Repository navigation
fix(models): replay malformed tool-call arguments as valid JSON - #1327
Merged
Merged
Conversation
A model that emits a tool call with truncated or otherwise invalid JSON arguments fails that one call, but the raw string is recorded in the session. Strict OpenAI-compatible servers (vLLM, SGLang) validate every assistant tool call in the request, so each later turn is rejected with "Assistant tool call function.arguments must be valid JSON" and the agent never recovers. The turn guard now rewrites such arguments on the way out to a JSON object carrying the original text, alongside the existing duplicate call-id repair.
Contributor
 [Medium impact] The PR appears safe to merge; no new actionable issues remain. SummaryRepairs malformed tool-call arguments before replaying conversation history and asks the model to retry calls that could not run.
Reviews (3) · Last reviewed commit: "fix(models): treat over-nested tool-call..." · Reviewed by Greptile |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
…e not valid JSON A streamed turn that ends mid-tool-call leaves the client with a JSON prefix as the arguments. Instead of the SDK's generic parse-error result, the tool wrapper now short-circuits with a clear 'not executed, re-issue with complete arguments' message so the model recovers in one turn.
…ll-arguments # Conflicts: # strix/config/models.py
Collaborator
Author
|
@greptile |
Collaborator
Author
|
@greptile |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A model that emits a tool call with truncated or otherwise invalid JSON arguments fails that one call, but the raw string is recorded in the session. Strict OpenAI-compatible servers (vLLM, SGLang) validate every assistant tool call in the request, so each later turn is rejected with "Assistant tool call function.arguments must be valid JSON" and the agent never recovers. The turn guard now rewrites such arguments on the way out to a JSON object carrying the original text, alongside the existing duplicate call-id repair.