fix: include tool executions in _extract_trace_level #77
Conversation
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
The TraceLevelInput type supports list[ToolExecution] in session_history, but _extract_trace_level was not populating it. This caused FaithfulnessEvaluator to evaluate without tool context, even though its prompt mentions tool outputs. This fix adds tool execution extraction to match _extract_tool_level behavior.
razkenari
requested a deployment
to
manual-approval
GitHub Actions
Waiting
cagataycali
approved these changes
Jan 10, 2026
Member
cagataycali
left a comment
cagataycali
left a comment
There was a problem hiding this comment.
LGTM! ✅
This PR correctly addresses issue #76 where FaithfulnessEvaluator was missing tool execution context.
Review Summary
Change Analysis:
- Adds tool execution extraction to
_extract_trace_level() - Matches existing behavior in
_extract_tool_level() - Small, focused change (+14/-1 lines)
- Single file modified (
trace_extractor.py)
Code Quality:
- ✅ Fix is consistent with existing patterns in the codebase
- ✅ PR description clearly explains the problem and solution
- ✅ Links to related issue (#76)
- ✅ Checklist completed
Impact:
FaithfulnessEvaluatorwill now properly receive tool call/result data- Enables accurate faithfulness evaluation for agents using tools
- No breaking changes expected
Suggestion for Maintainers:
Consider if tests should be added to verify tool executions appear in TraceLevelInput.session_history. The PR mentions manual verification but automated tests would prevent regression.
Review by strands-coder autonomous agent 🤖
Member
🤖 Merge Readiness CheckStatus:
This fix addresses tool execution extraction in trace-level operations - important for accurate evaluation traces. Recommendation: CI needs to run. Once CI passes, this PR is ready for merge. Automated analysis by strands-coder 🤖 |
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.
The TraceLevelInput type supports list[ToolExecution] in session_history, but _extract_trace_level was not populating it. This caused FaithfulnessEvaluator to evaluate without tool context, even though its prompt mentions tool outputs.
This fix adds tool execution extraction to match _extract_tool_level behavior.
Description
_extract_trace_level()now includes tool executions insession_history, matching the behavior of_extract_tool_level(). This ensuresFaithfulnessEvaluatorreceives tool call/result data for proper faithfulness evaluation.Related Issues
Fixes #76
Documentation PR
N/A - no documentation changes needed
Type of Change
Bug fix
Testing
Verified tool executions now appear in
TraceLevelInput.session_historyCompared output with
_extract_tool_level()to confirm consistencyI ran
hatch run prepareChecklist