feat(langchain) GenAI semconv compliance#3822
Open
max-deygin-traceloop wants to merge 6 commits intomax/tlp-1925-python-sdk-otel-semantic-conventionfrom
Open
feat(langchain) GenAI semconv compliance#3822max-deygin-traceloop wants to merge 6 commits intomax/tlp-1925-python-sdk-otel-semantic-conventionfrom
max-deygin-traceloop wants to merge 6 commits intomax/tlp-1925-python-sdk-otel-semantic-conventionfrom
Conversation
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
max-deygin-traceloop
changed the title
max-deygin-traceloop
force-pushed
the
max/tlp-1925-python-sdk-otel-semantic-convention
branch
from
740ee81 to
6401889
Compare
max-deygin-traceloop
force-pushed
the
max/tlp-1927-langchain-instrumentation
branch
2 times, most recently
from
072b0ac to
1400d4e
Compare
|
|
max-deygin-traceloop
force-pushed
the
max/tlp-1927-langchain-instrumentation
branch
3 times, most recently
from
35fa2f9 to
63b8553
Compare
avivhalfon
reviewed
Mar 19, 2026
|
|
||
| # Record token usage metrics | ||
| vendor = span.attributes.get(GenAIAttributes.GEN_AI_SYSTEM, "Langchain") | ||
| vendor = span.attributes.get(GenAIAttributes.GEN_AI_SYSTEM, "langchain") |
Contributor
There was a problem hiding this comment.
@max-deygin-traceloop @OzBenSimhonTraceloop we need to set also GEN_AI_PROVIDER_NAME
here:
https://github.com/traceloop/openllmetry/pull/3808/changes#r2959993030
…→ GEN_AI_ - Replace SpanAttributes.LLM_REQUEST_FUNCTIONS with GenAIAttributes.GEN_AI_TOOL_DEFINITIONS - Replace SpanAttributes.LLM_REQUEST_TYPE with GenAIAttributes.GEN_AI_OPERATION_NAME - Replace SpanAttributes.LLM_USAGE_TOTAL_TOKENS with SpanAttributes.GEN_AI_USAGE_TOTAL_TOKENS - Update test_llms.py, test_tool_calls.py, test_langgraph.py accordingly - Add test_semconv_compliance.py Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…nitions to JSON array Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Replace flat gen_ai.prompt.{i}.* attributes with GEN_AI_INPUT_MESSAGES JSON array
- Replace flat gen_ai.completion.{i}.* attributes with GEN_AI_OUTPUT_MESSAGES JSON array
- Convert _set_chat_tool_calls (flat span attrs) to _build_tool_calls_list (returns list)
- Fix vendor_detection: "Anthropic" → "anthropic" to match OTel semconv lowercase
- Update all affected tests to parse GEN_AI_INPUT/OUTPUT_MESSAGES JSON arrays
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…emove debug print - vendor_detection.py: use canonical GenAISystem string values for all vendors (AWS → aws.bedrock, HuggingFace → hugging_face, Google → google, Azure → az.ai.openai, Cohere → cohere, Ollama → ollama, Together → together_ai, Replicate → replicate, Fireworks → fireworks, Groq → groq, MistralAI → mistral_ai) - span_utils.py: remove debug print() from production exception handler - tests: update GEN_AI_SYSTEM assertions to match new lowercase values Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ck, add vendor unit tests - vendor_detection.py: Google/Vertex AI → "gcp.gen_ai" (matches GenAISystem.GOOGLE) - vendor_detection.py: both fallback returns "Langchain" → "langchain" (matches GenAISystem.LANGCHAIN) - callback_handler.py: two GEN_AI_SYSTEM default fallbacks "Langchain" → "langchain" - span_utils.py: GEN_AI_SYSTEM default fallback "Langchain" → "langchain" - tests: add parameterized test_vendor_detection.py covering all 13 vendors + default fallback Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
max-deygin-traceloop
force-pushed
the
max/tlp-1927-langchain-instrumentation
branch
from
63b8553 to
aadef1d
Compare
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
3 participants
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.
Migrate LangChain instrumentation to OTel GenAI semconv
Aligns the LangChain instrumentation with the upstream OpenTelemetry GenAI semantic
conventions.
Changes:
SpanAttributes.LLM_*constants with upstreamGenAIAttributes.GEN_AI_*equivalentsgen_ai.prompt.{i}.*/gen_ai.completion.{i}.*attributes togen_ai.input.messages/gen_ai.output.messagesJSON arrays (set_llm_request,set_chat_request,set_chat_response)gen_ai.tool.definitions.{i}.*attributes togen_ai.tool.definitionsJSON array
_set_chat_tool_calls(flat span attrs) with_build_tool_calls_list(returns list for embedding in JSON)
gen_ai.operation.namebug incallback_handler.py"Anthropic"→"anthropic"to match OTel semconvgen_ai.input.messages/gen_ai.output.messagesJSON arrays