Feature/302 provider model api #582

zerob13 · 2025-07-07T11:23:48Z

支持302 模型解析的api，可以拿到官方定义的模型配置

Summary by CodeRabbit

New Features
- Enhanced support for 302AI models with dynamic model metadata parsing and automatic configuration updates.
Style
- Improved code formatting and readability across several components and test files.
- Adjusted indentation and grouping in UI components for clearer structure.
- Updated JSON formatting for consistency in settings.
Bug Fixes
- Minor syntax correction in the chat input editor extension configuration.
Tests
- Reformatted test code for better clarity without changing test coverage or logic.

coderabbitai · 2025-07-07T11:23:55Z

Walkthrough

This update introduces a dynamic model metadata fetching and configuration update mechanism for the 302AI provider, allowing it to retrieve and merge model information from the 302AI API. Other changes are limited to formatting, indentation, and minor syntax adjustments across several files, with no functional impact on logic, control flow, or public interfaces.

Changes

File(s)	Change Summary
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts	Adds `_302AIModelResponse` interface and dynamic `fetchOpenAIModels` method for 302AI; minor whitespace fix in `check`.
src/main/presenter/llmProviderPresenter/baseProvider.ts	Adds newline at end of file for formatting; no logic change.
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts, src/main/presenter/llmProviderPresenter/providers/openAIResponsesProvider.ts	Refactors `summaryTitles` method to simplify array construction and formatting; no logic change.
src/main/presenter/mcpPresenter/inMemoryServers/filesystem.ts, test/main/presenter/filesystem.test.ts	Reformatting for readability, indentation, and consistency; no logic or test behavior changes.
src/renderer/src/components/ChatInput.vue	Removes trailing comma in configuration object; syntax only.
src/renderer/src/components/editor/mention/PromptParamsDialog.vue	Adjusts template structure for better grouping of input elements; no script changes.
src/renderer/src/i18n/ko-KR/settings.json	Fixes indentation of two keys for consistency; no content changes.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant _302AIProvider
    participant 302AI API
    participant configPresenter

    User->>_302AIProvider: Request available models
    _302AIProvider->>302AI API: Fetch model list
    302AI API-->>_302AIProvider: Return model metadata
    _302AIProvider->>configPresenter: Get existing model config
    _302AIProvider->>configPresenter: Update config if API data differs
    _302AIProvider-->>User: Return processed model metadata

Possibly related PRs

ThinkInAIXYZ/deepchat#527: Adds dynamic model metadata fetching and configuration update for OpenRouter and PPIO providers, similar to the new 302AI logic in this PR.

Poem

A hop and a skip, new models appear,
302AI now fetches them clear!
Formatting’s tidy, arrays in a line,
Inputs grouped neatly, everything’s fine.
With configs refreshed and code looking bright,
This bunny approves—what a delight!
🐇✨

✨ Finishing Touches

📝 Generate Docstrings

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

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Explain this complex logic.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai explain this code block.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and explain its main purpose.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
- @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (`.coderabbit.yaml`)

You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
Please see the configuration documentation for more information.
If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

coderabbitai

Actionable comments posted: 1

🔭 Outside diff range comments (1)

src/renderer/src/components/editor/mention/PromptParamsDialog.vue (1)
5-6: Replace hardcoded Chinese text with i18n keys.

The component violates the coding guidelines by using hardcoded user-facing text. All user-visible strings must use vue-i18n translation keys.

Replace the hardcoded Chinese text with appropriate i18n keys:
-        <DialogTitle>{{ promptName }} 参数设置</DialogTitle>
-        <DialogDescription> 请填写以下参数，带 * 的为必填项 </DialogDescription>
+        <DialogTitle>{{ t('prompt.paramsDialog.title', { name: promptName }) }}</DialogTitle>
+        <DialogDescription>{{ t('prompt.paramsDialog.description') }}</DialogDescription>
-        <Button variant="outline" @click="$emit('close')"> 取消 </Button>
-        <Button :disabled="hasErrors" @click="handleSubmit"> 确认 </Button>
+        <Button variant="outline" @click="$emit('close')">{{ t('common.cancel') }}</Button>
+        <Button :disabled="hasErrors" @click="handleSubmit">{{ t('common.confirm') }}</Button>
-      errors.value[param.name] = '此参数为必填项'
+      errors.value[param.name] = t('prompt.paramsDialog.requiredError')
Don't forget to import useI18n and add the corresponding translation keys to your i18n files.

Also applies to: 33-34, 88-88

🧹 Nitpick comments (3)

src/main/presenter/mcpPresenter/inMemoryServers/filesystem.ts (1)
1228-1230: Remove unnecessary continue statement.

The continue statement is redundant here as it's the last statement in the catch block.
   } catch (error) {
     // Skip paths outside allowed directories
     console.error(`[globSearch] Path validation failed for ${result}:`, error)
-    continue
   }
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (1)
151-162: Use optional chaining for cleaner code.

The vision detection logic is comprehensive, but can be simplified using optional chaining as suggested by static analysis.
 const hasVision =
   modelId.includes('vision') ||
   modelId.includes('gpt-4o') ||
   (_302aiModel.description && _302aiModel.description.includes('vision')) ||
-  (_302aiModel.description_en &&
-    _302aiModel.description_en.toLowerCase().includes('vision')) ||
+  _302aiModel.description_en?.toLowerCase().includes('vision') ||
   modelId.includes('claude') || // Some Claude models support vision
   modelId.includes('gemini') || // Gemini models often support vision
   (modelId.includes('qwen') && modelId.includes('vl')) // Qwen VL models
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (1)
1202-1202: Consider using a system role for the prompt wrapper

Placing the summarisation instructions in a system message more closely matches OpenAI’s recommended pattern and avoids conflating user content with instructions.
-const fullMessage: ChatMessage[] = [{ role: 'user', content: summaryText }]
+const fullMessage: ChatMessage[] = [{ role: 'system', content: summaryText }]

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between cb931ca and 8a1a78a.

📒 Files selected for processing (9)

src/main/presenter/llmProviderPresenter/baseProvider.ts (1 hunks)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (3 hunks)
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (1 hunks)
src/main/presenter/llmProviderPresenter/providers/openAIResponsesProvider.ts (1 hunks)
src/main/presenter/mcpPresenter/inMemoryServers/filesystem.ts (10 hunks)
src/renderer/src/components/ChatInput.vue (1 hunks)
src/renderer/src/components/editor/mention/PromptParamsDialog.vue (1 hunks)
src/renderer/src/i18n/ko-KR/settings.json (1 hunks)
test/main/presenter/filesystem.test.ts (11 hunks)

🧰 Additional context used

📓 Path-based instructions (9)

`src/renderer/src/**/*`: All user-facing strings in the renderer must use i18n k...

src/renderer/src/**/*: All user-facing strings in the renderer must use i18n keys (do not hardcode user-visible text in code; use vue-i18n translation keys instead)
Do not hardcode user-facing text in code; always use the translation system (vue-i18n) for all user-visible strings

📄 Source: CodeRabbit Inference Engine (.cursor/rules/i18n.mdc)