Conversation
184e060 to
ef42d9d
Compare
ef42d9d to
bd26cdc
Compare
13d5b1d to
0e3eb9c
Compare
0e3eb9c to
c4727a6
Compare
wangzlei
previously approved these changes
Apr 2, 2026
4d1c9ec to
2fee0e1
Compare
2fee0e1 to
d7d22f5
Compare
wangzlei
previously approved these changes
Apr 3, 2026
0a71710 to
bd3ac27
Compare
P0: - Use SpanKind.CLIENT for inference spans (chat, text_completion, embeddings) P1: - Replace deprecated error.message with error.type in CrewAI - Replace deprecated gen_ai.prompt with gen_ai.input.messages in LangChain - Replace deprecated gen_ai.prompt with gen_ai.prompt.name in MCP - Add gen_ai.response.model extraction in LlamaIndex - Add gen_ai.response.finish_reasons (LangChain, CrewAI - real values only) - Remove system_instructions from invoke_agent spans (redundant with chat) - Remove on_agent_action/on_agent_finish from LangChain (dead code) - Add record_exception() to LangChain error handling P2: - Rename retrieve to retrieval using GenAiOperationNameValues.RETRIEVAL - Add ToolCallRequestPart and ReasoningPart to LlamaIndex output messages - Add request params (frequency_penalty, presence_penalty, stop_sequences, top_p, top_k) to LangChain, CrewAI, and LlamaIndex - Replace hardcoded strings with OTel semconv imports in contract tests - Add system_instructions assertion to chat spans in contract tests Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
…entions" This reverts commit 3979988.
leiw706
approved these changes
Apr 3, 2026
wangzlei
approved these changes
Apr 3, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description of changes:
invoke_workflowspan for LlamaIndexAgentWorkflow.run()and CrewAICrew.kickoff()following the OTel GenAI semantic conventions open-telemetry/semantic-conventions#3249invoke_agentspan for LlamaIndex workflow agent steps, merging ReAct iterations into one span per agentjinja2instrumentation in agent observability mode to reduce trace noise from LlamaIndex template rendering0.10.44to0.13.0Testing:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.