fix(agent): recognize emoji and caret as natural response endings (#28168)#28324
Merged
Conversation
GLM models via Ollama report finish_reason='stop' even when the response was truncated by max_tokens. The continuation mechanism uses _has_natural_response_ending() as one of the heuristics to detect whether the response was genuinely finished. Currently only ASCII punctuation and CJK punctuation are recognized. This means any response ending with an emoji (e.g. ⚡, 👍) or the caret character ^ (common in French ^^ smiley) is not recognized as naturally ended, triggering a false-positive continuation where the model receives 'Continue where you left off' and produces garbled output. Add: - ^ (caret) to the punctuation set - Unicode emoji range (codepoint >= 0x1F300) as natural ending This only affects GLM/Ollama users but the fix is safe for all backends since _has_natural_response_ending() is only consulted inside the continuation flow.
23 tasks
Contributor
🔎 Lint report:
|
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Salvage of #28168 by @oseftg.
What: GLM models via Ollama report
finish_reason='stop'even when the response was truncated by max_tokens. The continuation heuristic uses_has_natural_response_ending()to detect truncation, but the regex didn't cover responses ending in emoji or caret (^), so legitimate model outputs ending that way were misclassified as truncated and re-prompted unnecessarily.How: Add caret to the punctuation set, and accept any character with
ord() >= 0x1F300(covers Misc Symbols, Dingbats, Emoticons, Supplemental) as a natural ending.Original PR: #28168