Skip to content

chat: allow unclosed thinking tags #13931

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 31, 2025

Conversation

ochafik
Copy link
Collaborator

@ochafik ochafik commented May 30, 2025

Fixes #13812 & #13877

Note: won't try and scavenge tool calls inside unclosed thinking tags (I've seen legit thought traces that contained mock-tool calls), although this might end up being a frequent failure mode for small Qwen3 models. Can disable thinking w/ --reasoning-budget 0 to avoid the issue w/ these.

@github-actions github-actions bot added the testing Everything test related label May 30, 2025
@ochafik ochafik changed the title server: allow unclosed thinking tags chat: allow unclosed thinking tags May 30, 2025
@ochafik ochafik marked this pull request as ready for review May 31, 2025 00:06
@ochafik ochafik merged commit e15898d into ggml-org:master May 31, 2025
46 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
testing Everything test related
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Eval bug: uncaught std::runtime_exception thrown in llama-server during tool use
2 participants