Skip to content

feat: add 302 balance api #575

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
zerob13 merged 3 commits into from
Jul 2, 2025
Merged

feat: add 302 balance api #575

zerob13 merged 3 commits into from
Jul 2, 2025

Conversation

@zerob13
Copy link
Collaborator

@zerob13 zerob13 commented Jul 2, 2025 •
edited by coderabbitai bot
Loading

302 provider 支持余额查询

Summary by CodeRabbit

  • New Features

    • Added support for the 302AI provider, including API key status checking and usage monitoring.

  • Bug Fixes

    • Improved consistency in summary generation by standardizing prompt usage across providers.

  • Refactor

    • Removed summary methods from several providers to streamline functionality.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jul 2, 2025 •
edited
Loading

Walkthrough

A new LLM provider, '302ai', has been integrated into the system. This includes implementing the _302AIProvider class, updating the provider instantiation logic, and enabling key status checks for '302ai' in the settings UI. Additionally, summary title prompt handling was unified across several providers, and redundant or duplicate summary methods were removed.

Changes

File(s) Change Summary
src/main/presenter/llmProviderPresenter/index.ts Added support for '302ai' provider; imports and instantiates _302AIProvider.
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts Introduced _302AIProvider class with completions, generateText, key status, and check logic.
src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts Removed summaries method.
src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts Replaced hardcoded summary prompt with imported SUMMARY_TITLES_PROMPT in summaryTitles.
src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts Used SUMMARY_TITLES_PROMPT constant for summary prompts instead of hardcoded string.
src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts,
.../githubProvider.ts		 Removed summaries method from both provider classes.
src/renderer/src/components/settings/ProviderApiConfig.vue Added '302ai' to provider IDs for which key status is fetched in settings UI.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant SettingsUI
    participant LLMProviderPresenter
    participant _302AIProvider
    participant 302AI_API

    User->>SettingsUI: Open provider settings
    SettingsUI->>LLMProviderPresenter: Request key status for '302ai'
    LLMProviderPresenter->>_302AIProvider: getKeyStatus()
    _302AIProvider->>302AI_API: GET /dashboard/balance with API key
    302AI_API-->>_302AIProvider: Respond with balance
    _302AIProvider-->>LLMProviderPresenter: Return KeyStatus
    LLMProviderPresenter-->>SettingsUI: Provide key status info
Loading

Poem

A new provider hops in, '302ai' by name,
With key checks and prompts now all the same.
Old summaries trimmed, the code feels light,
Prompts unified for titles bright.
In the warren of logic, things are neat—
Another carrot for our code to eat! 🥕

✨ Finishing Touches
  • 📝 Generate Docstrings

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
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

coderabbitai[bot]
coderabbitai bot reviewed Jul 2, 2025
View reviewed changes
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 2

🧹 Nitpick comments (1)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (1)

13-15: Remove unnecessary constructor.

The constructor only calls the parent constructor with the same parameters and provides no additional functionality.

-  constructor(provider: LLM_PROVIDER, configPresenter: ConfigPresenter) {
-    super(provider, configPresenter)
-  }
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e514af0 and 9ff13b4.

📒 Files selected for processing (8)
  • src/main/presenter/llmProviderPresenter/index.ts (2 hunks)
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (1 hunks)
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts (1 hunks)
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts (2 hunks)
  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts (2 hunks)
  • src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts (0 hunks)
  • src/main/presenter/llmProviderPresenter/providers/githubProvider.ts (0 hunks)
  • src/renderer/src/components/settings/ProviderApiConfig.vue (1 hunks)
💤 Files with no reviewable changes (2)
  • src/main/presenter/llmProviderPresenter/providers/doubaoProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/githubProvider.ts
🧰 Additional context used
📓 Path-based instructions (9)
`**/*.{js,jsx,ts,tsx}`: 使用 OxLint 进行代码检查 Log和注释使用英文书写

**/*.{js,jsx,ts,tsx}: 使用 OxLint 进行代码检查
Log和注释使用英文书写

📄 Source: CodeRabbit Inference Engine (.cursor/rules/development-setup.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts
  • src/main/presenter/llmProviderPresenter/index.ts
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/main/presenter/**/*.ts`: Use context isolation for improved security Use El...

src/main/presenter/**/*.ts: Use context isolation for improved security
Use Electron's built-in APIs for file system and native dialogs
Optimize application startup time with lazy loading

📄 Source: CodeRabbit Inference Engine (.cursor/rules/electron-best-practices.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts
  • src/main/presenter/llmProviderPresenter/index.ts
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`{src/main/presenter/**/*.ts,src/renderer/stores/**/*.ts}`: Implement proper inter-process communication (IPC) patterns Implement proper error handling and logging for debugging

{src/main/presenter/**/*.ts,src/renderer/stores/**/*.ts}: Implement proper inter-process communication (IPC) patterns
Implement proper error handling and logging for debugging

📄 Source: CodeRabbit Inference Engine (.cursor/rules/electron-best-practices.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts
  • src/main/presenter/llmProviderPresenter/index.ts
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`**/*.{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 使用结构化日志 避免记录敏感信息 设置适当的日志级别 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

**/*.{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
使用结构化日志
避免记录敏感信息
设置适当的日志级别
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

📄 Source: CodeRabbit Inference Engine (.cursor/rules/error-logging.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts
  • src/main/presenter/llmProviderPresenter/index.ts
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/main/presenter/llmProviderPresenter/providers/*.ts`: Each file in `src/main...

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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.
Provider implementations must use a standardized interface in their coreStream method to yield events, decoupling the main Agent loop from provider-specific details.
The coreStream method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.
Provider files must implement the coreStream(messages, modelId, temperature, maxTokens) method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.
Provider files should include provider-specific helper functions such as formatMessages, convertToProviderTools, parseFunctionCalls, and prepareFunctionCallPrompt as needed.

📄 Source: CodeRabbit Inference Engine (.cursor/rules/llm-agent-loop.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/main/**`: 主进程代码放在 `src/main`

src/main/**: 主进程代码放在 src/main

📄 Source: CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts
  • src/main/presenter/llmProviderPresenter/index.ts
  • src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/renderer/src/**/*`: All user-facing strings in the renderer must use i18n k...

src/renderer/src/**/*: All user-facing strings in the renderer must use i18n keys (do not hardcode user-visible text in code; use vue-i18n translation keys instead)
Do not hardcode user-facing text in code; always use the translation system (vue-i18n) for all user-visible strings

📄 Source: CodeRabbit Inference Engine (.cursor/rules/i18n.mdc)

List of files the instruction was applied to:

  • src/renderer/src/components/settings/ProviderApiConfig.vue
`src/renderer/**`: 渲染进程代码放在 `src/renderer`

src/renderer/**: 渲染进程代码放在 src/renderer

📄 Source: CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)

List of files the instruction was applied to:

  • src/renderer/src/components/settings/ProviderApiConfig.vue
`src/main/presenter/llmProviderPresenter/index.ts`: `src/main/presenter/llmProvi...

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 communication with the frontend via eventBus.
The main Agent loop, including the while loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in src/main/presenter/llmProviderPresenter/index.ts.

📄 Source: CodeRabbit Inference Engine (.cursor/rules/llm-agent-loop.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/index.ts
🧠 Learnings (6)
📓 Common learnings 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Ensure that adding a new Provider only requires implementing the `coreStream` method according to the standardized interface, without duplicating Agent loop logic.
src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts (10) 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop, including the `while` loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in `src/main/presenter/llmProviderPresenter/index.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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 communication with the frontend via `eventBus`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/streamEvents.ts : Define the standardized stream event interface (`LLMCoreStreamEvent`) in a shared location, such as `src/main/presenter/llmProviderPresenter/streamEvents.ts`.

Learnt from: neoragex2002
PR: ThinkInAIXYZ/deepchat#550
File: src/main/presenter/mcpPresenter/inMemoryServers/meetingServer.ts:250-252
Timestamp: 2025-06-21T15:48:29.950Z
Learning: In the meeting server implementation (src/main/presenter/mcpPresenter/inMemoryServers/meetingServer.ts), when multiple tabs have the same title, the user prefers to let the code silently select the first match without adding warnings or additional ambiguity handling.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/electron-best-practices.mdc:0-0
Timestamp: 2025-06-30T12:23:13.304Z
Learning: Applies to src/renderer/src/composables/usePresenter.ts : The IPC in the renderer process is implemented in usePresenter.ts, allowing direct calls to the presenter-related interfaces exposed by the main process
src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts (10) 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop, including the `while` loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in `src/main/presenter/llmProviderPresenter/index.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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 communication with the frontend via `eventBus`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/streamEvents.ts : Define the standardized stream event interface (`LLMCoreStreamEvent`) in a shared location, such as `src/main/presenter/llmProviderPresenter/streamEvents.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/electron-best-practices.mdc:0-0
Timestamp: 2025-06-30T12:23:13.304Z
Learning: Applies to src/renderer/src/composables/usePresenter.ts : The IPC in the renderer process is implemented in usePresenter.ts, allowing direct calls to the presenter-related interfaces exposed by the main process

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/electron-best-practices.mdc:0-0
Timestamp: 2025-06-30T12:23:13.304Z
Learning: Applies to {src/main/presenter/**/*.ts,src/renderer/stores/**/*.ts} : Implement proper inter-process communication (IPC) patterns
src/main/presenter/llmProviderPresenter/index.ts (12) 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop, including the `while` loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in `src/main/presenter/llmProviderPresenter/index.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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 communication with the frontend via `eventBus`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/streamEvents.ts : Define the standardized stream event interface (`LLMCoreStreamEvent`) in a shared location, such as `src/main/presenter/llmProviderPresenter/streamEvents.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Maintain separation of concerns by centralizing Agent loop logic in `index.ts` and keeping provider files focused on API interaction and event standardization.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/electron-best-practices.mdc:0-0
Timestamp: 2025-06-30T12:23:13.304Z
Learning: Applies to src/main/presenter/**/*.ts : Use context isolation for improved security

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Ensure that adding a new Provider only requires implementing the `coreStream` method according to the standardized interface, without duplicating Agent loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/electron-best-practices.mdc:0-0
Timestamp: 2025-06-30T12:23:13.304Z
Learning: Applies to {src/main/presenter/**/*.ts,src/renderer/stores/**/*.ts} : Implement proper inter-process communication (IPC) patterns
src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts (8) 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop, including the `while` loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in `src/main/presenter/llmProviderPresenter/index.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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 communication with the frontend via `eventBus`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Maintain separation of concerns by centralizing Agent loop logic in `index.ts` and keeping provider files focused on API interaction and event standardization.
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (9) 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop, including the `while` loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in `src/main/presenter/llmProviderPresenter/index.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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 communication with the frontend via `eventBus`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Maintain separation of concerns by centralizing Agent loop logic in `index.ts` and keeping provider files focused on API interaction and event standardization.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/streamEvents.ts : Define the standardized stream event interface (`LLMCoreStreamEvent`) in a shared location, such as `src/main/presenter/llmProviderPresenter/streamEvents.ts`.
🧬 Code Graph Analysis (3)
src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts (1)
src/main/presenter/llmProviderPresenter/baseProvider.ts (1)
  • SUMMARY_TITLES_PROMPT (602-604)
src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts (1)
src/main/presenter/llmProviderPresenter/baseProvider.ts (1)
  • SUMMARY_TITLES_PROMPT (602-604)
src/main/presenter/llmProviderPresenter/index.ts (1)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (1)
  • _302AIProvider (12-108)
🪛 GitHub Check: build-check (x64)
src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts

[failure] 7-7:
'SUMMARY_TITLES_PROMPT' is declared but its value is never read.

🪛 GitHub Actions: PR Check
src/main/presenter/llmProviderPresenter/providers/aihubmixProvider.ts

[error] 7-7: TypeScript error TS6133: 'SUMMARY_TITLES_PROMPT' is declared but its value is never read.

🪛 Biome (1.9.4)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts

[error] 13-15: This constructor is unnecessary.

Unsafe fix: Remove the unnecessary constructor.

(lint/complexity/noUselessConstructor)

🔇 Additional comments (9)
src/main/presenter/llmProviderPresenter/providers/deepseekProvider.ts (2)

4-4: LGTM! Good refactoring to use shared prompt constant.

This change centralizes prompt management and reduces code duplication across providers.

41-41: Excellent standardization of summary prompt usage.

The replacement of the hardcoded prompt with the shared SUMMARY_TITLES_PROMPT constant improves maintainability and ensures consistency across providers.

src/main/presenter/llmProviderPresenter/providers/anthropicProvider.ts (2)

10-10: LGTM! Consistent with prompt standardization effort.

Adding the shared prompt constant import aligns with the broader refactoring to centralize prompt management.

500-500: Good standardization of prompt usage in summaryTitles method.

The refactoring to use SUMMARY_TITLES_PROMPT improves consistency across providers and centralizes prompt management.

src/renderer/src/components/settings/ProviderApiConfig.vue (1)

181-183: Correctly integrates 302AI provider for key status checking.

This addition enables the UI to display API key status for the new 302AI provider, which implements the required getKeyStatus method.

src/main/presenter/llmProviderPresenter/index.ts (2)

38-38: LGTM! Proper import for new 302AI provider.

The import follows the established naming convention and pattern for provider imports.

97-99: Excellent integration of 302AI provider following established patterns.

The provider instantiation logic is correctly placed before the switch statement and follows the same pattern as other provider-specific handlers like minimax and openrouter.

src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (2)

17-43: LGTM! Method implementations follow the correct provider pattern.

The completions and generateText methods properly delegate to the OpenAI-compatible base implementation, which aligns with the established provider architecture patterns.

83-107: Excellent error handling implementation.

The error handling follows TypeScript best practices with proper type guards, descriptive error messages, and comprehensive logging. This aligns well with the coding guidelines for error handling.

@zerob13 zerob13 merged commit 0e09f07 into dev Jul 2, 2025
1 of 2 checks passed
coderabbitai[bot]
coderabbitai bot reviewed Jul 2, 2025
View reviewed changes
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (1)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (1)

12-15: Remove unnecessary constructor.

The constructor only calls super() with the same parameters and doesn't add any functionality.

-  constructor(provider: LLM_PROVIDER, configPresenter: ConfigPresenter) {
-    super(provider, configPresenter)
-  }
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 70dd4bf and d79edf5.

📒 Files selected for processing (1)
  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (1 hunks)
🧰 Additional context used
📓 Path-based instructions (6)
`**/*.{js,jsx,ts,tsx}`: 使用 OxLint 进行代码检查 Log和注释使用英文书写

**/*.{js,jsx,ts,tsx}: 使用 OxLint 进行代码检查
Log和注释使用英文书写

📄 Source: CodeRabbit Inference Engine (.cursor/rules/development-setup.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/main/presenter/**/*.ts`: Use context isolation for improved security Use El...

src/main/presenter/**/*.ts: Use context isolation for improved security
Use Electron's built-in APIs for file system and native dialogs
Optimize application startup time with lazy loading

📄 Source: CodeRabbit Inference Engine (.cursor/rules/electron-best-practices.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`{src/main/presenter/**/*.ts,src/renderer/stores/**/*.ts}`: Implement proper inter-process communication (IPC) patterns Implement proper error handling and logging for debugging

{src/main/presenter/**/*.ts,src/renderer/stores/**/*.ts}: Implement proper inter-process communication (IPC) patterns
Implement proper error handling and logging for debugging

📄 Source: CodeRabbit Inference Engine (.cursor/rules/electron-best-practices.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`**/*.{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 使用结构化日志 避免记录敏感信息 设置适当的日志级别 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

**/*.{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
使用结构化日志
避免记录敏感信息
设置适当的日志级别
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

📄 Source: CodeRabbit Inference Engine (.cursor/rules/error-logging.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/main/presenter/llmProviderPresenter/providers/*.ts`: Each file in `src/main...

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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.
Provider implementations must use a standardized interface in their coreStream method to yield events, decoupling the main Agent loop from provider-specific details.
The coreStream method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.
Provider files must implement the coreStream(messages, modelId, temperature, maxTokens) method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.
Provider files should include provider-specific helper functions such as formatMessages, convertToProviderTools, parseFunctionCalls, and prepareFunctionCallPrompt as needed.

📄 Source: CodeRabbit Inference Engine (.cursor/rules/llm-agent-loop.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
`src/main/**`: 主进程代码放在 `src/main`

src/main/**: 主进程代码放在 src/main

📄 Source: CodeRabbit Inference Engine (.cursor/rules/project-structure.mdc)

List of files the instruction was applied to:

  • src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts
🧠 Learnings (2)
📓 Common learnings 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Ensure that adding a new Provider only requires implementing the `coreStream` method according to the standardized interface, without duplicating Agent loop logic.
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (10) 
Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files must implement the `coreStream(messages, modelId, temperature, maxTokens)` method, which receives formatted messages and generation parameters, handles tool support (native or via prompt wrapping), makes a single streaming API call, parses provider-specific data, and yields standardized stream events.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider files should include provider-specific helper functions such as `formatMessages`, `convertToProviderTools`, `parseFunctionCalls`, and `prepareFunctionCallPrompt` as needed.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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, management of native/non-native tool call mechanisms (prompt wrapping), and standardizing output streams to a common event format.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : Provider implementations must use a standardized interface in their `coreStream` method to `yield` events, decoupling the main Agent loop from provider-specific details.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/index.ts : The main Agent loop, including the `while` loop for conversation flow, state management, provider interaction, event handling, and frontend communication, must be implemented in `src/main/presenter/llmProviderPresenter/index.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
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 communication with the frontend via `eventBus`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/providers/*.ts : The `coreStream` method in each Provider must perform a single-pass streaming API request per conversation round and must not contain multi-round tool call loop logic.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Maintain separation of concerns by centralizing Agent loop logic in `index.ts` and keeping provider files focused on API interaction and event standardization.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/llm-agent-loop.mdc:0-0
Timestamp: 2025-06-30T12:24:03.541Z
Learning: Applies to src/main/presenter/llmProviderPresenter/streamEvents.ts : Define the standardized stream event interface (`LLMCoreStreamEvent`) in a shared location, such as `src/main/presenter/llmProviderPresenter/streamEvents.ts`.

Learnt from: CR
PR: ThinkInAIXYZ/deepchat#0
File: .cursor/rules/electron-best-practices.mdc:0-0
Timestamp: 2025-06-30T12:23:13.304Z
Learning: Applies to src/main/presenter/**/*.ts : Use context isolation for improved security
🪛 Biome (1.9.4)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts

[error] 13-15: This constructor is unnecessary.

Unsafe fix: Remove the unnecessary constructor.

(lint/complexity/noUselessConstructor)

⏰ Context from checks skipped due to timeout of 90000ms (1)
  • GitHub Check: build-check (x64)
🔇 Additional comments (7)
src/main/presenter/llmProviderPresenter/providers/_302AIProvider.ts (7)

1-4: Imports look appropriate for the provider implementation.

The imports correctly include all necessary types and the base class.

5-10: Interface definition provides good type safety.

The _302AIBalanceResponse interface properly defines the expected structure for the API response.

17-24: Appropriate delegation to OpenAI-compatible base class.

The completions method correctly delegates to the inherited openAICompletion method.

26-43: Proper prompt formatting for OpenAI-compatible API.

The method correctly formats the prompt as a user message and delegates to the base class implementation.

49-77: Well-implemented API key status check with proper security.

The method correctly uses HTTPS, validates the API key, handles errors appropriately, and formats the response properly.

83-107: Excellent error handling and quota validation.

The method properly handles different error types, provides meaningful error messages, and includes appropriate logging as required by the coding guidelines.

12-108: No missing coreStream – it’s inherited from OpenAICompatibleProvider.

The _302AIProvider extends OpenAICompatibleProvider, which already implements the standardized coreStream method (handling streaming requests, tool support, parsing, and yielding events). There is no need to re-declare or override it in this subclass unless you require provider-specific streaming logic.

Likely an incorrect or invalid review comment.

@coderabbitai coderabbitai bot mentioned this pull request Jul 24, 2025
Merged
@coderabbitai coderabbitai bot mentioned this pull request Aug 15, 2025
Merged
@coderabbitai coderabbitai bot mentioned this pull request Sep 4, 2025
Merged
@zerob13 zerob13 deleted the feature/302-provider-amount-api branch September 21, 2025 15:15
This was referenced Oct 13, 2025
Merged
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@coderabbitai coderabbitai[bot] coderabbitai[bot] left review comments

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@zerob13