fix(conversation_manager): filter toolUse blocks from summary messages #1448
+174
−2
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Outdated suggestions cannot be applied.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
Fixes a
ValidationExceptionthat occurs when usingstructured_output_modelwithSummarizingConversationManager.Problem
When an agent is configured with
structured_output_model, every response containstoolUseblocks for the structured output. TheSummarizingConversationManager._generate_summary()method converts the assistant's response to a user message (for context continuity), but this includes thetoolUseblocks.According to AWS Bedrock's Converse API constraints:
text,toolResult,image,documenttext,toolUse,reasoningContentThis mismatch causes:
Solution
Filter out assistant-only content blocks (
toolUse,reasoningContent) when converting the summary to a user message. If no valid content remains after filtering (edge case), create a fallback text representation.Related Issues
Fixes #1160
Documentation PR
No documentation changes required.
Type of Change
Testing
toolUseblocks from structured output responsesreasoningContentblockstoolUseruff formatandruff checkChecklist
Created by strands-coder 🦆