fix: add qwen, deepseek, claude to TOOL_USE_ENFORCEMENT_MODELS#28081
Closed
wzgrx wants to merge 1 commit into
Closed
fix: add qwen, deepseek, claude to TOOL_USE_ENFORCEMENT_MODELS#28081wzgrx wants to merge 1 commit into
wzgrx wants to merge 1 commit into
Conversation
19 tasks
Contributor
|
Closing in favor of #28195 by @briandevans, which is a strict superset: same fix for |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem\nModels like Qwen (qwen3.6-plus), DeepSeek, and Anthropic Claude were not triggering tool-use enforcement instructions in
automode. This caused agents to hallucinate actions ("saying but not doing") instead of actually executing tools.\n\n## Solution\nAdded"qwen","deepseek","claude", and"anthropic"to theTOOL_USE_ENFORCEMENT_MODELStuple inagent/prompt_builder.py.\n\n## Impact\nThis ensures that when users use Qwen, DeepSeek, or Claude withtool_use_enforcement: auto, the agent receives the strict instructions to actually call tools instead of just describing them.