mirror of
https://github.com/langbot-app/LangBot.git
synced 2025-11-25 03:15:06 +08:00
b6cdf18c1a
* feat: add comprehensive unit tests for pipeline stages * fix: deps install in ci * ci: use venv * ci: run run_tests.sh * fix: resolve circular import issues in pipeline tests Update all test files to use lazy imports via importlib.import_module() to avoid circular dependency errors. Fix mock_conversation fixture to properly mock list.copy() method. Changes: - Use lazy import pattern in all test files - Fix conftest.py fixture for conversation messages - Add integration test file for full import tests - Update documentation with known issues and workarounds Tests now successfully avoid circular import errors while maintaining full test coverage of pipeline stages. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * docs: add comprehensive testing summary Document implementation details, challenges, solutions, and future improvements for the pipeline unit test suite. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: rewrite unit tests to test actual pipeline stage code Rewrote unit tests to properly test real stage implementations instead of mock logic: - Test actual BanSessionCheckStage with 7 test cases (100% coverage) - Test actual RateLimit stage with 3 test cases (70% coverage) - Test actual PipelineManager with 5 test cases - Use lazy imports via import_module to avoid circular dependencies - Import pipelinemgr first to ensure proper stage registration - Use Query.model_construct() to bypass Pydantic validation in tests - Remove obsolete pure unit tests that didn't test real code - All 20 tests passing with 48% overall pipeline coverage 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * test: add unit tests for GroupRespondRuleCheckStage Added comprehensive unit tests for resprule stage: - Test person message skips rule check - Test group message with no matching rules (INTERRUPT) - Test group message with matching rule (CONTINUE) - Test AtBotRule removes At component correctly - Test AtBotRule when no At component present Coverage: 100% on resprule.py and atbot.py All 25 tests passing with 51% overall pipeline coverage 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: restructure tests to tests/unit_tests/pipeline Reorganized test directory structure to support multiple test categories: - Move tests/pipeline → tests/unit_tests/pipeline - Rename .github/workflows/pipeline-tests.yml → run-tests.yml - Update run_tests.sh to run all unit tests (not just pipeline) - Update workflow to trigger on all pkg/** and tests/** changes - Coverage now tracks entire pkg/ module instead of just pipeline This structure allows for easy addition of more unit tests for other modules in the future. All 25 tests passing with 21% overall pkg coverage. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * ci: upload codecov report * ci: codecov file * ci: coverage.xml --------- Co-authored-by: Claude <noreply@anthropic.com>
LangBot is an open-source LLM native instant messaging robot development platform, aiming to provide out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, adapting to global instant messaging platforms, and providing rich API interfaces, supporting custom development.
📦 Getting Started
Docker Compose Deployment
git clone https://github.com/langbot-app/LangBot
cd LangBot/docker
docker compose up -d
Visit http://localhost:5300 to start using it.
Detailed documentation Docker Deployment.
One-click Deployment on BTPanel
LangBot has been listed on the BTPanel, if you have installed the BTPanel, you can use the document to use it.
Zeabur Cloud Deployment
Community contributed Zeabur template.
Railway Cloud Deployment
Other Deployment Methods
Directly use the released version to run, see the Manual Deployment documentation.
😎 Stay Ahead
Click the Star and Watch button in the upper right corner of the repository to get the latest updates.
✨ Features
- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, multi-modal, and streaming output capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with Dify.
- 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic MCP protocol; Currently has hundreds of plugins.
- 😻 Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.
For more detailed specifications, please refer to the documentation.
Or visit the demo environment: https://demo.langbot.dev/
- Login information: Email:
demo@langbot.appPassword:langbot123456 - Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.
Message Platform
| Platform | Status | Remarks |
|---|---|---|
| Discord | ✅ | |
| Telegram | ✅ | |
| Slack | ✅ | |
| LINE | ✅ | |
| Personal QQ | ✅ | |
| QQ Official API | ✅ | |
| WeCom | ✅ | |
| WeComCS | ✅ | |
| WeCom AI Bot | ✅ | |
| Personal WeChat | ✅ | |
| Lark | ✅ | |
| DingTalk | ✅ |
LLMs
| LLM | Status | Remarks |
|---|---|---|
| OpenAI | ✅ | Available for any OpenAI interface format model |
| DeepSeek | ✅ | |
| Moonshot | ✅ | |
| Anthropic | ✅ | |
| xAI | ✅ | |
| Zhipu AI | ✅ | |
| CompShare | ✅ | LLM and GPU resource platform |
| Dify | ✅ | LLMOps platform |
| PPIO | ✅ | LLM and GPU resource platform |
| ShengSuanYun | ✅ | LLM and GPU resource platform |
| 302.AI | ✅ | LLM gateway(MaaS) |
| Google Gemini | ✅ | |
| Ollama | ✅ | Local LLM running platform |
| LMStudio | ✅ | Local LLM running platform |
| GiteeAI | ✅ | LLM interface gateway(MaaS) |
| SiliconFlow | ✅ | LLM gateway(MaaS) |
| Aliyun Bailian | ✅ | LLM gateway(MaaS), LLMOps platform |
| Volc Engine Ark | ✅ | LLM gateway(MaaS), LLMOps platform |
| ModelScope | ✅ | LLM gateway(MaaS) |
| MCP | ✅ | Support tool access through MCP protocol |
🤝 Community Contribution
Thank you for the following code contributors and other members in the community for their contributions to LangBot: