fix(agent): always use role=assistant for system error messages, never role=user#2236
Closed
ygd58 wants to merge 1 commit intoNousResearch:mainfrom
Closed
fix(agent): always use role=assistant for system error messages, never role=user#2236ygd58 wants to merge 1 commit intoNousResearch:mainfrom
ygd58 wants to merge 1 commit intoNousResearch:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #2228
Problem
System error messages were dynamically assigned role="user" when the last message was "assistant". This misattributes system behavior to the user, confusing the model about conversation state.
Fix
Always use role="assistant" for system error messages. Added
system_injected: truemetadata flag to distinguish these from real assistant responses.Consecutive assistant messages (if they occur) are the lesser evil and are already handled by
_sanitize_api_messages()at API-call time.