chore: bump adapter versions and improve image input handling #709
Conversation
Bump all adapter packages to reflect latest model updates and improvements: - shared-adapter: 1.0.22 → 1.0.23 (reasoning effort variants, image input enhancements) - adapter-zhipu: 1.3.3 → 1.3.4 (add GLM-4.7-FlashX model) - adapter-wenxin: 1.3.2 → 1.3.3 (image input support, defensive normalization) - adapter-spark: 1.3.2 → 1.3.3 (update to spark-x1.5) - adapter-claude: 1.3.4 → 1.3.5 (latest Claude models) - adapter-qwen: 1.3.2 → 1.3.3 (qwen3-max thinking variants) - adapter-doubao: 1.3.2 → 1.3.3 (reasoning effort refactor, new models) - adapter-deepseek: 1.3.6 → 1.3.7 - adapter-openai: 1.3.4 → 1.3.5 - adapter-openai-like: 1.3.4 → 1.3.5 - adapter-gemini: 1.3.20 → 1.3.21 - adapter-azure-openai: 1.3.2 → 1.3.3 - adapter-hunyuan: 1.3.2 → 1.3.3 - adapter-ollama: 1.3.2 → 1.3.3 - adapter-rwkv: 1.3.2 → 1.3.3 - adapter-dify: 1.3.3 → 1.3.4
Use centralized supportImageInput utility from shared-adapter for consistent image input model detection instead of hardcoded model name checks.
|
Caution Review failedThe pull request is closed. 概览在 QWen 适配器中扩展了图像处理逻辑。通过导入 变更
可能相关的 PR
代码审查工作量评估🎯 2 (Simple) | ⏱️ ~10 分钟 兔子的诗
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello @dingyi222666, 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 focuses on a routine maintenance update across the adapter ecosystem. It systematically bumps the versions of various individual adapter packages and their shared utility dependency to ensure they are current with the latest model updates and internal improvements. A key functional enhancement is introduced in the Qwen adapter, where image input detection is standardized by integrating a new utility from the shared adapter, promoting better code consistency and maintainability. Highlights
🧠 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
Activity
Using Gemini Code AssistThe 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
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 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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request primarily bumps the versions of multiple adapter packages and their shared dependency. The changes also include a refinement in the Qwen adapter to improve how it detects models with image input capabilities. My review focuses on the implementation of this refinement and dependency consistency. I've suggested a change to further simplify the code and remove redundancy, aligning better with the goal of using a centralized utility. I also noted a small inconsistency in dependency versioning in one of the package.json files that could be addressed for better maintainability.
| ], | ||
| "dependencies": { | ||
| "@chatluna/v1-shared-adapter": "1.0.22", | ||
| "@chatluna/v1-shared-adapter": "1.0.23", |
There was a problem hiding this comment.
The dependency on @chatluna/v1-shared-adapter is pinned to an exact version, while most other adapter packages in this repository use a caret (^) to allow for compatible minor and patch updates. For consistency and easier dependency management, consider using ^1.0.23 here as well, unless there's a specific reason to pin this version.
| "@chatluna/v1-shared-adapter": "1.0.23", | |
| "@chatluna/v1-shared-adapter": "^1.0.23", |
1 participant
Summary
This PR bumps adapter package versions to reflect latest model updates and improvements from the recent adapter updates PR. Also includes refinement to Qwen adapter's image input detection.
New Features
supportImageInpututility for consistent image model detectionVersion Updates
Other Changes