feat: skip auto-commit when LLM response is truncated#5033
Open
Fatty911 wants to merge 1 commit intoAider-AI:mainfrom
Open
feat: skip auto-commit when LLM response is truncated#5033Fatty911 wants to merge 1 commit intoAider-AI:mainfrom
Fatty911 wants to merge 1 commit intoAider-AI:mainfrom
Conversation
Detect both explicit (FinishReasonLength) and silent truncation (output tokens >= 92% of model limit) and skip auto-commit so users can review potentially incomplete edits before committing. - Reset response_was_truncated flag at start of each send_message - Set flag on FinishReasonLength for non-prefill models - Add silent truncation heuristic (non-prefill models only to avoid false positives from multi-response continuation) - Guard auto_commit to skip and warn when truncation detected
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Detect both explicit (FinishReasonLength) and silent truncation (output tokens >= 92% of model limit) and skip auto-commit so users can review potentially incomplete edits before committing.