Add OTel GenAI framework support to LLM Observability docs#35974
Merged
ZStriker19 merged 11 commits intomasterfrom Apr 24, 2026
Merged
Add OTel GenAI framework support to LLM Observability docs#35974ZStriker19 merged 11 commits intomasterfrom
ZStriker19 merged 11 commits intomasterfrom
Conversation
Spring AI uses Micrometer's Observation API to emit gen_ai.* span attributes, which the Datadog Java tracer captures automatically. Token usage metrics are correctly parsed even though Micrometer's KeyValues abstraction sends them as strings. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Contributor
Preview links (active after the
|
Adds a "Tested frameworks and libraries" section with tables for Python, Node.js, and Java frameworks that emit OpenTelemetry GenAI semantic convention spans. Includes both native emitters and those requiring separate instrumentation packages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Contributor
Author
|
Closing — Spring AI is included in the OTel tested frameworks table instead. Auto-instrumentation docs will be a separate PR. |
- OpenAI Python: >= 1.26.0 (instrumentation requirement) - Anthropic: >= 0.51.0 (instrumentation requirement) - Google GenAI: >= 1.32.0 (instrumentation requirement) - LangChain: >= 0.3.21 (instrumentation requirement) - LlamaIndex: >= 0.14.12 (per test fixtures) - OpenAI Node.js: >= 4.19.0 (instrumentation README) - LangChain4j: >= 0.31.0 (ChatModelListener added) - AWS Bedrock Java: AWS SDK >= 2.2 (per OTel agent metadata) - Remove Semantic Kernel, AutoGen (no OTel gen_ai instrumentation) - Remove Mastra (version doesn't exist), Quarkus LangChain4j (wrong versioning) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
domalessi
requested changes
Apr 15, 2026
Contributor
There was a problem hiding this comment.
Thanks for the PR! Left some suggestions.
Also, a few high level things:
- The PR description says this is a WIP. Hit me up when it's finalized!
- The framework counts in the PR description (11 Python, 2 Node.js, 4 Java) don't match the tables in the diff (9 Python, 1 Node.js, 3 Java) -- perhaps expected with the WIP status?
- The description also mentions changes that don't appear in the diff: Spring AI added to
auto_instrumentation.md's supported frameworks table, and a Spring AI collapsible section.
Hit me up when ready for another look.
- Promote "Tested frameworks and libraries" to H2 - Restructure opening sentences for flow; remove directional "here" - Add missing [5] strands-agents reference in Python tab - Replace "via" with "through" per word list - Remove hardcoded language list from auto_instrumentation info box Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
domalessi
approved these changes
Apr 22, 2026
Contributor
domalessi
left a comment
There was a problem hiding this comment.
a few final tweaks, but otherwise looks good. approving so you can merge after checking out my suggestions!
…ion.md Co-authored-by: domalessi <111786334+domalessi@users.noreply.github.com>
…ion.md Co-authored-by: domalessi <111786334+domalessi@users.noreply.github.com>
…ion.md Co-authored-by: domalessi <111786334+domalessi@users.noreply.github.com>
…ion.md Co-authored-by: domalessi <111786334+domalessi@users.noreply.github.com>
…-llmobs-docs # Conflicts: # content/en/llm_observability/instrumentation/auto_instrumentation.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a new "Tested frameworks and libraries" section to the OTel instrumentation page with tables for Python (9 frameworks), Node.js (1 framework), and Java (3 frameworks) that emit OTel GenAI semantic convention spans.
Also updates the auto instrumentation page's info box to link directly to the new OTel frameworks section.
Framework versions reflect the minimum supported version per each instrumentation package's requirements (verified against GitHub repos).
Test plan
🤖 Generated with Claude Code