Merge remote-tracking branch 'origin/develop' into pratik/otel-phase1a-plan-docs

Co-authored-by: Bart <11445373+bthomee@users.noreply.github.com>

.clang-tidy

@@ -1,173 +1,102 @@
 ---
 Checks: "-*,
-  bugprone-argument-comment,
-  bugprone-assert-side-effect,
-  bugprone-bad-signal-to-kill-thread,
-  bugprone-bool-pointer-implicit-conversion,
-  bugprone-capturing-this-in-member-variable,
-  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-misleading-setter-of-reference,
-  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,
-  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-unused-local-non-trivial-variable,
-  bugprone-unused-raii,
-  bugprone-unused-return-value,
-  bugprone-use-after-move,
-  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-use-enum-class,
-  cppcoreguidelines-virtual-class-destructor,
-  hicpp-ignored-remove-result,
+  bugprone-*,
+  -bugprone-easily-swappable-parameters,
+  -bugprone-exception-escape,
+  -bugprone-implicit-widening-of-multiplication-result,
+  -bugprone-narrowing-conversions,
+  -bugprone-throwing-static-initialization,
+
+  cppcoreguidelines-*,
+  -cppcoreguidelines-avoid-c-arrays,
+  -cppcoreguidelines-avoid-const-or-ref-data-members,
+  -cppcoreguidelines-avoid-do-while,
+  -cppcoreguidelines-avoid-magic-numbers,
+  -cppcoreguidelines-avoid-non-const-global-variables,
+  -cppcoreguidelines-c-copy-assignment-signature,
+  -cppcoreguidelines-interfaces-global-init,
+  -cppcoreguidelines-macro-usage,
+  -cppcoreguidelines-missing-std-forward,
+  -cppcoreguidelines-narrowing-conversions,
+  -cppcoreguidelines-noexcept-move-operations,
+  -cppcoreguidelines-non-private-member-variables-in-classes,
+  -cppcoreguidelines-owning-memory,
+  -cppcoreguidelines-pro-bounds-array-to-pointer-decay,
+  -cppcoreguidelines-pro-bounds-avoid-unchecked-container-access,
+  -cppcoreguidelines-pro-bounds-constant-array-index,
+  -cppcoreguidelines-pro-bounds-pointer-arithmetic,
+  -cppcoreguidelines-pro-type-reinterpret-cast,
+  -cppcoreguidelines-pro-type-union-access,
+  -cppcoreguidelines-special-member-functions,
+
   llvm-namespace-comment,
-  misc-const-correctness,
-  misc-definitions-in-headers,
-  misc-header-include-cycle,
-  misc-include-cleaner,
-  misc-misplaced-const,
-  misc-redundant-expression,
-  misc-static-assert,
-  misc-throw-by-value-catch-by-reference,
-  misc-unused-alias-decls,
-  misc-unused-using-decls,
-  modernize-concat-nested-namespaces,
-  modernize-deprecated-headers,
-  modernize-make-shared,
-  modernize-make-unique,
-  modernize-pass-by-value,
-  modernize-type-traits,
-  modernize-use-designated-initializers,
-  modernize-use-emplace,
-  modernize-use-equals-default,
-  modernize-use-equals-delete,
-  modernize-use-nodiscard,
-  modernize-use-override,
-  modernize-use-ranges,
-  modernize-use-scoped-lock,
-  modernize-use-starts-ends-with,
-  modernize-use-std-numbers,
-  modernize-use-using,
-  performance-faster-string-find,
-  performance-for-range-copy,
-  performance-implicit-conversion-in-loop,
-  performance-inefficient-vector-operation,
-  performance-move-const-arg,
-  performance-move-constructor-init,
-  performance-no-automatic-move,
-  performance-trivially-destructible,
-  readability-ambiguous-smartptr-reset-call,
-  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-identifier-naming,
-  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
+
+  misc-*,
+  -misc-multiple-inheritance,
+  -misc-no-recursion,
+  -misc-non-private-member-variables-in-classes,
+  -misc-override-with-different-visibility,
+  -misc-unused-parameters,
+  -misc-use-anonymous-namespace,
+  -misc-use-internal-linkage,
+
+  modernize-*,
+  -modernize-avoid-c-arrays,
+  -modernize-avoid-c-style-cast,
+  -modernize-return-braced-init-list,
+  -modernize-use-integer-sign-comparison,
+  -modernize-use-trailing-return-type,
+
+  performance-*,
+  -performance-avoid-endl,
+  -performance-enum-size,
+  -performance-noexcept-move-constructor,
+  -performance-unnecessary-copy-initialization,
+  -performance-unnecessary-value-param,
+
+  readability-*,
+  -readability-avoid-const-params-in-decls,
+  -readability-container-data-pointer,
+  -readability-function-cognitive-complexity,
+  -readability-identifier-length,
+  -readability-inconsistent-declaration-parameter-name,
+  -readability-isolate-declaration,
+  -readability-magic-numbers,
+  -readability-named-parameter,
+  -readability-qualified-auto,
+  -readability-redundant-access-specifiers,
+  -readability-static-accessed-through-instance,
+  -readability-uppercase-literal-suffix
   "
 # ---
+# bugprone-narrowing-conversions,                      # This will break a lot of code but we should enable it in the future because it can eliminate a lot of bugs
+# misc-override-with-different-visibility,             # Will be addressed in a future PR, but for now it generates too many warnings
 # 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
 # ---
 
+FormatStyle: file
+
 CheckOptions:
   bugprone-unsafe-functions.ReportMoreUnsafeFunctions: true
   bugprone-unused-return-value.CheckedReturnTypes: ::std::error_code;::std::error_condition;::std::errc
 
-  misc-include-cleaner.IgnoreHeaders: ".*/(detail|impl)/.*;.*fwd\\.h(pp)?;time.h;stdlib.h;sqlite3.h;netinet/in\\.h;sys/resource\\.h;sys/sysinfo\\.h;linux/sysinfo\\.h;__chrono/.*;bits/.*;_abort\\.h;boost/uuid/uuid_hash.hpp;boost/beast/core/flat_buffer\\.hpp;boost/beast/http/field\\.hpp;boost/beast/http/dynamic_body\\.hpp;boost/beast/http/message\\.hpp;boost/beast/http/read\\.hpp;boost/beast/http/write\\.hpp;openssl/obj_mac\\.h"
+  misc-include-cleaner.IgnoreHeaders: ".*/(detail|impl)/.*;.*fwd\\.h(pp)?;time.h;stdlib.h;sqlite3.h;netinet/in\\.h;sys/resource\\.h;sys/sysinfo\\.h;linux/sysinfo\\.h;__chrono/.*;bits/.*;_abort\\.h;boost/.*;openssl/obj_mac\\.h"
 
   readability-braces-around-statements.ShortStatementLines: 2
   readability-identifier-naming.MacroDefinitionCase: UPPER_CASE
+  readability-identifier-naming.NamespaceCase: lower_case
+  readability-identifier-naming.InlineNamespaceCase: lower_case
   readability-identifier-naming.ClassCase: CamelCase
   readability-identifier-naming.StructCase: CamelCase
   readability-identifier-naming.UnionCase: CamelCase
+  readability-identifier-naming.TypeAliasCase: CamelCase
+  readability-identifier-naming.TypedefCase: CamelCase
+  # Member type names mandated by std/Boost concepts. Subtrees that need more
+  # than these carry their own .clang-tidy (include/xrpl/{beast,basics,protocol,
+  # peerfinder}, src/test/beast); one-off cases use an inline NOLINT.
+  readability-identifier-naming.TypeAliasIgnoredRegexp: "^(const_iterator|const_reference|difference_type|duration|iterator|iterator_category|key_type|mapped_type|period|pointer|reference|rep|result_type|size_type|time_point|value_type)$"
+  readability-identifier-naming.TypedefIgnoredRegexp: "^(const_iterator|const_reference|difference_type|duration|iterator|iterator_category|key_type|mapped_type|period|pointer|reference|rep|result_type|size_type|time_point|value_type)$"
   readability-identifier-naming.EnumCase: CamelCase
   readability-identifier-naming.EnumConstantCase: CamelCase
   readability-identifier-naming.ScopedEnumConstantCase: CamelCase
@@ -200,5 +129,5 @@ CheckOptions:
   readability-identifier-naming.GlobalFunctionIgnoredRegexp: "^(to_string|hash_append|tuple_hash)$"
 
 HeaderFilterRegex: '^.*/(tests?|xrpl|xrpld)/.*\.(h|hpp|ipp)$'
-ExcludeHeaderFilterRegex: '^.*/protocol_autogen/.*\.(h|hpp)$'
+ExcludeHeaderFilterRegex: '^.*/protocol_autogen/.*\.(h|hpp)$|^.*\.pb\.h$'
 WarningsAsErrors: "*"

.codecov.yml

@@ -1,10 +1,32 @@
 codecov:
   require_ci_to_pass: true
+  # The C++ and Rust uploads land minutes apart; without this gate Codecov
+  # publishes a near-zero total from whichever one arrives first.
+  notify:
+    after_n_builds: 2
+    wait_for_ci: true
 
 comment:
   behavior: default
   layout: reach,diff,flags,tree,reach
-  show_carryforward_flags: false
+  show_carryforward_flags: true
+  after_n_builds: 2
+
+# C++ and Rust coverage upload from independent workflows under the `cpp` and
+# `rust` flags; carryforward keeps one language's total when only the other reran.
+flag_management:
+  default_rules:
+    carryforward: true
+  individual_flags:
+    - name: cpp
+      carryforward: true
+      paths:
+        - include/
+        - src/
+    - name: rust
+      carryforward: true
+      paths:
+        - crates/
 
 coverage:
   range: "70..85"

.cspell.config.yaml

@@ -7,6 +7,7 @@ ignorePaths:
   - cmake/**
   - LICENSE.md
   - .clang-tidy
+  - nix/check-tools/*.txt # generated, and full of Nix store hashes
 language: en
 allowCompoundWords: true # TODO (#6334)
 ignoreRandomStrings: true
@@ -30,15 +31,15 @@ ignoreRegExpList:
   - ABCDEFGHIJKLMNOPQRSTUVWXYZ
   - ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
 overrides:
-  - filename: "**/*_test.cpp" # all test files
+  - filename:
+      - "**/*_test.cpp" # legacy boost.test files
+      - "src/tests/**/*.cpp" # gtest test files
     ignoreRegExpList:
       - /"[^"]*"/g # double-quoted strings
       - /'[^']*'/g # single-quoted strings
       - /`[^`]*`/g # backtick strings
 suggestWords:
-  - xprl->xrpl
-  - xprld->xrpld # cspell: disable-line not sure what this problem is....
-  - unsynched->unsynced # cspell: disable-line not sure what this problem is....
+  - unsynched->unsynced
   - synched->synced
   - synch->sync
 words:
@@ -60,12 +61,17 @@ words:
   - autobridging
   - bimap
   - bindir
+  - blindings
   - bookdir
   - Bougalis
+  - bthomee
   - Britto
   - Btrfs
   - Buildx
   - canonicality
+  - CGNAT
+  - canonicalised
+  - cctools
   - changespq
   - checkme
   - choco
@@ -73,6 +79,7 @@ words:
   - citardauq
   - clawback
   - clawbacks
+  - clippy
   - cmaketoolchain
   - coeffs
   - coldwallet
@@ -95,6 +102,7 @@ words:
   - daria
   - dcmake
   - dearmor
+  - decryptor
   - dedented
   - deleteme
   - demultiplexer
@@ -105,7 +113,9 @@ words:
   - disablerepo
   - distro
   - doxyfile
+  - dsymutil
   - dxrpl
+  - elgamal
   - enabled
   - enablerepo
   - endmacro
@@ -119,6 +129,9 @@ words:
   - fmtdur
   - fsanitize
   - funclets
+  - Gamal
+  - gantt
+  - Gantt
   - gcov
   - gcovr
   - ghead
@@ -126,11 +139,13 @@ words:
   - godexsoft
   - gpgcheck
   - gpgkey
+  - Hinnant
   - hotwallet
   - hwaddress
   - hwrap
   - ifndef
   - inequation
+  - Injectivity
   - insuf
   - insuff
   - invasively
@@ -159,18 +174,18 @@ words:
   - llection
   - LOCALGOOD
   - logwstream
+  - Lombrozo
+  - lresolv
   - lseq
   - lsmf
   - ltype
   - mathbunnyru
   - mcmodel
   - MEMORYSTATUSEX
-  - MPTAMM
-  - MPTDEX
   - Merkle
-  - Metafuncton
   - misprediction
   - missingok
+  - MPTAMM
   - mptbalance
   - MPTDEX
   - mptflags
@@ -196,6 +211,7 @@ words:
   - nftokens
   - nftpage
   - nikb
+  - Nikolaos
   - nixfmt
   - nixos
   - nixpkgs
@@ -204,6 +220,7 @@ words:
   - nonxrp
   - noreplace
   - noripple
+  - nostd
   - nostdinc
   - notifempty
   - nudb
@@ -212,10 +229,14 @@ words:
   - Nyffenegger
   - onlatest
   - ostr
+  - otelc
+  - otool
+  - oxalica
   - pargs
   - partitioner
   - paychan
   - paychans
+  - Pedersen
   - permdex
   - perminute
   - permissioned
@@ -238,8 +259,17 @@ words:
   - queuable
   - Raphson
   - rcflags
+  - reencrypted
   - replayer
+  - repodata
+  - repomd
+  - rerandomize
+  - rerandomization
+  - rerandomized
+  - rerandomizes
   - rerere
+  - retargeted
+  - retargets
   - retriable
   - RIPD
   - ripdtop
@@ -252,9 +282,13 @@ words:
   - rocksdb
   - Rohrs
   - roundings
+  - rustc
+  - rustfmt
+  - rustup
   - sahyadri
   - Satoshi
   - scons
+  - Schnorr
   - secp
   - sendq
   - seqit
@@ -271,6 +305,9 @@ words:
   - sles
   - soci
   - socidb
+  - Sonatype
+  - sponsee
+  - sponsees
   - SRPMS
   - sslws
   - statsd
@@ -285,12 +322,17 @@ words:
   - stvar
   - stvector
   - stxchainattestations
+  - summands
   - superpeer
   - superpeers
+  - Swatinem
   - takergets
   - takerpays
   - ters
   - TMEndpointv2
+  - toolchain
+  - tparam
+  - traceql
   - trixie
   - tx
   - txid
@@ -298,9 +340,11 @@ words:
   - txjson
   - txn
   - txns
+  - txqueue
   - txs
   - ubsan
   - UBSAN
+  - ufdio
   - umant
   - unacquired
   - unambiguity
@@ -311,15 +355,18 @@ words:
   - unfindable
   - unflatten
   - unfund
+  - ungated
   - unimpair
   - unroutable
   - unscalable
   - unserviced
   - unshareable
   - unshares
+  - unsponsored
   - unsquelch
   - unsquelched
   - unsquelching
+  - unsuffixed
   - unvalidated
   - unveto
   - unvetoed
@@ -337,12 +384,16 @@ words:
   - wthread
   - xbridge
   - xchain
+  - xcrun
   - ximinez
   - XMACRO
+  - xored
   - xrpkuwait
   - xrpl
   - xrpld
   - xrplf
   - xxhash
   - xxhasher
-  - CGNAT
+  - xychart
+  - zpages
+  - zstdio

.envrc

@@ -0,0 +1,14 @@
+watch_file nix/*.nix
+
+# Pinned Rust toolchain, read by nix/packages.nix via fromRustupToolchainFile.
+watch_file rust-toolchain.toml
+
+# The dev shell derivation includes all of conan/ (see nix/devshell.nix), so any
+# change in there has to invalidate direnv's cached environment.
+watch_dir conan
+
+use flake
+
+# Optional, untracked local overrides. To use a different shell, put e.g.
+# `use flake .#formal-verification` in .envrc.local.
+source_env_if_exists .envrc.local

.gersemi/definitions.cmake

@@ -11,6 +11,9 @@ endfunction()
 function(create_symbolic_link target link)
 endfunction()
 
+function(xrpl_add_benchmark name)
+endfunction()
+
 macro(exclude_from_default target_)
 endmacro()
 
@@ -48,6 +51,12 @@ endfunction()
 function(add_module parent name)
 endfunction()
 
+function(verify_target_headers target headers_dir)
+endfunction()
+
+function(_verify_add_headers target dir)
+endfunction()
+
 function(setup_protocol_autogen)
 endfunction()
 
@@ -96,3 +105,6 @@ function(verbose_find_path variable name)
         ${ARGN}
     )
 endfunction()
+
+function(patch_nix_binary target)
+endfunction()

.git-blame-ignore-revs

@@ -5,6 +5,18 @@
 # 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.
 
+# chore: CamelCase for typedef/using in `clang-tidy` (#8177)
+97a1824537d20d82d25bf151a37a7a4532ebf085
+# chore: Rename CamelCase namespaces to snake_case (#7933)
+06488c1318d96f56d0536251bee08ac85fa7fdd3
+# style: Unify style for all Doxygen comments (#7776)
+73b6852a122854140336e6e6bc30a3a4b41aa5fd
+# style: More clang-tidy identifier renaming (#7290)
+a830ab10efed8d3e59ef2fc15d66efdf9c6bb0d8
+# refactor: Rename static constants (#7120)
+5b6e8b6f93b19c1e3f6a3467a25639031d9d9a53
+# chore: More fixes for bad renames (#7092)
+7afdd71a54d562b32a50b29a5aa00bb997dc9053
 # refactor: Enable clang-tidy `readability-identifier-naming` check (#6571)
 8995564ed6b9e453e144bb663303072a3c1ba305
 # refactor: Enable remaining clang-tidy `cppcoreguidelines` checks (#6538)

.github/actions/cargo-cache/action.yml

@@ -0,0 +1,39 @@
+name: Use cargo artifacts cache
+description: >
+  Cache the cargo build artifacts with rust-cache. Never caches ~/.cargo/bin:
+  when saving the cache, rust-cache deletes all binaries that were already
+  present there, which on persistent self-hosted runners wipes the tools
+  installed by prepare-runner. Harmless on ephemeral runners, but kept
+  consistent everywhere.
+
+inputs:
+  workspaces:
+    description: "Workspaces to cache, as 'workspace -> target' lines."
+    required: false
+    default: crates
+  key:
+    description: "Additional part of the cache key."
+    required: false
+    default: ""
+  cache-directories:
+    description: "Additional non-workspace directories to cache."
+    required: false
+    default: ""
+  save-if:
+    description: >
+      Condition for saving the cache after the job. Defaults to save only from develop branch
+    required: false
+    default: ${{ github.ref == 'refs/heads/develop' }}
+
+runs:
+  using: composite
+
+  steps:
+    - name: Use cargo artifacts cache
+      uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
+      with:
+        cache-bin: "false"
+        cache-directories: ${{ inputs.cache-directories }}
+        key: ${{ inputs.key }}
+        save-if: ${{ inputs.save-if }}
+        workspaces: ${{ inputs.workspaces }}

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

@@ -1,44 +0,0 @@
-name: Generate build version number
-description: "Generate build version number."
-
-outputs:
-  version:
-    description: "The generated build version number."
-    value: ${{ steps.version.outputs.version }}
-
-runs:
-  using: composite
-  steps:
-    # When a tag is pushed, the version is used as-is.
-    - name: Generate version for tag event
-      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 (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: ${{ !startsWith(github.ref, 'refs/tags/') }}
-      shell: bash
-      run: |
-        echo 'Extracting version from BuildInfo.cpp.'
-        VERSION="$(cat src/libxrpl/protocol/BuildInfo.cpp | grep "versionString =" | awk -F '"' '{print $2}')"
-        if [[ -z "${VERSION}" ]]; then
-            echo 'Unable to extract version from BuildInfo.cpp.'
-            exit 1
-        fi
-
-        echo 'Appending shortened commit hash to version.'
-        SHA='${{ github.sha }}'
-        VERSION="${VERSION}+${SHA:0:7}"
-
-        echo "VERSION=${VERSION}" >>"${GITHUB_ENV}"
-
-    - name: Output version
-      id: version
-      shell: bash
-      run: echo "version=${VERSION}" >>"${GITHUB_OUTPUT}"

.github/actions/release-info/action.yml

@@ -0,0 +1,39 @@
+name: Release info
+description: "Derive the version, release channel and package release number for this build."
+
+outputs:
+  version:
+    description: "The build version number."
+    value: ${{ steps.version.outputs.version }}
+  channel:
+    description: "The release channel this build belongs to."
+    value: ${{ steps.release_info.outputs.channel }}
+  pkg_release:
+    description: "The package release number: 1 for a tag, <run number>.<commit date>git<short commit hash> otherwise."
+    value: ${{ steps.release_info.outputs.pkg_release }}
+
+runs:
+  using: composite
+  steps:
+    # A tag names its own version. Anything else is a development build named by
+    # its commit hash, matching what cmake/XrplVersion.cmake derives: the head of
+    # a pull request rather than the merge commit GitHub creates for it.
+    - name: Determine version
+      id: version
+      shell: bash
+      env:
+        IS_TAG: ${{ startsWith(github.ref, 'refs/tags/') }}
+        REF_NAME: ${{ github.ref_name }}
+        SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+      run: |
+        if [[ "${IS_TAG}" == "true" ]]; then
+            version="${REF_NAME}"
+        else
+            version="0.0.0-dev+${SHA:0:7}"
+        fi
+
+        echo "version=${version}" | tee -a "${GITHUB_OUTPUT}"
+
+    - name: Determine release channel and package release
+      id: release_info
+      uses: XRPLF/actions/release-info@a9f2eeca6fb3980ba3a84cf68566f1c69ad30674

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

@@ -9,7 +9,7 @@ inputs:
   remote_url:
     description: "The URL of the Conan endpoint to use."
     required: false
-    default: https://conan.ripplex.io
+    default: https://conan.xrplf.org/repository/conan/
 
 runs:
   using: composite

.github/actions/setup-nix-env/action.yml

@@ -0,0 +1,70 @@
+name: Setup Nix environment
+description: "Build the flake's CI environment and put its tools on PATH."
+
+# The environment from nix/ci-env.nix, the same one the Linux CI images bake in
+# (see nix/docker). Exported onto PATH rather than entered with `nix develop`:
+# the composite actions below run plain `bash` and would escape a dev shell.
+
+runs:
+  using: composite
+
+  steps:
+    - name: Build the CI environment
+      id: build
+      shell: bash
+      env:
+        # --out-link doubles as a GC root for the length of the job.
+        OUT_LINK: ${{ runner.temp }}/xrpld-ci-env
+      run: |
+        # --extra-experimental-features: flakes may not be on in the runner's nix.conf.
+        nix --extra-experimental-features "nix-command flakes" \
+            build .#default --out-link "${OUT_LINK}" --print-build-logs
+        echo "path=$(readlink -f "${OUT_LINK}")" >>"${GITHUB_OUTPUT}"
+
+    - name: Export the environment
+      shell: bash
+      env:
+        ENV_PATH: ${{ steps.build.outputs.path }}
+      run: |
+        echo "${ENV_PATH}/bin" >>"${GITHUB_PATH}"
+
+        # Already KEY=VALUE per line. See `darwinEnv` in nix/ci-env.nix.
+        ENV_FILE="${ENV_PATH}/share/xrpld-ci-env/env"
+        if [ -f "${ENV_FILE}" ]; then
+            cat "${ENV_FILE}" >>"${GITHUB_ENV}"
+        fi
+
+        # XrplSanity.cmake otherwise rejects a Nix compiler as one that leaked.
+        echo "XRPL_DEVSHELL=ci-env" >>"${GITHUB_ENV}"
+
+        # Unlike the Linux nix images, macOS needs no SSL_CERT_FILE: it has its
+        # own trust store, and pinning would break TLS to hosts relying on it.
+
+        # In RUNNER_TEMP, which the runner empties per job, like the `.conan2`
+        # prepare-runner hands the system toolchain - but under its own name:
+        # that Conan is a different version, and the two would migrate each
+        # other's cache.
+        echo "CONAN_HOME=${RUNNER_TEMP}/.conan2-nix" >>"${GITHUB_ENV}"
+
+    # Config, profiles and remote, exactly as the dev shell sets them up on
+    # entry; the `setup-conan` action is skipped for this toolchain.
+    - name: Setup Conan
+      shell: bash
+      run: ./conan/init.sh
+
+    # `Check tools` runs later but swallows failures; a bad export would just
+    # build with the system toolchain.
+    - name: Verify the toolchain resolves into the Nix store
+      shell: bash
+      run: |
+        for tool in clang clang++ cmake ninja conan; do
+            path="$(command -v "${tool}" || true)"
+            echo "${tool} -> ${path:-<not found>}"
+            case "${path}" in
+                /nix/store/*) ;;
+                *)
+                    echo "::error::${tool} does not resolve into the Nix store"
+                    exit 1
+                    ;;
+            esac
+        done

.github/dependabot.yml

@@ -4,7 +4,8 @@ updates:
     directories:
       - /
       - .github/actions/build-deps/
-      - .github/actions/generate-version/
+      - .github/actions/cargo-cache/
+      - .github/actions/release-info/
       - .github/actions/set-compiler-env/
       - .github/actions/setup-conan/
     schedule:
@@ -15,3 +16,23 @@ updates:
     commit-message:
       prefix: "ci: [DEPENDABOT] "
     target-branch: develop
+    groups:
+      github-actions:
+        patterns:
+          - "*"
+
+  - package-ecosystem: cargo
+    directory: /crates
+    schedule:
+      interval: weekly
+      day: monday
+      time: "04:00"
+      timezone: Etc/GMT
+    commit-message:
+      prefix: "chore: [DEPENDABOT] "
+    target-branch: develop
+    open-pull-requests-limit: 10
+    groups:
+      rust-dependencies:
+        patterns:
+          - "*"

.github/pull_request_template.md

@@ -1,10 +1,10 @@
 <!--
-This PR template helps you to write a good pull request description.
+This PR template helps you write a good pull request description.
 Please feel free to include additional useful information even beyond what is requested below.
 
 If your branch is on a personal fork and has a name that allows it to
 run CI build/test jobs (e.g. "ci/foo"), remember to rename it BEFORE
-opening the PR.  This avoids unnecessary redundant test runs. Renaming
+opening the PR. This avoids redundant test runs. Renaming
 the branch after opening the PR will close the PR.
 https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-repository/managing-branches-in-your-repository/renaming-a-branch
 -->
@@ -15,10 +15,10 @@ https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-
 Please include a summary of the changes.
 This may be a direct input to the release notes.
 If too broad, please consider splitting into multiple PRs.
-If a relevant task or issue, please link it here.
+If there is a relevant task or issue, please link it here.
 -->
 
-### Context of Change
+## Context of Change
 
 <!--
 Please include the context of a change.
@@ -29,7 +29,7 @@ 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.
 -->
 
-### API Impact
+## API Impact
 
 <!--
 Please check [x] relevant options, delete irrelevant ones.
@@ -65,5 +65,5 @@ This section may not be needed if your change includes thoroughly commented unit
 
 <!--
 ## Future Tasks
-For future tasks related to PR.
+For future tasks related to this PR.
 -->

.github/scripts/levelization/README.md

@@ -40,18 +40,18 @@ listed later.
 | 04           | xrpl/protocol                       |
 | 05           | xrpl/core xrpl/resource xrpl/server |
 | 06           | xrpl/ledger xrpl/nodestore xrpl/net |
-| 07           | xrpl/shamap                         |
+| 07           | xrpl/shamap xrpl/consensus          |
 
 ## xrpld Modules (Application Implementation)
 
-| Level / Tier | Module(s)                        |
-| ------------ | -------------------------------- |
-| 05           | xrpld/conditions xrpld/consensus |
-| 06           | xrpld/core xrpld/peerfinder      |
-| 07           | xrpld/shamap xrpld/overlay       |
-| 08           | xrpld/app                        |
-| 09           | xrpld/rpc                        |
-| 10           | xrpld/perflog                    |
+| Level / Tier | Module(s)                   |
+| ------------ | --------------------------- |
+| 05           | xrpld/conditions            |
+| 06           | xrpld/core xrpld/peerfinder |
+| 07           | xrpld/shamap xrpld/overlay  |
+| 08           | xrpld/app                   |
+| 09           | xrpld/rpc                   |
+| 10           | xrpld/perflog               |
 
 ## Test Modules
 

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

@@ -1,15 +1,6 @@
-Loop: test.jtx test.toplevel
-  test.toplevel > test.jtx
-
-Loop: test.jtx test.unit_test
-  test.unit_test ~= test.jtx
-
 Loop: xrpld.app xrpld.overlay
   xrpld.app > xrpld.overlay
 
-Loop: xrpld.app xrpld.peerfinder
-  xrpld.peerfinder ~= xrpld.app
-
 Loop: xrpld.app xrpld.rpc
   xrpld.rpc > xrpld.app
 

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

@@ -1,8 +1,13 @@
+benchmarks.libxrpl > xrpl.basics
+benchmarks.libxrpl > xrpl.config
+benchmarks.libxrpl > xrpl.nodestore
 libxrpl.basics > xrpl.basics
 libxrpl.conditions > xrpl.basics
 libxrpl.conditions > xrpl.conditions
 libxrpl.config > xrpl.basics
 libxrpl.config > xrpl.config
+libxrpl.consensus > xrpl.basics
+libxrpl.consensus > xrpl.consensus
 libxrpl.core > xrpl.basics
 libxrpl.core > xrpl.core
 libxrpl.core > xrpl.json
@@ -14,7 +19,6 @@ libxrpl.ledger > xrpl.json
 libxrpl.ledger > xrpl.ledger
 libxrpl.ledger > xrpl.nodestore
 libxrpl.ledger > xrpl.protocol
-libxrpl.ledger > xrpl.server
 libxrpl.ledger > xrpl.shamap
 libxrpl.net > xrpl.basics
 libxrpl.net > xrpl.net
@@ -23,6 +27,9 @@ libxrpl.nodestore > xrpl.config
 libxrpl.nodestore > xrpl.json
 libxrpl.nodestore > xrpl.nodestore
 libxrpl.nodestore > xrpl.protocol
+libxrpl.peerfinder > xrpl.basics
+libxrpl.peerfinder > xrpl.peerfinder
+libxrpl.peerfinder > xrpl.protocol
 libxrpl.protocol > xrpl.basics
 libxrpl.protocol > xrpl.json
 libxrpl.protocol > xrpl.protocol
@@ -58,9 +65,9 @@ test.app > test.jtx
 test.app > test.unit_test
 test.app > xrpl.basics
 test.app > xrpl.config
+test.app > xrpl.consensus
 test.app > xrpl.core
 test.app > xrpld.app
-test.app > xrpld.consensus
 test.app > xrpld.core
 test.app > xrpld.overlay
 test.app > xrpld.rpc
@@ -73,22 +80,16 @@ test.app > xrpl.server
 test.app > xrpl.shamap
 test.app > xrpl.tx
 test.basics > test.jtx
-test.basics > test.unit_test
 test.basics > xrpl.basics
 test.basics > xrpl.core
-test.basics > xrpld.rpc
 test.basics > xrpl.json
 test.basics > xrpl.protocol
 test.beast > xrpl.basics
 test.conditions > xrpl.basics
 test.conditions > xrpl.conditions
-test.consensus > test.csf
 test.consensus > test.jtx
-test.consensus > test.toplevel
-test.consensus > test.unit_test
 test.consensus > xrpl.basics
 test.consensus > xrpld.app
-test.consensus > xrpld.consensus
 test.consensus > xrpl.ledger
 test.consensus > xrpl.protocol
 test.consensus > xrpl.shamap
@@ -103,18 +104,15 @@ test.core > xrpl.json
 test.core > xrpl.protocol
 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.json > test.jtx
 test.json > xrpl.json
+test.jtx > test.unit_test
 test.jtx > xrpl.basics
 test.jtx > xrpl.config
 test.jtx > xrpl.core
 test.jtx > xrpld.app
 test.jtx > xrpld.core
+test.jtx > xrpld.overlay
 test.jtx > xrpld.rpc
 test.jtx > xrpl.json
 test.jtx > xrpl.ledger
@@ -132,12 +130,9 @@ test.ledger > xrpl.json
 test.ledger > xrpl.ledger
 test.ledger > xrpl.protocol
 test.nodestore > test.jtx
-test.nodestore > test.unit_test
 test.nodestore > xrpl.basics
-test.nodestore > xrpl.config
 test.nodestore > xrpld.core
 test.nodestore > xrpl.nodestore
-test.nodestore > xrpl.protocol
 test.nodestore > xrpl.rdb
 test.overlay > test.jtx
 test.overlay > test.unit_test
@@ -146,27 +141,19 @@ test.overlay > xrpl.config
 test.overlay > xrpld.app
 test.overlay > xrpld.core
 test.overlay > xrpld.overlay
-test.overlay > xrpld.peerfinder
 test.overlay > xrpl.json
 test.overlay > xrpl.nodestore
+test.overlay > xrpl.peerfinder
 test.overlay > xrpl.protocol
 test.overlay > xrpl.resource
 test.overlay > xrpl.server
 test.overlay > xrpl.shamap
-test.peerfinder > test.beast
-test.peerfinder > test.unit_test
-test.peerfinder > xrpl.basics
-test.peerfinder > xrpld.core
-test.peerfinder > xrpld.peerfinder
-test.peerfinder > xrpl.protocol
 test.protocol > test.jtx
 test.protocol > test.unit_test
 test.protocol > xrpl.basics
+test.protocol > xrpld.core
 test.protocol > xrpl.json
 test.protocol > xrpl.protocol
-test.resource > test.unit_test
-test.resource > xrpl.basics
-test.resource > xrpl.resource
 test.rpc > test.jtx
 test.rpc > xrpl.basics
 test.rpc > xrpl.config
@@ -190,43 +177,49 @@ test.server > xrpld.core
 test.server > xrpl.json
 test.server > xrpl.protocol
 test.server > xrpl.server
-test.shamap > test.unit_test
-test.shamap > xrpl.basics
-test.shamap > xrpl.config
-test.shamap > xrpl.nodestore
-test.shamap > xrpl.protocol
-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 > xrpl.config
+tests.libxrpl > xrpl.consensus
 tests.libxrpl > xrpl.core
 tests.libxrpl > xrpl.json
 tests.libxrpl > xrpl.ledger
 tests.libxrpl > xrpl.net
 tests.libxrpl > xrpl.nodestore
+tests.libxrpl > xrpl.peerfinder
 tests.libxrpl > xrpl.protocol
 tests.libxrpl > xrpl.protocol_autogen
+tests.libxrpl > xrpl.resource
 tests.libxrpl > xrpl.server
 tests.libxrpl > xrpl.shamap
 tests.libxrpl > xrpl.tx
+tests.xrpld > xrpld.rpc
+tests.xrpld > xrpl.json
+tests.xrpld > xrpl.protocol
 xrpl.conditions > xrpl.basics
 xrpl.conditions > xrpl.protocol
 xrpl.config > xrpl.basics
+xrpl.consensus > xrpl.basics
+xrpl.consensus > xrpl.json
+xrpl.consensus > xrpl.ledger
+xrpl.consensus > 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.json
+xrpl.ledger > xrpl.nodestore
 xrpl.ledger > xrpl.protocol
-xrpl.ledger > xrpl.server
 xrpl.ledger > xrpl.shamap
 xrpl.net > xrpl.basics
 xrpl.nodestore > xrpl.basics
 xrpl.nodestore > xrpl.config
+xrpl.nodestore > xrpl.json
 xrpl.nodestore > xrpl.protocol
+xrpl.peerfinder > xrpl.basics
+xrpl.peerfinder > xrpl.protocol
 xrpl.protocol > xrpl.basics
 xrpl.protocol > xrpl.json
 xrpl.protocol_autogen > xrpl.json
@@ -243,7 +236,6 @@ 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
@@ -254,23 +246,20 @@ xrpl.tx > xrpl.protocol
 xrpld.app > test.unit_test
 xrpld.app > xrpl.basics
 xrpld.app > xrpl.config
+xrpld.app > xrpl.consensus
 xrpld.app > xrpl.core
-xrpld.app > xrpld.consensus
 xrpld.app > xrpld.core
 xrpld.app > xrpl.json
 xrpld.app > xrpl.ledger
 xrpld.app > xrpl.net
 xrpld.app > xrpl.nodestore
+xrpld.app > xrpl.peerfinder
 xrpld.app > xrpl.protocol
 xrpld.app > xrpl.rdb
 xrpld.app > xrpl.resource
 xrpld.app > xrpl.server
 xrpld.app > xrpl.shamap
 xrpld.app > xrpl.tx
-xrpld.consensus > xrpl.basics
-xrpld.consensus > xrpl.json
-xrpld.consensus > xrpl.ledger
-xrpld.consensus > xrpl.protocol
 xrpld.core > xrpl.basics
 xrpld.core > xrpl.config
 xrpld.core > xrpl.core
@@ -279,28 +268,31 @@ xrpld.core > xrpl.protocol
 xrpld.core > xrpl.rdb
 xrpld.overlay > xrpl.basics
 xrpld.overlay > xrpl.config
+xrpld.overlay > xrpl.consensus
 xrpld.overlay > xrpl.core
-xrpld.overlay > xrpld.consensus
 xrpld.overlay > xrpld.core
 xrpld.overlay > xrpld.peerfinder
 xrpld.overlay > xrpl.json
 xrpld.overlay > xrpl.ledger
+xrpld.overlay > xrpl.peerfinder
 xrpld.overlay > xrpl.protocol
 xrpld.overlay > xrpl.resource
 xrpld.overlay > xrpl.server
 xrpld.overlay > xrpl.shamap
 xrpld.overlay > xrpl.tx
 xrpld.peerfinder > xrpl.basics
-xrpld.peerfinder > xrpl.config
+xrpld.peerfinder > xrpld.app
 xrpld.peerfinder > xrpld.core
-xrpld.peerfinder > xrpl.protocol
+xrpld.peerfinder > xrpl.peerfinder
 xrpld.peerfinder > xrpl.rdb
 xrpld.perflog > xrpl.basics
 xrpld.perflog > xrpl.config
 xrpld.perflog > xrpl.core
-xrpld.perflog > xrpld.rpc
+xrpld.perflog > xrpld.app
 xrpld.perflog > xrpl.json
+xrpld.perflog > xrpl.nodestore
 xrpld.perflog > xrpl.protocol
+xrpld.perflog > xrpl.server
 xrpld.rpc > xrpl.basics
 xrpld.rpc > xrpl.config
 xrpld.rpc > xrpl.core
@@ -317,5 +309,6 @@ xrpld.rpc > xrpl.shamap
 xrpld.rpc > xrpl.tx
 xrpld.shamap > xrpl.basics
 xrpld.shamap > xrpld.core
+xrpld.shamap > xrpl.nodestore
 xrpld.shamap > xrpl.protocol
 xrpld.shamap > xrpl.shamap

.github/scripts/releasing/check-merge-back-commits.sh

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+
+# Exit the script as soon as an error occurs.
+set -euo pipefail
+
+# This script fails if <head> merges a release back into <base>,
+# but also adds commits that aren't on a release or staging branch, see RELEASING.md.
+# Merge commits are allowed.
+# Usage: .github/scripts/releasing/check-merge-back-commits.sh <base> <head>
+
+if [ "$#" -ne 2 ]; then
+    echo "Usage: $0 <base> <head>"
+    exit 1
+fi
+
+BASE=$1
+HEAD=$2
+
+SCRIPT_DIR=$(dirname "${BASH_SOURCE[0]}")
+# shellcheck source=.github/scripts/releasing/common.sh
+source "${SCRIPT_DIR}/common.sh"
+load_release_branches
+
+# A PR is a merge-back if some of its commits are on a release or staging branch.
+PR_COUNT=$(git rev-list --no-merges --count "${BASE}..${HEAD}")
+NEW_COUNT=$(git rev-list --no-merges --count "${BASE}..${HEAD}" --not "${BRANCHES[@]}")
+if ((NEW_COUNT == PR_COUNT)); then
+    echo "This PR doesn't merge a release back."
+    exit 0
+fi
+if ((NEW_COUNT == 0)); then
+    echo "This merge-back adds no commits of its own."
+    exit 0
+fi
+
+echo "This PR merges a release back, but also adds commits that aren't on a release or staging branch:"
+git log --no-merges --format='  %h %s' "${BASE}..${HEAD}" --not "${BRANCHES[@]}"
+echo
+echo "Make these changes in a separate PR, see RELEASING.md."
+exit 1

.github/scripts/releasing/check-no-copied-release-commits.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+
+# Exit the script as soon as an error occurs.
+set -euo pipefail
+
+# This script fails if the commits in <base>..<head> copy commits from a release or staging branch
+# (e.g. by rebasing or cherry-picking them) instead of merging that branch, see RELEASING.md.
+# Commits are compared by patch-id,
+# and only against release and staging commits that <head> does not already contain.
+# Usage: .github/scripts/releasing/check-no-copied-release-commits.sh <base> <head>
+
+if [ "$#" -ne 2 ]; then
+    echo "Usage: $0 <base> <head>"
+    exit 1
+fi
+
+BASE=$1
+HEAD=$2
+
+patch_ids() {
+    git log --no-merges --patch --no-color --no-ext-diff "$@" | git patch-id --stable | sort
+}
+
+SCRIPT_DIR=$(dirname "${BASH_SOURCE[0]}")
+# shellcheck source=.github/scripts/releasing/common.sh
+source "${SCRIPT_DIR}/common.sh"
+load_release_branches
+
+# Each line is "<patch-id> <commit>".
+RELEASE_PATCHES=$(patch_ids "${BRANCHES[@]}" --not "${HEAD}")
+PR_PATCHES=$(patch_ids "${BASE}..${HEAD}")
+
+# Each line is "<patch-id> <release commit> <PR commit>".
+COPIES=$(join <(echo "${RELEASE_PATCHES}") <(echo "${PR_PATCHES}"))
+if [ -z "${COPIES}" ]; then
+    echo "No copied release commits found."
+    exit 0
+fi
+
+echo "These commits copy release commits instead of merging them:"
+while read -r _ RELEASE_COMMIT PR_COMMIT; do
+    echo "  $(git log -1 --format='%h %s' "${PR_COMMIT}") (copies ${RELEASE_COMMIT:0:10})"
+done <<<"${COPIES}"
+echo
+echo "Merge the release tag (or branch) instead, see RELEASING.md."
+exit 1

.github/scripts/releasing/check-no-merge-back.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+
+# Exit the script as soon as an error occurs.
+set -euo pipefail
+
+# This script fails if <head> contains release or staging commits that <base> does not,
+# i.e. if <head> merges a release back into <base>.
+# Used in the merge queue, which squashes PRs and would drop the merge commit, see RELEASING.md.
+# Usage: .github/scripts/releasing/check-no-merge-back.sh <base> <head>
+
+if [ "$#" -ne 2 ]; then
+    echo "Usage: $0 <base> <head>"
+    exit 1
+fi
+
+BASE=$1
+HEAD=$2
+
+SCRIPT_DIR=$(dirname "${BASH_SOURCE[0]}")
+# shellcheck source=.github/scripts/releasing/common.sh
+source "${SCRIPT_DIR}/common.sh"
+load_release_branches
+
+RELEASE_COMMITS=$(git rev-list "${BRANCHES[@]}" --not "${BASE}")
+HEAD_COMMITS=$(git rev-list "${BASE}..${HEAD}")
+# The release commits in <head>, newest first.
+MERGED=$(grep -xF -f <(echo "${RELEASE_COMMITS}") <<<"${HEAD_COMMITS}" || true)
+if [ -z "${MERGED}" ]; then
+    echo "No release commits are merged back."
+    exit 0
+fi
+
+echo "This PR merges $(wc -l <<<"${MERGED}" | tr -d ' ') release commits back, e.g.:"
+head -5 <<<"${MERGED}" | xargs git log --no-walk --format='  %h %s'
+echo
+echo "Merge-backs must not go through the merge queue, which squashes them."
+echo "Fast-forward develop to the PR branch instead, see RELEASING.md."
+exit 1

.github/scripts/releasing/check-releases-merged.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+
+# Exit the script as soon as an error occurs.
+set -euo pipefail
+
+# This script fails if a final release (a tag like 3.4.0) on a release branch
+# is not merged back into <develop> within a few days, see RELEASING.md.
+# Usage: .github/scripts/releasing/check-releases-merged.sh <develop>
+
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 <develop>"
+    exit 1
+fi
+
+DEVELOP=$1
+GRACE_DAYS=3
+
+mapfile -t MERGED_ARGS < <(git for-each-ref --format='--merged=%(refname)' 'refs/remotes/*/release/*')
+if [ "${#MERGED_ARGS[@]}" -eq 0 ]; then
+    echo "Error: No release branches found."
+    exit 1
+fi
+
+# Tags on a release branch that <develop> does not contain.
+TAGS=$(git for-each-ref --format='%(refname:short) %(creatordate:unix)' \
+    "${MERGED_ARGS[@]}" --no-merged="${DEVELOP}" 'refs/tags/[0-9]*')
+
+MISSING=0
+while read -r TAG CREATED; do
+    if ! [[ "${TAG}" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+        continue
+    fi
+    if (($(date +%s) - CREATED < GRACE_DAYS * 86400)); then
+        echo "${TAG}: not merged yet, still within the ${GRACE_DAYS}-day grace period."
+    else
+        echo "${TAG}: not merged into develop."
+        MISSING=1
+    fi
+done <<<"${TAGS}"
+
+if [ "${MISSING}" -ne 0 ]; then
+    echo
+    echo "Merge the missing releases back into develop, see RELEASING.md."
+    exit 1
+fi
+echo "No releases past the grace period are missing from develop."

.github/scripts/releasing/common.sh

@@ -0,0 +1,12 @@
+# shellcheck shell=bash
+
+# Helpers shared by the release checks in this directory, see RELEASING.md.
+
+# Sets BRANCHES to all release and staging branches, and fails if there are none.
+load_release_branches() {
+    mapfile -t BRANCHES < <(git for-each-ref --format='%(refname)' 'refs/remotes/*/release/*' 'refs/remotes/*/staging/*')
+    if [ "${#BRANCHES[@]}" -eq 0 ]; then
+        echo "Error: No release or staging branches found."
+        exit 1
+    fi
+}

.github/scripts/rename/binary.sh

@@ -49,7 +49,7 @@ ${SED_COMMAND} -i -E 's@ripple/xrpld@XRPLF/rippled@g' BUILD.md
 ${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' BUILD.md
 ${SED_COMMAND} -i -E 's@xrpld \(`xrpld`\)@xrpld@g' BUILD.md
 ${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' CONTRIBUTING.md
-${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' docs/build/install.md
+${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' docs/install.md
 
 popd
 echo "Processing complete."

.github/scripts/rename/config.sh

@@ -62,7 +62,7 @@ ${SED_COMMAND} -i 's@ripple/@xrpld/@g' src/test/core/Config_test.cpp
 ${SED_COMMAND} -i 's/Rippled/File/g' src/test/core/Config_test.cpp
 
 # Restore the old config file name in the code that maintains support for now.
-${SED_COMMAND} -i 's/kConfigLegacyName = "xrpld.cfg"/kConfigLegacyName = "rippled.cfg"/g' src/xrpld/core/detail/Config.cpp
+${SED_COMMAND} -i 's/kConfigLegacyName = "xrpld.cfg"/kConfigLegacyName = "rippled.cfg"/g' src/xrpld/core/Config.h
 
 # Restore an URL.
 ${SED_COMMAND} -i 's/connect-your-xrpld-to-the-xrp-test-net.html/connect-your-rippled-to-the-xrp-test-net.html/g' cfg/xrpld-example.cfg

.github/scripts/rename/docs.sh

@@ -77,8 +77,8 @@ ${SED_COMMAND} -i 's/Ripple integrators/XRPL developers/' README.md
 ${SED_COMMAND} -i 's/sanitizer-configuration-for-rippled/sanitizer-configuration-for-xrpld/' docs/build/sanitizers.md
 ${SED_COMMAND} -i 's/rippled/xrpld/g' .github/scripts/levelization/README.md
 ${SED_COMMAND} -i 's/rippled/xrpld/g' .github/scripts/strategy-matrix/generate.py
-${SED_COMMAND} -i 's@/rippled@/xrpld@g' docs/build/install.md
-${SED_COMMAND} -i 's@github.com/XRPLF/xrpld@github.com/XRPLF/rippled@g' docs/build/install.md
+${SED_COMMAND} -i 's@/rippled@/xrpld@g' docs/install.md
+${SED_COMMAND} -i 's@github.com/XRPLF/xrpld@github.com/XRPLF/rippled@g' docs/install.md
 ${SED_COMMAND} -i 's/rippled/xrpld/g' docs/Doxyfile
 ${SED_COMMAND} -i 's/ripple_basics/basics/' include/xrpl/basics/CountedObject.h
 ${SED_COMMAND} -i 's/<ripple/<xrpl/' include/xrpl/protocol/AccountID.h
@@ -90,7 +90,7 @@ ${SED_COMMAND} -i 's/www.ripple.com/www.xrpl.org/g' src/test/protocol/Seed_test.
 # Restore specific changes.
 ${SED_COMMAND} -i 's@b5efcc/src/xrpld@b5efcc/src/ripple@' include/xrpl/protocol/README.md
 ${SED_COMMAND} -i 's/dbPrefix_ = "xrpldb"/dbPrefix_ = "rippledb"/' src/xrpld/app/misc/SHAMapStoreImp.h # cspell: disable-line
-${SED_COMMAND} -i 's/kConfigLegacyName = "xrpld.cfg"/kConfigLegacyName = "rippled.cfg"/' src/xrpld/core/detail/Config.cpp
+${SED_COMMAND} -i 's/kConfigLegacyName = "xrpld.cfg"/kConfigLegacyName = "rippled.cfg"/' src/xrpld/core/Config.h
 
 popd
 echo "Renaming complete."

.github/scripts/rename/namespace.sh

@@ -46,9 +46,6 @@ for DIRECTORY in "${DIRECTORIES[@]}"; do
     done
 done
 
-# Special case for NuDBFactory that has ripple twice in the test suite name.
-${SED_COMMAND} -i -E 's/(BEAST_DEFINE_TESTSUITE.+)ripple(.+)/\1xrpl\2/g' src/test/nodestore/NuDBFactory_test.cpp
-
 DIRECTORY=$1
 find "${DIRECTORY}" -type f -name "*.md" | while read -r FILE; do
     echo "Processing file: ${FILE}"

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

@@ -7,7 +7,21 @@ from pathlib import Path
 
 THIS_DIR = Path(__file__).parent.resolve()
 
-_BASE_CMAKE_ARGS = ["-Dtests=ON", "-Dwerr=ON", "-Dxrpld=ON", "-Dwextra=ON"]
+_BASE_CMAKE_ARGS = [
+    "-Dtests=ON",
+    "-Dwerr=ON",
+    "-Dxrpld=ON",
+    "-Dwextra=ON",
+    "-Drust=ON",
+]
+
+# The package formats a config can be packaged as, each with its own
+# install-test job in reusable-package.yml.
+PACKAGE_TYPES = ("deb", "rpm")
+
+# The package name a variant suffixes, as build_pkg.py's BASE_NAME spells it:
+# the two have to agree, or the artifact globs miss what was built.
+BASE_NAME = "xrpld"
 
 # Maps sanitizer names (as used in cmake) to short config-name suffixes.
 _SANITIZER_SUFFIX: dict[str, str] = {
@@ -17,48 +31,78 @@ _SANITIZER_SUFFIX: dict[str, str] = {
 }
 
 
+def config_name(
+    distro: str,
+    compiler: str,
+    build_type: str,
+    arch: str,
+    suffix: str = "",
+    sanitizer: str = "",
+) -> str:
+    """Name a config. Its artifacts are named after it, so packaging reuses this."""
+    parts = [s for s in [suffix, _SANITIZER_SUFFIX.get(sanitizer, "")] if s]
+    return "-".join([f"{distro}-{compiler}-{build_type.lower()}-{arch}", *parts])
+
+
 def get_cmake_args(build_type: str, extra_args: str) -> str:
     """Get the full list of CMake arguments for a config."""
     args = _BASE_CMAKE_ARGS.copy()
-    if build_type == "Release":
-        args.append("-Dassert=ON")
     if extra_args:
         args.extend(extra_args.split())
     return " ".join(args)
 
 
-def runs_on_event(exclude_event_types: list[str], event: str | None) -> bool:
-    """Whether a config should run for the current event.
-
-    'exclude_event_types' is a list of GitHub event names (e.g.
-    ["pull_request"]) on which the config should NOT run; an empty list means
-    the config runs on every event. When no event is given (event is None), no
-    filtering is applied.
-    """
-    if event is None:
-        return True
-    return event not in exclude_event_types
-
-
 # ---------------------------------------------------------------------------
 # Input types — shapes of the JSON config files
 # ---------------------------------------------------------------------------
 
 
+# Every config must declare 'minimal'. Minimal configs form the reduced matrix
+# built for pull requests by default; the full matrix adds the rest.
+#
+# Configs may also opt into 'benchmark' to smoke-run the benchmarks, or carry a
+# 'package' map to be packaged as well. Note that either applies to every entry
+# a config expands into, so only set them on configs that expand to a single
+# combination.
+
+
+@dataclasses.dataclass
+class PackageConfig:
+    """The 'package' map of a config whose binaries are also packaged."""
+
+    type: str  # has to match what the image provides
+    # The packaging container image: a vanilla distro image, not the nix image
+    # the config itself builds in.
+    image: str
+    # A flavour of the package, named xrpld-<variant>, for a config whose
+    # binaries are not the plain release build. A variant needs no counterpart
+    # in the other format.
+    variant: str = ""
+
+    def __post_init__(self) -> None:
+        assert self.type in PACKAGE_TYPES, (
+            f"unsupported package type {self.type!r}: "
+            f"use one of {', '.join(PACKAGE_TYPES)}."
+        )
+
+
 @dataclasses.dataclass
 class LinuxConfig:
-    """One entry in linux.json's 'configs' or 'package_configs' arrays."""
+    """One entry in a linux.json 'configs' array."""
 
     compiler: list[str]
     build_type: list[str]
     arch: list[str]
+    minimal: bool
+    benchmark: bool = False  # if true, smoke-run the benchmarks after testing
     sanitizers: list[str] = dataclasses.field(default_factory=list)
     suffix: str = ""
     extra_cmake_args: str = ""
-    image: str = ""  # only used by package_configs entries
-    # List of GitHub event names (e.g. "pull_request") on which this config
-    # should NOT run. Empty means it runs on every event.
-    exclude_event_types: list[str] = dataclasses.field(default_factory=list)
+    package: PackageConfig | None = None  # set to also package this config
+
+    def __post_init__(self) -> None:
+        if isinstance(self.package, dict):
+            self.package = PackageConfig(**self.package)
 
 
 @dataclasses.dataclass
@@ -67,22 +111,16 @@ class LinuxFile:
 
     image_tag: str
     configs: dict[str, list[LinuxConfig]]  # distro → configs
-    package_configs: dict[str, list[LinuxConfig]]  # distro → packaging configs
 
     @classmethod
     def load(cls, path: Path) -> "LinuxFile":
         data = json.loads(path.read_text())
-
-        def parse(section: dict) -> dict[str, list[LinuxConfig]]:
-            return {
-                distro: [LinuxConfig(**c) for c in cfgs]
-                for distro, cfgs in section.items()
-            }
-
         return cls(
             image_tag=data["image_tag"],
-            configs=parse(data["configs"]),
-            package_configs=parse(data.get("package_configs", {})),
+            configs={
+                distro: [LinuxConfig(**c) for c in cfgs]
+                for distro, cfgs in data["configs"].items()
+            },
         )
 
 
@@ -91,11 +129,13 @@ class PlatformConfig:
     """One entry in macos.json's or windows.json's 'configs' array."""
 
     build_type: list[str]
+    minimal: bool
     build_only: bool = False  # if true, skip tests (e.g. macos/Windows Debug)
+    benchmark: bool = False  # if true, smoke-run the benchmarks after testing
     extra_cmake_args: str = ""
-    # List of GitHub event names (e.g. "pull_request") on which this config
-    # should NOT run. Empty means it runs on every event.
-    exclude_event_types: list[str] = dataclasses.field(default_factory=list)
+    # "" is the runner's system compiler, "nix" the flake's CI environment.
+    # macOS only: Linux always builds in a Nix image, Windows has no Nix.
+    toolchain: str = ""
 
     def __post_init__(self) -> None:
         if isinstance(self.build_type, str):
@@ -139,20 +179,25 @@ class MatrixEntry:
     cmake_args: str
     cmake_target: str
     build_only: bool
+    benchmark: bool
     build_type: str
     architecture: Architecture
     sanitizers: str
     image: str = ""  # container image; empty for macOS/Windows (runs natively)
     compiler: str = ""  # compiler name ("gcc" or "clang"); empty for macOS/Windows
+    toolchain: str = ""  # "nix" for the flake's CI environment; see PlatformConfig
 
 
 @dataclasses.dataclass
 class PackagingEntry:
     """One entry in the generated packaging strategy matrix."""
 
-    artifact_name: str
+    xrpld_artifact_name: str
+    validator_keys_artifact_name: str
     image: str
-    distro: str  # e.g. "debian" or "rhel"; drives package-format-specific steps
+    package_type: str  # "deb" or "rpm"; drives the format-specific steps
+    package_variant: str  # passed to build_pkg.py --variant; empty for xrpld
+    package_name: str  # the name it builds under, which the artifact globs use
 
 
 # ---------------------------------------------------------------------------
@@ -170,20 +215,18 @@ _ARCHS: dict[str, Architecture] = {
 }
 
 
-def expand_linux_matrix(
-    linux: LinuxFile, event: str | None = None
-) -> list[MatrixEntry]:
+def expand_linux_matrix(linux: LinuxFile, minimal: bool) -> list[MatrixEntry]:
     """Expand a LinuxFile into a flat list of matrix entries.
 
     Each config entry is expanded over the cross-product of its
-    compiler, build_type, sanitizers, and architecture lists. Configs that
-    exclude the current event are skipped.
+    compiler, build_type, sanitizers, and architecture lists. When 'minimal' is
+    true, only configs flagged as minimal are included.
     """
     entries: list[MatrixEntry] = []
 
     for distro, configs in linux.configs.items():
         for cfg in configs:
-            if not runs_on_event(cfg.exclude_event_types, event):
+            if minimal and not cfg.minimal:
                 continue
             # An empty sanitizers list means "one entry with no sanitizer".
             effective_sanitizers = cfg.sanitizers or [""]
@@ -195,13 +238,9 @@ def expand_linux_matrix(
                 effective_sanitizers,
                 effective_archs.items(),
             ):
-                name = f"{distro}-{compiler}-{build_type.lower()}-{arch}"
-                suffix_parts = [
-                    s for s in [cfg.suffix, _SANITIZER_SUFFIX.get(sanitizer, "")] if s
-                ]
-                if suffix_parts:
-                    name += "-" + "-".join(suffix_parts)
-
+                name = config_name(
+                    distro, compiler, build_type, arch, cfg.suffix, sanitizer
+                )
                 entries.append(
                     MatrixEntry(
                         config_name=name,
@@ -209,6 +248,7 @@ def expand_linux_matrix(
                         cmake_args=get_cmake_args(build_type, cfg.extra_cmake_args),
                         cmake_target="all",
                         build_only=False,
+                        benchmark=cfg.benchmark,
                         build_type=build_type,
                         architecture=arch_info,
                         sanitizers=sanitizer,
@@ -220,52 +260,86 @@ def expand_linux_matrix(
 
 
 def expand_linux_packaging(linux: LinuxFile) -> list[PackagingEntry]:
-    """Generate the packaging matrix from a LinuxFile's package_configs section.
+    """Generate the packaging matrix from the configs that carry a 'package' map.
 
-    Packaging uses vanilla distro images (debian:bookworm, ubi9, …) instead of
-    the nix-based build images, because deb/rpm tooling (debhelper, rpm-build)
-    is taken from the distro's archive rather than from nixpkgs. Each config
-    entry carries its own 'image'.
+    Packaging consumes the binaries that config's build job uploaded, so the
+    artifact names come from the same config name, and a packaged config is one
+    that passes -Dvalidator_keys=ON.
+
+    Packaging itself runs in vanilla distro images (debian:trixie, almalinux:10)
+    instead of the nix-based build images, because deb/rpm tooling (debhelper,
+    rpm-build) is taken from the distro's archive rather than from nixpkgs.
     """
     entries = []
-    for distro, configs in linux.package_configs.items():
+    for distro, configs in linux.configs.items():
         for cfg in configs:
-            for compiler, build_type in itertools.product(cfg.compiler, cfg.build_type):
+            if cfg.package is None:
+                continue
+            for compiler, build_type, arch in itertools.product(
+                cfg.compiler, cfg.build_type, cfg.arch
+            ):
+                # The packaging workflow hardcodes an amd64 runner.
+                assert arch == "amd64", f"cannot package {distro} on {arch}"
+                name = config_name(distro, compiler, build_type, arch, cfg.suffix)
                 entries.append(
                     PackagingEntry(
-                        artifact_name=f"xrpld-{distro}-{compiler}-{build_type.lower()}-amd64",
-                        image=cfg.image,
-                        distro=distro,
+                        xrpld_artifact_name=f"xrpld-{name}",
+                        validator_keys_artifact_name=f"validator-keys-{name}",
+                        image=cfg.package.image,
+                        package_type=cfg.package.type,
+                        package_variant=cfg.package.variant,
+                        package_name=(
+                            f"{BASE_NAME}-{cfg.package.variant}"
+                            if cfg.package.variant
+                            else BASE_NAME
+                        ),
                     )
                 )
 
     return entries
 
 
-def expand_platform_matrix(
-    pf: PlatformFile, event: str | None = None
-) -> list[MatrixEntry]:
+def package_names_by_type(entries: list[PackagingEntry]) -> dict[str, list[str]]:
+    """The names of the packages in 'entries', keyed by format.
+
+    Derived from the packaging matrix rather than listed again, so the packages
+    the install-test jobs look for are the packages that were built.
+    """
+    return {
+        package_type: sorted(
+            {e.package_name for e in entries if e.package_type == package_type}
+        )
+        for package_type in PACKAGE_TYPES
+    }
+
+
+def expand_platform_matrix(pf: PlatformFile, minimal: bool) -> list[MatrixEntry]:
     """Expand a PlatformFile (macOS or Windows) into matrix entries.
 
-    Configs that exclude the current event are skipped.
+    When 'minimal' is true, only configs flagged as minimal are included.
     """
     platform_name, arch = pf.platform.split("/")
     is_windows = platform_name == "windows"
 
     entries: list[MatrixEntry] = []
     for cfg in pf.configs:
-        if not runs_on_event(cfg.exclude_event_types, event):
+        if minimal and not cfg.minimal:
             continue
         for build_type in cfg.build_type:
+            name = f"{platform_name}-{arch}-{build_type.lower()}"
+            if cfg.toolchain:
+                name += f"-{cfg.toolchain}"
             entries.append(
                 MatrixEntry(
-                    config_name=f"{platform_name}-{arch}-{build_type.lower()}",
+                    config_name=name,
                     cmake_args=get_cmake_args(build_type, cfg.extra_cmake_args),
                     cmake_target="install" if is_windows else "all",
                     build_only=cfg.build_only,
+                    benchmark=cfg.benchmark,
                     build_type=build_type,
                     architecture=Architecture(platform=pf.platform, runner=pf.runner),
                     sanitizers="",
+                    toolchain=cfg.toolchain,
                 )
             )
     return entries
@@ -294,12 +368,12 @@ if __name__ == "__main__":
         action="store_true",
     )
     parser.add_argument(
-        "-e",
-        "--event",
-        help="The GitHub event name that triggered the workflow (e.g. 'push', "
-        "'pull_request'). Configs are filtered by their 'event_type'. If "
-        "omitted, no filtering is applied.",
-        default=None,
+        "-m",
+        "--minimal",
+        help="Emit only the minimal matrix (the configs flagged 'minimal'), "
+        "used for pull requests by default. If omitted, the full matrix is "
+        "emitted.",
+        action="store_true",
     )
     args = parser.parse_args()
 
@@ -307,18 +381,22 @@ if __name__ == "__main__":
 
     if args.packaging:
         matrix = expand_linux_packaging(LinuxFile.load(THIS_DIR / "linux.json"))
+        # One list per format, so each install-test job installs the packages its
+        # own format produced.
+        for package_type, names in package_names_by_type(matrix).items():
+            print(f"{package_type}_package_names={json.dumps(names)}")
     else:
         if args.config in ("linux", None):
             matrix += expand_linux_matrix(
-                LinuxFile.load(THIS_DIR / "linux.json"), args.event
+                LinuxFile.load(THIS_DIR / "linux.json"), args.minimal
             )
         if args.config in ("macos", None):
             matrix += expand_platform_matrix(
-                PlatformFile.load(THIS_DIR / "macos.json"), args.event
+                PlatformFile.load(THIS_DIR / "macos.json"), args.minimal
             )
         if args.config in ("windows", None):
             matrix += expand_platform_matrix(
-                PlatformFile.load(THIS_DIR / "windows.json"), args.event
+                PlatformFile.load(THIS_DIR / "windows.json"), args.minimal
             )
 
     print(f"matrix={json.dumps({'include': [dataclasses.asdict(e) for e in matrix]})}")

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

@@ -1,31 +1,49 @@
 {
-  "image_tag": "sha-fe4c8ae",
+  "image_tag": "sha-060957e",
   "configs": {
     "ubuntu": [
-      {
-        "compiler": ["gcc", "clang"],
-        "build_type": ["Debug", "Release"],
-        "arch": ["amd64", "arm64"]
-      },
-
-      {
-        "compiler": ["gcc", "clang"],
-        "build_type": ["Debug", "Release"],
-        "arch": ["amd64"],
-        "sanitizers": ["address", "undefinedbehavior"]
-      },
-
       {
         "compiler": ["gcc"],
         "build_type": ["Debug"],
         "arch": ["amd64"],
+        "minimal": true,
         "suffix": "coverage",
         "extra_cmake_args": "-DUNIT_TEST_REFERENCE_FEE=500 -Dcoverage=ON -Dcoverage_format=xml -DCODE_COVERAGE_VERBOSE=ON -DCMAKE_C_FLAGS=-O0 -DCMAKE_CXX_FLAGS=-O0"
       },
+      {
+        "compiler": ["clang"],
+        "build_type": ["Release"],
+        "arch": ["amd64"],
+        "minimal": true,
+        "benchmark": true
+      },
+
+      {
+        "compiler": ["gcc"],
+        "build_type": ["Release"],
+        "arch": ["amd64"],
+        "minimal": false
+      },
+      {
+        "compiler": ["gcc", "clang"],
+        "build_type": ["Debug", "Release"],
+        "arch": ["arm64"],
+        "minimal": false
+      },
+
+      {
+        "compiler": ["gcc", "clang"],
+        "build_type": ["Debug", "Release"],
+        "arch": ["amd64"],
+        "minimal": false,
+        "sanitizers": ["address", "undefinedbehavior"]
+      },
+
       {
         "compiler": ["clang"],
         "build_type": ["Debug"],
         "arch": ["amd64"],
+        "minimal": false,
         "suffix": "voidstar",
         "extra_cmake_args": "-Dvoidstar=ON"
       },
@@ -33,6 +51,7 @@
         "compiler": ["clang"],
         "build_type": ["Release"],
         "arch": ["amd64"],
+        "minimal": false,
         "suffix": "reffee",
         "extra_cmake_args": "-DUNIT_TEST_REFERENCE_FEE=1000"
       },
@@ -40,35 +59,36 @@
         "compiler": ["gcc"],
         "build_type": ["Debug"],
         "arch": ["amd64"],
+        "minimal": false,
         "suffix": "unity",
-        "extra_cmake_args": "-Dunity=ON",
-        "exclude_event_types": ["pull_request"]
+        "extra_cmake_args": "-Dunity=ON"
       }
     ],
 
-    "debian": [
-      {
-        "compiler": ["gcc"],
-        "build_type": ["Release"],
-        "arch": ["amd64"]
-      }
-    ],
-
-    "rhel": [
-      {
-        "compiler": ["gcc"],
-        "build_type": ["Release"],
-        "arch": ["amd64"]
-      }
-    ]
-  },
-  "package_configs": {
     "debian": [
       {
         "compiler": ["gcc"],
         "build_type": ["Release"],
         "arch": ["amd64"],
-        "image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-577d745"
+        "minimal": false,
+        "extra_cmake_args": "-Dvalidator_keys=ON",
+        "package": {
+          "type": "deb",
+          "image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-3a2d19f"
+        }
+      },
+      {
+        "compiler": ["gcc"],
+        "build_type": ["Release"],
+        "arch": ["amd64"],
+        "minimal": false,
+        "suffix": "assert",
+        "extra_cmake_args": "-Dvalidator_keys=ON -Dassert=ON",
+        "package": {
+          "type": "deb",
+          "image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-3a2d19f",
+          "variant": "assert"
+        }
       }
     ],
 
@@ -77,7 +97,12 @@
         "compiler": ["gcc"],
         "build_type": ["Release"],
         "arch": ["amd64"],
-        "image": "ghcr.io/xrplf/xrpld/packaging-rhel:sha-577d745"
+        "minimal": false,
+        "extra_cmake_args": "-Dvalidator_keys=ON",
+        "package": {
+          "type": "rpm",
+          "image": "ghcr.io/xrplf/xrpld/packaging-rhel:sha-3a2d19f"
+        }
       }
     ]
   }

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

@@ -1,16 +1,30 @@
 {
   "platform": "macos/arm64",
-  "runner": ["self-hosted", "macOS", "ARM64", "mac-runner-m1"],
+  "runner": ["self-hosted", "macOS", "ARM64", "macos-26-apple-clang-21"],
   "configs": [
     {
       "build_type": "Release",
-      "extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5"
+      "extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
+      "minimal": true
     },
     {
       "build_type": "Debug",
       "extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
       "build_only": true,
-      "exclude_event_types": ["pull_request"]
+      "minimal": false
+    },
+    {
+      "build_type": "Release",
+      "extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
+      "toolchain": "nix",
+      "minimal": false
+    },
+    {
+      "build_type": "Debug",
+      "extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
+      "toolchain": "nix",
+      "build_only": true,
+      "minimal": false
     }
   ]
 }

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

@@ -1,12 +1,12 @@
 {
   "platform": "windows/amd64",
-  "runner": ["self-hosted", "Windows", "devbox"],
+  "runner": ["self-hosted", "Windows", "dev-box-windows-2026"],
   "configs": [
-    { "build_type": "Release" },
+    { "build_type": "Release", "minimal": true },
     {
       "build_type": "Debug",
       "build_only": true,
-      "exclude_event_types": ["pull_request"]
+      "minimal": false
     }
   ]
 }

.github/workflows/build-nix-images.yml

@@ -1,27 +1,31 @@
-name: Build Nix Docker images
+name: Build `nix` Docker images
 
 on:
   push:
     branches:
       - develop
     paths:
-      - ".github/workflows/build-nix-images.yml"
       - "flake.nix"
       - "flake.lock"
+      - "rust-toolchain.toml"
       - "nix/**"
       - "!nix/docker/README.md"
       - "!nix/devshell.nix"
-      - "bin/check-tools.sh"
+      - "!nix/check-tools/**"
+      - "bin/default-loader-path.sh"
       - "bin/install-sanitizer-libs.sh"
   pull_request:
     paths:
       - ".github/workflows/build-nix-images.yml"
       - "flake.nix"
       - "flake.lock"
+      - "rust-toolchain.toml"
       - "nix/**"
       - "!nix/docker/README.md"
       - "!nix/devshell.nix"
+      - "!nix/check-tools/**"
       - "bin/check-tools.sh"
+      - "bin/default-loader-path.sh"
       - "bin/install-sanitizer-libs.sh"
   workflow_dispatch:
 
@@ -36,7 +40,7 @@ defaults:
 
 jobs:
   build-merge:
-    name: Build and push nix-${{ matrix.distro.name }}
+    name: Build and push `nix-${{ matrix.distro.name }}` image
     permissions:
       contents: read
       packages: write
@@ -54,9 +58,9 @@ jobs:
             base_image: debian:bookworm
           - name: rhel
             base_image: registry.access.redhat.com/ubi9/ubi:latest
-    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@c1b480188519e0cad040e6aa70db1cbc5a797e07
+    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@696384b292577293292daed06af0306d1b83bd7d
     with:
-      image_name: ghcr.io/xrplf/xrpld/nix-${{ matrix.distro.name }}
+      image_name: xrpld/nix-${{ matrix.distro.name }}
       dockerfile: nix/docker/Dockerfile
       base_image: ${{ matrix.distro.base_image }}
-      push: ${{ github.repository == 'XRPLF/rippled' && github.event_name == 'push' }}
+      push: ${{ github.event_name == 'push' }}

.github/workflows/build-packaging-images.yml

@@ -1,4 +1,4 @@
-name: Build packaging Docker images
+name: Build `packaging` Docker images
 
 on:
   push:
@@ -6,13 +6,13 @@ on:
       - develop
     paths:
       - ".github/workflows/build-packaging-images.yml"
-      - "package/Dockerfile"
-      - "package/install-packaging-tools.sh"
+      - "bin/install-packaging-tools.sh"
+      - "package/images/packaging/**"
   pull_request:
     paths:
       - ".github/workflows/build-packaging-images.yml"
-      - "package/Dockerfile"
-      - "package/install-packaging-tools.sh"
+      - "bin/install-packaging-tools.sh"
+      - "package/images/packaging/**"
   workflow_dispatch:
 
 concurrency:
@@ -26,21 +26,24 @@ defaults:
 
 jobs:
   build-merge:
-    name: Build and push packaging-${{ matrix.distro.name }}
+    name: Build and push `packaging-${{ matrix.distro.name }}` image
     permissions:
       contents: read
       packages: write
     strategy:
       fail-fast: false
       matrix:
+        # Newest of each distro: these images only wrap pre-built binaries, so
+        # they set no floor for consumers. build_pkg.py pins the RPM dist tag.
         distro:
           - name: debian
-            base_image: debian:bookworm
+            base_image: debian:trixie
+          # AlmaLinux rather than UBI, which does not ship rpm-sign.
           - name: rhel
-            base_image: registry.access.redhat.com/ubi9/ubi:latest
-    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@c1b480188519e0cad040e6aa70db1cbc5a797e07
+            base_image: almalinux:10
+    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@696384b292577293292daed06af0306d1b83bd7d
     with:
-      image_name: ghcr.io/xrplf/xrpld/packaging-${{ matrix.distro.name }}
-      dockerfile: package/Dockerfile
+      image_name: xrpld/packaging-${{ matrix.distro.name }}
+      dockerfile: package/images/packaging/Dockerfile
       base_image: ${{ matrix.distro.base_image }}
-      push: ${{ github.repository == 'XRPLF/rippled' && github.event_name == 'push' }}
+      push: ${{ github.event_name == 'push' }}

.github/workflows/build-pre-commit-image.yml

@@ -0,0 +1,38 @@
+name: Build `pre-commit` Docker image
+
+on:
+  push:
+    branches:
+      - develop
+    paths:
+      - ".github/workflows/build-pre-commit-image.yml"
+      - "bin/pre-commit/Dockerfile"
+      - "rust-toolchain.toml"
+  pull_request:
+    paths:
+      - ".github/workflows/build-pre-commit-image.yml"
+      - "bin/pre-commit/Dockerfile"
+      - "rust-toolchain.toml"
+  workflow_dispatch:
+
+concurrency:
+  # Read `on-trigger.yml` for the rationale behind this concurrency group name.
+  group: ${{ github.workflow }}-${{ github.event_name == 'push' && github.ref == 'refs/heads/develop' && github.sha || github.ref }}
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  build-merge:
+    name: Build and push `pre-commit` image
+    permissions:
+      contents: read
+      packages: write
+    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@696384b292577293292daed06af0306d1b83bd7d
+    with:
+      image_name: xrpld/pre-commit
+      dockerfile: bin/pre-commit/Dockerfile
+      base_image: ubuntu:26.04
+      push: ${{ github.event_name == 'push' }}

.github/workflows/cargo-audit.yml

@@ -0,0 +1,80 @@
+name: Cargo audit
+
+on:
+  schedule:
+    # 06:32 UTC every Monday.
+    - cron: "32 6 * * 1"
+  push:
+    branches:
+      - "develop"
+      - "release/*"
+    paths:
+      - "crates/**/Cargo.toml"
+      - "crates/Cargo.lock"
+      - ".github/workflows/cargo-audit.yml"
+  pull_request:
+    paths:
+      - "crates/**/Cargo.toml"
+      - "crates/Cargo.lock"
+      - ".github/workflows/cargo-audit.yml"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+    working-directory: crates
+
+permissions:
+  contents: read
+
+jobs:
+  audit:
+    runs-on: ubuntu-latest
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
+    permissions:
+      contents: read
+      # Needed to open an issue on scheduled failures.
+      issues: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Run cargo audit
+        id: audit
+        continue-on-error: true
+        run: |
+          set -o pipefail
+          cargo audit | tee /tmp/cargo-audit.txt
+
+      - name: Prepare issue body
+        if: ${{ steps.audit.outcome != 'success' && github.event_name == 'schedule' }}
+        run: |
+          {
+              echo "## \`cargo audit\` found advisories"
+              echo
+              echo '```'
+              cat /tmp/cargo-audit.txt
+              echo '```'
+              echo
+              echo "---"
+              echo "*This issue was automatically created by the cargo-audit workflow.*"
+          } >/tmp/cargo-audit-issue.md
+
+      - name: Create issue
+        if: ${{ steps.audit.outcome != 'success' && github.event_name == 'schedule' }}
+        uses: XRPLF/actions/create-issue@2b8bc36af85b88bca0dd7bfac2e2dc05f94ad712
+        with:
+          title: "cargo audit found vulnerabilities"
+          body_file: /tmp/cargo-audit-issue.md
+          labels: "Bug,Security"
+
+      - name: Fail if advisories were found
+        if: ${{ steps.audit.outcome != 'success' }}
+        run: |
+          echo "cargo audit found advisories!"
+          cat /tmp/cargo-audit.txt
+          exit 1

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

@@ -13,7 +13,6 @@ on:
       - ready_for_review
     branches:
       - develop
-      - "release-*"
       - "release/*"
       - "staging/*"
 
@@ -23,7 +22,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Write PR body to file
         env:

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

@@ -13,11 +13,10 @@ on:
       - ready_for_review
     branches:
       - develop
-      - "release-*"
       - "release/*"
       - "staging/*"
 
 jobs:
   check_title:
     if: ${{ github.event.pull_request.draft != true }}
-    uses: XRPLF/actions/.github/workflows/check-pr-title.yml@cba1f0891650baf1a9c88624dc2d72573be2eb81
+    uses: XRPLF/actions/.github/workflows/check-pr-title.yml@d7c65e49225a38f6d8010eacf017bb5a98d7476c

.github/workflows/check-releases-merged.yml

@@ -0,0 +1,60 @@
+# This workflow checks that every final release on a release branch
+# has been merged back into develop, see RELEASING.md.
+name: Check releases merged
+
+on:
+  schedule:
+    # 06:47 UTC every Monday.
+    - cron: "47 6 * * 1"
+  push:
+    branches:
+      - "develop"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+env:
+  OUTPUT_FILE: /tmp/releases-merged.txt
+  ISSUE_FILE: /tmp/releases-merged-issue.md
+
+jobs:
+  releases-merged:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      # Needed to open an issue on scheduled failures.
+      issues: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          # The check needs the full history of develop, the release branches and tags.
+          fetch-depth: 0
+
+      - name: Check releases are merged into develop
+        run: |
+          set -o pipefail
+          .github/scripts/releasing/check-releases-merged.sh origin/develop | tee "${OUTPUT_FILE}"
+
+      - name: Prepare issue body
+        if: ${{ failure() && github.event_name == 'schedule' && github.repository == 'XRPLF/rippled' }}
+        run: |
+          {
+              echo '```'
+              cat "${OUTPUT_FILE}"
+              echo '```'
+          } >"${ISSUE_FILE}"
+
+      - name: Create issue
+        if: ${{ failure() && github.event_name == 'schedule' && github.repository == 'XRPLF/rippled' }}
+        uses: XRPLF/actions/create-issue@2b8bc36af85b88bca0dd7bfac2e2dc05f94ad712
+        with:
+          title: "Releases not merged back into develop"
+          body_file: ${{ env.ISSUE_FILE }}
+          labels: "Bug"

.github/workflows/check-tools.yml

@@ -0,0 +1,114 @@
+# Verifies the committed snapshots of `bin/check-tools.sh` output for each Nix
+# environment (see nix/check-tools/). If the environment changes — a new image
+# tag, an updated flake.lock, a different tool list — without the matching
+# snapshot being regenerated and committed, this workflow fails so the drift is
+# caught in review.
+#
+# To regenerate the snapshots, see nix/check-tools/README.md.
+name: Check tools
+
+on:
+  pull_request:
+    paths:
+      - ".github/workflows/check-tools.yml"
+      - ".github/scripts/strategy-matrix/linux.json"
+      - "bin/check-tools.sh"
+      - "nix/**"
+      - "flake.nix"
+      - "flake.lock"
+      - "rust-toolchain.toml"
+  push:
+    branches:
+      - "develop"
+    paths:
+      - ".github/workflows/check-tools.yml"
+      - ".github/scripts/strategy-matrix/linux.json"
+      - "bin/check-tools.sh"
+      - "nix/**"
+      - "flake.nix"
+      - "flake.lock"
+      - "rust-toolchain.toml"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  # The nix-nixos image tag is pinned alongside the build matrix in linux.json,
+  # so snapshots are checked against the exact image CI builds against.
+  linux-image-tag:
+    runs-on: ubuntu-latest
+    outputs:
+      tag: ${{ steps.tag.outputs.tag }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Read nix image tag
+        id: tag
+        run: echo "tag=$(jq -r .image_tag .github/scripts/strategy-matrix/linux.json)" >>"${GITHUB_OUTPUT}"
+
+  # One job for all environments; they differ only in whether the tools come
+  # from the nix-nixos container (Linux) or `nix develop` (macOS).
+  check-tools:
+    needs: linux-image-tag
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: ubuntu-latest
+            snapshot: nix/check-tools/nix-ubuntu-amd64.txt
+            nix_develop: false
+          - runner: ubuntu-24.04-arm
+            snapshot: nix/check-tools/nix-ubuntu-arm64.txt
+            nix_develop: false
+          - runner: macos-26-apple-clang-21
+            snapshot: nix/check-tools/macos.txt
+            nix_develop: true
+    runs-on: ${{ matrix.runner }}
+    # Linux runs inside the pinned nix-nixos image; macOS runs natively and uses
+    # the flake's dev shell instead (see the run step below).
+    container: ${{ !matrix.nix_develop && format('ghcr.io/xrplf/xrpld/nix-ubuntu:{0}', needs.linux-image-tag.outputs.tag) || null }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
+        with:
+          enable_ccache: false
+
+      - name: Regenerate snapshot
+        env:
+          CHECK_TOOLS_SKIP_CLONE: "1"
+          # check-tools.sh skips some macOS tools when CI is set; the snapshots
+          # capture the full `nix develop` environment, so unset it here.
+          CI: ""
+        run: |
+          if [ "${{ matrix.nix_develop }}" = "true" ]; then
+              # `nix develop` prints the dev-shell greeting first; keep only the
+              # check-tools.sh output (from the "Detected OS:" line onward).
+              nix --extra-experimental-features "nix-command flakes" develop \
+                  -c bash bin/check-tools.sh | sed -n '/^Detected OS:/,$p' >"${{ matrix.snapshot }}"
+          else
+              bash bin/check-tools.sh >"${{ matrix.snapshot }}"
+          fi
+
+      - name: Verify snapshot is up to date
+        run: |
+          if ! git diff --exit-code -- "${{ matrix.snapshot }}"; then
+              echo "::error::${{ matrix.snapshot }} is out of date. Regenerate it (see nix/check-tools/README.md) and commit the result."
+              exit 1
+          fi
+
+      - name: Upload regenerated snapshot
+        if: failure()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: check-tools-${{ runner.os }}-${{ runner.arch }}
+          path: ${{ matrix.snapshot }}

.github/workflows/conflicting-pr.yml

@@ -14,6 +14,7 @@ permissions:
 
 jobs:
   main:
+    if: ${{ !contains(github.event.pull_request.labels.*.name, 'IgnoreConflicts') }}
     runs-on: ubuntu-latest
     steps:
       - name: Check if PRs are dirty

.github/workflows/on-pr.yml

@@ -1,7 +1,11 @@
-# This workflow runs all workflows to check, build and test the project on
-# various Linux flavors, as well as on MacOS and Windows, on every push to a
-# user branch. However, it will not run if the pull request is a draft unless it
-# has the 'DraftRunCI' label. For commits to PRs that target a release branch,
+# This workflow runs workflows to check, build and test the project
+# on every meaningful change on pull_request.
+# However, it will not run if the PR is a draft
+# unless it has the 'DraftRunCI' or 'Full CI build' label.
+#
+# By default a PR builds only a minimal matrix.
+# The full matrix runs once the PR is labeled "Ready to merge" or "Full CI build".
+# For commits to PRs that target a release branch,
 # it also uploads the libxrpl recipe to the Conan remote.
 name: PR
 
@@ -15,8 +19,16 @@ on:
       - reopened
       - synchronize
       - ready_for_review
+      # Trigger on label changes so toggling "Ready to merge" or "Full CI build"
+      # switches between the minimal and full matrix without needing a new push.
+      - labeled
+      - unlabeled
 
 concurrency:
+  # A single per-ref group with cancel-in-progress means any newer run (a push
+  # or a label change) supersedes the in-progress one for that ref. Keeping
+  # exactly one authoritative run per ref ensures a fast do-nothing run can never
+  # mask a real build's checks.
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
@@ -25,15 +37,22 @@ defaults:
     shell: bash
 
 jobs:
-  # This job determines whether the rest of the workflow should run. It runs
-  # when the PR is not a draft (which should also cover merge-group) or
-  # has the 'DraftRunCI' label.
+  # This job determines whether the rest of the workflow should run at all,
+  # based on the current set of labels: it runs when the PR is not a draft
+  # (which should also cover merge-group) or has the 'DraftRunCI' or
+  # 'Full CI build' label. Whether a build then happens, and whether it is the
+  # minimal or full matrix, is decided further below and in the strategy matrix.
   should-run:
-    if: ${{ !github.event.pull_request.draft || contains(github.event.pull_request.labels.*.name, 'DraftRunCI') }}
+    if: >-
+      ${{
+        !github.event.pull_request.draft
+        || contains(github.event.pull_request.labels.*.name, 'DraftRunCI')
+        || contains(github.event.pull_request.labels.*.name, 'Full CI build')
+      }}
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
       - 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
@@ -58,21 +77,29 @@ jobs:
 
             # Keep the paths below in sync with those in `on-trigger.yml`.
             .github/actions/build-deps/**
-            .github/actions/generate-version/**
+            .github/actions/release-info/**
             .github/actions/setup-conan/**
+            .github/actions/setup-nix-env/**
             .github/scripts/strategy-matrix/**
             .github/workflows/reusable-build-test-config.yml
             .github/workflows/reusable-build-test.yml
+            .github/workflows/reusable-check-autogen.yml
             .github/workflows/reusable-clang-tidy.yml
+            .github/workflows/reusable-package-test-install.yml
             .github/workflows/reusable-package.yml
+            .github/workflows/reusable-rust.yml
             .github/workflows/reusable-strategy-matrix.yml
             .github/workflows/reusable-test.yml
             .github/workflows/reusable-upload-recipe.yml
             .clang-tidy
             .codecov.yml
+            bin/check-nix-store-refs.sh
+            bin/check-tools.sh
+            bin/default-loader-path.sh
             cfg/**
             cmake/**
             conan/**
+            crates/**
             external/**
             include/**
             src/**
@@ -80,6 +107,9 @@ jobs:
             CMakeLists.txt
             conanfile.py
             conan.lock
+            flake.lock
+            flake.nix
+            nix/**
             LICENSE.md
             package/**
             README.md
@@ -90,19 +120,26 @@ jobs:
         # least one of:
         # * Any of the files checked in the `changes` step were modified
         # * The PR is NOT a draft and is labeled "Ready to merge"
+        # * The PR is labeled "Full CI build" (draft or not)
         # * The workflow is running from the merge queue
         id: go
         env:
           FILES: ${{ steps.changes.outputs.any_changed }}
           DRAFT: ${{ github.event.pull_request.draft }}
           READY: ${{ contains(github.event.pull_request.labels.*.name, 'Ready to merge') }}
+          FULL: ${{ contains(github.event.pull_request.labels.*.name, 'Full CI build') }}
           MERGE: ${{ github.event_name == 'merge_group' }}
         run: |
-          echo "go=${{ (env.DRAFT != 'true' && env.READY == 'true') || env.FILES == 'true' || env.MERGE == 'true' }}" >>"${GITHUB_OUTPUT}"
+          echo "go=${{ (env.DRAFT != 'true' && env.READY == 'true') || env.FULL == 'true' || env.FILES == 'true' || env.MERGE == 'true' }}" >>"${GITHUB_OUTPUT}"
           cat "${GITHUB_OUTPUT}"
     outputs:
       go: ${{ steps.go.outputs.go == 'true' }}
 
+  check-autogen:
+    needs: should-run
+    if: ${{ needs.should-run.outputs.go == 'true' }}
+    uses: ./.github/workflows/reusable-check-autogen.yml
+
   check-levelization:
     needs: should-run
     if: ${{ needs.should-run.outputs.go == 'true' }}
@@ -113,6 +150,48 @@ jobs:
     if: ${{ needs.should-run.outputs.go == 'true' }}
     uses: ./.github/workflows/reusable-check-rename.yml
 
+  # Runs regardless of the changed files.
+  # PRs into staging branches are skipped, since fixes may be cherry-picked between release lines.
+  check-release-commits:
+    needs: should-run
+    if: ${{ github.event.pull_request.base.ref == 'develop' || github.event.merge_group.base_ref == 'refs/heads/develop' }}
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          # The check needs the full history of the release and staging branches.
+          fetch-depth: 0
+          persist-credentials: false
+      - name: Check for copied release commits
+        if: ${{ github.event_name == 'pull_request' }}
+        env:
+          BASE: ${{ github.event.pull_request.base.sha }}
+          HEAD: ${{ github.event.pull_request.head.sha }}
+        run: .github/scripts/releasing/check-no-copied-release-commits.sh "${BASE}" "${HEAD}"
+      # Runs even if the previous check fails, so that both problems are reported at once.
+      - name: Check merge-back has no new commits
+        if: ${{ !cancelled() && github.event_name == 'pull_request' }}
+        env:
+          BASE: ${{ github.event.pull_request.base.sha }}
+          HEAD: ${{ github.event.pull_request.head.sha }}
+        run: .github/scripts/releasing/check-merge-back-commits.sh "${BASE}" "${HEAD}"
+      # The queue squashes PRs, so check the PR's own branch, named in the queue branch.
+      - name: Check the merge queue doesn't merge a release back
+        if: ${{ github.event_name == 'merge_group' }}
+        env:
+          BASE: ${{ github.event.merge_group.base_sha }}
+          HEAD_REF: ${{ github.event.merge_group.head_ref }}
+        run: |
+          if ! [[ "${HEAD_REF}" =~ /pr-([0-9]+)-[0-9a-f]+$ ]]; then
+              echo "Error: Can't find the PR number in '${HEAD_REF}'."
+              exit 1
+          fi
+          git fetch --no-tags origin "refs/pull/${BASH_REMATCH[1]}/head"
+          .github/scripts/releasing/check-no-merge-back.sh "${BASE}" FETCH_HEAD
+
   clang-tidy:
     needs: should-run
     if: ${{ needs.should-run.outputs.go == 'true' }}
@@ -121,7 +200,6 @@ jobs:
       issues: write
       contents: read
     with:
-      check_only_changed: true
       create_issue_on_failure: false
 
   build-test:
@@ -140,10 +218,26 @@ jobs:
     secrets:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
+  rust:
+    needs: should-run
+    if: ${{ needs.should-run.outputs.go == 'true' }}
+    uses: ./.github/workflows/reusable-rust.yml
+    secrets:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
   package:
     needs: [should-run, build-test]
-    if: ${{ needs.should-run.outputs.go == 'true' }}
+    # Packaging consumes the debian/rhel release binaries, which are only built
+    # by the full matrix. Skip it for pull requests that ran only the minimal
+    # matrix (i.e. not yet labeled "Ready to merge" or "Full CI build").
+    if: ${{ needs.should-run.outputs.go == 'true' && (github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'Ready to merge') || contains(github.event.pull_request.labels.*.name, 'Full CI build')) }}
     uses: ./.github/workflows/reusable-package.yml
+    with:
+      # A pull request builds packages to prove they still build, and publishes
+      # nothing. Stated rather than left to the input's default, so that changing
+      # that default cannot start publishing from pull requests. No secrets are
+      # passed either, which is the second reason a publish here cannot succeed.
+      publish: false
 
   upload-recipe:
     needs:
@@ -153,8 +247,8 @@ jobs:
     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 }}
-      remote_password: ${{ secrets.CONAN_REMOTE_PASSWORD }}
+      remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
+      remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
 
   notify-clio:
     needs: upload-recipe
@@ -175,10 +269,13 @@ jobs:
   passed:
     if: failure() || cancelled()
     needs:
+      - check-autogen
       - check-levelization
       - check-rename
+      - check-release-commits
       - clang-tidy
       - build-test
+      - rust
       - package
       - upload-recipe
       - notify-clio

.github/workflows/on-tag.yml

@@ -1,5 +1,12 @@
-# This workflow uploads the libxrpl recipe to the Conan remote and builds
-# release packages when a versioned tag is pushed.
+# When a versioned tag is pushed, this workflow:
+#
+#   - builds and tests the release binaries
+#   - uploads the libxrpl recipe to the Conan remote
+#   - builds the DEB and RPM packages
+#   - publishes those packages to the XRPLF package repositories
+#
+# Nothing is published unless the build passes, which is also where CMake
+# rejects a tag that is not a valid version, e.g. 3.2.01.
 name: Tag
 
 on:
@@ -18,13 +25,14 @@ defaults:
 jobs:
   upload-recipe:
     if: ${{ github.repository == 'XRPLF/rippled' }}
+    needs: build-test
     uses: ./.github/workflows/reusable-upload-recipe.yml
     secrets:
-      remote_username: ${{ secrets.CONAN_REMOTE_USERNAME }}
-      remote_password: ${{ secrets.CONAN_REMOTE_PASSWORD }}
+      remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
+      remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
 
   build-test:
-    if: ${{ github.repository == 'XRPLF/rippled' }}
+    if: ${{ github.repository_owner == 'XRPLF' }}
     uses: ./.github/workflows/reusable-build-test.yml
     strategy:
       fail-fast: true
@@ -37,6 +45,16 @@ jobs:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
   package:
-    if: ${{ github.repository == 'XRPLF/rippled' }}
+    if: ${{ github.repository_owner == 'XRPLF' }}
     needs: build-test
     uses: ./.github/workflows/reusable-package.yml
+    with:
+      publish: true
+    secrets:
+      remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
+      remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
+      signing_key: ${{ secrets.NEXUS_PACKAGES_PRIVATE_KEY }}
+      dockerhub_token: ${{ secrets.DOCKERHUB_TOKEN }}
+      antithesis_docker_host: ${{ secrets.ANTITHESIS_DOCKER_HOST }}
+      antithesis_docker_path: ${{ secrets.ANTITHESIS_DOCKER_PATH }}
+      antithesis_docker_credentials: ${{ secrets.ANTITHESIS_DOCKER_CREDENTIALS }}

.github/workflows/on-trigger.yml

@@ -15,21 +15,29 @@ on:
 
       # Keep the paths below in sync with those in `on-pr.yml`.
       - ".github/actions/build-deps/**"
-      - ".github/actions/generate-version/**"
+      - ".github/actions/release-info/**"
       - ".github/actions/setup-conan/**"
+      - ".github/actions/setup-nix-env/**"
       - ".github/scripts/strategy-matrix/**"
       - ".github/workflows/reusable-build-test-config.yml"
       - ".github/workflows/reusable-build-test.yml"
+      - ".github/workflows/reusable-check-autogen.yml"
       - ".github/workflows/reusable-clang-tidy.yml"
+      - ".github/workflows/reusable-package-test-install.yml"
       - ".github/workflows/reusable-package.yml"
+      - ".github/workflows/reusable-rust.yml"
       - ".github/workflows/reusable-strategy-matrix.yml"
       - ".github/workflows/reusable-test.yml"
       - ".github/workflows/reusable-upload-recipe.yml"
       - ".clang-tidy"
       - ".codecov.yml"
+      - "bin/check-nix-store-refs.sh"
+      - "bin/check-tools.sh"
+      - "bin/default-loader-path.sh"
       - "cfg/**"
       - "cmake/**"
       - "conan/**"
+      - "crates/**"
       - "external/**"
       - "include/**"
       - "src/**"
@@ -37,6 +45,9 @@ on:
       - "CMakeLists.txt"
       - "conanfile.py"
       - "conan.lock"
+      - "flake.lock"
+      - "flake.nix"
+      - "nix/**"
       - "LICENSE.md"
       - "package/**"
       - "README.md"
@@ -65,13 +76,15 @@ defaults:
     shell: bash
 
 jobs:
+  check-autogen:
+    uses: ./.github/workflows/reusable-check-autogen.yml
+
   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:
@@ -91,15 +104,32 @@ jobs:
     secrets:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
+  rust:
+    uses: ./.github/workflows/reusable-rust.yml
+    secrets:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
   upload-recipe:
     needs: build-test
     # 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 }}
-      remote_password: ${{ secrets.CONAN_REMOTE_PASSWORD }}
+      remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
+      remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
 
   package:
     needs: build-test
     uses: ./.github/workflows/reusable-package.yml
+    with:
+      # Packages are built on every trigger; only develop pushes in XRPLF/rippled
+      # publish them, matching upload-recipe above.
+      publish: ${{ github.repository == 'XRPLF/rippled' && github.event_name == 'push' && github.ref == 'refs/heads/develop' }}
+    secrets:
+      remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
+      remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
+      signing_key: ${{ secrets.NEXUS_PACKAGES_PRIVATE_KEY }}
+      dockerhub_token: ${{ secrets.DOCKERHUB_TOKEN }}
+      antithesis_docker_host: ${{ secrets.ANTITHESIS_DOCKER_HOST }}
+      antithesis_docker_path: ${{ secrets.ANTITHESIS_DOCKER_PATH }}
+      antithesis_docker_credentials: ${{ secrets.ANTITHESIS_DOCKER_CREDENTIALS }}

.github/workflows/pre-commit.yml

@@ -14,7 +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@312aaab296060ff89d7f798dcab59f019bea6e02
+    uses: XRPLF/actions/.github/workflows/pre-commit.yml@279ec358f4a1be4088be3e024b07916fa97c75b6
     with:
       runs_on: ubuntu-latest
-      container: '{ "image": "ghcr.io/xrplf/ci/tools-rippled-pre-commit:sha-41ec7c1" }'
+      container: '{ "image": "ghcr.io/xrplf/xrpld/pre-commit:sha-473fe44" }'

.github/workflows/publish-docs.yml

@@ -41,13 +41,13 @@ env:
 jobs:
   build:
     runs-on: ubuntu-latest
-    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-fe4c8ae
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@c47daebb2f9db64ffbac71b47d68a661498d5ce8
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
         with:
           enable_ccache: false
 
@@ -91,4 +91,4 @@ jobs:
     steps:
       - name: Deploy to GitHub Pages
         id: deploy
-        uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128 # v5.0.0
+        uses: actions/deploy-pages@368f82528645a54fb793d4d04e342629a3f51346 # v5.0.1

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

@@ -3,6 +3,12 @@ name: Build and test configuration
 on:
   workflow_call:
     inputs:
+      benchmark:
+        description: "Whether to smoke-run the benchmarks after testing."
+        required: false
+        type: boolean
+        default: false
+
       build_only:
         description: 'Whether to only build or to build and test the code ("true", "false").'
         required: true
@@ -63,6 +69,12 @@ on:
         type: string
         default: ""
 
+      toolchain:
+        description: 'Where the toolchain comes from ("nix" to build the flake CI environment on the runner, empty for the system one). macOS only: Linux always builds in a Nix image, and Nix has no Windows support.'
+        required: false
+        type: string
+        default: ""
+
     secrets:
       CODECOV_TOKEN:
         description: "The Codecov token to use for uploading coverage reports."
@@ -82,7 +94,7 @@ jobs:
     name: ${{ inputs.config_name }}
     runs-on: ${{ fromJSON(inputs.runs_on) }}
     container: ${{ inputs.image != '' && inputs.image || null }}
-    timeout-minutes: ${{ inputs.sanitizers != '' && 360 || 90 }}
+    timeout-minutes: ${{ inputs.sanitizers != '' && 360 || 180 }}
     env:
       # Use a namespace to keep the objects separate for each configuration.
       CCACHE_NAMESPACE: ${{ inputs.config_name }}
@@ -100,23 +112,32 @@ jobs:
       # header files are copied into separate directories by CMake, which will
       # otherwise result in cache misses.
       CCACHE_SLOPPINESS: include_file_ctime,include_file_mtime
-      # Determine if coverage and voidstar should be enabled.
+      # Determine if coverage, voidstar and validator-keys should be enabled.
       COVERAGE_ENABLED: ${{ contains(inputs.cmake_args, '-Dcoverage=ON') }}
       VOIDSTAR_ENABLED: ${{ contains(inputs.cmake_args, '-Dvoidstar=ON') }}
+      VALIDATOR_KEYS_ENABLED: ${{ contains(inputs.cmake_args, '-Dvalidator_keys=ON') }}
       SANITIZERS_ENABLED: ${{ inputs.sanitizers != '' }}
+      # The binaries reusable-package.yml consumes. A private repository skips
+      # them except on a tag push, which is what produces its release packages.
+      PACKAGING_ARTIFACTS_ENABLED: ${{ github.event.repository.visibility == 'public' || startsWith(github.ref, 'refs/tags/') }}
     steps:
       - name: Cleanup workspace (macOS and Windows)
         if: ${{ runner.os == 'macOS' || runner.os == 'Windows' }}
         uses: XRPLF/actions/cleanup-workspace@c7d9ce5ebb03c752a354889ecd870cadfc2b1cd4
 
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@c47daebb2f9db64ffbac71b47d68a661498d5ce8
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
         with:
           enable_ccache: ${{ inputs.ccache_enabled }}
 
+      # Before any step that uses a build tool, composite actions included.
+      - name: Setup Nix environment
+        if: ${{ inputs.toolchain == 'nix' }}
+        uses: ./.github/actions/setup-nix-env
+
       - name: Set ccache log file
         if: ${{ inputs.ccache_enabled && runner.debug == '1' }}
         run: echo "CCACHE_LOGFILE=${{ runner.temp }}/ccache.log" >>"${GITHUB_ENV}"
@@ -124,7 +145,7 @@ jobs:
       - name: Check tools
         env:
           CHECK_TOOLS_SKIP_CLONE: "1"
-        run: ./bin/check-tools.sh
+        run: ./bin/check-tools.sh || true
 
       - name: Print build environment
         uses: XRPLF/actions/print-build-env@59dec886e4afb05a1724443af08baccbc045b574
@@ -141,7 +162,21 @@ jobs:
         with:
           compiler: ${{ inputs.compiler }}
 
+      - name: Use cargo artifacts cache
+        uses: ./.github/actions/cargo-cache
+        with:
+          cache-directories: ${{ env.BUILD_DIR }}/corrosion
+          key: ${{ inputs.config_name }}
+          # two workspaces here because build artifacts are located in 2 places:
+          # - crates/target when cargo is called directly
+          # - build/cargo when cargo is called by cmake
+          workspaces: |
+            crates
+            crates -> ${{ runner.os == 'Windows' && format('../{0}/x64/{1}/cargo', env.BUILD_DIR, inputs.build_type) || format('../{0}/cargo', env.BUILD_DIR) }}
+
+      # `setup-nix-env` already did this for the Nix toolchain.
       - name: Setup Conan
+        if: ${{ inputs.toolchain != 'nix' }}
         env:
           SANITIZERS: ${{ inputs.sanitizers }}
         uses: ./.github/actions/setup-conan
@@ -161,18 +196,31 @@ jobs:
         env:
           BUILD_TYPE: ${{ inputs.build_type }}
           CMAKE_ARGS: ${{ inputs.cmake_args }}
+          # GitHub creates a merge commit for a PR
+          # https://www.kenmuse.com/blog/the-many-shas-of-a-github-pull-request/
+          #
+          # We:
+          # - explicitly provide branch name
+          # - use `github.event.pull_request.head.sha` to get the SHA of last commit in the PR branch
+          #
+          # This way it works both for PRs and pushes to branches.
+          GITHUB_BRANCH_NAME: "${{ github.head_ref || github.ref_name }}"
+          GITHUB_HEAD_SHA: "${{ github.event.pull_request.head.sha || github.sha }}"
+          #
+          # If tag is being pushed, we use that version.
+          FORCE_XRPLD_VERSION: ${{ startsWith(github.ref, 'refs/tags/') && github.ref_name || '' }}
         run: |
           cmake \
-              -G '${{ runner.os == 'Windows' && 'Visual Studio 17 2022' || 'Ninja' }}' \
+              -G '${{ runner.os == 'Windows' && 'Visual Studio 18 2026' || 'Ninja' }}' \
               -DCMAKE_TOOLCHAIN_FILE:FILEPATH=build/generators/conan_toolchain.cmake \
               -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
               ${CMAKE_ARGS} \
               ..
 
       # Export the sanitizer options before any instrumented binary runs. The
-      # protocol code-gen and build steps below invoke instrumented dependency
-      # tools (protoc, grpc), so setting UBSAN_OPTIONS here lets the UBSan
-      # suppression list silence their diagnostics too, not just at test time.
+      # build step below invokes instrumented dependency tools (protoc, grpc),
+      # so setting UBSAN_OPTIONS here lets the UBSan suppression list silence
+      # their diagnostics too, not just at test time.
       # GITHUB_WORKSPACE (not the github.workspace context) is used so the path
       # resolves correctly inside the container job.
       - name: Set sanitizer options
@@ -190,32 +238,6 @@ jobs:
           echo "UBSAN_OPTIONS=include=${SUPP}/runtime-ubsan-options.txt:suppressions=${SUPP}/ubsan.supp" >>${GITHUB_ENV}
           echo "LSAN_OPTIONS=include=${SUPP}/runtime-lsan-options.txt:suppressions=${SUPP}/lsan.supp" >>${GITHUB_ENV}
 
-      - name: Check protocol autogen files are up-to-date
-        working-directory: ${{ env.BUILD_DIR }}
-        env:
-          MESSAGE: |
-
-            The generated protocol wrapper classes are out of date.
-
-            This typically happens when the macro files or generator scripts
-            have changed but the generated files were not regenerated.
-
-            To fix this:
-              1. Run: cmake --build . --target setup_code_gen
-              2. Run: cmake --build . --target code_gen
-              3. Commit and push the regenerated files
-        run: |
-          set -e
-          cmake --build . --target setup_code_gen
-          cmake --build . --target code_gen
-          DIFF=$(git -C .. status --porcelain -- include/xrpl/protocol_autogen src/tests/libxrpl/protocol_autogen)
-          if [ -n "${DIFF}" ]; then
-              echo "::error::Generated protocol files are out of date"
-              git -C .. diff -- include/xrpl/protocol_autogen src/tests/libxrpl/protocol_autogen
-              echo "${MESSAGE}"
-              exit 1
-          fi
-
       - name: Build the binary
         working-directory: ${{ env.BUILD_DIR }}
         env:
@@ -223,26 +245,32 @@ jobs:
           BUILD_TYPE: ${{ inputs.build_type }}
           CMAKE_TARGET: ${{ inputs.cmake_target }}
         run: |
+          set -o pipefail
           cmake \
               --build . \
               --config "${BUILD_TYPE}" \
               --parallel "${BUILD_NPROC}" \
-              --target "${CMAKE_TARGET}"
+              --target "${CMAKE_TARGET}" \
+              2>&1 | tee "${GITHUB_WORKSPACE}/build.log"
 
-      # This step is needed to allow running in non-Nix environments
-      - name: Patch binary to use default loader and remove rpath (Linux)
+      # Nothing may reference the store, so whole trees are checked - the Conan
+      # cache included, since what it holds is what gets uploaded and reused.
+      - name: Check the build output for Nix store references (Nix toolchain)
+        if: ${{ inputs.toolchain == 'nix' }}
+        run: ./bin/check-nix-store-refs.sh "${BUILD_DIR}"
+
+      - name: Check the Conan cache for Nix store references (Nix toolchain)
+        if: ${{ inputs.toolchain == 'nix' }}
+        run: ./bin/check-nix-store-refs.sh "${CONAN_HOME}"
+
+      # Only what PatchNixBinary.cmake retargets: the toolchain in the Linux
+      # images always references the store. Same condition it uses.
+      - name: Check for Nix store references (Linux)
         if: ${{ runner.os == 'Linux' && env.SANITIZERS_ENABLED == 'false' }}
         run: |
-          loader="$(/tmp/loader-path.sh)"
-          patchelf --set-interpreter "${loader}" --remove-rpath "${{ env.BUILD_DIR }}/xrpld"
-
-      # We're only running aarch64 Linux builds in Ubuntu-based images, so this is kept simple
-      - name: Install libatomic (Linux aarch64)
-        if: ${{ runner.os == 'Linux' && runner.arch == 'ARM64' }}
-        run: |
-          apt update --yes
-          apt install -y --no-install-recommends \
-              libatomic1
+          ./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpld"
+          ./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpl_tests"
+          ./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpld_tests"
 
       - name: Show ccache statistics
         if: ${{ inputs.ccache_enabled }}
@@ -254,7 +282,7 @@ jobs:
           fi
 
       - name: Upload the binary (Linux)
-        if: ${{ github.event.repository.visibility == 'public' && runner.os == 'Linux' }}
+        if: ${{ env.PACKAGING_ARTIFACTS_ENABLED == 'true' && runner.os == 'Linux' }}
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: xrpld-${{ inputs.config_name }}
@@ -262,6 +290,22 @@ jobs:
           retention-days: 3
           if-no-files-found: error
 
+      - name: Run the validator-keys tests
+        if: ${{ env.VALIDATOR_KEYS_ENABLED == 'true' }}
+        working-directory: ${{ env.BUILD_DIR }}
+        run: ./validator-keys --unittest
+
+      - name: Upload the validator-keys binary
+        if: ${{ env.PACKAGING_ARTIFACTS_ENABLED == 'true' && env.VALIDATOR_KEYS_ENABLED == 'true' }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: validator-keys-${{ inputs.config_name }}
+          path: |
+            ${{ env.BUILD_DIR }}/validator-keys
+            ${{ env.BUILD_DIR }}/validator-keys-LICENSE
+          retention-days: 3
+          if-no-files-found: error
+
       - name: Upload the test binary (Linux)
         if: ${{ github.event.repository.visibility == 'public' && runner.os == 'Linux' }}
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
@@ -279,7 +323,7 @@ jobs:
           ./xrpld --definitions | python3 -m json.tool >server_definitions.json
 
       - name: Upload server definitions
-        if: ${{ github.event.repository.visibility == 'public' && inputs.config_name == 'debian-gcc-release-amd64' }}
+        if: ${{ github.event.repository.visibility == 'public' && inputs.config_name == 'ubuntu-gcc-debug-amd64-coverage' }}
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: server-definitions
@@ -308,7 +352,9 @@ jobs:
       - name: Run the separate tests
         if: ${{ !inputs.build_only }}
         working-directory: ${{ runner.os == 'Windows' && format('{0}/{1}', env.BUILD_DIR, inputs.build_type) || env.BUILD_DIR }}
-        run: ./xrpl_tests
+        run: |
+          ./xrpl_tests
+          ./xrpld_tests
 
       - name: Run the embedded tests
         if: ${{ !inputs.build_only }}
@@ -337,27 +383,54 @@ jobs:
               PRELOAD=""
           fi
 
-          LD_PRELOAD="$PRELOAD" ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}" 2>&1 | tee unittest.log
+          LD_PRELOAD="$PRELOAD" ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}" 2>&1 | tee "${GITHUB_WORKSPACE}/unittest.log"
 
-      - name: Show test failure summary
-        if: ${{ failure() && !inputs.build_only }}
-        env:
-          WORKING_DIR: ${{ runner.os == 'Windows' && format('{0}\{1}', env.BUILD_DIR, inputs.build_type) || env.BUILD_DIR }}
+      - name: Run Rust tests
+        if: ${{ !inputs.build_only }}
+        working-directory: crates
+        run: cargo nextest run --workspace --all-features --locked --no-tests=warn
+
+      # Smoke-run every benchmark module with a single repetition to confirm the
+      # benchmarks still build and execute. This is a correctness check, not a
+      # performance measurement, so there is nothing to gain from repeating it
+      # across configurations: it is opted into by a single config in the
+      # strategy matrix (see the 'benchmark' flag in the JSON files), which
+      # keeps it off instrumented builds (sanitizers/coverage/voidstar), where
+      # it would be slow and meaningless, off Debug builds, where it is much
+      # slower, and off Windows, where the `install` target does not build them.
+      - name: Run the benchmarks
+        if: ${{ inputs.benchmark }}
+        working-directory: ${{ env.BUILD_DIR }}
         run: |
-          if [ ! -d "${WORKING_DIR}" ]; then
-              echo "Working directory '${WORKING_DIR}' does not exist."
-              exit 0
-          fi
+          rc=0
+          while IFS= read -r bench; do
+              echo "::group::${bench}"
+              "./${bench}" --benchmark_repetitions=1 || rc=1
+              echo "::endgroup::"
+          done < <(find src/benchmarks -type f -perm -u+x -name 'xrpl.bench.*')
+          exit "${rc}"
 
-          cd "${WORKING_DIR}"
+      - name: Show build/test failure summary
+        if: ${{ failure() }}
+        run: |
+          cd "${GITHUB_WORKSPACE}"
 
-          if [ ! -f unittest.log ]; then
-              echo "unittest.log not found; embedded tests may not have run."
-              exit 0
-          fi
-
-          if ! grep -E "failed" unittest.log; then
-              echo "Log present but no failure lines found in unittest.log."
+          if [ -f unittest.log ]; then
+              if ! grep -E "failed" unittest.log | grep -vE "^I[0-9]|^[0-9]+> (ERR:|FTL:)"; then
+                  echo "unittest.log present but no failure lines found."
+              fi
+          elif [ -f build.log ]; then
+              # GCC/Clang emit "error:" (covers "fatal error:"); MSVC emits
+              # "error C####:", "error LNK####:", and "fatal error LNK####:".
+              # -A6 prints the lines that follow each match (source line, caret,
+              # notes, and the "N errors generated" tally) to capture the whole
+              # diagnostic block.
+              if ! grep -E -A6 "error:|error C[0-9]{4}|error LNK[0-9]{4}|fatal error" build.log; then
+                  echo "build.log present but no compile errors found."
+              fi
+          else
+              echo "unittest.log/build.log not found; something went wrong."
+              exit 1
           fi
       - name: Debug failure (Linux)
         if: ${{ failure() && runner.os == 'Linux' && !inputs.build_only }}
@@ -381,13 +454,14 @@ jobs:
               --target coverage
 
       - name: Upload coverage report
-        if: ${{ github.repository == 'XRPLF/rippled' && !inputs.build_only && env.COVERAGE_ENABLED == 'true' }}
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f # v7.0.0
+        if: ${{ github.repository_owner == 'XRPLF' && !inputs.build_only && env.COVERAGE_ENABLED == 'true' }}
+        uses: codecov/codecov-action@303a32d7a59b442fa8d48b6a1cc6825c09c847a5 # v7.1.1
         with:
           disable_search: true
           disable_telem: true
           fail_ci_if_error: true
           files: ${{ env.BUILD_DIR }}/coverage.xml
+          flags: cpp
           plugins: noop
           token: ${{ secrets.CODECOV_TOKEN }}
           verbose: true

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

@@ -40,6 +40,7 @@ jobs:
       fail-fast: ${{ github.event_name == 'merge_group' }}
       matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
     with:
+      benchmark: ${{ matrix.benchmark }}
       build_only: ${{ matrix.build_only }}
       build_type: ${{ matrix.build_type }}
       ccache_enabled: ${{ inputs.ccache_enabled }}
@@ -50,5 +51,6 @@ jobs:
       config_name: ${{ matrix.config_name }}
       sanitizers: ${{ matrix.sanitizers }}
       compiler: ${{ matrix.compiler || '' }}
+      toolchain: ${{ matrix.toolchain || '' }}
     secrets:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

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

@@ -0,0 +1,76 @@
+# This workflow checks that the generated protocol wrapper classes are
+# up-to-date with the macro files and generator scripts they are produced from,
+# see more info in include/xrpl/protocol_autogen/README.md.
+name: Check autogen
+
+# This workflow can only be triggered by other workflows.
+on: workflow_call
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-autogen
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+env:
+  BUILD_DIR: build/codegen
+
+jobs:
+  autogen:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Set up Python
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
+        with:
+          python-version: "3.13"
+
+      # Code generation is pure Python, so the standalone project below offers
+      # the same targets as the main build without needing its dependencies or
+      # a compiler, which keeps this job down to a few seconds.
+      - name: Configure CMake
+        run: cmake -S cmake/codegen -B "${BUILD_DIR}"
+
+      - name: Install code generation dependencies
+        run: cmake --build "${BUILD_DIR}" --target setup_code_gen
+
+      - name: Generate code
+        run: cmake --build "${BUILD_DIR}" --target code_gen
+
+      - name: Check for differences
+        env:
+          MESSAGE: |
+
+            The generated protocol wrapper classes are out of date.
+
+            This typically happens when the macro files or generator scripts
+            have changed but the generated files were not regenerated.
+
+            Run the following from the repository root, then commit and push
+            the regenerated files. This needs neither the dependencies nor a
+            compiler. See include/xrpl/protocol_autogen/README.md for more info.
+
+              cmake -S cmake/codegen -B build/codegen
+              cmake --build build/codegen --target setup_code_gen
+              cmake --build build/codegen --target code_gen
+
+            In an already configured build directory, the 'setup_code_gen' and
+            'code_gen' targets do the same thing.
+        run: |
+          # Record untracked files in the index without staging their contents,
+          # so that classes generated for a newly added transaction or ledger
+          # entry type show up in the diff below rather than silently as an
+          # empty one.
+          git add --intent-to-add .
+          DIFF=$(git status --porcelain)
+          if [ -n "${DIFF}" ]; then
+              # Print the differences to give the contributor a hint about what to
+              # expect when running code generation on their own machine.
+              git diff
+              echo "${MESSAGE}"
+              exit 1
+          fi

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

@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
       - name: Check levelization
         run: python .github/scripts/levelization/generate.py
       - name: Check for differences

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

@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
       - name: Check definitions
         run: .github/scripts/rename/definitions.sh .
       - name: Check copyright notices

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

@@ -3,10 +3,6 @@ name: Run clang-tidy on files
 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
@@ -20,32 +16,34 @@ env:
   BUILD_DIR: build
   BUILD_TYPE: Debug # Debug so that ASSERTS and such participate in clang-tidy check
 
-  OUTPUT_FILE: clang-tidy-output.txt
-  DIFF_FILE: clang-tidy-git-diff.txt
-  ISSUE_FILE: clang-tidy-issue.md
+  OUTPUT_FILE: /tmp/clang-tidy-output.txt
+  FILTERED_OUTPUT_FILE: /tmp/clang-tidy-filtered-output.txt
+  DIFF_FILE: /tmp/clang-tidy-git-diff.txt
+  ISSUE_FILE: /tmp/clang-tidy-issue.md
+
+  COMPILER: clang
 
 jobs:
   determine-files:
-    if: ${{ inputs.check_only_changed }}
     permissions:
       contents: read
-    uses: XRPLF/actions/.github/workflows/determine-tidy-files.yml@312aaab296060ff89d7f798dcab59f019bea6e02
+    uses: XRPLF/actions/.github/workflows/determine-tidy-files.yml@70145243b905dc3e040a61d39c00e178cfb96f71
 
   run-clang-tidy:
     name: Run clang tidy
     needs: [determine-files]
-    if: ${{ always() && !cancelled() && (!inputs.check_only_changed || needs.determine-files.outputs.cpp_changed_files != '' || needs.determine-files.outputs.clang_tidy_config_changed == 'true') }}
+    if: ${{ needs.determine-files.outputs.cpp_changed_files != '' || needs.determine-files.outputs.need_full_run == 'true' }}
     runs-on: ["self-hosted", "Linux", "X64", "heavy"]
-    container: "ghcr.io/xrplf/xrpld/nix-debian:sha-fe4c8ae"
+    container: "ghcr.io/xrplf/xrpld/nix-debian:sha-060957e"
     permissions:
       contents: read
       issues: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@c47daebb2f9db64ffbac71b47d68a661498d5ce8
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
         with:
           enable_ccache: false
 
@@ -59,7 +57,13 @@ jobs:
       - name: Set compiler environment
         uses: ./.github/actions/set-compiler-env
         with:
-          compiler: clang
+          compiler: ${{ env.COMPILER }}
+
+      - name: Use cargo artifacts cache
+        uses: ./.github/actions/cargo-cache
+        with:
+          cache-directories: ${{ env.BUILD_DIR }}/corrosion
+          workspaces: crates -> ../${{ env.BUILD_DIR }}/cargo
 
       - name: Setup Conan
         uses: ./.github/actions/setup-conan
@@ -81,27 +85,28 @@ jobs:
               -Dtests=ON \
               -Dwerr=ON \
               -Dxrpld=ON \
+              -Dverify_headers=ON \
+              -Drust=ON \
               ..
 
-      # clang-tidy needs headers generated from proto files
-      - name: Build libxrpl.libpb
+      - name: Build clang-tidy prerequisites
         working-directory: ${{ env.BUILD_DIR }}
         run: |
-          ninja -j ${{ steps.nproc.outputs.nproc }} xrpl.libpb
+          ninja -j ${{ steps.nproc.outputs.nproc }} tidy_prerequisites
 
       - name: Run clang tidy
         id: run_clang_tidy
         continue-on-error: true
         env:
-          TARGETS: ${{ (needs.determine-files.outputs.clang_tidy_config_changed != 'true' && inputs.check_only_changed) && needs.determine-files.outputs.cpp_changed_files || 'src tests' }}
+          TARGETS: ${{ needs.determine-files.outputs.need_full_run != 'true' && needs.determine-files.outputs.cpp_changed_files || 'include src tests' }}
         run: |
           set -o pipefail
-          run-clang-tidy -j ${{ steps.nproc.outputs.nproc }} -p "${BUILD_DIR}" -quiet -fix -allow-no-checks ${TARGETS} 2>&1 | tee "${OUTPUT_FILE}"
+          run-clang-tidy -j ${{ steps.nproc.outputs.nproc }} -p "${BUILD_DIR}" -quiet -fix -format -allow-no-checks ${TARGETS} 2>&1 | tee "${OUTPUT_FILE}"
 
-      - name: Print errors
+      - name: Print filtered clang-tidy errors
         if: ${{ steps.run_clang_tidy.outcome != 'success' }}
         run: |
-          sed '/error\||/!d' "${OUTPUT_FILE}"
+          bin/filter-clang-tidy.py "${OUTPUT_FILE}"
 
       - name: Upload clang-tidy output
         if: ${{ github.event.repository.visibility == 'public' && steps.run_clang_tidy.outcome != 'success' }}
@@ -145,26 +150,26 @@ jobs:
           \`\`\`
           EOF
 
-      - name: Append clang-tidy output to issue body (filter for errors and warnings)
+      - name: Append filtered clang-tidy output to issue body
         if: ${{ steps.run_clang_tidy.outcome != 'success' }}
         run: |
           if [ -f "${OUTPUT_FILE}" ]; then
-              # Extract lines containing 'error:', 'warning:', or 'note:'
-              grep -E '(error:|warning:|note:)' "${OUTPUT_FILE}" >filtered-output.txt || true
+              # Filter to the unique errors with their source context.
+              bin/filter-clang-tidy.py "${OUTPUT_FILE}" >"${FILTERED_OUTPUT_FILE}" || true
 
               # If filtered output is empty, use original (might be a different error format)
-              if [ ! -s filtered-output.txt ]; then
-                  cp "${OUTPUT_FILE}" filtered-output.txt
+              if [ ! -s "${FILTERED_OUTPUT_FILE}" ]; then
+                  cp "${OUTPUT_FILE}" "${FILTERED_OUTPUT_FILE}"
               fi
 
               # Truncate if too large
-              head -c 60000 filtered-output.txt >>"${ISSUE_FILE}"
-              if [ "$(wc -c <filtered-output.txt)" -gt 60000 ]; then
+              head -c 60000 "${FILTERED_OUTPUT_FILE}" >>"${ISSUE_FILE}"
+              if [ "$(wc -c <"${FILTERED_OUTPUT_FILE}")" -gt 60000 ]; then
                   echo "" >>"${ISSUE_FILE}"
                   echo "... (output truncated, see artifacts for full output)" >>"${ISSUE_FILE}"
               fi
 
-              rm filtered-output.txt
+              rm "${FILTERED_OUTPUT_FILE}"
           else
               echo "No output file found" >>"${ISSUE_FILE}"
           fi

.github/workflows/reusable-package-test-install.yml

@@ -0,0 +1,120 @@
+# Install one package format on every distro family it targets, one job per
+# package name and image, and run the binaries there. Called once per format by
+# reusable-package.yml, which owns the names and the image lists.
+name: Install packages
+
+on:
+  workflow_call:
+    inputs:
+      package_type:
+        description: 'The package format to install ("deb" or "rpm").'
+        required: true
+        type: string
+      package_names:
+        description: "JSON array of package names built for this format."
+        required: true
+        type: string
+      images:
+        description: "JSON array of container images to install in."
+        required: true
+        type: string
+
+defaults:
+  run:
+    shell: bash
+
+env:
+  PACKAGE_DIR: packages
+
+jobs:
+  install:
+    strategy:
+      fail-fast: false
+      matrix:
+        package_name: ${{ fromJson(inputs.package_names) }}
+        image: ${{ fromJson(inputs.images) }}
+    name: "${{ matrix.package_name }} on ${{ matrix.image }}"
+    permissions:
+      contents: read
+    runs-on: ubuntu-latest
+    container: ${{ matrix.image }}
+    timeout-minutes: 5
+
+    steps:
+      # Every package lands in one directory; the step below picks its own,
+      # which keeps this independent of the artifact names.
+      - name: Download package artifacts
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          pattern: "*-pkg"
+          merge-multiple: true
+          path: ${{ env.PACKAGE_DIR }}
+
+      - name: Find the package
+        id: find
+        env:
+          PACKAGE_NAME: ${{ matrix.package_name }}
+          PACKAGE_TYPE: ${{ inputs.package_type }}
+        run: |
+          # The version follows the name, separated by '_' in a DEB and '-' in an
+          # RPM. Requiring a digit after it is what keeps 'xrpld' from picking up
+          # another package, such as 'xrpld-assert'.
+          pattern="${PACKAGE_NAME}[_-][0-9]*.${PACKAGE_TYPE}"
+          package="$(find "${PACKAGE_DIR}" -type f -name "${pattern}" -print -quit)"
+          test -n "${package}" || {
+              echo "no ${pattern} found in ${PACKAGE_DIR}" >&2
+              exit 1
+          }
+          echo "package=${package}" >>"${GITHUB_OUTPUT}"
+
+      # Debian 11 went end-of-life on 2026-08-31
+      # (https://www.debian.org/News/2026/20260831) and its packages are
+      # already partly gone from deb.debian.org, so switch to the
+      # snapshot.debian.org entries the image ships commented out in its
+      # sources.list: they are pinned to the snapshot the image was built
+      # from, so they serve every version it needs and never go away.
+      # Snapshots keep their original, long-passed Valid-Until, hence the
+      # disabled check; the retries absorb snapshot.debian.org's throttling.
+      - name: Switch Debian 11 to snapshot.debian.org
+        if: ${{ matrix.image == 'debian:11' }}
+        run: |
+          sed -i 's|^deb |# deb |; s|^# deb http://snapshot|deb http://snapshot|' /etc/apt/sources.list
+          printf '%s\n' \
+              'Acquire::Check-Valid-Until "false";' \
+              'Acquire::Retries "3";' \
+              >/etc/apt/apt.conf.d/99snapshot
+
+      - name: Install the DEB
+        if: ${{ inputs.package_type == 'deb' }}
+        env:
+          DEBIAN_FRONTEND: noninteractive
+          PACKAGE: ${{ steps.find.outputs.package }}
+        run: |
+          # Stock Debian and Ubuntu images carry no package lists, so apt has
+          # nothing to resolve the systemd dependency from until it fetches them.
+          apt-get update -qq
+          apt-get install -y "./${PACKAGE}"
+
+      - name: Install the RPM
+        if: ${{ inputs.package_type == 'rpm' }}
+        env:
+          PACKAGE: ${{ steps.find.outputs.package }}
+        run: dnf install -y "./${PACKAGE}"
+
+      - name: Run xrpld
+        run: xrpld --version
+
+      - name: Run validator-keys
+        run: validator-keys --version
+
+      - name: Run rippled, the legacy compatibility symlink
+        run: rippled --version
+
+      - name: Check the service account
+        run: id xrpld
+
+      - name: Check the state directory
+        run: test -d /var/lib/xrpld
+
+      - name: Check the log directory
+        run: test -d /var/log/xrpld

.github/workflows/reusable-package.yml

@@ -1,17 +1,57 @@
-# Build Linux packages (DEB and RPM) from pre-built binary artifacts.
-# Discovers which configurations to package from linux.json (configs in
-# "package_configs") and fans out one job per distro. Only linux/amd64 is
-# supported; the runner is hardcoded in the job below.
+# Build, verify and publish Linux packages from the pre-built xrpld and
+# validator-keys artifacts, in these stages:
+#
+#   - 'package' builds and signs one format per config that carries a "package"
+#     map in linux.json; that map names the container image and the format
+#   - 'test-install-deb' and 'test-install-rpm' call
+#     reusable-package-test-install.yml to install what was built on a range of
+#     distros and run the binaries there, so a package that cannot be installed
+#     never reaches Nexus
+#   - 'publish' uploads with the image's publish_pkg.py, doing a --dry-run
+#     unless 'publish: true'
+#   - 'docker' builds an Ubuntu image from the tested DEB, and one with the
+#     voidstar binary for Antithesis, pushing them to Docker Hub and to the
+#     Antithesis registry only with 'publish: true'
+#
+# Only linux/amd64 is supported; the runner is hardcoded in the jobs below.
 name: Package
 
 on:
   workflow_call:
     inputs:
-      pkg_release:
-        description: "Package release number. Increment when repackaging the same executable."
+      publish:
+        description: "Whether to publish the packages after building them."
+        required: false
+        type: boolean
+        default: false
+      nexus_url:
+        description: "The base URL of the Nexus instance hosting the deb and rpm repositories."
         required: false
         type: string
-        default: "1"
+        default: https://packages-upload.xrplf.org
+
+    secrets:
+      remote_username:
+        description: "The username of a Nexus account with write access to the repositories."
+        required: false
+      remote_password:
+        description: "The password or token for that Nexus account."
+        required: false
+      signing_key:
+        description: "Armoured PGP private key used to sign the RPMs."
+        required: false
+      dockerhub_token:
+        description: "A Docker Hub organization access token for xrplf, with push access to xrplf/xrpld."
+        required: false
+      antithesis_docker_host:
+        description: "The host of the Antithesis container registry, e.g. us-central1-docker.pkg.dev."
+        required: false
+      antithesis_docker_path:
+        description: "The repository path in that registry, the image name excluded."
+        required: false
+      antithesis_docker_credentials:
+        description: "The JSON key of a service account with push access to that repository."
+        required: false
 
 defaults:
   run:
@@ -19,18 +59,21 @@ defaults:
 
 env:
   BUILD_DIR: build
+  PACKAGE_DIR: packages
 
 jobs:
   generate-matrix:
     runs-on: ubuntu-latest
     outputs:
       matrix: ${{ steps.generate.outputs.matrix }}
+      deb_package_names: ${{ steps.generate.outputs.deb_package_names }}
+      rpm_package_names: ${{ steps.generate.outputs.rpm_package_names }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Set up Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
         with:
           python-version: "3.13"
 
@@ -39,28 +82,138 @@ jobs:
         working-directory: .github/scripts/strategy-matrix
         run: ./generate.py --packaging >>"${GITHUB_OUTPUT}"
 
-  generate-version:
-    runs-on: ubuntu-latest
-    outputs:
-      version: ${{ steps.version.outputs.version }}
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
-        with:
-          sparse-checkout: |
-            .github/actions/generate-version
-            src/libxrpl/protocol/BuildInfo.cpp
-      - name: Generate version
-        id: version
-        uses: ./.github/actions/generate-version
-
   package:
-    needs: [generate-matrix, generate-version]
-    if: ${{ github.event.repository.visibility == 'public' }}
+    needs: [generate-matrix]
+    if: ${{ github.event.repository.visibility == 'public' || startsWith(github.ref, 'refs/tags/') }}
     strategy:
       fail-fast: false
       matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
-    name: "${{ matrix.artifact_name }}"
+    name: "${{ matrix.xrpld_artifact_name }}"
+    permissions:
+      contents: read
+    runs-on: ["self-hosted", "Linux", "X64", "heavy"]
+    container: ${{ matrix.image }}
+    timeout-minutes: 10
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
+        with:
+          enable_ccache: false
+
+      - name: Download pre-built xrpld binary
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: ${{ matrix.xrpld_artifact_name }}
+          path: ${{ env.BUILD_DIR }}
+
+      - name: Download pre-built validator-keys binary
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: ${{ matrix.validator_keys_artifact_name }}
+          path: ${{ env.BUILD_DIR }}
+
+      - name: Make binaries executable
+        run: chmod +x "${BUILD_DIR}/xrpld" "${BUILD_DIR}/validator-keys"
+
+      - name: Determine release info
+        id: release_info
+        uses: ./.github/actions/release-info
+
+      - name: Build package
+        env:
+          PACKAGE_TYPE: ${{ matrix.package_type }}
+          PACKAGE_VARIANT: ${{ matrix.package_variant }}
+          PKG_RELEASE: ${{ steps.release_info.outputs.pkg_release }}
+          CHANNEL: ${{ steps.release_info.outputs.channel }}
+        run: |
+          ./package/build_pkg.py \
+              --package-type "${PACKAGE_TYPE}" \
+              --build-dir "${BUILD_DIR}" \
+              --pkg-release "${PKG_RELEASE}" \
+              --variant "${PACKAGE_VARIANT}" \
+              --channel "${CHANNEL}"
+
+      # Before the upload, so the artifact, the tested package and the published
+      # package are the same bytes.
+      - name: Sign RPM
+        if: ${{ inputs.publish && matrix.package_type == 'rpm' }}
+        env:
+          PKG_SIGNING_KEY: ${{ secrets.signing_key }}
+        run: ./package/sign_rpm.py --package-dir "${BUILD_DIR}"
+
+      # Split from the debug symbols, which are an order of magnitude larger, so
+      # that test-install downloads only what it installs. In the globs below the
+      # version follows the name, separated by '_' in a DEB and '-' in an RPM. A
+      # version starts with a digit and a longer name does not, so that one digit
+      # is what tells 'xrpld-3.4.1-...' from 'xrpld-assert-3.4.1-...'.
+      - name: Upload package artifact
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: ${{ matrix.xrpld_artifact_name }}-pkg
+          path: |
+            ${{ env.BUILD_DIR }}/debbuild/${{ matrix.package_name }}_[0-9]*.deb
+            ${{ env.BUILD_DIR }}/rpmbuild/RPMS/**/${{ matrix.package_name }}-[0-9]*.rpm
+          if-no-files-found: error
+
+      - name: Upload debug symbol artifact
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: ${{ matrix.xrpld_artifact_name }}-pkg-debug
+          path: |
+            ${{ env.BUILD_DIR }}/debbuild/${{ matrix.package_name }}-dbgsym_[0-9]*.deb
+            ${{ env.BUILD_DIR }}/debbuild/${{ matrix.package_name }}-dbgsym_[0-9]*.ddeb
+            ${{ env.BUILD_DIR }}/rpmbuild/RPMS/**/${{ matrix.package_name }}-debuginfo-[0-9]*.rpm
+          if-no-files-found: error
+
+  # One call per format, so a variant packaged for one format is installed for
+  # that format alone. The images are every distro family that format targets,
+  # oldest release first, so both ends of the dependency range the packages
+  # declare are exercised.
+  test-install-deb:
+    needs: [generate-matrix, package]
+    name: install deb
+    uses: ./.github/workflows/reusable-package-test-install.yml
+    with:
+      package_type: deb
+      package_names: ${{ needs.generate-matrix.outputs.deb_package_names }}
+      images: |
+        [
+          "debian:11",
+          "debian:12",
+          "debian:13",
+          "ubuntu:20.04",
+          "ubuntu:22.04",
+          "ubuntu:24.04",
+          "ubuntu:26.04"
+        ]
+
+  test-install-rpm:
+    needs: [generate-matrix, package]
+    name: install rpm
+    uses: ./.github/workflows/reusable-package-test-install.yml
+    with:
+      package_type: rpm
+      package_names: ${{ needs.generate-matrix.outputs.rpm_package_names }}
+      images: |
+        [
+          "almalinux:9",
+          "almalinux:10",
+          "rockylinux/rockylinux:9",
+          "rockylinux/rockylinux:10",
+          "registry.access.redhat.com/ubi9/ubi",
+          "registry.access.redhat.com/ubi10/ubi"
+        ]
+
+  publish:
+    needs: [generate-matrix, package, test-install-deb, test-install-rpm]
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
+    name: "publish ${{ matrix.xrpld_artifact_name }}${{ !inputs.publish && ' (dry run)' || '' }}"
     permissions:
       contents: read
     runs-on: ["self-hosted", "Linux", "X64", "heavy"]
@@ -69,29 +222,127 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
-      - name: Download pre-built binary
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
+        with:
+          enable_ccache: false
+
+      # Both artifacts, so the debug symbols are published alongside the package.
+      - name: Download package artifacts
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: ${{ matrix.artifact_name }}
-          path: ${{ env.BUILD_DIR }}
+          pattern: ${{ matrix.xrpld_artifact_name }}-pkg*
+          merge-multiple: true
+          path: ${{ env.PACKAGE_DIR }}
 
-      - name: Make binary executable
-        run: chmod +x "${BUILD_DIR}/xrpld"
+      - name: Determine release info
+        id: release_info
+        uses: ./.github/actions/release-info
 
-      - name: Build package
+      - name: Publish package
         env:
-          PKG_VERSION: ${{ needs.generate-version.outputs.version }}
-          PKG_RELEASE: ${{ inputs.pkg_release }}
-        run: ./package/build_pkg.sh
+          CHANNEL: ${{ steps.release_info.outputs.channel }}
+          DRY_RUN_OPTION: ${{ !inputs.publish && '--dry-run' || '' }}
+          NEXUS_URL: ${{ inputs.nexus_url }}
+          NEXUS_USERNAME: ${{ inputs.publish && secrets.remote_username || '' }}
+          NEXUS_PASSWORD: ${{ inputs.publish && secrets.remote_password || '' }}
+        run: |
+          publish_pkg.py \
+              --channel "${CHANNEL}" \
+              --package-dir "${PACKAGE_DIR}" \
+              --nexus-url "${NEXUS_URL}" \
+              ${DRY_RUN_OPTION}
 
-      - name: Upload package artifact
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+  docker:
+    needs: [test-install-deb, test-install-rpm]
+    strategy:
+      fail-fast: false
+      matrix:
+        target: [xrpld, voidstar]
+    name: "docker ${{ matrix.target }}${{ !inputs.publish && ' (dry run)' || '' }}"
+    permissions:
+      contents: read
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    env:
+      CONTEXT: image-context
+      IMAGE: ${{ matrix.target == 'voidstar' && 'xrpld-voidstar' || 'xrplf/xrpld' }}:${{ github.ref_type == 'tag' && github.ref_name || 'develop' }}
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Determine release info
+        id: release_info
+        uses: ./.github/actions/release-info
+
+      # Docker Hub is public, so it only gets builds whose packages are public:
+      # those of a public codebase, and stable releases.
+      # The Antithesis registry is private, so it gets every build.
+      - name: Decide whether to push
+        env:
+          PUSH: ${{ inputs.publish && (matrix.target == 'voidstar' || github.event.repository.visibility == 'public' || steps.release_info.outputs.channel == 'stable') }}
+        run: echo "PUSH=${PUSH}" | tee -a "${GITHUB_ENV}"
+
+      - name: Download package artifacts
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: ${{ matrix.artifact_name }}-pkg-${{ needs.generate-version.outputs.version }}
-          path: |
-            ${{ env.BUILD_DIR }}/debbuild/*.deb
-            ${{ env.BUILD_DIR }}/debbuild/*.ddeb
-            ${{ env.BUILD_DIR }}/rpmbuild/RPMS/**/*.rpm
-          if-no-files-found: error
+          pattern: "*-pkg"
+          merge-multiple: true
+          path: ${{ env.PACKAGE_DIR }}
+
+      - name: Download voidstar binary
+        if: ${{ matrix.target == 'voidstar' }}
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          name: xrpld-ubuntu-clang-debug-amd64-voidstar
+          path: ${{ env.CONTEXT }}
+
+      - name: Build image
+        env:
+          TARGET: ${{ matrix.target }}
+        run: |
+          mkdir -p "${CONTEXT}"
+          find "${PACKAGE_DIR}" -type f -name 'xrpld_[0-9]*.deb' -exec cp {} "${CONTEXT}/" \;
+          docker build --pull --file package/images/xrpld/Dockerfile --target "${TARGET}" --tag "${IMAGE}" "${CONTEXT}"
+
+      - name: Start the server
+        run: |
+          container="$(docker run --detach "${IMAGE}" --standalone --silent --conf /etc/xrpld/xrpld.cfg)"
+          trap 'docker rm --force "${container}" >/dev/null' EXIT
+
+          for _ in $(seq 30); do
+              output="$(docker exec "${container}" xrpld --conf /etc/xrpld/xrpld.cfg server_info || true)"
+              if [[ "${output}" == *'"status" : "success"'* ]]; then
+                  exit 0
+              fi
+              sleep 2
+          done
+
+          docker logs "${container}"
+          exit 1
+
+      - name: Log in to Docker Hub
+        if: ${{ env.PUSH == 'true' && matrix.target == 'xrpld' }}
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
+        with:
+          username: xrplf
+          password: ${{ secrets.dockerhub_token }}
+
+      - name: Log in to the Antithesis registry
+        if: ${{ env.PUSH == 'true' && matrix.target == 'voidstar' }}
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
+        with:
+          registry: ${{ secrets.antithesis_docker_host }}
+          username: _json_key
+          password: ${{ secrets.antithesis_docker_credentials }}
+
+      - name: Push image
+        if: ${{ env.PUSH == 'true' }}
+        env:
+          REGISTRY: ${{ matrix.target == 'voidstar' && format('{0}/{1}/', secrets.antithesis_docker_host, secrets.antithesis_docker_path) || '' }}
+        run: |
+          docker tag "${IMAGE}" "${REGISTRY}${IMAGE}"
+          docker push "${REGISTRY}${IMAGE}"

.github/workflows/reusable-rust.yml

@@ -0,0 +1,84 @@
+# Clippy, coverage and documentation for the Rust crates in crates/. Each runs
+# as an independent job on a GitHub-hosted runner, but inside the same container
+# image used to build the crates in the C++/Corrosion path, so the toolchain
+# (and therefore the lints and the cargo cache) matches what production builds
+# use. Coverage is the exception: it needs the nightly rustc that honours
+# #[coverage(off)], which the image carries alongside the pinned stable.
+#
+# Rust unit tests are deliberately NOT run here. They run as part of the C++
+# build (reusable-build-test-config.yml), which already compiles the crates on a
+# self-hosted runner, so there is no need to provision a toolchain again.
+name: Rust
+
+on:
+  workflow_call:
+    secrets:
+      CODECOV_TOKEN:
+        description: "The Codecov token to use for uploading coverage reports."
+        required: true
+
+defaults:
+  run:
+    shell: bash
+    working-directory: crates
+
+permissions:
+  contents: read
+
+jobs:
+  clippy:
+    runs-on: ubuntu-latest
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Use cargo artifacts cache
+        uses: ./.github/actions/cargo-cache
+
+      - name: Run clippy
+        run: cargo clippy --workspace --all-targets --all-features --locked -- -D warnings
+
+  coverage:
+    runs-on: ubuntu-latest
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Use the nightly Rust toolchain
+        run: rust-nightly path >>"${GITHUB_PATH}"
+
+      - name: Use cargo artifacts cache
+        uses: ./.github/actions/cargo-cache
+
+      - name: Generate coverage report
+        run: cargo llvm-cov nextest --workspace --all-features --locked --no-tests=warn --lcov --output-path lcov.info
+
+      - name: Upload coverage report
+        if: ${{ github.repository == 'XRPLF/rippled' }}
+        uses: codecov/codecov-action@303a32d7a59b442fa8d48b6a1cc6825c09c847a5 # v7.1.1
+        with:
+          disable_search: true
+          disable_telem: true
+          fail_ci_if_error: true
+          files: crates/lcov.info
+          flags: rust
+          plugins: noop
+          token: ${{ secrets.CODECOV_TOKEN }}
+          verbose: true
+
+  doc:
+    runs-on: ubuntu-latest
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - name: Use cargo artifacts cache
+        uses: ./.github/actions/cargo-cache
+
+      - name: Build documentation
+        env:
+          RUSTDOCFLAGS: "-D warnings"
+        run: cargo doc --workspace --no-deps --all-features --locked

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

@@ -23,10 +23,10 @@ jobs:
       matrix: ${{ steps.generate.outputs.matrix }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Set up Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
         with:
           python-version: "3.13"
 
@@ -35,5 +35,8 @@ jobs:
         id: generate
         env:
           GENERATE_CONFIG: ${{ inputs.os != '' && format('--config={0}', inputs.os) || '' }}
-          GENERATE_EVENT: ${{ github.event_name }}
-        run: ./generate.py ${GENERATE_CONFIG} --event="${GENERATE_EVENT}" >>"${GITHUB_OUTPUT}"
+          # Run only the minimal matrix for pull requests that are not yet
+          # labeled "Ready to merge" or "Full CI build". Any other event (merge
+          # queue, push, schedule, manual dispatch) runs the full matrix.
+          GENERATE_MINIMAL: ${{ (github.event_name == 'pull_request' && !contains(github.event.pull_request.labels.*.name, 'Ready to merge') && !contains(github.event.pull_request.labels.*.name, 'Full CI build')) && '--minimal' || '' }}
+        run: ./generate.py ${GENERATE_CONFIG} ${GENERATE_MINIMAL} >>"${GITHUB_OUTPUT}"

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

@@ -14,7 +14,7 @@ on:
         description: "The URL of the Conan endpoint to use."
         required: false
         type: string
-        default: https://conan.ripplex.io
+        default: https://conan.xrplf.org/repository/conan/
 
     secrets:
       remote_username:
@@ -40,14 +40,23 @@ defaults:
 jobs:
   upload:
     runs-on: ubuntu-latest
-    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-fe4c8ae
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
+    env:
+      REMOTE_NAME: ${{ inputs.remote_name }}
+      CONAN_LOGIN_USERNAME_XRPLF: ${{ secrets.remote_username }}
+      CONAN_PASSWORD_XRPLF: ${{ secrets.remote_password }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
-      - name: Generate build version number
-        id: version
-        uses: ./.github/actions/generate-version
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
+        with:
+          enable_ccache: false
+
+      - name: Determine release info
+        id: release_info
+        uses: ./.github/actions/release-info
 
       - name: Set up Conan
         uses: ./.github/actions/setup-conan
@@ -56,48 +65,20 @@ jobs:
           remote_url: ${{ inputs.remote_url }}
 
       - name: Log into Conan remote
-        env:
-          REMOTE_NAME: ${{ inputs.remote_name }}
-          REMOTE_USERNAME: ${{ secrets.remote_username }}
-          REMOTE_PASSWORD: ${{ secrets.remote_password }}
-        run: conan remote login "${REMOTE_NAME}" "${REMOTE_USERNAME}" --password "${REMOTE_PASSWORD}"
+        run: conan remote login "${REMOTE_NAME}" "${CONAN_LOGIN_USERNAME_XRPLF}" --password "${CONAN_PASSWORD_XRPLF}"
 
       - name: Upload Conan recipe (version)
         env:
-          REMOTE_NAME: ${{ inputs.remote_name }}
+          VERSION: ${{ steps.release_info.outputs.version }}
         run: |
-          conan export . --version=${{ steps.version.outputs.version }}
-          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/${{ steps.version.outputs.version }}
+          conan export . --version="${VERSION}"
+          conan upload --confirm --check --remote="${REMOTE_NAME}" "xrpl/${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 }}
+        if: ${{ github.ref == 'refs/heads/develop' }}
         run: |
           conan export . --version=develop
           conan upload --confirm --check --remote="${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: xrpl/${{ steps.version.outputs.version }}
+      ref: xrpl/${{ steps.release_info.outputs.version }}

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

@@ -34,7 +34,7 @@ on:
 
 env:
   CONAN_REMOTE_NAME: xrplf
-  CONAN_REMOTE_URL: https://conan.ripplex.io
+  CONAN_REMOTE_URL: https://conan.xrplf.org/repository/conan/
   NPROC_SUBTRACT: 2
 
 concurrency:
@@ -65,13 +65,18 @@ jobs:
         uses: XRPLF/actions/cleanup-workspace@c7d9ce5ebb03c752a354889ecd870cadfc2b1cd4
 
       - name: Checkout repository
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@c47daebb2f9db64ffbac71b47d68a661498d5ce8
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
         with:
           enable_ccache: false
 
+      # Before any step that uses a build tool, composite actions included.
+      - name: Setup Nix environment
+        if: ${{ matrix.toolchain == 'nix' }}
+        uses: ./.github/actions/setup-nix-env
+
       - name: Print build environment
         uses: XRPLF/actions/print-build-env@59dec886e4afb05a1724443af08baccbc045b574
 
@@ -87,7 +92,9 @@ jobs:
         with:
           compiler: ${{ matrix.compiler }}
 
+      # `setup-nix-env` already did this for the Nix toolchain.
       - name: Setup Conan
+        if: ${{ matrix.toolchain != 'nix' }}
         env:
           SANITIZERS: ${{ matrix.sanitizers }}
         uses: ./.github/actions/setup-conan
@@ -106,12 +113,18 @@ jobs:
           log_verbosity: ${{ runner.os == 'Windows' && 'quiet' || 'verbose' }}
           sanitizers: ${{ matrix.sanitizers }}
 
+      - name: Check the Conan cache for Nix store references (Nix toolchain)
+        if: ${{ matrix.toolchain == 'nix' }}
+        run: ./bin/check-nix-store-refs.sh "${CONAN_HOME}"
+
       - name: Log into Conan remote
         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 }}"
+        run: conan remote login "${CONAN_REMOTE_NAME}" "${{ secrets.NEXUS_REMOTE_USERNAME }}" --password "${{ secrets.NEXUS_REMOTE_PASSWORD }}"
 
       - name: Upload Conan packages
         if: ${{ github.repository == 'XRPLF/rippled' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') }}
         env:
           FORCE_OPTION: ${{ github.event.inputs.force_upload == 'true' && '--force' || '' }}
+          CONAN_LOGIN_USERNAME_XRPLF: ${{ secrets.NEXUS_REMOTE_USERNAME }}
+          CONAN_PASSWORD_XRPLF: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
         run: conan upload "*" --remote="${CONAN_REMOTE_NAME}" --confirm ${FORCE_OPTION}

.gitignore

@@ -72,17 +72,31 @@ DerivedData
 /.zed/
 
 # AI tools.
+# Shared/committable AI agent config (AGENTS.md, CLAUDE.md, GEMINI.md, .claude/settings.json,
+# tool-specific rules files, etc.) should be checked in — see CONTRIBUTING.md. Only the
+# personal/local variants below are ignored.
 /.agent
 /.agents
 /.augment
-/.claude
-/CLAUDE.md
+/.claude/settings.local.json
+AGENTS.override.md
+CLAUDE.local.md
+GEMINI.local.md
 
 # Python
 __pycache__
 
+# Rust build artifacts.
+target/
+
 # Direnv's directory
 /.direnv
 
+# Direnv's local, per-developer overrides
+/.envrc.local
+
 # clangd cache
 /.cache
+
+# Rust build directory
+crates/target

.pre-commit-config.yaml

@@ -15,6 +15,7 @@ repos:
     hooks:
       - id: check-added-large-files
         args: [--maxkb=400, --enforce-all]
+      - id: check-executables-have-shebangs
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-merge-conflict
@@ -27,41 +28,93 @@ repos:
         entry: ./bin/pre-commit/clang_tidy_check.py
         language: python
         types_or: [c++, c]
-        exclude: ^include/xrpl/protocol_autogen
-        pass_filenames: false # script determines the staged files itself
+        # .ipp fragments are included by their owning header rather than compiled
+        # as standalone translation units, so they have no compile_commands.json
+        # entry to lint (verify_headers checks them transitively).
+        exclude: '^include/xrpl/protocol_autogen|\.ipp$'
+        # run-clang-tidy --fix may edit headers included by files it is not run on,
+        # so pre-commit must not split the files across parallel hook invocations.
+        # The script determines the staged files itself and lets run-clang-tidy
+        # handle parallelism internally.
+        pass_filenames: false
       - id: fix-include-style
         name: fix include style
         entry: ./bin/pre-commit/fix_include_style.py
         language: python
         types_or: [c++, c]
         exclude: ^include/xrpl/protocol_autogen/(transactions|ledger_entries)/
+      - id: fix-pragma-once
+        name: fix missing '#pragma once' declarations in header files
+        language: python
+        entry: ./bin/pre-commit/fix_pragma_once.py
+        files: \.(h|hpp)$
+      - id: check-doxygen-style
+        name: check Doxygen comment style
+        entry: ./bin/pre-commit/check_doxygen_style.py
+        language: python
+        types_or: [c++, c]
+      - id: fix-gtest-names
+        name: "fix gtest names: CamelCase suite, snake_case test case"
+        entry: ./bin/pre-commit/fix_gtest_names.py
+        language: python
+        types_or: [c++, c]
 
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: dd18dad857d6133e90bbe478f4f2f22ec0030269 # frozen: v22.1.5
+    rev: e2b496dc2bd8340c2524cb9a2d2a943cde1bb6df # frozen: v23.1.1
     hooks:
       - id: clang-format
         args: [--style=file]
-        "types_or": [c++, c, proto]
+        types_or: [c++, c, proto]
         exclude: ^include/xrpl/protocol_autogen/(transactions|ledger_entries)/
 
+  - repo: local
+    hooks:
+      - id: cargo-fmt
+        name: cargo fmt
+        entry: cargo fmt --manifest-path crates/Cargo.toml --all
+        language: system
+        types: [rust]
+        pass_filenames: false # rustfmt formats the whole workspace
+      - id: check-coverage-attrs
+        name: check Rust coverage attributes
+        entry: ./bin/pre-commit/check_rust_coverage_attrs.py
+        language: python
+        files: ^crates/.*\.rs$
+
   - repo: https://github.com/BlankSpruce/gersemi-pre-commit
-    rev: faadd6a9d852369ca94f4d15b2404c967ba8cb01 # frozen: 0.27.6
+    rev: f1c4833f8cf23c6d952673abc73525411a5719e8 # frozen: 0.29.1
     hooks:
       - id: gersemi
 
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: 515f543f5718ebfd6ce22e16708bb32c68ff96e1 # frozen: v3.8.3
+    rev: ef4a397f916211b4a39ccf9d3d9cbb6562157251 # frozen: v3.9.9
     hooks:
       - id: prettier
         args: [--end-of-line=auto]
 
+  # Scoped to package/: the rest of the repo's Python has pre-existing findings,
+  # so widening these is its own change.
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: a56c0b927e6465d37cae3e97d35d4d18ab2b96cd # frozen: v0.16.9
+    hooks:
+      - id: ruff-check
+        args: [--fix]
+        files: ^package/.*\.py$
+
   - repo: https://github.com/psf/black-pre-commit-mirror
     rev: 4160603246a6b365d4a2af661c6d71b0a0f50478 # frozen: 26.5.1
     hooks:
       - id: black
 
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 7ff8d35ae36a7d2b968f2f90b4c723e292e594ee # frozen: v2.3.1
+    hooks:
+      - id: mypy
+        args: [--strict]
+        files: ^package/.*\.py$
+
   - repo: https://github.com/scop/pre-commit-shfmt
-    rev: 05c1426671b9237fb5e1444dd63aa5731bec0dfb # frozen: v3.13.1-1
+    rev: 479be5958357ba5ab65ce47172117348516860e9 # frozen: v3.14.1-1
     hooks:
       - id: shfmt
         args: [--write, --indent=4, --case-indent=true]
@@ -80,22 +133,21 @@ repos:
         files: \.md$
 
   - repo: https://github.com/streetsidesoftware/cspell-cli
-    rev: 4643f154907327ee0a2c7038f0296e0dd77d9776 # frozen: v10.0.0
+    rev: f5c5d72342f35643988a9ffa0705c05bd3ff8383 # frozen: v10.3.0
     hooks:
-      - id: cspell # Spell check changed files
+      - id: cspell
+        name: check changed files spelling
         exclude: |
           (?x)^(
-              .config/cspell.config.yaml|
+              \.cspell\.config\.yaml|
               include/xrpl/protocol_autogen/(transactions|ledger_entries)/.*
           )$
-      - id: cspell # Spell check the commit message
+      - id: cspell
         name: check commit message spelling
         args:
           - --no-must-find-files
           - --no-progress
           - --no-summary
-          - --files
-          - .git/COMMIT_EDITMSG
         stages: [commit-msg]
 
   - repo: local

AGENTS.md

@@ -0,0 +1,42 @@
+# AGENTS.md
+
+This file provides guidance to AI coding agents (Claude Code, and other AGENTS.md-compatible tools) when working with code in this repository.
+
+## Build
+
+Required on Linux/macOS: use the Nix devshell, which sets up the compiler, Conan, ccache, and (optionally) Rust automatically.
+
+```bash
+nix develop
+```
+
+For alternate devshell variants (specific compiler, no-compiler, coverage), see [docs/build/nix.md](./docs/build/nix.md). For the manual build steps, CMake options, and protocol codegen commands, see [BUILD.md](./BUILD.md) (`## Steps`, `## Options`, `## Code generation`).
+
+Rust crate tests (independent of the CMake build): `cargo test --manifest-path crates/Cargo.toml --workspace` (CI uses `cargo nextest`).
+
+## Testing
+
+Unit tests are a custom framework built into the `xrpld` binary itself (not Boost.Test/GTest/Catch); see [CONTRIBUTING.md](./CONTRIBUTING.md#unit-tests) for the basic invocation. Notes not covered there:
+
+- A suite's `--unittest` name is built from the arguments to its `BEAST_DEFINE_TESTSUITE`/`BEAST_DEFINE_TESTSUITE_PRIO` macro (usually at the bottom of the test file), in reverse order and joined with `.`: `BEAST_DEFINE_TESTSUITE(Credentials, app, xrpl)` → `xrpl.app.Credentials`.
+- `--unittest-arg` does nothing — don't use it.
+- Tests that run offline in under a minute should be automatic `--unittest` suites; anything else is a manual/integration test.
+- New tests should be written using `gtest` under `src/tests/` unless that isn't possible, in which case fall back to the legacy Beast framework under `src/test/`. `tests/` (top-level) holds integration tests exercised against `libxrpl`/`xrpld`.
+
+## Lint/Format
+
+See [CONTRIBUTING.md](./CONTRIBUTING.md#pre-commit-hooks) for `pre-commit` setup and [CONTRIBUTING.md](./CONTRIBUTING.md#clang-tidy) for `clang-tidy` (opt-in, needs local `clang-tidy` and generated headers).
+
+## Code Style
+
+New file placement and header levelization: see [CONTRIBUTING.md](./CONTRIBUTING.md#before-making-a-pull-request). Braces, whitespace, member order, and other conventions: see [docs/CodingStyle.md](./docs/CodingStyle.md). `XRPL_ASSERT`/`UNREACHABLE` contracts: see [CONTRIBUTING.md](./CONTRIBUTING.md#contracts-and-instrumentation). Commit messages: see [CONTRIBUTING.md](./CONTRIBUTING.md#good-commit-messages).
+
+## Architecture
+
+Paths below reflect the current layout; update this section if modularization moves a subsystem to a different directory.
+
+- `include/xrpl/` + `src/libxrpl/` — the core protocol library: ledger, shamap, consensus, crypto, json, resource, nodestore, rdb, peerfinder, and `tx/` (transaction application: `Transactor.cpp`, `applySteps.cpp`, invariants, payment paths). `tx/transactors/` has one file per transaction type, grouped by subsystem: `escrow/`, `vault/`, `lending/`, `sponsor/`, `nft/`, `token/` (MPT), `payment_channel/`, `permissioned_domain/`, `dex/`, `oracle/`, `did/`, `credentials/`, `bridge/`, `check/`, `delegate/`, `account/`, `system/`. Any change to transaction-processing behavior must be gated behind an Amendment.
+- `src/xrpld/` — the server application built on top of `libxrpl`: `app`, `core`, `overlay` (P2P networking), `peerfinder`, `perflog`, `rpc`, `shamap`. `main` builds an `ApplicationImp` implementing `Application`; most components hold a reference to it (`app_`), giving broad cross-component access — expect to trace call chains through `Application&`.
+- `src/test/` — unit tests mirroring the subsystems above, plus `jtx/` (the transaction-building test DSL — e.g. `jtx/escrow.h`, `jtx/vault.h`, `jtx/sponsor.h`, `jtx/permissioned_dex.h`) and `unit_test/` (the custom test framework itself, derived from Beast).
+- `src/tests/` — unit tests for `libxrpl` written in `gtest`, gradually replacing the `src/test` equivalents.
+- `crates/` — a Rust workspace (only built with `-Dxrpld -Drust=ON`) bridged into C++ via `cxxbridge`/the `cxx` crate; currently just a `hello_world` interop scaffold. Requires the Rust toolchain pinned in `rust-toolchain.toml` (the Nix devshell provides it automatically).

API-CHANGELOG.md

@@ -22,14 +22,56 @@ API version 2 is available in `xrpld` version 2.0.0 and later. See [API-VERSION-
 
 This version is supported by all `xrpld` versions. For WebSocket and HTTP JSON-RPC requests, it is currently the default API version used when no `api_version` is specified.
 
-## Unreleased
+## XRP Ledger server version 3.5.0
 
-This section contains changes targeting a future version.
+Version 3.5.0 is not yet released.
 
-### Additions
+### Additions in 3.5.0
+
+- `subscribe`, `unsubscribe`: Added an optional `mpt_issuances` request field, an array of MPT issuance IDs (hex strings). Subscribers receive a message with `type` `mptTransaction` for each validated transaction whose metadata affects a subscribed issuance; the message has the same fields as the `transactions` stream. MPT issuance subscriptions count toward the per-connection subscription limit. An empty array, a non-array value, or an invalid ID returns `invalidParams`. ([#5671](https://github.com/XRPLF/rippled/pull/5671))
+
+## XRP Ledger server version 3.4.0
+
+Version 3.4.0 is not yet released. These changes are available in the 3.4.0 beta releases.
+
+### Additions in 3.4.0
+
+- `ledger`: `nftoken_id`, `nftoken_ids`, and `offer_id` are now included in transaction metadata when transactions are expanded (`expand`, or admin-only `full`), matching the `tx`, `account_tx`, and `subscribe` (`transactions` stream) responses. ([#5706](https://github.com/XRPLF/rippled/pull/5706))
+
+### Bugfixes in 3.4.0
+
+- `sign`, `sign_for`, `submit`: `signature_target` now returns `invalidParams` unless it names `CounterpartySignature` or `SponsorSignature`. It previously accepted any inner object field, such as `Book` or `NFToken`, and signed into it.
+- `sign`, `sign_for`, `submit`, `submit_multisigned`: With `fixCleanup3_4_0` enabled, a signature in `CounterpartySignature` or `SponsorSignature` covers a different prefix than the transaction's own signature, so a signature can no longer be moved from one of those roles into another. Clients that build these signatures themselves must use the new prefixes: `CPT` and `CPM` (single- and multi-signing) for `CounterpartySignature`, and `SPN` and `SPM` for `SponsorSignature`.
+- `get_aggregate_price`: Duplicate entries in the `oracles` request array are now ignored. [#6586](https://github.com/XRPLF/rippled/pull/6586)
+- `vault_info`: Errors now identify what the request got wrong instead of reporting every failure as the unregistered token `malformedRequest`, and the `error`, `error_code` and `error_message` fields now agree with each other. An invalid `vault_id` or `seq` returns `invalidParams`, an invalid `owner` returns `actMalformed`, and a request that mixes `vault_id` with `owner`/`seq` or supplies neither returns `invalidParams` with a message naming the accepted combinations. [#8015](https://github.com/XRPLF/rippled/pull/8015)
+- `vault_info`: A well-formed all-zero `vault_id` now returns `entryNotFound` instead of being rejected as malformed, and `entryNotFound` responses now include `error_code` and `error_message`. Clients that request `ripplerpc` 3.0 or above therefore receive HTTP 400 with that error rather than HTTP 200. [#8015](https://github.com/XRPLF/rippled/pull/8015)
+- `vault_info`: `vault_id` and `owner` must now be strings, matching how `ledger_entry` reads the same fields. An object or an array in either field previously produced an internal error, and a number was silently converted to its decimal text; `vault_id` now returns `invalidParams` and `owner` returns `actMalformed`. [#8015](https://github.com/XRPLF/rippled/pull/8015)
+- `gateway_balances`: The `account` and `ident` fields now return an `invalidParams` error if the value is not a string, instead of an `internal` error. [#7655](https://github.com/XRPLF/rippled/pull/7655)
+- `account_lines`: The `peer` field now returns an error if the value is not a string. [#7728](https://github.com/XRPLF/rippled/pull/7728)
+- `ledger`: `delivered_amount` is now included in the metadata of successful `AccountDelete` transactions when transactions are expanded (`expand`, or admin-only `full`). Previously it was only added for `Payment` and `CheckCash`, which made `ledger` inconsistent with `tx` and `account_tx`. [#5706](https://github.com/XRPLF/rippled/pull/5706)
+- `noripple_check`: The `transactions` field is no longer included in error responses; it is still returned (possibly as an empty array) whenever `transactions` is `true` and the request succeeds. A malformed `account` is now rejected before the ledger is looked up, so that error response no longer carries the `ledger_hash`, `ledger_index`, and `validated` fields ([#6303](https://github.com/XRPLF/rippled/pull/6303)).
+
+## XRP Ledger server version 3.3.0
+
+[Version 3.3.0](https://github.com/XRPLF/rippled/releases/tag/3.3.0) was released on Aug 6, 2026.
+
+### Additions in 3.3.0
+
+- `account_tx`: Added an optional `delegate` request object to filter delegated transactions. The object requires `delegate_filter`, which must be either `actor` for transactions owned by the requested account but signed by another account, or `authorizer` for transactions signed by the requested account on behalf of another account. The optional `counter_party` account narrows the results to a specific signer/delegate for `actor` or a specific owner/delegator for `authorizer`. Malformed `delegate`, `delegate_filter`, and `counter_party` values return standard invalid field errors, and invalid account IDs return `actMalformed`. When paginating delegate-filtered queries, a marker from a delegate-filtered query includes a `delegate` flag and is only valid for follow-up requests that also supply `delegate` (mixing marker conventions returns `invalidParams`). Because filtering is applied after the ledger scan, a page may contain fewer results than `limit` (possibly zero) while still returning a marker, so callers must continue until no marker is present. ([#6126](https://github.com/XRPLF/rippled/pull/6126))
+
+## XRP Ledger server version 3.2.1
+
+[Version 3.2.1](https://github.com/XRPLF/rippled/releases/tag/3.2.1) was released on Aug 1, 2026.
+
+This release contains bug fixes only and no API changes.
+
+## XRP Ledger server version 3.2.0
+
+[Version 3.2.0](https://github.com/XRPLF/rippled/releases/tag/3.2.0) was released on Jun 16, 2026.
+
+### Additions in 3.2.0
 
 - `ledger_entry`, `account_objects`: The `Delegate` ledger entry now includes an optional `DestinationNode` field, which stores the index into the authorized account's owner directory. This field is present on entries created after bidirectional directory tracking was introduced and may appear in RPC responses for those entries. ([#6681](https://github.com/XRPLF/rippled/pull/6681))
-
 - `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.
@@ -37,7 +79,7 @@ This section contains changes targeting a future version.
   - `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
+### Bugfixes in 3.2.0
 
 - 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)
 - `ping`: The `ip` field is no longer returned as an empty string for proxied connections without a forwarded-for header. It is now omitted, consistent with the behavior for identified connections. [#6730](https://github.com/XRPLF/rippled/pull/6730)
@@ -51,6 +93,24 @@ This section contains changes targeting a future version.
 - `subscribe`: The `taker` field in the `books` array now returns `actMalformed` instead of `badIssuer` if the value is not a valid account. [#6529](https://github.com/XRPLF/rippled/pull/6529)
 - Fixed a bug in `Forwarded` HTTP header parsing where the extracted IP address could be incorrect when no comma or semicolon delimiter follows the address. This could cause the server to misidentify a client's IP address when operating behind a reverse proxy. [#6529](https://github.com/XRPLF/rippled/pull/6529)
 
+## XRP Ledger server version 3.1.3
+
+[Version 3.1.3](https://github.com/XRPLF/rippled/releases/tag/3.1.3) was released on May 8, 2026.
+
+This release contains bug fixes only and no API changes.
+
+## XRP Ledger server version 3.1.2
+
+[Version 3.1.2](https://github.com/XRPLF/rippled/releases/tag/3.1.2) was released on Mar 12, 2026.
+
+This release contains bug fixes only and no API changes.
+
+## XRP Ledger server version 3.1.1
+
+[Version 3.1.1](https://github.com/XRPLF/rippled/releases/tag/3.1.1) was released on Feb 23, 2026.
+
+This release contains bug fixes only and no API changes.
+
 ## 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.

BUILD.md

@@ -4,34 +4,14 @@
 
 ## Minimum Requirements
 
-See [System Requirements](https://xrpl.org/system-requirements.html).
+For the hardware needed to run a node, see
+[System Requirements](https://xrpl.org/system-requirements.html).
 
-Building xrpld generally requires Git, Python, Conan, CMake, and a C++
-compiler.
-
-- [Python](https://www.python.org/downloads/)
-- [Conan](https://conan.io/downloads.html)
-- [CMake](https://cmake.org/download/)
-
-You can verify that the required tools are installed and runnable with:
-
-```bash
-./bin/check-tools.sh
-```
-
-`xrpld` is written in the C++23 dialect. The [tested compiler versions][cpp23-support] are:
-
-| Compiler    | Version         |
-| ----------- | --------------- |
-| GCC         | 15.2            |
-| Clang       | 22              |
-| Apple Clang | 17              |
-| MSVC        | 19.44[^windows] |
+For the software needed to build xrpld, see the
+[environment setup guide](./docs/build/environment.md).
 
 ## Operating Systems
 
-Please see the [environment setup guide](./docs/build/environment.md) for detailed instructions for all platforms.
-
 ### Linux
 
 The Ubuntu Linux distribution has received the highest level of quality
@@ -42,12 +22,13 @@ Our Linux CI tooling is distro-independent and uses a Nix-based environment, so
 ### macOS
 
 Many `xrpld` engineers use macOS for development.
+The minimum supported version is macOS 15 (Sequoia).
+CI testing is done in macOS 26 (Tahoe), but the build defaults `CMAKE_OSX_DEPLOYMENT_TARGET` to 15.
 
 ### Windows
 
-Windows is used by some engineers for development only.
-
-[^windows]: Windows is not recommended for production use.
+Windows is used by some engineers for development only, and is not recommended
+for production use.
 
 ## Steps
 
@@ -60,49 +41,41 @@ branch.
 git checkout develop
 ```
 
-For a release candidate, choose the relevant release branch, e.g.
-`release/3.2.x`.
+For a release or release candidate, check out its [tag](https://github.com/XRPLF/rippled/releases), e.g.:
 
 ```bash
-git checkout release/3.2.x
+git checkout 3.4.0
 ```
 
-For a stable release, choose one of the [tagged
-releases](https://github.com/XRPLF/rippled/releases).
+See [RELEASING.md](./RELEASING.md) for how branches and releases are organized.
+
+A build reports `0.0.0-dev` with its short commit hash as build metadata, e.g.
+`0.0.0-dev+0123abc`. Only builds of a release, from a tag in CI or a versioned
+Conan reference, report a release version. To use another version, set the
+`FORCE_XRPLD_VERSION` environment variable when running CMake, e.g.
+`FORCE_XRPLD_VERSION=3.4.0`.
 
 ### Set Up Conan
 
-After you have a [C++ development environment](./docs/build/environment.md) ready with Git, Python,
-Conan, CMake, and a C++ compiler, you may need to set up your Conan profile.
-
-These instructions assume a basic familiarity with Conan and CMake. If you are
-unfamiliar with Conan, then please read [this crash course](./docs/build/conan.md) or the official
-[Getting Started][conan-getting-started] walkthrough.
-
-#### Profiles
-
-We recommend that you install our Conan profiles:
+Once your [development environment](./docs/build/environment.md) is ready, set
+Conan up for this repository:
 
 ```bash
-conan config install conan/profiles/ -tf $(conan config home)/profiles/
+./conan/init.sh
 ```
 
-You can check your Conan profile by running:
+That installs our [`global.conf`](./conan/global.conf), our Conan
+[profiles](./conan/profiles), and the `xrplf` remote that hosts some of our
+dependencies. It honours `CONAN_HOME` and never deletes an existing Conan home,
+so it is safe to re-run — it only overwrites the files it manages.
 
-```bash
-conan profile show
-```
+> [!TIP]
+> In the [Nix development shell](./docs/build/nix.md#conan-configuration) this is
+> already done for you: the script runs on entry.
 
-If the default profile is not suitable for your environment, you can create a custom profile and pass it to Conan.
-More information on customizing Conan can be found in the [Advanced Conan configuration](./docs/build/advanced_conan.md).
-
-#### Add xrplf remote
-
-Run the following command to add the `xrplf` remote, which hosts some of our dependencies:
-
-```bash
-conan remote add --index 0 --force xrplf https://conan.ripplex.io
-```
+You can inspect the resulting profile with `conan profile show`. If it is not
+suitable for your environment, create a custom profile and pass it to Conan — see
+[Advanced Conan configuration](./docs/build/advanced_conan.md).
 
 ### Set Up Ccache
 
@@ -245,7 +218,17 @@ cmake --build . --target setup_code_gen  # create venv and install dependencies
 cmake --build . --target code_gen        # regenerate code
 ```
 
-The regenerated files should be committed alongside your changes.
+The same targets are also available as a standalone project, which does not
+need the dependencies to be configured first:
+
+```
+cmake -S cmake/codegen -B build/codegen
+cmake --build build/codegen --target setup_code_gen
+cmake --build build/codegen --target code_gen
+```
+
+The regenerated files should be committed alongside your changes. CI verifies
+that they are up-to-date.
 
 ## Coverage report
 
@@ -257,10 +240,14 @@ which is only enabled when the `coverage` option is set, e.g. with
 Prerequisites for the coverage report:
 
 - [gcovr tool][gcovr] (can be installed e.g. with [pip][python-pip])
-- `gcov` for GCC (installed with the compiler by default) or
-- `llvm-cov` for Clang (installed with the compiler by default)
+- `gcov` for GCC or `llvm-cov` for Clang, usually installed with the compiler
 - `Debug` build type
 
+> [!NOTE]
+> Clang coverage is not available in the [Nix development shell](./docs/build/nix.md#building-xrpld-in-the-nix-shell):
+> its `clang` shells do not ship `llvm-cov`. Use a `gcc` shell instead (`.#gcc`,
+> or `.#gcc-plain` on Linux), which provides a `gcov` matching its compiler.
+
 A coverage report is created when the following steps are completed, in order:
 
 1. `xrpld` binary built with instrumentation data, enabled by the `coverage`
@@ -317,21 +304,66 @@ See [Sanitizers docs](./docs/build/sanitizers.md) for more details.
 
 ## Options
 
-| Option     | Default Value | Description                                                    |
-| ---------- | ------------- | -------------------------------------------------------------- |
-| `assert`   | OFF           | Force enabling assertions.                                     |
-| `coverage` | OFF           | Prepare the coverage report.                                   |
-| `tests`    | OFF           | Build tests.                                                   |
-| `unity`    | OFF           | Configure a unity build.                                       |
-| `xrpld`    | OFF           | Build the xrpld application, and not just the libxrpl library. |
-| `werr`     | OFF           | Treat compilation warnings as errors                           |
-| `wextra`   | OFF           | Enable additional compilation warnings                         |
+| Option           | Default Value | Description                                                                   |
+| ---------------- | ------------- | ----------------------------------------------------------------------------- |
+| `assert`         | OFF           | Force enabling assertions.                                                    |
+| `coverage`       | OFF           | Prepare the coverage report.                                                  |
+| `rust`           | OFF           | Build the Rust crates and the C++ code that depends on them.                  |
+| `tests`          | OFF           | Build tests.                                                                  |
+| `unity`          | OFF           | Configure a unity build.                                                      |
+| `verify_headers` | ON            | Make the `verify-headers` target available to compile each header on its own. |
+| `xrpld`          | OFF           | Build the xrpld application, and not just the libxrpl library.                |
+| `werr`           | OFF           | Treat compilation warnings as errors                                          |
+| `wextra`         | OFF           | Enable additional compilation warnings                                        |
 
 [Unity builds][unity-build] 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.
 
+### Rust crates
+
+The Rust crates in `crates/` are only part of the build when `rust` is ON. With
+`-Drust=OFF` (the default) the `crates` directory is not added to the build, no
+cxxbridge bindings are generated, and the C++ tests that exercise the Rust
+interop are not compiled — so no Rust toolchain is needed. CI builds always pass
+`-Drust=ON`.
+
+With `-Drust=ON` you need one extra dependency: a Rust toolchain (`cargo`,
+`rustc`) matching the channel pinned in
+[`rust-toolchain.toml`](./rust-toolchain.toml), which compiles the crates and
+generates the cxxbridge bindings. It is provided by the
+[Nix development shell](./docs/build/nix.md), so `-Drust=ON` works there without
+any extra setup; otherwise install it as described in
+[Rust](./docs/build/environment.md#rust).
+
+The crates also have their own Rust unit tests. Those are run with `cargo` and
+need only the Rust toolchain, independently of CMake and of the `rust` option
+(CI runs them with `cargo nextest`):
+
+```bash
+cargo test --manifest-path crates/Cargo.toml --workspace
+```
+
+### Verifying headers
+
+The regular build only compiles `.cpp` files, so a header is only ever checked
+through whatever translation unit happens to include it. A header that forgets
+an `#include` is not caught as long as every `.cpp` that uses it includes its
+missing dependency first. The `verify_headers` option (ON by default) adds a
+`verify-headers` target that compiles every header on its own, which fails if a
+header is not self-contained:
+
+```bash
+cmake --build . --target verify-headers
+```
+
+The per-header objects are excluded from the `all` target, so a normal build
+never compiles them; they are built only through `verify-headers`. The generated
+translation units do appear in `compile_commands.json`, so clang-tidy (and
+clangd and IDEs) can lint each header on its own. Pass `-Dverify_headers=OFF` to
+omit them entirely.
+
 ## Troubleshooting
 
 ### Conan
@@ -357,10 +389,14 @@ After any updates or changes to dependencies, you may need to do the following:
 4. [Regenerate lockfile](./docs/build/advanced_conan.md#conan-lockfile).
 5. Re-run [conan install](#build-and-test).
 
+If you are using the Nix development shell, whether prebuilt Conan binaries apply
+depends on your platform — see
+[Prebuilt packages](./docs/build/nix.md#prebuilt-packages).
+
 #### ERROR: Package not resolved
 
 If you're seeing an error like `ERROR: Package 'snappy/1.1.10' not resolved: Unable to find 'snappy/1.1.10#968fef506ff261592ec30c574d4a7809%1756234314.246' in remotes.`,
-please [add `xrplf` remote](#add-xrplf-remote) or re-run `conan export` for [patched recipes](./docs/build/advanced_conan.md#patched-recipes).
+please [set Conan up](#set-up-conan) so the `xrplf` remote is configured, or re-run `conan export` for [patched recipes](./docs/build/advanced_conan.md#patched-recipes).
 
 ### `protobuf/port_def.inc` file not found
 
@@ -380,7 +416,6 @@ For example, if you want to build Debug:
 1. For conan install, pass `--settings build_type=Debug`
 2. For cmake, pass `-DCMAKE_BUILD_TYPE=Debug`
 
-[cpp23-support]: https://en.cppreference.com/w/cpp/compiler_support/23
 [conan-getting-started]: https://docs.conan.io/en/latest/getting_started.html
 [unity-build]: https://en.wikipedia.org/wiki/Unity_build
 [gcovr]: https://gcovr.com/en/stable/getting-started.html

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

CMakeLists.txt

@@ -13,6 +13,23 @@ if(DEFINED CMAKE_MODULE_PATH)
 endif()
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
 
+# Must be set before project() because project() consumes it when configuring the compiler and SDK.
+# A user-provided -DCMAKE_OSX_DEPLOYMENT_TARGET still takes precedence.
+#
+# CMAKE_SYSTEM_NAME can't be used before project(), so CMAKE_HOST_SYSTEM_NAME is used instead.
+#
+# When CMAKE_OSX_DEPLOYMENT_TARGET is bumped to >=26.0, FastFloat dependency won't be needed anymore
+if(
+    CMAKE_HOST_SYSTEM_NAME STREQUAL "Darwin"
+    AND NOT DEFINED CMAKE_OSX_DEPLOYMENT_TARGET
+)
+    set(CMAKE_OSX_DEPLOYMENT_TARGET
+        "15.0"
+        CACHE STRING
+        "Minimum macOS deployment version"
+    )
+endif()
+
 project(xrpl)
 set(CMAKE_CXX_EXTENSIONS OFF)
 set(CMAKE_CXX_STANDARD 23)
@@ -57,8 +74,9 @@ if(target)
     )
 endif()
 
+include(PatchNixBinary)
+
 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)
@@ -85,21 +103,26 @@ include(deps/Boost)
 add_subdirectory(external/antithesis-sdk)
 find_package(date REQUIRED)
 find_package(ed25519 REQUIRED)
+find_package(FastFloat REQUIRED)
 find_package(gRPC REQUIRED)
 find_package(LibArchive REQUIRED)
 find_package(lz4 REQUIRED)
+find_package(mpt-crypto REQUIRED)
 find_package(nudb REQUIRED)
 find_package(OpenSSL REQUIRED)
 find_package(secp256k1 REQUIRED)
 find_package(SOCI REQUIRED)
 find_package(SQLite3 REQUIRED)
 find_package(xxHash REQUIRED)
+find_package(xrpl-rpc-spec REQUIRED)
 
 target_link_libraries(
     xrpl_libs
     INTERFACE
         ed25519::ed25519
+        FastFloat::fast_float
         lz4::lz4
+        mpt-crypto::mpt-crypto
         OpenSSL::Crypto
         OpenSSL::SSL
         secp256k1::secp256k1
@@ -127,17 +150,34 @@ else()
 endif()
 target_link_libraries(xrpl_libs INTERFACE ${nudb})
 
+if(benchmark)
+    find_package(benchmark REQUIRED)
+endif()
+
 if(coverage)
     include(XrplCov)
 endif()
 
+add_custom_target(tidy_prerequisites)
+
+if(rust)
+    add_subdirectory(crates)
+endif()
 include(XrplCore)
+
 include(XrplProtocolAutogen)
 include(XrplInstall)
-include(XrplPackaging)
 include(XrplValidatorKeys)
+# Must come after XrplValidatorKeys: the 'package' target depends on the
+# validator-keys target existing.
+include(XrplPackaging)
 
 if(tests)
     include(CTest)
     add_subdirectory(src/tests/libxrpl)
+    add_subdirectory(src/tests/xrpld)
+endif()
+
+if(benchmark)
+    add_subdirectory(src/benchmarks/libxrpl)
 endif()

CODEOWNERS

@@ -0,0 +1,4 @@
+# By default, anyone can review changes.
+
+# The CI tooling team should review changes to the CI configuration.
+/.github/ @XRPLF/ci-tooling

CONTRIBUTING.md

@@ -14,9 +14,13 @@ The following branches exist in the main project repository:
 
 - `develop`: The latest set of unreleased features, and the most common
   starting point for contributions.
-- `release/*` (e.g. `release/3.2.x`): Release branches, one per release line,
-  holding the latest release candidate, or stable release for that line.
-  Stable releases are published as [tagged releases](https://github.com/XRPLF/rippled/releases).
+- `staging/*` (e.g. `staging/3.4.x`): Staging branches, one per release line,
+  where fixes for that line are developed.
+- `release/*` (e.g. `release/3.4.x`): Release branches, one per release line,
+  holding the latest public release candidate or release for that line.
+  Releases are published as [tagged releases](https://github.com/XRPLF/rippled/releases).
+
+See [RELEASING.md](./RELEASING.md) for how these branches are used.
 
 The tip of each branch must be signed. In order for GitHub to sign a
 squashed commit that it builds from your pull request, GitHub must know
@@ -59,6 +63,17 @@ to an existing XLS. Neither change will be released (in an amendment's
 case, marked as `Supported::yes`) until the corresponding XLS's status
 is `Final`.
 
+## AI coding agents
+
+[`AGENTS.md`](./AGENTS.md) (and its `CLAUDE.md` symlink, for Claude Code) holds shared, checked-in guidance for AI coding agents working in this repository — build/test/lint commands and architecture notes. Additional `AGENTS.md` files may exist in subdirectories to give agents context specific to that part of the codebase; whenever you add one, also add a `CLAUDE.md` symlink pointing to it (`ln -s AGENTS.md CLAUDE.md`) so Claude Code picks it up too.
+
+If you want to give an agent personal instructions that shouldn't be shared with other contributors (e.g. your own workflow preferences), those are gitignored, not checked in:
+
+- `CLAUDE.local.md` — read by Claude Code alongside `CLAUDE.md`.
+- `AGENTS.override.md` — read by AGENTS.md-compatible tools that support a personal override file layered on top of `AGENTS.md`.
+
+Likewise, `.claude/settings.local.json` is for personal, untracked Claude Code settings, while `.claude/settings.json` is shared.
+
 ## Before making a pull request
 
 (Or marking a draft pull request as ready.)
@@ -82,9 +97,12 @@ If you create new source files, they must be organized as follows:
   under `include/xrpl`, and source (`.cpp`) files must go under
   `src/libxrpl`.
 - All other non-test files must go under `src/xrpld`.
-- All test source files must go under `src/test`.
+- New test source files should use `gtest` and go under `src/tests`, unless that isn't possible, in which case they should use our legacy test framework and go under `src/test`.
+- All benchmark source files must go under `src/benchmarks`.
 
-The source must be formatted according to the style guide below.
+The source must be formatted according to the style guide below. The easiest
+way to satisfy this is to install the [`pre-commit`](#pre-commit-hooks) hooks,
+which format and lint your changes automatically on every commit.
 
 Header includes must be [levelized](.github/scripts/levelization).
 
@@ -131,8 +149,8 @@ tl;dr
 
 In general, pull requests use `develop` as the base branch.
 
-The exceptions are fixes, improvements, and hotfixes for an existing release,
-which use that release's branch (e.g. `release/3.2.x`) as the base.
+The exceptions are fixes for an existing release line,
+which use that line's staging branch (e.g. `staging/3.4.x`) as the base.
 
 If your changes are not quite ready, but you want to make it easily available
 for preliminary examination or review, you can create a "Draft" pull request.
@@ -212,13 +230,63 @@ This is a non-exhaustive list of recommended style guidelines. These are
 not always strictly enforced and serve as a way to keep the codebase
 coherent rather than a set of _thou shalt not_ commandments.
 
+## Pre-commit hooks
+
+We use the [`pre-commit`](https://pre-commit.com/) framework to run the
+formatting and linting tools that keep the codebase consistent. `pre-commit`
+runs each tool configured in
+[`.pre-commit-config.yaml`](./.pre-commit-config.yaml) in its own isolated
+environment, so you don't need to install most of the individual tools
+yourself. The version of each hook sourced from an external repository
+(`clang-format`, `gersemi`, etc.) is pinned in that file, so running the hooks
+locally uses exactly the same versions as CI. A few `local` hooks — most notably
+`clang-tidy` and `cargo fmt` — run tools from your own environment; see
+[Installing clang-tidy](#installing-clang-tidy) and
+[Rust](./docs/build/environment.md#rust) for how to get those.
+
+To get started, install `pre-commit` and enable the git hook scripts:
+
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+Once installed, the hooks run automatically on your staged files every time you
+`git commit`. You can also run them on demand:
+
+```bash
+# Run all hooks against only the staged files
+pre-commit run
+
+# Run all hooks against every file in the repository
+pre-commit run --all-files
+
+# Run a single hook (e.g. clang-format) against all files
+pre-commit run clang-format --all-files
+```
+
+The hooks configured in this repository include, among others:
+
+- `clang-format` — C++/proto formatting (see [Formatting](#formatting))
+- `clang-tidy` — C++ static analysis (see [Clang-tidy](#clang-tidy)); opt in with `TIDY=1`
+- `fix-include-style`, `fix-pragma-once`, `check-doxygen-style` — C++ hygiene
+- `gersemi` — CMake formatting
+- `cargo fmt` — Rust formatting for the crates in `crates/`
+- `prettier`, `black`, `shfmt` — formatting for JavaScript/JSON/Markdown, Python, and shell
+- `cspell` — spell checking
+
+The same hooks run in CI on every pull request, so running them locally before
+you push helps you avoid CI failures.
+
 ## Formatting
 
-All code must conform to `clang-format` version 22,
-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
-this:
+All code must conform to `clang-format`, according to the settings in
+[`.clang-format`](./.clang-format), unless the result would be unreasonably
+difficult to read or maintain. The `clang-format` version is pinned in
+[`.pre-commit-config.yaml`](./.pre-commit-config.yaml), so the
+[`pre-commit`](#pre-commit-hooks) hook always formats with the same version as
+CI. To demarcate lines that should be left as-is, surround them with comments
+like this:
 
 ```
 // clang-format off
@@ -226,9 +294,21 @@ this:
 // clang-format on
 ```
 
-You can format individual files in place by running `clang-format -i <file>...`
+The easiest way to format your changes is to let the `pre-commit` hook run
+automatically on commit, or to run it manually:
+
+```bash
+pre-commit run clang-format --all-files
+```
+
+You can also format individual files in place by running `clang-format -i <file>...`
 from any directory within this project.
 
+> [!NOTE]
+> This uses whatever `clang-format` version is installed locally, which may
+> differ from the pinned version used by `pre-commit` and CI, so the results
+> can vary.
+
 There is a Continuous Integration job that runs clang-format on pull requests. If the code doesn't comply, a patch file that corrects auto-fixable formatting issues is generated.
 
 To download the patch file:
@@ -239,13 +319,6 @@ To download the patch file:
 4. Download the zip file and extract it to your local git repository. Run `git apply [patch-file-name]`.
 5. Commit and push.
 
-You can install a pre-commit hook to automatically run `clang-format` before every commit:
-
-```
-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).
@@ -263,11 +336,15 @@ See the [environment setup guide](./docs/build/environment.md#clang-tidy) for ho
 
 ### 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.
+Before running clang-tidy, you must generate the files it depends on (protobuf headers, and, when the project is configured with `-Drust=ON`, the cxxbridge headers from the Rust crates). Configure the project as described in [`BUILD.md`](./BUILD.md), then build the `tidy_prerequisites` target, which generates all of them:
+
+```bash
+cmake --build build --target tidy_prerequisites
+```
 
 #### Via pre-commit (recommended)
 
-If you have already installed the pre-commit hooks (see above), you can run clang-tidy on your staged files using:
+If you have already installed the [`pre-commit`](#pre-commit-hooks) hooks, you can run clang-tidy on your staged files using:
 
 ```
 TIDY=1 pre-commit run clang-tidy
@@ -292,12 +369,54 @@ run-clang-tidy -p build -allow-no-checks src 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:
+If you wish to automatically fix whatever clang-tidy finds _and_ is capable of fixing, add `-fix -format` to the above command:
 
 ```
-run-clang-tidy -p build -quiet -fix -allow-no-checks src tests
+run-clang-tidy -p build -quiet -fix -format -allow-no-checks src tests
 ```
 
+`-format` reformats the fixed code with [`.clang-format`](./.clang-format); without it the fixes are inserted in LLVM style and the `clang-format` hook rewrites them afterwards.
+
+## Telemetry span attribute naming
+
+OpenTelemetry span attribute keys follow these rules so they stay consistent
+across the code, the OTel collector, Tempo, Grafana dashboards, and docs. The
+constants in the `*SpanNames.h` headers are the single source of truth; every
+other layer must match them. A CI check enforces this end to end.
+
+1. Per-span unique attribute: bare field name — allowed when the field is
+   recorded by a single span/workflow, so the span name already supplies the
+   domain (e.g. `command`, `local`, `version` on `rpc.command` / `tx.process`).
+2. Shared attribute (same concept on more than one span): ONE key, reused
+   verbatim on every span that records it — the span name tells the occurrences
+   apart, so no per-emitter prefix is added. Pick the name by the field's
+   meaning: a property of a domain object keeps that object's bare field name
+   (`ledger_hash`, `ledger_seq`, `tx_hash`, `peer_id`, `full_validation`); a
+   field already qualified by a sub-kind keeps that qualifier on every emitter
+   (`proposal_trusted` on both `consensus.proposal.receive` and
+   `peer.proposal.receive`; `validation_trusted` likewise). Define it once in
+   the base `SpanNames.h` `namespace attr` block and re-export (`using`) it from
+   each domain header, so all emitters share the exact string.
+3. Collision qualifier: `<domain>_<field>` — only when a bare name would collide
+   with a DIFFERENT concept in the shared spanmetrics label space, or with the
+   OTel-reserved `status` key (e.g. `rpc_status`, `grpc_status`,
+   `consensus_phase`, `consensus_round`). This disambiguates distinct concepts
+   that share a word; it is NOT used to tag the same concept with the workflow
+   that emitted it — that is rule 2 (one shared name).
+4. Resource attribute: dotted `xrpl.<subsystem>.<field>` — reserved ONLY for
+   process/network identity set once at startup (`xrpl.network.id`,
+   `xrpl.network.type`). Never use the dotted `xrpl.` form for span attributes.
+5. Span names use `<subsystem>[.<component>]` (dotted). Only attribute _keys_
+   follow rules 1–4.
+
+Standard OpenTelemetry semantic-convention keys keep their canonical dotted
+form (e.g. `service.*` resource attributes, `http.*` span attributes); the
+"no dotted form" rule above applies to xrpl-custom keys, not to OTel-standard
+conventions.
+
+Always reference the `*SpanNames.h` constants — never pass string literals as
+attribute keys or values to `setAttribute`/`addEvent`.
+
 ## Contracts and instrumentation
 
 We are using [Antithesis](https://antithesis.com/) for continuous fuzzing,
@@ -404,8 +523,12 @@ exists, then no other unit test will be executed, apart from `TestSuiteName`.
     elsewhere in the codebase.
 12. Use clear and self-explanatory names for functions, variables,
     structs and classes.
-13. Use TitleCase for classes, structs and filenames, camelCase for
-    function and variable names, lower case for namespaces and folders.
+13. Use TitleCase for classes, structs, type aliases and filenames,
+    camelCase for function and variable names, lower case for namespaces and
+    folders. The exception is a type alias that generic code looks up by name
+    (`value_type`, `iterator`, `result_type`, and the rest of the standard
+    container, hash and clock members), which keeps its snake_case spelling;
+    `.clang-tidy` lists the names that are allowed.
 14. Provide as many comments as you feel that a competent programmer
     would need to understand what your code does.
 
@@ -512,15 +635,16 @@ the suggested commit message, or modify it as needed.
 
 #### Slightly more complicated pull requests
 
-Some pull requests need to be pushed to `develop` as more than one
-commit. A PR author may _request_ to merge as separate commits. They
+Some pull requests need to be pushed to their base branch (usually `develop`)
+as more than one commit.
+A PR author may _request_ to merge as separate commits. They
 must _justify_ why separate commits are needed, and _specify_ how they
 would like the commits to be merged. If you disagree with the author,
 discuss it with them directly.
 
 If the process is reasonable, follow it. The simplest option is to do a
-fast forward only merge (`--ff-only`) on the command line and push to
-`develop`.
+fast forward only merge (`--ff-only`) on the command line
+and push to the base branch.
 
 Some examples of when separate commits are worthwhile are:
 
@@ -533,9 +657,10 @@ Some examples of when separate commits are worthwhile are:
 
 Either way, check that:
 
-- The commits are based on the current tip of `develop`.
-- The commits are clean: No merge commits (except when reverse
-  merging), no "[FOLD]" or "fixup!" messages.
+- The commits are based on the current tip of the base branch.
+- The commits are clean:
+  No merge commits (except when merging a release, see [RELEASING.md](./RELEASING.md)),
+  no "[FOLD]" or "fixup!" messages.
 - All commits are signed. If the commits are not signed by the author, use
   `git commit --amend -S` to sign them yourself.
 - At least one (but preferably all) of the commits has the PR number
@@ -547,578 +672,8 @@ use them!**
 
 ### Releases
 
-All releases, including release candidates and betas, are handled
-differently from typical PRs. Most importantly, never use
-the Github UI to merge a release.
-
-Xrpld uses a linear workflow model that can be summarized as:
-
-1. In between releases, developers work against the `develop` branch.
-2. Periodically, a maintainer will build and tag a beta version from
-   `develop`, which is pushed to `release`.
-   - Betas are usually released every two to three weeks, though that
-     schedule can vary depending on progress, availability, and other
-     factors.
-3. When the changes in `develop` are considered stable and mature enough
-   to be ready to release, a release candidate (RC) is built and tagged
-   from `develop`, and merged to `release`.
-   - Further development for that release (primarily fixes) then
-     continues against `release`, while other development continues on
-     `develop`. Effectively, `release` is forked from `develop`. Changes
-     to `release` must be reverse merged to `develop`.
-4. When the candidate has passed testing and is ready for release, the
-   final release is merged to `master`.
-5. If any issues are found post-release, a hotfix / point release may be
-   created, which is merged to `master`, and then reverse merged to
-   `develop`.
-
-#### Betas, and the first release candidate
-
-##### Preparing the `develop` branch
-
-1. Optimally, the `develop` branch will be ready to go, with all
-   relevant PRs already merged.
-2. If there are any PRs pending, merge them **BEFORE** preparing the beta.
-   1. If only one or two PRs need to be merged, merge those PRs [as
-      normal](#when-and-how-to-merge-pull-requests), updating the second
-      one, and waiting for CI to finish in between.
-   2. If there are several pending PRs, do not use the Github UI,
-      because the delays waiting for CI in between each merge will be
-      unnecessarily onerous. (Incidentally, this process can also be
-      used to merge if the Github UI has issues.) Merge each PR branch
-      directly to a `release-next` on your local machine and create a single
-      PR, then push your branch to `develop`.
-      1. Squash the changes from each PR, one commit each (unless more
-         are needed), being sure to sign each commit and update the
-         commit message to include the PR number. You may be able to use
-         a fast-forward merge for the first PR.
-      2. Push your branch.
-      3. Continue to [Making the release](#making-the-release) to update
-         the version number, etc.
-
-      The workflow may look something like:
-
-```
-git fetch --multiple upstreams user1 user2 user3 [...]
-git checkout -B release-next --no-track upstream/develop
-
-# Only do an ff-only merge if pr-branch1 is either already
-# squashed, or needs to be merged with separate commits,
-# and has no merge commits.
-# Use -S on the ff-only merge if pr-branch1 isn't signed.
-git merge [-S] --ff-only user1/pr-branch1
-
-git merge --squash user2/pr-branch2
-git commit -S # Use the commit message provided on the PR
-
-git merge --squash user3/pr-branch3
-git commit -S # Use the commit message provided on the PR
-
-[...]
-
-# Make sure the commits look right
-git log --show-signature "upstream/develop..HEAD"
-
-git push --set-upstream origin
-
-# Continue to "Making the release" to update the version number, so
-# everything can be done in one PR.
-```
-
-You can also use the [squash-branches] script.
-
-You may also need to manually close the open PRs after the changes are
-merged to `develop`. Be sure to include the commit ID.
-
-##### Making the release
-
-This includes, betas, and the first release candidate (RC).
-
-1. If you didn't create one [preparing the `develop`
-   branch](#preparing-the-develop-branch), Ensure there is no old
-   `release-next` branch hanging around. Then make a `release-next`
-   branch that only changes the version number. e.g.
-
-```
-git fetch upstreams
-
-git checkout --no-track -B release-next upstream/develop
-
-v="A.B.C-bD"
-build=$( find -name BuildInfo.cpp )
-sed 's/\(^.*versionString =\).*$/\1 "'${v}'"/' ${build} > version.cpp && mv -vi version.cpp ${build}
-
-git diff
-
-git add ${build}
-
-git commit -S -m "Set version to ${v}"
-
-# You could use your "origin" repo, but some CI tests work better on upstream.
-git push upstream-push
-git fetch upstreams
-git branch --set-upstream-to=upstream/release-next
-```
-
-You can also use the [update-version] script. 2. Create a Pull Request for `release-next` with **`develop`** as
-the base branch.
-
-1.  Use the title "[TRIVIAL] Set version to X.X.X-bX".
-2.  Instead of the default description template, use the following:
-
-```
-## High Level Overview of Change
-
-This PR only changes the version number. It will be merged as
-soon as Github CI actions successfully complete.
-```
-
-3. Wait for CI to successfully complete, and get someone to approve
-   the PR. (It is safe to ignore known CI issues.)
-4. Push the updated `develop` branch using your `release-next`
-   branch. **Do not use the Github UI. It's important to preserve
-   commit IDs.**
-
-```
-git push upstream-push release-next:develop
-```
-
-5. In the unlikely event that the push fails because someone has merged
-   something else in the meantime, rebase your branch onto the updated
-   `develop` branch, push again, and go back to step 3.
-6. Ensure that your PR against `develop` is closed. Github should do it
-   automatically.
-7. Once this is done, forward progress on `develop` can continue
-   (other PRs may be merged).
-8. Now create a Pull Request for `release-next` with **`release`** as
-   the base branch. Instead of the default template, reuse and update
-   the message from the previous release. Include the following verbiage
-   somewhere in the description:
-
-```
-The base branch is `release`. [All releases (including
-betas)](https://github.com/XRPLF/rippled/blob/develop/CONTRIBUTING.md#before-you-start)
-go in `release`. This PR branch will be pushed directly to `release` (not
-squashed or rebased, and not using the GitHub UI).
-```
-
-7. Sign-offs for the three platforms (Linux, Mac, Windows) usually occur
-   offline, but at least one approval will be needed on the PR.
-   - If issues are discovered during testing, simply abandon the
-     release. It's easy to start a new release, it should be easy to
-     abandon one. **DO NOT REUSE THE VERSION NUMBER.** e.g. If you
-     abandon 2.4.0-b1, the next attempt will be 2.4.0-b2.
-8. Once everything is ready to go, push to `release`.
-
-```
-git fetch upstreams
-
-# Just to be safe, do a dry run first:
-git push --dry-run upstream-push release-next:release
-
-# If everything looks right, push the branch
-git push upstream-push release-next:release
-
-# Check that all of the branches are updated
-git fetch upstreams
-git log -1 --oneline
-# The output should look like:
-# 0123456789 (HEAD -> upstream/release-next, upstream/release,
-#            upstream/develop) Set version to 2.4.0-b1
-# Note that upstream/develop may not be on this commit, but
-# upstream/release must be.
-# Other branches, including some from upstream-push, may also be
-# present.
-```
-
-9. Tag the release, too.
-
-```
-git tag <version number>
-git push upstream-push <version number>
-```
-
-10. Delete the `release-next` branch on the repo. Use the Github UI or:
-
-```
-git push --delete upstream-push release-next
-```
-
-11. Finally [create a new release on
-    Github](https://github.com/XRPLF/rippled/releases).
-
-#### Release candidates after the first
-
-Once the first release candidate is [merged into
-release](#making-the-release), then `release` and `develop` _are allowed
-to diverge_.
-
-If a bug or issue is discovered in a version that has a release
-candidate being tested, any fix and new version will need to be applied
-against `release`, then reverse-merged to `develop`. This helps keep git
-history as linear as possible.
-
-A `release-next` branch will be created from `release`, and any further
-work for that release must be based on `release-next`. Specifically,
-PRs must use `release-next` as the base, and those PRs will be merged
-directly to `release-next` when approved. Changes should be restricted
-to bug fixes, but other changes may be necessary from time to time.
-
-1. Open any PRs for the pending release using `release-next` as the base,
-   so they can be merged directly in to it. Unlike `develop`, though,
-   `release-next` can be thrown away and recreated if necessary.
-2. Once a new release candidate is ready, create a version commit as in
-   step 1 [above](#making-the-release) on `release-next`. You can use
-   the [update-version] script for this, too.
-3. Jump to step 8 ("Now create a Pull Request for `release-next` with
-   **`release`** as the base") from the process
-   [above](#making-the-release) to merge `release-next` into `release`.
-
-##### Follow up: reverse merge
-
-Once the RC is merged and tagged, it needs to be reverse merged into
-`develop` as soon as possible.
-
-1. Create a branch, based on `upstream/develop`.
-   The branch name is not important, but could include "mergeNNNrcN".
-   E.g. For release A.B.C-rcD, use `mergeABCrcD`.
-
-```
-git fetch upstreams
-
-git checkout --no-track -b mergeABCrcD upstream/develop
-```
-
-2. Merge `release` into your branch.
-
-```
-# I like the "--edit --log --verbose" parameters, but they are
-# not required.
-git merge upstream/release
-```
-
-3. `BuildInfo.cpp` will have a conflict with the version number.
-   Resolve it with the version from `develop` - the higher version.
-4. Push your branch to your repo (or `upstream` if you have permission),
-   and open a normal PR against `develop`. The "High level overview" can
-   simply indicate that this is a merge of the RC. The "Context" should
-   summarize the changes from the RC. Include the following text
-   prominently:
-
-```
-This PR must be merged manually using a push. Do not use the Github UI.
-```
-
-5. Depending on the complexity of the changes, and/or merge conflicts,
-   the PR may need a thorough review, or just a sign-off that the
-   merge was done correctly.
-6. If `develop` is updated before this PR is merged, do not merge
-   `develop` back into your branch. Instead rebase preserving merges,
-   or do the merge again. (See also the `rerere` git config setting.)
-
-```
-git rebase --rebase-merges upstream/develop
-# OR
-git reset --hard upstream/develop
-git merge upstream/release
-```
-
-7. When the PR is ready, push it to `develop`.
-
-```
-git fetch upstreams
-
-# Make sure the commits look right
-git log --show-signature "upstream/develop^..HEAD"
-
-git push upstream-push mergeABCrcD:develop
-
-git fetch upstreams
-```
-
-Development on `develop` can proceed as normal.
-
-#### Final releases
-
-A final release is any release that is not a beta or RC, such as 2.2.0.
-
-Only code that has already been tested and vetted across all three
-platforms should be included in a final release. Most of the time, that
-means that the commit immediately preceding the commit setting the
-version number will be an RC. Occasionally, there may be last-minute bug
-fixes included as well. If so, those bug fixes must have been tested
-internally as if they were RCs (at minimum, ensuring unit tests pass,
-and the app starts, syncs, and stops cleanly across all three
-platforms.)
-
-_If in doubt, make an RC first._
-
-The process for building a final release is very similar to [the process
-for building a beta](#making-the-release), except the code will be
-moving from `release` to `master` instead of from `develop` to
-`release`, and both branches will be pushed at the same time.
-
-1. Ensure there is no old `master-next` branch hanging around.
-   Then make a `master-next` branch that only changes the version
-   number. As above, or using the
-   [update-version] script.
-2. Create a Pull Request for `master-next` with **`master`** as
-   the base branch. Instead of the default template, reuse and update
-   the message from the previous final release. Include the following verbiage
-   somewhere in the description:
-
-```
-The base branch is `master`. This PR branch will be pushed directly to
-`release` and `master` (not squashed or rebased, and not using the
-GitHub UI).
-```
-
-7. Sign-offs for the three platforms (Linux, Mac, Windows) usually occur
-   offline, but at least one approval will be needed on the PR.
-   - If issues are discovered during testing, close the PR, delete
-     `master-next`, and move development back to `release`, [issuing
-     more RCs as necessary](#release-candidates-after-the-first)
-8. Once everything is ready to go, push to `release` and `master`.
-
-```
-git fetch upstreams
-
-# Just to be safe, do dry runs first:
-git push --dry-run upstream-push master-next:release
-git push --dry-run upstream-push master-next:master
-
-# If everything looks right, push the branch
-git push upstream-push master-next:release
-git push upstream-push master-next:master
-
-# Check that all of the branches are updated
-git fetch upstreams
-git log -1 --oneline
-# The output should look like:
-# 0123456789 (HEAD -> upstream/master-next, upstream/master,
-#            upstream/release) Set version to A.B.0
-# Note that both upstream/release and upstream/master must be on this
-# commit.
-# Other branches, including some from upstream-push, may also be
-# present.
-```
-
-9. Tag the release, too.
-
-```
-git tag <version number>
-git push upstream-push <version number>
-```
-
-10. Delete the `master-next` branch on the repo. Use the Github UI or:
-
-```
-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. 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.
-
-On occasion, a bug or issue is discovered in a version that already
-had a final release. Most of the time, development will have started
-on the next version, and will usually have changes in `develop`
-and often in `release`.
-
-Because git history is kept as linear as possible, any fix and new
-version will need to be applied against `master`.
-
-The process for building a hotfix release is very similar to [the
-process for building release candidates after the
-first](#release-candidates-after-the-first) and [for building a final
-release](#final-releases), except the changes will be done against
-`master` instead of `release`.
-
-If there is only a single issue for the hotfix, the work can be done in
-any branch. When it's ready to merge, jump to step 3 using your branch
-instead of `master-next`.
-
-1. Create a `master-next` branch from `master`.
-
-```
-git checkout --no-track -b master-next upstream/master
-git push upstream-push
-git fetch upstreams
-```
-
-2. Open any PRs for the pending hotfix using `master-next` as the base,
-   so they can be merged directly in to it. Unlike `develop`, though,
-   `master-next` can be thrown away and recreated if necessary.
-3. Once the hotfix is ready, create a version commit using the same
-   steps as above, or use the
-   [update-version] script.
-4. Create a Pull Request for `master-next` with **`master`** as
-   the base branch. Instead of the default template, reuse and update
-   the message from the previous final release. Include the following verbiage
-   somewhere in the description:
-
-```
-The base branch is `master`. This PR branch will be pushed directly to
-`master` (not squashed or rebased, and not using the GitHub UI).
-```
-
-7. Sign-offs for the three platforms (Linux, Mac, Windows) usually occur
-   offline, but at least one approval will be needed on the PR.
-   - If issues are discovered during testing, update `master-next` as
-     needed, but ensure that the changes are properly squashed, and the
-     version setting commit remains last
-8. Once everything is ready to go, push to `master` **only**.
-
-```
-git fetch upstreams
-
-# Just to be safe, do a dry run first:
-git push --dry-run upstream-push master-next:master
-
-# If everything looks right, push the branch
-git push upstream-push master-next:master
-
-# Check that all of the branches are updated
-git fetch upstreams
-git log -1 --oneline
-# The output should look like:
-# 0123456789 (HEAD -> upstream/master-next, upstream/master) Set version
-#            to 2.4.1
-# Note that upstream/master must be on this commit. upstream/release and
-# upstream/develop should not.
-# Other branches, including some from upstream-push, may also be
-# present.
-```
-
-9. Tag the release, too.
-
-```
-git tag <version number>
-git push upstream-push <version number>
-```
-
-9. Delete the `master-next` branch on the repo.
-
-```
-git push --delete upstream-push master-next
-```
-
-10. [Create a new release on
-    Github](https://github.com/XRPLF/rippled/releases). Be sure that
-    "Set as the latest release" is checked.
-
-Once the hotfix is released, it needs to be reverse merged into
-`develop` as soon as possible. It may also need to be merged into
-`release` if a release candidate is under development.
-
-1. Create a branch in your own repo, based on `upstream/develop`.
-   The branch name is not important, but could include "mergeNNN".
-   E.g. For release 2.2.3, use `merge223`.
-
-```
-git fetch upstreams
-
-git checkout --no-track -b merge223 upstream/develop
-```
-
-2. Merge master into your branch.
-
-```
-# I like the "--edit --log --verbose" parameters, but they are
-# not required.
-git merge upstream/master
-```
-
-3. `BuildInfo.cpp` will have a conflict with the version number.
-   Resolve it with the version from `develop` - the higher version.
-4. Push your branch to your repo, and open a normal PR against
-   `develop`. The "High level overview" can simply indicate that this
-   is a merge of the hotfix version. The "Context" should summarize
-   the changes from the hotfix. Include the following text
-   prominently:
-
-```
-This PR must be merged manually using a --ff-only merge. Do not use the Github UI.
-```
-
-5. Depending on the complexity of the hotfix, and/or merge conflicts,
-   the PR may need a thorough review, or just a sign-off that the
-   merge was done correctly.
-6. If `develop` is updated before this PR is merged, do not merge
-   `develop` back into your branch. Instead rebase preserving merges,
-   or do the merge again. (See also the `rerere` git config setting.)
-
-```
-git rebase --rebase-merges upstream/develop
-# OR
-git reset --hard upstream/develop
-git merge upstream/master
-```
-
-7. When the PR is ready, push it to `develop`.
-
-```
-git fetch upstreams
-
-# Make sure the commits look right
-git log --show-signature "upstream/develop..HEAD"
-
-git push upstream-push HEAD:develop
-```
-
-Development on `develop` can proceed as normal. It is recommended to
-create a beta (or RC) immediately to ensure that everything worked as
-expected.
-
-##### An even rarer scenario: A hotfix on an old release
-
-Historically, once a final release is tagged and packages are released,
-versions older than the latest final release are no longer supported.
-However, there is a possibility that a very high severity bug may occur
-in a non-amendment blocked version that is still being run by
-a significant fraction of users, which would necessitate a hotfix / point
-release to that version as well as any later versions.
-
-This scenario would follow the same basic procedure as above,
-except that _none_ of `develop`, `release`, or `master`
-would be touched during the release process.
-
-In this example, consider if version 2.1.1 needed to be patched.
-
-1. Create two branches in the main (`upstream`) repo.
-
-```
-git fetch upstreams
-
-# Create a base branch off the tag
-git checkout --no-track -b master-2.1.2 2.1.1
-git push upstream-push
-
-# Create a working branch
-git checkout --no-track -b master212-next master-2.1.2
-git push upstream-push
-
-git fetch upstreams
-```
-
-2. Work continues as above, except using `master-2.1.2`as
-   the base branch for any merging, packaging, etc.
-3. After the release is tagged and packages are built, you could
-   potentially delete both branches, e.g. `master-2.1.2` and
-   `master212-next`. However, it may be useful to keep `master-2.1.2`
-   around indefinitely for reference.
-4. Assuming that a hotfix is also released for the latest
-   version in parallel with this one, or if the issue is
-   already fixed in the latest version, do no do any
-   reverse merges. However, if it is not, it probably makes
-   sense to reverse merge `master-2.1.2` into `master`,
-   release a hotfix for _that_ version, then reverse merge
-   from `master` to `develop`. (Please don't do this unless absolutely
-   necessary.)
+Releases, release branches, and merging releases back into `develop`
+are described in [RELEASING.md](./RELEASING.md).
 
 [contrib]: https://docs.github.com/en/get-started/quickstart/contributing-to-projects
 [squash]: https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/incorporating-changes-from-a-pull-request/about-pull-request-merges#squash-and-merge-your-commits
@@ -1126,5 +681,3 @@ git fetch upstreams
 [xrpld]: https://github.com/XRPLF/rippled
 [signing]: https://docs.github.com/en/authentication/managing-commit-signature-verification/about-commit-signature-verification
 [setup-upstreams]: ./bin/git/setup-upstreams.sh
-[squash-branches]: ./bin/git/squash-branches.sh
-[update-version]: ./bin/git/update-version.sh

OpenTelemetryPlan/00-tracing-fundamentals.md

@@ -0,0 +1,570 @@
+# 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
+(Trace 1)`"] -.-|link| Y["`Span Y
+(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::previousLedger_ → 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
+(tx traces)`"| T3
+    C3 --> V1
+    F1 -.-|"`span link
+(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 xrpld, 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 (xrpld P2P messages)
+
+xrpld P2P messages such as `TMTransaction` carry the trace context in two added byte fields alongside the existing payload: `trace_parent` holds the W3C traceparent (`trace_id`, `span_id`, and `trace_flags`), and `trace_state` holds the optional W3C tracestate. Together they propagate the trace across the P2P boundary so a receiving node can attach its spans to the sender's span.
+
+---
+
+## Sampling
+
+Not every trace needs to be recorded. **Sampling** reduces overhead:
+
+### Head Sampling (at trace start)
+
+```
+Request arrives → Random N% chance → Record or skip entire trace
+```
+
+- ✅ Low overhead
+- ❌ May miss interesting traces
+
+> **xrpld note**: xrpld intentionally fixes head sampling at 100% (sample
+> everything) and does not expose a configurable ratio. A per-node ratio
+> would let different nodes make divergent keep/drop decisions for the same
+> distributed trace, producing broken/partial traces. A span with a remote
+> parent is decided by the same trace-id ratio sampler, not by the peer's
+> sampled flag, so nodes agree on every trace. Volume reduction is
+> delegated to collector-side tail sampling.
+
+### 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 xrpld
+
+| 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 xrpld Architecture Overview
+
+> **WS** = WebSocket | **UNL** = Unique Node List | **TxQ** = Transaction Queue | **StatsD** = Statistics Daemon
+
+The xrpld node software consists of several interconnected components that need instrumentation for distributed tracing:
+
+```mermaid
+flowchart TB
+    subgraph xrpld["xrpld 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 xrpld 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 xrpld -- 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        | xrpld 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/>ledger_seq = 12345678<br/>consensus_mode = proposing<br/>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/>command = submit"]
+
+        subgraph enqueue["jobqueue.enqueue"]
+            job_attr["job_type = jtCLIENT_RPC"]
+        end
+
+        subgraph command["rpc.command.submit"]
+            cmd_attrs["version = 2<br/>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="xrpld" && tx_hash="ABC123..."}` |
+| **Cross-Node Propagation** | Transaction path across multiple xrpld nodes with timing                                    | `{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                                          | `{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 `tx_hash` to get full trace
+2. **Identify Bottleneck**: Look at span durations to find slowest component
+3. **Check Attributes**: Review `validity`, `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 +1,589 @@
+# Design Decisions
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Architecture Analysis](./01-architecture-analysis.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_http_exporter` | OTLP/HTTP export       | Yes (shipped in Phase 1b) |
+| `opentelemetry-cpp::otlp_grpc_exporter` | OTLP/gRPC export       | Future (not yet wired up) |
+
+### 2.1.2 Instrumentation Strategy
+
+**Manual Instrumentation** (recommended):
+
+| Approach   | Pros                                                            | Cons                                                    |
+| ---------- | --------------------------------------------------------------- | ------------------------------------------------------- |
+| **Manual** | Precise control, optimized placement, xrpld-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["xrpld Nodes"]
+        node1["xrpld<br/>Node 1"]
+        node2["xrpld<br/>Node 2"]
+        node3["xrpld<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/HTTP<br/>:4318"| collector
+    node2 -->|"OTLP/HTTP<br/>:4318"| collector
+    node3 -->|"OTLP/HTTP<br/>:4318"| 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:**
+
+- **xrpld Nodes (blue)**: The source of telemetry data. Each xrpld node exports spans via OTLP/HTTP on port 4318 (the only exporter shipped in Phase 1b).
+- **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 HTTP, then the Collector fans out to the configured backends.
+
+### 2.2.1 OTLP/HTTP (Shipped in Phase 1b)
+
+OTLP/HTTP is the only exporter wired up in Phase 1b. It is configured via
+`OtlpHttpExporterOptions` with the collector traces endpoint
+(`http://localhost:4318/v1/traces` by default) and a JSON content type
+(binary protobuf is also available).
+
+### 2.2.2 OTLP/gRPC (Future Work — Planned Upgrade)
+
+OTLP/gRPC is planned as a future upgrade from the HTTP exporter. The gRPC
+transport offers lower per-span overhead and tighter back-pressure semantics
+than HTTP/JSON, making it attractive for production deployments once the HTTP
+path is validated in earlier phases.
+
+Required to land this upgrade:
+
+1. Add `opentelemetry-cpp::otlp_grpc_exporter` to the Conan recipe (the
+   dependency already exists but is not linked in Phase 1b builds).
+2. Extend `TelemetryConfig.cpp` to parse an `exporter` key (`otlp_http`
+   default, `otlp_grpc` opt-in) and a gRPC endpoint override.
+3. In `Telemetry::start()` branch on the parsed exporter type and construct
+   either `OtlpHttpExporterFactory::Create(httpOpts)` or
+   `OtlpGrpcExporterFactory::Create(grpcOpts)` accordingly.
+4. Update the runbook and dashboards to document the alternate port and TLS
+   settings.
+
+When wired up, the gRPC path will use `OtlpGrpcExporterOptions` configured with
+the collector endpoint (host on port 4317), TLS credentials enabled, and a CA
+certificate path.
+
+Until that work lands, `OtlpGrpcExporterOptions` is **not** used by any code
+path in Phase 1b through Phase 5.
+
+---
+
+## 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
+
+| Span name                      | Description                             |
+| ------------------------------ | --------------------------------------- |
+| `tx.receive`                   | Transaction received from network       |
+| `tx.validate`                  | Transaction signature/format validation |
+| `tx.process`                   | Full transaction processing             |
+| `tx.relay`                     | Transaction relay to peers              |
+| `tx.apply`                     | Apply transaction to ledger             |
+| `consensus.round`              | Complete consensus round                |
+| `consensus.phase.open`         | Open phase - collecting transactions    |
+| `consensus.phase.establish`    | Establish phase - reaching agreement    |
+| `consensus.phase.accept`       | Accept phase - applying consensus       |
+| `consensus.proposal.receive`   | Receive peer proposal                   |
+| `consensus.proposal.send`      | Send our proposal                       |
+| `consensus.validation.receive` | Receive peer validation                 |
+| `consensus.validation.send`    | Send our validation                     |
+| `rpc.request`                  | HTTP/WebSocket request handling         |
+| `rpc.command.*`                | Specific RPC command (dynamic)          |
+| `peer.connect`                 | Peer connection establishment           |
+| `peer.disconnect`              | Peer disconnection                      |
+| `peer.message.send`            | Send protocol message                   |
+| `peer.message.receive`         | Receive protocol message                |
+| `ledger.acquire`               | Ledger acquisition from network         |
+| `ledger.build`                 | Build new ledger                        |
+| `ledger.validate`              | Ledger validation                       |
+| `ledger.close`                 | Close ledger                            |
+| `ledger.replay`                | Ledger replay executed                  |
+| `ledger.delta`                 | Delta-based ledger acquired             |
+| `pathfind.request`             | Path request initiated                  |
+| `pathfind.compute`             | Path computation executed               |
+| `txq.enqueue`                  | Transaction queued                      |
+| `txq.apply`                    | Queued transaction applied              |
+| `fee.escalate`                 | Fee escalation triggered                |
+| `validator.list.fetch`         | UNL list fetched                        |
+| `validator.manifest`           | Manifest update processed               |
+| `amendment.vote`               | Amendment voting executed               |
+| `shamap.sync`                  | State tree synchronization              |
+| `job.enqueue`                  | Job added to queue                      |
+| `job.execute`                  | Job execution                           |
+
+### 2.3.3 Attribute Naming Conventions
+
+Span **names** follow §2.3.1 (dotted `<component>.<operation>`). Span
+**attribute keys** follow the rules below. The constants in the `*SpanNames.h`
+headers are the single source of truth; the collector, Tempo, the Grafana
+dashboards, and the runbook all consume these exact keys, so every layer must
+agree with the code. A CI check enforces this end to end.
+
+1. **Per-span unique attribute** → bare field name, allowed when the field is
+   recorded by a single span/workflow so the span name already supplies the
+   domain (e.g. `command`, `version`, `local` on `rpc.command`).
+2. **Shared attribute (same concept on more than one span)** → ONE key, reused
+   verbatim on every span that records it; the span name tells the occurrences
+   apart, so no per-emitter prefix is added. Name it by the field's meaning: a
+   property of a domain object keeps that object's bare field name (`ledger_hash`,
+   `ledger_seq`, `tx_hash`, `peer_id`, `full_validation`); a field already
+   qualified by a sub-kind keeps that qualifier on every emitter (`proposal_trusted`
+   on both `consensus.proposal.receive` and `peer.proposal.receive`;
+   `validation_trusted` likewise). Defined once in the base `SpanNames.h`
+   `namespace attr` block and re-exported (`using`) by each domain header.
+3. **Collision qualifier** → `<domain>_<field>`, only when a bare name would
+   collide with a DIFFERENT concept in the shared spanmetrics label space or with
+   the OTel-reserved `status` key (e.g. `rpc_status`, `grpc_status`,
+   `consensus_phase`, `consensus_round`, `consensus_mode`). This disambiguates
+   distinct concepts that share a word; it is NOT used to tag the same concept
+   with its emitting workflow — that is rule 2 (one shared name).
+4. **Resource attribute** → dotted `xrpl.<subsystem>.<field>`, reserved ONLY
+   for process/network identity set once at startup (`xrpl.network.id`,
+   `xrpl.network.type`). Span attributes are never dotted in the `xrpl.` form —
+   it blurs the resource/span scope boundary and parses awkwardly in TraceQL.
+5. **Span names** use `<subsystem>[.<component>]` (dotted, per §2.3.1). Only
+   attribute _keys_ follow rules 1–4.
+
+Standard OpenTelemetry semantic-convention keys keep their canonical dotted
+form (e.g. `service.*` resource attributes, `http.*` span attributes); the
+"no dotted form" rule applies to xrpl-custom keys only.
+
+The same rules are recorded in `CONTRIBUTING.md` (the permanent home, since
+`OpenTelemetryPlan/` is removed once the rollout completes). The attribute
+examples in §2.4 below follow these rules.
+
+---
+
+## 2.4 Attribute Schema
+
+> **TxQ** = Transaction Queue | **UNL** = Unique Node List | **OTLP** = OpenTelemetry Protocol
+
+### 2.4.1 Resource Attributes (Set Once at Startup)
+
+Resource attributes identify the process and are set once at startup. They use
+the standard OpenTelemetry semantic conventions plus custom dotted `xrpl.*`
+keys (the dotted form is reserved for resource scope per §2.3.3).
+
+| Key                   | Type / value                                            | Description                    |
+| --------------------- | ------------------------------------------------------- | ------------------------------ |
+| `service.name`        | `"xrpld"`                                               | Standard `SERVICE_NAME`        |
+| `service.version`     | `build_info::getVersionString()`                        | Standard `SERVICE_VERSION`     |
+| `service.instance.id` | node public key (base58)                                | Standard `SERVICE_INSTANCE_ID` |
+| `xrpl.network.id`     | network id (e.g. 0 for mainnet)                         | Network identifier             |
+| `xrpl.network.type`   | `"mainnet"` \| `"testnet"` \| `"devnet"` \| `"unknown"` | Network kind                   |
+| `xrpl.node.type`      | `"validator"` \| `"stock"` \| `"reporting"`             | Node role                      |
+| `xrpl.node.cluster`   | cluster name                                            | Cluster name, if clustered     |
+
+### 2.4.2 Span Attributes by Category
+
+> Span attribute keys use the underscore form from §2.3.3 (shared/qualified
+> keys are `<domain>_<field>`; per-span unique keys are bare). The dotted form
+> is reserved for the resource attributes in §2.4.1 above. This catalog lists
+> the planned attribute set by category; the exact emitted key for each
+> implemented span is defined by the `*SpanNames.h` constants, which are the
+> single source of truth where the two differ.
+
+#### Transaction Attributes
+
+| Key                  | Type   | Description                           |
+| -------------------- | ------ | ------------------------------------- |
+| `tx_hash`            | string | Transaction hash (hex)                |
+| `tx_type`            | string | `"Payment"`, `"OfferCreate"`, etc.    |
+| `tx_account`         | string | Source account (redacted in prod)     |
+| `tx_sequence`        | int64  | Account sequence number               |
+| `tx_fee`             | int64  | Fee in drops                          |
+| `tx_result`          | string | `"tesSUCCESS"`, `"tecPATH_DRY"`, etc. |
+| `current_ledger_seq` | int64  | Open ledger the transaction targeted  |
+| `relay_count`        | int64  | Peers the transaction was relayed to  |
+
+> **Note:** `current_ledger_seq` and `ledger_seq` are the same concept — a ledger's sequence number — but they name different ledgers, so the design keeps two keys rather than one. `current_ledger_seq` is the open or in-flight ledger a transaction's work was applied into; it is named after the RPC field `ledger_current_index`. `ledger_seq` (see [Ledger & Job Attributes](#ledger--job-attributes)) is a closed or validated ledger, set by the ledger and consensus spans. Neither is spelled `ledger_index`: per rule 2 of [Telemetry span attribute naming](../CONTRIBUTING.md#telemetry-span-attribute-naming), one concept gets one key reused verbatim, and a different referent is disambiguated with a prefix rather than a synonym.
+
+#### Consensus Attributes
+
+| Key                  | Type    | Description                         |
+| -------------------- | ------- | ----------------------------------- |
+| `consensus_round`    | int64   | Round number                        |
+| `consensus_phase`    | string  | `"open"`, `"establish"`, `"accept"` |
+| `consensus_mode`     | string  | `"proposing"`, `"observing"`, etc.  |
+| `proposers`          | int64   | Number of proposers                 |
+| `prev_ledger_prefix` | string  | Previous ledger hash prefix         |
+| `ledger_seq`         | int64   | Ledger sequence                     |
+| `tx_count`           | int64   | Transactions in consensus set       |
+| `round_time_ms`      | float64 | Round duration                      |
+
+#### RPC Attributes
+
+| Key           | Type    | Description                                                                   |
+| ------------- | ------- | ----------------------------------------------------------------------------- |
+| `command`     | string  | Command name (per-span unique on `rpc.command`)                               |
+| `version`     | int64   | API version                                                                   |
+| `rpc_role`    | string  | `"admin"` or `"user"` (qualified — `role` is generic)                         |
+| `params`      | string  | Sanitized parameters (optional)                                               |
+| `rpc_status`  | string  | Response status: `success` \| `error` (qualified — `status` is OTel-reserved) |
+| `duration_ms` | float64 | Request duration in milliseconds                                              |
+
+#### Peer & Message Attributes
+
+| Key                  | Type    | Description                |
+| -------------------- | ------- | -------------------------- |
+| `peer_id`            | string  | Peer public key (base58)   |
+| `peer_address`       | string  | IP:port                    |
+| `peer_latency_ms`    | float64 | Measured latency           |
+| `peer_cluster`       | string  | Cluster name if clustered  |
+| `message_type`       | string  | Protocol message type name |
+| `message_size_bytes` | int64   | Message size               |
+| `message_compressed` | bool    | Whether compressed         |
+
+#### Ledger & Job Attributes
+
+| Key                         | Type    | Description                      |
+| --------------------------- | ------- | -------------------------------- |
+| `ledger_hash`               | string  | Ledger hash                      |
+| `ledger_seq`                | int64   | Closed/validated ledger sequence |
+| `close_time_ripple_epoch_s` | int64   | Close time (XRPL epoch seconds)  |
+| `ledger_tx_count`           | int64   | Transaction count                |
+| `job_type`                  | string  | Job type name                    |
+| `job_queue_ms`              | float64 | Time spent in queue              |
+| `job_worker`                | int64   | Worker thread ID                 |
+
+#### PathFinding Attributes
+
+| Key                        | Type   | Description               |
+| -------------------------- | ------ | ------------------------- |
+| `pathfind_source_currency` | string | Source currency code      |
+| `pathfind_dest_currency`   | string | Destination currency code |
+| `pathfind_path_count`      | int64  | Number of paths found     |
+| `pathfind_cache_hit`       | bool   | RippleLineCache hit       |
+
+#### TxQ Attributes
+
+| Key                   | Type   | Description                 |
+| --------------------- | ------ | --------------------------- |
+| `txq_queue_depth`     | int64  | Current queue depth         |
+| `txq_fee_level`       | int64  | Fee level of transaction    |
+| `txq_eviction_reason` | string | Why transaction was evicted |
+
+#### Fee Attributes
+
+| Key                    | Type  | Description               |
+| ---------------------- | ----- | ------------------------- |
+| `fee_load_factor`      | int64 | Current load factor       |
+| `fee_escalation_level` | int64 | Fee escalation multiplier |
+
+#### Validator Attributes
+
+| Key                      | Type  | Description               |
+| ------------------------ | ----- | ------------------------- |
+| `validator_list_size`    | int64 | UNL size                  |
+| `validator_list_age_sec` | int64 | Seconds since last update |
+
+#### Amendment Attributes
+
+| Key                | Type   | Description                            |
+| ------------------ | ------ | -------------------------------------- |
+| `amendment_name`   | string | Amendment name                         |
+| `amendment_status` | string | `"enabled"`, `"vetoed"`, `"supported"` |
+
+#### SHAMap Attributes
+
+| Key                    | Type    | Description                                   |
+| ---------------------- | ------- | --------------------------------------------- |
+| `shamap_type`          | string  | `"transaction"`, `"state"`, `"account_state"` |
+| `shamap_missing_nodes` | int64   | Number of missing nodes during sync           |
+| `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`, `current_ledger_seq`                                 | Trace transaction lifecycle  |
+| **Consensus**   | `consensus_round`, `consensus_phase`, `consensus_mode`, `proposers`, `round_time_ms`              | Analyze consensus timing     |
+| **RPC**         | `command`, `version`, `rpc_status`, `duration_ms`                                                 | Monitor RPC performance      |
+| **Peer**        | `peer_id` (public key), `peer_latency_ms`, `message_type`, `message_size_bytes`                   | Network topology analysis    |
+| **Ledger**      | `ledger_hash`, `ledger_seq`, `close_time`, `ledger_tx_count`                                      | Ledger progression tracking  |
+| **Job**         | `job_type`, `job_queue_ms`, `job_worker`                                                          | JobQueue performance         |
+| **PathFinding** | `pathfind_source_currency`, `pathfind_dest_currency`, `pathfind_path_count`, `pathfind_cache_hit` | Payment path analysis        |
+| **TxQ**         | `txq_queue_depth`, `txq_fee_level`, `txq_eviction_reason`                                         | Queue depth and fee tracking |
+| **Fee**         | `fee_load_factor`, `fee_escalation_level`                                                         | Fee escalation monitoring    |
+| **Validator**   | `validator_list_size`, `validator_list_age_sec`                                                   | UNL health monitoring        |
+| **Amendment**   | `amendment_name`, `amendment_status`                                                              | Protocol upgrade tracking    |
+| **SHAMap**      | `shamap_type`, `shamap_missing_nodes`, `shamap_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**           | `tx_account` is hashed at collector level before storage                                                                                |
+| **Configurable Redaction**    | Sensitive fields can be excluded via `[telemetry]` config section                                                                       |
+| **Collector Tail Sampling**   | xrpld head sampling is fixed at 1.0 (every span emitted); the collector retains ~10% of non-error traces, reducing stored 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 (via an `attributes` processor)
+to hash or redact sensitive attributes before export — for example, hashing
+`tx_account`, deleting `peer_address` to drop IP addresses, and deleting
+`params` to redact request parameters.
+
+#### Configuration Options for Privacy
+
+In `xrpld.cfg`, operators control data collection granularity through the
+`[telemetry]` section. Besides `enabled`, per-component toggles
+(`trace_transactions`, `trace_consensus`, `trace_rpc`, `trace_peer` — the last
+often disabled due to high volume) select which spans are emitted, and
+redaction flags (`redact_account` to hash account addresses, `redact_peer_address`
+to remove peer IP addresses) control SDK-level redaction before export.
+
+> **Note**: The `redact_account` configuration in `xrpld.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: xrpld=..."]
+    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/>  reserved 4;  // trace_state, later<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 xrpld 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
+
+xrpld 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
+
+A PerfLog entry is a JSON object with fields such as `time`, `method`,
+`duration_us`, and `result`.
+
+#### 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
+  - Aggregation happens on the StatsD server, not in the process
+
+In xrpld, Beast Insight is used through `increment` (counters), `gauge`
+(point-in-time values), and `timing` (durations) calls. A `timing` call sends
+each measured value as its own raw `|ms` sample, so the histogram a dashboard
+reads is built by the StatsD server from that stream of values.
+
+#### OpenTelemetry (NEW)
+
+- **Purpose**: Distributed request tracing across nodes
+- **Strengths**:
+  - **Cross-node correlation** via `trace_id`
+  - Parent-child span relationships
+  - Rich attributes per span
+  - A `Histogram` instrument that aggregates **at the point of measure**
+  - Industry standard (CNCF)
+- **Limitations**:
+  - Requires collector infrastructure
+  - Higher complexity than logging
+
+A span is created via `startSpan` (e.g. `"tx.relay"`), annotated with
+attributes such as `tx_hash` and `peer_id`, and is automatically linked to its
+parent through the active context.
+
+OpenTelemetry is not only spans. The same SDK offers a `Histogram` instrument,
+and a `Record()` call folds the value straight into bucket counts inside the
+process — no per-event record is shipped and no server-side aggregation step is
+needed. That is what makes it affordable in a hot loop where one span per event
+would not be, and it is the one thing Beast Insight cannot do, because its
+`timing` path ships raw values and aggregates them on the StatsD server.
+
+### 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" | ❌         | ❌     | ✅            |
+| "p99 NodeStore fetch latency?"          | ❌         | ❌     | ✅            |
+
+The last row is the case a span cannot answer. One `TMGetObjectByHash` message
+requests up to `tuning::kHardMaxReplyNodes` objects, so a span per NodeStore
+fetch is not affordable in that loop. Instead the fetch loop's wall time is
+recorded once per message into an OpenTelemetry `Histogram`
+(`getobject_lookup_us`), and the quantile is read off its buckets. StatsD is
+marked ❌ because that instrument is recorded on the native OpenTelemetry metrics
+path, not through Beast Insight.
+
+### 2.6.4 Coexistence Strategy
+
+```mermaid
+flowchart TB
+    subgraph xrpld["xrpld 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 xrpld fill:#212121,stroke:#0a0a0a,color:#ffffff
+    style grafana fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **xrpld Process (dark gray)**: The single xrpld 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/HTTP to a Collector, which then forwards to a trace backend (Tempo). (OTLP/gRPC is future work — §2.2.2.)
+- **Grafana (red, unified UI)**: All three data streams converge in Grafana, enabling operators to correlate logs, metrics, and traces in a single dashboard.
+
+### 2.6.5 Correlation with PerfLog
+
+Trace IDs can be correlated with existing PerfLog entries for comprehensive
+debugging. The design is for `RPCHandler.cpp` to start an `rpc.command.<method>`
+span alongside the existing PerfLog `rpcStart`/`rpcFinish`/`rpcError` calls,
+extract the span's `trace_id` (when valid), and eventually stamp it onto the
+PerfLog entry (a planned `setTraceId` hook) so logs and traces share a key. The
+span status is set to OK on success or to error (recording the exception) on
+failure.
+
+---
+
+_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 +1,415 @@
+# Implementation Strategy
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Configuration Reference](./05-configuration-reference.md)
+
+---
+
+## 3.1 Directory Structure
+
+The telemetry implementation follows xrpld'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/HTTP exporter (client init)     | ~64 KB      | At startup |
+| Propagator registry                  | ~8 KB       | At startup |
+| **Total static**                     | **~8.1 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/HTTP exporter allocates a small client and TLS
+> initialization buffer. 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)
+
+> **Measured outcome**: A perf-iac comparison (telemetry compiled-in + enabled vs compiled-out,
+> 9 nodes — validators and client-handlers — under sustained payment load) recorded **no measurable
+> RSS increase over the telemetry-off baseline** (~15 GiB mean / ~18–19 GiB peak on both sides),
+> with no OOM, no swap, and no leak across the run. The ~10 MB ceiling above is therefore a
+> provisioning safety margin (dominated by virtual thread-stack address space), not an expected
+> resident-memory increase. Steady-state cost shows up as throughput (~3–4% at head sampling 1.0),
+> not memory.
+
+### 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
+
+Instrumentation is gated on two levels. A compile-time feature flag (`XRPL_ENABLE_TELEMETRY`) reduces the trace macros to no-ops when telemetry is built out, so disabled builds carry zero cost. At runtime, per-component guards (e.g. `shouldTracePeer()`) skip span creation for components whose tracing is turned off, incurring no overhead beyond a single boolean check.
+
+---
+
+## 3.8 Links to Detailed Documentation
+
+- **[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 xrpld codebase.
+
+### 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):** Instrumenting an RPC handler adds roughly 3-4 lines: one macro to start the span and one or two `setAttribute` calls (command name, status). The span ends automatically via RAII, so the existing control flow — process the request, send the result — is untouched.
+
+**Consensus Instrumentation (Medium Intrusiveness):** Consensus is slightly more intrusive because child spans in later phase transitions need the round's context. Beyond the span-start and attribute macros, this requires storing the active context in a new member variable (`currentRoundContext_`) at round start. The existing round logic itself remains unchanged.
+
+---
+
+_Previous: [Design Decisions](./02-design-decisions.md)_ | _Next: [Configuration Reference](./05-configuration-reference.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/05-configuration-reference.md

@@ -0,0 +1,265 @@
+# Configuration Reference
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Implementation Phases](./06-implementation-phases.md)
+
+---
+
+## 5.1 xrpld Configuration
+
+> **OTLP** = OpenTelemetry Protocol | **TxQ** = Transaction Queue
+
+### 5.1.1 Configuration File Section
+
+The authoritative `[telemetry]` example lives in `cfg/xrpld-example.cfg`. Telemetry is disabled by default (`enabled=0`); enabling it turns on distributed tracing for transaction flow, consensus, and RPC calls, with traces exported to an OpenTelemetry Collector over OTLP. Head sampling is intentionally fixed at 1.0 (sample everything) and is not configurable — per-node head-sampling would produce broken/partial distributed traces, so volume reduction is delegated to the collector's tail sampling (see Section 7.4.2). The full option reference follows.
+
+### 5.1.2 Configuration Options Summary
+
+| Option                | Type   | Default                           | Description                                          |
+| --------------------- | ------ | --------------------------------- | ---------------------------------------------------- |
+| `enabled`             | bool   | `false`                           | Enable/disable telemetry                             |
+| `traces_endpoint`     | string | `http://localhost:4318/v1/traces` | Full OTLP/HTTP URL for spans, used verbatim          |
+| `use_tls`             | bool   | `false`                           | Enable TLS for exporter connection                   |
+| `tls_ca_cert`         | string | `""`                              | Path to CA certificate file                          |
+| `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`  | 0 or 1 | `1`                               | Enable transaction tracing                           |
+| `trace_consensus`     | 0 or 1 | `1`                               | Enable consensus tracing                             |
+| `trace_rpc`           | 0 or 1 | `1`                               | Enable RPC tracing                                   |
+| `trace_peer`          | 0 or 1 | `1`                               | Enable peer message tracing (high volume)            |
+| `trace_ledger`        | 0 or 1 | `1`                               | Enable ledger tracing                                |
+| `service_name`        | string | `"xrpld"`                         | Service name (`service.name`) for traces and metrics |
+| `service_instance_id` | string | `<node_pubkey>`                   | Instance identifier                                  |
+
+**Planned (not yet implemented)**: the following options appear in the design
+documents but are not parsed by `TelemetryConfig.cpp` in Phase 1b and later
+phases. They will be added as the corresponding subsystems are instrumented:
+
+| Option                     | Planned Phase | Purpose                                                                 |
+| -------------------------- | ------------- | ----------------------------------------------------------------------- |
+| `exporter`                 | Future        | Select between OTLP/HTTP and OTLP/gRPC                                  |
+| `trace_pathfind`           | Phase 2       | Path computation tracing toggle                                         |
+| `trace_txq`                | Phase 3       | Transaction queue tracing toggle                                        |
+| `trace_validator`          | Future        | Validator list / manifest update tracing                                |
+| `trace_amendment`          | Future        | Amendment voting tracing                                                |
+| `consensus_trace_strategy` | Phase 4       | Trace ID strategy for consensus rounds (`deterministic` \| `attribute`) |
+
+---
+
+## 5.2 Configuration Parser
+
+> **TxQ** = Transaction Queue
+
+The parser `setup_Telemetry()` in `src/libxrpl/telemetry/TelemetryConfig.cpp` reads the `[telemetry]` `Section` and populates a `Telemetry::Setup` struct, applying the defaults listed in Section 5.1.2 via `section.value_or(...)`. It derives `serviceInstanceId` from the node public key when not overridden, selects the exporter endpoint default by exporter type, and leaves the sampling ratio at its fixed 1.0 default (not read from config — see Section 7.4.2).
+
+---
+
+## 5.3 Application Integration
+
+### 5.3.1 ApplicationImp Changes
+
+> **Deferred identity**: The node public key (`nodeIdentity_`) is not
+> available during `ApplicationImp`'s member initializer list — it is
+> resolved later in `setup()`. The `Telemetry` object is therefore
+> constructed with an empty `serviceInstanceId` and patched via
+> `setServiceInstanceId()` once `setup()` has called `getNodeIdentity()`.
+
+`ApplicationImp` (in `src/xrpld/app/main/Application.cpp`) owns a `std::unique_ptr<telemetry::Telemetry> telemetry_`. It is built in the member initializer list via `make_Telemetry(setup_Telemetry(...))` with an empty `serviceInstanceId`, then patched in `setup()` by calling `setServiceInstanceId()` with the Base58 node public key (unless the user supplied a custom `service_instance_id`). `start()` and `run()` forward to `telemetry_->start()` / `telemetry_->stop()`, and `getTelemetry()` returns the owned instance.
+
+### 5.3.2 ServiceRegistry Interface Addition
+
+`include/xrpl/core/ServiceRegistry.h` gains a pure-virtual `telemetry::Telemetry& getTelemetry()` (with a forward declaration of `telemetry::Telemetry`), giving every component a uniform accessor for the tracing subsystem.
+
+> **Note:** `Application` extends `ServiceRegistry`, so `getTelemetry()` is
+> available on both. Components that hold a `ServiceRegistry&` (e.g.
+> `NetworkOPsImp`) call `registry_.get().getTelemetry()`. Components that
+> still hold an `Application&` (e.g. `ServerHandler`, `PeerImp`,
+> `RCLConsensus::Adaptor`) call `app_.getTelemetry()` directly.
+
+---
+
+## 5.4 CMake Integration
+
+> **OTLP** = OpenTelemetry Protocol
+
+### 5.4.1 Find OpenTelemetry Module
+
+A `cmake/FindOpenTelemetry.cmake` module locates the OpenTelemetry C++ SDK. It first tries `find_package(opentelemetry-cpp CONFIG)`, aliasing the imported targets `OpenTelemetry::api`, `OpenTelemetry::sdk`, and `OpenTelemetry::otlp_grpc_exporter`, and falls back to `pkg-config` when no CMake config package is present.
+
+### 5.4.2 CMakeLists.txt Changes
+
+The top-level `CMakeLists.txt` adds an `XRPL_ENABLE_TELEMETRY` option (default `OFF`). When enabled, it runs `find_package(OpenTelemetry REQUIRED)`, defines the `XRPL_ENABLE_TELEMETRY` compile flag, and builds the `xrpl_telemetry` library from the real telemetry sources linked against the OpenTelemetry targets; when disabled, it builds the same target from a no-op `NullTelemetry.cpp` so call sites compile unchanged.
+
+---
+
+## 5.5 OpenTelemetry Collector Configuration
+
+> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring
+
+The authoritative collector config lives in the repo at `docker/telemetry/otel-collector-config.yaml` (with Tempo backend config in `docker/telemetry/tempo.yaml`). The sections below summarize the development and production shapes of that pipeline.
+
+### 5.5.1 Development Configuration
+
+The development collector enables an OTLP receiver on both gRPC (`0.0.0.0:4317`) and HTTP (`0.0.0.0:4318`), a single `batch` processor (1s timeout, batch size 100), and two exporters: a `logging` exporter for console debugging and `otlp/tempo` (insecure) for trace visualization. The single `traces` pipeline wires receiver → batch → both exporters.
+
+### 5.5.2 Production Configuration
+
+The production collector adds TLS on the OTLP gRPC receiver and a richer processor chain: a `memory_limiter` (OOM guard), `batch` (5s timeout, size 512), `tail_sampling`, and an `attributes` processor that hashes sensitive fields (e.g. `tx_account`) and stamps `deployment.environment`. Tail sampling keeps all `ERROR` traces, slow consensus rounds (>5s) and slow RPC requests (>1s), and probabilistically samples the remainder at 10%. Exporters target Grafana Tempo (TLS) and Elastic APM; `health_check` and `zpages` extensions are enabled for operability.
+
+---
+
+## 5.6 Docker Compose Development Environment
+
+> **OTLP** = OpenTelemetry Protocol
+
+The authoritative development stack lives in the repo at `docker/telemetry/docker-compose.yml`. It brings up four services on a shared `xrpld-telemetry` network: an `otel-collector` (otel/opentelemetry-collector-contrib) exposing OTLP gRPC `4317`, OTLP HTTP `4318`, and health check `13133`; `tempo` for trace storage/visualization; `grafana` with provisioned datasources and dashboards (anonymous admin enabled); and an optional `prometheus` for metric correlation.
+
+---
+
+## 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, per-component trace toggles) while the CMake flag controls whether telemetry is compiled in at all. Head sampling is fixed at 1.0 and is not a config option; volume reduction happens via tail sampling in the collector.
+- **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 xrpld process via OTLP/HTTP and enters the external Collector pipeline. (OTLP/gRPC is future work — see design decisions §2.2.2.)
+- **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 xrpld traces with Grafana.
+
+### 5.8.1 Data Source Configuration
+
+#### Tempo (Recommended)
+
+A Tempo datasource (`grafana/provisioning/datasources/tempo.yaml`, provisioned from `docker/telemetry/grafana/`) points at `http://tempo:3200` and enables `tracesToLogs` (linking to Loki on `service.name`/`tx_hash` and mapping `trace_id` → `traceID`), `serviceMap` against Prometheus, the node graph, and Loki search.
+
+#### Elastic APM
+
+Alternatively, an Elasticsearch datasource (`grafana/provisioning/datasources/elastic-apm.yaml`) of type `elasticsearch` points at `http://elasticsearch:9200` against the `apm-*` index, using `@timestamp` as the time field and mapping the log message/level fields.
+
+### 5.8.2 Dashboard Provisioning
+
+A dashboard provider (`grafana/provisioning/dashboards/dashboards.yaml`) loads the `xrpld` dashboard folder from disk (`/var/lib/grafana/dashboards/rippled`), polling for changes every 30s with deletion disabled.
+
+### 5.8.3 Example Dashboard: RPC Performance
+
+An example `xrpld RPC Performance` dashboard (uid `xrpld-rpc-performance`) sourced from Tempo via TraceQL provides four panels: RPC latency by command (heatmap), RPC error rate by command (timeseries), the top 10 slowest RPC commands by average duration (table), and a recent-traces table.
+
+### 5.8.4 Example Dashboard: Transaction Tracing
+
+An example `xrpld Transaction Tracing` dashboard (uid `xrpld-tx-tracing`) over Tempo provides three panels: transaction throughput (`tx.receive` rate, stat), cross-node relay count (average `span.relay_count` on `tx.relay`, timeseries), and a table of transaction validation errors (`tx.validate` with `status = error`).
+
+### 5.8.5 TraceQL Query Examples
+
+Common queries for xrpld traces:
+
+```
+# Find all traces for a specific transaction hash
+{resource.service.name="xrpld" && span.tx_hash="ABC123..."}
+
+# Find slow RPC commands (>100ms)
+{resource.service.name="xrpld" && name=~"rpc.command.*"} | { duration > 100ms }
+
+# Find consensus rounds taking >5 seconds
+{resource.service.name="xrpld" && name="consensus.round"} | { duration > 5s }
+
+# Find failed transactions with error details
+{resource.service.name="xrpld" && name="tx.validate" && status = error}
+
+# Find transactions relayed to many peers
+{resource.service.name="xrpld" && name="tx.relay"} | { span.relay_count > 10 }
+
+# Compare latency across nodes
+{resource.service.name="xrpld" && name="rpc.command.account_info"} | avg_over_time(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**
+
+Configure a Promtail scrape job (`promtail-config.yaml`) that tails `/var/log/rippled/perf*.log`, parses each JSON line, and promotes `trace_id`, `ledger_seq`, and `tx_hash` to Loki labels.
+
+**Step 2: Add trace_id to PerfLog entries**
+
+Modify PerfLog so its JSON output includes a `trace_id` field whenever a valid span is active: fetch the current span from the OpenTelemetry runtime context, and if its context is valid, render the trace ID as a 32-character lowercase hex string into the log entry.
+
+**Step 3: Configure Grafana trace-to-logs link**
+
+In the Tempo datasource, set the `tracesToLogs` derived field to link to Loki on the `trace_id` and `tx_hash` tags, with `filterByTraceID: true`.
+
+### 5.8.7 Correlation with Insight/StatsD Metrics
+
+To correlate traces with existing Beast Insight metrics:
+
+**Step 1: Export Insight metrics to Prometheus**
+
+Add a Prometheus scrape job (`prometheus.yaml`) named `xrpld-statsd` targeting the StatsD exporter at `statsd-exporter:9102`.
+
+**Step 2: Add exemplars to metrics**
+
+The OpenTelemetry SDK automatically adds exemplars (trace IDs) to metrics when using the Prometheus exporter, linking metric spikes to specific traces.
+
+**Step 3: Configure Grafana metric-to-trace link**
+
+In the Prometheus datasource, set `exemplarTraceIdDestinations` to map the `trace_id` exemplar to the Tempo datasource.
+
+**Step 4: Dashboard panel with exemplars**
+
+Add a timeseries panel over Prometheus (e.g. `histogram_quantile(0.99, rate(xrpld_rpc_duration_seconds_bucket[5m]))`) with `exemplar: true` enabled.
+
+This allows clicking on metric data points to jump directly to the related trace.
+
+---
+
+_Previous: [Implementation Strategy](./03-implementation-strategy.md)_ | _Next: [Implementation Phases](./06-implementation-phases.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/06-implementation-phases.md

@@ -0,0 +1,576 @@
+# 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 `xrpl::rpc::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 `RCLConsensus::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                  |
+
+### Exit Criteria
+
+- [ ] Complete consensus round traces
+- [ ] Phase transitions visible
+- [ ] Proposals and validations traced
+- [ ] No impact on consensus timing
+- [ ] Multi-validator test network validated
+
+### Implementation Status — Phase 4a Plan
+
+Phase 4a (establish-phase gap fill & cross-node correlation) will add:
+
+- **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 `"random"` which is
+  experimental and not used).
+  See [Configuration Reference](./05-configuration-reference.md) for full
+  configuration options.
+- **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`).
+
+The `Phase4_taskList.md` spec document is introduced in the Phase 2 PR (#6424)
+and will contain the full task breakdown and implementation notes.
+
+---
+
+## 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 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        |
+
+---
+
+## 6.8 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]
+```
+
+---
+
+## 6.10 Definition of Done
+
+> **TxQ** = Transaction Queue | **HA** = High Availability
+
+Clear, measurable criteria for each phase.
+
+### 6.10.1 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.
+
+### 6.10.2 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.
+
+### 6.10.3 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           | Duplicates produce no span |
+| Performance      | TX throughput overhead          | <5% degradation            |
+
+**Definition of Done**: Transaction traces span 3+ nodes in test network, performance within bounds.
+
+### 6.10.4 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.
+
+### 6.10.5 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.
+
+### 6.10.6 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 |
+
+---
+
+## 6.11 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 +1,407 @@
+# 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[xrpld<br/>Validator 1]
+        v2[xrpld<br/>Validator 2]
+    end
+
+    subgraph stock["Stock Nodes"]
+        s1[xrpld<br/>Stock 1]
+        s2[xrpld<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 xrpld 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. Enrichment includes deployment-tier tagging: each collector stamps `deployment.environment` and (as a fallback) `xrpl.network.type` so one Grafana stack can filter data from many collectors by tier.
+- **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 xrpld 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/>fixed at 100%<br/>not configurable]
+    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)**: xrpld pins head sampling at 100% (sample everything) and does not expose a configurable ratio. This is intentional: a per-node ratio would let different nodes make divergent keep/drop decisions for the same distributed trace, producing broken/partial traces. A span inheriting a remote parent is decided by the same ratio sampler, not by the peer's sampled flag. Volume reduction is delegated to the collector's tail sampling.
+- **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 xrpld observability.
+
+### 7.6.1 Consensus Health Dashboard
+
+A Tempo-backed dashboard (uid `xrpld-consensus-health`) with four panels, all driven by TraceQL:
+
+- **Consensus Round Duration** (timeseries, ms): average `consensus.round` span duration per node instance, with yellow/red thresholds at 4s/5s.
+- **Phase Duration Breakdown** (barchart): average duration of `consensus.phase.*` spans grouped by span name.
+- **Proposers per Round** (stat): average of the `span.proposers` attribute on `consensus.round` spans.
+- **Recent Slow Rounds (>5s)** (table): `consensus.round` spans filtered to `duration > 5s`.
+
+Each panel's TraceQL query is described inline in its bullet above.
+
+### 7.6.2 Node Overview Dashboard
+
+A Tempo-backed dashboard (uid `xrpld-node-overview`) with four panels:
+
+- **Active Nodes** (stat): count of distinct `resource.service.instance.id` values seen for the `xrpld` service.
+- **Total Transactions (1h)** (stat): count of `tx.receive` spans.
+- **Error Rate** (gauge, percent): ratio of `status = error` spans to all spans, with yellow/red thresholds at 1%/5%.
+- **Service Map** (nodeGraph): Tempo-generated service dependency graph.
+
+### 7.6.3 Alert Rules
+
+Grafana provisions three TraceQL-based alert rules (group `xrpld-tracing-alerts`, evaluated every 1m) against the Tempo datasource:
+
+- **Consensus Round Slow** (warning, `for: 5m`): fires when average `consensus.round` duration exceeds 5s.
+
+  ```
+  {resource.service.name="xrpld" && name="consensus.round"} | avg(duration) > 5s
+  ```
+
+- **RPC Error Rate Spike** (critical, `for: 2m`): fires when the error rate across `rpc.command.*` spans exceeds 5%. Error _rate_ is a ratio, so it must divide the error-span rate by the total-span rate — a single TraceQL `rate()` returns spans/second, not a percentage, and would fire on traffic volume alone. This uses span metrics emitted by the collector's `spanmetrics` connector (Prometheus datasource), not a TraceQL query:
+
+  ```
+  sum(rate(traces_spanmetrics_calls_total{service_name="xrpld", span_name=~"rpc.command.*", status_code="STATUS_CODE_ERROR"}[5m]))
+  /
+  sum(rate(traces_spanmetrics_calls_total{service_name="xrpld", span_name=~"rpc.command.*"}[5m]))
+  > 0.05
+  ```
+
+- **Transaction Throughput Drop** (warning, `for: 10m`): fires when the `tx.receive` span rate falls below 10/s.
+
+  ```
+  {resource.service.name="xrpld" && name="tx.receive"} | rate() < 10
+  ```
+
+> **Note**: The Consensus Round Slow and Transaction Throughput Drop rules use TraceQL aggregates (`avg(duration)`, `rate()`), which require Tempo 2.3+ with TraceQL metrics enabled. Verify aggregate query support in your Tempo version before provisioning. The RPC Error Rate Spike rule instead queries Prometheus span metrics (collector `spanmetrics` connector), so it needs that connector enabled in the collector pipeline.
+
+---
+
+## 7.7 PerfLog and Insight Correlation
+
+> **OTLP** = OpenTelemetry Protocol
+
+How to correlate OpenTelemetry traces with existing xrpld observability.
+
+### 7.7.1 Correlation Architecture
+
+```mermaid
+flowchart TB
+    subgraph xrpld["xrpld 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 xrpld 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:**
+
+- **xrpld 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`, `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**   | `tx_hash`           | Logs, Metrics | Find TX-related data       |
+| **Trace**   | `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="xrpld" && span.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="xrpld"} |= "4bf92f3577b34da6a3ce929d0e0e4736"
+```
+
+**Step 4: Check Insight metrics for the time window**
+
+```
+# In Grafana with Prometheus
+rate(xrpld_tx_applied_total[1m])
+  @ timestamp_from_trace
+```
+
+### 7.7.4 Unified Dashboard Example
+
+A single dashboard (uid `xrpld-unified`) that ties traces, metrics, and logs together across the Tempo, Prometheus, and Loki datasources:
+
+- **Transaction Latency (Traces)** (timeseries, Tempo): `histogram_over_time(duration)` of `tx.receive` spans.
+- **Transaction Rate (Metrics)** (timeseries, Prometheus): `rate(xrpld_tx_received_total[5m])` per instance, with a data link that opens the matching `tx.receive` traces in Tempo.
+- **Recent Logs** (logs, Loki): `{job="xrpld"} | json`.
+- **Trace Search** (table, Tempo): all `xrpld` traces, with per-row data links on `traceID` that jump to the trace in Tempo and to the correlated logs in Loki (`{job="xrpld"} |= "<traceID>"`).
+
+The cross-datasource data links are what make this a single-pane debugging view; the correlation fields they rely on are listed in section 7.7.2.
+
+---
+
+_Previous: [Implementation Phases](./06-implementation-phases.md)_ | _Next: [Appendix](./08-appendix.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/08-appendix.md

@@ -0,0 +1,187 @@
+# 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                           |
+
+### xrpld-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 xrpld                  |
+| **Beast Insight** | Existing metrics framework in xrpld                           |
+| **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/)
+
+### xrpld Resources
+
+8. [xrpld Source Code](https://github.com/XRPLF/rippled)
+9. [XRP Ledger Documentation](https://xrpl.org/docs/)
+10. [xrpld Overlay README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/README.md)
+11. [xrpld RPC README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/README.md)
+12. [xrpld 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)     | xrpld 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    |
+| [05-configuration-reference.md](./05-configuration-reference.md) | xrpld 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        |
+
+---
+
+_Previous: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/OpenTelemetryPlan.md

@@ -0,0 +1,199 @@
+# [OpenTelemetry](00-tracing-fundamentals.md) Distributed Tracing Implementation Plan for xrpld
+
+## Executive Summary
+
+> **OTLP** = OpenTelemetry Protocol
+
+This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the xrpld 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        | <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               |
+
+---
+
+## 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"]
+        config["05-configuration-reference.md"]
+    end
+
+    subgraph deploy["Deployment & Planning"]
+        phases["06-implementation-phases.md"]
+        backends["07-observability-backends.md"]
+        appendix["08-appendix.md"]
+    end
+
+    overview --> fundamentals
+    overview --> analysis
+    overview --> impl
+    overview --> deploy
+
+    fund --> arch
+    arch --> design
+    design --> strategy
+    strategy --> config
+    config --> phases
+    phases --> backends
+    backends --> appendix
+
+    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 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
+```
+
+</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)     | xrpld 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          |
+| **5**   | [Configuration Reference](./05-configuration-reference.md) | xrpld 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                                  |
+
+---
+
+## 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 xrpld-specific scenarios like transaction relay and consensus.
+
+➡️ **[Read Tracing Fundamentals](./00-tracing-fundamentals.md)**
+
+---
+
+## 1. Architecture Analysis
+
+> **WS** = WebSocket | **TxQ** = Transaction Queue
+
+The xrpld 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/HTTP to an OpenTelemetry Collector, which provides flexible routing and sampling. OTLP/gRPC is planned future work (see design decisions §2.2.2).
+
+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 head sampling fixed at 100% (intentionally not configurable, so trace keep/drop decisions stay coherent across nodes), tail-based sampling at the collector for errors and slow traces to reduce volume, batch export to reduce network overhead, and conditional instrumentation that compiles to no-ops when disabled.
+
+➡️ **[Read full Implementation Strategy](./03-implementation-strategy.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, and component-level filtering. Head sampling is fixed at 1.0 (not operator-configurable); volume reduction is done by tail sampling in the collector. 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 9 weeks across 5 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                       |
+
+**Total Effort**: 47 person-days (2 developers working in parallel)
+
+➡️ **[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 xrpld-specific terms, references to external documentation and specifications, version history for this implementation plan, and a complete document index.
+
+➡️ **[View Appendix](./08-appendix.md)**
+
+---
+
+_This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the xrpld XRP Ledger node software. For detailed information on any section, follow the links to the corresponding sub-documents._

README.md

@@ -54,6 +54,7 @@ Here are some good places to start learning the source code:
 | `./docs`   | Source documentation files and doxygen config. |
 | `./cfg`    | Example configuration files.                   |
 | `./src`    | Source code.                                   |
+| `./crates` | Rust source code.                              |
 
 Some of the directories under `src` are external repositories included using
 git-subtree. See those directories' README files for more details.

RELEASING.md

@@ -0,0 +1,152 @@
+# Branching and Release Management
+
+This document describes how we branch, release, and merge releases back into `develop`.
+It does not define version naming
+(e.g., what constitutes a major-minor, patch, or beta release).
+
+Examples use `X.Y` for a release line:
+`X` and `Y` are placeholders, while the trailing `x` is literal,
+e.g., `release/X.Y.x` is `release/3.4.x` for the `3.4` line.
+
+## Branches
+
+| Branch          | Purpose                                                                                   |
+| :-------------- | :---------------------------------------------------------------------------------------- |
+| `develop`       | Main development branch. Betas and the first RC of a major-minor release are tagged here. |
+| `staging/X.Y.x` | Where fixes for the `X.Y` line are developed and RCs are prepared.                        |
+| `release/X.Y.x` | The last public RC or release of the `X.Y` line.                                          |
+
+A release line is named `X.Y.x`
+because one branch serves every patch release of that line (`X.Y.0`, `X.Y.1`, `X.Y.2`, ...).
+The `/` groups branches hierarchically,
+so tools can filter them and protection rules can target `release/*` and `staging/*`.
+
+## Principles
+
+- **Releases are merged back into `develop`, never cherry-picked or rebased onto it.**
+  Cherry-picked and rebased commits get new hashes,
+  so Git can't tell that `develop` already has them.
+  Future merges then replay them and produce artificial conflicts,
+  and it's hard to verify that every fix actually reached `develop`.
+  Merging keeps a single history:
+  Git knows exactly which release commits `develop` contains,
+  and no fix is left behind.
+- **Branches only move forward.**
+  `develop`, `staging/X.Y.x`, and `release/X.Y.x` are never rewritten.
+- **Cherry-picking only goes from `develop` to a staging branch**,
+  for fixes that must get into a release after the code freeze
+  (see [Emergency Fixes From `develop`](#emergency-fixes-from-develop)).
+- **Security fixes are prepared privately and published with the release that contains them**,
+  so vulnerabilities are not disclosed prematurely.
+
+## Release Lifecycle
+
+This diagram shows a major-minor release and its first patch release.
+The staging and release branches are drawn as one line.
+
+```text
+develop                            staging/X.Y.x & release/X.Y.x
+   │
+   ├── Tag: X.Y.0-b1
+   ├── Tag: X.Y.0-bN
+   ├── Tag: X.Y.0-rc1 ───────────────┐ (branches created)
+   │                                 │
+   │  (development continues)        ├── Fixes
+   │                                 ├── Tag: X.Y.0-rcN
+   │                                 ├── Tag: X.Y.0 (final)
+   ◀──── (merge) ────────────────────┤
+   │                                 ├── Fixes
+   │                                 ├── Tag: X.Y.1-rcN
+   │                                 ├── Tag: X.Y.1 (final)
+   ◀──── (merge) ────────────────────┤
+   │
+   ▼
+```
+
+### Betas, First RC & Branching
+
+> [!NOTE]
+> This phase applies only to a new major-minor release (e.g., `X.Y.0`).
+> Patch releases work on the existing branches of the line.
+
+1. **Betas:** All beta versions (e.g., `X.Y.0-b1`) are built and tagged directly on `develop`.
+2. **First RC:** We release the first RC (`X.Y.0-rc1`)
+   once everything that should be included in the release has been merged.
+3. **Branches:** `staging/X.Y.x` and `release/X.Y.x` are created from `develop`
+   at the commit tagged `X.Y.0-rc1`.
+   The first RC also kicks off the QE process.
+4. **Code freeze:** No new features or unrelated changes are pulled from `develop`
+   into `staging/X.Y.x` or `release/X.Y.x`.
+   Only critical stabilization fixes go into the line.
+5. **No large changes on `develop`:** Until `X.Y.0` is [merged back](#merging-back-into-develop),
+   large changes (e.g., big refactors, moving or renaming many files, mass reformatting)
+   are not merged into `develop`,
+   so that fixes on the line and the merge back don't run into conflicts.
+
+### Release Candidates
+
+1. Fixes are developed against `staging/X.Y.x`.
+2. When ready, a new RC is created on `staging/X.Y.x`,
+   and `release/X.Y.x` is fast-forwarded to it.
+
+RCs that contain unpublished security fixes are not published,
+and don't touch the public branches.
+
+RCs are not merged back into `develop`:
+`X.Y.0-rc1` is tagged on `develop` itself,
+and all later changes reach `develop` with the [final release](#final-release).
+
+### Final Release
+
+Security fixes become public as soon as they reach the public repo,
+so these steps happen only once the release is ready to be published,
+one right after the other.
+
+1. Unpublished security fixes, if any, are merged into `staging/X.Y.x`.
+2. `release/X.Y.x` is fast-forwarded to `staging/X.Y.x`,
+   and the release is tagged on it.
+3. The release is immediately [merged back into `develop`](#merging-back-into-develop).
+   For a major-minor release, this lifts the freeze on large changes in `develop`.
+
+### Merging Back Into `develop`
+
+The merge back is a regular PR into `develop`
+whose branch contains a real merge commit of the release tag:
+
+1. Create a branch from `develop`, run `git merge --no-ff <tag>`, and resolve any conflicts.
+2. Once the PR is approved, `develop` is fast-forwarded to the PR branch,
+   so the merge commit lands as it is.
+   Never squash or rebase it.
+   Never add it to the merge queue either: the queue squashes PRs, which would drop the merge commit.
+3. If `develop` moves while the PR is open, redo the merge on top of the new `develop`.
+
+After the merge, `git log develop..<tag>` must be empty.
+
+## Special Cases
+
+### Emergency Fixes From `develop`
+
+If a commit was merged to `develop`
+and needs to be included in a release after the code freeze:
+
+1. Create a PR that cherry-picks the commit onto `staging/X.Y.x`.
+2. Leave `develop` as it is, with no reverts.
+3. Follow the [release candidates](#release-candidates) process as usual.
+
+When the release is later merged back into `develop`,
+both sides already contain the same change,
+so the merge usually resolves it cleanly or with a trivial conflict.
+From Git's perspective, the cherry-picked commit then becomes part of `develop` too.
+
+### Several Supported Lines
+
+When a fix must ship in more than one supported line (e.g., `X.Y` and `X.(Y+1)`),
+the lines are merged upwards rather than cherry-picked between:
+
+1. The fix goes into the oldest line first.
+2. After that line's release,
+   its `release/X.Y.x` is merged into the staging branch of the next newer line,
+   and so on up to the newest line.
+3. The newest line is merged back into `develop` as usual.
+
+This way every newer line, and eventually `develop`, contains the history of the older lines.

bin/check-nix-store-refs.sh

@@ -0,0 +1,111 @@
+#!/usr/bin/env bash
+# Fail if a binary under <path> records a /nix/store path it resolves at run
+# time. See docs/build/nix.md#prebuilt-packages for why that matters.
+#
+# <path> is a file or a directory. macOS: nothing may reference the store, so
+# point it at whole trees. Linux: the toolchain always writes the store into
+# PT_INTERP and RUNPATH, so only at what cmake/PatchNixBinary.cmake retargets.
+#
+# Only Mach-O / ELF is inspected. Static archives hold store paths in debug info
+# alone; the scripts in a Conan cache are all git hook samples and autotools
+# scratch, 36 false positives to 0 real.
+#
+# Usage: bin/check-nix-store-refs.sh <path>
+
+set -euo pipefail
+
+if [ "$#" -ne 1 ]; then
+    echo "usage: $0 <path>" >&2
+    exit 2
+fi
+
+if [ ! -e "$1" ]; then
+    echo "$0: no such path: $1" >&2
+    exit 2
+fi
+
+case "$(uname -s)" in
+    Darwin)
+        format=Mach-O
+        recorded_paths=macho_recorded_paths
+        tool=otool
+        ;;
+    Linux)
+        format=ELF
+        recorded_paths=elf_recorded_paths
+        tool=readelf
+        ;;
+    *)
+        echo "Unsupported OS - skipping the Nix store reference check."
+        exit 0
+        ;;
+esac
+
+# `pipefail` would catch this too, but only as a bare nonzero exit.
+if ! command -v "${tool}" >/dev/null; then
+    echo "$0: ${tool} not found; cannot inspect binaries" >&2
+    exit 2
+fi
+
+# Both list what the file records. `ldd` would answer what this machine resolves
+# now, which is wrong both ways: store paths for a correctly patched binary,
+# silence for a store RUNPATH that resolves nowhere.
+
+# `name` covers LC_ID_DYLIB and LC_LOAD*_DYLIB, `path` covers LC_RPATH.
+macho_recorded_paths() {
+    otool -l "$1" | sed -nE 's#^ *(name|path) ([^ ]*).*#\2#p'
+}
+
+# RPATH and RUNPATH are colon-separated.
+elf_recorded_paths() {
+    readelf -ldW "$1" |
+        sed -nE \
+            -e 's#.*program interpreter: ([^]]*)\].*#\1#p' \
+            -e 's#.*\((RPATH|RUNPATH|NEEDED)\).*\[([^]]*)\].*#\2#p' |
+        tr ':' '\n'
+}
+
+checked=0
+skipped=0
+leaked=0
+
+while IFS= read -r file; do
+    case "$(file -b "${file}" 2>/dev/null)" in
+        *"${format}"*) ;;
+        *)
+            skipped=$((skipped + 1))
+            continue
+            ;;
+    esac
+    checked=$((checked + 1))
+
+    # Filter after extracting, or a search path starting elsewhere ($ORIGIN)
+    # hides the rest. `sed` not `grep`: grep calls "no matches" a failure, and
+    # the `|| true` that would need masks a broken pipeline too.
+    refs="$("${recorded_paths}" "${file}" | sed -n '\#^/nix/store/#p' | sort -u)"
+    if [ -n "${refs}" ]; then
+        leaked=$((leaked + 1))
+        echo "::error file=${file}::references the Nix store at run time"
+        echo "${file}"
+        echo "${refs}" | sed 's/^/    /'
+    fi
+done < <(find "$1" -type f \( -perm -u+x -o -name '*.dylib' -o -name '*.so*' \))
+
+echo "$1: checked ${checked}, skipped ${skipped}, ${leaked} with Nix store references."
+
+if [ "${leaked}" -ne 0 ]; then
+    cat >&2 <<'EOF'
+
+Fixes, in order of preference:
+  - A Conan package built before this check existed: drop it
+    (`conan remove '<name>/*'`) and rebuild.
+  - A binary that should have been retargeted to the system loader: check that
+    cmake/PatchNixBinary.cmake ran for it.
+  - Link the macOS system library instead of the Nix one - see
+    libresolvSystemStub in nix/darwin.nix.
+  - No system library exists (libstdc++): link it statically.
+  - None of the above: pin the toolchain into the package ID, following
+    `user.package:libc_version` in conan/profiles/ci.
+EOF
+    exit 1
+fi

bin/check-tools.sh

@@ -15,23 +15,46 @@
 #   - Windows: the core build tools only (CMake, Conan, Git, Python).
 #              MSVC is expected to be provided separately and is not checked here.
 #
-# Some tools (clang-format, doxygen, gcovr, gh, git-cliff, gpg, pre-commit,
-# run-clang-tidy) are present in our Linux CI images and in local development
-# setups, but not in the macOS CI environment. They are checked everywhere
-# except when running in CI on macOS.
+# Some tools (clang-format, clang-tidy, doxygen, gcovr, gh, git-cliff, gpg,
+# pre-commit, run-clang-tidy) are present in our Linux CI images and in local
+# development setups, but not in the macOS CI environment. They are checked
+# everywhere except when running in CI on macOS.
+#
+# Tools that Nix also exposes under a version-suffixed name (`clang-tidy-22`,
+# `g++-15`, ...) are probed under both names: a suffixed name can break while
+# the plain one still works (see mkVersionedToolLinks in nix/packages.nix).
+#
+# Tools scoped to a single dev shell rather than to commonPackages are checked
+# only in that shell, keyed off XRPL_DEVSHELL.
 #
 # Environment variables:
 #   CI                      if set, skip the tools above when on macOS.
 #   CHECK_TOOLS_SKIP_CLONE  if set, skip the git-over-HTTPS connectivity check.
+#   XRPL_DEVSHELL           active dev shell; selects shell-specific tools.
 
 set -uo pipefail
 
+# Version suffixes of the Nix tool links, tracking nix/packages.nix.
+gcc_version=15
+llvm_version=22
+
 missing=()
 checked=0
 
+# tool_path <name>
+# Fully resolved path of a tool, so the snapshots record which derivation
+# provides it. Prints nothing when it isn't on PATH.
+tool_path() {
+    local path
+    path="$(command -v "$1" 2>/dev/null)" || return 0
+    readlink -f "${path}" 2>/dev/null || printf '%s' "${path}"
+}
+
 # check <name> [probe-command...]
-# Runs the probe (default: "<name> --version") quietly. Records <name> as
-# missing if the command is not found or exits non-zero.
+# Runs the probe (default: "<name> --version"), capturing both stdout and
+# stderr, and prints three lines: the status and name, the first non-blank line
+# of the probe output (its version, or the error when it failed), and the tool's
+# resolved path. Records <name> as missing if it is not found or exits non-zero.
 check() {
     local name="$1"
     shift
@@ -40,14 +63,18 @@ check() {
         probe=("${name}" --version)
     fi
 
-    echo "Checking ${name}..."
     checked=$((checked + 1))
-    if "${probe[@]}" | head -n 1; then
-        printf '  [ ok ] %s\n' "${name}"
+    local output version path
+    path="$(tool_path "${name}")"
+    if output="$("${probe[@]}" 2>&1)"; then
+        printf '  ✅ %s\n' "${name}"
     else
-        printf '  [MISS] %s\n' "${name}"
+        printf '  ❌ %s\n' "${name}"
         missing+=("${name}")
     fi
+    version="$(printf '%s\n' "${output}" | grep -m1 '[^[:space:]]' || true)"
+    printf '     %s\n' "${version:-(no output)}"
+    printf '     %s\n' "${path:-(not found)}"
 }
 
 case "$(uname -s)" in
@@ -79,41 +106,86 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
     echo "Development tooling:"
     check ccache
     check clang
+    check "clang-${llvm_version}"
     check clang++
+    check "clang++-${llvm_version}"
     check ClangBuildAnalyzer
     check curl
     check file
     check less
     check make
-    check netstat which netstat
+    # net-tools netstat reports "net-tools X.Y"; macOS ships BSD netstat with no
+    # version flag, so fall back to a presence marker there.
+    check netstat sh -c 'command -v netstat >/dev/null && { netstat --version 2>&1 | grep -m1 -oE "net-tools [0-9.]+" || echo present; }'
     check ninja
-    check perl
+    check perl perl -e 'print "$^V\n"'
     check pkg-config
     check vim
+    check zip bash -c 'zip --version 2>&1 | grep -m1 -oE "Zip [0-9.]+"'
 
     # These tools are present in our Linux CI images and in local development
     # setups, but not in the macOS CI environment. So check them everywhere
     # except when running in CI on macOS.
     if [ "${os}" = "linux" ] || [ -z "${CI:-}" ]; then
+        check clang-apply-replacements
+        check "clang-apply-replacements-${llvm_version}"
         check clang-format
+        check "clang-format-${llvm_version}"
+        # clang-tidy leads --version with the LLVM banner, not the version.
+        tidy_probe="--version | grep -m1 -oE 'LLVM version [0-9.]+'"
+        check clang-tidy sh -c "clang-tidy ${tidy_probe}"
+        check "clang-tidy-${llvm_version}" sh -c "clang-tidy-${llvm_version} ${tidy_probe}"
+        check dot
         check doxygen
         check gcovr
         check gh
         check git-cliff
+        check git-lfs
         check gpg
         # pre-commit, or its alternative implementation prek
         check pre-commit sh -c 'pre-commit --version || prek --version'
         check run-clang-tidy run-clang-tidy --help
+        check "run-clang-tidy-${llvm_version}" "run-clang-tidy-${llvm_version}" --help
     fi
 fi
 
+# Rust toolchain. Part of the Nix commonPackages, so available on both Linux
+# and macOS. The cargo plugins are invoked through cargo (`cargo <sub>`), which
+# resolves the matching `cargo-<sub>` binary on PATH; `--version` is offline and
+# does not need a Cargo project.
+if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
+    echo
+    echo "Rust toolchain:"
+    check cargo
+    check cargo-audit cargo audit --version
+    check cargo-llvm-cov cargo llvm-cov --version
+    check cargo-nextest cargo nextest --version
+    check clippy-driver
+    check rust-analyzer
+    check rust-nightly rust-nightly run rustc --version
+    check rustc
+    check rustfmt
+fi
+
+# Lean4 is in the formal-verification shell only, not in commonPackages.
+if [ "${XRPL_DEVSHELL:-}" = "formal-verification" ]; then
+    echo
+    echo "Formal verification toolchain:"
+    check lean
+    check lake
+fi
+
 # GCC is the default compiler on Linux. macOS uses the system Apple Clang
 # instead, so GCC/g++/gcov are not expected there.
 if [ "${os}" = "linux" ]; then
     echo
     echo "GCC toolchain:"
     check gcc
+    check "gcc-${gcc_version}"
     check g++
+    check "g++-${gcc_version}"
+    check cpp
+    check "cpp-${gcc_version}"
     check gcov
 
     echo
@@ -138,9 +210,9 @@ else
     checked=$((checked + 1))
     tmp_clone="$(mktemp -d)"
     if git clone --depth 1 https://github.com/XRPLF/actions.git "${tmp_clone}/actions" >/dev/null 2>&1; then
-        printf '  [ ok ] git clone over HTTPS\n'
+        printf '  ✅ git clone over HTTPS\n'
     else
-        printf '  [MISS] git clone over HTTPS\n'
+        printf '  ❌ git clone over HTTPS\n'
         missing+=("git-https-clone")
     fi
     rm -rf "${tmp_clone}"
@@ -148,9 +220,9 @@ fi
 
 echo
 if [ "${#missing[@]}" -eq 0 ]; then
-    echo "All ${checked} checked tools are present and runnable."
+    echo "✅ All ${checked} checked tools are present and runnable."
 else
-    echo "Missing or non-functional tools (${#missing[@]} of ${checked}):" >&2
+    echo "❌ Missing or non-functional tools (${#missing[@]} of ${checked}):" >&2
     for tool in "${missing[@]}"; do
         echo "  - ${tool}" >&2
     done

bin/filter-clang-tidy.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+"""
+Reduce run-clang-tidy output to its unique errors.
+
+It does two things:
+
+  1. Filters the raw output down to diagnostics and their source-context lines
+     (the indented "  103 | ..." / "      | ^" lines clang-tidy prints),
+     matching the "path:line:col: error:" diagnostic shape.
+
+  2. Deduplicates. The same diagnostic in a header is reported once per
+     translation unit that includes it, so identical error blocks are collapsed
+     to their first occurrence.
+
+An "error block" is an "error:" line together with the indented context lines
+and any "note:" lines that follow it (up to the next "error:" line). Blocks are
+compared as a whole, so an error stays attached to its own context, and
+first-occurrence order is preserved.
+
+The deduplicated output goes to stdout; a summary of unique error counts per
+check is printed to stderr.
+
+Usage:
+  bin/filter-clang-tidy.py [INPUT_FILE]            # read from file, or
+  run-clang-tidy ... | bin/filter-clang-tidy.py    # read from stdin
+"""
+
+import re
+import sys
+from collections import Counter
+
+# A clang-tidy diagnostic line looks like "path:line:col: error: msg [check]".
+# Matching on that shape (rather than a loose "error" substring) avoids treating
+# progress lines whose paths contain "error" as diagnostics, e.g.
+#   [284/850][0.7s] /nix/.../clang-tidy ... src/.../error.cpp
+DIAG_RE = re.compile(r":\d+:\d+: (?:error|warning|note):")
+ERROR_RE = re.compile(r":\d+:\d+: error:")
+CHECK_RE = re.compile(r" error: .*\[([^\],]+)")
+
+
+def filter_and_dedup(lines: list[str]) -> list[str]:
+    """Keep diagnostics with their context, then drop duplicate error blocks."""
+    blocks: list[str] = []
+    seen: set[str] = set()
+    current: list[str] = []
+
+    def flush() -> None:
+        if not current:
+            return
+        block = "".join(current)
+        if block not in seen:
+            seen.add(block)
+            blocks.append(block)
+
+    for line in lines:
+        # Keep only diagnostics and their indented source-context lines; drop
+        # progress/status output and blank lines.
+        if not (DIAG_RE.search(line) or line[:1] in (" ", "\t")):
+            continue
+        # An "error:" line starts a new block; its context and any following
+        # "note:" lines (and their context) belong to it.
+        if ERROR_RE.search(line):
+            flush()
+            current = []
+        current.append(line)
+    flush()
+
+    return blocks
+
+
+def summarize(blocks: list[str]) -> Counter[str]:
+    """Count unique errors per check name (e.g. "bugprone-branch-clone")."""
+    counts: Counter[str] = Counter()
+    for block in blocks:
+        # The error line is the first line of the block.
+        match = CHECK_RE.search(block.splitlines()[0])
+        if match:
+            counts[match.group(1)] += 1
+    return counts
+
+
+def main() -> int:
+    if len(sys.argv) > 1 and sys.argv[1] != "-":
+        with open(sys.argv[1], encoding="utf-8") as f:
+            lines = f.readlines()
+    else:
+        lines = sys.stdin.readlines()
+
+    blocks = filter_and_dedup(lines)
+    # Blank line between blocks so distinct errors are easy to tell apart.
+    sys.stdout.write("\n".join(blocks))
+
+    print("\nUnique errors per check:", file=sys.stderr)
+    for check, count in summarize(blocks).most_common():
+        print(f"{count:>4} {check}", file=sys.stderr)
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/git/update-version.sh

@@ -1,56 +0,0 @@
-#!/bin/bash
-
-if [[ $# -ne 3 || "$1" == "--help" || "$1" = "-h" ]]; then
-    name=$(basename $0)
-    cat <<-USAGE
-    Usage: $name workbranch base/branch version
-
-    * workbranch will be created locally from base/branch. If it exists,
-        it will be reused, so make sure you don't overwrite any work.
-    * base/branch may be specified as user:branch to allow easy copying
-        from Github PRs.
-USAGE
-    exit 0
-fi
-
-work="$1"
-shift
-
-base=$(echo "$1" | sed "s/:/\//")
-shift
-
-version=$1
-shift
-
-set -e
-
-git fetch upstreams
-
-git checkout -B "${work}" --no-track "${base}"
-
-push=$(git rev-parse --abbrev-ref --symbolic-full-name '@{push}' \
-    2>/dev/null) || true
-if [[ "${push}" != "" ]]; then
-    echo "Warning: ${push} may already exist."
-fi
-
-build=$(find -name BuildInfo.cpp)
-sed 's/\(^.*versionString =\).*$/\1 "'${version}'"/' ${build} >version.cpp &&
-    diff "${build}" version.cpp && exit 1 ||
-    mv -vi version.cpp ${build}
-
-git diff
-
-git add ${build}
-
-git commit -S -m "Set version to ${version}"
-
-git log --oneline --first-parent ${base}^..
-
-cat <<PUSH
-
--------------------------------------------------------------------
-This script will not push. Verify everything is correct, then push
-to your repo, and create a PR as described in CONTRIBUTING.md.
--------------------------------------------------------------------
-PUSH

bin/install-packaging-tools.sh

@@ -22,23 +22,41 @@ case "${ID}" in
         ;;
 esac
 
+# Packaging runs in a vanilla distro image, so the tooling comes from the distro's
+# archive rather than from nixpkgs:
+#
+#   - debhelper and dpkg-dev build the DEB, and lintian checks it
+#   - binutils gives debian/rules the readelf its glibc-floor check runs; it
+#     already arrives via dpkg-dev, but that tool is called directly
+#   - rpm-build builds the RPM, with systemd-rpm-macros and redhat-rpm-config
+#     supplying the systemd and find-debuginfo macros the spec uses
+#   - rpm-sign and gnupg2 sign the built RPM
+#   - python3 runs the packaging scripts
+#   - git gives build_pkg.py the commit timestamp it stamps files with
+#   - ca-certificates lets git and the packaging scripts verify TLS
 function install() {
     case "${ID}" in
         debian | ubuntu)
             apt-get update -y
             apt-get install -y --no-install-recommends \
+                binutils \
                 ca-certificates \
                 debhelper \
                 debhelper-compat \
                 dpkg-dev \
-                git
+                git \
+                lintian \
+                python3
             ;;
 
         rhel | centos | rocky | almalinux)
             dnf install -y --setopt=install_weak_deps=False \
                 git \
-                rpm-build \
+                gnupg2 \
+                python3 \
                 redhat-rpm-config \
+                rpm-build \
+                rpm-sign \
                 systemd-rpm-macros
             ;;
     esac

bin/pre-commit/Dockerfile

@@ -0,0 +1,55 @@
+ARG BASE_IMAGE=ubuntu:26.04
+
+FROM ${BASE_IMAGE}
+
+SHELL ["/bin/bash", "-e", "-o", "pipefail", "-c"]
+ENTRYPOINT ["/bin/bash"]
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN <<EOF
+pkgs=()
+pkgs+=(curl)         # Required to install nix.
+pkgs+=(doxygen)      # Needed for Clio's check-doxygen-docs.sh.
+pkgs+=(git)          # Required for prepare-runner.
+pkgs+=(libatomic1)   # Required to run pre-commit provided `node`.
+pkgs+=(python3)      # Python 3 interpreter.
+pkgs+=(python3-pip)  # Package manager for Python applications.
+pkgs+=(xz-utils)     # Required to install nix
+
+apt-get update
+apt-get install -y --no-install-recommends "${pkgs[@]}"
+apt-get clean
+rm -rf /var/lib/apt/lists/*
+EOF
+
+ARG PRE_COMMIT_VERSION=4.6.0
+RUN pip install --no-cache --break-system-packages \
+    pre-commit==${PRE_COMMIT_VERSION}
+
+RUN sh <(curl --proto '=https' --tlsv1.2 -L https://nixos.org/nix/install) --daemon --yes
+
+# Add nix to PATH and set NIX environment variables,
+# so nix is available in all shells including non-interactive shells (e.g., GitHub Actions).
+ENV PATH="/nix/var/nix/profiles/default/bin:${PATH}"
+ENV NIX_PROFILES="/nix/var/nix/profiles/default"
+ENV NIX_SSL_CERT_FILE="/nix/var/nix/profiles/default/etc/ssl/certs/ca-bundle.crt"
+
+# Verify nix installation
+RUN nix --version
+
+ENV RUSTUP_HOME="/opt/rust/rustup"
+ENV CARGO_HOME="/opt/rust/cargo"
+ENV PATH="/opt/rust/cargo/bin:${PATH}"
+
+WORKDIR /tmp
+COPY rust-toolchain.toml /tmp/rust-toolchain.toml
+RUN <<EOF
+curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
+    | sh -s -- -y --no-modify-path --profile minimal --default-toolchain none
+rustup toolchain install
+rustup show
+cargo fmt --version
+EOF
+
+WORKDIR /

bin/pre-commit/check_doxygen_style.py

@@ -0,0 +1,440 @@
+#!/usr/bin/env python3
+"""
+Check C++ Doxygen comment style.
+
+Enforces the house convention for documentation comments:
+
+  * Use ``/** ... */`` blocks, not ``///``, ``//!`` or ``/*! ... */``; a plain
+    ``/* ... */`` that contains Doxygen commands is a doc comment missing its
+    second star. Trailing member-after comments use ``///<`` (not ``//!<``,
+    ``/*!< ... */`` or ``/**< ... */`` -- the block forms get reflowed and
+    mis-attached by clang-format on packed enum values, the line form does not).
+  * ``/**`` sits alone on its line; the closing ``*/`` sits alone on its line.
+  * Every content line is prefixed with `` * `` (no bare-indented continuation).
+  * The first content line is flush (not over-indented).
+  * Doxygen commands use the ``@cmd`` form, not ``\\cmd``.
+  * Use ``@return`` / ``@throws`` rather than prose ``Returns:`` / ``Throws:``.
+  * A plain ``//`` comment carrying a block-level ``@command`` (``@param``,
+    ``@return``, ``@see``, ...) is documentation and must be a ``/** ... */``
+    block (Doxygen ignores ``//``).
+  * Use canonical command spellings: ``@return`` (not ``@returns``),
+    ``@throws`` (not ``@throw``), ``@see`` (not ``@sa``).
+  * Order block tags ``@tparam`` -> ``@param`` -> ``@return``. (Whether
+    ``@param`` order matches the signature is not checked here -- too fragile to
+    parse; Doxygen's WARN_IF_DOC_ERROR covers name mismatches.)
+  * One-liners are expanded to three lines, EXCEPT bare markers ``@{`` / ``@}``
+    / ``@cond [label]`` / ``@endcond`` / ``@file [name]`` which stay on one line.
+
+Left intentionally alone (recognized, valid Doxygen that is not this style's
+concern):
+
+  * ``///<`` trailing "member-after" comments (the house form).
+  * Divider lines made only of slashes (``//////////``).
+  * Plain ``/* ... */`` (non-Doxygen) comments.
+
+Usage:
+    check_doxygen_style.py [FILE ...]      # explicit files
+    check_doxygen_style.py                 # default: src/ and include/ trees
+
+Exit status is non-zero if any violation is found.
+"""
+
+import argparse
+import re
+import sys
+from collections.abc import Iterable, Iterator
+from dataclasses import dataclass
+from enum import Enum
+from pathlib import Path
+
+
+class Category(Enum):
+    """A kind of style violation: a printed ``label`` and its ``description``.
+
+    The description is the default message; a few categories whose wording
+    depends on the offending text (see ``Finding.detail``) override it.
+    """
+
+    def __init__(self, label: str, description: str) -> None:
+        self.label = label
+        self.description = description
+
+    BACKSLASH_COMMAND = ("backslash-command", "use the @cmd form, not \\cmd")
+    WRONG_COMMAND = ("wrong-command", "use the canonical command spelling")
+    TRIPLE_SLASH = ("triple-slash", "use a /** ... */ block instead of ///")
+    QT_MEMBER = ("qt-member", "use ///< instead of //!<")
+    QT_LINE = ("qt-line", "use a /** ... */ block instead of //!")
+    BLOCK_MEMBER = ("block-member", "use ///< instead of /**<")
+    QT_BLOCK_MEMBER = ("qt-block-member", "use ///< instead of /*!<")
+    DOC_IN_LINE_COMMENT = (
+        "doc-in-line-comment",
+        "use a /** ... */ block for documentation, not //",
+    )
+    QT_COMMENT = ("qt-comment", "use /** instead of /*!")
+    SINGLE_LINE_BLOCK = (
+        "single-line-block",
+        "expand one-line /** ... */ to a multi-line block "
+        "(markers @{ @} @cond @endcond @file may stay)",
+    )
+    TEXT_ON_OPENER = ("text-on-opener", "move text off the /** opener line")
+    BARE_CONTINUATION = ("bare-continuation", 'prefix continuation lines with " * "')
+    OVER_INDENTED = ("over-indented", "first content line is over-indented")
+    OVER_INDENTED_TAG = (
+        "over-indented-tag",
+        'Doxygen tag over-indented; use a single space after "*"',
+    )
+    COMBINED_MARKER = (
+        "combined-marker",
+        "scope marker @{ / @} should be its own single-line /** @{ */ block",
+    )
+    PROSE_LABEL = ("prose-label", "use a Doxygen tag instead of a prose label")
+    CONTENT_ON_CLOSER = ("content-on-closer", "move content off the closing */ line")
+    PLAIN_BLOCK_DOC = (
+        "plain-block-doc",
+        "documentation comment must open with /** not /*",
+    )
+    TAG_ORDER = (
+        "tag-order",
+        "block tags out of order; expected @tparam, then @param, then @return",
+    )
+
+
+@dataclass(frozen=True)
+class Finding:
+    """A single style violation at a 1-based line number.
+
+    ``detail`` overrides the category's default description when the message
+    depends on the offending text (e.g. which command was misspelled).
+    """
+
+    line: int
+    category: Category
+    detail: str | None = None
+
+    @property
+    def message(self) -> str:
+        return self.detail if self.detail is not None else self.category.description
+
+
+DEFAULT_ROOTS = ("src", "include")
+EXTS = {".h", ".hpp", ".cpp", ".ipp", ".cxx", ".cc"}
+
+# Every Doxygen command we recognize when written with a backslash (\cmd).
+_ALL_COMMANDS = (
+    "brief|param|tparam|return|returns|retval|note|warning|pre|post|see|sa|ref|"
+    "throw|throws|exception|deprecated|details|code|endcode|verbatim|endverbatim|"
+    "li|arg|c|internal|since|todo|attention|remark|remarks|ingroup|defgroup"
+)
+# Block-level tags whose over-indentation we flag inside a block body.
+_BLOCK_TAGS = (
+    "param|tparam|returns?|retval|brief|throws?|note|warning|"
+    "pre|post|see|sa|details|deprecated"
+)
+# Tags that, appearing anywhere in a comment, mark it as documentation.
+_ANY_DOC_TAGS = (
+    "param|tparam|returns?|retval|brief|throws?|note|warning|pre|post|see|sa"
+)
+# Tags that make a plain // comment a mis-styled doc comment.
+_LINE_DOC_TAGS = "brief|param|tparam|returns?|retval|throws?|note|see|pre|post"
+
+# \cmd that should be @cmd.
+RE_BACKSLASH_CMD = re.compile(r"\\(" + _ALL_COMMANDS + r")\b")
+# Bare markers that may legitimately stay on a single line.
+RE_MARKER = re.compile(r"^@(\{|\}|cond(\s.*)?|endcond|file(\s.*)?)$")
+# Prose section labels that should be Doxygen tags.
+RE_PROSE_LABEL = re.compile(r"^\*\s(Returns|Throws|Exceptions):\s*$")
+# An over-indented block tag: "*" followed by 2+ spaces then the tag.
+RE_OVERINDENTED_TAG = re.compile(r"^\*\s{2,}@(" + _BLOCK_TAGS + r")\b")
+# Any documentation tag (used to spot a doc comment hiding in a plain /* */).
+RE_ANY_DOC_TAG = re.compile(r"@(" + _ANY_DOC_TAGS + r")\b")
+# A documentation tag inside a // comment.
+RE_LINE_DOC_TAG = re.compile(r"@(" + _LINE_DOC_TAGS + r")\b")
+# Order-relevant tags, for the @tparam -> @param -> @return ordering check.
+RE_ORDER_TAG = re.compile(r"^\*\s*@(param|tparam|returns?|retval)\b")
+# First content line indented by 2+ spaces after the "*".
+RE_FIRST_OVERINDENT = re.compile(r"^\s*\*\s{2,}\S")
+# A scope marker @{ / @} sharing a comment with other text.
+RE_COMBINED_MARKER = re.compile(r"^\*\s*@[{}]\s*$")
+
+# Non-canonical command spellings -> the house spelling (bare command names).
+# Used both to flag a wrong @form and to suggest the right @form for a \wrong.
+CANONICAL_COMMAND = {"returns": "return", "throw": "throws", "sa": "see"}
+WRONG_SPELLINGS = [
+    (re.compile(rf"@{wrong}\b"), f"@{right}")
+    for wrong, right in CANONICAL_COMMAND.items()
+]
+
+# Order block tags should appear in; a body out of this order is a violation.
+EXPECTED_TAG_ORDER = ("tparam", "param", "return")
+
+
+def is_doxy_open(stripped: str) -> bool:
+    """True for a line-start Doxygen block opener we should normalize."""
+    if stripped.startswith("/*!"):  # Qt-style Doxygen
+        return not stripped.startswith("/*!<")  # member-after, leave inline
+    return (
+        stripped.startswith("/**")
+        and not stripped.startswith("/***")
+        and not stripped.startswith("/**/")
+        and not stripped.startswith("/**<")
+    )
+
+
+def _flag_commands(raw_line: str, stripped: str, index: int) -> list[Finding]:
+    """Flag \\cmd and misspelled @cmd on a comment line (opener, body, or closer)."""
+    if not stripped.startswith(("*", "//", "/*")):
+        return []
+    findings: list[Finding] = []
+    backslash = RE_BACKSLASH_CMD.search(raw_line)
+    if backslash:
+        command = backslash.group(1)
+        canonical = CANONICAL_COMMAND.get(command, command)
+        findings.append(
+            Finding(
+                index + 1,
+                Category.BACKSLASH_COMMAND,
+                f"use @{canonical} instead of \\{command}",
+            )
+        )
+    for pattern, replacement in WRONG_SPELLINGS:
+        wrong = pattern.search(raw_line)
+        if wrong:
+            findings.append(
+                Finding(
+                    index + 1,
+                    Category.WRONG_COMMAND,
+                    f"use {replacement} instead of {wrong.group(0)}",
+                )
+            )
+    return findings
+
+
+def _flag_line_comment(raw_line: str, stripped: str, index: int) -> Finding | None:
+    """Return the finding for a single-line comment form (///, //!, /**<, ...), else None."""
+    if stripped.startswith("///") and not stripped.startswith(("////", "///<")):
+        return Finding(index + 1, Category.TRIPLE_SLASH)
+    if "//!<" in raw_line:
+        return Finding(index + 1, Category.QT_MEMBER)
+    if stripped.startswith("//!"):
+        return Finding(index + 1, Category.QT_LINE)
+    if "/**<" in raw_line:
+        return Finding(index + 1, Category.BLOCK_MEMBER)
+    if "/*!<" in raw_line:
+        return Finding(index + 1, Category.QT_BLOCK_MEMBER)
+    if stripped.startswith("//") and RE_LINE_DOC_TAG.search(stripped):
+        return Finding(index + 1, Category.DOC_IN_LINE_COMMENT)
+    return None
+
+
+def _flag_single_line_block(stripped: str, line_no: int, is_qt: bool) -> list[Finding]:
+    """Findings for a whole /** ... */ or /*! ... */ block on one line."""
+    inner = re.sub(r"^/\*[*!]", "", stripped)
+    inner = re.sub(r"\*/\s*$", "", inner).strip()
+    findings: list[Finding] = []
+    if is_qt:
+        findings.append(Finding(line_no, Category.QT_COMMENT))
+    if inner and not RE_MARKER.match(inner):
+        findings.append(Finding(line_no, Category.SINGLE_LINE_BLOCK))
+    return findings
+
+
+def _canonical_order_tag(body: str) -> str | None:
+    """The order-relevant tag (tparam/param/return) a body line opens with, if any."""
+    match = RE_ORDER_TAG.match(body)
+    if match is None:
+        return None
+    command = match.group(1)
+    return "return" if command in ("return", "returns", "retval") else command
+
+
+def _flag_body_line(
+    body_line: str, line_no: int, is_first_content: bool
+) -> list[Finding]:
+    """Findings for one interior line of a multi-line block."""
+    body = body_line.strip()
+    findings: list[Finding] = []
+    if body and not body.startswith("*"):
+        findings.append(Finding(line_no, Category.BARE_CONTINUATION))
+    if body.startswith("*"):
+        if is_first_content and RE_FIRST_OVERINDENT.match(body_line):
+            findings.append(Finding(line_no, Category.OVER_INDENTED))
+        if RE_OVERINDENTED_TAG.match(body):
+            findings.append(Finding(line_no, Category.OVER_INDENTED_TAG))
+        if RE_COMBINED_MARKER.match(body):
+            findings.append(Finding(line_no, Category.COMBINED_MARKER))
+        label = RE_PROSE_LABEL.match(body)
+        if label:
+            suggested_tag = "@return" if label.group(1) == "Returns" else "@throws"
+            findings.append(
+                Finding(
+                    line_no,
+                    Category.PROSE_LABEL,
+                    f'use {suggested_tag} instead of prose "{label.group(1)}:"',
+                )
+            )
+    return findings
+
+
+def _flag_closer(closer_line: str, line_no: int) -> list[Finding]:
+    """Findings for content sharing the closing */ line."""
+    before = closer_line[: closer_line.index("*/")].strip()
+    if before and before != "*":
+        return [Finding(line_no, Category.CONTENT_ON_CLOSER)]
+    return []
+
+
+def _flag_tag_order(first_tag_line: dict[str, int]) -> list[Finding]:
+    """One finding if the present block tags are not in EXPECTED_TAG_ORDER."""
+    tag_lines = [
+        first_tag_line[tag] for tag in EXPECTED_TAG_ORDER if tag in first_tag_line
+    ]
+    if tag_lines != sorted(tag_lines):
+        return [Finding(min(tag_lines), Category.TAG_ORDER)]
+    return []
+
+
+def _flag_doxy_block(lines: list[str], start: int) -> tuple[int, list[Finding]]:
+    """Handle a /** or /*! block opening at ``start``; return (next index, findings)."""
+    raw_line = lines[start]
+    stripped = raw_line.lstrip()
+    open_pos = raw_line.index("/*")
+    is_qt = stripped.startswith("/*!")
+
+    # A whole block on one line: /** ... */.
+    if "*/" in raw_line[open_pos + 2 :]:
+        return start + 1, _flag_single_line_block(stripped, start + 1, is_qt)
+
+    # Multi-line block: opener, then scan the body to the closer.
+    findings: list[Finding] = []
+    if is_qt:
+        findings.append(Finding(start + 1, Category.QT_COMMENT))
+    if raw_line[open_pos + 3 :].strip():
+        findings.append(Finding(start + 1, Category.TEXT_ON_OPENER))
+
+    line_count = len(lines)
+    cursor = start + 1
+    is_first_content = True
+    first_tag_line: dict[str, int] = {}  # canonical tag -> 1-based first line
+    while cursor < line_count and "*/" not in lines[cursor]:
+        body_line = lines[cursor]
+        body = body_line.strip()
+        findings.extend(_flag_commands(body_line, body, cursor))
+        tag = _canonical_order_tag(body)
+        if tag is not None:
+            first_tag_line.setdefault(tag, cursor + 1)
+        findings.extend(_flag_body_line(body_line, cursor + 1, is_first_content))
+        if body.startswith("*"):
+            is_first_content = False
+        cursor += 1
+
+    if cursor < line_count:
+        closer_line = lines[cursor]
+        findings.extend(_flag_commands(closer_line, closer_line.strip(), cursor))
+        findings.extend(_flag_closer(closer_line, cursor + 1))
+    findings.extend(_flag_tag_order(first_tag_line))
+
+    return cursor + 1, findings
+
+
+def _flag_plain_block(lines: list[str], start: int) -> tuple[int, list[Finding]]:
+    """Handle a line-start plain /* ... */ block; return (next index, findings).
+
+    Only flagged when it hides a documentation command (a missing second star).
+    """
+    line_count = len(lines)
+    cursor = start
+    while cursor < line_count and "*/" not in lines[cursor]:
+        cursor += 1
+    findings: list[Finding] = []
+    # The opener (start) is command-checked by check_file; check the rest here.
+    for i in range(start + 1, min(cursor + 1, line_count)):
+        findings.extend(_flag_commands(lines[i], lines[i].strip(), i))
+    block_text = "\n".join(
+        lines[start : cursor + 1] if cursor < line_count else lines[start:]
+    )
+    if RE_ANY_DOC_TAG.search(block_text):
+        findings.append(Finding(start + 1, Category.PLAIN_BLOCK_DOC))
+    next_index = cursor + 1 if cursor < line_count else line_count
+    return next_index, findings
+
+
+def check_source(text: str) -> list[Finding]:
+    """Return all style violations found in the given source text."""
+    lines = text.split("\n")
+    findings: list[Finding] = []
+    line_count = len(lines)
+    index = 0
+    in_plain_block = False  # inside a mid-line, non-Doxygen /* ... */
+    while index < line_count:
+        raw_line = lines[index]
+        stripped = raw_line.lstrip()
+
+        # Skip the interior of a plain block opened on an earlier line.
+        if in_plain_block:
+            in_plain_block = "*/" not in raw_line
+            index += 1
+            continue
+
+        findings.extend(_flag_commands(raw_line, stripped, index))
+
+        line_finding = _flag_line_comment(raw_line, stripped, index)
+        if line_finding is not None:
+            findings.append(line_finding)
+            index += 1
+        elif is_doxy_open(stripped):
+            index, block_findings = _flag_doxy_block(lines, index)
+            findings.extend(block_findings)
+        elif stripped.startswith("/*"):
+            index, block_findings = _flag_plain_block(lines, index)
+            findings.extend(block_findings)
+        else:
+            # A /* that opens mid-line without closing starts a plain block.
+            if "/*" in raw_line and not stripped.startswith("//"):
+                if "*/" not in raw_line[raw_line.index("/*") + 2 :]:
+                    in_plain_block = True
+            index += 1
+    return findings
+
+
+def check_file(path: Path) -> list[Finding]:
+    """Return all style violations found in one file."""
+    return check_source(path.read_text(encoding="utf-8"))
+
+
+def iter_files(paths: Iterable[str]) -> Iterator[Path]:
+    """Yield every C++ source file among the given files and directories."""
+    for raw_path in paths:
+        path = Path(raw_path)
+        if path.is_dir():
+            for candidate in path.rglob("*"):
+                if candidate.is_file() and candidate.suffix in EXTS:
+                    yield candidate
+        elif path.suffix in EXTS:
+            yield path
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Check Doxygen comment style.")
+    parser.add_argument(
+        "files", nargs="*", help="files or directories (default: src/ include/)"
+    )
+    parser.add_argument(
+        "-q", "--quiet", action="store_true", help="only print the summary count"
+    )
+    args = parser.parse_args()
+    roots = args.files or [root for root in DEFAULT_ROOTS if Path(root).is_dir()]
+
+    total = 0
+    for path in sorted(set(iter_files(roots)), key=str):
+        for finding in check_file(path):
+            total += 1
+            if not args.quiet:
+                print(
+                    f"{path}:{finding.line}: {finding.category.label}: {finding.message}"
+                )
+    print(f"\n{total} doxygen-style violation(s)", file=sys.stderr)
+    return 1 if total else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/pre-commit/check_rust_coverage_attrs.py

@@ -0,0 +1,149 @@
+#!/usr/bin/env python3
+"""
+Check that Rust unit tests stay out of the coverage report.
+
+cargo-llvm-cov instruments the test code along with everything else, so a test
+module that is not excluded counts its own body as covered and inflates the
+reported number. Excluding it takes two attributes:
+
+  * every `#[cfg(test)]` module carries
+    `#[cfg_attr(coverage_nightly, coverage(off))]`;
+  * every crate root (lib.rs, main.rs) carries
+    `#![cfg_attr(coverage_nightly, feature(coverage_attribute))]`, which the
+    attribute above needs in order to compile.
+
+Both are inert outside the coverage job: cargo-llvm-cov defines
+`coverage_nightly` only when it runs on a nightly toolchain.
+
+The crate-root gate is checked even in a crate that has no tests yet, because
+that is what lets the first test module added later carry the attribute without
+a build failure. Missing it is a hard error, so it cannot go unnoticed; a
+missing `coverage(off)` fails open, which is why this check exists.
+
+Matching is on exact attribute text, which works because `cargo fmt` runs over
+the whole workspace in the hook ahead of this one: rustfmt puts every attribute
+on its own line and normalizes what is inside it, turning `#[cfg( test )]`
+and `#[cfg(test,)]` alike into `#[cfg(test)]`. So there is nothing here that
+parses Rust. The price is that a cfg this file does not spell out literally --
+`all(test, ...)`, `any(test, ...)`, `not(test)` -- is reported rather than
+classified, on the grounds that guessing at coverage semantics is how a check
+like this ends up quietly wrong.
+
+Usage: ./bin/pre-commit/check_rust_coverage_attrs.py <file1> <file2> ...
+
+Exit status is non-zero if any violation is found.
+"""
+
+import re
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+
+CRATE_ROOTS = {"lib.rs", "main.rs"}
+
+FEATURE_ATTR = "#![cfg_attr(coverage_nightly, feature(coverage_attribute))]"
+COVERAGE_OFF_ATTR = "#[cfg_attr(coverage_nightly, coverage(off))]"
+CFG_TEST_ATTR = "#[cfg(test)]"
+
+# Any other cfg that mentions `test`. String literals are blanked before this
+# runs, so `feature = "test"` does not read as the `test` cfg.
+RE_CFG_MENTIONS_TEST = re.compile(r"^#\[cfg\(.*\btest\b.*\)\]$")
+RE_STRING = re.compile(r'"(?:[^"\\]|\\.)*"')
+RE_MOD = re.compile(r"^(?:pub(?:\([^)]*\))?\s+)?mod\s+([A-Za-z_]\w*)")
+
+
+@dataclass(frozen=True)
+class Finding:
+    line: int
+    label: str
+    message: str
+
+
+def _check_module(attrs: list[str], line: int, name: str) -> list[Finding]:
+    """Findings for one module, given the attributes attached to it."""
+    if COVERAGE_OFF_ATTR in attrs:
+        return []  # excluded from coverage; which cfg gates it does not matter
+    if CFG_TEST_ATTR in attrs:
+        return [
+            Finding(
+                line,
+                "missing-coverage-off",
+                f"`mod {name}` is #[cfg(test)] but not excluded from coverage; "
+                f"add {COVERAGE_OFF_ATTR}",
+            )
+        ]
+    unclassified = [
+        attr for attr in attrs if RE_CFG_MENTIONS_TEST.match(RE_STRING.sub('""', attr))
+    ]
+    if unclassified:
+        return [
+            Finding(
+                line,
+                "unclassified-cfg",
+                f"`mod {name}` is gated on {unclassified[0]}, which this check "
+                f"cannot tell apart from a module that ships in the library; "
+                f"add {COVERAGE_OFF_ATTR} if it is test-only, or teach this "
+                f"check the cfg if it is not",
+            )
+        ]
+    return []
+
+
+def _check_test_modules(lines: list[str]) -> list[Finding]:
+    """Findings for every test module that is not excluded from coverage."""
+    findings: list[Finding] = []
+    attrs: list[str] = []
+    attrs_line = 0
+    for number, raw in enumerate(lines, start=1):
+        stripped = raw.strip()
+        # Blank lines and comments are allowed between an attribute and its item.
+        if not stripped or stripped.startswith("//"):
+            continue
+        if stripped.startswith("#["):
+            if not attrs:
+                attrs_line = number
+            attrs.append(stripped)
+            continue
+        module = RE_MOD.match(stripped)
+        if module is not None and attrs:
+            findings += _check_module(attrs, attrs_line, module.group(1))
+        attrs = []
+    return findings
+
+
+def _check_crate_root(name: str, lines: list[str]) -> list[Finding]:
+    """A finding if a crate root is missing the coverage_attribute feature gate."""
+    if name not in CRATE_ROOTS:
+        return []
+    if any(line.strip() == FEATURE_ATTR for line in lines):
+        return []
+    return [
+        Finding(
+            1,
+            "missing-feature-gate",
+            f"crate root is missing {FEATURE_ATTR}",
+        )
+    ]
+
+
+def check_source(name: str, text: str) -> list[Finding]:
+    """Findings for one file's contents; `name` is its base name (lib.rs, ...)."""
+    lines = text.splitlines()
+    return _check_crate_root(name, lines) + _check_test_modules(lines)
+
+
+def check_file(path: Path) -> list[Finding]:
+    return check_source(path.name, path.read_text(encoding="utf-8"))
+
+
+def main() -> int:
+    total = 0
+    for path in (Path(name) for name in sys.argv[1:]):
+        for finding in check_file(path):
+            total += 1
+            print(f"{path}:{finding.line}: {finding.label}: {finding.message}")
+    return 1 if total else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/pre-commit/clang_tidy_check.py

@@ -1,24 +1,46 @@
 #!/usr/bin/env python3
-"""Pre-commit hook that runs clang-tidy on changed files using run-clang-tidy."""
+"""Pre-commit hook that runs clang-tidy on staged files using run-clang-tidy.
+
+The script determines the staged files itself (see `pass_filenames: false` in
+.pre-commit-config.yaml) so run-clang-tidy is run once and handles parallelism
+internally: pre-commit would otherwise split the files across parallel hook
+invocations that race when fixes edit a shared header.
+
+Fixes are collected with `-export-fixes` and applied by clang-apply-replacements
+in a separate step rather than with run-clang-tidy's `-fix`. The `add_module`
+build isolates each module's headers behind a per-module symlink directory
+(build/modules/<module>/...), so a header reachable from several translation
+units is referenced through different paths that all resolve to the same source
+file. clang-apply-replacements deduplicates identical replacements by their
+literal path, so those paths must be canonicalised to the real source path
+first; otherwise the same fix is applied once per path and corrupts the header.
+"""
 
 from __future__ import annotations
 
-import json
 import os
 import re
 import shutil
 import subprocess
 import sys
-from collections import defaultdict
+import tempfile
 from pathlib import Path
 
-HEADER_EXTENSIONS = {".h", ".hpp", ".ipp"}
-SOURCE_EXTENSIONS = {".cpp"}
-INCLUDE_RE = re.compile(r"^\s*#\s*include\s*[<\"]([^>\"]+)[>\"]")
+CLANG_TIDY_VERSION = 22
+
+# Extensions run-clang-tidy can analyse: `.cpp` translation units and, thanks to
+# the `verify_headers` build option, `.h`/`.hpp` headers (each has its own
+# compile_commands.json entry). `.ipp` fragments have no entry and are skipped.
+TIDY_EXTENSIONS = {".cpp", ".h", ".hpp"}
+
+# A single-quoted `FilePath:` entry in an -export-fixes YAML file, allowing the
+# `- ` marker that precedes it inside a `Replacements:` sequence. clang-tidy
+# emits paths single-quoted and doubles any embedded quote per YAML rules.
+FILEPATH_RE = re.compile(r"^(\s*(?:-\s+)?FilePath:\s*)'((?:[^']|'')*)'\s*$")
 
 
-def find_run_clang_tidy() -> str | None:
-    for candidate in ("run-clang-tidy-21", "run-clang-tidy"):
+def find_tool(name: str) -> str | None:
+    for candidate in (f"{name}-{CLANG_TIDY_VERSION}", name):
         if path := shutil.which(candidate):
             return path
     return None
@@ -32,136 +54,37 @@ def find_build_dir(repo_root: Path) -> Path | None:
     return None
 
 
-def build_include_graph(build_dir: Path, repo_root: Path) -> tuple[dict, set]:
+def staged_files(repo_root: Path) -> list[Path]:
+    """Return absolute paths of staged, lint-able C/C++ files.
+
+    `--diff-filter=d` excludes deletions so we never lint a removed file.
     """
-    Scan all files reachable from compile_commands.json and build an inverted include graph.
-
-    Returns:
-        inverted: header_path -> set of files that include it
-        source_files: set of all TU paths from compile_commands.json
-    """
-    with open(build_dir / "compile_commands.json") as f:
-        db = json.load(f)
-
-    source_files = {Path(e["file"]).resolve() for e in db}
-    include_roots = [repo_root / "include", repo_root / "src"]
-    inverted: dict[Path, set[Path]] = defaultdict(set)
-
-    to_scan: set[Path] = set(source_files)
-    scanned: set[Path] = set()
-
-    while to_scan:
-        file = to_scan.pop()
-        if file in scanned or not file.exists():
-            continue
-        scanned.add(file)
-
-        content = file.read_text()
-
-        for line in content.splitlines():
-            m = INCLUDE_RE.match(line)
-            if not m:
-                continue
-            for root in include_roots:
-                candidate = (root / m.group(1)).resolve()
-                if candidate.exists():
-                    inverted[candidate].add(file)
-                    if candidate not in scanned:
-                        to_scan.add(candidate)
-                    break
-
-    return inverted, source_files
-
-
-def find_tus_for_headers(
-    headers: list[Path],
-    inverted: dict[Path, set[Path]],
-    source_files: set[Path],
-) -> set[Path]:
-    """
-    For each header, pick one TU that transitively includes it.
-    Prefers a TU whose stem matches the header's stem, otherwise picks the first found.
-    """
-    result: set[Path] = set()
-
-    for header in headers:
-        preferred: Path | None = None
-        visited: set[Path] = {header}
-        stack: list[Path] = [header]
-
-        while stack:
-            h = stack.pop()
-            for inc in inverted.get(h, ()):
-                if inc in source_files:
-                    if inc.stem == header.stem:
-                        preferred = inc
-                        break
-                    if preferred is None:
-                        preferred = inc
-                if inc not in visited:
-                    visited.add(inc)
-                    stack.append(inc)
-            if preferred is not None and preferred.stem == header.stem:
-                break
-
-        if preferred is not None:
-            result.add(preferred)
-
-    return result
-
-
-def resolve_files(
-    input_files: list[str], build_dir: Path, repo_root: Path
-) -> list[str]:
-    """
-    Split input into source files and headers. Source files are passed through;
-    headers are resolved to the TUs that transitively include them.
-    """
-    sources: list[Path] = []
-    headers: list[Path] = []
-
-    for f in input_files:
-        p = Path(f).resolve()
-        if p.suffix in SOURCE_EXTENSIONS:
-            sources.append(p)
-        elif p.suffix in HEADER_EXTENSIONS:
-            headers.append(p)
-
-    if not headers:
-        return [str(p) for p in sources]
-
-    print(
-        f"Resolving {len(headers)} header(s) to compilation units...", file=sys.stderr
-    )
-    inverted, source_files = build_include_graph(build_dir, repo_root)
-    tus = find_tus_for_headers(headers, inverted, source_files)
-
-    if not tus:
-        print(
-            "Warning: no compilation units found that include the modified headers; "
-            "skipping clang-tidy for headers.",
-            file=sys.stderr,
-        )
-
-    return sorted({str(p) for p in (*sources, *tus)})
-
-
-def staged_files(repo_root: Path) -> list[str]:
-    result = subprocess.run(
-        ["git", "diff", "--staged", "--name-only", "--diff-filter=d"],
-        capture_output=True,
+    output = subprocess.check_output(
+        ["git", "diff", "--staged", "--name-only", "--diff-filter=d", "--"]
+        + [f"*{ext}" for ext in TIDY_EXTENSIONS],
         text=True,
         cwd=repo_root,
     )
-    if result.returncode != 0:
-        print(
-            "clang-tidy check failed: 'git diff --staged' command failed.",
-            file=sys.stderr,
-        )
-        if result.stderr:
-            print(result.stderr, file=sys.stderr)
-        sys.exit(result.returncode or 1)
-    return [str(repo_root / p) for p in result.stdout.splitlines() if p]
+    return [repo_root / rel for rel in output.splitlines() if rel]
+
+
+def canonicalize_fix_paths(fixes_dir: Path) -> None:
+    """Rewrite every `FilePath` in the exported fixes to its real source path.
+
+    A header included through a module's isolation symlink is recorded under that
+    symlink's path; collapsing all paths to the same real file lets
+    clang-apply-replacements recognise the per-translation-unit duplicates and
+    apply each fix once.
+    """
+    for yaml in fixes_dir.glob("*.yaml"):
+        lines = []
+        for line in yaml.read_text().splitlines():
+            if m := FILEPATH_RE.match(line):
+                path = m.group(2).replace("''", "'")
+                real = os.path.realpath(path).replace("'", "''")
+                line = f"{m.group(1)}'{real}'"
+            lines.append(line)
+        yaml.write_text("\n".join(lines) + "\n")
 
 
 def main():
@@ -175,15 +98,25 @@ def main():
             text=True,
         ).strip()
     )
+
     files = staged_files(repo_root)
     if not files:
         return 0
 
-    run_clang_tidy = find_run_clang_tidy()
-    if not run_clang_tidy:
+    run_clang_tidy = find_tool("run-clang-tidy")
+    clang_apply_replacements = find_tool("clang-apply-replacements")
+    missing = [
+        name
+        for name, path in (
+            ("run-clang-tidy", run_clang_tidy),
+            ("clang-apply-replacements", clang_apply_replacements),
+        )
+        if not path
+    ]
+    if missing:
         print(
-            "clang-tidy check failed: TIDY is enabled but neither "
-            "'run-clang-tidy-21' nor 'run-clang-tidy' was found in PATH.",
+            f"clang-tidy check failed: TIDY is enabled but {' and '.join(missing)} "
+            f"was not found in PATH (tried the '-{CLANG_TIDY_VERSION}' suffix too).",
             file=sys.stderr,
         )
         return 1
@@ -197,15 +130,27 @@ def main():
         )
         return 1
 
-    tidy_files = resolve_files(files, build_dir, repo_root)
-    if not tidy_files:
-        return 0
+    with tempfile.TemporaryDirectory() as fixes_dir:
+        result = subprocess.run(
+            [
+                run_clang_tidy,
+                "-quiet",
+                "-p",
+                build_dir,
+                "-export-fixes",
+                fixes_dir,
+                "-allow-no-checks",
+            ]
+            + files
+        )
+        canonicalize_fix_paths(Path(fixes_dir))
+        # `FormatStyle` in .clang-tidy does not reach this path,
+        # so ask for the repository style here.
+        applied = subprocess.run(
+            [clang_apply_replacements, "--format", "--style=file", fixes_dir]
+        )
 
-    result = subprocess.run(
-        [run_clang_tidy, "-quiet", "-p", str(build_dir), "-fix", "-allow-no-checks"]
-        + tidy_files
-    )
-    return result.returncode
+    return result.returncode or applied.returncode
 
 
 if __name__ == "__main__":

bin/pre-commit/fix_gtest_names.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+
+"""
+Rewrites gtest names to the required style in this project: the suite name is
+CamelCase, the test-case name is snake_case.
+
+    TEST(SuiteName, test_case_name)
+
+The gtest `DISABLED_` prefix is kept verbatim on either name.
+
+Both conversions fold acronyms the way a reader expects:
+`SetAndResetAccountTxnID` -> `set_and_reset_account_txn_id`, not
+`set_and_reset_account_txn_i_d`.
+
+The first argument of `TEST_F`, `TEST_P`, `TYPED_TEST` and `TYPED_TEST_P` is a
+fixture class rather than a free identifier, so rewriting it here would leave
+the class it names behind. Those are reported for a human to rename (clang-tidy
+checks the class declaration itself, via readability-identifier-naming).
+
+Usage: ./bin/pre-commit/fix_gtest_names.py <file1> <file2> ...
+"""
+
+import re
+import sys
+from collections import Counter
+from pathlib import Path
+
+# A test-case definition, `MACRO(SuiteOrFixture, TestName)`, anchored at the
+# start of a line so that commented-out definitions and project macros that
+# merely look similar (`TEST_EXPECT(...)`) are left alone. The `\s*` between
+# arguments allows for a definition clang-format wrapped over several lines.
+PATTERN = re.compile(
+    r"(?P<head>^[ \t]*(?P<macro>TYPED_TEST_P|TYPED_TEST|TEST_F|TEST_P|TEST)\s*\(\s*)"
+    r"(?P<suite>\w+)(?P<mid>\s*,\s*)(?P<name>\w+)(?P<tail>\s*\))",
+    re.MULTILINE,
+)
+
+# The macros whose first argument names a fixture class, not a free identifier.
+FIXTURE_MACROS = ("TEST_F", "TEST_P", "TYPED_TEST", "TYPED_TEST_P")
+
+DISABLED = "DISABLED_"
+
+ACRONYM_BOUNDARY = re.compile(r"([A-Z]+)([A-Z][a-z])")
+WORD_BOUNDARY = re.compile(r"([a-z\d])([A-Z])")
+
+
+def _split_disabled(name: str) -> tuple[str, str]:
+    """Splits off gtest's `DISABLED_` prefix, which is kept verbatim."""
+    if name.startswith(DISABLED):
+        return DISABLED, name[len(DISABLED) :]
+    return "", name
+
+
+def snake_case(name: str) -> str:
+    """Returns the name in snake_case, leaving acronyms whole.
+
+    `SetAndResetAccountTxnID` -> `set_and_reset_account_txn_id`,
+    `parseStatRSSkB` -> `parse_stat_rs_sk_b`.
+    """
+    prefix, core = _split_disabled(name)
+    core = ACRONYM_BOUNDARY.sub(r"\1_\2", core)
+    return prefix + WORD_BOUNDARY.sub(r"\1_\2", core).lower()
+
+
+def camel_case(name: str) -> str:
+    """Returns the name in CamelCase, capitalizing each underscored word.
+
+    Only the letters that have to change are touched, so acronyms survive: a
+    conversion that went via snake_case would turn `SHAMapTest` into
+    `ShaMapTest`, whereas here it is already CamelCase and stays put.
+    `json_value` -> `JsonValue`, `parseStatRSSkB` -> `ParseStatRSSkB`.
+    """
+    prefix, core = _split_disabled(name)
+    return prefix + "".join(w[:1].upper() + w[1:] for w in core.split("_") if w)
+
+
+def _corrected(match: re.Match) -> tuple[str, str]:
+    """Returns the suite and test-case names this definition should end up with."""
+    suite = match["suite"]
+    return (
+        suite if match["macro"] in FIXTURE_MACROS else camel_case(suite),
+        snake_case(match["name"]),
+    )
+
+
+def fix_source(text: str) -> tuple[str, list[str]]:
+    """Returns the corrected text and one `line: message` report per bad name."""
+    # gtest joins the suite and test names into one class name, so two test
+    # cases whose joined names agree cannot coexist: `TEST(a, b_c)` and
+    # `TEST(a_b, c)` both define `a_b_c_Test`. A rename that would introduce
+    # such a clash is reported for a human instead of applied.
+    joined = Counter("_".join(_corrected(m)) for m in PATTERN.finditer(text))
+    reports = []
+
+    def rewrite(match: re.Match) -> str:
+        suite, name = match["suite"], match["name"]
+        new_suite, new_name = _corrected(match)
+        line = text.count("\n", 0, match.start()) + 1
+
+        if match["macro"] in FIXTURE_MACROS and camel_case(suite) != suite:
+            reports.append(
+                f"{line}: fixture '{suite}' is not CamelCase: rename the class "
+                f"to '{camel_case(suite)}' by hand"
+            )
+        if (new_suite, new_name) == (suite, name):
+            return match[0]
+        if joined[f"{new_suite}_{new_name}"] > 1:
+            reports.append(
+                f"{line}: cannot rename '{suite}, {name}' to '{new_suite}, "
+                f"{new_name}': another test case already generates that name"
+            )
+            return match[0]
+        if new_suite != suite:
+            reports.append(f"{line}: renamed suite '{suite}' to '{new_suite}'")
+        if new_name != name:
+            reports.append(f"{line}: renamed test case '{name}' to '{new_name}'")
+        return match["head"] + new_suite + match["mid"] + new_name + match["tail"]
+
+    return PATTERN.sub(rewrite, text), reports
+
+
+def fix_names(path: Path) -> bool:
+    """Corrects one file's gtest names, reporting each on stdout."""
+    original = path.read_text(encoding="utf-8")
+    fixed, reports = fix_source(original)
+    for report in reports:
+        print(f"{path}:{report}")
+    if fixed != original:
+        path.write_text(fixed, encoding="utf-8")
+    return not reports
+
+
+def main() -> int:
+    files = [Path(f) for f in sys.argv[1:]]
+    success = True
+
+    for path in files:
+        success &= fix_names(path)
+
+    return 0 if success else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/pre-commit/fix_pragma_once.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+
+"""
+Adds "#pragma once" to the top of header files that don't already have it.
+
+Usage: ./bin/pre-commit/fix_pragma_once.py <file1> <file2> ...
+"""
+
+import sys
+from pathlib import Path
+
+PRAGMA_ONCE = "#pragma once\n\n"
+
+
+def fix_pragma_once(path: Path) -> bool:
+    original = path.read_text(encoding="utf-8")
+    if PRAGMA_ONCE not in original:
+        path.write_text(PRAGMA_ONCE + original, encoding="utf-8")
+        return False
+    return True
+
+
+def main() -> int:
+    files = [Path(f) for f in sys.argv[1:]]
+    success = True
+
+    for path in files:
+        success &= fix_pragma_once(path)
+
+    return 0 if success else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/pre-commit/test_check_doxygen_style.py

@@ -0,0 +1,406 @@
+#!/usr/bin/env python3
+"""
+Tests for check_doxygen_style.py.
+
+Run directly (no test framework needed):
+    ./bin/pre-commit/test_check_doxygen_style.py
+or under pytest:
+    pytest bin/pre-commit/test_check_doxygen_style.py
+"""
+
+import sys
+import textwrap
+
+from check_doxygen_style import Finding, check_source
+
+
+def findings_for(text: str) -> list[Finding]:
+    """Return the style violations for the given source text.
+
+    The text is dedented and its leading newline stripped, so fixtures can be
+    written as indented triple-quoted here-docs while keeping honest 1-based
+    line numbers.
+    """
+    text = textwrap.dedent(text).lstrip("\n")
+    return check_source(text)
+
+
+def labels_for(text: str) -> list[str]:
+    return [f.category.label for f in findings_for(text)]
+
+
+def messages_for(text: str) -> list[str]:
+    return [f.message for f in findings_for(text)]
+
+
+# --- well-formed input produces nothing -------------------------------------
+
+
+def test_clean_block_ok() -> None:
+    code = """
+    /**
+     * Brief.
+     *
+     * @tparam T a type
+     * @param x the x
+     * @return the result
+     */
+    """
+    assert findings_for(code) == []
+
+
+def test_blank_lines_inside_block_ok() -> None:
+    code = """
+    /**
+     * a
+     *
+     * b
+     */
+    """
+    assert findings_for(code) == []
+
+
+def test_member_and_divider_allowed() -> None:
+    assert findings_for("int x;  ///< ok member\n") == []
+    assert findings_for("//////////\n") == []
+    assert findings_for("//// text\n") == []
+
+
+# --- line-comment forms ------------------------------------------------------
+
+
+def test_triple_slash() -> None:
+    code = "/// doc\n"
+    assert labels_for(code) == ["triple-slash"]
+
+
+def test_qt_line() -> None:
+    code = "//! doc\n"
+    assert labels_for(code) == ["qt-line"]
+
+
+def test_qt_member() -> None:
+    code = "int x;  //!< doc\n"
+    assert labels_for(code) == ["qt-member"]
+
+
+def test_block_member() -> None:
+    code = "int x;  /**< doc */\n"
+    assert labels_for(code) == ["block-member"]
+
+
+def test_qt_block_member() -> None:
+    code = "int x;  /*!< doc */\n"
+    assert labels_for(code) == ["qt-block-member"]
+
+
+def test_doc_in_line_comment() -> None:
+    code = "// @param x\n"
+    assert labels_for(code) == ["doc-in-line-comment"]
+
+
+# --- block forms -------------------------------------------------------------
+
+
+def test_qt_comment() -> None:
+    code = """
+    /*!
+     * brief
+     */
+    """
+    assert labels_for(code) == ["qt-comment"]
+
+
+def test_qt_comment_single_line() -> None:
+    # /*! ... */ on one line -> qt-comment (plus single-line-block)
+    code = "/*! brief */\n"
+    assert labels_for(code) == ["qt-comment", "single-line-block"]
+
+
+def test_single_line_block() -> None:
+    code = "/** brief */\n"
+    assert labels_for(code) == ["single-line-block"]
+
+
+def test_single_line_markers_allowed() -> None:
+    for marker in ("@{", "@}", "@cond LABEL", "@endcond", "@file foo.h"):
+        code = f"/** {marker} */\n"
+        assert findings_for(code) == [], marker
+
+
+def test_text_on_opener() -> None:
+    code = """
+    /** text here
+     * more
+     */
+    """
+    assert labels_for(code) == ["text-on-opener"]
+
+
+def test_bare_continuation() -> None:
+    code = """
+    /**
+     * a
+       bare line
+     */
+    """
+    assert labels_for(code) == ["bare-continuation"]
+
+
+def test_over_indented_first_line() -> None:
+    code = """
+    /**
+     *   over
+     */
+    """
+    assert labels_for(code) == ["over-indented"]
+
+
+def test_over_indented_tag() -> None:
+    # a flush first line consumes "first content", isolating the tag check
+    code = """
+    /**
+     * brief
+     *   @param x
+     */
+    """
+    assert labels_for(code) == ["over-indented-tag"]
+
+
+def test_combined_marker() -> None:
+    code = """
+    /**
+     * @{
+     */
+    """
+    assert labels_for(code) == ["combined-marker"]
+
+
+def test_prose_label() -> None:
+    for word in ("Returns", "Throws", "Exceptions"):
+        code = f"""
+        /**
+         * {word}:
+         */
+        """
+        assert labels_for(code) == ["prose-label"], word
+
+
+def test_content_on_closer() -> None:
+    code = """
+    /**
+     * a
+     * b */
+    """
+    assert labels_for(code) == ["content-on-closer"]
+
+
+def test_plain_block_doc() -> None:
+    assert labels_for("/* @param x */\n") == ["plain-block-doc"]
+    assert findings_for("/* just an ordinary note */\n") == []
+
+
+def test_tag_order() -> None:
+    out_of_order = """
+    /**
+     * @param x
+     * @tparam T
+     */
+    """
+    assert labels_for(out_of_order) == ["tag-order"]
+
+    correct = """
+    /**
+     * @tparam T
+     * @param x
+     * @return r
+     */
+    """
+    assert findings_for(correct) == []
+
+    single = """
+    /**
+     * @param x
+     */
+    """
+    assert findings_for(single) == []  # single tag: never out of order
+
+
+# --- command spelling (must work on body/closer lines, not just the opener) --
+
+
+def test_backslash_command_on_body_line() -> None:
+    code = r"""
+    /**
+     * \brief x
+     */
+    """
+    assert labels_for(code) == ["backslash-command"]
+
+
+def test_backslash_command_suggests_canonical_spelling() -> None:
+    # a backslash + non-canonical spelling is fixed in one pass, not two:
+    # \sa -> @see (not @sa), \returns -> @return (not @returns)
+    sa = r"""
+    /**
+     * \sa other
+     */
+    """
+    assert messages_for(sa) == [r"use @see instead of \sa"]
+
+    returns = r"""
+    /**
+     * \returns x
+     */
+    """
+    assert messages_for(returns) == [r"use @return instead of \returns"]
+
+
+def test_wrong_command_on_body_line() -> None:
+    code = """
+    /**
+     * @returns x
+     */
+    """
+    assert labels_for(code) == ["wrong-command"]
+
+
+def test_body_line_commands_regression() -> None:
+    # regression: these live on body lines of a multi-line block
+    code = r"""
+    /**
+     * @returns bad
+     * @throw ex
+     * @sa other
+     * \param y
+     */
+    """
+    assert labels_for(code) == [
+        "wrong-command",
+        "wrong-command",
+        "wrong-command",
+        "backslash-command",
+    ]
+
+
+def test_command_on_closer_line() -> None:
+    code = """
+    /**
+     * a
+     * @sa b */
+    """
+    assert labels_for(code) == ["wrong-command", "content-on-closer"]
+
+
+def test_no_double_count_across_opener_body_closer() -> None:
+    code = """
+    /** @returns opener
+     * @throw body
+     * @sa closer */
+    """
+    assert labels_for(code).count("wrong-command") == 3
+
+
+def test_code_with_word_allowed() -> None:
+    # @code{.cpp} is valid Doxygen and must not be flagged
+    code = """
+    /**
+     * @code{.cpp}
+     * int x;
+     * @endcode
+     */
+    """
+    assert findings_for(code) == []
+
+
+# --- rendered message text ---------------------------------------------------
+
+
+def test_message_uses_category_description() -> None:
+    # a static category renders its default description
+    code = "/// doc\n"
+    assert messages_for(code) == ["use a /** ... */ block instead of ///"]
+
+
+def test_message_detail_overrides() -> None:
+    # dynamic categories render the offending text via Finding.detail
+    backslash = r"""
+    /**
+     * \param y
+     */
+    """
+    assert messages_for(backslash) == [r"use @param instead of \param"]
+
+    wrong = """
+    /**
+     * @returns x
+     */
+    """
+    assert messages_for(wrong) == ["use @return instead of @returns"]
+
+    prose = """
+    /**
+     * Throws:
+     */
+    """
+    assert messages_for(prose) == ['use @throws instead of prose "Throws:"']
+
+
+# --- robustness --------------------------------------------------------------
+
+
+def test_empty_file_no_crash() -> None:
+    assert findings_for("") == []
+
+
+def test_mid_line_plain_block_skipped() -> None:
+    # a /* opened mid-line (after code) and spanning lines is skipped, so its
+    # comment-like contents are not analyzed
+    code = """
+    int x = 0;  /* note: @returns is not a real tag here
+     * @param also not real
+     */
+    int y = 0;
+    """
+    assert findings_for(code) == []
+
+
+def test_unclosed_block_scanned_to_eof() -> None:
+    # an unterminated /** block is still scanned to EOF (no crash, body checked)
+    code = """
+    /**
+     * @returns x
+    """
+    assert labels_for(code) == ["wrong-command"]
+
+
+def test_banner_and_empty_comment_not_flagged() -> None:
+    code = """
+    /***
+     * banner
+     ***/
+    """
+    assert findings_for(code) == []
+    assert findings_for("/**/\n") == []
+
+
+def main() -> int:
+    tests = sorted(
+        (name, fn)
+        for name, fn in globals().items()
+        if name.startswith("test_") and callable(fn)
+    )
+    failed = 0
+    for name, fn in tests:
+        try:
+            fn()
+            print(f"PASS {name}")
+        except AssertionError as exc:
+            failed += 1
+            print(f"FAIL {name}: {exc!r}")
+    print(f"\n{len(tests) - failed}/{len(tests)} passed")
+    return 1 if failed else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/pre-commit/test_fix_gtest_names.py

@@ -0,0 +1,259 @@
+#!/usr/bin/env python3
+"""
+Tests for fix_gtest_names.py.
+
+Run directly (no test framework needed):
+    ./bin/pre-commit/test_fix_gtest_names.py
+or under pytest:
+    pytest bin/pre-commit/test_fix_gtest_names.py
+"""
+
+import sys
+import textwrap
+
+from fix_gtest_names import camel_case, fix_source, snake_case
+
+
+def dedent(text: str) -> str:
+    """Removes a fixture's common indentation and its leading newline.
+
+    Lets fixtures be written as indented triple-quoted here-docs while keeping
+    honest 1-based line numbers.
+    """
+    return textwrap.dedent(text).lstrip("\n")
+
+
+def fixed(text: str) -> str:
+    return fix_source(dedent(text))[0]
+
+
+def reports(text: str) -> list[str]:
+    return fix_source(dedent(text))[1]
+
+
+# --- conversion --------------------------------------------------------------
+
+
+def test_snake_case_conversion() -> None:
+    assert snake_case("BadInputs") == "bad_inputs"
+    assert snake_case("mulDiv") == "mul_div"
+    assert snake_case("already_snake") == "already_snake"
+    assert snake_case("base64") == "base64"
+
+
+def test_snake_case_keeps_acronyms_whole() -> None:
+    assert snake_case("SetAndResetAccountTxnID") == "set_and_reset_account_txn_id"
+    assert snake_case("XRPToIOU") == "xrp_to_iou"
+    assert snake_case("STAmountMath") == "st_amount_math"
+
+
+def test_camel_case_conversion() -> None:
+    assert camel_case("json_value") == "JsonValue"
+    assert camel_case("mulDiv") == "MulDiv"
+    assert camel_case("scope") == "Scope"
+    assert camel_case("base64") == "Base64"
+
+
+def test_camel_case_leaves_acronyms_alone() -> None:
+    # A snake_case round-trip would give `ShaMapTest` / `ParseStatmRsSkB` here.
+    assert camel_case("SHAMapTest") == "SHAMapTest"
+    assert camel_case("parseStatmRSSkB") == "ParseStatmRSSkB"
+    assert camel_case("XRPAmount") == "XRPAmount"
+    assert camel_case("CSPRNG") == "CSPRNG"
+
+
+def test_disabled_prefix_preserved() -> None:
+    assert snake_case("DISABLED_FooBar") == "DISABLED_foo_bar"
+    assert snake_case("DISABLED_foo_bar") == "DISABLED_foo_bar"
+    assert snake_case("DISABLED_") == "DISABLED_"
+    assert camel_case("DISABLED_foo_bar") == "DISABLED_FooBar"
+    assert camel_case("DISABLED_") == "DISABLED_"
+
+
+# --- what counts as a test definition ---------------------------------------
+
+
+def test_all_macros_recognized() -> None:
+    code = """
+    TEST(Suite, oneName)
+    TEST_F(Fixture, twoName)
+    TEST_P(Fixture, threeName)
+    TYPED_TEST(Fixture, fourName)
+    TYPED_TEST_P(Fixture, fiveName)
+    """
+    assert fixed(code) == dedent("""
+        TEST(Suite, one_name)
+        TEST_F(Fixture, two_name)
+        TEST_P(Fixture, three_name)
+        TYPED_TEST(Fixture, four_name)
+        TYPED_TEST_P(Fixture, five_name)
+        """)
+
+
+def test_conforming_definitions_untouched() -> None:
+    code = """
+    TEST(AccountSet, bad_inputs)
+    TEST_F(MutexMakeTest, default_constructor)
+    TEST(SHAMap, DISABLED_slow_path)
+    """
+    assert reports(code) == []
+    assert fixed(code) == dedent(code)
+
+
+def test_lookalikes_ignored() -> None:
+    code = """
+    // TEST(Suite, notATest)
+    TEST_EXPECT(someCall())
+    TEST_EXPECTS(amount == value, amount.getText())
+    INSTANTIATE_TEST_SUITE_P(Prefix, Fixture, testValues());
+    auto x = TEST(Suite, notATest);
+    TYPED_TEST_SUITE(Fixture, MyTypes);
+    """
+    assert reports(code) == []
+    assert fixed(code) == dedent(code)
+
+
+def test_indented_and_wrapped_definitions() -> None:
+    code = """
+    namespace ripple {
+        TEST(Suite, indentedName)
+    }
+    TEST_F(
+        SomeVeryLongFixtureName,
+        wrappedName)
+    """
+    assert fixed(code) == dedent("""
+        namespace ripple {
+            TEST(Suite, indented_name)
+        }
+        TEST_F(
+            SomeVeryLongFixtureName,
+            wrapped_name)
+        """)
+
+
+# --- rewriting --------------------------------------------------------------
+
+
+def test_only_the_two_names_are_rewritten() -> None:
+    code = """
+    TEST(mulDiv, mulDiv)
+    {
+        auto const mulDiv = 1;  // mulDiv stays
+    }
+    """
+    assert fixed(code) == dedent("""
+        TEST(MulDiv, mul_div)
+        {
+            auto const mulDiv = 1;  // mulDiv stays
+        }
+        """)
+
+
+def test_suite_name_camel_cased() -> None:
+    code = """
+    TEST(json_value, limits)
+    TEST(scope, ScopeExit)
+    """
+    assert reports(code) == [
+        "1: renamed suite 'json_value' to 'JsonValue'",
+        "2: renamed suite 'scope' to 'Scope'",
+        "2: renamed test case 'ScopeExit' to 'scope_exit'",
+    ]
+    assert fixed(code) == dedent("""
+        TEST(JsonValue, limits)
+        TEST(Scope, scope_exit)
+        """)
+
+
+def test_fixture_reported_but_not_renamed() -> None:
+    # The first argument names a class, so only a human (or clang-tidy) can
+    # rename it; the test-case name is still fixed.
+    code = """
+    TEST_F(my_fixture, someTest)
+    """
+    assert reports(code) == [
+        "1: fixture 'my_fixture' is not CamelCase: rename the class to "
+        "'MyFixture' by hand",
+        "1: renamed test case 'someTest' to 'some_test'",
+    ]
+    assert fixed(code) == dedent("""
+        TEST_F(my_fixture, some_test)
+        """)
+
+
+def test_reports_carry_line_numbers() -> None:
+    code = """
+    #include <foo.h>
+
+    TEST(Suite, firstName)
+
+    TEST(Suite, secondName)
+    """
+    assert reports(code) == [
+        "3: renamed test case 'firstName' to 'first_name'",
+        "5: renamed test case 'secondName' to 'second_name'",
+    ]
+
+
+# --- collisions -------------------------------------------------------------
+
+
+def test_collision_reported_and_not_applied() -> None:
+    # Both would define `Suite_mul_div_Test`.
+    code = """
+    TEST(Suite, mulDiv)
+    TEST(Suite, mul_div)
+    """
+    assert reports(code) == [
+        "1: cannot rename 'Suite, mulDiv' to 'Suite, mul_div': another test "
+        "case already generates that name"
+    ]
+    assert fixed(code) == dedent(code)
+
+
+def test_collision_between_converging_suites() -> None:
+    # Both suites camel-case to `SuiteA`, so both would define
+    # `SuiteA_one_test_Test`.
+    code = """
+    TEST(SuiteA, oneTest)
+    TEST(Suite_a, one_test)
+    """
+    assert [r.split(":")[1].strip() for r in reports(code)] == [
+        "cannot rename 'SuiteA, oneTest' to 'SuiteA, one_test'",
+        "cannot rename 'Suite_a, one_test' to 'SuiteA, one_test'",
+    ]
+    assert fixed(code) == dedent(code)
+
+
+def test_same_name_in_different_suites_is_not_a_collision() -> None:
+    code = """
+    TEST(SuiteOne, mulDiv)
+    TEST(SuiteTwo, mulDiv)
+    """
+    assert fixed(code) == dedent("""
+        TEST(SuiteOne, mul_div)
+        TEST(SuiteTwo, mul_div)
+        """)
+
+
+def main() -> int:
+    tests = sorted(
+        (name, fn)
+        for name, fn in globals().items()
+        if name.startswith("test_") and callable(fn)
+    )
+    failed = 0
+    for name, fn in tests:
+        try:
+            fn()
+            print(f"PASS {name}")
+        except AssertionError as exc:
+            failed += 1
+            print(f"FAIL {name}: {exc!r}")
+    print(f"\n{len(tests) - failed}/{len(tests)} passed")
+    return 1 if failed else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

cfg/xrpld-example.cfg

@@ -488,6 +488,17 @@
 #   Must be a number between 100 and 1000, defaults to 250
 #
 #
+# [max_subscriptions_per_connection]
+#
+#   Maximum number of account, real-time account, and account-history
+#   subscriptions a single client connection may hold at once. Bounds the
+#   per-connection state torn down when the connection disconnects. Book
+#   subscriptions are tracked separately and are not counted here.
+#
+#   Defaults to 100000 if not set; large enough for legitimate power users
+#   such as block explorers.
+#
+#
 # [overlay]
 #
 #   Controls settings related to the peer to peer overlay.
@@ -538,6 +549,45 @@
 #       only be used for local testing and debugging. Do not disable
 #       on mainnet.
 #
+#   max_untrusted_count = <number>
+#
+#       The number of manifests the server keeps for validators it does not
+#       list, and the number it sends and processes in a single peer protocol
+#       message. Once the server holds this many, a manifest for a new
+#       unlisted validator is rejected, so peer gossip cannot grow the cache
+#       without end.
+#
+#       This option can take any value between 50 and 1000, inclusive. If
+#       the option is not present the server uses its built-in value.
+#
+#       The current default (which is subject to change) is 300.
+#
+#   max_trusted_count = <number>
+#
+#       The number of manifests for listed validators to allow for when
+#       sizing peer protocol messages. Manifests for listed validators are
+#       never dropped, whether sending or receiving, because doing so would
+#       delay a validator key change reaching this server. Set this above the
+#       number of validators the server lists.
+#
+#       Together the two counts above set the largest manifest message the
+#       server accepts: bigger messages are discarded without reading them,
+#       and without penalising the sender. Raising either means the server
+#       accepts and sends bigger messages than a peer using the defaults, and
+#       those peers will discard what this server sends. Lowering either below
+#       what peers send makes this server discard their manifest messages,
+#       which it does without recording anything.
+#
+#       This option can take any value between 50 and 1000, inclusive. If
+#       the option is not present the server uses its built-in value.
+#
+#       The current default (which is subject to change) is 300.
+#
+#       NOTE: These two options (max_untrusted_count and max_trusted_count)
+#       are transitional. They exist to bound manifest-message size and cache
+#       growth during the network upgrade. They may be removed in a future
+#       release once the fleet has upgraded, and should not be relied upon as
+#       stable configuration.
 #
 # [transaction_queue] EXPERIMENTAL
 #
@@ -1044,8 +1094,8 @@
 #                           Default is 100.
 #
 #       back_off_milliseconds
-#                           Number of milliseconds to wait between
-#                           online_delete batches to allow other functions
+#                           Number of milliseconds to wait between online_delete
+#                           SQL deletion batches to allow other functions
 #                           to catch up.
 #                           Default is 100.
 #
@@ -1059,10 +1109,22 @@
 #                           The online delete process checks periodically
 #                           that xrpld is still in sync with the network,
 #                           and that the validated ledger is less than
-#                           'age_threshold_seconds' old. If not, then continue
+#                           'age_threshold_seconds' old, and that all
+#                           recent ledgers are available. If not, then continue
 #                           sleeping for this number of seconds and
 #                           checking until healthy.
-#                           Default is 5.
+#                           Default is 2.
+#
+#       max_waiting_ledgers
+#                           The maximum number of ledgers that may be validated
+#                           while online deletion is waiting for the node to get
+#                           fully synced with the rest of the network. If more than
+#                           this number of ledgers are validated while waiting, then
+#                           online deletion gives up on the current ledger and tries
+#                           again later. Note this only affects situations that cause
+#                           rotation to wait, such as going out of sync, or missing
+#                           ledgers. Forward progress is not penalized. Minimum is 64.
+#                           Default is the online_delete value.
 #
 #   Notes:
 #       The 'node_db' entry configures the primary, persistent storage.

cmake/CompilationEnv.cmake

@@ -29,6 +29,27 @@ if(CMAKE_GENERATOR STREQUAL "Xcode")
     set(is_xcode TRUE)
 endif()
 
+# --------------------------------------------------------------------
+# Nix toolchain detection
+# --------------------------------------------------------------------
+# True when the C++ compiler resolves into the Nix store. CMAKE_CXX_COMPILER may
+# be referenced through a symlink outside the store (a Nix profile, a /usr/bin
+# alternative, ...), so resolve the real path before matching.
+set(is_nix_compiler FALSE)
+get_filename_component(_cxx_real "${CMAKE_CXX_COMPILER}" REALPATH)
+if(_cxx_real MATCHES "^/nix/store/")
+    set(is_nix_compiler TRUE)
+endif()
+unset(_cxx_real)
+
+# True inside the Nix CI Docker image, identified by the /nix/ci-env tree it
+# ships (see nix/docker/Dockerfile). The dev shell and bare systems don't have
+# it, so it distinguishes the CI image from other Nix-compiler environments.
+set(is_ci_image FALSE)
+if(EXISTS "/nix/ci-env/bin")
+    set(is_ci_image TRUE)
+endif()
+
 # --------------------------------------------------------------------
 # Operating system detection
 # --------------------------------------------------------------------
@@ -56,3 +77,16 @@ elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64|ARM64")
 else()
     message(FATAL_ERROR "Unknown architecture: ${CMAKE_SYSTEM_PROCESSOR}")
 endif()
+
+# --------------------------------------------------------------------
+# Sanitizers
+# --------------------------------------------------------------------
+# SANITIZERS is injected by the Conan toolchain when a sanitizer build is
+# requested (see conan/profiles/sanitizers). The flags are applied to the
+# 'common' target in XrplSanitizers; this flag lets other modules know a
+# sanitizer build is active without depending on that module.
+if(DEFINED SANITIZERS)
+    set(SANITIZERS_ENABLED TRUE)
+else()
+    set(SANITIZERS_ENABLED FALSE)
+endif()

cmake/GitInfo.cmake

@@ -1,28 +0,0 @@
-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/PatchNixBinary.cmake

@@ -0,0 +1,90 @@
+#[===================================================================[
+   Patch executables to run in non-Nix environments.
+
+   The Nix toolchain links binaries against an ELF interpreter (loader)
+   that lives in the Nix store, so the resulting binaries don't run elsewhere
+   (including once installed from the .deb package). `patch_nix_binary` resets
+   the interpreter to the system default loader and drops the rpath, once the
+   binary has been linked.
+
+   This runs by default for Nix-toolchain builds (determined by whether the compiler resolves under /nix/store/).
+   Those builds are where binaries get a Nix-store loader.
+   It is opted out of by setting the XRPLD_NO_PATCH_NIX_BINARY environment variable —
+   the plain Nix dev shells set it, since their binaries link a newer glibc
+   and must not be retargeted to the system loader.
+
+   Non-Nix builds (a system compiler, already using the system loader) and sanitizer builds
+   (runtime libraries resolved through the rpath) are skipped too.
+   Everywhere else `patch_nix_binary` is a no-op.
+
+   The default loader is resolved by bin/default-loader-path.sh.
+#]===================================================================]
+
+include_guard(GLOBAL)
+
+include(CompilationEnv)
+
+# Resolves the system default ELF loader path for the current architecture.
+set(_loader_path_script "${CMAKE_SOURCE_DIR}/bin/default-loader-path.sh")
+
+if(
+    is_linux
+    AND NOT SANITIZERS_ENABLED
+    AND is_nix_compiler
+    AND NOT DEFINED ENV{XRPLD_NO_PATCH_NIX_BINARY}
+)
+    execute_process(
+        COMMAND "${_loader_path_script}"
+        OUTPUT_VARIABLE DEFAULT_LOADER_PATH
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        COMMAND_ERROR_IS_FATAL ANY
+    )
+    find_program(PATCHELF_COMMAND patchelf REQUIRED)
+    set(PATCH_NIX_BINARIES TRUE)
+    message(
+        STATUS
+        "Binaries will be patched to use loader '${DEFAULT_LOADER_PATH}'"
+    )
+else()
+    set(PATCH_NIX_BINARIES FALSE)
+endif()
+
+function(patch_nix_binary target)
+    if(NOT PATCH_NIX_BINARIES)
+        return()
+    endif()
+
+    set(patch_command
+        "${PATCHELF_COMMAND}"
+        --set-interpreter
+        "${DEFAULT_LOADER_PATH}"
+        --remove-rpath
+        "$<TARGET_FILE:${target}>"
+    )
+    set(comment "Patching ${target}: set default loader, remove rpath")
+
+    # POST_BUILD is the cheap way to do this: it runs only when the binary is
+    # relinked. It is also only available in the directory that defined the
+    # target, so for a target from elsewhere (e.g. a FetchContent subproject)
+    # fall back to a custom target that runs after the binary is linked. That
+    # one runs on every build, which is harmless because patchelf is idempotent.
+    get_target_property(target_source_dir ${target} SOURCE_DIR)
+    if("${target_source_dir}" STREQUAL "${CMAKE_CURRENT_SOURCE_DIR}")
+        add_custom_command(
+            TARGET ${target}
+            POST_BUILD
+            COMMAND ${patch_command}
+            COMMENT "${comment}"
+            VERBATIM
+        )
+    else()
+        add_custom_target(
+            ${target}-patch-nix
+            ALL
+            COMMAND ${patch_command}
+            COMMENT "${comment}"
+            VERBATIM
+        )
+        add_dependencies(${target}-patch-nix ${target})
+    endif()
+endfunction()

cmake/XrplAddBenchmark.cmake

@@ -0,0 +1,38 @@
+include_guard()
+
+include(isolate_headers)
+
+# Define a benchmark executable for the module `name`.
+#
+# This follows the same general pattern as other build helpers in this repo
+# (e.g. `add_module`): create a target and isolate headers, but here the target
+# is a benchmark executable and no `add_test(...)` is registered.
+#
+# `isolate_headers` exposes only `${CMAKE_CURRENT_SOURCE_DIR}/${name}` on the
+# include path, rooted at `src`, so a benchmark's own headers are reached as
+# `<benchmarks/.../${name}/...>` and nothing else in the tree leaks in.
+function(xrpl_add_benchmark name)
+    set(target ${PROJECT_NAME}.bench.${name})
+
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}/*.cpp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}.cpp"
+    )
+    add_executable(${target} ${ARGN} ${sources})
+
+    # Benchmark sources register cases through Google Benchmark's static
+    # registrars (anonymous-namespace lambdas). Merging several such files into
+    # one unity translation unit collides those internal-linkage entities, so
+    # keep benchmarks out of the unity build - mirroring xrpl.libpb in
+    # XrplCore.cmake. Each file compiles fine on its own.
+    set_target_properties(${target} PROPERTIES UNITY_BUILD OFF)
+
+    isolate_headers(
+        ${target}
+        "${CMAKE_SOURCE_DIR}/src"
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}"
+        PRIVATE
+    )
+endfunction()

cmake/XrplCompiler.cmake

@@ -120,7 +120,10 @@ if(MSVC)
             _SILENCE_ALL_CXX17_DEPRECATION_WARNINGS
             $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:_CRTDBG_MAP_ALLOC>
     )
-    target_link_libraries(common INTERFACE -errorreport:none -machine:X64)
+    target_link_libraries(
+        common
+        INTERFACE -errorreport:none -machine:X64 -ignore:4099
+    )
 else()
     target_compile_options(
         common
@@ -154,6 +157,15 @@ else()
             >
     )
 
+    # On aarch64, libatomic is required for atomic operations. It is not needed on x86_64.
+    # Linking it statically on Linux
+    if(is_arm64 AND is_linux)
+        target_link_options(
+            common
+            INTERFACE -Wl,--push-state -Wl,-Bstatic -latomic -Wl,--pop-state
+        )
+    endif()
+
     # Keep -stdlib=libstdc++ off the compile commands, but preserve it for linking.
     #
     # Conan turns `compiler.libcxx=libstdc++` into `-stdlib=libstdc++` and puts it in
@@ -162,9 +174,8 @@ else()
     # Clang wrapper supplies those paths itself (via -nostdinc++), so at compile time the
     # flag is unused -> Clang errors under our -Werror. At link time the flag IS consumed
     # (it selects the C++ runtime), so we move it there instead of dropping it entirely.
-    get_filename_component(_cxx_real "${CMAKE_CXX_COMPILER}" REALPATH)
     if(
-        _cxx_real MATCHES "^/nix/store/"
+        is_nix_compiler
         AND is_linux
         AND is_clang
         AND CMAKE_CXX_FLAGS MATCHES "stdlib=libstdc"
@@ -258,10 +269,50 @@ elseif(use_lld)
     )
     if("${LD_VERSION}" MATCHES "LLD")
         target_link_libraries(common INTERFACE -fuse-ld=lld)
+        # remembered for the linker flag probe below
+        set(fuse_ld_flag "-fuse-ld=lld")
     endif()
     unset(LD_VERSION)
 endif()
 
+# Linker warnings are errors where we control the toolchain and the dependencies: CI and the Nix dev shell.
+# On non-Nix macOS we suppress the deployment target warning: an old Conan profile may not pin os.version.
+# Only the new Apple linker understands the flag, so probe the actual linker (lld may be selected above).
+if(is_macos OR is_linux)
+    if(is_ci OR is_nix_compiler)
+        if(is_macos)
+            set(fatal_warnings_flag "-Wl,-fatal_warnings")
+        else()
+            set(fatal_warnings_flag "-Wl,--fatal-warnings")
+        endif()
+        message(
+            STATUS
+            "Treating all linker warnings as errors (${fatal_warnings_flag})"
+        )
+        target_link_options(common INTERFACE "${fatal_warnings_flag}")
+        unset(fatal_warnings_flag)
+    elseif(is_macos)
+        set(silence_flag "-Wl,-deployment_target_mismatches,suppress")
+        set(probe_flags ${fuse_ld_flag} "${silence_flag}")
+        include(CheckLinkerFlag)
+        check_linker_flag(
+            CXX
+            "${probe_flags}"
+            have_deployment_target_mismatches
+        )
+        if(have_deployment_target_mismatches)
+            message(
+                STATUS
+                "Silencing macOS deployment target mismatch warnings (${silence_flag})"
+            )
+            target_link_options(common INTERFACE "${silence_flag}")
+        endif()
+        unset(probe_flags)
+        unset(silence_flag)
+    endif()
+endif()
+unset(fuse_ld_flag)
+
 if(assert)
     foreach(var_ CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_RELEASE)
         string(REGEX REPLACE "[-/]DNDEBUG" "" ${var_} "${${var_}}")

cmake/XrplCore.cmake

@@ -51,6 +51,8 @@ target_compile_options(
 
 target_link_libraries(xrpl.libpb PUBLIC protobuf::libprotobuf gRPC::grpc++)
 
+add_dependencies(tidy_prerequisites xrpl.libpb)
+
 # TODO: Clean up the number of library targets later.
 add_library(xrpl.imports.main INTERFACE)
 
@@ -79,7 +81,7 @@ include(target_link_modules)
 add_module(xrpl beast)
 target_link_libraries(xrpl.libxrpl.beast PUBLIC xrpl.imports.main)
 
-include(GitInfo)
+include(XrplVersion)
 add_module(xrpl git)
 target_compile_definitions(
     xrpl.libxrpl.git
@@ -109,6 +111,11 @@ target_link_libraries(
     xrpl.libxrpl.protocol
     PUBLIC xrpl.libxrpl.crypto xrpl.libxrpl.git xrpl.libxrpl.json
 )
+# Only on BuildInfo.cpp, so a new version does not rebuild the whole module.
+set_source_files_properties(
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/libxrpl/protocol/BuildInfo.cpp
+    PROPERTIES COMPILE_DEFINITIONS XRPLD_VERSION="${XRPLD_VERSION}"
+)
 
 # Level 05
 add_module(xrpl protocol_autogen)
@@ -133,6 +140,12 @@ target_link_libraries(
 add_module(xrpl resource)
 target_link_libraries(xrpl.libxrpl.resource PUBLIC xrpl.libxrpl.protocol)
 
+add_module(xrpl peerfinder)
+target_link_libraries(
+    xrpl.libxrpl.peerfinder
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.protocol
+)
+
 # Level 08
 add_module(xrpl net)
 target_link_libraries(
@@ -201,6 +214,16 @@ target_link_libraries(
 add_module(xrpl tx)
 target_link_libraries(xrpl.libxrpl.tx PUBLIC xrpl.libxrpl.ledger)
 
+add_module(xrpl consensus)
+target_link_libraries(
+    xrpl.libxrpl.consensus
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.json
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.ledger
+)
+
 add_library(xrpl.libxrpl)
 set_target_properties(xrpl.libxrpl PROPERTIES OUTPUT_NAME xrpl)
 
@@ -220,6 +243,7 @@ target_link_modules(
     beast
     conditions
     config
+    consensus
     core
     crypto
     git
@@ -227,6 +251,7 @@ target_link_modules(
     ledger
     net
     nodestore
+    peerfinder
     protocol
     protocol_autogen
     rdb
@@ -247,6 +272,7 @@ target_link_modules(
 
 if(xrpld)
     add_executable(xrpld)
+    patch_nix_binary(xrpld)
     if(tests)
         target_compile_definitions(xrpld PUBLIC ENABLE_TESTS)
         target_compile_definitions(
@@ -275,7 +301,14 @@ if(xrpld)
         target_sources(xrpld PRIVATE ${sources})
     endif()
 
-    target_link_libraries(xrpld Xrpl::boost Xrpl::opts Xrpl::libs xrpl.libxrpl)
+    target_link_libraries(
+        xrpld
+        Xrpl::boost
+        Xrpl::opts
+        Xrpl::libs
+        xrpl.libxrpl
+        rpcspec::rpcspec
+    )
     exclude_if_included(xrpld)
     # define a macro for tests that might need to
     # be excluded or run differently in CI environment
@@ -292,4 +325,13 @@ if(xrpld)
             PRIVATE ${CMAKE_SOURCE_DIR}/external/antithesis-sdk
         )
     endif()
+
+    # The xrpld headers are not built with add_module, so verify them against
+    # the executable's own compile environment.
+    if(verify_headers)
+        verify_target_headers(xrpld "${CMAKE_CURRENT_SOURCE_DIR}/src/xrpld")
+        if(tests)
+            verify_target_headers(xrpld "${CMAKE_CURRENT_SOURCE_DIR}/src/test")
+        endif()
+    endif()
 endif()

cmake/XrplCov.cmake

@@ -44,10 +44,11 @@ setup_target_for_coverage_gcovr(
     EXCLUDE
         "src/test"
         "src/tests"
+        "src/benchmarks"
         "include/xrpl/beast/test"
         "include/xrpl/beast/unit_test"
         "${CMAKE_BINARY_DIR}/pb-xrpl.libpb"
-    DEPENDENCIES xrpld xrpl_tests
+    DEPENDENCIES xrpld xrpl_tests xrpld_tests
 )
 
 add_code_coverage_to_target(opts INTERFACE)

cmake/XrplPackaging.cmake

@@ -1,7 +1,7 @@
 #[===================================================================[
    Linux packaging support: 'package' target.
 
-   The packaging script (package/build_pkg.sh) installs to FHS-standard
+   The packaging script (package/build_pkg.py) installs to FHS-standard
    paths (/usr/bin, /etc/xrpld, etc.) regardless of CMAKE_INSTALL_PREFIX,
    so no prefix guard is needed here.
 #]===================================================================]
@@ -25,20 +25,39 @@ if(NOT (RPMBUILD_EXECUTABLE OR DPKG_BUILDPACKAGE_EXECUTABLE))
     return()
 endif()
 
-set(package_env
-    SRC_DIR=${CMAKE_SOURCE_DIR}
-    BUILD_DIR=${CMAKE_BINARY_DIR}
-    PKG_VERSION=${xrpld_version}
-    PKG_RELEASE=${pkg_release}
-)
+if(NOT TARGET xrpld)
+    message(STATUS "xrpld=ON is required; 'package' target not available")
+    return()
+endif()
+
+if(NOT TARGET validator-keys)
+    message(
+        STATUS
+        "validator_keys=ON is required; 'package' target not available"
+    )
+    return()
+endif()
+
+if(DPKG_BUILDPACKAGE_EXECUTABLE)
+    set(pkg_type deb)
+else()
+    set(pkg_type rpm)
+endif()
+
+# Unquoted below, so an empty value adds no argument at all.
+set(pkg_variant_option "")
+if(assert)
+    set(pkg_variant_option --variant=assert)
+endif()
 
 add_custom_target(
     package
     COMMAND
-        ${CMAKE_COMMAND} -E env ${package_env}
-        ${CMAKE_SOURCE_DIR}/package/build_pkg.sh
+        ${CMAKE_SOURCE_DIR}/package/build_pkg.py --package-type=${pkg_type}
+        --build-dir=${CMAKE_BINARY_DIR} --pkg-release=${pkg_release}
+        ${pkg_variant_option} --channel=UNRELEASED
     WORKING_DIRECTORY ${CMAKE_BINARY_DIR}
-    DEPENDS xrpld
-    COMMENT "Building Linux package (deb/rpm inferred from host tooling)"
+    DEPENDS xrpld validator-keys
+    COMMENT "Building Linux ${pkg_type} package"
     VERBATIM
 )

cmake/XrplProtocolAutogen.cmake

@@ -2,21 +2,22 @@
    Protocol Autogen - Code generation for protocol wrapper classes
 #]===================================================================]
 
+# The repository root, derived from the location of this file rather than from
+# the including project, so that the targets below can also be offered on their
+# own by cmake/codegen/CMakeLists.txt.
+get_filename_component(XRPL_ROOT "${CMAKE_CURRENT_LIST_DIR}/.." ABSOLUTE)
+
 set(CODEGEN_VENV_DIR
-    "${CMAKE_CURRENT_SOURCE_DIR}/.venv"
+    "${XRPL_ROOT}/.venv"
     CACHE PATH
     "Path to a Python virtual environment for code generation. A venv will be created here by setup_code_gen and used to run generation scripts."
 )
 
 # 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}/cmake/scripts/codegen")
+set(MACRO_DIR "${XRPL_ROOT}/include/xrpl/protocol/detail")
+set(AUTOGEN_HEADER_DIR "${XRPL_ROOT}/include/xrpl/protocol_autogen")
+set(AUTOGEN_TEST_DIR "${XRPL_ROOT}/src/tests/libxrpl/protocol_autogen")
+set(SCRIPTS_DIR "${XRPL_ROOT}/cmake/scripts/codegen")
 
 # Input macro files
 set(TRANSACTIONS_MACRO "${MACRO_DIR}/transactions.macro")
@@ -114,14 +115,14 @@ if(CODEGEN_VENV_DIR)
         setup_code_gen
         COMMAND ${Python3_EXECUTABLE} -m venv "${CODEGEN_VENV_DIR}"
         COMMAND ${CODEGEN_PYTHON} -m pip install -r "${REQUIREMENTS_FILE}"
-        WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
+        WORKING_DIRECTORY "${XRPL_ROOT}"
         COMMENT "Creating venv and installing code generation dependencies..."
     )
 else()
     add_custom_target(
         setup_code_gen
         COMMAND ${Python3_EXECUTABLE} -m pip install -r "${REQUIREMENTS_FILE}"
-        WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
+        WORKING_DIRECTORY "${XRPL_ROOT}"
         COMMENT "Installing code generation dependencies..."
     )
 endif()
@@ -139,8 +140,8 @@ add_custom_target(
         -DSFIELDS_MACRO=${SFIELDS_MACRO}
         -DAUTOGEN_HEADER_DIR=${AUTOGEN_HEADER_DIR}
         -DAUTOGEN_TEST_DIR=${AUTOGEN_TEST_DIR} -P
-        "${CMAKE_CURRENT_SOURCE_DIR}/cmake/XrplProtocolAutogenRun.cmake"
-    WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
+        "${CMAKE_CURRENT_LIST_DIR}/XrplProtocolAutogenRun.cmake"
+    WORKING_DIRECTORY "${XRPL_ROOT}"
     COMMENT "Running protocol code generation..."
     SOURCES ${ALL_INPUT_FILES}
 )

cmake/XrplSanitizers.cmake

@@ -14,11 +14,9 @@
 include_guard(GLOBAL)
 include(CompilationEnv)
 
-if(NOT DEFINED SANITIZERS)
-    set(SANITIZERS_ENABLED FALSE)
+if(NOT SANITIZERS_ENABLED)
     return()
 endif()
-set(SANITIZERS_ENABLED TRUE)
 
 message(STATUS "=== Configuring Sanitizers ===")
 message(STATUS "  SANITIZERS: ${SANITIZERS}")