fix: toolcall failed on deepseek #1155

zerob13 · 2025-12-03T04:48:12Z

Summary by CodeRabbit

Bug Fixes
- Fixed variant selection preservation during conversation creation, ensuring user-selected variants remain properly accessible and maintained when creating new conversation branches.
- Enhanced tool interaction processing to only include completed exchanges in conversation history, preventing incomplete tool interactions from affecting conversation accuracy and reliability.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

coderabbitai · 2025-12-03T04:48:21Z

Walkthrough

Two focused enhancements: initialization of selectedVariantsMap during settings copy in conversation creation, and guarding tool_call processing in promptBuilder to only create tool response entries when a response actually exists.

Changes

Cohort / File(s)	Summary
Settings initialization `src/main/presenter/threadPresenter/managers/conversationManager.ts`	Initialize `defaultSettings.selectedVariantsMap = {}` when copying settings from latestConversation during conversation creation to ensure the property exists in merged defaults.
Tool response handling `src/main/presenter/threadPresenter/utils/promptBuilder.ts`	Guard tool_call entry processing by checking for `block.tool_call.response` existence; only add tool_call and generate toolCallId when a response is present. Added clarifying comments.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Single property initialization in conversationManager is straightforward
Tool response guard logic requires understanding the response structure and its impact on pairing behavior
Both changes are localized with minimal surface area

Possibly related PRs

ThinkInAIXYZ/deepchat#1081: Directly related—both PRs modify promptBuilder logic for handling tool_calls and tool responses, ensuring entries and IDs are only created when responses exist.

Poem

🐰 A map springs to life, initialized with care,
Tool responses now guard their rightful share,
No orphaned calls in the code so bright,
Just matched pairs dancing through the night! ✨

Pre-merge checks and finishing touches

❌ Failed checks (1 warning, 1 inconclusive)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.
Title check	❓ Inconclusive	The title 'fix: toolcall failed on deepseek' is partially related to the changeset. It references the tool call fix but is vague about the specific issue being addressed and lacks detail about the actual changes.	Consider making the title more specific about the actual fix, such as 'fix: initialize selectedVariantsMap in conversation settings and guard tool_call response handling' to better reflect the scope of changes.

✅ 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/toolcall-id

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 5638862 and dc8384f.

📒 Files selected for processing (2)

src/main/presenter/threadPresenter/managers/conversationManager.ts (1 hunks)
src/main/presenter/threadPresenter/utils/promptBuilder.ts (1 hunks)

🧰 Additional context used

📓 Path-based instructions (13)

**/*.{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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.ts

src/main/**/*.ts

📄 CodeRabbit inference engine (CLAUDE.md)

Use EventBus from src/main/eventbus.ts for main-to-renderer communication, broadcasting events via mainWindow.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 in src/main/ with presenters in presenter/ (Window/Tab/Thread/Mcp/Config/LLMProvider) and eventbus.ts for app events
Use the Presenter pattern in the main process for UI coordination

Files:

src/main/presenter/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.ts

src/**/*

📄 CodeRabbit inference engine (.cursor/rules/project-structure.mdc)

New features should be developed in the src directory

Files:

src/main/presenter/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.ts

src/**/*.{ts,tsx,js,jsx}

📄 CodeRabbit inference engine (AGENTS.md)

Use OxLint for linting JavaScript and TypeScript files

Files:

src/main/presenter/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.ts

src/**/*.ts

📄 CodeRabbit inference engine (AGENTS.md)

Use EventBus for inter-process communication events

Files:

src/main/presenter/threadPresenter/managers/conversationManager.ts
src/main/presenter/threadPresenter/utils/promptBuilder.ts

🧠 Learnings (10)

📚 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/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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 `stop` events by checking `stop_reason`: if `'tool_use'`, add the buffered assistant message and prepare for the next loop iteration; otherwise, add the final assistant message and exit the loop

Applied to files:

src/main/presenter/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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/threadPresenter/utils/promptBuilder.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/mcpPresenter/**/*.ts : Register new MCP tools in `mcpPresenter/index.ts` after implementing them in `inMemoryServers/`

Applied to files:

src/main/presenter/threadPresenter/utils/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/managers/conversationManager.ts (1)

177-186: LGTM! Defensive initialization ensures property consistency.

The initialization of selectedVariantsMap = {} when copying settings from the latest conversation is appropriate. This ensures the property exists for later use (e.g., in forkConversation at line 407) and is consistent with how other session-specific properties are cleared.

src/main/presenter/threadPresenter/utils/promptBuilder.ts (1)

474-491: LGTM! Critical fix for incomplete tool calls.

The guard if (block.tool_call.response) correctly ensures that only completed tool calls are added to the message context. This prevents inconsistencies where a tool_call is present without a corresponding response, which aligns with the PR objective to fix "toolcall failed on deepseek."

The logic correctly:

Only generates toolCallId when a response exists (line 477)

Pairs each tool_call with its response for proper role:tool message creation

Includes clear comments explaining the intent

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.}

zerob13 added 2 commits December 3, 2025 12:36

fix: #1153 only success tool_call block in message with response

fec8da8

fix: selectedVariantsMap cache

dc8384f

zerob13 merged commit 2d23600 into dev Dec 3, 2025
2 checks passed

zerob13 deleted the bugfix/toolcall-id branch December 13, 2025 06:59

This was referenced Dec 18, 2025

fix: tool call error #1191

Merged

fix: context trim remove tools first #1196

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix: toolcall failed on deepseek #1155

fix: toolcall failed on deepseek #1155

Uh oh!

zerob13 commented Dec 3, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

coderabbitai bot commented Dec 3, 2025 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

fix: toolcall failed on deepseek #1155

fix: toolcall failed on deepseek #1155

Uh oh!

Conversation

zerob13 commented Dec 3, 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 Dec 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Poem

Pre-merge checks and finishing touches

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

zerob13 commented Dec 3, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Dec 3, 2025 •

edited

Loading