GPT constrain glued with message fix for streaming #3913
+83
−4
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
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes a streaming bug where the model generates json<|message|>{ in a single iteration, causing the constrain token to be incorrectly glued to the tool call message. The fix modifies the READING_CONSTRAIN state to detect and handle the <|message|> token within the same chunk.
Changes:
- Enhanced constrain reading logic to search for and handle embedded
<|message|>tokens - Added comprehensive test case covering the scenario where constrain is glued with tool call message
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| src/llm/io_processing/gptoss/tool_parser.cpp | Added logic to detect `< |
| src/test/llm/output_parsers/gptoss_output_parser_test.cpp | Added test case ConstrainGluedWithToolCall to verify correct handling of glued constrain and message tokens |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
dtrawins
approved these changes
Jan 20, 2026
mzegla
approved these changes
Jan 20, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
🛠 Summary
Fix for scenarios where model generated
json<|message|>{in single iteration