feat: add Qwen3-VL and Qwen3-Max 0924 #932

yyhhyyyyyy · 2025-09-24T14:00:05Z

add Qwen3-VL and Qwen3-Max

Summary by CodeRabbit

New Features
- Added support for new Qwen3 models: qwen3-max-2025-09-23 and qwen3-vl-plus.
- Enabled web search for qwen3-max-2025-09-23.
- Enabled “thinking” mode for qwen3-vl-plus with a max thinking budget of 81,920.
- Increased max tokens for Qwen3 Max Preview to 65,536.
UI Improvements
- Thinking budget controls now include qwen3-vl-plus and use a dynamic minimum (1).
- Updated settings and chat configuration to reflect new models and search/thinking capabilities.

coderabbitai · 2025-09-24T14:00:14Z

Walkthrough

Adds new Qwen3 models (qwen3-max-2025-09-23, qwen3-vl-plus) to provider model settings, updates DashScope provider capability lists (enable_thinking/search), increases qwen3-max-preview maxTokens, and updates UI (ChatConfig, ModelConfigDialog) to support Qwen3 thinking budget (including min/max) and search visibility.

Changes

Cohort / File(s)	Summary
Provider model definitions `src/main/presenter/configPresenter/providerModelSettings.ts`	Added entries for `qwen3-max-2025-09-23` and `qwen3-vl-plus` (vision/reasoning/thinkingBudget/search flags); increased `qwen3-max-preview` maxTokens to 65536.
DashScope provider capability flags `src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts`	Included `qwen3-vl-plus` in ENABLE_THINKING_MODELS; added `qwen3-max-2025-09-23` to ENABLE_SEARCH_MODELS.
Chat UI config and validation `src/renderer/src/components/ChatConfig.vue`	Added `qwen3-vl-plus` to thinking models; introduced getQwen3MinBudget(); set Qwen3 thinking budget min/max (min=1, max=81920); updated validation and UI bindings; surfaced search for `qwen3-max-2025-09-23`.
Model dialog thinking/search config `src/renderer/src/components/settings/ModelConfigDialog.vue`	Added `qwen3-vl-plus` thinking-budget config (min 1, max 81920, default 81920, canDisable); enabled its thinking-budget UI; added `qwen3-max-2025-09-23` to search models.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  actor User
  participant UI as Chat UI
  participant Cfg as Model Settings
  participant Prov as DashScopeProvider
  participant API as DashScope API

  User->>UI: Select Qwen3 model + set thinking/search
  UI->>Cfg: Resolve model params (min/max budget, tokens)
  Cfg-->>UI: {thinkingBudget, enable_search, vision...}

  alt Qwen3 with thinking (e.g., qwen3-vl-plus)
    UI->>Prov: send request (thinkingBudget <= 81920)
    Prov->>API: chat.create(enable_thinking=true, budget)
    API-->>Prov: response
  else No thinking
    UI->>Prov: send request (no thinking params)
    Prov->>API: chat.create()
    API-->>Prov: response
  end

  opt Search-enabled (e.g., qwen3-max-2025-09-23)
    Prov->>API: enable_search=true
  end

  Prov-->>UI: message stream/result
  UI-->>User: Render output

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

feat: add qwen3 thinking budget support in ChatConfig #849 — Also updates ChatConfig.vue for Qwen3 thinking-budget logic and validation.
feat: implement dedicated DashScope provider with enable_thinking support #844 — Adjusts DashscopeProvider enable_thinking/enable_search lists for Qwen3 models.
fix: add missing qwen3-max search configuration in frontend #877 — Extends Dashscope search config for Qwen3 “max” variants.

Suggested reviewers

zerob13

Poem

I twitch my ears at models new,
Qwen3 hops in, with tokens due.
VL-Plus dreams with thinking bright,
Max seeks webs through day and night.
Budgets bounded, flags aligned—
A rabbit signs: “Ship it, fine!” 🐇✨

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The PR description "add Qwen3-VL and Qwen3-Max" does not follow the repository's required template and is missing key sections such as the problem statement, a detailed solution description, UI/UX changes, platform compatibility notes, testing steps, additional context, and the Chinese translation requested by the template, so reviewers cannot fully evaluate the change from the current description.	Please update the PR description to follow the repository template: provide a clear problem statement, a detailed description of the solution including which files and model behaviors were changed, any UI/UX changes with screenshots if applicable, platform compatibility/testing notes, testing steps for reviewers, and the additional context plus the Chinese translation section; also note any configuration or migration impacts (e.g., new model names and default budgets) so reviewers can verify the changes.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title "feat: add Qwen3-VL and Qwen3-Max 0924" clearly and concisely summarizes the primary change (adding Qwen3-VL and Qwen3-Max models) and matches the changes in the diff; it is specific and readable for teammates scanning history. The trailing date is non-essential but not misleading.
Docstring Coverage	✅ Passed	No functions found in the changes. Docstring coverage check skipped.

✨ Finishing touches

📝 Generate Docstrings

🧪 Generate unit tests

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch feat/qwen3-models-0924

Tip

👮 Agentic pre-merge checks are now available in preview!

Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.

Built-in checks – Quickly apply ready-made checks to enforce title conventions, require pull request descriptions that follow templates, validate linked issues for compliance, and more.
Custom agentic checks – Define your own rules using CodeRabbit’s advanced agentic capabilities to enforce organization-specific policies and workflows. For example, you can instruct CodeRabbit’s agent to verify that API documentation is updated whenever API schema files are modified in a PR. Note: Upto 5 custom checks are currently allowed during the preview period. Pricing for this feature will be announced in a few weeks.

Please see the documentation for more information.

Example:

reviews:
  pre_merge_checks:
    custom_checks:
      - name: "Undocumented Breaking Changes"
        mode: "warning"
        instructions: |
          Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).

Please share your feedback with us on this Discord post.

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

coderabbitai

Actionable comments posted: 0

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts (1)
106-111: Don’t drop zero budgets: check against undefined, not truthy

Using a truthy check skips valid 0 values if we ever allow “disable” via 0 for DashScope models.
-          if (modelConfig?.thinkingBudget) {
+          if (modelConfig?.thinkingBudget !== undefined) {
             modifiedParams.thinking_budget = modelConfig.thinkingBudget
           }

🧹 Nitpick comments (3)

src/renderer/src/components/settings/ModelConfigDialog.vue (2)
306-315: Use dynamic min from thinkingBudgetRange to avoid drift

The Qwen3 UI currently hard‑codes min=1 and displays min:1 in help text. Prefer the computed range for consistency with getThinkingBudgetConfig.
 <Input
   v-model.number="config.thinkingBudget"
   type="number"
-  :min="1"
+  :min="thinkingBudgetRange.min"
   :max="thinkingBudgetRange.max"
   :step="128"
   :placeholder="t('settings.model.modelConfig.thinkingBudget.qwen3.placeholder')"
   :class="{ 'border-destructive': qwen3ThinkingBudgetError }"
 />
 ...
 {{ 
   t('settings.model.modelConfig.thinkingBudget.range', {
-    min: 1,
+    min: thinkingBudgetRange.min,
     max: thinkingBudgetRange.max
   })
 }}
Also applies to: 321-327

660-792: Normalize modelId in getThinkingBudgetConfig to lower‑case

Several includes checks assume lower‑case; normalizing prevents case‑sensitivity bugs.
// At the start of getThinkingBudgetConfig:
const getThinkingBudgetConfig = (modelId: string) => {
  const id = modelId.toLowerCase()
  // Replace all `modelId.includes('...')` with `id.includes('...')`
}
src/renderer/src/components/ChatConfig.vue (1)

162-178: Avoid drift: derive supported model lists from a single source

ENABLE_SEARCH_MODELS is duplicated across provider, settings dialog, and here. Consider centralizing in shared constants or deriving from providerModelSettings.

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 5876d61 and 830ba9c.

📒 Files selected for processing (4)

src/main/presenter/configPresenter/providerModelSettings.ts (2 hunks)
src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts (2 hunks)
src/renderer/src/components/ChatConfig.vue (7 hunks)
src/renderer/src/components/settings/ModelConfigDialog.vue (3 hunks)

🧰 Additional context used

📓 Path-based instructions (23)

src/renderer/src/**/*

📄 CodeRabbit inference engine (.cursor/rules/i18n.mdc)

src/renderer/src/**/*: All user-facing strings must use i18n keys (avoid hardcoded user-visible text in code)
Use the 'vue-i18n' framework for all internationalization in the renderer
Ensure all user-visible text in the renderer uses the translation system

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/**/*.{vue,ts,js,tsx,jsx}

📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)

渲染进程代码放在 src/renderer

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/src/**/*.{vue,ts,tsx,js,jsx}

📄 CodeRabbit inference engine (.cursor/rules/vue-best-practices.mdc)

src/renderer/src/**/*.{vue,ts,tsx,js,jsx}: Use the Composition API for better code organization and reusability
Implement proper state management with Pinia
Utilize Vue Router for navigation and route management
Leverage Vue's built-in reactivity system for efficient data handling

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/src/**/*.vue

📄 CodeRabbit inference engine (.cursor/rules/vue-best-practices.mdc)

Use scoped styles to prevent CSS conflicts between components

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/**/*.{ts,tsx,vue}

📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)

src/renderer/**/*.{ts,tsx,vue}: Use descriptive variable names with auxiliary verbs (e.g., isLoading, hasError).
Use TypeScript for all code; prefer types over interfaces.
Avoid enums; use const objects instead.
Use arrow functions for methods and computed properties.
Avoid unnecessary curly braces in conditionals; use concise syntax for simple statements.

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/**/*.{vue,ts}

📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)

Implement lazy loading for routes and components.

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/**/*.{ts,vue}

📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)

src/renderer/**/*.{ts,vue}: Use useFetch and useAsyncData for data fetching.
Implement SEO best practices using Nuxt's useHead and useSeoMeta.

Use Pinia for frontend state management (do not introduce alternative state libraries)

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

**/*.{ts,tsx,js,vue}

📄 CodeRabbit inference engine (CLAUDE.md)

Use English for all logs and comments

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/renderer/src/components/ChatConfig.vue
src/main/presenter/configPresenter/providerModelSettings.ts

**/*.{ts,tsx,vue}

📄 CodeRabbit inference engine (CLAUDE.md)

Enable and adhere to strict TypeScript typing (avoid implicit any, prefer precise types)

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/renderer/src/components/ChatConfig.vue
src/main/presenter/configPresenter/providerModelSettings.ts

src/renderer/{src,shell,floating}/**/*.vue

📄 CodeRabbit inference engine (CLAUDE.md)

src/renderer/{src,shell,floating}/**/*.vue: Use Vue 3 Composition API for all components
All user-facing strings must use i18n keys via vue-i18n (no hard-coded UI strings)
Use Tailwind CSS utilities and ensure styles are scoped in Vue components

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/src/components/**/*

📄 CodeRabbit inference engine (CLAUDE.md)

Organize UI components by feature within src/renderer/src/

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/src/**

📄 CodeRabbit inference engine (AGENTS.md)

Put application code for the Vue app under src/renderer/src (components, stores, views, i18n, lib)

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

src/renderer/src/**/*.{vue,ts}

📄 CodeRabbit inference engine (AGENTS.md)

All user-facing strings in the renderer must use vue-i18n keys defined in src/renderer/src/i18n

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

**/*.{js,jsx,ts,tsx,vue}

📄 CodeRabbit inference engine (AGENTS.md)

Apply Prettier formatting: single quotes, no semicolons, max width 100

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/renderer/src/components/ChatConfig.vue
src/main/presenter/configPresenter/providerModelSettings.ts

src/renderer/**/*.vue

📄 CodeRabbit inference engine (AGENTS.md)

Name Vue components in PascalCase (e.g., ChatInput.vue)

Files:

src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/ChatConfig.vue

**/*.{js,jsx,ts,tsx}

📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)

**/*.{js,jsx,ts,tsx}: 使用 OxLint 进行代码检查
Log和注释使用英文书写

**/*.{js,jsx,ts,tsx}: Use OxLint for JS/TS code; pre-commit hooks run lint-staged and typecheck
Use camelCase for variables and functions
Use PascalCase for types and classes
Use SCREAMING_SNAKE_CASE for constants

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

src/{main,renderer}/**/*.ts

📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)

src/{main,renderer}/**/*.ts: Use context isolation for improved security
Implement proper inter-process communication (IPC) patterns
Optimize application startup time with lazy loading
Implement proper error handling and logging for debugging

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

src/main/**/*.ts

📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)

Use Electron's built-in APIs for file system and native dialogs

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

**/*.{ts,tsx}

📄 CodeRabbit inference engine (.cursor/rules/error-logging.mdc)

**/*.{ts,tsx}: 始终使用 try-catch 处理可能的错误
提供有意义的错误信息
记录详细的错误日志
优雅降级处理
日志应包含时间戳、日志级别、错误代码、错误描述、堆栈跟踪（如适用）、相关上下文信息
日志级别应包括 ERROR、WARN、INFO、DEBUG
不要吞掉错误
提供用户友好的错误信息
实现错误重试机制
避免记录敏感信息
使用结构化日志
设置适当的日志级别

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

src/main/presenter/llmProviderPresenter/providers/*.ts

📄 CodeRabbit inference engine (.cursor/rules/llm-agent-loop.mdc)

src/main/presenter/llmProviderPresenter/providers/*.ts: Each file in src/main/presenter/llmProviderPresenter/providers/*.ts should handle interaction with a specific LLM API, including request/response formatting, tool definition conversion, native/non-native tool call management, and standardizing output streams to a common event format.
Provider implementations must use a coreStream method that yields standardized stream events to decouple the main loop from provider-specific details.
The coreStream method in each Provider must perform a single streaming API request per conversation round and must not contain multi-round tool call loop logic.
Provider files should implement helper methods such as formatMessages, convertToProviderTools, parseFunctionCalls, and prepareFunctionCallPrompt as needed for provider-specific logic.
All provider implementations must parse provider-specific data chunks and yield standardized events for text, reasoning, tool calls, usage, errors, stop reasons, and image data.
When a provider does not support native function calling, it must prepare messages using prompt wrapping (e.g., prepareFunctionCallPrompt) before making the API call.
When a provider supports native function calling, MCP tools must be converted to the provider's format (e.g., using convertToProviderTools) and included in the API request.
Provider implementations should aggregate and yield usage events as part of the standardized stream.
Provider implementations should yield image data events in the standardized format when applicable.
Provider implementations should yield reasoning events in the standardized format when applicable.
Provider implementations should yield tool call events (tool_call_start, tool_call_chunk, tool_call_end) in the standardized format.
Provider implementations should yield stop events with appropriate stop_reason in the standardized format.
Provider implementations should yield error events in the standardized format...

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts

src/main/**/*.{ts,js,tsx,jsx}

📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)

主进程代码放在 src/main

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

src/main/**

📄 CodeRabbit inference engine (AGENTS.md)

Place all Electron main-process code under src/main/

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

src/main/presenter/**

📄 CodeRabbit inference engine (AGENTS.md)

src/main/presenter/**: Organize main-process presenters under src/main/presenter/ (Window/Tab/Thread/Mcp/Config/LLMProvider)
Follow the Presenter pattern for main-process modules

Files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

🧠 Learnings (2)

📚 Learning: 2025-09-06T03:07:23.817Z

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-06T03:07:23.817Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : New LLM providers must be added under src/main/presenter/llmProviderPresenter/providers/ as separate files

Applied to files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts

📚 Learning: 2025-09-06T03:07:23.817Z

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-06T03:07:23.817Z
Learning: Applies to src/main/presenter/configPresenter/providers.ts : Add provider configuration entries in src/main/presenter/configPresenter/providers.ts

Applied to files:

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts
src/main/presenter/configPresenter/providerModelSettings.ts

🔇 Additional comments (14)

src/renderer/src/components/settings/ModelConfigDialog.vue (3)

709-716: Qwen3 VL‑Plus thinking budget added — looks good

Config aligns with other 81,920‑cap Qwen3 entries.

Please confirm VL‑Plus indeed requires min=1 (others often allow 0). If min should be model‑driven, see the next comment for a UI tweak to source min from the computed range.

834-843: Enable Qwen3 VL‑Plus thinking UI — OK

VL‑Plus correctly added to supportedThinkingModels.

858-866: DashScope search support updated — OK

qwen3-max-2025-09-23 correctly included.

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts (2)

27-36: Add Qwen3 VL‑Plus to enable_thinking — OK

Matches UI and provider settings.

40-52: Add qwen3‑max‑2025‑09‑23 to enable_search — OK

Consistent with renderer/UI.

src/main/presenter/configPresenter/providerModelSettings.ts (3)

2750-2750: Increase qwen3‑max‑preview maxTokens to 65,536 — OK

Matches upstream expectations.

2881-2891: Qwen3 VL‑Plus model added — OK

Vision=true, reasoning=true, 81,920 budget; match includes dated variant. Looks consistent with UI.

2733-2745: qwen3-max-2025-09-23 — repo references consistent; confirm external model ID

Model ID appears in:

src/main/presenter/configPresenter/providerModelSettings.ts

src/main/presenter/llmProviderPresenter/providers/dashscopeProvider.ts

src/renderer/src/components/ChatConfig.vue

src/renderer/src/components/settings/ModelConfigDialog.vue

Config: enableSearch = true, maxTokens = 65536. Confirm this exact ID matches DashScope’s published model IDs.

src/renderer/src/components/ChatConfig.vue (6)

144-148: Include Qwen3 VL‑Plus in thinking‑capable models — OK

165-176: DashScope search models updated — OK

247-252: Add VL‑Plus to 81,920‑cap budget group — OK

268-272: Centralize Qwen3 min budget — OK

Helper keeps UI consistent.

365-372: Validation now uses dynamic min — OK

Leverages getQwen3MinBudget.

592-599: Reflect dynamic min/max in Qwen3 input and help — OK

Switched to getters; aligns UI and validation.

Also applies to: 606-611

* fix: katex style (#926) * refactor: reorganize artifact processing logic and improve attribute parsing (#927) * fix(thinkingBlock): pre style (#930) * refactor: remove DOMPurify dependency and replace MessageBlockThink `v-html` with vue-markdown-renderer (#931) * refactor: remove DOMPurify dependency and replace MessageBlockThink `v-html` with vue-markdown-renderer * chore: update * feat: add Qwen3-VL and Qwen3-Max 0924 (#932) * refactor: update vue-renderer-markdown to 0.0.54-beta.6 and remove Re… (#934) * refactor: update vue-renderer-markdown to 0.0.54-beta.6 and remove ReferenceNode component * chore: format * chore: version 0.3.7 --------- Co-authored-by: Simon He <57086651+Simon-He95@users.noreply.github.com> Co-authored-by: yyhhyyyyyy <yyhhyyyyyy8@gmail.com>

feat: add Qwen3-VL and Qwen3-Max 0924

830ba9c

coderabbitai bot reviewed Sep 24, 2025

View reviewed changes

zerob13 merged commit 3cb064c into dev Sep 24, 2025
2 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat: add Qwen3-VL and Qwen3-Max 0924 #932

feat: add Qwen3-VL and Qwen3-Max 0924 #932

Uh oh!

yyhhyyyyyy commented Sep 24, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

coderabbitai bot commented Sep 24, 2025 •

edited

Loading

Uh oh!

coderabbitai bot left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

feat: add Qwen3-VL and Qwen3-Max 0924 #932

feat: add Qwen3-VL and Qwen3-Max 0924 #932

Uh oh!

Conversation

yyhhyyyyyy commented Sep 24, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Sep 24, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Possibly related PRs

Suggested reviewers

Poem

Pre-merge checks and finishing touches

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

yyhhyyyyyy commented Sep 24, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Sep 24, 2025 •

edited

Loading