feat: add live search support for Grok provider #886
Conversation
WalkthroughAdds explicit enableSearch flags to several Grok model configs, introduces enableSearch handling in Grok provider by conditionally injecting search_parameters into requests, updates effective model config post-injection, and adds a Grok-specific search toggle in the ModelConfigDialog. Also hardens thinkingBudgetRange with a default when missing. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor U as User
participant V as ModelConfigDialog (Renderer)
participant P as Presenter
participant G as grokProvider
participant A as Grok API
U->>V: Toggle "Enable Search" (Grok model)
V->>P: Save model config (enableSearch flag)
U->>P: Send message (Grok model)
P->>G: createCompletion/coreStream(modelId, config)
rect rgba(200,220,255,0.25)
note right of G: Determine flags
G->>G: supportsEnableSearch(modelId)?<br/>supportsReasoningEffort?
alt needs parameter modification
note over G,A: Temporarily wrap API call
G->>A: chat.completions.create(..., search_parameters:on?, reasoning_effort?)
A-->>G: Stream/response
G->>G: Restore original method
else no modification
G->>A: chat.completions.create(original params)
A-->>G: Stream/response
end
G->>G: Update effectiveModelConfig<br/>(enableSearch:false, reasoningEffort:undefined)
end
G-->>P: Result
P-->>V: Display assistant output
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
Pre-merge checks (2 passed, 1 warning)❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
Poem
✨ Finishing Touches
🧪 Generate unit tests
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
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/main/presenter/configPresenter/providerModelSettings.ts (1)
3134-3145: Add explicitgrok-4entry to providerModelSettings.ts
Noid: 'grok-4'mapping exists in src/main/presenter/configPresenter/providerModelSettings.ts, so calls to “grok-4” will fall back to generic defaults—define itscontextLength,maxTokens,matchpatterns, and flags to ensure correct limits.
🧹 Nitpick comments (3)
src/renderer/src/components/settings/ModelConfigDialog.vue (1)
833-853: Simplify Grok model detection to avoid drift with provider constants.You already return true when
modelId.includes('grok'), making the curated list redundant. Either:
- keep only the
'grok'substring check, or- source a single shared list (e.g., from a shared module) to avoid divergence with
GrokProvider.ENABLE_SEARCH_MODELS.Apply this minimal simplification:
-const supportedSearchModels = [ - 'grok-4', - 'grok-3-mini', - 'grok-3-mini-fast', - 'grok-3-fast', - 'grok-3', - 'grok-2', - 'grok-2-vision', - 'grok-2-image' -] -const isSupported = - supportedSearchModels.some((supportedModel) => modelId.includes(supportedModel)) || - modelId.includes('grok') -return isGrok && isSupported +return isGrok && modelId.includes('grok')src/main/presenter/llmProviderPresenter/providers/grokProvider.ts (2)
16-25: ENABLE_SEARCH_MODELS list is redundant given the fallback.Since
supportsEnableSearch()also returns true for anymodelIdcontaining'grok', this list adds maintenance overhead without functional benefit. Consider removing the array and keeping the substring check only.- private static readonly ENABLE_SEARCH_MODELS: string[] = [ - 'grok-4', - 'grok-3-mini', - 'grok-3-mini-fast', - 'grok-2', - 'grok-2-image' - ]
49-62: Confirm single source of truth for “which Grok models support search”.The UI (ModelConfigDialog) and provider both embed their own “supported” logic. To avoid future drift, consider centralizing this in a shared helper.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
src/main/presenter/configPresenter/providerModelSettings.ts(7 hunks)src/main/presenter/llmProviderPresenter/providers/grokProvider.ts(3 hunks)src/renderer/src/components/settings/ModelConfigDialog.vue(2 hunks)
🧰 Additional context used
📓 Path-based instructions (17)
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/development-setup.mdc)
**/*.{js,jsx,ts,tsx}: 使用 OxLint 进行代码检查
Log和注释使用英文书写
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
src/{main,renderer}/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
src/{main,renderer}/**/*.ts: Use context isolation for improved security
Implement proper inter-process communication (IPC) patterns
Optimize application startup time with lazy loading
Implement proper error handling and logging for debugging
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
src/main/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Use Electron's built-in APIs for file system and native dialogs
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/error-logging.mdc)
**/*.{ts,tsx}: 始终使用 try-catch 处理可能的错误
提供有意义的错误信息
记录详细的错误日志
优雅降级处理
日志应包含时间戳、日志级别、错误代码、错误描述、堆栈跟踪（如适用）、相关上下文信息
日志级别应包括 ERROR、WARN、INFO、DEBUG
不要吞掉错误
提供用户友好的错误信息
实现错误重试机制
避免记录敏感信息
使用结构化日志
设置适当的日志级别
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
src/main/**/*.{ts,js,tsx,jsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
主进程代码放在
src/main
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
**/*.{ts,tsx,js,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for all logs and comments
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/renderer/src/components/settings/ModelConfigDialog.vuesrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and adhere to strict TypeScript typing (avoid implicit any, prefer precise types)
Files:
src/main/presenter/configPresenter/providerModelSettings.tssrc/renderer/src/components/settings/ModelConfigDialog.vuesrc/main/presenter/llmProviderPresenter/providers/grokProvider.ts
src/renderer/src/**/*
📄 CodeRabbit inference engine (.cursor/rules/i18n.mdc)
src/renderer/src/**/*: All user-facing strings must use i18n keys (avoid hardcoded user-visible text in code)
Use the 'vue-i18n' framework for all internationalization in the renderer
Ensure all user-visible text in the renderer uses the translation system
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/**/*.{vue,ts,js,tsx,jsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
渲染进程代码放在
src/renderer
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/**/*.{vue,ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.cursor/rules/vue-best-practices.mdc)
src/renderer/src/**/*.{vue,ts,tsx,js,jsx}: Use the Composition API for better code organization and reusability
Implement proper state management with Pinia
Utilize Vue Router for navigation and route management
Leverage Vue's built-in reactivity system for efficient data handling
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/**/*.vue
📄 CodeRabbit inference engine (.cursor/rules/vue-best-practices.mdc)
Use scoped styles to prevent CSS conflicts between components
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
src/renderer/**/*.{ts,tsx,vue}: Use descriptive variable names with auxiliary verbs (e.g., isLoading, hasError).
Use TypeScript for all code; prefer types over interfaces.
Avoid enums; use const objects instead.
Use arrow functions for methods and computed properties.
Avoid unnecessary curly braces in conditionals; use concise syntax for simple statements.
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/**/*.{vue,ts}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
Implement lazy loading for routes and components.
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/**/*.{ts,vue}
📄 CodeRabbit inference engine (.cursor/rules/vue-shadcn.mdc)
src/renderer/**/*.{ts,vue}: Use useFetch and useAsyncData for data fetching.
Implement SEO best practices using Nuxt's useHead and useSeoMeta.Use Pinia for frontend state management (do not introduce alternative state libraries)
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/{src,shell,floating}/**/*.vue
📄 CodeRabbit inference engine (CLAUDE.md)
src/renderer/{src,shell,floating}/**/*.vue: Use Vue 3 Composition API for all components
All user-facing strings must use i18n keys via vue-i18n (no hard-coded UI strings)
Use Tailwind CSS utilities and ensure styles are scoped in Vue components
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/renderer/src/components/**/*
📄 CodeRabbit inference engine (CLAUDE.md)
Organize UI components by feature within src/renderer/src/
Files:
src/renderer/src/components/settings/ModelConfigDialog.vue
src/main/presenter/llmProviderPresenter/providers/*.ts
📄 CodeRabbit inference engine (.cursor/rules/llm-agent-loop.mdc)
src/main/presenter/llmProviderPresenter/providers/*.ts: Each file insrc/main/presenter/llmProviderPresenter/providers/*.tsshould handle interaction with a specific LLM API, including request/response formatting, tool definition conversion, native/non-native tool call management, and standardizing output streams to a common event format.
Provider implementations must use acoreStreammethod that yields standardized stream events to decouple the main loop from provider-specific details.
ThecoreStreammethod in each Provider must perform a single streaming API request per conversation round and must not contain multi-round tool call loop logic.
Provider files should implement helper methods such asformatMessages,convertToProviderTools,parseFunctionCalls, andprepareFunctionCallPromptas needed for provider-specific logic.
All provider implementations must parse provider-specific data chunks and yield standardized events for text, reasoning, tool calls, usage, errors, stop reasons, and image data.
When a provider does not support native function calling, it must prepare messages using prompt wrapping (e.g.,prepareFunctionCallPrompt) before making the API call.
When a provider supports native function calling, MCP tools must be converted to the provider's format (e.g., usingconvertToProviderTools) and included in the API request.
Provider implementations should aggregate and yield usage events as part of the standardized stream.
Provider implementations should yield image data events in the standardized format when applicable.
Provider implementations should yield reasoning events in the standardized format when applicable.
Provider implementations should yield tool call events (tool_call_start,tool_call_chunk,tool_call_end) in the standardized format.
Provider implementations should yield stop events with appropriatestop_reasonin the standardized format.
Provider implementations should yield error events in the standardized format...
Files:
src/main/presenter/llmProviderPresenter/providers/grokProvider.ts
🧠 Learnings (1)
📚 Learning: 2025-09-06T03:07:23.794Z
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-06T03:07:23.794Z
Learning: Applies to src/main/presenter/configPresenter/providers.ts : Add provider configuration entries in src/main/presenter/configPresenter/providers.ts
Applied to files:
src/main/presenter/configPresenter/providerModelSettings.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 (5)
src/main/presenter/configPresenter/providerModelSettings.ts (1)
3143-3145: Explicit enableSearch flags for Grok models — good alignment with UI/provider logic.The explicit
enableSearch: falsedefaults and lowreasoningEfforton the Grok 3 mini variants look consistent with the provider handling.Also applies to: 3156-3158, 3168-3170, 3180-3182, 3192-3194, 3204-3206, 3216-3218
src/renderer/src/components/settings/ModelConfigDialog.vue (1)
373-384: Grok internet search toggle UI — consistent with i18n and config binding.Binding to
config.enableSearchreuses existing translation keys and mirrors DashScope UX. Looks good.src/main/presenter/llmProviderPresenter/providers/grokProvider.ts (3)
238-242: Resetting flags in effectiveModelConfig — good to prevent double-injection.Clearing
reasoningEffortandenableSearchbefore delegating avoids repeated mutation downstream. Looks good.
227-233: Confirmedsearch_parameters: { mode: 'on' }aligns with xAI Grok’s OpenAI-compatible API; no changes needed.
217-236: Runtime monkey-patching of the OpenAI client is not concurrency-safe.Overriding
this.openai.chat.completions.createon a shared provider instance can bleed settings across parallel requests. Confirm whetherGrokProvideris instantiated per request or held as a singleton; if it’s shared, refactor to supply per-call parameters (for example via anaugmentParams(params)hook onOpenAICompatibleProvider) or create a fresh client instance for each call instead of mutating the global client.
| // Handle reasoning models and search functionality | ||
| const shouldAddReasoningEffort = this.isReasoningModel(modelId) && modelConfig?.reasoningEffort | ||
| const shouldAddEnableSearch = this.supportsEnableSearch(modelId) && modelConfig?.enableSearch | ||
| const needsParameterModification = shouldAddReasoningEffort || shouldAddEnableSearch | ||
|
|
There was a problem hiding this comment.
🛠️ Refactor suggestion
Non-stream path may not inject search/reasoning parameters.
coreStream handles injection, but completions() delegates to openAICompletion() without the same injection. If live search must work for non-stream calls too, mirror the injection there.
Apply a scoped patch around openAICompletion:
async completions(
messages: ChatMessage[],
modelId: string,
temperature?: number,
maxTokens?: number
): Promise<LLMResponse> {
// Image generation models require special handling
if (this.isImageModel(modelId)) {
return this.handleImageGeneration(messages)
}
- return this.openAICompletion(messages, modelId, temperature, maxTokens)
+ // Parity with coreStream: inject reasoning/search when enabled
+ const modelConfig = await this.configPresenter.getModelConfig(modelId, this.provider)
+ const shouldAddReasoningEffort = this.isReasoningModel(modelId) && modelConfig?.reasoningEffort
+ const shouldAddEnableSearch = this.supportsEnableSearch(modelId) && modelConfig?.enableSearch
+ const needsParameterModification = shouldAddReasoningEffort || shouldAddEnableSearch
+
+ if (!needsParameterModification) {
+ return this.openAICompletion(messages, modelId, temperature, maxTokens)
+ }
+
+ const originalCreate = this.openai.chat.completions.create.bind(this.openai.chat.completions)
+ this.openai.chat.completions.create = ((params: any, options?: any) => {
+ const modifiedParams = { ...params }
+ if (shouldAddReasoningEffort && this.supportsReasoningEffort(modelId)) {
+ modifiedParams.reasoning_effort = modelConfig.reasoningEffort
+ }
+ if (shouldAddEnableSearch) {
+ modifiedParams.search_parameters = { mode: 'on' }
+ }
+ return originalCreate(modifiedParams, options)
+ }) as any
+ try {
+ return this.openAICompletion(messages, modelId, temperature, maxTokens)
+ } finally {
+ this.openai.chat.completions.create = originalCreate
+ }
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| // Handle reasoning models and search functionality | |
| const shouldAddReasoningEffort = this.isReasoningModel(modelId) && modelConfig?.reasoningEffort | |
| const shouldAddEnableSearch = this.supportsEnableSearch(modelId) && modelConfig?.enableSearch | |
| const needsParameterModification = shouldAddReasoningEffort || shouldAddEnableSearch | |
| async completions( | |
| messages: ChatMessage[], | |
| modelId: string, | |
| temperature?: number, | |
| maxTokens?: number | |
| ): Promise<LLMResponse> { | |
| // Image generation models require special handling | |
| if (this.isImageModel(modelId)) { | |
| return this.handleImageGeneration(messages) | |
| } | |
| // Parity with coreStream: inject reasoning/search when enabled | |
| const modelConfig = await this.configPresenter.getModelConfig(modelId, this.provider) | |
| const shouldAddReasoningEffort = this.isReasoningModel(modelId) && modelConfig?.reasoningEffort | |
| const shouldAddEnableSearch = this.supportsEnableSearch(modelId) && modelConfig?.enableSearch | |
| const needsParameterModification = shouldAddReasoningEffort || shouldAddEnableSearch | |
| if (!needsParameterModification) { | |
| return this.openAICompletion(messages, modelId, temperature, maxTokens) | |
| } | |
| // Monkey-patch the chat completion call to inject parameters | |
| const originalCreate = this.openai.chat.completions.create.bind(this.openai.chat.completions) | |
| this.openai.chat.completions.create = ((params: any, options?: any) => { | |
| const modifiedParams = { ...params } | |
| if (shouldAddReasoningEffort && this.supportsReasoningEffort(modelId)) { | |
| modifiedParams.reasoning_effort = modelConfig.reasoningEffort | |
| } | |
| if (shouldAddEnableSearch) { | |
| modifiedParams.search_parameters = { mode: 'on' } | |
| } | |
| return originalCreate(modifiedParams, options) | |
| }) as any | |
| try { | |
| return this.openAICompletion(messages, modelId, temperature, maxTokens) | |
| } finally { | |
| // Restore original behavior | |
| this.openai.chat.completions.create = originalCreate | |
| } | |
| } |
🤖 Prompt for AI Agents
In src/main/presenter/llmProviderPresenter/providers/grokProvider.ts around
lines 212 to 216, the non-stream path that calls openAICompletion does not get
the same reasoning/search parameter injection as the coreStream path; mirror the
coreStream injection logic for shouldAddReasoningEffort and
shouldAddEnableSearch so that when needsParameterModification is true you
build/merge the reasoningEffort and enableSearch fields into the completion
request payload and pass that modified payload into openAICompletion; ensure you
reuse the same condition checks and parameter names used for streaming, perform
a shallow merge so existing request fields are preserved, and keep the change
scoped to the openAICompletion invocation in the completions() non-stream
branch.
add live search support for Grok provider
Summary by CodeRabbit
New Features
Bug Fixes