property(has_parent PARENT_DIRECTORY)
+    if(has_parent)
+        exclude_from_default(${target_})
+    endif()
+endmacro()
 
 find_package(Git)
 
-function (git_branch branch_val)
-  if (NOT GIT_FOUND)
-    return ()
-  endif ()
-  set (_branch "")
-  execute_process (COMMAND ${GIT_EXECUTABLE} "rev-parse" "--abbrev-ref" "HEAD"
-                   WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-                   RESULT_VARIABLE _git_exit_code
-                   OUTPUT_VARIABLE _temp_branch
-                   OUTPUT_STRIP_TRAILING_WHITESPACE
-                   ERROR_QUIET)
-  if (_git_exit_code EQUAL 0)
-    set (_branch ${_temp_branch})
-  endif ()
-  set (${branch_val} "${_branch}" PARENT_SCOPE)
-endfunction ()
+function(git_branch branch_val)
+    if(NOT GIT_FOUND)
+        return()
+    endif()
+    set(_branch "")
+    execute_process(
+        COMMAND ${GIT_EXECUTABLE} "rev-parse" "--abbrev-ref" "HEAD"
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        RESULT_VARIABLE _git_exit_code
+        OUTPUT_VARIABLE _temp_branch
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        ERROR_QUIET
+    )
+    if(_git_exit_code EQUAL 0)
+        set(_branch ${_temp_branch})
+    endif()
+    set(${branch_val} "${_branch}" PARENT_SCOPE)
+endfunction()

cmake/Ccache.cmake

@@ -1,57 +1,62 @@
 find_program(CCACHE_PATH "ccache")
-if (NOT CCACHE_PATH)
+if(NOT CCACHE_PATH)
     return()
-endif ()
+endif()
 
 # For Linux and macOS we can use the ccache binary directly.
-if (NOT MSVC)
+if(NOT MSVC)
     set(CMAKE_C_COMPILER_LAUNCHER "${CCACHE_PATH}")
     set(CMAKE_CXX_COMPILER_LAUNCHER "${CCACHE_PATH}")
     message(STATUS "Found ccache: ${CCACHE_PATH}")
     return()
-endif ()
+endif()
 
 # For Windows more effort is required. The code below is a modified version of
 # https://github.com/ccache/ccache/wiki/MS-Visual-Studio#usage-with-cmake.
-if ("${CCACHE_PATH}" MATCHES "chocolatey")
+if("${CCACHE_PATH}" MATCHES "chocolatey")
     message(DEBUG "Ccache path: ${CCACHE_PATH}")
-    # Chocolatey uses a shim executable that we cannot use directly, in which
-    # case we have to find the executable it points to. If we cannot find the
-    # target executable then we cannot use ccache.
+    # Chocolatey uses a shim executable that we cannot use directly, in which case we have to find the executable it
+    # points to. If we cannot find the target executable then we cannot use ccache.
     find_program(BASH_PATH "bash")
-    if (NOT BASH_PATH)
+    if(NOT BASH_PATH)
         message(WARNING "Could not find bash.")
         return()
-    endif ()
+    endif()
 
     execute_process(
-            COMMAND bash -c "export LC_ALL='en_US.UTF-8'; ${CCACHE_PATH} --shimgen-noop | grep -oP 'path to executable: \\K.+' | head -c -1"
-            OUTPUT_VARIABLE CCACHE_PATH)
+        COMMAND
+            bash -c
+            "export LC_ALL='en_US.UTF-8'; ${CCACHE_PATH} --shimgen-noop | grep -oP 'path to executable: \\K.+' | head -c -1"
+        OUTPUT_VARIABLE CCACHE_PATH
+    )
 
-    if (NOT CCACHE_PATH)
+    if(NOT CCACHE_PATH)
         message(WARNING "Could not find ccache target.")
         return()
-    endif ()
+    endif()
     file(TO_CMAKE_PATH "${CCACHE_PATH}" CCACHE_PATH)
-endif ()
+endif()
 message(STATUS "Found ccache: ${CCACHE_PATH}")
 
 # Tell cmake to use ccache for compiling with Visual Studio.
-file(COPY_FILE
-        ${CCACHE_PATH} ${CMAKE_BINARY_DIR}/cl.exe
-        ONLY_IF_DIFFERENT)
+file(COPY_FILE ${CCACHE_PATH} ${CMAKE_BINARY_DIR}/cl.exe ONLY_IF_DIFFERENT)
 set(CMAKE_VS_GLOBALS
-        "CLToolExe=cl.exe"
-        "CLToolPath=${CMAKE_BINARY_DIR}"
-        "TrackFileAccess=false"
-        "UseMultiToolTask=true")
+    "CLToolExe=cl.exe"
+    "CLToolPath=${CMAKE_BINARY_DIR}"
+    "TrackFileAccess=false"
+    "UseMultiToolTask=true"
+)
 
-# By default Visual Studio generators will use /Zi to capture debug information,
-# which is not compatible with ccache, so tell it to use /Z7 instead.
-if (MSVC)
-    foreach (var_
-        CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE
-        CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE)
-        string (REPLACE "/Zi" "/Z7" ${var_} "${${var_}}")
-    endforeach ()
-endif ()
+# By default Visual Studio generators will use /Zi to capture debug information, which is not compatible with ccache, so
+# tell it to use /Z7 instead.
+if(MSVC)
+    foreach(
+        var_
+        CMAKE_C_FLAGS_DEBUG
+        CMAKE_C_FLAGS_RELEASE
+        CMAKE_CXX_FLAGS_DEBUG
+        CMAKE_CXX_FLAGS_RELEASE
+    )
+        string(REPLACE "/Zi" "/Z7" ${var_} "${${var_}}")
+    endforeach()
+endif()

cmake/CodeCoverage.cmake

@@ -172,44 +172,49 @@ include(CMakeParseArguments)
 option(CODE_COVERAGE_VERBOSE "Verbose information" FALSE)
 
 # Check prereqs
-find_program( GCOVR_PATH gcovr PATHS ${CMAKE_SOURCE_DIR}/scripts/test)
+find_program(GCOVR_PATH gcovr PATHS ${CMAKE_SOURCE_DIR}/scripts/test)
 
 if(DEFINED CODE_COVERAGE_GCOV_TOOL)
-  set(GCOV_TOOL "${CODE_COVERAGE_GCOV_TOOL}")
+    set(GCOV_TOOL "${CODE_COVERAGE_GCOV_TOOL}")
 elseif(DEFINED ENV{CODE_COVERAGE_GCOV_TOOL})
-  set(GCOV_TOOL "$ENV{CODE_COVERAGE_GCOV_TOOL}")
+    set(GCOV_TOOL "$ENV{CODE_COVERAGE_GCOV_TOOL}")
 elseif("${CMAKE_CXX_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
-  if(APPLE)
-    execute_process( COMMAND xcrun -f llvm-cov
-      OUTPUT_VARIABLE LLVMCOV_PATH
-      OUTPUT_STRIP_TRAILING_WHITESPACE
-    )
-  else()
-    find_program( LLVMCOV_PATH llvm-cov )
-  endif()
-  if(LLVMCOV_PATH)
-    set(GCOV_TOOL "${LLVMCOV_PATH} gcov")
-  endif()
+    if(APPLE)
+        execute_process(
+            COMMAND xcrun -f llvm-cov
+            OUTPUT_VARIABLE LLVMCOV_PATH
+            OUTPUT_STRIP_TRAILING_WHITESPACE
+        )
+    else()
+        find_program(LLVMCOV_PATH llvm-cov)
+    endif()
+    if(LLVMCOV_PATH)
+        set(GCOV_TOOL "${LLVMCOV_PATH} gcov")
+    endif()
 elseif("${CMAKE_CXX_COMPILER_ID}" MATCHES "GNU")
-  find_program( GCOV_PATH gcov )
-  set(GCOV_TOOL "${GCOV_PATH}")
+    find_program(GCOV_PATH gcov)
+    set(GCOV_TOOL "${GCOV_PATH}")
 endif()
 
 # Check supported compiler (Clang, GNU and Flang)
 get_property(LANGUAGES GLOBAL PROPERTY ENABLED_LANGUAGES)
 foreach(LANG ${LANGUAGES})
-  if("${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
-    if("${CMAKE_${LANG}_COMPILER_VERSION}" VERSION_LESS 3)
-      message(FATAL_ERROR "Clang version must be 3.0.0 or greater! Aborting...")
+    if("${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
+        if("${CMAKE_${LANG}_COMPILER_VERSION}" VERSION_LESS 3)
+            message(
+                FATAL_ERROR
+                "Clang version must be 3.0.0 or greater! Aborting..."
+            )
+        endif()
+    elseif(
+        NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "GNU"
+        AND NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(LLVM)?[Ff]lang"
+    )
+        message(FATAL_ERROR "Compiler is not GNU or Flang! Aborting...")
     endif()
-  elseif(NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "GNU"
-         AND NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(LLVM)?[Ff]lang")
-    message(FATAL_ERROR "Compiler is not GNU or Flang! Aborting...")
-  endif()
 endforeach()
 
-set(COVERAGE_COMPILER_FLAGS "-g --coverage"
-    CACHE INTERNAL "")
+set(COVERAGE_COMPILER_FLAGS "-g --coverage" CACHE INTERNAL "")
 
 set(COVERAGE_CXX_COMPILER_FLAGS "")
 set(COVERAGE_C_COMPILER_FLAGS "")
@@ -228,49 +233,75 @@ if(CMAKE_CXX_COMPILER_ID MATCHES "(GNU|Clang)")
 
     check_cxx_compiler_flag(-fprofile-abs-path HAVE_cxx_fprofile_abs_path)
     if(HAVE_cxx_fprofile_abs_path)
-        set(COVERAGE_CXX_COMPILER_FLAGS "${COVERAGE_CXX_COMPILER_FLAGS} -fprofile-abs-path")
+        set(COVERAGE_CXX_COMPILER_FLAGS
+            "${COVERAGE_CXX_COMPILER_FLAGS} -fprofile-abs-path"
+        )
     endif()
 
     check_c_compiler_flag(-fprofile-abs-path HAVE_c_fprofile_abs_path)
     if(HAVE_c_fprofile_abs_path)
-        set(COVERAGE_C_COMPILER_FLAGS "${COVERAGE_C_COMPILER_FLAGS} -fprofile-abs-path")
+        set(COVERAGE_C_COMPILER_FLAGS
+            "${COVERAGE_C_COMPILER_FLAGS} -fprofile-abs-path"
+        )
     endif()
 
     check_linker_flag(CXX -fprofile-abs-path HAVE_cxx_linker_fprofile_abs_path)
     if(HAVE_cxx_linker_fprofile_abs_path)
-        set(COVERAGE_CXX_LINKER_FLAGS "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-abs-path")
+        set(COVERAGE_CXX_LINKER_FLAGS
+            "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-abs-path"
+        )
     endif()
 
     check_linker_flag(C -fprofile-abs-path HAVE_c_linker_fprofile_abs_path)
     if(HAVE_c_linker_fprofile_abs_path)
-        set(COVERAGE_C_LINKER_FLAGS "${COVERAGE_C_LINKER_FLAGS} -fprofile-abs-path")
+        set(COVERAGE_C_LINKER_FLAGS
+            "${COVERAGE_C_LINKER_FLAGS} -fprofile-abs-path"
+        )
     endif()
 
     check_cxx_compiler_flag(-fprofile-update=atomic HAVE_cxx_fprofile_update)
     if(HAVE_cxx_fprofile_update)
-        set(COVERAGE_CXX_COMPILER_FLAGS "${COVERAGE_CXX_COMPILER_FLAGS}  -fprofile-update=atomic")
+        set(COVERAGE_CXX_COMPILER_FLAGS
+            "${COVERAGE_CXX_COMPILER_FLAGS}  -fprofile-update=atomic"
+        )
     endif()
 
     check_c_compiler_flag(-fprofile-update=atomic HAVE_c_fprofile_update)
     if(HAVE_c_fprofile_update)
-        set(COVERAGE_C_COMPILER_FLAGS "${COVERAGE_C_COMPILER_FLAGS} -fprofile-update=atomic")
+        set(COVERAGE_C_COMPILER_FLAGS
+            "${COVERAGE_C_COMPILER_FLAGS} -fprofile-update=atomic"
+        )
     endif()
 
-    check_linker_flag(CXX -fprofile-update=atomic HAVE_cxx_linker_fprofile_update)
+    check_linker_flag(
+        CXX
+        -fprofile-update=atomic
+        HAVE_cxx_linker_fprofile_update
+    )
     if(HAVE_cxx_linker_fprofile_update)
-        set(COVERAGE_CXX_LINKER_FLAGS "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-update=atomic")
+        set(COVERAGE_CXX_LINKER_FLAGS
+            "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-update=atomic"
+        )
     endif()
 
     check_linker_flag(C -fprofile-update=atomic HAVE_c_linker_fprofile_update)
     if(HAVE_c_linker_fprofile_update)
-        set(COVERAGE_C_LINKER_FLAGS "${COVERAGE_C_LINKER_FLAGS} -fprofile-update=atomic")
+        set(COVERAGE_C_LINKER_FLAGS
+            "${COVERAGE_C_LINKER_FLAGS} -fprofile-update=atomic"
+        )
     endif()
-
 endif()
 
-get_property(GENERATOR_IS_MULTI_CONFIG GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
+get_property(
+    GENERATOR_IS_MULTI_CONFIG
+    GLOBAL
+    PROPERTY GENERATOR_IS_MULTI_CONFIG
+)
 if(NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG))
-    message(WARNING "Code coverage results with an optimised (non-Debug) build may be misleading")
+    message(
+        WARNING
+        "Code coverage results with an optimised (non-Debug) build may be misleading"
+    )
 endif() # NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG)
 
 # Defines a target for running and collection code coverage information
@@ -299,7 +330,13 @@ function(setup_target_for_coverage_gcovr)
     set(options NONE)
     set(oneValueArgs BASE_DIRECTORY NAME FORMAT)
     set(multiValueArgs EXCLUDE EXECUTABLE EXECUTABLE_ARGS DEPENDENCIES)
-    cmake_parse_arguments(Coverage "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
+    cmake_parse_arguments(
+        Coverage
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
 
     if(NOT GCOV_TOOL)
         message(FATAL_ERROR "Could not find gcov or llvm-cov tool! Aborting...")
@@ -321,21 +358,33 @@ function(setup_target_for_coverage_gcovr)
     endif()
 
     if(NOT DEFINED Coverage_EXECUTABLE AND DEFINED Coverage_EXECUTABLE_ARGS)
-        message(FATAL_ERROR "EXECUTABLE_ARGS must not be set if EXECUTABLE is not set")
+        message(
+            FATAL_ERROR
+            "EXECUTABLE_ARGS must not be set if EXECUTABLE is not set"
+        )
     endif()
 
     if("--output" IN_LIST GCOVR_ADDITIONAL_ARGS)
-        message(FATAL_ERROR "Unsupported --output option detected in GCOVR_ADDITIONAL_ARGS! Aborting...")
+        message(
+            FATAL_ERROR
+            "Unsupported --output option detected in GCOVR_ADDITIONAL_ARGS! Aborting..."
+        )
     else()
-        if((Coverage_FORMAT STREQUAL "html-details")
-            OR (Coverage_FORMAT STREQUAL "html-nested"))
-            set(GCOVR_OUTPUT_FILE ${PROJECT_BINARY_DIR}/${Coverage_NAME}/index.html)
+        if(
+            (Coverage_FORMAT STREQUAL "html-details")
+            OR (Coverage_FORMAT STREQUAL "html-nested")
+        )
+            set(GCOVR_OUTPUT_FILE
+                ${PROJECT_BINARY_DIR}/${Coverage_NAME}/index.html
+            )
             set(GCOVR_CREATE_FOLDER ${PROJECT_BINARY_DIR}/${Coverage_NAME})
         elseif(Coverage_FORMAT STREQUAL "html-single")
             set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.html)
-        elseif((Coverage_FORMAT STREQUAL "json-summary")
+        elseif(
+            (Coverage_FORMAT STREQUAL "json-summary")
             OR (Coverage_FORMAT STREQUAL "json-details")
-            OR (Coverage_FORMAT STREQUAL "coveralls"))
+            OR (Coverage_FORMAT STREQUAL "coveralls")
+        )
             set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.json)
         elseif(Coverage_FORMAT STREQUAL "txt")
             set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.txt)
@@ -348,50 +397,65 @@ function(setup_target_for_coverage_gcovr)
         endif()
     endif()
 
-    if((Coverage_FORMAT STREQUAL "cobertura")
-        OR (Coverage_FORMAT STREQUAL "xml"))
-        list(APPEND GCOVR_ADDITIONAL_ARGS --cobertura "${GCOVR_OUTPUT_FILE}" )
-        list(APPEND GCOVR_ADDITIONAL_ARGS --cobertura-pretty )
+    if(
+        (Coverage_FORMAT STREQUAL "cobertura")
+        OR (Coverage_FORMAT STREQUAL "xml")
+    )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --cobertura "${GCOVR_OUTPUT_FILE}")
+        list(APPEND GCOVR_ADDITIONAL_ARGS --cobertura-pretty)
         set(Coverage_FORMAT cobertura) # overwrite xml
     elseif(Coverage_FORMAT STREQUAL "sonarqube")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --sonarqube "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --sonarqube "${GCOVR_OUTPUT_FILE}")
     elseif(Coverage_FORMAT STREQUAL "jacoco")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --jacoco "${GCOVR_OUTPUT_FILE}" )
-        list(APPEND GCOVR_ADDITIONAL_ARGS --jacoco-pretty )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --jacoco "${GCOVR_OUTPUT_FILE}")
+        list(APPEND GCOVR_ADDITIONAL_ARGS --jacoco-pretty)
     elseif(Coverage_FORMAT STREQUAL "clover")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --clover "${GCOVR_OUTPUT_FILE}" )
-        list(APPEND GCOVR_ADDITIONAL_ARGS --clover-pretty )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --clover "${GCOVR_OUTPUT_FILE}")
+        list(APPEND GCOVR_ADDITIONAL_ARGS --clover-pretty)
     elseif(Coverage_FORMAT STREQUAL "lcov")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --lcov "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --lcov "${GCOVR_OUTPUT_FILE}")
     elseif(Coverage_FORMAT STREQUAL "json-summary")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --json-summary "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --json-summary "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --json-summary-pretty)
     elseif(Coverage_FORMAT STREQUAL "json-details")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --json "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --json "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --json-pretty)
     elseif(Coverage_FORMAT STREQUAL "coveralls")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --coveralls "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --coveralls "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --coveralls-pretty)
     elseif(Coverage_FORMAT STREQUAL "csv")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --csv "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --csv "${GCOVR_OUTPUT_FILE}")
     elseif(Coverage_FORMAT STREQUAL "txt")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --txt "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --txt "${GCOVR_OUTPUT_FILE}")
     elseif(Coverage_FORMAT STREQUAL "html-single")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --html "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --html "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --html-self-contained)
     elseif(Coverage_FORMAT STREQUAL "html-nested")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --html-nested "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --html-nested "${GCOVR_OUTPUT_FILE}")
     elseif(Coverage_FORMAT STREQUAL "html-details")
-        list(APPEND GCOVR_ADDITIONAL_ARGS --html-details "${GCOVR_OUTPUT_FILE}" )
+        list(APPEND GCOVR_ADDITIONAL_ARGS --html-details "${GCOVR_OUTPUT_FILE}")
     else()
-        message(FATAL_ERROR "Unsupported output style ${Coverage_FORMAT}! Aborting...")
+        message(
+            FATAL_ERROR
+            "Unsupported output style ${Coverage_FORMAT}! Aborting..."
+        )
     endif()
 
     # Collect excludes (CMake 3.4+: Also compute absolute paths)
     set(GCOVR_EXCLUDES "")
-    foreach(EXCLUDE ${Coverage_EXCLUDE} ${COVERAGE_EXCLUDES} ${COVERAGE_GCOVR_EXCLUDES})
+    foreach(
+        EXCLUDE
+        ${Coverage_EXCLUDE}
+        ${COVERAGE_EXCLUDES}
+        ${COVERAGE_GCOVR_EXCLUDES}
+    )
         if(CMAKE_VERSION VERSION_GREATER 3.4)
-            get_filename_component(EXCLUDE ${EXCLUDE} ABSOLUTE BASE_DIR ${BASEDIR})
+            get_filename_component(
+                EXCLUDE
+                ${EXCLUDE}
+                ABSOLUTE
+                BASE_DIR ${BASEDIR}
+            )
         endif()
         list(APPEND GCOVR_EXCLUDES "${EXCLUDE}")
     endforeach()
@@ -409,22 +473,29 @@ function(setup_target_for_coverage_gcovr)
     # before running the coverage target NAME
     if(DEFINED Coverage_EXECUTABLE)
         set(GCOVR_EXEC_TESTS_CMD
-            ${Coverage_EXECUTABLE} ${Coverage_EXECUTABLE_ARGS}
+            ${Coverage_EXECUTABLE}
+            ${Coverage_EXECUTABLE_ARGS}
         )
     endif()
 
     # Create folder
     if(DEFINED GCOVR_CREATE_FOLDER)
         set(GCOVR_FOLDER_CMD
-            ${CMAKE_COMMAND} -E make_directory ${GCOVR_CREATE_FOLDER})
+            ${CMAKE_COMMAND}
+            -E
+            make_directory
+            ${GCOVR_CREATE_FOLDER}
+        )
     endif()
 
     # Running gcovr
     set(GCOVR_CMD
         ${GCOVR_PATH}
-        --gcov-executable ${GCOV_TOOL}
+        --gcov-executable
+        ${GCOV_TOOL}
         --gcov-ignore-parse-errors=negative_hits.warn_once_per_file
-        -r ${BASEDIR}
+        -r
+        ${BASEDIR}
         ${GCOVR_ADDITIONAL_ARGS}
         ${GCOVR_EXCLUDE_ARGS}
         --object-directory=${PROJECT_BINARY_DIR}
@@ -435,13 +506,23 @@ function(setup_target_for_coverage_gcovr)
 
         if(NOT "${GCOVR_EXEC_TESTS_CMD}" STREQUAL "")
             message(STATUS "Command to run tests: ")
-            string(REPLACE ";" " " GCOVR_EXEC_TESTS_CMD_SPACED "${GCOVR_EXEC_TESTS_CMD}")
+            string(
+                REPLACE ";"
+                " "
+                GCOVR_EXEC_TESTS_CMD_SPACED
+                "${GCOVR_EXEC_TESTS_CMD}"
+            )
             message(STATUS "${GCOVR_EXEC_TESTS_CMD_SPACED}")
         endif()
 
         if(NOT "${GCOVR_FOLDER_CMD}" STREQUAL "")
             message(STATUS "Command to create a folder: ")
-            string(REPLACE ";" " " GCOVR_FOLDER_CMD_SPACED "${GCOVR_FOLDER_CMD}")
+            string(
+                REPLACE ";"
+                " "
+                GCOVR_FOLDER_CMD_SPACED
+                "${GCOVR_FOLDER_CMD}"
+            )
             message(STATUS "${GCOVR_FOLDER_CMD_SPACED}")
         endif()
 
@@ -450,11 +531,11 @@ function(setup_target_for_coverage_gcovr)
         message(STATUS "${GCOVR_CMD_SPACED}")
     endif()
 
-    add_custom_target(${Coverage_NAME}
+    add_custom_target(
+        ${Coverage_NAME}
         COMMAND ${GCOVR_EXEC_TESTS_CMD}
         COMMAND ${GCOVR_FOLDER_CMD}
         COMMAND ${GCOVR_CMD}
-
         BYPRODUCTS ${GCOVR_OUTPUT_FILE}
         WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
         DEPENDS ${Coverage_DEPENDENCIES}
@@ -463,25 +544,49 @@ function(setup_target_for_coverage_gcovr)
     )
 
     # Show info where to find the report
-    add_custom_command(TARGET ${Coverage_NAME} POST_BUILD
+    add_custom_command(
+        TARGET ${Coverage_NAME}
+        POST_BUILD
         COMMAND echo
-        COMMENT "Code coverage report saved in ${GCOVR_OUTPUT_FILE} formatted as ${Coverage_FORMAT}"
+        COMMENT
+            "Code coverage report saved in ${GCOVR_OUTPUT_FILE} formatted as ${Coverage_FORMAT}"
     )
 endfunction() # setup_target_for_coverage_gcovr
 
 function(add_code_coverage_to_target name scope)
-    separate_arguments(COVERAGE_CXX_COMPILER_FLAGS NATIVE_COMMAND "${COVERAGE_CXX_COMPILER_FLAGS}")
-    separate_arguments(COVERAGE_C_COMPILER_FLAGS NATIVE_COMMAND "${COVERAGE_C_COMPILER_FLAGS}")
-    separate_arguments(COVERAGE_CXX_LINKER_FLAGS NATIVE_COMMAND "${COVERAGE_CXX_LINKER_FLAGS}")
-    separate_arguments(COVERAGE_C_LINKER_FLAGS NATIVE_COMMAND "${COVERAGE_C_LINKER_FLAGS}")
+    separate_arguments(
+        COVERAGE_CXX_COMPILER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_CXX_COMPILER_FLAGS}"
+    )
+    separate_arguments(
+        COVERAGE_C_COMPILER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_C_COMPILER_FLAGS}"
+    )
+    separate_arguments(
+        COVERAGE_CXX_LINKER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_CXX_LINKER_FLAGS}"
+    )
+    separate_arguments(
+        COVERAGE_C_LINKER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_C_LINKER_FLAGS}"
+    )
 
     # Add compiler options to the target
-    target_compile_options(${name} ${scope}
-            $<$<COMPILE_LANGUAGE:CXX>:${COVERAGE_CXX_COMPILER_FLAGS}>
-            $<$<COMPILE_LANGUAGE:C>:${COVERAGE_C_COMPILER_FLAGS}>)
+    target_compile_options(
+        ${name}
+        ${scope}
+        $<$<COMPILE_LANGUAGE:CXX>:${COVERAGE_CXX_COMPILER_FLAGS}>
+        $<$<COMPILE_LANGUAGE:C>:${COVERAGE_C_COMPILER_FLAGS}>
+    )
 
-    target_link_libraries (${name} ${scope}
-            $<$<LINK_LANGUAGE:CXX>:${COVERAGE_CXX_LINKER_FLAGS} gcov>
-            $<$<LINK_LANGUAGE:C>:${COVERAGE_C_LINKER_FLAGS} gcov>
+    target_link_libraries(
+        ${name}
+        ${scope}
+        $<$<LINK_LANGUAGE:CXX>:${COVERAGE_CXX_LINKER_FLAGS}>
+        $<$<LINK_LANGUAGE:C>:${COVERAGE_C_LINKER_FLAGS}>
     )
 endfunction() # add_code_coverage_to_target

cmake/CompilationEnv.cmake

@@ -1,8 +1,7 @@
- # Shared detection of compiler, operating system, and architecture.
- #
- # This module centralizes environment detection so that other
- # CMake modules can use the same variables instead of repeating
- # checks on CMAKE_* and built-in platform variables.
+# Shared detection of compiler, operating system, and architecture.
+#
+# This module centralizes environment detection so that other CMake modules can use the same variables instead of
+# repeating checks on CMAKE_* and built-in platform variables.
 
 # Only run once per configure step.
 include_guard(GLOBAL)
@@ -13,17 +12,22 @@ include_guard(GLOBAL)
 set(is_clang FALSE)
 set(is_gcc FALSE)
 set(is_msvc FALSE)
+set(is_xcode FALSE)
 
 if(CMAKE_CXX_COMPILER_ID MATCHES ".*Clang") # Clang or AppleClang
-  set(is_clang TRUE)
+    set(is_clang TRUE)
 elseif(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-  set(is_gcc TRUE)
+    set(is_gcc TRUE)
 elseif(MSVC)
-  set(is_msvc TRUE)
+    set(is_msvc TRUE)
 else()
-  message(FATAL_ERROR "Unsupported C++ compiler: ${CMAKE_CXX_COMPILER_ID}")
+    message(FATAL_ERROR "Unsupported C++ compiler: ${CMAKE_CXX_COMPILER_ID}")
 endif()
 
+# Xcode generator detection
+if(CMAKE_GENERATOR STREQUAL "Xcode")
+    set(is_xcode TRUE)
+endif()
 
 # --------------------------------------------------------------------
 # Operating system detection
@@ -33,11 +37,11 @@ set(is_windows FALSE)
 set(is_macos FALSE)
 
 if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
-  set(is_linux TRUE)
+    set(is_linux TRUE)
 elseif(CMAKE_SYSTEM_NAME STREQUAL "Windows")
-  set(is_windows TRUE)
+    set(is_windows TRUE)
 elseif(CMAKE_SYSTEM_NAME STREQUAL "Darwin")
-  set(is_macos TRUE)
+    set(is_macos TRUE)
 endif()
 
 # --------------------------------------------------------------------
@@ -46,9 +50,9 @@ endif()
 set(is_amd64 FALSE)
 set(is_arm64 FALSE)
 if(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64|AMD64")
-  set(is_amd64 TRUE)
-elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
-  set(is_arm64 TRUE)
+    set(is_amd64 TRUE)
+elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64|ARM64")
+    set(is_arm64 TRUE)
 else()
-  message(FATAL_ERROR "Unknown architecture: ${CMAKE_SYSTEM_PROCESSOR}")
+    message(FATAL_ERROR "Unknown architecture: ${CMAKE_SYSTEM_PROCESSOR}")
 endif()

cmake/GitInfo.cmake

@@ -0,0 +1,28 @@
+include_guard()
+
+set(GIT_BUILD_BRANCH "")
+set(GIT_COMMIT_HASH "")
+
+find_package(Git)
+if(NOT Git_FOUND)
+    message(WARNING "Git not found. Git branch and commit hash will be empty.")
+    return()
+endif()
+
+set(GIT_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/.git)
+
+execute_process(
+    COMMAND
+        ${GIT_EXECUTABLE} --git-dir=${GIT_DIRECTORY} rev-parse --abbrev-ref HEAD
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+    OUTPUT_VARIABLE GIT_BUILD_BRANCH
+)
+
+execute_process(
+    COMMAND ${GIT_EXECUTABLE} --git-dir=${GIT_DIRECTORY} rev-parse HEAD
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+    OUTPUT_VARIABLE GIT_COMMIT_HASH
+)
+
+message(STATUS "Git branch: ${GIT_BUILD_BRANCH}")
+message(STATUS "Git commit hash: ${GIT_COMMIT_HASH}")

cmake/XrplAddTest.cmake

@@ -1,25 +1,22 @@
 include(isolate_headers)
 
 function(xrpl_add_test name)
-  set(target ${PROJECT_NAME}.test.${name})
+    set(target ${PROJECT_NAME}.test.${name})
 
-  file(GLOB_RECURSE sources CONFIGURE_DEPENDS
-  "${CMAKE_CURRENT_SOURCE_DIR}/${name}/*.cpp"
-  "${CMAKE_CURRENT_SOURCE_DIR}/${name}.cpp"
-  )
-  add_executable(${target} ${ARGN} ${sources})
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}/*.cpp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}.cpp"
+    )
+    add_executable(${target} ${ARGN} ${sources})
 
-  isolate_headers(
-    ${target}
-    "${CMAKE_SOURCE_DIR}"
-    "${CMAKE_SOURCE_DIR}/tests/${name}"
-    PRIVATE
-  )
+    isolate_headers(
+        ${target}
+        "${CMAKE_SOURCE_DIR}"
+        "${CMAKE_SOURCE_DIR}/tests/${name}"
+        PRIVATE
+    )
 
-  # Make sure the test isn't optimized away in unity builds
-  set_target_properties(${target} PROPERTIES
-    UNITY_BUILD_MODE GROUP
-    UNITY_BUILD_BATCH_SIZE 0)  # Adjust as needed
-
-  add_test(NAME ${target} COMMAND ${target})
+    add_test(NAME ${target} COMMAND ${target})
 endfunction()

cmake/XrplCompiler.cmake

@@ -8,153 +8,192 @@ include(CompilationEnv)
    TODO some/most of these common settings belong in a
    toolchain file, especially the ABI-impacting ones
 #]=========================================================]
-add_library (common INTERFACE)
-add_library (Xrpl::common ALIAS common)
+add_library(common INTERFACE)
+add_library(Xrpl::common ALIAS common)
 include(XrplSanitizers)
 # add a single global dependency on this interface lib
-link_libraries (Xrpl::common)
+link_libraries(Xrpl::common)
 # Respect CMAKE_POSITION_INDEPENDENT_CODE setting (may be set by Conan toolchain)
 if(NOT DEFINED CMAKE_POSITION_INDEPENDENT_CODE)
-  set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+    set(CMAKE_POSITION_INDEPENDENT_CODE ON)
 endif()
-set_target_properties (common
-  PROPERTIES INTERFACE_POSITION_INDEPENDENT_CODE ${CMAKE_POSITION_INDEPENDENT_CODE})
+set_target_properties(
+    common
+    PROPERTIES
+        INTERFACE_POSITION_INDEPENDENT_CODE ${CMAKE_POSITION_INDEPENDENT_CODE}
+)
 set(CMAKE_CXX_EXTENSIONS OFF)
-target_compile_definitions (common
-  INTERFACE
-    $<$<CONFIG:Debug>:DEBUG _DEBUG>
-    #[===[
+target_compile_definitions(
+    common
+    INTERFACE
+        $<$<CONFIG:Debug>:DEBUG
+        _DEBUG>
+        #[===[
     NOTE: CMAKE release builds already have NDEBUG defined, so no need to add it
     explicitly except for the special case of (profile ON) and (assert OFF).
     Presumably this is because we don't want profile builds asserting unless
     asserts were specifically requested.
     ]===]
-    $<$<AND:$<BOOL:${profile}>,$<NOT:$<BOOL:${assert}>>>:NDEBUG>
-    # TODO: Remove once we have migrated functions from OpenSSL 1.x to 3.x.
-    OPENSSL_SUPPRESS_DEPRECATED
+        $<$<AND:$<BOOL:${profile}>,$<NOT:$<BOOL:${assert}>>>:NDEBUG>
+        # TODO: Remove once we have migrated functions from OpenSSL 1.x to 3.x.
+        OPENSSL_SUPPRESS_DEPRECATED
 )
 
-if (MSVC)
-  # remove existing exception flag since we set it to -EHa
-  string (REGEX REPLACE "[-/]EH[a-z]+" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
+if(MSVC)
+    # remove existing exception flag since we set it to -EHa
+    string(REGEX REPLACE "[-/]EH[a-z]+" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
 
-  foreach (var_
-      CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE
-      CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE)
+    foreach(
+        var_
+        CMAKE_C_FLAGS_DEBUG
+        CMAKE_C_FLAGS_RELEASE
+        CMAKE_CXX_FLAGS_DEBUG
+        CMAKE_CXX_FLAGS_RELEASE
+    )
+        # also remove dynamic runtime
+        string(REGEX REPLACE "[-/]MD[d]*" " " ${var_} "${${var_}}")
 
-    # also remove dynamic runtime
-    string (REGEX REPLACE "[-/]MD[d]*" " " ${var_} "${${var_}}")
+        # /ZI (Edit & Continue debugging information) is incompatible with Gy-
+        string(REPLACE "/ZI" "/Zi" ${var_} "${${var_}}")
 
-    # /ZI (Edit & Continue debugging information) is incompatible with Gy-
-    string (REPLACE "/ZI" "/Zi" ${var_} "${${var_}}")
+        # omit debug info completely under CI (not needed)
+        if(is_ci)
+            string(REPLACE "/Zi" " " ${var_} "${${var_}}")
+            string(REPLACE "/Z7" " " ${var_} "${${var_}}")
+        endif()
+    endforeach()
 
-    # omit debug info completely under CI (not needed)
-    if (is_ci)
-      string (REPLACE "/Zi" " " ${var_} "${${var_}}")
-      string (REPLACE "/Z7" " " ${var_} "${${var_}}")
-    endif ()
-  endforeach ()
-
-  target_compile_options (common
-    INTERFACE
-      -bigobj            # Increase object file max size
-      -fp:precise        # Floating point behavior
-      -Gd                # __cdecl calling convention
-      -Gm-               # Minimal rebuild: disabled
-      -Gy-               # Function level linking: disabled
-      -MP                # Multiprocessor compilation
-      -openmp-           # pragma omp: disabled
-      -errorReport:none  # No error reporting to Internet
-      -nologo            # Suppress login banner
-      -wd4018            # Disable signed/unsigned comparison warnings
-      -wd4244            # Disable float to int possible loss of data warnings
-      -wd4267            # Disable size_t to T possible loss of data warnings
-      -wd4800            # Disable C4800(int to bool performance)
-      -wd4503            # Decorated name length exceeded, name was truncated
-      $<$<COMPILE_LANGUAGE:CXX>:
-        -EHa
-        -GR
-      >
-      $<$<CONFIG:Release>:-Ox>
-      $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:
-        -GS
-        -Zc:forScope
-      >
-      # static runtime
-      $<$<CONFIG:Debug>:-MTd>
-      $<$<NOT:$<CONFIG:Debug>>:-MT>
-      $<$<BOOL:${werr}>:-WX>
-      )
-  target_compile_definitions (common
-    INTERFACE
-      _WIN32_WINNT=0x6000
-      _SCL_SECURE_NO_WARNINGS
-      _CRT_SECURE_NO_WARNINGS
-      WIN32_CONSOLE
-      WIN32_LEAN_AND_MEAN
-      NOMINMAX
-      # TODO: Resolve these warnings, don't just silence them
-      _SILENCE_ALL_CXX17_DEPRECATION_WARNINGS
-      $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:_CRTDBG_MAP_ALLOC>)
-  target_link_libraries (common
-    INTERFACE
-      -errorreport:none
-      -machine:X64)
-else ()
-  target_compile_options (common
-    INTERFACE
-      -Wall
-      -Wdeprecated
-      $<$<BOOL:${is_clang}>:-Wno-deprecated-declarations>
-      $<$<BOOL:${wextra}>:-Wextra -Wno-unused-parameter>
-      $<$<BOOL:${werr}>:-Werror>
-      -fstack-protector
-      -Wno-sign-compare
-      -Wno-unused-but-set-variable
-      $<$<NOT:$<CONFIG:Debug>>:-fno-strict-aliasing>
-      # tweak gcc optimization for debug
-      $<$<AND:$<BOOL:${is_gcc}>,$<CONFIG:Debug>>:-O0>
-      # Add debug symbols to release config
-      $<$<CONFIG:Release>:-g>)
-  target_link_libraries (common
-    INTERFACE
-      -rdynamic
-      $<$<BOOL:${is_linux}>:-Wl,-z,relro,-z,now,--build-id>
-      # link to static libc/c++ iff:
-      #   * static option set and
-      #   * NOT APPLE (AppleClang does not support static libc/c++) and
-      #   * NOT SANITIZERS (sanitizers typically don't work with static libc/c++)
-      $<$<AND:$<BOOL:${static}>,$<NOT:$<BOOL:${APPLE}>>,$<NOT:$<BOOL:${SANITIZERS_ENABLED}>>>:
-      -static-libstdc++
-      -static-libgcc
-      >)
-endif ()
+    target_compile_options(
+        common
+        INTERFACE # Increase object file max size
+            -bigobj
+            # Floating point behavior
+            -fp:precise
+            # __cdecl calling convention
+            -Gd
+            # Minimal rebuild: disabled
+            -Gm-
+            # Function level linking: disabled
+            -Gy-
+            # Multiprocessor compilation
+            -MP
+            # pragma omp: disabled
+            -openmp-
+            # No error reporting to Internet
+            -errorReport:none
+            # Suppress login banner
+            -nologo
+            # Disable signed/unsigned comparison warnings
+            -wd4018
+            # Disable float to int possible loss of data warnings
+            -wd4244
+            # Disable size_t to T possible loss of data warnings
+            -wd4267
+            # Disable C4800(int to bool performance)
+            -wd4800
+            # Decorated name length exceeded, name was truncated
+            -wd4503
+            $<$<COMPILE_LANGUAGE:CXX>:
+            -EHa
+            -GR
+            >
+            $<$<CONFIG:Release>:-Ox>
+            $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:
+            -GS
+            -Zc:forScope
+            >
+            # static runtime
+            $<$<CONFIG:Debug>:-MTd>
+            $<$<NOT:$<CONFIG:Debug>>:-MT>
+            $<$<BOOL:${werr}>:-WX>
+    )
+    target_compile_definitions(
+        common
+        INTERFACE
+            _WIN32_WINNT=0x6000
+            _SCL_SECURE_NO_WARNINGS
+            _CRT_SECURE_NO_WARNINGS
+            WIN32_CONSOLE
+            WIN32_LEAN_AND_MEAN
+            NOMINMAX
+            # TODO: Resolve these warnings, don't just silence them
+            _SILENCE_ALL_CXX17_DEPRECATION_WARNINGS
+            $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>,$<NOT:$<BOOL:${is_ci}>>>:_CRTDBG_MAP_ALLOC>
+    )
+    target_link_libraries(common INTERFACE -errorreport:none -machine:X64)
+else()
+    target_compile_options(
+        common
+        INTERFACE
+            -Wall
+            -Wdeprecated
+            $<$<BOOL:${is_clang}>:-Wno-deprecated-declarations>
+            $<$<BOOL:${wextra}>:-Wextra
+            -Wno-unused-parameter>
+            $<$<BOOL:${werr}>:-Werror>
+            -fstack-protector
+            -Wno-sign-compare
+            -Wno-unused-but-set-variable
+            $<$<NOT:$<CONFIG:Debug>>:-fno-strict-aliasing>
+            # tweak gcc optimization for debug
+            $<$<AND:$<BOOL:${is_gcc}>,$<CONFIG:Debug>>:-O0>
+            # Add debug symbols to release config
+            $<$<CONFIG:Release>:-g>
+    )
+    target_link_libraries(
+        common
+        INTERFACE
+            -rdynamic
+            $<$<BOOL:${is_linux}>:-Wl,-z,relro,-z,now,--build-id>
+            # link to static libc/c++ iff: * static option set and * NOT APPLE (AppleClang does not support static
+            # libc/c++) and * NOT SANITIZERS (sanitizers typically don't work with static libc/c++)
+            $<$<AND:$<BOOL:${static}>,$<NOT:$<BOOL:${APPLE}>>,$<NOT:$<BOOL:${SANITIZERS_ENABLED}>>>:
+            -static-libstdc++
+            -static-libgcc
+            >
+    )
+endif()
 
 # Antithesis instrumentation will only be built and deployed using machines running Linux.
-if (voidstar)
-  if (NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
-    message(FATAL_ERROR "Antithesis instrumentation requires Debug build type, aborting...")
-  elseif (NOT is_linux)
-    message(FATAL_ERROR "Antithesis instrumentation requires Linux, aborting...")
-  elseif (NOT (is_clang AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 16.0))
-    message(FATAL_ERROR "Antithesis instrumentation requires Clang version 16 or later, aborting...")
-  endif ()
-endif ()
+if(voidstar)
+    if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
+        message(
+            FATAL_ERROR
+            "Antithesis instrumentation requires Debug build type, aborting..."
+        )
+    elseif(NOT is_linux)
+        message(
+            FATAL_ERROR
+            "Antithesis instrumentation requires Linux, aborting..."
+        )
+    elseif(
+        NOT (is_clang AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 16.0)
+    )
+        message(
+            FATAL_ERROR
+            "Antithesis instrumentation requires Clang version 16 or later, aborting..."
+        )
+    endif()
+endif()
 
-if (use_mold)
-  # use mold linker if available
-  execute_process (
-    COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=mold -Wl,--version
-    ERROR_QUIET OUTPUT_VARIABLE LD_VERSION)
-  if ("${LD_VERSION}" MATCHES "mold")
-    target_link_libraries (common INTERFACE -fuse-ld=mold)
-  endif ()
-  unset (LD_VERSION)
-elseif (use_gold AND is_gcc)
-  # use gold linker if available
-  execute_process (
-    COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=gold -Wl,--version
-    ERROR_QUIET OUTPUT_VARIABLE LD_VERSION)
+if(use_mold)
+    # use mold linker if available
+    execute_process(
+        COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=mold -Wl,--version
+        ERROR_QUIET
+        OUTPUT_VARIABLE LD_VERSION
+    )
+    if("${LD_VERSION}" MATCHES "mold")
+        target_link_libraries(common INTERFACE -fuse-ld=mold)
+    endif()
+    unset(LD_VERSION)
+elseif(use_gold AND is_gcc)
+    # use gold linker if available
+    execute_process(
+        COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=gold -Wl,--version
+        ERROR_QUIET
+        OUTPUT_VARIABLE LD_VERSION
+    )
     #[=========================================================[
        NOTE: THE gold linker inserts -rpath as DT_RUNPATH by
        default instead of DT_RPATH, so you might have slightly
@@ -168,34 +207,37 @@ elseif (use_gold AND is_gcc)
        disabling would be to figure out all the settings
        required to make gold play nicely with jemalloc.
     #]=========================================================]
-  if (("${LD_VERSION}" MATCHES "GNU gold") AND (NOT jemalloc))
-    target_link_libraries (common
-      INTERFACE
-        -fuse-ld=gold
-        -Wl,--no-as-needed
-        #[=========================================================[
+    if(("${LD_VERSION}" MATCHES "GNU gold") AND (NOT jemalloc))
+        target_link_libraries(
+            common
+            INTERFACE
+                -fuse-ld=gold
+                -Wl,--no-as-needed
+                #[=========================================================[
            see https://bugs.launchpad.net/ubuntu/+source/eglibc/+bug/1253638/comments/5
            DT_RUNPATH does not work great for transitive
            dependencies (of which boost has a few) - so just
            switch to DT_RPATH if doing dynamic linking with gold
         #]=========================================================]
-        $<$<NOT:$<BOOL:${static}>>:-Wl,--disable-new-dtags>)
-  endif ()
-  unset (LD_VERSION)
-elseif (use_lld)
-  # use lld linker if available
-  execute_process (
-    COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=lld -Wl,--version
-    ERROR_QUIET OUTPUT_VARIABLE LD_VERSION)
-  if ("${LD_VERSION}" MATCHES "LLD")
-    target_link_libraries (common INTERFACE -fuse-ld=lld)
-  endif ()
-  unset (LD_VERSION)
+                $<$<NOT:$<BOOL:${static}>>:-Wl,--disable-new-dtags>
+        )
+    endif()
+    unset(LD_VERSION)
+elseif(use_lld)
+    # use lld linker if available
+    execute_process(
+        COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=lld -Wl,--version
+        ERROR_QUIET
+        OUTPUT_VARIABLE LD_VERSION
+    )
+    if("${LD_VERSION}" MATCHES "LLD")
+        target_link_libraries(common INTERFACE -fuse-ld=lld)
+    endif()
+    unset(LD_VERSION)
 endif()
 
-
-if (assert)
-  foreach (var_ CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_RELEASE)
-    STRING (REGEX REPLACE "[-/]DNDEBUG" "" ${var_} "${${var_}}")
-  endforeach ()
-endif ()
+if(assert)
+    foreach(var_ CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_RELEASE)
+        string(REGEX REPLACE "[-/]DNDEBUG" "" ${var_} "${${var_}}")
+    endforeach()
+endif()

cmake/XrplConfig.cmake

@@ -1,54 +0,0 @@
-include (CMakeFindDependencyMacro)
-# need to represent system dependencies of the lib here
-#[=========================================================[
-  Boost
-#]=========================================================]
-if (static OR APPLE OR MSVC)
-  set (Boost_USE_STATIC_LIBS ON)
-endif ()
-set (Boost_USE_MULTITHREADED ON)
-if (static OR MSVC)
-  set (Boost_USE_STATIC_RUNTIME ON)
-else ()
-  set (Boost_USE_STATIC_RUNTIME OFF)
-endif ()
-find_dependency (Boost
-  COMPONENTS
-    chrono
-    container
-    context
-    coroutine
-    date_time
-    filesystem
-    program_options
-    regex
-    system
-    thread)
-#[=========================================================[
-  OpenSSL
-#]=========================================================]
-if (NOT DEFINED OPENSSL_ROOT_DIR)
-  if (DEFINED ENV{OPENSSL_ROOT})
-    set (OPENSSL_ROOT_DIR $ENV{OPENSSL_ROOT})
-  elseif (APPLE)
-    find_program (homebrew brew)
-    if (homebrew)
-      execute_process (COMMAND ${homebrew} --prefix openssl
-        OUTPUT_VARIABLE OPENSSL_ROOT_DIR
-        OUTPUT_STRIP_TRAILING_WHITESPACE)
-    endif ()
-  endif ()
-  file (TO_CMAKE_PATH "${OPENSSL_ROOT_DIR}" OPENSSL_ROOT_DIR)
-endif ()
-
-if (static OR APPLE OR MSVC)
-  set (OPENSSL_USE_STATIC_LIBS ON)
-endif ()
-set (OPENSSL_MSVC_STATIC_RT ON)
-find_dependency (OpenSSL REQUIRED)
-find_dependency (ZLIB)
-find_dependency (date)
-if (TARGET ZLIB::ZLIB)
-  set_target_properties(OpenSSL::Crypto PROPERTIES
-    INTERFACE_LINK_LIBRARIES ZLIB::ZLIB)
-endif ()

cmake/XrplCore.cmake

@@ -10,62 +10,66 @@ include(target_protobuf_sources)
 # so we just build them as a separate library.
 add_library(xrpl.libpb)
 set_target_properties(xrpl.libpb PROPERTIES UNITY_BUILD OFF)
-target_protobuf_sources(xrpl.libpb xrpl/proto
-  LANGUAGE cpp
-  IMPORT_DIRS include/xrpl/proto
-  PROTOS include/xrpl/proto/xrpl.proto
+target_protobuf_sources(
+    xrpl.libpb
+    xrpl/proto
+    LANGUAGE cpp
+    IMPORT_DIRS include/xrpl/proto
+    PROTOS include/xrpl/proto/xrpl.proto
 )
 
 file(GLOB_RECURSE protos "include/xrpl/proto/org/*.proto")
-target_protobuf_sources(xrpl.libpb xrpl/proto
-  LANGUAGE cpp
-  IMPORT_DIRS include/xrpl/proto
-  PROTOS "${protos}"
+target_protobuf_sources(
+    xrpl.libpb
+    xrpl/proto
+    LANGUAGE cpp
+    IMPORT_DIRS include/xrpl/proto
+    PROTOS "${protos}"
 )
-target_protobuf_sources(xrpl.libpb xrpl/proto
-  LANGUAGE grpc
-  IMPORT_DIRS include/xrpl/proto
-  PROTOS "${protos}"
-  PLUGIN protoc-gen-grpc=$<TARGET_FILE:gRPC::grpc_cpp_plugin>
-  GENERATE_EXTENSIONS .grpc.pb.h .grpc.pb.cc
+target_protobuf_sources(
+    xrpl.libpb
+    xrpl/proto
+    LANGUAGE grpc
+    IMPORT_DIRS include/xrpl/proto
+    PROTOS "${protos}"
+    PLUGIN protoc-gen-grpc=$<TARGET_FILE:gRPC::grpc_cpp_plugin>
+    GENERATE_EXTENSIONS .grpc.pb.h .grpc.pb.cc
 )
 
-target_compile_options(xrpl.libpb
-  PUBLIC
-    $<$<BOOL:${MSVC}>:-wd4996>
-    $<$<BOOL:${XCODE}>:
-      --system-header-prefix="google/protobuf"
-      -Wno-deprecated-dynamic-exception-spec
-    >
-  PRIVATE
-    $<$<BOOL:${MSVC}>:-wd4065>
-    $<$<NOT:$<BOOL:${MSVC}>>:-Wno-deprecated-declarations>
+target_compile_options(
+    xrpl.libpb
+    PUBLIC
+        $<$<BOOL:${is_msvc}>:-wd4996>
+        $<$<BOOL:${is_xcode}>:
+        --system-header-prefix="google/protobuf"
+        -Wno-deprecated-dynamic-exception-spec
+        >
+    PRIVATE
+        $<$<BOOL:${is_msvc}>:-wd4065>
+        $<$<NOT:$<BOOL:${is_msvc}>>:-Wno-deprecated-declarations>
 )
 
-target_link_libraries(xrpl.libpb
-  PUBLIC
-    protobuf::libprotobuf
-    gRPC::grpc++
-)
+target_link_libraries(xrpl.libpb PUBLIC protobuf::libprotobuf gRPC::grpc++)
 
 # TODO: Clean up the number of library targets later.
 add_library(xrpl.imports.main INTERFACE)
 
-target_link_libraries(xrpl.imports.main
-  INTERFACE
-    absl::random_random
-    date::date
-    ed25519::ed25519
-    LibArchive::LibArchive
-    OpenSSL::Crypto
-    Xrpl::boost
-    Xrpl::libs
-    Xrpl::opts
-    Xrpl::syslibs
-    secp256k1::secp256k1
-    xrpl.libpb
-    xxHash::xxhash
-    $<$<BOOL:${voidstar}>:antithesis-sdk-cpp>
+target_link_libraries(
+    xrpl.imports.main
+    INTERFACE
+        absl::random_random
+        date::date
+        ed25519::ed25519
+        LibArchive::LibArchive
+        OpenSSL::Crypto
+        Xrpl::boost
+        Xrpl::libs
+        Xrpl::opts
+        Xrpl::syslibs
+        secp256k1::secp256k1
+        xrpl.libpb
+        xxHash::xxhash
+        $<$<BOOL:${voidstar}>:antithesis-sdk-cpp>
 )
 
 include(add_module)
@@ -74,6 +78,23 @@ include(target_link_modules)
 # Level 01
 add_module(xrpl beast)
 target_link_libraries(xrpl.libxrpl.beast PUBLIC xrpl.imports.main)
+# OTelCollector in beast/insight uses OTel Metrics SDK when telemetry is enabled.
+if(telemetry)
+    target_link_libraries(
+        xrpl.libxrpl.beast
+        PUBLIC opentelemetry-cpp::opentelemetry-cpp
+    )
+endif()
+
+include(GitInfo)
+add_module(xrpl git)
+target_compile_definitions(
+    xrpl.libxrpl.git
+    PRIVATE
+        GIT_COMMIT_HASH="${GIT_COMMIT_HASH}"
+        GIT_BUILD_BRANCH="${GIT_BUILD_BRANCH}"
+)
+target_link_libraries(xrpl.libxrpl.git PUBLIC xrpl.imports.main)
 
 # Level 02
 add_module(xrpl basics)
@@ -88,80 +109,158 @@ target_link_libraries(xrpl.libxrpl.crypto PUBLIC xrpl.libxrpl.basics)
 
 # Level 04
 add_module(xrpl protocol)
-target_link_libraries(xrpl.libxrpl.protocol PUBLIC
-  xrpl.libxrpl.crypto
-  xrpl.libxrpl.json
+target_link_libraries(
+    xrpl.libxrpl.protocol
+    PUBLIC xrpl.libxrpl.crypto xrpl.libxrpl.git xrpl.libxrpl.json
 )
 
 # Level 05
-add_module(xrpl core)
-target_link_libraries(xrpl.libxrpl.core PUBLIC
-  xrpl.libxrpl.basics
-  xrpl.libxrpl.json
-  xrpl.libxrpl.protocol
+## Set up code generation for protocol_autogen module
+include(XrplProtocolAutogen)
+# Must call setup_protocol_autogen before add_module so that:
+# 1. Stale generated files are cleared before GLOB runs
+# 2. Output file list is known for custom commands
+setup_protocol_autogen()
+
+add_module(xrpl protocol_autogen)
+target_link_libraries(
+    xrpl.libxrpl.protocol_autogen
+    PUBLIC xrpl.libxrpl.protocol
 )
 
+# Ensure code generation runs before compiling protocol_autogen
+if(TARGET protocol_autogen_generate)
+    add_dependencies(xrpl.libxrpl.protocol_autogen protocol_autogen_generate)
+endif()
+
 # Level 06
-add_module(xrpl resource)
-target_link_libraries(xrpl.libxrpl.resource PUBLIC xrpl.libxrpl.protocol)
-
-# Level 07
-add_module(xrpl net)
-target_link_libraries(xrpl.libxrpl.net PUBLIC
-  xrpl.libxrpl.basics
-  xrpl.libxrpl.json
-  xrpl.libxrpl.protocol
-  xrpl.libxrpl.resource
-)
-
-add_module(xrpl server)
-target_link_libraries(xrpl.libxrpl.server PUBLIC xrpl.libxrpl.protocol)
-
-add_module(xrpl nodestore)
-target_link_libraries(xrpl.libxrpl.nodestore PUBLIC
+add_module(xrpl core)
+target_link_libraries(
+    xrpl.libxrpl.core
+    PUBLIC
         xrpl.libxrpl.basics
         xrpl.libxrpl.json
         xrpl.libxrpl.protocol
+        xrpl.libxrpl.protocol_autogen
+)
+
+# Level 07
+add_module(xrpl resource)
+target_link_libraries(xrpl.libxrpl.resource PUBLIC xrpl.libxrpl.protocol)
+
+# Level 08
+add_module(xrpl net)
+target_link_libraries(
+    xrpl.libxrpl.net
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.json
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.resource
+)
+
+add_module(xrpl nodestore)
+target_link_libraries(
+    xrpl.libxrpl.nodestore
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol
 )
 
 add_module(xrpl shamap)
-target_link_libraries(xrpl.libxrpl.shamap PUBLIC
+target_link_libraries(
+    xrpl.libxrpl.shamap
+    PUBLIC
         xrpl.libxrpl.basics
         xrpl.libxrpl.crypto
         xrpl.libxrpl.protocol
         xrpl.libxrpl.nodestore
 )
 
-add_module(xrpl ledger)
-target_link_libraries(xrpl.libxrpl.ledger PUBLIC
-  xrpl.libxrpl.basics
-  xrpl.libxrpl.json
-  xrpl.libxrpl.protocol
+add_module(xrpl rdb)
+target_link_libraries(
+    xrpl.libxrpl.rdb
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.core
 )
 
+add_module(xrpl server)
+target_link_libraries(
+    xrpl.libxrpl.server
+    PUBLIC
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.core
+        xrpl.libxrpl.rdb
+        xrpl.libxrpl.resource
+)
+
+add_module(xrpl conditions)
+target_link_libraries(xrpl.libxrpl.conditions PUBLIC xrpl.libxrpl.server)
+
+add_module(xrpl ledger)
+target_link_libraries(
+    xrpl.libxrpl.ledger
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.json
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.protocol_autogen
+        xrpl.libxrpl.rdb
+        xrpl.libxrpl.server
+        xrpl.libxrpl.shamap
+        xrpl.libxrpl.conditions
+)
+
+add_module(xrpl tx)
+target_link_libraries(xrpl.libxrpl.tx PUBLIC xrpl.libxrpl.ledger)
+
+# Telemetry module — OpenTelemetry distributed tracing support.
+# Sources: include/xrpl/telemetry/ (headers), src/libxrpl/telemetry/ (impl).
+# When telemetry=ON, links the Conan-provided umbrella target
+# opentelemetry-cpp::opentelemetry-cpp (individual component targets like
+# ::api, ::sdk are not available in the Conan package).
+add_module(xrpl telemetry)
+target_link_libraries(
+    xrpl.libxrpl.telemetry
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.beast
+)
+if(telemetry)
+    target_link_libraries(
+        xrpl.libxrpl.telemetry
+        PUBLIC opentelemetry-cpp::opentelemetry-cpp
+    )
+endif()
+
 add_library(xrpl.libxrpl)
 set_target_properties(xrpl.libxrpl PROPERTIES OUTPUT_NAME xrpl)
 
 add_library(xrpl::libxrpl ALIAS xrpl.libxrpl)
 
-file(GLOB_RECURSE sources CONFIGURE_DEPENDS
-  "${CMAKE_CURRENT_SOURCE_DIR}/src/libxrpl/*.cpp"
+file(
+    GLOB_RECURSE sources
+    CONFIGURE_DEPENDS
+    "${CMAKE_CURRENT_SOURCE_DIR}/src/libxrpl/*.cpp"
 )
 target_sources(xrpl.libxrpl PRIVATE ${sources})
 
-target_link_modules(xrpl PUBLIC
-  basics
-  beast
-  core
-  crypto
-  json
-  protocol
-  resource
-  server
-  nodestore
-  shamap
-  net
-  ledger
+target_link_modules(
+    xrpl
+    PUBLIC
+    basics
+    beast
+    conditions
+    core
+    crypto
+    git
+    json
+    ledger
+    net
+    nodestore
+    protocol
+    protocol_autogen
+    rdb
+    resource
+    server
+    shamap
+    telemetry
+    tx
 )
 
 # All headers in libxrpl are in modules.
@@ -174,62 +273,50 @@ target_link_modules(xrpl PUBLIC
 #     $<INSTALL_INTERFACE:include>)
 
 if(xrpld)
-  add_executable(xrpld)
-  if(tests)
-    target_compile_definitions(xrpld PUBLIC ENABLE_TESTS)
-    target_compile_definitions(xrpld PRIVATE
-                                       UNIT_TEST_REFERENCE_FEE=${UNIT_TEST_REFERENCE_FEE}
+    add_executable(xrpld)
+    if(tests)
+        target_compile_definitions(xrpld PUBLIC ENABLE_TESTS)
+        target_compile_definitions(
+            xrpld
+            PRIVATE UNIT_TEST_REFERENCE_FEE=${UNIT_TEST_REFERENCE_FEE}
+        )
+    endif()
+    target_include_directories(
+        xrpld
+        PRIVATE $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>
     )
-  endif()
-  target_include_directories(xrpld
-    PRIVATE
-      $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>
-  )
 
-  file(GLOB_RECURSE sources CONFIGURE_DEPENDS
-    "${CMAKE_CURRENT_SOURCE_DIR}/src/xrpld/*.cpp"
-  )
-  target_sources(xrpld PRIVATE ${sources})
-
-  if(tests)
-    file(GLOB_RECURSE sources CONFIGURE_DEPENDS
-      "${CMAKE_CURRENT_SOURCE_DIR}/src/test/*.cpp"
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/xrpld/*.cpp"
     )
     target_sources(xrpld PRIVATE ${sources})
-  endif()
 
-  target_link_libraries(xrpld
-    Xrpl::boost
-    Xrpl::opts
-    Xrpl::libs
-    xrpl.libxrpl
-  )
-  exclude_if_included(xrpld)
-  # define a macro for tests that might need to
-  # be excluded or run differently in CI environment
-  if(is_ci)
-    target_compile_definitions(xrpld PRIVATE XRPL_RUNNING_IN_CI)
-  endif ()
+    if(tests)
+        file(
+            GLOB_RECURSE sources
+            CONFIGURE_DEPENDS
+            "${CMAKE_CURRENT_SOURCE_DIR}/src/test/*.cpp"
+        )
+        target_sources(xrpld PRIVATE ${sources})
+    endif()
 
-  if(voidstar)
-    target_compile_options(xrpld
-      PRIVATE
-        -fsanitize-coverage=trace-pc-guard
-    )
-    # xrpld requires access to antithesis-sdk-cpp implementation file
-    # antithesis_instrumentation.h, which is not exported as INTERFACE
-    target_include_directories(xrpld
-      PRIVATE
-        ${CMAKE_SOURCE_DIR}/external/antithesis-sdk
-    )
-  endif()
+    target_link_libraries(xrpld Xrpl::boost Xrpl::opts Xrpl::libs xrpl.libxrpl)
+    exclude_if_included(xrpld)
+    # define a macro for tests that might need to
+    # be excluded or run differently in CI environment
+    if(is_ci)
+        target_compile_definitions(xrpld PRIVATE XRPL_RUNNING_IN_CI)
+    endif()
 
-  # any files that don't play well with unity should be added here
-  if(tests)
-    set_source_files_properties(
-      # these two seem to produce conflicts in beast teardown template methods
-      src/test/rpc/ValidatorRPC_test.cpp
-      src/test/ledger/Invariants_test.cpp
-      PROPERTIES SKIP_UNITY_BUILD_INCLUSION TRUE)
-  endif()
+    if(voidstar)
+        target_compile_options(xrpld PRIVATE -fsanitize-coverage=trace-pc-guard)
+        # xrpld requires access to antithesis-sdk-cpp implementation file
+        # antithesis_instrumentation.h, which is not exported as INTERFACE
+        target_include_directories(
+            xrpld
+            PRIVATE ${CMAKE_SOURCE_DIR}/external/antithesis-sdk
+        )
+    endif()
 endif()

cmake/XrplCov.cmake

@@ -3,12 +3,15 @@
 #]===================================================================]
 
 if(NOT coverage)
-  message(FATAL_ERROR "Code coverage not enabled! Aborting ...")
+    message(FATAL_ERROR "Code coverage not enabled! Aborting ...")
 endif()
 
 if(CMAKE_CXX_COMPILER_ID MATCHES "MSVC")
-  message(WARNING "Code coverage on Windows is not supported, ignoring 'coverage' flag")
-  return()
+    message(
+        WARNING
+        "Code coverage on Windows is not supported, ignoring 'coverage' flag"
+    )
+    return()
 endif()
 
 include(ProcessorCount)
@@ -16,26 +19,35 @@ ProcessorCount(PROCESSOR_COUNT)
 
 include(CodeCoverage)
 
-# The instructions for these commands come from the `CodeCoverage` module,
-# which was copied from https://github.com/bilke/cmake-modules, commit fb7d2a3,
-# then locally changed (see CHANGES: section in `CodeCoverage.cmake`)
+# The instructions for these commands come from the `CodeCoverage` module, which was copied from
+# https://github.com/bilke/cmake-modules, commit fb7d2a3, then locally changed (see CHANGES: section in
+# `CodeCoverage.cmake`)
 
 set(GCOVR_ADDITIONAL_ARGS ${coverage_extra_args})
 if(NOT GCOVR_ADDITIONAL_ARGS STREQUAL "")
-  separate_arguments(GCOVR_ADDITIONAL_ARGS)
+    separate_arguments(GCOVR_ADDITIONAL_ARGS)
 endif()
 
-list(APPEND GCOVR_ADDITIONAL_ARGS
-  --exclude-throw-branches
-  --exclude-noncode-lines
-  --exclude-unreachable-branches -s
-  -j ${PROCESSOR_COUNT})
+list(
+    APPEND GCOVR_ADDITIONAL_ARGS
+    --exclude-throw-branches
+    --exclude-noncode-lines
+    --exclude-unreachable-branches
+    -s
+    -j
+    ${PROCESSOR_COUNT}
+)
 
 setup_target_for_coverage_gcovr(
-  NAME coverage
-  FORMAT ${coverage_format}
-  EXCLUDE "src/test" "src/tests" "include/xrpl/beast/test" "include/xrpl/beast/unit_test" "${CMAKE_BINARY_DIR}/pb-xrpl.libpb"
-  DEPENDENCIES xrpld xrpl.tests
+    NAME coverage
+    FORMAT ${coverage_format}
+    EXCLUDE
+        "src/test"
+        "src/tests"
+        "include/xrpl/beast/test"
+        "include/xrpl/beast/unit_test"
+        "${CMAKE_BINARY_DIR}/pb-xrpl.libpb"
+    DEPENDENCIES xrpld xrpl.tests
 )
 
 add_code_coverage_to_target(opts INTERFACE)

cmake/XrplDocs.cmake

@@ -3,13 +3,13 @@
 #]===================================================================]
 
 if(NOT only_docs)
-  return()
+    return()
 endif()
 
 find_package(Doxygen)
 if(NOT TARGET Doxygen::doxygen)
-  message(STATUS "doxygen executable not found -- skipping docs target")
-  return()
+    message(STATUS "doxygen executable not found -- skipping docs target")
+    return()
 endif()
 
 set(doxygen_output_directory "${CMAKE_BINARY_DIR}/docs")
@@ -17,40 +17,44 @@ set(doxygen_include_path "${CMAKE_CURRENT_SOURCE_DIR}/src")
 set(doxygen_index_file "${doxygen_output_directory}/html/index.html")
 set(doxyfile "${CMAKE_CURRENT_SOURCE_DIR}/docs/Doxyfile")
 
-file(GLOB_RECURSE doxygen_input
-  docs/*.md
-  include/*.h
-  include/*.cpp
-  include/*.md
-  src/*.h
-  src/*.cpp
-  src/*.md
-  Builds/*.md
-  *.md)
-list(APPEND doxygen_input
-  external/README.md
-  )
+file(
+    GLOB_RECURSE doxygen_input
+    docs/*.md
+    include/*.h
+    include/*.cpp
+    include/*.md
+    src/*.h
+    src/*.cpp
+    src/*.md
+    Builds/*.md
+    *.md
+)
+list(APPEND doxygen_input external/README.md)
 set(dependencies "${doxygen_input}" "${doxyfile}")
 
 function(verbose_find_path variable name)
-  # find_path sets a CACHE variable, so don't try using a "local" variable.
-  find_path(${variable} "${name}" ${ARGN})
-  if(NOT ${variable})
-    message(NOTICE "could not find ${name}")
-  else()
-    message(STATUS "found ${name}: ${${variable}}/${name}")
-  endif()
+    # find_path sets a CACHE variable, so don't try using a "local" variable.
+    find_path(${variable} "${name}" ${ARGN})
+    if(NOT ${variable})
+        message(NOTICE "could not find ${name}")
+    else()
+        message(STATUS "found ${name}: ${${variable}}/${name}")
+    endif()
 endfunction()
 
-verbose_find_path(doxygen_plantuml_jar_path plantuml.jar PATH_SUFFIXES share/plantuml)
+verbose_find_path(
+    doxygen_plantuml_jar_path
+    plantuml.jar
+    PATH_SUFFIXES share/plantuml
+)
 verbose_find_path(doxygen_dot_path dot)
 
 # https://en.cppreference.com/w/Cppreference:Archives
 # https://stackoverflow.com/questions/60822559/how-to-move-a-file-download-from-configure-step-to-build-step
 set(download_script "${CMAKE_BINARY_DIR}/docs/download-cppreference.cmake")
-file(WRITE
-  "${download_script}"
-  "file(DOWNLOAD \
+file(
+    WRITE "${download_script}"
+    "file(DOWNLOAD \
     https://github.com/PeterFeicht/cppreference-doc/releases/download/v20250209/html-book-20250209.zip \
     ${CMAKE_BINARY_DIR}/docs/cppreference.zip \
     EXPECTED_HASH MD5=bda585f72fbca4b817b29a3d5746567b \
@@ -61,23 +65,27 @@ file(WRITE
 )
 set(tagfile "${CMAKE_BINARY_DIR}/docs/cppreference-doxygen-web.tag.xml")
 add_custom_command(
-  OUTPUT "${tagfile}"
-  COMMAND "${CMAKE_COMMAND}" -P "${download_script}"
-  WORKING_DIRECTORY "${CMAKE_BINARY_DIR}/docs"
+    OUTPUT "${tagfile}"
+    COMMAND "${CMAKE_COMMAND}" -P "${download_script}"
+    WORKING_DIRECTORY "${CMAKE_BINARY_DIR}/docs"
 )
 set(doxygen_tagfiles "${tagfile}=http://en.cppreference.com/w/")
 
 add_custom_command(
-  OUTPUT "${doxygen_index_file}"
-  COMMAND "${CMAKE_COMMAND}" -E env
-    "DOXYGEN_OUTPUT_DIRECTORY=${doxygen_output_directory}"
-    "DOXYGEN_INCLUDE_PATH=${doxygen_include_path}"
-    "DOXYGEN_TAGFILES=${doxygen_tagfiles}"
-    "DOXYGEN_PLANTUML_JAR_PATH=${doxygen_plantuml_jar_path}"
-    "DOXYGEN_DOT_PATH=${doxygen_dot_path}"
-    "${DOXYGEN_EXECUTABLE}" "${doxyfile}"
-  WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
-  DEPENDS "${dependencies}" "${tagfile}")
-add_custom_target(docs
-  DEPENDS "${doxygen_index_file}"
-  SOURCES "${dependencies}")
+    OUTPUT "${doxygen_index_file}"
+    COMMAND
+        "${CMAKE_COMMAND}" -E env
+        "DOXYGEN_OUTPUT_DIRECTORY=${doxygen_output_directory}"
+        "DOXYGEN_INCLUDE_PATH=${doxygen_include_path}"
+        "DOXYGEN_TAGFILES=${doxygen_tagfiles}"
+        "DOXYGEN_PLANTUML_JAR_PATH=${doxygen_plantuml_jar_path}"
+        "DOXYGEN_DOT_PATH=${doxygen_dot_path}" "${DOXYGEN_EXECUTABLE}"
+        "${doxyfile}"
+    WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
+    DEPENDS "${dependencies}" "${tagfile}"
+)
+add_custom_target(
+    docs
+    DEPENDS "${doxygen_index_file}"
+    SOURCES "${dependencies}"
+)

cmake/XrplInstall.cmake

@@ -2,79 +2,38 @@
    install stuff
 #]===================================================================]
 
-include(create_symbolic_link)
+include(GNUInstallDirs)
 
-install (
-  TARGETS
-    common
-    opts
-    xrpl_boost
-    xrpl_libs
-    xrpl_syslibs
-    xrpl.imports.main
-    xrpl.libpb
-    xrpl.libxrpl
-    xrpl.libxrpl.basics
-    xrpl.libxrpl.beast
-    xrpl.libxrpl.core
-    xrpl.libxrpl.crypto
-    xrpl.libxrpl.json
-    xrpl.libxrpl.ledger
-    xrpl.libxrpl.net
-    xrpl.libxrpl.nodestore
-    xrpl.libxrpl.protocol
-    xrpl.libxrpl.resource
-    xrpl.libxrpl.server
-    xrpl.libxrpl.shamap
-    antithesis-sdk-cpp
-  EXPORT XrplExports
-  LIBRARY DESTINATION lib
-  ARCHIVE DESTINATION lib
-  RUNTIME DESTINATION bin
-  INCLUDES DESTINATION include)
+if(is_root_project AND TARGET xrpld)
+    install(
+        TARGETS xrpld
+        RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}" COMPONENT runtime
+    )
+
+    install(
+        FILES "${CMAKE_CURRENT_SOURCE_DIR}/cfg/xrpld-example.cfg"
+        DESTINATION "${CMAKE_INSTALL_SYSCONFDIR}/xrpld"
+        RENAME xrpld.cfg
+        COMPONENT runtime
+    )
+
+    install(
+        FILES "${CMAKE_CURRENT_SOURCE_DIR}/cfg/validators-example.txt"
+        DESTINATION "${CMAKE_INSTALL_SYSCONFDIR}/xrpld"
+        RENAME validators.txt
+        COMPONENT runtime
+    )
+endif()
 
 install(
-  DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl"
-  DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
+    TARGETS xrpl.libpb xrpl.libxrpl
+    LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}" COMPONENT development
+    ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}" COMPONENT development
+    RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}" COMPONENT development
 )
 
-install (EXPORT XrplExports
-  FILE XrplTargets.cmake
-  NAMESPACE Xrpl::
-  DESTINATION lib/cmake/xrpl)
-include (CMakePackageConfigHelpers)
-write_basic_package_version_file (
-  XrplConfigVersion.cmake
-  VERSION ${xrpld_version}
-  COMPATIBILITY SameMajorVersion)
-
-if (is_root_project AND TARGET xrpld)
-  install (TARGETS xrpld RUNTIME DESTINATION bin)
-  set_target_properties(xrpld PROPERTIES INSTALL_RPATH_USE_LINK_PATH ON)
-  # sample configs should not overwrite existing files
-  # install if-not-exists workaround as suggested by
-  # https://cmake.org/Bug/view.php?id=12646
-  install(CODE "
-    macro (copy_if_not_exists SRC DEST NEWNAME)
-      if (NOT EXISTS \"\$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}/\${DEST}/\${NEWNAME}\")
-        file (INSTALL FILE_PERMISSIONS OWNER_READ OWNER_WRITE DESTINATION \"\${CMAKE_INSTALL_PREFIX}/\${DEST}\" FILES \"\${SRC}\" RENAME \"\${NEWNAME}\")
-      else ()
-        message (\"-- Skipping : \$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}/\${DEST}/\${NEWNAME}\")
-      endif ()
-    endmacro()
-    copy_if_not_exists(\"${CMAKE_CURRENT_SOURCE_DIR}/cfg/xrpld-example.cfg\" etc xrpld.cfg)
-    copy_if_not_exists(\"${CMAKE_CURRENT_SOURCE_DIR}/cfg/validators-example.txt\" etc validators.txt)
-  ")
-  install(CODE "
-    set(CMAKE_MODULE_PATH \"${CMAKE_MODULE_PATH}\")
-    include(create_symbolic_link)
-    create_symbolic_link(xrpld${suffix} \
-       \$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/rippled${suffix})
-  ")
-endif ()
-
-install (
-  FILES
-    ${CMAKE_CURRENT_SOURCE_DIR}/cmake/XrplConfig.cmake
-    ${CMAKE_CURRENT_BINARY_DIR}/XrplConfigVersion.cmake
-  DESTINATION lib/cmake/xrpl)
+install(
+    DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl"
+    DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
+    COMPONENT development
+)

cmake/XrplInterface.cmake

@@ -4,80 +4,93 @@
 
 include(CompilationEnv)
 
-add_library (opts INTERFACE)
-add_library (Xrpl::opts ALIAS opts)
-target_compile_definitions (opts
-  INTERFACE
-    BOOST_ASIO_DISABLE_HANDLER_TYPE_REQUIREMENTS
-    BOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT
-    BOOST_CONTAINER_FWD_BAD_DEQUE
-    HAS_UNCAUGHT_EXCEPTIONS=1
-    $<$<BOOL:${boost_show_deprecated}>:
-      BOOST_ASIO_NO_DEPRECATED
-      BOOST_FILESYSTEM_NO_DEPRECATED
-    >
-    $<$<NOT:$<BOOL:${boost_show_deprecated}>>:
-      BOOST_COROUTINES_NO_DEPRECATION_WARNING
-      BOOST_BEAST_ALLOW_DEPRECATED
-      BOOST_FILESYSTEM_DEPRECATED
-    >
-    $<$<BOOL:${beast_no_unit_test_inline}>:BEAST_NO_UNIT_TEST_INLINE=1>
-    $<$<BOOL:${beast_disable_autolink}>:BEAST_DONT_AUTOLINK_TO_WIN32_LIBRARIES=1>
-    $<$<BOOL:${single_io_service_thread}>:XRPL_SINGLE_IO_SERVICE_THREAD=1>
-    $<$<BOOL:${voidstar}>:ENABLE_VOIDSTAR>)
-target_compile_options (opts
-  INTERFACE
-    $<$<AND:$<BOOL:${is_gcc}>,$<COMPILE_LANGUAGE:CXX>>:-Wsuggest-override>
-    $<$<BOOL:${is_gcc}>:-Wno-maybe-uninitialized>
-    $<$<BOOL:${perf}>:-fno-omit-frame-pointer>
-    $<$<BOOL:${profile}>:-pg>
-    $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>)
+# Set defaults for optional variables to avoid uninitialized variable warnings
+if(NOT DEFINED voidstar)
+    set(voidstar OFF)
+endif()
 
-target_link_libraries (opts
-  INTERFACE
-    $<$<BOOL:${profile}>:-pg>
-    $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>)
+add_library(opts INTERFACE)
+add_library(Xrpl::opts ALIAS opts)
+target_compile_definitions(
+    opts
+    INTERFACE
+        BOOST_ASIO_DISABLE_HANDLER_TYPE_REQUIREMENTS
+        BOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT
+        BOOST_CONTAINER_FWD_BAD_DEQUE
+        HAS_UNCAUGHT_EXCEPTIONS=1
+        $<$<BOOL:${boost_show_deprecated}>:
+        BOOST_ASIO_NO_DEPRECATED
+        BOOST_FILESYSTEM_NO_DEPRECATED
+        >
+        $<$<NOT:$<BOOL:${boost_show_deprecated}>>:
+        BOOST_COROUTINES2_NO_DEPRECATION_WARNING
+        BOOST_BEAST_ALLOW_DEPRECATED
+        BOOST_FILESYSTEM_DEPRECATED
+        >
+        $<$<BOOL:${beast_no_unit_test_inline}>:BEAST_NO_UNIT_TEST_INLINE=1>
+        $<$<BOOL:${beast_disable_autolink}>:BEAST_DONT_AUTOLINK_TO_WIN32_LIBRARIES=1>
+        $<$<BOOL:${single_io_service_thread}>:XRPL_SINGLE_IO_SERVICE_THREAD=1>
+        $<$<BOOL:${voidstar}>:ENABLE_VOIDSTAR>
+)
+target_compile_options(
+    opts
+    INTERFACE
+        $<$<AND:$<BOOL:${is_gcc}>,$<COMPILE_LANGUAGE:CXX>>:-Wsuggest-override>
+        $<$<BOOL:${is_gcc}>:-Wno-maybe-uninitialized>
+        $<$<BOOL:${perf}>:-fno-omit-frame-pointer>
+        $<$<BOOL:${profile}>:-pg>
+        $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>
+)
+
+target_link_libraries(
+    opts
+    INTERFACE
+        $<$<BOOL:${profile}>:-pg>
+        $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>
+)
 
 if(jemalloc)
-  find_package(jemalloc REQUIRED)
-  target_compile_definitions(opts INTERFACE PROFILE_JEMALLOC)
-  target_link_libraries(opts INTERFACE jemalloc::jemalloc)
-endif ()
+    find_package(jemalloc REQUIRED)
+    target_compile_definitions(opts INTERFACE PROFILE_JEMALLOC)
+    target_link_libraries(opts INTERFACE jemalloc::jemalloc)
+endif()
 
 #[===================================================================[
    xrpld transitive library deps via an interface library
 #]===================================================================]
 
-add_library (xrpl_syslibs INTERFACE)
-add_library (Xrpl::syslibs ALIAS xrpl_syslibs)
-target_link_libraries (xrpl_syslibs
-  INTERFACE
-    $<$<BOOL:${MSVC}>:
-      legacy_stdio_definitions.lib
-      Shlwapi
-      kernel32
-      user32
-      gdi32
-      winspool
-      comdlg32
-      advapi32
-      shell32
-      ole32
-      oleaut32
-      uuid
-      odbc32
-      odbccp32
-      crypt32
-    >
-    $<$<NOT:$<BOOL:${MSVC}>>:dl>
-    $<$<NOT:$<OR:$<BOOL:${MSVC}>,$<BOOL:${APPLE}>>>:rt>)
+add_library(xrpl_syslibs INTERFACE)
+add_library(Xrpl::syslibs ALIAS xrpl_syslibs)
+target_link_libraries(
+    xrpl_syslibs
+    INTERFACE
+        $<$<BOOL:${is_msvc}>:
+        legacy_stdio_definitions.lib
+        Shlwapi
+        kernel32
+        user32
+        gdi32
+        winspool
+        comdlg32
+        advapi32
+        shell32
+        ole32
+        oleaut32
+        uuid
+        odbc32
+        odbccp32
+        crypt32
+        >
+        $<$<NOT:$<BOOL:${is_msvc}>>:dl>
+        $<$<NOT:$<OR:$<BOOL:${is_msvc}>,$<BOOL:${is_macos}>>>:rt>
+)
 
-if (NOT MSVC)
-  set (THREADS_PREFER_PTHREAD_FLAG ON)
-  find_package (Threads)
-  target_link_libraries (xrpl_syslibs INTERFACE Threads::Threads)
-endif ()
+if(NOT is_msvc)
+    set(THREADS_PREFER_PTHREAD_FLAG ON)
+    find_package(Threads)
+    target_link_libraries(xrpl_syslibs INTERFACE Threads::Threads)
+endif()
 
-add_library (xrpl_libs INTERFACE)
-add_library (Xrpl::libs ALIAS xrpl_libs)
-target_link_libraries (xrpl_libs INTERFACE Xrpl::syslibs)
+add_library(xrpl_libs INTERFACE)
+add_library(Xrpl::libs ALIAS xrpl_libs)
+target_link_libraries(xrpl_libs INTERFACE Xrpl::syslibs)

cmake/XrplProtocolAutogen.cmake

@@ -0,0 +1,309 @@
+#[===================================================================[
+   Protocol Autogen - Code generation for protocol wrapper classes
+#]===================================================================]
+
+# Options for code generation
+option(
+    XRPL_NO_CODEGEN
+    "Disable code generation (use pre-generated files from repository)"
+    OFF
+)
+set(CODEGEN_VENV_DIR
+    ""
+    CACHE PATH
+    "Path to Python virtual environment for code generation. If provided, automatic venv setup is skipped."
+)
+
+# Function to set up code generation for protocol_autogen module
+# This runs at configure time to generate C++ wrapper classes from macro files
+function(setup_protocol_autogen)
+    # Directory paths
+    set(MACRO_DIR "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl/protocol/detail")
+    set(AUTOGEN_HEADER_DIR
+        "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl/protocol_autogen"
+    )
+    set(AUTOGEN_TEST_DIR
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/tests/libxrpl/protocol_autogen"
+    )
+    set(SCRIPTS_DIR "${CMAKE_CURRENT_SOURCE_DIR}/scripts")
+
+    # Input macro files
+    set(TRANSACTIONS_MACRO "${MACRO_DIR}/transactions.macro")
+    set(LEDGER_ENTRIES_MACRO "${MACRO_DIR}/ledger_entries.macro")
+    set(SFIELDS_MACRO "${MACRO_DIR}/sfields.macro")
+
+    # Python scripts and templates
+    set(GENERATE_TX_SCRIPT "${SCRIPTS_DIR}/generate_tx_classes.py")
+    set(GENERATE_LEDGER_SCRIPT "${SCRIPTS_DIR}/generate_ledger_classes.py")
+    set(REQUIREMENTS_FILE "${SCRIPTS_DIR}/requirements.txt")
+    set(MACRO_PARSER_COMMON "${SCRIPTS_DIR}/macro_parser_common.py")
+    set(TX_TEMPLATE "${SCRIPTS_DIR}/templates/Transaction.h.mako")
+    set(TX_TEST_TEMPLATE "${SCRIPTS_DIR}/templates/TransactionTests.cpp.mako")
+    set(LEDGER_TEMPLATE "${SCRIPTS_DIR}/templates/LedgerEntry.h.mako")
+    set(LEDGER_TEST_TEMPLATE
+        "${SCRIPTS_DIR}/templates/LedgerEntryTests.cpp.mako"
+    )
+
+    # Check if code generation is disabled
+    if(XRPL_NO_CODEGEN)
+        message(
+            WARNING
+            "Protocol autogen: Code generation is disabled (XRPL_NO_CODEGEN=ON). "
+            "Generated files may be out of date."
+        )
+        return()
+    endif()
+
+    # Create output directories
+    file(MAKE_DIRECTORY "${AUTOGEN_HEADER_DIR}/transactions")
+    file(MAKE_DIRECTORY "${AUTOGEN_HEADER_DIR}/ledger_entries")
+    file(MAKE_DIRECTORY "${AUTOGEN_TEST_DIR}/ledger_entries")
+    file(MAKE_DIRECTORY "${AUTOGEN_TEST_DIR}/transactions")
+
+    # Find Python3 - check if already found by Conan or find it ourselves
+    if(NOT Python3_EXECUTABLE)
+        find_package(Python3 COMPONENTS Interpreter QUIET)
+    endif()
+
+    if(NOT Python3_EXECUTABLE)
+        # Try finding python3 executable directly
+        find_program(Python3_EXECUTABLE NAMES python3 python)
+    endif()
+
+    if(NOT Python3_EXECUTABLE)
+        message(
+            FATAL_ERROR
+            "Python3 not found. Code generation cannot proceed.\n"
+            "Please install Python 3, or set -DXRPL_NO_CODEGEN=ON to use existing generated files."
+        )
+        return()
+    endif()
+
+    message(STATUS "Using Python3 for code generation: ${Python3_EXECUTABLE}")
+
+    # Set up Python virtual environment for code generation
+    if(CODEGEN_VENV_DIR)
+        # User-provided venv - skip automatic setup
+        set(VENV_DIR "${CODEGEN_VENV_DIR}")
+        message(STATUS "Using user-provided Python venv: ${VENV_DIR}")
+    else()
+        # Use default venv in build directory
+        set(VENV_DIR "${CMAKE_CURRENT_BINARY_DIR}/codegen_venv")
+    endif()
+
+    # Determine the Python executable path in the venv
+    if(WIN32)
+        set(VENV_PYTHON "${VENV_DIR}/Scripts/python.exe")
+        set(VENV_PIP "${VENV_DIR}/Scripts/pip.exe")
+    else()
+        set(VENV_PYTHON "${VENV_DIR}/bin/python")
+        set(VENV_PIP "${VENV_DIR}/bin/pip")
+    endif()
+
+    # Only auto-setup venv if not user-provided
+    if(NOT CODEGEN_VENV_DIR)
+        # Check if venv needs to be created or updated
+        set(VENV_NEEDS_UPDATE FALSE)
+        if(NOT EXISTS "${VENV_PYTHON}")
+            set(VENV_NEEDS_UPDATE TRUE)
+            message(
+                STATUS
+                "Creating Python virtual environment for code generation..."
+            )
+        elseif(
+            "${REQUIREMENTS_FILE}"
+                IS_NEWER_THAN
+                "${VENV_DIR}/.requirements_installed"
+        )
+            set(VENV_NEEDS_UPDATE TRUE)
+            message(
+                STATUS
+                "Updating Python virtual environment (requirements changed)..."
+            )
+        endif()
+
+        # Create/update virtual environment if needed
+        if(VENV_NEEDS_UPDATE)
+            message(
+                STATUS
+                "Setting up Python virtual environment at ${VENV_DIR}"
+            )
+            execute_process(
+                COMMAND ${Python3_EXECUTABLE} -m venv "${VENV_DIR}"
+                RESULT_VARIABLE VENV_RESULT
+                ERROR_VARIABLE VENV_ERROR
+            )
+            if(NOT VENV_RESULT EQUAL 0)
+                message(
+                    FATAL_ERROR
+                    "Failed to create virtual environment: ${VENV_ERROR}"
+                )
+            endif()
+
+            # Check pip index URL configuration
+            execute_process(
+                COMMAND ${VENV_PIP} config get global.index-url
+                OUTPUT_VARIABLE PIP_INDEX_URL
+                OUTPUT_STRIP_TRAILING_WHITESPACE
+                ERROR_QUIET
+            )
+
+            # Default PyPI URL
+            set(DEFAULT_PIP_INDEX "https://pypi.org/simple")
+
+            # Show warning if using non-default index
+            if(PIP_INDEX_URL AND NOT PIP_INDEX_URL STREQUAL "")
+                if(NOT PIP_INDEX_URL STREQUAL DEFAULT_PIP_INDEX)
+                    message(
+                        WARNING
+                        "Private pip index URL detected: ${PIP_INDEX_URL}\n"
+                        "You may need to connect to VPN to access this URL."
+                    )
+                endif()
+            endif()
+
+            message(STATUS "Installing Python dependencies...")
+            execute_process(
+                COMMAND ${VENV_PIP} install --upgrade pip
+                RESULT_VARIABLE PIP_UPGRADE_RESULT
+                OUTPUT_QUIET
+                ERROR_VARIABLE PIP_UPGRADE_ERROR
+            )
+            if(NOT PIP_UPGRADE_RESULT EQUAL 0)
+                message(WARNING "Failed to upgrade pip: ${PIP_UPGRADE_ERROR}")
+            endif()
+
+            execute_process(
+                COMMAND ${VENV_PIP} install -r "${REQUIREMENTS_FILE}"
+                RESULT_VARIABLE PIP_INSTALL_RESULT
+                ERROR_VARIABLE PIP_INSTALL_ERROR
+            )
+            if(NOT PIP_INSTALL_RESULT EQUAL 0)
+                message(
+                    FATAL_ERROR
+                    "Failed to install Python dependencies: ${PIP_INSTALL_ERROR}"
+                )
+            endif()
+
+            # Mark requirements as installed
+            file(TOUCH "${VENV_DIR}/.requirements_installed")
+            message(STATUS "Python virtual environment ready")
+        endif()
+    endif()
+
+    # At configure time - get list of output files for transactions
+    execute_process(
+        COMMAND
+            ${VENV_PYTHON} "${GENERATE_TX_SCRIPT}" "${TRANSACTIONS_MACRO}"
+            --header-dir "${AUTOGEN_HEADER_DIR}/transactions" --test-dir
+            "${AUTOGEN_TEST_DIR}/transactions" --list-outputs
+        OUTPUT_VARIABLE TX_OUTPUT_FILES
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        RESULT_VARIABLE TX_LIST_RESULT
+        ERROR_VARIABLE TX_LIST_ERROR
+    )
+    if(NOT TX_LIST_RESULT EQUAL 0)
+        message(
+            FATAL_ERROR
+            "Failed to list transaction output files:\n${TX_LIST_ERROR}"
+        )
+    endif()
+    # Convert newline-separated list to CMake list
+    string(REPLACE "\\" "/" TX_OUTPUT_FILES "${TX_OUTPUT_FILES}")
+    string(REPLACE "\n" ";" TX_OUTPUT_FILES "${TX_OUTPUT_FILES}")
+
+    # At configure time - get list of output files for ledger entries
+    execute_process(
+        COMMAND
+            ${VENV_PYTHON} "${GENERATE_LEDGER_SCRIPT}" "${LEDGER_ENTRIES_MACRO}"
+            --header-dir "${AUTOGEN_HEADER_DIR}/ledger_entries" --test-dir
+            "${AUTOGEN_TEST_DIR}/ledger_entries" --list-outputs
+        OUTPUT_VARIABLE LEDGER_OUTPUT_FILES
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        RESULT_VARIABLE LEDGER_LIST_RESULT
+        ERROR_VARIABLE LEDGER_LIST_ERROR
+    )
+    if(NOT LEDGER_LIST_RESULT EQUAL 0)
+        message(
+            FATAL_ERROR
+            "Failed to list ledger entry output files:\n${LEDGER_LIST_ERROR}"
+        )
+    endif()
+    # Convert newline-separated list to CMake list
+    string(REPLACE "\\" "/" LEDGER_OUTPUT_FILES "${LEDGER_OUTPUT_FILES}")
+    string(REPLACE "\n" ";" LEDGER_OUTPUT_FILES "${LEDGER_OUTPUT_FILES}")
+
+    # Custom command to generate transaction classes at build time
+    add_custom_command(
+        OUTPUT ${TX_OUTPUT_FILES}
+        COMMAND
+            ${VENV_PYTHON} "${GENERATE_TX_SCRIPT}" "${TRANSACTIONS_MACRO}"
+            --header-dir "${AUTOGEN_HEADER_DIR}/transactions" --test-dir
+            "${AUTOGEN_TEST_DIR}/transactions" --sfields-macro
+            "${SFIELDS_MACRO}"
+        WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
+        DEPENDS
+            "${TRANSACTIONS_MACRO}"
+            "${SFIELDS_MACRO}"
+            "${GENERATE_TX_SCRIPT}"
+            "${MACRO_PARSER_COMMON}"
+            "${TX_TEMPLATE}"
+            "${TX_TEST_TEMPLATE}"
+            "${REQUIREMENTS_FILE}"
+        COMMENT "Generating transaction classes from transactions.macro..."
+        VERBATIM
+    )
+
+    # Custom command to generate ledger entry classes at build time
+    add_custom_command(
+        OUTPUT ${LEDGER_OUTPUT_FILES}
+        COMMAND
+            ${VENV_PYTHON} "${GENERATE_LEDGER_SCRIPT}" "${LEDGER_ENTRIES_MACRO}"
+            --header-dir "${AUTOGEN_HEADER_DIR}/ledger_entries" --test-dir
+            "${AUTOGEN_TEST_DIR}/ledger_entries" --sfields-macro
+            "${SFIELDS_MACRO}"
+        WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
+        DEPENDS
+            "${LEDGER_ENTRIES_MACRO}"
+            "${SFIELDS_MACRO}"
+            "${GENERATE_LEDGER_SCRIPT}"
+            "${MACRO_PARSER_COMMON}"
+            "${LEDGER_TEMPLATE}"
+            "${LEDGER_TEST_TEMPLATE}"
+            "${REQUIREMENTS_FILE}"
+        COMMENT "Generating ledger entry classes from ledger_entries.macro..."
+        VERBATIM
+    )
+
+    # Create a custom target that depends on all generated files
+    add_custom_target(
+        protocol_autogen_generate
+        DEPENDS ${TX_OUTPUT_FILES} ${LEDGER_OUTPUT_FILES}
+        COMMENT "Protocol autogen code generation"
+    )
+
+    # Extract test files from output lists (files ending in Tests.cpp)
+    set(PROTOCOL_AUTOGEN_TEST_SOURCES "")
+    foreach(FILE ${TX_OUTPUT_FILES} ${LEDGER_OUTPUT_FILES})
+        if(FILE MATCHES "Tests\\.cpp$")
+            list(APPEND PROTOCOL_AUTOGEN_TEST_SOURCES "${FILE}")
+        endif()
+    endforeach()
+    # Export test sources to parent scope for use in test CMakeLists.txt
+    set(PROTOCOL_AUTOGEN_TEST_SOURCES
+        "${PROTOCOL_AUTOGEN_TEST_SOURCES}"
+        CACHE INTERNAL
+        "Generated protocol_autogen test sources"
+    )
+
+    # Register dependencies so CMake reconfigures when macro files change
+    # (to update the list of output files)
+    set_property(
+        DIRECTORY
+        APPEND
+        PROPERTY
+            CMAKE_CONFIGURE_DEPENDS
+                "${TRANSACTIONS_MACRO}"
+                "${LEDGER_ENTRIES_MACRO}"
+    )
+endfunction()

cmake/XrplSanitizers.cmake

@@ -43,7 +43,10 @@
 include(CompilationEnv)
 
 # Read environment variable
-set(SANITIZERS $ENV{SANITIZERS})
+set(SANITIZERS "")
+if(DEFINED ENV{SANITIZERS})
+    set(SANITIZERS "$ENV{SANITIZERS}")
+endif()
 
 # Set SANITIZERS_ENABLED flag for use in other modules
 if(SANITIZERS MATCHES "address|thread|undefinedbehavior")
@@ -55,8 +58,11 @@ endif()
 
 # Sanitizers are not supported on Windows/MSVC
 if(is_msvc)
-    message(FATAL_ERROR "Sanitizers are not supported on Windows/MSVC. "
-            "Please unset the SANITIZERS environment variable.")
+    message(
+        FATAL_ERROR
+        "Sanitizers are not supported on Windows/MSVC. "
+        "Please unset the SANITIZERS environment variable."
+    )
 endif()
 
 message(STATUS "Configuring sanitizers: ${SANITIZERS}")
@@ -79,15 +85,21 @@ foreach(san IN LISTS san_list)
     elseif(san STREQUAL "undefinedbehavior")
         set(enable_ubsan TRUE)
     else()
-        message(FATAL_ERROR "Unsupported sanitizer type: ${san}"
-              "Supported: address, thread, undefinedbehavior and their combinations.")
+        message(
+            FATAL_ERROR
+            "Unsupported sanitizer type: ${san}"
+            "Supported: address, thread, undefinedbehavior and their combinations."
+        )
     endif()
 endforeach()
 
 # Validate sanitizer compatibility
 if(enable_asan AND enable_tsan)
-    message(FATAL_ERROR "AddressSanitizer and ThreadSanitizer are incompatible and cannot be enabled simultaneously. "
-          "Use 'address' or 'thread', optionally with 'undefinedbehavior'.")
+    message(
+        FATAL_ERROR
+        "AddressSanitizer and ThreadSanitizer are incompatible and cannot be enabled simultaneously. "
+        "Use 'address' or 'thread', optionally with 'undefinedbehavior'."
+    )
 endif()
 
 # Frame pointer is required for meaningful stack traces. Sanitizers recommend minimum of -O1 for reasonable performance
@@ -106,25 +118,28 @@ if(enable_ubsan)
     # UB sanitizer flags
     list(APPEND SANITIZER_TYPES "undefined" "float-divide-by-zero")
     if(is_clang)
-        # Clang supports additional UB checks. More info here https://clang.llvm.org/docs/UndefinedBehaviorSanitizer.html
+        # Clang supports additional UB checks. More info here
+        # https://clang.llvm.org/docs/UndefinedBehaviorSanitizer.html
         list(APPEND SANITIZER_TYPES "unsigned-integer-overflow")
     endif()
 endif()
 
-# Configure code model for GCC on amd64
-# Use large code model for ASAN to avoid relocation errors
-# Use medium code model for TSAN (large is not compatible with TSAN)
+# Configure code model for GCC on amd64 Use large code model for ASAN to avoid relocation errors Use medium code model
+# for TSAN (large is not compatible with TSAN)
 set(SANITIZERS_RELOCATION_FLAGS)
 
 # Compiler-specific configuration
 if(is_gcc)
-    # Disable mold, gold and lld linkers for GCC with sanitizers
-    # Use default linker (bfd/ld) which is more lenient with mixed code models
-    # This is needed since the size of instrumented binary exceeds the limits set by mold, lld and gold linkers
+    # Disable mold, gold and lld linkers for GCC with sanitizers Use default linker (bfd/ld) which is more lenient with
+    # mixed code models This is needed since the size of instrumented binary exceeds the limits set by mold, lld and
+    # gold linkers
     set(use_mold OFF CACHE BOOL "Use mold linker" FORCE)
     set(use_gold OFF CACHE BOOL "Use gold linker" FORCE)
     set(use_lld OFF CACHE BOOL "Use lld linker" FORCE)
-    message(STATUS "  Disabled mold, gold, and lld linkers for GCC with sanitizers")
+    message(
+        STATUS
+        "  Disabled mold, gold, and lld linkers for GCC with sanitizers"
+    )
 
     # Suppress false positive warnings in GCC with stringop-overflow
     list(APPEND SANITIZERS_COMPILE_FLAGS "-Wno-stringop-overflow")
@@ -146,17 +161,26 @@ if(is_gcc)
 
     # Add sanitizer to compile and link flags
     list(APPEND SANITIZERS_COMPILE_FLAGS "-fsanitize=${SANITIZER_TYPES_STR}")
-    set(SANITIZERS_LINK_FLAGS "${SANITIZERS_RELOCATION_FLAGS}" "-fsanitize=${SANITIZER_TYPES_STR}")
-
+    set(SANITIZERS_LINK_FLAGS
+        "${SANITIZERS_RELOCATION_FLAGS}"
+        "-fsanitize=${SANITIZER_TYPES_STR}"
+    )
 elseif(is_clang)
-    # Add ignorelist for Clang (GCC doesn't support this)
-    # Use CMAKE_SOURCE_DIR to get the path to the ignorelist
-    set(IGNORELIST_PATH "${CMAKE_SOURCE_DIR}/sanitizers/suppressions/sanitizer-ignorelist.txt")
+    # Add ignorelist for Clang (GCC doesn't support this) Use CMAKE_SOURCE_DIR to get the path to the ignorelist
+    set(IGNORELIST_PATH
+        "${CMAKE_SOURCE_DIR}/sanitizers/suppressions/sanitizer-ignorelist.txt"
+    )
     if(NOT EXISTS "${IGNORELIST_PATH}")
-        message(FATAL_ERROR "Sanitizer ignorelist not found: ${IGNORELIST_PATH}")
+        message(
+            FATAL_ERROR
+            "Sanitizer ignorelist not found: ${IGNORELIST_PATH}"
+        )
     endif()
 
-    list(APPEND SANITIZERS_COMPILE_FLAGS "-fsanitize-ignorelist=${IGNORELIST_PATH}")
+    list(
+        APPEND SANITIZERS_COMPILE_FLAGS
+        "-fsanitize-ignorelist=${IGNORELIST_PATH}"
+    )
     message(STATUS "  Using sanitizer ignorelist: ${IGNORELIST_PATH}")
 
     # Join sanitizer flags with commas for -fsanitize option
@@ -170,11 +194,12 @@ endif()
 message(STATUS "  Compile flags: ${SANITIZERS_COMPILE_FLAGS}")
 message(STATUS "  Link flags: ${SANITIZERS_LINK_FLAGS}")
 
-# Apply the sanitizer flags to the 'common' interface library
-# This is the same library used by XrplCompiler.cmake
-target_compile_options(common INTERFACE
-    $<$<COMPILE_LANGUAGE:CXX>:${SANITIZERS_COMPILE_FLAGS}>
-    $<$<COMPILE_LANGUAGE:C>:${SANITIZERS_COMPILE_FLAGS}>
+# Apply the sanitizer flags to the 'common' interface library This is the same library used by XrplCompiler.cmake
+target_compile_options(
+    common
+    INTERFACE
+        $<$<COMPILE_LANGUAGE:CXX>:${SANITIZERS_COMPILE_FLAGS}>
+        $<$<COMPILE_LANGUAGE:C>:${SANITIZERS_COMPILE_FLAGS}>
 )
 
 # Apply linker flags

cmake/XrplSanity.cmake

@@ -6,40 +6,57 @@ include(CompilationEnv)
 
 get_property(is_multiconfig GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
 
-set (CMAKE_CONFIGURATION_TYPES "Debug;Release" CACHE STRING "" FORCE)
-if (NOT is_multiconfig)
-  if (NOT CMAKE_BUILD_TYPE)
-    message (STATUS "Build type not specified - defaulting to Release")
-    set (CMAKE_BUILD_TYPE Release CACHE STRING "build type" FORCE)
-  elseif (NOT (CMAKE_BUILD_TYPE STREQUAL Debug OR CMAKE_BUILD_TYPE STREQUAL Release))
-    # for simplicity, these are the only two config types we care about. Limiting
-    # the build types simplifies dealing with external project builds especially
-    message (FATAL_ERROR " *** Only Debug or Release build types are currently supported ***")
-  endif ()
-endif ()
+set(CMAKE_CONFIGURATION_TYPES "Debug;Release" CACHE STRING "" FORCE)
+if(NOT is_multiconfig)
+    if(NOT CMAKE_BUILD_TYPE)
+        message(STATUS "Build type not specified - defaulting to Release")
+        set(CMAKE_BUILD_TYPE Release CACHE STRING "build type" FORCE)
+    elseif(
+        NOT (CMAKE_BUILD_TYPE STREQUAL Debug OR CMAKE_BUILD_TYPE STREQUAL Release)
+    )
+        # for simplicity, these are the only two config types we care about. Limiting the build types simplifies dealing
+        # with external project builds especially
+        message(
+            FATAL_ERROR
+            " *** Only Debug or Release build types are currently supported ***"
+        )
+    endif()
+endif()
 
-if (is_clang) # both Clang and AppleClang
-  if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang" AND
-         CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16.0)
-    message (FATAL_ERROR "This project requires clang 16 or later")
-  endif ()
-elseif (is_gcc)
-  if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS 12.0)
-    message (FATAL_ERROR "This project requires GCC 12 or later")
-  endif ()
-endif ()
+if(is_clang) # both Clang and AppleClang
+    if(
+        "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang"
+        AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16.0
+    )
+        message(FATAL_ERROR "This project requires clang 16 or later")
+    endif()
+elseif(is_gcc)
+    if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS 12.0)
+        message(FATAL_ERROR "This project requires GCC 12 or later")
+    endif()
+endif()
 
 # check for in-source build and fail
-if ("${CMAKE_CURRENT_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
-  message (FATAL_ERROR "Builds (in-source) are not allowed in "
-    "${CMAKE_CURRENT_SOURCE_DIR}. Please remove CMakeCache.txt and the CMakeFiles "
-    "directory from ${CMAKE_CURRENT_SOURCE_DIR} and try building in a separate directory.")
-endif ()
+if("${CMAKE_CURRENT_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
+    message(
+        FATAL_ERROR
+        "Builds (in-source) are not allowed in "
+        "${CMAKE_CURRENT_SOURCE_DIR}. Please remove CMakeCache.txt and the CMakeFiles "
+        "directory from ${CMAKE_CURRENT_SOURCE_DIR} and try building in a separate directory."
+    )
+endif()
 
-if (MSVC AND CMAKE_GENERATOR_PLATFORM STREQUAL "Win32")
-  message (FATAL_ERROR "Visual Studio 32-bit build is not supported.")
-endif ()
+if(MSVC AND CMAKE_GENERATOR_PLATFORM STREQUAL "Win32")
+    message(FATAL_ERROR "Visual Studio 32-bit build is not supported.")
+endif()
 
-if (APPLE AND NOT HOMEBREW)
-  find_program (HOMEBREW brew)
-endif ()
+if(voidstar AND NOT is_amd64)
+    message(
+        FATAL_ERROR
+        "The voidstar library only supported on amd64/x86_64. Detected archictecture was: ${CMAKE_SYSTEM_PROCESSOR}"
+    )
+endif()
+
+if(APPLE AND NOT HOMEBREW)
+    find_program(HOMEBREW brew)
+endif()

cmake/XrplSettings.cmake

@@ -4,17 +4,18 @@
 
 include(CompilationEnv)
 
-if("$ENV{CI}" STREQUAL "true" OR "$ENV{CONTINUOUS_INTEGRATION}" STREQUAL "true")
-  set(is_ci TRUE)
-else()
-  set(is_ci FALSE)
+set(is_ci FALSE)
+if(DEFINED ENV{CI})
+    if("$ENV{CI}" STREQUAL "true")
+        set(is_ci TRUE)
+    endif()
 endif()
 
 get_directory_property(has_parent PARENT_DIRECTORY)
 if(has_parent)
-  set(is_root_project OFF)
+    set(is_root_project OFF)
 else()
-  set(is_root_project ON)
+    set(is_root_project ON)
 endif()
 
 option(assert "Enables asserts, even in release builds" OFF)
@@ -23,106 +24,132 @@ option(xrpld "Build xrpld" ON)
 
 option(tests "Build tests" ON)
 if(tests)
-  # This setting allows making a separate workflow to test fees other than default 10
-  if(NOT UNIT_TEST_REFERENCE_FEE)
-    set(UNIT_TEST_REFERENCE_FEE "10" CACHE STRING "")
-  endif()
+    # This setting allows making a separate workflow to test fees other than default 10
+    if(NOT UNIT_TEST_REFERENCE_FEE)
+        set(UNIT_TEST_REFERENCE_FEE "10" CACHE STRING "")
+    endif()
 endif()
 
 option(unity "Creates a build using UNITY support in cmake." OFF)
 if(unity)
-  if(NOT is_ci)
-    set(CMAKE_UNITY_BUILD_BATCH_SIZE 15 CACHE STRING "")
-  endif()
-  set(CMAKE_UNITY_BUILD ON CACHE BOOL "Do a unity build")
+    if(NOT is_ci)
+        set(CMAKE_UNITY_BUILD_BATCH_SIZE 15 CACHE STRING "")
+    endif()
+    set(CMAKE_UNITY_BUILD ON CACHE BOOL "Do a unity build")
 endif()
 
 if(is_clang AND is_linux)
-  option(voidstar "Enable Antithesis instrumentation." OFF)
+    option(voidstar "Enable Antithesis instrumentation." OFF)
 endif()
 
 if(is_gcc OR is_clang)
-  include(ProcessorCount)
-  ProcessorCount(PROCESSOR_COUNT)
+    include(ProcessorCount)
+    ProcessorCount(PROCESSOR_COUNT)
 
-  option(coverage "Generates coverage info." OFF)
-  option(profile "Add profiling flags" OFF)
-  set(coverage_format "html-details" CACHE STRING
-    "Output format of the coverage report.")
-  set(coverage_extra_args "" CACHE STRING
-    "Additional arguments to pass to gcovr.")
-  option(wextra "compile with extra gcc/clang warnings enabled" ON)
+    option(coverage "Generates coverage info." OFF)
+    option(profile "Add profiling flags" OFF)
+    set(coverage_format
+        "html-details"
+        CACHE STRING
+        "Output format of the coverage report."
+    )
+    set(coverage_extra_args
+        ""
+        CACHE STRING
+        "Additional arguments to pass to gcovr."
+    )
+    option(wextra "compile with extra gcc/clang warnings enabled" ON)
 else()
-  set(profile OFF CACHE BOOL "gcc/clang only" FORCE)
-  set(coverage OFF CACHE BOOL "gcc/clang only" FORCE)
-  set(wextra OFF CACHE BOOL "gcc/clang only" FORCE)
+    set(profile OFF CACHE BOOL "gcc/clang only" FORCE)
+    set(coverage OFF CACHE BOOL "gcc/clang only" FORCE)
+    set(wextra OFF CACHE BOOL "gcc/clang only" FORCE)
 endif()
 
 if(is_linux AND NOT SANITIZER)
-  option(BUILD_SHARED_LIBS "build shared xrpl libraries" OFF)
-  option(static "link protobuf, openssl, libc++, and boost statically" ON)
-  option(perf "Enables flags that assist with perf recording" OFF)
-  option(use_gold "enables detection of gold (binutils) linker" ON)
-  option(use_mold "enables detection of mold (binutils) linker" ON)
-  # Set a default value for the log flag based on the build type.
-  # This provides a sensible default (on for debug, off for release)
-  # while still allowing the user to override it for any build.
-  if(CMAKE_BUILD_TYPE STREQUAL "Debug")
-    set(TRUNCATED_LOGS_DEFAULT ON)
-  else()
-    set(TRUNCATED_LOGS_DEFAULT OFF)
-  endif()
-  option(TRUNCATED_THREAD_NAME_LOGS
-    "Show warnings about truncated thread names on Linux."
-    ${TRUNCATED_LOGS_DEFAULT}
-  )
-  if(TRUNCATED_THREAD_NAME_LOGS)
-    add_compile_definitions(TRUNCATED_THREAD_NAME_LOGS)
-  endif()
+    option(BUILD_SHARED_LIBS "build shared xrpl libraries" OFF)
+    option(static "link protobuf, openssl, libc++, and boost statically" ON)
+    option(perf "Enables flags that assist with perf recording" OFF)
+    option(use_gold "enables detection of gold (binutils) linker" ON)
+    option(use_mold "enables detection of mold (binutils) linker" ON)
+    # Set a default value for the log flag based on the build type. This provides a sensible default (on for debug, off
+    # for release) while still allowing the user to override it for any build.
+    if(CMAKE_BUILD_TYPE STREQUAL "Debug")
+        set(TRUNCATED_LOGS_DEFAULT ON)
+    else()
+        set(TRUNCATED_LOGS_DEFAULT OFF)
+    endif()
+    option(
+        TRUNCATED_THREAD_NAME_LOGS
+        "Show warnings about truncated thread names on Linux."
+        ${TRUNCATED_LOGS_DEFAULT}
+    )
+    if(TRUNCATED_THREAD_NAME_LOGS)
+        add_compile_definitions(TRUNCATED_THREAD_NAME_LOGS)
+    endif()
 else()
-  # we are not ready to allow shared-libs on windows because it would require
-  # export declarations. On macos it's more feasible, but static openssl
-  # produces odd linker errors, thus we disable shared lib builds for now.
-  set(BUILD_SHARED_LIBS OFF CACHE BOOL "build shared xrpl libraries - OFF for win/macos" FORCE)
-  set(static ON CACHE BOOL "static link, linux only. ON for WIN/macos" FORCE)
-  set(perf OFF CACHE BOOL "perf flags, linux only" FORCE)
-  set(use_gold OFF CACHE BOOL "gold linker, linux only" FORCE)
-  set(use_mold OFF CACHE BOOL "mold linker, linux only" FORCE)
+    # we are not ready to allow shared-libs on windows because it would require export declarations. On macos it's more
+    # feasible, but static openssl produces odd linker errors, thus we disable shared lib builds for now.
+    set(BUILD_SHARED_LIBS
+        OFF
+        CACHE BOOL
+        "build shared xrpl libraries - OFF for win/macos"
+        FORCE
+    )
+    set(static ON CACHE BOOL "static link, linux only. ON for WIN/macos" FORCE)
+    set(perf OFF CACHE BOOL "perf flags, linux only" FORCE)
+    set(use_gold OFF CACHE BOOL "gold linker, linux only" FORCE)
+    set(use_mold OFF CACHE BOOL "mold linker, linux only" FORCE)
 endif()
 
 if(is_clang)
-  option(use_lld "enables detection of lld linker" ON)
+    option(use_lld "enables detection of lld linker" ON)
 else()
-  set(use_lld OFF CACHE BOOL "try lld linker, clang only" FORCE)
+    set(use_lld OFF CACHE BOOL "try lld linker, clang only" FORCE)
 endif()
 
 option(jemalloc "Enables jemalloc for heap profiling" OFF)
 option(werr "treat warnings as errors" OFF)
-option(local_protobuf
-  "Force a local build of protobuf instead of looking for an installed version." OFF)
-option(local_grpc
-  "Force a local build of gRPC instead of looking for an installed version." OFF)
+option(
+    local_protobuf
+    "Force a local build of protobuf instead of looking for an installed version."
+    OFF
+)
+option(
+    local_grpc
+    "Force a local build of gRPC instead of looking for an installed version."
+    OFF
+)
 
 # the remaining options are obscure and rarely used
-option(beast_no_unit_test_inline
-  "Prevents unit test definitions from being inserted into global table"
-  OFF)
-option(single_io_service_thread
-  "Restricts the number of threads calling io_context::run to one. \
+option(
+    beast_no_unit_test_inline
+    "Prevents unit test definitions from being inserted into global table"
+    OFF
+)
+option(
+    single_io_service_thread
+    "Restricts the number of threads calling io_context::run to one. \
   This can be useful when debugging."
-  OFF)
-option(boost_show_deprecated
-  "Allow boost to fail on deprecated usage. Only useful if you're trying\
+    OFF
+)
+option(
+    boost_show_deprecated
+    "Allow boost to fail on deprecated usage. Only useful if you're trying\
   to find deprecated calls."
-  OFF)
+    OFF
+)
 
 if(WIN32)
-  option(beast_disable_autolink "Disables autolinking of system libraries on WIN32" OFF)
+    option(
+        beast_disable_autolink
+        "Disables autolinking of system libraries on WIN32"
+        OFF
+    )
 else()
-  set(beast_disable_autolink OFF CACHE BOOL "WIN32 only" FORCE)
+    set(beast_disable_autolink OFF CACHE BOOL "WIN32 only" FORCE)
 endif()
 
 if(coverage)
-  message(STATUS "coverage build requested - forcing Debug build")
-  set(CMAKE_BUILD_TYPE Debug CACHE STRING "build type" FORCE)
+    message(STATUS "coverage build requested - forcing Debug build")
+    set(CMAKE_BUILD_TYPE Debug CACHE STRING "build type" FORCE)
 endif()

cmake/XrplValidatorKeys.cmake

@@ -1,20 +1,26 @@
-option (validator_keys "Enables building of validator-keys tool as a separate target (imported via FetchContent)" OFF)
-
-if (validator_keys)
-  git_branch (current_branch)
-  # default to tracking VK master branch unless we are on release
-  if (NOT (current_branch STREQUAL "release"))
-    set (current_branch "master")
-  endif ()
-  message (STATUS "Tracking ValidatorKeys branch: ${current_branch}")
-
-  FetchContent_Declare (
+option(
     validator_keys
-    GIT_REPOSITORY https://github.com/ripple/validator-keys-tool.git
-    GIT_TAG        "${current_branch}"
-  )
-  FetchContent_MakeAvailable(validator_keys)
-  set_target_properties(validator-keys PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}")
-  install(TARGETS validator-keys RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+    "Enables building of validator-keys tool as a separate target (imported via FetchContent)"
+    OFF
+)
 
-endif ()
+if(validator_keys)
+    git_branch(current_branch)
+    # default to tracking VK master branch unless we are on release
+    if(NOT (current_branch STREQUAL "release"))
+        set(current_branch "master")
+    endif()
+    message(STATUS "Tracking ValidatorKeys branch: ${current_branch}")
+
+    FetchContent_Declare(
+        validator_keys
+        GIT_REPOSITORY https://github.com/ripple/validator-keys-tool.git
+        GIT_TAG "${current_branch}"
+    )
+    FetchContent_MakeAvailable(validator_keys)
+    set_target_properties(
+        validator-keys
+        PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}"
+    )
+    install(TARGETS validator-keys RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+endif()

cmake/XrplVersion.cmake

@@ -4,12 +4,12 @@
 
 file(STRINGS src/libxrpl/protocol/BuildInfo.cpp BUILD_INFO)
 foreach(line_ ${BUILD_INFO})
-  if(line_ MATCHES "versionString[ ]*=[ ]*\"(.+)\"")
-    set(xrpld_version ${CMAKE_MATCH_1})
-  endif()
+    if(line_ MATCHES "versionString[ ]*=[ ]*\"(.+)\"")
+        set(xrpld_version ${CMAKE_MATCH_1})
+    endif()
 endforeach()
 if(xrpld_version)
-  message(STATUS "xrpld version: ${xrpld_version}")
+    message(STATUS "xrpld version: ${xrpld_version}")
 else()
-  message(FATAL_ERROR "unable to determine xrpld version")
+    message(FATAL_ERROR "unable to determine xrpld version")
 endif()

cmake/add_module.cmake

@@ -13,25 +13,28 @@ include(isolate_headers)
 # add_module(parent b)
 # target_link_libraries(project.libparent.b PUBLIC project.libparent.a)
 function(add_module parent name)
-  set(target ${PROJECT_NAME}.lib${parent}.${name})
-  add_library(${target} OBJECT)
-  file(GLOB_RECURSE sources CONFIGURE_DEPENDS
-    "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}/*.cpp"
-  )
-  target_sources(${target} PRIVATE ${sources})
-  target_include_directories(${target} PUBLIC
-    "$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>"
-  )
-  isolate_headers(
-    ${target}
-    "${CMAKE_CURRENT_SOURCE_DIR}/include"
-    "${CMAKE_CURRENT_SOURCE_DIR}/include/${parent}/${name}"
-    PUBLIC
-  )
-  isolate_headers(
-    ${target}
-    "${CMAKE_CURRENT_SOURCE_DIR}/src"
-    "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}"
-    PRIVATE
-  )
+    set(target ${PROJECT_NAME}.lib${parent}.${name})
+    add_library(${target} OBJECT)
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}/*.cpp"
+    )
+    target_sources(${target} PRIVATE ${sources})
+    target_include_directories(
+        ${target}
+        PUBLIC "$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>"
+    )
+    isolate_headers(
+        ${target}
+        "${CMAKE_CURRENT_SOURCE_DIR}/include"
+        "${CMAKE_CURRENT_SOURCE_DIR}/include/${parent}/${name}"
+        PUBLIC
+    )
+    isolate_headers(
+        ${target}
+        "${CMAKE_CURRENT_SOURCE_DIR}/src"
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}"
+        PRIVATE
+    )
 endfunction()

cmake/create_symbolic_link.cmake

@@ -1,20 +1,21 @@
-# file(CREATE_SYMLINK) only works on Windows with administrator privileges.
-# https://stackoverflow.com/a/61244115/618906
+# file(CREATE_SYMLINK) only works on Windows with administrator privileges. https://stackoverflow.com/a/61244115/618906
 function(create_symbolic_link target link)
-  if(WIN32)
-    if(NOT IS_SYMLINK "${link}")
-      if(NOT IS_ABSOLUTE "${target}")
-        # Relative links work do not work on Windows.
-        set(target "${link}/../${target}")
-      endif()
-      file(TO_NATIVE_PATH "${target}" target)
-      file(TO_NATIVE_PATH "${link}" link)
-      execute_process(COMMAND cmd.exe /c mklink /J "${link}" "${target}")
+    if(WIN32)
+        if(NOT IS_SYMLINK "${link}")
+            if(NOT IS_ABSOLUTE "${target}")
+                # Relative links work do not work on Windows.
+                set(target "${link}/../${target}")
+            endif()
+            file(TO_NATIVE_PATH "${target}" target)
+            file(TO_NATIVE_PATH "${link}" link)
+            execute_process(
+                COMMAND cmd.exe /c mklink /J "${link}" "${target}"
+            )
+        endif()
+    else()
+        file(CREATE_LINK "${target}" "${link}" SYMBOLIC)
+    endif()
+    if(NOT IS_SYMLINK "${link}")
+        message(ERROR "failed to create symlink: <${link}>")
     endif()
-  else()
-    file(CREATE_LINK "${target}" "${link}" SYMBOLIC)
-  endif()
-  if(NOT IS_SYMLINK "${link}")
-    message(ERROR "failed to create symlink: <${link}>")
-  endif()
 endfunction()

cmake/deps/Boost.cmake

@@ -1,50 +1,63 @@
 include(CompilationEnv)
 include(XrplSanitizers)
 
-find_package(Boost REQUIRED
-  COMPONENTS
-    chrono
-    container
-    coroutine
-    date_time
-    filesystem
-    json
-    program_options
-    regex
-    system
-    thread
+find_package(
+    Boost
+    REQUIRED
+    COMPONENTS
+        chrono
+        container
+        context
+        date_time
+        filesystem
+        json
+        program_options
+        regex
+        system
+        thread
 )
 
 add_library(xrpl_boost INTERFACE)
 add_library(Xrpl::boost ALIAS xrpl_boost)
 
-target_link_libraries(xrpl_boost
-  INTERFACE
-    Boost::headers
-    Boost::chrono
-    Boost::container
-    Boost::coroutine
-    Boost::date_time
-    Boost::filesystem
-    Boost::json
-    Boost::process
-    Boost::program_options
-    Boost::regex
-    Boost::system
-    Boost::thread)
-if(Boost_COMPILER)
-  target_link_libraries(xrpl_boost INTERFACE Boost::disable_autolinking)
-endif()
-if(SANITIZERS_ENABLED AND is_clang)
-  # TODO: gcc does not support -fsanitize-blacklist...can we do something else
-  # for gcc ?
-  if(NOT Boost_INCLUDE_DIRS AND TARGET Boost::headers)
-    get_target_property(Boost_INCLUDE_DIRS Boost::headers INTERFACE_INCLUDE_DIRECTORIES)
-  endif()
-  message(STATUS "Adding [${Boost_INCLUDE_DIRS}] to sanitizer blacklist")
-  file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/san_bl.txt "src:${Boost_INCLUDE_DIRS}/*")
-  target_compile_options(opts
+target_link_libraries(
+    xrpl_boost
     INTERFACE
-      # ignore boost headers for sanitizing
-      -fsanitize-blacklist=${CMAKE_CURRENT_BINARY_DIR}/san_bl.txt)
+        Boost::headers
+        Boost::chrono
+        Boost::container
+        Boost::context
+        Boost::date_time
+        Boost::filesystem
+        Boost::json
+        Boost::process
+        Boost::program_options
+        Boost::regex
+        Boost::thread
+)
+if(Boost_COMPILER)
+    target_link_libraries(xrpl_boost INTERFACE Boost::disable_autolinking)
+endif()
+
+# GCC 14+ has a false positive -Wuninitialized warning in Boost.Coroutine2's
+# state.hpp when compiled with -O3. This is due to GCC's intentional behavior
+# change (Bug #98871, #119388) where warnings from inlined system header code
+# are no longer suppressed by -isystem. The warning occurs in operator|= in
+# boost/coroutine2/detail/state.hpp when inlined from push_control_block::destroy().
+# See: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119388
+if(is_gcc AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 14)
+    target_compile_options(xrpl_boost INTERFACE -Wno-uninitialized)
+endif()
+
+# Boost.Context's ucontext backend has ASAN fiber-switching annotations
+# (start/finish_switch_fiber) that are compiled in when BOOST_USE_ASAN is defined.
+# This tells ASAN about coroutine stack switches, preventing false positive
+# stack-use-after-scope errors. BOOST_USE_UCONTEXT ensures the ucontext backend
+# is selected (fcontext does not support ASAN annotations).
+# These defines must match what Boost was compiled with (see conan/profiles/sanitizers).
+if(enable_asan)
+    target_compile_definitions(
+        xrpl_boost
+        INTERFACE BOOST_USE_ASAN BOOST_USE_UCONTEXT
+    )
 endif()

cmake/isolate_headers.cmake

@@ -38,11 +38,11 @@ include(create_symbolic_link)
 #
 # isolate_headers(target A B scope)
 function(isolate_headers target A B scope)
-  file(RELATIVE_PATH C "${A}" "${B}")
-  set(X "${CMAKE_CURRENT_BINARY_DIR}/modules/${target}")
-  set(Y "${X}/${C}")
-  cmake_path(GET Y PARENT_PATH parent)
-  file(MAKE_DIRECTORY "${parent}")
-  create_symbolic_link("${B}" "${Y}")
-  target_include_directories(${target} ${scope} "$<BUILD_INTERFACE:${X}>")
+    file(RELATIVE_PATH C "${A}" "${B}")
+    set(X "${CMAKE_CURRENT_BINARY_DIR}/modules/${target}")
+    set(Y "${X}/${C}")
+    cmake_path(GET Y PARENT_PATH parent)
+    file(MAKE_DIRECTORY "${parent}")
+    create_symbolic_link("${B}" "${Y}")
+    target_include_directories(${target} ${scope} "$<BUILD_INTERFACE:${X}>")
 endfunction()

cmake/target_link_modules.cmake

@@ -7,18 +7,21 @@
 # add_library(project.libparent)
 # target_link_modules(parent PUBLIC a b)
 function(target_link_modules parent scope)
-  set(library ${PROJECT_NAME}.lib${parent})
-  foreach(name ${ARGN})
-    set(module ${library}.${name})
-    get_target_property(sources ${library} SOURCES)
-    list(LENGTH sources before)
-    get_target_property(dupes ${module} SOURCES)
-    list(LENGTH dupes expected)
-    list(REMOVE_ITEM sources ${dupes})
-    list(LENGTH sources after)
-    math(EXPR actual "${before} - ${after}")
-    message(STATUS "${module} with ${expected} sources took ${actual} sources from ${library}")
-    set_target_properties(${library} PROPERTIES SOURCES "${sources}")
-    target_link_libraries(${library} ${scope} ${module})
-  endforeach()
+    set(library ${PROJECT_NAME}.lib${parent})
+    foreach(name ${ARGN})
+        set(module ${library}.${name})
+        get_target_property(sources ${library} SOURCES)
+        list(LENGTH sources before)
+        get_target_property(dupes ${module} SOURCES)
+        list(LENGTH dupes expected)
+        list(REMOVE_ITEM sources ${dupes})
+        list(LENGTH sources after)
+        math(EXPR actual "${before} - ${after}")
+        message(
+            STATUS
+            "${module} with ${expected} sources took ${actual} sources from ${library}"
+        )
+        set_target_properties(${library} PROPERTIES SOURCES "${sources}")
+        target_link_libraries(${library} ${scope} ${module})
+    endforeach()
 endfunction()

cmake/target_protobuf_sources.cmake

@@ -36,27 +36,30 @@ find_package(Protobuf REQUIRED)
 # ARGN:
 #     A list of .proto files.
 function(target_protobuf_sources target prefix)
-  set(dir "${CMAKE_CURRENT_BINARY_DIR}/pb-${target}")
-  file(MAKE_DIRECTORY "${dir}/${prefix}")
+    set(dir "${CMAKE_CURRENT_BINARY_DIR}/pb-${target}")
+    file(MAKE_DIRECTORY "${dir}/${prefix}")
 
-  protobuf_generate(
-    TARGET ${target}
-    PROTOC_OUT_DIR "${dir}/${prefix}"
-    "${ARGN}"
-  )
-  target_include_directories(${target} SYSTEM PUBLIC
-    # Allows #include <package/path/to/file.proto> used by consumer files.
-    $<BUILD_INTERFACE:${dir}>
-    # Allows #include "path/to/file.proto" used by generated files.
-    $<BUILD_INTERFACE:${dir}/${prefix}>
-    # Allows #include <package/path/to/file.proto> used by consumer files.
-    $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>
-    # Allows #include "path/to/file.proto" used by generated files.
-    $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${prefix}>
-  )
-  install(
-    DIRECTORY ${dir}/
-    DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
-    FILES_MATCHING PATTERN "*.h"
-  )
+    protobuf_generate(
+        TARGET ${target}
+        PROTOC_OUT_DIR "${dir}/${prefix}"
+        "${ARGN}"
+    )
+    target_include_directories(
+        ${target}
+        SYSTEM
+        PUBLIC # Allows #include <package/path/to/file.proto> used by consumer files.
+            $<BUILD_INTERFACE:${dir}>
+            # Allows #include "path/to/file.proto" used by generated files.
+            $<BUILD_INTERFACE:${dir}/${prefix}>
+            # Allows #include <package/path/to/file.proto> used by consumer files.
+            $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>
+            # Allows #include "path/to/file.proto" used by generated files.
+            $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${prefix}>
+    )
+    install(
+        DIRECTORY ${dir}/
+        DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
+        FILES_MATCHING
+        PATTERN "*.h"
+    )
 endfunction()

conan.lock

@@ -1,58 +1,70 @@
 {
     "version": "0.5",
     "requires": [
-        "zlib/1.3.1#b8bc2603263cf7eccbd6e17e66b0ed76%1765850150.075",
+        "zlib/1.3.1#cac0f6daea041b0ccf42934163defb20%1774439233.809",
         "xxhash/0.8.3#681d36a0a6111fc56e5e45ea182c19cc%1765850149.987",
-        "sqlite3/3.49.1#8631739a4c9b93bd3d6b753bac548a63%1765850149.926",
-        "soci/4.0.3#a9f8d773cd33e356b5879a4b0564f287%1765850149.46",
+        "sqlite3/3.51.0#66aa11eabd0e34954c5c1c061ad44abe%1763899256.358",
+        "soci/4.0.3#fe32b9ad5eb47e79ab9e45a68f363945%1774450067.231",
         "snappy/1.1.10#968fef506ff261592ec30c574d4a7809%1765850147.878",
-        "secp256k1/0.7.0#9c4ab67bdc3860c16ea5b36aed8f74ea%1765850147.928",
+        "secp256k1/0.7.1#481881709eb0bdd0185a12b912bbe8ad%1770910500.329",
         "rocksdb/10.5.1#4a197eca381a3e5ae8adf8cffa5aacd0%1765850186.86",
-        "re2/20230301#ca3b241baec15bd31ea9187150e0b333%1765850148.103",
-        "protobuf/6.32.1#f481fd276fc23a33b85a3ed1e898b693%1765850161.038",
-        "openssl/3.5.4#1b986e61b38fdfda3b40bebc1b234393%1768312656.257",
-        "nudb/2.0.9#fb8dfd1a5557f5e0528114c2da17721e%1765850143.957",
+        "re2/20251105#8579cfd0bda4daf0683f9e3898f964b4%1774398111.888",
+        "protobuf/6.33.5#d96d52ba5baaaa532f47bda866ad87a5%1773224203.27",
+        "opentelemetry-cpp/1.18.0#efd9851e173f8a13b9c7d35232de8cf1%1750409186.472",
+        "openssl/3.6.1#e6399de266349245a4542fc5f6c71552%1774458290.139",
+        "nudb/2.0.9#0432758a24204da08fee953ec9ea03cb%1769436073.32",
+        "nlohmann_json/3.11.3#45828be26eb619a2e04ca517bb7b828d%1701220705.259",
         "lz4/1.10.0#59fc63cac7f10fbe8e05c7e62c2f3504%1765850143.914",
         "libiconv/1.17#1e65319e945f2d31941a9d28cc13c058%1765842973.492",
+        "libcurl/8.18.0#364bc3755cb9ef84ed9a7ae9c7efc1c1%1770984390.024",
         "libbacktrace/cci.20210118#a7691bfccd8caaf66309df196790a5a1%1765842973.03",
         "libarchive/3.8.1#ffee18995c706e02bf96e7a2f7042e0d%1765850144.736",
         "jemalloc/5.3.0#e951da9cf599e956cebc117880d2d9f8%1729241615.244",
         "gtest/1.17.0#5224b3b3ff3b4ce1133cbdd27d53ee7d%1768312129.152",
-        "grpc/1.72.0#f244a57bff01e708c55a1100b12e1589%1765850193.734",
+        "grpc/1.78.1#b1a9e74b145cc471bed4dc64dc6eb2c1%1772623605.068",
         "ed25519/2015.03#ae761bdc52730a843f0809bdf6c1b1f6%1765850143.772",
         "date/3.0.4#862e11e80030356b53c2c38599ceb32b%1765850143.772",
-        "c-ares/1.34.5#5581c2b62a608b40bb85d965ab3ec7c8%1765850144.336",
+        "c-ares/1.34.6#545240bb1c40e2cacd4362d6b8967650%1774439234.681",
         "bzip2/1.0.8#c470882369c2d95c5c77e970c0c7e321%1765850143.837",
-        "boost/1.88.0#8852c0b72ce8271fb8ff7c53456d4983%1765850172.862",
-        "abseil/20250127.0#99262a368bd01c0ccca8790dfced9719%1766517936.993"
+        "boost/1.90.0#d5e8defe7355494953be18524a7f135b%1769454080.269",
+        "abseil/20250127.0#bb0baf1f362bc4a725a24eddd419b8f7%1774365460.196"
     ],
     "build_requires": [
-        "zlib/1.3.1#b8bc2603263cf7eccbd6e17e66b0ed76%1765850150.075",
-        "strawberryperl/5.32.1.1#707032463aa0620fa17ec0d887f5fe41%1765850165.196",
-        "protobuf/6.32.1#f481fd276fc23a33b85a3ed1e898b693%1765850161.038",
+        "zlib/1.3.1#cac0f6daea041b0ccf42934163defb20%1774439233.809",
+        "strawberryperl/5.32.1.1#8d114504d172cfea8ea1662d09b6333e%1774447376.964",
+        "protobuf/6.33.5#d96d52ba5baaaa532f47bda866ad87a5%1773224203.27",
+        "pkgconf/2.5.1#93c2051284cba1279494a43a4fcfeae2%1757684701.089",
+        "opentelemetry-proto/1.4.0#4096a3b05916675ef9628f3ffd571f51%1732731336.11",
+        "ninja/1.13.2#c8c5dc2a52ed6e4e42a66d75b4717ceb%1764096931.974",
         "nasm/2.16.01#31e26f2ee3c4346ecd347911bd126904%1765850144.707",
-        "msys2/cci.latest#1996656c3c98e5765b25b60ff5cf77b4%1764840888.758",
-        "m4/1.4.19#70dc8bbb33e981d119d2acc0175cf381%1763158052.846",
-        "cmake/4.2.0#ae0a44f44a1ef9ab68fd4b3e9a1f8671%1765850153.937",
-        "cmake/3.31.10#313d16a1aa16bbdb2ca0792467214b76%1765850153.479",
-        "b2/5.3.3#107c15377719889654eb9a162a673975%1765850144.355",
+        "msys2/cci.latest#d22fe7b2808f5fd34d0a7923ace9c54f%1770657326.649",
+        "meson/1.10.0#60786758ea978964c24525de19603cf4%1768294926.103",
+        "m4/1.4.19#5d7a4994e5875d76faf7acf3ed056036%1774365463.87",
+        "libtool/2.4.7#14e7739cc128bc1623d2ed318008e47e%1755679003.847",
+        "gnu-config/cci.20210814#466e9d4d7779e1c142443f7ea44b4284%1762363589.329",
+        "cmake/4.3.0#b939a42e98f593fb34d3a8c5cc860359%1774439249.183",
+        "b2/5.4.2#ffd6084a119587e70f11cd45d1a386e2%1774439233.447",
         "automake/1.16.5#b91b7c384c3deaa9d535be02da14d04f%1755524470.56",
         "autoconf/2.71#51077f068e61700d65bb05541ea1e4b0%1731054366.86",
-        "abseil/20250127.0#99262a368bd01c0ccca8790dfced9719%1766517936.993"
+        "abseil/20250127.0#bb0baf1f362bc4a725a24eddd419b8f7%1774365460.196"
     ],
     "python_requires": [],
     "overrides": {
-        "protobuf/5.27.0": [
-            "protobuf/6.32.1"
+        "boost/1.90.0#d5e8defe7355494953be18524a7f135b": [
+            null,
+            "boost/1.90.0"
+        ],
+        "protobuf/[>=5.27.0 <7]": [
+            "protobuf/6.33.5"
         ],
         "lz4/1.9.4": [
             "lz4/1.10.0"
         ],
-        "boost/1.83.0": [
-            "boost/1.88.0"
+        "sqlite3/[>=3.44 <4]": [
+            "sqlite3/3.51.0"
         ],
-        "sqlite3/3.44.2": [
-            "sqlite3/3.49.1"
+        "boost/1.83.0": [
+            "boost/1.90.0"
         ],
         "lz4/[>=1.9.4 <2]": [
             "lz4/1.10.0#59fc63cac7f10fbe8e05c7e62c2f3504"

conan/profiles/sanitizers

@@ -7,16 +7,21 @@ include(default)
     {% if compiler == "gcc" %}
         {% if "address" in sanitizers or "thread" in sanitizers or "undefinedbehavior" in sanitizers %}
             {% set sanitizer_list = [] %}
+            {% set defines = [] %}
             {% set model_code = "" %}
             {% set extra_cxxflags = ["-fno-omit-frame-pointer", "-O1", "-Wno-stringop-overflow"] %}
 
             {% if "address" in sanitizers %}
                 {% set _ = sanitizer_list.append("address") %}
                 {% set model_code = "-mcmodel=large" %}
+                {% set _ = defines.append("BOOST_USE_ASAN")%}
+                {% set _ = defines.append("BOOST_USE_UCONTEXT")%}
             {% elif "thread" in sanitizers %}
                 {% set _ = sanitizer_list.append("thread") %}
                 {% set model_code = "-mcmodel=medium" %}
                 {% set _ = extra_cxxflags.append("-Wno-tsan") %}
+                {% set _ = defines.append("BOOST_USE_TSAN")%}
+                {% set _ = defines.append("BOOST_USE_UCONTEXT")%}
             {% endif %}
 
             {% if "undefinedbehavior" in sanitizers %}
@@ -29,16 +34,22 @@ include(default)
             tools.build:cxxflags+=['{{sanitizer_flags}} {{" ".join(extra_cxxflags)}}']
             tools.build:sharedlinkflags+=['{{sanitizer_flags}}']
             tools.build:exelinkflags+=['{{sanitizer_flags}}']
+            tools.build:defines+={{defines}}
         {% endif %}
     {% elif compiler == "apple-clang" or compiler == "clang" %}
         {% if "address" in sanitizers or "thread" in sanitizers or "undefinedbehavior" in sanitizers %}
             {% set sanitizer_list = [] %}
+            {% set defines = [] %}
             {% set extra_cxxflags = ["-fno-omit-frame-pointer", "-O1"] %}
 
             {% if "address" in sanitizers %}
                 {% set _ = sanitizer_list.append("address") %}
+                {% set _ = defines.append("BOOST_USE_ASAN")%}
+                {% set _ = defines.append("BOOST_USE_UCONTEXT")%}
             {% elif "thread" in sanitizers %}
                 {% set _ = sanitizer_list.append("thread") %}
+                {% set _ = defines.append("BOOST_USE_TSAN")%}
+                {% set _ = defines.append("BOOST_USE_UCONTEXT")%}
             {% endif %}
 
             {% if "undefinedbehavior" in sanitizers %}
@@ -52,8 +63,24 @@ include(default)
             tools.build:cxxflags+=['{{sanitizer_flags}} {{" ".join(extra_cxxflags)}}']
             tools.build:sharedlinkflags+=['{{sanitizer_flags}}']
             tools.build:exelinkflags+=['{{sanitizer_flags}}']
+            tools.build:defines+={{defines}}
         {% endif %}
     {% endif %}
 {% endif %}
 
-tools.info.package_id:confs+=["tools.build:cxxflags", "tools.build:exelinkflags", "tools.build:sharedlinkflags"]
+tools.info.package_id:confs+=["tools.build:cxxflags", "tools.build:exelinkflags", "tools.build:sharedlinkflags", "tools.build:defines"]
+
+[options]
+{% if sanitizers %}
+    {% if "address" in sanitizers %}
+        # Build Boost.Context with ucontext backend (not fcontext) so that
+        # ASAN fiber-switching annotations (__sanitizer_start/finish_switch_fiber)
+        # are compiled into the library. fcontext (assembly) has no ASAN support.
+        # define=BOOST_USE_ASAN=1 is critical: it must be defined when building
+        # Boost.Context itself so the ucontext backend compiles in the ASAN annotations.
+        boost/*:extra_b2_flags=context-impl=ucontext address-sanitizer=on define=BOOST_USE_ASAN=1
+        boost/*:without_context=False
+        # Boost stacktrace fails to build with some sanitizers
+        boost/*:without_stacktrace=True
+    {% endif %}
+{% endif %}

conanfile.py

@@ -1,9 +1,9 @@
+import os
 import re
 
 from conan.tools.cmake import CMake, CMakeToolchain, cmake_layout
 
 from conan import ConanFile
-from conan import __version__ as conan_version
 
 
 class Xrpl(ConanFile):
@@ -22,6 +22,7 @@ class Xrpl(ConanFile):
         "rocksdb": [True, False],
         "shared": [True, False],
         "static": [True, False],
+        "telemetry": [True, False],
         "tests": [True, False],
         "unity": [True, False],
         "xrpld": [True, False],
@@ -29,11 +30,11 @@ class Xrpl(ConanFile):
 
     requires = [
         "ed25519/2015.03",
-        "grpc/1.72.0",
+        "grpc/1.78.1",
         "libarchive/3.8.1",
         "nudb/2.0.9",
-        "openssl/3.5.4",
-        "secp256k1/0.7.0",
+        "openssl/3.6.1",
+        "secp256k1/0.7.1",
         "soci/4.0.3",
         "zlib/1.3.1",
     ]
@@ -43,7 +44,7 @@ class Xrpl(ConanFile):
     ]
 
     tool_requires = [
-        "protobuf/6.32.1",
+        "protobuf/6.33.5",
     ]
 
     default_options = {
@@ -54,9 +55,13 @@ class Xrpl(ConanFile):
         "rocksdb": True,
         "shared": False,
         "static": True,
+        "telemetry": True,
         "tests": False,
         "unity": False,
         "xrpld": False,
+        "boost/*:without_context": False,
+        "boost/*:without_coroutine": True,
+        "boost/*:without_coroutine2": False,
         "date/*:header_only": True,
         "ed25519/*:shared": False,
         "grpc/*:shared": False,
@@ -126,21 +131,27 @@ class Xrpl(ConanFile):
         if self.settings.compiler in ["clang", "gcc"]:
             self.options["boost"].without_cobalt = True
 
+        # Check if environment variable exists
+        if "SANITIZERS" in os.environ:
+            sanitizers = os.environ["SANITIZERS"]
+            if "address" in sanitizers.lower():
+                self.default_options["fPIC"] = False
+
     def requirements(self):
-        # Conan 2 requires transitive headers to be specified
-        transitive_headers_opt = (
-            {"transitive_headers": True} if conan_version.split(".")[0] == "2" else {}
-        )
-        self.requires("boost/1.88.0", force=True, **transitive_headers_opt)
-        self.requires("date/3.0.4", **transitive_headers_opt)
+        self.requires("boost/1.90.0", force=True, transitive_headers=True)
+        self.requires("date/3.0.4", transitive_headers=True)
         self.requires("lz4/1.10.0", force=True)
-        self.requires("protobuf/6.32.1", force=True)
-        self.requires("sqlite3/3.49.1", force=True)
+        self.requires("protobuf/6.33.5", force=True)
+        self.requires("sqlite3/3.51.0", force=True)
         if self.options.jemalloc:
             self.requires("jemalloc/5.3.0")
         if self.options.rocksdb:
             self.requires("rocksdb/10.5.1")
-        self.requires("xxhash/0.8.3", **transitive_headers_opt)
+        # OpenTelemetry C++ SDK for distributed tracing (optional).
+        # Provides OTLP/HTTP exporter, batch span processor, and trace API.
+        if self.options.telemetry:
+            self.requires("opentelemetry-cpp/1.18.0")
+        self.requires("xxhash/0.8.3", transitive_headers=True)
 
     exports_sources = (
         "CMakeLists.txt",
@@ -168,6 +179,7 @@ class Xrpl(ConanFile):
         tc.variables["rocksdb"] = self.options.rocksdb
         tc.variables["BUILD_SHARED_LIBS"] = self.options.shared
         tc.variables["static"] = self.options.static
+        tc.variables["telemetry"] = self.options.telemetry
         tc.variables["unity"] = self.options.unity
         tc.variables["xrpld"] = self.options.xrpld
         tc.generate()
@@ -196,14 +208,13 @@ class Xrpl(ConanFile):
             "boost::headers",
             "boost::chrono",
             "boost::container",
-            "boost::coroutine",
+            "boost::context",
             "boost::date_time",
             "boost::filesystem",
             "boost::json",
             "boost::program_options",
             "boost::process",
             "boost::regex",
-            "boost::system",
             "boost::thread",
             "date::date",
             "ed25519::ed25519",
@@ -221,3 +232,5 @@ class Xrpl(ConanFile):
         ]
         if self.options.rocksdb:
             libxrpl.requires.append("rocksdb::librocksdb")
+        if self.options.telemetry:
+            libxrpl.requires.append("opentelemetry-cpp::opentelemetry-cpp")

cspell.config.yaml

@@ -1,14 +1,14 @@
 ignorePaths:
   - build/**
   - src/libxrpl/crypto
-  - src/test/** # Will be removed in the future
   - CMakeUserPresets.json
   - Doxyfile
   - docs/**/*.puml
   - cmake/**
   - LICENSE.md
+  - .clang-tidy
 language: en
-allowCompoundWords: true
+allowCompoundWords: true # TODO (#6334)
 ignoreRandomStrings: true
 minWordLength: 5
 dictionaries:
@@ -16,20 +16,29 @@ dictionaries:
   - en_US
   - en_GB
 ignoreRegExpList:
-  - /[rs][1-9A-HJ-NP-Za-km-z]{25,34}/g # addresses and seeds
-  - /(XRPL|BEAST)_[A-Z_0-9]+_H_INCLUDED+/g # include guards
-  - /(XRPL|BEAST)_[A-Z_0-9]+_H+/g # include guards
+  - /\b[rs][1-9A-HJ-NP-Za-km-z]{25,34}/g # addresses and seeds
+  - /\bC[A-Z0-9]{15}/g # CTIDs
+  - /\b(XRPL|BEAST)_[A-Z_0-9]+_H_INCLUDED+/g # include guards
+  - /\b(XRPL|BEAST)_[A-Z_0-9]+_H+/g # include guards
   - /::[a-z:_]+/g # things from other namespaces
-  - /lib[a-z]+/g # libraries
-  - /[0-9]{4}-[0-9]{2}-[0-9]{2}[,:][A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright dates
-  - /[0-9]{4}[,:]?\s*[A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright years
+  - /\blib[a-z]+/g # libraries
+  - /\b[0-9]{4}-[0-9]{2}-[0-9]{2}[,:][A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright dates
+  - /\b[0-9]{4}[,:]?\s*[A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright years
   - /\[[A-Za-z0-9-]+\]\(https:\/\/github.com\/[A-Za-z0-9-]+\)/g # Github usernames
   - /-[DWw][a-zA-Z0-9_-]+=/g # compile flags
   - /[\['"`]-[DWw][a-zA-Z0-9_-]+['"`\]]/g # compile flags
+  - ABCDEFGHIJKLMNOPQRSTUVWXYZ
+  - ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
+overrides:
+  - filename: "**/*_test.cpp" # all test files
+    ignoreRegExpList:
+      - /"[^"]*"/g # double-quoted strings
+      - /'[^']*'/g # single-quoted strings
+      - /`[^`]*`/g # backtick strings
 suggestWords:
   - xprl->xrpl
-  - xprld->xrpld
-  - unsynched->unsynced
+  - xprld->xrpld # cspell: disable-line not sure what this problem is....
+  - unsynched->unsynced # cspell: disable-line not sure what this problem is....
   - synched->synced
   - synch->sync
 words:
@@ -51,6 +60,7 @@ words:
   - Britto
   - Btrfs
   - canonicality
+  - changespq
   - checkme
   - choco
   - chrono
@@ -77,6 +87,8 @@ words:
   - daria
   - dcmake
   - dearmor
+  - Dedup
+  - dedup
   - deleteme
   - demultiplexer
   - deserializaton
@@ -87,8 +99,10 @@ words:
   - doxyfile
   - dxrpl
   - endmacro
+  - EOCFG
   - exceptioned
   - Falco
+  - fcontext
   - finalizers
   - firewalled
   - fmtdur
@@ -101,19 +115,25 @@ words:
   - gpgcheck
   - gpgkey
   - hotwallet
+  - hwaddress
+  - hwrap
   - ifndef
   - inequation
   - insuf
   - insuff
+  - invasively
   - iou
   - ious
   - isrdc
   - itype
   - jemalloc
   - jlog
+  - jtnofill
   - keylet
   - keylets
   - keyvadb
+  - kwarg
+  - kwargs
   - ledgerentry
   - ledgerhash
   - ledgerindex
@@ -135,6 +155,7 @@ words:
   - Metafuncton
   - misprediction
   - mptbalance
+  - MPTDEX
   - mptflags
   - mptid
   - mptissuance
@@ -144,6 +165,7 @@ words:
   - mptokenissuance
   - mptokens
   - mpts
+  - mtgox
   - multisig
   - multisign
   - multisigned
@@ -156,20 +178,31 @@ words:
   - nftokens
   - nftpage
   - nikb
+  - nixfmt
+  - nixos
+  - nixpkgs
+  - NOLINT
+  - NOLINTNEXTLINE
   - nonxrp
   - noripple
+  - nostd
   - nudb
   - nullptr
   - nunl
   - Nyffenegger
   - ostr
+  - pargs
   - partitioner
   - paychan
   - paychans
   - permdex
   - perminute
   - permissioned
+  - pgrep
+  - pkill
   - pointee
+  - populator
+  - pratik
   - preauth
   - preauthorization
   - preauthorize
@@ -178,11 +211,15 @@ words:
   - protobuf
   - protos
   - ptrs
+  - pushd
   - pyenv
+  - pyparsing
   - qalloc
   - queuable
   - Raphson
+  - reparent
   - replayer
+  - reqps
   - rerere
   - retriable
   - RIPD
@@ -204,6 +241,7 @@ words:
   - seqit
   - sf
   - SFIELD
+  - sfields
   - shamap
   - shamapitem
   - sidechain
@@ -238,6 +276,7 @@ words:
   - txjson
   - txn
   - txns
+  - txqueue
   - txs
   - UBSAN
   - ubsan
@@ -268,6 +307,7 @@ words:
   - venv
   - vfalco
   - vinnie
+  - wasmi
   - wextra
   - wptr
   - writeme
@@ -277,6 +317,10 @@ words:
   - xchain
   - ximinez
   - EXPECT_STREQ
+  - Gantt
+  - gantt
+  - otelc
+  - traceql
   - XMACRO
   - xrpkuwait
   - xrpl
@@ -284,3 +328,5 @@ words:
   - xrplf
   - xxhash
   - xxhasher
+  - xychart
+  - zpages

docker/telemetry/.gitignore

@@ -0,0 +1,2 @@
+# Runtime data generated by xrpld and telemetry stack
+data/

docker/telemetry/TESTING.md

@@ -0,0 +1,512 @@
+# OpenTelemetry Integration Testing Guide
+
+This document describes how to verify the rippled OpenTelemetry telemetry
+pipeline end-to-end, from span generation through the observability stack
+(otel-collector, Tempo, Prometheus, Grafana).
+
+---
+
+## Prerequisites
+
+### Build xrpld with telemetry
+
+```bash
+conan install . --build=missing -o telemetry=True
+cmake --preset default -Dtelemetry=ON
+cmake --build --preset default --target xrpld
+```
+
+The binary is at `.build/xrpld`.
+
+### Required tools
+
+- **Docker** with `docker compose` (v2)
+- **curl**
+- **jq** (JSON processor)
+
+### Verify binary
+
+```bash
+.build/xrpld --version
+```
+
+---
+
+## Test 1: Single-Node Standalone (Quick Verification)
+
+This test verifies RPC and transaction spans in standalone mode. Consensus
+spans will not fire because standalone mode does not run consensus.
+
+### Step 1: Start the observability stack
+
+```bash
+docker compose -f docker/telemetry/docker-compose.yml up -d
+```
+
+Wait for services to be ready:
+
+```bash
+# otel-collector health
+curl -sf http://localhost:13133/ && echo "collector ready"
+
+# Tempo readiness
+curl -sf http://localhost:3200/ready > /dev/null && echo "tempo ready"
+```
+
+### Step 2: Start xrpld in standalone mode
+
+```bash
+.build/xrpld --conf docker/telemetry/xrpld-telemetry.cfg -a --start
+```
+
+Wait a few seconds for the node to initialize.
+
+### Step 3: Exercise RPC spans
+
+```bash
+# server_info
+curl -s http://localhost:5005 \
+  -d '{"method":"server_info"}' | jq .result.info.server_state
+
+# server_state
+curl -s http://localhost:5005 \
+  -d '{"method":"server_state"}' | jq .result.state.server_state
+
+# ledger
+curl -s http://localhost:5005 \
+  -d '{"method":"ledger","params":[{"ledger_index":"current"}]}' \
+  | jq .result.ledger_current_index
+```
+
+### Step 4: Submit a transaction
+
+Close the ledger first (required in standalone mode):
+
+```bash
+curl -s http://localhost:5005 -d '{"method":"ledger_accept"}'
+```
+
+Submit a Payment from the genesis account:
+
+```bash
+curl -s http://localhost:5005 -d '{
+  "method": "submit",
+  "params": [{
+    "secret": "snoPBrXtMeMyMHUVTgbuqAfg1SUTb",
+    "tx_json": {
+      "TransactionType": "Payment",
+      "Account": "rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh",
+      "Destination": "rPMh7Pi9ct699iZUTWzJaUMR1o42VEfGqF",
+      "Amount": "10000000"
+    }
+  }]
+}' | jq .result.engine_result
+```
+
+Expected result: `"tesSUCCESS"`.
+
+Close the ledger again to finalize:
+
+```bash
+curl -s http://localhost:5005 -d '{"method":"ledger_accept"}'
+```
+
+### Step 5: Verify traces in Tempo
+
+Wait 5 seconds for the batch export, then:
+
+```bash
+TEMPO="http://localhost:3200"
+
+# Check rippled service is registered
+curl -s "$TEMPO/api/v2/search/tag/resource.service.name/values" | jq '.tagValues[].value'
+
+# Check RPC spans
+curl -s "$TEMPO/api/search" \
+  --data-urlencode 'q={resource.service.name="rippled" && name="rpc.request"}' \
+  --data-urlencode 'limit=5' | jq '.traces | length'
+
+curl -s "$TEMPO/api/search" \
+  --data-urlencode 'q={resource.service.name="rippled" && name="rpc.process"}' \
+  --data-urlencode 'limit=5' | jq '.traces | length'
+
+curl -s "$TEMPO/api/search" \
+  --data-urlencode 'q={resource.service.name="rippled" && name="rpc.command.server_info"}' \
+  --data-urlencode 'limit=5' | jq '.traces | length'
+
+# Check transaction spans
+curl -s "$TEMPO/api/search" \
+  --data-urlencode 'q={resource.service.name="rippled" && name="tx.process"}' \
+  --data-urlencode 'limit=5' | jq '.traces | length'
+```
+
+Or open Grafana Explore with Tempo datasource: http://localhost:3000
+
+### Step 6: Teardown
+
+```bash
+# Kill xrpld (Ctrl+C or)
+kill $(pgrep -f 'xrpld.*xrpld-telemetry')
+
+# Stop observability stack
+docker compose -f docker/telemetry/docker-compose.yml down
+
+# Clean xrpld data
+rm -rf data/
+```
+
+### Expected spans (standalone mode)
+
+| Span Name                   | Expected | Notes                         |
+| --------------------------- | -------- | ----------------------------- |
+| `rpc.request`               | Yes      | Every HTTP RPC call           |
+| `rpc.process`               | Yes      | Every RPC processing          |
+| `rpc.command.server_info`   | Yes      | server_info RPC               |
+| `rpc.command.server_state`  | Yes      | server_state RPC              |
+| `rpc.command.ledger`        | Yes      | ledger RPC                    |
+| `rpc.command.submit`        | Yes      | submit RPC                    |
+| `rpc.command.ledger_accept` | Yes      | ledger_accept RPC             |
+| `tx.process`                | Yes      | Transaction submission        |
+| `tx.receive`                | No       | No peers in standalone        |
+| `consensus.*`               | No       | Consensus disabled standalone |
+
+---
+
+## Test 2: 6-Node Consensus Network (Full Verification)
+
+This test verifies ALL span categories including consensus and peer
+transaction relay, using a 6-node validator network.
+
+### Automated
+
+Run the integration test script:
+
+```bash
+bash docker/telemetry/integration-test.sh
+```
+
+The script will:
+
+1. Start the observability stack
+2. Generate 6 validator key pairs
+3. Create config files for each node
+4. Start all 6 nodes
+5. Wait for consensus ("proposing" state)
+6. Exercise RPC, submit transactions
+7. Verify all span categories in Tempo
+8. Verify spanmetrics in Prometheus
+9. Print results and leave the stack running
+
+### Manual
+
+If you prefer to run the steps manually:
+
+#### Step 1: Start observability stack
+
+```bash
+docker compose -f docker/telemetry/docker-compose.yml up -d
+```
+
+#### Step 2: Generate validator keys
+
+Start a temporary standalone xrpld:
+
+```bash
+.build/xrpld --conf docker/telemetry/xrpld-telemetry.cfg -a --start &
+TEMP_PID=$!
+sleep 5
+```
+
+Generate 6 key pairs:
+
+```bash
+for i in $(seq 1 6); do
+  curl -s http://localhost:5005 \
+    -d '{"method":"validation_create"}' | jq '.result'
+done
+```
+
+Record the `validation_seed` and `validation_public_key` for each.
+Kill the temporary node:
+
+```bash
+kill $TEMP_PID
+rm -rf data/
+```
+
+#### Step 3: Create node configs
+
+For each node (1-6), create a config file. Template:
+
+```ini
+[server]
+port_rpc
+port_peer
+
+[port_rpc]
+port = {5004 + node_number}
+ip = 127.0.0.1
+admin = 127.0.0.1
+protocol = http
+
+[port_peer]
+port = {51234 + node_number}
+ip = 0.0.0.0
+protocol = peer
+
+[node_db]
+type=NuDB
+path=/tmp/xrpld-integration/node{N}/nudb
+online_delete=256
+
+[database_path]
+/tmp/xrpld-integration/node{N}/db
+
+[debug_logfile]
+/tmp/xrpld-integration/node{N}/debug.log
+
+[validation_seed]
+{seed from step 2}
+
+[validators_file]
+/tmp/xrpld-integration/validators.txt
+
+[ips_fixed]
+127.0.0.1 51235
+127.0.0.1 51236
+127.0.0.1 51237
+127.0.0.1 51238
+127.0.0.1 51239
+127.0.0.1 51240
+
+[peer_private]
+1
+
+[telemetry]
+enabled=1
+endpoint=http://localhost:4318/v1/traces
+exporter=otlp_http
+sampling_ratio=1.0
+batch_size=512
+batch_delay_ms=2000
+max_queue_size=2048
+trace_rpc=1
+trace_transactions=1
+trace_consensus=1
+trace_peer=0
+trace_ledger=1
+
+[rpc_startup]
+{ "command": "log_level", "severity": "warning" }
+
+[ssl_verify]
+0
+```
+
+#### Step 4: Create validators.txt
+
+```ini
+[validators]
+{public_key_1}
+{public_key_2}
+{public_key_3}
+{public_key_4}
+{public_key_5}
+{public_key_6}
+```
+
+#### Step 5: Start all 6 nodes
+
+```bash
+for i in $(seq 1 6); do
+  .build/xrpld --conf /tmp/xrpld-integration/node$i/xrpld.cfg --start &
+  echo $! > /tmp/xrpld-integration/node$i/xrpld.pid
+done
+```
+
+#### Step 6: Wait for consensus
+
+Poll each node until `server_state` = `"proposing"`:
+
+```bash
+for port in 5005 5006 5007 5008 5009 5010; do
+  while true; do
+    state=$(curl -s http://localhost:$port \
+      -d '{"method":"server_info"}' \
+      | jq -r '.result.info.server_state')
+    echo "Port $port: $state"
+    [ "$state" = "proposing" ] && break
+    sleep 5
+  done
+done
+```
+
+#### Step 7: Exercise RPC and submit transaction
+
+```bash
+# RPC calls
+curl -s http://localhost:5005 -d '{"method":"server_info"}'
+curl -s http://localhost:5005 -d '{"method":"server_state"}'
+curl -s http://localhost:5005 -d '{"method":"ledger","params":[{"ledger_index":"current"}]}'
+
+# Submit transaction
+curl -s http://localhost:5005 -d '{
+  "method": "submit",
+  "params": [{
+    "secret": "snoPBrXtMeMyMHUVTgbuqAfg1SUTb",
+    "tx_json": {
+      "TransactionType": "Payment",
+      "Account": "rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh",
+      "Destination": "rPMh7Pi9ct699iZUTWzJaUMR1o42VEfGqF",
+      "Amount": "10000000"
+    }
+  }]
+}'
+```
+
+Wait 15 seconds for consensus and batch export.
+
+#### Step 8: Verify in Tempo
+
+See the "Verification Queries" section below.
+
+---
+
+## Expected Span Catalog
+
+All 12 production span names instrumented across Phases 2-4:
+
+| Span Name                   | Source File           | Phase | Key Attributes                                                                    | How to Trigger            |
+| --------------------------- | --------------------- | ----- | --------------------------------------------------------------------------------- | ------------------------- |
+| `rpc.request`               | ServerHandler.cpp:271 | 2     | --                                                                                | Any HTTP RPC call         |
+| `rpc.process`               | ServerHandler.cpp:573 | 2     | --                                                                                | Any HTTP RPC call         |
+| `rpc.ws_message`            | ServerHandler.cpp:384 | 2     | --                                                                                | WebSocket RPC message     |
+| `rpc.command.<name>`        | RPCHandler.cpp:161    | 2     | `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role`                           | Any RPC command           |
+| `tx.process`                | NetworkOPs.cpp:1227   | 3     | `xrpl.tx.hash`, `xrpl.tx.local`, `xrpl.tx.path`                                   | Submit transaction        |
+| `tx.receive`                | PeerImp.cpp:1273      | 3     | `xrpl.peer.id`                                                                    | Peer relays transaction   |
+| `consensus.proposal.send`   | RCLConsensus.cpp:177  | 4     | `xrpl.consensus.round`                                                            | Consensus proposing phase |
+| `consensus.ledger_close`    | RCLConsensus.cpp:282  | 4     | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode`                                | Ledger close event        |
+| `consensus.accept`          | RCLConsensus.cpp:395  | 4     | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms`                        | Ledger accepted           |
+| `consensus.validation.send` | RCLConsensus.cpp:753  | 4     | `xrpl.consensus.ledger.seq`, `xrpl.consensus.proposing`                           | Validation sent           |
+| `consensus.accept.apply`    | RCLConsensus.cpp:453  | 4     | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state` | Ledger apply + close time |
+
+---
+
+## Verification Queries
+
+### Tempo API
+
+Base URL: `http://localhost:3200`
+
+```bash
+TEMPO="http://localhost:3200"
+
+# List all services
+curl -s "$TEMPO/api/v2/search/tag/resource.service.name/values" | jq '.tagValues[].value'
+
+# Query traces by operation
+for op in "rpc.request" "rpc.process" \
+          "rpc.command.server_info" "rpc.command.server_state" "rpc.command.ledger" \
+          "tx.process" "tx.receive" \
+          "consensus.proposal.send" "consensus.ledger_close" \
+          "consensus.accept" "consensus.accept.apply" \
+          "consensus.validation.send"; do
+  count=$(curl -s "$TEMPO/api/search" \
+    --data-urlencode "q={resource.service.name=\"rippled\" && name=\"$op\"}" \
+    --data-urlencode "limit=5" \
+    | jq '.traces | length')
+  printf "%-35s %s traces\n" "$op" "$count"
+done
+```
+
+### Prometheus API
+
+Base URL: `http://localhost:9090`
+
+```bash
+PROM="http://localhost:9090"
+
+# Span call counts (from spanmetrics connector)
+curl -s "$PROM/api/v1/query?query=traces_span_metrics_calls_total" \
+  | jq '.data.result[] | {span: .metric.span_name, count: .value[1]}'
+
+# Latency histogram
+curl -s "$PROM/api/v1/query?query=traces_span_metrics_duration_milliseconds_count" \
+  | jq '.data.result[] | {span: .metric.span_name, count: .value[1]}'
+
+# RPC calls by command
+curl -s "$PROM/api/v1/query?query=traces_span_metrics_calls_total{span_name=~\"rpc.command.*\"}" \
+  | jq '.data.result[] | {command: .metric["xrpl.rpc.command"], count: .value[1]}'
+```
+
+### Grafana
+
+Open http://localhost:3000 (anonymous admin access enabled).
+
+Pre-configured dashboards:
+
+- **RPC Performance**: Request rates, latency percentiles by command
+- **Transaction Overview**: Transaction processing rates and paths
+- **Consensus Health**: Consensus round duration and proposer counts
+
+Pre-configured datasources:
+
+- **Tempo**: Trace data at `http://tempo:3200`
+- **Prometheus**: Metrics at `http://prometheus:9090`
+
+---
+
+## Troubleshooting
+
+### No traces in Tempo
+
+1. Check otel-collector logs:
+   ```bash
+   docker compose -f docker/telemetry/docker-compose.yml logs otel-collector
+   ```
+2. Verify xrpld telemetry config has `enabled=1` and correct endpoint
+3. Check that otel-collector port 4318 is accessible:
+   ```bash
+   curl -sf http://localhost:4318 && echo "reachable"
+   ```
+4. Increase `batch_delay_ms` or decrease `batch_size` in xrpld config
+
+### Nodes not reaching "proposing" state
+
+1. Check that all peer ports (51235-51240) are not in use:
+   ```bash
+   for p in 51235 51236 51237 51238 51239 51240; do
+     ss -tlnp | grep ":$p " && echo "port $p in use"
+   done
+   ```
+2. Verify `[ips_fixed]` lists all 6 peer ports
+3. Verify `validators.txt` has all 6 public keys
+4. Check node debug logs: `tail -50 /tmp/xrpld-integration/node1/debug.log`
+5. Ensure `[peer_private]` is set to `1` (prevents reaching out to public network)
+
+### Transaction not processing
+
+1. Verify genesis account exists:
+   ```bash
+   curl -s http://localhost:5005 \
+     -d '{"method":"account_info","params":[{"account":"rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}]}' \
+     | jq .result.account_data.Balance
+   ```
+2. Check submit response for error codes
+3. In standalone mode, remember to call `ledger_accept` after submitting
+
+### Spanmetrics not appearing in Prometheus
+
+1. Verify otel-collector config has `spanmetrics` connector
+2. Check that the metrics pipeline is configured:
+   ```yaml
+   service:
+     pipelines:
+       metrics:
+         receivers: [spanmetrics]
+         exporters: [prometheus]
+   ```
+3. Verify Prometheus can reach collector:
+   ```bash
+   curl -s http://localhost:9090/api/v1/targets | jq '.data.activeTargets'
+   ```

docker/telemetry/docker-compose.yml

@@ -0,0 +1,84 @@
+# Docker Compose stack for rippled OpenTelemetry observability.
+#
+# Provides services for local development:
+#   - otel-collector: receives OTLP traces from rippled, batches and
+#     forwards them to Tempo. Listens on ports 4317 (gRPC)
+#     and 4318 (HTTP).
+#   - tempo: Grafana Tempo tracing backend, queryable via Grafana Explore
+#     on port 3000. Recommended for production (S3/GCS storage, TraceQL).
+#   - grafana: dashboards on port 3000, pre-configured with Tempo
+#     and Prometheus datasources.
+#
+# Usage:
+#   docker compose -f docker/telemetry/docker-compose.yml up -d
+#
+# Configure rippled to export traces by adding to xrpld.cfg:
+#   [telemetry]
+#   enabled=1
+#   endpoint=http://localhost:4318/v1/traces
+
+version: "3.8"
+
+services:
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:latest
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    ports:
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP (traces + native OTel metrics)
+      - "8889:8889" # Prometheus metrics (spanmetrics + OTLP)
+      - "13133:13133" # Health check
+      # StatsD UDP port removed — beast::insight now uses native OTLP.
+      # Uncomment if using server=statsd fallback:
+      # - "8125:8125/udp"
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
+    depends_on:
+      - tempo
+    networks:
+      - rippled-telemetry
+
+  tempo:
+    image: grafana/tempo:2.7.2
+    command: ["-config.file=/etc/tempo.yaml"]
+    ports:
+      - "3200:3200" # Tempo HTTP API (health, query)
+    volumes:
+      - ./tempo.yaml:/etc/tempo.yaml:ro
+      - tempo-data:/var/tempo
+    networks:
+      - rippled-telemetry
+
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+    depends_on:
+      - otel-collector
+    networks:
+      - rippled-telemetry
+
+  grafana:
+    image: grafana/grafana:latest
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+    ports:
+      - "3000:3000"
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+    depends_on:
+      - tempo
+      - prometheus
+    networks:
+      - rippled-telemetry
+
+volumes:
+  tempo-data:
+
+networks:
+  rippled-telemetry:
+    driver: bridge

docker/telemetry/grafana/dashboards/consensus-health.json

@@ -0,0 +1,454 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Consensus Round Duration",
+      "description": "p95 and p50 duration of consensus accept rounds. The consensus.accept span (RCLConsensus.cpp:395) measures the time to process an accepted ledger including transaction application and state finalization. The span carries xrpl.consensus.proposers and xrpl.consensus.round_time_ms attributes. Normal range is 3-6 seconds on mainnet.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])))",
+          "legendFormat": "P95 Round Duration [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])))",
+          "legendFormat": "P50 Round Duration [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Consensus Proposals Sent Rate",
+      "description": "Rate at which this node sends consensus proposals to the network. Sourced from the consensus.proposal.send span (RCLConsensus.cpp:177) which fires each time the node proposes a transaction set. The span carries xrpl.consensus.round identifying the consensus round number. A healthy proposing node should show steady proposal output.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.proposal.send\"}[5m]))",
+          "legendFormat": "Proposals / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Proposals / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Close Duration",
+      "description": "p95 duration of the ledger close event. The consensus.ledger_close span (RCLConsensus.cpp:282) measures the time from when consensus triggers a ledger close to completion. Carries xrpl.consensus.ledger.seq and xrpl.consensus.mode attributes. Compare with Consensus Round Duration to understand how close timing relates to overall round time.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m])))",
+          "legendFormat": "P95 Close Duration [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Validation Send Rate",
+      "description": "Rate at which this node sends ledger validations to the network. Sourced from the consensus.validation.send span (RCLConsensus.cpp:753). Each validation confirms the node has fully validated a ledger. The span carries xrpl.consensus.ledger.seq and xrpl.consensus.proposing. Should closely track the ledger close rate when the node is healthy.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.validation.send\"}[5m]))",
+          "legendFormat": "Validations / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Apply Duration (doAccept)",
+      "description": "Time spent applying the consensus result to build a new ledger. Measured by the consensus.accept.apply span in doAccept().",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m])))",
+          "legendFormat": "P95 Apply Duration [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m])))",
+          "legendFormat": "P50 Apply Duration [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Close Time Agreement",
+      "description": "Rate of close time agreement vs disagreement across consensus rounds. Based on xrpl.consensus.close_time_correct attribute (true = validators agreed, false = agreed to disagree per avCT_CONSENSUS_PCT).",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m]))",
+          "legendFormat": "Total Rounds / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Rounds / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Consensus Mode Over Time",
+      "description": "Breakdown of consensus ledger close events by the node's consensus mode (Proposing, Observing, Wrong Ledger, Switched Ledger). Grouped by the xrpl.consensus.mode span attribute from consensus.ledger_close. A healthy validator should be predominantly in Proposing mode. Frequent Wrong Ledger or Switched Ledger indicates sync issues.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_consensus_mode, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[5m]))",
+          "legendFormat": "{{xrpl_consensus_mode}} [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Events / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Accept vs Close Rate",
+      "description": "Compares the rate of consensus.accept (ledger accepted after consensus) vs consensus.ledger_close (ledger close initiated). These should track closely in a healthy network. A divergence means some close events are not completing the accept phase, potentially indicating consensus failures or timeouts.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m]))",
+          "legendFormat": "Accepts / Sec [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m]))",
+          "legendFormat": "Closes / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Events / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Validation vs Close Rate",
+      "description": "Compares the rate of consensus.validation.send vs consensus.ledger_close. Each validated ledger should produce one validation message. If validations lag behind closes, the node may be falling behind on validation or experiencing issues with the validation pipeline.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.validation.send\"}[5m]))",
+          "legendFormat": "Validations / Sec [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m]))",
+          "legendFormat": "Closes / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Events / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Consensus Accept Duration Heatmap",
+      "description": "Heatmap showing the distribution of consensus.accept span durations across histogram buckets over time. Each cell represents how many accept events fell into that duration bucket in a 5m window. Useful for detecting outlier consensus rounds that take abnormally long.",
+      "type": "heatmap",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 32
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "yAxis": {
+          "axisLabel": "Duration (ms)"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])) by (le)",
+          "legendFormat": "{{le}}",
+          "format": "heatmap"
+        }
+      ]
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "consensus", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id — e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "consensus_mode",
+        "label": "Consensus Mode",
+        "description": "Filter by consensus mode (Proposing, Observing, Wrong Ledger, Switched Ledger)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total{span_name=\"consensus.ledger_close\"}, xrpl_consensus_mode)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Consensus Health",
+  "uid": "rippled-consensus"
+}

docker/telemetry/grafana/dashboards/ledger-operations.json

@@ -0,0 +1,353 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Ledger Build Rate",
+      "description": "Rate at which new ledgers are being built. The ledger.build span (BuildLedger.cpp:31) wraps the entire buildLedgerImpl() function which creates a new ledger from a parent, applies transactions, flushes SHAMap nodes, and sets the accepted state. Should match the consensus close rate (~0.25/sec on mainnet with ~4s rounds).",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m]))",
+          "legendFormat": "Builds / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Build Duration",
+      "description": "p95 and p50 duration of ledger builds. Measures the full buildLedgerImpl() call including transaction application, SHAMap flushing, and ledger acceptance. The span records xrpl.ledger.seq as an attribute. Long build times indicate expensive transaction sets or I/O pressure from SHAMap flushes.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
+          "legendFormat": "P95 Build Duration [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
+          "legendFormat": "P50 Build Duration [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Validation Rate",
+      "description": "Rate at which ledgers pass the validation threshold and are accepted as fully validated. The ledger.validate span (LedgerMaster.cpp:915) fires in checkAccept() only after the ledger receives sufficient trusted validations (>= quorum). Records xrpl.ledger.seq and xrpl.ledger.validations (the number of validations received).",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.validate\"}[5m]))",
+          "legendFormat": "Validations / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Build Duration Heatmap",
+      "description": "Heatmap showing the distribution of ledger.build durations across histogram buckets over time. Each cell represents the count of ledger builds that fell into that duration bucket in a 5m window. Useful for spotting occasional slow ledger builds that may not appear in percentile charts.",
+      "type": "heatmap",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "yAxis": {
+          "axisLabel": "Duration (ms)"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])) by (le)",
+          "legendFormat": "{{le}}",
+          "format": "heatmap"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Apply Duration",
+      "description": "p95 and p50 duration of applying the consensus transaction set during ledger building. The tx.apply span (BuildLedger.cpp:88) wraps applyTransactions() which iterates through the CanonicalTXSet with multiple retry passes. Records xrpl.ledger.tx_count (successful) and xrpl.ledger.tx_failed (failed) as attributes.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
+          "legendFormat": "P95 tx.apply [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
+          "legendFormat": "P50 tx.apply [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Apply Rate",
+      "description": "Rate of tx.apply span invocations, reflecting how frequently the transaction application phase runs during ledger building. Each ledger build triggers one tx.apply call. Should closely match the ledger build rate.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m]))",
+          "legendFormat": "tx.apply / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Operations / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Store Rate",
+      "description": "Rate at which ledgers are stored into the ledger history. The ledger.store span (LedgerMaster.cpp:409) wraps storeLedger() which inserts the ledger into the LedgerHistory cache. Records xrpl.ledger.seq. Should match the ledger build rate under normal operation.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.store\"}[5m]))",
+          "legendFormat": "Stores / Sec [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Build vs Close Duration",
+      "description": "Compares p95 durations of ledger.build (the actual ledger construction in BuildLedger.cpp) vs consensus.ledger_close (the consensus close event in RCLConsensus.cpp). Build time is a subset of close time. A large gap between them indicates overhead in the consensus pipeline outside of ledger construction itself.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
+          "legendFormat": "P95 ledger.build [{{exported_instance}}]"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m])))",
+          "legendFormat": "P95 consensus.ledger_close [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "ledger", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Ledger Operations",
+  "uid": "rippled-ledger-ops"
+}