feat(providers): parse thinking tags in OpenAI compatible models

[yunxilyf]

Description

[Describe what this PR does and why]

Related Issue: Fixes #(issue_number) or Relates to #(issue_number)

Security Considerations: [If applicable, e.g. channel auth, env/config handling]

Type of Change

• [*] Bug fix
• New feature
• Breaking change
• Documentation
• Refactoring

Component(s) Affected

• Core / Backend (app, agents, config, providers, utils, local_models)
• Console (frontend web UI)
• Channels (DingTalk, Feishu, QQ, Discord, iMessage, etc.)
• Skills
• CLI
• Documentation (website)
• Tests
• CI/CD
• Scripts / Deploy

Checklist

• I ran pre-commit run --all-files locally and it passes
• If pre-commit auto-fixed files, I committed those changes and reran checks
• I ran tests locally (pytest or as relevant) and they pass
• Documentation updated (if needed)
• Ready for review

Testing

[How to test these changes]

Local Verification Evidence

pre-commit run --all-files
# paste summary result

pytest
# paste summary result

Additional Notes

[Optional: any other context]

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a significant enhancement by enabling the system to parse and extract 'thinking' tags from responses generated by OpenAI compatible models. This allows for a more granular understanding and display of an AI's internal reasoning. Concurrently, the user interface for channel settings has been refined to consistently show filtering options, and the underlying data handling for these settings has been made more robust to prevent type-related issues.

Highlights

• Thinking Tag Parsing: Implemented functionality to parse 'thinking' tags from OpenAI compatible model responses, allowing for structured extraction of internal thought processes.
• UI/UX Improvement: Adjusted the channel configuration UI to always display the 'filter tool messages' and 'filter thinking' switches, removing previous conditional rendering.
• Data Handling Refinement: Enhanced the handling of boolean values for 'filter tool messages' and 'filter thinking' in the channel configuration logic to ensure correct type conversion.
• Git Ignore Update: Added new entries to .gitignore for .copaw and .copaw.secret files.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• .gitignore
  • Added .copaw to the ignore list
  • Added .copaw.secret to the ignore list
• console/src/pages/Control/Channels/components/ChannelDrawer.tsx
  • Removed conditional rendering for 'filter_tool_messages' and 'filter_thinking' switches, making them always visible
• console/src/pages/Control/Channels/index.tsx
  • Updated boolean conversion for 'filter_tool_messages' and 'filter_thinking' when setting form field values
  • Updated boolean conversion for 'filter_tool_messages' and 'filter_thinking' when saving channel configurations
• src/copaw/providers/openai_chat_model_compat.py
  • Imported extract_thinking_from_text and text_contains_think_tag from local models
  • Implemented logic within _parse_openai_stream_response to detect and parse 'thinking' tags from text content blocks
  • Restructured chat response content to include new 'thinking' type blocks alongside 'text' blocks

Activity

• No human activity has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Generative AI Prohibited Use Policy, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request enables parsing of <think> tags from OpenAI-compatible model responses and exposes the filtering options for thinking and tool messages on the console channel UI. The changes in the Python backend correctly parse these tags from streaming responses. In the frontend, the logic for handling the filter toggles in console/src/pages/Control/Channels/index.tsx can be simplified by removing the redundant Boolean() constructor, as the logical NOT ! operator is sufficient and more idiomatic. Additionally, a small redundancy was found in the Python code where or "" is used unnecessarily.