Merge branch 'pratik/otel-phase1c-rpc-integration' into pratik/otel-phase2-rpc-tracing

std::ranges::transform/all_of come from <algorithm>, which is already included.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.cspell.config.yaml

@@ -65,6 +65,7 @@ words:
   - Btrfs
   - Buildx
   - canonicality
+  - CGNAT
   - changespq
   - checkme
   - choco
@@ -121,6 +122,8 @@ words:
   - fsanitize
   - funclets
   - Gamal
+  - gantt
+  - Gantt
   - gcov
   - gcovr
   - ghead
@@ -129,6 +132,7 @@ words:
   - gpgcheck
   - gpgkey
   - hotwallet
+  - hicpp
   - hwaddress
   - hwrap
   - ifndef
@@ -167,12 +171,11 @@ words:
   - mathbunnyru
   - mcmodel
   - MEMORYSTATUSEX
-  - MPTAMM
-  - MPTDEX
   - Merkle
   - Metafuncton
   - misprediction
   - missingok
+  - MPTAMM
   - mptbalance
   - MPTDEX
   - mptflags
@@ -206,6 +209,7 @@ words:
   - nonxrp
   - noreplace
   - noripple
+  - nostd
   - nostdinc
   - notifempty
   - nudb
@@ -214,6 +218,7 @@ words:
   - Nyffenegger
   - onlatest
   - ostr
+  - otelc
   - pargs
   - partitioner
   - paychan
@@ -222,6 +227,7 @@ words:
   - permdex
   - perminute
   - permissioned
+  - pimpl
   - pointee
   - populator
   - preauth
@@ -300,6 +306,7 @@ words:
   - takerpays
   - ters
   - TMEndpointv2
+  - traceql
   - trixie
   - tx
   - txid
@@ -307,6 +314,7 @@ words:
   - txjson
   - txn
   - txns
+  - txqueue
   - txs
   - ubsan
   - UBSAN
@@ -355,4 +363,7 @@ words:
   - xrplf
   - xxhash
   - xxhasher
-  - CGNAT
+  - xychart
+  - zpages
+  - pratik
+  - dedup

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

@@ -1,3 +1,6 @@
+Loop: xrpl.telemetry xrpld.rpc
+  xrpld.rpc > xrpl.telemetry
+
 Loop: xrpld.app xrpld.overlay
   xrpld.app > xrpld.overlay
 

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

@@ -45,6 +45,10 @@ 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
@@ -198,6 +202,7 @@ 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
@@ -235,6 +240,7 @@ xrpl.server > xrpl.resource
 xrpl.shamap > xrpl.basics
 xrpl.shamap > xrpl.nodestore
 xrpl.shamap > xrpl.protocol
+xrpl.telemetry > xrpl.config
 xrpl.tx > xrpl.basics
 xrpl.tx > xrpl.core
 xrpl.tx > xrpl.ledger
@@ -254,6 +260,7 @@ 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

.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`/`childSpan`. 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 +1,885 @@
+#!/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/...).
+
+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/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/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::childSpan(`  (static factory)
+#   - `<obj>.span(` / `<obj>->setAttribute(` etc.   (member call)
+# `span`/`childSpan` additionally require the `SpanGuard`/`.`/`->` receiver;
+# `setAttribute`/`addEvent` only ever exist on a guard, so a `.`/`->` suffices.
+CALLSITE = re.compile(
+    r"(?:SpanGuard::|\.|->)\s*(setAttribute|addEvent|span|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)
+#   childSpan(name[, parentCtx])    -> check arg 0 (span-name leaf)
+CONSTANT_ARG_POSITIONS: Dict[str, Set[int]] = {
+    "setAttribute": {0},
+    "addEvent": {0},
+    "span": {1, 2},
+    "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/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/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
+
+
+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), or a Prometheus/Grafana builtin.
+    valid = l1_keys | metric_labels | builtins
+    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 +1,864 @@
+#!/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_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"],
+        )
+
+    def test_builtin_labels_not_flagged(self):
+        self.assertEqual(
+            self._run('"expr": "sum by (le, span_name, exported_instance) (x)"', set()),
+            [],
+        )
+
+    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__) (rate(x[5m]))"', set()),
+            [],
+        )
+
+    def test_l1_label_passes(self):
+        self.assertEqual(self._run('"q": "{command=\\"x\\"}"', {"command"}), [])
+
+    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):
+        self.assertEqual(self._run('"q": "{resource.service_name=\\"x\\"}"', set()), [])
+
+    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/workflows/on-pr.yml

@@ -51,8 +51,10 @@ 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
 
@@ -109,6 +111,11 @@ jobs:
     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' }}
@@ -176,6 +183,7 @@ jobs:
     if: failure() || cancelled()
     needs:
       - check-levelization
+      - check-otel-naming
       - check-rename
       - clang-tidy
       - build-test

.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

.gitignore

@@ -86,3 +86,6 @@ __pycache__
 
 # clangd cache
 /.cache
+
+# Env. file carrying environmental setup data for local or cloud runs.
+.env.*

CMakeLists.txt

@@ -121,6 +121,18 @@ 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 (default), all tracing code compiles to no-ops with zero overhead.
+# Enable via: conan install -o telemetry=True, or cmake -Dtelemetry=ON.
+option(telemetry "Enable OpenTelemetry tracing" ON)
+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)

CONTRIBUTING.md

@@ -298,6 +298,66 @@ If you wish to automatically fix whatever clang-tidy finds _and_ is capable of f
 run-clang-tidy -p build -quiet -fix -allow-no-checks src tests
 ```
 
+## 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 +1,565 @@
+# Distributed Tracing Fundamentals
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Next**: [Architecture Analysis](./01-architecture-analysis.md)
+
+---
+
+## What is Distributed Tracing?
+
+Distributed tracing is a method for tracking data objects as they flow through distributed systems. In a network like XRP Ledger, a single transaction touches multiple independent nodes—each with no shared memory or logging. Distributed tracing connects these dots.
+
+**Without tracing:** You see isolated logs on each node with no way to correlate them.
+
+**With tracing:** You see the complete journey of a transaction or an event across all nodes it touched.
+
+---
+
+## Actors and Actions at a Glance
+
+### Actors
+
+| Who (Plain English)                            | Technical Term  |
+| ---------------------------------------------- | --------------- |
+| A single unit of work being tracked            | Span            |
+| The complete journey of a request              | Trace           |
+| Data that links spans across services          | Trace Context   |
+| Code that creates spans and propagates context | Instrumentation |
+| Service that receives and processes traces     | Collector       |
+| Storage and visualization system               | Backend (Tempo) |
+| Decision logic for which traces to keep        | Sampler         |
+
+### Actions
+
+| What Happens (Plain English)            | Technical Term          |
+| --------------------------------------- | ----------------------- |
+| Start tracking a new operation          | Create a Span           |
+| Connect a child operation to its parent | Set `parent_span_id`    |
+| Group all related operations together   | Share a `trace_id`      |
+| Pass tracking data between services     | Context Propagation     |
+| Decide whether to record a trace        | Sampling (Head or Tail) |
+| Send completed traces to storage        | Export (OTLP)           |
+
+---
+
+## Core Concepts
+
+### 1. Trace
+
+A **trace** represents the entire journey of a request through the system. It has a unique `trace_id` that stays constant across all nodes.
+
+```
+Trace ID: abc123
+├── Node A: received transaction
+├── Node B: relayed transaction
+├── Node C: included in consensus
+└── Node D: applied to ledger
+```
+
+### 2. Span
+
+A **span** represents a single unit of work within a trace. Each span has:
+
+| Attribute        | Description                      | Example                    |
+| ---------------- | -------------------------------- | -------------------------- |
+| `trace_id`       | Identifies the trace             | `event123`                 |
+| `span_id`        | Unique identifier                | `span456`                  |
+| `parent_span_id` | Parent span (if any)             | `p_span123`                |
+| `name`           | Operation name                   | `rpc.submit`               |
+| `start_time`     | When work began (local time)     | `2024-01-15T10:30:00Z`     |
+| `end_time`       | When work completed (local time) | `2024-01-15T10:30:00.050Z` |
+| `attributes`     | Key-value metadata               | `tx_hash=ABC...`           |
+| `status`         | OK, ERROR MSG                    | `OK`                       |
+
+### 3. Trace Context
+
+**Trace context** is the data that propagates between services to link spans together. It contains:
+
+- `trace_id` - The trace this span belongs to
+- `span_id` - The current span (becomes parent for child spans)
+- `trace_flags` - Sampling decisions
+
+---
+
+## How Spans Form a Trace
+
+Spans have parent-child relationships forming a tree structure:
+
+```mermaid
+flowchart TB
+    subgraph trace["Trace: abc123"]
+        A["tx.submit<br/>span_id: 001<br/>50ms"] --> B["tx.validate<br/>span_id: 002<br/>5ms"]
+        A --> C["tx.relay<br/>span_id: 003<br/>10ms"]
+        A --> D["tx.apply<br/>span_id: 004<br/>30ms"]
+        D --> E["ledger.update<br/>span_id: 005<br/>20ms"]
+    end
+
+    style A fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style B fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style D fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style E fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **tx.submit (blue, root)**: The top-level span representing the entire transaction submission; all other spans are its descendants.
+- **tx.validate, tx.relay, tx.apply (green)**: Direct children of tx.submit, representing the three main stages -- validation, relay to peers, and application to the ledger.
+- **ledger.update (red)**: A grandchild span nested under tx.apply, representing the actual ledger state mutation triggered by applying the transaction.
+- **Arrows (parent to child)**: Each arrow indicates a parent-child span relationship where the parent's completion depends on the child finishing.
+
+The same trace visualized as a **timeline (Gantt chart)**:
+
+```
+Time →   0ms    10ms    20ms    30ms    40ms    50ms
+         ├───────────────────────────────────────────┤
+tx.submit│▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+         ├─────┤
+tx.valid │▓▓▓▓▓│
+         │     ├──────────┤
+tx.relay │     │▓▓▓▓▓▓▓▓▓▓│
+         │               ├────────────────────────────┤
+tx.apply │               │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+         │                         ├──────────────────┤
+ledger   │                         │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+```
+
+---
+
+## Span Relationships
+
+Spans don't always form simple parent-child trees. Distributed tracing defines several relationship types to capture different causal patterns:
+
+### 1. Parent-Child (ChildOf)
+
+The default relationship. The parent span **depends on** or **contains** the child span. The child runs within the scope of the parent.
+
+```
+tx.submit (parent)
+├── tx.validate (child)     ← parent waits for this
+├── tx.relay (child)        ← parent waits for this
+└── tx.apply (child)        ← parent waits for this
+```
+
+**When to use:** Synchronous calls, nested operations, any case where the parent's completion depends on the child.
+
+### 2. Follows-From
+
+A causal relationship where the first span **triggers** the second, but does **not wait** for it. The originator fires and moves on.
+
+```
+Time →
+
+tx.receive [=======]
+                     ↓ triggers (follows-from)
+              tx.relay   [===========]   ← runs independently
+```
+
+**When to use:** Asynchronous jobs, queued work, fire-and-forget patterns. For example, a node receives a transaction and queues it for relay — the relay span _follows from_ the receive span but the receiver doesn't wait for relaying to complete.
+
+> **OpenTracing** defined `FollowsFrom` as a first-class reference type alongside `ChildOf`.
+> **OpenTelemetry** represents this using **Span Links** with descriptive attributes instead (see below).
+
+### 3. Span Links (Cross-Trace and Non-Hierarchical)
+
+Links connect spans that are **causally related but not in a parent-child hierarchy**. Unlike parent-child, links can cross trace boundaries.
+
+```
+Trace A                          Trace B
+──────                           ──────
+batch.schedule                   batch.execute
+├─ item.enqueue (span X)    ┌──► process.item
+├─ item.enqueue (span Y) ───┤    (links to X, Y, Z)
+├─ item.enqueue (span Z)    └──►
+```
+
+**Use cases:**
+
+| Pattern              | Description                                                                 |
+| -------------------- | --------------------------------------------------------------------------- |
+| **Batch processing** | A batch span links back to all individual spans that contributed to it      |
+| **Fan-in**           | An aggregation span links to the multiple producer spans it merges          |
+| **Fan-out**          | Multiple downstream spans link back to the single span that triggered them  |
+| **Async handoff**    | A deferred job links back to the request that queued it (follows-from)      |
+| **Cross-trace**      | Correlating spans across independent traces (e.g., retries, related events) |
+
+**Link structure:** Each link carries the target span's context plus optional attributes:
+
+```
+Link {
+    trace_id:   <target trace>
+    span_id:    <target span>
+    attributes: { "link.description": "triggered by batch scheduler" }
+}
+```
+
+### Relationship Summary
+
+```mermaid
+flowchart LR
+    subgraph parent_child["Parent-Child"]
+        direction TB
+        P["Parent"] --> C["Child"]
+    end
+
+    subgraph follows_from["Follows-From"]
+        direction TB
+        A["Span A"] -.->|triggers| B["Span B"]
+    end
+
+    subgraph links["Span Links"]
+        direction TB
+        X["Span X\n(Trace 1)"] -.-|link| Y["Span Y\n(Trace 2)"]
+    end
+
+    parent_child ~~~ follows_from ~~~ links
+
+    style P fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style C fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style A fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style B fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style X fill:#4a148c,stroke:#38006b,color:#ffffff
+    style Y fill:#4a148c,stroke:#38006b,color:#ffffff
+```
+
+| Relationship     | Same Trace? | Dependency?                | OTel Mechanism    |
+| ---------------- | ----------- | -------------------------- | ----------------- |
+| **Parent-Child** | Yes         | Parent depends on child    | `parent_span_id`  |
+| **Follows-From** | Usually     | Causal but no dependency   | Link + attributes |
+| **Span Link**    | Either      | Correlation, no dependency | Link + attributes |
+
+---
+
+## Trace ID Generation
+
+A `trace_id` is a 128-bit (16-byte) identifier that groups all spans belonging to one logical operation. How it's generated determines how easily you can find and correlate traces later.
+
+### General Approaches
+
+#### 1. Random (W3C Default)
+
+Generate a random 128-bit ID when a trace starts. Standard approach for most services.
+
+```
+trace_id = random_128_bits()
+```
+
+| Pros                        | Cons                                          |
+| --------------------------- | --------------------------------------------- |
+| Simple, standard            | No natural correlation to domain events       |
+| Guaranteed unique per trace | If propagation is lost, trace is broken       |
+| Works with all OTel tooling | "Find trace for TX abc" requires index lookup |
+
+#### 2. Deterministic (Derived from Domain Data)
+
+Compute the trace_id from a hash of a natural identifier. Every node independently derives the **same** trace_id for the same event.
+
+```
+trace_id = SHA-256(domain_identifier)[0:16]   // truncate to 128 bits
+```
+
+| Pros                                                | Cons                                                       |
+| --------------------------------------------------- | ---------------------------------------------------------- |
+| Propagation-resilient — same ID computed everywhere | Same event processed twice (retry) shares trace_id         |
+| Natural search — domain ID maps directly to trace   | Non-standard (tooling assumes random)                      |
+| No coordination needed between nodes                | 256→128 bit truncation (collision risk negligible at ~2⁶⁴) |
+
+#### 3. Hybrid (Deterministic Prefix + Random Suffix)
+
+First 8 bytes derived from domain data, last 8 bytes random.
+
+```
+trace_id = SHA-256(domain_identifier)[0:8] || random_64_bits()
+```
+
+| Pros                                        | Cons                                     |
+| ------------------------------------------- | ---------------------------------------- |
+| Prefix search: "find all traces for TX abc" | Must propagate to maintain full trace_id |
+| Unique per processing instance              | More complex generation logic            |
+| Retries get distinct trace_ids              | Partial correlation only (prefix match)  |
+
+### XRPL Workflow Analysis
+
+XRPL has a unique advantage: its core workflows produce **globally unique 256-bit hashes** that are known on every node. This makes deterministic trace_id generation practical in ways most systems can't achieve.
+
+#### Natural Identifiers by Workflow
+
+| Workflow            | Natural Identifier                | Size       | Known at Start?               | Same on All Nodes?               |
+| ------------------- | --------------------------------- | ---------- | ----------------------------- | -------------------------------- |
+| **Transaction**     | Transaction hash (`tid_`)         | 256-bit    | Yes — computed before signing | Yes — hash of canonical tx data  |
+| **Consensus round** | Previous ledger hash + ledger seq | 256+32 bit | Yes — known when round opens  | Yes — all validators agree       |
+| **Validation**      | Ledger hash being validated       | 256-bit    | Yes — from consensus result   | Yes — same closed ledger         |
+| **Ledger catch-up** | Target ledger hash                | 256-bit    | Yes — we know what to fetch   | Yes — identifies ledger globally |
+
+#### Where These Identifiers Live in Code
+
+```
+Transaction:     STTx::getTransactionID()     → uint256 tid_
+                 TMTransaction::rawTransaction → recompute hash from bytes
+
+Consensus:       ConsensusProposal::prevLedger_ → uint256 (previous ledger hash)
+                 ConsensusProposal::position_   → uint256 (TxSet hash)
+                 LedgerHeader::seq              → uint32_t (ledger sequence)
+
+Validation:      STValidation::getLedgerHash()  → uint256
+                 STValidation::getNodeID()      → NodeID (160-bit)
+
+Ledger fetch:    InboundLedger constructor      → uint256 hash, uint32_t seq
+                 TMGetLedger::ledgerHash        → bytes (uint256)
+```
+
+### Recommended Strategy: Workflow-Scoped Deterministic
+
+Each workflow type derives its trace_id from its natural domain identifier:
+
+```
+Transaction trace:   trace_id = SHA-256("tx"    || tx_hash)[0:16]
+Consensus trace:     trace_id = SHA-256("cons"  || prev_ledger_hash || ledger_seq)[0:16]
+Ledger catch-up:     trace_id = SHA-256("fetch" || target_ledger_hash)[0:16]
+```
+
+The string prefix (`"tx"`, `"cons"`, `"fetch"`) prevents collisions between workflows that might share underlying hashes.
+
+**Why this works for XRPL:**
+
+1. **Propagation-resilient** — Even if a P2P message drops trace context, every node independently computes the same trace_id from the same tx_hash or ledger_hash. Spans still correlate.
+
+2. **Zero-cost search** — "Show me the trace for transaction ABC" becomes a direct lookup: compute `SHA-256("tx" || ABC)[0:16]` and query. No secondary index needed.
+
+3. **Cross-workflow linking via Span Links** — A consensus trace links to individual transaction traces. A validation span links to the consensus trace. This connects the full picture without forcing everything into one giant trace.
+
+### Cross-Workflow Correlation
+
+Each workflow gets its own trace. Span Links tie them together:
+
+```mermaid
+flowchart TB
+    subgraph tx_trace["Transaction Trace"]
+        direction LR
+        Tn["trace_id = f(tx_hash)"]:::note --> T1["tx.receive"] --> T2["tx.validate"] --> T3["tx.relay"]
+    end
+
+    subgraph cons_trace["Consensus Trace"]
+        direction LR
+        Cn["trace_id = f(prev_ledger, seq)"]:::note --> C1["cons.open"] --> C2["cons.propose"] --> C3["cons.accept"]
+    end
+
+    subgraph val_trace["Validation"]
+        direction LR
+        Vn["spans within consensus trace"]:::note --> V1["val.create"] --> V2["val.broadcast"]
+    end
+
+    subgraph fetch_trace["Catch-Up Trace"]
+        direction LR
+        Fn["trace_id = f(ledger_hash)"]:::note --> F1["fetch.request"] --> F2["fetch.receive"] --> F3["fetch.apply"]
+    end
+
+    C1 -.-|"span link\n(tx traces)"| T3
+    C3 --> V1
+    F1 -.-|"span link\n(target ledger)"| C3
+
+    classDef note fill:none,stroke:#888,stroke-dasharray:5 5,color:#333,font-style:italic
+    style T1 fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style T2 fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style T3 fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style C1 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C2 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C3 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style V1 fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style V2 fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style F1 fill:#4a148c,stroke:#38006b,color:#ffffff
+    style F2 fill:#4a148c,stroke:#38006b,color:#ffffff
+    style F3 fill:#4a148c,stroke:#38006b,color:#ffffff
+```
+
+**Reading the diagram:**
+
+- **Transaction Trace (blue)**: An independent trace whose `trace_id` is deterministically derived from the transaction hash. Contains receive, validate, and relay spans.
+- **Consensus Trace (green)**: An independent trace whose `trace_id` is derived from the previous ledger hash and sequence number. Covers the open, propose, and accept phases.
+- **Validation (red)**: Validation spans live within the consensus trace (not a separate trace). They are created after the accept phase completes.
+- **Catch-Up Trace (purple)**: An independent trace for ledger acquisition, derived from the target ledger hash. Used when a node is behind and fetching missing ledgers.
+- **Dotted arrows (span links)**: Cross-trace correlations. Consensus links to transaction traces it included; catch-up links to the consensus trace that produced the target ledger.
+- **Solid arrow (C3 to V1)**: A parent-child relationship -- validation spans are direct children of the consensus accept span within the same trace.
+
+**How a query flows:**
+
+```
+"Why was TX abc slow?"
+  1. Compute trace_id = SHA-256("tx" || abc)[0:16]
+  2. Find transaction trace → see it was included in consensus round N
+  3. Follow span link → consensus trace for round N
+  4. See which phase was slow (propose? accept?)
+  5. If a node was catching up, follow link → catch-up trace
+```
+
+### Trade-offs to Consider
+
+| Concern                       | Mitigation                                                                                                                    |
+| ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
+| **Retries get same trace_id** | Add `attempt` attribute to root span; spans have unique span_ids and timestamps                                               |
+| **256→128 bit truncation**    | Birthday-bound collision at ~2⁶⁴ operations — negligible for XRPL's throughput                                                |
+| **Non-standard generation**   | OTel spec allows any 16-byte non-zero value; tooling works on the hex string                                                  |
+| **Hash computation cost**     | SHA-256 is ~0.3μs per call; XRPL already computes these hashes for other purposes                                             |
+| **Late-binding identifiers**  | Ledger hash isn't known until after consensus — validation spans use ledger_seq as fallback, then link to the consensus trace |
+
+---
+
+## Distributed Traces Across Nodes
+
+In distributed systems like 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 +1,584 @@
+# 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`     | `BuildInfo::getVersionString()`                         | Standard `SERVICE_VERSION`     |
+| `service.instance.id` | node public key (base58)                                | Standard `SERVICE_INSTANCE_ID` |
+| `xrpl.network.id`     | network id (e.g. 0 for mainnet)                         | Network identifier             |
+| `xrpl.network.type`   | `"mainnet"` \| `"testnet"` \| `"devnet"` \| `"unknown"` | Network kind                   |
+| `xrpl.node.type`      | `"validator"` \| `"stock"` \| `"reporting"`             | Node role                      |
+| `xrpl.node.cluster`   | cluster name                                            | Cluster name, if clustered     |
+
+### 2.4.2 Span Attributes by Category
+
+> Span attribute keys use the underscore form from §2.3.3 (shared/qualified
+> keys are `<domain>_<field>`; per-span unique keys are bare). The dotted form
+> is reserved for the resource attributes in §2.4.1 above. This catalog lists
+> the planned attribute set by category; the exact emitted key for each
+> implemented span is defined by the `*SpanNames.h` constants, which are the
+> single source of truth where the two differ.
+
+#### Transaction Attributes
+
+| Key            | Type   | Description                           |
+| -------------- | ------ | ------------------------------------- |
+| `tx_hash`      | string | Transaction hash (hex)                |
+| `tx_type`      | string | `"Payment"`, `"OfferCreate"`, etc.    |
+| `tx_account`   | string | Source account (redacted in prod)     |
+| `tx_sequence`  | int64  | Account sequence number               |
+| `tx_fee`       | int64  | Fee in drops                          |
+| `tx_result`    | string | `"tesSUCCESS"`, `"tecPATH_DRY"`, etc. |
+| `ledger_index` | int64  | Ledger containing transaction         |
+| `relay_count`  | int64  | Peers the transaction was relayed to  |
+| `suppressed`   | bool   | `true` when HashRouter dropped a dup  |
+
+#### Consensus Attributes
+
+| Key                  | Type    | Description                         |
+| -------------------- | ------- | ----------------------------------- |
+| `consensus_round`    | int64   | Round number                        |
+| `consensus_phase`    | string  | `"open"`, `"establish"`, `"accept"` |
+| `consensus_mode`     | string  | `"proposing"`, `"observing"`, etc.  |
+| `proposers`          | int64   | Number of proposers                 |
+| `prev_ledger_prefix` | string  | Previous ledger hash prefix         |
+| `ledger_seq`         | int64   | Ledger sequence                     |
+| `tx_count`           | int64   | Transactions in consensus set       |
+| `round_time_ms`      | float64 | Round duration                      |
+
+#### RPC Attributes
+
+| Key           | Type    | Description                                                                   |
+| ------------- | ------- | ----------------------------------------------------------------------------- |
+| `command`     | string  | Command name (per-span unique on `rpc.command`)                               |
+| `version`     | int64   | API version                                                                   |
+| `rpc_role`    | string  | `"admin"` or `"user"` (qualified — `role` is generic)                         |
+| `params`      | string  | Sanitized parameters (optional)                                               |
+| `rpc_status`  | string  | Response status: `success` \| `error` (qualified — `status` is OTel-reserved) |
+| `duration_ms` | float64 | Request duration in milliseconds                                              |
+
+#### Peer & Message Attributes
+
+| Key                  | Type    | Description                |
+| -------------------- | ------- | -------------------------- |
+| `peer_id`            | string  | Peer public key (base58)   |
+| `peer_address`       | string  | IP:port                    |
+| `peer_latency_ms`    | float64 | Measured latency           |
+| `peer_cluster`       | string  | Cluster name if clustered  |
+| `message_type`       | string  | Protocol message type name |
+| `message_size_bytes` | int64   | Message size               |
+| `message_compressed` | bool    | Whether compressed         |
+
+#### Ledger & Job Attributes
+
+| Key               | Type    | Description           |
+| ----------------- | ------- | --------------------- |
+| `ledger_hash`     | string  | Ledger hash           |
+| `ledger_index`    | int64   | Ledger sequence/index |
+| `close_time`      | int64   | Close time (epoch)    |
+| `ledger_tx_count` | int64   | Transaction count     |
+| `job_type`        | string  | Job type name         |
+| `job_queue_ms`    | float64 | Time spent in queue   |
+| `job_worker`      | int64   | Worker thread ID      |
+
+#### PathFinding Attributes
+
+| Key                        | Type   | Description               |
+| -------------------------- | ------ | ------------------------- |
+| `pathfind_source_currency` | string | Source currency code      |
+| `pathfind_dest_currency`   | string | Destination currency code |
+| `pathfind_path_count`      | int64  | Number of paths found     |
+| `pathfind_cache_hit`       | bool   | RippleLineCache hit       |
+
+#### TxQ Attributes
+
+| Key                   | Type   | Description                 |
+| --------------------- | ------ | --------------------------- |
+| `txq_queue_depth`     | int64  | Current queue depth         |
+| `txq_fee_level`       | int64  | Fee level of transaction    |
+| `txq_eviction_reason` | string | Why transaction was evicted |
+
+#### Fee Attributes
+
+| Key                    | Type  | Description               |
+| ---------------------- | ----- | ------------------------- |
+| `fee_load_factor`      | int64 | Current load factor       |
+| `fee_escalation_level` | int64 | Fee escalation multiplier |
+
+#### Validator Attributes
+
+| Key                      | Type  | Description               |
+| ------------------------ | ----- | ------------------------- |
+| `validator_list_size`    | int64 | UNL size                  |
+| `validator_list_age_sec` | int64 | Seconds since last update |
+
+#### Amendment Attributes
+
+| Key                | Type   | Description                            |
+| ------------------ | ------ | -------------------------------------- |
+| `amendment_name`   | string | Amendment name                         |
+| `amendment_status` | string | `"enabled"`, `"vetoed"`, `"supported"` |
+
+#### SHAMap Attributes
+
+| Key                    | Type    | Description                                   |
+| ---------------------- | ------- | --------------------------------------------- |
+| `shamap_type`          | string  | `"transaction"`, `"state"`, `"account_state"` |
+| `shamap_missing_nodes` | int64   | Number of missing nodes during sync           |
+| `shamap_duration_ms`   | float64 | Sync duration                                 |
+
+### 2.4.3 Data Collection Summary
+
+The following table summarizes what data is collected by category:
+
+| Category        | Attributes Collected                                                                                             | Purpose                      |
+| --------------- | ---------------------------------------------------------------------------------------------------------------- | ---------------------------- |
+| **Transaction** | `tx_hash`, `tx_type`, `tx_result`, `tx_fee`, `ledger_index`                                                      | 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_index`, `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 Hashing**           | Account addresses are hashed both SDK-side (`pathfind_source_account`, `pathfind_dest_account` — always hashed before emission) and again at the collector level, so raw addresses never reach storage |
+| **Configurable Redaction**    | Sensitive fields can be excluded via `[telemetry]` config section                                                                                                                                      |
+| **Collector Tail Sampling**   | xrpld head sampling is fixed at 1.0 (every span emitted); the collector retains ~10% of non-error traces, reducing stored data exposure                                                                |
+| **Sampling**                  | Only 10% of traces recorded by default, reducing data exposure                                                                                                                                         |
+| **Local Control**             | Node operators have full control over what gets exported                                                                                                                                               |
+| **No Raw Payloads**           | Transaction content is never recorded, only metadata (hash, type, result)                                                                                                                              |
+| **Collector-Level Filtering** | Additional redaction/hashing can be configured at OTel Collector                                                                                                                                       |
+
+#### Account Address Hashing
+
+Account addresses are **always** hashed before they reach the telemetry
+backend — there is no opt-out flag and therefore no insecure-by-default
+failure mode. Protection is applied in two independent layers:
+
+1. **SDK-side** (this node): the path-finding RPC handlers call
+   `redactAccount()` (`xrpl::telemetry`, `Redaction.h`) before setting the
+   `pathfind_source_account` / `pathfind_dest_account` span attributes. The
+   helper emits the first 16 characters of `sha512Half(address)` as
+   lowercase hex — deterministic (spans for one account still correlate)
+   but non-reversible.
+2. **Collector-side** (defense-in-depth): an `attributes/hash` processor in
+   the OpenTelemetry Collector re-hashes those same attributes, so any node
+   that emitted a raw value is still redacted before storage.
+
+#### Collector-Level Data Protection
+
+The OpenTelemetry Collector can be configured (via an `attributes` processor)
+to hash or redact sensitive attributes before export — for example, hashing
+`pathfind_source_account` / `pathfind_dest_account`, deleting `peer_address`
+to drop IP addresses, and deleting `params` to redact request parameters.
+
+#### Configuration Options for Privacy
+
+In `xrpld.cfg`, operators control data collection granularity through the
+`[telemetry]` section. Besides `enabled`, per-component toggles
+(`trace_transactions`, `trace_consensus`, `trace_rpc`, `trace_peer` — the last
+often disabled due to high volume) select which spans are emitted. Account
+address hashing is not configurable: addresses are hashed unconditionally by
+the SDK helper described above, with collector-level hashing as a second
+layer.
+
+> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes) — never **sensitive content** (keys, balances, amounts, raw payloads).
+
+---
+
+## 2.5 Context Propagation Design
+
+> **WS** = WebSocket
+
+### 2.5.1 Propagation Boundaries
+
+```mermaid
+flowchart TB
+    subgraph http["HTTP/WebSocket (RPC)"]
+        w3c["W3C Trace Context Headers:<br/>traceparent:<br/>00-trace_id-span_id-flags<br/>tracestate: xrpld=..."]
+    end
+
+    subgraph protobuf["Protocol Buffers (P2P)"]
+        proto["message TraceContext {<br/>  bytes trace_id = 1;  // 16 bytes<br/>  bytes span_id = 2;   // 8 bytes<br/>  uint32 trace_flags = 3;<br/>  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
+
+In xrpld, Beast Insight is used through `increment` (counters), `gauge`
+(point-in-time values), and `timing` (durations) calls.
+
+#### OpenTelemetry (NEW)
+
+- **Purpose**: Distributed request tracing across nodes
+- **Strengths**:
+  - **Cross-node correlation** via `trace_id`
+  - Parent-child span relationships
+  - Rich attributes per span
+  - Industry standard (CNCF)
+- **Limitations**:
+  - Requires collector infrastructure
+  - Higher complexity than logging
+
+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.
+
+### 2.6.3 When to Use Each
+
+| Scenario                                | PerfLog    | StatsD | OpenTelemetry |
+| --------------------------------------- | ---------- | ------ | ------------- |
+| "How many TXs per second?"              | ❌         | ✅     | ✅            |
+| "What's the p99 RPC latency?"           | ❌         | ✅     | ✅            |
+| "Why was this specific TX slow?"        | ⚠️ partial | ❌     | ✅            |
+| "Which node delayed consensus?"         | ❌         | ❌     | ✅            |
+| "What happened on node X at time T?"    | ✅         | ❌     | ✅            |
+| "Show me the TX journey across 5 nodes" | ❌         | ❌     | ✅            |
+
+### 2.6.4 Coexistence Strategy
+
+```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 +1,483 @@
+# 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.
+
+### 3.9.1 Files Modified Summary
+
+| Component             | Files Modified | Architectural Impact |
+| --------------------- | -------------- | -------------------- |
+| **Core Telemetry**    | 10 new files   | None (new module)    |
+| **Application Init**  | 2 files        | Minimal              |
+| **RPC Layer**         | 3 files        | Minimal              |
+| **Transaction Relay** | 4 files        | Low                  |
+| **Consensus**         | 3 files        | Low-Medium           |
+| **Protocol Buffers**  | 1 file         | Low                  |
+| **CMake/Build**       | 3 files        | Minimal              |
+| **PathFinding**       | 2              | Minimal              |
+| **TxQ/Fee**           | 2              | Minimal              |
+| **Validator/Amend**   | 3              | Minimal              |
+| **Total**             | **~33 files**  | **Low**              |
+
+### 3.9.2 Detailed File Impact
+
+```mermaid
+pie title Code Changes by Component
+    "New Telemetry Module" : 800
+    "Transaction Relay" : 160
+    "Consensus" : 130
+    "RPC Layer" : 100
+    "PathFinding" : 80
+    "TxQ/Fee" : 60
+    "Validator/Amendment" : 40
+    "Application Init" : 35
+    "Protocol Buffers" : 25
+    "Build System" : 60
+```
+
+#### New Files (No Impact on Existing Code)
+
+| File                                        | Purpose                   |
+| ------------------------------------------- | ------------------------- |
+| `include/xrpl/telemetry/Telemetry.h`        | Main interface            |
+| `include/xrpl/telemetry/TelemetryConfig.h`  | Configuration structures  |
+| `include/xrpl/telemetry/TraceContext.h`     | Context propagation       |
+| `include/xrpl/telemetry/SpanGuard.h`        | RAII wrapper              |
+| `include/xrpl/telemetry/DiscardFlag.h`      | Thread-local discard flag |
+| `include/xrpl/telemetry/SpanAttributes.h`   | Attribute helpers         |
+| `src/libxrpl/telemetry/Telemetry.cpp`       | Implementation            |
+| `src/libxrpl/telemetry/TelemetryConfig.cpp` | Config parsing            |
+| `src/libxrpl/telemetry/TraceContext.cpp`    | Context serialization     |
+| `src/libxrpl/telemetry/NullTelemetry.cpp`   | No-op implementation      |
+
+#### Modified Files (Existing Xrpld Code)
+
+| File                                              | Risk Level |
+| ------------------------------------------------- | ---------- |
+| `src/xrpld/app/main/Application.cpp`              | Low        |
+| `include/xrpl/core/ServiceRegistry.h`             | Low        |
+| `src/xrpld/rpc/detail/ServerHandler.cpp`          | Low        |
+| `src/xrpld/rpc/handlers/*.cpp`                    | Low        |
+| `src/xrpld/overlay/detail/PeerImp.cpp`            | Medium     |
+| `src/xrpld/overlay/detail/OverlayImpl.cpp`        | Medium     |
+| `src/xrpld/app/consensus/RCLConsensus.cpp`        | Medium     |
+| `src/xrpld/app/consensus/RCLConsensusAdaptor.cpp` | Medium     |
+| `src/xrpld/core/JobQueue.cpp`                     | Low        |
+| `src/xrpld/app/paths/PathRequest.cpp`             | Low        |
+| `src/xrpld/app/paths/Pathfinder.cpp`              | Low        |
+| `src/xrpld/app/misc/TxQ.cpp`                      | Low        |
+| `src/xrpld/app/main/LoadManager.cpp`              | Low        |
+| `src/xrpld/app/misc/ValidatorList.cpp`            | Low        |
+| `src/xrpld/app/misc/AmendmentTable.cpp`           | Low        |
+| `src/xrpld/app/misc/Manifest.cpp`                 | Low        |
+| `src/xrpld/shamap/SHAMap.cpp`                     | Low        |
+| `src/xrpld/overlay/detail/ripple.proto`           | Low        |
+| `CMakeLists.txt`                                  | Low        |
+| `cmake/FindOpenTelemetry.cmake`                   | None (new) |
+
+### 3.9.3 Risk Assessment by Component
+
+<div align="center">
+
+**Do First** ↖ ↗ **Plan Carefully**
+
+```mermaid
+quadrantChart
+    title Code Intrusiveness Risk Matrix
+    x-axis Low Risk --> High Risk
+    y-axis Low Value --> High Value
+
+    RPC Tracing: [0.2, 0.55]
+    Transaction Relay: [0.55, 0.85]
+    Consensus Tracing: [0.75, 0.92]
+    Peer Message Tracing: [0.85, 0.35]
+    JobQueue Context: [0.3, 0.42]
+    Ledger Acquisition: [0.48, 0.65]
+    PathFinding: [0.38, 0.72]
+    TxQ and Fees: [0.25, 0.62]
+    Validator Mgmt: [0.15, 0.35]
+```
+
+**Optional** ↙ ↘ **Avoid**
+
+</div>
+
+#### Risk Level Definitions
+
+| Risk Level | Definition                                                       | Mitigation                         |
+| ---------- | ---------------------------------------------------------------- | ---------------------------------- |
+| **Low**    | Additive changes only; no modification to existing logic         | Standard code review               |
+| **Medium** | Minor modifications to existing functions; clear boundaries      | Comprehensive unit tests           |
+| **High**   | Changes to core logic or data structures; potential side effects | Integration tests + staged rollout |
+
+### 3.9.4 Architectural Impact Assessment
+
+| Aspect               | Impact  | Justification                                                                    |
+| -------------------- | ------- | -------------------------------------------------------------------------------- |
+| **Data Flow**        | Minimal | Read-only instrumentation; no modification to consensus or transaction data flow |
+| **Threading Model**  | Minimal | Context propagation uses thread-local storage (standard OTel pattern)            |
+| **Memory Model**     | Low     | Bounded queues prevent unbounded growth; RAII ensures cleanup                    |
+| **Network Protocol** | Low     | Optional fields in protobuf (high field numbers); backward compatible            |
+| **Configuration**    | None    | New config section; existing configs unaffected                                  |
+| **Build System**     | Low     | Optional CMake flag; builds work without OpenTelemetry                           |
+| **Dependencies**     | Low     | OpenTelemetry SDK is optional; null implementation when disabled                 |
+
+### 3.9.5 Backward Compatibility
+
+| Compatibility   | Status  | Notes                                                 |
+| --------------- | ------- | ----------------------------------------------------- |
+| **Config File** | ✅ Full | New `[telemetry]` section is optional                 |
+| **Protocol**    | ✅ Full | Optional protobuf fields with high field numbers      |
+| **Build**       | ✅ Full | `XRPL_ENABLE_TELEMETRY=OFF` produces identical binary |
+| **Runtime**     | ✅ Full | `enabled=0` produces zero overhead                    |
+| **API**         | ✅ Full | No changes to public RPC or P2P APIs                  |
+
+### 3.9.6 Rollback Strategy
+
+If issues are discovered after deployment:
+
+1. **Immediate**: Set `enabled=0` in config and restart (zero code change)
+2. **Quick**: Rebuild with `XRPL_ENABLE_TELEMETRY=OFF`
+3. **Complete**: Revert telemetry commits (clean separation makes this easy)
+
+### 3.9.7 Code Change Examples
+
+**Minimal RPC Instrumentation (Low Intrusiveness):** Instrumenting an RPC handler adds roughly 3-4 lines: one macro to start the span and one or two `setAttribute` calls (command name, status). The span ends automatically via RAII, so the existing control flow — process the request, send the result — is untouched.
+
+**Consensus Instrumentation (Medium Intrusiveness):** Consensus is slightly more intrusive because child spans in later phase transitions need the round's context. Beyond the span-start and attribute macros, this requires storing the active context in a new member variable (`currentRoundContext_`) at round start. The existing round logic itself remains unchanged.
+
+---
+
+_Previous: [Design Decisions](./02-design-decisions.md)_ | _Next: [Configuration Reference](./05-configuration-reference.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/05-configuration-reference.md

@@ -0,0 +1,265 @@
+# Configuration Reference
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Implementation Phases](./06-implementation-phases.md)
+
+---
+
+## 5.1 xrpld Configuration
+
+> **OTLP** = OpenTelemetry Protocol | **TxQ** = Transaction Queue
+
+### 5.1.1 Configuration File Section
+
+The authoritative `[telemetry]` example lives in `cfg/xrpld-example.cfg`. Telemetry is disabled by default (`enabled=0`); enabling it turns on distributed tracing for transaction flow, consensus, and RPC calls, with traces exported to an OpenTelemetry Collector over OTLP. Head sampling is intentionally fixed at 1.0 (sample everything) and is not configurable — per-node head-sampling would produce broken/partial distributed traces, so volume reduction is delegated to the collector's tail sampling (see Section 7.4.2). The full option reference follows.
+
+### 5.1.2 Configuration Options Summary
+
+| Option                | Type   | Default                           | Description                                          |
+| --------------------- | ------ | --------------------------------- | ---------------------------------------------------- |
+| `enabled`             | bool   | `false`                           | Enable/disable telemetry                             |
+| `endpoint`            | string | `http://localhost:4318/v1/traces` | OTLP/HTTP collector endpoint                         |
+| `use_tls`             | bool   | `false`                           | Enable TLS for exporter connection                   |
+| `tls_ca_cert`         | string | `""`                              | Path to CA certificate file                          |
+| `batch_size`          | uint   | `512`                             | Spans per export batch                               |
+| `batch_delay_ms`      | uint   | `5000`                            | Max delay before sending batch (ms)                  |
+| `max_queue_size`      | uint   | `2048`                            | Maximum queued spans                                 |
+| `trace_transactions`  | bool   | `true`                            | Enable transaction tracing                           |
+| `trace_consensus`     | bool   | `true`                            | Enable consensus tracing                             |
+| `trace_rpc`           | bool   | `true`                            | Enable RPC tracing                                   |
+| `trace_peer`          | bool   | `true`                            | Enable peer message tracing (high volume)            |
+| `trace_ledger`        | bool   | `true`                            | Enable ledger tracing                                |
+| `service_name`        | string | `"xrpld"`                         | Service name (`service.name`) for traces and metrics |
+| `service_instance_id` | string | `<node_pubkey>`                   | Instance identifier                                  |
+
+**Planned (not yet implemented)**: the following options appear in the design
+documents but are not parsed by `TelemetryConfig.cpp` in Phase 1b and later
+phases. They will be added as the corresponding subsystems are instrumented:
+
+| Option                     | Planned Phase | Purpose                                                                 |
+| -------------------------- | ------------- | ----------------------------------------------------------------------- |
+| `exporter`                 | Future        | Select between OTLP/HTTP and OTLP/gRPC                                  |
+| `trace_pathfind`           | Phase 2       | Path computation tracing toggle                                         |
+| `trace_txq`                | Phase 3       | Transaction queue tracing toggle                                        |
+| `trace_validator`          | Future        | Validator list / manifest update tracing                                |
+| `trace_amendment`          | Future        | Amendment voting tracing                                                |
+| `consensus_trace_strategy` | Phase 4       | Trace ID strategy for consensus rounds (`deterministic` \| `attribute`) |
+
+---
+
+## 5.2 Configuration Parser
+
+> **TxQ** = Transaction Queue
+
+The parser `setupTelemetry()` in `src/libxrpl/telemetry/TelemetryConfig.cpp` reads the `[telemetry]` `Section` and populates a `Telemetry::Setup` struct, applying the defaults listed in Section 5.1.2 via `section.value_or(...)`. It derives `serviceInstanceId` from the node public key when not overridden, selects the exporter endpoint default by exporter type, and leaves the sampling ratio at its fixed 1.0 default (not read from config — see Section 7.4.2).
+
+---
+
+## 5.3 Application Integration
+
+### 5.3.1 ApplicationImp Changes
+
+> **Deferred identity**: The node public key (`nodeIdentity_`) is not
+> available during `ApplicationImp`'s member initializer list — it is
+> resolved later in `setup()`. The `Telemetry` object is therefore
+> constructed with an empty `serviceInstanceId` and patched via
+> `setServiceInstanceId()` once `setup()` has called `getNodeIdentity()`.
+
+`ApplicationImp` (in `src/xrpld/app/main/Application.cpp`) owns a `std::unique_ptr<telemetry::Telemetry> telemetry_`. It is built in the member initializer list via `makeTelemetry(setupTelemetry(...))` 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`,
+> `RCLConsensusAdaptor`) call `app_.getTelemetry()` directly.
+
+---
+
+## 5.4 CMake Integration
+
+> **OTLP** = OpenTelemetry Protocol
+
+### 5.4.1 Find OpenTelemetry Module
+
+A `cmake/FindOpenTelemetry.cmake` module locates the OpenTelemetry C++ SDK. It first tries `find_package(opentelemetry-cpp CONFIG)`, aliasing the imported targets `OpenTelemetry::api`, `OpenTelemetry::sdk`, and `OpenTelemetry::otlp_grpc_exporter`, and falls back to `pkg-config` when no CMake config package is present.
+
+### 5.4.2 CMakeLists.txt Changes
+
+The top-level `CMakeLists.txt` adds an `XRPL_ENABLE_TELEMETRY` option (default `OFF`). When enabled, it runs `find_package(OpenTelemetry REQUIRED)`, defines the `XRPL_ENABLE_TELEMETRY` compile flag, and builds the `xrpl_telemetry` library from the real telemetry sources linked against the OpenTelemetry targets; when disabled, it builds the same target from a no-op `NullTelemetry.cpp` so call sites compile unchanged.
+
+---
+
+## 5.5 OpenTelemetry Collector Configuration
+
+> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring
+
+The authoritative collector config lives in the repo at `docker/telemetry/otel-collector-config.yaml` (with Tempo backend config in `docker/telemetry/tempo.yaml`). The sections below summarize the development and production shapes of that pipeline.
+
+### 5.5.1 Development Configuration
+
+The development collector enables an OTLP receiver on both gRPC (`0.0.0.0:4317`) and HTTP (`0.0.0.0:4318`), a single `batch` processor (1s timeout, batch size 100), and two exporters: a `logging` exporter for console debugging and `otlp/tempo` (insecure) for trace visualization. The single `traces` pipeline wires receiver → batch → both exporters.
+
+### 5.5.2 Production Configuration
+
+The production collector adds TLS on the OTLP gRPC receiver and a richer processor chain: a `memory_limiter` (OOM guard), `batch` (5s timeout, size 512), `tail_sampling`, and an `attributes` processor that hashes sensitive fields (e.g. `tx_account`) and stamps `deployment.environment`. Tail sampling keeps all `ERROR` traces, slow consensus rounds (>5s) and slow RPC requests (>1s), and probabilistically samples the remainder at 10%. Exporters target Grafana Tempo (TLS) and Elastic APM; `health_check` and `zpages` extensions are enabled for operability.
+
+---
+
+## 5.6 Docker Compose Development Environment
+
+> **OTLP** = OpenTelemetry Protocol
+
+The authoritative development stack lives in the repo at `docker/telemetry/docker-compose.yml`. It brings up four services on a shared `xrpld-telemetry` network: an `otel-collector` (otel/opentelemetry-collector-contrib) exposing OTLP gRPC `4317`, OTLP HTTP `4318`, and health check `13133`; `tempo` for trace storage/visualization; `grafana` with provisioned datasources and dashboards (anonymous admin enabled); and an optional `prometheus` for metric correlation.
+
+---
+
+## 5.7 Configuration Architecture
+
+> **OTLP** = OpenTelemetry Protocol
+
+```mermaid
+flowchart TB
+    subgraph config["Configuration Sources"]
+        cfgFile["xrpld.cfg<br/>[telemetry] section"]
+        cmake["CMake<br/>XRPL_ENABLE_TELEMETRY"]
+    end
+
+    subgraph init["Initialization"]
+        parse["setupTelemetry()"]
+        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**: `setupTelemetry()` 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.code=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.code=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(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 +1,575 @@
+# Implementation Phases
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Configuration Reference](./05-configuration-reference.md) | [Observability Backends](./07-observability-backends.md)
+
+---
+
+## 6.1 Phase Overview
+
+> **TxQ** = Transaction Queue
+
+```mermaid
+gantt
+    title OpenTelemetry Implementation Timeline
+    dateFormat  YYYY-MM-DD
+    axisFormat  Week %W
+
+    section Phase 1
+    Core Infrastructure        :p1, 2024-01-01, 2w
+    SDK Integration           :p1a, 2024-01-01, 4d
+    Telemetry Interface       :p1b, after p1a, 3d
+    Configuration & CMake     :p1c, after p1b, 3d
+    Unit Tests                :p1d, after p1c, 2d
+    Buffer & Integration      :p1e, after p1d, 2d
+
+    section Phase 2
+    RPC Tracing               :p2, after p1, 2w
+    HTTP Context Extraction   :p2a, after p1, 2d
+    RPC Handler Instrumentation :p2b, after p2a, 4d
+    PathFinding Instrumentation :p2f, after p2b, 2d
+    TxQ Instrumentation       :p2g, after p2f, 2d
+    WebSocket Support         :p2c, after p2g, 2d
+    Integration Tests         :p2d, after p2c, 2d
+    Buffer & Review           :p2e, after p2d, 4d
+
+    section Phase 3
+    Transaction Tracing       :p3, after p2, 2w
+    Protocol Buffer Extension :p3a, after p2, 2d
+    PeerImp Instrumentation   :p3b, after p3a, 3d
+    Fee Escalation Instrumentation :p3f, after p3b, 2d
+    Relay Context Propagation :p3c, after p3f, 3d
+    Multi-node Tests          :p3d, after p3c, 2d
+    Buffer & Review           :p3e, after p3d, 4d
+
+    section Phase 4
+    Consensus Tracing         :p4, after p3, 2w
+    Consensus Round Spans     :p4a, after p3, 3d
+    Proposal Handling         :p4b, after p4a, 3d
+    Validator List & Manifest Tracing :p4f, after p4b, 2d
+    Amendment Voting Tracing  :p4g, after p4f, 2d
+    SHAMap Sync Tracing       :p4h, after p4g, 2d
+    Validation Tests          :p4c, after p4h, 4d
+    Buffer & Review           :p4e, after p4c, 4d
+
+    section Phase 5
+    Documentation & Deploy    :p5, after p4, 1w
+```
+
+---
+
+## 6.2 Phase 1: Core Infrastructure (Weeks 1-2)
+
+**Objective**: Establish foundational telemetry infrastructure
+
+### Tasks
+
+| Task | Description                                           |
+| ---- | ----------------------------------------------------- |
+| 1.1  | Add OpenTelemetry C++ SDK to Conan/CMake              |
+| 1.2  | Implement `Telemetry` interface and factory           |
+| 1.3  | Implement `SpanGuard` RAII wrapper                    |
+| 1.4  | Implement configuration parser                        |
+| 1.5  | Integrate into `ApplicationImp`                       |
+| 1.6  | Add conditional compilation (`XRPL_ENABLE_TELEMETRY`) |
+| 1.7  | Create `NullTelemetry` no-op implementation           |
+| 1.8  | Unit tests for core infrastructure                    |
+
+### Exit Criteria
+
+- [ ] OpenTelemetry SDK compiles and links
+- [ ] Telemetry can be enabled/disabled via config
+- [ ] Basic span creation works
+- [ ] No performance regression when disabled
+- [ ] Unit tests passing
+
+---
+
+## 6.3 Phase 2: RPC Tracing (Weeks 3-4)
+
+> **TxQ** = Transaction Queue
+
+**Objective**: Complete tracing for all RPC operations
+
+### Tasks
+
+| Task | Description                                                                |
+| ---- | -------------------------------------------------------------------------- |
+| 2.1  | Implement W3C Trace Context HTTP header extraction                         |
+| 2.2  | Instrument `ServerHandler::onRequest()`                                    |
+| 2.3  | Instrument `RPCHandler::doCommand()`                                       |
+| 2.4  | Add RPC-specific attributes                                                |
+| 2.5  | Instrument WebSocket handler                                               |
+| 2.6  | PathFinding instrumentation (`pathfind.request`, `pathfind.compute` spans) |
+| 2.7  | TxQ instrumentation (`txq.enqueue`, `txq.apply` spans)                     |
+| 2.8  | Integration tests for RPC tracing                                          |
+| 2.9  | Performance benchmarks                                                     |
+| 2.10 | Documentation                                                              |
+
+### Exit Criteria
+
+- [ ] All RPC commands traced
+- [ ] Trace context propagates from HTTP headers
+- [ ] WebSocket and HTTP both instrumented
+- [ ] <1ms overhead per RPC call
+- [ ] Integration tests passing
+
+---
+
+## 6.4 Phase 3: Transaction Tracing (Weeks 5-6)
+
+**Objective**: Trace transaction lifecycle across network
+
+### Tasks
+
+| Task | Description                                          |
+| ---- | ---------------------------------------------------- |
+| 3.1  | Define `TraceContext` Protocol Buffer message        |
+| 3.2  | Implement protobuf context serialization             |
+| 3.3  | Instrument `PeerImp::handleTransaction()`            |
+| 3.4  | Instrument `NetworkOPs::submitTransaction()`         |
+| 3.5  | Instrument HashRouter integration                    |
+| 3.6  | Fee escalation instrumentation (`fee.escalate` span) |
+| 3.7  | Implement relay context propagation                  |
+| 3.8  | Integration tests (multi-node)                       |
+| 3.9  | Performance benchmarks                               |
+
+### Exit Criteria
+
+- [ ] Transaction traces span across nodes
+- [ ] Trace context in Protocol Buffer messages
+- [ ] HashRouter deduplication visible in traces
+- [ ] Multi-node integration tests passing
+- [ ] <5% overhead on transaction throughput
+
+---
+
+## 6.5 Phase 4: Consensus Tracing (Weeks 7-8)
+
+**Objective**: Full observability into consensus rounds
+
+### Tasks
+
+| Task | Description                                    |
+| ---- | ---------------------------------------------- |
+| 4.1  | Instrument `RCLConsensusAdaptor::startRound()` |
+| 4.2  | Instrument phase transitions                   |
+| 4.3  | Instrument proposal handling                   |
+| 4.4  | Instrument validation handling                 |
+| 4.5  | Add consensus-specific attributes              |
+| 4.6  | Correlate with transaction traces              |
+| 4.7  | Validator list and manifest tracing            |
+| 4.8  | Amendment voting tracing                       |
+| 4.9  | SHAMap sync tracing                            |
+| 4.10 | Multi-validator integration tests              |
+| 4.11 | Performance validation                         |
+
+### Exit Criteria
+
+- [ ] Complete consensus round traces
+- [ ] Phase transitions visible
+- [ ] Proposals and validations traced
+- [ ] No impact on consensus timing
+- [ ] Multi-validator test network validated
+
+### Implementation Status — Phase 4a Plan
+
+Phase 4a (establish-phase gap fill & cross-node correlation) will add:
+
+- **Deterministic trace ID** derived from `previousLedger.id()` so all validators
+  in the same round share the same `trace_id` (switchable via
+  `consensus_trace_strategy` config: `"deterministic"` or `"attribute"`).
+  See [Configuration Reference](./05-configuration-reference.md) for full
+  configuration options.
+- **Round lifecycle spans**: `consensus.round` with round-to-round span links.
+- **Establish phase**: `consensus.establish`, `consensus.update_positions` (with
+  `dispute.resolve` events), `consensus.check` (with threshold tracking).
+- **Mode changes**: `consensus.mode_change` spans.
+- **Validation**: `consensus.validation.send` with span link to round span
+  (thread-safe cross-thread access via `roundSpanContext_` snapshot).
+- **Separation of concerns**: telemetry extracted to private helpers
+  (`startRoundTracing`, `createValidationSpan`, `startEstablishTracing`,
+  `updateEstablishTracing`, `endEstablishTracing`).
+
+The `Phase4_taskList.md` spec document is introduced in the Phase 2 PR (#6424)
+and will contain the full task breakdown and implementation notes.
+
+---
+
+## 6.6 Phase 5: Documentation & Deployment (Week 9)
+
+**Objective**: Production readiness
+
+### Tasks
+
+| Task | Description                   |
+| ---- | ----------------------------- |
+| 5.1  | Operator runbook              |
+| 5.2  | Grafana dashboards            |
+| 5.3  | Alert definitions             |
+| 5.4  | Collector deployment examples |
+| 5.5  | Developer documentation       |
+| 5.6  | Training materials            |
+| 5.7  | Final integration testing     |
+
+---
+
+## 6.7 Risk Assessment
+
+```mermaid
+quadrantChart
+    title Risk Assessment Matrix
+    x-axis Low Impact --> High Impact
+    y-axis Low Likelihood --> High Likelihood
+    quadrant-1 Mitigate Immediately
+    quadrant-2 Plan Mitigation
+    quadrant-3 Accept Risk
+    quadrant-4 Monitor Closely
+
+    SDK Compat: [0.2, 0.18]
+    Protocol Chg: [0.75, 0.72]
+    Perf Overhead: [0.58, 0.42]
+    Context Prop: [0.4, 0.55]
+    Memory Leaks: [0.85, 0.25]
+```
+
+### Risk Details
+
+| Risk                                 | Likelihood | Impact | Mitigation                              |
+| ------------------------------------ | ---------- | ------ | --------------------------------------- |
+| Protocol changes break compatibility | Medium     | High   | Use high field numbers, optional fields |
+| Performance overhead unacceptable    | Medium     | Medium | Sampling, conditional compilation       |
+| Context propagation complexity       | Medium     | Medium | Phased rollout, extensive testing       |
+| SDK compatibility issues             | Low        | Medium | Pin SDK version, fallback to no-op      |
+| Memory leaks in long-running nodes   | Low        | High   | Memory profiling, bounded queues        |
+
+---
+
+## 6.8 Success Metrics
+
+| Metric                   | Target                                                         | Measurement           |
+| ------------------------ | -------------------------------------------------------------- | --------------------- |
+| Trace coverage           | >95% of transaction code paths (independent of sampling ratio) | Sampling verification |
+| CPU overhead             | <3%                                                            | Benchmark tests       |
+| Memory overhead          | <10 MB                                                         | Memory profiling      |
+| Latency impact (p99)     | <2%                                                            | Performance tests     |
+| Trace completeness       | >99% spans with required attrs                                 | Validation script     |
+| Cross-node trace linkage | >90% of multi-hop transactions                                 | Integration tests     |
+
+---
+
+## 6.9 Quick Wins and Crawl-Walk-Run Strategy
+
+> **TxQ** = Transaction Queue
+
+This section outlines a prioritized approach to maximize ROI with minimal initial investment.
+
+### 6.9.1 Crawl-Walk-Run Overview
+
+<div align="center">
+
+```mermaid
+flowchart TB
+    subgraph crawl["🐢 CRAWL (Week 1-2)"]
+        direction LR
+        c1[Core SDK Setup] ~~~ c2[RPC Tracing Only] ~~~ c3[PathFinding + TxQ Tracing] ~~~ c4[Single Node]
+    end
+
+    subgraph walk["🚶 WALK (Week 3-5)"]
+        direction LR
+        w1[Transaction Tracing] ~~~ w2[Fee Escalation Tracing] ~~~ w3[Cross-Node Context] ~~~ w4[Basic Dashboards]
+    end
+
+    subgraph run["🏃 RUN (Week 6-9)"]
+        direction LR
+        r1[Consensus Tracing] ~~~ r2[Validator, Amendment,<br/>SHAMap Tracing] ~~~ r3[Full Correlation] ~~~ r4[Production Deploy]
+    end
+
+    crawl --> walk --> run
+
+    style crawl fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style walk fill:#bf360c,stroke:#8c2809,color:#fff
+    style run fill:#0d47a1,stroke:#082f6a,color:#fff
+    style c1 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style c2 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style c3 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style c4 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style w1 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style w2 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style w3 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style w4 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
+    style r1 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style r2 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style r3 fill:#0d47a1,stroke:#082f6a,color:#fff
+    style r4 fill:#0d47a1,stroke:#082f6a,color:#fff
+```
+
+</div>
+
+**Reading the diagram:**
+
+- **CRAWL (Weeks 1-2)**: Minimal investment -- set up the SDK, instrument RPC and PathFinding/TxQ handlers, and verify on a single node. Delivers immediate latency visibility.
+- **WALK (Weeks 3-5)**: Expand to transaction lifecycle tracing, fee escalation, cross-node context propagation, and basic Grafana dashboards. This is where distributed tracing starts working.
+- **RUN (Weeks 6-9)**: Full consensus instrumentation, validator/amendment/SHAMap tracing, end-to-end correlation, and production deployment with sampling and alerting.
+- **Arrows (crawl → walk → run)**: Each phase builds on the prior one; you cannot skip ahead because later phases depend on infrastructure established earlier.
+
+### 6.9.2 Quick Wins (Immediate Value)
+
+| Quick Win                      | Value  | When to Deploy |
+| ------------------------------ | ------ | -------------- |
+| **RPC Command Tracing**        | High   | Week 2         |
+| **RPC Latency Histograms**     | High   | Week 2         |
+| **Error Rate Dashboard**       | Medium | Week 2         |
+| **Transaction Submit Tracing** | High   | Week 3         |
+| **Consensus Round Duration**   | Medium | Week 6         |
+
+### 6.9.3 CRAWL Phase (Weeks 1-2)
+
+**Goal**: Get basic tracing working with minimal code changes.
+
+**What You Get**:
+
+- RPC request/response traces for all commands
+- Latency breakdown per RPC command
+- PathFinding and TxQ tracing (directly impacts RPC latency)
+- Error visibility with stack traces
+- Basic Grafana dashboard
+
+**Code Changes**: ~15 lines in `ServerHandler.cpp`, ~40 lines in new telemetry module
+
+**Why Start Here**:
+
+- RPC is the lowest-risk, highest-visibility component
+- PathFinding and TxQ are RPC-adjacent and directly affect latency
+- Immediate value for debugging client issues
+- No cross-node complexity
+- Single file modification to existing code
+
+### 6.9.4 WALK Phase (Weeks 3-5)
+
+**Goal**: Add transaction lifecycle tracing across nodes.
+
+**What You Get**:
+
+- End-to-end transaction traces from submit to relay
+- Fee escalation tracing within the transaction pipeline
+- Cross-node correlation (see transaction path)
+- HashRouter deduplication visibility
+- Relay latency metrics
+
+**Code Changes**: ~120 lines across 4 files, plus protobuf extension
+
+**Why Do This Second**:
+
+- Builds on RPC tracing (transactions submitted via RPC)
+- Fee escalation is integral to the transaction processing pipeline
+- Moderate complexity (requires context propagation)
+- High value for debugging transaction issues
+
+### 6.9.5 RUN Phase (Weeks 6-9)
+
+**Goal**: Full observability including consensus.
+
+**What You Get**:
+
+- Complete consensus round visibility
+- Phase transition timing
+- Validator proposal tracking
+- Validator list and manifest tracing
+- Amendment voting tracing
+- SHAMap sync tracing
+- Full end-to-end traces (client → RPC → TX → consensus → ledger)
+
+**Code Changes**: ~100 lines across 3 consensus files, plus validator/amendment/SHAMap modules
+
+**Why Do This Last**:
+
+- Highest complexity (consensus is critical path)
+- Validator, amendment, and SHAMap components are lower priority
+- Requires thorough testing
+- Lower relative value (consensus issues are rarer)
+
+### 6.9.6 ROI Prioritization Matrix
+
+```mermaid
+quadrantChart
+    title Implementation ROI Matrix
+    x-axis Low Effort --> High Effort
+    y-axis Low Value --> High Value
+    quadrant-1 Quick Wins - Do First
+    quadrant-2 Major Projects - Plan Carefully
+    quadrant-3 Nice to Have - Optional
+    quadrant-4 Time Sinks - Avoid
+
+    RPC Tracing: [0.15, 0.92]
+    TX Submit Trace: [0.3, 0.78]
+    TX Relay Trace: [0.5, 0.88]
+    Consensus Trace: [0.72, 0.72]
+    Peer Msg Trace: [0.85, 0.3]
+    Ledger Acquire: [0.55, 0.52]
+```
+
+---
+
+## 6.10 Definition of Done
+
+> **TxQ** = Transaction Queue | **HA** = High Availability
+
+Clear, measurable criteria for each phase.
+
+### 6.10.1 Phase 1: Core Infrastructure
+
+| Criterion       | Measurement                                                | Target                       |
+| --------------- | ---------------------------------------------------------- | ---------------------------- |
+| SDK Integration | `cmake --build` succeeds with `-DXRPL_ENABLE_TELEMETRY=ON` | ✅ Compiles                  |
+| Runtime Toggle  | `enabled=0` produces zero overhead                         | <0.1% CPU difference         |
+| Span Creation   | Unit test creates and exports span                         | Span appears in Tempo        |
+| Configuration   | All config options parsed correctly                        | Config validation tests pass |
+| Documentation   | Developer guide exists                                     | PR approved                  |
+
+**Definition of Done**: All criteria met, PR merged, no regressions in CI.
+
+### 6.10.2 Phase 2: RPC Tracing
+
+| Criterion          | Measurement                        | Target                     |
+| ------------------ | ---------------------------------- | -------------------------- |
+| Coverage           | All RPC commands instrumented      | 100% of commands           |
+| Context Extraction | traceparent header propagates      | Integration test passes    |
+| Attributes         | Command, status, duration recorded | Validation script confirms |
+| Performance        | RPC latency overhead               | <1ms p99                   |
+| Dashboard          | Grafana dashboard deployed         | Screenshot in docs         |
+
+**Definition of Done**: RPC traces visible in Tempo for all commands, dashboard shows latency distribution.
+
+### 6.10.3 Phase 3: Transaction Tracing
+
+| Criterion        | Measurement                     | Target                             |
+| ---------------- | ------------------------------- | ---------------------------------- |
+| Local Trace      | Submit → validate → TxQ traced  | Single-node test passes            |
+| Cross-Node       | Context propagates via protobuf | Multi-node test passes             |
+| Relay Visibility | relay_count attribute correct   | Spot check 100 txs                 |
+| HashRouter       | Deduplication visible in trace  | Duplicate txs show suppressed=true |
+| Performance      | TX throughput overhead          | <5% degradation                    |
+
+**Definition of Done**: Transaction traces span 3+ nodes in test network, performance within bounds.
+
+### 6.10.4 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.code=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). Privacy protection includes account hashing, configurable redaction, sampling, and collector-level filtering. Node operators retain full control over telemetry configuration.
+
+➡️ **[Read full Design Decisions](./02-design-decisions.md)**
+
+---
+
+## 3. Implementation Strategy
+
+The telemetry code is organized under `include/xrpl/telemetry/` for headers and `src/libxrpl/telemetry/` for implementation. Key principles include RAII-based span management via `SpanGuard` (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 `setupTelemetry` 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 +1,245 @@
+# 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`)
+
+> **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. `tx_hash`, `peer_id`); the `*SpanNames.h` constants are
+> the single source of truth.
+
+### 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: `xrpl.tx.hash`, `xrpl.peer.id`, `xrpl.tx.status`
+    - On HashRouter suppression (duplicate): set `xrpl.tx.suppressed=true`, add `tx.duplicate` event
+    - Wrap validation call with child span `tx.validate`
+    - Wrap relay with `tx.relay` span
+  - When relaying to peers:
+    - Inject current trace context into outgoing `TMTransaction::trace_context`
+    - Set `xrpl.tx.relay_count` attribute
+
+- Include `TracingInstrumentation.h` and use `XRPL_TRACE_TX` macro
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Full PeerImp instrumentation example
+- [01-architecture-analysis.md §1.3](./01-architecture-analysis.md) — Transaction flow diagram
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.receive trace point
+
+---
+
+## Task 3.4: Instrument NetworkOPs Transaction Processing
+
+**Objective**: Trace the transaction processing pipeline in NetworkOPs, covering both sync and async paths.
+
+**What to do**:
+
+- Edit `src/xrpld/app/misc/NetworkOPs.cpp`:
+  - In `processTransaction()`:
+    - Create `tx.process` span
+    - Set attributes: `xrpl.tx.hash`, `xrpl.tx.type`, `xrpl.tx.local` (whether from RPC or peer)
+    - Record whether sync or async path is taken
+
+  - In `doTransactionAsync()`:
+    - Capture parent context before queuing
+    - Create `tx.queue` span with queue depth attribute
+    - Add event when transaction is dequeued for processing
+
+  - In `doTransactionSync()`:
+    - Create `tx.process_sync` span
+    - Record result (applied, queued, rejected)
+
+**Key modified files**:
+
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+**Reference**:
+
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.validate and tx.process trace points
+- [02-design-decisions.md §2.4.3](./02-design-decisions.md) — Transaction attribute schema
+
+---
+
+## Task 3.5: Instrument HashRouter for Dedup Visibility
+
+**Objective**: Make transaction deduplication visible in traces by recording HashRouter decisions as span attributes/events.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp` (in handleTransaction):
+  - After calling `HashRouter::shouldProcess()` or `addSuppressionPeer()`:
+    - Record `xrpl.tx.suppressed` attribute (true/false)
+    - Record `xrpl.tx.flags` showing current HashRouter state (SAVED, TRUSTED, etc.)
+    - Add `tx.first_seen` or `tx.duplicate` event
+
+- This is NOT a modification to HashRouter itself — just recording its decisions as span attributes in the existing PeerImp instrumentation from Task 3.3.
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp` (same changes as 3.3, logically grouped)
+
+---
+
+## Task 3.6: Context Propagation in Transaction Relay
+
+**Objective**: Ensure trace context flows correctly when transactions are relayed between peers, creating linked spans across nodes.
+
+**What to do**:
+
+- Verify the relay path injects trace context:
+  - When `PeerImp` relays a transaction, the `TMTransaction` message should carry `trace_context`
+  - When a remote peer receives it, the context is extracted and used as parent
+
+- Test context propagation:
+  - Manually verify with 2+ node setup that trace IDs match across nodes
+  - Confirm parent-child span relationships are correct in Tempo
+
+- Handle edge cases:
+  - Missing trace context (older peers): create new root span
+  - Corrupted trace context: log warning, create new root span
+  - Sampled-out traces: respect trace flags
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+- `src/xrpld/overlay/detail/OverlayImpl.cpp` (if relay method needs context param)
+
+**Reference**:
+
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — Context propagation design
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Relay context injection pattern
+
+---
+
+## Task 3.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 3 changes compile and work correctly.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions
+3. Run existing unit tests
+4. Verify protobuf regeneration produces correct C++ code
+5. Document any issues encountered
+
+**Verification Checklist**:
+
+- [ ] Protobuf changes generate valid C++
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass
+- [ ] No undefined symbols from new telemetry calls
+
+---
+
+## 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    |
+
+**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.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.3](./06-implementation-phases.md)):
+
+- [ ] Transaction traces span across nodes
+- [ ] Trace context in Protocol Buffer messages
+- [ ] HashRouter deduplication visible in traces
+- [ ] <5% overhead on transaction throughput

OpenTelemetryPlan/Phase4_taskList.md

@@ -0,0 +1,228 @@
+# 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.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - In `RCLConsensus::startRound()` (or the Adaptor's startRound):
+    - Create `consensus.round` span using `XRPL_TRACE_CONSENSUS` macro
+    - Set attributes:
+      - `xrpl.consensus.ledger.prev` — previous ledger hash
+      - `xrpl.consensus.ledger.seq` — target ledger sequence
+      - `xrpl.consensus.proposers` — number of trusted proposers
+      - `xrpl.consensus.mode` — "proposing" or "observing"
+    - Store the span context for use by child spans in phase transitions
+
+- Add a member to hold current round trace context:
+  - `opentelemetry::context::Context currentRoundContext_` (guarded by `#ifdef`)
+  - Updated at round start, used by phase transition spans
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/consensus/RCLConsensus.h` (add context member)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — startRound instrumentation example
+- [01-architecture-analysis.md §1.4](./01-architecture-analysis.md) — Consensus round flow
+
+---
+
+## Task 4.2: Instrument Phase Transitions
+
+**Objective**: Create child spans for each consensus phase (open, establish, accept) to show timing breakdown.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - Identify where phase transitions occur (the `Consensus<Adaptor>` template drives this)
+  - For each phase entry:
+    - Create span as child of `currentRoundContext_`: `consensus.phase.open`, `consensus.phase.establish`, `consensus.phase.accept`
+    - Set `xrpl.consensus.phase` attribute
+    - Add `phase.enter` event at start, `phase.exit` event at end
+    - Record phase duration in milliseconds
+
+  - In the `onClose` adaptor method:
+    - Create `consensus.ledger_close` span
+    - Set attributes: close_time, mode, transaction count in initial position
+
+  - Note: The Consensus template class in `include/xrpl/consensus/Consensus.h` drives phase transitions — check if instrumentation goes there or in the Adaptor
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- Possibly `include/xrpl/consensus/Consensus.h` (for template-level phase tracking)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — phaseTransition instrumentation
+
+---
+
+## Task 4.3: Instrument Proposal Handling
+
+**Objective**: Trace proposal send and receive to show validator coordination.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - In `Adaptor::propose()`:
+    - Create `consensus.proposal.send` span
+    - Set attributes: `xrpl.consensus.round` (proposal sequence), proposal hash
+    - Inject trace context into outgoing `TMProposeSet::trace_context` (from Phase 3 protobuf)
+
+  - In `Adaptor::peerProposal()` (or wherever peer proposals are received):
+    - Extract trace context from incoming `TMProposeSet::trace_context`
+    - Create `consensus.proposal.receive` span as child of extracted context
+    - Set attributes: `xrpl.consensus.proposer` (node ID), `xrpl.consensus.round`
+
+  - In `Adaptor::share(RCLCxPeerPos)`:
+    - Create `consensus.proposal.relay` span for relaying peer proposals
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — peerProposal instrumentation
+- [02-design-decisions.md §2.4.4](./02-design-decisions.md) — Consensus attribute schema
+
+---
+
+## Task 4.4: Instrument Validation Handling
+
+**Objective**: Trace validation send and receive to show ledger validation flow.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp` (or the validation handler):
+  - When sending our validation:
+    - Create `consensus.validation.send` span
+    - Set attributes: validated ledger hash, sequence, signing time
+
+  - When receiving a peer validation:
+    - Extract trace context from `TMValidation::trace_context` (if present)
+    - Create `consensus.validation.receive` span
+    - Set attributes: `xrpl.consensus.validator` (node ID), ledger hash
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp` (if validation handling is here)
+
+---
+
+## Task 4.5: Add Consensus-Specific Attributes
+
+**Objective**: Enrich consensus spans with detailed attributes for debugging and analysis.
+
+**What to do**:
+
+- Review all consensus spans and ensure they include:
+  - `xrpl.consensus.ledger.seq` — target ledger sequence number
+  - `xrpl.consensus.round` — consensus round number
+  - `xrpl.consensus.mode` — proposing/observing/wrongLedger
+  - `xrpl.consensus.phase` — current phase name
+  - `xrpl.consensus.phase_duration_ms` — time spent in phase
+  - `xrpl.consensus.proposers` — number of trusted proposers
+  - `xrpl.consensus.tx_count` — transactions in proposed set
+  - `xrpl.consensus.disputes` — number of disputed transactions
+  - `xrpl.consensus.converge_percent` — convergence percentage
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Task 4.6: Correlate Transaction and Consensus Traces
+
+**Objective**: Link transaction traces from Phase 3 with consensus traces so you can follow a transaction from submission through consensus into the ledger.
+
+**What to do**:
+
+- In `onClose()` or `onAccept()`:
+  - When building the consensus position, link the round span to individual transaction spans using span links (if OTel SDK supports it) or events
+  - At minimum, record the transaction hashes included in the consensus set as span events: `tx.included` with `xrpl.tx.hash` attribute
+
+- In `processTransactionSet()` (NetworkOPs):
+  - If the consensus round span context is available, create child spans for each transaction applied to the ledger
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+---
+
+## Task 4.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 4 changes compile and don't affect consensus timing.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions (critical for consensus code)
+3. Run existing consensus-related unit tests
+4. Verify that all macros expand to no-ops when disabled
+5. Check that no consensus-critical code paths are affected by instrumentation overhead
+
+**Verification Checklist**:
+
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing consensus tests pass
+- [ ] No new includes in consensus headers when telemetry is OFF
+- [ ] Phase timing instrumentation doesn't use blocking operations
+
+---
+
+## Summary
+
+| Task | Description                           | New Files | Modified Files | Depends On    |
+| ---- | ------------------------------------- | --------- | -------------- | ------------- |
+| 4.1  | Consensus round start instrumentation | 0         | 2              | Phase 3       |
+| 4.2  | Phase transition instrumentation      | 0         | 1-2            | 4.1           |
+| 4.3  | Proposal handling instrumentation     | 0         | 1              | 4.1           |
+| 4.4  | Validation handling instrumentation   | 0         | 1-2            | 4.1           |
+| 4.5  | Consensus-specific attributes         | 0         | 1              | 4.2, 4.3, 4.4 |
+| 4.6  | Transaction-consensus correlation     | 0         | 2              | 4.2, Phase 3  |
+| 4.7  | Build verification and testing        | 0         | 0              | 4.1-4.6       |
+
+**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.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.4](./06-implementation-phases.md)):
+
+- [ ] Complete consensus round traces
+- [ ] Phase transitions visible
+- [ ] Proposals and validations traced
+- [ ] No impact on consensus timing

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: xrpl.rpc.command
+          - name: xrpl.rpc.status
+          - name: xrpl.consensus.phase
+          - name: xrpl.tx.type
+    ```
+  - Add `prometheus` exporter:
+    ```yaml
+    exporters:
+      prometheus:
+        endpoint: 0.0.0.0:8889
+    ```
+  - Wire the pipeline:
+    ```yaml
+    service:
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [debug, otlp/tempo, spanmetrics]
+        metrics:
+          receivers: [spanmetrics]
+          exporters: [prometheus]
+    ```
+
+- Edit `docker/telemetry/docker-compose.yml`:
+  - Expose port `8889` on the collector for Prometheus scraping
+  - Add Prometheus service
+  - Add Prometheus as Grafana datasource
+
+**Key modified files**:
+
+- `docker/telemetry/otel-collector-config.yaml`
+- `docker/telemetry/docker-compose.yml`
+
+**Key new files**:
+
+- `docker/telemetry/prometheus.yml` (Prometheus scrape config)
+- `docker/telemetry/grafana/provisioning/datasources/prometheus.yaml`
+
+**Reference**:
+
+- [POC_taskList.md §Next Steps](./POC_taskList.md) — Metrics pipeline for Grafana dashboards
+
+---
+
+## Task 5.2: Create Grafana Dashboards
+
+**Objective**: Provide pre-built Grafana dashboards for RPC performance, transaction lifecycle, and consensus health.
+
+**What to do**:
+
+- Create `docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml` (provisioning config)
+- Create dashboard JSON files:
+  1. **RPC Performance Dashboard** (`rpc-performance.json`):
+     - RPC request latency (p50/p95/p99) by command — histogram panel
+     - RPC throughput (requests/sec) by command — time series
+     - RPC error rate by command — bar gauge
+     - Top slowest RPC commands — table
+
+  2. **Transaction Overview Dashboard** (`transaction-overview.json`):
+     - Transaction processing rate — time series
+     - Transaction latency distribution — histogram
+     - Suppression rate (duplicates) — stat panel
+     - Transaction processing path (sync vs async) — pie chart
+
+  3. **Consensus Health Dashboard** (`consensus-health.json`):
+     - Consensus round duration — time series
+     - Phase duration breakdown (open/establish/accept) — stacked bar
+     - Proposals sent/received per round — stat panel
+     - Consensus mode distribution (proposing/observing) — pie chart
+
+- Store dashboards in `docker/telemetry/grafana/dashboards/`
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml`
+- `docker/telemetry/grafana/dashboards/rpc-performance.json`
+- `docker/telemetry/grafana/dashboards/transaction-overview.json`
+- `docker/telemetry/grafana/dashboards/consensus-health.json`
+
+**Reference**:
+
+- [07-observability-backends.md §7.6](./07-observability-backends.md) — Grafana dashboard specifications
+- [01-architecture-analysis.md §1.8.3](./01-architecture-analysis.md) — Dashboard panel examples
+
+---
+
+## Task 5.3: Define Alert Rules
+
+**Objective**: Create alert definitions for key telemetry anomalies.
+
+**What to do**:
+
+- Create `docker/telemetry/grafana/provisioning/alerting/alerts.yaml`:
+  - **RPC Latency Alert**: p99 latency > 1s for any command over 5 minutes
+  - **RPC Error Rate Alert**: Error rate > 5% for any command over 5 minutes
+  - **Consensus Duration Alert**: Round duration > 10s (warn), > 30s (critical)
+  - **Transaction Processing Alert**: Processing rate drops below threshold
+  - **Telemetry Pipeline Health**: No spans received for > 2 minutes
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/alerting/alerts.yaml`
+
+**Reference**:
+
+- [07-observability-backends.md §7.6.3](./07-observability-backends.md) — Alert rule definitions
+
+---
+
+## Task 5.4: Production Collector Configuration
+
+**Objective**: Create a production-ready OTel Collector configuration with tail-based sampling and resource limits.
+
+**What to do**:
+
+- Create `docker/telemetry/otel-collector-config-production.yaml`:
+  - Tail-based sampling policy:
+    - Always sample errors and slow traces
+    - 10% base sampling rate for normal traces
+    - Always sample first trace for each unique RPC command
+  - Resource limits:
+    - Memory limiter processor (80% of available memory)
+    - Queued retry for export failures
+  - TLS configuration for production endpoints
+  - Health check endpoint
+
+**Key new files**:
+
+- `docker/telemetry/otel-collector-config-production.yaml`
+
+**Reference**:
+
+- [05-configuration-reference.md §5.5.2](./05-configuration-reference.md) — Production collector config
+
+---
+
+## Task 5.5: Operator Runbook
+
+**Objective**: Create operator documentation for managing the telemetry system in production.
+
+**What to do**:
+
+- Create `docs/telemetry-runbook.md`:
+  - **Setup**: How to enable telemetry in 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

cfg/xrpld-example.cfg

@@ -1621,3 +1621,96 @@ 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`. Uniquely identifies
+#   this node. Default: the node's public key (auto-detected).
+#
+# endpoint=http://localhost:4318/v1/traces
+#
+#   The OTLP/HTTP exporter endpoint. The server sends trace data as
+#   protobuf-encoded HTTP POST requests to this URL.
+#   Default: http://localhost:4318/v1/traces.
+#
+# --- TLS settings for the OTLP exporter connection ---
+#
+# use_tls=0
+#
+#   Enable TLS for the OTLP/HTTP exporter connection. Default: 0 (off).
+#
+# tls_ca_cert=
+#
+#   Path to a PEM-encoded CA certificate bundle for TLS verification.
+#   Only used when use_tls=1. Default: empty (system CA store).
+#
+#   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.
+#
+# --- Batch processor tuning ---
+#
+# batch_size=512
+#
+#   Maximum number of spans exported in a single batch. Default: 512.
+#
+# batch_delay_ms=5000
+#
+#   Maximum delay (milliseconds) before a partial batch is flushed.
+#   Default: 5000 (5 seconds).
+#
+# max_queue_size=2048
+#
+#   Maximum number of spans queued in memory before drops occur.
+#   Default: 2048.
+#

cmake/XrplCore.cmake

@@ -201,6 +201,26 @@ target_link_libraries(
 add_module(xrpl tx)
 target_link_libraries(xrpl.libxrpl.tx PUBLIC xrpl.libxrpl.ledger)
 
+# Telemetry module — OpenTelemetry distributed tracing support.
+# Sources: include/xrpl/telemetry/ (headers), src/libxrpl/telemetry/ (impl).
+# When telemetry=ON, links the Conan-provided umbrella target
+# opentelemetry-cpp::opentelemetry-cpp (individual component targets like
+# ::api, ::sdk are not available in the Conan package).
+#
+# Links xrpl.libxrpl.protocol PRIVATELY for sha512Half (digest.h)
+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()
+
 add_library(xrpl.libxrpl)
 set_target_properties(xrpl.libxrpl PROPERTIES OUTPUT_NAME xrpl)
 
@@ -233,6 +253,7 @@ target_link_modules(
     resource
     server
     shamap
+    telemetry
     tx
 )
 

conan.lock

@@ -10,11 +10,14 @@
         "rocksdb/10.5.1#4a197eca381a3e5ae8adf8cffa5aacd0%1782392413.075713",
         "re2/20251105#8579cfd0bda4daf0683f9e3898f964b4%1782392402.431897",
         "protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81%1782392410.233933",
+        "opentelemetry-cpp/1.26.0#9d81768342c78cb897345fd419b358d2%1776934712.672",
         "openssl/3.6.3#1163d4ddc603907084d08a6a0c6e580f%1782307150.583886",
         "nudb/2.0.9#11149c73f8f2baff9a0198fe25971fc7%1782392402.297166",
+        "nlohmann_json/3.11.3#45828be26eb619a2e04ca517bb7b828d%1701220705.259",
         "mpt-crypto/0.4.0-rc2#a580f2f9ad0e795de696aa62d54fb9af%1782425834.488828",
         "lz4/1.10.0#982d9b673900f665a1da109e09c17cab%1782392402.164188",
         "libiconv/1.17#9923bc6dc6f106646d6967e0039a5ada%1782392792.775744",
+        "libcurl/8.20.0#c90b0c91a33d9a79b519c1c70bafc823%1780907438.587",
         "libbacktrace/cci.20210118#a7691bfccd8caaf66309df196790a5a1%1782392402.420732",
         "libarchive/3.8.7#c446109bd1f1d8ba7936c94189bc50e6%1782392403.066892",
         "jemalloc/5.3.1#1fc58d55316041f10fbc1e8a2eae632a%1776700028.228",
@@ -31,9 +34,15 @@
         "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",
+        "meson/1.10.2#9d2d10681fe7fe61c788c58626c89b25%1775558003.754",
         "m4/1.4.19#34c4bbc3eeebe98ca6edf2f52d602e7d%1777282960.259",
+        "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",
@@ -59,6 +68,9 @@
         ],
         "lz4/[>=1.9.4 <2]": [
             "lz4/1.10.0#982d9b673900f665a1da109e09c17cab"
+        ],
+        "protobuf/[>=4.25.3 <7]": [
+            "protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81"
         ]
     },
     "config_requires": []

conan/profiles/default

@@ -25,3 +25,18 @@ compiler.libcxx={{ detect_api.detect_libcxx(compiler, version, compiler_exe) }}
 {# 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 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

@@ -21,6 +21,7 @@ class Xrpl(ConanFile):
         "rocksdb": [True, False],
         "shared": [True, False],
         "static": [True, False],
+        "telemetry": [True, False],
         "tests": [True, False],
         "unity": [True, False],
         "xrpld": [True, False],
@@ -52,6 +53,7 @@ class Xrpl(ConanFile):
         "rocksdb": True,
         "shared": False,
         "static": True,
+        "telemetry": True,
         "tests": False,
         "unity": False,
         "xrpld": False,
@@ -140,6 +142,10 @@ class Xrpl(ConanFile):
             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/1.26.0")
         self.requires("xxhash/0.8.3", transitive_headers=True)
 
     exports_sources = (
@@ -168,6 +174,7 @@ class Xrpl(ConanFile):
         tc.variables["rocksdb"] = self.options.rocksdb
         tc.variables["BUILD_SHARED_LIBS"] = self.options.shared
         tc.variables["static"] = self.options.static
+        tc.variables["telemetry"] = self.options.telemetry
         tc.variables["unity"] = self.options.unity
         tc.variables["xrpld"] = self.options.xrpld
         tc.generate()
@@ -221,3 +228,5 @@ class Xrpl(ConanFile):
         ]
         if self.options.rocksdb:
             libxrpl.requires.append("rocksdb::librocksdb")
+        if self.options.telemetry:
+            libxrpl.requires.append("opentelemetry-cpp::opentelemetry-cpp")

docker/telemetry/docker-compose.yml

@@ -0,0 +1,80 @@
+# Docker Compose stack for xrpld OpenTelemetry observability.
+#
+# Provides services for local development:
+#   - otel-collector: receives OTLP traces from xrpld, batches and
+#     forwards them to Tempo. Listens on ports 4317 (gRPC)
+#     and 4318 (HTTP).
+#   - tempo: Grafana Tempo tracing backend, queryable via Grafana Explore
+#     on port 3000. Recommended for production (S3/GCS storage, TraceQL).
+#   - grafana: dashboards on port 3000, pre-configured with Tempo
+#     datasource.
+#
+# Usage:
+#   docker compose -f docker/telemetry/docker-compose.yml up -d
+#
+# Configure xrpld to export traces by adding to xrpld.cfg:
+#   [telemetry]
+#   enabled=1
+#   endpoint=http://localhost:4318/v1/traces
+
+services:
+  # OpenTelemetry Collector: receives spans from xrpld via OTLP protocol,
+  # batches them for efficiency, and forwards to Tempo for storage.
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:0.121.0
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    ports:
+      - "4317:4317" # OTLP gRPC receiver
+      - "4318:4318" # OTLP HTTP receiver (xrpld sends traces here)
+      - "13133:13133" # Health check endpoint
+    volumes:
+      # Mount collector pipeline config (receivers → processors → exporters)
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
+    depends_on:
+      - tempo
+    networks:
+      - xrpld-telemetry
+
+  # Grafana Tempo: distributed tracing backend that stores and indexes
+  # spans. Queryable via TraceQL in Grafana Explore.
+  tempo:
+    image: grafana/tempo:2.7.2
+    command: ["-config.file=/etc/tempo.yaml"]
+    ports:
+      - "3200:3200" # Tempo HTTP API (health check, query)
+    volumes:
+      # Mount Tempo storage and ingestion config
+      - ./tempo.yaml:/etc/tempo.yaml:ro
+      # Persistent volume for trace data (WAL + blocks)
+      - tempo-data:/var/tempo
+    networks:
+      - xrpld-telemetry
+
+  # Grafana: visualization UI with Tempo pre-configured as a datasource.
+  # Anonymous admin access enabled for local development convenience.
+  grafana:
+    image: grafana/grafana:11.5.2
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true # No login required for local dev
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin # Full access without auth
+    ports:
+      - "3000:3000" # Grafana web UI
+    volumes:
+      # Auto-provision Tempo datasource and search filters on startup
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+    depends_on:
+      - tempo
+    networks:
+      - xrpld-telemetry
+
+# Named volume for Tempo trace storage (WAL and compacted blocks).
+# Data persists across container restarts. Remove with:
+#   docker compose -f docker/telemetry/docker-compose.yml down -v
+volumes:
+  tempo-data:
+
+# Isolated bridge network so services communicate by container name
+# (e.g., the collector reaches Tempo at http://tempo:4317).
+networks:
+  xrpld-telemetry:
+    driver: bridge

docker/telemetry/grafana/provisioning/datasources/tempo.yaml

@@ -0,0 +1,108 @@
+# Grafana datasource provisioning for Grafana Tempo.
+# Auto-configures Tempo as a trace data source on Grafana startup.
+# Access Grafana at http://localhost:3000, then use Explore -> Tempo
+# to browse xrpld traces using TraceQL.
+#
+# Search filters provide pre-configured dropdowns in the Explore UI.
+# Each phase adds filters for the span attributes it introduces.
+# Base filters — node identity, service, span name, status.
+# RPC command, status, role filters.
+
+apiVersion: 1
+
+datasources:
+  - name: Tempo
+    type: tempo
+    access: proxy
+    url: http://tempo:3200
+    uid: tempo
+    jsonData:
+      nodeGraph:
+        enabled: true
+      # Service map and traces-to-metrics require a Prometheus datasource
+      # (not included in this stack). These features are inactive until a
+      # Prometheus service is added to docker-compose.yml.
+      serviceMap:
+        datasourceUid: prometheus
+      tracesToMetrics:
+        datasourceUid: prometheus
+        spanStartTimeShift: "-1h"
+        spanEndTimeShift: "1h"
+      search:
+        filters:
+          # --- Node identification filters ---
+          # service.name: logical service name (default: "xrpld").
+          #   Useful when running multiple service types in the same collector.
+          - id: service-name
+            tag: service.name
+            operator: "="
+            scope: resource
+            type: dynamic
+          # service.instance.id: unique node identifier — defaults to the
+          #   node's public key (e.g., nHB1X37...). Distinguishes individual
+          #   nodes in a multi-node cluster or network.
+          - id: node-id
+            tag: service.instance.id
+            operator: "="
+            scope: resource
+            type: dynamic
+          # service.version: xrpld build version (e.g., "2.4.0-b1").
+          #   Filter traces from specific software releases.
+          - id: node-version
+            tag: service.version
+            operator: "="
+            scope: resource
+            type: dynamic
+          # xrpl.network.id: numeric network identifier
+          #   (0 = mainnet, 1 = testnet, 2 = devnet, etc.).
+          #   Derived from the [network_id] config section.
+          - id: network-id
+            tag: xrpl.network.id
+            operator: "="
+            scope: resource
+            type: dynamic
+          # xrpl.network.type: human-readable network name derived from
+          #   network ID ("mainnet", "testnet", "devnet", "unknown").
+          - id: network-type
+            tag: xrpl.network.type
+            operator: "="
+            scope: resource
+            type: dynamic
+          # --- Span intrinsic filters ---
+          # name: the span operation name (e.g., "rpc.command.server_info").
+          #   Use to find traces for a specific RPC command or subsystem.
+          - id: span-name
+            tag: name
+            operator: "="
+            scope: intrinsic
+            type: dynamic
+          # status: span completion status ("ok", "error", "unset").
+          #   Filter for failed operations to diagnose errors.
+          - id: span-status
+            tag: status
+            operator: "="
+            scope: intrinsic
+            type: dynamic
+          # duration: span wall-clock duration. Use with ">" operator
+          #   to find slow operations (e.g., duration > 500ms).
+          - id: span-duration
+            tag: duration
+            operator: ">"
+            scope: intrinsic
+            type: dynamic
+          # RPC tracing filters
+          - id: rpc-command
+            tag: command
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: rpc-status
+            tag: rpc_status
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: rpc-role
+            tag: rpc_role
+            operator: "="
+            scope: span
+            type: dynamic

docker/telemetry/otel-collector-config.yaml

@@ -0,0 +1,79 @@
+# OpenTelemetry Collector configuration for xrpld development.
+#
+# Pipeline: OTLP receiver -> batch processor -> debug + Tempo.
+# xrpld sends traces via OTLP/HTTP to port 4318. The collector batches
+# them and forwards to Tempo via OTLP/gRPC on the Docker network. Tempo
+# is queryable via Grafana Explore using TraceQL.
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 100
+  # Deployment-tier tagging. Each collector serves ONE environment and ONE
+  # network, so it stamps both onto every signal it forwards. This lets a
+  # single Grafana stack hold data from many collectors and filter by tier.
+  #   - deployment.environment: the collector IS the environment (local, ci,
+  #     test, prod), so it is authoritative -> upsert (overwrite).
+  #   - xrpl.network.type: the xrpld node knows its own chain and already
+  #     stamps this, so the collector only fills it when absent -> insert.
+  #     This keeps a node's real network (e.g. a local node on mainnet)
+  #     from being overwritten by a collector's default.
+  # Replace the placeholder values per collector; see docker/telemetry
+  # tier examples.
+  resource/tier:
+    attributes:
+      - key: deployment.environment
+        value: local
+        action: upsert
+      - key: xrpl.network.type
+        value: mainnet
+        action: insert
+  # Strip SDK-injected resource attributes (telemetry.sdk.language/name/version).
+  # The OpenTelemetry SDK auto-adds these to every Resource; they carry no
+  # operational value and clutter the attribute set on every backend, so drop
+  # them here for all signals.
+  resource/stripsdk:
+    attributes:
+      - key: telemetry.sdk.language
+        action: delete
+      - key: telemetry.sdk.name
+        action: delete
+      - key: telemetry.sdk.version
+        action: delete
+  # Defense-in-depth: hash path-finding account attributes. The xrpld SDK
+  # already hashes these before export, but a node that emitted raw values
+  # is caught here so raw addresses never reach the backend.
+  attributes/hash:
+    actions:
+      - key: pathfind_source_account
+        action: hash
+      - key: pathfind_dest_account
+        action: hash
+
+exporters:
+  debug:
+    verbosity: detailed
+  otlp/tempo:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+
+service:
+  extensions: [health_check]
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [resource/tier, resource/stripsdk, attributes/hash, batch]
+      exporters: [debug, otlp/tempo]

docker/telemetry/tempo.yaml

@@ -0,0 +1,61 @@
+# Grafana Tempo configuration for xrpld telemetry stack.
+#
+# Runs in single-binary mode for local development.
+# Receives traces via OTLP/gRPC from the OTel Collector and stores
+# them locally. Queryable via Grafana Explore using the Tempo datasource.
+#
+# Search filters are configured on the Grafana datasource side
+# (grafana/provisioning/datasources/tempo.yaml). Tempo auto-indexes
+# all span attributes for search in single-binary mode.
+#
+# For production, replace local storage with S3/GCS backend and adjust
+# retention via the compactor settings. See:
+# https://grafana.com/docs/tempo/latest/configuration/
+
+stream_over_http_enabled: true
+
+server:
+  http_listen_port: 3200
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+
+ingester:
+  max_block_duration: 5m
+
+compactor:
+  compaction:
+    block_retention: 1h
+
+# Enable metrics generator for service graph and span metrics.
+# Produces RED metrics (rate, errors, duration) per service/span,
+# feeding Grafana's service map visualization.
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+  storage:
+    path: /var/tempo/generator/wal
+    # Uncomment and add a Prometheus service to docker-compose.yml
+    # to enable remote_write for service graph metrics:
+    # remote_write:
+    #   - url: http://prometheus:9090/api/v1/write
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors:
+        - service-graphs
+        - span-metrics
+
+storage:
+  trace:
+    backend: local
+    wal:
+      path: /var/tempo/wal
+    local:
+      path: /var/tempo/blocks

docs/build/telemetry.md

@@ -0,0 +1,129 @@
+# OpenTelemetry Tracing for xrpld
+
+This document explains how to build xrpld with OpenTelemetry distributed tracing support, configure the runtime telemetry options, and set up the observability backend to view traces.
+
+- [OpenTelemetry Tracing for xrpld](#opentelemetry-tracing-for-xrpld)
+  - [Overview](#overview)
+  - [Building with Telemetry](#building-with-telemetry)
+    - [Summary](#summary)
+    - [Build steps](#build-steps)
+      - [Install dependencies](#install-dependencies)
+      - [Call CMake](#call-cmake)
+      - [Build](#build)
+  - [Building without telemetry](#building-without-telemetry)
+  - [Troubleshooting](#troubleshooting)
+    - [Conan lockfile error](#conan-lockfile-error)
+    - [CMake target not found](#cmake-target-not-found)
+  - [Conditional compilation](#conditional-compilation)
+
+## Overview
+
+xrpld supports optional [OpenTelemetry](https://opentelemetry.io/) distributed tracing.
+When enabled, it instruments RPC requests with trace spans that are exported via
+OTLP/HTTP to an OpenTelemetry Collector, which forwards them to a tracing backend
+such as Grafana Tempo.
+
+Telemetry is **off by default** at both compile time and runtime:
+
+- **Compile time**: The Conan option `telemetry` and CMake option `telemetry` must be set to `True`/`ON`.
+  When disabled, all `SpanGuard` calls compile to inline no-ops (defined in `SpanGuard.h`)
+  with zero overhead — no OTel SDK dependency required.
+- **Runtime**: The `[telemetry]` config section must set `enabled=1`.
+  When disabled at runtime, a no-op implementation is used.
+
+## Building with Telemetry
+
+### Summary
+
+Follow the same instructions as mentioned in [BUILD.md](../../BUILD.md) but with the following changes:
+
+1. Pass `-o telemetry=True` to `conan install` to pull the `opentelemetry-cpp` dependency.
+2. CMake will automatically pick up `telemetry=ON` from the Conan-generated toolchain.
+3. Build as usual.
+
+---
+
+### Build steps
+
+```bash
+cd /path/to/xrpld
+rm -rf .build
+mkdir .build
+cd .build
+```
+
+#### Install dependencies
+
+The `telemetry` option adds `opentelemetry-cpp/1.26.0` as a dependency.
+If the Conan lockfile does not yet include this package, bypass it with `--lockfile=""`.
+
+```bash
+conan install .. \
+    --output-folder . \
+    --build missing \
+    --settings build_type=Debug \
+    -o telemetry=True \
+    -o tests=True \
+    -o xrpld=True \
+    --lockfile=""
+```
+
+> **Note**: The first build with telemetry may take longer as `opentelemetry-cpp`
+> and its transitive dependencies are compiled from source.
+
+#### Call CMake
+
+The Conan-generated toolchain file sets `telemetry=ON` automatically.
+No additional CMake flags are needed beyond the standard ones.
+
+```bash
+cmake .. -G Ninja \
+    -DCMAKE_TOOLCHAIN_FILE:FILEPATH=build/generators/conan_toolchain.cmake \
+    -DCMAKE_BUILD_TYPE=Debug \
+    -Dtests=ON -Dxrpld=ON
+```
+
+You should see in the CMake output:
+
+```
+-- OpenTelemetry tracing enabled
+```
+
+#### Build
+
+```bash
+cmake --build . --parallel $(nproc)
+```
+
+## Building without telemetry
+
+Omit the `-o telemetry=True` option (or pass `-o telemetry=False`).
+The `opentelemetry-cpp` dependency will not be downloaded,
+the `XRPL_ENABLE_TELEMETRY` preprocessor define will not be set,
+and all tracing macros will compile to no-ops.
+The resulting binary is identical to one built before telemetry support was added.
+
+## Troubleshooting
+
+### Conan lockfile error
+
+If you see `ERROR: Requirement 'opentelemetry-cpp/1.26.0' not in lockfile 'requires'`,
+the lockfile was generated without the telemetry dependency.
+Pass `--lockfile=""` to bypass the lockfile, or regenerate it with telemetry enabled.
+
+### CMake target not found
+
+If CMake reports that `opentelemetry-cpp` targets are not found,
+ensure you ran `conan install` with `-o telemetry=True` and that the
+Conan-generated toolchain file is being used.
+The Conan package provides a single umbrella target
+`opentelemetry-cpp::opentelemetry-cpp` (not individual component targets).
+
+## Conditional compilation
+
+All OpenTelemetry SDK types are hidden behind the pimpl idiom in `SpanGuard.cpp`.
+When `XRPL_ENABLE_TELEMETRY` is not defined, `SpanGuard.h` provides an all-inline
+no-op stub class with zero overhead and zero OTel dependencies.
+At runtime, if `enabled=0` is set in config (or the section is omitted), a
+`NullTelemetry` implementation is used that returns no-op spans.
+This two-layer approach ensures zero overhead when telemetry is not wanted.

include/xrpl/core/ServiceRegistry.h

@@ -24,6 +24,9 @@ class Manager;
 namespace perf {
 class PerfLog;
 }  // namespace perf
+namespace telemetry {
+class Telemetry;
+}  // namespace telemetry
 
 // This is temporary until we migrate all code to use ServiceRegistry.
 class Application;
@@ -224,6 +227,9 @@ public:
     virtual perf::PerfLog&
     getPerfLog() = 0;
 
+    virtual telemetry::Telemetry&
+    getTelemetry() = 0;
+
     // Configuration and state
     [[nodiscard]] virtual bool
     isStopping() const = 0;

include/xrpl/telemetry/DiscardFlag.h

@@ -0,0 +1,89 @@
+#pragma once
+
+/** Thread-local discard signaling between SpanGuard and the span processor.
+
+    SpanGuard::discard() wants to drop a span without sending it to the
+    exporter. The OTel SDK calls SpanProcessor::OnEnd() synchronously on the
+    same thread that calls Span::End(), so a thread-local flag set just before
+    End() and read inside OnEnd() lets FilteringSpanProcessor drop the span
+    before it enters the batch export queue.
+
+    This side-channel avoids inspecting the Recordable's internals (which vary
+    by exporter type — SpanData vs OtlpRecordable).
+
+    The flag is a *private* thread-local member of DiscardScope, mutated only by
+    its constructor and destructor. This gives real access control rather than a
+    naming convention: no code that includes this header can flip the flag
+    directly — it can only enter a DiscardScope (which sets and clears the flag
+    over its own lifetime) and observe the state via DiscardScope::isActive().
+    Binding set/clear to a scope also means the flag cannot leak onto the next
+    span even if End() were to throw.
+
+    Kept in a separate header to avoid transitive include bloat: SpanGuard.h
+    only needs this signaling, not the full Telemetry.h with BasicConfig/Journal.
+
+    Usage:
+    @code
+        // In SpanGuard::discard():
+        {
+            DiscardScope discardScope;  // flag set for this scope only
+            span->End();                // OnEnd() runs synchronously, sees flag
+        }                               // flag cleared here, unconditionally
+
+        // In FilteringSpanProcessor::OnEnd():
+        if (DiscardScope::isActive())
+            return;  // drop the span
+    @endcode
+
+    @note Thread safety: the flag is thread-local, so each thread observes only
+    its own discard signal — no synchronization is required.
+
+    @see SpanGuard::discard(), FilteringSpanProcessor (Telemetry.cpp)
+*/
+
+namespace xrpl::telemetry {
+
+/** RAII guard that marks the current thread's span for discard.
+
+    Sets the thread-local discard flag on construction and clears it on
+    destruction, so a span ended within the guard's scope is dropped by
+    FilteringSpanProcessor::OnEnd() while the flag stays confined to that scope.
+    The flag is private and mutated only here, so no other code can set it.
+    Non-copyable and non-movable — its sole purpose is the scoped flag lifetime.
+*/
+class DiscardScope
+{
+public:
+    DiscardScope() noexcept
+    {
+        discarding = true;
+    }
+
+    ~DiscardScope()
+    {
+        discarding = false;
+    }
+
+    DiscardScope(DiscardScope const&) = delete;
+    DiscardScope&
+    operator=(DiscardScope const&) = delete;
+    DiscardScope(DiscardScope&&) = delete;
+    DiscardScope&
+    operator=(DiscardScope&&) = delete;
+
+    /** @return true if the current thread is inside a DiscardScope, i.e. the
+        span ending now should be dropped rather than exported. Read by
+        FilteringSpanProcessor::OnEnd(). */
+    [[nodiscard]] static bool
+    isActive() noexcept
+    {
+        return discarding;
+    }
+
+private:
+    /** Thread-local discard flag. Private, so only this class's ctor/dtor can
+        mutate it; observers use isActive(). One instance per thread. */
+    inline static thread_local bool discarding = false;
+};
+
+}  // namespace xrpl::telemetry

include/xrpl/telemetry/Redaction.h

@@ -0,0 +1,64 @@
+#pragma once
+
+/** Account-address redaction for telemetry span attributes.
+
+    Path-finding RPC handlers would otherwise emit the caller's raw
+    account addresses as span attributes. To keep plaintext addresses out
+    of the telemetry backend, they are hashed at the point of emission.
+    This header exposes a single pure helper that turns an address into a
+    short, stable, obfuscated token.
+
+    Data flow:
+
+        handler -> redactAccount(addr) -> span attribute -> OTLP export
+
+    The returned token is the first 16 hex characters (lowercase) of the
+    SHA-512Half digest of the address. It is deterministic (same address
+    always maps to the same token) so operators can still correlate spans
+    for a given account across nodes and restarts.
+
+    The hash is unsalted, so it is obfuscation, not a secrecy guarantee:
+    XRP account addresses are a public, enumerable set, so a determined
+    observer with the telemetry stream could rebuild the address->token
+    mapping. The goal here is to keep plaintext addresses out of traces
+    and dashboards, not to defend against a precomputation attack. A salt
+    is intentionally omitted because it would break cross-node/restart
+    correlation, which is the reason for hashing rather than dropping.
+
+    A second, independent hashing layer runs in the OpenTelemetry
+    Collector (an `attributes/hash` processor) as defense-in-depth for
+    any node that emits a raw value.
+
+    @note This function is pure and reentrant: it holds no global state,
+    performs no I/O, and is safe to call concurrently from any thread.
+
+    Usage example:
+    @code
+        #include <xrpl/telemetry/Redaction.h>
+        using namespace xrpl::telemetry;
+
+        span.setAttribute(
+            pathfind_span::attr::sourceAccount, redactAccount(src.asString()));
+    @endcode
+
+    Edge case (empty input yields empty output):
+    @code
+        assert(redactAccount("") == "");
+    @endcode
+*/
+
+#include <string>
+#include <string_view>
+
+namespace xrpl::telemetry {
+
+/** Hash an account address into a short, stable, obfuscated token.
+
+    @param addr  The account address to redact (e.g. an r-address).
+    @return The first 16 lowercase hex characters of sha512Half(addr),
+            or an empty string when @p addr is empty.
+*/
+[[nodiscard]] std::string
+redactAccount(std::string_view addr);
+
+}  // namespace xrpl::telemetry

include/xrpl/telemetry/SpanGuard.h

@@ -0,0 +1,419 @@
+#pragma once
+
+/** RAII guard for OpenTelemetry trace spans.
+
+    Wraps an OTel Span and Scope behind the pimpl idiom so that no
+    opentelemetry headers are exposed in this public header. When
+    XRPL_ENABLE_TELEMETRY is not defined, SpanGuard is an empty class
+    with all-inline no-op methods — zero overhead, zero dependencies.
+
+    Dependency diagram:
+
+        +-------------------------------------------+
+        |              SpanGuard                     |
+        +-------------------------------------------+
+        | - impl_ : unique_ptr<Impl>  (pimpl)       |
+        +-------------------------------------------+
+        | + span(cat, prefix, name)         [static] |
+        | + childSpan(name) : SpanGuard              |
+        | + linkedSpan(name) : SpanGuard             |
+        | + captureContext() : SpanContext            |
+        | + setAttribute(key, value)                 |
+        | + setOk() / setError(desc)                 |
+        | + addEvent(name)                           |
+        | + recordException(e)                       |
+        | + discard()                                |
+        | + operator bool()                          |
+        +-------------------------------------------+
+                        |  hides (pimpl)
+                +-------+-------+
+                |               |
+           +--------+   +-------------+
+           |  Span  |   |    Scope    |
+           | (OTel) |   | (OTel, non- |
+           |        |   |  movable)   |
+           +--------+   +-------------+
+
+    Static factory methods access the global Telemetry instance
+    internally (via Telemetry::getInstance()), check whether tracing
+    is enabled for the requested subsystem, and return either an
+    active guard or a null (no-op) guard. Callers never need a
+    Telemetry reference.
+
+    Usage examples:
+
+    Span names and attribute keys come from per-module `*SpanNames.h`
+    headers (e.g. RpcSpanNames.h, TxSpanNames.h) as typed compile-time
+    constants — never raw string literals — so the naming spec is
+    enforced at the call site and dashboards stay in sync.
+
+    1. Basic RPC tracing (factory method with category):
+    @code
+        #include <xrpld/rpc/detail/RpcSpanNames.h>
+        using namespace xrpl::telemetry;
+
+        auto span = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::command, commandName);
+        span.setAttribute(rpc_span::attr::command, commandName);
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::success);
+        // span ended automatically on scope exit
+    @endcode
+
+    2. Error recording:
+    @code
+        auto span = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::command, commandName);
+        try {
+            doWork();
+            span.setOk();
+        } catch (std::exception const& e) {
+            span.recordException(e);
+        }
+    @endcode
+
+    3. Cross-thread context propagation:
+    @code
+        #include <xrpld/rpc/detail/RpcSpanNames.h>
+        using namespace xrpl::telemetry;
+
+        // Thread A: create span and capture context
+        auto span = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::process);
+        auto ctx = span.captureContext();
+
+        // Thread B: create child with captured context
+        auto child = SpanGuard::childSpan(rpc_span::op::process, ctx);
+    @endcode
+
+    4. Conditional check (rarely needed — methods are no-ops on null):
+    @code
+        auto span = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::httpRequest);
+        if (span) {
+            // expensive attribute computation only when active
+            span.setAttribute(rpc_span::attr::requestPayloadSize, computeSize());
+        }
+    @endcode
+
+    5. Tail-based filtering via discard():
+    @code
+        auto span = SpanGuard::span(
+            TraceCategory::Transactions, tx_span::prefix::tx, tx_span::op::process);
+        auto result = preflight(tx);
+        if (result != tesSUCCESS) {
+            span.discard();  // drop span, never exported
+            return result;
+        }
+    @endcode
+
+    @note Thread safety: A SpanGuard must only be used on the thread
+    where it was constructed (the internal Scope binds to the
+    thread-local context stack). Use captureContext() to propagate
+    the trace to other threads.
+
+    @note Move semantics: Move construction transfers ownership of
+    the pimpl pointer — no double-Scope issues. Move assignment is
+    deleted to prevent re-scoping mid-flight.
+
+    @note Known limitations:
+    - Attributes cannot be removed per the OTel spec; use
+      setAttribute with an empty value as a convention.
+    - SpanGuard::span() (raw Span access) is intentionally not
+      exposed — all interaction goes through the public methods.
+*/
+
+#include <cstdint>
+#include <exception>
+#include <memory>
+#include <string_view>
+
+namespace xrpl::telemetry {
+
+/** Trace subsystem categories for conditional span creation.
+
+    Each value maps to a runtime config flag (e.g. `trace_rpc=1`).
+    Used by SpanGuard::span(TraceCategory, prefix, name) to decide
+    whether to create a real span or return a null guard.
+*/
+enum class TraceCategory { Rpc, Transactions, Consensus, Peer, Ledger };
+
+/** Opaque wrapper for an OTel context snapshot.
+
+    Used to propagate trace context across threads. Created by
+    SpanGuard::captureContext(), consumed by SpanGuard::childSpan()
+    or SpanGuard::linkedSpan() with an explicit parent/link context.
+*/
+class SpanContext
+{
+    friend class SpanGuard;
+
+#ifdef XRPL_ENABLE_TELEMETRY
+    struct Impl;
+    std::shared_ptr<Impl> impl_;
+    explicit SpanContext(std::shared_ptr<Impl> impl);
+#endif
+
+public:
+    SpanContext() = default;
+
+    /** @return true if this context holds a valid trace context. */
+#ifdef XRPL_ENABLE_TELEMETRY
+    [[nodiscard]] bool
+    isValid() const;
+#else
+    // NOLINTBEGIN(readability-convert-member-functions-to-static)
+    [[nodiscard]] bool
+    isValid() const
+    {
+        return false;
+    }
+    // NOLINTEND(readability-convert-member-functions-to-static)
+#endif
+};
+
+// ---------------------------------------------------------------------------
+// Real implementation (pimpl, compiled in SpanGuard.cpp)
+// ---------------------------------------------------------------------------
+#ifdef XRPL_ENABLE_TELEMETRY
+
+/** RAII wrapper that activates a span on construction and ends it on
+    destruction. All OTel types are hidden behind the Impl pointer.
+    Non-copyable, move-constructible.
+*/
+class SpanGuard
+{
+    struct Impl;
+    std::unique_ptr<Impl> impl_;
+
+    explicit SpanGuard(std::unique_ptr<Impl> impl);
+
+public:
+    /** Construct a null (no-op) guard. All methods are safe to call. */
+    SpanGuard();
+    ~SpanGuard();
+
+    SpanGuard(SpanGuard&& other) noexcept;
+    SpanGuard&
+    operator=(SpanGuard&&) = delete;
+    SpanGuard(SpanGuard const&) = delete;
+    SpanGuard&
+    operator=(SpanGuard const&) = delete;
+
+    // --- Static factory methods ----------------------------------------
+
+    /** Create a span guarded by a TraceCategory flag.
+        The span name is built as "prefix.name". Returns a null guard
+        if the category is disabled in config.
+        @param cat     Trace subsystem category.
+        @param prefix  Span name prefix (e.g. "rpc.command").
+        @param name    Span name suffix (e.g. "submit").
+    */
+    [[nodiscard]] static SpanGuard
+    span(TraceCategory cat, std::string_view prefix, std::string_view name);
+
+    // --- Child / linked span creation ----------------------------------
+
+    /** Create a child span parented to this guard's active context.
+        @param name  Span name for the child.
+        @return A new guard, or null if this guard is inactive.
+    */
+    [[nodiscard]] SpanGuard
+    childSpan(std::string_view name) const;
+
+    /** Create a child span parented to an explicit captured context.
+        @param name       Span name for the child.
+        @param parentCtx  Context captured via captureContext().
+        @return A new guard, or null if parentCtx is invalid.
+    */
+    [[nodiscard]] static SpanGuard
+    childSpan(std::string_view name, SpanContext const& parentCtx);
+
+    /** Create a span linked (follows-from) to this guard's span.
+        The new span is NOT a child — it starts a new sub-tree but
+        carries a causal link to this span.
+        @param name  Span name for the linked span.
+        @return A new guard, or null if this guard is inactive.
+    */
+    [[nodiscard]] SpanGuard
+    linkedSpan(std::string_view name) const;
+
+    /** Create a span linked to an explicit captured context.
+        @param name     Span name for the linked span.
+        @param linkCtx  Context to link from.
+        @return A new guard, or null if linkCtx is invalid.
+    */
+    [[nodiscard]] static SpanGuard
+    linkedSpan(std::string_view name, SpanContext const& linkCtx);
+
+    // --- Context capture -----------------------------------------------
+
+    /** Snapshot the current thread's OTel context for cross-thread use.
+        @return An opaque SpanContext, or an invalid one if null guard.
+    */
+    [[nodiscard]] SpanContext
+    captureContext() const;
+
+    // --- Attribute setters (explicit overloads, no OTel types) ---------
+
+    /** Set a string attribute. No-op on a null guard. */
+    void
+    setAttribute(std::string_view key, std::string_view value);
+
+    /** Set a string attribute (C-string overload). No-op on a null guard. */
+    void
+    setAttribute(std::string_view key, char const* value);
+
+    /** Set an integer attribute. No-op on a null guard. */
+    void
+    setAttribute(std::string_view key, std::int64_t value);
+
+    /** Set a floating-point attribute. No-op on a null guard. */
+    void
+    setAttribute(std::string_view key, double value);
+
+    /** Set a boolean attribute. No-op on a null guard. */
+    void
+    setAttribute(std::string_view key, bool value);
+
+    // --- Status / events -----------------------------------------------
+
+    /** Mark the span status as OK. No-op on a null guard. */
+    void
+    setOk();
+
+    /** Mark the span status as error. No-op on a null guard.
+        @param description  Optional human-readable error description.
+    */
+    void
+    setError(std::string_view description = "");
+
+    /** Add a named event to the span's timeline. No-op on a null guard.
+        @param name  Event name.
+    */
+    void
+    addEvent(std::string_view name);
+
+    /** Record an exception as a span event following OTel semantic
+        conventions, and mark the span status as error.
+        No-op on a null guard.
+        @param e  The exception to record.
+    */
+    void
+    recordException(std::exception const& e);
+
+    /** Mark this span for discard and end it immediately.
+        The FilteringSpanProcessor drops the span before it enters the
+        batch export queue. After discard(), the guard is inert.
+    */
+    void
+    discard();
+
+    /** @return true if this guard holds an active span. */
+    explicit
+    operator bool() const;
+};
+
+// ---------------------------------------------------------------------------
+// No-op stub (all inline, zero overhead, no OTel dependency)
+// ---------------------------------------------------------------------------
+#else  // XRPL_ENABLE_TELEMETRY not defined
+
+class SpanGuard
+{
+public:
+    SpanGuard() = default;
+    ~SpanGuard() = default;
+    SpanGuard(SpanGuard&&) noexcept = default;
+    SpanGuard&
+    operator=(SpanGuard&&) = delete;
+    SpanGuard(SpanGuard const&) = delete;
+    SpanGuard&
+    operator=(SpanGuard const&) = delete;
+
+    [[nodiscard]] static SpanGuard
+    span(TraceCategory, std::string_view, std::string_view)
+    {
+        return {};
+    }
+
+    // NOLINTBEGIN(readability-convert-member-functions-to-static)
+    [[nodiscard]] SpanGuard
+    childSpan(std::string_view) const
+    {
+        return {};
+    }
+    [[nodiscard]] static SpanGuard
+    childSpan(std::string_view, SpanContext const&)
+    {
+        return {};
+    }
+    [[nodiscard]] SpanGuard
+    linkedSpan(std::string_view) const
+    {
+        return {};
+    }
+    [[nodiscard]] static SpanGuard
+    linkedSpan(std::string_view, SpanContext const&)
+    {
+        return {};
+    }
+
+    [[nodiscard]] SpanContext
+    captureContext() const
+    {
+        return {};
+    }
+    // NOLINTEND(readability-convert-member-functions-to-static)
+
+    void
+    setAttribute(std::string_view, std::string_view)
+    {
+    }
+    void
+    setAttribute(std::string_view, char const*)
+    {
+    }
+    void
+    setAttribute(std::string_view, std::int64_t)
+    {
+    }
+    void
+    setAttribute(std::string_view, double)
+    {
+    }
+    void
+    setAttribute(std::string_view, bool)
+    {
+    }
+
+    void
+    setOk()
+    {
+    }
+    void
+    setError(std::string_view = "")
+    {
+    }
+    void
+    addEvent(std::string_view)
+    {
+    }
+    void
+    recordException(std::exception const&)
+    {
+    }
+    void
+    discard()
+    {
+    }
+
+    explicit
+    operator bool() const
+    {
+        return false;
+    }
+};
+
+#endif  // XRPL_ENABLE_TELEMETRY
+
+}  // namespace xrpl::telemetry

include/xrpl/telemetry/SpanNames.h

@@ -0,0 +1,119 @@
+#pragma once
+
+/** Compile-time string concatenation utility and shared telemetry constants.
+ *
+ *  Provides StaticStr<N> — a compile-time string buffer that implicitly
+ *  converts to std::string_view — and join() for dot-separated concatenation.
+ *  Module-specific span names (e.g. RPC, consensus) live in their respective
+ *  modules and build upon these shared primitives.
+ *
+ *  @note These constants are NOT guarded by XRPL_ENABLE_TELEMETRY because
+ *  call sites reference them even when SpanGuard methods are no-ops
+ *  (the no-op stubs still accept string_view parameters). The compiler
+ *  elides all inline constexpr values whose only uses are in dead code.
+ *
+ *  @note Json::StaticString (jss.h) is a pointer wrapper without
+ *  concatenation support. boost::static_string is not constexpr.
+ *  StaticStr<N> exists specifically for compile-time dot-join composition.
+ *
+ *  Naming conventions (see spec 2026-05-13-span-attr-naming-design):
+ *  - Per-span attribute keys: bare field name (span name carries the domain).
+ *  - Collision qualifier: <domain>_<field> when bare name collides across
+ *    domains or with OTel reserved `status` (e.g. rpc_status, grpc_status).
+ *  - Shared cross-span attributes: <domain>_<field> (underscore) form
+ *    (e.g. tx_hash, peer_id, ledger_seq, consensus_round).
+ *  - Resource attribute keys: xrpl.<subsystem>.<field> (dotted) form is
+ *    RESERVED for process-identity attributes set once at startup on the
+ *    OTel resource (e.g. xrpl.network.id, xrpl.network.type). Do not use
+ *    this form for span attributes — it parses awkwardly in TraceQL and
+ *    blurs the resource/span scope distinction.
+ *  - Span prefixes: <subsystem>[.<component>].
+ */
+
+#include <cstddef>
+#include <string_view>
+
+namespace xrpl::telemetry {
+
+// ===== Compile-time string utility =========================================
+
+/// Fixed-size character buffer for compile-time string operations.
+/// Implicitly converts to std::string_view at zero cost.
+template <std::size_t N>
+struct StaticStr
+{
+    char data[N + 1]{};
+    static constexpr std::size_t size = N;
+
+    constexpr StaticStr() = default;
+
+    constexpr explicit StaticStr(char const (&str)[N + 1])
+    {
+        for (std::size_t i = 0; i <= N; ++i)
+            data[i] = str[i];
+    }
+
+    constexpr
+    operator std::string_view() const noexcept
+    {
+        return {data, N};
+    }
+};
+
+/// Deduction guide: StaticStr from string literal.
+template <std::size_t N>
+StaticStr(char const (&)[N]) -> StaticStr<N - 1>;
+
+/// Create a StaticStr from a string literal.
+template <std::size_t N>
+constexpr auto
+makeStr(char const (&str)[N])
+{
+    return StaticStr<N - 1>(str);
+}
+
+/// Concatenate two StaticStr values with a dot separator.
+template <std::size_t A, std::size_t B>
+constexpr auto
+join(StaticStr<A> const& lhs, StaticStr<B> const& rhs)
+{
+    constexpr std::size_t len = A + 1 + B;  // lhs + '.' + rhs
+    StaticStr<len> result;
+    std::size_t pos = 0;
+    for (std::size_t i = 0; i < A; ++i)
+        result.data[pos++] = lhs.data[i];
+    result.data[pos++] = '.';
+    for (std::size_t i = 0; i < B; ++i)
+        result.data[pos++] = rhs.data[i];
+    result.data[pos] = '\0';
+    return result;
+}
+
+// ===== Shared root segments ================================================
+
+namespace seg {
+inline constexpr auto xrpl = makeStr("xrpl");
+inline constexpr auto rpc = makeStr("rpc");
+inline constexpr auto tx = makeStr("tx");
+inline constexpr auto consensus = makeStr("consensus");
+inline constexpr auto peer = makeStr("peer");
+inline constexpr auto ledger = makeStr("ledger");
+inline constexpr auto network = makeStr("network");
+inline constexpr auto link = makeStr("link");
+}  // namespace seg
+
+// ===== Shared attribute keys (used across modules) =========================
+
+namespace attr {
+inline constexpr auto networkId = join(join(seg::xrpl, seg::network), makeStr("id"));
+inline constexpr auto networkType = join(join(seg::xrpl, seg::network), makeStr("type"));
+}  // namespace attr
+
+// ===== Shared attribute values =============================================
+
+namespace attr_val {
+inline constexpr auto success = makeStr("success");
+inline constexpr auto error = makeStr("error");
+}  // namespace attr_val
+
+}  // namespace xrpl::telemetry

include/xrpl/telemetry/Telemetry.h

@@ -0,0 +1,349 @@
+#pragma once
+
+/** Abstract interface for OpenTelemetry distributed tracing.
+
+    Provides the Telemetry base class that all components use to create trace
+    spans. Three concrete implementations exist, selected at construction time
+    by makeTelemetry():
+
+      - TelemetryImpl (Telemetry.cpp): real OTel SDK integration, compiled
+        only when XRPL_ENABLE_TELEMETRY is defined and enabled at runtime.
+      - NullTelemetry (NullTelemetry.cpp): no-op stub used when telemetry is
+        disabled at compile time or runtime.
+      - NullTelemetryOtel (Telemetry.cpp): no-op stub that still depends on
+        the OTel API (used during transition or for testing).
+
+    Inheritance / dependency diagram:
+
+        +--------------------+
+        |    Telemetry       |  (abstract, this file)
+        |  <<interface>>     |
+        +---------+----------+
+                  |
+        +---------+-----------+-------------------+
+        |                     |                   |
+    +---+------------+  +-----+---------+  +------+----------+
+    | TelemetryImpl  |  | NullTelemetry |  | NullTelemetryOtel|
+    | (Telemetry.cpp)|  |(NullTelemetry |  | (Telemetry.cpp)  |
+    | OTel SDK       |  | .cpp)         |  | noop w/ OTel API |
+    +----------------+  +---------------+  +------------------+
+
+    The Setup struct holds all configuration parsed from the [telemetry]
+    section of xrpld.cfg. See TelemetryConfig.cpp for the parser and
+    cfg/xrpld-example.cfg for the available options.
+
+    OTel SDK headers are conditionally included behind XRPL_ENABLE_TELEMETRY
+    so that builds without telemetry have zero dependency on opentelemetry-cpp.
+
+    Usage examples:
+
+    1. Root span at a subsystem entry point (typical usage):
+    @code
+        #include <xrpld/rpc/detail/RpcSpanNames.h>
+        using namespace xrpl::telemetry;
+
+        // In an RPC handler dispatch:
+        auto guard = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::command, commandName);
+        guard.setAttribute(rpc_span::attr::command, commandName);
+        // ... process request
+        // guard destructor automatically ends the span on scope exit
+    @endcode
+
+    2. Child span for a sub-operation (scoped child):
+    @code
+        auto parent = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::process);
+        {
+            auto child = parent.childSpan(rpc_span::op::process);
+            child.setAttribute(rpc_span::attr::version, apiVersion);
+            // child ends here
+        }
+    @endcode
+
+    3. Unrelated span (cross-scope, same thread):
+    @code
+        // gRPC and RPC handlers can be active simultaneously
+        auto grpcSpan = SpanGuard::span(
+            TraceCategory::Rpc, grpc_span::prefix::grpc, grpc_span::attr::method);
+        auto rpcSpan = SpanGuard::span(
+            TraceCategory::Rpc, rpc_span::prefix::command, commandName);
+        // both spans end on scope exit
+    @endcode
+
+    4. Cross-thread context propagation:
+    @code
+        // Thread A: capture the active context while span is in scope
+        auto ctx = parentGuard.captureContext();
+
+        // Thread B: create child span with explicit parent
+        auto child = SpanGuard::childSpan(rpc_span::op::process, ctx);
+    @endcode
+
+    @note Thread safety: The Telemetry interface is safe for concurrent reads
+    (isEnabled, shouldTrace*, getTracer, startSpan) after start() completes.
+    setServiceInstanceId() must be called before start() and is not thread-safe.
+    The OTel SDK's TracerProvider and Tracer are internally thread-safe.
+*/
+
+#include <xrpl/beast/utility/Journal.h>
+#include <xrpl/config/BasicConfig.h>
+
+#include <atomic>
+#include <chrono>
+#include <cstdint>
+#include <memory>
+#include <string>
+#include <string_view>
+
+#ifdef XRPL_ENABLE_TELEMETRY
+#include <opentelemetry/context/context.h>
+#include <opentelemetry/nostd/shared_ptr.h>
+#include <opentelemetry/trace/span.h>
+#include <opentelemetry/trace/span_metadata.h>
+#include <opentelemetry/trace/tracer.h>
+#endif
+
+namespace xrpl::telemetry {
+
+#ifdef XRPL_ENABLE_TELEMETRY
+/** OTel instrumentation scope (tracer) name. Identifies this library as the
+    source of spans; distinct from the `service.name` resource attribute
+    (Setup::serviceName), which is config-overridable. */
+inline constexpr std::string_view kTracerName{"xrpld"};
+#endif
+
+class Telemetry
+{
+    /** Global singleton pointer, set by start()/stop() in the active
+        implementation. Allows SpanGuard factory methods to access the
+        Telemetry instance without callers passing it explicitly.
+
+        Atomic with acquire/release ordering: start()/stop() store on
+        the initialization thread, factory methods load on worker threads.
+        @see setInstance(), getInstance()
+    */
+    inline static std::atomic<Telemetry*> instance{nullptr};
+
+public:
+    /** Get the global Telemetry instance.
+        @return Pointer to the active instance, or nullptr if not started.
+    */
+    static Telemetry*
+    getInstance()
+    {
+        return instance.load(std::memory_order_acquire);
+    }
+
+    /** Set the global Telemetry instance.
+        Called by start()/stop() in concrete implementations.
+        Tests can call this with a mock to override the global instance.
+        @param t  Pointer to the Telemetry instance, or nullptr to clear.
+    */
+    static void
+    setInstance(Telemetry* t)
+    {
+        instance.store(t, std::memory_order_release);
+    }
+
+    /** Configuration parsed from the [telemetry] section of xrpld.cfg.
+
+        All fields have sensible defaults so the section can be minimal
+        or omitted entirely. See TelemetryConfig.cpp for the parser.
+    */
+    struct Setup
+    {
+        /** Master switch: true to enable tracing at runtime. */
+        bool enabled = false;
+
+        /** OTel resource attribute `service.name`. */
+        std::string serviceName = "xrpld";
+
+        /** OTel resource attribute `service.version` (set from BuildInfo). */
+        std::string serviceVersion;
+
+        /** OTel resource attribute `service.instance.id` (defaults to node
+            public key). */
+        std::string serviceInstanceId;
+
+        /** OTLP/HTTP endpoint URL where spans are sent. */
+        std::string exporterEndpoint = "http://localhost:4318/v1/traces";
+
+        /** Whether to use TLS for the exporter connection. */
+        bool useTls = false;
+
+        /** Path to a CA certificate bundle for TLS verification. */
+        std::string tlsCertPath;
+
+        /** Head-based sampling ratio. Intentionally fixed at 1.0 (sample
+            everything) and NOT read from config. A per-node ratio would let
+            nodes make divergent keep/drop decisions for the same distributed
+            trace, producing broken/partial traces. The ratio sampler is wrapped
+            in a ParentBasedSampler (see Telemetry.cpp) so spans inheriting a
+            remote parent honor the upstream sampled flag. Volume reduction is
+            delegated to the collector's tail sampling; for node-local post-hoc
+            dropping see SpanGuard::discard().
+        */
+        static constexpr double samplingRatio = 1.0;
+
+        /** Maximum number of spans per batch export. */
+        std::uint32_t batchSize = 512;
+
+        /** Delay between batch exports. */
+        std::chrono::milliseconds batchDelay = std::chrono::milliseconds{5000};
+
+        /** Maximum number of spans queued before dropping. */
+        std::uint32_t maxQueueSize = 2048;
+
+        /** Network identifier, added as an OTel resource attribute. */
+        std::uint32_t networkId = 0;
+
+        /** Network type label (e.g. "mainnet", "testnet", "devnet"). */
+        std::string networkType = "mainnet";
+
+        /** Enable tracing for transaction processing. */
+        bool traceTransactions = true;
+
+        /** Enable tracing for consensus rounds. */
+        bool traceConsensus = true;
+
+        /** Enable tracing for RPC request handling. */
+        bool traceRpc = true;
+
+        /** Enable tracing for peer-to-peer messages (enabled by default;
+            high volume). */
+        bool tracePeer = true;
+
+        /** Enable tracing for ledger close/accept. */
+        bool traceLedger = true;
+    };
+
+    virtual ~Telemetry() = default;
+
+    /** Update the service instance ID (OTel resource attribute
+        `service.instance.id`).
+
+        Must be called before start(). The node public key is not available
+        when Telemetry is constructed (during the ApplicationImp member
+        initializer list), so this setter allows Application::setup() to
+        inject the identity once nodeIdentity_ is known.
+
+        @param id  The node's base58-encoded public key or custom identifier.
+    */
+    virtual void
+    setServiceInstanceId(std::string const& id)
+    {
+        // Default no-op for NullTelemetry implementations.
+        (void)id;
+    }
+
+    /** Initialize the tracing pipeline (exporter, processor, provider).
+        Call after construction.
+    */
+    virtual void
+    start() = 0;
+
+    /** Flush pending spans and shut down the tracing pipeline.
+        Call before destruction.
+    */
+    virtual void
+    stop() = 0;
+
+    /** @return true if this instance is actively exporting spans. */
+    [[nodiscard]] virtual bool
+    isEnabled() const = 0;
+
+    /** @return true if transaction processing should be traced. */
+    [[nodiscard]] virtual bool
+    shouldTraceTransactions() const = 0;
+
+    /** @return true if consensus rounds should be traced. */
+    [[nodiscard]] virtual bool
+    shouldTraceConsensus() const = 0;
+
+    /** @return true if RPC request handling should be traced. */
+    [[nodiscard]] virtual bool
+    shouldTraceRpc() const = 0;
+
+    /** @return true if peer-to-peer messages should be traced. */
+    [[nodiscard]] virtual bool
+    shouldTracePeer() const = 0;
+
+    /** @return true if ledger close/accept should be traced. */
+    [[nodiscard]] virtual bool
+    shouldTraceLedger() const = 0;
+
+#ifdef XRPL_ENABLE_TELEMETRY
+    /** Get or create a named tracer instance.
+
+        @param name  Tracer name used to identify the instrumentation library.
+        @return A shared pointer to the Tracer.
+    */
+    virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Tracer>
+    getTracer(std::string_view name = kTracerName) = 0;
+
+    /** Start a new span on the current thread's context.
+
+        The span becomes a child of the current active span (if any) via
+        OpenTelemetry's context propagation.
+
+        @param name  Span name (typically "rpc.command.<cmd>").
+        @param kind  The span kind (defaults to kInternal). Possible values:
+                     - kInternal: default, in-process operation
+                     - kServer:   incoming synchronous request (e.g. RPC)
+                     - kClient:   outgoing synchronous request
+                     - kProducer: async message send (e.g. peer broadcast)
+                     - kConsumer: async message receive
+        @return A shared pointer to the new Span.
+    */
+    virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+    startSpan(
+        std::string_view name,
+        opentelemetry::trace::SpanKind kind = opentelemetry::trace::SpanKind::kInternal) = 0;
+
+    /** Start a new span with an explicit parent context.
+
+        Use this overload when the parent span is not on the current
+        thread's context stack (e.g. cross-thread trace propagation).
+
+        @param name           Span name.
+        @param parentContext  The parent span's context.
+        @param kind           The span kind (defaults to kInternal).
+        @return A shared pointer to the new Span.
+    */
+    virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+    startSpan(
+        std::string_view name,
+        opentelemetry::context::Context const& parentContext,
+        opentelemetry::trace::SpanKind kind = opentelemetry::trace::SpanKind::kInternal) = 0;
+#endif
+};
+
+/** Create a Telemetry instance.
+
+    Returns a TelemetryImpl when setup.enabled is true, or a
+    NullTelemetry no-op stub otherwise.
+
+    @param setup    Configuration from the [telemetry] config section.
+    @param journal  Journal for log output during initialization.
+*/
+std::unique_ptr<Telemetry>
+makeTelemetry(Telemetry::Setup const& setup, beast::Journal journal);
+
+/** Parse the [telemetry] config section into a Setup struct.
+
+    @param section        The [telemetry] config section.
+    @param nodePublicKey  Node public key, used as default instance ID.
+    @param version        Build version string.
+    @param networkId      Network identifier from [network_id] config
+                          (0 = mainnet, 1 = testnet, 2 = devnet).
+    @return A populated Setup struct with defaults for missing values.
+*/
+Telemetry::Setup
+makeTelemetrySetup(
+    Section const& section,
+    std::string const& nodePublicKey,
+    std::string const& version,
+    std::uint32_t networkId);
+
+}  // namespace xrpl::telemetry

src/libxrpl/telemetry/NullTelemetry.cpp

@@ -0,0 +1,137 @@
+/** No-op implementation of the Telemetry interface.
+
+    Always compiled (regardless of XRPL_ENABLE_TELEMETRY). Provides the
+    makeTelemetry() factory when telemetry is compiled out (#ifndef), which
+    unconditionally returns a NullTelemetry that does nothing.
+
+    When XRPL_ENABLE_TELEMETRY IS defined, the OTel virtual methods
+    (getTracer, startSpan) return noop tracers/spans. The makeTelemetry()
+    factory in this file is not used in that case -- Telemetry.cpp provides
+    its own factory that can return the real TelemetryImpl.
+*/
+
+#include <xrpl/telemetry/Telemetry.h>
+
+#include <memory>
+#include <utility>
+
+#ifdef XRPL_ENABLE_TELEMETRY
+#include <opentelemetry/context/context.h>
+#include <opentelemetry/nostd/shared_ptr.h>
+#include <opentelemetry/trace/noop.h>
+#include <opentelemetry/trace/span.h>
+#include <opentelemetry/trace/span_metadata.h>
+#include <opentelemetry/trace/tracer.h>
+
+#include <string_view>
+#endif
+
+namespace xrpl::telemetry {
+
+namespace {
+
+/** No-op Telemetry that returns immediately from every method.
+
+    Used as the sole implementation when XRPL_ENABLE_TELEMETRY is not
+    defined, or as a fallback when it is defined but enabled=0.
+*/
+class NullTelemetry : public Telemetry
+{
+    /** Retained configuration (unused, kept for diagnostic access). */
+    Setup const setup_;
+
+public:
+    explicit NullTelemetry(Setup setup) : setup_{std::move(setup)}
+    {
+    }
+
+    void
+    start() override
+    {
+        Telemetry::setInstance(this);
+    }
+
+    void
+    stop() override
+    {
+        Telemetry::setInstance(nullptr);
+    }
+
+    [[nodiscard]] bool
+    isEnabled() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceTransactions() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceConsensus() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceRpc() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTracePeer() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceLedger() const override
+    {
+        return false;
+    }
+
+#ifdef XRPL_ENABLE_TELEMETRY
+    opentelemetry::nostd::shared_ptr<opentelemetry::trace::Tracer>
+    getTracer(std::string_view) override
+    {
+        static auto noopTracer = opentelemetry::nostd::shared_ptr<opentelemetry::trace::Tracer>(
+            new opentelemetry::trace::NoopTracer());
+        return noopTracer;
+    }
+
+    opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+    startSpan(std::string_view, opentelemetry::trace::SpanKind) override
+    {
+        return opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>(
+            new opentelemetry::trace::NoopSpan(nullptr));
+    }
+
+    opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+    startSpan(
+        std::string_view,
+        opentelemetry::context::Context const&,
+        opentelemetry::trace::SpanKind) override
+    {
+        return opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>(
+            new opentelemetry::trace::NoopSpan(nullptr));
+    }
+#endif
+};
+
+}  // namespace
+
+/** Factory used when XRPL_ENABLE_TELEMETRY is not defined.
+    Unconditionally returns a NullTelemetry instance.
+*/
+#ifndef XRPL_ENABLE_TELEMETRY
+std::unique_ptr<Telemetry>
+makeTelemetry(Telemetry::Setup const& setup, beast::Journal)
+{
+    return std::make_unique<NullTelemetry>(setup);
+}
+#endif
+
+}  // namespace xrpl::telemetry

src/libxrpl/telemetry/Redaction.cpp

@@ -0,0 +1,31 @@
+#include <xrpl/telemetry/Redaction.h>
+
+#include <xrpl/basics/Slice.h>
+#include <xrpl/basics/base_uint.h>
+#include <xrpl/protocol/digest.h>
+
+#include <algorithm>
+#include <cctype>
+#include <string>
+#include <string_view>
+
+namespace xrpl::telemetry {
+
+std::string
+redactAccount(std::string_view addr)
+{
+    // Empty in, empty out: nothing to hash and no token to emit.
+    if (addr.empty())
+        return {};
+
+    // sha512Half yields a uint256; to_string renders it as uppercase hex.
+    // Keep the first 16 chars (64 bits) — enough to correlate spans while
+    // staying non-reversible — and lowercase them for a stable token.
+    auto const digest = sha512Half(Slice(addr.data(), addr.size()));
+    std::string token = to_string(digest).substr(0, 16);
+    std::ranges::transform(
+        token, token.begin(), [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
+    return token;
+}
+
+}  // namespace xrpl::telemetry

src/libxrpl/telemetry/SpanGuard.cpp

@@ -0,0 +1,378 @@
+/** Pimpl implementation for SpanGuard and SpanContext.
+
+    All OpenTelemetry SDK types are confined to this translation unit.
+    The public SpanGuard.h header contains only standard-library types
+    and forward-declares the Impl struct.
+
+    Static factory methods access the global Telemetry instance via
+    Telemetry::getInstance(), check whether the requested TraceCategory
+    is enabled, and return either an active guard with a real Span+Scope
+    or a null guard whose methods are all no-ops.
+
+    The Impl struct holds the OTel Span (shared_ptr) and Scope.
+    Scope is non-movable, but since Impl lives behind a unique_ptr,
+    SpanGuard's move constructor simply transfers the pointer — no
+    double-Scope issues.
+
+    @see SpanGuard (SpanGuard.h), Telemetry (Telemetry.h),
+         FilteringSpanProcessor (Telemetry.cpp)
+*/
+
+#ifdef XRPL_ENABLE_TELEMETRY
+
+#include <xrpl/telemetry/SpanGuard.h>
+
+#include <xrpl/telemetry/DiscardFlag.h>
+#include <xrpl/telemetry/Telemetry.h>
+
+#include <opentelemetry/context/context.h>
+#include <opentelemetry/context/runtime_context.h>
+#include <opentelemetry/nostd/shared_ptr.h>
+#include <opentelemetry/semconv/exception_attributes.h>
+#include <opentelemetry/trace/context.h>
+#include <opentelemetry/trace/scope.h>
+#include <opentelemetry/trace/span.h>
+#include <opentelemetry/trace/span_metadata.h>
+#include <opentelemetry/trace/span_startoptions.h>
+
+#include <cstdint>
+#include <exception>
+#include <format>
+#include <memory>
+#include <string>
+#include <string_view>
+#include <typeinfo>
+#include <utility>
+
+namespace xrpl::telemetry {
+
+namespace otel_trace = opentelemetry::trace;
+
+// ===== SpanContext::Impl ===================================================
+
+struct SpanContext::Impl
+{
+    opentelemetry::context::Context ctx;
+
+    explicit Impl(opentelemetry::context::Context c) : ctx(std::move(c))
+    {
+    }
+};
+
+SpanContext::SpanContext(std::shared_ptr<Impl> impl) : impl_(std::move(impl))
+{
+}
+
+bool
+SpanContext::isValid() const
+{
+    return impl_ != nullptr;
+}
+
+// ===== SpanGuard::Impl ====================================================
+
+struct SpanGuard::Impl
+{
+    /** The OTel span being guarded. Set to nullptr after discard(). */
+    opentelemetry::nostd::shared_ptr<otel_trace::Span> span;
+
+    /** Scope that activates span on the current thread's context stack. */
+    otel_trace::Scope scope;
+
+    explicit Impl(opentelemetry::nostd::shared_ptr<otel_trace::Span> s)
+        : span(std::move(s)), scope(span)
+    {
+    }
+
+    ~Impl()
+    {
+        if (span)
+            span->End();
+    }
+
+    Impl(Impl const&) = delete;
+    Impl&
+    operator=(Impl const&) = delete;
+    Impl(Impl&&) = delete;
+    Impl&
+    operator=(Impl&&) = delete;
+};
+
+// ===== SpanGuard core lifecycle ============================================
+
+SpanGuard::SpanGuard() = default;
+SpanGuard::~SpanGuard() = default;
+SpanGuard::SpanGuard(SpanGuard&&) noexcept = default;
+
+SpanGuard::SpanGuard(std::unique_ptr<Impl> impl) : impl_(std::move(impl))
+{
+}
+
+SpanGuard::
+operator bool() const
+{
+    return impl_ != nullptr;
+}
+
+// ===== Static factory methods ==============================================
+
+/** Check whether the given TraceCategory is enabled on the Telemetry instance.
+    @return true if the category's shouldTrace*() flag is on.
+*/
+static bool
+isCategoryEnabled(Telemetry const& tel, TraceCategory cat)
+{
+    switch (cat)
+    {
+        case TraceCategory::Rpc:
+            return tel.shouldTraceRpc();
+        case TraceCategory::Transactions:
+            return tel.shouldTraceTransactions();
+        case TraceCategory::Consensus:
+            return tel.shouldTraceConsensus();
+        case TraceCategory::Peer:
+            return tel.shouldTracePeer();
+        case TraceCategory::Ledger:
+            return tel.shouldTraceLedger();
+    }
+    return false;  // unreachable, silences compiler warning
+}
+
+namespace {
+
+// Span-link attribute marking a "follows-from" (causal, non-parent) link,
+// emitted by both linkedSpan() overloads. Custom xrpl attribute — not part
+// of the OTel semantic conventions, so defined here rather than pulled from
+// <opentelemetry/semconv/...>.
+constexpr char const* kLinkTypeKey = "link_type";
+constexpr char const* kLinkTypeFollowsFrom = "follows_from";
+
+// Map a TraceCategory to an OTel SpanKind so Tempo's service-graph /
+// RED metrics see the correct direction. RPC spans are emitted at the
+// server entry point (handler dispatch), Peer spans at inbound-message
+// receipt. Transactions / Consensus / Ledger are internal processing
+// and keep the default kInternal.
+otel_trace::SpanKind
+categoryToSpanKind(TraceCategory cat)
+{
+    switch (cat)
+    {
+        case TraceCategory::Rpc:
+            return otel_trace::SpanKind::kServer;
+        case TraceCategory::Peer:
+            return otel_trace::SpanKind::kConsumer;
+        case TraceCategory::Transactions:
+        case TraceCategory::Consensus:
+        case TraceCategory::Ledger:
+            return otel_trace::SpanKind::kInternal;
+    }
+    return otel_trace::SpanKind::kInternal;  // unreachable
+}
+
+}  // namespace
+
+SpanGuard
+SpanGuard::span(TraceCategory cat, std::string_view prefix, std::string_view name)
+{
+    auto* tel = Telemetry::getInstance();
+    if ((tel == nullptr) || !tel->isEnabled() || !isCategoryEnabled(*tel, cat))
+        return {};
+    auto fullName = std::format("{}.{}", prefix, name);
+    return SpanGuard(std::make_unique<Impl>(tel->startSpan(fullName, categoryToSpanKind(cat))));
+}
+
+// ===== Child / linked span creation ========================================
+
+SpanGuard
+SpanGuard::childSpan(std::string_view name) const
+{
+    if (!impl_)
+        return {};
+    auto* tel = Telemetry::getInstance();
+    if ((tel == nullptr) || !tel->isEnabled())
+        return {};
+    auto ctx = opentelemetry::context::RuntimeContext::GetCurrent();
+    return SpanGuard(std::make_unique<Impl>(tel->startSpan(name, ctx)));
+}
+
+SpanGuard
+SpanGuard::childSpan(std::string_view name, SpanContext const& parentCtx)
+{
+    if (!parentCtx.isValid())
+        return {};
+    auto* tel = Telemetry::getInstance();
+    if ((tel == nullptr) || !tel->isEnabled())
+        return {};
+    return SpanGuard(std::make_unique<Impl>(tel->startSpan(name, parentCtx.impl_->ctx)));
+}
+
+SpanGuard
+SpanGuard::linkedSpan(std::string_view name) const
+{
+    if (!impl_)
+        return {};
+    auto* tel = Telemetry::getInstance();
+    if ((tel == nullptr) || !tel->isEnabled())
+        return {};
+
+    auto tracer = tel->getTracer();
+    auto spanCtx = impl_->span->GetContext();
+
+    // Mark as root span so it starts a new trace sub-tree rather than
+    // inheriting the current thread's active span as parent.
+    otel_trace::StartSpanOptions opts;
+    opts.parent = opentelemetry::context::Context{otel_trace::kIsRootSpanKey, true};
+
+    // LCOV_EXCL_START
+    return SpanGuard(
+        std::make_unique<Impl>(tracer->StartSpan(
+            std::string(name), {}, {{spanCtx, {{kLinkTypeKey, kLinkTypeFollowsFrom}}}}, opts)));
+    // LCOV_EXCL_STOP
+}
+
+SpanGuard
+SpanGuard::linkedSpan(std::string_view name, SpanContext const& linkCtx)
+{
+    if (!linkCtx.isValid())
+        return {};
+    auto* tel = Telemetry::getInstance();
+    if ((tel == nullptr) || !tel->isEnabled())
+        return {};
+
+    auto tracer = tel->getTracer();
+
+    // Extract the span from the captured context to get its SpanContext.
+    auto linkSpan = otel_trace::GetSpan(linkCtx.impl_->ctx);
+    if (!linkSpan || !linkSpan->GetContext().IsValid())
+        return {};
+
+    // Mark as root span so it starts a new trace sub-tree rather than
+    // inheriting the current thread's active span as parent.
+    otel_trace::StartSpanOptions opts;
+    opts.parent = opentelemetry::context::Context{otel_trace::kIsRootSpanKey, true};
+
+    // LCOV_EXCL_START
+    return SpanGuard(
+        std::make_unique<Impl>(tracer->StartSpan(
+            std::string(name),
+            {},
+            {{linkSpan->GetContext(), {{kLinkTypeKey, kLinkTypeFollowsFrom}}}},
+            opts)));
+    // LCOV_EXCL_STOP
+}
+
+// ===== Context capture =====================================================
+
+SpanContext
+SpanGuard::captureContext() const
+{
+    if (!impl_)
+        return {};
+    auto ctx = opentelemetry::context::RuntimeContext::GetCurrent();
+    return SpanContext(std::make_shared<SpanContext::Impl>(std::move(ctx)));
+}
+
+// ===== Attribute setters ===================================================
+
+void
+SpanGuard::setAttribute(std::string_view key, std::string_view value)
+{
+    if (impl_)
+    {
+        impl_->span->SetAttribute(
+            opentelemetry::nostd::string_view(key.data(), key.size()),
+            opentelemetry::nostd::string_view(value.data(), value.size()));
+    }
+}
+
+void
+SpanGuard::setAttribute(std::string_view key, char const* value)
+{
+    setAttribute(key, std::string_view(value));
+}
+
+void
+SpanGuard::setAttribute(std::string_view key, std::int64_t value)
+{
+    if (impl_)
+        impl_->span->SetAttribute(opentelemetry::nostd::string_view(key.data(), key.size()), value);
+}
+
+void
+SpanGuard::setAttribute(std::string_view key, double value)
+{
+    if (impl_)
+        impl_->span->SetAttribute(opentelemetry::nostd::string_view(key.data(), key.size()), value);
+}
+
+void
+SpanGuard::setAttribute(std::string_view key, bool value)
+{
+    if (impl_)
+        impl_->span->SetAttribute(opentelemetry::nostd::string_view(key.data(), key.size()), value);
+}
+
+// ===== Status / events =====================================================
+
+void
+SpanGuard::setOk()
+{
+    if (impl_)
+        impl_->span->SetStatus(otel_trace::StatusCode::kOk);
+}
+
+void
+SpanGuard::setError(std::string_view description)
+{
+    if (impl_)
+        impl_->span->SetStatus(otel_trace::StatusCode::kError, std::string(description));
+}
+
+void
+SpanGuard::addEvent(std::string_view name)
+{
+    if (impl_)
+        impl_->span->AddEvent(std::string(name));
+}
+
+void
+SpanGuard::recordException(std::exception const& e)
+{
+    if (!impl_)
+        return;
+    namespace semconv_exc = opentelemetry::semconv::exception;
+    // Event name "exception" and the attribute keys follow the OTel semantic
+    // conventions; the keys come from semconv constants rather than literals.
+    impl_->span->AddEvent(
+        "exception",
+        {{semconv_exc::kExceptionType, typeid(e).name()},
+         {semconv_exc::kExceptionMessage, std::string(e.what())}});
+    impl_->span->SetStatus(otel_trace::StatusCode::kError, e.what());
+}
+
+void
+SpanGuard::discard()
+{
+    if (impl_)
+    {
+        {
+            // DiscardScope owns the flag's whole lifetime: it sets the flag,
+            // and clears it on scope exit — even if End() were to throw. The
+            // SDK invokes FilteringSpanProcessor::OnEnd() synchronously from
+            // End() on this thread, so the flag is observed while still set.
+            // Today every valid guard wraps a recording span (head sampling is
+            // 1.0), so OnEnd() always runs — but scoping set/clear keeps the
+            // flag leak-proof if a later phase can hand back a non-recording
+            // span (e.g. honoring a non-sampled remote parent during
+            // propagation), so it can never spill onto the next span.
+            DiscardScope const discardScope;
+            impl_->span->End();
+        }
+        impl_->span = nullptr;  // prevent ~Impl from calling End() again
+        impl_.reset();
+    }
+}
+
+}  // namespace xrpl::telemetry
+
+#endif  // XRPL_ENABLE_TELEMETRY

src/libxrpl/telemetry/Telemetry.cpp

@@ -0,0 +1,442 @@
+/** OpenTelemetry SDK implementation of the Telemetry interface.
+
+    Compiled only when XRPL_ENABLE_TELEMETRY is defined (via CMake
+    telemetry=ON). Contains:
+
+      - FilteringSpanProcessor: decorator that drops spans marked with
+        kDiscardedAttr before they enter the batch export queue.
+      - TelemetryImpl: configures the OTel SDK with an OTLP/HTTP exporter,
+        FilteringSpanProcessor wrapping a batch span processor,
+        trace-ID-ratio sampler, and resource attributes.
+      - NullTelemetryOtel: no-op fallback used when telemetry is compiled in
+        but disabled at runtime (enabled=0 in config).
+      - makeTelemetry(): factory that selects the appropriate implementation.
+*/
+
+#ifdef XRPL_ENABLE_TELEMETRY
+
+#include <xrpl/telemetry/Telemetry.h>
+
+#include <xrpl/basics/Log.h>
+#include <xrpl/beast/utility/Journal.h>
+#include <xrpl/telemetry/DiscardFlag.h>
+#include <xrpl/telemetry/SpanNames.h>
+
+#include <opentelemetry/context/context.h>
+#include <opentelemetry/exporters/otlp/otlp_http_exporter_factory.h>
+#include <opentelemetry/exporters/otlp/otlp_http_exporter_options.h>
+#include <opentelemetry/nostd/shared_ptr.h>
+#include <opentelemetry/sdk/resource/resource.h>
+#include <opentelemetry/sdk/trace/batch_span_processor_factory.h>
+#include <opentelemetry/sdk/trace/batch_span_processor_options.h>
+#include <opentelemetry/sdk/trace/processor.h>
+#include <opentelemetry/sdk/trace/sampler.h>
+#include <opentelemetry/sdk/trace/samplers/parent_factory.h>
+#include <opentelemetry/sdk/trace/samplers/trace_id_ratio.h>
+#include <opentelemetry/sdk/trace/tracer_provider.h>
+#include <opentelemetry/sdk/trace/tracer_provider_factory.h>
+#include <opentelemetry/semconv/incubating/service_attributes.h>
+#include <opentelemetry/trace/noop.h>
+#include <opentelemetry/trace/provider.h>
+#include <opentelemetry/trace/span.h>
+#include <opentelemetry/trace/span_metadata.h>
+#include <opentelemetry/trace/span_startoptions.h>
+#include <opentelemetry/trace/tracer.h>
+#include <opentelemetry/trace/tracer_provider.h>
+
+#include <chrono>
+#include <cstdint>
+#include <memory>
+#include <string>
+#include <string_view>
+#include <utility>
+
+namespace xrpl::telemetry {
+
+namespace {
+
+namespace trace_api = opentelemetry::trace;
+namespace trace_sdk = opentelemetry::sdk::trace;
+namespace otlp_http = opentelemetry::exporter::otlp;
+namespace resource = opentelemetry::sdk::resource;
+
+/** SpanProcessor decorator that drops discarded spans.
+
+    Wraps a delegate processor (typically BatchSpanProcessor). In OnEnd(),
+    calls DiscardScope::isActive(). If the calling thread is inside a
+    DiscardScope (entered by SpanGuard::discard()), the span is silently
+    dropped — never entering the batch queue, never sent over the network,
+    never stored.
+
+    Uses a thread-local flag rather than inspecting Recordable attributes
+    because the Recordable type varies by exporter (SpanData for simple
+    exporters, OtlpRecordable for OTLP) and none expose a uniform getter.
+    The flag is safe because Span::End() calls OnEnd() synchronously on
+    the same thread.
+
+    All other methods delegate directly to the wrapped processor.
+
+    Dependency diagram:
+
+        +---------------------------+
+        | FilteringSpanProcessor    |
+        +---------------------------+
+        | - delegate_ : unique_ptr  |
+        |   <SpanProcessor>         |
+        +---------------------------+
+                    |  wraps
+          +---------+-----------+
+          | BatchSpanProcessor  |
+          +---------------------+
+
+    @note Thread safety: OnEnd() may be called concurrently from multiple
+    threads. The discard flag behind DiscardScope is thread-local, so each
+    thread's discard state is independent — no synchronization needed.
+*/
+class FilteringSpanProcessor : public trace_sdk::SpanProcessor
+{
+    std::unique_ptr<trace_sdk::SpanProcessor> delegate_;
+
+public:
+    explicit FilteringSpanProcessor(std::unique_ptr<trace_sdk::SpanProcessor> delegate)
+        : delegate_(std::move(delegate))
+    {
+    }
+
+    std::unique_ptr<trace_sdk::Recordable>
+    MakeRecordable() noexcept override
+    {
+        return delegate_->MakeRecordable();
+    }
+
+    void
+    OnStart(
+        trace_sdk::Recordable& span,
+        opentelemetry::trace::SpanContext const& parentContext) noexcept override
+    {
+        delegate_->OnStart(span, parentContext);
+    }
+
+    void
+    OnEnd(std::unique_ptr<trace_sdk::Recordable>&& span) noexcept override
+    {
+        if (DiscardScope::isActive())
+        {
+            // SpanGuard::discard() is inside a DiscardScope on this thread,
+            // which it entered just before calling Span::End() — and End()
+            // invokes OnEnd() synchronously. Drop the span.
+            return;
+        }
+        delegate_->OnEnd(std::move(span));
+    }
+
+    bool
+    ForceFlush(
+        std::chrono::microseconds timeout = std::chrono::microseconds::max()) noexcept override
+    {
+        return delegate_->ForceFlush(timeout);
+    }
+
+    bool
+    Shutdown(std::chrono::microseconds timeout = std::chrono::microseconds::max()) noexcept override
+    {
+        return delegate_->Shutdown(timeout);
+    }
+};
+
+/** No-op implementation used when XRPL_ENABLE_TELEMETRY is defined but
+    setup.enabled is false at runtime.
+
+    Lives in the anonymous namespace so there is no ODR conflict with the
+    NullTelemetry in NullTelemetry.cpp.
+*/
+class NullTelemetryOtel : public Telemetry
+{
+    /** Retained configuration (unused, kept for diagnostic access). */
+    Setup const setup_;
+
+public:
+    explicit NullTelemetryOtel(Setup setup) : setup_(std::move(setup))
+    {
+    }
+
+    void
+    start() override
+    {
+        Telemetry::setInstance(this);
+    }
+
+    void
+    stop() override
+    {
+        Telemetry::setInstance(nullptr);
+    }
+
+    [[nodiscard]] bool
+    isEnabled() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceTransactions() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceConsensus() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceRpc() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTracePeer() const override
+    {
+        return false;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceLedger() const override
+    {
+        return false;
+    }
+
+    opentelemetry::nostd::shared_ptr<trace_api::Tracer>
+    getTracer(std::string_view) override
+    {
+        static auto noopTracer =
+            opentelemetry::nostd::shared_ptr<trace_api::Tracer>(new trace_api::NoopTracer());
+        return noopTracer;
+    }
+
+    opentelemetry::nostd::shared_ptr<trace_api::Span>
+    startSpan(std::string_view, trace_api::SpanKind) override
+    {
+        return opentelemetry::nostd::shared_ptr<trace_api::Span>(new trace_api::NoopSpan(nullptr));
+    }
+
+    opentelemetry::nostd::shared_ptr<trace_api::Span>
+    startSpan(std::string_view, opentelemetry::context::Context const&, trace_api::SpanKind)
+        override
+    {
+        return opentelemetry::nostd::shared_ptr<trace_api::Span>(new trace_api::NoopSpan(nullptr));
+    }
+};
+
+/** Full OTel SDK implementation that exports trace spans via OTLP/HTTP.
+
+    Configures an OTLP/HTTP exporter, batch span processor,
+    TraceIdRatioBasedSampler, and resource attributes on start().
+*/
+class TelemetryImpl : public Telemetry
+{
+    /** Configuration from the [telemetry] config section.
+        Non-const so setServiceInstanceId() can update the instance ID
+        before start() creates the OTel resource.
+    */
+    Setup setup_;
+
+    /** Journal used for log output during start/stop. */
+    beast::Journal const journal_;
+
+    /** The SDK TracerProvider that owns the export pipeline.
+
+        Held as std::shared_ptr so we can call ForceFlush() on shutdown.
+        Wrapped in a nostd::shared_ptr when registered as the global provider.
+    */
+    std::shared_ptr<trace_sdk::TracerProvider> sdkProvider_;
+
+public:
+    TelemetryImpl(Setup setup, beast::Journal journal) : setup_(std::move(setup)), journal_(journal)
+    {
+    }
+
+    void
+    setServiceInstanceId(std::string const& id) override
+    {
+        setup_.serviceInstanceId = id;
+    }
+
+    void
+    start() override
+    {
+        JLOG(journal_.info()) << "Telemetry starting: endpoint=" << setup_.exporterEndpoint
+                              << " sampling=" << setup_.samplingRatio;
+
+        // Configure OTLP HTTP exporter
+        otlp_http::OtlpHttpExporterOptions exporterOpts;
+        exporterOpts.url = setup_.exporterEndpoint;
+        if (setup_.useTls)
+        {
+            exporterOpts.ssl_ca_cert_path = setup_.tlsCertPath;
+        }
+
+        auto exporter = otlp_http::OtlpHttpExporterFactory::Create(exporterOpts);
+
+        // Configure batch processor
+        trace_sdk::BatchSpanProcessorOptions processorOpts;
+        processorOpts.max_queue_size = setup_.maxQueueSize;
+        processorOpts.schedule_delay_millis = std::chrono::milliseconds(setup_.batchDelay);
+        processorOpts.max_export_batch_size = setup_.batchSize;
+
+        auto batchProcessor =
+            trace_sdk::BatchSpanProcessorFactory::Create(std::move(exporter), processorOpts);
+
+        // Wrap batch processor with filtering processor that drops spans
+        // marked with kDiscardedAttr (via SpanGuard::discard()).
+        auto processor = std::make_unique<FilteringSpanProcessor>(std::move(batchProcessor));
+
+        // Configure resource attributes
+        auto resourceAttrs = resource::Resource::Create({
+            {opentelemetry::semconv::service::kServiceName, setup_.serviceName},
+            {opentelemetry::semconv::service::kServiceVersion, setup_.serviceVersion},
+            {opentelemetry::semconv::service::kServiceInstanceId, setup_.serviceInstanceId},
+            {std::string(attr::networkId),
+             static_cast<int64_t>(setup_.networkId)},              // LCOV_EXCL_LINE
+            {std::string(attr::networkType), setup_.networkType},  // LCOV_EXCL_LINE
+        });
+
+        // Configure sampler. Head sampling is fixed at 1.0 (sample everything);
+        // setup_.samplingRatio is not config-driven. Wrap the ratio sampler in a
+        // ParentBasedSampler so spans with a remote parent honor the upstream
+        // sampled flag — this keeps keep/drop decisions coherent for a single
+        // distributed trace spanning multiple nodes. Volume reduction is left to
+        // the collector's tail sampling.
+        auto rootSampler =
+            std::make_shared<trace_sdk::TraceIdRatioBasedSampler>(setup_.samplingRatio);
+        auto sampler = trace_sdk::ParentBasedSamplerFactory::Create(std::move(rootSampler));
+
+        // Create TracerProvider
+        sdkProvider_ = trace_sdk::TracerProviderFactory::Create(
+            std::move(processor), resourceAttrs, std::move(sampler));
+
+        // Set as global provider
+        trace_api::Provider::SetTracerProvider(
+            opentelemetry::nostd::shared_ptr<trace_api::TracerProvider>(sdkProvider_));
+
+        // Register as the global Telemetry instance so SpanGuard factory
+        // methods can access it without callers passing a reference.
+        Telemetry::setInstance(this);
+
+        JLOG(journal_.info()) << "Telemetry started successfully";
+    }
+
+    void
+    stop() override
+    {
+        JLOG(journal_.info()) << "Telemetry stopping";
+
+        // Unregister global instance before tearing down the pipeline.
+        Telemetry::setInstance(nullptr);
+
+        if (sdkProvider_)
+        {
+            // Force flush with timeout to avoid blocking indefinitely
+            // when the OTLP endpoint is unreachable.
+            sdkProvider_->ForceFlush(std::chrono::milliseconds(5000));
+            // TODO: sdkProvider_ is not thread-safe. This reset() races with
+            // getTracer() if any thread is still calling startSpan().
+            // Currently safe because Application::stop() shuts down
+            // serverHandler_, overlay_, and jobQueue_ before calling
+            // telemetry_->stop() — so no callers should remain. If the
+            // shutdown order ever changes, add an std::atomic<bool> stopped_
+            // flag checked in getTracer() to make this robust.
+            sdkProvider_.reset();
+            trace_api::Provider::SetTracerProvider(
+                opentelemetry::nostd::shared_ptr<trace_api::TracerProvider>(
+                    new trace_api::NoopTracerProvider()));
+        }
+        JLOG(journal_.info()) << "Telemetry stopped";
+    }
+
+    [[nodiscard]] bool
+    isEnabled() const override
+    {
+        return true;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceTransactions() const override
+    {
+        return setup_.traceTransactions;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceConsensus() const override
+    {
+        return setup_.traceConsensus;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceRpc() const override
+    {
+        return setup_.traceRpc;
+    }
+
+    [[nodiscard]] bool
+    shouldTracePeer() const override
+    {
+        return setup_.tracePeer;
+    }
+
+    [[nodiscard]] bool
+    shouldTraceLedger() const override
+    {
+        return setup_.traceLedger;
+    }
+
+    opentelemetry::nostd::shared_ptr<trace_api::Tracer>
+    getTracer(std::string_view name = kTracerName) override
+    {
+        if (!sdkProvider_)
+        {
+            return trace_api::Provider::GetTracerProvider()->GetTracer(std::string(name));
+        }
+        return sdkProvider_->GetTracer(std::string(name));
+    }
+
+    opentelemetry::nostd::shared_ptr<trace_api::Span>
+    startSpan(std::string_view name, trace_api::SpanKind kind) override
+    {
+        auto tracer = getTracer();
+        trace_api::StartSpanOptions opts;
+        opts.kind = kind;
+        return tracer->StartSpan(std::string(name), opts);
+    }
+
+    opentelemetry::nostd::shared_ptr<trace_api::Span>
+    startSpan(
+        std::string_view name,
+        opentelemetry::context::Context const& parentContext,
+        trace_api::SpanKind kind) override
+    {
+        auto tracer = getTracer();
+        trace_api::StartSpanOptions opts;
+        opts.kind = kind;
+        opts.parent = parentContext;
+        return tracer->StartSpan(std::string(name), opts);
+    }
+};
+
+}  // namespace
+
+std::unique_ptr<Telemetry>
+makeTelemetry(Telemetry::Setup const& setup, beast::Journal journal)
+{
+    if (setup.enabled)
+    {
+        return std::make_unique<TelemetryImpl>(setup, journal);
+    }
+    return std::make_unique<NullTelemetryOtel>(setup);
+}
+
+}  // namespace xrpl::telemetry
+
+#endif  // XRPL_ENABLE_TELEMETRY

src/libxrpl/telemetry/TelemetryConfig.cpp

@@ -0,0 +1,124 @@
+/** Parser for the [telemetry] section of xrpld.cfg.
+
+    Reads configuration values from the config file and populates a
+    Telemetry::Setup struct. All options have sensible defaults so the
+    section can be minimal or omitted entirely.
+
+    See cfg/xrpld-example.cfg for the full list of available options.
+*/
+
+#include <xrpl/config/BasicConfig.h>
+#include <xrpl/telemetry/Telemetry.h>
+
+#include <chrono>
+#include <cstdint>
+#include <string>
+
+namespace xrpl::telemetry {
+
+namespace {
+
+/** Config key names for the [telemetry] section.
+
+    Each must match the corresponding option documented in
+    cfg/xrpld-example.cfg verbatim. Defined as `char const*` so they
+    pass to Section::valueOr() (which takes `std::string const&`)
+    without an explicit conversion, exactly as a literal would.
+*/
+namespace key {
+constexpr char const* enabled = "enabled";
+constexpr char const* serviceName = "service_name";
+constexpr char const* serviceInstanceId = "service_instance_id";
+constexpr char const* endpoint = "endpoint";
+constexpr char const* useTls = "use_tls";
+constexpr char const* tlsCaCert = "tls_ca_cert";
+constexpr char const* batchSize = "batch_size";
+constexpr char const* batchDelayMs = "batch_delay_ms";
+constexpr char const* maxQueueSize = "max_queue_size";
+constexpr char const* traceTransactions = "trace_transactions";
+constexpr char const* traceConsensus = "trace_consensus";
+constexpr char const* traceRpc = "trace_rpc";
+constexpr char const* tracePeer = "trace_peer";
+constexpr char const* traceLedger = "trace_ledger";
+}  // namespace key
+
+/** Default values applied when a key is absent from the config.
+
+    @note serviceName mirrors SystemParameters' systemName() ("xrpld") but
+    is duplicated here as a literal: the telemetry module deliberately does
+    not link xrpl.libxrpl.protocol, so including SystemParameters.h would
+    introduce an undeclared cross-module dependency.
+*/
+namespace dflt {
+constexpr char const* serviceName = "xrpld";
+constexpr char const* endpoint = "http://localhost:4318/v1/traces";
+constexpr std::uint32_t batchSize = 512u;
+constexpr std::uint32_t batchDelayMs = 5000u;
+constexpr std::uint32_t maxQueueSize = 2048u;
+}  // namespace dflt
+
+/** Derive a human-readable network type label from the numeric network ID.
+    @param networkId  The network identifier from [network_id] config.
+    @return "mainnet", "testnet", "devnet", or "unknown" for other values.
+*/
+std::string
+networkTypeFromId(std::uint32_t networkId)
+{
+    switch (networkId)
+    {
+        case 0:
+            return "mainnet";
+        case 1:
+            return "testnet";
+        case 2:
+            return "devnet";
+        default:
+            return "unknown";
+    }
+}
+
+}  // namespace
+
+Telemetry::Setup
+makeTelemetrySetup(
+    Section const& section,
+    std::string const& nodePublicKey,
+    std::string const& version,
+    std::uint32_t networkId)
+{
+    Telemetry::Setup setup;
+
+    setup.enabled = section.valueOr<int>(key::enabled, 0) != 0;
+    setup.serviceName = section.valueOr<std::string>(key::serviceName, dflt::serviceName);
+    setup.serviceVersion = version;
+    setup.serviceInstanceId = section.valueOr<std::string>(key::serviceInstanceId, nodePublicKey);
+
+    setup.exporterEndpoint = section.valueOr<std::string>(key::endpoint, dflt::endpoint);
+
+    setup.useTls = section.valueOr<int>(key::useTls, 0) != 0;
+    setup.tlsCertPath = section.valueOr<std::string>(key::tlsCaCert, "");
+
+    // Head sampling is intentionally fixed at 1.0 (sample everything) and is
+    // not read from config. A per-node ratio would let nodes make divergent
+    // keep/drop decisions for the same distributed trace, producing broken
+    // traces; volume reduction is delegated to the collector's tail sampling.
+    // setup.samplingRatio is a const member fixed at 1.0; nothing to parse.
+
+    setup.batchSize = section.valueOr<std::uint32_t>(key::batchSize, dflt::batchSize);
+    setup.batchDelay = std::chrono::milliseconds{
+        section.valueOr<std::uint32_t>(key::batchDelayMs, dflt::batchDelayMs)};
+    setup.maxQueueSize = section.valueOr<std::uint32_t>(key::maxQueueSize, dflt::maxQueueSize);
+
+    setup.networkId = networkId;
+    setup.networkType = networkTypeFromId(networkId);
+
+    setup.traceTransactions = section.valueOr<int>(key::traceTransactions, 1) != 0;
+    setup.traceConsensus = section.valueOr<int>(key::traceConsensus, 1) != 0;
+    setup.traceRpc = section.valueOr<int>(key::traceRpc, 1) != 0;
+    setup.tracePeer = section.valueOr<int>(key::tracePeer, 1) != 0;
+    setup.traceLedger = section.valueOr<int>(key::traceLedger, 1) != 0;
+
+    return setup;
+}
+
+}  // namespace xrpl::telemetry

src/tests/libxrpl/CMakeLists.txt

@@ -33,6 +33,7 @@ set(test_modules
     shamap
     tx
     protocol_autogen
+    telemetry
 )
 if(NOT WIN32)
     list(APPEND test_modules net)
@@ -63,4 +64,13 @@ if(verify_headers)
     verify_target_headers(xrpl_tests "${CMAKE_CURRENT_SOURCE_DIR}")
 endif()
 
+# The telemetry test module exercises SpanGuard/Telemetry, which link against
+# the OpenTelemetry SDK when the telemetry build option is enabled.
+if(telemetry)
+    target_link_libraries(
+        xrpl_tests
+        PRIVATE opentelemetry-cpp::opentelemetry-cpp
+    )
+endif()
+
 gtest_discover_tests(xrpl_tests DISCOVERY_TIMEOUT 60)

src/tests/libxrpl/helpers/TestServiceRegistry.h

@@ -9,6 +9,7 @@
 #include <xrpl/core/ServiceRegistry.h>
 #include <xrpl/ledger/PendingSaves.h>
 #include <xrpl/server/LoadFeeTrack.h>
+#include <xrpl/telemetry/Telemetry.h>
 
 #include <boost/asio/io_context.hpp>
 
@@ -332,6 +333,12 @@ public:
         throw std::logic_error("TestServiceRegistry::getPerfLog() not implemented");
     }
 
+    telemetry::Telemetry&
+    getTelemetry() override
+    {
+        throw std::logic_error("TestServiceRegistry::getTelemetry() not implemented");
+    }
+
     // Configuration and state
     bool
     isStopping() const override

src/tests/libxrpl/telemetry/Redaction.cpp

@@ -0,0 +1,44 @@
+#include <xrpl/telemetry/Redaction.h>
+
+#include <gtest/gtest.h>
+
+#include <algorithm>
+#include <cctype>
+#include <string>
+
+using namespace xrpl;
+using namespace xrpl::telemetry;
+
+// Empty input must produce empty output (edge / negative path).
+TEST(Redaction, empty_input_returns_empty)
+{
+    EXPECT_EQ(redactAccount(""), "");
+}
+
+// Success path: assert the EXACT expected token. The value is the first
+// 16 chars of sha512Half(addr) rendered as lowercase hex, computed once
+// and hard-coded here so any change to the hashing recipe is caught.
+TEST(Redaction, known_account_exact_hash)
+{
+    EXPECT_EQ(redactAccount("rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"), "a513895f49311f54");
+}
+
+// Structural invariants: length, lowercase-hex alphabet, and stability.
+TEST(Redaction, token_is_16_lowercase_hex_and_stable)
+{
+    auto const token = redactAccount("rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh");
+    EXPECT_EQ(token.size(), 16u);
+    EXPECT_TRUE(std::ranges::all_of(token, [](unsigned char c) {
+        return std::isdigit(c) || (c >= 'a' && c <= 'f');
+    }));
+    // Deterministic: hashing the same input twice yields the same token.
+    EXPECT_EQ(token, redactAccount("rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"));
+}
+
+// Distinct inputs must produce distinct tokens (no accidental constant).
+TEST(Redaction, distinct_inputs_distinct_tokens)
+{
+    EXPECT_NE(
+        redactAccount("rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"),
+        redactAccount("rDifferentAccount1234567890abcdefgh"));
+}

src/tests/libxrpl/telemetry/SpanGuardFactory.cpp

@@ -0,0 +1,82 @@
+#include <xrpl/telemetry/SpanGuard.h>
+
+#include <gtest/gtest.h>
+
+#include <cstdint>
+#include <exception>
+#include <stdexcept>
+#include <utility>
+
+using namespace xrpl;
+using namespace xrpl::telemetry;
+
+TEST(SpanGuardFactory, null_guard_methods_are_safe)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc", "nonexistent");
+    EXPECT_FALSE(span);
+
+    span.setAttribute("key", "value");
+    span.setAttribute("int_key", static_cast<int64_t>(42));
+    span.setAttribute("bool_key", true);
+    span.setOk();
+    span.setError("test");
+    span.addEvent("event");
+}
+
+TEST(SpanGuardFactory, category_span_returns_null_when_disabled)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc", "test");
+    EXPECT_FALSE(span);
+
+    span.setAttribute("command", "test");
+    span.setAttribute("rpc_status", "success");
+}
+
+TEST(SpanGuardFactory, child_span_null_when_no_parent)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc", "parent");
+    auto child = span.childSpan("child.test");
+    EXPECT_FALSE(child);
+}
+
+TEST(SpanGuardFactory, linked_span_null_when_no_context)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc", "source");
+    auto linked = span.linkedSpan("linked.test");
+    EXPECT_FALSE(linked);
+}
+
+TEST(SpanGuardFactory, capture_context_returns_invalid_on_null)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc", "ctx");
+    auto ctx = span.captureContext();
+    EXPECT_FALSE(ctx.isValid());
+}
+
+TEST(SpanGuardFactory, move_construction_transfers_ownership)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc", "move");
+    auto moved = std::move(span);
+    EXPECT_FALSE(span);  // NOLINT(bugprone-use-after-move,hicpp-invalid-access-moved)
+    moved.setAttribute("key", "value");
+}
+
+TEST(SpanGuardFactory, record_exception_safe_on_null)
+{
+    auto span = SpanGuard::span(TraceCategory::Rpc, "rpc.command", "test");
+    try
+    {
+        throw std::runtime_error("test error");
+    }
+    catch (std::exception const& e)
+    {
+        span.recordException(e);
+    }
+}
+
+TEST(SpanGuardFactory, discard_safe_on_null)
+{
+    auto span = SpanGuard::span(TraceCategory::Transactions, "tx", "process");
+    span.discard();
+    EXPECT_FALSE(span);
+}

src/tests/libxrpl/telemetry/TelemetryConfig.cpp

@@ -0,0 +1,105 @@
+#include <xrpl/beast/utility/Journal.h>
+#include <xrpl/config/BasicConfig.h>
+#include <xrpl/telemetry/Telemetry.h>
+
+#include <gtest/gtest.h>
+
+using namespace xrpl;
+
+TEST(TelemetryConfig, setup_defaults)
+{
+    telemetry::Telemetry::Setup const s;
+    EXPECT_FALSE(s.enabled);
+    EXPECT_EQ(s.serviceName, "xrpld");
+    EXPECT_TRUE(s.serviceVersion.empty());
+    EXPECT_TRUE(s.serviceInstanceId.empty());
+    EXPECT_EQ(s.exporterEndpoint, "http://localhost:4318/v1/traces");
+    EXPECT_FALSE(s.useTls);
+    EXPECT_TRUE(s.tlsCertPath.empty());
+    EXPECT_DOUBLE_EQ(s.samplingRatio, 1.0);
+    EXPECT_EQ(s.batchSize, 512u);
+    EXPECT_EQ(s.batchDelay, std::chrono::milliseconds{5000});
+    EXPECT_EQ(s.maxQueueSize, 2048u);
+    EXPECT_EQ(s.networkId, 0u);
+    EXPECT_EQ(s.networkType, "mainnet");
+    EXPECT_TRUE(s.traceTransactions);
+    EXPECT_TRUE(s.traceConsensus);
+    EXPECT_TRUE(s.traceRpc);
+    EXPECT_TRUE(s.tracePeer);
+    EXPECT_TRUE(s.traceLedger);
+}
+
+TEST(TelemetryConfig, parse_empty_section)
+{
+    Section const section;
+    auto setup = telemetry::makeTelemetrySetup(section, "nHUtest123", "2.0.0", 0);
+
+    EXPECT_FALSE(setup.enabled);
+    EXPECT_EQ(setup.serviceName, "xrpld");
+    EXPECT_EQ(setup.serviceVersion, "2.0.0");
+    EXPECT_EQ(setup.serviceInstanceId, "nHUtest123");
+    EXPECT_DOUBLE_EQ(setup.samplingRatio, 1.0);
+    EXPECT_TRUE(setup.traceRpc);
+    EXPECT_TRUE(setup.traceTransactions);
+    EXPECT_TRUE(setup.traceConsensus);
+    EXPECT_TRUE(setup.tracePeer);
+    EXPECT_TRUE(setup.traceLedger);
+}
+
+TEST(TelemetryConfig, parse_full_section)
+{
+    Section section;
+    section.set("enabled", "1");
+    section.set("service_name", "my-rippled");
+    section.set("service_instance_id", "custom-id");
+    section.set("exporter", "otlp_http");
+    section.set("endpoint", "http://collector:4318/v1/traces");
+    section.set("use_tls", "1");
+    section.set("tls_ca_cert", "/etc/ssl/ca.pem");
+    section.set("batch_size", "256");
+    section.set("batch_delay_ms", "3000");
+    section.set("max_queue_size", "4096");
+    section.set("trace_transactions", "0");
+    section.set("trace_consensus", "0");
+    section.set("trace_rpc", "1");
+    section.set("trace_peer", "1");
+    section.set("trace_ledger", "0");
+
+    auto setup = telemetry::makeTelemetrySetup(section, "nHUtest123", "2.0.0", 1);
+
+    EXPECT_TRUE(setup.enabled);
+    EXPECT_EQ(setup.serviceName, "my-rippled");
+    EXPECT_EQ(setup.serviceInstanceId, "custom-id");
+    EXPECT_EQ(setup.exporterEndpoint, "http://collector:4318/v1/traces");
+    EXPECT_TRUE(setup.useTls);
+    EXPECT_EQ(setup.tlsCertPath, "/etc/ssl/ca.pem");
+    EXPECT_EQ(setup.batchSize, 256u);
+    EXPECT_EQ(setup.batchDelay, std::chrono::milliseconds{3000});
+    EXPECT_EQ(setup.maxQueueSize, 4096u);
+    EXPECT_FALSE(setup.traceTransactions);
+    EXPECT_FALSE(setup.traceConsensus);
+    EXPECT_TRUE(setup.traceRpc);
+    EXPECT_TRUE(setup.tracePeer);
+    EXPECT_FALSE(setup.traceLedger);
+}
+
+TEST(TelemetryConfig, null_telemetry_factory)
+{
+    telemetry::Telemetry::Setup setup;
+    setup.enabled = false;
+
+    beast::Journal::Sink& sink = beast::Journal::getNullSink();
+    beast::Journal const j(sink);
+    auto tel = telemetry::makeTelemetry(setup, j);
+    EXPECT_TRUE(tel != nullptr);
+    EXPECT_FALSE(tel->isEnabled());
+    EXPECT_FALSE(tel->shouldTraceRpc());
+    EXPECT_FALSE(tel->shouldTraceTransactions());
+    EXPECT_FALSE(tel->shouldTraceConsensus());
+    EXPECT_FALSE(tel->shouldTracePeer());
+    EXPECT_FALSE(tel->shouldTraceLedger());
+
+    // start/stop should be no-ops without crashing
+    tel->start();
+    tel->stop();
+}

src/xrpld/app/main/Application.cpp

@@ -81,10 +81,12 @@
 #include <xrpl/protocol/Feature.h>
 #include <xrpl/protocol/Indexes.h>  // IWYU pragma: keep
 #include <xrpl/protocol/Protocol.h>
+#include <xrpl/protocol/PublicKey.h>
 #include <xrpl/protocol/STParsedJSON.h>
 #include <xrpl/protocol/Serializer.h>
 #include <xrpl/protocol/SystemParameters.h>  // IWYU pragma: keep
 #include <xrpl/protocol/jss.h>
+#include <xrpl/protocol/tokens.h>
 #include <xrpl/rdb/DatabaseCon.h>
 #include <xrpl/resource/Charge.h>
 #include <xrpl/resource/Consumer.h>
@@ -98,6 +100,7 @@
 #include <xrpl/shamap/SHAMap.h>
 #include <xrpl/shamap/SHAMapMissingNode.h>
 #include <xrpl/shamap/TreeNodeCache.h>
+#include <xrpl/telemetry/Telemetry.h>
 #include <xrpl/tx/apply.h>
 
 #include <boost/algorithm/string/predicate.hpp>
@@ -212,6 +215,7 @@ public:
 
     beast::Journal journal_;
     std::unique_ptr<perf::PerfLog> perfLog_;
+    std::unique_ptr<telemetry::Telemetry> telemetry_;
     Application::MutexType masterMutex_;
 
     // Required by the SHAMapStore
@@ -321,6 +325,15 @@ public:
                   *this,
                   logs_->journal("PerfLog"),
                   [this] { signalStop("PerfLog"); }))
+        , telemetry_(
+              telemetry::makeTelemetry(
+                  telemetry::makeTelemetrySetup(
+                      config_->section("telemetry"),
+                      "",  // Updated later via setServiceInstanceId()
+                      BuildInfo::getVersionString(),
+                      config_->networkId),
+                  logs_->journal("Telemetry")))
+
         , txMaster_(*this)
         , collectorManager_(makeCollectorManager(
               config_->section(Sections::kInsight),
@@ -649,6 +662,12 @@ public:
         return *perfLog_;
     }
 
+    telemetry::Telemetry&
+    getTelemetry() override
+    {
+        return *telemetry_;
+    }
+
     NodeCache&
     getTempNodeCache() override
     {
@@ -1297,6 +1316,14 @@ ApplicationImp::setup(boost::program_options::variables_map const& cmdline)
 
     nodeIdentity_ = getNodeIdentity(*this, cmdline);
 
+    // Now that the node identity is known, inject it into the telemetry
+    // resource attributes — but only if the user didn't already set a
+    // custom service_instance_id in [telemetry].  The Telemetry object
+    // was constructed with an empty serviceInstanceId because
+    // nodeIdentity_ is not available in the member initializer list.
+    if (!config_->section("telemetry").exists("service_instance_id"))
+        telemetry_->setServiceInstanceId(toBase58(TokenType::NodePublic, nodeIdentity_->first));
+
     if (!cluster_->load(config().section(Sections::kClusterNodes)))
     {
         JLOG(journal_.fatal()) << "Invalid entry in cluster configuration.";
@@ -1509,6 +1536,7 @@ ApplicationImp::start(bool withTimers)
 
     ledgerCleaner_->start();
     perfLog_->start();
+    telemetry_->start();
 }
 
 void
@@ -1599,6 +1627,11 @@ ApplicationImp::run()
     ledgerCleaner_->stop();
     nodeStore_->stop();
     perfLog_->stop();
+    // Telemetry must stop last among trace-producing components.
+    // serverHandler_, overlay_, and jobQueue_ are already stopped above,
+    // so no threads should be calling startSpan() at this point.
+    // See TODO in TelemetryImpl::stop() re: thread-safety of sdkProvider_.
+    telemetry_->stop();
 
     JLOG(journal_.info()) << "Done.";
 }

src/xrpld/app/main/GRPCServer.cpp

@@ -2,6 +2,7 @@
 
 #include <xrpld/app/ledger/LedgerMaster.h>  // IWYU pragma: keep
 #include <xrpld/app/main/Application.h>
+#include <xrpld/app/main/GrpcSpanNames.h>
 #include <xrpld/rpc/Context.h>
 #include <xrpld/rpc/GRPCHandlers.h>
 #include <xrpld/rpc/Role.h>
@@ -23,6 +24,7 @@
 #include <xrpl/resource/Consumer.h>
 #include <xrpl/resource/Fees.h>
 #include <xrpl/server/InfoSub.h>
+#include <xrpl/telemetry/SpanGuard.h>
 
 #include <boost/algorithm/string/trim.hpp>
 #include <boost/asio/ip/address.hpp>
@@ -49,6 +51,7 @@
 #include <sstream>
 #include <stdexcept>
 #include <string>
+#include <string_view>
 #include <utility>
 #include <vector>
 
@@ -94,7 +97,8 @@ GRPCServerImpl::CallData<Request, Response>::CallData(
     Forward<Request, Response> forward,
     RPC::Condition requiredCondition,
     Resource::Charge loadType,
-    std::vector<boost::asio::ip::address> const& secureGatewayIPs)
+    std::vector<boost::asio::ip::address> const& secureGatewayIPs,
+    std::string_view name)
     : service_(service)
     , cq_(cq)
     , finished_(false)
@@ -106,6 +110,7 @@ GRPCServerImpl::CallData<Request, Response>::CallData(
     , requiredCondition_(requiredCondition)
     , loadType_(std::move(loadType))
     , secureGatewayIPs_(secureGatewayIPs)
+    , name_(name)
 {
     // Bind a listener. When a request is received, "this" will be returned
     // from CompletionQueue::Next
@@ -125,7 +130,8 @@ GRPCServerImpl::CallData<Request, Response>::clone()
         forward_,
         requiredCondition_,
         loadType_,
-        secureGatewayIPs_);
+        secureGatewayIPs_,
+        name_);
 }
 
 template <class Request, class Response>
@@ -163,12 +169,19 @@ template <class Request, class Response>
 void
 GRPCServerImpl::CallData<Request, Response>::process(std::shared_ptr<JobQueue::Coro> coro)
 {
+    using namespace telemetry;
+    auto span = SpanGuard::span(TraceCategory::Rpc, grpc_span::prefix::grpc, name_);
+    span.setAttribute(grpc_span::attr::method, name_);
+
     try
     {
         auto usage = getUsage();
         bool const isUnlimited = clientIsUnlimited();
         if (!isUnlimited && usage.disconnect(app_.getJournal("gRPCServer")))
         {
+            span.setAttribute(
+                grpc_span::attr::grpcStatus, grpc_span::val::error);  // LCOV_EXCL_LINE
+            span.setError(grpc_span::val::resourceExhausted);         // LCOV_EXCL_LINE
             grpc::Status const status{
                 grpc::StatusCode::RESOURCE_EXHAUSTED, "usage balance exceeds threshold"};
             responder_.FinishWithError(status, this);
@@ -179,6 +192,11 @@ GRPCServerImpl::CallData<Request, Response>::process(std::shared_ptr<JobQueue::C
             usage.charge(loadType);
             auto role = getRole(isUnlimited);
 
+            span.setAttribute(
+                grpc_span::attr::grpcRole,
+                role == Role::ADMIN ? std::string_view{grpc_span::val::admin}
+                                    : std::string_view{grpc_span::val::user});
+
             {
                 std::stringstream toLog;
                 toLog << "role = " << (int)role;
@@ -214,6 +232,9 @@ GRPCServerImpl::CallData<Request, Response>::process(std::shared_ptr<JobQueue::C
             if (conditionMetRes != RpcSuccess)
             {
                 RPC::ErrorInfo const errorInfo = RPC::getErrorInfo(conditionMetRes);
+                span.setAttribute(
+                    grpc_span::attr::grpcStatus, grpc_span::val::error);  // LCOV_EXCL_LINE
+                span.setError(errorInfo.token.cStr());                    // LCOV_EXCL_LINE
                 grpc::Status const status{
                     grpc::StatusCode::FAILED_PRECONDITION, errorInfo.message.cStr()};
                 responder_.FinishWithError(status, this);
@@ -222,12 +243,16 @@ GRPCServerImpl::CallData<Request, Response>::process(std::shared_ptr<JobQueue::C
             {
                 std::pair<Response, grpc::Status> result = handler_(context);
                 setIsUnlimited(result.first, isUnlimited);
+                span.setAttribute(grpc_span::attr::grpcStatus, grpc_span::val::success);
+                span.setOk();
                 responder_.Finish(result.first, result.second, this);
             }
         }
     }
     catch (std::exception const& ex)
     {
+        span.setAttribute(grpc_span::attr::grpcStatus, grpc_span::val::error);  // LCOV_EXCL_LINE
+        span.recordException(ex);                                               // LCOV_EXCL_LINE
         grpc::Status const status{grpc::StatusCode::INTERNAL, ex.what()};
         responder_.FinishWithError(status, this);
     }
@@ -546,7 +571,8 @@ GRPCServerImpl::setupListeners()
                 &org::xrpl::rpc::v1::XRPLedgerAPIService::Stub::GetLedger,
                 Condition::NoCondition,
                 Resource::kFeeMediumBurdenRpc,
-                secureGatewayIPs_));
+                secureGatewayIPs_,
+                "GetLedger"));
     }
     {
         using cd = CallData<
@@ -563,7 +589,8 @@ GRPCServerImpl::setupListeners()
                 &org::xrpl::rpc::v1::XRPLedgerAPIService::Stub::GetLedgerData,
                 Condition::NoCondition,
                 Resource::kFeeMediumBurdenRpc,
-                secureGatewayIPs_));
+                secureGatewayIPs_,
+                "GetLedgerData"));
     }
     {
         using cd = CallData<
@@ -580,7 +607,8 @@ GRPCServerImpl::setupListeners()
                 &org::xrpl::rpc::v1::XRPLedgerAPIService::Stub::GetLedgerDiff,
                 Condition::NoCondition,
                 Resource::kFeeMediumBurdenRpc,
-                secureGatewayIPs_));
+                secureGatewayIPs_,
+                "GetLedgerDiff"));
     }
     {
         using cd = CallData<
@@ -597,7 +625,8 @@ GRPCServerImpl::setupListeners()
                 &org::xrpl::rpc::v1::XRPLedgerAPIService::Stub::GetLedgerEntry,
                 Condition::NoCondition,
                 Resource::kFeeMediumBurdenRpc,
-                secureGatewayIPs_));
+                secureGatewayIPs_,
+                "GetLedgerEntry"));
     }
     return requests;
 }

src/xrpld/app/main/GRPCServer.h

@@ -20,6 +20,7 @@
 #include <memory>
 #include <optional>
 #include <string>
+#include <string_view>
 #include <thread>
 #include <utility>
 #include <vector>
@@ -196,6 +197,9 @@ private:
 
         std::vector<boost::asio::ip::address> const& secureGatewayIPs_;
 
+        /// Human-readable name for telemetry spans (e.g. "GetLedger").
+        std::string_view name_;
+
     public:
         ~CallData() override = default;
 
@@ -211,7 +215,8 @@ private:
             Forward<Request, Response> forward,
             RPC::Condition requiredCondition,
             Resource::Charge loadType,
-            std::vector<boost::asio::ip::address> const& secureGatewayIPs);
+            std::vector<boost::asio::ip::address> const& secureGatewayIPs,
+            std::string_view name = "");
 
         CallData(CallData const&) = delete;
 

src/xrpld/app/main/GrpcSpanNames.h

@@ -0,0 +1,57 @@
+#pragma once
+
+/** Compile-time span name constants for the gRPC subsystem.
+ *
+ *  All span prefixes, operation names, and attribute keys used by gRPC
+ *  tracing call sites are defined here. Built on the StaticStr/join()
+ *  primitives from <xrpl/telemetry/SpanNames.h>.
+ *
+ *  Span hierarchy:
+ *
+ *    +-------------------------------------------------------+
+ *    | grpc.<MethodName>  (e.g. grpc.GetLedger)              |
+ *    | CallData::process(coro)                               |
+ *    |   attrs: method, grpc_role, grpc_status               |
+ *    +-------------------------------------------------------+
+ *
+ *  Unlike the HTTP/WS RPC path, gRPC has a flat single-span structure
+ *  per request since each CallData handles exactly one RPC method.
+ *  The method name is embedded in the span name (rather than only as
+ *  an attribute) so dashboards can break out per-method latency and
+ *  error rates without needing TraceQL attribute filters.
+ */
+
+#include <xrpl/telemetry/SpanNames.h>
+
+namespace xrpl::telemetry::grpc_span {
+
+// ===== Span prefixes =======================================================
+
+namespace prefix {
+/// "grpc" — root prefix for gRPC transport spans. The full span name is
+/// formed at the call site as `grpc.<MethodName>` (see GRPCServer.cpp).
+inline constexpr auto grpc = makeStr("grpc");
+}  // namespace prefix
+
+// ===== Attribute keys ======================================================
+
+namespace attr {
+/// "method" — gRPC method name (e.g. GetLedger).
+inline constexpr auto method = makeStr("method");
+/// "grpc_role" — Domain-qualified: collides with rpc_role.
+inline constexpr auto grpcRole = makeStr("grpc_role");
+/// "grpc_status" — Domain-qualified: avoids OTel reserved span status.
+inline constexpr auto grpcStatus = makeStr("grpc_status");
+}  // namespace attr
+
+// ===== Attribute values ====================================================
+
+namespace val {
+using telemetry::attr_val::error;
+using telemetry::attr_val::success;
+inline constexpr auto admin = makeStr("admin");
+inline constexpr auto user = makeStr("user");
+inline constexpr auto resourceExhausted = makeStr("resource_exhausted");
+}  // namespace val
+
+}  // namespace xrpl::telemetry::grpc_span

src/xrpld/rpc/ServerHandler.h

@@ -192,7 +192,11 @@ private:
     void
     processSession(std::shared_ptr<Session> const&, std::shared_ptr<JobQueue::Coro> coro);
 
-    void
+    /** Process an RPC request and write the reply to `output`.
+        @return false if the request resulted in an error response, true
+                otherwise. Lets the caller's enclosing span reflect the outcome.
+    */
+    bool
     processRequest(
         Port const& port,
         std::string const& request,

src/xrpld/rpc/detail/PathFindSpanNames.h

@@ -0,0 +1,93 @@
+#pragma once
+
+/** Compile-time span name constants for PathFind tracing.
+ *
+ *  Covers the path_find and ripple_path_find RPC handlers, the
+ *  PathRequest computation engine, and the Pathfinder graph exploration.
+ *
+ *  Span hierarchy:
+ *
+ *    RPC entry (one-shot or subscription):
+ *
+ *    +----------------------------------------------------------------+
+ *    | pathfind.request                                               |
+ *    | doPathFind() / doRipplePathFind()                              |
+ *    |   attrs: pathfind_source_account, pathfind_dest_account        |
+ *    |          (set when present in request params)                  |
+ *    |                                                                |
+ *    |  +-----------------------------------------------------------+ |
+ *    |  | pathfind.compute                                          | |
+ *    |  | PathRequest::doUpdate()                                   | |
+ *    |  | attrs: pathfind_fast                                      | |
+ *    |  |                                                           | |
+ *    |  |  +-----------------------------------------------------+  | |
+ *    |  |  | pathfind.discover  (one per RPC call, hoisted above | |
+ *    |  |  | the per-source-asset loop in PathRequest::findPaths)| |
+ *    |  |  |   attrs: pathfind_search_level, pathfind_num_paths  | |
+ *    |  |  +-----------------------------------------------------+ | |
+ *    |  +-----------------------------------------------------------+ |
+ *    +----------------------------------------------------------------+
+ *
+ *    Async recomputation (ledger close):
+ *
+ *    +----------------------------------------------------------------+
+ *    | pathfind.update_all                                            |
+ *    | PathRequestManager::updateAll()                                |
+ *    |   attrs: pathfind_ledger_index, pathfind_num_requests          |
+ *    |                                                                |
+ *    |  +-----------------------------------------------------------+ |
+ *    |  | pathfind.compute  (per active request)                    | |
+ *    |  +-----------------------------------------------------------+ |
+ *    +----------------------------------------------------------------+
+ */
+
+#include <xrpl/telemetry/SpanNames.h>
+
+namespace xrpl::telemetry::pathfind_span {
+
+// ===== Span prefixes =======================================================
+
+namespace prefix {
+/// "pathfind" — root prefix for path finding spans.
+inline constexpr auto pathfind = makeStr("pathfind");
+}  // namespace prefix
+
+// ===== Span operation suffixes =============================================
+
+namespace op {
+inline constexpr auto request = makeStr("request");
+inline constexpr auto compute = makeStr("compute");
+inline constexpr auto updateAll = makeStr("update_all");
+inline constexpr auto discover = makeStr("discover");
+}  // namespace op
+
+// ===== Attribute keys ======================================================
+//
+// All pathfind attributes are namespaced under `pathfind_*` (underscore form,
+// per Phase 1c naming spec rule 5). Avoids collisions with bare keys like
+// `fast` or `num_paths` that other subsystems may introduce.
+
+namespace attr {
+/// "pathfind_source_account" — originating account for path search.
+inline constexpr auto sourceAccount = makeStr("pathfind_source_account");
+/// "pathfind_dest_account" — destination account.
+inline constexpr auto destAccount = makeStr("pathfind_dest_account");
+/// "pathfind_fast" — whether fast pathfinding mode enabled.
+inline constexpr auto fast = makeStr("pathfind_fast");
+/// "pathfind_search_level" — depth of graph exploration.
+inline constexpr auto searchLevel = makeStr("pathfind_search_level");
+/// "pathfind_num_paths" — total paths produced across the per-source-asset
+/// loop in PathRequest::findPaths (sum of getBestPaths().size() per asset).
+inline constexpr auto numPaths = makeStr("pathfind_num_paths");
+/// "pathfind_num_requests" — snapshot size of requests_ at update_all start
+/// (may include weak_ptrs that subsequently expire during processing).
+inline constexpr auto numRequests = makeStr("pathfind_num_requests");
+/// "pathfind_ledger_index" — pathfind target ledger index.
+inline constexpr auto ledgerIndex = makeStr("pathfind_ledger_index");
+/// "pathfind_dest_currency" — destination currency code.
+inline constexpr auto destCurrency = makeStr("pathfind_dest_currency");
+/// "pathfind_num_source_assets" — candidate source assets count.
+inline constexpr auto numSourceAssets = makeStr("pathfind_num_source_assets");
+}  // namespace attr
+
+}  // namespace xrpl::telemetry::pathfind_span

src/xrpld/rpc/detail/PathRequest.cpp

@@ -3,6 +3,7 @@
 #include <xrpld/app/main/Application.h>
 #include <xrpld/core/Config.h>
 #include <xrpld/rpc/detail/AccountAssets.h>
+#include <xrpld/rpc/detail/PathFindSpanNames.h>
 #include <xrpld/rpc/detail/PathRequestManager.h>
 #include <xrpld/rpc/detail/Pathfinder.h>
 #include <xrpld/rpc/detail/PathfinderUtils.h>
@@ -34,10 +35,12 @@
 #include <xrpl/resource/Consumer.h>
 #include <xrpl/server/InfoSub.h>
 #include <xrpl/server/LoadFeeTrack.h>
+#include <xrpl/telemetry/SpanGuard.h>
 #include <xrpl/tx/paths/RippleCalc.h>
 
 #include <algorithm>
 #include <chrono>
+#include <cstdint>
 #include <functional>
 #include <memory>
 #include <mutex>
@@ -579,6 +582,22 @@ PathRequest::findPaths(
 
     auto const dstAmount = convertAmount(saDstAmount_, convertAll_);
     hash_map<PathAsset, std::unique_ptr<Pathfinder>> currencyMap;
+
+    // One `pathfind.discover` span wraps the entire per-source-asset loop so
+    // that a single RPC call produces one discover span instead of N (one per
+    // candidate source asset). Trade-off: per-asset discovery/ranking timing
+    // is no longer split into individual spans — span count and Tempo storage
+    // are bounded per RPC at the cost of per-asset visibility. If per-asset
+    // breakdown is needed in the future, add child spans inside the loop body
+    // (`Pathfinder::findPaths`/`computePathRanks`) parented off this span.
+    using namespace telemetry;
+    auto span = SpanGuard::span(
+        TraceCategory::Rpc, pathfind_span::prefix::pathfind, pathfind_span::op::discover);
+    span.setAttribute(pathfind_span::attr::searchLevel, static_cast<int64_t>(level));
+    span.setAttribute(
+        pathfind_span::attr::numSourceAssets, static_cast<int64_t>(sourceAssets.size()));
+
+    std::int64_t totalPaths = 0;
     for (auto const& asset : sourceAssets)
     {
         if (continueCallback && !continueCallback())
@@ -598,6 +617,7 @@ PathRequest::findPaths(
         auto ps = pathfinder->getBestPaths(
             kMaxPaths, fullLiquidityPath, context_[asset], asset.getIssuer(), continueCallback);
         context_[asset] = ps;
+        totalPaths += static_cast<std::int64_t>(ps.size());
 
         auto const& sourceAccount = [&] {
             if (!isXRP(asset.getIssuer()))
@@ -700,6 +720,8 @@ PathRequest::findPaths(
         }
     }
 
+    span.setAttribute(pathfind_span::attr::numPaths, totalPaths);
+
     /*  The resource fee is based on the number of source currencies used.
         The minimum cost is 50 and the maximum is 400. The cost increases
         after four source currencies, 50 - (4 * 4) = 34.
@@ -716,6 +738,12 @@ PathRequest::doUpdate(
     std::function<bool(void)> const& continueCallback)
 {
     using namespace std::chrono;
+    using namespace telemetry;
+    auto span = SpanGuard::span(
+        TraceCategory::Rpc, pathfind_span::prefix::pathfind, pathfind_span::op::compute);
+    span.setAttribute(pathfind_span::attr::fast, fast);
+    span.setAttribute(pathfind_span::attr::destCurrency, to_string(saDstAmount_.asset()).c_str());
+
     JLOG(journal_.debug()) << iIdentifier_ << " update " << (fast ? "fast" : "normal");
 
     {

src/xrpld/rpc/detail/PathRequestManager.cpp

@@ -3,6 +3,7 @@
 #include <xrpld/app/ledger/LedgerMaster.h>
 #include <xrpld/app/main/Application.h>
 #include <xrpld/rpc/detail/AssetCache.h>
+#include <xrpld/rpc/detail/PathFindSpanNames.h>
 #include <xrpld/rpc/detail/PathRequest.h>
 
 #include <xrpl/basics/Log.h>
@@ -15,6 +16,7 @@
 #include <xrpl/protocol/jss.h>
 #include <xrpl/resource/Consumer.h>
 #include <xrpl/server/InfoSub.h>
+#include <xrpl/telemetry/SpanGuard.h>
 
 #include <algorithm>
 #include <cstdint>
@@ -71,6 +73,19 @@ PathRequestManager::updateAll(std::shared_ptr<ReadView const> const& inLedger)
         cache = getAssetCache(inLedger, true);
     }
 
+    using namespace telemetry;
+    // updateAll runs on every ledger close. Skip span emission when there are
+    // no active path subscriptions, to avoid a steady stream of empty spans at
+    // mainnet close cadence. A null guard is used in that case; all other work
+    // still runs unchanged (notably the isNewPathRequest() flag reset below),
+    // so behaviour matches the pre-span code path.
+    auto span = requests.empty()
+        ? SpanGuard{}
+        : SpanGuard::span(
+              TraceCategory::Rpc, pathfind_span::prefix::pathfind, pathfind_span::op::updateAll);
+    span.setAttribute(pathfind_span::attr::ledgerIndex, static_cast<int64_t>(inLedger->seq()));
+    span.setAttribute(pathfind_span::attr::numRequests, static_cast<int64_t>(requests.size()));
+
     bool newRequests = app_.getLedgerMaster().isNewPathRequest();
     bool mustBreak = false;
 

src/xrpld/rpc/detail/RPCHandler.cpp

@@ -7,6 +7,7 @@
 #include <xrpld/rpc/Role.h>
 #include <xrpld/rpc/Status.h>
 #include <xrpld/rpc/detail/Handler.h>
+#include <xrpld/rpc/detail/RpcSpanNames.h>
 #include <xrpld/rpc/detail/Tuning.h>
 
 #include <xrpl/basics/Log.h>
@@ -17,14 +18,18 @@
 #include <xrpl/protocol/ErrorCodes.h>
 #include <xrpl/protocol/jss.h>
 #include <xrpl/resource/Fees.h>
+#include <xrpl/telemetry/SpanGuard.h>
 
 #include <atomic>
 #include <chrono>
 #include <cstdint>
 #include <exception>
 #include <string>
+#include <string_view>
 
-namespace xrpl::RPC {
+namespace xrpl {
+using namespace telemetry;
+namespace RPC {
 
 namespace {
 
@@ -158,6 +163,14 @@ template <class Object, class Method>
 Status
 callMethod(JsonContext& context, Method method, std::string const& name, Object& result)
 {
+    auto span = SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::command, name);
+    span.setAttribute(rpc_span::attr::command, name.c_str());
+    span.setAttribute(rpc_span::attr::version, static_cast<int64_t>(context.apiVersion));
+    span.setAttribute(
+        rpc_span::attr::rpcRole,
+        context.role == Role::ADMIN ? std::string_view(rpc_span::val::admin)
+                                    : std::string_view(rpc_span::val::user));
+
     static std::atomic<std::uint64_t> kRequestId{0};
     auto& perfLog = context.app.getPerfLog();
     std::uint64_t const curId = ++kRequestId;
@@ -173,12 +186,32 @@ callMethod(JsonContext& context, Method method, std::string const& name, Object&
         JLOG(context.j.debug()) << "RPC call " << name << " completed in "
                                 << ((end - start).count() / 1000000000.0) << "seconds";
         perfLog.rpcFinish(name, curId);
+        span.setAttribute(rpc_span::attr::loadType, context.loadType.label().c_str());
+        // Status::operator bool() returns true when there IS an error
+        // (code_ != OK), so the ternary correctly maps error->error, ok->success.
+        span.setAttribute(
+            rpc_span::attr::rpcStatus,
+            ret ? std::string_view{rpc_span::val::error}
+                : std::string_view{rpc_span::val::success});
+        // Reflect the result in the OTel span status, not just the attribute,
+        // so non-exception RPC errors (rpcTOO_BUSY, rpcNO_PERMISSION, ...) are
+        // visible to {status.code=error} queries.
+        if (ret)
+        {
+            span.setError(rpc_span::val::error);
+        }
+        else
+        {
+            span.setOk();
+        }
         return ret;
     }
     catch (std::exception& e)
     {
         perfLog.rpcError(name, curId);
         JLOG(context.j.info()) << "Caught throw: " << e.what();
+        span.recordException(e);
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
 
         if (context.loadType == Resource::kFeeReferenceRpc)
             context.loadType = Resource::kFeeExceptionRpc;
@@ -188,6 +221,31 @@ callMethod(JsonContext& context, Method method, std::string const& name, Object&
     }
 }
 
+// Resolve the span suffix / command attribute for a request that failed in
+// fillHandler. Returns the canonical handler name for a recognized command
+// (a finite, bounded set) or the literal "unknown" for a request that omits
+// both fields or names an unregistered command. The raw request value is
+// deliberately NOT used: the command attribute is promoted to a Prometheus
+// label by the spanmetrics connector, so an attacker-controlled string would
+// let arbitrary request input drive unbounded span-name / label cardinality.
+// Resolving against the registry keeps per-command error attribution for real
+// commands (e.g. a submit rejected with rpcTOO_BUSY stays rpc.command.submit)
+// while collapsing garbage input to a single series.
+std::string_view
+resolveCommandSpanName(JsonContext const& context)
+{
+    if (!context.params.isMember(jss::command) && !context.params.isMember(jss::method))
+        return rpc_span::val::unknownCommand;
+
+    std::string const cmd = context.params.isMember(jss::command)
+        ? context.params[jss::command].asString()
+        : context.params[jss::method].asString();
+
+    auto const* handler = getHandler(context.apiVersion, context.app.config().betaRpcApi, cmd);
+    return (handler != nullptr) ? std::string_view{handler->name}
+                                : std::string_view{rpc_span::val::unknownCommand};
+}
+
 }  // namespace
 
 Status
@@ -196,6 +254,15 @@ doCommand(RPC::JsonContext& context, json::Value& result)
     Handler const* handler = nullptr;
     if (auto error = fillHandler(context, handler))
     {
+        // Bound the span name and command attribute to the finite set of
+        // registered handler names (plus "unknown") — see the helper for why
+        // raw request input must not reach the telemetry pipeline.
+        auto const cmdName = resolveCommandSpanName(context);
+        auto span = SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::command, cmdName);
+        span.setAttribute(rpc_span::attr::command, cmdName);
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
+        span.setError(getErrorInfo(error).token.cStr());
+
         injectError(error, result);
         return error;
     }
@@ -235,4 +302,5 @@ roleRequired(unsigned int version, bool betaEnabled, std::string const& method)
     return handler->role;
 }
 
-}  // namespace xrpl::RPC
+}  // namespace RPC
+}  // namespace xrpl

src/xrpld/rpc/detail/RpcSpanNames.h

@@ -0,0 +1,167 @@
+#pragma once
+
+/** Compile-time span name constants for the RPC subsystem.
+ *
+ *  All span prefixes, operation names, and attribute keys used by RPC
+ *  tracing call sites are defined here. Built on the StaticStr/join()
+ *  primitives from <xrpl/telemetry/SpanNames.h>.
+ *
+ *  Usage:
+ *  @code
+ *      #include <xrpld/rpc/detail/RpcSpanNames.h>
+ *      using namespace telemetry;
+ *
+ *      auto span = SpanGuard::span(
+ *          TraceCategory::Rpc, rpc_span::prefix::command, "submit");
+ *      span.setAttribute(rpc_span::attr::command, "submit");
+ *      span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::success);
+ *  @endcode
+ *
+ *  Span hierarchy (automatic nesting via OTel thread-local context):
+ *
+ *  HTTP JSON-RPC path (single request):
+ *
+ *    +-------------------------------------------------------+
+ *    | rpc.http_request                                      |
+ *    | ServerHandler::processSession(Session)                |
+ *    |                                                       |
+ *    |  +--------------------------------------------------+ |
+ *    |  | rpc.process                                      | |
+ *    |  | ServerHandler::processRequest()                  | |
+ *    |  |                                                  | |
+ *    |  |  +---------------------------------------------+ | |
+ *    |  |  | rpc.command.{name}                          | | |
+ *    |  |  | RPC::callMethod()                           | | |
+ *    |  |  | attrs: command, version, rpc_role, rpc_status | | |
+ *    |  |  +---------------------------------------------+ | |
+ *    |  +--------------------------------------------------+ |
+ *    +-------------------------------------------------------+
+ *
+ *  HTTP batch path (multiple commands per request):
+ *
+ *    +-------------------------------------------------------+
+ *    | rpc.http_request                                      |
+ *    |                                                       |
+ *    |  +--------------------------------------------------+ |
+ *    |  | rpc.process                                      | |
+ *    |  |                                                  | |
+ *    |  |  +------------------+  +------------------+      | |
+ *    |  |  | rpc.command.{a}  |  | rpc.command.{b}  | ...  | |
+ *    |  |  +------------------+  +------------------+      | |
+ *    |  +--------------------------------------------------+ |
+ *    +-------------------------------------------------------+
+ *
+ *  WebSocket path:
+ *
+ *    +-------------------------------------------------------+
+ *    | rpc.ws_message                                        |
+ *    | ServerHandler::processSession(WSSession)              |
+ *    |                                                       |
+ *    |  +--------------------------------------------------+ |
+ *    |  | rpc.command.{name}                               | |
+ *    |  | RPC::callMethod()                                | |
+ *    |  | attrs: command, version, rpc_role, rpc_status     | |
+ *    |  +--------------------------------------------------+ |
+ *    +-------------------------------------------------------+
+ *
+ *  WebSocket error paths:
+ *
+ *    +-------------------------------------------------------+
+ *    | rpc.ws_message (error: invalid_json)                  |
+ *    | ServerHandler::onWSMessage() — parse failure           |
+ *    +-------------------------------------------------------+
+ *
+ *    +-------------------------------------------------------+
+ *    | rpc.ws_upgrade                                        |
+ *    | ServerHandler::onHandoff() — upgrade try/catch         |
+ *    +-------------------------------------------------------+
+ *
+ *  Command dispatch error path:
+ *
+ *    +-------------------------------------------------------+
+ *    | rpc.command.{name} (error: too_busy/unknown/etc)       |
+ *    | RPC::doCommand() — fillHandler() rejection             |
+ *    +-------------------------------------------------------+
+ *
+ *  gRPC path (see GrpcSpanNames.h for constants):
+ *
+ *    +-------------------------------------------------------+
+ *    | grpc.<MethodName>  (e.g. grpc.GetLedger)              |
+ *    | CallData::process(coro)                               |
+ *    |   attrs: method, grpc_status                          |
+ *    +-------------------------------------------------------+
+ *
+ *  Covered paths:
+ *    - HTTP JSON-RPC (single and batch requests)
+ *    - WebSocket RPC commands
+ *    - WebSocket message parse errors (invalid JSON, oversized)
+ *    - WebSocket upgrade failures (protocol handshake errors)
+ *    - Admin CLI (connects via HTTP internally)
+ *    - Command dispatch rejections (unknown cmd, too busy, no perm)
+ *    - gRPC endpoints (GetLedger, GetLedgerData, GetLedgerDiff,
+ *      GetLedgerEntry)
+ *    - Command execution: timing, success/failure, exceptions
+ *    - Per-command attributes: name, API version, rpc_role, rpc_status
+ *
+ *  Known gaps (not yet instrumented):
+ *    - Early validation errors in processRequest() before rpc.process
+ *      span (malformed JSON, auth failures, oversized requests)
+ *    - Subscription push notifications (server-initiated, not RPC)
+ */
+
+#include <xrpl/telemetry/SpanNames.h>
+
+namespace xrpl::telemetry::rpc_span {
+
+// ===== Span prefixes =======================================================
+
+namespace prefix {
+/// "rpc" — root prefix for transport-level spans.
+inline constexpr auto rpc = seg::rpc;
+/// "rpc.command" — prefix for individual RPC command spans.
+inline constexpr auto command = join(seg::rpc, makeStr("command"));
+}  // namespace prefix
+
+// ===== Span operation suffixes =============================================
+
+namespace op {
+inline constexpr auto wsMessage = makeStr("ws_message");
+inline constexpr auto wsUpgrade = makeStr("ws_upgrade");
+inline constexpr auto httpRequest = makeStr("http_request");
+inline constexpr auto process = makeStr("process");
+}  // namespace op
+
+// ===== Attribute keys ======================================================
+
+namespace attr {
+/// "command" — RPC method name.
+inline constexpr auto command = makeStr("command");
+/// "version" — api_version per request.
+inline constexpr auto version = makeStr("version");
+/// "rpc_role" — admin|user. Domain-qualified: collides with grpc_role.
+inline constexpr auto rpcRole = makeStr("rpc_role");
+/// "rpc_status" — success|error. Domain-qualified: avoids OTel reserved span status.
+inline constexpr auto rpcStatus = makeStr("rpc_status");
+/// "request_payload_size" — bytes of inbound request payload.
+inline constexpr auto requestPayloadSize = makeStr("request_payload_size");
+/// "is_batch" — whether request is a JSON-RPC batch.
+inline constexpr auto isBatch = makeStr("is_batch");
+/// "batch_size" — number of sub-requests in a batch.
+inline constexpr auto batchSize = makeStr("batch_size");
+/// "load_type" — resource cost category after execution.
+inline constexpr auto loadType = makeStr("load_type");
+}  // namespace attr
+
+// ===== Attribute values ====================================================
+
+namespace val {
+using telemetry::attr_val::error;
+using telemetry::attr_val::success;
+inline constexpr auto admin = makeStr("admin");
+inline constexpr auto user = makeStr("user");
+inline constexpr auto unknownCommand = makeStr("unknown");
+/// "invalid_json" — WS message parse failure or oversize.
+inline constexpr auto invalidJson = makeStr("invalid_json");
+}  // namespace val
+
+}  // namespace xrpl::telemetry::rpc_span

src/xrpld/rpc/detail/ServerHandler.cpp

@@ -4,8 +4,10 @@
 #include <xrpld/overlay/Overlay.h>
 #include <xrpld/rpc/RPCHandler.h>
 #include <xrpld/rpc/Role.h>
+#include <xrpld/rpc/detail/RpcSpanNames.h>
 #include <xrpld/rpc/detail/Tuning.h>
 #include <xrpld/rpc/detail/WSInfoSub.h>
+#include <xrpld/rpc/json_body.h>  // IWYU pragma: keep
 
 #include <xrpl/basics/Log.h>
 #include <xrpl/basics/base64.h>
@@ -43,6 +45,7 @@
 #include <xrpl/server/SimpleWriter.h>
 #include <xrpl/server/WSSession.h>
 #include <xrpl/server/detail/JSONRPCUtil.h>
+#include <xrpl/telemetry/SpanGuard.h>
 
 #include <boost/algorithm/string/trim.hpp>
 #include <boost/asio/buffer.hpp>
@@ -60,6 +63,7 @@
 #include <algorithm>
 #include <cctype>
 #include <chrono>
+#include <cstdint>
 #include <exception>
 #include <map>
 #include <memory>
@@ -71,6 +75,7 @@
 #include <vector>
 
 namespace xrpl {
+using namespace telemetry;
 
 class Peer;
 class LedgerMaster;
@@ -224,13 +229,17 @@ ServerHandler::onHandoff(
         if (!isWs)
             return statusRequestResponse(request, http::status::unauthorized);
 
+        auto span =
+            SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::wsUpgrade);
         std::shared_ptr<WSSession> ws;
         try
         {
             ws = session.websocketUpgrade();
+            span.setOk();
         }
         catch (std::exception const& e)
         {
+            span.recordException(e);  // LCOV_EXCL_LINE
             JLOG(journal_.error()) << "Exception upgrading websocket: " << e.what() << "\n";
             return statusRequestResponse(request, http::status::internal_server_error);
         }
@@ -339,10 +348,14 @@ ServerHandler::onWSMessage(
     auto const size = boost::asio::buffer_size(buffers);
     if (size > RPC::Tuning::kMaxRequestSize || !json::Reader{}.parse(jv, buffers) || !jv.isObject())
     {
+        auto span =
+            SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::wsMessage);
+        span.setError(rpc_span::val::invalidJson);
+
         json::Value jvResult(json::ValueType::Object);
         jvResult[jss::type] = jss::error;
         jvResult[jss::error] = "jsonInvalid";
-        jvResult[jss::value] = buffersToString(buffers);
+        jvResult[jss::value] = ::xrpl::buffersToString(buffers);
         boost::beast::multi_buffer sb;
         json::stream(jvResult, [&sb](auto const p, auto const n) {
             sb.commit(boost::asio::buffer_copy(sb.prepare(n), boost::asio::buffer(p, n)));
@@ -415,12 +428,24 @@ ServerHandler::processSession(
     std::shared_ptr<JobQueue::Coro> const& coro,
     json::Value const& jv)
 {
+    auto span = SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::wsMessage);
+    if (jv.isMember(jss::command) && jv[jss::command].isString())
+    {
+        span.setAttribute(rpc_span::attr::command, jv[jss::command].asString().c_str());
+    }
+    else if (jv.isMember(jss::method) && jv[jss::method].isString())
+    {
+        span.setAttribute(rpc_span::attr::command, jv[jss::method].asString().c_str());
+    }
+
     auto is = std::static_pointer_cast<WSInfoSub>(session->appDefined);
     if (is->getConsumer().disconnect(journal_))
     {
         session->close({boost::beast::websocket::policy_error, "threshold exceeded"});
         // FIX: This rpcError is not delivered since the session
         // was just closed.
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
+        span.setError("resource threshold exceeded");
         return rpcError(RpcSlowDown);
     }
 
@@ -452,6 +477,8 @@ ServerHandler::processSession(
                 jr[jss::api_version] = jv[jss::api_version];
 
             is->getConsumer().charge(Resource::kFeeMalformedRpc);
+            span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
+            span.setError(jr[jss::error].asString());
             return jr;
         }
 
@@ -498,6 +525,8 @@ ServerHandler::processSession(
         jr[jss::result] = RPC::makeError(RpcInternal);
         JLOG(journal_.error()) << "Exception while processing WS: " << ex.what() << "\n"
                                << "Input JSON: " << json::Compact{json::Value{jv}};
+        span.recordException(ex);
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
         // LCOV_EXCL_STOP
     }
 
@@ -530,12 +559,19 @@ ServerHandler::processSession(
         }
 
         jr[jss::request] = rq;
+        // Mark the span according to the final result. Doing it here (rather
+        // than an unconditional setOk later) ensures error responses — from
+        // doCommand, a FORBID role, or the catch block above — are not
+        // overwritten as OK.
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
+        span.setError(jr[jss::error].asString());
     }
     else
     {
         if (jr[jss::result].isMember("forwarded") && jr[jss::result]["forwarded"])
             jr = jr[jss::result];
         jr[jss::status] = jss::success;
+        span.setOk();
     }
 
     if (jv.isMember(jss::id))
@@ -557,9 +593,15 @@ ServerHandler::processSession(
     std::shared_ptr<Session> const& session,
     std::shared_ptr<JobQueue::Coro> coro)
 {
-    processRequest(
+    auto span =
+        SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::httpRequest);
+
+    auto const requestBody = ::xrpl::buffersToString(session->request().body().data());
+    span.setAttribute(rpc_span::attr::requestPayloadSize, static_cast<int64_t>(requestBody.size()));
+
+    bool const ok = processRequest(
         session->port(),
-        buffersToString(session->request().body().data()),
+        requestBody,
         session->remoteAddress().atPort(0),
         makeOutput(*session),
         coro,
@@ -579,6 +621,15 @@ ServerHandler::processSession(
     {
         session->close(true);
     }
+    // Reflect the request outcome on the wrapper span instead of always OK.
+    if (ok)
+    {
+        span.setOk();
+    }
+    else
+    {
+        span.setError(rpc_span::val::error);
+    }
 }
 
 static json::Value
@@ -597,7 +648,7 @@ constexpr json::Int kServerOverloaded = -32604;
 constexpr json::Int kForbidden = -32605;
 constexpr json::Int kWrongVersion = -32606;
 
-void
+bool
 ServerHandler::processRequest(
     Port const& port,
     std::string const& request,
@@ -607,20 +658,33 @@ ServerHandler::processRequest(
     std::string_view forwardedFor,
     std::string_view user)
 {
+    auto span = SpanGuard::span(TraceCategory::Rpc, rpc_span::prefix::rpc, rpc_span::op::process);
     auto rpcJ = app_.getJournal("RPC");
 
+    // Tracks whether any failure occurred. Set on every error path (early
+    // returns, the catch block, and per-request error replies) and used at the
+    // end to mark the span status. The HTTP status code alone is insufficient:
+    // it stays 200 for batch responses and for ripplerpc < 3.0, so relying on
+    // it would let payload-level errors end the span as successful.
+    bool spanHadError = false;
+
+    // Marks the span as failed before sending an error reply, so the
+    // early-return validation paths below are not later seen as successful
+    // (the span would otherwise end UNSET, invisible to {status.code=error}).
+    auto httpReplyError = [&](int status, std::string const& message) {
+        spanHadError = true;
+        span.setError(message);
+        httpReply(status, message, output, rpcJ);
+    };
+
     json::Value jsonOrig;
     {
         json::Reader reader;
         if ((request.size() > RPC::Tuning::kMaxRequestSize) || !reader.parse(request, jsonOrig) ||
             !jsonOrig || !jsonOrig.isObject())
         {
-            httpReply(
-                400,
-                "Unable to parse request: " + reader.getFormattedErrorMessages(),
-                output,
-                rpcJ);
-            return;
+            httpReplyError(400, "Unable to parse request: " + reader.getFormattedErrorMessages());
+            return false;
         }
     }
 
@@ -631,11 +695,14 @@ ServerHandler::processRequest(
         batch = true;
         if (!jsonOrig.isMember(jss::params) || !jsonOrig[jss::params].isArray())
         {
-            httpReply(400, "Malformed batch request", output, rpcJ);
-            return;
+            httpReplyError(400, "Malformed batch request");
+            return false;
         }
         size = jsonOrig[jss::params].size();
     }
+    span.setAttribute(rpc_span::attr::isBatch, batch);
+    if (batch)
+        span.setAttribute(rpc_span::attr::batchSize, static_cast<int64_t>(size));
 
     json::Value reply(batch ? json::ValueType::Array : json::ValueType::Object);
     auto const start(std::chrono::high_resolution_clock::now());
@@ -670,8 +737,8 @@ ServerHandler::processRequest(
         {
             if (!batch)
             {
-                httpReply(400, jss::invalid_API_version.cStr(), output, rpcJ);
-                return;
+                httpReplyError(400, jss::invalid_API_version.cStr());
+                return false;
             }
             json::Value r(json::ValueType::Object);
             r[jss::request] = jsonRPC;
@@ -713,8 +780,8 @@ ServerHandler::processRequest(
             {
                 if (!batch)
                 {
-                    httpReply(503, "Server is overloaded", output, rpcJ);
-                    return;
+                    httpReplyError(503, "Server is overloaded");
+                    return false;
                 }
                 json::Value r = jsonRPC;
                 r[jss::error] = makeJsonError(kServerOverloaded, "Server is overloaded");
@@ -728,8 +795,8 @@ ServerHandler::processRequest(
             usage.charge(Resource::kFeeMalformedRpc);
             if (!batch)
             {
-                httpReply(403, "Forbidden", output, rpcJ);
-                return;
+                httpReplyError(403, "Forbidden");
+                return false;
             }
             json::Value r = jsonRPC;
             r[jss::error] = makeJsonError(kForbidden, "Forbidden");
@@ -742,8 +809,8 @@ ServerHandler::processRequest(
             usage.charge(Resource::kFeeMalformedRpc);
             if (!batch)
             {
-                httpReply(400, "Null method", output, rpcJ);
-                return;
+                httpReplyError(400, "Null method");
+                return false;
             }
             json::Value r = jsonRPC;
             r[jss::error] = makeJsonError(kMethodNotFound, "Null method");
@@ -757,8 +824,8 @@ ServerHandler::processRequest(
             usage.charge(Resource::kFeeMalformedRpc);
             if (!batch)
             {
-                httpReply(400, "method is not string", output, rpcJ);
-                return;
+                httpReplyError(400, "method is not string");
+                return false;
             }
             json::Value r = jsonRPC;
             r[jss::error] = makeJsonError(kMethodNotFound, "method is not string");
@@ -772,8 +839,8 @@ ServerHandler::processRequest(
             usage.charge(Resource::kFeeMalformedRpc);
             if (!batch)
             {
-                httpReply(400, "method is empty", output, rpcJ);
-                return;
+                httpReplyError(400, "method is empty");
+                return false;
             }
             json::Value r = jsonRPC;
             r[jss::error] = makeJsonError(kMethodNotFound, "method is empty");
@@ -798,8 +865,8 @@ ServerHandler::processRequest(
             else if (!params.isArray() || params.size() != 1)
             {
                 usage.charge(Resource::kFeeMalformedRpc);
-                httpReply(400, "params unparsable", output, rpcJ);
-                return;
+                httpReplyError(400, "params unparsable");
+                return false;
             }
             else
             {
@@ -807,8 +874,8 @@ ServerHandler::processRequest(
                 if (!params.isObjectOrNull())
                 {
                     usage.charge(Resource::kFeeMalformedRpc);
-                    httpReply(400, "params unparsable", output, rpcJ);
-                    return;
+                    httpReplyError(400, "params unparsable");
+                    return false;
                 }
             }
         }
@@ -825,8 +892,8 @@ ServerHandler::processRequest(
                 usage.charge(Resource::kFeeMalformedRpc);
                 if (!batch)
                 {
-                    httpReply(400, "ripplerpc is not a string", output, rpcJ);
-                    return;
+                    httpReplyError(400, "ripplerpc is not a string");
+                    return false;
                 }
 
                 json::Value r = jsonRPC;
@@ -883,6 +950,9 @@ ServerHandler::processRequest(
             JLOG(journal_.error())
                 << "Internal error : " << ex.what()
                 << " when processing request: " << json::Compact{json::Value{params}};
+            span.recordException(ex);
+            span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
+            spanHadError = true;
             // LCOV_EXCL_STOP
         }
 
@@ -899,6 +969,7 @@ ServerHandler::processRequest(
         {
             if (result.isMember(jss::error))
             {
+                spanHadError = true;
                 result[jss::status] = jss::error;
                 result["code"] = result[jss::error_code];
                 result["message"] = result[jss::error_message];
@@ -919,6 +990,7 @@ ServerHandler::processRequest(
             // received.
             if (result.isMember(jss::error))
             {
+                spanHadError = true;
                 auto rq = params;
 
                 if (rq.isObject())
@@ -1014,7 +1086,20 @@ ServerHandler::processRequest(
         }
     }
 
+    // Mark the span error if any request failed or the HTTP status is an error.
+    // spanHadError catches payload-level errors that httpStatus misses (batch
+    // responses and ripplerpc < 3.0 always return HTTP 200).
+    if (spanHadError || httpStatus >= 400)
+    {
+        span.setAttribute(rpc_span::attr::rpcStatus, rpc_span::val::error);
+        span.setError(rpc_span::val::error);
+    }
+    else
+    {
+        span.setOk();
+    }
     httpReply(httpStatus, response, output, rpcJ);
+    return !spanHadError;
 }
 
 //------------------------------------------------------------------------------

src/xrpld/rpc/handlers/orderbook/PathFind.cpp

@@ -1,6 +1,7 @@
 #include <xrpld/app/ledger/LedgerMaster.h>
 #include <xrpld/app/main/Application.h>
 #include <xrpld/rpc/Context.h>
+#include <xrpld/rpc/detail/PathFindSpanNames.h>
 #include <xrpld/rpc/detail/PathRequestManager.h>
 
 #include <xrpl/json/json_value.h>
@@ -9,12 +10,23 @@
 #include <xrpl/protocol/jss.h>
 #include <xrpl/resource/Fees.h>
 #include <xrpl/server/InfoSub.h>
+#include <xrpl/telemetry/Redaction.h>
+#include <xrpl/telemetry/SpanGuard.h>
 
 namespace xrpl {
 
 json::Value
 doPathFind(RPC::JsonContext& context)
 {
+    using namespace telemetry;
+    auto span = SpanGuard::span(
+        TraceCategory::Rpc, pathfind_span::prefix::pathfind, pathfind_span::op::request);
+    // Addresses are hashed before emission for privacy.
+    if (auto const& src = context.params[jss::source_account]; src.isString())
+        span.setAttribute(pathfind_span::attr::sourceAccount, redactAccount(src.asString()));
+    if (auto const& dst = context.params[jss::destination_account]; dst.isString())
+        span.setAttribute(pathfind_span::attr::destAccount, redactAccount(dst.asString()));
+
     if (context.app.config().pathSearchMax == 0)
         return rpcError(RpcNotSupported);
 

src/xrpld/rpc/handlers/orderbook/RipplePathFind.cpp

@@ -2,6 +2,7 @@
 #include <xrpld/rpc/Context.h>
 #include <xrpld/rpc/Role.h>
 #include <xrpld/rpc/detail/LegacyPathFind.h>
+#include <xrpld/rpc/detail/PathFindSpanNames.h>
 #include <xrpld/rpc/detail/PathRequest.h>
 #include <xrpld/rpc/detail/PathRequestManager.h>
 #include <xrpld/rpc/detail/RPCLedgerHelpers.h>
@@ -13,6 +14,8 @@
 #include <xrpl/protocol/RPCErr.h>
 #include <xrpl/protocol/jss.h>
 #include <xrpl/resource/Fees.h>
+#include <xrpl/telemetry/Redaction.h>
+#include <xrpl/telemetry/SpanGuard.h>
 
 #include <memory>
 #include <utility>
@@ -23,6 +26,15 @@ namespace xrpl {
 json::Value
 doRipplePathFind(RPC::JsonContext& context)
 {
+    using namespace telemetry;
+    auto span = SpanGuard::span(
+        TraceCategory::Rpc, pathfind_span::prefix::pathfind, pathfind_span::op::request);
+    // Addresses are hashed before emission for privacy.
+    if (auto const& src = context.params[jss::source_account]; src.isString())
+        span.setAttribute(pathfind_span::attr::sourceAccount, redactAccount(src.asString()));
+    if (auto const& dst = context.params[jss::destination_account]; dst.isString())
+        span.setAttribute(pathfind_span::attr::destAccount, redactAccount(dst.asString()));
+
     if (context.app.config().pathSearchMax == 0)
         return rpcError(RpcNotSupported);