Merge branch 'pratik/otel-phase4-consensus-tracing' into pratik/otel-phase5-docs-deployment

develop's new fix-gtest-names pre-commit hook requires a snake_case test-case
name. CI runs it with --all-files, so the existing CamelCase names fail the
check on every branch that carries these files.

.clang-tidy

@@ -75,6 +75,8 @@ Checks: "-*,
 # 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
@@ -83,6 +85,8 @@ CheckOptions:
 
   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

.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"
@@ -36,3 +58,15 @@ ignore:
   - "src/tests/"
   - "include/xrpl/beast/test/"
   - "include/xrpl/beast/unit_test/"
+  # Telemetry modules. Telemetry compiles in by default (conanfile.py,
+  # CMakeLists.txt), but the unit-test suite never starts an exporter, so these
+  # files record no coverage. This block belongs on the earliest branch that
+  # adds telemetry code — codecov config only flows child-ward, so an ignore
+  # added on a later branch can never cover the branches before it.
+  - "src/xrpld/telemetry/"
+  - "src/libxrpl/telemetry/"
+  - "include/xrpl/telemetry/"
+  # Per-module span-name and span-label constant headers: compile-time
+  # constants only, colocated with their subsystem rather than under telemetry/.
+  - "**/*SpanNames.h"
+  - "**/*SpanLabels.h"

.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
@@ -30,7 +31,9 @@ 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
@@ -61,11 +64,14 @@ words:
   - blindings
   - bookdir
   - Bougalis
+  - bthomee
   - Britto
   - Btrfs
   - Buildx
   - canonicality
+  - CGNAT
   - canonicalised
+  - cctools
   - changespq
   - checkme
   - choco
@@ -107,6 +113,7 @@ words:
   - disablerepo
   - distro
   - doxyfile
+  - dsymutil
   - dxrpl
   - elgamal
   - enabled
@@ -115,6 +122,7 @@ words:
   - envrc
   - exceptioned
   - EXPECT_STREQ
+  - exfiltration
   - Falco
   - fcontext
   - finalizers
@@ -123,6 +131,8 @@ words:
   - fsanitize
   - funclets
   - Gamal
+  - gantt
+  - Gantt
   - gcov
   - gcovr
   - ghead
@@ -130,11 +140,15 @@ words:
   - godexsoft
   - gpgcheck
   - gpgkey
+  - Hinnant
   - hotwallet
+  - hicpp
+  - htpasswd
   - hwaddress
   - hwrap
   - ifndef
   - inequation
+  - Injectivity
   - insuf
   - insuff
   - invasively
@@ -163,18 +177,18 @@ words:
   - llection
   - LOCALGOOD
   - logwstream
+  - Lombrozo
+  - lresolv
   - lseq
   - lsmf
   - ltype
   - mathbunnyru
   - mcmodel
   - MEMORYSTATUSEX
-  - MPTAMM
-  - MPTDEX
   - Merkle
-  - Metafuncton
   - misprediction
   - missingok
+  - MPTAMM
   - mptbalance
   - MPTDEX
   - mptflags
@@ -200,6 +214,7 @@ words:
   - nftokens
   - nftpage
   - nikb
+  - Nikolaos
   - nixfmt
   - nixos
   - nixpkgs
@@ -208,6 +223,7 @@ words:
   - nonxrp
   - noreplace
   - noripple
+  - nostd
   - nostdinc
   - notifempty
   - nudb
@@ -216,6 +232,9 @@ words:
   - Nyffenegger
   - onlatest
   - ostr
+  - otelc
+  - otool
+  - oxalica
   - pargs
   - partitioner
   - paychan
@@ -224,6 +243,7 @@ words:
   - permdex
   - perminute
   - permissioned
+  - pimpl
   - pointee
   - populator
   - preauth
@@ -243,12 +263,17 @@ words:
   - queuable
   - Raphson
   - rcflags
+  - reparent
   - replayer
+  - repodata
+  - repomd
   - rerandomize
   - rerandomization
   - rerandomized
   - rerandomizes
   - rerere
+  - retargeted
+  - retargets
   - retriable
   - RIPD
   - ripdtop
@@ -262,6 +287,8 @@ words:
   - Rohrs
   - roundings
   - rustc
+  - rustfmt
+  - rustup
   - sahyadri
   - Satoshi
   - scons
@@ -282,6 +309,7 @@ words:
   - sles
   - soci
   - socidb
+  - Sonatype
   - sponsee
   - sponsees
   - SRPMS
@@ -301,11 +329,14 @@ words:
   - summands
   - superpeer
   - superpeers
+  - Swatinem
   - takergets
   - takerpays
   - ters
   - TMEndpointv2
+  - toolchain
   - tparam
+  - traceql
   - trixie
   - tx
   - txid
@@ -313,6 +344,7 @@ words:
   - txjson
   - txn
   - txns
+  - txqueue
   - txs
   - ubsan
   - UBSAN
@@ -327,6 +359,7 @@ words:
   - unfindable
   - unflatten
   - unfund
+  - ungated
   - unimpair
   - unroutable
   - unscalable
@@ -337,6 +370,7 @@ words:
   - unsquelch
   - unsquelched
   - unsquelching
+  - unsuffixed
   - unvalidated
   - unveto
   - unvetoed
@@ -354,12 +388,18 @@ words:
   - wthread
   - xbridge
   - xchain
+  - xcrun
   - ximinez
   - XMACRO
+  - xored
   - xrpkuwait
   - xrpl
   - xrpld
   - xrplf
   - xxhash
   - xxhasher
-  - CGNAT
+  - xychart
+  - zpages
+  - zstdio
+  - pratik
+  - dedup

.envrc

@@ -1 +1,10 @@
+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

.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()
 

.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 +1,44 @@
+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 takes it from BuildInfo.cpp and
+    # appends the commit hash as build metadata, joined with a plus sign because a
+    # Conan version cannot contain two hyphens.
+    - name: Determine version
+      id: version
+      shell: bash
+      env:
+        IS_TAG: ${{ startsWith(github.ref, 'refs/tags/') }}
+        REF_NAME: ${{ github.ref_name }}
+        SHA: ${{ github.sha }}
+      run: |
+        if [[ "${IS_TAG}" == "true" ]]; then
+            version="${REF_NAME}"
+        else
+            version="$(awk -F'"' '/versionString =/ { print $2 }' src/libxrpl/protocol/BuildInfo.cpp)"
+            if [[ -z "${version}" ]]; then
+                echo "Unable to read versionString from BuildInfo.cpp." >&2
+                exit 1
+            fi
+            version="${version}+${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@7cc0e4a8d9d0b838f92c48d312856b190341bbba

.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

@@ -1,9 +1,6 @@
 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
@@ -22,6 +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
@@ -45,6 +53,10 @@ libxrpl.shamap > xrpl.basics
 libxrpl.shamap > xrpl.nodestore
 libxrpl.shamap > xrpl.protocol
 libxrpl.shamap > xrpl.shamap
+libxrpl.telemetry > xrpl.basics
+libxrpl.telemetry > xrpl.config
+libxrpl.telemetry > xrpl.protocol
+libxrpl.telemetry > xrpl.telemetry
 libxrpl.tx > xrpl.basics
 libxrpl.tx > xrpl.conditions
 libxrpl.tx > xrpl.core
@@ -52,14 +64,15 @@ libxrpl.tx > xrpl.json
 libxrpl.tx > xrpl.ledger
 libxrpl.tx > xrpl.protocol
 libxrpl.tx > xrpl.server
+libxrpl.tx > xrpl.telemetry
 libxrpl.tx > xrpl.tx
 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
@@ -74,18 +87,14 @@ test.app > xrpl.tx
 test.basics > test.jtx
 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.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
@@ -100,10 +109,6 @@ 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.json > test.jtx
 test.json > xrpl.json
 test.jtx > test.unit_test
@@ -112,6 +117,7 @@ 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
@@ -129,12 +135,9 @@ 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
@@ -143,19 +146,13 @@ 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
@@ -189,20 +186,28 @@ 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.telemetry
 tests.libxrpl > xrpl.tx
 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.consensus > xrpl.telemetry
 xrpl.core > xrpl.basics
 xrpl.core > xrpl.json
 xrpl.core > xrpl.protocol
@@ -217,6 +222,8 @@ 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
@@ -236,30 +243,32 @@ xrpl.server > xrpl.resource
 xrpl.shamap > xrpl.basics
 xrpl.shamap > xrpl.nodestore
 xrpl.shamap > xrpl.protocol
+xrpl.telemetry > xrpl.basics
+xrpl.telemetry > xrpl.config
 xrpl.tx > xrpl.basics
 xrpl.tx > xrpl.core
 xrpl.tx > xrpl.ledger
 xrpl.tx > xrpl.protocol
+xrpl.tx > xrpl.telemetry
 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 > xrpld.telemetry
 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.telemetry
 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
@@ -268,30 +277,33 @@ 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 > xrpld.telemetry
 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.telemetry
 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.app
-xrpld.perflog > xrpld.rpc
 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
@@ -305,9 +317,13 @@ xrpld.rpc > xrpl.rdb
 xrpld.rpc > xrpl.resource
 xrpld.rpc > xrpl.server
 xrpld.rpc > xrpl.shamap
+xrpld.rpc > xrpl.telemetry
 xrpld.rpc > xrpl.tx
 xrpld.shamap > xrpl.basics
 xrpld.shamap > xrpld.core
 xrpld.shamap > xrpl.nodestore
 xrpld.shamap > xrpl.protocol
 xrpld.shamap > xrpl.shamap
+xrpld.telemetry > xrpl.basics
+xrpld.telemetry > xrpl.consensus
+xrpld.telemetry > xrpl.telemetry

.github/scripts/otel-naming/README.md

@@ -0,0 +1,70 @@
+# OTel naming-consistency check
+
+`check_otel_naming.py` enforces the OpenTelemetry span-attribute naming
+convention documented in
+[CONTRIBUTING.md](../../../CONTRIBUTING.md#telemetry-span-attribute-naming)
+across every layer of the telemetry pipeline. The `*SpanNames.h` constants are
+the single source of truth (L1); every other layer must agree with them.
+
+## Running locally
+
+```
+python .github/scripts/otel-naming/check_otel_naming.py
+```
+
+It takes no arguments, can be run from any directory inside the repo, and uses
+only the Python standard library (no `pip install`, matching the levelization
+check). A non-zero exit code means a violation was found; the output lists each
+violation as `RULE | location | token | expected`.
+
+## What it checks
+
+The valid key set is **derived dynamically from the OTel code** — there is no
+hardcoded allowlist:
+
+- **L1 keys** come from the `namespace attr { ... }` blocks of every
+  `*SpanNames.h`, resolving the `makeStr("x")` / `join(seg::a, seg::b)` DSL
+  (cross-file, so `join(seg::rpc, ...)` resolves `seg::rpc` from the base
+  `SpanNames.h`). Each constant is resolved against **its own** header, so two
+  headers that define a same-named constant (e.g. a base `attr::ledgerHash` and
+  a domain `attr::ledgerHash`) each contribute their real wire key — a later
+  header cannot clobber an earlier one's value in a flat table.
+- **Legitimate dotted keys** = ONLY the keys the code actually sets as resource
+  attributes, i.e. the entries inside `Telemetry.cpp`'s `Resource::Create({...})`
+  call: the `semconv::service::*` keys (`service.*`) plus any `attr::<name>`
+  constants passed there (`xrpl.network.*`). A dotted key that is _declared_ in a
+  header but never set as a resource attr is a span attribute in resource
+  clothing — a Rule-A violation, even if it lives in the base `SpanNames.h`.
+
+### Rules (each fails the build, when its inputs are present)
+
+| Rule | Check                                                                                                                                                                                                                                                                                    |
+| ---- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| A    | No stray dotted span-attribute key (only the derived resource keys may be dotted).                                                                                                                                                                                                       |
+| G    | Attribute keys are `lower_snake_case` (`^[a-z][a-z0-9_]*$` per dot-segment) — no camelCase, UPPERCASE, or spaces.                                                                                                                                                                        |
+| F    | No string literals as attribute keys or span-name arguments in `setAttribute`/`addEvent`/`span`/`rootSpan`/`childSpan` (`rootSpan` shares `span`'s `(cat, prefix, name)` signature). Attribute _values_ are exempt (runtime data); `*SpanNames.h` definitions and test files are exempt. |
+| B    | Every collector `spanmetrics.dimensions` name exists in the L1 key set.                                                                                                                                                                                                                  |
+| C    | Every Tempo span-filter tag exists in the L1 key set.                                                                                                                                                                                                                                    |
+| D    | Every dashboard label resolves to an L1 span attribute, a native-metric label (L6, emitted by MetricsRegistry), or a Prometheus/Grafana builtin. TraceQL scope prefixes (`span.`/`resource.`/…) are stripped before the L1 lookup.                                                       |
+| E    | No dotted `xrpl.<domain>.<field>` attribute key in the runbook (only the L1 resource attrs `xrpl.network.*` may be dotted). Span names, filenames, OTel-standard keys, and metric labels are not flagged.                                                                                |
+
+Rule F runs **unconditionally** (it is a purely syntactic check on the
+call-sites and needs no `*SpanNames.h`), so a code path that calls
+`SpanGuard::span`/`setAttribute` directly without ever defining a header is
+still caught.
+
+### Warnings (printed, never fail the build)
+
+| Rule | Check                                                                                                                                                                                                                                                                                                                                                                                      |
+| ---- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| H    | A namespace-qualified constant (e.g. `foo::bar::myKey`) used at a telemetry call-site is not defined in any `*SpanNames.h`. The constant should live in the proper header; defining it in-place bypasses rules A/G/F. Warns rather than fails — the argument may be a legitimately dynamic value, and the header may live on a later branch. Bare locals and `std::` names are not warned. |
+
+## Presence-gated
+
+Every rule runs **only when the source files it needs are present** in the tree
+and is otherwise skipped (printed as `SKIP: <rule> — <reason>`), never failed.
+This keeps the check correct no matter how telemetry work is split across PRs —
+a stacked chain, one large PR, or independent per-stage PRs where (for example)
+the collector config lands before the dashboards. The collector/Tempo/dashboard/
+runbook layers are introduced in later phases; on a branch without them, only
+the L1-intrinsic rules (A, G, F) run.

.github/scripts/otel-naming/check_otel_naming.py

@@ -0,0 +1,916 @@
+#!/usr/bin/env python3
+
+"""
+Usage: check_otel_naming.py
+This script takes no parameters and can be called from any directory inside the
+repository (it locates the repo root via `git rev-parse`).
+
+Enforces the OpenTelemetry span-attribute naming convention documented in
+CONTRIBUTING.md ("Telemetry span attribute naming") across every layer of the
+telemetry pipeline. The `*SpanNames.h` constants are the single source of truth
+(L1); every other layer must agree with them.
+
+Design principles
+-----------------
+1. No hardcoded allowlist. The set of valid attribute keys — including which
+   dotted keys are legitimate resource attributes — is derived dynamically by
+   parsing the repository's own OTel code:
+     * `*SpanNames.h` `namespace attr { ... }` blocks (the underscore/bare keys
+       and the `join(seg::..., ...)` dotted resource compositions), and
+     * the keys the code passes to `Resource::Create({ ... })` in Telemetry.cpp
+       (the standard `semconv::service::*` keys -> service.name/version/...).
+   The one narrow, explicit exception is EXTERNAL_INFRA_LABELS (Rule D):
+   identity labels stamped by infrastructure outside this repo's OTel code
+   (the perf-iac harness), which by definition have no source in-tree to
+   derive from. Kept separate from the generic Prometheus/Grafana builtins
+   set so the exception stays visible rather than blending into "things
+   every OTel setup has".
+
+2. Presence-gated enforcement. Every rule runs ONLY when the source files it
+   needs are present in the tree, and is otherwise skipped (never failed). This
+   keeps the check correct no matter how work is split across PRs: a stacked
+   chain, one large PR, or independent per-stage PRs where (for example) the
+   collector config lands in a different PR than the dashboards. The check never
+   assumes a file from another phase/PR exists.
+
+Layers
+------
+  L1 code      : src/**/*SpanNames.h, include/**/*SpanNames.h  (ground truth)
+  L1 resource  : src/libxrpl/telemetry/Telemetry.cpp           (dotted allowlist)
+  L1 callsites : setAttribute/addEvent/span/rootSpan/childSpan in src/**,
+                 include/**
+  L2 collector : docker/telemetry/otel-collector-config.yaml   (spanmetrics dims)
+  L3 tempo     : docker/telemetry/tempo.yaml                    (span filter tags)
+  L4 dashboards: docker/telemetry/grafana/dashboards/*.json     (PromQL labels)
+  L5 runbook   : docs/telemetry-runbook.md                      (attr tables)
+  L6 metrics   : MetricsRegistry.cpp instrument labels          (native-metric
+                 label keys, a valid dashboard-label source besides L1)
+
+Rules (each FAILS the build, when its inputs are present)
+---------------------------------------------------------
+  A  No stray dotted span-attribute key. A dotted `<a>.<b>` used as a span
+     attribute that is not in the derived resource-key set is a violation.
+  G  Attribute keys must be lower_snake_case (^[a-z][a-z0-9_]*$ per segment).
+     Flags camelCase, UPPERCASE, spaces, and other stray characters.
+  F  No string literals as attribute keys or span-name arguments. The
+     setAttribute/addEvent key and the span/rootSpan/childSpan prefix/name args
+     must reference a *SpanNames.h constant, never a "literal". Attribute VALUES
+     are exempt (runtime data). Definitions inside *SpanNames.h are exempt, and
+     test files are exempt (they pass arbitrary literals to exercise the API).
+  B  Every collector spanmetrics dimension exists in the L1 key set.
+  C  Every tempo span-filter tag exists in the L1 key set.
+  D  Every dashboard label resolves to an L1 span attribute, an L6
+     native-metric label, or a builtin. TraceQL `span.`/`resource.` scope
+     prefixes are stripped before the L1 lookup.
+  E  No dotted `xrpl.<domain>.<field>` attribute key in the runbook (only the
+     L1 resource attrs xrpl.network.* may be dotted). Span names, filenames,
+     OTel-standard keys, and metric labels are not flagged.
+
+Warnings (printed, but do NOT fail the build)
+----------------------------------------------
+  H  A constant referenced at a telemetry call-site is not defined in any
+     *SpanNames.h. Span constants should live in the corresponding
+     *SpanNames.h (single source of truth); defining one in-place bypasses the
+     naming rules. A warning (not a failure) because the argument may instead
+     be a legitimately dynamic local (e.g. a computed span-name leaf).
+
+Exit code is non-zero if any present-and-enforced rule finds a violation.
+Warnings never change the exit code.
+"""
+
+import re
+import subprocess
+import sys
+from pathlib import Path
+from typing import Dict, List, Optional, Set, Tuple
+
+# ---------------------------------------------------------------------------
+# Repo location
+# ---------------------------------------------------------------------------
+
+
+def repo_root() -> Path:
+    """Return the repository root, so the script works from any CWD.
+
+    Exits with a readable message (not a traceback) if git is unavailable or the
+    CWD is outside a repository."""
+    try:
+        out = subprocess.run(
+            ["git", "rev-parse", "--show-toplevel"],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        print(
+            "error: check_otel_naming.py must be run inside the git repository.",
+            file=sys.stderr,
+        )
+        sys.exit(2)
+    return Path(out.stdout.strip())
+
+
+def read_source(path: Path) -> str:
+    """Read a file as UTF-8, tolerating stray non-UTF-8 bytes rather than
+    crashing the whole check on one bad byte."""
+    return path.read_text(encoding="utf-8", errors="ignore")
+
+
+# ---------------------------------------------------------------------------
+# Regexes (compiled once)
+# ---------------------------------------------------------------------------
+
+# A segment/string constant definition: `inline constexpr auto NAME = <expr>;`
+CONST_DEF = re.compile(r"inline\s+constexpr\s+auto\s+(\w+)\s*=\s*(.+?);", re.DOTALL)
+MAKESTR = re.compile(r'makeStr\(\s*"([^"]*)"\s*\)')
+# A `namespace <name> {` opener, to track which namespace a constant lives in.
+NS_OPEN = re.compile(r"namespace\s+([\w:]+)\s*\{")
+# A `using ::a::b::field;` re-export inside an attr block; captures the leaf.
+USING_DECL = re.compile(r"using\s+(?:::)?[\w:]*::(\w+)\s*;")
+# Telemetry call-sites whose string arguments must be constants, not literals.
+# Require a receiver so we match real SpanGuard calls, not std::span / a math
+# `span(...)` / a bare method declaration:
+#   - `SpanGuard::span(` / `SpanGuard::rootSpan(` / `SpanGuard::childSpan(`
+#     (static factories)
+#   - `<obj>.span(` / `<obj>->setAttribute(` etc.   (member call)
+# `span`/`rootSpan`/`childSpan` additionally require the `SpanGuard`/`.`/`->`
+# receiver; `setAttribute`/`addEvent` only ever exist on a guard, so a `.`/`->`
+# suffices. `rootSpan` shares `span`'s (cat, prefix, name) signature.
+CALLSITE = re.compile(
+    r"(?:SpanGuard::|\.|->)\s*(setAttribute|addEvent|span|rootSpan|childSpan)\s*\("
+)
+# A C++ string literal (used to flag literals inside call-site argument lists).
+STRING_LITERAL = re.compile(r'"((?:[^"\\]|\\.)*)"')
+# A C++ line comment (`//` ... end of line) and a block comment (`/* ... */`).
+LINE_COMMENT = re.compile(r"//[^\n]*")
+BLOCK_COMMENT = re.compile(r"/\*.*?\*/", re.DOTALL)
+# A TraceQL scope prefix on a label (`span.`, `resource.`, `event.`, etc.).
+# Dashboards reference span attributes in TraceQL as `span.<attr>`; the bare
+# attribute is what must exist in L1, so strip the scope before validating.
+TRACEQL_SCOPE = re.compile(r"^(?:span|resource|event|link|instrumentation_scope)\.")
+# An OTel metric label key as emitted in C++: `Add(.., {{"label", ...}})` /
+# `{{"label", value}}` instrument calls in MetricsRegistry.
+METRIC_LABEL = re.compile(r'\{\{\s*"([a-z_][a-z0-9_]*)"\s*,')
+
+
+def strip_comments(text: str) -> str:
+    """Remove C/C++ `//` line comments and `/* ... */` block comments.
+
+    Used only for L1 attribute-key extraction so that a commented-out or
+    illustrative `makeStr("...")` inside a `namespace attr` block does not leak
+    into the authoritative key set. Rule F deliberately does NOT strip comments
+    — it must still see `@code` doc-comment examples so their call-site
+    arguments are held to the constant-only convention.
+
+    String literals are not specially handled; a `//` or `/*` appearing inside a
+    string is vanishingly rare in the *SpanNames.h headers and would at worst
+    drop a constant from L1 (a conservative direction).
+    """
+    text = BLOCK_COMMENT.sub("", text)
+    text = LINE_COMMENT.sub("", text)
+    return text
+
+
+# ---------------------------------------------------------------------------
+# L1: parse *SpanNames.h into the authoritative key set
+# ---------------------------------------------------------------------------
+
+
+def find_spanname_headers(root: Path) -> List[Path]:
+    return sorted(
+        p
+        for p in list((root / "src").rglob("*SpanNames.h"))
+        + list((root / "include").rglob("*SpanNames.h"))
+        if p.is_file()
+    )
+
+
+def resolve_constants(
+    text: str, symbols: Optional[Dict[str, str]] = None
+) -> Dict[str, str]:
+    """Resolve `inline constexpr auto NAME = <makeStr/join expr>` to strings.
+
+    Supports the small constexpr DSL used by SpanNames.h:
+      makeStr("x")          -> "x"
+      join(a, b)            -> resolve(a) + "." + resolve(b)
+      seg::xrpl / attr::foo -> looked up in the symbol table
+    The optional `symbols` argument seeds (and is updated in place with) the
+    table, so a global pass over ALL *SpanNames.h headers can resolve
+    cross-file references such as `join(seg::rpc, ...)` where `seg::rpc` is
+    defined in the base SpanNames.h. Keys are stored by their bare name
+    (last `::` component), so `seg::rpc` and `rpc` both resolve.
+    """
+    if symbols is None:
+        symbols = {}
+
+    def resolve_expr(expr: str) -> Optional[str]:
+        expr = expr.strip()
+        m = MAKESTR.fullmatch(expr)
+        if m:
+            return m.group(1)
+        if expr.startswith("join(") and expr.endswith(")"):
+            args = split_top_level_args(expr[len("join(") : -1])
+            parts = [resolve_expr(a) for a in args]
+            if any(p is None for p in parts):
+                return None
+            return ".".join(p for p in parts if p is not None)
+        # Bare or qualified symbol reference, e.g. `seg::xrpl` or `networkId`.
+        key = expr.split("::")[-1]
+        return symbols.get(key, symbols.get(expr))
+
+    # Iterate definitions in source order so earlier symbols are available.
+    for m in CONST_DEF.finditer(text):
+        name, expr = m.group(1), m.group(2)
+        val = resolve_expr(expr)
+        if val is not None:
+            symbols[name] = val
+    return symbols
+
+
+def build_global_symbols(headers: List[Path]) -> Dict[str, str]:
+    """Resolve constants across ALL headers so cross-file `seg::`/`join`
+    references (e.g. `join(seg::rpc, ...)` in RpcSpanNames.h, where `seg::rpc`
+    lives in the base SpanNames.h) resolve. Base SpanNames.h is processed
+    first so its `seg::` segments seed the table."""
+    symbols: Dict[str, str] = {}
+    ordered = sorted(headers, key=lambda p: (p.name != "SpanNames.h", str(p)))
+    # Two passes: the first seeds segments, the second resolves dependents.
+    # Comments are stripped so a commented-out constant cannot seed the table.
+    for _ in range(2):
+        for h in ordered:
+            resolve_constants(strip_comments(read_source(h)), symbols)
+    return symbols
+
+
+def split_top_level_args(s: str) -> List[str]:
+    """Split a comma-separated arg list, respecting nested parentheses and
+    ignoring parens/commas that appear inside a "string literal" (so a value
+    like `setAttribute(k, ",")` does not get mis-split)."""
+    args, depth, cur = [], 0, ""
+    in_str = False
+    escaped = False
+    for ch in s:
+        if in_str:
+            cur += ch
+            if escaped:
+                escaped = False
+            elif ch == "\\":
+                escaped = True
+            elif ch == '"':
+                in_str = False
+            continue
+        if ch == '"':
+            in_str = True
+            cur += ch
+        elif ch == "(":
+            depth += 1
+            cur += ch
+        elif ch == ")":
+            depth -= 1
+            cur += ch
+        elif ch == "," and depth == 0:
+            args.append(cur)
+            cur = ""
+        else:
+            cur += ch
+    if cur.strip():
+        args.append(cur)
+    return args
+
+
+def attr_namespace_spans(text: str) -> List[str]:
+    """Return the source text of each `namespace attr { ... }` block in `text`.
+
+    Brace-matched over the whole (comment-stripped) text, so a definition that
+    wraps across several physical lines is contained in one span. Nested braces
+    inside the block are balanced correctly."""
+    spans: List[str] = []
+    for opener in NS_OPEN.finditer(text):
+        if opener.group(1).split("::")[-1] != "attr":
+            continue
+        # Walk from the opening brace, balancing nesting to the matching close.
+        i = opener.end()  # one char past the namespace's `{`
+        depth = 1
+        start = i
+        while i < len(text) and depth > 0:
+            c = text[i]
+            if c == "{":
+                depth += 1
+            elif c == "}":
+                depth -= 1
+            i += 1
+        spans.append(text[start : i - 1])
+    return spans
+
+
+def attr_keys_from_header(path: Path, symbols: Dict[str, str]) -> Set[str]:
+    """Return the set of attribute-key strings declared in a header's
+    `namespace attr { ... }` block(s). `symbols` is the global cross-file
+    table, used ONLY to seed `seg::`/segment references for `join(...)`
+    resolution — never to look up an attr constant's value.
+
+    A constant DEFINED in this header is resolved against this header's OWN
+    text, so two headers that each define a same-named constant (e.g. the base
+    `attr::ledgerHash = xrpl.ledger.hash` and consensus
+    `attr::ledgerHash = ledger_hash`) each report their real wire key. The
+    global table is keyed by bare name and would otherwise let a later header
+    clobber an earlier one, erasing the real key from L1 (a Rule-A blind spot).
+    A `using`-re-export, by contrast, imports a constant defined elsewhere, so
+    it is resolved against the global table.
+
+    Comments are stripped first (a commented constant must not enter L1), and
+    each attr block is brace-matched over the whole text so multi-line
+    `inline constexpr auto NAME = join(\\n  ...);` definitions are captured."""
+    text = strip_comments(read_source(path))
+    # Local table: the global segments/symbols seed cross-file `join` parts,
+    # then this header's own definitions overwrite any same-named global entry
+    # so a locally-defined attr resolves to ITS value, not another header's.
+    local = dict(symbols)
+    resolve_constants(text, local)
+    keys: Set[str] = set()
+    for block in attr_namespace_spans(text):
+        for md in CONST_DEF.finditer(block):
+            # Resolve a locally-defined constant against the LOCAL table; this
+            # captures makeStr("x") and join(seg::y, ...) with the header's own
+            # value, immune to cross-header bare-name collisions.
+            val = local.get(md.group(1))
+            if val is not None:
+                keys.add(val)
+        # `using ::ns::attr::field;` re-exports a constant defined in ANOTHER
+        # header (e.g. PeerSpanNames imports the base ledgerHash). Resolve the
+        # imported name against the global table.
+        for um in USING_DECL.finditer(block):
+            val = symbols.get(um.group(1))
+            if val is not None:
+                keys.add(val)
+    return keys
+
+
+# ---------------------------------------------------------------------------
+# Reporting
+# ---------------------------------------------------------------------------
+
+
+class Report:
+    def __init__(self) -> None:
+        self.violations: List[Tuple[str, str, str, str]] = []
+        self.warnings: List[Tuple[str, str, str, str]] = []
+        self.skips: List[str] = []
+        self.checked: List[str] = []
+
+    def violation(self, rule: str, loc: str, token: str, expected: str) -> None:
+        self.violations.append((rule, loc, token, expected))
+
+    def warning(self, rule: str, loc: str, token: str, note: str) -> None:
+        """A non-fatal finding: printed, but does not fail the build. Used where
+        the script cannot be certain a finding is wrong (e.g. a constant used at
+        a call-site that is not defined in any *SpanNames.h — it might be a
+        misplaced constant, or a legitimately dynamic value)."""
+        self.warnings.append((rule, loc, token, note))
+
+    def skip(self, rule: str, reason: str) -> None:
+        self.skips.append(f"SKIP: {rule} — {reason}")
+
+    def ok(self, msg: str) -> None:
+        self.checked.append(f"OK:   {msg}")
+
+    def render_and_exit(self) -> None:
+        for line in self.skips:
+            print(line)
+        for line in self.checked:
+            print(line)
+        if self.warnings:
+            print("\nNaming-convention warnings (non-fatal):\n")
+            print(f"  {'RULE':<5} {'LOCATION':<48} {'TOKEN':<28} NOTE")
+            print(f"  {'-' * 5} {'-' * 48} {'-' * 28} {'-' * 30}")
+            for rule, loc, token, note in self.warnings:
+                print(f"  {rule:<5} {loc:<48} {token:<28} {note}")
+        if self.violations:
+            print("\nNaming-convention violations:\n")
+            print(f"  {'RULE':<5} {'LOCATION':<48} {'TOKEN':<28} EXPECTED")
+            print(f"  {'-' * 5} {'-' * 48} {'-' * 28} {'-' * 30}")
+            for rule, loc, token, expected in self.violations:
+                print(f"  {rule:<5} {loc:<48} {token:<28} {expected}")
+            print(
+                "\nSee CONTRIBUTING.md -> 'Telemetry span attribute naming'. "
+                "The *SpanNames.h constants are the single source of truth."
+            )
+            sys.exit(1)
+        print("\nAll present telemetry naming layers are consistent.")
+        sys.exit(0)
+
+
+def main() -> None:
+    root = repo_root()
+    report = Report()
+
+    # --- Build the L1 ground-truth key set (presence-gated) ----------------
+    headers = find_spanname_headers(root)
+    l1_keys: Set[str] = set()
+    if headers:
+        symbols = build_global_symbols(headers)
+        # Map each key to the header(s) that declare it, so Rule A can tell a
+        # legitimate resource attr (declared in the base SpanNames.h) from a
+        # stray dotted key declared in a domain header.
+        keys_by_header: Dict[Path, Set[str]] = {}
+        for h in headers:
+            hk = attr_keys_from_header(h, symbols)
+            keys_by_header[h] = hk
+            l1_keys |= hk
+        report.ok(
+            f"L1: {len(l1_keys)} attribute keys from {len(headers)} "
+            f"*SpanNames.h header(s)"
+        )
+    else:
+        report.skip("L1", "no *SpanNames.h present (not a naming-relevant tree)")
+        keys_by_header = {}
+
+    # --- Derive the legitimate dotted (resource) keys dynamically ----------
+    # ONLY the keys actually passed to Resource::Create() in Telemetry.cpp
+    # (semconv service.* + the attr:: constants set there, e.g. xrpl.network.*).
+    # A dotted key declared in a header but NOT set as a resource attr is a
+    # Rule-A violation, not an allowlist entry.
+    resource_symbols = symbols if headers else {}
+    dotted_allow = derive_dotted_resource_keys(root, resource_symbols, report)
+
+    # --- Rule A: no stray dotted span-attribute keys -----------------------
+    if l1_keys:
+        run_rule_a(keys_by_header, dotted_allow, report)
+    # --- Rule G: keys must be lower_snake_case -----------------------------
+    if l1_keys:
+        run_rule_g(keys_by_header, report)
+    # --- Rule F (+ Rule H): scan telemetry call-sites ----------------------
+    # Runs UNCONDITIONALLY: Rule F is a purely syntactic check (is this argument
+    # a literal?) and does not need the L1 key set, so a code path that uses
+    # SpanGuard::span/setAttribute directly without ever defining a *SpanNames.h
+    # is still caught. Rule H (warning) additionally flags constant references
+    # not defined in any *SpanNames.h.
+    header_symbols = spanname_symbol_names(headers)
+    run_rule_f(root, report, header_symbols)
+
+    # --- Cross-layer rules B/C/D/E (each presence-gated) -------------------
+    # L6 native-metric labels: span attributes are not the only valid dashboard
+    # labels — the MetricsRegistry emits OTel metrics whose label keys are an
+    # additional source of truth. Derive them dynamically (same principle as L1)
+    # so dashboards may reference them without tripping Rule D.
+    metric_labels = metric_label_names(root)
+    run_rule_b_collector(root, l1_keys, report)
+    run_rule_c_tempo(root, l1_keys, report)
+    run_rule_d_dashboards(root, l1_keys, metric_labels, report)
+    run_rule_e_runbook(root, l1_keys, report)
+
+    report.render_and_exit()
+
+
+def resource_create_block(text: str) -> str:
+    """Return the text inside the first `Resource::Create({ ... })` argument
+    list, brace-matched so nested `{key, value}` initializers are contained.
+    Empty string if the call is absent."""
+    m = re.search(r"Resource::Create\(\s*\{", text)
+    if not m:
+        return ""
+    i = m.end()  # one char past the opening `{`
+    depth, start = 1, i
+    while i < len(text) and depth > 0:
+        c = text[i]
+        if c == "{":
+            depth += 1
+        elif c == "}":
+            depth -= 1
+        i += 1
+    return text[start : i - 1]
+
+
+def derive_dotted_resource_keys(
+    root: Path, symbols: Dict[str, str], report: Report
+) -> Set[str]:
+    """Legitimate dotted keys = ONLY the keys the code actually sets as RESOURCE
+    attributes, i.e. the entries inside Telemetry.cpp's `Resource::Create({...})`
+    call: the standard semconv keys (`service.*`) plus any `attr::<name>`
+    constants passed there (resolved to their wire key via the global symbol
+    table, e.g. `attr::networkId` -> `xrpl.network.id`).
+
+    A dotted key DECLARED in a `*SpanNames.h` header but NOT passed to
+    Resource::Create() is a span attribute wearing the resource form — a Rule-A
+    violation, never allowlisted. Deriving the allowlist from the actual
+    resource call (not from "any dotted key in the base header") is what lets
+    Rule A catch a stray dotted span attr such as `xrpl.ledger.hash`."""
+    allow: Set[str] = set()
+    tele = root / "src" / "libxrpl" / "telemetry" / "Telemetry.cpp"
+    if not tele.is_file():
+        report.skip("resource-derive", "Telemetry.cpp not present")
+        return allow
+    block = resource_create_block(read_source(tele))
+    # semconv::<group>::k<CamelKey> -> the dotted OTel-standard key. The
+    # CamelKey already embeds the group, e.g. service::kServiceInstanceId
+    # -> service.instance.id. Split the CamelCase name into dotted lowercase
+    # segments; if it does not lead with the group, prepend the group.
+    for m in re.finditer(r"semconv::(\w+)::k(\w+)", block):
+        group, camel = m.group(1), m.group(2)
+        segments = camel_to_dotsegments(camel)
+        if segments and segments[0] == group:
+            allow.add(".".join(segments))
+        else:
+            allow.add(group + "." + ".".join(segments))
+    # attr::<name> constants set as resource attrs (e.g. networkId/networkType);
+    # resolve each to its wire key and allowlist only the dotted ones.
+    for m in re.finditer(r"attr::(\w+)", block):
+        val = symbols.get(m.group(1))
+        if val is not None and "." in val:
+            allow.add(val)
+    report.ok(f"resource dotted-key allowlist derived: {sorted(allow)}")
+    return allow
+
+
+def camel_to_dotsegments(s: str) -> List[str]:
+    """Split a CamelCase identifier into lowercase dot-segment parts, e.g.
+    `ServiceInstanceId` -> ['service', 'instance', 'id']."""
+    return [w.lower() for w in re.findall(r"[A-Z][a-z0-9]*", s)]
+
+
+def run_rule_a(
+    keys_by_header: Dict[Path, Set[str]], dotted_allow: Set[str], report: Report
+) -> None:
+    """Any dotted attribute key that is not an allowed resource key is a
+    violation, reported against the header that declares it."""
+    found = False
+    for h in sorted(keys_by_header):
+        for key in sorted(keys_by_header[h]):
+            if "." in key and key not in dotted_allow:
+                found = True
+                report.violation("A", h.name, key, "underscore form, not dotted")
+    if not found:
+        report.ok("A: no stray dotted span-attribute keys")
+
+
+# A lower_snake_case identifier segment: starts lowercase, then lowercase /
+# digits / underscores. No uppercase, no spaces, no camelCase.
+SNAKE_SEGMENT = re.compile(r"^[a-z][a-z0-9_]*$")
+
+
+def run_rule_g(keys_by_header: Dict[Path, Set[str]], report: Report) -> None:
+    """Every attribute key must be lower_snake_case. Bare/underscore keys must
+    match ^[a-z][a-z0-9_]*$; dotted resource keys must be lowercase
+    dot-separated segments (each segment lower_snake_case). Flags camelCase,
+    UPPERCASE, spaces, and other stray characters."""
+    found = False
+    for h in sorted(keys_by_header):
+        for key in sorted(keys_by_header[h]):
+            segments = key.split(".")
+            if all(SNAKE_SEGMENT.match(seg) for seg in segments):
+                continue
+            found = True
+            report.violation("G", h.name, key, "must be lower_snake_case")
+    if not found:
+        report.ok("G: all attribute keys are lower_snake_case")
+
+
+# Which argument positions of each call must be a constant (0-based). The
+# attribute VALUE position is intentionally absent: values are runtime data
+# (command names, hashes, counts), not naming-convention surface.
+#   setAttribute(key, value)        -> check arg 0 (key); value (arg 1) exempt
+#   addEvent(name[, attrs])         -> check arg 0 (event name)
+#   span(category, prefix, name)    -> check args 1,2 (prefix + span-name leaf)
+#   rootSpan(category, prefix, name)-> check args 1,2 (same signature as span)
+#   childSpan(name[, parentCtx])    -> check arg 0 (span-name leaf)
+CONSTANT_ARG_POSITIONS: Dict[str, Set[int]] = {
+    "setAttribute": {0},
+    "addEvent": {0},
+    "span": {1, 2},
+    "rootSpan": {1, 2},  # same signature as span(cat, prefix, name)
+    "childSpan": {0},
+}
+
+
+def is_test_path(path: Path) -> bool:
+    """True if the path is test code. Tests legitimately pass arbitrary literal
+    keys/names to exercise the API mechanics, so Rule F does not apply to them.
+    Matches a `test`/`tests` directory anywhere in the path (e.g. src/test/,
+    src/tests/, .../detail/tests/)."""
+    return any(part in ("test", "tests") for part in path.parts)
+
+
+# A constant reference passed at a call-site, e.g. `rpc_span::attr::command`
+# or a bare `myKey`. We capture the leaf identifier (after the last `::`).
+IDENTIFIER_ARG = re.compile(r"^[\s&*]*([A-Za-z_][\w:]*)\s*$")
+
+
+def spanname_symbol_names(headers: List[Path]) -> Set[str]:
+    """Every `inline constexpr auto NAME = ...;` symbol defined across the
+    *SpanNames.h headers, by bare name. Used by Rule H to tell whether a
+    constant referenced at a call-site actually lives in a SpanNames header."""
+    names: Set[str] = set()
+    for h in headers:
+        for m in CONST_DEF.finditer(strip_comments(read_source(h))):
+            names.add(m.group(1))
+    return names
+
+
+def run_rule_f(root: Path, report: Report, header_symbols: Set[str]) -> None:
+    """Walk every telemetry call-site (non-test, non-*SpanNames.h) and check the
+    constant-only argument positions of
+    setAttribute/addEvent/span/rootSpan/childSpan:
+
+      Rule F (FAIL): a string literal in a key / span-name position. Attribute
+        VALUES are exempt (runtime data).
+      Rule H (WARN): a constant reference whose name is not defined in any
+        *SpanNames.h. The constant should live in the corresponding
+        *SpanNames.h (single source of truth); defining it in-place bypasses
+        the naming rules. Warn rather than fail — the argument may instead be a
+        legitimately dynamic local (e.g. a computed span-name leaf)."""
+    found_f = False
+    sources = [
+        p
+        for base in ("src", "include")
+        for ext in ("*.h", "*.cpp")
+        for p in (root / base).rglob(ext)
+        if p.is_file()
+    ]
+    for path in sorted(sources):
+        if path.name.endswith("SpanNames.h") or is_test_path(path):
+            continue
+        text = read_source(path)
+        rel = path.relative_to(root)
+        for call, arglist, lineno in iter_calls(text):
+            positions = CONSTANT_ARG_POSITIONS.get(call, set())
+            args = split_top_level_args(arglist)
+            for idx in positions:
+                if idx >= len(args):
+                    continue
+                arg = args[idx]
+                lit = STRING_LITERAL.search(arg)
+                if lit:
+                    found_f = True
+                    report.violation(
+                        "F",
+                        f"{rel}:{lineno}",
+                        f'{call} arg{idx} "{lit.group(1)}"',
+                        "use a *SpanNames.h constant",
+                    )
+                    continue
+                # Not a literal: Rule H warns when a NAMESPACE-QUALIFIED constant
+                # reference (e.g. `consensus::span::accept`) is not defined in
+                # any *SpanNames.h — i.e. the constant was defined in-place
+                # instead of in the proper header. We only consider qualified
+                # refs (containing `::`): a bare lowercase identifier is almost
+                # always a legitimately dynamic local (a computed span-name leaf
+                # or attribute value), not a misplaced constant, so warning on it
+                # would be noise. Standard-library types (std::...) are skipped.
+                ident = IDENTIFIER_ARG.match(arg)
+                if not (ident and header_symbols):
+                    continue
+                ref = ident.group(1)
+                if "::" not in ref or ref.startswith("std::"):
+                    continue
+                leaf = ref.split("::")[-1]
+                if leaf not in header_symbols:
+                    report.warning(
+                        "H",
+                        f"{rel}:{lineno}",
+                        f"{call} arg{idx} {ref}",
+                        "not defined in any *SpanNames.h",
+                    )
+    if not found_f:
+        report.ok("F: no string-literal keys/names at telemetry call-sites")
+
+
+def iter_calls(text: str):
+    """Yield (call_name, raw_arglist, lineno) for each setAttribute/addEvent/
+    span/rootSpan/childSpan invocation, spanning multiple physical lines if
+    needed."""
+    for m in CALLSITE.finditer(text):
+        name = m.group(1)
+        # Walk from the opening paren, balancing nesting to find the close.
+        # Parens inside a "string literal" are ignored so a value such as
+        # `setAttribute(k, ")")` does not close the call early.
+        i = m.end()  # one char past the '('
+        depth = 1
+        in_str = False
+        escaped = False
+        while i < len(text) and depth > 0:
+            c = text[i]
+            if in_str:
+                if escaped:
+                    escaped = False
+                elif c == "\\":
+                    escaped = True
+                elif c == '"':
+                    in_str = False
+            elif c == '"':
+                in_str = True
+            elif c == "(":
+                depth += 1
+            elif c == ")":
+                depth -= 1
+            i += 1
+        arglist = text[m.end() : i - 1]
+        lineno = text.count("\n", 0, m.start()) + 1
+        yield name, arglist, lineno
+
+
+def run_rule_b_collector(root: Path, l1_keys: Set[str], report: Report) -> None:
+    path = root / "docker" / "telemetry" / "otel-collector-config.yaml"
+    if not path.is_file():
+        report.skip("B", "collector config not present")
+        return
+    text = read_source(path)
+    if "spanmetrics" not in text:
+        report.skip("B", "no spanmetrics block in collector config")
+        return
+    dims = extract_spanmetrics_dimensions(text)
+    if not l1_keys:
+        report.skip("B", "no L1 key set to validate against")
+        return
+    miss = [d for d in dims if d not in l1_keys]
+    for d in miss:
+        report.violation("B", str(path.relative_to(root)), d, "must exist in L1")
+    if not miss:
+        report.ok(f"B: {len(dims)} collector dimension(s) all in L1")
+
+
+def extract_spanmetrics_dimensions(text: str) -> List[str]:
+    dims: List[str] = []
+    in_dims = False
+    for line in text.splitlines():
+        if re.search(r"\bdimensions\s*:", line):
+            in_dims = True
+            continue
+        if in_dims:
+            m = re.search(r"-\s*name\s*:\s*([A-Za-z0-9_.]+)", line)
+            if m:
+                dims.append(m.group(1))
+            elif line.strip() and not line.lstrip().startswith("-") and ":" in line:
+                in_dims = False
+    return dims
+
+
+def run_rule_c_tempo(root: Path, l1_keys: Set[str], report: Report) -> None:
+    # The trace-search filter tags live in the Grafana Tempo DATASOURCE
+    # provisioning file (search.filters[].{tag,scope}); the Tempo server
+    # tempo.yaml has no such tags. Prefer the datasource file; fall back to the
+    # server file so the rule still does something if the layout changes.
+    candidates = [
+        root / "docker/telemetry/grafana/provisioning/datasources/tempo.yaml",
+        root / "docker/telemetry/tempo.yaml",
+    ]
+    path = next((p for p in candidates if p.is_file()), None)
+    if path is None:
+        report.skip("C", "tempo datasource provisioning not present")
+        return
+    if not l1_keys:
+        report.skip("C", "no L1 key set to validate against")
+        return
+    # Pair each filter's `tag:` with its `scope:` (a few lines below it) and
+    # validate only span-scope tags — resource/intrinsic tags (service.*, name,
+    # status, duration) are not span attributes. Strip a TraceQL span. prefix.
+    lines = read_source(path).splitlines()
+    span_tags: List[str] = []
+    for i, line in enumerate(lines):
+        m = re.search(r"^\s*tag:\s*(\S+)", line)
+        if not m:
+            continue
+        scope = next(
+            (
+                sm.group(1)
+                for j in range(i, min(i + 4, len(lines)))
+                for sm in [re.search(r"scope:\s*(\S+)", lines[j])]
+                if sm
+            ),
+            "",
+        )
+        if scope == "span":
+            span_tags.append(TRACEQL_SCOPE.sub("", m.group(1)))
+    if not span_tags:
+        report.skip("C", "no span-scope filter tags in tempo datasource")
+        return
+    miss = [t for t in span_tags if t not in l1_keys]
+    for t in sorted(set(miss)):
+        report.violation("C", str(path.relative_to(root)), t, "must exist in L1")
+    if not miss:
+        report.ok(f"C: {len(span_tags)} tempo span-filter tag(s) all in L1")
+
+
+def metric_label_names(root: Path) -> Set[str]:
+    """L6: OTel native-metric label keys emitted by the telemetry code, e.g.
+    `counter->Add(1, {{"job_type", value}})` in MetricsRegistry.cpp. These are
+    a valid source of dashboard labels distinct from span attributes (L1)."""
+    labels: Set[str] = set()
+    for base in ("src", "include"):
+        for p in (root / base).rglob("*.cpp"):
+            if not p.is_file():
+                continue
+            text = read_source(p)
+            if "MetricsRegistry" not in p.name and "metric" not in text.lower():
+                continue
+            labels |= set(METRIC_LABEL.findall(text))
+    return labels
+
+
+# Identity labels stamped by EXTERNAL infrastructure the OTel pipeline in this
+# repo does not own: the perf-iac harness attaches these to every metric it
+# scrapes so dashboards can filter by which build/role produced a series. They
+# have no L1 (*SpanNames.h), L2 (collector config), or L6 (MetricsRegistry.cpp)
+# source to derive from, so — unlike every other dashboard label — they cannot
+# be validated dynamically. This is a deliberate, narrow exception to the "no
+# hardcoded allowlist" design principle, kept separate from the generic
+# Prometheus/Grafana `builtins` set below so it stays visible and auditable.
+# Add a label here ONLY if it is genuinely injected by infra outside this
+# repo's OTel code (never as a workaround for a dashboard querying a label
+# that nothing actually emits — that is a real Rule D violation).
+EXTERNAL_INFRA_LABELS = {
+    "xrpl_branch",  # perf-iac: git ref of the xrpld build under test
+    "xrpl_node_role",  # perf-iac: validator/peer role in the perf cluster
+}
+
+
+def run_rule_d_dashboards(
+    root: Path, l1_keys: Set[str], metric_labels: Set[str], report: Report
+) -> None:
+    dash_dir = root / "docker" / "telemetry" / "grafana" / "dashboards"
+    files = sorted(dash_dir.glob("*.json")) if dash_dir.is_dir() else []
+    if not files:
+        report.skip("D", "no dashboard JSON present")
+        return
+    if not l1_keys:
+        report.skip("D", "no L1 key set to validate against")
+        return
+    builtins = {
+        "__name__",  # Prometheus reserved label for the metric name itself
+        "le",
+        "exported_instance",
+        "span_name",
+        "status_code",
+        "service_name",
+        "service_version",
+        "service_instance_id",
+        "job",
+        "instance",
+    }
+    # A dashboard label is valid if it is a span attribute (L1), a native-metric
+    # label (L6), a Prometheus/Grafana builtin, or an external-infra identity
+    # label (EXTERNAL_INFRA_LABELS).
+    valid = l1_keys | metric_labels | builtins | EXTERNAL_INFRA_LABELS
+    found = False
+    for f in files:
+        try:
+            text = read_source(f)
+        except OSError:
+            continue
+        # PromQL `sum by (a, b)` and `{label="..."}` references.
+        labels: Set[str] = set()
+        for m in re.finditer(r"by\s*\(([^)]*)\)", text):
+            labels |= {x.strip() for x in m.group(1).split(",") if x.strip()}
+        for m in re.finditer(r"\b([a-z_][a-z0-9_.]*)\s*[=!]~?\s*\"", text):
+            labels.add(m.group(1))
+        for lbl in sorted(labels):
+            # Strip a TraceQL scope prefix (span./resource./...) — the bare
+            # attribute is what must resolve against L1.
+            bare = TRACEQL_SCOPE.sub("", lbl)
+            if bare in valid:
+                continue
+            found = True
+            report.violation(
+                "D",
+                str(f.relative_to(root)),
+                lbl,
+                "must exist in L1, a metric label, or be a builtin",
+            )
+    if not found:
+        report.ok(f"D: dashboard PromQL labels all resolve ({len(files)} file(s))")
+
+
+def run_rule_e_runbook(root: Path, l1_keys: Set[str], report: Report) -> None:
+    path = root / "docs" / "telemetry-runbook.md"
+    if not path.is_file():
+        report.skip("E", "runbook not present")
+        return
+    if not l1_keys:
+        report.skip("E", "no L1 key set to validate against")
+        return
+    text = read_source(path)
+    found = False
+    # Only the dotted `xrpl.<domain>.<field>` attribute form is a violation. The
+    # `xrpl.`-with-trailing-dot anchor is the discriminator: it matches the old
+    # dotted attribute convention being migrated away from, while everything
+    # else legitimately dotted in the runbook does NOT match it —
+    #   * span names      (`consensus.round`, `tx.process`)   no `xrpl.` prefix
+    #   * filenames       (`xrpld.cfg`, `RCLConsensus.cpp`)   `xrpld.`/`.cpp`, not `xrpl.`
+    #   * OTel-standard   (`service.name`, `http.method`)     no `xrpl.` prefix
+    #   * metric labels   (`xrpl_rpc_command`)                underscore, no dot
+    # Legitimate dotted resource attrs (`xrpl.network.id`/`.type`) are in L1 and
+    # are skipped. A dotted `xrpl.` token absent from L1 is a genuine doc/code
+    # mismatch (e.g. `xrpl.tx.hash` where the code emits `tx_hash`).
+    for m in re.finditer(r"`(xrpl\.[a-z][a-z0-9_.]*)`", text):
+        token = m.group(1)
+        if token in l1_keys:  # legitimate dotted resource attr (xrpl.network.*)
+            continue
+        found = True
+        report.violation(
+            "E", str(path.relative_to(root)), token, "underscore, not dotted"
+        )
+    if not found:
+        report.ok("E: runbook attribute references consistent with L1")
+
+
+if __name__ == "__main__":
+    main()

.github/scripts/otel-naming/test_check_otel_naming.py

@@ -0,0 +1,927 @@
+#!/usr/bin/env python3
+
+"""Unit tests for check_otel_naming.py.
+
+Stdlib-only (unittest), matching the dependency-free policy of the check itself.
+Run from anywhere:
+
+    python .github/scripts/otel-naming/test_check_otel_naming.py
+
+Each rule is exercised in isolation against a synthetic tree / synthetic L1 key
+set, covering positive (must flag), negative (must not flag), and boundary
+cases. Rule E (runbook dotted-attribute detection) has the densest coverage
+because its discriminator — the `xrpl.<domain>.` prefix vs span names,
+filenames, OTel-standard keys, and metric labels — is the subtlest.
+"""
+
+import contextlib
+import importlib.util
+import io
+import shutil
+import tempfile
+import unittest
+from pathlib import Path
+
+# Load the check module by path (it is not an importable package).
+_spec = importlib.util.spec_from_file_location(
+    "check_otel_naming", str(Path(__file__).with_name("check_otel_naming.py"))
+)
+chk = importlib.util.module_from_spec(_spec)
+_spec.loader.exec_module(chk)
+
+
+# A controlled L1 set used across tests: the two legitimate dotted resource
+# attrs plus a handful of underscore span-attribute keys.
+L1 = {
+    "xrpl.network.id",
+    "xrpl.network.type",
+    "tx_hash",
+    "peer_id",
+    "consensus_mode",
+    "command",
+    "rpc_status",
+    "ledger_seq",
+}
+
+
+def _run_rule_e(runbook_text: str):
+    """Run Rule E against a synthetic runbook; return the flagged tokens."""
+    d = Path(tempfile.mkdtemp())
+    try:
+        (d / "docs").mkdir()
+        (d / "docs" / "telemetry-runbook.md").write_text(runbook_text)
+        report = chk.Report()
+        chk.run_rule_e_runbook(d, set(L1), report)
+        return sorted(v[2] for v in report.violations)
+    finally:
+        shutil.rmtree(d)
+
+
+class RuleERunbook(unittest.TestCase):
+    """Rule E: only dotted `xrpl.<domain>.<field>` attribute keys are flagged."""
+
+    # ----- positive: genuine dotted attribute-key violations -----
+    def test_single_dotted_attr(self):
+        self.assertEqual(_run_rule_e("`xrpl.tx.hash`"), ["xrpl.tx.hash"])
+
+    def test_multiple_dotted_attrs(self):
+        self.assertEqual(
+            _run_rule_e("`xrpl.tx.hash` and `xrpl.consensus.mode`"),
+            ["xrpl.consensus.mode", "xrpl.tx.hash"],
+        )
+
+    def test_deep_dotted_three_segments(self):
+        self.assertEqual(
+            _run_rule_e("`xrpl.consensus.ledger.seq`"), ["xrpl.consensus.ledger.seq"]
+        )
+
+    def test_dotted_attr_with_underscore_field(self):
+        self.assertEqual(
+            _run_rule_e("`xrpl.consensus.round_id`"), ["xrpl.consensus.round_id"]
+        )
+
+    def test_repeated_token_reported_each_occurrence(self):
+        self.assertEqual(
+            _run_rule_e("`xrpl.tx.hash` ... `xrpl.tx.hash`"),
+            ["xrpl.tx.hash", "xrpl.tx.hash"],
+        )
+
+    def test_resource_attr_not_in_l1_is_flagged(self):
+        self.assertEqual(
+            _run_rule_e("`xrpl.network.unknown`"), ["xrpl.network.unknown"]
+        )
+
+    # ----- negative: legitimately-dotted tokens that must NOT be flagged -----
+    def test_span_name_single(self):
+        self.assertEqual(_run_rule_e("`consensus.round`"), [])
+
+    def test_span_name_multi_segment(self):
+        self.assertEqual(
+            _run_rule_e("`consensus.phase.open` `rpc.command.server_info`"), []
+        )
+
+    def test_filename_cfg(self):
+        self.assertEqual(_run_rule_e("`xrpld.cfg`"), [])
+
+    def test_filename_cpp(self):
+        self.assertEqual(_run_rule_e("`RCLConsensus.cpp`"), [])
+
+    def test_otel_standard_service_name(self):
+        self.assertEqual(_run_rule_e("`service.name`"), [])
+
+    def test_otel_standard_http_method(self):
+        self.assertEqual(_run_rule_e("`http.method`"), [])
+
+    def test_metric_label_underscore(self):
+        self.assertEqual(_run_rule_e("`xrpl_rpc_command`"), [])
+
+    def test_bare_underscore_attrs(self):
+        self.assertEqual(_run_rule_e("`tx_hash` `consensus_mode`"), [])
+
+    def test_legit_dotted_resource_attrs_in_l1(self):
+        self.assertEqual(_run_rule_e("`xrpl.network.id` `xrpl.network.type`"), [])
+
+    def test_prose_word(self):
+        self.assertEqual(_run_rule_e("the `command` attribute"), [])
+
+    def test_plain_prose_no_backticks(self):
+        self.assertEqual(_run_rule_e("xrpl.tx.hash without backticks is prose"), [])
+
+    # ----- boundary -----
+    def test_empty_runbook(self):
+        self.assertEqual(_run_rule_e(""), [])
+
+    def test_lookalike_prefix_xrpld(self):
+        # `xrpld.` is NOT `xrpl.` — must not match.
+        self.assertEqual(_run_rule_e("`xrpld.foo`"), [])
+
+    def test_lookalike_prefix_underscore(self):
+        # `xrpl_rpc.command` starts with `xrpl_`, not `xrpl.`.
+        self.assertEqual(_run_rule_e("`xrpl_rpc.command`"), [])
+
+    def test_uppercase_segment_not_matched(self):
+        # The pattern requires a lowercase char after `xrpl.`; uppercase keys are
+        # caught by Rule G at the L1 layer, not by the runbook text scan.
+        self.assertEqual(_run_rule_e("`xrpl.TX.hash`"), [])
+
+    def test_token_touching_table_pipes(self):
+        self.assertEqual(_run_rule_e("| `xrpl.tx.hash` | desc |"), ["xrpl.tx.hash"])
+
+    def test_mixed_line_only_xrpl_dotted_flagged(self):
+        self.assertEqual(
+            _run_rule_e("`consensus.round` uses `xrpl.tx.hash` and `service.name`"),
+            ["xrpl.tx.hash"],
+        )
+
+    def test_skips_when_runbook_absent(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            report = chk.Report()
+            chk.run_rule_e_runbook(d, set(L1), report)
+            self.assertEqual(report.violations, [])
+            self.assertTrue(any("SKIP: E" in s for s in report.skips))
+        finally:
+            shutil.rmtree(d)
+
+    def test_skips_when_l1_empty(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            (d / "docs").mkdir()
+            (d / "docs" / "telemetry-runbook.md").write_text("`xrpl.tx.hash`")
+            report = chk.Report()
+            chk.run_rule_e_runbook(d, set(), report)
+            self.assertEqual(report.violations, [])
+            self.assertTrue(any("SKIP: E" in s for s in report.skips))
+        finally:
+            shutil.rmtree(d)
+
+
+class DslParser(unittest.TestCase):
+    """The makeStr/join/seg:: constexpr DSL resolver — the foundation of the
+    L1 key set. Covers flat, nested, cross-file, alias, and multi-line forms."""
+
+    def test_flat_join(self):
+        syms = chk.resolve_constants(
+            'inline constexpr auto a = makeStr("xrpl");\n'
+            'inline constexpr auto b = makeStr("network");\n'
+            "inline constexpr auto c = join(a, b);\n"
+        )
+        self.assertEqual(syms["c"], "xrpl.network")
+
+    def test_nested_join_three_segments(self):
+        syms = chk.resolve_constants(
+            'inline constexpr auto xrpl = makeStr("xrpl");\n'
+            'inline constexpr auto network = makeStr("network");\n'
+            "inline constexpr auto networkId = "
+            'join(join(xrpl, network), makeStr("id"));\n'
+        )
+        self.assertEqual(syms["networkId"], "xrpl.network.id")
+
+    def test_qualified_seg_reference(self):
+        # `seg::rpc` resolves by its bare leaf `rpc`.
+        syms = chk.resolve_constants('inline constexpr auto rpc = makeStr("rpc");\n')
+        syms2 = chk.resolve_constants(
+            'inline constexpr auto command = join(seg::rpc, makeStr("command"));\n',
+            syms,
+        )
+        self.assertEqual(syms2["command"], "rpc.command")
+
+    def test_alias_reference(self):
+        syms = chk.resolve_constants('inline constexpr auto rpc = makeStr("rpc");\n')
+        chk.resolve_constants("inline constexpr auto alias = seg::rpc;\n", syms)
+        self.assertEqual(syms["alias"], "rpc")
+
+    def test_unresolvable_expr_omitted(self):
+        syms = chk.resolve_constants("inline constexpr auto x = join(unknown, y);\n")
+        self.assertNotIn("x", syms)
+
+    def test_split_top_level_args_respects_nesting(self):
+        self.assertEqual(
+            chk.split_top_level_args("join(seg::a, b), c"),
+            ["join(seg::a, b)", " c"],
+        )
+
+    def test_split_top_level_args_ignores_comma_in_string(self):
+        self.assertEqual(
+            chk.split_top_level_args('key, ","'),
+            ["key", ' ","'],
+        )
+
+    def test_strip_comments_removes_line_and_block(self):
+        self.assertEqual(
+            chk.strip_comments("a // line\nb /* blk */ c").split(),
+            ["a", "b", "c"],
+        )
+
+
+def _write(path: Path, text: str) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(text)
+
+
+def _header(ns_attr_body: str, prefix_seg: str = "") -> str:
+    """A minimal *SpanNames.h body: optional seg defs + a namespace attr block."""
+    return (
+        "#pragma once\n"
+        + prefix_seg
+        + "namespace xrpl::telemetry::demo::span {\n"
+        + "namespace attr {\n"
+        + ns_attr_body
+        + "}  // namespace attr\n"
+        + "}\n"
+    )
+
+
+class AttrKeyExtraction(unittest.TestCase):
+    """attr_keys_from_header: comment-stripping + multi-line + using re-export."""
+
+    def _l1(self, header_text):
+        d = Path(tempfile.mkdtemp())
+        try:
+            h = d / "src" / "DemoSpanNames.h"
+            _write(h, header_text)
+            syms = chk.build_global_symbols([h])
+            return chk.attr_keys_from_header(h, syms)
+        finally:
+            shutil.rmtree(d)
+
+    def test_single_line_makestr(self):
+        keys = self._l1(_header('inline constexpr auto k = makeStr("tx_hash");\n'))
+        self.assertIn("tx_hash", keys)
+
+    def test_multiline_constexpr_captured(self):
+        keys = self._l1(
+            _header("inline constexpr auto k =\n" '    makeStr("round_time_ms");\n')
+        )
+        self.assertIn("round_time_ms", keys)
+
+    def test_commented_makestr_not_leaked(self):
+        keys = self._l1(
+            _header(
+                'inline constexpr auto k = makeStr("good");\n'
+                '// inline constexpr auto bad = makeStr("old.dotted");\n'
+            )
+        )
+        self.assertIn("good", keys)
+        self.assertNotIn("old.dotted", keys)
+
+    def test_block_commented_makestr_not_leaked(self):
+        keys = self._l1(
+            _header(
+                'inline constexpr auto k = makeStr("good");\n'
+                '/* makeStr("blockbad") */\n'
+            )
+        )
+        self.assertNotIn("blockbad", keys)
+
+
+class CamelToDotSegments(unittest.TestCase):
+    """semconv CamelCase -> dotted OTel-standard key derivation."""
+
+    def test_service_instance_id(self):
+        self.assertEqual(
+            chk.camel_to_dotsegments("ServiceInstanceId"),
+            ["service", "instance", "id"],
+        )
+
+    def test_service_name(self):
+        self.assertEqual(chk.camel_to_dotsegments("ServiceName"), ["service", "name"])
+
+    def test_derive_keys_from_telemetry_cpp(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            tele = d / "src" / "libxrpl" / "telemetry" / "Telemetry.cpp"
+            _write(
+                tele,
+                "resource::Resource::Create({\n"
+                "  {semconv::service::kServiceName, x},\n"
+                "  {semconv::service::kServiceInstanceId, y},\n"
+                "});\n",
+            )
+            report = chk.Report()
+            allow = chk.derive_dotted_resource_keys(d, {}, report)
+            self.assertIn("service.name", allow)
+            self.assertIn("service.instance.id", allow)
+        finally:
+            shutil.rmtree(d)
+
+
+class SymbolCollision(unittest.TestCase):
+    """attr_keys_from_header must resolve a constant against ITS OWN header, so
+    two headers defining a same-named constant each report their real wire key.
+    Regression for the flat-symbol-table collision that let a later header
+    clobber an earlier one and erased a dotted key from L1 (a Rule-A blind
+    spot)."""
+
+    def _build(self, files):
+        d = Path(tempfile.mkdtemp())
+        paths = {}
+        for rel, text in files.items():
+            p = d / rel
+            _write(p, text)
+            paths[rel] = p
+        return d, paths
+
+    def test_same_named_const_not_clobbered_across_headers(self):
+        base = (
+            "#pragma once\n"
+            "namespace xrpl::telemetry {\n"
+            'namespace seg { inline constexpr auto xrpl = makeStr("xrpl");\n'
+            'inline constexpr auto ledger = makeStr("ledger"); }\n'
+            "namespace attr {\n"
+            "inline constexpr auto ledgerHash = "
+            'join(join(seg::xrpl, seg::ledger), makeStr("hash"));\n'
+            "}\n}\n"
+        )
+        cons = (
+            "#pragma once\n"
+            "namespace xrpl::telemetry::consensus::span {\n"
+            "namespace attr { inline constexpr auto ledgerHash = "
+            'makeStr("ledger_hash"); }\n}\n'
+        )
+        d, paths = self._build(
+            {
+                "include/xrpl/telemetry/SpanNames.h": base,
+                "src/xrpld/consensus/ConsensusSpanNames.h": cons,
+            }
+        )
+        try:
+            headers = chk.find_spanname_headers(d)
+            syms = chk.build_global_symbols(headers)
+            by_name = {p.name: chk.attr_keys_from_header(p, syms) for p in headers}
+            # The base header keeps its dotted key; consensus keeps the bare one.
+            self.assertIn("xrpl.ledger.hash", by_name["SpanNames.h"])
+            self.assertEqual(by_name["ConsensusSpanNames.h"], {"ledger_hash"})
+        finally:
+            shutil.rmtree(d)
+
+    def test_using_reexport_still_resolves_globally(self):
+        # A `using`-re-export imports a constant defined elsewhere; it must
+        # resolve against the global table, not the local header.
+        base = (
+            "#pragma once\n"
+            "namespace xrpl::telemetry {\n"
+            "namespace attr { inline constexpr auto txHash = "
+            'makeStr("tx_hash"); }\n}\n'
+        )
+        dom = (
+            "#pragma once\n"
+            "namespace xrpl::telemetry::tx::span {\n"
+            "namespace attr { using ::xrpl::telemetry::attr::txHash; }\n}\n"
+        )
+        d, paths = self._build(
+            {
+                "include/xrpl/telemetry/SpanNames.h": base,
+                "src/xrpld/app/misc/TxSpanNames.h": dom,
+            }
+        )
+        try:
+            headers = chk.find_spanname_headers(d)
+            syms = chk.build_global_symbols(headers)
+            keys = chk.attr_keys_from_header(
+                paths["src/xrpld/app/misc/TxSpanNames.h"], syms
+            )
+            self.assertEqual(keys, {"tx_hash"})
+        finally:
+            shutil.rmtree(d)
+
+
+class ResourceAllowlistScope(unittest.TestCase):
+    """derive_dotted_resource_keys must allowlist ONLY the dotted keys actually
+    passed to Resource::Create() — not every dotted key in the base header. A
+    dotted attr declared in a header but not set as a resource attr is a Rule-A
+    violation."""
+
+    def _derive(self, tele_text, span_text):
+        d = Path(tempfile.mkdtemp())
+        try:
+            _write(d / "src" / "libxrpl" / "telemetry" / "Telemetry.cpp", tele_text)
+            _write(d / "include" / "xrpl" / "telemetry" / "SpanNames.h", span_text)
+            headers = chk.find_spanname_headers(d)
+            syms = chk.build_global_symbols(headers)
+            allow = chk.derive_dotted_resource_keys(d, syms, chk.Report())
+            return allow, syms, headers, d
+        except Exception:
+            shutil.rmtree(d)
+            raise
+
+    def test_dotted_span_attr_not_allowlisted_and_flagged(self):
+        span = (
+            "#pragma once\n"
+            "namespace xrpl::telemetry {\n"
+            'namespace seg { inline constexpr auto xrpl = makeStr("xrpl");\n'
+            'inline constexpr auto ledger = makeStr("ledger");\n'
+            'inline constexpr auto network = makeStr("network"); }\n'
+            "namespace attr {\n"
+            "inline constexpr auto networkId = "
+            'join(join(seg::xrpl, seg::network), makeStr("id"));\n'
+            "inline constexpr auto ledgerHash = "
+            'join(join(seg::xrpl, seg::ledger), makeStr("hash"));\n'
+            "}\n}\n"
+        )
+        tele = (
+            "auto r = resource::Resource::Create({\n"
+            "  {semconv::service::kServiceName, x},\n"
+            "  {std::string(attr::networkId), n},\n"
+            "});\n"
+        )
+        allow, syms, headers, d = self._derive(tele, span)
+        try:
+            # networkId IS a resource attr; ledgerHash is NOT, despite living in
+            # the base header.
+            self.assertIn("xrpl.network.id", allow)
+            self.assertNotIn("xrpl.ledger.hash", allow)
+            kbh = {h: chk.attr_keys_from_header(h, syms) for h in headers}
+            report = chk.Report()
+            chk.run_rule_a(kbh, allow, report)
+            self.assertEqual([v[2] for v in report.violations], ["xrpl.ledger.hash"])
+        finally:
+            shutil.rmtree(d)
+
+    def test_resource_block_brace_matched(self):
+        # A nested {key,value} initializer must not truncate the block scan.
+        tele = (
+            "auto r = resource::Resource::Create({\n"
+            "  {semconv::service::kServiceName, x},\n"
+            "  {std::string(attr::networkType), t},\n"
+            "});\n"
+        )
+        span = (
+            "#pragma once\n"
+            "namespace xrpl::telemetry {\n"
+            'namespace seg { inline constexpr auto xrpl = makeStr("xrpl");\n'
+            'inline constexpr auto network = makeStr("network"); }\n'
+            "namespace attr { inline constexpr auto networkType = "
+            'join(join(seg::xrpl, seg::network), makeStr("type")); }\n}\n'
+        )
+        allow, _syms, _headers, d = self._derive(tele, span)
+        try:
+            self.assertIn("xrpl.network.type", allow)
+            self.assertIn("service.name", allow)
+        finally:
+            shutil.rmtree(d)
+
+
+def _run_rule_a(keys_by_header, allow):
+    report = chk.Report()
+    chk.run_rule_a(keys_by_header, allow, report)
+    return sorted(v[2] for v in report.violations)
+
+
+class RuleADotted(unittest.TestCase):
+    def test_dotted_attr_not_in_allow_flagged(self):
+        kbh = {Path("src/RpcSpanNames.h"): {"xrpl.tx.hash", "command"}}
+        self.assertEqual(_run_rule_a(kbh, {"xrpl.network.id"}), ["xrpl.tx.hash"])
+
+    def test_resource_attr_in_allow_passes(self):
+        kbh = {Path("src/SpanNames.h"): {"xrpl.network.id"}}
+        self.assertEqual(_run_rule_a(kbh, {"xrpl.network.id"}), [])
+
+    def test_bare_key_never_flagged(self):
+        kbh = {Path("src/TxSpanNames.h"): {"tx_hash", "command"}}
+        self.assertEqual(_run_rule_a(kbh, set()), [])
+
+
+def _run_rule_g(keys_by_header):
+    report = chk.Report()
+    chk.run_rule_g(keys_by_header, report)
+    return sorted(v[2] for v in report.violations)
+
+
+class RuleGSnakeCase(unittest.TestCase):
+    def test_camelcase_flagged(self):
+        self.assertEqual(_run_rule_g({Path("h"): {"txHash"}}), ["txHash"])
+
+    def test_uppercase_flagged(self):
+        self.assertEqual(_run_rule_g({Path("h"): {"TX_HASH"}}), ["TX_HASH"])
+
+    def test_space_flagged(self):
+        self.assertEqual(_run_rule_g({Path("h"): {"bad key"}}), ["bad key"])
+
+    def test_snake_case_passes(self):
+        self.assertEqual(_run_rule_g({Path("h"): {"tx_hash", "rpc_status"}}), [])
+
+    def test_dotted_resource_segments_pass(self):
+        self.assertEqual(_run_rule_g({Path("h"): {"xrpl.network.id"}}), [])
+
+    def test_dotted_with_bad_segment_flagged(self):
+        self.assertEqual(
+            _run_rule_g({Path("h"): {"xrpl.Network.id"}}), ["xrpl.Network.id"]
+        )
+
+
+class RuleFAndH(unittest.TestCase):
+    """run_rule_f: literal keys/span-names flagged; values & tests exempt.
+    Rule H: qualified constant not in any header warns (non-fatal)."""
+
+    def _run(self, rel_path, source, header_symbols=frozenset()):
+        d = Path(tempfile.mkdtemp())
+        try:
+            _write(d / rel_path, source)
+            report = chk.Report()
+            chk.run_rule_f(d, report, set(header_symbols))
+            return (
+                sorted(v[2] for v in report.violations),
+                sorted(w[2] for w in report.warnings),
+            )
+        finally:
+            shutil.rmtree(d)
+
+    def test_literal_key_flagged(self):
+        v, _ = self._run("src/Foo.cpp", 'g.setAttribute("lit_key", v);\n')
+        self.assertEqual(v, ['setAttribute arg0 "lit_key"'])
+
+    def test_literal_value_exempt(self):
+        v, _ = self._run("src/Foo.cpp", 'g.setAttribute(attr::command, "submit");\n')
+        self.assertEqual(v, [])
+
+    def test_span_name_args_flagged(self):
+        v, _ = self._run("src/Foo.cpp", 'SpanGuard::span(cat, "rpc", "command");\n')
+        self.assertEqual(v, ['span arg1 "rpc"', 'span arg2 "command"'])
+
+    def test_rootspan_literal_flagged_by_rule_f(self):
+        # rootSpan(cat, prefix, name) shares span()'s signature, so a string
+        # literal in the prefix/name position must FAIL rule F exactly as it
+        # does for span() — otherwise a call switched to rootSpan silently
+        # escapes span-name validation.
+        v, _ = self._run(
+            "src/Foo.cpp",
+            'SpanGuard::rootSpan(cat, "peer", "validation.receive");\n',
+        )
+        self.assertEqual(
+            v, ['rootSpan arg1 "peer"', 'rootSpan arg2 "validation.receive"']
+        )
+
+    def test_rootspan_constant_args_accepted(self):
+        # Constant references in the prefix/name position are accepted (no
+        # rule F), mirroring span()'s constant-arg handling.
+        v, _ = self._run(
+            "src/Foo.cpp",
+            "SpanGuard::rootSpan(TraceCategory::Peer, seg::peer, "
+            "peer_span::op::validationReceive);\n",
+        )
+        self.assertEqual(v, [])
+
+    def test_test_path_exempt(self):
+        v, _ = self._run("src/test/Foo.cpp", 'g.setAttribute("lit_key", v);\n')
+        self.assertEqual(v, [])
+
+    def test_spannames_header_exempt(self):
+        v, _ = self._run("src/DemoSpanNames.h", 'g.setAttribute("lit_key", v);\n')
+        self.assertEqual(v, [])
+
+    def test_bare_span_call_not_matched(self):
+        # No SpanGuard/./-> receiver -> not a telemetry call-site.
+        v, _ = self._run("src/Foo.cpp", 'auto s = span("not", "telemetry");\n')
+        self.assertEqual(v, [])
+
+    def test_multiline_call_reports_first_line(self):
+        v, _ = self._run("src/Foo.cpp", 'g.setAttribute(\n    "k",\n    v);\n')
+        self.assertEqual(v, ['setAttribute arg0 "k"'])
+
+    def test_paren_in_string_value_does_not_break_parsing(self):
+        # The ")" inside the value must not end the call early; key still seen.
+        v, _ = self._run("src/Foo.cpp", 'g.setAttribute("k", ")");\n')
+        self.assertEqual(v, ['setAttribute arg0 "k"'])
+
+    def test_rule_h_qualified_constant_warns(self):
+        v, w = self._run(
+            "src/Foo.cpp",
+            "g.setAttribute(consensus::span::accept, v);\n",
+            header_symbols={"command"},
+        )
+        self.assertEqual(v, [])
+        self.assertEqual(w, ["setAttribute arg0 consensus::span::accept"])
+
+    def test_rule_h_known_constant_no_warning(self):
+        _, w = self._run(
+            "src/Foo.cpp",
+            "g.setAttribute(rpc_span::attr::command, v);\n",
+            header_symbols={"command"},
+        )
+        self.assertEqual(w, [])
+
+    def test_rule_h_bare_local_no_warning(self):
+        _, w = self._run(
+            "src/Foo.cpp", "g.setAttribute(myLeaf, v);\n", header_symbols={"command"}
+        )
+        self.assertEqual(w, [])
+
+
+class RuleBCollector(unittest.TestCase):
+    def _run(self, yaml_text, l1):
+        d = Path(tempfile.mkdtemp())
+        try:
+            _write(d / "docker" / "telemetry" / "otel-collector-config.yaml", yaml_text)
+            report = chk.Report()
+            chk.run_rule_b_collector(d, set(l1), report)
+            return sorted(v[2] for v in report.violations), report.skips
+        finally:
+            shutil.rmtree(d)
+
+    def test_dimension_not_in_l1_flagged(self):
+        y = "spanmetrics:\n  dimensions:\n    - name: bogus_dim\n    - name: command\n"
+        v, _ = self._run(y, {"command"})
+        self.assertEqual(v, ["bogus_dim"])
+
+    def test_all_dimensions_in_l1_pass(self):
+        y = "spanmetrics:\n  dimensions:\n    - name: command\n    - name: rpc_status\n"
+        v, _ = self._run(y, {"command", "rpc_status"})
+        self.assertEqual(v, [])
+
+    def test_skip_when_no_spanmetrics_block(self):
+        v, skips = self._run("receivers:\n  otlp:\n", {"command"})
+        self.assertEqual(v, [])
+        self.assertTrue(any("SKIP: B" in s for s in skips))
+
+
+class RuleCTempo(unittest.TestCase):
+    """Rule C reads the Grafana Tempo DATASOURCE file's search.filters and
+    validates only span-scope tags against L1."""
+
+    DS = "docker/telemetry/grafana/provisioning/datasources/tempo.yaml"
+
+    def _run(self, yaml_text, l1):
+        d = Path(tempfile.mkdtemp())
+        try:
+            _write(d / self.DS, yaml_text)
+            report = chk.Report()
+            chk.run_rule_c_tempo(d, set(l1), report)
+            return sorted(v[2] for v in report.violations), report.skips
+        finally:
+            shutil.rmtree(d)
+
+    def _filter(self, fid, tag, scope):
+        return (
+            f"          - id: {fid}\n"
+            f"            tag: {tag}\n"
+            f'            operator: "="\n'
+            f"            scope: {scope}\n"
+            f"            type: static\n"
+        )
+
+    def test_span_tag_not_in_l1_flagged(self):
+        y = "search:\n        filters:\n" + self._filter("f1", "bogus_tag", "span")
+        v, _ = self._run(y, {"command"})
+        self.assertEqual(v, ["bogus_tag"])
+
+    def test_span_tags_in_l1_pass(self):
+        y = (
+            "search:\n        filters:\n"
+            + self._filter("f1", "command", "span")
+            + self._filter("f2", "tx_hash", "span")
+        )
+        v, _ = self._run(y, {"command", "tx_hash"})
+        self.assertEqual(v, [])
+
+    def test_resource_and_intrinsic_tags_ignored(self):
+        # service.* (resource) and name/status/duration (intrinsic) are not
+        # span attributes — they must not be validated against L1.
+        y = (
+            "search:\n        filters:\n"
+            + self._filter("f1", "service.instance.id", "resource")
+            + self._filter("f2", "name", "intrinsic")
+            + self._filter("f3", "duration", "intrinsic")
+        )
+        v, skips = self._run(y, {"command"})
+        self.assertEqual(v, [])
+        self.assertTrue(any("SKIP: C" in s for s in skips))
+
+    def test_skip_when_datasource_absent(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            report = chk.Report()
+            chk.run_rule_c_tempo(d, {"command"}, report)
+            self.assertEqual(report.violations, [])
+            self.assertTrue(any("SKIP: C" in s for s in report.skips))
+        finally:
+            shutil.rmtree(d)
+
+
+class RuleDDashboards(unittest.TestCase):
+    def _run(self, json_text, l1, metric_labels=frozenset()):
+        d = Path(tempfile.mkdtemp())
+        try:
+            _write(
+                d / "docker" / "telemetry" / "grafana" / "dashboards" / "x.json",
+                json_text,
+            )
+            report = chk.Report()
+            chk.run_rule_d_dashboards(d, set(l1), set(metric_labels), report)
+            return sorted(v[2] for v in report.violations)
+        finally:
+            shutil.rmtree(d)
+
+    def test_unknown_promql_label_flagged(self):
+        self.assertEqual(
+            self._run('"expr": "sum by (bogus_label) (x)"', {"command"}),
+            ["bogus_label"],
+        )
+
+    # Rule D returns early on an empty L1 set, so a test that passes one asserts
+    # nothing. Each test below passes a nonempty L1 set and puts `bogus_label` in
+    # the same expression as the labels under test: the assertion then pins both
+    # halves at once — the accepted labels are absent from the result, and Rule D
+    # demonstrably ran because it flagged the bad one.
+
+    def test_builtin_labels_not_flagged(self):
+        self.assertEqual(
+            self._run(
+                '"expr": "sum by (le, span_name, exported_instance, bogus_label) (x)"',
+                {"command"},
+            ),
+            ["bogus_label"],
+        )
+
+    def test_external_infra_labels_not_flagged(self):
+        # EXTERNAL_INFRA_LABELS (perf-iac identity labels with no in-tree
+        # source) must be recognized as valid, distinct from `builtins`. The
+        # names are spelled out rather than joined from chk.EXTERNAL_INFRA_LABELS
+        # because building the query from the set that validates it passes for
+        # whatever that set happens to hold — including an empty one.
+        self.assertEqual(
+            self._run(
+                '"expr": "sum by (xrpl_branch, xrpl_node_role, bogus_label) (x)"',
+                {"command"},
+            ),
+            ["bogus_label"],
+        )
+
+    def test_prometheus_name_label_not_flagged(self):
+        # `__name__` is the Prometheus reserved metric-name label; the renamed
+        # system-*.json dashboards use `sum by (le, __name__)`.
+        self.assertEqual(
+            self._run(
+                '"expr": "sum by (le, __name__, bogus_label) (rate(x[5m]))"',
+                {"command"},
+            ),
+            ["bogus_label"],
+        )
+
+    def test_l1_label_passes(self):
+        # `by (...)` form, not a `{command="x"}` selector: a dashboard stores the
+        # query inside a JSON string, so its quotes are escaped on disk and the
+        # selector branch extracts nothing from them here.
+        self.assertEqual(
+            self._run('"expr": "sum by (command, bogus_label) (x)"', {"command"}),
+            ["bogus_label"],
+        )
+
+    def test_traceql_span_prefix_stripped(self):
+        # `span.establish_count` must validate against the bare L1 key.
+        self.assertEqual(
+            self._run(
+                '"expr": "count_over_time(x) by (span.establish_count)"',
+                {"establish_count"},
+            ),
+            [],
+        )
+
+    def test_traceql_resource_prefix_stripped(self):
+        # `resource.service_name` must validate against the bare builtin, same as
+        # the `span.` case above.
+        self.assertEqual(
+            self._run(
+                '"expr": "count_over_time(x) by (resource.service_name, bogus_label)"',
+                {"command"},
+            ),
+            ["bogus_label"],
+        )
+
+    def test_native_metric_label_passes(self):
+        # `job_type` / `reason` are emitted by MetricsRegistry, not span attrs.
+        self.assertEqual(
+            self._run(
+                '"expr": "sum by (job_type, reason) (x)"',
+                {"command"},
+                metric_labels={"job_type", "reason"},
+            ),
+            [],
+        )
+
+    def test_unknown_label_still_flagged_with_metric_labels(self):
+        # A label that is neither L1, metric label, nor builtin still fails.
+        self.assertEqual(
+            self._run(
+                '"expr": "sum by (bogus) (x)"',
+                {"command"},
+                metric_labels={"job_type"},
+            ),
+            ["bogus"],
+        )
+
+    def test_span_prefixed_unknown_still_flagged(self):
+        # `span.not_a_key` whose bare form is unknown is still a violation.
+        self.assertEqual(
+            self._run('"expr": "x by (span.not_a_key)"', {"command"}),
+            ["span.not_a_key"],
+        )
+
+
+class MetricLabelExtraction(unittest.TestCase):
+    """L6: native-metric label keys parsed from C++ instrument calls."""
+
+    def test_extracts_add_label(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            _write(
+                d / "src" / "xrpld" / "telemetry" / "MetricsRegistry.cpp",
+                'counter->Add(1, {{"job_type", std::string(jobType)}});\n'
+                'c2->Add(1, {{"reason", std::string(r)}});\n',
+            )
+            self.assertEqual(chk.metric_label_names(d), {"job_type", "reason"})
+        finally:
+            shutil.rmtree(d)
+
+    def test_no_metrics_file_empty(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            (d / "src").mkdir()
+            self.assertEqual(chk.metric_label_names(d), set())
+        finally:
+            shutil.rmtree(d)
+
+
+class ReportExitContract(unittest.TestCase):
+    @staticmethod
+    def _exit_code(report):
+        """Call render_and_exit (which prints + raises SystemExit), swallowing
+        its stdout, and return the exit code."""
+        with contextlib.redirect_stdout(io.StringIO()):
+            try:
+                report.render_and_exit()
+            except SystemExit as e:
+                return e.code
+        return None  # pragma: no cover - render_and_exit always exits
+
+    def test_violation_exits_nonzero(self):
+        r = chk.Report()
+        r.violation("A", "f", "tok", "exp")
+        self.assertEqual(self._exit_code(r), 1)
+
+    def test_clean_exits_zero(self):
+        r = chk.Report()
+        r.ok("all good")
+        self.assertEqual(self._exit_code(r), 0)
+
+    def test_warning_only_exits_zero(self):
+        r = chk.Report()
+        r.warning("H", "f", "tok", "note")
+        self.assertEqual(self._exit_code(r), 0)
+
+
+class RuleEReportTuple(unittest.TestCase):
+    """Assert Rule E records the full (rule, expected) tuple, not just token."""
+
+    def test_violation_tuple_fields(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            (d / "docs").mkdir()
+            (d / "docs" / "telemetry-runbook.md").write_text("`xrpl.tx.hash`")
+            report = chk.Report()
+            chk.run_rule_e_runbook(d, {"xrpl.network.id"}, report)
+            self.assertEqual(len(report.violations), 1)
+            rule, _loc, token, expected = report.violations[0]
+            self.assertEqual(rule, "E")
+            self.assertEqual(token, "xrpl.tx.hash")
+            self.assertEqual(expected, "underscore, not dotted")
+        finally:
+            shutil.rmtree(d)
+
+    def test_clean_runbook_records_ok(self):
+        d = Path(tempfile.mkdtemp())
+        try:
+            (d / "docs").mkdir()
+            (d / "docs" / "telemetry-runbook.md").write_text(
+                "`tx_hash` `consensus.round`"
+            )
+            report = chk.Report()
+            chk.run_rule_e_runbook(d, {"tx_hash"}, report)
+            self.assertEqual(report.violations, [])
+            self.assertTrue(any("E:" in c for c in report.checked))
+        finally:
+            shutil.rmtree(d)
+
+
+if __name__ == "__main__":
+    unittest.main(verbosity=2)

.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/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

.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] = {
@@ -17,6 +31,19 @@ _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()
@@ -31,22 +58,51 @@ def get_cmake_args(build_type: str, extra_args: str) -> str:
 
 
 # Every config must declare 'minimal'. Minimal configs form the reduced matrix
-# built for pull requests by default; the full matrix adds the rest. Packaging
-# configs declare it too, but packaging is gated in the workflow, not by it.
+# 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
+    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
@@ -55,22 +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()
+            },
         )
 
 
@@ -81,7 +131,11 @@ class PlatformConfig:
     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 = ""
+    # "" 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):
@@ -125,20 +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
 
 
 # ---------------------------------------------------------------------------
@@ -179,13 +238,9 @@ def expand_linux_matrix(linux: LinuxFile, minimal: bool) -> list[MatrixEntry]:
                 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,
@@ -193,6 +248,7 @@ def expand_linux_matrix(linux: LinuxFile, minimal: bool) -> list[MatrixEntry]:
                         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,
@@ -204,28 +260,59 @@ def expand_linux_matrix(linux: LinuxFile, minimal: bool) -> list[MatrixEntry]:
 
 
 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 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.
 
@@ -239,15 +326,20 @@ def expand_platform_matrix(pf: PlatformFile, minimal: bool) -> list[MatrixEntry]
         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
@@ -289,6 +381,10 @@ 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(

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

@@ -1,13 +1,23 @@
 {
-  "image_tag": "sha-e29b523",
+  "image_tag": "sha-060957e",
   "configs": {
     "ubuntu": [
+      {
+        "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
+        "minimal": true,
+        "benchmark": true
       },
+
       {
         "compiler": ["gcc"],
         "build_type": ["Release"],
@@ -29,14 +39,6 @@
         "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": ["Debug"],
@@ -68,27 +70,25 @@
         "compiler": ["gcc"],
         "build_type": ["Release"],
         "arch": ["amd64"],
-        "minimal": false
-      }
-    ],
-
-    "rhel": [
-      {
-        "compiler": ["gcc"],
-        "build_type": ["Release"],
-        "arch": ["amd64"],
-        "minimal": false
-      }
-    ]
-  },
-  "package_configs": {
-    "debian": [
+        "minimal": false,
+        "extra_cmake_args": "-Dvalidator_keys=ON",
+        "package": {
+          "type": "deb",
+          "image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-49cdc10"
+        }
+      },
       {
         "compiler": ["gcc"],
         "build_type": ["Release"],
         "arch": ["amd64"],
         "minimal": false,
-        "image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-577d745"
+        "suffix": "assert",
+        "extra_cmake_args": "-Dvalidator_keys=ON -Dassert=ON",
+        "package": {
+          "type": "deb",
+          "image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-49cdc10",
+          "variant": "assert"
+        }
       }
     ],
 
@@ -98,7 +98,11 @@
         "build_type": ["Release"],
         "arch": ["amd64"],
         "minimal": false,
-        "image": "ghcr.io/xrplf/xrpld/packaging-rhel:sha-577d745"
+        "extra_cmake_args": "-Dvalidator_keys=ON",
+        "package": {
+          "type": "rpm",
+          "image": "ghcr.io/xrplf/xrpld/packaging-rhel:sha-49cdc10"
+        }
       }
     ]
   }

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

@@ -12,6 +12,19 @@
       "extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
       "build_only": true,
       "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/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
@@ -54,7 +58,7 @@ 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@ee03d31bcc4501d7599dc1b1ecd7a34af582ad1c
+    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@034e87065fcd0100214cf0672923bd38d193cf78
     with:
       image_name: xrpld/nix-${{ matrix.distro.name }}
       dockerfile: nix/docker/Dockerfile

.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/docker/**"
   pull_request:
     paths:
       - ".github/workflows/build-packaging-images.yml"
-      - "package/Dockerfile"
-      - "package/install-packaging-tools.sh"
+      - "bin/install-packaging-tools.sh"
+      - "package/docker/**"
   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@ee03d31bcc4501d7599dc1b1ecd7a34af582ad1c
+            base_image: almalinux:10
+    uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@034e87065fcd0100214cf0672923bd38d193cf78
     with:
       image_name: xrpld/packaging-${{ matrix.distro.name }}
-      dockerfile: package/Dockerfile
+      dockerfile: package/docker/Dockerfile
       base_image: ${{ matrix.distro.base_image }}
       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@034e87065fcd0100214cf0672923bd38d193cf78
+    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

@@ -23,7 +23,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Write PR body to file
         env:

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

@@ -20,4 +20,4 @@ on:
 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-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/on-pr.yml

@@ -25,18 +25,11 @@ on:
       - unlabeled
 
 concurrency:
-  # Use a per-ref group so a newer run (a push, or a change to a label below)
-  # supersedes the in-progress one for that ref. Label events we don't act on get
-  # their own unique group (per run id) instead, keeping them out of the shared
-  # group so real builds keep running. Keep this list in sync with `should-run`.
-  group: >-
-    ${{ github.workflow }}-${{ github.ref }}${{
-      ((github.event.action == 'labeled' || github.event.action == 'unlabeled')
-      && github.event.label.name != 'Ready to merge'
-      && github.event.label.name != 'DraftRunCI'
-      && github.event.label.name != 'Full CI build')
-      && format('-{0}', github.run_id) || ''
-    }}
+  # 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
 
 defaults:
@@ -44,26 +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' or 'Full CI build' label. For label events it only runs when the
-  # label added or removed is one we act on ('Ready to merge', 'DraftRunCI' or
-  # 'Full CI build'), so unrelated label changes do not trigger a redundant run.
+  # 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.action != 'labeled' && github.event.action != 'unlabeled')
-          || github.event.label.name == 'Ready to merge'
-          || github.event.label.name == 'DraftRunCI'
-          || github.event.label.name == 'Full CI build')
-        && (!github.event.pull_request.draft
-          || contains(github.event.pull_request.labels.*.name, 'DraftRunCI')
-          || contains(github.event.pull_request.labels.*.name, 'Full CI build'))
+        !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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        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
@@ -81,29 +70,38 @@ jobs:
           files: |
             # These paths are unique to `on-pr.yml`.
             .github/scripts/levelization/**
+            .github/scripts/otel-naming/**
             .github/scripts/rename/**
             .github/workflows/reusable-check-levelization.yml
+            .github/workflows/reusable-check-otel-naming.yml
             .github/workflows/reusable-check-rename.yml
             .github/workflows/on-pr.yml
 
             # 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/**
@@ -111,6 +109,9 @@ jobs:
             CMakeLists.txt
             conanfile.py
             conan.lock
+            flake.lock
+            flake.nix
+            nix/**
             LICENSE.md
             package/**
             README.md
@@ -136,11 +137,21 @@ jobs:
     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' }}
     uses: ./.github/workflows/reusable-check-levelization.yml
 
+  check-otel-naming:
+    needs: should-run
+    if: ${{ needs.should-run.outputs.go == 'true' }}
+    uses: ./.github/workflows/reusable-check-otel-naming.yml
+
   check-rename:
     needs: should-run
     if: ${{ needs.should-run.outputs.go == 'true' }}
@@ -172,6 +183,13 @@ 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]
     # Packaging consumes the debian/rhel release binaries, which are only built
@@ -179,6 +197,12 @@ jobs:
     # 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:
@@ -210,10 +234,13 @@ jobs:
   passed:
     if: failure() || cancelled()
     needs:
+      - check-autogen
       - check-levelization
+      - check-otel-naming
       - check-rename
       - clang-tidy
       - build-test
+      - rust
       - package
       - upload-recipe
       - notify-clio

.github/workflows/on-tag.yml

@@ -1,5 +1,9 @@
-# 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:
+#
+#   - uploads the libxrpl recipe to the Conan remote
+#   - builds and tests the release binaries
+#   - builds the DEB and RPM packages
+#   - publishes those packages to the XRPLF package repositories
 name: Tag
 
 on:
@@ -24,7 +28,7 @@ jobs:
       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 +41,12 @@ 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 }}

.github/workflows/on-trigger.yml

@@ -15,22 +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/**"
@@ -38,6 +45,9 @@ on:
       - "CMakeLists.txt"
       - "conanfile.py"
       - "conan.lock"
+      - "flake.lock"
+      - "flake.nix"
+      - "nix/**"
       - "LICENSE.md"
       - "package/**"
       - "README.md"
@@ -66,6 +76,9 @@ defaults:
     shell: bash
 
 jobs:
+  check-autogen:
+    uses: ./.github/workflows/reusable-check-autogen.yml
+
   clang-tidy:
     uses: ./.github/workflows/reusable-clang-tidy.yml
     permissions:
@@ -91,6 +104,11 @@ 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.
@@ -103,3 +121,11 @@ jobs:
   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 }}

.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@1bde119a1ab71305ba5d3716e7a82cea1c7bdede
+    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-e29b523
+    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-060957e
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@64ec3cf3b152b4444638f470bbd6df7a7a30c81c
+        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."
@@ -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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@64ec3cf3b152b4444638f470bbd6df7a7a30c81c
+        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}"
@@ -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
@@ -170,9 +205,9 @@ jobs:
               ..
 
       # 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 +225,6 @@ 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:
@@ -223,11 +232,31 @@ 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"
+
+      # 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: ${{ runner.os == 'Linux' && env.SANITIZERS_ENABLED == 'false' }}
+        run: |
+          ./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpld"
+          ./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpl_tests"
 
       - name: Show ccache statistics
         if: ${{ inputs.ccache_enabled }}
@@ -239,7 +268,7 @@ 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 }}
@@ -247,6 +276,22 @@ 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
@@ -264,7 +309,7 @@ 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
@@ -322,27 +367,54 @@ 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 }}
@@ -366,13 +438,14 @@ 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        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-otel-naming.yml

@@ -0,0 +1,28 @@
+# This workflow checks that OpenTelemetry span-attribute names stay consistent
+# across the code (*SpanNames.h), collector, Tempo, dashboards, and docs.
+# See .github/scripts/otel-naming/check_otel_naming.py and the
+# "Telemetry span attribute naming" section in CONTRIBUTING.md.
+name: Check OTel naming
+
+# This workflow can only be triggered by other workflows.
+on: workflow_call
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-otel-naming
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  otel-naming:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
+      - name: Check OTel naming
+        # The script is stdlib-only and reads only files already in the tree;
+        # it enforces each rule only when the layer it needs is present, so it
+        # works whether telemetry changes land in one PR or several.
+        run: python .github/scripts/otel-naming/check_otel_naming.py

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

@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        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

@@ -27,23 +27,23 @@ jobs:
   determine-files:
     permissions:
       contents: read
-    uses: XRPLF/actions/.github/workflows/determine-tidy-files.yml@d041ac9f1fa9f07a4ba335eb4c1c82233fb3fef6
+    uses: XRPLF/actions/.github/workflows/determine-tidy-files.yml@70145243b905dc3e040a61d39c00e178cfb96f71
 
   run-clang-tidy:
     name: Run clang tidy
     needs: [determine-files]
     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-e29b523"
+    container: "ghcr.io/xrplf/xrpld/nix-debian:sha-060957e"
     permissions:
       contents: read
       issues: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@64ec3cf3b152b4444638f470bbd6df7a7a30c81c
+        uses: XRPLF/actions/prepare-runner@b3e255d74d785d053e4903da8ac90983cd7d9e82
         with:
           enable_ccache: false
 
@@ -59,6 +59,12 @@ jobs:
         with:
           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
 
@@ -80,13 +86,13 @@ jobs:
               -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
@@ -95,7 +101,7 @@ jobs:
           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 filtered clang-tidy errors
         if: ${{ steps.run_clang_tidy.outcome != 'success' }}

.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 +1,42 @@
-# 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 three 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'
+#
+# 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 when publishing."
+        required: false
 
 defaults:
   run:
@@ -19,18 +44,21 @@ 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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Set up Python
-        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
         with:
           python-version: "3.13"
 
@@ -41,11 +69,139 @@ jobs:
 
   package:
     needs: [generate-matrix]
-    if: ${{ github.event.repository.visibility == 'public' }}
+    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) }}
+    # The name says which of the two this is, because the job runs either way:
+    # with publish false it passes --dry-run and uploads nothing, and a job
+    # called "publish ..." succeeding on a pull request reads like a release.
+    name: "publish ${{ matrix.xrpld_artifact_name }}${{ !inputs.publish && ' (dry run)' || '' }}"
     permissions:
       contents: read
     runs-on: ["self-hosted", "Linux", "X64", "heavy"]
@@ -54,28 +210,35 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        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_RELEASE: ${{ inputs.pkg_release }}
-        run: ./package/build_pkg.sh
-
-      - name: Upload package artifact
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: ${{ matrix.artifact_name }}-pkg
-          path: |
-            ${{ env.BUILD_DIR }}/debbuild/*.deb
-            ${{ env.BUILD_DIR }}/debbuild/*.ddeb
-            ${{ env.BUILD_DIR }}/rpmbuild/RPMS/**/*.rpm
-          if-no-files-found: error
+          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}

.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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Set up Python
-        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
         with:
           python-version: "3.13"
 

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

@@ -40,18 +40,23 @@ defaults:
 jobs:
   upload:
     runs-on: ubuntu-latest
-    container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-e29b523
+    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@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        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
@@ -64,8 +69,8 @@ jobs:
 
       - name: Upload Conan recipe (version)
         run: |
-          conan export . --version=${{ steps.version.outputs.version }}
-          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/${{ steps.version.outputs.version }}
+          conan export . --version=${{ steps.release_info.outputs.version }}
+          conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/${{ steps.release_info.outputs.version }}
 
       # When this workflow is triggered by a push event, it will always be when merging into the
       # 'develop' branch, see on-trigger.yml.
@@ -92,4 +97,4 @@ jobs:
           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

@@ -65,13 +65,18 @@ jobs:
         uses: XRPLF/actions/cleanup-workspace@c7d9ce5ebb03c752a354889ecd870cadfc2b1cd4
 
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
 
       - name: Prepare runner
-        uses: XRPLF/actions/prepare-runner@64ec3cf3b152b4444638f470bbd6df7a7a30c81c
+        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
@@ -106,6 +113,10 @@ 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}" "${{ secrets.NEXUS_REMOTE_USERNAME }}" --password "${{ secrets.NEXUS_REMOTE_PASSWORD }}"

.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
 
 # clangd cache
 /.cache
+
+# Rust build directory
+crates/target
+
+# Env. file carrying environmental setup data for local or cloud runs.
+.env.*

.pre-commit-config.yaml

@@ -53,31 +53,66 @@ repos:
         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: f4d7745e17a28aad7eed2f4874ca8d1568c11c4c # frozen: v22.1.8
     hooks:
       - id: clang-format
         args: [--style=file]
         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: e98930bdc210d3387007f9252d8c1694ea7e410f # frozen: 0.27.7
     hooks:
       - id: gersemi
 
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: 39e2973981e6d2f9b6c543b0086a2d2393abdc89 # frozen: v3.9.4
+    rev: 9337a74165b178ae2c766f60bee7252a0f06f3e8 # frozen: v3.9.5
     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: 7c55798a78262d14b2074abf623d8a992ebb70d4 # frozen: v0.16.2
+    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: 41e691678310dfd3833f7ab4e180ddb014310356 # frozen: v2.3.0
+    hooks:
+      - id: mypy
+        args: [--strict]
+        files: ^package/.*\.py$
+
   - repo: https://github.com/scop/pre-commit-shfmt
     rev: 05c1426671b9237fb5e1444dd63aa5731bec0dfb # frozen: v3.13.1-1
     hooks:

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

@@ -22,17 +22,48 @@ 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 3.4.0
 
-This section contains changes targeting a future version.
+Version 3.4.0 is not yet released. These changes are available in the 3.4.0 beta releases.
 
-### Additions
+### Additions in 3.4.0
 
-- `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.
+- `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.
@@ -40,7 +71,7 @@ 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)
@@ -54,6 +85,24 @@ 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 | 21              |
-| 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
 
@@ -72,37 +53,25 @@ releases](https://github.com/XRPLF/rippled/releases).
 
 ### 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.xrplf.org/repository/conan/
-```
+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 +214,17 @@ 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 +236,14 @@ 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`
@@ -321,6 +304,7 @@ See [Sanitizers docs](./docs/build/sanitizers.md) for more details.
 | ---------------- | ------------- | ----------------------------------------------------------------------------- |
 | `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. |
@@ -333,6 +317,30 @@ 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
@@ -377,10 +385,14 @@ 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
 
@@ -400,7 +412,6 @@ 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)
@@ -87,6 +104,7 @@ 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)
@@ -102,6 +120,7 @@ target_link_libraries(
     xrpl_libs
     INTERFACE
         ed25519::ed25519
+        FastFloat::fast_float
         lz4::lz4
         mpt-crypto::mpt-crypto
         OpenSSL::Crypto
@@ -121,6 +140,20 @@ if(rocksdb)
     target_link_libraries(xrpl_libs INTERFACE RocksDB::rocksdb)
 endif()
 
+# OpenTelemetry distributed tracing (optional).
+# When on, links against opentelemetry-cpp and defines XRPL_ENABLE_TELEMETRY
+# so that SpanGuard factory methods produce real OTel spans.
+# When off, all tracing code compiles to no-ops with zero overhead.
+#
+# There is no CMake option. The one switch is `conan install -o telemetry=`,
+# which decides whether opentelemetry-cpp is fetched and sets the variable read
+# below through the generated toolchain.
+if(telemetry)
+    find_package(opentelemetry-cpp CONFIG REQUIRED)
+    add_compile_definitions(XRPL_ENABLE_TELEMETRY)
+    message(STATUS "OpenTelemetry tracing enabled")
+endif()
+
 # Work around changes to Conan recipe for now.
 if(TARGET nudb::core)
     set(nudb nudb::core)
@@ -131,17 +164,33 @@ 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)
 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

@@ -59,6 +59,17 @@ 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.)
@@ -82,7 +93,8 @@ 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 easiest
 way to satisfy this is to install the [`pre-commit`](#pre-commit-hooks) hooks,
@@ -224,8 +236,9 @@ 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` — run tools from your own environment; see
-[Installing clang-tidy](#installing-clang-tidy) for how to get those.
+`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:
 
@@ -254,6 +267,7 @@ The hooks configured in this repository include, among others:
 - `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
 
@@ -318,7 +332,11 @@ 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)
 
@@ -347,12 +365,74 @@ 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.
+
+All attribute keys are `lower_snake_case` (lowercase letters, digits, and
+underscores; each dot-separated segment of a resource key likewise). No
+camelCase, uppercase, or spaces.
+
+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 for attribute keys and span
+names — never pass a string literal as a key or as a `span`/`childSpan` name
+argument. (Attribute _values_ may be runtime data.)
+
+These rules are enforced by `.github/scripts/otel-naming/check_otel_naming.py`,
+run in CI on every pull request. The check derives the set of valid keys
+directly from the `*SpanNames.h` constants and the resource attributes the code
+registers, so there is no separate list to keep in sync. It cross-validates the
+collector, Tempo, dashboards, and docs against those keys, and each rule runs
+only when the file it needs is present — so it works whether telemetry changes
+land in one pull request or several. Run it locally with:
+
+```
+python .github/scripts/otel-naming/check_otel_naming.py
+```
+
+See [.github/scripts/otel-naming/README.md](.github/scripts/otel-naming/README.md)
+for the full rule list.
+
 ## Contracts and instrumentation
 
 We are using [Antithesis](https://antithesis.com/) for continuous fuzzing,

OpenTelemetryPlan/00-tracing-fundamentals.md

@@ -0,0 +1,569 @@
+# 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. xrpld uses a
+> `ParentBased` sampler so spans with a remote parent honor the upstream
+> decision. 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 +1,705 @@
+# 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 | Sending account, raw r-address                                                                                                                                |
+| `tx_<field>`         | string | One per account-typed top-level field the transaction carries (`tx_destination`, `tx_owner`, `tx_issuer`, ...), raw r-address; keys in `TxAccountSpanNames.h` |
+| `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                      |
+
+Establish-phase gap fill and cross-node correlation attributes (Phase 4a):
+
+| Key                   | Type   | Description                                               |
+| --------------------- | ------ | --------------------------------------------------------- |
+| `consensus_round_id`  | int64  | Consensus round number                                    |
+| `consensus_ledger_id` | string | `previousLedger.id()` — shared across nodes               |
+| `trace_strategy`      | string | `"deterministic"` or `"random"`                           |
+| `converge_percent`    | int64  | Convergence % (0-100+)                                    |
+| `establish_count`     | int64  | Number of establish iterations                            |
+| `disputes_count`      | int64  | Active disputed transactions                              |
+| `agree_count`         | int64  | Peers that agree (haveConsensus)                          |
+| `disagree_count`      | int64  | Peers that disagree                                       |
+| `threshold_percent`   | int64  | Close-time consensus threshold (`avCT_CONSENSUS_PCT`=75%) |
+| `consensus_result`    | string | `"yes"`, `"no"`, `"moved_on"`, `"expired"`                |
+| `mode_old`            | string | Previous consensus mode                                   |
+| `mode_new`            | string | New consensus mode                                        |
+
+#### 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_account`  | string | Source r-address, raw                                                  |
+| `pathfind_dest_account`    | string | Destination r-address, raw                                             |
+| `pathfind_source_currency` | string | Source currency code                                                   |
+| `pathfind_dest_currency`   | string | Destination asset: `XRP`, `<issuer>/<currency>`, or an MPT issuance id |
+| `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_fast`, `pathfind_search_level`, `pathfind_num_paths`, `pathfind_ledger_index`, `pathfind_num_requests` | 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 Addresses**         | Emitted raw (`pathfind_source_account`, `pathfind_dest_account`). An account address is a public ledger identifier; hashing it protects nothing and breaks the join against explorers, RPC and logs |
+| **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                                                             |
+| **Sampling**                  | Only 10% of traces recorded by default, reducing data exposure                                                                                                                                      |
+| **Local Control**             | Node operators have full control over what gets exported                                                                                                                                            |
+| **No Raw Payloads**           | Transaction content is never recorded, only metadata (hash, type, result)                                                                                                                           |
+| **Collector-Level Filtering** | Available for a future genuinely sensitive attribute via an `attributes` processor. None is shipped, and none must be added for account addresses                                                   |
+
+#### Account Addresses
+
+Account addresses are emitted **raw**, at every layer:
+
+1. **SDK-side** (this node): the path-finding RPC handlers set
+   `pathfind_source_account` / `pathfind_dest_account` to the request's
+   r-address, only when it parses as one, and `pathfind_dest_currency` to `to_string(Asset)`,
+   which carries the IOU issuer's r-address. The rationale sits on the attribute
+   constants in `PathFindSpanNames.h`.
+2. **Collector-side**: no collector configuration in this repository hashes
+   or deletes these attributes.
+
+Why raw: an r-address is a public, enumerable identifier on the ledger. An
+unsalted hash of it is reversible by table lookup, so it protects nothing, and
+it breaks the one thing the attribute is for: joining a span to the account as
+explorers, RPC responses and logs show it. The helper `redactAccount()`
+(`xrpl::telemetry`, `Redaction.h`) remains available for a value that is
+genuinely private, but it is applied to no span.
+
+#### Collector-Level Data Protection
+
+No hashing or redaction processor is shipped. If a future span introduces a
+genuinely sensitive attribute, an `attributes` processor in the collector is the
+place to strip it, and the attribute is added to the §2.4 catalogue with that
+note in the same change. Account addresses are not such an attribute.
+
+#### 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. There is no
+redaction setting: account addresses are public and are emitted raw.
+
+> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes, public identifiers) — never **sensitive content** (keys, balances, amounts, raw payloads).
+
+---
+
+## 2.5 Context Propagation Design
+
+> **WS** = WebSocket
+
+### 2.5.0 Deterministic Trace ID Strategy
+
+Both transaction and consensus tracing use **deterministic trace IDs** derived from
+a globally known hash, so all nodes handling the same workflow independently produce
+spans under the same `trace_id`. This is combined with protobuf `span_id` propagation
+for parent-child relay ordering when available.
+
+#### Transactions — `trace_id = txHash[0:16]`
+
+Every node that handles a transaction knows its `txID` (the `uint256` transaction
+hash). The first 16 bytes of this hash are used as the OTel `trace_id`:
+
+```
+uint256 txHash:  A1B2C3D4 E5F6A7B8 C9D0E1F2 A3B4C5D6  E7F8A9B0 C1D2E3F4 A5B6C7D8 E9F0A1B2
+                 |---------- trace_id (16 bytes) ---------|  (remaining 16 bytes unused)
+```
+
+Each node generates a **random 8-byte `span_id`** so its span is unique within the
+shared trace. When protobuf `TraceContext` is present in the incoming `TMTransaction`,
+the sender's `span_id` is extracted and used as the parent — preserving the relay
+chain as a parent-child tree. When absent (older peers, first hop from client), the
+span appears as a root in the same trace — correlation is preserved, only the tree
+structure degrades.
+
+```
+Node A (submitter)        Node B (relay)          Node C (relay)
+trace_id: A1B2...         trace_id: A1B2...       trace_id: A1B2...
+span_id:  1234 (random)   span_id:  5678 (random) span_id:  9ABC (random)
+parent:   (none)          parent:   1234 (proto)   parent:   5678 (proto)
+                               ↑                        ↑
+                       protobuf propagation      protobuf propagation
+```
+
+If protobuf propagation fails at Node B (old peer):
+
+```
+Node A                    Node B (old peer)       Node C
+trace_id: A1B2...         trace_id: A1B2...       trace_id: A1B2...
+span_id:  1234            span_id:  5678          span_id:  9ABC
+parent:   (none)          parent:   (none)        parent:   5678 (proto)
+                          ↑ no parent, but same trace_id — still grouped
+```
+
+#### Consensus — `trace_id = prevLedgerHash[0:16]`
+
+All validators in the same consensus round share the same `previousLedger.id()`.
+The first 16 bytes are used as trace_id. See [Phase 4a implementation status](./06-implementation-phases.md)
+and `createDeterministicContext()` in `RCLConsensus.cpp` for the implementation.
+
+Switchable via `consensus_trace_strategy` config:
+`"deterministic"` (default) or `"random"` (random trace_id, correlation via attribute queries).
+`"random"` is experimental and not used: it would break cross-node trace correlation.
+
+#### Why Not Random IDs with Propagation Only?
+
+Random trace IDs require **unbroken context propagation** across every hop. In a
+mixed-version network (common during upgrades), older peers silently drop the
+`trace_context` protobuf field. The trace splits and downstream spans become
+impossible to find. Deterministic IDs make correlation **propagation-resilient** — the trace
+backend groups all spans for the same transaction/round regardless of whether
+propagation succeeded.
+
+#### Why Keep Protobuf Propagation?
+
+Deterministic trace IDs alone provide correlation (all spans grouped) but not
+**causality** (which node relayed to which). Protobuf `span_id` propagation adds
+parent-child ordering that shows the exact relay path. The two mechanisms complement
+each other:
+
+| Mechanism                    | Provides                    | Fails when                             |
+| ---------------------------- | --------------------------- | -------------------------------------- |
+| Deterministic trace_id       | Cross-node correlation      | Never (hash is always known)           |
+| Protobuf span_id propagation | Parent-child relay ordering | Older peer drops `trace_context` field |
+
+#### Implementation Reference
+
+The utility function `createDeterministicTxContext(uint256 const& txHash)` follows
+the same pattern as `createDeterministicContext(uint256 const& ledgerId)` in
+`RCLConsensus.cpp`. See [Phase 3 Task 3.9](./Phase3_taskList.md) for the full spec.
+
+### 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/>  string trace_state = 4;<br/>}"]
+    end
+
+    subgraph jobqueue["JobQueue (Internal Async)"]
+        job["Context captured at job creation,<br/>restored at execution<br/><br/>class Job {<br/>  otel::context::Context<br/>    traceContext_;<br/>};"]
+    end
+
+    style http fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style protobuf fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style jobqueue fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **HTTP/WebSocket - RPC (blue)**: For client-facing RPC requests, trace context is propagated using the W3C `traceparent` header. This is the standard approach and works with any OTel-compatible client.
+- **Protocol Buffers - P2P (green)**: For peer-to-peer messages between 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 +1,411 @@
+# 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 (global singleton)
+│   ├── TelemetryConfig.h        # Configuration structures
+│   ├── TraceContext.h           # Context propagation utilities
+│   ├── SpanGuard.h              # RAII span management with factory methods + discard()
+│   ├── DiscardFlag.h            # Thread-local discard flag
+│   └── SpanAttributes.h         # Attribute helper functions
+
+src/libxrpl/
+├── telemetry/
+│   ├── Telemetry.cpp            # Implementation + FilteringSpanProcessor
+│   ├── TelemetryConfig.cpp      # Config parsing
+│   ├── TraceContext.cpp         # Context serialization
+│   └── NullTelemetry.cpp        # No-op implementation
+```
+
+---
+
+## 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 +1,268 @@
+# 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 | **mTLS** = mutual TLS
+
+### 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`                  | 0 or 1 | `0`                               | Enable/disable telemetry                                                                                                |
+| `traces_endpoint`          | string | `http://localhost:4318/v1/traces` | Full OTLP/HTTP URL for spans, used verbatim                                                                             |
+| `use_tls`                  | 0 or 1 | `0`                               | Enable TLS for exporter connection                                                                                      |
+| `tls_ca_cert`              | string | `""`                              | Path to CA certificate file                                                                                             |
+| `tls_client_cert`          | string | `""`                              | Client cert (PEM) for mTLS; empty = one-way; if `enabled=1`, needs key + `use_tls=1` or startup fails                   |
+| `tls_client_key`           | string | `""`                              | Private key (PEM) for `tls_client_cert`; if set with `enabled=1`, needs the cert + `use_tls=1` or fails                 |
+| `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                                                                                                   |
+| `tx_trace_strategy`        | string | `"deterministic"`                 | TX trace ID strategy: `"deterministic"` (trace_id = txHash[0:16]) or `"attribute"` (random)                             |
+| `consensus_trace_strategy` | string | `"deterministic"`                 | Consensus trace ID strategy: `"deterministic"` (trace_id = prevLedgerHash[0:16]) or `"random"` (experimental, not used) |
+| `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                 |
+
+---
+
+## 5.2 Configuration Parser
+
+> **TxQ** = Transaction Queue
+
+The parser `makeTelemetrySetup()` 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.valueOr(...)`. 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 `makeTelemetry(makeTelemetrySetup(...))` 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_grpc/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 stamps `deployment.environment`. Account addresses are public identifiers and are not hashed at any layer. 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["makeTelemetrySetup()"]
+        factory["makeTelemetry()"]
+    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**: `makeTelemetrySetup()` parses config values, then `makeTelemetry()` 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 +1,673 @@
+# 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
+    Establish Phase (4a)      :p4f, after p4b, 3d
+    Validation Tests          :p4c, after p4f, 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 with deterministic cross-node correlation
+
+### 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  | Deterministic transaction trace ID (`trace_id = txHash[0:16]`) |
+| 3.10 | Performance benchmarks                                         |
+
+### Deterministic Trace ID (Task 3.9)
+
+Transaction spans use **deterministic trace IDs** derived from the transaction hash:
+`trace_id = txHash[0:16]`. All nodes handling the same transaction independently
+produce spans under the same trace_id. Protobuf `span_id` propagation (Task 3.7)
+additionally provides parent-child relay ordering when available. See
+[02-design-decisions.md §2.5.0](./02-design-decisions.md) for the design rationale
+and [Phase3_taskList.md Task 3.9](./Phase3_taskList.md) for the full implementation spec.
+
+### 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
+- [ ] Deterministic trace_id: all nodes produce same trace_id for same transaction
+- [ ] Protobuf span_id propagation preserves parent-child ordering when available
+
+---
+
+## 6.5 Phase 4: Consensus Tracing (Weeks 7-8)
+
+**Objective**: Full observability into consensus rounds
+
+### Tasks
+
+| Task | Description                                 | Status             |
+| ---- | ------------------------------------------- | ------------------ |
+| 4.1  | Instrument `RCLConsensus::startRound()`     | ✅ Done (via 4a.2) |
+| 4.2  | Instrument phase transitions                | ✅ Done            |
+| 4.3  | Instrument proposal handling                | ✅ Done            |
+| 4.4  | Instrument validation handling              | ✅ Done            |
+| 4.5  | Add consensus-specific attributes           | ✅ Done            |
+| 4.6  | Correlate with transaction traces           | ✅ Done            |
+| 4.7  | Build verification and testing              | ✅ Done            |
+| 4.8  | Validation span enrichment (ext. dashboard) | ❌ Not done        |
+
+**Note**: The original plan doc listed tasks 4.7-4.11 as "Validator list tracing",
+"Amendment voting tracing", "SHAMap sync tracing", "Multi-validator integration tests",
+and "Performance validation". These were descoped and replaced by the tasklist's 4.7
+(build verification) and 4.8 (validation span enrichment). Validator, amendment, and
+SHAMap tracing are not implemented.
+
+### Spans Produced
+
+| Span Name                   | Location           | Attributes                                                                                                                                                                                                                                                    |
+| --------------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `consensus.phase.open`      | `Consensus.h`      | _(none)_                                                                                                                                                                                                                                                      |
+| `consensus.proposal.send`   | `RCLConsensus.cpp` | `consensus_round`                                                                                                                                                                                                                                             |
+| `consensus.ledger_close`    | `RCLConsensus.cpp` | `ledger_seq`, `consensus_mode`                                                                                                                                                                                                                                |
+| `consensus.accept`          | `RCLConsensus.cpp` | `proposers`, `round_time_ms`, `quorum`                                                                                                                                                                                                                        |
+| `consensus.accept.apply`    | `RCLConsensus.cpp` | `close_time_ripple_epoch_s`, `close_time_correct`, `close_resolution_ms`, `consensus_state`, `proposing`, `round_time_ms`, `ledger_seq`, `parent_close_time_ripple_epoch_s`, `close_time_self_ripple_epoch_s`, `close_time_vote_bins`, `resolution_direction` |
+| `consensus.validation.send` | `RCLConsensus.cpp` | `ledger_seq`, `proposing`                                                                                                                                                                                                                                     |
+
+### Exit Criteria
+
+- [x] Complete consensus round traces
+- [x] Phase transitions visible (open, establish, close, accept)
+- [x] Proposals and validations traced — send and receive; relay deferred to Phase 4b
+- [x] Close time agreement tracked (per `avCT_CONSENSUS_PCT`)
+- [x] No impact on consensus timing
+- [ ] Multi-validator test network validated
+- [x] Transaction-consensus correlation (Task 4.6) — `tx.included` events in doAccept
+- [ ] Validation span enrichment (Task 4.8) — not implemented
+
+### Implementation Status — Phase 4a Complete
+
+Phase 4a (establish-phase gap fill & cross-node correlation) adds:
+
+- **Deterministic trace ID** derived from `previousLedger.id()` so all validators
+  in the same round share the same `trace_id` (switchable via
+  `consensus_trace_strategy` config: `"deterministic"`, or `"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`).
+
+See [Phase4_taskList.md](./Phase4_taskList.md) for the full spec and implementation notes.
+
+---
+
+## 6.5a Phase 4a: Establish-Phase Gap Fill & Cross-Node Correlation
+
+**Objective**: Fill tracing gaps in the establish phase and establish cross-node
+correlation using deterministic trace IDs derived from `previousLedger.id()`.
+
+**Approach**: Direct instrumentation in `Consensus.h` and `RCLConsensus.cpp`.
+All spans use `SpanGuard` factory methods (`span()`, `hashSpan()`, `linkedSpan()`)
+with `TraceCategory::Consensus` gating. No macros used — all tracing via direct
+`SpanGuard` API calls.
+
+### Tasks
+
+| Task | Description                                      | Effort | Risk   | Status                   |
+| ---- | ------------------------------------------------ | ------ | ------ | ------------------------ |
+| 4a.0 | Prerequisites: extend SpanGuard & Telemetry APIs | 1d     | Medium | ✅ Done (no macros)      |
+| 4a.1 | Adaptor `getTelemetry()` method                  | 0.5d   | Low    | ⏭️ Skipped (not needed)  |
+| 4a.2 | Switchable round span with deterministic traceID | 2d     | High   | ✅ Done                  |
+| 4a.3 | Span members in `Consensus.h`                    | 0.5d   | Medium | ✅ Done (with deviation) |
+| 4a.4 | Instrument `phaseEstablish()`                    | 1d     | Medium | ✅ Done                  |
+| 4a.5 | Instrument `updateOurPositions()`                | 1d     | Medium | ✅ Done                  |
+| 4a.6 | Instrument `haveConsensus()` (thresholds)        | 1d     | Medium | ✅ Done                  |
+| 4a.7 | Instrument mode changes                          | 0.5d   | Low    | ✅ Done                  |
+| 4a.8 | Reparent existing spans under round              | 0.5d   | Low    | ✅ Done                  |
+| 4a.9 | Build verification and testing                   | 1d     | Low    | ✅ Done                  |
+
+**Total Effort**: 9 days
+
+### Spans Produced
+
+| Span Name                    | Location           | Key Attributes (actually set)                                                                                                 |
+| ---------------------------- | ------------------ | ----------------------------------------------------------------------------------------------------------------------------- |
+| `consensus.round`            | `RCLConsensus.cpp` | `consensus_round_id`, `consensus_ledger_id`, `ledger_seq`, `consensus_mode`, `trace_strategy`                                 |
+| `consensus.establish`        | `Consensus.h`      | `converge_percent`, `establish_count`, `proposers`                                                                            |
+| `consensus.update_positions` | `Consensus.h`      | `converge_percent`, `proposers`, `have_close_time_consensus`, `close_time_threshold`, `disputes_count`, `avalanche_threshold` |
+| `consensus.check`            | `Consensus.h`      | `agree_count`, `disagree_count`, `converge_percent`, `have_close_time_consensus`, `threshold_percent`, `consensus_result`     |
+| `consensus.mode_change`      | `RCLConsensus.cpp` | `mode_old`, `mode_new`                                                                                                        |
+
+### Exit Criteria
+
+- [x] Establish phase internals traced (establish, update_positions, check spans)
+- [x] Establish phase fully traced — `disputes_count`, `avalanche_threshold`, dispute `yays`/`nays` all implemented
+- [x] Cross-node correlation works via deterministic trace_id
+- [x] Strategy switchable via config (`deterministic` / `attribute`)
+- [x] Consecutive rounds linked via follows-from spans
+- [x] Build passes with telemetry ON and OFF
+- [x] No impact on consensus timing
+
+See [Phase4_taskList.md](./Phase4_taskList.md) for full task details.
+
+---
+
+## 6.5b Phase 4b: Cross-Node Propagation (Future)
+
+**Objective**: Wire `TraceContextPropagator` for P2P messages (proposals,
+validations) to enable true distributed tracing between nodes.
+
+**Status**: Partially implemented. Send-side injection (proposals and
+validations) and receive-side extraction (`consensus.{proposal,validation}.
+receive` spans parented on the sender's context) are wired in Phase 4a.
+Remaining Phase 4b work: relay spans in `share(RCLCxPeerPos)` and multi-node
+validation of the propagation path.
+
+**Prerequisites**: Phase 4a complete and validated.
+
+See [Phase4_taskList.md § Phase 4b](./Phase4_taskList.md) for full design.
+
+---
+
+## 6.6 Phase 5: Documentation & Deployment (Week 9)
+
+**Objective**: Production readiness
+
+### Tasks
+
+| Task | Description                   |
+| ---- | ----------------------------- |
+| 5.1  | Operator runbook              |
+| 5.2  | Grafana dashboards            |
+| 5.3  | Alert definitions             |
+| 5.4  | Collector deployment examples |
+| 5.5  | Developer documentation       |
+| 5.6  | Training materials            |
+| 5.7  | Final integration testing     |
+
+---
+
+## 6.7 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[Establish Phase<br/>& Cross-Node Correlation] ~~~ r3[StatsD Integration] ~~~ 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, establish-phase gap fill, cross-node correlation, StatsD integration, 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~~ — descoped
+- ~~Amendment voting tracing~~ — descoped
+- ~~SHAMap sync tracing~~ — descoped
+- Full end-to-end traces (client → RPC → TX → consensus → ledger) — partial (tx-consensus correlation not yet done)
+
+**Code Changes**: ~100 lines across 3 consensus files
+
+**Why Do This Last**:
+
+- Highest complexity (consensus is critical path)
+- Validator, amendment, and SHAMap components were descoped (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                                   |
+| Deterministic TraceID | Same trace_id on all nodes for same tx            | Multi-node test: query by txHash[0:16] returns all spans |
+| Relay Ordering        | Protobuf span_id propagation creates parent-child | Tempo trace tree shows relay chain                       |
+| Graceful Degradation  | Old peer drops trace_context                      | Spans still grouped by deterministic trace_id            |
+| 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 with deterministic trace_id correlation, parent-child ordering via protobuf propagation, and 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. xrpld uses a `ParentBased` sampler so spans inheriting a remote parent honor the upstream decision. 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 +1,196 @@
+# 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        |
+
+### Task Lists
+
+| Document                                   | Description                          |
+| ------------------------------------------ | ------------------------------------ |
+| [Phase2_taskList.md](./Phase2_taskList.md) | RPC layer trace instrumentation      |
+| [Phase3_taskList.md](./Phase3_taskList.md) | Peer overlay & consensus tracing     |
+| [Phase4_taskList.md](./Phase4_taskList.md) | Transaction lifecycle tracing        |
+| [Phase5_taskList.md](./Phase5_taskList.md) | Ledger processing & advanced tracing |
+
+---
+
+_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). Account addresses are public ledger identifiers and are emitted raw; there is no redaction setting. Trace volume is reduced, where wanted, by collector-side sampling. 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` (with `discard()` for dropping unwanted spans), a `FilteringSpanProcessor` that intercepts `OnEnd()` to prevent discarded spans from entering the export pipeline, 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._

OpenTelemetryPlan/Phase2_taskList.md

@@ -0,0 +1,207 @@
+# Phase 2: RPC Tracing Completion Task List
+
+> **Goal**: Complete RPC tracing coverage with unit tests, Grafana search filters, PathFind instrumentation, and config hardening. Build on the Phase 1c SpanGuard factory foundation to achieve production-quality RPC observability.
+>
+> **Scope**: Unit tests for core telemetry, Grafana Tempo search filters, PathFind RPC tracing, config validation (`std::clamp`).
+>
+> **Branch**: `pratik/otel-phase2-rpc-tracing` (from `pratik/otel-phase1c-rpc-integration`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                     |
+| ------------------------------------------------------------ | ------------------------------------------------------------- |
+| [04-code-samples.md](./04-code-samples.md)                   | TraceContextPropagator (§4.4.2), RPC instrumentation (§4.5.3) |
+| [02-design-decisions.md](./02-design-decisions.md)           | W3C Trace Context (§2.5), span attributes (§2.4.2)            |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 2 tasks (§6.3), definition of done (§6.11.2)            |
+
+---
+
+## Task 2.1: W3C Trace Context HTTP Header Extraction
+
+**Status**: DEFERRED → Phase 3
+
+**Reason**: W3C context propagation (`traceparent`/`tracestate` headers) requires a consumer — in Phase 2, RPC spans are entirely local to the node. Phase 3 introduces cross-node transaction tracing via protobuf context propagation, which is the first use case for extracted trace context. Implementing it here without a consumer would be dead code.
+
+**Implemented in**: `pratik/otel-phase3-tx-tracing` — `TraceContextPropagator.h/.cpp`
+
+---
+
+## Task 2.2: Per-Category Span Creation
+
+**Status**: COMPLETE (superseded by Phase 1c design)
+
+**Original plan**: Add `XRPL_TRACE_PEER` and `XRPL_TRACE_LEDGER` macros.
+
+**Actual implementation**: Phase 1c replaced all tracing macros with the `SpanGuard::span(TraceCategory, prefix, name)` factory pattern. The `TraceCategory` enum (`Rpc`, `Transactions`, `Consensus`, `Peer`, `Ledger`) serves the same conditional-creation purpose without macros. No separate task needed — the factory already supports all categories.
+
+---
+
+## Task 2.3: Add shouldTraceLedger() to Telemetry Interface
+
+**Objective**: The `Setup` struct has a `traceLedger` field but there's no corresponding virtual method. Add it for interface completeness.
+
+**What to do**:
+
+- Edit `include/xrpl/telemetry/Telemetry.h`:
+  - Add `virtual bool shouldTraceLedger() const = 0;`
+
+- Update all implementations:
+  - `src/libxrpl/telemetry/Telemetry.cpp` (TelemetryImpl, NullTelemetryOtel)
+  - `src/libxrpl/telemetry/NullTelemetry.cpp` (NullTelemetry)
+
+**Key modified files**:
+
+- `include/xrpl/telemetry/Telemetry.h`
+- `src/libxrpl/telemetry/Telemetry.cpp`
+- `src/libxrpl/telemetry/NullTelemetry.cpp`
+
+---
+
+## Task 2.4: Unit Tests for Core Telemetry Infrastructure
+
+**Status**: COMPLETE
+
+**Objective**: Add unit tests for the core telemetry abstractions to validate correctness and catch regressions.
+
+**Implemented**:
+
+- `src/tests/libxrpl/telemetry/TelemetryConfig.cpp`:
+  - Test Setup defaults (all fields have correct initial values)
+  - Test `makeTelemetrySetup` config parser (empty section, full section, edge cases)
+  - Test `samplingRatio` clamping (values outside 0.0-1.0)
+
+- `src/tests/libxrpl/telemetry/SpanGuardFactory.cpp`:
+  - Test null guard methods are safe (setAttribute, setOk, setError, addEvent on null)
+  - Test category span returns null when telemetry disabled
+  - Test child/linked span null when no parent context
+  - Test move construction transfers ownership
+  - Test recordException safe on null guard
+  - Test discard() safe on null guard
+
+- `src/tests/libxrpl/telemetry/main.cpp` — GTest runner
+- `src/tests/libxrpl/CMakeLists.txt` — test target with optional OTel linking
+
+---
+
+## Task 2.5: Enhance RPC Span Attributes
+
+**Status**: DEFERRED (low priority)
+
+**Reason**: The high-value attributes (`command`, `version`, `role`, `status`) are already set by Phase 1c. The remaining HTTP transport-level attributes (`http.method`, `net.peer.ip`, `http.status_code`) provide limited additional insight since:
+
+- `http.method` is always POST for JSON-RPC
+- `net.peer.ip` is debug-level info available in logs
+- `duration_ms` is redundant with span duration (OTel captures start/end time natively)
+
+These can be added later if dashboard queries specifically need them. The node health attributes (Task 2.8) provide far more operational value and were prioritized instead.
+
+---
+
+## Task 2.6: Build Verification and Performance Baseline
+
+**Objective**: Verify the build succeeds with and without telemetry, and establish a performance baseline.
+
+**What to do**:
+
+1. Build with `telemetry=ON` and verify no compilation errors
+2. Build with `telemetry=OFF` and verify no regressions
+3. Run existing unit tests to verify no breakage
+4. Document any build issues in lessons.md
+
+**Verification Checklist**:
+
+- [ ] `conan install . --build=missing -o telemetry=True` succeeds
+- [ ] `cmake --preset default -Dtelemetry=ON` configures correctly
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass with telemetry ON
+- [ ] Existing tests pass with telemetry OFF
+
+---
+
+## Task 2.8: RPC Span Attribute Enrichment — Node Health Context
+
+**Status**: DROPPED.
+
+Node health (`amendment_blocked`, `server_state`) is not part of the telemetry surface. Operators consume the same data via the existing `server_info` / `server_state` RPC commands, so duplicating it on traces adds storage and cardinality cost without new value. The OTel C++ SDK 1.18.0 also does not support runtime updates to the resource, ruling out resource-level emission of these dynamic-by-nature flags.
+
+---
+
+## Task 2.9: PathFind RPC Instrumentation
+
+**Status**: COMPLETE
+
+**Objective**: Trace the path_find and ripple_path_find RPC handlers to capture request latency and computation cost.
+
+**Spans added**:
+
+- `pathfind.request` — wraps `doPathFind()` and `doRipplePathFind()` RPC handlers
+- `pathfind.compute` — wraps `PathRequest::doUpdate()` (`pathfind_fast` attr)
+- `pathfind.update_all` — wraps `PathRequestManager::updateAll()` on ledger close (`pathfind_ledger_index`, `pathfind_num_requests` attrs; emitted only when active subscriptions exist)
+- `pathfind.discover` — wraps the entire per-source-asset loop in `PathRequest::findPaths()` (`pathfind_search_level`, `pathfind_num_paths` attrs). One span per RPC call instead of N (one per source asset). Trade-off: per-asset breakdown is lost; storage and cardinality bounded.
+
+**Attribute namespacing**: All pathfind attributes use the `pathfind_*` underscore form per the Phase 1c naming-spec rule 5.
+
+**New file**: `src/xrpld/rpc/detail/PathFindSpanNames.h`
+
+**Modified files**:
+
+- `src/xrpld/rpc/handlers/orderbook/PathFind.cpp`
+- `src/xrpld/rpc/handlers/orderbook/RipplePathFind.cpp`
+- `src/xrpld/rpc/detail/PathRequest.cpp`
+- `src/xrpld/rpc/detail/PathRequestManager.cpp`
+- `src/xrpld/rpc/detail/Pathfinder.cpp`
+
+---
+
+## Task 2.10: RPC and PathFind Span Attribute Gap Fill
+
+**Status**: COMPLETE
+
+**Objective**: Wire up workflow-identifying attributes that enable filtering and grouping traces by request characteristics without drilling into child spans.
+
+**Attributes added**:
+
+| Span                | Attribute                    | Type   | Source                            |
+| ------------------- | ---------------------------- | ------ | --------------------------------- |
+| `rpc.http_request`  | `request_payload_size`       | int64  | `request.body().size()`           |
+| `rpc.process`       | `is_batch`                   | bool   | `method == "batch"` check         |
+| `rpc.process`       | `batch_size`                 | int64  | `params.size()` (only when batch) |
+| `rpc.ws_message`    | `command`                    | string | `jv[command]` or `jv[method]`     |
+| `rpc.command.*`     | `load_type`                  | string | `context.loadType.label()`        |
+| `pathfind.compute`  | `pathfind_dest_currency`     | string | `to_string(saDstAmount_.asset())` |
+| `pathfind.discover` | `pathfind_num_source_assets` | int64  | `sourceAssets.size()`             |
+
+_Note: `pathfind_dest_amount` was removed — the destination amount is a financial value excluded by the privacy policy (design §2.4.4)._
+
+**New attr keys**: `RpcSpanNames.h` (`isBatch`, `batchSize`, `loadType`), `PathFindSpanNames.h` (`destCurrency`, `numSourceAssets`).
+
+**Modified files**:
+
+- `src/xrpld/rpc/detail/RpcSpanNames.h`
+- `src/xrpld/rpc/detail/PathFindSpanNames.h`
+- `src/xrpld/rpc/detail/ServerHandler.cpp`
+- `src/xrpld/rpc/detail/RPCHandler.cpp`
+- `src/xrpld/rpc/detail/PathRequest.cpp`
+
+---
+
+## Summary
+
+| Task | Description                                 | Status              | Notes                                                     |
+| ---- | ------------------------------------------- | ------------------- | --------------------------------------------------------- |
+| 2.1  | W3C Trace Context header extraction         | Deferred → Phase 3  | No consumer in Phase 2; needs cross-node tracing          |
+| 2.2  | Per-category span creation                  | Complete (Phase 1c) | Superseded by TraceCategory enum + SpanGuard              |
+| 2.3  | Add shouldTraceLedger() interface method    | Complete (Phase 1c) | Delivered in Phase 1c base branch                         |
+| 2.4  | Unit tests for core telemetry               | Complete            | TelemetryConfig + SpanGuardFactory tests                  |
+| 2.5  | Enhanced RPC span attributes (HTTP-level)   | Deferred            | Low value; span duration covers timing natively           |
+| 2.6  | Build verification and performance baseline | Complete            | Verified in CI on Phase 1c                                |
+| 2.7  | Grafana Tempo search filters                | Complete            | rpc-command, rpc-status, rpc-role filters                 |
+| 2.8  | RPC span attribute enrichment (node health) | Dropped             | Available via `server_info`/`server_state` RPC            |
+| 2.9  | PathFind RPC instrumentation                | Complete            | request, compute, update_all, discover                    |
+| 2.10 | RPC/PathFind span attribute gap fill        | Complete            | Batch detection, payload size, load cost, pathfind params |
+
+**Delivered in this branch**: Tasks 2.4, 2.7, 2.9, 2.10.
+**Deferred with rationale**: Tasks 2.1 (→Phase 3), 2.5 (low priority).
+**Dropped**: Task 2.8 (node health not duplicated on traces).
+**Superseded**: Task 2.2 (Phase 1c SpanGuard factory covers this).

OpenTelemetryPlan/Phase3_taskList.md

@@ -0,0 +1,547 @@
+# Phase 3: Transaction Tracing Task List
+
+> **Goal**: Trace the full transaction lifecycle from RPC submission through peer relay, including cross-node context propagation via Protocol Buffer extensions. This is the WALK phase that demonstrates true distributed tracing.
+>
+> **Scope**: Protocol Buffer `TraceContext` message, context serialization, PeerImp transaction instrumentation, NetworkOPs processing instrumentation, HashRouter visibility, and multi-node relay context propagation.
+>
+> **Branch**: `pratik/otel-phase3-tx-tracing` (from `pratik/otel-phase2-rpc-tracing`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                                                        |
+| ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
+| [04-code-samples.md](./04-code-samples.md)                   | TraceContext protobuf (§4.4.1), PeerImp instrumentation (§4.5.1), context serialization (§4.4.2) |
+| [01-architecture-analysis.md](./01-architecture-analysis.md) | Transaction flow (§1.3), key trace points (§1.6)                                                 |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 3 tasks (§6.4), definition of done (§6.11.3)                                               |
+| [02-design-decisions.md](./02-design-decisions.md)           | Context propagation design (§2.5), attribute schema (§2.4.3)                                     |
+
+---
+
+## Task 3.1: Define TraceContext Protocol Buffer Message
+
+**Objective**: Add trace context fields to the P2P protocol messages so trace IDs can propagate across nodes.
+
+**What to do**:
+
+- Edit `include/xrpl/proto/xrpl.proto` (or `src/xrpld/proto/ripple.proto`, wherever the proto is):
+  - Add `TraceContext` message definition:
+    ```protobuf
+    message TraceContext {
+        bytes trace_id = 1;      // 16-byte trace identifier
+        bytes span_id = 2;       // 8-byte span identifier
+        uint32 trace_flags = 3;  // bit 0 = sampled
+        string trace_state = 4;  // W3C tracestate value
+    }
+    ```
+  - Add `optional TraceContext trace_context = 1001;` to:
+    - `TMTransaction`
+    - `TMProposeSet` (for Phase 4 use)
+    - `TMValidation` (for Phase 4 use)
+  - Use high field numbers (1001+) to avoid conflicts with existing fields
+
+- Regenerate protobuf C++ code
+
+**Key modified files**:
+
+- `include/xrpl/proto/xrpl.proto` (or equivalent)
+
+**Reference**:
+
+- [04-code-samples.md §4.4.1](./04-code-samples.md) — TraceContext message definition
+- [02-design-decisions.md §2.5.2](./02-design-decisions.md) — Protocol buffer context propagation design
+
+---
+
+## Task 3.2: Implement Protobuf Context Serialization
+
+**Objective**: Create utilities to serialize/deserialize OTel trace context to/from protobuf `TraceContext` messages.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/TraceContextPropagator.h` (extend from Phase 2 if exists, or add protobuf methods):
+  - Add protobuf-specific methods:
+    - `static Context extractFromProtobuf(protocol::TraceContext const& proto)` — reconstruct OTel context from protobuf fields
+    - `static void injectToProtobuf(Context const& ctx, protocol::TraceContext& proto)` — serialize current span context into protobuf fields
+  - Both methods guard behind `#ifdef XRPL_ENABLE_TELEMETRY`
+
+- Create/extend `src/libxrpl/telemetry/TraceContextPropagator.cpp`:
+  - Implement extraction: read trace_id (16 bytes), span_id (8 bytes), trace_flags from protobuf, construct `SpanContext`, wrap in `Context`
+  - Implement injection: get current span from context, serialize its TraceId, SpanId, and TraceFlags into protobuf fields
+
+**Key new/modified files**:
+
+- `include/xrpl/telemetry/TraceContextPropagator.h`
+- `src/libxrpl/telemetry/TraceContextPropagator.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.4.2](./04-code-samples.md) — Full extract/inject implementation
+
+---
+
+## Task 3.3: Instrument PeerImp Transaction Handling
+
+**Objective**: Add trace spans to the peer-level transaction receive and relay path.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - In `onMessage(TMTransaction)` / `handleTransaction()`:
+    - Extract parent trace context from incoming `TMTransaction::trace_context` field (if present)
+    - Create `tx.receive` span as child of extracted context (or new root if none)
+    - Set attributes: `tx_hash`, `peer_id`, `tx_status`
+    - Create the span only after `HashRouter::shouldProcess()` accepts, so a dropped duplicate produces no span
+    - Wrap validation call with child span `tx.validate`
+    - Wrap relay with `tx.relay` span
+  - When relaying to peers:
+    - Inject current trace context into outgoing `TMTransaction::trace_context`
+    - Set `relay_count` attribute
+
+- Use `SpanGuard::span(TraceCategory::Transactions, "tx", "receive")` factory
+  (Phase 1c replaced macros with the SpanGuard factory pattern)
+
+> **Note**: The `tx.receive` guard is `.detached()` before being moved into the
+> `RcvCheckTx` job so its Scope is popped on the peer thread, not leaked to the
+> worker (else later peer messages would inherit this transaction's trace).
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Full PeerImp instrumentation example
+- [01-architecture-analysis.md §1.3](./01-architecture-analysis.md) — Transaction flow diagram
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.receive trace point
+
+---
+
+## Task 3.4: Instrument NetworkOPs Transaction Processing
+
+**Objective**: Trace the transaction processing pipeline in NetworkOPs, covering both sync and async paths.
+
+**What to do**:
+
+- Edit `src/xrpld/app/misc/NetworkOPs.cpp`:
+  - In `processTransaction()`:
+    - Create `tx.process` span
+    - Set attributes: `tx_hash`, `tx_type`, `local` (whether from RPC or peer)
+    - Record whether sync or async path is taken
+    - `.detached()` the guard before storing it in `TransactionStatus::span`,
+      since it is applied on a batch worker thread — this pops the Scope on the
+      origin thread and stops later work inheriting this transaction's trace
+
+  - In `doTransactionAsync()`:
+    - Capture parent context before queuing
+    - Create `tx.queue` span with queue depth attribute
+    - Add event when transaction is dequeued for processing
+
+  - In `doTransactionSync()`:
+    - Create `tx.process_sync` span
+    - Record result (applied, queued, rejected)
+
+**Key modified files**:
+
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+**Reference**:
+
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.validate and tx.process trace points
+- [02-design-decisions.md §2.4.3](./02-design-decisions.md) — Transaction attribute schema
+
+---
+
+## Task 3.5: Instrument HashRouter for Dedup Visibility
+
+**Objective**: Make transaction deduplication visible in traces by recording HashRouter decisions as span attributes/events.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp` (in handleTransaction):
+  - After calling `HashRouter::shouldProcess()` or `addSuppressionPeer()`:
+    - Start the span here, not before, so only transactions this node will process are traced
+    - Record `tx_flags` showing current HashRouter state (SAVED, TRUSTED, etc.)
+    - Add `tx.first_seen` or `tx.duplicate` event
+
+- This is NOT a modification to HashRouter itself — just recording its decisions as span attributes in the existing PeerImp instrumentation from Task 3.3.
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp` (same changes as 3.3, logically grouped)
+
+---
+
+## Task 3.6: Context Propagation in Transaction Relay
+
+**Status**: COMPLETE (transaction relay). Consensus proposal/validation
+propagation is deferred to Phase 4 — see "Planned (Phase 4)" below.
+
+**Objective**: Ensure trace context flows correctly when transactions are relayed between peers, creating linked spans across nodes.
+
+**What was done**:
+
+- **TX send side**: `NetworkOPs::apply()` now injects the tx.process span's trace
+  context into the outgoing `TMTransaction` protobuf before relay, using
+  `telemetry::injectSpanContext()`. The receiving node's `txReceiveSpan()` (already
+  wired in PeerImp) extracts the parent span_id and creates the tx.receive span
+  as a child of the sender's tx.process span.
+
+- **Edge cases**: Missing trace context (older peers) degrades gracefully to
+  standalone spans. Invalid/corrupted context is treated as absent. Trace
+  flags are propagated and respected.
+
+**New infrastructure**:
+
+- `SpanGuard::getTraceBytes()` — extracts raw trace_id/span_id/trace_flags
+  from a span without exposing OTel types. Safe to call from any thread.
+- `PropagationHelpers.h` — `injectSpanContext(SpanGuard&, proto)` bridge
+  between SpanGuard and protobuf TraceContext.
+- `TraceContextPropagator.h` — `injectToProtobuf(ctx, proto)` for
+  same-thread injection via OTel RuntimeContext.
+
+**Key modified files**:
+
+- `src/xrpld/app/misc/NetworkOPs.cpp` — tx relay injection
+- `include/xrpl/telemetry/SpanGuard.h` — `TraceBytes` struct, `getTraceBytes()`
+- `src/libxrpl/telemetry/SpanGuard.cpp` — `getTraceBytes()` implementation
+- `src/xrpld/telemetry/PropagationHelpers.h` — inject helpers (new file)
+
+**Planned (Phase 4 — not in this PR)**:
+
+The consensus proposal/validation propagation below is Phase 4 scope and is
+not implemented on this branch. It is listed here only to record the intended
+design.
+
+- **Proposal send/receive**: `RCLConsensus::Adaptor::propose()` injects the
+  current thread's active span context into the `TMProposeSet` protobuf via
+  `telemetry::injectToProtobuf()`. PeerImp creates a
+  `consensus.proposal.receive` span that extracts the sender's trace context
+  as parent (via `ConsensusReceiveTracing.h`).
+
+- **Validation send/receive**: `RCLConsensus::Adaptor::validate()` injects
+  the current thread's active span context into the `TMValidation` protobuf.
+  PeerImp creates a `consensus.validation.receive` span that extracts the
+  sender's trace context as parent.
+
+- Planned files: `src/xrpld/app/consensus/RCLConsensus.cpp` (send injection),
+  `src/xrpld/overlay/detail/PeerImp.cpp` (receive spans),
+  `src/xrpld/telemetry/ConsensusReceiveTracing.h` (receive span helpers,
+  new file).
+
+**Reference**:
+
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — Context propagation design
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Relay context injection pattern
+
+---
+
+## Task 3.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 3 changes compile and work correctly.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions
+3. Run existing unit tests
+4. Verify protobuf regeneration produces correct C++ code
+5. Document any issues encountered
+
+**Verification Checklist**:
+
+- [ ] Protobuf changes generate valid C++
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass
+- [ ] No undefined symbols from new telemetry calls
+
+---
+
+## Task 3.8: Transaction Span Peer Version Attribute
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md) — adds peer version context inspired by the community [xrpl-validator-dashboard](https://github.com/realgrapedrop/xrpl-validator-dashboard).
+>
+> **Upstream**: Phase 2 (RPC span infrastructure must exist).
+> **Downstream**: Phase 10 (validation checks for this attribute).
+
+**Objective**: Add the relaying peer's xrpld version to `tx.receive` spans so operators can correlate transaction issues with peer version mismatches during network upgrades.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - In the `tx.receive` span block (after existing `peer_id` setAttribute call):
+    - Add `peer_version` (string) — from `this->getVersion()`
+    - Only set if `getVersion()` returns a non-empty string (avoid empty-string attributes)
+
+**New span attribute**:
+
+| Attribute      | Type   | Source               | Example         |
+| -------------- | ------ | -------------------- | --------------- |
+| `peer_version` | string | `peer->getVersion()` | `"xrpld-2.4.0"` |
+
+**Rationale**: Transaction relay is where version mismatches cause subtle serialization or validation bugs. Tracing "this tx came from a v2.3.0 peer" helps diagnose compatibility issues. The community dashboard tracks peer versions externally; this brings version awareness into the trace itself.
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Exit Criteria**:
+
+- [ ] `tx.receive` spans carry `peer_version` attribute with a non-empty version string
+- [ ] Attribute is omitted (not set to empty string) when `getVersion()` returns empty
+- [ ] Attribute visible in Jaeger span detail view
+
+---
+
+## Task 3.9: Deterministic Transaction Trace ID
+
+> **Upstream**: Task 3.2 (protobuf serialization), Task 3.3 (PeerImp span exists).
+> **Downstream**: Phase 10 (workload validation can query by tx hash directly).
+> **Pattern**: Mirrors the consensus deterministic trace ID in Phase 4a
+> (`createDeterministicContext` in `RCLConsensus.cpp`), adapted for transactions.
+
+**Objective**: Derive the trace_id for transaction spans deterministically from the
+transaction hash so that all nodes handling the same transaction independently produce
+spans under the same trace_id — regardless of whether protobuf context propagation
+succeeds.
+
+**Why**: The current approach creates spans with random trace_ids and relies entirely
+on protobuf `TraceContext` propagation to link them. If any hop in the relay chain
+drops the context (older peers, message corruption, mixed-version networks), the trace
+splits and downstream spans become impossible to find. With deterministic trace_ids,
+correlation is guaranteed because every node derives the same trace_id from the same
+`txID`.
+
+**Approach — deterministic trace_id + protobuf span_id propagation**:
+
+1. Derive `trace_id = txHash[0:16]` (first 16 bytes of the 32-byte transaction hash).
+2. Generate a random 8-byte `span_id` per node (each node's span is unique within
+   the shared trace).
+3. Create the span under this deterministic context as parent.
+4. **Additionally**, if protobuf `TraceContext` is present in the incoming
+   `TMTransaction` message, extract the sender's `span_id` and use it as the span's
+   parent — this preserves parent-child ordering in the trace tree.
+5. If protobuf context is absent (older peer, first hop), the span still has the
+   correct deterministic `trace_id` — it appears as a sibling root in the same trace
+   rather than being lost.
+
+This gives the best of both worlds: guaranteed cross-node correlation via deterministic
+`trace_id`, plus parent-child relay ordering via protobuf `span_id` when available.
+
+**What to do**:
+
+- Create `createDeterministicTxContext(uint256 const& txHash)` utility function:
+  - Location: shared header or file-local in `PeerImp.cpp` and `NetworkOPs.cpp`
+    (or a shared telemetry utility if both need it).
+  - Pattern: identical to `createDeterministicContext(uint256 const& ledgerId)` in
+    `RCLConsensus.cpp` — take `txHash[0:16]` as trace_id, random span_id via
+    `default_prng()`, sampled flag set, `remote=false`.
+  - Guard behind `#ifdef XRPL_ENABLE_TELEMETRY`.
+
+  ```cpp
+  opentelemetry::context::Context
+  createDeterministicTxContext(uint256 const& txHash)
+  {
+      namespace trace = opentelemetry::trace;
+
+      // First 16 bytes of the 32-byte tx hash as trace ID.
+      trace::TraceId traceId(
+          opentelemetry::nostd::span<uint8_t const, 16>(txHash.data(), 16));
+
+      // Random span_id so each node's span is unique within the trace.
+      uint8_t spanIdBytes[8];
+      auto const rval = default_prng()();
+      std::memcpy(spanIdBytes, &rval, sizeof(spanIdBytes));
+      trace::SpanId spanId(
+          opentelemetry::nostd::span<uint8_t const, 8>(spanIdBytes, 8));
+
+      trace::SpanContext syntheticCtx(
+          traceId, spanId, trace::TraceFlags(1), /* remote = */ false);
+
+      return opentelemetry::context::Context{}.SetValue(
+          trace::kSpanKey,
+          opentelemetry::nostd::shared_ptr<trace::Span>(
+              new trace::DefaultSpan(syntheticCtx)));
+  }
+  ```
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp` — restructure `handleTransaction()`:
+  - **Move span creation after deserialization** (txID must be known first):
+    1. Deserialize `STTx` and get `txID` (existing code at line ~1382).
+    2. Create deterministic parent context: `auto detCtx = createDeterministicTxContext(txID)`.
+    3. If `m->has_trace_context()`: extract protobuf context via `extractFromProtobuf()`,
+       **combine** with deterministic trace_id — use the protobuf span_id as parent
+       to preserve relay ordering, but override trace_id with the deterministic one.
+    4. If no protobuf context: create span under `detCtx` directly.
+    5. Set all existing attributes (`hash`, `peerId`, `peerVersion`, etc.).
+
+  - **Combining deterministic trace_id with protobuf parent span_id**:
+    When both are available, construct a synthetic `SpanContext` with:
+    - `trace_id` = `txHash[0:16]` (deterministic)
+    - `span_id` = extracted from protobuf (sender's span_id → becomes parent)
+    - `trace_flags` = from protobuf
+    - `remote` = true (came from another node)
+
+    ```cpp
+    // Pseudo-code for the combined context:
+    auto detTraceId = trace::TraceId(txHash.data(), 16);
+    auto remoteSpanId = /* from extractFromProtobuf */;
+    auto remoteFlags = /* from extractFromProtobuf */;
+
+    trace::SpanContext combinedCtx(
+        detTraceId, remoteSpanId, remoteFlags, /* remote = */ true);
+    // Use as parent context for the new span.
+    ```
+
+- Edit `src/xrpld/app/misc/NetworkOPs.cpp` — update `processTransaction()`:
+  - `transaction->getID()` is already available at the top of the function.
+  - Create deterministic parent context from `txID`.
+  - Create `tx.process` span under this context.
+  - No protobuf context to extract here (NetworkOPs is intra-node), so
+    deterministic context alone is sufficient.
+
+- Add `trace_strategy` attribute to spans:
+  - Add `inline constexpr auto traceStrategy = "trace_strategy";`
+    to `TxSpanNames.h`.
+  - Set on each tx span: `span.setAttribute(tx_span::attr::traceStrategy, "deterministic")`.
+
+**Key new/modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp` — restructured span creation
+- `src/xrpld/app/misc/NetworkOPs.cpp` — deterministic context for tx.process
+- `src/xrpld/telemetry/TxSpanNames.h` — new `traceStrategy` attribute constant
+- New or shared utility for `createDeterministicTxContext()` (location TBD: could be
+  a shared header like `include/xrpl/telemetry/DeterministicContext.h`, or file-local
+  if only used in two places)
+
+**Interaction with existing tasks**:
+
+- **Task 3.3 (PeerImp instrumentation)**: The span creation in `handleTransaction()`
+  must be restructured — the span currently starts before `txID` is known. This task
+  moves it after deserialization.
+- **Task 3.6 (Relay context propagation)**: Protobuf injection at the relay site
+  remains the same — `injectToProtobuf()` serializes the current span's `span_id`.
+  The receiver extracts it and combines with the deterministic `trace_id`.
+- **Phase 4a (Consensus deterministic trace ID)**: This task follows the same pattern.
+  Consider extracting a shared utility (e.g., `createDeterministicContext(uint256)`)
+  that both consensus and transaction tracing use.
+
+**Exit Criteria**:
+
+- [ ] `tx.receive` and `tx.process` spans have deterministic trace_id = `txHash[0:16]`
+- [ ] All nodes handling the same transaction produce spans under the same trace_id
+- [x] Protobuf `span_id` propagation still works when available (parent-child ordering)
+- [ ] Missing protobuf context (old peer) degrades gracefully to sibling spans, not lost traces
+- [ ] `trace_strategy` attribute set to `"deterministic"` on all tx spans
+- [ ] Trace queryable by tx hash (truncate hash → trace_id → direct lookup in Tempo)
+
+**Deliverables implemented (not in original plan)**:
+
+- **`SpanGuard::txSpan()` factory method** (`include/xrpl/telemetry/SpanGuard.h`):
+  Two overloads for creating transaction spans with deterministic trace IDs:
+  - `txSpan(category, group, name, txHash)` — standalone span (deterministic
+    trace_id from `txHash[0:16]`, no parent span_id).
+  - `txSpan(category, group, name, txHash, parentCtx)` — child span (deterministic
+    trace_id combined with protobuf-extracted parent span_id for relay ordering).
+
+- **`TxTracing.h` helper functions** (`src/xrpld/telemetry/TxTracing.h`):
+  File-local helpers that wrap `SpanGuard::txSpan()` for the two main PeerImp call
+  sites:
+  - `txReceiveSpan(txHash, parentCtx)` — creates `tx.receive` span with
+    deterministic trace_id and optional protobuf parent context.
+  - `txProcessSpan(txHash)` — creates `tx.process` span with deterministic
+    trace_id only (no protobuf parent, used intra-node).
+  - **Note**: `TxTracing.h` includes `xrpl.pb.h` unconditionally (outside
+    `#ifdef XRPL_ENABLE_TELEMETRY`) because `protocol::TMTransaction` appears in
+    the function signatures regardless of telemetry build mode.
+
+---
+
+## Task 3.10: TxQ Instrumentation
+
+**Status**: COMPLETE
+
+**Objective**: Trace the transaction queue lifecycle — enqueue decisions, direct apply, batch clear, ledger-close accept loop, per-tx apply, and cleanup.
+
+**Spans added**:
+
+- `txq.enqueue` — wraps `TxQ::apply()` with tx_hash attribute
+- `txq.apply_direct` — wraps `TxQ::tryDirectApply()` fast-path
+- `txq.batch_clear` — wraps `TxQ::tryClearAccountQueueUpThruTx()`
+- `txq.accept` — wraps `TxQ::accept()` ledger-close dequeue with queue_size attr
+- `txq.accept_tx` — per-tx span inside accept loop with tx_hash, ter_code,
+  retries_remaining attributes
+- `txq.cleanup` — wraps `TxQ::processClosedLedger()` with ledger_seq attribute
+
+**New file**: `src/xrpld/app/misc/detail/TxQSpanNames.h`
+
+**Modified file**: `src/xrpld/app/misc/detail/TxQ.cpp`
+
+---
+
+## Task 3.11: TX and TxQ Span Attribute Gap Fill
+
+**Status**: COMPLETE
+
+**Objective**: Add workflow-identifying attributes to transaction spans so operators can filter by transaction type and see outcomes without off-chain correlation.
+
+**Attributes added**:
+
+| Span              | Attribute            | Type   | Source                                                                                                                     |
+| ----------------- | -------------------- | ------ | -------------------------------------------------------------------------------------------------------------------------- |
+| `tx.process`      | `tx_type`            | string | `TxFormats::getInstance().findByType(stx->getTxnType())->getName()`                                                        |
+| `tx.process`      | `fee`                | int64  | `stx->getFieldAmount(sfFee).xrp().drops()`                                                                                 |
+| `tx.process`      | `sequence`           | int64  | `stx->getSeqProxy().value()`                                                                                               |
+| `tx.process`      | `tx_<account field>` | string | one per top-level `STI_ACCOUNT` field, raw r-address (`tx_account`, `tx_destination`, ...); keys in `TxAccountSpanNames.h` |
+| `tx.process`      | `ter_result`         | string | `transToken(e.result)` (set after batch application)                                                                       |
+| `tx.process`      | `applied`            | bool   | `e.applied` (set after batch application)                                                                                  |
+| `tx.receive`      | `tx_type`            | string | `TxFormats::getInstance().findByType(stx->getTxnType())->getName()`                                                        |
+| `txq.enqueue`     | `tx_type`            | string | same pattern as above                                                                                                      |
+| `txq.enqueue`     | `txq_status`         | string | `queued` / `applied_direct` / `applied` / `failed` / `rejected`                                                            |
+| `txq.enqueue`     | `ter_code`           | string | `transToken(directApplied->ter)` (set on the direct-apply path)                                                            |
+| `txq.enqueue`     | `fee_level_paid`     | int64  | `getFeeLevelPaid(view, *tx).value()`                                                                                       |
+| `txq.enqueue`     | `required_fee_level` | int64  | `getRequiredFeeLevel(...).value()`                                                                                         |
+| `txq.batch_clear` | `num_cleared`        | int64  | queued txs cleared ahead of the applying tx                                                                                |
+| `txq.cleanup`     | `expired_count`      | int64  | entries dropped for passed `LastLedgerSequence`                                                                            |
+| `txq.accept_tx`   | `txq_status`         | string | `applied` / `failed` / `retried`                                                                                           |
+| `txq.accept_tx`   | `ter_code`           | string | `transToken(txnResult)` (set before branching on the outcome)                                                              |
+| `txq.accept`      | `ledger_changed`     | bool   | set at end of accept loop                                                                                                  |
+
+**New attr keys**: `TxSpanNames.h` (`txType`, `fee`, `sequence`, `terResult`, `applied`), `TxQSpanNames.h` (`txType`).
+
+**Modified files**:
+
+- `src/xrpld/telemetry/TxSpanNames.h`
+- `src/xrpld/app/misc/detail/TxQSpanNames.h`
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+- `src/xrpld/app/misc/detail/TxQ.cpp`
+
+---
+
+## Summary
+
+| Task | Description                         | New Files | Modified Files | Depends On |
+| ---- | ----------------------------------- | --------- | -------------- | ---------- |
+| 3.1  | TraceContext protobuf message       | 0         | 1              | Phase 2    |
+| 3.2  | Protobuf context serialization      | 1-2       | 0              | 3.1        |
+| 3.3  | PeerImp transaction instrumentation | 0         | 1              | 3.2        |
+| 3.4  | NetworkOPs transaction processing   | 0         | 1              | Phase 2    |
+| 3.5  | HashRouter dedup visibility         | 0         | 1              | 3.3        |
+| 3.6  | Relay context propagation           | 0         | 1-2            | 3.3, 3.5   |
+| 3.7  | Build verification and testing      | 0         | 0              | 3.1-3.6    |
+| 3.8  | TX span peer version attribute      | 0         | 1              | 3.3        |
+| 3.9  | Deterministic transaction trace ID  | 0-1       | 3              | 3.2, 3.3   |
+| 3.10 | TxQ instrumentation (6 spans)       | 1         | 1              | 3.4        |
+| 3.11 | TX/TxQ span attribute gap fill      | 0         | 5              | 3.3, 3.10  |
+
+**Parallel work**: Tasks 3.1 and 3.4 can start in parallel. Task 3.2 depends on 3.1. Tasks 3.3 and 3.5 depend on 3.2. Task 3.6 depends on 3.3 and 3.5. Task 3.8 depends on 3.3 (span must exist). Task 3.9 depends on 3.2 and 3.3. Task 3.10 depends on 3.4 (tx.process span must exist).
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.3](./06-implementation-phases.md)):
+
+- [x] Transaction traces span across nodes
+- [x] Trace context in Protocol Buffer messages
+- [ ] HashRouter deduplication visible in traces
+- [ ] <5% overhead on transaction throughput
+- [x] Deterministic trace_id: same trace_id for same tx across all nodes
+- [x] Protobuf span_id propagation preserves parent-child ordering when available

OpenTelemetryPlan/Phase4_taskList.md

@@ -0,0 +1,949 @@
+# Phase 4: Consensus Tracing Task List
+
+> **Goal**: Full observability into consensus rounds — track round lifecycle, phase transitions, proposal handling, and validation. This is the RUN phase that completes the distributed tracing story.
+>
+> **Scope**: RCLConsensus instrumentation for round starts, phase transitions (open/establish/accept), proposal send/receive, validation handling, and correlation with transaction traces from Phase 3.
+>
+> **Branch**: `pratik/otel-phase4-consensus-tracing` (from `pratik/otel-phase3-tx-tracing`)
+
+> **Note on attribute names**: the `xrpl.<domain>.<field>` keys shown below are
+> written in the older dotted form for readability — it mirrors how the fully
+> qualified attribute reads in a Tempo trace view. The implemented keys follow
+> the convention in [CONTRIBUTING.md](../CONTRIBUTING.md#telemetry-span-attribute-naming)
+> (underscore form, e.g. `consensus_round`, `consensus_mode`); the
+> `*SpanNames.h` constants are the single source of truth.
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                   |
+| ------------------------------------------------------------ | ----------------------------------------------------------- |
+| [04-code-samples.md](./04-code-samples.md)                   | Consensus instrumentation (§4.5.2), consensus span patterns |
+| [01-architecture-analysis.md](./01-architecture-analysis.md) | Consensus round flow (§1.4), key trace points (§1.6)        |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 4 tasks (§6.5), definition of done (§6.11.4)          |
+| [02-design-decisions.md](./02-design-decisions.md)           | Consensus attribute schema (§2.4.4)                         |
+
+---
+
+## Task 4.1: Instrument Consensus Round Start ✅
+
+**Objective**: Create a root span for each consensus round that captures the round's key parameters.
+
+**Status**: DONE (implemented via Task 4a.2 `startRoundTracing()` helper).
+
+**What was done**:
+
+- `RCLConsensus::Adaptor::startRoundTracing()` creates `consensus.round` span
+  via `SpanGuard::hashSpan()` (deterministic) or `SpanGuard::span()` (attribute strategy)
+- Attributes set: `xrpl.consensus.ledger_id`, `xrpl.ledger.seq`,
+  `xrpl.consensus.mode`, `trace_strategy`, `xrpl.consensus.round_id`
+- Round span stored as `roundSpan_` member in `RCLConsensus::Adaptor`
+- `roundSpanContext_` snapshot captured for cross-thread span linking
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/consensus/RCLConsensus.h` (span and context members)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — startRound instrumentation example
+- [01-architecture-analysis.md §1.4](./01-architecture-analysis.md) — Consensus round flow
+
+---
+
+## Task 4.2: Instrument Phase Transitions ✅
+
+**Objective**: Create child spans for each consensus phase (open, establish, accept) to show timing breakdown.
+
+**Status**: DONE. All consensus phases are now instrumented:
+
+- `consensus.establish` — created in `Consensus.h::startEstablishTracing()`
+- `consensus.ledger_close` — created in `RCLConsensus.cpp::onClose()`
+- `consensus.accept` / `consensus.accept.apply` — created in `onAccept()` / `doAccept()`
+- `consensus.phase.open` — `openSpan_` member in `Consensus.h`, created in `startRoundInternal()`, ended in `closeLedger()`
+
+**Design notes**:
+
+- `phase` attribute — phases are distinguished by span names instead
+- `phase.enter` / `phase.exit` events — not added (span start/end serves this purpose)
+- `phase_duration_ms` attribute — not set (span duration captures this)
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/consensus/Consensus.h` (template-level establish phase tracking)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — phaseTransition instrumentation
+
+---
+
+## Task 4.3: Instrument Proposal Handling ✅
+
+**Objective**: Trace proposal send and receive to show validator coordination.
+
+**Status**: DONE. Both send and receive paths are instrumented.
+
+**What was done**:
+
+- In `Adaptor::propose()`:
+  - Creates `consensus.proposal.send` span via `SpanGuard::span()`
+  - Sets `xrpl.consensus.round` attribute
+
+- In `PeerImp::onMessage(TMProposeSet)`:
+  - Creates `consensus.proposal.receive` span
+  - Sets `trusted` attribute (bool)
+
+**Done here** (cross-node propagation, send + receive):
+
+- Trace context injection for `TMProposeSet::trace_context` in `propose()`
+- Receive-side extraction in `PeerImp::onMessage(TMProposeSet)` via
+  `telemetry::proposalReceiveSpan()` (parents the receive span on the
+  sender's context when a valid `trace_context` is present)
+
+**Not implemented** (deferred to Phase 4b):
+
+- `consensus.proposal.relay` span in `share(RCLCxPeerPos)`
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — peerProposal instrumentation
+- [02-design-decisions.md §2.4.4](./02-design-decisions.md) — Consensus attribute schema
+
+---
+
+## Task 4.4: Instrument Validation Handling ✅
+
+**Objective**: Trace validation send and receive to show ledger validation flow.
+
+**Status**: DONE. Both send and receive paths are instrumented.
+
+**What was done**:
+
+- In `Adaptor::validate()` (called from `doAccept()`):
+  - Creates `consensus.validation.send` span via `Adaptor::createValidationSpan()`
+  - Uses `SpanGuard::linkedSpan()` to create a follows-from link to the round span
+  - Thread-safe: uses `roundSpanContext_` snapshot (captured on consensus thread,
+    read on jtACCEPT thread)
+  - Sets `xrpl.ledger.seq` and `proposing` attributes
+
+- In `PeerImp::onMessage(TMValidation)`:
+  - Creates `consensus.validation.receive` span
+  - Sets `trusted` attribute (bool)
+  - Sets `xrpl.ledger.seq` attribute
+
+**Not implemented** (deferred to Phase 4b — cross-node propagation):
+
+- Validated ledger hash, signing time attributes on send span (see Task 4.8)
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Task 4.5: Add Consensus-Specific Attributes ✅
+
+**Objective**: Enrich consensus spans with detailed attributes for debugging and analysis.
+
+**Status**: DONE. All core attributes are set across various spans, including the previously missing `tx_count` and `disputes_count`.
+
+**Implemented attributes** (across various spans):
+
+- `xrpl.ledger.seq` — on `consensus.round`, `consensus.accept.apply`
+- `xrpl.consensus.round` — on `consensus.proposal.send`
+- `xrpl.consensus.mode` — on `consensus.round`, `consensus.ledger_close`
+- `proposers` — on `consensus.accept`, `consensus.establish`, `consensus.update_positions`
+- `converge_percent` — on `consensus.establish`, `consensus.update_positions`, `consensus.check`
+- `tx_count` — on `consensus.accept.apply` span (in `doAccept()`)
+- `disputes_count` — on `consensus.update_positions` span (in `updateOurPositions()`)
+- `close_reason` — on `consensus.phase.open`, from `whyCloseLedger()` (`anomaly`, `others_closed`, `idle`, `normal`)
+- `close_time_avalanche_state` — on `consensus.establish`, terminal regime (`init`, `mid`, `late`, `stuck`)
+
+**Design notes**:
+
+- `phase` — phases distinguished by span names instead
+- `phase_duration_ms` — span duration captures this
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/consensus/Consensus.h`
+
+---
+
+## Task 4.6: Correlate Transaction and Consensus Traces ✅
+
+**Objective**: Link transaction traces from Phase 3 with consensus traces so you can follow a transaction from submission through consensus into the ledger.
+
+**Status**: DONE. Transaction-consensus correlation implemented via `tx.included` events in `doAccept()`.
+
+**What was done**:
+
+- In `doAccept()` (RCLConsensus.cpp):
+  - Records `tx.included` events on the `consensus.accept.apply` span for each transaction in the accepted set
+  - Each event includes `xrpl.tx.id` attribute with the transaction hash
+  - This links consensus traces to individual transactions
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Task 4.7: Build Verification and Testing ✅
+
+**Objective**: Verify all Phase 4 changes compile and don't affect consensus timing.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions (critical for consensus code)
+3. Run existing consensus-related unit tests
+4. Verify that `SpanGuard` factory methods compile to no-ops when disabled
+5. Check that no consensus-critical code paths are affected by instrumentation overhead
+
+**Verification Checklist**:
+
+- [x] Build succeeds with telemetry ON
+- [x] Build succeeds with telemetry OFF
+- [x] Existing consensus tests pass
+- [x] `SpanGuard` no-op implementation prevents overhead when telemetry is OFF
+- [x] Phase timing instrumentation doesn't use blocking operations
+
+---
+
+## Task 4.8: Consensus Validation Span Enrichment — NOT DONE
+
+> **Source**: [External Dashboard Parity](../docs/superpowers/specs/2026-03-30-external-dashboard-parity-design.md) — adds validation agreement context inspired by the community [xrpl-validator-dashboard](https://github.com/realgrapedrop/xrpl-validator-dashboard).
+>
+> **Upstream**: Phase 4 tasks 4.1-4.4 (span creation must exist).
+> **Downstream**: Phase 7 (ValidationTracker reads these attributes), Phase 10 (validation checks).
+
+**Objective**: Add ledger hash, validation type, and quorum data to consensus validation spans on both send and receive paths. This enables trace-level validation agreement analysis — filter by ledger hash to see which validators agreed for a given ledger.
+
+**Status**: Not implemented. None of the enrichment attributes are set. The `consensus.validation.send` span only has `ledger.seq` and `proposing`. The `consensus.accept` span has `quorum` set to `result.proposers` (not the actual validator quorum from `app_.validators().quorum()`). No `PeerImp.cpp` changes were made.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - On the `consensus.validation.send` span (in `validate()` / `doAccept()`):
+    - Add `xrpl.validation.ledger_hash` (string) — the ledger hash being validated
+    - Add `xrpl.validation.full` (bool) — whether this is a full validation (not partial)
+  - On the `consensus.accept` span (in `onAccept()`):
+    - Add `validation_quorum` (int64) — from `app_.validators().quorum()`
+    - Add `proposers_validated` (int64) — from `result.proposers`
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - On the `peer.validation.receive` span:
+    - Add `xrpl.peer.validation.ledger_hash` (string) — from deserialized `STValidation` object
+    - Add `xrpl.peer.validation.full` (bool) — from `STValidation` flags
+
+**New span attributes**:
+
+| Span                        | Attribute                          | Type   | Source                            |
+| --------------------------- | ---------------------------------- | ------ | --------------------------------- |
+| `consensus.validation.send` | `xrpl.validation.ledger_hash`      | string | Ledger hash from validate() args  |
+| `consensus.validation.send` | `xrpl.validation.full`             | bool   | Full vs partial validation        |
+| `peer.validation.receive`   | `xrpl.peer.validation.ledger_hash` | string | From STValidation deserialization |
+| `peer.validation.receive`   | `xrpl.peer.validation.full`        | bool   | From STValidation flags           |
+| `consensus.accept`          | `validation_quorum`                | int64  | `app_.validators().quorum()`      |
+| `consensus.accept`          | `proposers_validated`              | int64  | `result.proposers`                |
+
+**Rationale**: The external dashboard's most valuable feature is validation agreement tracking. By recording the ledger hash on both outgoing and incoming validation spans, we create the raw data for agreement analysis at the trace level. Example Tempo query:
+
+```
+{name="consensus.validation.send"} | xrpl.validation.ledger_hash = "A1B2C3..."
+```
+
+Phase 7's `ValidationTracker` builds metric-level aggregation (1h/24h agreement %) on top of this data.
+
+**Key modified files (not yet modified)**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Exit Criteria**:
+
+- [x] `consensus.validation.send` spans carry `ledger_hash` and `full_validation`
+- [ ] `peer.validation.receive` spans carry `xrpl.peer.validation.ledger_hash` and `xrpl.peer.validation.full`
+- [ ] `consensus.accept` spans carry `validation_quorum` and `proposers_validated`
+- [x] Ledger hash attributes match between send and receive for the same ledger
+- [ ] No impact on consensus performance
+
+---
+
+## Task 4.9: Consensus Span Attribute Gap Fill
+
+**Status**: COMPLETE
+
+**Objective**: Add workflow-critical attributes to consensus spans that enable operators to understand consensus outcomes, identify bow-out proposals, and correlate validations to specific ledgers.
+
+**Attributes added**:
+
+| Span                        | Attribute         | Type   | Source                                |
+| --------------------------- | ----------------- | ------ | ------------------------------------- |
+| `consensus.proposal.send`   | `is_bow_out`      | bool   | `proposal.isBowOut()`                 |
+| `consensus.accept`          | `consensus_state` | string | `result.state` (yes/moved_on/expired) |
+| `consensus.accept`          | `disputes_count`  | int64  | `result.disputes.size()`              |
+| `consensus.validation.send` | `ledger_hash`     | string | `ledger.ledger->header().hash`        |
+
+**New attr keys**: `ConsensusSpanNames.h` (`isBowOut`, `ledgerHash`).
+
+**Modified files**:
+
+- `src/xrpld/consensus/ConsensusSpanNames.h`
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Summary
+
+| Task | Description                                 | Status      | New Files | Modified Files | Depends On    |
+| ---- | ------------------------------------------- | ----------- | --------- | -------------- | ------------- |
+| 4.1  | Consensus round start instrumentation       | ✅ Done     | 0         | 2              | Phase 3       |
+| 4.2  | Phase transition instrumentation            | ✅ Done     | 0         | 1-2            | 4.1           |
+| 4.3  | Proposal handling instrumentation           | ✅ Done     | 0         | 2              | 4.1           |
+| 4.4  | Validation handling instrumentation         | ✅ Done     | 0         | 2              | 4.1           |
+| 4.5  | Consensus-specific attributes               | ✅ Done     | 0         | 2              | 4.2, 4.3, 4.4 |
+| 4.6  | Transaction-consensus correlation           | ✅ Done     | 0         | 1              | 4.2, Phase 3  |
+| 4.7  | Build verification and testing              | ✅ Done     | 0         | 0              | 4.1-4.6       |
+| 4.8  | Validation span enrichment (ext. dashboard) | ❌ Not done | 0         | 2              | 4.4           |
+| 4.9  | Consensus span attribute gap fill           | ✅ Done     | 0         | 2              | 4.1-4.5       |
+
+**Parallel work**: Tasks 4.2, 4.3, and 4.4 can run in parallel after 4.1 is complete. Task 4.5 depends on all three. Task 4.6 depends on 4.2 and Phase 3. Task 4.8 depends on 4.4 (validation spans must exist).
+
+### Implemented Spans
+
+| Span Name                   | Method                             | Key Attributes                                                                                                                                                                                                                                                     |
+| --------------------------- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `consensus.proposal.send`   | `Adaptor::propose`                 | `xrpl.consensus.round`, `is_bow_out`                                                                                                                                                                                                                               |
+| `consensus.ledger_close`    | `Adaptor::onClose`                 | `xrpl.ledger.seq`, `xrpl.consensus.mode`                                                                                                                                                                                                                           |
+| `consensus.accept`          | `Adaptor::onAccept`                | `proposers`, `round_time_ms`, `quorum`, `disputes_count`, `consensus_state`                                                                                                                                                                                        |
+| `consensus.accept.apply`    | `Adaptor::doAccept`                | `close_time_ripple_epoch_s`, `close_time_correct`, `close_resolution_ms`, `consensus_state`, `proposing`, `round_time_ms`, `xrpl.ledger.seq`, `parent_close_time_ripple_epoch_s`, `close_time_self_ripple_epoch_s`, `close_time_vote_bins`, `resolution_direction` |
+| `consensus.validation.send` | `Adaptor::onAccept` (via validate) | `proposing`, `ledger_hash`, `ledger_seq`, `full_validation`, `validation_sign_time`                                                                                                                                                                                |
+
+#### Close Time Attributes (consensus.accept.apply)
+
+The `consensus.accept.apply` span captures ledger close time agreement details
+driven by `avCT_CONSENSUS_PCT` (75% validator agreement threshold):
+
+- **`close_time_ripple_epoch_s`** — Agreed-upon ledger close time (XRPL epoch seconds). When validators disagree (`consensusCloseTime == epoch`), this is synthetically set to `prevCloseTime + 1s`.
+- **`close_time_correct`** — `true` if validators reached agreement, `false` if they "agreed to disagree" (close time forced to prev+1s).
+- **`close_resolution_ms`** — Rounding granularity for close time (starts at 30s, decreases as ledger interval stabilizes).
+- **`consensus_state`** — `"finished"` (normal) or `"moved_on"` (consensus failed, adopted best available).
+- **`proposing`** — Whether this node was proposing.
+- **`round_time_ms`** — Total consensus round duration.
+- **`parent_close_time_ripple_epoch_s`** — Previous ledger's close time (XRPL epoch seconds). Enables computing close-time deltas across consecutive rounds without correlating separate spans.
+- **`close_time_self_ripple_epoch_s`** — This node's own proposed close time before consensus voting.
+- **`close_time_vote_bins`** — Number of distinct close-time vote bins from peer proposals. Higher values indicate less agreement among validators.
+- **`resolution_direction`** — Whether close-time resolution `"increased"` (coarser), `"decreased"` (finer), or stayed `"unchanged"` relative to the previous ledger.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.4](./06-implementation-phases.md)):
+
+- [x] Complete consensus round traces
+- [x] Phase transitions visible (open, establish, close, accept)
+- [x] Proposals and validations traced — send and receive; relay deferred to Phase 4b
+- [x] Close time agreement tracked (per `avCT_CONSENSUS_PCT`)
+- [x] No impact on consensus timing
+- [x] Transaction-consensus correlation (Task 4.6) — `tx.included` events in doAccept
+- [ ] Validation span enrichment (Task 4.8) — not implemented
+
+---
+
+# Phase 4a: Establish-Phase Gap Fill & Cross-Node Correlation
+
+> **Goal**: Fill tracing gaps in the consensus establish phase (disputes, convergence,
+> threshold escalation, mode changes) and establish cross-node correlation using a
+> deterministic shared trace ID derived from `previousLedger.id()`.
+>
+> **Approach**: Direct instrumentation in `Consensus.h` and `RCLConsensus.cpp`.
+> All spans use `SpanGuard` factory methods (`span()`, `hashSpan()`, `linkedSpan()`)
+> with `TraceCategory::Consensus` gating. Long-lived spans (round, establish) are
+> stored as `std::optional<SpanGuard>` class members. Short-lived scoped spans
+> (update_positions, check) are local variables. No macros are used — all tracing
+> is via direct `SpanGuard` API calls. `SpanGuard` compiles to no-ops when
+> telemetry is disabled.
+>
+> **Branch**: `pratik/otel-phase4-consensus-tracing`
+
+## Design: Switchable Correlation Strategy
+
+Two strategies for cross-node trace correlation, switchable via config:
+
+### Strategy A — Deterministic Trace ID (Default)
+
+Derive `trace_id = SHA256(previousLedger.id())[0:16]` so all nodes in the same
+consensus round share the same trace_id without P2P context propagation.
+
+- **Pros**: All nodes appear in the same trace in Tempo/Jaeger automatically.
+  No collector-side post-processing needed.
+- **Cons**: Overrides OTel's random trace_id generation; requires custom
+  `IdGenerator` or manual span context construction.
+
+### Strategy B — Attribute-Based Correlation
+
+Use normal random trace_id but attach `xrpl.consensus.ledger_id` as an attribute
+on every consensus span. Correlation happens at query time via Tempo/Grafana
+`by attribute` queries.
+
+- **Pros**: Standard OTel trace_id semantics; no SDK customization.
+- **Cons**: Cross-node correlation requires query-time joins, not automatic.
+
+### Config
+
+```ini
+[telemetry]
+# "deterministic" (default) or "attribute"
+consensus_trace_strategy=deterministic
+```
+
+The C++ API to query this at runtime is `Telemetry::getConsensusTraceStrategy()`,
+which returns a `std::string const&` (`"deterministic"` or `"attribute"`).
+
+### Implementation
+
+In `RCLConsensus::Adaptor::startRound()`:
+
+- If `deterministic`:
+  1. Compute `trace_id_bytes = SHA256(prevLedgerID)[0:16]`
+  2. Construct `opentelemetry::trace::TraceId(trace_id_bytes)`
+  3. Create a synthetic `SpanContext` with this trace_id and a random span_id:
+     ```cpp
+     auto traceId = opentelemetry::trace::TraceId(trace_id_bytes);
+     auto spanId  = opentelemetry::trace::SpanId(random_8_bytes);
+     auto syntheticCtx = opentelemetry::trace::SpanContext(
+         traceId, spanId, opentelemetry::trace::TraceFlags(1), false);
+     ```
+  4. Wrap in `opentelemetry::context::Context` via
+     `opentelemetry::trace::SetSpan(context, syntheticSpan)`
+  5. Call `startSpan("consensus.round", parentContext)` so the new span
+     inherits the deterministic trace_id.
+- If `attribute`: start a normal `consensus.round` span, set
+  `xrpl.consensus.ledger_id = previousLedger.id()` as attribute.
+
+Both strategies always set `xrpl.consensus.round_id` (round number) and
+`xrpl.consensus.ledger_id` (previous ledger hash) as attributes.
+
+---
+
+## Design: Span Hierarchy
+
+```
+consensus.round  (root — created in RCLConsensus::startRound, closed at accept)
+│   link → previous round's SpanContext (follows-from)
+│
+├── consensus.establish  (phaseEstablish → acceptance, in Consensus.h)
+│   ├── consensus.update_positions  (each updateOurPositions call)
+│   │   └── consensus.dispute.resolve  (per-tx dispute resolution event)
+│   ├── consensus.check  (each haveConsensus call)
+│   └── consensus.mode_change  (short-lived span in adaptor on mode transition)
+│
+├── consensus.accept  (existing onAccept span — reparented under round)
+│
+└── consensus.validation.send  (existing — reparented, follows-from link to round)
+```
+
+### Span Links (follows-from relationships)
+
+| Link Source                               | Link Target                | Rationale                                                                      |
+| ----------------------------------------- | -------------------------- | ------------------------------------------------------------------------------ |
+| `consensus.round` (N+1)                   | `consensus.round` (N)      | Causal chain: round N+1 exists because round N accepted                        |
+| `consensus.validation.send`               | `consensus.round`          | Validation follows from the round that produced it; may outlive the round span |
+| _(Phase 4b)_ Received proposal processing | Sender's `consensus.round` | Cross-node causal link via P2P context propagation                             |
+
+---
+
+## Task 4a.0: Prerequisites — Extend SpanGuard and Telemetry APIs ✅
+
+**Objective**: Add missing API surface needed by later tasks.
+
+**Status**: Done, but implemented differently than originally planned. The macro-based
+approach (`XRPL_TRACE_CONSENSUS`, `XRPL_TRACE_ADD_EVENT`, `XRPL_TRACE_SET_ATTR`) was
+**not used**. Instead, all consensus tracing uses `SpanGuard` factory methods and
+direct method calls, which is cleaner and avoids macro control-flow issues.
+
+**What was done**:
+
+1. **`SpanGuard::addEvent()` with attributes** — implemented as planned:
+
+   ```cpp
+   using EventAttribute = std::pair<std::string_view, std::string_view>;
+
+   void addEvent(std::string_view name,
+       std::initializer_list<EventAttribute> attrs);
+   ```
+
+   Callers pass plain `string_view` pairs; the implementation converts internally.
+
+   ```cpp
+   // Actual usage in Consensus.h::updateOurPositions():
+   span.addEvent(
+       "dispute.resolve",
+       {{consensus::span::attr::txId, to_string(txId)},
+        {consensus::span::attr::disputeOurVote, dispute.getOurVote() ? "yes" : "no"}});
+   ```
+
+2. **Span link support** — implemented via `SpanGuard::linkedSpan()` static factory
+   instead of a `Telemetry::startSpan()` overload:
+
+   ```cpp
+   static SpanGuard linkedSpan(
+       std::string_view name, SpanContext const& linkTarget);
+   ```
+
+3. **No macros added** — `TracingInstrumentation.h` was not created. The `XRPL_TRACE_CONSENSUS`,
+   `XRPL_TRACE_ADD_EVENT`, and `XRPL_TRACE_SET_ATTR` macros from the original plan were
+   not implemented. All consensus tracing uses direct `SpanGuard` API:
+   - `SpanGuard::span()` — create scoped spans
+   - `SpanGuard::hashSpan()` — create spans with deterministic trace IDs
+   - `SpanGuard::linkedSpan()` — create spans with follows-from links
+   - `span.setAttribute()` — set attributes directly
+   - `span.addEvent()` — add events directly
+
+**Key modified files**:
+
+- `include/xrpl/telemetry/SpanGuard.h` — `addEvent()` overload, `EventAttribute` type alias
+- `src/libxrpl/telemetry/SpanGuard.cpp` — `addEvent()` implementation
+
+---
+
+## Task 4a.1: Adaptor `getTelemetry()` Method — NOT DONE (Not Needed)
+
+**Objective**: Give `Consensus.h` access to the telemetry subsystem without
+coupling the generic template to OTel headers.
+
+**Status**: Not implemented as specified. The `getTelemetry()` adaptor method was
+not needed because `SpanGuard::span()` is a static factory method that internally
+checks telemetry state via the global `Telemetry` singleton. `Consensus.h` creates
+spans by calling `SpanGuard::span(TraceCategory::Consensus, ...)` directly, without
+needing adaptor access. Only `RCLConsensus::Adaptor` uses `app_.getTelemetry()`
+directly (for `getConsensusTraceStrategy()` in `startRoundTracing()`).
+
+**Key insight**: The `XRPL_TRACE_*` macro approach would have required
+`adaptor_.getTelemetry()`. Since macros were not used, this task became unnecessary.
+
+---
+
+## Task 4a.2: Switchable Round Span with Deterministic Trace ID ✅
+
+**Objective**: Create a `consensus.round` root span in `startRound()` that uses
+the switchable correlation strategy. Store span context as a member for child
+spans in `Consensus.h`.
+
+**Status**: Done. Implemented in `Adaptor::startRoundTracing()`.
+
+**What was done**:
+
+- `RCLConsensus::Adaptor::startRoundTracing()` helper:
+  - Reads `consensus_trace_strategy` via `app_.getTelemetry().getConsensusTraceStrategy()`
+  - **Deterministic**: uses `SpanGuard::hashSpan()` with `prevLgr.id()` data
+  - **Attribute**: uses `SpanGuard::span(TraceCategory::Consensus, seg::consensus, "round")`
+  - Sets attributes: `xrpl.consensus.ledger_id`, `xrpl.ledger.seq`, `xrpl.consensus.mode`, `trace_strategy`, `xrpl.consensus.round_id`
+  - Captures `roundSpanContext_` snapshot for cross-thread span linking
+  - Saves `prevRoundContext_` from previous round for follows-from links
+
+- **`SpanGuard::hashSpan()` factory**: encapsulates deterministic trace ID logic:
+
+  ```cpp
+  static SpanGuard hashSpan(
+      TraceCategory cat, std::string_view name,
+      std::uint8_t const* hashData, std::size_t hashSize);
+  ```
+
+  Derives `trace_id = hashData[0:16]` so all nodes in the same round share
+  the same trace_id. Compiles to no-op when telemetry is disabled.
+
+- `consensus_trace_strategy` config parsed in `TelemetryConfig.cpp`,
+  stored in `Telemetry::Setup`, accessible via `Telemetry::getConsensusTraceStrategy()`
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp` — `startRoundTracing()` implementation
+- `src/xrpld/app/consensus/ConsensusSpanNames.h` — **(new)** compile-time span name and attribute key constants
+- `include/xrpl/telemetry/Telemetry.h` — `consensusTraceStrategy` in Setup, `getConsensusTraceStrategy()`
+- `src/libxrpl/telemetry/TelemetryConfig.cpp` — parse new config option
+
+---
+
+## Task 4a.3: Span Members in `Consensus.h` ✅
+
+**Objective**: Add span storage to the `Consensus` class so that spans created
+in `startRound()` (adaptor) are accessible from `phaseEstablish()`,
+`updateOurPositions()`, and `haveConsensus()` (template methods).
+
+**Status**: Done with documented plan deviation.
+
+**What was done**:
+
+- `establishSpan_` added to `Consensus` private members (as planned):
+
+  ```cpp
+  std::optional<xrpl::telemetry::SpanGuard> establishSpan_;
+  ```
+
+- **Plan deviation**: `roundSpan_`, `prevRoundContext_`, and `roundSpanContext_`
+  are stored in `RCLConsensus::Adaptor` (not `Consensus.h`) because the adaptor
+  has access to telemetry config for the deterministic trace ID strategy.
+
+- **No `#ifdef XRPL_ENABLE_TELEMETRY` guards**: Members use `std::optional<SpanGuard>`
+  and `SpanContext` which have no-op implementations when telemetry is disabled,
+  so `#ifdef` guards are unnecessary. The members are always present in the class
+  layout but incur negligible overhead.
+
+- Includes added unconditionally to `Consensus.h`:
+  ```cpp
+  #include <xrpl/telemetry/SpanGuard.h>
+  #include <xrpld/app/consensus/ConsensusSpanNames.h>
+  ```
+  No `TracingInstrumentation.h` include (file doesn't exist; macros not used).
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h`
+- `src/xrpld/app/consensus/RCLConsensus.h` (round span and context members)
+
+---
+
+## Task 4a.4: Instrument `phaseEstablish()` ✅
+
+**Objective**: Create `consensus.establish` span wrapping the establish phase,
+with attributes for convergence progress.
+
+**Status**: Done. Implemented via three private helpers in `Consensus.h`.
+
+**What was done**:
+
+- `startEstablishTracing()` — creates `consensus.establish` span via
+  `SpanGuard::span(TraceCategory::Consensus, seg::consensus, "establish")`.
+  Called once at start of establish phase. No `#ifdef` guards needed —
+  `SpanGuard::span()` returns a no-op guard when telemetry is disabled.
+
+- `updateEstablishTracing()` — sets attributes on each `phaseEstablish()` call:
+  - `converge_percent` — `convergePercent_`
+  - `establish_count` — `establishCounter_`
+  - `proposers` — `currPeerPositions_.size()`
+
+- `endEstablishTracing()` — calls `establishSpan_.reset()` on phase exit.
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h` — `phaseEstablish()` method + 3 helper methods
+
+---
+
+## Task 4a.5: Instrument `updateOurPositions()` ✅
+
+**Objective**: Trace each position update cycle including dispute resolution
+details.
+
+**Status**: DONE. Span, dispute events with yays/nays, and disputes_count attribute are all implemented.
+
+**What was done**:
+
+- Creates `consensus.update_positions` scoped span via
+  `SpanGuard::span(TraceCategory::Consensus, seg::consensus, "update_positions")`:
+
+  ```cpp
+  auto span = SpanGuard::span(TraceCategory::Consensus, seg::consensus, "update_positions");
+  ```
+
+- Attributes set:
+  - `converge_percent` — current convergence
+  - `proposers` — `currPeerPositions_.size()`
+  - `have_close_time_consensus` — close time consensus state
+  - `close_time_threshold` — `avCT_CONSENSUS_PCT`
+  - `disputes_count` — number of active disputes
+
+- Dispute events recorded via direct `span.addEvent()` call with yays/nays:
+  ```cpp
+  span.addEvent(
+      "dispute.resolve",
+      {{consensus::span::attr::txId, to_string(txId)},
+       {consensus::span::attr::disputeOurVote, dispute.getOurVote() ? "yes" : "no"},
+       {consensus::span::attr::disputeYays, std::to_string(dispute.getYays())},
+       {consensus::span::attr::disputeNays, std::to_string(dispute.getNays())}});
+  ```
+
+**Not implemented**:
+
+- `proposers_agreed` / `proposers_total` attributes — not set
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h` — `updateOurPositions()` method
+- `src/xrpld/consensus/DisputedTx.h` — added `getYays()` / `getNays()` (currently unused)
+
+---
+
+## Task 4a.6: Instrument `haveConsensus()` (Threshold & Convergence) ✅
+
+**Objective**: Trace consensus checking including threshold escalation.
+
+**Status**: DONE. The `consensus.check` span is created with all planned attributes
+including the avalanche threshold.
+
+**What was done**:
+
+- Creates `consensus.check` scoped span via
+  `SpanGuard::span(TraceCategory::Consensus, seg::consensus, "check")`:
+
+  ```cpp
+  auto span = SpanGuard::span(TraceCategory::Consensus, seg::consensus, "check");
+  ```
+
+- Attributes set:
+  - `agree_count` — peers that agree with our position
+  - `disagree_count` — peers that disagree
+  - `converge_percent` — convergence percentage
+  - `have_close_time_consensus` — close time consensus state
+  - `threshold_percent` — set to `avCT_CONSENSUS_PCT` (75%)
+  - `consensus_result` — "yes", "no", or "moved_on"
+  - `avalanche_threshold` — the escalated weight from `getNeededWeight()` on the `consensus.update_positions` span
+
+**Key modified files**:
+
+- `src/xrpld/consensus/Consensus.h` — `haveConsensus()` method
+
+---
+
+## Task 4a.7: Instrument Mode Changes ✅
+
+**Objective**: Trace consensus mode transitions (proposing ↔ observing,
+wrongLedger, switchedLedger).
+
+**Status**: Done.
+
+**What was done**:
+
+- In `RCLConsensus::Adaptor::onModeChange()`, creates a scoped span via direct
+  `SpanGuard::span()` call:
+
+  ```cpp
+  auto span = telemetry::SpanGuard::span(
+      telemetry::TraceCategory::Consensus, telemetry::seg::consensus, "mode_change");
+  span.setAttribute(consensus::span::attr::modeOld, to_string(before).c_str());   // "mode_old"
+  span.setAttribute(consensus::span::attr::modeNew, to_string(after).c_str());   // "mode_new"
+  ```
+
+- `MonitoredMode::set()` in `Consensus.h` calls `adaptor_.onModeChange(before, after)`.
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp` — `onModeChange()`
+
+---
+
+## Task 4a.8: Reparent Existing Spans Under Round ✅
+
+**Objective**: Make existing consensus spans (`consensus.accept`,
+`consensus.accept.apply`, `consensus.validation.send`) children of the
+`consensus.round` root span instead of being standalone.
+
+**Status**: DONE. All three spans are now parented under the round span.
+
+**What was done**:
+
+- `consensus.validation.send` uses `SpanGuard::linkedSpan()` to create a
+  follows-from link to `roundSpanContext_`. This is thread-safe because
+  `roundSpanContext_` is a lightweight `SpanContext` snapshot captured on the
+  consensus thread and read on the jtACCEPT worker thread.
+
+- `consensus.accept` and `consensus.accept.apply` now use
+  `SpanGuard::childSpan(name, roundSpanContext_)` instead of `SpanGuard::span()`
+  to explicitly parent under the round span context. This solves the cross-thread
+  parenting problem:
+  - `doAccept()` runs on the jtACCEPT worker thread (not the consensus thread)
+  - `childSpan()` explicitly passes the parent context, bypassing OTel's
+    thread-local context propagation
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Task 4a.9: Build Verification and Testing ✅
+
+**Objective**: Verify all Phase 4a changes compile cleanly with telemetry ON
+and OFF, and don't affect consensus timing.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify `SpanGuard` compiles to no-ops
+3. Run existing consensus unit tests
+4. Verify `SpanGuard` / `SpanContext` members have negligible overhead when disabled
+5. Run `pccl` pre-commit checks
+
+**Verification Checklist**:
+
+- [x] Build succeeds with telemetry ON
+- [x] Build succeeds with telemetry OFF
+- [x] Existing consensus tests pass
+- [x] `SpanGuard` no-op path verified (no `#ifdef` needed — disabled at runtime)
+- [x] No new virtual calls in hot consensus paths
+- [x] `pccl` passes
+
+---
+
+## Phase 4a Summary
+
+| Task | Description                                      | Status                   | New Files | Modified Files | Depends On |
+| ---- | ------------------------------------------------ | ------------------------ | --------- | -------------- | ---------- |
+| 4a.0 | Prerequisites: extend SpanGuard & Telemetry APIs | ✅ Done (no macros)      | 0         | 2              | Phase 4    |
+| 4a.1 | Adaptor `getTelemetry()` method                  | ⏭️ Skipped (not needed)  | 0         | 0              | Phase 4    |
+| 4a.2 | Switchable round span with deterministic traceID | ✅ Done                  | 1         | 3              | 4a.0       |
+| 4a.3 | Span members in `Consensus.h`                    | ✅ Done (with deviation) | 0         | 2              | —          |
+| 4a.4 | Instrument `phaseEstablish()`                    | ✅ Done                  | 0         | 1              | 4a.3       |
+| 4a.5 | Instrument `updateOurPositions()`                | ✅ Done                  | 0         | 2              | 4a.0, 4a.3 |
+| 4a.6 | Instrument `haveConsensus()` (thresholds)        | ✅ Done                  | 0         | 1              | 4a.3       |
+| 4a.7 | Instrument mode changes                          | ✅ Done                  | 0         | 1              | —          |
+| 4a.8 | Reparent existing spans under round              | ✅ Done                  | 0         | 1              | 4a.0, 4a.2 |
+| 4a.9 | Build verification and testing                   | ✅ Done                  | 0         | 0              | 4a.0-4a.8  |
+
+**Parallel work**: Tasks 4a.0 and 4a.1 can run in parallel. Tasks 4a.4, 4a.5, 4a.6, and 4a.7 can run in parallel after 4a.3 (and 4a.0 for 4a.5).
+
+### New Spans (Phase 4a)
+
+| Span Name                    | Location           | Key Attributes (actually set)                                                                                                                                                                                             |
+| ---------------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `consensus.round`            | `RCLConsensus.cpp` | `xrpl.consensus.round_id`, `xrpl.consensus.ledger_id`, `xrpl.ledger.seq`, `xrpl.consensus.mode`, `trace_strategy`                                                                                                         |
+| `consensus.phase.open`       | `Consensus.h`      | `start_reason`, `previous_close_agree`, `peer_positions_at_open`, `early_close_triggered` (at start); `open_duration_ms`, `peer_positions_at_close`, `tx_sets_acquired`, `close_reason`, `proposers_validated` (at close) |
+| `consensus.establish`        | `Consensus.h`      | `converge_percent`, `establish_count`, `proposers`, `disputes_count`, `close_time_avalanche_state`                                                                                                                        |
+| `consensus.update_positions` | `Consensus.h`      | `converge_percent`, `proposers`, `have_close_time_consensus`, `close_time_threshold`, `disputes_count`, `avalanche_threshold`                                                                                             |
+| `consensus.check`            | `Consensus.h`      | `agree_count`, `disagree_count`, `converge_percent`, `have_close_time_consensus`, `threshold_percent`, `consensus_result`                                                                                                 |
+| `consensus.mode_change`      | `RCLConsensus.cpp` | `mode_old`, `mode_new`                                                                                                                                                                                                    |
+
+### New Events (Phase 4a)
+
+| Event Name        | Parent Span                  | Attributes (actually set)                                        |
+| ----------------- | ---------------------------- | ---------------------------------------------------------------- |
+| `dispute.resolve` | `consensus.update_positions` | `xrpl.tx.id`, `dispute_our_vote`, `dispute_yays`, `dispute_nays` |
+| `tx.included`     | `consensus.accept.apply`     | `xrpl.tx.id`                                                     |
+
+### New Attributes (Phase 4a)
+
+```cpp
+// Round-level (on consensus.round) — ALL IMPLEMENTED
+"xrpl.consensus.round_id"             = int64    // Consensus round number
+"xrpl.consensus.ledger_id"            = string   // previousLedger.id() hash
+"trace_strategy"                       = string   // "deterministic" or "attribute"
+
+// Establish-level — IMPLEMENTED
+"converge_percent"                     = int64    // Convergence % (0-100+)
+"establish_count"                      = int64    // Number of establish iterations
+"agree_count"                          = int64    // Peers that agree (haveConsensus)
+"disagree_count"                       = int64    // Peers that disagree
+"threshold_percent"                    = int64    // Current threshold (avCT_CONSENSUS_PCT = 75%)
+"consensus_result"                     = string   // "yes", "no", "moved_on"
+"have_close_time_consensus"            = bool     // Close time consensus reached
+"close_time_threshold"                 = int64    // Close time voting threshold
+
+// Establish-level — IMPLEMENTED
+"disputes_count"                       = int64    // Active disputes (on update_positions)
+"avalanche_threshold"                  = int64    // Escalated weight (on update_positions)
+
+// Establish-level — NOT IMPLEMENTED
+// "proposers_agreed"                  = int64    // Peers agreeing with us — not set
+// "proposers_total"                   = int64    // Total peer positions — not set (not defined)
+
+// Mode change — ALL IMPLEMENTED
+"mode_old"                             = string   // Previous mode
+"mode_new"                             = string   // New mode
+```
+
+### Implementation Notes
+
+- **No macros**: The planned `XRPL_TRACE_CONSENSUS`, `XRPL_TRACE_ADD_EVENT`, and
+  `XRPL_TRACE_SET_ATTR` macros were not implemented. All consensus tracing uses
+  `SpanGuard` factory methods (`span()`, `hashSpan()`, `linkedSpan()`) and direct
+  method calls (`setAttribute()`, `addEvent()`). This avoids macro control-flow
+  issues and is cleaner than the planned approach.
+- **Separation of concerns**: All non-trivial telemetry code extracted to private
+  helpers (`startRoundTracing`, `createValidationSpan`, `startEstablishTracing`,
+  `updateEstablishTracing`, `endEstablishTracing`). Business logic methods contain
+  single-line calls to these helpers.
+- **Thread safety**: `createValidationSpan()` runs on the jtACCEPT worker thread.
+  Instead of accessing `roundSpan_` across threads, a `roundSpanContext_` snapshot
+  (lightweight `SpanContext` value type) is captured on the consensus thread in
+  `startRoundTracing()` and read by `createValidationSpan()`. The job queue
+  provides the happens-before guarantee.
+- **No `#ifdef` guards**: Span members use `std::optional<SpanGuard>` and `SpanContext`
+  which have no-op implementations when telemetry is disabled. No `#ifdef XRPL_ENABLE_TELEMETRY`
+  guards needed around members or includes.
+- **No `getTelemetry()` adaptor method**: `SpanGuard::span()` is a static factory that
+  internally checks telemetry state, so `Consensus.h` doesn't need adaptor access
+  for span creation. Only `RCLConsensus::Adaptor` accesses `app_.getTelemetry()` directly.
+- **Config validation**: `consensus_trace_strategy` is validated to be either
+  `"deterministic"` or `"attribute"`, falling back to `"deterministic"` for
+  unrecognised values.
+- **Plan deviation**: `roundSpan_` is stored in `RCLConsensus::Adaptor` (not
+  `Consensus.h`) because the adaptor has access to telemetry config and can
+  implement the deterministic trace ID strategy. `establishSpan_` is correctly
+  in `Consensus.h` as planned.
+
+---
+
+# Phase 4b: Cross-Node Propagation (Future — Documentation Only)
+
+> **Goal**: Wire `TraceContextPropagator` for P2P messages so that proposals
+> and validations carry trace context between nodes. This enables true
+> distributed tracing where a proposal sent by Node A creates a child span
+> on Node B.
+>
+> **Status**: NOT IMPLEMENTED. The protobuf fields and propagator class exist
+> but are not wired. This section documents the design for future work.
+
+## Architecture
+
+```
+Node A (proposing)                         Node B (receiving)
+─────────────────                         ──────────────────
+consensus.round                           consensus.round
+├── propose()                             ├── peerProposal()
+│   └── TraceContextPropagator            │   └── TraceContextPropagator
+│       ::injectToProtobuf(               │       ::extractFromProtobuf(
+│           TMProposeSet.trace_context)   │           TMProposeSet.trace_context)
+│                                         │   └── span link → Node A's context
+└── validate()                            └── onValidation()
+    └── inject into TMValidation              └── extract from TMValidation
+```
+
+## Wiring Points
+
+| Message         | Inject Location                    | Extract Location                    | Protobuf Field             |
+| --------------- | ---------------------------------- | ----------------------------------- | -------------------------- |
+| `TMProposeSet`  | `Adaptor::propose()`               | `PeerImp::onMessage(TMProposeSet)`  | field 1001: `TraceContext` |
+| `TMValidation`  | `Adaptor::validate()`              | `PeerImp::onMessage(TMValidation)`  | field 1001: `TraceContext` |
+| `TMTransaction` | `NetworkOPs::processTransaction()` | `PeerImp::onMessage(TMTransaction)` | field 1001: `TraceContext` |
+
+## Span Link Semantics
+
+Received messages use **span links** (follows-from), NOT parent-child:
+
+- The receiver's processing span links to the sender's context
+- This preserves each node's independent trace tree
+- Cross-node correlation visible via linked traces in Tempo/Jaeger
+
+## Interaction with Deterministic Trace ID (Strategy A)
+
+When using deterministic trace_id (Phase 4a default), cross-node spans already
+share the same trace_id. P2P propagation adds **span-level** linking:
+
+- Without propagation: spans from different nodes appear in the same trace
+  (same trace_id) but without parent-child or follows-from relationships.
+- With propagation: spans have explicit links showing which proposal/validation
+  from Node A caused processing on Node B.
+
+## Prerequisites
+
+- Phase 4a (this task list) — establish phase tracing must be in place
+- `TraceContextPropagator` free functions (already exist in
+  `include/xrpl/telemetry/TraceContextPropagator.h`)
+- Protobuf `TraceContext` message (already exists, field 1001)

OpenTelemetryPlan/Phase5_taskList.md

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

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.

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

@@ -15,10 +15,14 @@
 #   - 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).
 #
 # Environment variables:
 #   CI                      if set, skip the tools above when on macOS.
@@ -26,12 +30,27 @@
 
 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="$1"
     shift
@@ -40,14 +59,18 @@ check() {
         probe=("${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 "$(uname -s)" in
@@ -79,24 +102,35 @@ if [ "${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
+    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} ${tidy_probe}"
         check dot
         check doxygen
         check gcovr
@@ -107,6 +141,7 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
         # pre-commit, or its alternative implementation prek
         check pre-commit sh -c 'pre-commit --version || prek --version'
         check run-clang-tidy run-clang-tidy --help
+        check "run-clang-tidy-${llvm_version}" "run-clang-tidy-${llvm_version}" --help
     fi
 fi
 
@@ -121,8 +156,9 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
     check cargo-audit cargo audit --version
     check cargo-llvm-cov cargo llvm-cov --version
     check cargo-nextest cargo nextest --version
-    check clippy clippy-driver --version
+    check clippy-driver
     check rust-analyzer
+    check rust-nightly rust-nightly run rustc --version
     check rustc
     check rustfmt
 fi
@@ -133,7 +169,11 @@ 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
@@ -158,9 +198,9 @@ 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}"
@@ -168,9 +208,9 @@ 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/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_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

@@ -144,7 +144,11 @@ def main():
             + files
         )
         canonicalize_fix_paths(Path(fixes_dir))
-        applied = subprocess.run([clang_apply_replacements, 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]
+        )
 
     return result.returncode or applied.returncode
 

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/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.
@@ -1621,3 +1683,163 @@ validators.txt
 # set to ssl_verify to 0.
 [ssl_verify]
 1
+#-------------------------------------------------------------------------------
+#
+# 11. Telemetry (OpenTelemetry Tracing)
+#
+#-------------------------------------------------------------------------------
+#
+# Enables distributed tracing via OpenTelemetry. Requires building with
+# -DXRPL_ENABLE_TELEMETRY=ON (telemetry Conan option).
+#
+# [telemetry]
+#
+# enabled=0
+#
+#   Enable or disable telemetry at runtime. Default: 0 (disabled).
+#
+# service_name=xrpld
+#
+#   OTel resource attribute `service.name`. Default: xrpld.
+#   The node's network ID (from [network_id]) is automatically added
+#   as the `xrpl.network.id` and `xrpl.network.type` resource attributes.
+#
+# service_instance_id=<node_public_key>
+#
+#   OTel resource attribute `service.instance.id`, which tells one node's
+#   telemetry apart from another's. Normally left unset: the node identity
+#   is not known when telemetry is constructed, so the server fills this in
+#   with its own Base58 node public key later during startup. Set it only
+#   to pin a stable instance name of your own choosing; doing so suppresses
+#   the node-public-key fallback.
+#   Default: the node's Base58 public key.
+#
+# traces_endpoint=http://localhost:4318/v1/traces
+#
+#   The OTLP/HTTP endpoint spans are exported to. The server sends trace
+#   data as protobuf-encoded HTTP POST requests to this URL. The full URL
+#   including the signal path is used verbatim; no other endpoint is
+#   derived from it.
+#   Default: http://localhost:4318/v1/traces.
+#
+#   The scheme of this URL is what decides whether the connection is
+#   encrypted, and it is matched exactly: only a lower-case https:// URL
+#   gives TLS. Because of that, setting tls_client_cert requires this URL
+#   to start with https:// — including leaving it at the default above,
+#   which makes xrpld fail to start rather than export without the client
+#   identity it was configured with.
+#
+# --- TLS settings for the OTLP exporter connection ---
+#
+# use_tls=0
+#
+#   Whether to hand tls_ca_cert to the exporter as its CA bundle. TLS is
+#   selected by the scheme of traces_endpoint, not by this key; setting it
+#   to 1 only supplies a custom CA file for verifying the collector.
+#   Default: 0 (no CA file is passed, so the exporter keeps its own
+#   default trust store).
+#
+# tls_ca_cert=
+#
+#   Path to a PEM-encoded CA certificate bundle for verifying the
+#   collector's certificate. Only used when use_tls=1, and passed to the
+#   exporter unchanged. The path is not checked while the config is parsed,
+#   so a missing or unreadable file surfaces as an export failure at
+#   runtime rather than as a startup error.
+#   Default: empty (system CA store).
+#
+#   Leaving this empty stays valid and selects the system CA store. A path
+#   that is set is checked like the client paths below: with enabled=1 and
+#   use_tls=1, one that does not exist or cannot be read makes xrpld fail
+#   to start.
+#
+# tls_client_cert=
+#
+#   Path to this node's PEM-encoded client certificate, presented to the
+#   collector for mutual TLS (mTLS). Requires use_tls=1. Leave empty
+#   for one-way (server-only) TLS. Default: empty.
+#
+#   To enable mTLS, both tls_client_cert and tls_client_key must be
+#   specified. If only one is provided, xrpld will fail to start. Providing
+#   them while use_tls=0 also fails to start, rather than being ignored.
+#   traces_endpoint must be an https:// URL, because that scheme is what
+#   makes the exporter present the certificate at all. With use_tls=1 each
+#   path is opened at startup, so one that does not exist or cannot be read
+#   fails to start too, rather than failing later as an opaque TLS
+#   handshake error. All four checks apply only when enabled=1; with
+#   telemetry disabled these settings are read but never validated.
+#
+# tls_client_key=
+#
+#   Path to the PEM-encoded private key for tls_client_cert. Required
+#   whenever tls_client_cert is set. Requires use_tls=1, and must be
+#   readable. All three conditions are enforced exactly as described under
+#   tls_client_cert above: when enabled=1, breaking any one of them makes
+#   xrpld fail to start.
+#   Default: empty.
+#
+#   Head sampling is intentionally fixed at 1.0 (sample everything) and is
+#   not configurable. A per-node sampling ratio would let nodes make
+#   divergent keep/drop decisions for the same distributed trace, producing
+#   broken/partial traces. A ParentBasedSampler ensures spans inheriting a
+#   remote parent honor the upstream decision. Reduce volume at the collector
+#   via tail sampling instead; for node-local post-hoc dropping use
+#   SpanGuard::discard() in code.
+#
+# trace_rpc=1
+#
+#   Enable tracing for JSON-RPC and WebSocket API request handling —
+#   command parsing, execution, and response serialization. Default: 1.
+#
+# trace_transactions=1
+#
+#   Enable tracing for the transaction lifecycle — submission, validation,
+#   application to ledgers, and final disposition. Default: 1.
+#
+# trace_consensus=1
+#
+#   Enable tracing for the consensus round lifecycle — proposals,
+#   validations, mode changes, and ledger acceptance. Default: 1.
+#
+# trace_peer=1
+#
+#   Enable tracing for peer-to-peer protocol messages — overlay message
+#   send/receive, peer handshakes, and routing. High volume; enabled
+#   by default. Default: 1.
+#
+# trace_ledger=1
+#
+#   Enable tracing for ledger close and accept operations — ledger
+#   building, state hashing, and write-back to the node store. Default: 1.
+#
+# consensus_trace_strategy=deterministic
+#
+#   How the consensus round span picks its trace id. Two values are
+#   accepted, and anything else makes xrpld fail to start.
+#
+#   deterministic (the default, and the value to use): the trace id comes
+#   from the previous ledger hash, so every validator of a round reports
+#   into one trace and the round can be read end to end across nodes.
+#
+#   random: experimental only, and not used. Each node invents its own
+#   trace id, so a single round arrives as one separate trace per node.
+#   Those traces can only be lined up by hand through the
+#   consensus_ledger_id span attribute.
+#
+# --- Batch processor tuning ---
+#
+# batch_size=512
+#
+#   Maximum number of spans exported in a single batch. Must be at least 1
+#   and must not exceed max_queue_size. Default: 512.
+#
+# batch_delay_ms=5000
+#
+#   Maximum delay (milliseconds) before a partial batch is flushed.
+#   Must be at least 1. Default: 5000 (5 seconds).
+#
+# max_queue_size=2048
+#
+#   Maximum number of spans queued in memory before drops occur. Must be
+#   at least 1 and at least as large as batch_size. Default: 2048.
+#

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
 # --------------------------------------------------------------------

cmake/PatchNixBinary.cmake

@@ -1,26 +1,38 @@
 #[===================================================================[
    Patch executables to run in non-Nix environments.
 
-   The Nix-based CI image links binaries against an ELF interpreter (loader)
+   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` adds a
-   POST_BUILD step that resets the interpreter to the system default loader and
-   drops the rpath.
+   (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 is only active inside the Nix-based image, detected by the presence of
-   /tmp/loader-path.sh (shipped by that image, resolves the default loader). It
-   is skipped for sanitizer builds, whose runtime libraries are resolved through
-   the rpath. Everywhere else `patch_nix_binary` is a no-op.
+   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)
 
-# Provided by the Nix-based CI image; prints the system default ELF loader path.
-set(_loader_path_script "/tmp/loader-path.sh")
+# 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 EXISTS "${_loader_path_script}")
+if(
+    is_linux
+    AND NOT SANITIZERS_ENABLED
+    AND is_nix_compiler
+    AND NOT DEFINED ENV{XRPLD_NO_PATCH_NIX_BINARY}
+)
     execute_process(
         COMMAND "${_loader_path_script}"
         OUTPUT_VARIABLE DEFAULT_LOADER_PATH
@@ -41,13 +53,38 @@ function(patch_nix_binary target)
     if(NOT PATCH_NIX_BINARIES)
         return()
     endif()
-    add_custom_command(
-        TARGET ${target}
-        POST_BUILD
-        COMMAND
-            "${PATCHELF_COMMAND}" --set-interpreter "${DEFAULT_LOADER_PATH}"
-            --remove-rpath "$<TARGET_FILE:${target}>"
-        COMMENT "Patching ${target}: set default loader, remove rpath"
-        VERBATIM
+
+    set(patch_command
+        "${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
@@ -171,9 +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 "${CMAKE_CXX_COMPILER}" REALPATH)
     if(
-        _cxx_real MATCHES "^/nix/store/"
+        is_nix_compiler
         AND is_linux
         AND is_clang
         AND CMAKE_CXX_FLAGS MATCHES "stdlib=libstdc"
@@ -267,10 +269,50 @@ elseif(use_lld)
     )
     if("${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)
 
@@ -133,6 +135,12 @@ 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(
@@ -198,8 +206,49 @@ target_link_libraries(
         xrpl.libxrpl.conditions
 )
 
+# Telemetry module — OpenTelemetry distributed tracing support.
+# Sources: include/xrpl/telemetry/ (headers), src/libxrpl/telemetry/ (impl).
+# When telemetry=ON, links the Conan-provided umbrella target
+# opentelemetry-cpp::opentelemetry-cpp (individual component targets like
+# ::api, ::sdk are not available in the Conan package).
+#
+# Declared before its consumers (consensus, tx) because add_module isolates
+# each module's headers: a module can only include xrpl/telemetry/ headers if
+# it links this target, and the target must already exist at that point.
+#
+# Links xrpl.libxrpl.protocol PRIVATELY for sha512Half (digest.h) and the
+# SField table behind TxAccountSpanNames.cpp
+add_module(xrpl telemetry)
+target_link_libraries(
+    xrpl.libxrpl.telemetry
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.beast xrpl.libxrpl.config
+    PRIVATE xrpl.libxrpl.protocol
+)
+if(telemetry)
+    target_link_libraries(
+        xrpl.libxrpl.telemetry
+        PUBLIC opentelemetry-cpp::opentelemetry-cpp
+    )
+endif()
+
+# Links xrpl.libxrpl.telemetry for the consensus tracing spans declared in
+# include/xrpl/consensus/ConsensusSpanNames.h.
+add_module(xrpl consensus)
+target_link_libraries(
+    xrpl.libxrpl.consensus
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.json
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.ledger
+        xrpl.libxrpl.telemetry
+)
+
 add_module(xrpl tx)
-target_link_libraries(xrpl.libxrpl.tx PUBLIC xrpl.libxrpl.ledger)
+target_link_libraries(
+    xrpl.libxrpl.tx
+    PUBLIC xrpl.libxrpl.ledger xrpl.libxrpl.telemetry
+)
 
 add_library(xrpl.libxrpl)
 set_target_properties(xrpl.libxrpl PROPERTIES OUTPUT_NAME xrpl)
@@ -220,6 +269,7 @@ target_link_modules(
     beast
     conditions
     config
+    consensus
     core
     crypto
     git
@@ -227,12 +277,14 @@ target_link_modules(
     ledger
     net
     nodestore
+    peerfinder
     protocol
     protocol_autogen
     rdb
     resource
     server
     shamap
+    telemetry
     tx
 )
 

cmake/XrplCov.cmake

@@ -44,6 +44,7 @@ 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"

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.
 #]===================================================================]
@@ -25,19 +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_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/XrplSanity.cmake

@@ -36,6 +36,19 @@ elseif(is_gcc)
     endif()
 endif()
 
+# A Nix compiler is only meant to be used from a managed environment: the xrpld
+# dev shell (which exports XRPL_DEVSHELL) or the CI image. Using one from a bare
+# shell usually means a leaked toolchain (picked up via PATH or a Conan profile)
+# and leads to confusing breakage, so fail early with guidance.
+if(is_nix_compiler AND NOT is_ci_image AND NOT DEFINED ENV{XRPL_DEVSHELL})
+    message(
+        FATAL_ERROR
+        "A Nix compiler (${CMAKE_CXX_COMPILER}) is being used outside the xrpld "
+        "dev shell. Enter it with `nix develop` (see docs/build/nix.md) before "
+        "configuring the build."
+    )
+endif()
+
 # check for in-source build and fail
 if("${CMAKE_CURRENT_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
     message(

cmake/XrplSettings.cmake

@@ -30,6 +30,13 @@ if(tests)
     endif()
 endif()
 
+option(benchmark "Build benchmarks" ON)
+
+# When OFF, the crates directory is not added to the build at all: no Rust
+# toolchain is required, no cxxbridge bindings are generated, and the C++ tests
+# that consume those bindings are left out of the build tree.
+option(rust "Build the Rust crates and the C++ code that depends on them" OFF)
+
 # Enabled by default so every header is compiled on its own as the main file of
 # its own compile_commands.json entry - this is what lets clang-tidy (and clangd
 # and IDEs) analyse a header's own includes directly. The per-header objects are

cmake/XrplValidatorKeys.cmake

@@ -5,22 +5,39 @@ option(
 )
 
 if(validator_keys)
-    git_branch(current_branch)
-    # default to tracking VK master branch unless we are on release
-    if(NOT (current_branch STREQUAL "release"))
-        set(current_branch "master")
-    endif()
-    message(STATUS "Tracking ValidatorKeys branch: ${current_branch}")
+    # Own the install destination below rather than relying on another module
+    # having pulled this in first.
+    include(GNUInstallDirs)
+
+    # Pinned to an exact commit, not a branch: the tool ships inside our
+    # packages, so the same xrpld version must always package the same
+    # validator-keys. Bump this deliberately.
+    set(validator_keys_commit "4c0fb75eec9601c711645998c904507e87e910ae")
+    message(STATUS "Using ValidatorKeys commit: ${validator_keys_commit}")
 
     FetchContent_Declare(
         validator_keys
         GIT_REPOSITORY https://github.com/ripple/validator-keys-tool.git
-        GIT_TAG "${current_branch}"
+        GIT_TAG "${validator_keys_commit}"
     )
     FetchContent_MakeAvailable(validator_keys)
+    # The tool's own CMakeLists excludes the target from 'all' when it is built
+    # as a subproject. Undo that, so validator_keys=ON really does build it.
     set_target_properties(
         validator-keys
-        PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}"
+        PROPERTIES
+            RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}"
+            EXCLUDE_FROM_ALL OFF
+            EXCLUDE_FROM_DEFAULT_BUILD OFF
+    )
+    # We ship this binary, so like xrpld it must not keep the Nix store's ELF
+    # loader, or it cannot run on the target distro at all.
+    patch_nix_binary(validator-keys)
+
+    configure_file(
+        "${validator_keys_SOURCE_DIR}/LICENSE"
+        "${CMAKE_BINARY_DIR}/validator-keys-LICENSE"
+        COPYONLY
     )
     install(TARGETS validator-keys RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 endif()

cmake/codegen/CMakeLists.txt

@@ -0,0 +1,21 @@
+#[===================================================================[
+   Protocol Autogen - Standalone project
+
+   Exposes the 'setup_code_gen' and 'code_gen' targets on their own, without
+   configuring the rest of xrpl. Code generation is pure Python, so this needs
+   neither the dependencies nor a compiler, which makes it usable in CI and by
+   contributors who only want to regenerate the protocol wrapper classes:
+
+     cmake -S cmake/codegen -B build/codegen
+     cmake --build build/codegen --target setup_code_gen
+     cmake --build build/codegen --target code_gen
+
+   The targets are identical to the ones offered by the top-level build, since
+   both come from cmake/XrplProtocolAutogen.cmake.
+#]===================================================================]
+
+cmake_minimum_required(VERSION 3.16)
+
+project(xrpl_codegen LANGUAGES NONE)
+
+include("${CMAKE_CURRENT_LIST_DIR}/../XrplProtocolAutogen.cmake")

cmake/scripts/codegen/generate_tx_classes.py

@@ -8,6 +8,7 @@ Uses pcpp to preprocess the macro file and pyparsing to parse the DSL.
 
 import io
 import argparse
+import re
 from pathlib import Path
 import pyparsing as pp
 
@@ -53,28 +54,89 @@ def create_transaction_parser():
     return macro_parser
 
 
+# Defaults for xrpl::TxSettings members, mirroring
+# include/xrpl/protocol/TxSettings.h. A transaction's settings blob only names
+# the members that differ from these.
+SETTING_DEFAULTS = {
+    "delegable": "Delegation::NotDelegable",
+    "amendment": "uint256{}",
+    "privileges": "Privilege::NoPriv",
+}
+
+
+def parse_settings(settings_str):
+    """Parse a TxSettings blob into a dict, filling in defaults.
+
+    Args:
+        settings_str: A string like '({.delegable = Delegation::NotDelegable,
+                      .privileges = Privilege::CreateAcct})', or '({})'.
+
+    Returns:
+        A dict with a value for every key in SETTING_DEFAULTS.
+    """
+    body = settings_str.strip()
+    if not (body.startswith("(") and body.endswith(")")):
+        raise ValueError(
+            f"Malformed settings blob, expected '({{...}})': {settings_str!r}"
+        )
+    body = body[1:-1].strip()
+    if not (body.startswith("{") and body.endswith("}")):
+        raise ValueError(
+            f"Malformed settings blob, expected '({{...}})': {settings_str!r}"
+        )
+    body = body[1:-1]
+
+    # Strip comments, which may be interleaved with the designated initializers.
+    body = re.sub(r"//[^\n]*", "", body)
+
+    settings = dict(SETTING_DEFAULTS)
+    seen = set()
+    # Each entry runs from '.key =' up to the next '.key =' or the end.
+    for key, value in re.findall(
+        r"\.(\w+)\s*=\s*(.*?)(?=,\s*\.\w+\s*=|,?\s*$)", body, re.S
+    ):
+        if key not in SETTING_DEFAULTS:
+            raise ValueError(f"Unknown TxSettings member '.{key}' in {settings_str!r}")
+        settings[key] = " ".join(value.split()).rstrip(",")
+        seen.add(key)
+
+    # Catch a typo'd or unparsed initializer rather than silently defaulting it.
+    # Every '.member' in the blob must have been consumed above.
+    if len(re.findall(r"\.\w+", body)) != len(seen):
+        raise ValueError(f"Could not parse every setting in {settings_str!r}")
+
+    # A blob with content but no designated initializer is positional, which
+    # would otherwise be read as "all defaults" and silently generate the
+    # wrong output.
+    if body.strip() and not seen:
+        raise ValueError(
+            "TxSettings requires designated initializers (.member = value), "
+            f"got {settings_str!r}"
+        )
+
+    return settings
+
+
 def parse_transaction_args(args_list):
     """Parse the arguments of a TRANSACTION macro call.
 
     Args:
         args_list: A list of parsed arguments from pyparsing, e.g.,
-                   ['ttPAYMENT', '0', 'Payment', 'Delegation::delegable',
-                    'uint256{}', 'createAcct', '({...})']
+                   ['ttPAYMENT', '0', 'Payment',
+                    '({.privileges = Privilege::CreateAcct})', '({...})']
 
     Returns:
         A dict with parsed transaction information.
     """
-    if len(args_list) < 7:
+    if len(args_list) < 5:
         raise ValueError(
-            f"Expected at least 7 parts in TRANSACTION, got {len(args_list)}: {args_list}"
+            f"Expected at least 5 parts in TRANSACTION, got {len(args_list)}: {args_list}"
         )
 
     tag = args_list[0]
     value = args_list[1]
     name = args_list[2]
-    delegable = args_list[3]
-    amendments = args_list[4]
-    privileges = args_list[5]
+    settings = parse_settings(args_list[3])
     fields_str = args_list[-1]
 
     # Parse fields: ({field1, field2, ...})
@@ -84,9 +146,9 @@ def parse_transaction_args(args_list):
         "tag": tag,
         "value": value,
         "name": name,
-        "delegable": delegable,
-        "amendments": amendments,
-        "privileges": privileges,
+        "delegable": settings["delegable"],
+        "amendments": settings["amendment"],
+        "privileges": settings["privileges"],
         "fields": fields,
     }
 

conan.lock

@@ -10,35 +10,47 @@
         "rocksdb/10.5.1#4a197eca381a3e5ae8adf8cffa5aacd0%1782392413.075713",
         "re2/20251105#8579cfd0bda4daf0683f9e3898f964b4%1782392402.431897",
         "protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81%1782392410.233933",
-        "openssl/3.6.3#1163d4ddc603907084d08a6a0c6e580f%1782307150.583886",
+        "opentelemetry-cpp/1.28.0#2cbf71db4e0e0535df20be305005cb2f%1785939947.292581",
+        "openssl/3.6.3#f806de8933e3bf6f01016c6a888cee2e%1783945160.863288",
         "nudb/2.0.9#11149c73f8f2baff9a0198fe25971fc7%1782392402.297166",
-        "mpt-crypto/0.4.0-rc2#a580f2f9ad0e795de696aa62d54fb9af%1782425834.488828",
+        "nlohmann_json/3.11.3#45828be26eb619a2e04ca517bb7b828d%1701220705.259",
+        "mpt-crypto/1.0.2#b313cef0c1a493eb970ad185b2e9bab7%1784285108.866483",
         "lz4/1.10.0#982d9b673900f665a1da109e09c17cab%1782392402.164188",
         "libiconv/1.17#9923bc6dc6f106646d6967e0039a5ada%1782392792.775744",
+        "libcurl/8.21.0#8c26e59c04891ba3373ea3552e18f67f%1783067699.863",
         "libbacktrace/cci.20210118#a7691bfccd8caaf66309df196790a5a1%1782392402.420732",
         "libarchive/3.8.7#c446109bd1f1d8ba7936c94189bc50e6%1782392403.066892",
         "jemalloc/5.3.1#1fc58d55316041f10fbc1e8a2eae632a%1776700028.228",
         "gtest/1.17.0#5224b3b3ff3b4ce1133cbdd27d53ee7d%1782392402.791979",
-        "grpc/1.81.1#5217e6ef0544c42b46f4af35d5e7f649%1782307148.845616",
+        "grpc/1.81.1#f729f6d75992d20f9c72828e9142d62f%1783945160.094135",
+        "fast_float/8.2.10#f6f28d6bb22112078e7dbda611caf681%1785888854.601666",
         "ed25519/2015.03#ae761bdc52730a843f0809bdf6c1b1f6%1782307148.15562",
         "date/3.0.4#862e11e80030356b53c2c38599ceb32b%1782392402.538492",
+        "corrosion/0.6.1#bfa292df0a957bc70a450ff316cd9435%1786119416.131296",
         "c-ares/1.34.6#545240bb1c40e2cacd4362d6b8967650%1782392402.681654",
         "bzip2/1.0.8#c470882369c2d95c5c77e970c0c7e321%1782392402.296732",
         "boost/1.91.0#ea540ca2133d831b560036aa24dece3c%1782392419.475605",
-        "abseil/20250127.0#bb0baf1f362bc4a725a24eddd419b8f7%1782307147.395833"
+        "benchmark/1.9.5#b885dc73ad67b40a55d45684d1c88ad1%1782736613.864841",
+        "abseil/20250127.0#9ef01c1451a8340f9022e46238c0fbb6%1783945159.651047"
     ],
     "build_requires": [
         "zlib/1.3.2#1cb806da49011867778ffb6ac7190fcb%1782392402.122708",
         "strawberryperl/5.32.1.1#8d114504d172cfea8ea1662d09b6333e%1782395692.540639",
         "protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81%1782392410.233933",
+        "pkgconf/2.5.1#93c2051284cba1279494a43a4fcfeae2%1757684701.089",
+        "opentelemetry-proto/1.7.0#ed6d5bd761bef0afb0ba09676420b9ea%1749461220.268",
+        "ninja/1.13.2#c8c5dc2a52ed6e4e42a66d75b4717ceb%1764096931.974",
         "nasm/2.16.01#31e26f2ee3c4346ecd347911bd126904%1782395690.33162",
         "msys2/cci.latest#d22fe7b2808f5fd34d0a7923ace9c54f%1770657326.649",
-        "m4/1.4.19#34c4bbc3eeebe98ca6edf2f52d602e7d%1777282960.259",
+        "meson/1.10.2#9d2d10681fe7fe61c788c58626c89b25%1775558003.754",
+        "m4/1.4.19#1727f439cf74e83826ec96d0b4904eee%1784541921.659",
+        "libtool/2.4.7#14e7739cc128bc1623d2ed318008e47e%1755679003.847",
+        "gnu-config/cci.20210814#466e9d4d7779e1c142443f7ea44b4284%1762363589.329",
         "cmake/4.3.3#840cf00ea09777e05c2050a50a82c722%1782392418.696091",
         "b2/5.4.2#ffd6084a119587e70f11cd45d1a386e2%1782392402.624226",
         "automake/1.16.5#b91b7c384c3deaa9d535be02da14d04f%1755524470.56",
         "autoconf/2.71#51077f068e61700d65bb05541ea1e4b0%1731054366.86",
-        "abseil/20250127.0#bb0baf1f362bc4a725a24eddd419b8f7%1782307147.395833"
+        "abseil/20250127.0#9ef01c1451a8340f9022e46238c0fbb6%1783945159.651047"
     ],
     "python_requires": [],
     "overrides": {
@@ -59,6 +71,9 @@
         ],
         "lz4/[>=1.9.4 <2]": [
             "lz4/1.10.0#982d9b673900f665a1da109e09c17cab"
+        ],
+        "protobuf/[>=4.25.3 <7]": [
+            "protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81"
         ]
     },
     "config_requires": []

conan/init.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+# Install our Conan configuration, profiles and the xrplf remote into CONAN_HOME.
+# Safe to re-run; never deletes the Conan home.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
+CONAN_DIR="$(conan config home)"
+
+echo "Installing Conan configuration into ${CONAN_DIR}"
+conan config install "${SCRIPT_DIR}/global.conf"
+conan config install "${SCRIPT_DIR}/profiles" -tf "${CONAN_DIR}/profiles"
+# This script manages these files, so make them read-only - Conan does not
+# preserve the source mode. Only the files: the directories must stay writable
+# for `conan config install` to replace them.
+chmod a-w "${CONAN_DIR}/global.conf"
+find "${CONAN_DIR}/profiles" -type f -exec chmod a-w {} +
+
+echo "Adding the xrplf Conan remote"
+# --index 0: our patched recipes must win over Conan Center.
+conan remote add --index 0 --force xrplf https://conan.xrplf.org/repository/conan/

conan/profiles/default

@@ -1,9 +1,13 @@
 {% set os = detect_api.detect_os() %}
 {% set arch = detect_api.detect_arch() %}
 {% set compiler, version, compiler_exe = detect_api.detect_default_compiler() %}
-{% set compiler_version = version %}
-{% if os == "Linux" %}
 {% set compiler_version = detect_api.default_compiler_version(compiler, version) %}
+{% if os == "Macos" %}
+{# Minimum macOS the dependencies target. #}
+{# Without this, Conan builds each dependency against the (possibly newer) host SDK, so the #}
+{# dependency objects target a newer macOS than the binary and the linker warns. #}
+{# Keep at or below CMAKE_OSX_DEPLOYMENT_TARGET in CMakeLists.txt. #}
+{% set min_macos_version = "15.0" %}
 {% endif %}
 
 [settings]
@@ -18,10 +22,54 @@ compiler.runtime=static
 {% else %}
 compiler.libcxx={{ detect_api.detect_libcxx(compiler, version, compiler_exe) }}
 {% endif %}
+{% if os == "Macos" %}
+os.version={{ min_macos_version }}
+{% endif %}
 
 [conf]
+{# The Boost recipe builds with b2, which doesn't use Conan's toolchain files. #}
+{# Instead it hand-rolls the compiler for user-config.jam, #}
+{# and its fallback probes a version-suffixed binary (e.g. `g++-15`) before plain `g++`. #}
+{# Inside the Nix shell the wrapper only provides `g++`/`gcc` (no `-15` suffix), #}
+{# so on a host that also has a system `g++-15` the probe escapes Nix #}
+{# and picks the system compiler, which is mismatched with the Nix libraries #}
+{# and breaks the build (e.g. Boost.Stacktrace link checks fail). #}
+{# Pinning the executables here short-circuits that probe so Boost (and the rest of the toolchain) #}
+{# resolve the same compiler. #}
+{# Not part of the package ID, so binaries stay shareable. #}
+{% if os != "Windows" %}
+{% set cc_exe  = {"gcc": "gcc",  "clang": "clang",   "apple-clang": "clang"}.get(compiler) %}
+{% set cxx_exe = {"gcc": "g++",  "clang": "clang++", "apple-clang": "clang++"}.get(compiler) %}
+tools.build:compiler_executables={'c':'{{ cc_exe }}','cpp':'{{ cxx_exe }}'}
+{% endif %}
+
 {# By default, Conan tries to reuse binaries built with different cppstd versions. #}
 {# We want to avoid that to improve reproduceability, so we add the cppstd version to the package ID. #}
 {# More info: https://docs.conan.io/2/reference/extensions/binary_compatibility.html #}
 user.package:cppstd_version=23
 tools.info.package_id:confs+=["user.package:cppstd_version"]
+
+{% if os == "Macos" %}
+[buildenv]
+{# os.version adds -mmacosx-version-min to compiler command lines, #}
+{# but Boost.Context's b2 assembly (.S) rule ignores it, #}
+{# so those objects keep the host SDK version and still warn at link time. #}
+{# clang's assembler honors this env var regardless, pinning them. #}
+{# Scoped to boost/* since it is the only gap. #}
+boost/*:MACOSX_DEPLOYMENT_TARGET={{ min_macos_version }}
+{% endif %}
+{% if compiler == "gcc" and compiler_version < 13 %}
+tools.build:cxxflags+=['-Wno-restrict']
+{% endif %}
+{% if os == "Windows" %}
+# opentelemetry-cpp's recipe removes the `shared` option on Windows and never
+# sets BUILD_SHARED_LIBS, so its upstream CMake defaults the protobuf-generated
+# `opentelemetry_proto` target to a DLL (opentelemetry_proto.dll). The rest of
+# the project links statically and nothing deploys that DLL next to the
+# executables, so the telemetry unit test fails to start with
+# STATUS_DLL_NOT_FOUND (0xC0000135). Force the dependency to build fully static
+# so no runtime DLL is produced. The conf is folded into the package id so a
+# fresh static binary is built instead of reusing a previously cached one.
+opentelemetry-cpp/*:tools.cmake.cmaketoolchain:extra_variables={"BUILD_SHARED_LIBS": "OFF"}
+opentelemetry-cpp/*:tools.info.package_id:confs+=["tools.cmake.cmaketoolchain:extra_variables"]
+{% endif %}

conanfile.py

@@ -15,19 +15,23 @@ class Xrpl(ConanFile):
     settings = "os", "compiler", "build_type", "arch"
     options = {
         "assertions": [True, False],
+        "benchmark": [True, False],
         "coverage": [True, False],
         "fPIC": [True, False],
         "jemalloc": [True, False],
         "rocksdb": [True, False],
         "shared": [True, False],
         "static": [True, False],
+        "telemetry": [True, False],
         "tests": [True, False],
         "unity": [True, False],
         "xrpld": [True, False],
     }
 
     requires = [
+        "corrosion/0.6.1",
         "ed25519/2015.03",
+        "fast_float/8.2.10",
         "grpc/1.81.1",
         "libarchive/3.8.7",
         "nudb/2.0.9",
@@ -46,12 +50,14 @@ class Xrpl(ConanFile):
 
     default_options = {
         "assertions": False,
+        "benchmark": True,
         "coverage": False,
         "fPIC": True,
         "jemalloc": False,
         "rocksdb": True,
         "shared": False,
         "static": True,
+        "telemetry": True,
         "tests": False,
         "unity": False,
         "xrpld": False,
@@ -129,20 +135,27 @@ class Xrpl(ConanFile):
             self.options["boost"].without_cobalt = True
 
     def requirements(self):
+        if self.options.benchmark:
+            self.requires("benchmark/1.9.5")
         self.requires("boost/1.91.0", force=True, transitive_headers=True)
         self.requires("date/3.0.4", transitive_headers=True)
         if self.options.jemalloc:
             self.requires("jemalloc/5.3.1")
         self.requires("lz4/1.10.0", force=True)
-        self.requires("mpt-crypto/0.4.0-rc2", transitive_headers=True)
+        self.requires("mpt-crypto/1.0.2", transitive_headers=True)
         self.requires("protobuf/6.33.5", force=True)
         if self.options.rocksdb:
             self.requires("rocksdb/10.5.1")
         self.requires("secp256k1/0.7.1", transitive_headers=True)
         self.requires("sqlite3/3.53.0", force=True)
+        # OpenTelemetry C++ SDK for distributed tracing (optional).
+        # Provides OTLP/HTTP exporter, batch span processor, and trace API.
+        if self.options.telemetry:
+            self.requires("opentelemetry-cpp/1.28.0")
         self.requires("xxhash/0.8.3", transitive_headers=True)
 
     exports_sources = (
+        "bin/default-loader-path.sh",
         "CMakeLists.txt",
         "cfg/*",
         "cmake/*",
@@ -162,12 +175,14 @@ class Xrpl(ConanFile):
     def generate(self):
         tc = CMakeToolchain(self)
         tc.variables["tests"] = self.options.tests
+        tc.variables["benchmark"] = self.options.benchmark
         tc.variables["assert"] = self.options.assertions
         tc.variables["coverage"] = self.options.coverage
         tc.variables["jemalloc"] = self.options.jemalloc
         tc.variables["rocksdb"] = self.options.rocksdb
         tc.variables["BUILD_SHARED_LIBS"] = self.options.shared
         tc.variables["static"] = self.options.static
+        tc.variables["telemetry"] = self.options.telemetry
         tc.variables["unity"] = self.options.unity
         tc.variables["xrpld"] = self.options.xrpld
         tc.generate()
@@ -206,6 +221,7 @@ class Xrpl(ConanFile):
             "boost::thread",
             "date::date",
             "ed25519::ed25519",
+            "fast_float::fast_float",
             "grpc::grpc++",
             "libarchive::libarchive",
             "lz4::lz4",
@@ -221,3 +237,9 @@ class Xrpl(ConanFile):
         ]
         if self.options.rocksdb:
             libxrpl.requires.append("rocksdb::librocksdb")
+        if self.options.telemetry:
+            libxrpl.requires.append("opentelemetry-cpp::opentelemetry-cpp")
+            # The public telemetry headers pick their class layout on this
+            # define, so a consumer that does not see it compiles a different
+            # SpanGuard than the one inside the library it links.
+            libxrpl.defines.append("XRPL_ENABLE_TELEMETRY")

crates/.cargo/config.toml

@@ -0,0 +1,17 @@
+# The Rust static libraries are linked into C++ targets, so the runtime linkage
+# here has to match what the C++ build uses (see cmake/XrplCompiler.cmake).
+#
+# macOS needs nothing: AppleClang cannot link libgcc/libc++ statically, so the
+# C++ build skips those flags on Apple as well.
+
+# Both amd64 and arm64 Linux builds link libgcc statically. This only affects
+# links that rustc itself drives (`cargo test` binaries and the like) — the
+# `staticlib` crates consumed by CMake are archived, not linked, so rustc
+# silently ignores link args for them. Keeping libgcc_s.so.1 off the xrpld link
+# line is handled in crates/CMakeLists.txt instead.
+[target.'cfg(target_os = "linux")']
+rustflags = ["-C", "link-args=-static-libgcc"]
+
+# Windows builds use the static MSVC runtime.
+[target.'cfg(windows)']
+rustflags = ["-C", "target-feature=+crt-static"]

crates/CMakeLists.txt

@@ -0,0 +1,104 @@
+find_package(Corrosion REQUIRED)
+
+corrosion_import_crate(MANIFEST_PATH ${CMAKE_CURRENT_SOURCE_DIR}/Cargo.toml)
+
+# The generated C++ lands in the build tree, so put a .clang-tidy next to it to
+# keep clang-tidy from analyzing code we don't own.
+configure_file(
+    generated.clang-tidy
+    "${CMAKE_CURRENT_BINARY_DIR}/.clang-tidy"
+    COPYONLY
+)
+
+add_custom_target(xrpl_crates)
+add_dependencies(tidy_prerequisites xrpl_crates)
+
+# On macOS, ld warns `ignoring duplicate libraries` when linking a crate.
+# Corrosion is the source of both duplicates it names:
+#
+# * The crate archive and its cxxbridge archive, because
+#   `corrosion_add_cxxbridge` makes the two depend on each other, and CMake
+#   repeats a static library cycle on the link line so single-pass linkers can
+#   resolve it. (LINK_INTERFACE_MULTIPLICITY can only raise that count.)
+# * `-lSystem`, which Corrosion copies from rustc's `native-static-libs` even
+#   though the compiler driver always links libSystem.
+#
+# ld needs neither: it resolves the cycle from one copy of each archive and
+# links libSystem once. So silence the warning rather than rewrite Corrosion's
+# link interface, which the cycle is also part of. The option itself is old —
+# Xcode 15 is only where the warning became the default — and the check below
+# leaves it out on a linker that does not know it.
+if(is_macos)
+    include(CheckLinkerFlag)
+    check_linker_flag(
+        CXX
+        -Wl,-no_warn_duplicate_libraries
+        have_no_warn_duplicate_libraries
+    )
+endif()
+
+function(_unlink_libgcc_s crate)
+    if(NOT (is_linux AND static))
+        return()
+    endif()
+
+    # Corrosion exposes a crate's staticlib as an imported `<crate>-static`
+    # target and puts the native libs in its INTERFACE_LINK_LIBRARIES. If either
+    # of those changes, warn instead of silently letting libgcc_s.so.1 return.
+    set(imported "${crate}-static")
+    if(NOT TARGET ${imported})
+        message(
+            FATAL_ERROR
+            "Corrosion did not create the imported target '${imported}', so "
+            "libgcc_s cannot be removed from the link interface of '${crate}'. "
+            "xrpld will link libgcc_s.so.1 dynamically. Check where Corrosion "
+            "${CORROSION_VERSION} now records `native-static-libs`."
+        )
+        return()
+    endif()
+
+    get_target_property(libs ${imported} INTERFACE_LINK_LIBRARIES)
+    if(NOT "gcc_s" IN_LIST libs)
+        message(
+            WARNING
+            "'gcc_s' was not in the link interface of '${imported}' as "
+            "expected. If the Rust toolchain stopped reporting it this "
+            "workaround is obsolete and can be deleted; otherwise xrpld may "
+            "link libgcc_s.so.1 dynamically. Verify with: "
+            "objdump -p xrpld | grep NEEDED"
+        )
+        return()
+    endif()
+
+    list(REMOVE_ITEM libs gcc_s)
+    set_property(TARGET ${imported} PROPERTY INTERFACE_LINK_LIBRARIES ${libs})
+endfunction()
+
+function(add_xrpl_crate name)
+    cmake_parse_arguments(ARG "" "CRATE" "FILES" ${ARGN})
+    _unlink_libgcc_s(${ARG_CRATE})
+    # `cc` picks its runtime flag from `crt-static` alone, so it compiles a
+    # crate's C++ with `-MT`; Debug needs `-MTd` (to match cmake/XrplCompiler.cmake).
+    if(is_msvc)
+        corrosion_set_env_vars(
+            ${ARG_CRATE}
+            "$<$<CONFIG:Debug>:CXXFLAGS=-MTd>"
+        )
+    endif()
+    corrosion_add_cxxbridge(${name}_cxxbridge CRATE ${ARG_CRATE} FILES
+                            ${ARG_FILES}
+    )
+    # Generated cxxbridge headers don't exist at configure time; CMake 3.28+
+    # validates INTERFACE_SOURCES on consuming targets. Clear it to skip the
+    # existence check — build-time ordering is enforced by the custom commands.
+    set_target_properties(${name}_cxxbridge PROPERTIES INTERFACE_SOURCES "")
+    if(have_no_warn_duplicate_libraries)
+        target_link_options(
+            ${name}_cxxbridge
+            INTERFACE -Wl,-no_warn_duplicate_libraries
+        )
+    endif()
+    add_dependencies(xrpl_crates ${name}_cxxbridge)
+endfunction()
+
+add_xrpl_crate(rs_hello_world CRATE rs_hello_world FILES lib.rs)