chore: bump up deps and update new providers #1221
Conversation
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
📝 WalkthroughWalkthroughReplaces local provider-ID alias lookups with a centralized resolver, routes provider lookups through that resolver, swaps several providers' hard-coded model lists for DB-driven model metadata (with derived flags/types), centralizes logging, relaxes model-id validation, and bumps multiple dependencies. Changes
Sequence Diagram(s)sequenceDiagram
participant UI as Renderer/UI
participant Provider as Provider Presenter (e.g., Zhipu/Doubao/Minimax)
participant Cap as modelCapabilities / providerId resolver
participant Loader as providerDbLoader
participant DB as ProviderDB
UI->>Provider: fetch models request
Provider->>Cap: resolveProviderId(requestedId)
Note right of Cap `#E6F4EA`: Uses PROVIDER_ID_ALIASES\nreturns canonical id or original
Cap-->>Provider: resolvedProviderId
Provider->>Loader: getProvider(resolvedProviderId)
Loader->>DB: lookup provider entry
DB-->>Loader: provider object (models[])
Loader-->>Provider: provider | undefined
alt provider with models
Provider->>Provider: map provider.models -> MODEL_META[]\n(derive id,name,limits,vision,functionCall,reasoning,enableSearch,type)
Provider-->>UI: return MODEL_META[]
else no provider/models
Provider-->>UI: return []
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested labels
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
package.json
🧰 Additional context used
📓 Path-based instructions (1)
package.json
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
package.json: Node.js >= 22 required
pnpm >= 9 required
Files:
package.json
🧠 Learnings (9)
📓 Common learnings
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/development-setup.mdc:0-0
Timestamp: 2025-11-25T05:26:15.929Z
Learning: Applies to package.json : Node.js >= 22 required
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/development-setup.mdc:0-0
Timestamp: 2025-11-25T05:26:15.929Z
Learning: Applies to package.json : pnpm >= 9 required
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-11-25T05:28:20.513Z
Learning: Require Node ≥ 20.19 and pnpm ≥ 10.11 (pnpm only, not npm) as the project toolchain
📚 Learning: 2025-11-25T05:26:15.929Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/development-setup.mdc:0-0
Timestamp: 2025-11-25T05:26:15.929Z
Learning: Applies to package.json : Node.js >= 22 required
Applied to files:
package.json
📚 Learning: 2025-11-25T05:26:15.929Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/development-setup.mdc:0-0
Timestamp: 2025-11-25T05:26:15.929Z
Learning: Applies to package.json : pnpm >= 9 required
Applied to files:
package.json
📚 Learning: 2025-11-25T05:28:20.513Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-11-25T05:28:20.513Z
Learning: Require Node ≥ 20.19 and pnpm ≥ 10.11 (pnpm only, not npm) as the project toolchain
Applied to files:
package.json
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Use `pnpm` as the package manager (required Node.js >= 20.19.0, pnpm >= 10.11.0)
Applied to files:
package.json
📚 Learning: 2025-10-12T00:58:06.513Z
Learnt from: zerob13
Repo: ThinkInAIXYZ/deepchat PR: 977
File: package.json:137-137
Timestamp: 2025-10-12T00:58:06.513Z
Learning: In this Electron project, renderer process dependencies (used only in src/renderer/) should be placed in devDependencies because they are bundled by electron-vite during the build process. Only main process dependencies (used in src/main/) need to be in the dependencies section.
Applied to files:
package.json
📚 Learning: 2025-11-25T05:28:20.513Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-11-25T05:28:20.513Z
Learning: Applies to test/**/*.{test,spec}.ts : Use Vitest and Vue Test Utils for testing with jsdom configuration
Applied to files:
package.json
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to test/**/*.{test,spec}.{ts,tsx,js} : Use Vitest framework for unit and integration tests
Applied to files:
package.json
📚 Learning: 2025-11-25T05:28:04.454Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/vue-shadcn.mdc:0-0
Timestamp: 2025-11-25T05:28:04.454Z
Learning: Applies to src/renderer/**/*.vue : Use Shadcn Vue, Radix Vue, and Tailwind for components and styling
Applied to files:
package.json
⏰ 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)
🔇 Additional comments (3)
package.json (3)
108-109: DevDependency versions are all valid and accessible.All referenced packages in the devDependencies section are legitimate versions that exist on npm, including the @iconify packages, Vue ecosystem updates, and build tools specified at the indicated lines.
85-85: Major version jump in glob requires careful verification.The update from ^11.0.3 to ^13.0.0 introduces significant breaking changes:
- Glob constructor now requires an options object (no longer optional)
- API surface redesigned: new async functions (glob/globSync, globStream, globIterate)
- Return type changes when
withFileTypesis used (Path vs string)- CLI moved to separate
glob-binpackage- Dependency bumps: minimatch^10, path-scurry^2, minipass^7
Verify that all glob usages in the codebase are compatible with v13's new API. Pay particular attention to any Glob constructor calls, import statements, and CLI invocations.
63-64: AWS SDK minor version updates are valid and carry no known security vulnerabilities.Both @aws-sdk/client-bedrock and @aws-sdk/client-bedrock-runtime version 3.958.0 exist and were published Dec 23, 2025. The bumps from ^3.929.0 to ^3.958.0 follow semver conventions and are backward compatible.
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
resources/model-db/providers.jsonscripts/fetch-provider-db.mjs
🧰 Additional context used
📓 Path-based instructions (1)
**/*.{js,ts,jsx,tsx,mjs,cjs}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
Write logs and comments in English
Files:
scripts/fetch-provider-db.mjs
🧠 Learnings (3)
📓 Common learnings
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call IDs in Provider implementations must be globally unique and stable, with chunks arriving strictly in order
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call IDs in Provider implementations must be globally unique and stable, with chunks arriving strictly in order
Applied to files:
scripts/fetch-provider-db.mjs
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
Applied to files:
scripts/fetch-provider-db.mjs
🧬 Code graph analysis (1)
scripts/fetch-provider-db.mjs (1)
src/shared/types/model-db.ts (1)
isValidLowercaseProviderId(90-94)
⏰ 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)
🔇 Additional comments (3)
scripts/fetch-provider-db.mjs (2)
27-36: Provider ID normalization looks good.The mapping provides clear normalization from verbose provider IDs to canonical forms. This aligns with the renamings in
resources/model-db/providers.jsonas noted in the summary.
154-155: Correct usage of mapped provider ID.Using
mappedPidfor both the object key and theidfield ensures consistent normalization in the output. Downstream consumers will receive the canonical provider IDs.resources/model-db/providers.json (1)
17414-17418: Provider ID normalization is safe—no stale references to old IDs in the codebase.All provider keys now match their corresponding
idfields, and user-facingname/display_namevalues are preserved. Verification confirms no references to the old provider IDs (github-models,togetherai,azure,google-vertex,zhipuai,fireworks-ai,ppinfra,aws-bedrock) exist elsewhere in the codebase, so this change carries no breaking risk.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
src/main/presenter/configPresenter/modelCapabilities.ts (1)
102-106: Use structured logging instead ofconsole.log.Per coding guidelines, use
logger.debug()or similar structured logging methods instead ofconsole.logfor maintainability and proper log level control.🔎 Suggested fix
if (alias) { - console.log(`[ModelCapabilities] Provider ID mapped: "${providerId}" -> "${alias}"`) + // Consider using logger.debug() from your logging utility: + // logger.debug(`Provider ID mapped: "${providerId}" -> "${alias}"`) return alias }src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts (1)
19-24: Redundant provider ID resolution.Line 20 manually resolves the provider ID, but
providerDbLoader.getProvider()(line 21) also calls the resolver internally viasetProviderIdResolver. This double resolution is harmless but redundant. You can simplify by passingthis.provider.iddirectly.Additionally, consider adding a debug log when the provider is not found, to aid troubleshooting when the provider DB is misconfigured.
🔎 Suggested simplification
protected async fetchOpenAIModels(): Promise<MODEL_META[]> { - const resolvedId = modelCapabilities.resolveProviderId(this.provider.id) || this.provider.id - const provider = providerDbLoader.getProvider(resolvedId) + const provider = providerDbLoader.getProvider(this.provider.id) if (!provider || !Array.isArray(provider.models)) { + // Consider: logger.debug(`No provider models found for: ${this.provider.id}`) return [] }
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
src/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
🧰 Additional context used
📓 Path-based instructions (16)
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for logs and comments (Chinese text exists in legacy code, but new code should use English)
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and maintain strict TypeScript type checking for all files
**/*.{ts,tsx}: Always use try-catch to handle possible errors in TypeScript code
Provide meaningful error messages when catching errors
Log detailed error logs including error details, context, and stack traces
Distinguish and handle different error types (UserError, NetworkError, SystemError, BusinessError) with appropriate handlers in TypeScript
Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities
Do not suppress errors (avoid empty catch blocks or silently ignoring errors)
Provide user-friendly error messages for user-facing errors in TypeScript components
Implement error retry mechanisms for transient failures in TypeScript
Avoid logging sensitive information (passwords, tokens, PII) in logs
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/main/presenter/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Organize core business logic into dedicated Presenter classes, with one presenter per functional domain
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/main/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Use EventBus from
src/main/eventbus.tsfor main-to-renderer communication, broadcasting events viamainWindow.webContents.send()
src/main/**/*.ts: Use EventBus pattern for inter-process communication within the main process to decouple modules
Use Electron's built-in APIs for file system and native dialogs instead of Node.js or custom implementations
src/main/**/*.ts: Electron main process code belongs insrc/main/with presenters inpresenter/(Window/Tab/Thread/Mcp/Config/LLMProvider) andeventbus.tsfor app events
Use the Presenter pattern in the main process for UI coordination
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/main/presenter/configPresenter/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Store and retrieve custom prompts via
configPresenter.getCustomPrompts()for config-based data source management
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.ts
**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Do not include AI co-authoring information (e.g., 'Co-Authored-By: Claude') in git commits
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
**/*.{js,ts,jsx,tsx,mjs,cjs}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
Write logs and comments in English
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
{src/main/presenter/**/*.ts,src/renderer/**/*.ts}
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Implement proper inter-process communication (IPC) patterns using Electron's ipcRenderer and ipcMain APIs
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/**/*
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
New features should be developed in the
srcdirectory
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/main/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Main process code for Electron should be placed in
src/main
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/**/*.{ts,tsx,vue,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use Prettier with single quotes, no semicolons, and 100 character width
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use OxLint for linting JavaScript and TypeScript files
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.{ts,tsx}: Use camelCase for variable and function names in TypeScript files
Use PascalCase for type and class names in TypeScript
Use SCREAMING_SNAKE_CASE for constant names
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use EventBus for inter-process communication events
Files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/main/presenter/llmProviderPresenter/providers/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
src/main/presenter/llmProviderPresenter/providers/*.ts: Each LLM provider must implement thecoreStreammethod following the standardized event interface for tool calling and response streaming
Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
src/main/presenter/llmProviderPresenter/providers/*.ts: In Provider implementations (src/main/presenter/llmProviderPresenter/providers/*.ts), thecoreStream(messages, modelId, temperature, maxTokens)method should perform a single-pass streaming API request for each conversation round without containing multi-turn tool call loop logic
In Provider implementations, handle native tool support by converting MCP tools to Provider format usingconvertToProviderToolsand including them in the API request; for Providers without native function call support, prepare messages usingprepareFunctionCallPromptbefore making the API call
In Provider implementations, parse Provider-specific data chunks from the streaming response andyieldstandardizedLLMCoreStreamEventobjects conforming to the standard stream event interface, including text, reasoning, tool calls, usage, errors, stop reasons, and image data
In Provider implementations, include helper methods for Provider-specific operations such asformatMessages,convertToProviderTools,parseFunctionCalls, andprepareFunctionCallPrompt
Files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
src/main/presenter/llmProviderPresenter/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm-agent-loop.mdc)
Define the standardized
LLMCoreStreamEventinterface with fields:type(text | reasoning | tool_call_start | tool_call_chunk | tool_call_end | error | usage | stop | image_data),content(for text),reasoning_content(for reasoning),tool_call_id,tool_call_name,tool_call_arguments_chunk(for streaming),tool_call_arguments_complete(for complete arguments),error_message,usageobject with token counts,stop_reason(tool_use | max_tokens | stop_sequence | error | complete), andimage_dataobject with Base64-encoded data and mimeType
Files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
🧠 Learnings (14)
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, include helper methods for Provider-specific operations such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt`
Applied to files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Implement separation of concerns where `src/main/presenter/llmProviderPresenter/index.ts` manages the Agent loop and conversation history, while Provider files handle LLM API interactions, Provider-specific request/response formatting, tool definition conversion, and native vs non-native tool call mechanisms
Applied to files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call IDs in Provider implementations must be globally unique and stable, with chunks arriving strictly in order
Applied to files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
Applied to files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, handle native tool support by converting MCP tools to Provider format using `convertToProviderTools` and including them in the API request; for Providers without native function call support, prepare messages using `prepareFunctionCallPrompt` before making the API call
Applied to files:
src/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, parse Provider-specific data chunks from the streaming response and `yield` standardized `LLMCoreStreamEvent` objects conforming to the standard stream event interface, including text, reasoning, tool calls, usage, errors, stop reasons, and image data
Applied to files:
src/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Every event construction in Provider implementations must use factory functions
Applied to files:
src/main/presenter/configPresenter/modelCapabilities.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Reasoning events: `reasoning` is optional; if provided, ensure it contains the complete chain
Applied to files:
src/main/presenter/configPresenter/modelCapabilities.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations (`src/main/presenter/llmProviderPresenter/providers/*.ts`), the `coreStream(messages, modelId, temperature, maxTokens)` method should perform a *single-pass* streaming API request for each conversation round without containing multi-turn tool call loop logic
Applied to files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/**/*.ts : Define the standardized `LLMCoreStreamEvent` interface with fields: `type` (text | reasoning | tool_call_start | tool_call_chunk | tool_call_end | error | usage | stop | image_data), `content` (for text), `reasoning_content` (for reasoning), `tool_call_id`, `tool_call_name`, `tool_call_arguments_chunk` (for streaming), `tool_call_arguments_complete` (for complete arguments), `error_message`, `usage` object with token counts, `stop_reason` (tool_use | max_tokens | stop_sequence | error | complete), and `image_data` object with Base64-encoded data and mimeType
Applied to files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : In `src/main/presenter/llmProviderPresenter/index.ts`, listen for standardized events yielded by `coreStream` and handle them accordingly: buffer text content (`currentContent`), handle `tool_call_start/chunk/end` events by collecting tool details and calling `presenter.mcpPresenter.callTool`, send frontend events via `eventBus` with tool call status, format tool results for the next LLM call, and set `needContinueConversation = true`
Applied to files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Each LLM provider must implement the `coreStream` method following the standardized event interface for tool calling and response streaming
Applied to files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : In `src/main/presenter/llmProviderPresenter/index.ts` (`startStreamCompletion`), implement the Agent loop that manages the overall conversation flow, including multiple rounds of LLM calls and tool usage, maintaining `conversationMessages` history, calling `provider.coreStream()` on each iteration, and controlling the loop using `needContinueConversation` and `toolCallCount` (compared against `MAX_TOOL_CALLS`)
Applied to files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/configPresenter/**/*.ts : Store and retrieve custom prompts via `configPresenter.getCustomPrompts()` for config-based data source management
Applied to files:
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts
🧬 Code graph analysis (3)
src/main/presenter/configPresenter/providerDbLoader.ts (1)
src/shared/types/model-db.ts (1)
ProviderEntry(72-72)
src/main/presenter/configPresenter/modelCapabilities.ts (1)
src/main/presenter/configPresenter/providerDbLoader.ts (1)
providerDbLoader(241-241)
src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts (2)
src/main/presenter/configPresenter/modelCapabilities.ts (1)
modelCapabilities(190-190)src/main/presenter/configPresenter/providerDbLoader.ts (1)
providerDbLoader(241-241)
⏰ 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)
🔇 Additional comments (5)
src/main/presenter/configPresenter/modelCapabilities.ts (2)
20-31: LGTM on the expanded provider ID aliases.The alias mappings are well-organized and cover common provider ID variations. This enables cleaner provider resolution across the codebase.
33-37: Good initialization pattern for the resolver.Wiring the resolver in the constructor ensures it's available before any provider lookups occur, and the event subscriptions for index rebuilding are properly set up.
src/main/presenter/configPresenter/providerDbLoader.ts (2)
30-30: Well-designed resolver injection pattern.The nullable function type with the setter allows clean dependency injection of the resolver from
ModelCapabilities. This maintains separation of concerns between the loader and the aliasing logic.Also applies to: 67-69
71-76: Clean provider lookup with resolution fallback.The optional chaining with nullish coalescing (
??) correctly handles the case when no resolver is set, falling back to the originalproviderId.src/main/presenter/llmProviderPresenter/providers/zhipuProvider.ts (1)
26-47: Good dynamic model metadata construction.The mapping correctly handles:
- Fallback chain for model name (
display_name→name→id)- Default values for context/token limits
- Boolean coercion for capability flags
- Model type determination based on modalities
This is a clean transition from hard-coded data to provider-driven configuration.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
src/main/presenter/configPresenter/modelConfig.ts (1)
6-6: LGTM! Centralized provider ID resolution improves maintainability.The refactoring to delegate provider ID alias resolution to the external
resolveProviderIdutility eliminates code duplication and creates a single source of truth for provider ID mappings.Also applies to: 45-47
src/main/presenter/configPresenter/providerId.ts (1)
1-17: Good centralization of provider ID aliases.The implementation correctly encapsulates alias resolution logic in a single location. The function handles undefined input gracefully and uses the nullish coalescing operator appropriately.
Optional: Add documentation for maintainability
Consider adding JSDoc comments to explain the purpose of the aliases and the resolution behavior:
+/** + * Map of legacy or alternative provider IDs to their canonical IDs + * Used to maintain backward compatibility and support multiple naming conventions + */ const PROVIDER_ID_ALIASES: Record<string, string> = { dashscope: 'alibaba-cn', gemini: 'google', zhipu: 'zhipuai', vertex: 'google-vertex', together: 'togetherai', github: 'github-models', 'azure-openai': 'azure', 'aws-bedrock': 'amazon-bedrock', ppio: 'ppinfra', fireworks: 'fireworks-ai' } +/** + * Resolves provider ID aliases to their canonical form + * @param providerId - The provider ID (may be an alias or canonical ID) + * @returns The canonical provider ID, or undefined if input is undefined + */ export const resolveProviderId = (providerId: string | undefined): string | undefined => { if (!providerId) return undefined return PROVIDER_ID_ALIASES[providerId] ?? providerId }
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
src/main/presenter/configPresenter/modelCapabilities.tssrc/main/presenter/configPresenter/modelConfig.tssrc/main/presenter/configPresenter/providerDbLoader.tssrc/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.ts
🚧 Files skipped from review as they are similar to previous changes (2)
- src/main/presenter/configPresenter/providerDbLoader.ts
- src/main/presenter/configPresenter/modelCapabilities.ts
🧰 Additional context used
📓 Path-based instructions (15)
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for logs and comments (Chinese text exists in legacy code, but new code should use English)
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and maintain strict TypeScript type checking for all files
**/*.{ts,tsx}: Always use try-catch to handle possible errors in TypeScript code
Provide meaningful error messages when catching errors
Log detailed error logs including error details, context, and stack traces
Distinguish and handle different error types (UserError, NetworkError, SystemError, BusinessError) with appropriate handlers in TypeScript
Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities
Do not suppress errors (avoid empty catch blocks or silently ignoring errors)
Provide user-friendly error messages for user-facing errors in TypeScript components
Implement error retry mechanisms for transient failures in TypeScript
Avoid logging sensitive information (passwords, tokens, PII) in logs
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/main/presenter/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Organize core business logic into dedicated Presenter classes, with one presenter per functional domain
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/main/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Use EventBus from
src/main/eventbus.tsfor main-to-renderer communication, broadcasting events viamainWindow.webContents.send()
src/main/**/*.ts: Use EventBus pattern for inter-process communication within the main process to decouple modules
Use Electron's built-in APIs for file system and native dialogs instead of Node.js or custom implementations
src/main/**/*.ts: Electron main process code belongs insrc/main/with presenters inpresenter/(Window/Tab/Thread/Mcp/Config/LLMProvider) andeventbus.tsfor app events
Use the Presenter pattern in the main process for UI coordination
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/main/presenter/configPresenter/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Store and retrieve custom prompts via
configPresenter.getCustomPrompts()for config-based data source management
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/configPresenter/modelConfig.ts
**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Do not include AI co-authoring information (e.g., 'Co-Authored-By: Claude') in git commits
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
**/*.{js,ts,jsx,tsx,mjs,cjs}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
Write logs and comments in English
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
{src/main/presenter/**/*.ts,src/renderer/**/*.ts}
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Implement proper inter-process communication (IPC) patterns using Electron's ipcRenderer and ipcMain APIs
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/**/*
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
New features should be developed in the
srcdirectory
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/main/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Main process code for Electron should be placed in
src/main
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/**/*.{ts,tsx,vue,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use Prettier with single quotes, no semicolons, and 100 character width
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use OxLint for linting JavaScript and TypeScript files
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.{ts,tsx}: Use camelCase for variable and function names in TypeScript files
Use PascalCase for type and class names in TypeScript
Use SCREAMING_SNAKE_CASE for constant names
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use EventBus for inter-process communication events
Files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
src/main/presenter/llmProviderPresenter/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm-agent-loop.mdc)
Define the standardized
LLMCoreStreamEventinterface with fields:type(text | reasoning | tool_call_start | tool_call_chunk | tool_call_end | error | usage | stop | image_data),content(for text),reasoning_content(for reasoning),tool_call_id,tool_call_name,tool_call_arguments_chunk(for streaming),tool_call_arguments_complete(for complete arguments),error_message,usageobject with token counts,stop_reason(tool_use | max_tokens | stop_sequence | error | complete), andimage_dataobject with Base64-encoded data and mimeType
Files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
🧠 Learnings (19)
📓 Common learnings
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call IDs in Provider implementations must be globally unique and stable, with chunks arriving strictly in order
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call IDs in Provider implementations must be globally unique and stable, with chunks arriving strictly in order
Applied to files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/configPresenter/modelConfig.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, include helper methods for Provider-specific operations such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt`
Applied to files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
Applied to files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, handle native tool support by converting MCP tools to Provider format using `convertToProviderTools` and including them in the API request; for Providers without native function call support, prepare messages using `prepareFunctionCallPrompt` before making the API call
Applied to files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Implement separation of concerns where `src/main/presenter/llmProviderPresenter/index.ts` manages the Agent loop and conversation history, while Provider files handle LLM API interactions, Provider-specific request/response formatting, tool definition conversion, and native vs non-native tool call mechanisms
Applied to files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/llmProviderPresenter/baseProvider.tssrc/main/presenter/configPresenter/modelConfig.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Do not introduce renderer dependencies inside Provider implementations
Applied to files:
src/main/presenter/configPresenter/providerId.tssrc/main/presenter/configPresenter/modelConfig.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/**/*.ts : Define the standardized `LLMCoreStreamEvent` interface with fields: `type` (text | reasoning | tool_call_start | tool_call_chunk | tool_call_end | error | usage | stop | image_data), `content` (for text), `reasoning_content` (for reasoning), `tool_call_id`, `tool_call_name`, `tool_call_arguments_chunk` (for streaming), `tool_call_arguments_complete` (for complete arguments), `error_message`, `usage` object with token counts, `stop_reason` (tool_use | max_tokens | stop_sequence | error | complete), and `image_data` object with Base64-encoded data and mimeType
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:26:35.317Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/error-logging.mdc:0-0
Timestamp: 2025-11-25T05:26:35.317Z
Learning: Applies to **/*.{ts,tsx} : Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, parse Provider-specific data chunks from the streaming response and `yield` standardized `LLMCoreStreamEvent` objects conforming to the standard stream event interface, including text, reasoning, tool calls, usage, errors, stop reasons, and image data
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : In `src/main/presenter/llmProviderPresenter/index.ts`, listen for standardized events yielded by `coreStream` and handle them accordingly: buffer text content (`currentContent`), handle `tool_call_start/chunk/end` events by collecting tool details and calling `presenter.mcpPresenter.callTool`, send frontend events via `eventBus` with tool call status, format tool results for the next LLM call, and set `needContinueConversation = true`
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Each LLM provider must implement the `coreStream` method following the standardized event interface for tool calling and response streaming
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations (`src/main/presenter/llmProviderPresenter/providers/*.ts`), the `coreStream(messages, modelId, temperature, maxTokens)` method should perform a *single-pass* streaming API request for each conversation round without containing multi-turn tool call loop logic
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Use standardized stream events interface to decouple the main Agent loop from Provider-specific details, enabling consistent behavior across all LLM Providers while allowing flexible Provider implementations
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Output only discriminated union `LLMCoreStreamEvent` in Provider implementations, do not use single interface with optional fields
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:28:20.513Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-11-25T05:28:20.513Z
Learning: Use a two-layer LLM provider architecture with Agent Loop and Provider layers
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Provide `rate_limit` events in Provider implementations if rate limiter is configured
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call events: strictly follow sequence `tool_call_start → tool_call_chunk* → tool_call_end`, ensure `tool_call_id` is required and stable
Applied to files:
src/main/presenter/llmProviderPresenter/baseProvider.ts
📚 Learning: 2025-11-25T05:28:04.454Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/vue-shadcn.mdc:0-0
Timestamp: 2025-11-25T05:28:04.454Z
Learning: Applies to src/renderer/**/*.{ts,vue} : Use provide/inject for dependency injection when appropriate
Applied to files:
src/main/presenter/configPresenter/modelConfig.ts
🧬 Code graph analysis (2)
src/main/presenter/configPresenter/providerId.ts (2)
src/main/presenter/configPresenter/modelCapabilities.ts (1)
resolveProviderId(87-90)src/main/presenter/configPresenter/modelConfig.ts (1)
resolveProviderId(45-47)
src/main/presenter/configPresenter/modelConfig.ts (2)
src/main/presenter/configPresenter/modelCapabilities.ts (1)
resolveProviderId(87-90)src/main/presenter/configPresenter/providerId.ts (1)
resolveProviderId(14-17)
⏰ 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)
🔇 Additional comments (2)
src/main/presenter/llmProviderPresenter/baseProvider.ts (2)
17-17: LGTM! Centralized logging implementation follows coding guidelines.The migration from console-based logging to the centralized logger module improves observability and aligns with the structured logging requirements. All log messages and context have been preserved correctly.
Based on coding guidelines: "Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities"
Also applies to: 82-208
446-547: LGTM! Error handling in parseFunctionCalls is robust.The function correctly uses structured logging for errors and implements graceful degradation by returning null or empty arrays on parse failures. The use of jsonrepair for resilient JSON parsing is a good practice.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
src/shared/types/model-db.ts (1)
87-87: Update the comment to reflect uppercase support.The comment states "lowercase and allowed chars" but the
MODEL_ID_REGEXon line 89 now permits uppercase letters. Update the comment to accurately describe the validation rule.🔎 Proposed fix
-// strengthened id check: lowercase and allowed chars +// strengthened id check: alphanumeric and allowed charsscripts/fetch-provider-db.mjs (1)
21-21: Consider eliminating validation logic duplication.The model ID validation logic (regex pattern and
isValidModelIdfunction) is duplicated between this script andsrc/shared/types/model-db.ts. This creates a maintenance burden—changes to validation rules must be synchronized across both files.Consider one of these approaches:
- Option 1: Import the validation utilities from the TypeScript file if the build environment supports it
- Option 2: Generate this validation code from a single source during the build process
- Option 3: Document clearly that these must be kept in sync and add a test to verify consistency
If duplication is intentional due to build-time constraints, add a comment explaining the decision and referencing the source of truth.
Also applies to: 24-25, 42-42
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
resources/model-db/providers.jsonscripts/fetch-provider-db.mjssrc/shared/types/model-db.ts
🧰 Additional context used
📓 Path-based instructions (11)
**/*.{js,ts,jsx,tsx,mjs,cjs}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
Write logs and comments in English
Files:
scripts/fetch-provider-db.mjssrc/shared/types/model-db.ts
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for logs and comments (Chinese text exists in legacy code, but new code should use English)
Files:
src/shared/types/model-db.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and maintain strict TypeScript type checking for all files
**/*.{ts,tsx}: Always use try-catch to handle possible errors in TypeScript code
Provide meaningful error messages when catching errors
Log detailed error logs including error details, context, and stack traces
Distinguish and handle different error types (UserError, NetworkError, SystemError, BusinessError) with appropriate handlers in TypeScript
Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities
Do not suppress errors (avoid empty catch blocks or silently ignoring errors)
Provide user-friendly error messages for user-facing errors in TypeScript components
Implement error retry mechanisms for transient failures in TypeScript
Avoid logging sensitive information (passwords, tokens, PII) in logs
Files:
src/shared/types/model-db.ts
**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Do not include AI co-authoring information (e.g., 'Co-Authored-By: Claude') in git commits
Files:
src/shared/types/model-db.ts
src/**/*
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
New features should be developed in the
srcdirectory
Files:
src/shared/types/model-db.ts
src/shared/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Shared type definitions and utilities between main and renderer processes should be placed in
src/shared
Files:
src/shared/types/model-db.ts
src/shared/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Shared types and utilities should be placed in
src/shared/
Files:
src/shared/types/model-db.ts
src/**/*.{ts,tsx,vue,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use Prettier with single quotes, no semicolons, and 100 character width
Files:
src/shared/types/model-db.ts
src/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use OxLint for linting JavaScript and TypeScript files
Files:
src/shared/types/model-db.ts
src/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.{ts,tsx}: Use camelCase for variable and function names in TypeScript files
Use PascalCase for type and class names in TypeScript
Use SCREAMING_SNAKE_CASE for constant names
Files:
src/shared/types/model-db.ts
src/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use EventBus for inter-process communication events
Files:
src/shared/types/model-db.ts
🧠 Learnings (1)
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Tool call IDs in Provider implementations must be globally unique and stable, with chunks arriving strictly in order
Applied to files:
scripts/fetch-provider-db.mjssrc/shared/types/model-db.ts
🧬 Code graph analysis (1)
scripts/fetch-provider-db.mjs (1)
src/shared/types/model-db.ts (2)
isValidLowercaseProviderId(90-94)isValidModelId(95-97)
⏰ 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)
🔇 Additional comments (1)
src/shared/types/model-db.ts (1)
89-89: No breaking change to verify—this is a new file.
isValidModelIdis a new function in this new file, not a rename ofisValidLowercaseModelId(which does not exist in the codebase). The validation logic correctly relaxes the model ID constraints to support uppercase characters and additional characters like:, matching the requirement to support providers like minimax. The function is used only internally withinmodel-db.tsand no external consumers import it.Likely an incorrect or invalid review comment.
zerob13
changed the title
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (3)
src/renderer/src/stores/providerStore.ts (1)
348-354: Redundant refetch of default providers ininitialize.
refreshProviders()at line 352 already callsdefaultProvidersQuery.refetch()(line 144), making the explicit call at line 353 redundant. This results in two consecutive fetches of default providers during initialization.🔎 Proposed fix
const initialize = async () => { await loadProviderTimestamps() await loadProviderOrder() setupProviderListeners() await refreshProviders() - await defaultProvidersQuery.refetch() }src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts (1)
85-114: Dynamic model loading implementation looks good.The refactored
fetchOpenAIModelscorrectly:
- Resolves provider ID through the centralized resolver
- Derives model capabilities from provider data (vision, functionCall, reasoning, etc.)
- Uses sensible defaults for
contextLength(8192) andmaxTokens(4096)- Correctly determines model type based on output modalities
Note: Returning an empty array when provider data is unavailable (lines 88-90) is a silent failure. Consider whether logging a warning would help with debugging when models unexpectedly don't appear.
🔎 Optional: Add debug logging for missing provider data
const resolvedId = modelCapabilities.resolveProviderId(this.provider.id) || this.provider.id const provider = providerDbLoader.getProvider(resolvedId) if (!provider || !Array.isArray(provider.models)) { + this.logger.debug(`No provider data found for ${resolvedId}, returning empty model list`) return [] }src/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts (1)
12-35: Consider extracting shared model mapping logic.The model metadata mapping logic (lines 12-35) is nearly identical to
DoubaoProvider.fetchOpenAIModels(). Consider extracting this to a shared utility function inproviderDbLoaderor a protected method inBaseLLMProviderto reduce duplication and ensure consistent model capability derivation across providers.🔎 Example shared utility
// In providerDbLoader.ts or a shared utility export function mapProviderModelToMeta( model: ProviderModel, providerId: string ): MODEL_META { const inputs = model.modalities?.input const outputs = model.modalities?.output const hasImageInput = Array.isArray(inputs) && inputs.includes('image') const hasImageOutput = Array.isArray(outputs) && outputs.includes('image') return { id: model.id, name: model.display_name || model.name || model.id, group: 'default', providerId, isCustom: false, contextLength: model.limit?.context ?? 8192, maxTokens: model.limit?.output ?? 4096, vision: hasImageInput, functionCall: Boolean(model.tool_call), reasoning: Boolean(model.reasoning?.supported), enableSearch: Boolean(model.search?.supported), type: hasImageOutput ? ModelType.ImageGeneration : ModelType.Chat } }
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
src/main/presenter/configPresenter/index.tssrc/main/presenter/configPresenter/providers.tssrc/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/renderer/settings/components/ModelProviderSettings.vuesrc/renderer/src/stores/providerStore.ts
🧰 Additional context used
📓 Path-based instructions (30)
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for logs and comments (Chinese text exists in legacy code, but new code should use English)
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
**/*.vue
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.vue: Use Vue 3 Composition API for all components instead of Options API
Use Tailwind CSS with scoped styles for component styling
Files:
src/renderer/settings/components/ModelProviderSettings.vue
src/renderer/**/*.vue
📄 CodeRabbit inference engine (CLAUDE.md)
src/renderer/**/*.vue: All user-facing strings must use i18n keys via vue-i18n for internationalization
Ensure proper error handling and loading states in all UI components
Implement responsive design using Tailwind CSS utilities for all UI components
src/renderer/**/*.vue: Use composition API and declarative programming patterns; avoid options API
Structure files: exported component, composables, helpers, static content, types
Use PascalCase for component names (e.g., AuthWizard.vue)
Use Vue 3 with TypeScript, leveraging defineComponent and PropType
Use template syntax for declarative rendering
Use Shadcn Vue, Radix Vue, and Tailwind for components and styling
Implement responsive design with Tailwind CSS; use a mobile-first approach
Use Suspense for asynchronous components
Use <script setup> syntax for concise component definitions
Prefer 'lucide:' icon family as the primary choice for Iconify icons
Import Icon component from '@iconify/vue' and use with lucide icons following pattern '{collection}:{icon-name}'
Files:
src/renderer/settings/components/ModelProviderSettings.vue
src/**/*
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
New features should be developed in the
srcdirectory
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
src/renderer/**/*.{vue,js,ts}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Renderer process code should be placed in
src/renderer(Vue 3 application)
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/renderer/src/stores/providerStore.ts
src/renderer/**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
src/renderer/**/*.{ts,tsx,vue}: Write concise, technical TypeScript code with accurate examples
Use descriptive variable names with auxiliary verbs (e.g., isLoading, hasError)
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 statementsVue 3 app code in
src/renderer/srcshould be organized intocomponents/,stores/,views/,i18n/,lib/directories with shell UI insrc/renderer/shell/
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/renderer/src/stores/providerStore.ts
src/renderer/**
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
Use lowercase with dashes for directories (e.g., components/auth-wizard)
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/renderer/src/stores/providerStore.ts
src/renderer/**/*.{ts,vue}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
src/renderer/**/*.{ts,vue}: Use useFetch and useAsyncData for data fetching
Leverage ref, reactive, and computed for reactive state management
Use provide/inject for dependency injection when appropriate
Use Iconify/Vue for icon implementation
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/renderer/src/stores/providerStore.ts
src/**/*.{ts,tsx,vue,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use Prettier with single quotes, no semicolons, and 100 character width
Files:
src/renderer/settings/components/ModelProviderSettings.vuesrc/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and maintain strict TypeScript type checking for all files
**/*.{ts,tsx}: Always use try-catch to handle possible errors in TypeScript code
Provide meaningful error messages when catching errors
Log detailed error logs including error details, context, and stack traces
Distinguish and handle different error types (UserError, NetworkError, SystemError, BusinessError) with appropriate handlers in TypeScript
Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities
Do not suppress errors (avoid empty catch blocks or silently ignoring errors)
Provide user-friendly error messages for user-facing errors in TypeScript components
Implement error retry mechanisms for transient failures in TypeScript
Avoid logging sensitive information (passwords, tokens, PII) in logs
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
src/main/presenter/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Organize core business logic into dedicated Presenter classes, with one presenter per functional domain
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
src/main/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Use EventBus from
src/main/eventbus.tsfor main-to-renderer communication, broadcasting events viamainWindow.webContents.send()
src/main/**/*.ts: Use EventBus pattern for inter-process communication within the main process to decouple modules
Use Electron's built-in APIs for file system and native dialogs instead of Node.js or custom implementations
src/main/**/*.ts: Electron main process code belongs insrc/main/with presenters inpresenter/(Window/Tab/Thread/Mcp/Config/LLMProvider) andeventbus.tsfor app events
Use the Presenter pattern in the main process for UI coordination
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Do not include AI co-authoring information (e.g., 'Co-Authored-By: Claude') in git commits
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
**/*.{js,ts,jsx,tsx,mjs,cjs}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
Write logs and comments in English
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
{src/main/presenter/**/*.ts,src/renderer/**/*.ts}
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Implement proper inter-process communication (IPC) patterns using Electron's ipcRenderer and ipcMain APIs
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
src/main/presenter/llmProviderPresenter/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm-agent-loop.mdc)
Define the standardized
LLMCoreStreamEventinterface with fields:type(text | reasoning | tool_call_start | tool_call_chunk | tool_call_end | error | usage | stop | image_data),content(for text),reasoning_content(for reasoning),tool_call_id,tool_call_name,tool_call_arguments_chunk(for streaming),tool_call_arguments_complete(for complete arguments),error_message,usageobject with token counts,stop_reason(tool_use | max_tokens | stop_sequence | error | complete), andimage_dataobject with Base64-encoded data and mimeType
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts
src/main/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Main process code for Electron should be placed in
src/main
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
src/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use OxLint for linting JavaScript and TypeScript files
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
src/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.{ts,tsx}: Use camelCase for variable and function names in TypeScript files
Use PascalCase for type and class names in TypeScript
Use SCREAMING_SNAKE_CASE for constant names
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
src/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use EventBus for inter-process communication events
Files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.tssrc/renderer/src/stores/providerStore.ts
src/main/presenter/configPresenter/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Store and retrieve custom prompts via
configPresenter.getCustomPrompts()for config-based data source management
Files:
src/main/presenter/configPresenter/index.tssrc/main/presenter/configPresenter/providers.ts
src/main/presenter/llmProviderPresenter/providers/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
src/main/presenter/llmProviderPresenter/providers/*.ts: Each LLM provider must implement thecoreStreammethod following the standardized event interface for tool calling and response streaming
Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
src/main/presenter/llmProviderPresenter/providers/*.ts: In Provider implementations (src/main/presenter/llmProviderPresenter/providers/*.ts), thecoreStream(messages, modelId, temperature, maxTokens)method should perform a single-pass streaming API request for each conversation round without containing multi-turn tool call loop logic
In Provider implementations, handle native tool support by converting MCP tools to Provider format usingconvertToProviderToolsand including them in the API request; for Providers without native function call support, prepare messages usingprepareFunctionCallPromptbefore making the API call
In Provider implementations, parse Provider-specific data chunks from the streaming response andyieldstandardizedLLMCoreStreamEventobjects conforming to the standard stream event interface, including text, reasoning, tool calls, usage, errors, stop reasons, and image data
In Provider implementations, include helper methods for Provider-specific operations such asformatMessages,convertToProviderTools,parseFunctionCalls, andprepareFunctionCallPrompt
Files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts
src/renderer/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Use the
usePresenter.tscomposable for renderer-to-main IPC communication to call presenter methods directly
Files:
src/renderer/src/stores/providerStore.ts
src/renderer/src/**/*.{vue,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/i18n.mdc)
src/renderer/src/**/*.{vue,ts,tsx}: All user-facing strings must use i18n keys with vue-i18n framework in the renderer
Import and use useI18n() composable with the t() function to access translations in Vue components and TypeScript files
Use the dynamic locale.value property to switch languages at runtime
Avoid hardcoding user-facing text and ensure all user-visible text uses the i18n translation system
Files:
src/renderer/src/stores/providerStore.ts
src/renderer/src/stores/**/*.{vue,ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.cursor/rules/pinia-best-practices.mdc)
src/renderer/src/stores/**/*.{vue,ts,tsx,js,jsx}: Use modules to organize related state and actions in Pinia stores
Implement proper state persistence for maintaining data across sessions in Pinia stores
Use getters for computed state properties in Pinia stores
Utilize actions for side effects and asynchronous operations in Pinia stores
Keep Pinia stores focused on global state, not component-specific data
Files:
src/renderer/src/stores/providerStore.ts
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 in Vue.js applications
Implement proper state management with Pinia in Vue.js applications
Utilize Vue Router for navigation and route management in Vue.js applications
Leverage Vue's built-in reactivity system for efficient data handling
Files:
src/renderer/src/stores/providerStore.ts
src/renderer/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
Use TypeScript for all code; prefer types over interfaces
Files:
src/renderer/src/stores/providerStore.ts
src/renderer/**/stores/*.ts
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
Use Pinia for state management
Files:
src/renderer/src/stores/providerStore.ts
src/renderer/src/**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (AGENTS.md)
src/renderer/src/**/*.{ts,tsx,vue}: Use TypeScript with Vue 3 Composition API for the renderer application
All user-facing strings must use vue-i18n keys insrc/renderer/src/i18n
Files:
src/renderer/src/stores/providerStore.ts
src/renderer/src/stores/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use Pinia for state management
Files:
src/renderer/src/stores/providerStore.ts
🧠 Learnings (12)
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Convert MCP tools to provider-specific formats and normalize streaming responses to standard events in each provider implementation
Applied to files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Implement separation of concerns where `src/main/presenter/llmProviderPresenter/index.ts` manages the Agent loop and conversation history, while Provider files handle LLM API interactions, Provider-specific request/response formatting, tool definition conversion, and native vs non-native tool call mechanisms
Applied to files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, include helper methods for Provider-specific operations such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt`
Applied to files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, handle native tool support by converting MCP tools to Provider format using `convertToProviderTools` and including them in the API request; for Providers without native function call support, prepare messages using `prepareFunctionCallPrompt` before making the API call
Applied to files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.tssrc/main/presenter/configPresenter/index.tssrc/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.tssrc/main/presenter/configPresenter/providers.ts
📚 Learning: 2025-11-25T05:27:39.200Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-11-25T05:27:39.200Z
Learning: Applies to **/*Provider**/index.ts : Every event construction in Provider implementations must use factory functions
Applied to files:
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations, parse Provider-specific data chunks from the streaming response and `yield` standardized `LLMCoreStreamEvent` objects conforming to the standard stream event interface, including text, reasoning, tool calls, usage, errors, stop reasons, and image data
Applied to files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : In Provider implementations (`src/main/presenter/llmProviderPresenter/providers/*.ts`), the `coreStream(messages, modelId, temperature, maxTokens)` method should perform a *single-pass* streaming API request for each conversation round without containing multi-turn tool call loop logic
Applied to files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Each LLM provider must implement the `coreStream` method following the standardized event interface for tool calling and response streaming
Applied to files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.tssrc/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : In `src/main/presenter/llmProviderPresenter/index.ts`, listen for standardized events yielded by `coreStream` and handle them accordingly: buffer text content (`currentContent`), handle `tool_call_start/chunk/end` events by collecting tool details and calling `presenter.mcpPresenter.callTool`, send frontend events via `eventBus` with tool call status, format tool results for the next LLM call, and set `needContinueConversation = true`
Applied to files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/**/*.ts : Define the standardized `LLMCoreStreamEvent` interface with fields: `type` (text | reasoning | tool_call_start | tool_call_chunk | tool_call_end | error | usage | stop | image_data), `content` (for text), `reasoning_content` (for reasoning), `tool_call_id`, `tool_call_name`, `tool_call_arguments_chunk` (for streaming), `tool_call_arguments_complete` (for complete arguments), `error_message`, `usage` object with token counts, `stop_reason` (tool_use | max_tokens | stop_sequence | error | complete), and `image_data` object with Base64-encoded data and mimeType
Applied to files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : In `src/main/presenter/llmProviderPresenter/index.ts`, handle `reasoning`, `text`, `image_data`, and `usage` events by processing and forwarding them through `STREAM_EVENTS.RESPONSE` events to the frontend
Applied to files:
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts
📚 Learning: 2025-11-25T05:27:12.209Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-11-25T05:27:12.209Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : In `src/main/presenter/llmProviderPresenter/index.ts` (`startStreamCompletion`), implement the Agent loop that manages the overall conversation flow, including multiple rounds of LLM calls and tool usage, maintaining `conversationMessages` history, calling `provider.coreStream()` on each iteration, and controlling the loop using `needContinueConversation` and `toolCallCount` (compared against `MAX_TOOL_CALLS`)
Applied to files:
src/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts
🧬 Code graph analysis (4)
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.ts (1)
src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts (1)
AnthropicProvider(81-1392)
src/main/presenter/configPresenter/index.ts (2)
src/shared/types/presenters/legacy.presenters.d.ts (1)
LLM_PROVIDER(714-735)src/shared/types/presenters/llmprovider.presenter.d.ts (1)
LLM_PROVIDER(45-61)
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts (3)
src/main/presenter/configPresenter/modelCapabilities.ts (1)
modelCapabilities(173-173)src/main/presenter/configPresenter/providerDbLoader.ts (1)
providerDbLoader(237-237)scripts/fetch-provider-db.mjs (1)
modelType(105-105)
src/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts (4)
src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts (1)
AnthropicProvider(81-1392)src/main/presenter/configPresenter/modelCapabilities.ts (1)
modelCapabilities(173-173)src/main/presenter/configPresenter/providerDbLoader.ts (1)
providerDbLoader(237-237)scripts/fetch-provider-db.mjs (1)
modelType(105-105)
⏰ 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)
🔇 Additional comments (6)
src/main/presenter/llmProviderPresenter/managers/providerInstanceManager.ts (1)
102-104: LGTM - Provider type mapping updated for minimax migration.The change from
OpenAIProvidertoAnthropicProviderinPROVIDER_TYPE_MAPis consistent with the broader minimax migration. SincePROVIDER_ID_MAPtakes precedence increateProviderInstance(line 406), the dedicatedMinimaxProvider(which now extendsAnthropicProvider) will be used for providers with id'minimax'.src/main/presenter/configPresenter/index.ts (2)
230-232: Migration hook placement looks correct.The
migrateMinimaxProvider()call is appropriately placed after version-based migrations and before new provider initialization. This ensures legacy minimax configurations are migrated to the Anthropic format before any new provider logic runs.
431-461: Well-structured migration for minimax provider.The migration correctly:
- Identifies legacy minimax configurations (apiType
'openai'or'minimax')- Preserves the user's
apiKeyduring migration- Cleans up the
'minimax-an'provider if present (likely from earlier migration attempts)The early returns for missing providers are appropriate defensive guards.
src/main/presenter/configPresenter/providers.ts (1)
416-430: Verify domain consistency betweenbaseUrlanddefaultBaseUrl.The minimax provider configuration uses different domains:
baseUrl:https://api.minimaxi.com/anthropicdefaultBaseUrl:https://api.minimax.io/anthropicPlease confirm this is intentional. If these should be the same, consider aligning them to avoid confusion.
src/renderer/settings/components/ModelProviderSettings.vue (1)
172-179: Correct routing adjustment for Anthropic settings panel.Narrowing the condition to
activeProvider.id === 'anthropic'is correct. TheAnthropicProviderSettingsDetailcomponent handles OAuth authentication and other Anthropic-specific settings that only apply to the canonical Anthropic provider. Minimax (which now hasapiType: 'anthropic') should use the standardModelProviderSettingsDetailsince it uses API key authentication, not OAuth.src/main/presenter/llmProviderPresenter/providers/minimaxProvider.ts (1)
7-38: LGTM - Clean migration to Anthropic-based provider.The refactored
MinimaxProvidercorrectly:
- Extends
AnthropicProviderinstead ofOpenAICompatibleProvider- Implements dynamic model loading from the provider DB
- Falls back to
super.fetchProviderModels()when DB data is unavailable
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (13)
src/renderer/settings/components/ProviderApiConfig.vuesrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/ja-JP/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/zh-TW/index.ts
💤 Files with no reviewable changes (1)
- src/renderer/settings/components/ProviderApiConfig.vue
🧰 Additional context used
📓 Path-based instructions (19)
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for logs and comments (Chinese text exists in legacy code, but new code should use English)
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and maintain strict TypeScript type checking for all files
**/*.{ts,tsx}: Always use try-catch to handle possible errors in TypeScript code
Provide meaningful error messages when catching errors
Log detailed error logs including error details, context, and stack traces
Distinguish and handle different error types (UserError, NetworkError, SystemError, BusinessError) with appropriate handlers in TypeScript
Use structured logging with logger.error(), logger.warn(), logger.info(), logger.debug() methods from logging utilities
Do not suppress errors (avoid empty catch blocks or silently ignoring errors)
Provide user-friendly error messages for user-facing errors in TypeScript components
Implement error retry mechanisms for transient failures in TypeScript
Avoid logging sensitive information (passwords, tokens, PII) in logs
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Use the
usePresenter.tscomposable for renderer-to-main IPC communication to call presenter methods directly
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
**/*.ts
📄 CodeRabbit inference engine (CLAUDE.md)
Do not include AI co-authoring information (e.g., 'Co-Authored-By: Claude') in git commits
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
**/*.{js,ts,jsx,tsx,mjs,cjs}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
Write logs and comments in English
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
{src/main/presenter/**/*.ts,src/renderer/**/*.ts}
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Implement proper inter-process communication (IPC) patterns using Electron's ipcRenderer and ipcMain APIs
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/src/**/*.{vue,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/i18n.mdc)
src/renderer/src/**/*.{vue,ts,tsx}: All user-facing strings must use i18n keys with vue-i18n framework in the renderer
Import and use useI18n() composable with the t() function to access translations in Vue components and TypeScript files
Use the dynamic locale.value property to switch languages at runtime
Avoid hardcoding user-facing text and ensure all user-visible text uses the i18n translation system
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/**/*
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
New features should be developed in the
srcdirectory
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/**/*.{vue,js,ts}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
Renderer process code should be placed in
src/renderer(Vue 3 application)
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
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 in Vue.js applications
Implement proper state management with Pinia in Vue.js applications
Utilize Vue Router for navigation and route management in Vue.js applications
Leverage Vue's built-in reactivity system for efficient data handling
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
src/renderer/**/*.{ts,tsx,vue}: Write concise, technical TypeScript code with accurate examples
Use descriptive variable names with auxiliary verbs (e.g., isLoading, hasError)
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 statementsVue 3 app code in
src/renderer/srcshould be organized intocomponents/,stores/,views/,i18n/,lib/directories with shell UI insrc/renderer/shell/
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/**
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
Use lowercase with dashes for directories (e.g., components/auth-wizard)
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
Use TypeScript for all code; prefer types over interfaces
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/**/*.{ts,vue}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
src/renderer/**/*.{ts,vue}: Use useFetch and useAsyncData for data fetching
Leverage ref, reactive, and computed for reactive state management
Use provide/inject for dependency injection when appropriate
Use Iconify/Vue for icon implementation
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/renderer/src/**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (AGENTS.md)
src/renderer/src/**/*.{ts,tsx,vue}: Use TypeScript with Vue 3 Composition API for the renderer application
All user-facing strings must use vue-i18n keys insrc/renderer/src/i18n
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/**/*.{ts,tsx,vue,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use Prettier with single quotes, no semicolons, and 100 character width
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use OxLint for linting JavaScript and TypeScript files
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/**/*.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.{ts,tsx}: Use camelCase for variable and function names in TypeScript files
Use PascalCase for type and class names in TypeScript
Use SCREAMING_SNAKE_CASE for constant names
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
src/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Use EventBus for inter-process communication events
Files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
🧠 Learnings (8)
📚 Learning: 2025-11-25T05:26:43.510Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/i18n.mdc:0-0
Timestamp: 2025-11-25T05:26:43.510Z
Learning: Applies to src/renderer/src/i18n/**/*.json : Maintain consistent key-value structure across all language translation files (zh-CN, en-US, ko-KR, ru-RU, zh-HK, fr-FR, fa-IR)
Applied to files:
src/renderer/src/i18n/fa-IR/index.tssrc/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
📚 Learning: 2025-11-25T05:26:43.510Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/i18n.mdc:0-0
Timestamp: 2025-11-25T05:26:43.510Z
Learning: Applies to src/renderer/src/**/*.{vue,ts,tsx} : Avoid hardcoding user-facing text and ensure all user-visible text uses the i18n translation system
Applied to files:
src/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
📚 Learning: 2025-11-25T05:26:43.510Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/i18n.mdc:0-0
Timestamp: 2025-11-25T05:26:43.510Z
Learning: Applies to src/renderer/src/**/*.{vue,ts,tsx} : All user-facing strings must use i18n keys with vue-i18n framework in the renderer
Applied to files:
src/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
📚 Learning: 2025-11-25T05:26:43.510Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/i18n.mdc:0-0
Timestamp: 2025-11-25T05:26:43.510Z
Learning: Applies to src/renderer/src/**/*.{vue,ts,tsx} : Use the dynamic locale.value property to switch languages at runtime
Applied to files:
src/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.ts
📚 Learning: 2025-11-25T05:28:20.513Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-11-25T05:28:20.513Z
Learning: Applies to src/renderer/src/**/*.{ts,tsx,vue} : All user-facing strings must use vue-i18n keys in `src/renderer/src/i18n`
Applied to files:
src/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/ko-KR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/en-US/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to **/*.{ts,tsx,js,jsx,vue} : Use English for logs and comments (Chinese text exists in legacy code, but new code should use English)
Applied to files:
src/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/zh-CN/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/da-DK/index.tssrc/renderer/src/i18n/zh-HK/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
📚 Learning: 2025-11-25T05:26:43.510Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/i18n.mdc:0-0
Timestamp: 2025-11-25T05:26:43.510Z
Learning: Applies to src/renderer/src/i18n/**/*.json : Translation key naming convention: use dot-separated hierarchical structure with lowercase letters and descriptive names (e.g., 'common.button.submit')
Applied to files:
src/renderer/src/i18n/ru-RU/index.tssrc/renderer/src/i18n/pt-BR/index.tssrc/renderer/src/i18n/he-IL/index.tssrc/renderer/src/i18n/fr-FR/index.tssrc/renderer/src/i18n/zh-TW/index.tssrc/renderer/src/i18n/ja-JP/index.ts
📚 Learning: 2025-11-25T05:26:11.312Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-11-25T05:26:11.312Z
Learning: Applies to src/renderer/**/*.vue : All user-facing strings must use i18n keys via vue-i18n for internationalization
Applied to files:
src/renderer/src/i18n/fr-FR/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)
🔇 Additional comments (12)
src/renderer/src/i18n/ko-KR/index.ts (1)
26-26: LGTM! Consistent i18n label update.The Doubao label update to 'Volcano Engine' is consistent with the broader cross-locale rebranding effort mentioned in the PR summary. The change maintains the proper key-value structure for i18n translations.
src/renderer/src/i18n/zh-TW/index.ts (1)
25-25: LGTM! Proper Traditional Chinese translation.The update from '豆包' to '火山引擎' (Volcano Engine) is accurate and maintains consistency with other Chinese locales in this PR.
src/renderer/src/i18n/he-IL/index.ts (1)
27-27: LGTM! Consistent localization update.The Doubao to 'Volcano Engine' mapping aligns with the standardized label updates across all locales in this PR.
src/renderer/src/i18n/zh-HK/index.ts (1)
25-25: LGTM! Accurate Hong Kong Chinese translation.The '火山引擎' (Volcano Engine) translation is consistent with other Chinese locales (zh-CN, zh-TW) in this PR.
src/renderer/src/i18n/en-US/index.ts (1)
27-27: LGTM! Clean localization update.The English locale update from 'Doubao' to 'Volcano Engine' is straightforward and maintains proper i18n structure.
src/renderer/src/i18n/ru-RU/index.ts (1)
25-25: LGTM! Consistent with cross-locale updates.The Doubao to 'Volcano Engine' update follows the same pattern as other non-CJK locales in this PR.
src/renderer/src/i18n/ja-JP/index.ts (1)
26-26: LGTM! Appropriate Japanese localization.The update to '火山引擎' (Volcano Engine using kanji) is consistent with other CJK locales and follows Japanese localization conventions for technical terms.
src/renderer/src/i18n/pt-BR/index.ts (1)
26-26: LGTM! Final locale update completes the set.The Portuguese (Brazil) locale update to 'Volcano Engine' completes the consistent cross-locale rebranding effort. All translations maintain proper i18n structure and follow localization best practices.
src/renderer/src/i18n/fa-IR/index.ts (1)
25-25: LGTM! Localization update for Doubao rebranding.The update from 'Doubao' to 'Volcano Engine' aligns with the provider rebranding reflected across multiple locales in this PR.
src/renderer/src/i18n/fr-FR/index.ts (1)
26-26: LGTM! Localization update for Doubao rebranding.The update to 'Volcano Engine' is consistent with the provider rebranding applied across all locales in this PR.
src/renderer/src/i18n/da-DK/index.ts (1)
27-27: LGTM! Localization update for Doubao rebranding.The update to 'Volcano Engine' is consistent with the provider rebranding applied across all locales.
src/renderer/src/i18n/zh-CN/index.ts (1)
27-27: LGTM! Localization update for Doubao rebranding.The Chinese translation '火山引擎' (Volcano Engine) correctly reflects the provider rebranding applied across all locales in this PR.
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.