Add async fallback support for missing LLM attributes in LlamaIndex #282
Open
Add async fallback support for missing LLM attributes in LlamaIndex #282
Conversation
…gent flows In async agent flows (ReActAgent using astream_chat), LlamaIndex stores tool definitions on the Agent object rather than in the LLM callback payload. The ContextVar tracking the current agent may not propagate across asyncio.Task boundaries, so multiple fallback strategies are needed. Changes: - Extract tool_definitions from agent context with fallback chain: serialized payload -> parent agent ContextVar -> find_agent_with_tools() - Extract response_model from raw response with fallback to request model - Extract finish_reasons from raw response choices - Add max_tokens fallback chain (serialized -> metadata -> Settings.llm) - Detect provider from LLM class name - Register agent + tools in wrap_agent_run() before wrapped() is called - Add find_agent_with_tools() to search shared dict when ContextVar fails Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In async agent flows (ReActAgent using astream_chat), LlamaIndex stores tool definitions on the Agent object rather than in the LLM callback payload. The ContextVar tracking the current agent may not propagate across asyncio.Task boundaries, so multiple fallback strategies are needed.
Changes:
Parent PR #274