Add thinking/reasoning capability detection #20
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
- Add supports_thinking flag to detect reasoning_content field support - Add supports_disable_thinking, supports_reasoning_only, supports_reasoning_with_content flags - Add reasoning_requires_tools flag for templates that only reason with tools - Add tests for Qwen3-235B-A22B-Thinking-2507 and GLM-4.6 - Add model IDs: DeepSeek-V3.1, granite-3.3-2b-instruct, GLM-4.7 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
1 task
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Outdated suggestions cannot be applied.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
This PR implements auto-detection of thinking/reasoning capabilities for chat templates, as requested in #19.
Changes
New Capability Flags
Added 5 new capability flags to `chat_template_caps`:
Detection Logic
The detection tests templates by rendering messages with `reasoning_content` field and checking if the content appears in the output.
Tests
Both templates correctly detect `supports_thinking = true`.
Model IDs
Added model IDs from llama.cpp tests:
Note on GLM-4.7
GLM-4.7 introduces a new `clear_thinking` variable for "Preserved Thinking" - thinking content stays in context but can be shown as empty ``` tags. This differs from `enable_thinking` which controls whether ``` tags are emitted at all.
Closes #19