fix(logger): return non-tool-call captures back to prose - #9
Merged
Conversation
Compare the live llama-server build (b9209) against the latest GitHub release (b9670), document build-from-source vs prebuilt tradeoffs, and record that mmproj (vision) + draft-mtp speculative decoding now coexist as of b9670 (the old multimodal guard is removed). No GitHub issue ref: ad-hoc upgrade/analysis, not tracked by an issue. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Bare <function=NAME> tags without JSON arguments are no longer treated as genuine tool calls. Failed rescue captures are returned to prose_parts instead of being discarded, preventing text loss when the model literally mentions markers like <function=read> or <thinking> tags. Issue #8
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bare
<function=NAME>tags without JSON arguments are no longer treated as genuine tool calls. Failed rescue captures are returned toprose_partsinstead of being discarded, preventing text loss when the model literally mentions markers like<function=read>or<thinking>tags.Changes:
chat_logger.py: ReturnNonefor bare function tags; append failed rescue buffer back to prosetests/test_toolcall_rescue.py: Two regression tests for literal marker mentions (tests 10 & 11).gitignore: Ignore.pi/and_task.mdIssue #8