fix: the message format for the role tool #1089
Conversation
… tools were called simultaneously.
WalkthroughAdded comprehensive native and mock tool-call scaffolding to OpenAICompatibleProvider: tracking structures, ID management, multi-part content splitting, mock response injection, streaming/function_call edge-case handling, and a parseFunctionCalls signature update with fallbackIdPrefix; also expanded model-version gating to include gpt-4.1. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Provider as OpenAICompatibleProvider
participant Tracker as ToolCallTracker
participant Parser as FunctionCallParser
User->>Provider: formatMessages(messages)
activate Provider
Provider->>Parser: parseFunctionCalls(response, fallbackIdPrefix)
Parser-->>Provider: function_call entries (with IDs)
alt Native tool-call path
Provider->>Tracker: enqueue native tool_call_ids
Tracker-->>Provider: pendingNativeToolCallIds snapshot
else Mock tool-call path
Provider->>Tracker: map to mock tool responses
end
Provider->>Provider: splitMergedToolContent (if merged)
Provider->>Tracker: pushMockToolResponse / consumeNativeToolCallId
Provider->>Provider: emit tool_call_end (when finalizable)
Provider-->>User: return formatted messages/stream events
deactivate Provider
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes
Possibly related PRs
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 inconclusive)
✅ Passed checks (4 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: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (1)
1523-1527: Base class signature mismatch requires correction.The
parseFunctionCallsmethod is overridden in derived classes with an additionalfallbackIdPrefixparameter, but the base class inbaseProvider.ts:425retains the original single-parameter signature. This violates the Liskov Substitution Principle and creates type safety issues.Update required: Add the
fallbackIdPrefixparameter to the base class signature insrc/main/presenter/llmProviderPresenter/baseProvider.ts:425to match the derived implementations:protected parseFunctionCalls( response: string, fallbackIdPrefix: string = 'tool-call' ): { id: string; type: string; function: { name: string; arguments: string } }[] {All call sites correctly pass appropriate prefixes or use defaults, but the type hierarchy must be consistent.
🧹 Nitpick comments (4)
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (4)
332-361: Add error handling for the function_call_record structure.The
pushMockToolResponsefunction constructs afunction_call_recordobject, but if the arguments parsing fails (caught at line 343), it falls back to an empty object{}. However, the consuming code might expect the arguments to maintain some structure or type information from the original failed parse.Consider logging a warning when the parse fails to aid debugging:
argsObj = typeof pendingCall.arguments === 'string' ? JSON.parse(pendingCall.arguments) : pendingCall.arguments } catch { + console.warn('[formatMessages] Failed to parse tool call arguments:', pendingCall.arguments) argsObj = {} }
405-412: Consider more robust ID generation for tool calls.Lines 406 and 431 use
tool-${Date.now()}-${Math.random()}to generate fallback IDs. WhileMath.random()collisions are unlikely in practice, using a more robust approach like a counter or UUID would eliminate any theoretical collision risk, especially in high-throughput scenarios.- const toolCallId = toolCall.id || `tool-${Date.now()}-${Math.random()}` + let toolCallIdCounter = 0 + const toolCallId = toolCall.id || `tool-${Date.now()}-${toolCallIdCounter++}`Alternatively, consider using a UUID library if available in the codebase.
588-647: Simplify the header repeat detection logic.The
trySplitByHeaderRepeatsmethod has complex nested logic with two fallback approaches (lines 608-625 and 627-644) that are very similar. This increases cognitive complexity and maintenance burden.Consider refactoring to a single, clearer approach:
private trySplitByHeaderRepeats(content: string, expectedParts: number): string[] | null { const headerRegex = /(?:^|\n)([-*]?\s*[A-Za-z][A-Za-z0-9\s,'"-]{0,80}?:)/g const matches = [...content.matchAll(headerRegex)] if (matches.length !== expectedParts) { return null } const segments: string[] = [] for (let i = 0; i < matches.length; i++) { const match = matches[i] const start = (match.index ?? 0) + (match[0].startsWith('\n') ? 1 : 0) const end = i + 1 < matches.length ? (matches[i + 1].index ?? content.length) : content.length const segment = content.slice(start, end).trim() if (!segment) return null segments.push(segment) } return segments.length === expectedParts ? segments : null }This eliminates the normalization logic and focuses on the simpler case where header count exactly matches expected parts.
1376-1401: Consider documenting incomplete tool call behavior.The code handles unclosed
<function_call>tags by appending '-incomplete' to the tool call ID and intentionally not emitting atool_call_endevent (line 1395). While this is a reasonable approach to signal incomplete calls, it's unclear if downstream consumers are aware of this convention.Document this behavior:
- In the method JSDoc explaining when incomplete tool calls can occur
- In any interface definition for tool call events
- Consider adding a property to the tool call event to explicitly mark it as incomplete rather than relying on ID suffix parsing
Based on learnings about tool call event requirements (tool_call_start → tool_call_chunk* → tool_call_end).
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts(8 hunks)
🧰 Additional context used
📓 Path-based instructions (11)
**/*.{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/llmProviderPresenter/providers/openAICompatibleProvider.ts
src/{main,renderer}/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
src/{main,renderer}/**/*.ts: Use context isolation for improved security
Implement proper inter-process communication (IPC) patterns
Optimize application startup time with lazy loading
Implement proper error handling and logging for debugging
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
src/main/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Use Electron's built-in APIs for file system and native dialogs
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/error-logging.mdc)
**/*.{ts,tsx}: 始终使用 try-catch 处理可能的错误
提供有意义的错误信息
记录详细的错误日志
优雅降级处理
日志应包含时间戳、日志级别、错误代码、错误描述、堆栈跟踪（如适用）、相关上下文信息
日志级别应包括 ERROR、WARN、INFO、DEBUG
不要吞掉错误
提供用户友好的错误信息
实现错误重试机制
避免记录敏感信息
使用结构化日志
设置适当的日志级别
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
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/openAICompatibleProvider.ts
src/main/**/*.{ts,js,tsx,jsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
主进程代码放在
src/main
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,js,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for all logs and comments
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and adhere to strict TypeScript typing (avoid implicit any, prefer precise types)
Use PascalCase for TypeScript types and classes
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
src/main/presenter/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Place Electron main-process presenters under src/main/presenter/ (Window, Tab, Thread, Mcp, Config, LLMProvider)
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,js,jsx,vue,css,scss,md,json,yml,yaml}
📄 CodeRabbit inference engine (AGENTS.md)
Prettier style: single quotes, no semicolons, print width 100; run pnpm run format
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{ts,tsx,js,jsx,vue}: Use OxLint for JS/TS code; keep lint clean
Use camelCase for variables and functions
Use SCREAMING_SNAKE_CASE for constants
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
🧠 Learnings (11)
📓 Common learnings
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : When a provider supports native function calling, MCP tools must be converted to the provider's format (e.g., using `convertToProviderTools`) and included in the API request.
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-09-04T11:03:30.184Z
Learning: Tool calls must follow tool_call_start → tool_call_chunk* → tool_call_end; tool_call_id is required and stable
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : When a provider supports native function calling, MCP tools must be converted to the provider's format (e.g., using `convertToProviderTools`) and included in the API request.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should implement helper methods such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed for provider-specific logic.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations should yield tool call events (`tool_call_start`, `tool_call_chunk`, `tool_call_end`) in the standardized format.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : When a provider does not support native function calling, it must prepare messages using prompt wrapping (e.g., `prepareFunctionCallPrompt`) before making the API call.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Each file in `src/main/presenter/llmProviderPresenter/providers/*.ts` should handle interaction with a specific LLM API, including request/response formatting, tool definition conversion, native/non-native tool call management, and standardizing output streams to a common event format.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : 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.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single streaming API request per conversation round and must not contain multi-round tool call loop logic.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop in `llmProviderPresenter/index.ts` should handle multi-round LLM calls and tool usage, maintaining conversation state and controlling the loop with `needContinueConversation` and `toolCallCount`.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-08-28T05:55:31.482Z
Learnt from: zerob13
Repo: ThinkInAIXYZ/deepchat PR: 804
File: src/main/presenter/llmProviderPresenter/providers/tokenfluxProvider.ts:153-156
Timestamp: 2025-08-28T05:55:31.482Z
Learning: TokenFlux models generally support function calling by default, so it's reasonable to assume hasFunctionCalling = true for TokenFlux provider implementations in src/main/presenter/llmProviderPresenter/providers/tokenfluxProvider.ts
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop should buffer text content, handle tool call events, format tool results for the next LLM call, and manage conversation continuation logic.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.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 (3)
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (3)
481-521: Good fallback handling for orphaned tool responses.The code properly handles the case where a tool response arrives without a matching pending tool call (lines 507-520). The fallback creates a mock
function_call_recordwithname: 'unknown', which allows the conversation to continue gracefully rather than failing.This defensive approach aligns with the goal of fixing tool_call_id errors.
452-467: Add safety check for undefined toolCallId.At line 456,
toolCallIdis assigned frompendingIds[index], but there's no verification thatpendingIds[index]exists before using it. If the array is shorter than expected or contains undefined values, this could lead to issues downstream.Add a guard:
splitParts.forEach((part, index) => { const toolCallId = pendingIds[index] + if (!toolCallId) { + console.warn('[formatMessages] Missing toolCallId for split part at index', index) + return + } consumeNativeToolCallId(toolCallId) result.push({ role: 'tool', content: part, tool_call_id: toolCallId } as ChatCompletionMessageParam) })Likely an incorrect or invalid review comment.
673-679: No action required — the code is correct as written.GPT-4.1 is a real model family released April 14, 2025 (including variants: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano) that supports the max_completion_tokens parameter in the chat/completions API. The use of
.includes('gpt-4.1')correctly matches all model variants in this family, and is semantically appropriate since these models can have hyphenated suffixes. This approach is intentional and consistent with howgpt-5is handled elsewhere in the same conditionals. The original review comment misidentified this as an inconsistency.Likely an incorrect or invalid review comment.
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
Show resolved
Hide resolved
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
Show resolved
Hide resolved
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts(8 hunks)
🧰 Additional context used
📓 Path-based instructions (11)
**/*.{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/llmProviderPresenter/providers/openAICompatibleProvider.ts
src/{main,renderer}/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
src/{main,renderer}/**/*.ts: Use context isolation for improved security
Implement proper inter-process communication (IPC) patterns
Optimize application startup time with lazy loading
Implement proper error handling and logging for debugging
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
src/main/**/*.ts
📄 CodeRabbit inference engine (.cursor/rules/electron-best-practices.mdc)
Use Electron's built-in APIs for file system and native dialogs
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx}
📄 CodeRabbit inference engine (.cursor/rules/error-logging.mdc)
**/*.{ts,tsx}: 始终使用 try-catch 处理可能的错误
提供有意义的错误信息
记录详细的错误日志
优雅降级处理
日志应包含时间戳、日志级别、错误代码、错误描述、堆栈跟踪（如适用）、相关上下文信息
日志级别应包括 ERROR、WARN、INFO、DEBUG
不要吞掉错误
提供用户友好的错误信息
实现错误重试机制
避免记录敏感信息
使用结构化日志
设置适当的日志级别
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
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/openAICompatibleProvider.ts
src/main/**/*.{ts,js,tsx,jsx}
📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)
主进程代码放在
src/main
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,js,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Use English for all logs and comments
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,vue}
📄 CodeRabbit inference engine (CLAUDE.md)
Enable and adhere to strict TypeScript typing (avoid implicit any, prefer precise types)
Use PascalCase for TypeScript types and classes
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
src/main/presenter/**/*.ts
📄 CodeRabbit inference engine (AGENTS.md)
Place Electron main-process presenters under src/main/presenter/ (Window, Tab, Thread, Mcp, Config, LLMProvider)
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,js,jsx,vue,css,scss,md,json,yml,yaml}
📄 CodeRabbit inference engine (AGENTS.md)
Prettier style: single quotes, no semicolons, print width 100; run pnpm run format
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
**/*.{ts,tsx,js,jsx,vue}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{ts,tsx,js,jsx,vue}: Use OxLint for JS/TS code; keep lint clean
Use camelCase for variables and functions
Use SCREAMING_SNAKE_CASE for constants
Files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
🧠 Learnings (11)
📓 Common learnings
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : When a provider supports native function calling, MCP tools must be converted to the provider's format (e.g., using `convertToProviderTools`) and included in the API request.
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations should yield tool call events (`tool_call_start`, `tool_call_chunk`, `tool_call_end`) in the standardized format.
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : When a provider supports native function calling, MCP tools must be converted to the provider's format (e.g., using `convertToProviderTools`) and included in the API request.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should implement helper methods such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed for provider-specific logic.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations should yield tool call events (`tool_call_start`, `tool_call_chunk`, `tool_call_end`) in the standardized format.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : When a provider does not support native function calling, it must prepare messages using prompt wrapping (e.g., `prepareFunctionCallPrompt`) before making the API call.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Each file in `src/main/presenter/llmProviderPresenter/providers/*.ts` should handle interaction with a specific LLM API, including request/response formatting, tool definition conversion, native/non-native tool call management, and standardizing output streams to a common event format.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : 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.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single streaming API request per conversation round and must not contain multi-round tool call loop logic.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop in `llmProviderPresenter/index.ts` should handle multi-round LLM calls and tool usage, maintaining conversation state and controlling the loop with `needContinueConversation` and `toolCallCount`.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-07-21T01:46:52.880Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-07-21T01:46:52.880Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop should buffer text content, handle tool call events, format tool results for the next LLM call, and manage conversation continuation logic.
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts
📚 Learning: 2025-10-14T08:02:59.495Z
Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-10-14T08:02:59.495Z
Learning: Applies to src/main/presenter/LLMProvider/**/*.ts : Implement the two-layer LLM provider (Agent Loop + Provider) under src/main/presenter/LLMProvider
Applied to files:
src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.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)
fix #1088
Summary by CodeRabbit
New Features
Improvements