fix: custom provider add refresh-model #1079

zerob13 · 2025-11-04T03:56:43Z

Summary by CodeRabbit

New Features
- Added support for multimodal content and tool call handling in AI provider communications.
- Improved function call parsing with robust error handling.
Bug Fixes
- Fixed button rendering conditions for AI providers.

coderabbitai · 2025-11-04T03:56:54Z

Walkthrough

Two files are updated: ProviderApiConfig.vue simplifies a button rendering condition by removing a custom provider dependency check. openAICompatibleProvider.ts receives a substantial refactor to support multimodal content, tool calls, tool results, and improved function call parsing with a non-native tool call path in the streaming flow.

Changes

Cohort / File(s)	Summary
UI condition simplification `src/renderer/settings/components/ProviderApiConfig.vue`	Simplified button render condition from `v-if="!provider.custom && provider.id !== 'doubao'"` to `v-if="provider.id !== 'doubao'"`, broadening visibility to all providers except 'doubao'.
Multimodal and tool call support `src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts`	Refactored `formatMessages` to handle multimodal content, merge assistant tool_calls into messages, and append tool results. Enhanced `handleChatCompletion` to support non-native tool calls with text-based representation. Updated `parseFunctionCalls` signature and implementation for robust extraction and standardized tool call objects.

Sequence Diagram(s)

sequenceDiagram
    actor User
    participant formatMessages
    participant handleChatCompletion
    participant parseFunctionCalls
    participant API

    User->>formatMessages: Message with tool_calls
    Note over formatMessages: Process user/assistant/tool roles<br/>Merge tool_calls into assistant message<br/>Append tool results
    formatMessages-->>handleChatCompletion: Formatted messages

    alt Native tool support
        handleChatCompletion->>API: Send with native tools
    else Non-native tools
        Note over handleChatCompletion: Convert tool_calls to text<br/>Inject into system/user context
        handleChatCompletion->>API: Send text-based prompt
    end

    API-->>handleChatCompletion: Response (native or text)
    handleChatCompletion->>parseFunctionCalls: Extract function calls
    Note over parseFunctionCalls: Parse response text<br/>Apply jsonrepair if needed<br/>Standardize to tool call objects
    parseFunctionCalls-->>handleChatCompletion: Array of {id, type, function}
    handleChatCompletion-->>User: Tool calls or completion

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~45 minutes

openAICompatibleProvider.ts refactoring: Multiple interconnected logic changes across formatMessages, handleChatCompletion, and parseFunctionCalls require careful review of tool call merging, streaming paths, and JSON parsing fallback behavior.
Tool message handling: New logic for appending tool results and creating merged assistant messages needs validation to ensure proper state transitions and edge case handling (empty tool arrays, missing messages, etc.).
Function call extraction robustness: The updated parseFunctionCalls now handles JSON repair and filtering—verify that fallback ID generation and defensive checks prevent invalid tool call objects from propagating.
Integration across methods: Changes span three methods with interdependencies; trace the flow from message formatting through completion handling to ensure multimodal and tool call semantics are preserved end-to-end.

Possibly related PRs

fix(agent): fix inconsistent fc call record format in chained non-native function calling #515: Modifies parseFunctionCalls in openAICompatibleProvider.ts with fallback ID generation adjustments.
fix(agent): improve accuracy of semantic descriptions for non-native fc calling #526: Adjusts non-native function-call handling and tool call representation in the provider/agent flow.
feat: add comprehensive OpenAI reasoning models support for OpenRouter #751: Refactors handleChatCompletion in openAICompatibleProvider.ts for enhanced streaming and tool/non-native call support.

Suggested labels

codex

Poem

🐰 Tools and calls now merge with grace,
Multimodal content finds its place,
JSON repairs when parsing fails,
The streaming flow no longer derails—
Compatibility expands its wings! ✨

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Title check	⚠️ Warning	The PR title mentions 'custom provider' and 'refresh-model', but the actual changes involve modifying a render condition in ProviderApiConfig.vue and substantial refactoring of OpenAICompatibleProvider to support multimodal content and tool calls—neither of which clearly relates to adding a 'refresh-model' feature.	Update the title to accurately reflect the main changes: either modifying button visibility conditions and multimodal support in OpenAICompatibleProvider, or clarify what 'refresh-model' feature was intended if the summary is incomplete.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch bugfix/refresh-model

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

better compatibility

coderabbitai

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 9c40088 and ae4e0c5.

📒 Files selected for processing (2)

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (1 hunks)
src/main/presenter/threadPresenter/promptBuilder.ts (1 hunks)

✅ Files skipped from review due to trivial changes (1)

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts

🧰 Additional context used

📓 Path-based instructions (10)

**/*.{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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.ts

**/*.{ts,tsx,js,vue}

📄 CodeRabbit inference engine (CLAUDE.md)

Use English for all logs and comments

Files:

src/main/presenter/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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 : Provider implementations should yield tool call events (`tool_call_start`, `tool_call_chunk`, `tool_call_end`) in the standardized format.

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.

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.

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 : 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.

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`.

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.

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.

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-09-06T03:07:23.817Z
Learning: Applies to src/main/presenter/configPresenter/providers.ts : Add provider configuration entries in src/main/presenter/configPresenter/providers.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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/threadPresenter/promptBuilder.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 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/threadPresenter/promptBuilder.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 : `src/main/presenter/llmProviderPresenter/index.ts` should manage the overall Agent loop, conversation history, tool execution via `McpPresenter`, and frontend communication via `eventBus`.

Applied to files:

src/main/presenter/threadPresenter/promptBuilder.ts

📚 Learning: 2025-09-06T03:07:23.817Z

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-09-06T03:07:23.817Z
Learning: Applies to src/main/presenter/mcpPresenter/index.ts : Register new MCP tools in src/main/presenter/mcpPresenter/index.ts

Applied to files:

src/main/presenter/threadPresenter/promptBuilder.ts

📚 Learning: 2025-09-04T11:03:30.184Z

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-09-04T11:03:30.184Z
Learning: Do not emit AssistantMessageBlock or any UI-layer types from the Provider

Applied to files:

src/main/presenter/threadPresenter/promptBuilder.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 (2)

src/main/presenter/threadPresenter/promptBuilder.ts (2)

500-506: Control flow change is consistent with plain-text formatting approach.

The simplified logic correctly pushes all historical content (including tool calls) as plain text, which is consistent with the formatting changes above. The implementation is clean and the comment clearly explains the behavior.

471-478: Incomplete tool call check is defensive programming—not indicative of upstream issues.

Tool calls generated by all providers (OpenAI, Anthropic, Ollama, GitHub Copilot, AWS Bedrock) consistently include both id and name. This check handles edge cases in historical message processing: incomplete data from older formats or data reconstruction. The defensive skip is appropriate and safe. Plain text formatting for historical tool calls is the intended behavior for provider compatibility (comment notes this avoids validation errors). No upstream issues to investigate.

src/main/presenter/threadPresenter/promptBuilder.ts

…tool for" This reverts commit ae4e0c5.

coderabbitai

Actionable comments posted: 1

🧹 Nitpick comments (2)

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (2)
296-331: Consider logging the parsing error for tool call arguments.

Lines 314-321 parse tool call arguments to format them as JSON, but the catch block silently converts to string without logging. This could hide malformed tool call data.

Apply this diff to add error logging:
           try {
             const args =
               typeof toolCall.function?.arguments === 'string'
                 ? JSON.parse(toolCall.function.arguments)
                 : toolCall.function?.arguments
             argsText = JSON.stringify(args, null, 2)
-          } catch {
+          } catch (parseError) {
+            console.warn('[formatMessages] Failed to parse tool call arguments:', parseError)
             argsText = String(toolCall.function?.arguments || '{}')
           }
1232-1413: Consider refactoring parseFunctionCalls into smaller helper methods.

This method is quite complex (~180 lines) with deeply nested logic for parsing, validation, and extraction. While the error handling is robust, the method would be more maintainable if broken into focused helpers:

extractFunctionCallBlocks(response: string) - extract content between tags

parseAndRepairJson(content: string) - handle JSON.parse with jsonrepair fallback

extractFunctionNameAndArgs(parsedCall: any) - extract from various structures

createToolCallObject(name, args, id) - build standardized object

This would improve readability and make each piece easier to test independently.

Based on learnings

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between ae4e0c5 and a18a2d8.

📒 Files selected for processing (1)

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (4 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 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.
Provider implementations must use a coreStream method that yields standardized stream events to decouple the main loop from provider-specific details.
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.
Provider files should implement helper methods such as formatMessages, convertToProviderTools, parseFunctionCalls, and prepareFunctionCallPrompt as 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., using convertToProviderTools) 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 appropriate stop_reason in 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 (14)

📓 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 : Provider implementations should yield tool call events (`tool_call_start`, `tool_call_chunk`, `tool_call_end`) in the standardized format.

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.

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 files should implement helper methods such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed for provider-specific logic.

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/vue-shadcn.mdc:0-0
Timestamp: 2025-07-23T00:45:57.322Z
Learning: Applies to src/renderer/**/*.{vue} : Use provide/inject for dependency injection when appropriate.

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-09-06T03:07:23.817Z
Learning: Applies to src/main/presenter/configPresenter/providers.ts : Add provider configuration entries in src/main/presenter/configPresenter/providers.ts

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.

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.

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: The architecture should ensure consistent behavior for tool handling, reasoning content parsing, and event emission across all Providers.

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/vue-best-practices.mdc:0-0
Timestamp: 2025-07-21T01:47:28.817Z
Learning: Applies to src/renderer/src/**/*.{vue,ts,tsx,js,jsx} : Use the Composition API for better code organization and reusability

📚 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 : 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 : 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 : 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/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: 2025-07-21T01:46:52.880Z

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 : 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/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/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/providers/*.ts : Provider implementations should yield text events 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/index.ts : `src/main/presenter/llmProviderPresenter/index.ts` should manage the overall Agent loop, conversation history, tool execution via `McpPresenter`, and frontend communication via `eventBus`.

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

📚 Learning: 2025-09-04T11:03:30.184Z

Learnt from: CR
Repo: ThinkInAIXYZ/deepchat PR: 0
File: .cursor/rules/provider-guidelines.mdc:0-0
Timestamp: 2025-09-04T11:03:30.184Z
Learning: Integrate via the llmProviderPresenter entry point (src/main/presenter/llmProviderPresenter/index.ts) as the related implementation entry

Applied to files:

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts

🧬 Code graph analysis (1)

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts (1)

src/shared/types/presenters/legacy.presenters.d.ts (1)

ChatMessage (1384-1384)

⏰ 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/providers/openAICompatibleProvider.ts (2)

257-294: User message handling looks correct.

The multimodal content preservation for user messages and content conversion for other roles is properly implemented. The early continue pattern helps maintain clarity.

679-681: Non-native function call path correctly implemented.

The logic properly checks for tools and native function call support, then prepares the prompt wrapper when needed. This aligns with the provider architecture for handling non-native tool calls.

Based on learnings

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts

* Merge pull request #1079 from ThinkInAIXYZ/bugfix/refresh-model fix: custom provider add refresh-model * fix: add tool call context for better conv (#1081) * fix: update `tag_name` for release artifact urls (#1084) Signed-off-by: Rui Chen <rui@chenrui.dev> * refactor: standardize image block data structure (#1082) * refactor: standardize image block data structure with backward compatibility Normalize image_data structure in ThreadPresenter to ensure consistent mimeType handling. Update MessageBlockImage component to support legacy data formats (content as object/string/data URI) while maintaining compatibility with new image_data field. * fix: properly normalize image data URIs before persistence Extract base64 content and mime type from data URIs (data:image/jpeg;base64,...) to prevent double-encoding in renderer. This fixes image display errors where data:image/png;base64,data:image/jpeg;base64,... was being constructed. - Parse data URIs to extract real mime type and base64 content - Force URL schemes (http://, https://, imgcache://) to deepchat/image-url - Preserve provided mime types when available - Fallback to image/png only for raw base64 without metadata * fix: normalize legacy data URIs in renderer to prevent double-encoding Handle historical image_data records that may still contain full data:image/...;base64,... URIs. Extract base64 content and mime type before template binding to prevent constructing invalid data:image/png;base64,data:image/png;base64,... URIs. - Parse data URIs in both new image_data and legacy content formats - Always provide mimeType fallback for historical records - Ensure normalized data format before template consumption * feat: add request trace for llm (#1085) * feat: add trace support wip * feat: add trace dialog with monaco * feat: add i18n for trace dialog * feat: add config for trace params * fix: prevent stale previews when messageId changes * fix: toggle model config refresh (#1086) * release: 0.4.5 --------- Signed-off-by: Rui Chen <rui@chenrui.dev> Co-authored-by: Rui Chen <rui@chenrui.dev> Co-authored-by: 韦伟 <xweimvp@gmail.com>

fix: custom provider add refresh-model

9c40088

fix: #1078 change tool response to ai response remove role: tool for

ae4e0c5

better compatibility

coderabbitai bot reviewed Nov 4, 2025

View reviewed changes

src/main/presenter/threadPresenter/promptBuilder.ts Outdated Show resolved Hide resolved

zerob13 added 2 commits November 4, 2025 13:46

revert: "fix: #1078 change tool response to ai response remove role: …

8dd48d0

…tool for" This reverts commit ae4e0c5.

fix: change better tools message for openAICompatibleProvider

a18a2d8

coderabbitai bot reviewed Nov 4, 2025

View reviewed changes

src/main/presenter/llmProviderPresenter/providers/openAICompatibleProvider.ts Show resolved Hide resolved

zerob13 merged commit 0bee52f into dev Nov 4, 2025
2 checks passed

zerob13 deleted the bugfix/refresh-model branch November 6, 2025 10:52

coderabbitai bot mentioned this pull request Nov 10, 2025

fix: the message format for the role tool #1089

Merged

coderabbitai bot mentioned this pull request Dec 18, 2025

feat: an Embedded Electron Browser Sandbox with Auto-Injected Tools and Environment State #1192

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix: custom provider add refresh-model #1079

fix: custom provider add refresh-model #1079

Uh oh!

zerob13 commented Nov 4, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

coderabbitai bot commented Nov 4, 2025 •

edited

Loading

Uh oh!

coderabbitai bot left a comment

Uh oh!

Uh oh!

coderabbitai bot left a comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

fix: custom provider add refresh-model #1079

fix: custom provider add refresh-model #1079

Uh oh!

Conversation

zerob13 commented Nov 4, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Nov 4, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Possibly related PRs

Suggested labels

Poem

Pre-merge checks and finishing touches

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

zerob13 commented Nov 4, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Nov 4, 2025 •

edited

Loading