Merge coder-model and qwen3.5-plus, remove vision auto-switching#1852
Merged
tanzhenxin merged 6 commits intomainfrom Feb 27, 2026
Merged
Merge coder-model and qwen3.5-plus, remove vision auto-switching#1852tanzhenxin merged 6 commits intomainfrom
tanzhenxin merged 6 commits intomainfrom
Conversation
Contributor
📋 Review SummaryThis PR consolidates the 🔍 General Feedback
🎯 Specific Feedback🟡 High
🟢 Medium
🔵 Low
✅ Highlights
|
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
…tching - Merge coder-model and qwen3.5-plus into a single coder-model with vision capability - Remove vlmSwitchMode CLI argument and experimental.vlmSwitchMode setting - Remove useVisionAutoSwitch hook and inline image format checking into useGeminiStream - Remove ModelSwitchDialog and related vision switch UI components - Update all related tests to reflect the simplified model structure - Set DEFAULT_QWEN_MODEL to coder-model Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- 将 ModelDialog.test.tsx 中的 MAINLINE_CODER_MODEL 替换为 DEFAULT_QWEN_MODEL - 修复 modelConfigResolver.test.ts 中 OpenAI auth 类型的默认模型期望 - 统一使用 core 包导出的 MAINLINE_CODER_MODEL 常量 Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
7a07da7 to
51214d9
Compare
Contributor
Code Coverage Summary
CLI Package - Full Text ReportCore Package - Full Text ReportFor detailed HTML reports, please see the 'coverage-reports-22.x-ubuntu-latest' artifact from the main CI run. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
TLDR
Merge
coder-modelandqwen3.5-plusinto a singlecoder-modelwith vision capabilities. Remove the vision model auto-switching feature (vlmSwitchMode) and related UI components since the unified model now supports both coding and vision tasks.Dive Deeper
Model Consolidation
qwen3.5-plus(vision-capable) andcoder-model(non-vision)coder-modelwithcapabilities: { vision: true }qwen3.5-plustocoder-modelRemoved Features
--vlm-switch-modeand its processing logicexperimental.vlmSwitchModeconfiguration optionuseVisionAutoSwitch.tsand its test file (deleted)isVisionSwitchDialogOpenandhandleVisionSwitchSelectfrom UI contextsCode Changes
useGeminiStream.tsinstead of a separate hookavailableModels.ts- removed vision model filtering since all models now support visiontokenLimits.tsto remove qwen3.5-plus specific patternsRationale
Since the qwen3.5-plus model already supported both coding and vision capabilities, maintaining separate models added unnecessary complexity. The unified
coder-modelsimplifies the user experience by eliminating manual model switching when uploading images.Reviewer Test Plan
Build the project:
Run tests:
npm testTest vision capabilities:
Verify settings:
experimental.vlmSwitchModeno longer appears in settings--vlm-switch-modeCLI argument is not recognizedTest model listing:
/modelcommandcoder-modelappears for qwen-oauth (no separate vision model)Testing Matrix
Note: Tests were run on macOS with
npm run buildandnpm testpassing successfully.Linked issues / bugs