feat(llmobs): add agent attribution to Java SDK by yahya-mouman · Pull Request #12238 · DataDog/dd-trace-java

yahya-mouman · 2026-08-19T15:11:41Z

Summary

Agent attribution tracks the nearest `agent`-kind ancestor span for every LLMObs span and emits it as `meta.agent_attribution = {"pagent_name": str|null, "pagent_span_id": str}`. This feature is already merged in Python (#18788), JavaScript (#9175), and Go. This PR brings the Java SDK to parity.

Wire contract

Serialized field: `meta.agent_attribution = {"pagent_name": str|null, "pagent_span_id": str}`

Two-case in-process resolution (O(1) at span start)

This span is `kind=agent` → self-attribution (own span ID + name)
In-process LLMObs parent → inherit from `LLMObsContext` thread-local context

A trace-ID consistency gate prevents stale `LLMObsContext` values leaking across async boundaries: attribution is only inherited when the context's trace ID matches the new span's trace ID.

Changes

File	Change
`internal-api/.../LLMObsContext.java`	Two new `ContextKey` fields + 4-arg `attach()` overload for pagent propagation
`dd-trace-api/.../LLMObsTags.java`	Two new constants: `PAGENT_SPAN_ID` and `PAGENT_NAME`
`dd-trace-core/.../LLMObsSpanMapper.java`	Serializes two internal pagent tags as a single `agent_attribution` map in meta
`agent-llmobs/.../DDLLMObsSpan.java`	Resolution logic in constructor; wire-safe agent name validation (char-scan, no allocation)
`openai-java/.../CommonTags.java`	Two new tag constants for pagent propagation on auto-instrumented OpenAI spans
`openai-java/.../OpenAiDecorator.java`	Inherit pagent attribution from active `LLMObsContext` during `doAfterStart`
`agent-llmobs/.../DDLLMObsSpanAgentAttributionTest.java`	New JUnit 5 unit tests: self-attribution, unsafe name, tilde rejection, in-process inheritance, transitive, no-ancestor, stale-context gate
`agent-llmobs/.../AgentAttributionIntegrationTest.java`	New JUnit 5 integration tests through the public `LLMObs.start*Span()` API; includes OpenAI decorator context simulation

Test plan

`./gradlew :dd-java-agent:agent-llmobs:test` — `DDLLMObsSpanAgentAttributionTest` and `AgentAttributionIntegrationTest` cover all resolution cases
`./gradlew :dd-trace-core:test` — mapper tests verify `agent_attribution` wire format including explicit-null name path
`./gradlew spotlessCheck` — format check
Manual: create an agent → llm → tool chain and verify `meta.agent_attribution` appears on tool and llm spans pointing to the agent

🤖 Generated with Claude Code

dd-octo-sts · 2026-08-19T15:55:13Z

🟢 Java Benchmark SLOs — All performance SLOs passed

Suite	Status
Startup	🟢 pass

SLO thresholds are defined here based on automatically generated metrics. A warning is raised when results are within 5% of the threshold.

PR vs. master results

Scenario	Candidate	master	Δ (95% CI of mean)
startup:insecure-bank:iast:Agent	14.80 s	14.71 s	[-0.4%; +1.6%] (no difference)
startup:insecure-bank:tracing:Agent	13.66 s	13.59 s	[-0.4%; +1.4%] (no difference)
startup:petclinic:appsec:Agent	17.00 s	17.00 s	[-1.0%; +1.0%] (no difference)
startup:petclinic:iast:Agent	17.04 s	17.10 s	[-1.1%; +0.4%] (no difference)
startup:petclinic:profiling:Agent	16.79 s	17.10 s	[-2.9%; -0.9%] (maybe better)
startup:petclinic:sca:Agent	16.91 s	16.60 s	[+1.0%; +2.9%] (maybe worse)
startup:petclinic:tracing:Agent	16.20 s	16.13 s	[-0.6%; +1.4%] (no difference)

Commit: df8a0678 · CI Pipeline · Benchmarking Platform UI

Load and DaCapo benchmarks can be triggered manually in the GitLab pipeline. Results will appear in the Benchmarking Platform UI after completion.

yahya-mouman · 2026-08-25T10:56:12Z

@codex

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 65fb79c534

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

yahya-mouman · 2026-08-25T11:59:56Z

Deferred follow-up items (from Codex review)

Three issues flagged as P1 in the Codex review are intentionally deferred to separate PRs to keep this one reviewable:

1. W3C incoming decode — W3CPTagsCodec.fromHeaderValue does not extract llmobs_pagent_span_id / llmobs_pagent_name into the named fields on PTags. The Datadog-format codec handles this; W3C decode is a separate PR.

2. Auto-instrumented LLM spans — OpenAiDecorator and similar auto-instrumentation decorators don't set pagent tags. Attribution only works for manually-created DDLLMObsSpans in this PR. Follow-up will plumb pagent through the decorators.

3. Standalone agent without APM parent — When a kind=agent DDLLMObsSpan is the first span in a process (no APM root span), span.getLocalRootSpan() is the span itself and rootCtx is its own context, so stamping PTags works but the span cannot receive distributed pagent from upstream. This edge case is low-priority and deferred.

4. #12347

yahya-mouman · 2026-08-27T10:46:14Z

@codex

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 4fbafd9c86

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

sabrenner

lgtm overall!

Extends agent attribution (pagent_name/pagent_span_id) to dd-trace-java, matching the existing implementation in dd-trace-py, dd-trace-js, and dd-trace-go. Every LLMObs span now carries meta.agent_attribution = {pagent_name, pagent_span_id} identifying its nearest agent-kind ancestor, resolved O(1) at span start. Changes: - LLMObsPropagationAccess: new bridge interface in internal-api allowing agent-llmobs to read/write _dd.p.llmobs_pagent_* propagation tags on the APM span context without a direct dd-trace-core dependency - LLMObsContext: adds PAGENT_SPAN_ID_KEY/PAGENT_NAME_KEY context keys and extended attach() overload so agent attribution propagates in-process to descendants - PropagationTags + PTags: adds getParentAgentSpanId/Name and updateParentAgentSpanId/Name with volatile TagValue fields and header cache invalidation - PTagsCodec: defines PARENT_AGENT_SPAN_ID_TAG/PARENT_AGENT_NAME_TAG constants, emits both in headerValue() and fillTagMap() - DatadogPTagsCodec: extracts _dd.p.llmobs_pagent_* from incoming x-datadog-tags header - DDSpanContext: implements LLMObsPropagationAccess by delegating to getPropagationTags() - DDLLMObsSpan: resolves attribution at span start (agent spans write themselves; non-agent spans inherit from context; distributed case reads from root span PTags); wire-safe validation for agent names (printable ASCII, no commas/semicolons, ≤256 bytes) - LLMObsSpanMapper: serializes agent_attribution as a structured sub-map in meta, emitting pagent_name as explicit null when name was dropped Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Tests cover the three resolution cases in DDLLMObsSpan (self-as-agent, in-process context inheritance, distributed propagation) and the serializer's agent_attribution block emission in LLMObsSpanMapper, including the explicit-null name path when only pagent_span_id is set. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…guard Fix metaSize to subtract 1 whenever pagent_name is in tagsToRemapToMeta (not only when both pagent fields are present) to prevent an off-by-one if name is set without span_id, making the formula symmetric with the actual skip logic in the serializer loop. Replace getBytes(UTF_8) in agentNameWireSafe with a char-by-char scan, eliminating the per-agent-span byte array allocation. Because the loop rejects c > 0x7E, every passing char is single-byte UTF-8 so length() is an exact byte-count proxy for the 256-byte limit. Drop the redundant resolvedPagentSpanId != null guard on the agent-kind propagation block - always non-null at that point. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…pagent inheritance The stale-context trace-ID gate was correct for parent_id/session_id (APM-trace concepts) but wrong for pagent: LLMObsContext scopes are explicitly closed in finish(), so cross-trace leakage is impossible. Gating on trace IDs broke in-process inheritance because each DDLLMObsSpan creates its own APM trace when no APM scope is active. Also hardens LLMObsSpanMapper pagent_span_id validation (non-empty String check), fixes metaSize formula for pagent_name, removes byte-array alloc in agentNameWireSafe, and clears W3C cache in PTagsFactory on pagent updates. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

The stale-context gate (same applied to parent_id and session_id) must also cover pagent: without it a stale LLMObsContext from a different trace leaked across an async boundary would attribute spans to an unrelated agent. Tests now establish a root APM scope so all LLMObs spans share one APM trace, matching production behavior where the DD agent always activates a root scope. This makes the trace-ID consistency check reliable in tests. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…o auto-instrumented spans W3CPTagsCodec.fromHeaderValue now extracts llmobs_pagent_span_id and llmobs_pagent_name into the named PTags fields, matching what DatadogPTagsCodec already does. Without this, tracecontext-only hops lost attribution. OpenAiDecorator.doAfterStart now inherits agent attribution from LLMObsContext, following the same pattern already used for session_id. Auto-instrumented LLM spans inside a manual agent span now get the pagent_* tags set correctly. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Two cases the attribution test suite was missing: - inner agent finish() restores outer agent's PTags (nested agent support) - stale LLMObsContext from a different APM trace does not leak pagent attribution Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Three correctness fixes from review: - Reject tilde (0x7E) in agentNameWireSafe: W3C tracestate encoding rewrites ~ to _, which would silently corrupt the agent name after a tracecontext hop. Now treated as unsafe, matching the stricter bound. - Clear PAGENT_NAME_KEY in LLMObsContext.attach when name is null: previously an unsafe-named inner agent left the outer agent's name in the context, so tool spans under the inner agent inherited a mismatched ID/name pair. Context.with(key, null) removes the key. - Fix metaSize off-by-one in LLMObsSpanMapper: when pagent_span_id is present but invalid (non-String or empty), hasAgentAttribution=false skips the entry during serialization but the old formula still counted it in tagsToRemapToMeta.size(), producing a malformed msgpack map. Tests added for tilde rejection and the unsafe-name-clear case. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

When a manual agent span is started without an ambient APM root (e.g. a script or CLI with no DD agent HTTP server instrumentation), its local root is itself. Outgoing HTTP calls instrumented after it create a fresh APM root with empty PTags, so the pagent values stamped on the agent's root context are never injected into outgoing headers. Fix: detect the standalone case (kind=agent AND span.getLocalRootSpan()==span) and activate the underlying APM span as an AgentScope. Auto-instrumented outgoing spans then become children of the agent span, share its APM trace, and pick up the pagent PTags on injection. The scope is closed in finish(). In the production case (DD agent's HTTP server APM root already active), getLocalRootSpan() != span, so the activation is skipped and existing behavior is preserved. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…PTags Removes the LLMObsPropagationAccess bridge and all associated propagation tag plumbing. The shared-root PTags approach races for parallel agent subtrees, and the Java LLMObs SDK currently has no distributed tracing support — so cross-service propagation is deferred to a follow-up PR. In-process attribution via LLMObsContext is unaffected; meta.agent_attribution serialization is preserved. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Two tests created AGENT-kind DDLLMObsSpan instances without calling finish(). DDLLMObsSpan activates a standaloneApmScope when an agent span is its own APM local root (no ambient trace). Without finish(), that scope persisted across tests, causing all subsequent tests to fail on the activeSpan() == null guard in setup(). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Verifies agent attribution end-to-end through the public LLMObs.start*Span() API (the same path a user's code takes) rather than DDLLMObsSpan directly. Installs a RealSpanFactory backed by DDLLMObsSpan — mirroring what LLMObsSystem does when the agent boots with DD_LLMOBS_ENABLED=true. Scenarios covered: - agent self-attributes - LLM under agent inherits attribution - tool transitively inherits (agent → llm → tool) - nested agents: inner overrides outer for descendants; outer restores after inner finishes - no agent ancestor → no attribution tags - unsafe name (comma): ID set, name null; propagated to children - tilde in name: rejected by wire-safe guard - realistic router → executor multi-agent workflow Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

- Inline result variable in DatadogPTagsCodec.createValid call (left as a two-step assign-then-return by an earlier reverted commit) - Inline result variable in W3CPTagsCodec new W3CPTags call (same) - Rename hasInvalidPagentSpanId → hasInvalidParentAgentSpanId for readability per reviewer nit Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Rename all code variables that abbreviated the concept as `pagent` to the fully-spelled-out `parentAgent` prefix for readability, per sabrenner's review nit. Tag-name strings and constants (pagent_span_id, pagent_name in the wire format) are unchanged. Affected identifiers: resolvedPagentSpanId/Name → resolvedParentAgentSpanId/Name (DDLLMObsSpan) pagentSpanId/Name params → parentAgentSpanId/Name (LLMObsContext.attach) pagentSpanIdVal → parentAgentSpanIdVal (LLMObsSpanMapper) pagentSpanId/Name locals → parentAgentSpanId/Name (OpenAiDecorator) pagentSpanId/Name helpers → parentAgentSpanId/Name (integration tests) expectedPagent*/outerPagent* → expectedParentAgent*/outerParentAgent* (unit tests) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Removes the standalone APM scope activation from DDLLMObsSpan and its two tests. This feature (ensuring outgoing instrumented calls nest under a standalone agent span's APM trace) is correct but out of scope for this PR, which is focused on in-process pagent attribution. It will be reintroduced in a follow-up with proper distributed tracing tests. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

… in OpenAiDecorator The rename refactor (spell out pagent as parentAgent) updated the local variable declarations but missed the usages two lines below, causing undefined symbol compile errors. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Remove trailing blank lines flagged by google-java-format: - DDLLMObsSpan.java: blank line inside constructor body before closing brace - DDLLMObsSpanAgentAttributionTest.java: blank line before class closing brace Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 3b6a9529a0

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Without an active APM scope, each DDLLMObsSpan starts its own APM trace. The trace-ID consistency gate in DDLLMObsSpan then blocks in-process agent attribution inheritance because parent.getTraceId() != span.getTraceId(). In production the Datadog agent always activates an APM scope before user code runs, so all LLMObs spans within a request share one trace. The test must mirror this setup via @BeforeEach/@AfterEach APM scope lifecycle. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

datadog-prod-us1-5

Standalone public SDK nesting starts each manual span on a new trace, so child spans lose agent attribution. Stale LLMObs contexts can also copy an agent ID across traces into manual or OpenAI spans.

_{Open Bits AI session}

_{🤖 Datadog Autotest · Commit 3b6a952 · What is Autotest? · @DataDog review to ask questions · Any feedback? Reach out in #autotest}

datadog-prod-us1-5 · 2026-08-31T15:36:04Z

+      // leaked across an async boundary would otherwise attribute a span to an agent from a
+      // different trace. In production the DD agent always establishes a root APM scope, so
+      // all LLMObs spans within a request share one trace and this check passes.
+      if (null != parent && parent.getTraceId() == span.getTraceId()) {


Keep standalone child spans on the agent trace

Standalone public SDK users lose agent attribution from all manual child spans.

Assertion details

Input: Start a manual agent span and then start a manual LLM or tool span without an active APM scope.

Expected: A child LLMObs span must use the open manual agent span as its parent and inherit its agent ID and name.

Actual: The child span starts a new trace. The trace check then rejects the agent context and omits agent attribution.

Was this helpful? React 👍 or 👎
_{🤖 Datadog Autotest · What is Autotest? · @DataDog review to ask questions · Any feedback? Reach out in #autotest}

…ntract, add OpenAI test - Add PAGENT_SPAN_ID/PAGENT_NAME to LLMObsTags; derive all pagent tag string literals from it (DDLLMObsSpan, CommonTags, LLMObsSpanMapper) - Fix agentNameWireSafe Javadoc: correct range to 0x20-0x7D (exclusive of tilde) and rejection condition to c >= 0x7E - Document Context.with(key, null) null-removes-key contract in LLMObsContext.attach() comment with reference to the Context API - Add autoInstrumentedSpanInAgentScopeReadsAttributionFromContext test simulating what OpenAiDecorator.doAfterStart() reads from LLMObsContext Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…ionTest Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

LLMObsContext: always write both pagent keys in 4-arg attach(), so null clears stale values from an outer scope. Previously a non-agent span that had its attribution blocked by the trace-ID gate would still propagate the outer context's pagent keys to its same-trace children. OpenAiDecorator: gate pagent inheritance on trace-ID consistency, mirroring the check in DDLLMObsSpan. A stale LLMObsContext from a different async trace must not stamp its agent ID onto a new OpenAI span. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…striction Agent names are now accepted as-is — the character restrictions (tilde, non-ASCII, comma, semicolon) existed solely for x-datadog-tags header propagation, which was removed from this PR. The msgpack intake mapper accepts any string. For agent spans, annotateAgentManifest() now syncs the pagent name to the manifest name (manifest > span name fallback). Both the internal tag on the agent span and the LLMObsContext scope are updated so descendants started after the call inherit the manifest name. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…ifest Closing the original scope while a newer scope is on top corrupts the context stack: when the new scope is eventually closed it restores the old (already-closed) scope's context rather than the outer empty one, leaking pagent tags into subsequent tests. Only update PAGENT_NAME_TAG_INTERNAL (for the serializer's wire output); context propagation to children keeps the span name set at construction. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

yahya-mouman added type: feature Enhancements and improvements comp: core Tracer core labels Aug 19, 2026

This comment has been minimized.

Sign in to view

chatgpt-codex-connector Bot reviewed Aug 25, 2026

View reviewed changes

yahya-mouman force-pushed the yahya/llmobs-agent-attribution branch from 2a9e133 to 4fbafd9 Compare August 26, 2026 13:41

chatgpt-codex-connector Bot reviewed Aug 27, 2026

View reviewed changes

ncybul reviewed Aug 27, 2026

View reviewed changes

Comment thread dd-java-agent/agent-llmobs/src/main/java/datadog/trace/llmobs/domain/DDLLMObsSpan.java Outdated

Comment thread dd-trace-core/src/main/java/datadog/trace/core/propagation/ptags/DatadogPTagsCodec.java

sabrenner approved these changes Aug 31, 2026

View reviewed changes

yahya-mouman mentioned this pull request Aug 31, 2026

feat(llmobs): activate APM scope for standalone agent spans #12347

Draft

2 tasks

yahya-mouman and others added 17 commits August 31, 2026 16:47

Fix missing assertNull import in LLMObsSpanMapperTest

a8beb03

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

style(llmobs): apply spotless formatting

87e4045

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

yahya-mouman and others added 2 commits August 31, 2026 16:47

yahya-mouman force-pushed the yahya/llmobs-agent-attribution branch from 4554204 to 3b6a952 Compare August 31, 2026 14:56

yahya-mouman marked this pull request as ready for review August 31, 2026 15:04

yahya-mouman requested review from a team as code owners August 31, 2026 15:04

yahya-mouman requested review from ValentinZakharov and removed request for a team August 31, 2026 15:04

dd-octo-sts Bot added the tag: ai generated Largely based on code generated by an AI or LLM label Aug 31, 2026

chatgpt-codex-connector Bot reviewed Aug 31, 2026

View reviewed changes

datadog-prod-us1-5 Bot reviewed Aug 31, 2026

View reviewed changes

yahya-mouman and others added 7 commits August 31, 2026 17:48

Revert OpenAI auto-instrumentation test from AgentAttributionIntegrat…

355d061

…ionTest Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Remove AgentAttributionIntegrationTest — unit tests cover all cases

bd321e0

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

spotless: collapse PAGENT_NAME_TAG_INTERNAL onto one line

df8a067

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Uh oh!

Conversation

yahya-mouman commented Aug 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Wire contract

Two-case in-process resolution (O(1) at span start)

Changes

Test plan

Uh oh!

dd-octo-sts Bot commented Aug 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🟢 Java Benchmark SLOs — All performance SLOs passed

Uh oh!

This comment has been minimized.

yahya-mouman commented Aug 25, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

yahya-mouman commented Aug 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Deferred follow-up items (from Codex review)

Uh oh!

yahya-mouman commented Aug 27, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

sabrenner left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

datadog-prod-us1-5 Bot left a comment

Choose a reason for hiding this comment

Uh oh!

datadog-prod-us1-5 Bot Aug 31, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

yahya-mouman commented Aug 19, 2026 •

edited

Loading

dd-octo-sts Bot commented Aug 19, 2026 •

edited

Loading

yahya-mouman commented Aug 25, 2026 •

edited

Loading