gemini bug fix #586

zerob13 · 2025-07-08T11:10:14Z

修复 Gemini 加载速度较慢的问题

Summary by CodeRabbit

New Features
- Added a "Refresh Models" button in provider settings to manually update available models, with real-time status indication.
- Enhanced model caching for improved performance and reduced latency.
- UI now notifies users when model lists are refreshed or changed.
Improvements
- Safety level settings for providers are more robust, preventing stale or incorrect values.
- Gemini provider initialization now reliably updates the UI once models are ready.
- Expanded and improved localization for safety settings and model refresh status in multiple languages.
Bug Fixes
- Resolved issues with lingering or outdated safety level data when switching providers or updating settings.
Style
- Minor code style adjustments for consistency (e.g., semicolon removal).
Chores
- Updated localization files with new strings for risk blocking and model refresh actions.

coderabbitai · 2025-07-08T11:10:20Z

Walkthrough

This update introduces an in-memory caching layer for model configuration management, synchronizes cache and persistent storage in all relevant operations, and provides explicit cache control. It also adds model refresh functionality to provider presenters, updates UI components to support model refreshing and improved safety level handling, and extends localization files with new strings for these features.

Changes

File(s)	Change Summary
src/main/presenter/configPresenter/modelConfig.ts	Added in-memory cache and cache initialization logic to `ModelConfigHelper`. All config read/write methods now synchronize with the cache. New method `clearMemoryCache()` added.
src/main/presenter/llmProviderPresenter/baseProvider.ts	Enhanced `BaseLLMProvider` to initialize models from cache, synchronize custom model changes with config, and added a public `refreshModels()` method that fetches models and emits a UI event.
src/main/presenter/llmProviderPresenter/index.ts, src/shared/presenter.d.ts	Added `refreshModels(providerId: string): Promise<void>` method to both the presenter class and its interface.
src/main/presenter/llmProviderPresenter/providers/geminiProvider.ts	Added event dispatch after Gemini model initialization to notify UI of model list changes.
src/main/presenter/githubCopilotDeviceFlow.ts	Removed trailing semicolons for code style consistency; no logic changes.
src/renderer/src/components/settings/GeminiSafetyConfig.vue	Refactored safety level access to use accessor functions and improved reactivity and correctness in updating safety levels.
src/renderer/src/components/settings/ModelProviderSettingsDetail.vue	Cleared Gemini safety levels before reinitialization, improved type safety, and ensured proper reactivity when passing safety levels to child components.
src/renderer/src/components/settings/ProviderApiConfig.vue	Replaced "How to Get" button with a "Refresh Models" button, added loading state and refresh logic, removed provider website opening logic.
src/renderer/src/stores/settings.ts	Made model refresh calls non-blocking by removing `await` from refresh function calls.
src/renderer/src/i18n/en-US/settings.json and other i18n JSONs (fa-IR, fr-FR, ja-JP, etc)	Added new localization strings for safety levels and model refreshing status/messages in multiple languages.

Sequence Diagram(s)

sequenceDiagram
    participant UI as User Interface
    participant Renderer as Renderer Process
    participant Presenter as LLMProviderPresenter
    participant Provider as BaseLLMProvider
    participant Config as ModelConfigHelper

    UI->>Renderer: Click "Refresh Models"
    Renderer->>Presenter: refreshModels(providerId)
    Presenter->>Provider: refreshModels()
    Provider->>Provider: Fetch models from network
    Provider->>Config: Update model configs (sync cache & store)
    Provider->>Renderer: Emit MODEL_LIST_CHANGED event
    Renderer->>UI: Update model list display

Possibly related PRs

ThinkInAIXYZ/deepchat#516: Introduces the initial ModelConfigHelper class with persistent storage and config retrieval logic, which the current PR extends with in-memory caching and synchronization.

Poem

🐇✨
A cache now hops in memory bright,
Models refresh with a button’s light.
Safety levels clear and true,
Locales now greet in languages new.
With every hop, configs align—
The code is fresh, the models fine!
—Your code rabbit, on cloud nine.

📜 Recent review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 37423a7 and 23fc3d1.

📒 Files selected for processing (3)

src/main/presenter/llmProviderPresenter/index.ts (1 hunks)
src/renderer/src/i18n/ja-JP/settings.json (2 hunks)
src/renderer/src/i18n/zh-CN/settings.json (2 hunks)

🚧 Files skipped from review as they are similar to previous changes (3)

src/renderer/src/i18n/ja-JP/settings.json
src/renderer/src/i18n/zh-CN/settings.json
src/main/presenter/llmProviderPresenter/index.ts

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: build-check (x64)

✨ 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: 4

🧹 Nitpick comments (4)

src/renderer/src/i18n/fa-IR/settings.json (2)
251-256: Refine Persian wording for the new safety options
The current strings mix Persian and English and sound unnatural. A tighter translation would be:
-"blockMost": "خطرات متوسط را مسدود کنید",
+"blockMost": "مسدودسازی خطر متوسط",
-"blockSome": "بلوک ریسک کم"
+"blockSome": "مسدودسازی خطر کم"
This keeps phrasing parallel across the four options.

278-279: Polish the “refreshingModels” text
-"refreshingModels": "طراوت ..."
+"refreshingModels": "در حال تازه‌سازی مدل‌ها..."
A more idiomatic Persian progress message.
src/renderer/src/i18n/ko-KR/settings.json (2)
251-256: Improve the Korean safety-level wording

Current phrasing is awkward (“…을 차단하십시오”). Consider:
-"blockHighest": "높은 위험을 차단하십시오",
-"blockMost": "중간 위험을 차단합니다",
-"blockSome": "낮은 위험을 차단하십시오",
+"blockHighest": "높은 위험 차단",
+"blockMost": "중간 위험 차단",
+"blockSome": "낮은 위험 차단",
Shorter and consistent with common UI patterns.

278-279: More natural progress text
-"refreshingModels": "상쾌한 ..."
+"refreshingModels": "모델 새로고침 중..."

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between c216a60 and 37423a7.

📒 Files selected for processing (19)

src/main/presenter/configPresenter/modelConfig.ts (7 hunks)
src/main/presenter/githubCopilotDeviceFlow.ts (3 hunks)
src/main/presenter/llmProviderPresenter/baseProvider.ts (8 hunks)
src/main/presenter/llmProviderPresenter/index.ts (1 hunks)
src/main/presenter/llmProviderPresenter/providers/geminiProvider.ts (2 hunks)
src/renderer/src/components/settings/GeminiSafetyConfig.vue (3 hunks)
src/renderer/src/components/settings/ModelProviderSettingsDetail.vue (5 hunks)
src/renderer/src/components/settings/ProviderApiConfig.vue (4 hunks)
src/renderer/src/i18n/en-US/settings.json (2 hunks)
src/renderer/src/i18n/fa-IR/settings.json (2 hunks)
src/renderer/src/i18n/fr-FR/settings.json (2 hunks)
src/renderer/src/i18n/ja-JP/settings.json (2 hunks)
src/renderer/src/i18n/ko-KR/settings.json (2 hunks)
src/renderer/src/i18n/ru-RU/settings.json (2 hunks)
src/renderer/src/i18n/zh-CN/settings.json (2 hunks)
src/renderer/src/i18n/zh-HK/settings.json (2 hunks)
src/renderer/src/i18n/zh-TW/settings.json (2 hunks)
src/renderer/src/stores/settings.ts (4 hunks)
src/shared/presenter.d.ts (1 hunks)

🧰 Additional context used

📓 Path-based instructions (13)

`**/*.{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}: 使用 OxLint 进行代码检查
Log和注释使用英文书写

📄 Source: CodeRabbit Inference Engine (.cursor/rules/development-setup.mdc)