* fix: make token limits regex normalize e.g. `some-model-1.1` -> `some-model` while preserve e.g. `gpt-4.1` as-is.
* feat: update token limits regex for latest models `GLM-4.6`, `deepseek-v3.2-exp`.
* feat: add exact token limit number 202752 per the model config file for `GLM-4.6`.
- Add MCP Quick Start Guide with 5 practical examples
- Add 30+ ready-to-use MCP configuration examples
- Add MCP testing and validation guide
- Update tools documentation index with MCP guide links
This documentation makes it easier for users to get started
with Model Context Protocol servers in Qwen Code, reducing
setup time from hours to minutes.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* feat: Add Qwen3-VL-Plus token limits (256K input, 32K output)
- Added 256K input context window limit for Qwen3-VL-Plus model
- Updated output token limit from 8K to 32K for Qwen3-VL-Plus
- Added comprehensive tests for both input and output limits
As requested by Qwen maintainers for proper model support.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: enable high-res flag for qwen VL models
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Added 256K input context window limit for Qwen3-VL-Plus model
- Updated output token limit from 8K to 32K for Qwen3-VL-Plus
- Added comprehensive tests for both input and output limits
As requested by Qwen maintainers for proper model support.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add yolo mode support to auto vision model switch
* feat: add cli args & env variables for switch behavoir
* fix: use dedicated model names and settings
* docs: add vision model instructions
* fix: failed test case
* fix: setModel failure
- Add USE_OPENAI and QWEN_OAUTH authentication methods to GeminiAgent's authMethods array
- Enables Zed editor integration to support all available authentication options
- Add test case for QWEN_OAUTH authentication configuration
- Maintains backward compatibility with existing Google authentication methods
This allows Zed users to authenticate using:
- OpenAI API key (requires OPENAI_API_KEY environment variable)
- Qwen OAuth (2000 daily requests with OAuth2 flow)
- Existing Google authentication methods (unchanged)
- Delete QWEN.md from repository as it should be generated locally
- Add QWEN.md to .gitignore to prevent accidental commits
- Context files should be created by developers using /init command locally
- Add confirmation dialog when QWEN.md already exists and has content
- Use React.createElement to maintain .ts file compatibility
- Allow users to choose whether to regenerate existing context file
