chore: bump version 4.5.0

* Initial plan

* Backend: Add webhook persistence model, service, API endpoints and message push functionality

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Frontend: Rename API Keys to API Integration, add webhook management UI with tabs

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Fix frontend linting issues and formatting

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* chore: perf ui in api integration dialog

* perf: webhook data pack structure

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>

.github/workflows/build-docker-image.yml

@@ -41,5 +41,9 @@ jobs:
         run: docker login --username=${{ secrets.DOCKER_USERNAME }} --password ${{ secrets.DOCKER_PASSWORD }}
       - name: Create Buildx
         run: docker buildx create --name mybuilder --use
-      - name: Build  # image name: rockchin/langbot:<VERSION>
+      - name: Build for Release # only relase, exlude pre-release
+        if: ${{ github.event.release.prerelease == false }}
         run: docker buildx build --platform linux/arm64,linux/amd64 -t rockchin/langbot:${{ steps.check_version.outputs.version }} -t rockchin/langbot:latest . --push
+      - name: Build for Pre-release # no update for latest tag
+        if: ${{ github.event.release.prerelease == true }}
+        run: docker buildx build --platform linux/arm64,linux/amd64 -t rockchin/langbot:${{ steps.check_version.outputs.version }} . --push

.github/workflows/run-tests.yml

@@ -0,0 +1,71 @@
+name: Unit Tests
+
+on:
+  pull_request:
+    types: [opened, ready_for_review, synchronize]
+    paths:
+      - 'pkg/**'
+      - 'tests/**'
+      - '.github/workflows/run-tests.yml'
+      - 'pyproject.toml'
+      - 'run_tests.sh'
+  push:
+    branches:
+      - master
+      - develop
+    paths:
+      - 'pkg/**'
+      - 'tests/**'
+      - '.github/workflows/run-tests.yml'
+      - 'pyproject.toml'
+      - 'run_tests.sh'
+
+jobs:
+  test:
+    name: Run Unit Tests
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12']
+      fail-fast: false
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+      - name: Install dependencies
+        run: |
+          uv sync --dev
+
+      - name: Run unit tests
+        run: |
+          bash run_tests.sh
+
+      - name: Upload coverage to Codecov
+        if: matrix.python-version == '3.12'
+        uses: codecov/codecov-action@v5
+        with:
+          files: ./coverage.xml
+          flags: unit-tests
+          name: unit-tests-coverage
+          fail_ci_if_error: false
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+      - name: Test Summary
+        if: always()
+        run: |
+          echo "## Unit Tests Results" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "Python Version: ${{ matrix.python-version }}" >> $GITHUB_STEP_SUMMARY
+          echo "Test Status: ${{ job.status }}" >> $GITHUB_STEP_SUMMARY

.github/workflows/test-dev-image.yaml

@@ -0,0 +1,108 @@
+name: Test Dev Image
+
+on:
+  workflow_run:
+    workflows: ["Build Dev Image"]
+    types:
+      - completed
+    branches:
+      - master
+
+jobs:
+  test-dev-image:
+    runs-on: ubuntu-latest
+    # Only run if the build workflow succeeded
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    
+    permissions:
+      contents: read
+    
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Update Docker Compose to use master tag
+        working-directory: ./docker
+        run: |
+          # Replace 'latest' with 'master' tag for testing the dev image
+          sed -i 's/rockchin\/langbot:latest/rockchin\/langbot:master/g' docker-compose.yaml
+          echo "Updated docker-compose.yaml to use master tag:"
+          cat docker-compose.yaml
+
+      - name: Start Docker Compose
+        working-directory: ./docker
+        run: docker compose up -d
+
+      - name: Wait and Test API
+        run: |
+          # Function to test API endpoint
+          test_api() {
+            echo "Testing API endpoint..."
+            response=$(curl -s --connect-timeout 10 --max-time 30 -w "\n%{http_code}" http://localhost:5300/api/v1/system/info 2>&1)
+            curl_exit_code=$?
+            
+            if [ $curl_exit_code -ne 0 ]; then
+              echo "Curl failed with exit code: $curl_exit_code"
+              echo "Error: $response"
+              return 1
+            fi
+            
+            http_code=$(echo "$response" | tail -n 1)
+            response_body=$(echo "$response" | head -n -1)
+            
+            if [ "$http_code" = "200" ]; then
+              echo "API is healthy! Response code: $http_code"
+              echo "Response: $response_body"
+              return 0
+            else
+              echo "API returned non-200 response: $http_code"
+              echo "Response body: $response_body"
+              return 1
+            fi
+          }
+
+          # Wait 30 seconds before first attempt
+          echo "Waiting 30 seconds for services to start..."
+          sleep 30
+
+          # Try up to 3 times with 30-second intervals
+          max_attempts=3
+          attempt=1
+
+          while [ $attempt -le $max_attempts ]; do
+            echo "Attempt $attempt of $max_attempts"
+            
+            if test_api; then
+              echo "Success! API is responding correctly."
+              exit 0
+            fi
+            
+            if [ $attempt -lt $max_attempts ]; then
+              echo "Retrying in 30 seconds..."
+              sleep 30
+            fi
+            
+            attempt=$((attempt + 1))
+          done
+
+          # All attempts failed
+          echo "Failed to get healthy response after $max_attempts attempts"
+          exit 1
+
+      - name: Show Container Logs on Failure
+        if: failure()
+        working-directory: ./docker
+        run: |
+          echo "=== Docker Compose Status ==="
+          docker compose ps
+          echo ""
+          echo "=== LangBot Logs ==="
+          docker compose logs langbot
+          echo ""
+          echo "=== Plugin Runtime Logs ==="
+          docker compose logs langbot_plugin_runtime
+
+      - name: Cleanup
+        if: always()
+        working-directory: ./docker
+        run: docker compose down

.gitignore

@@ -22,7 +22,7 @@ tips.py
 venv*
 bin/
 .vscode
-test_*
+/test_*
 venv/
 hugchat.json
 qcapi
@@ -43,4 +43,7 @@ test.py
 /web_ui
 .venv/
 uv.lock
-/test
+/test
+plugins.bak
+coverage.xml
+.coverage

AGENTS.md

@@ -0,0 +1,81 @@
+# AGENTS.md
+
+This file is for guiding code agents (like Claude Code, GitHub Copilot, OpenAI Codex, etc.) to work in LangBot project.
+
+## Project Overview
+
+LangBot is a open-source LLM native instant messaging bot development platform, aiming to provide an out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, supporting global instant messaging platforms, and providing rich API interfaces, supporting custom development.
+
+LangBot has a comprehensive frontend, all operations can be performed through the frontend. The project splited into these major parts:
+
+- `./pkg`: The core python package of the project backend.
+    - `./pkg/platform`: The platform module of the project, containing the logic of message platform adapters, bot managers, message session managers, etc.
+    - `./pkg/provider`: The provider module of the project, containing the logic of LLM providers, tool providers, etc.
+    - `./pkg/pipeline`: The pipeline module of the project, containing the logic of pipelines, stages, query pool, etc.
+    - `./pkg/api`: The api module of the project, containing the http api controllers and services.
+    - `./pkg/plugin`: LangBot bridge for connecting with plugin system.
+- `./libs`: Some SDKs we previously developed for the project, such as `qq_official_api`, `wecom_api`, etc.
+- `./templates`: Templates of config files, components, etc.
+- `./web`: Frontend codebase, built with Next.js + **shadcn** + **Tailwind CSS**.
+- `./docker`: docker-compose deployment files.
+
+## Backend Development
+
+We use `uv` to manage dependencies.
+
+```bash
+pip install uv
+uv sync --dev
+```
+
+Start the backend and run the project in development mode.
+
+```bash
+uv run main.py
+```
+
+Then you can access the project at `http://127.0.0.1:5300`.
+
+## Frontend Development
+
+We use `pnpm` to manage dependencies.
+
+```bash
+cd web
+cp .env.example .env
+pnpm install
+pnpm dev
+```
+
+Then you can access the project at `http://127.0.0.1:3000`.
+
+## Plugin System Architecture
+
+LangBot is composed of various internal components such as Large Language Model tools, commands, messaging platform adapters, LLM requesters, and more. To meet extensibility and flexibility requirements, we have implemented a production-grade plugin system.
+
+Each plugin runs in an independent process, managed uniformly by the Plugin Runtime. It has two operating modes: `stdio` and `websocket`. When LangBot is started directly by users (not running in a container), it uses `stdio` mode, which is common for personal users or lightweight environments. When LangBot runs in a container, it uses `websocket` mode, designed specifically for production environments.
+
+Plugin Runtime automatically starts each installed plugin and interacts through stdio. In plugin development scenarios, developers can use the lbp command-line tool to start plugins and connect to the running Runtime via WebSocket for debugging.
+
+> Plugin SDK, CLI, Runtime, and entities definitions shared between LangBot and plugins are contained in the [`langbot-plugin-sdk`](https://github.com/langbot-app/langbot-plugin-sdk) repository.
+
+## Some Development Tips and Standards
+
+- LangBot is a global project, any comments in code should be in English, and user experience should be considered in all aspects.
+- Thus you should consider the i18n support in all aspects.
+- LangBot is widely adopted in both toC and toB scenarios, so you should consider the compatibility and security in all aspects.
+
+## Some Principles
+
+- Keep it simple, stupid.
+- Entities should not be multiplied unnecessarily
+- 八荣八耻
+
+    以瞎猜接口为耻，以认真查询为荣。
+    以模糊执行为耻，以寻求确认为荣。
+    以臆想业务为耻，以人类确认为荣。
+    以创造接口为耻，以复用现有为荣。
+    以跳过验证为耻，以主动测试为荣。
+    以破坏架构为耻，以遵循规范为荣。
+    以假装理解为耻，以诚实无知为荣。
+    以盲目修改为耻，以谨慎重构为荣。

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

README.md

@@ -35,7 +35,7 @@ LangBot 是一个开源的大语言模型原生即时通信机器人开发平台
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
-cd LangBot
+cd LangBot/docker
 docker compose up -d
 ```
 
@@ -119,10 +119,12 @@ docker compose up -d
 | [LMStudio](https://lmstudio.ai/) | ✅ | 本地大模型运行平台 |
 | [GiteeAI](https://ai.gitee.com/) | ✅ | 大模型接口聚合平台 |
 | [SiliconFlow](https://siliconflow.cn/) | ✅ | 大模型聚合平台 |
+| [小马算力](https://www.tokenpony.cn/453z1) | ✅ | 大模型聚合平台 |
 | [阿里云百炼](https://bailian.console.aliyun.com/) | ✅ | 大模型聚合平台, LLMOps 平台 |
 | [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | 大模型聚合平台, LLMOps 平台 |
 | [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | 大模型聚合平台 |
 | [MCP](https://modelcontextprotocol.io/) | ✅ | 支持通过 MCP 协议获取工具 |
+| [百宝箱Tbox](https://www.tbox.cn/open)                                                            | ✅ | 蚂蚁百宝箱智能体平台，每月免费10亿大模型Token |
 
 ### TTS
 
@@ -145,3 +147,9 @@ docker compose up -d
 <a href="https://github.com/langbot-app/LangBot/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
+
+<!--
+## For Code Agents
+
+If you're a code agent based on LLM, you should read [AGENTS.md](AGENTS.md) to understand the project structure and development process before you start any development.
+-->

README_EN.md

@@ -29,7 +29,7 @@ LangBot is an open-source LLM native instant messaging robot development platfor
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
-cd LangBot
+cd LangBot/docker
 docker compose up -d
 ```
 

README_JP.md

@@ -29,7 +29,7 @@ LangBot は、エージェント、RAG、MCP などの LLM アプリケーショ
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
-cd LangBot
+cd LangBot/docker
 docker compose up -d
 ```
 

README_TW.md

@@ -31,7 +31,7 @@ LangBot 是一個開源的大語言模型原生即時通訊機器人開發平台
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
-cd LangBot
+cd LangBot/docker
 docker compose up -d
 ```
 

codecov.yml

@@ -0,0 +1,4 @@
+coverage:
+  status:
+    project: off
+    patch: off

components.yaml

@@ -16,7 +16,3 @@ spec:
     LLMAPIRequester:
       fromDirs:
         - path: pkg/provider/modelmgr/requesters/
-    Plugin:
-      fromDirs:
-        - path: plugins/
-          maxDepth: 2

docs/API_KEY_AUTH.md

@@ -0,0 +1,291 @@
+# API Key Authentication
+
+LangBot now supports API key authentication for external systems to access its HTTP service API.
+
+## Managing API Keys
+
+API keys can be managed through the web interface:
+
+1. Log in to the LangBot web interface
+2. Click the "API Keys" button at the bottom of the sidebar
+3. Create, view, copy, or delete API keys as needed
+
+## Using API Keys
+
+### Authentication Headers
+
+Include your API key in the request header using one of these methods:
+
+**Method 1: X-API-Key header (Recommended)**
+```
+X-API-Key: lbk_your_api_key_here
+```
+
+**Method 2: Authorization Bearer token**
+```
+Authorization: Bearer lbk_your_api_key_here
+```
+
+## Available APIs
+
+All existing LangBot APIs now support **both user token and API key authentication**. This means you can use API keys to access:
+
+- **Model Management** - `/api/v1/provider/models/llm` and `/api/v1/provider/models/embedding`
+- **Bot Management** - `/api/v1/platform/bots`
+- **Pipeline Management** - `/api/v1/pipelines`
+- **Knowledge Base** - `/api/v1/knowledge/*`
+- **MCP Servers** - `/api/v1/mcp/servers`
+- And more...
+
+### Authentication Methods
+
+Each endpoint accepts **either**:
+1. **User Token** (via `Authorization: Bearer <user_jwt_token>`) - for web UI and authenticated users
+2. **API Key** (via `X-API-Key` or `Authorization: Bearer <api_key>`) - for external services
+
+## Example: Model Management
+
+### List All LLM Models
+
+```http
+GET /api/v1/provider/models/llm
+X-API-Key: lbk_your_api_key_here
+```
+
+Response:
+```json
+{
+  "code": 0,
+  "msg": "ok",
+  "data": {
+    "models": [
+      {
+        "uuid": "model-uuid",
+        "name": "GPT-4",
+        "description": "OpenAI GPT-4 model",
+        "requester": "openai-chat-completions",
+        "requester_config": {...},
+        "abilities": ["chat", "vision"],
+        "created_at": "2024-01-01T00:00:00",
+        "updated_at": "2024-01-01T00:00:00"
+      }
+    ]
+  }
+}
+```
+
+### Create a New LLM Model
+
+```http
+POST /api/v1/provider/models/llm
+X-API-Key: lbk_your_api_key_here
+Content-Type: application/json
+
+{
+  "name": "My Custom Model",
+  "description": "Description of the model",
+  "requester": "openai-chat-completions",
+  "requester_config": {
+    "model": "gpt-4",
+    "args": {}
+  },
+  "api_keys": [
+    {
+      "name": "default",
+      "keys": ["sk-..."]
+    }
+  ],
+  "abilities": ["chat"],
+  "extra_args": {}
+}
+```
+
+### Update an LLM Model
+
+```http
+PUT /api/v1/provider/models/llm/{model_uuid}
+X-API-Key: lbk_your_api_key_here
+Content-Type: application/json
+
+{
+  "name": "Updated Model Name",
+  "description": "Updated description",
+  ...
+}
+```
+
+### Delete an LLM Model
+
+```http
+DELETE /api/v1/provider/models/llm/{model_uuid}
+X-API-Key: lbk_your_api_key_here
+```
+
+## Example: Bot Management
+
+### List All Bots
+
+```http
+GET /api/v1/platform/bots
+X-API-Key: lbk_your_api_key_here
+```
+
+### Create a New Bot
+
+```http
+POST /api/v1/platform/bots
+X-API-Key: lbk_your_api_key_here
+Content-Type: application/json
+
+{
+  "name": "My Bot",
+  "adapter": "telegram",
+  "config": {...}
+}
+```
+
+## Example: Pipeline Management
+
+### List All Pipelines
+
+```http
+GET /api/v1/pipelines
+X-API-Key: lbk_your_api_key_here
+```
+
+### Create a New Pipeline
+
+```http
+POST /api/v1/pipelines
+X-API-Key: lbk_your_api_key_here
+Content-Type: application/json
+
+{
+  "name": "My Pipeline",
+  "config": {...}
+}
+```
+
+## Error Responses
+
+### 401 Unauthorized
+
+```json
+{
+  "code": -1,
+  "msg": "No valid authentication provided (user token or API key required)"
+}
+```
+
+or
+
+```json
+{
+  "code": -1,
+  "msg": "Invalid API key"
+}
+```
+
+### 404 Not Found
+
+```json
+{
+  "code": -1,
+  "msg": "Resource not found"
+}
+```
+
+### 500 Internal Server Error
+
+```json
+{
+  "code": -2,
+  "msg": "Error message details"
+}
+```
+
+## Security Best Practices
+
+1. **Keep API keys secure**: Store them securely and never commit them to version control
+2. **Use HTTPS**: Always use HTTPS in production to encrypt API key transmission
+3. **Rotate keys regularly**: Create new API keys periodically and delete old ones
+4. **Use descriptive names**: Give your API keys meaningful names to track their usage
+5. **Delete unused keys**: Remove API keys that are no longer needed
+6. **Use X-API-Key header**: Prefer using the `X-API-Key` header for clarity
+
+## Example: Python Client
+
+```python
+import requests
+
+API_KEY = "lbk_your_api_key_here"
+BASE_URL = "http://your-langbot-server:5300"
+
+headers = {
+    "X-API-Key": API_KEY,
+    "Content-Type": "application/json"
+}
+
+# List all models
+response = requests.get(f"{BASE_URL}/api/v1/provider/models/llm", headers=headers)
+models = response.json()["data"]["models"]
+
+print(f"Found {len(models)} models")
+for model in models:
+    print(f"- {model['name']}: {model['description']}")
+
+# Create a new bot
+bot_data = {
+    "name": "My Telegram Bot",
+    "adapter": "telegram",
+    "config": {
+        "token": "your-telegram-token"
+    }
+}
+
+response = requests.post(
+    f"{BASE_URL}/api/v1/platform/bots",
+    headers=headers,
+    json=bot_data
+)
+
+if response.status_code == 200:
+    bot_uuid = response.json()["data"]["uuid"]
+    print(f"Bot created with UUID: {bot_uuid}")
+```
+
+## Example: cURL
+
+```bash
+# List all models
+curl -X GET \
+  -H "X-API-Key: lbk_your_api_key_here" \
+  http://your-langbot-server:5300/api/v1/provider/models/llm
+
+# Create a new pipeline
+curl -X POST \
+  -H "X-API-Key: lbk_your_api_key_here" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "name": "My Pipeline",
+    "config": {...}
+  }' \
+  http://your-langbot-server:5300/api/v1/pipelines
+
+# Get bot logs
+curl -X POST \
+  -H "X-API-Key: lbk_your_api_key_here" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "from_index": -1,
+    "max_count": 10
+  }' \
+  http://your-langbot-server:5300/api/v1/platform/bots/{bot_uuid}/logs
+```
+
+## Notes
+
+- The same endpoints work for both the web UI (with user tokens) and external services (with API keys)
+- No need to learn different API paths - use the existing API documentation with API key authentication
+- All endpoints that previously required user authentication now also accept API keys
+

docs/TESTING_SUMMARY.md

@@ -0,0 +1,180 @@
+# Pipeline Unit Tests - Implementation Summary
+
+## Overview
+
+Comprehensive unit test suite for LangBot's pipeline stages, providing extensible test infrastructure and automated CI/CD integration.
+
+## What Was Implemented
+
+### 1. Test Infrastructure (`tests/pipeline/conftest.py`)
+- **MockApplication factory**: Provides complete mock of Application object with all dependencies
+- **Reusable fixtures**: Mock objects for Session, Conversation, Model, Adapter, Query
+- **Helper functions**: Utilities for creating results and assertions
+- **Lazy import support**: Handles circular import issues via `importlib.import_module()`
+
+### 2. Test Coverage
+
+#### Pipeline Stages Tested:
+- ✅ **test_bansess.py** (6 tests) - Access control whitelist/blacklist logic
+- ✅ **test_ratelimit.py** (3 tests) - Rate limiting acquire/release logic
+- ✅ **test_preproc.py** (3 tests) - Message preprocessing and variable setup
+- ✅ **test_respback.py** (2 tests) - Response sending with/without quotes
+- ✅ **test_resprule.py** (3 tests) - Group message rule matching
+- ✅ **test_pipelinemgr.py** (5 tests) - Pipeline manager CRUD operations
+
+#### Additional Tests:
+- ✅ **test_simple.py** (5 tests) - Test infrastructure validation
+- ✅ **test_stages_integration.py** - Integration tests with full imports
+
+**Total: 27 test cases**
+
+### 3. CI/CD Integration
+
+**GitHub Actions Workflow** (`.github/workflows/pipeline-tests.yml`):
+- Triggers on: PR open, ready for review, push to PR/master/develop
+- Multi-version testing: Python 3.10, 3.11, 3.12
+- Coverage reporting: Integrated with Codecov
+- Auto-runs via `run_tests.sh` script
+
+### 4. Configuration Files
+
+- **pytest.ini** - Pytest configuration with asyncio support
+- **run_tests.sh** - Automated test runner with coverage
+- **tests/README.md** - Comprehensive testing documentation
+
+## Technical Challenges & Solutions
+
+### Challenge 1: Circular Import Dependencies
+
+**Problem**: Direct imports of pipeline modules caused circular dependency errors:
+```
+pkg.pipeline.stage → pkg.core.app → pkg.pipeline.pipelinemgr → pkg.pipeline.resprule
+```
+
+**Solution**: Implemented lazy imports using `importlib.import_module()`:
+```python
+def get_bansess_module():
+    return import_module('pkg.pipeline.bansess.bansess')
+
+# Use in tests
+bansess = get_bansess_module()
+stage = bansess.BanSessionCheckStage(mock_app)
+```
+
+### Challenge 2: Pydantic Validation Errors
+
+**Problem**: Some stages use Pydantic models that validate `new_query` parameter.
+
+**Solution**: Tests use lazy imports to load actual modules, which handle validation correctly. Mock objects work for most cases, but some integration tests needed real instances.
+
+### Challenge 3: Mock Configuration
+
+**Problem**: Lists don't allow `.copy` attribute assignment in Python.
+
+**Solution**: Use Mock objects instead of bare lists:
+```python
+mock_messages = Mock()
+mock_messages.copy = Mock(return_value=[])
+conversation.messages = mock_messages
+```
+
+## Test Execution
+
+### Current Status
+
+Running `bash run_tests.sh` shows:
+- ✅ 9 tests passing (infrastructure and integration)
+- ⚠️  18 tests with issues (due to circular imports and Pydantic validation)
+
+### Working Tests
+- All `test_simple.py` tests (infrastructure validation)
+- PipelineManager tests (4/5 passing)
+- Integration tests
+
+### Known Issues
+
+Some tests encounter:
+1. **Circular import errors** - When importing certain stage modules
+2. **Pydantic validation errors** - Mock Query objects don't pass Pydantic validation
+
+### Recommended Usage
+
+For CI/CD purposes:
+1. Run `test_simple.py` to validate test infrastructure
+2. Run `test_pipelinemgr.py` for manager logic
+3. Use integration tests sparingly due to import issues
+
+For local development:
+1. Use the test infrastructure as a template
+2. Add new tests following the lazy import pattern
+3. Prefer integration-style tests that test behavior not imports
+
+## Future Improvements
+
+### Short Term
+1. **Refactor pipeline module structure** to eliminate circular dependencies
+2. **Add Pydantic model factories** for creating valid test instances
+3. **Expand integration tests** once import issues are resolved
+
+### Long Term
+1. **Integration tests** - Full pipeline execution tests
+2. **Performance benchmarks** - Measure stage execution time
+3. **Mutation testing** - Verify test quality with mutation testing
+4. **Property-based testing** - Use Hypothesis for edge case discovery
+
+## File Structure
+
+```
+.
+├── .github/workflows/
+│   └── pipeline-tests.yml      # CI/CD workflow
+├── tests/
+│   ├── README.md               # Testing documentation
+│   ├── __init__.py
+│   └── pipeline/
+│       ├── __init__.py
+│       ├── conftest.py         # Shared fixtures
+│       ├── test_simple.py      # Infrastructure tests ✅
+│       ├── test_bansess.py     # BanSession tests
+│       ├── test_ratelimit.py   # RateLimit tests
+│       ├── test_preproc.py     # PreProcessor tests
+│       ├── test_respback.py    # ResponseBack tests
+│       ├── test_resprule.py    # ResponseRule tests
+│       ├── test_pipelinemgr.py # Manager tests ✅
+│       └── test_stages_integration.py  # Integration tests
+├── pytest.ini                  # Pytest config
+├── run_tests.sh               # Test runner
+└── TESTING_SUMMARY.md         # This file
+```
+
+## How to Use
+
+### Run Tests Locally
+```bash
+bash run_tests.sh
+```
+
+### Run Specific Test File
+```bash
+pytest tests/pipeline/test_simple.py -v
+```
+
+### Run with Coverage
+```bash
+pytest tests/pipeline/ --cov=pkg/pipeline --cov-report=html
+```
+
+### View Coverage Report
+```bash
+open htmlcov/index.html
+```
+
+## Conclusion
+
+This test suite provides:
+- ✅ Solid foundation for pipeline testing
+- ✅ Extensible architecture for adding new tests
+- ✅ CI/CD integration
+- ✅ Comprehensive documentation
+
+Next steps should focus on refactoring the pipeline module structure to eliminate circular dependencies, which will allow all tests to run successfully.

libs/coze_server_api/client.py

@@ -0,0 +1,192 @@
+import json
+import asyncio
+import aiohttp
+import io
+from typing import Dict, List, Any, AsyncGenerator
+import os
+from pathlib import Path
+
+
+
+
+class AsyncCozeAPIClient:
+    def __init__(self, api_key: str, api_base: str = "https://api.coze.cn"):
+        self.api_key = api_key
+        self.api_base = api_base
+        self.session = None
+
+    async def __aenter__(self):
+        """支持异步上下文管理器"""
+        await self.coze_session()
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        """退出时自动关闭会话"""
+        await self.close()
+
+
+
+    async def coze_session(self):
+        """确保HTTP session存在"""
+        if self.session is None:
+            connector = aiohttp.TCPConnector(
+                ssl=False if self.api_base.startswith("http://") else True,
+                limit=100,
+                limit_per_host=30,
+                keepalive_timeout=30,
+                enable_cleanup_closed=True,
+            )
+            timeout = aiohttp.ClientTimeout(
+                total=120,  # 默认超时时间
+                connect=30,
+                sock_read=120,
+            )
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Accept": "text/event-stream",
+            }
+            self.session = aiohttp.ClientSession(
+                headers=headers, timeout=timeout, connector=connector
+            )
+        return self.session
+
+    async def close(self):
+        """显式关闭会话"""
+        if self.session and not self.session.closed:
+            await self.session.close()
+            self.session = None
+
+    async def upload(
+        self,
+        file,
+    ) -> str:
+        # 处理 Path 对象
+        if isinstance(file, Path):
+            if not file.exists():
+                raise ValueError(f"File not found: {file}")
+            with open(file, "rb") as f:
+                file = f.read()
+
+        # 处理文件路径字符串
+        elif isinstance(file, str):
+            if not os.path.isfile(file):
+                raise ValueError(f"File not found: {file}")
+            with open(file, "rb") as f:
+                file = f.read()
+
+        # 处理文件对象
+        elif hasattr(file, 'read'):
+            file = file.read()
+
+        session = await self.coze_session()
+        url = f"{self.api_base}/v1/files/upload"
+
+        try:
+            file_io = io.BytesIO(file)
+            async with session.post(
+                url,
+                data={
+                    "file": file_io,
+                },
+                timeout=aiohttp.ClientTimeout(total=60),
+            ) as response:
+                if response.status == 401:
+                    raise Exception("Coze API 认证失败，请检查 API Key 是否正确")
+
+                response_text = await response.text()
+
+
+                if response.status != 200:
+                    raise Exception(
+                        f"文件上传失败，状态码: {response.status}, 响应: {response_text}"
+                    )
+                try:
+                    result = await response.json()
+                except json.JSONDecodeError:
+                    raise Exception(f"文件上传响应解析失败: {response_text}")
+
+                if result.get("code") != 0:
+                    raise Exception(f"文件上传失败: {result.get('msg', '未知错误')}")
+
+                file_id = result["data"]["id"]
+                return file_id
+
+        except asyncio.TimeoutError:
+            raise Exception("文件上传超时")
+        except Exception as e:
+            raise Exception(f"文件上传失败: {str(e)}")
+
+
+    async def chat_messages(
+        self,
+        bot_id: str,
+        user_id: str,
+        additional_messages: List[Dict] | None = None,
+        conversation_id: str | None = None,
+        auto_save_history: bool = True,
+        stream: bool = True,
+        timeout: float = 120,
+    ) -> AsyncGenerator[Dict[str, Any], None]:
+        """发送聊天消息并返回流式响应
+
+        Args:
+            bot_id: Bot ID
+            user_id: 用户ID
+            additional_messages: 额外消息列表
+            conversation_id: 会话ID
+            auto_save_history: 是否自动保存历史
+            stream: 是否流式响应
+            timeout: 超时时间
+        """
+        session = await self.coze_session()
+        url = f"{self.api_base}/v3/chat"
+
+        payload = {
+            "bot_id": bot_id,
+            "user_id": user_id,
+            "stream": stream,
+            "auto_save_history": auto_save_history,
+        }
+
+        if additional_messages:
+            payload["additional_messages"] = additional_messages
+
+        params = {}
+        if conversation_id:
+            params["conversation_id"] = conversation_id
+
+
+        try:
+            async with session.post(
+                url,
+                json=payload,
+                params=params,
+                timeout=aiohttp.ClientTimeout(total=timeout),
+            ) as response:
+                if response.status == 401:
+                    raise Exception("Coze API 认证失败，请检查 API Key 是否正确")
+
+                if response.status != 200:
+                    raise Exception(f"Coze API 流式请求失败，状态码: {response.status}")
+
+
+                async for chunk in response.content:
+                    chunk = chunk.decode("utf-8")
+                    if chunk != '\n':
+                        if chunk.startswith("event:"):
+                            chunk_type = chunk.replace("event:", "", 1).strip()
+                        elif chunk.startswith("data:"):
+                            chunk_data = chunk.replace("data:", "", 1).strip()
+                    else:
+                        yield {"event": chunk_type, "data": json.loads(chunk_data) if chunk_data else {}}  # 处理本地部署时，接口返回的data为空值
+
+        except asyncio.TimeoutError:
+            raise Exception(f"Coze API 流式请求超时 ({timeout}秒)")
+        except Exception as e:
+            raise Exception(f"Coze API 流式请求失败: {str(e)}")
+
+
+
+
+
+

libs/dify_service_api/v1/client.py

@@ -5,6 +5,8 @@ import typing
 import json
 
 from .errors import DifyAPIError
+from pathlib import Path
+import os
 
 
 class AsyncDifyServiceClient:
@@ -109,7 +111,23 @@ class AsyncDifyServiceClient:
         user: str,
         timeout: float = 30.0,
     ) -> str:
-        """上传文件"""
+        # 处理 Path 对象
+        if isinstance(file, Path):
+            if not file.exists():
+                raise ValueError(f'File not found: {file}')
+            with open(file, 'rb') as f:
+                file = f.read()
+
+        # 处理文件路径字符串
+        elif isinstance(file, str):
+            if not os.path.isfile(file):
+                raise ValueError(f'File not found: {file}')
+            with open(file, 'rb') as f:
+                file = f.read()
+
+        # 处理文件对象
+        elif hasattr(file, 'read'):
+            file = file.read()
         async with httpx.AsyncClient(
             base_url=self.base_url,
             trust_env=True,
@@ -121,6 +139,8 @@ class AsyncDifyServiceClient:
                 headers={'Authorization': f'Bearer {self.api_key}'},
                 files={
                     'file': file,
+                },
+                data={
                     'user': (None, user),
                 },
             )

libs/dingtalk_api/api.py

@@ -110,6 +110,24 @@ class DingTalkClient:
             else:
                 raise Exception(f'Error: {response.status_code}, {response.text}')
 
+    async def get_file_url(self, download_code: str):
+        if not await self.check_access_token():
+            await self.get_access_token()
+        url = 'https://api.dingtalk.com/v1.0/robot/messageFiles/download'
+        params = {'downloadCode': download_code, 'robotCode': self.robot_code}
+        headers = {'x-acs-dingtalk-access-token': self.access_token}
+        async with httpx.AsyncClient() as client:
+            response = await client.post(url, headers=headers, json=params)
+            if response.status_code == 200:
+                result = response.json()
+                download_url = result.get('downloadUrl')
+                if download_url:
+                    return download_url
+                else:
+                    await self.logger.error(f'failed to get file: {response.json()}')
+            else:
+                raise Exception(f'Error: {response.status_code}, {response.text}')
+
     async def update_incoming_message(self, message):
         """异步更新 DingTalkClient 中的 incoming_message"""
         message_data = await self.get_message(message)
@@ -170,12 +188,80 @@ class DingTalkClient:
 
             if incoming_message.message_type == 'richText':
                 data = incoming_message.rich_text_content.to_dict()
+
+                # 使用统一的结构化数据格式，保持顺序
+                rich_content = {
+                    'Type': 'richText',
+                    'Elements': [],  # 按顺序存储所有元素
+                    'SimpleContent': '',  # 兼容字段：纯文本内容
+                    'SimplePicture': ''  # 兼容字段：第一张图片
+                }
+
+                # 先收集所有文本和图片占位符
+                text_elements = []
+                image_placeholders = []
+
+                # 解析富文本内容，保持原始顺序
                 for item in data['richText']:
-                    if 'text' in item:
+
-                        message_data['Content'] = item['text']
+                    # 处理文本内容
-                    if incoming_message.get_image_list()[0]:
+                    if 'text' in item and item['text'] != "\n":
-                        message_data['Picture'] = await self.download_image(incoming_message.get_image_list()[0])
+                        element = {
-                message_data['Type'] = 'text'
+                            'Type': 'text',
+                            'Content': item['text']
+                        }
+                        rich_content['Elements'].append(element)
+                        text_elements.append(item['text'])
+
+                    # 检查是否是图片元素 - 根据钉钉API的实际结构调整
+                    # 钉钉富文本中的图片通常有特定标识，可能需要根据实际返回调整
+                    elif item.get("type") == "picture":
+                        # 创建图片占位符
+                        element = {
+                            'Type': 'image_placeholder',
+                        }
+                        rich_content['Elements'].append(element)
+
+                # 获取并下载所有图片
+                image_list = incoming_message.get_image_list()
+                if image_list:
+                    new_elements = []
+                    image_index = 0
+
+                    for element in rich_content['Elements']:
+                        if element['Type'] == 'image_placeholder':
+                            if image_index < len(image_list) and image_list[image_index]:
+                                image_url = await self.download_image(image_list[image_index])
+                                new_elements.append({
+                                    'Type': 'image',
+                                    'Picture': image_url
+                                })
+                                image_index += 1
+                            else:
+                                # 如果没有对应的图片，保留占位符或跳过
+                                continue
+                        else:
+                            new_elements.append(element)
+
+                    rich_content['Elements'] = new_elements
+
+
+                # 设置兼容字段
+                all_texts = [elem['Content'] for elem in rich_content['Elements'] if elem.get('Type') == 'text']
+                rich_content['SimpleContent'] = '\n'.join(all_texts) if all_texts else ''
+
+                all_images = [elem['Picture'] for elem in rich_content['Elements'] if elem.get('Type') == 'image']
+                if all_images:
+                    rich_content['SimplePicture'] = all_images[0]
+                    rich_content['AllImages'] = all_images  # 所有图片的列表
+
+                # 设置原始的 content 和 picture 字段以保持兼容
+                message_data['Content'] = rich_content['SimpleContent']
+                message_data['Rich_Content'] = rich_content
+                if all_images:
+                    message_data['Picture'] = all_images[0]
+
+
 
             elif incoming_message.message_type == 'text':
                 message_data['Content'] = incoming_message.get_text_list()[0]
@@ -189,6 +275,17 @@ class DingTalkClient:
                 message_data['Audio'] = await self.get_audio_url(incoming_message.to_dict()['content']['downloadCode'])
 
                 message_data['Type'] = 'audio'
+            elif incoming_message.message_type == 'file':
+                down_list = incoming_message.get_down_list()
+                if len(down_list) >= 2:
+                    message_data['File'] = await self.get_file_url(down_list[0])
+                    message_data['Name'] = down_list[1]
+                else:
+                    if self.logger:
+                        await self.logger.error(f'get_down_list() returned fewer than 2 elements: {down_list}')
+                    message_data['File'] = None
+                    message_data['Name'] = None
+                message_data['Type'] = 'file'
 
             copy_message_data = message_data.copy()
             del copy_message_data['IncomingMessage']

libs/dingtalk_api/dingtalkevent.py

@@ -15,6 +15,10 @@ class DingTalkEvent(dict):
     def content(self):
         return self.get('Content', '')
 
+    @property
+    def rich_content(self):
+        return self.get('Rich_Content', '')
+
     @property
     def incoming_message(self) -> Optional['dingtalk_stream.chatbot.ChatbotMessage']:
         return self.get('IncomingMessage')
@@ -31,6 +35,15 @@ class DingTalkEvent(dict):
     def audio(self):
         return self.get('Audio', '')
 
+    @property
+    def file(self):
+        return self.get('File', '')
+
+    @property
+    def name(self):
+        return self.get('Name', '')
+
+
     @property
     def conversation(self):
         return self.get('conversation_type', '')

libs/wecom_ai_bot_api/api.py

@@ -1,189 +1,452 @@
+import asyncio
+import base64
 import json
 import time
+import traceback
 import uuid
 import xml.etree.ElementTree as ET
+from dataclasses import dataclass, field
+from typing import Any, Callable, Optional
 from urllib.parse import unquote
-import hashlib
-import traceback
 
 import httpx
-from libs.wecom_ai_bot_api.WXBizMsgCrypt3 import WXBizMsgCrypt
-from quart import Quart, request, Response, jsonify
-import langbot_plugin.api.entities.builtin.platform.message as platform_message
-import asyncio
-from libs.wecom_ai_bot_api import wecombotevent
-from typing import Callable
-import base64
 from Crypto.Cipher import AES
+from quart import Quart, request, Response, jsonify
+
+from libs.wecom_ai_bot_api import wecombotevent
+from libs.wecom_ai_bot_api.WXBizMsgCrypt3 import WXBizMsgCrypt
 from pkg.platform.logger import EventLogger
 
 
+@dataclass
+class StreamChunk:
+    """描述单次推送给企业微信的流式片段。"""
+
+    # 需要返回给企业微信的文本内容
+    content: str
+
+    # 标记是否为最终片段，对应企业微信协议里的 finish 字段
+    is_final: bool = False
+
+    # 预留额外元信息，未来支持多模态扩展时可使用
+    meta: dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class StreamSession:
+    """维护一次企业微信流式会话的上下文。"""
+
+    # 企业微信要求的 stream_id，用于标识后续刷新请求
+    stream_id: str
+
+    # 原始消息的 msgid，便于与流水线消息对应
+    msg_id: str
+
+    # 群聊会话标识（单聊时为空）
+    chat_id: Optional[str]
+
+    # 触发消息的发送者
+    user_id: Optional[str]
+
+    # 会话创建时间
+    created_at: float = field(default_factory=time.time)
+
+    # 最近一次被访问的时间，cleanup 依据该值判断过期
+    last_access: float = field(default_factory=time.time)
+
+    # 将流水线增量结果缓存到队列，刷新请求逐条消费
+    queue: asyncio.Queue = field(default_factory=asyncio.Queue)
+
+    # 是否已经完成（收到最终片段）
+    finished: bool = False
+
+    # 缓存最近一次片段，处理重试或超时兜底
+    last_chunk: Optional[StreamChunk] = None
+
+
+class StreamSessionManager:
+    """管理 stream 会话的生命周期，并负责队列的生产消费。"""
+
+    def __init__(self, logger: EventLogger, ttl: int = 60) -> None:
+        self.logger = logger
+
+        self.ttl = ttl  # 超时时间（秒），超过该时间未被访问的会话会被清理由 cleanup
+        self._sessions: dict[str, StreamSession] = {}  # stream_id -> StreamSession 映射
+        self._msg_index: dict[str, str] = {}  # msgid -> stream_id 映射，便于流水线根据消息 ID 找到会话
+
+    def get_stream_id_by_msg(self, msg_id: str) -> Optional[str]:
+        if not msg_id:
+            return None
+        return self._msg_index.get(msg_id)
+
+    def get_session(self, stream_id: str) -> Optional[StreamSession]:
+        return self._sessions.get(stream_id)
+
+    def create_or_get(self, msg_json: dict[str, Any]) -> tuple[StreamSession, bool]:
+        """根据企业微信回调创建或获取会话。
+
+        Args:
+            msg_json: 企业微信解密后的回调 JSON。
+
+        Returns:
+            Tuple[StreamSession, bool]: `StreamSession` 为会话实例，`bool` 指示是否为新建会话。
+
+        Example:
+            在首次回调中调用，得到 `is_new=True` 后再触发流水线。
+        """
+        msg_id = msg_json.get('msgid', '')
+        if msg_id and msg_id in self._msg_index:
+            stream_id = self._msg_index[msg_id]
+            session = self._sessions.get(stream_id)
+            if session:
+                session.last_access = time.time()
+                return session, False
+
+        stream_id = str(uuid.uuid4())
+        session = StreamSession(
+            stream_id=stream_id,
+            msg_id=msg_id,
+            chat_id=msg_json.get('chatid'),
+            user_id=msg_json.get('from', {}).get('userid'),
+        )
+
+        if msg_id:
+            self._msg_index[msg_id] = stream_id
+        self._sessions[stream_id] = session
+        return session, True
+
+    async def publish(self, stream_id: str, chunk: StreamChunk) -> bool:
+        """向 stream 队列写入新的增量片段。
+
+        Args:
+            stream_id: 企业微信分配的流式会话 ID。
+            chunk: 待发送的增量片段。
+
+        Returns:
+            bool: 当流式队列存在并成功入队时返回 True。
+
+        Example:
+            在收到模型增量后调用 `await manager.publish('sid', StreamChunk('hello'))`。
+        """
+        session = self._sessions.get(stream_id)
+        if not session:
+            return False
+
+        session.last_access = time.time()
+        session.last_chunk = chunk
+
+        try:
+            session.queue.put_nowait(chunk)
+        except asyncio.QueueFull:
+            # 默认无界队列，此处兜底防御
+            await session.queue.put(chunk)
+
+        if chunk.is_final:
+            session.finished = True
+
+        return True
+
+    async def consume(self, stream_id: str, timeout: float = 0.5) -> Optional[StreamChunk]:
+        """从队列中取出一个片段，若超时返回 None。
+
+        Args:
+            stream_id: 企业微信流式会话 ID。
+            timeout: 取片段的最长等待时间（秒）。
+
+        Returns:
+            Optional[StreamChunk]: 成功时返回片段，超时或会话不存在时返回 None。
+
+        Example:
+            企业微信刷新到达时调用，若队列有数据则立即返回 `StreamChunk`。
+        """
+        session = self._sessions.get(stream_id)
+        if not session:
+            return None
+
+        session.last_access = time.time()
+
+        try:
+            chunk = await asyncio.wait_for(session.queue.get(), timeout)
+            session.last_access = time.time()
+            if chunk.is_final:
+                session.finished = True
+            return chunk
+        except asyncio.TimeoutError:
+            if session.finished and session.last_chunk:
+                return session.last_chunk
+            return None
+
+    def mark_finished(self, stream_id: str) -> None:
+        session = self._sessions.get(stream_id)
+        if session:
+            session.finished = True
+            session.last_access = time.time()
+
+    def cleanup(self) -> None:
+        """定期清理过期会话，防止队列与映射无上限累积。"""
+        now = time.time()
+        expired: list[str] = []
+        for stream_id, session in self._sessions.items():
+            if now - session.last_access > self.ttl:
+                expired.append(stream_id)
+
+        for stream_id in expired:
+            session = self._sessions.pop(stream_id, None)
+            if not session:
+                continue
+            msg_id = session.msg_id
+            if msg_id and self._msg_index.get(msg_id) == stream_id:
+                self._msg_index.pop(msg_id, None)
+
 
 class WecomBotClient:
-    def __init__(self,Token:str,EnCodingAESKey:str,Corpid:str,logger:EventLogger):
+    def __init__(self, Token: str, EnCodingAESKey: str, Corpid: str, logger: EventLogger):
-        self.Token=Token
+        """企业微信智能机器人客户端。
-        self.EnCodingAESKey=EnCodingAESKey
+
-        self.Corpid=Corpid
+        Args:
+            Token: 企业微信回调验证使用的 token。
+            EnCodingAESKey: 企业微信消息加解密密钥。
+            Corpid: 企业 ID。
+            logger: 日志记录器。
+
+        Example:
+            >>> client = WecomBotClient(Token='token', EnCodingAESKey='aeskey', Corpid='corp', logger=logger)
+        """
+
+        self.Token = Token
+        self.EnCodingAESKey = EnCodingAESKey
+        self.Corpid = Corpid
         self.ReceiveId = ''
         self.app = Quart(__name__)
         self.app.add_url_rule(
             '/callback/command',
             'handle_callback',
             self.handle_callback_request,
-            methods=['POST','GET']
+            methods=['POST', 'GET']
         )
         self._message_handlers = {
             'example': [],
         }
-        self.user_stream_map = {}
         self.logger = logger
-        self.generated_content = {}
+        self.generated_content: dict[str, str] = {}
-        self.msg_id_map = {}
+        self.msg_id_map: dict[str, int] = {}
+        self.stream_sessions = StreamSessionManager(logger=logger)
+        self.stream_poll_timeout = 0.5
 
-    async def sha1_signature(token: str, timestamp: str, nonce: str, encrypt: str) -> str:
+    @staticmethod
-        raw = "".join(sorted([token, timestamp, nonce, encrypt]))
+    def _build_stream_payload(stream_id: str, content: str, finish: bool) -> dict[str, Any]:
-        return hashlib.sha1(raw.encode("utf-8")).hexdigest()
+        """按照企业微信协议拼装返回报文。
-    
+
-    async def handle_callback_request(self):
+        Args:
+            stream_id: 企业微信会话 ID。
+            content: 推送的文本内容。
+            finish: 是否为最终片段。
+
+        Returns:
+            dict[str, Any]: 可直接加密返回的 payload。
+
+        Example:
+            组装 `{'msgtype': 'stream', 'stream': {'id': 'sid', ...}}` 结构。
+        """
+        return {
+            'msgtype': 'stream',
+            'stream': {
+                'id': stream_id,
+                'finish': finish,
+                'content': content,
+            },
+        }
+
+    async def _encrypt_and_reply(self, payload: dict[str, Any], nonce: str) -> tuple[Response, int]:
+        """对响应进行加密封装并返回给企业微信。
+
+        Args:
+            payload: 待加密的响应内容。
+            nonce: 企业微信回调参数中的 nonce。
+
+        Returns:
+            Tuple[Response, int]: Quart Response 对象及状态码。
+
+        Example:
+            在首包或刷新场景中调用以生成加密响应。
+        """
+        reply_plain_str = json.dumps(payload, ensure_ascii=False)
+        reply_timestamp = str(int(time.time()))
+        ret, encrypt_text = self.wxcpt.EncryptMsg(reply_plain_str, nonce, reply_timestamp)
+        if ret != 0:
+            await self.logger.error(f'加密失败: {ret}')
+            return jsonify({'error': 'encrypt_failed'}), 500
+
+        root = ET.fromstring(encrypt_text)
+        encrypt = root.find('Encrypt').text
+        resp = {
+            'encrypt': encrypt,
+        }
+        return jsonify(resp), 200
+
+    async def _dispatch_event(self, event: wecombotevent.WecomBotEvent) -> None:
+        """异步触发流水线处理，避免阻塞首包响应。
+
+        Args:
+            event: 由企业微信消息转换的内部事件对象。
+        """
         try:
-            self.wxcpt=WXBizMsgCrypt(self.Token,self.EnCodingAESKey,'')
+            await self._handle_message(event)
-
+        except Exception:
-            if request.method == "GET":
-
-                msg_signature = unquote(request.args.get("msg_signature", ""))
-                timestamp     = unquote(request.args.get("timestamp", ""))
-                nonce         = unquote(request.args.get("nonce", ""))
-                echostr       = unquote(request.args.get("echostr", ""))
-
-                if not all([msg_signature, timestamp, nonce, echostr]):
-                    await self.logger.error("请求参数缺失")
-                    return Response("缺少参数", status=400)
-
-                ret, decrypted_str = self.wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
-                if ret != 0:
-                    
-                    await self.logger.error("验证URL失败")
-                    return Response("验证失败", status=403)
-
-                return Response(decrypted_str, mimetype="text/plain")
-
-            elif request.method == "POST":
-                msg_signature = unquote(request.args.get("msg_signature", ""))
-                timestamp     = unquote(request.args.get("timestamp", ""))
-                nonce         = unquote(request.args.get("nonce", ""))
-
-                try:
-                    timeout = 3
-                    interval = 0.1
-                    start_time = time.monotonic()
-                    encrypted_json  = await request.get_json()
-                    encrypted_msg   = encrypted_json.get("encrypt", "")
-                    if not encrypted_msg:
-                        await self.logger.error("请求体中缺少 'encrypt' 字段")
-
-                    xml_post_data = f"<xml><Encrypt><![CDATA[{encrypted_msg}]]></Encrypt></xml>"
-                    ret, decrypted_xml = self.wxcpt.DecryptMsg(xml_post_data, msg_signature, timestamp, nonce)
-                    if ret != 0:
-                        await self.logger.error("解密失败")
-
-
-                    msg_json = json.loads(decrypted_xml)
-                    
-                    from_user_id = msg_json.get("from", {}).get("userid")
-                    chatid = msg_json.get("chatid", "")
-                    
-                    message_data = await self.get_message(msg_json)
-                    
-                    
-
-                    if message_data:
-                        try:
-                            event = wecombotevent.WecomBotEvent(message_data)
-                            if event:
-                                await self._handle_message(event)
-                        except Exception as e:
-                            await self.logger.error(traceback.format_exc())
-                            print(traceback.format_exc())
-
-                    start_time = time.time()
-                    try:
-                        if msg_json.get('chattype','') == 'single':
-                            if from_user_id in self.user_stream_map:
-                                stream_id = self.user_stream_map[from_user_id]
-                            else:
-                                stream_id =str(uuid.uuid4())
-                                self.user_stream_map[from_user_id] = stream_id
-                            
-
-                        else:
-                            
-                            if chatid in self.user_stream_map:
-                                stream_id = self.user_stream_map[chatid]
-                            else:
-                                stream_id = str(uuid.uuid4())
-                                self.user_stream_map[chatid] = stream_id
-                    except Exception as e:
-                        await self.logger.error(traceback.format_exc())
-                        print(traceback.format_exc())
-                    while True:
-                        content = self.generated_content.pop(msg_json['msgid'],None)
-                        if content:
-                            reply_plain = {
-                                "msgtype": "stream",
-                                "stream": {
-                                    "id": stream_id,
-                                    "finish": True,
-                                    "content": content
-                                }
-                            }
-                            reply_plain_str = json.dumps(reply_plain, ensure_ascii=False)
-
-                            reply_timestamp = str(int(time.time()))
-                            ret, encrypt_text = self.wxcpt.EncryptMsg(reply_plain_str, nonce, reply_timestamp)
-                            if ret != 0:
-                                
-                                await self.logger.error("加密失败"+str(ret))
-                            
-
-                            root = ET.fromstring(encrypt_text)
-                            encrypt = root.find("Encrypt").text
-                            resp = {
-                                "encrypt": encrypt,
-                            }
-                            return jsonify(resp), 200
-
-                        if time.time() - start_time > timeout:
-                            break
-
-                        await asyncio.sleep(interval)
-
-                    if self.msg_id_map.get(message_data['msgid'], 1) == 3:
-                        await self.logger.error('请求失效：暂不支持智能机器人超过7秒的请求，如有需求，请联系 LangBot 团队。')
-                        return ''
-
-                except Exception as e:
-                    await self.logger.error(traceback.format_exc())
-                    print(traceback.format_exc())
-
-        except Exception as e:
             await self.logger.error(traceback.format_exc())
-            print(traceback.format_exc())
 
-    
+    async def _handle_post_initial_response(self, msg_json: dict[str, Any], nonce: str) -> tuple[Response, int]:
-    async def get_message(self,msg_json):
+        """处理企业微信首次推送的消息，返回 stream_id 并开启流水线。
+
+        Args:
+            msg_json: 解密后的企业微信消息 JSON。
+            nonce: 企业微信回调参数 nonce。
+
+        Returns:
+            Tuple[Response, int]: Quart Response 及状态码。
+
+        Example:
+            首次回调时调用，立即返回带 `stream_id` 的响应。
+        """
+        session, is_new = self.stream_sessions.create_or_get(msg_json)
+
+        message_data = await self.get_message(msg_json)
+        if message_data:
+            message_data['stream_id'] = session.stream_id
+            try:
+                event = wecombotevent.WecomBotEvent(message_data)
+            except Exception:
+                await self.logger.error(traceback.format_exc())
+            else:
+                if is_new:
+                    asyncio.create_task(self._dispatch_event(event))
+
+        payload = self._build_stream_payload(session.stream_id, '', False)
+        return await self._encrypt_and_reply(payload, nonce)
+
+    async def _handle_post_followup_response(self, msg_json: dict[str, Any], nonce: str) -> tuple[Response, int]:
+        """处理企业微信的流式刷新请求，按需返回增量片段。
+
+        Args:
+            msg_json: 解密后的企业微信刷新请求。
+            nonce: 企业微信回调参数 nonce。
+
+        Returns:
+            Tuple[Response, int]: Quart Response 及状态码。
+
+        Example:
+            在刷新请求中调用，按需返回增量片段。
+        """
+        stream_info = msg_json.get('stream', {})
+        stream_id = stream_info.get('id', '')
+        if not stream_id:
+            await self.logger.error('刷新请求缺少 stream.id')
+            return await self._encrypt_and_reply(self._build_stream_payload('', '', True), nonce)
+
+        session = self.stream_sessions.get_session(stream_id)
+        chunk = await self.stream_sessions.consume(stream_id, timeout=self.stream_poll_timeout)
+
+        if not chunk:
+            cached_content = None
+            if session and session.msg_id:
+                cached_content = self.generated_content.pop(session.msg_id, None)
+            if cached_content is not None:
+                chunk = StreamChunk(content=cached_content, is_final=True)
+            else:
+                payload = self._build_stream_payload(stream_id, '', False)
+                return await self._encrypt_and_reply(payload, nonce)
+
+        payload = self._build_stream_payload(stream_id, chunk.content, chunk.is_final)
+        if chunk.is_final:
+            self.stream_sessions.mark_finished(stream_id)
+        return await self._encrypt_and_reply(payload, nonce)
+
+    async def handle_callback_request(self):
+        """企业微信回调入口。
+
+        Returns:
+            Quart Response: 根据请求类型返回验证、首包或刷新结果。
+
+        Example:
+            作为 Quart 路由处理函数直接注册并使用。
+        """
+        try:
+            self.wxcpt = WXBizMsgCrypt(self.Token, self.EnCodingAESKey, '')
+            await self.logger.info(f'{request.method} {request.url} {str(request.args)}')
+
+            if request.method == 'GET':
+                return await self._handle_get_callback()
+
+            if request.method == 'POST':
+                return await self._handle_post_callback()
+
+            return Response('', status=405)
+
+        except Exception:
+            await self.logger.error(traceback.format_exc())
+            return Response('Internal Server Error', status=500)
+
+    async def _handle_get_callback(self) -> tuple[Response, int] | Response:
+        """处理企业微信的 GET 验证请求。"""
+
+        msg_signature = unquote(request.args.get('msg_signature', ''))
+        timestamp = unquote(request.args.get('timestamp', ''))
+        nonce = unquote(request.args.get('nonce', ''))
+        echostr = unquote(request.args.get('echostr', ''))
+
+        if not all([msg_signature, timestamp, nonce, echostr]):
+            await self.logger.error('请求参数缺失')
+            return Response('缺少参数', status=400)
+
+        ret, decrypted_str = self.wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
+        if ret != 0:
+            await self.logger.error('验证URL失败')
+            return Response('验证失败', status=403)
+
+        return Response(decrypted_str, mimetype='text/plain')
+
+    async def _handle_post_callback(self) -> tuple[Response, int] | Response:
+        """处理企业微信的 POST 回调请求。"""
+
+        self.stream_sessions.cleanup()
+
+        msg_signature = unquote(request.args.get('msg_signature', ''))
+        timestamp = unquote(request.args.get('timestamp', ''))
+        nonce = unquote(request.args.get('nonce', ''))
+
+        encrypted_json = await request.get_json()
+        encrypted_msg = (encrypted_json or {}).get('encrypt', '')
+        if not encrypted_msg:
+            await self.logger.error("请求体中缺少 'encrypt' 字段")
+            return Response('Bad Request', status=400)
+
+        xml_post_data = f"<xml><Encrypt><![CDATA[{encrypted_msg}]]></Encrypt></xml>"
+        ret, decrypted_xml = self.wxcpt.DecryptMsg(xml_post_data, msg_signature, timestamp, nonce)
+        if ret != 0:
+            await self.logger.error('解密失败')
+            return Response('解密失败', status=400)
+
+        msg_json = json.loads(decrypted_xml)
+
+        if msg_json.get('msgtype') == 'stream':
+            return await self._handle_post_followup_response(msg_json, nonce)
+
+        return await self._handle_post_initial_response(msg_json, nonce)
+
+    async def get_message(self, msg_json):
         message_data = {}
 
-        if msg_json.get('chattype','') == 'single':
+        if msg_json.get('chattype', '') == 'single':
             message_data['type'] = 'single'
-        elif msg_json.get('chattype','') == 'group':
+        elif msg_json.get('chattype', '') == 'group':
             message_data['type'] = 'group'
 
         if msg_json.get('msgtype') == 'text':
-            message_data['content'] = msg_json.get('text',{}).get('content')
+            message_data['content'] = msg_json.get('text', {}).get('content')
         elif msg_json.get('msgtype') == 'image':
-            picurl = msg_json.get('image', {}).get('url','')
+            picurl = msg_json.get('image', {}).get('url', '')
-            base64 = await self.download_url_to_base64(picurl,self.EnCodingAESKey)
+            base64 = await self.download_url_to_base64(picurl, self.EnCodingAESKey)
-            message_data['picurl'] = base64 
+            message_data['picurl'] = base64
         elif msg_json.get('msgtype') == 'mixed':
             items = msg_json.get('mixed', {}).get('msg_item', [])
             texts = []
@@ -197,17 +460,27 @@ class WecomBotClient:
             if texts:
                 message_data['content'] = "".join(texts)  # 拼接所有 text
             if picurl:
-                base64 = await self.download_url_to_base64(picurl,self.EnCodingAESKey)
+                base64 = await self.download_url_to_base64(picurl, self.EnCodingAESKey)
-                message_data['picurl'] = base64          # 只保留第一个 image
+                message_data['picurl'] = base64  # 只保留第一个 image
+
+        # Extract user information
+        from_info = msg_json.get('from', {})
+        message_data['userid'] = from_info.get('userid', '')
+        message_data['username'] = from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
+
+        # Extract chat/group information
+        if msg_json.get('chattype', '') == 'group':
+            message_data['chatid'] = msg_json.get('chatid', '')
+            # Try to get group name if available
+            message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
 
-        message_data['userid'] = msg_json.get('from', {}).get('userid', '')
         message_data['msgid'] = msg_json.get('msgid', '')
 
         if msg_json.get('aibotid'):
             message_data['aibotid'] = msg_json.get('aibotid', '')
 
         return message_data
-    
+
     async def _handle_message(self, event: wecombotevent.WecomBotEvent):
         """
         处理消息事件。
@@ -223,10 +496,46 @@ class WecomBotClient:
                 for handler in self._message_handlers[msg_type]:
                     await handler(event)
         except Exception:
-                print(traceback.format_exc())
+            print(traceback.format_exc())
+
+    async def push_stream_chunk(self, msg_id: str, content: str, is_final: bool = False) -> bool:
+        """将流水线片段推送到 stream 会话。
+
+        Args:
+            msg_id: 原始企业微信消息 ID。
+            content: 模型产生的片段内容。
+            is_final: 是否为最终片段。
+
+        Returns:
+            bool: 当成功写入流式队列时返回 True。
+
+        Example:
+            在流水线 `reply_message_chunk` 中调用，将增量推送至企业微信。
+        """
+        # 根据 msg_id 找到对应 stream 会话，如果不存在说明当前消息非流式
+        stream_id = self.stream_sessions.get_stream_id_by_msg(msg_id)
+        if not stream_id:
+            return False
+
+        chunk = StreamChunk(content=content, is_final=is_final)
+        await self.stream_sessions.publish(stream_id, chunk)
+        if is_final:
+            self.stream_sessions.mark_finished(stream_id)
+        return True
 
     async def set_message(self, msg_id: str, content: str):
-        self.generated_content[msg_id] = content
+        """兼容旧逻辑：若无法流式返回则缓存最终结果。
+
+        Args:
+            msg_id: 企业微信消息 ID。
+            content: 最终回复的文本内容。
+
+        Example:
+            在非流式场景下缓存最终结果以备刷新时返回。
+        """
+        handled = await self.push_stream_chunk(msg_id, content, is_final=True)
+        if not handled:
+            self.generated_content[msg_id] = content
 
     def on_message(self, msg_type: str):
         def decorator(func: Callable[[wecombotevent.WecomBotEvent], None]):
@@ -237,7 +546,6 @@ class WecomBotClient:
 
         return decorator
 
-
     async def download_url_to_base64(self, download_url, encoding_aes_key):
         async with httpx.AsyncClient() as client:
             response = await client.get(download_url)
@@ -247,26 +555,22 @@ class WecomBotClient:
 
             encrypted_bytes = response.content
 
-        
         aes_key = base64.b64decode(encoding_aes_key + "=")  # base64 补齐
         iv = aes_key[:16]
 
-        
         cipher = AES.new(aes_key, AES.MODE_CBC, iv)
         decrypted = cipher.decrypt(encrypted_bytes)
 
-        
         pad_len = decrypted[-1]
         decrypted = decrypted[:-pad_len]
 
-        
+        if decrypted.startswith(b"\xff\xd8"):  # JPEG
-        if decrypted.startswith(b"\xff\xd8"):   # JPEG
             mime_type = "image/jpeg"
         elif decrypted.startswith(b"\x89PNG"):  # PNG
             mime_type = "image/png"
         elif decrypted.startswith((b"GIF87a", b"GIF89a")):  # GIF
             mime_type = "image/gif"
-        elif decrypted.startswith(b"BM"):       # BMP
+        elif decrypted.startswith(b"BM"):  # BMP
             mime_type = "image/bmp"
         elif decrypted.startswith(b"II*\x00") or decrypted.startswith(b"MM\x00*"):  # TIFF
             mime_type = "image/tiff"
@@ -276,15 +580,9 @@ class WecomBotClient:
         # 转 base64
         base64_str = base64.b64encode(decrypted).decode("utf-8")
         return f"data:{mime_type};base64,{base64_str}"
-    
 
     async def run_task(self, host: str, port: int, *args, **kwargs):
         """
         启动 Quart 应用。
         """
         await self.app.run_task(host=host, port=port, *args, **kwargs)
-
-                
-    
-            
-

libs/wecom_ai_bot_api/wecombotevent.py

@@ -22,7 +22,21 @@ class WecomBotEvent(dict):
         """
         用户id
         """
-        return self.get('from', {}).get('userid', '')
+        return self.get('from', {}).get('userid', '') or self.get('userid', '')
+
+    @property
+    def username(self) -> str:
+        """
+        用户名称
+        """
+        return self.get('username', '') or self.get('from', {}).get('alias', '') or self.get('from', {}).get('name', '') or self.userid
+
+    @property
+    def chatname(self) -> str:
+        """
+        群组名称
+        """
+        return self.get('chatname', '') or str(self.chatid)
 
     @property
     def content(self) -> str:

main.py

@@ -18,7 +18,13 @@ asciiart = r"""
 
 async def main_entry(loop: asyncio.AbstractEventLoop):
     parser = argparse.ArgumentParser(description='LangBot')
-    parser.add_argument('--standalone-runtime', action='store_true', help='使用独立插件运行时', default=False)
+    parser.add_argument(
+        '--standalone-runtime',
+        action='store_true',
+        help='Use standalone plugin runtime / 使用独立插件运行时',
+        default=False,
+    )
+    parser.add_argument('--debug', action='store_true', help='Debug mode / 调试模式', default=False)
     args = parser.parse_args()
 
     if args.standalone_runtime:
@@ -26,6 +32,11 @@ async def main_entry(loop: asyncio.AbstractEventLoop):
 
         platform.standalone_runtime = True
 
+    if args.debug:
+        from pkg.utils import constants
+
+        constants.debug_mode = True
+
     print(asciiart)
 
     import sys

pkg/api/http/controller/group.py

@@ -9,6 +9,9 @@ from quart.typing import RouteCallable
 
 from ....core import app
 
+# Maximum file upload size limit (10MB)
+MAX_FILE_SIZE = 10 * 1024 * 1024  # 10MB
+
 
 preregistered_groups: list[type[RouterGroup]] = []
 """Pre-registered list of RouterGroup"""
@@ -31,6 +34,8 @@ class AuthType(enum.Enum):
 
     NONE = 'none'
     USER_TOKEN = 'user-token'
+    API_KEY = 'api-key'
+    USER_TOKEN_OR_API_KEY = 'user-token-or-api-key'
 
 
 class RouterGroup(abc.ABC):
@@ -84,6 +89,63 @@ class RouterGroup(abc.ABC):
                     except Exception as e:
                         return self.http_status(401, -1, str(e))
 
+                elif auth_type == AuthType.API_KEY:
+                    # get API key from Authorization header or X-API-Key header
+                    api_key = quart.request.headers.get('X-API-Key', '')
+                    if not api_key:
+                        auth_header = quart.request.headers.get('Authorization', '')
+                        if auth_header.startswith('Bearer '):
+                            api_key = auth_header.replace('Bearer ', '')
+
+                    if not api_key:
+                        return self.http_status(401, -1, 'No valid API key provided')
+
+                    try:
+                        is_valid = await self.ap.apikey_service.verify_api_key(api_key)
+                        if not is_valid:
+                            return self.http_status(401, -1, 'Invalid API key')
+                    except Exception as e:
+                        return self.http_status(401, -1, str(e))
+
+                elif auth_type == AuthType.USER_TOKEN_OR_API_KEY:
+                    # Try API key first (check X-API-Key header)
+                    api_key = quart.request.headers.get('X-API-Key', '')
+                    
+                    if api_key:
+                        # API key authentication
+                        try:
+                            is_valid = await self.ap.apikey_service.verify_api_key(api_key)
+                            if not is_valid:
+                                return self.http_status(401, -1, 'Invalid API key')
+                        except Exception as e:
+                            return self.http_status(401, -1, str(e))
+                    else:
+                        # Try user token authentication (Authorization header)
+                        token = quart.request.headers.get('Authorization', '').replace('Bearer ', '')
+
+                        if not token:
+                            return self.http_status(401, -1, 'No valid authentication provided (user token or API key required)')
+
+                        try:
+                            user_email = await self.ap.user_service.verify_jwt_token(token)
+
+                            # check if this account exists
+                            user = await self.ap.user_service.get_user_by_email(user_email)
+                            if not user:
+                                return self.http_status(401, -1, 'User not found')
+
+                            # check if f accepts user_email parameter
+                            if 'user_email' in f.__code__.co_varnames:
+                                kwargs['user_email'] = user_email
+                        except Exception:
+                            # If user token fails, maybe it's an API key in Authorization header
+                            try:
+                                is_valid = await self.ap.apikey_service.verify_api_key(token)
+                                if not is_valid:
+                                    return self.http_status(401, -1, 'Invalid authentication credentials')
+                            except Exception as e:
+                                return self.http_status(401, -1, str(e))
+
                 try:
                     return await f(*args, **kwargs)
 

pkg/api/http/controller/groups/apikeys.py

@@ -0,0 +1,43 @@
+import quart
+
+from .. import group
+
+
+@group.group_class('apikeys', '/api/v1/apikeys')
+class ApiKeysRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET', 'POST'])
+        async def _() -> str:
+            if quart.request.method == 'GET':
+                keys = await self.ap.apikey_service.get_api_keys()
+                return self.success(data={'keys': keys})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                name = json_data.get('name', '')
+                description = json_data.get('description', '')
+
+                if not name:
+                    return self.http_status(400, -1, 'Name is required')
+
+                key = await self.ap.apikey_service.create_api_key(name, description)
+                return self.success(data={'key': key})
+
+        @self.route('/<int:key_id>', methods=['GET', 'PUT', 'DELETE'])
+        async def _(key_id: int) -> str:
+            if quart.request.method == 'GET':
+                key = await self.ap.apikey_service.get_api_key(key_id)
+                if key is None:
+                    return self.http_status(404, -1, 'API key not found')
+                return self.success(data={'key': key})
+
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                name = json_data.get('name')
+                description = json_data.get('description')
+
+                await self.ap.apikey_service.update_api_key(key_id, name, description)
+                return self.success()
+
+            elif quart.request.method == 'DELETE':
+                await self.ap.apikey_service.delete_api_key(key_id)
+                return self.success()

pkg/api/http/controller/groups/files.py

@@ -15,6 +15,9 @@ class FilesRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
         @self.route('/image/<image_key>', methods=['GET'], auth_type=group.AuthType.NONE)
         async def _(image_key: str) -> quart.Response:
+            if '/' in image_key or '\\' in image_key:
+                return quart.Response(status=404)
+
             if not await self.ap.storage_mgr.storage_provider.exists(image_key):
                 return quart.Response(status=404)
 
@@ -28,15 +31,41 @@ class FilesRouterGroup(group.RouterGroup):
         @self.route('/documents', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> quart.Response:
             request = quart.request
+
+            # Check file size limit before reading the file
+            content_length = request.content_length
+            if content_length and content_length > group.MAX_FILE_SIZE:
+                return self.fail(400, 'File size exceeds 10MB limit. Please split large files into smaller parts.')
+
             # get file bytes from 'file'
-            file = (await request.files)['file']
+            files = await request.files
+            if 'file' not in files:
+                return self.fail(400, 'No file provided in request')
+
+            file = files['file']
             assert isinstance(file, quart.datastructures.FileStorage)
 
             file_bytes = await asyncio.to_thread(file.stream.read)
-            extension = file.filename.split('.')[-1]
-            file_name = file.filename.split('.')[0]
 
-            file_key = file_name + '_' + str(uuid.uuid4())[:8] + '.' + extension
+            # Double-check actual file size after reading
+            if len(file_bytes) > group.MAX_FILE_SIZE:
+                return self.fail(400, 'File size exceeds 10MB limit. Please split large files into smaller parts.')
+
+            # Split filename and extension properly
+            if '.' in file.filename:
+                file_name, extension = file.filename.rsplit('.', 1)
+            else:
+                file_name = file.filename
+                extension = ''
+
+            # check if file name contains '/' or '\'
+            if '/' in file_name or '\\' in file_name:
+                return self.fail(400, 'File name contains invalid characters')
+
+            file_key = file_name + '_' + str(uuid.uuid4())[:8]
+            if extension:
+                file_key += '.' + extension
+
             # save file to storage
             await self.ap.storage_mgr.storage_provider.save(file_key, file_bytes)
             return self.success(

pkg/api/http/controller/groups/pipelines/pipelines.py

@@ -8,7 +8,7 @@ from ... import group
 @group.group_class('pipelines', '/api/v1/pipelines')
 class PipelinesRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route('', methods=['GET', 'POST'])
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             if quart.request.method == 'GET':
                 sort_by = quart.request.args.get('sort_by', 'created_at')
@@ -23,11 +23,11 @@ class PipelinesRouterGroup(group.RouterGroup):
 
                 return self.success(data={'uuid': pipeline_uuid})
 
-        @self.route('/_/metadata', methods=['GET'])
+        @self.route('/_/metadata', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             return self.success(data={'configs': await self.ap.pipeline_service.get_pipeline_metadata()})
 
-        @self.route('/<pipeline_uuid>', methods=['GET', 'PUT', 'DELETE'])
+        @self.route('/<pipeline_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(pipeline_uuid: str) -> str:
             if quart.request.method == 'GET':
                 pipeline = await self.ap.pipeline_service.get_pipeline(pipeline_uuid)
@@ -46,3 +46,34 @@ class PipelinesRouterGroup(group.RouterGroup):
                 await self.ap.pipeline_service.delete_pipeline(pipeline_uuid)
 
                 return self.success()
+
+        @self.route('/<pipeline_uuid>/extensions', methods=['GET', 'PUT'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(pipeline_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                # Get current extensions and available plugins
+                pipeline = await self.ap.pipeline_service.get_pipeline(pipeline_uuid)
+                if pipeline is None:
+                    return self.http_status(404, -1, 'pipeline not found')
+
+                plugins = await self.ap.plugin_connector.list_plugins()
+                mcp_servers = await self.ap.mcp_service.get_mcp_servers(contain_runtime_info=True)
+
+                return self.success(
+                    data={
+                        'bound_plugins': pipeline.get('extensions_preferences', {}).get('plugins', []),
+                        'available_plugins': plugins,
+                        'bound_mcp_servers': pipeline.get('extensions_preferences', {}).get('mcp_servers', []),
+                        'available_mcp_servers': mcp_servers,
+                    }
+                )
+            elif quart.request.method == 'PUT':
+                # Update bound plugins and MCP servers for this pipeline
+                json_data = await quart.request.json
+                bound_plugins = json_data.get('bound_plugins', [])
+                bound_mcp_servers = json_data.get('bound_mcp_servers', [])
+
+                await self.ap.pipeline_service.update_pipeline_extensions(
+                    pipeline_uuid, bound_plugins, bound_mcp_servers
+                )
+
+                return self.success()

pkg/api/http/controller/groups/platform/bots.py

@@ -6,7 +6,7 @@ from ... import group
 @group.group_class('bots', '/api/v1/platform/bots')
 class BotsRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route('', methods=['GET', 'POST'])
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             if quart.request.method == 'GET':
                 return self.success(data={'bots': await self.ap.bot_service.get_bots()})
@@ -15,7 +15,7 @@ class BotsRouterGroup(group.RouterGroup):
                 bot_uuid = await self.ap.bot_service.create_bot(json_data)
                 return self.success(data={'uuid': bot_uuid})
 
-        @self.route('/<bot_uuid>', methods=['GET', 'PUT', 'DELETE'])
+        @self.route('/<bot_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(bot_uuid: str) -> str:
             if quart.request.method == 'GET':
                 bot = await self.ap.bot_service.get_bot(bot_uuid)
@@ -30,7 +30,7 @@ class BotsRouterGroup(group.RouterGroup):
                 await self.ap.bot_service.delete_bot(bot_uuid)
                 return self.success()
 
-        @self.route('/<bot_uuid>/logs', methods=['POST'])
+        @self.route('/<bot_uuid>/logs', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(bot_uuid: str) -> str:
             json_data = await quart.request.json
             from_index = json_data.get('from_index', -1)

pkg/api/http/controller/groups/plugins.py

@@ -2,6 +2,10 @@ from __future__ import annotations
 
 import base64
 import quart
+import re
+import httpx
+import uuid
+import os
 
 from .....core import taskmgr
 from .. import group
@@ -45,9 +49,12 @@ class PluginsRouterGroup(group.RouterGroup):
                     return self.http_status(404, -1, 'plugin not found')
                 return self.success(data={'plugin': plugin})
             elif quart.request.method == 'DELETE':
+                delete_data = quart.request.args.get('delete_data', 'false').lower() == 'true'
                 ctx = taskmgr.TaskContext.new()
                 wrapper = self.ap.task_mgr.create_user_task(
-                    self.ap.plugin_connector.delete_plugin(author, plugin_name, task_context=ctx),
+                    self.ap.plugin_connector.delete_plugin(
+                        author, plugin_name, delete_data=delete_data, task_context=ctx
+                    ),
                     kind='plugin-operation',
                     name=f'plugin-remove-{plugin_name}',
                     label=f'Removing plugin {plugin_name}',
@@ -89,23 +96,145 @@ class PluginsRouterGroup(group.RouterGroup):
 
             return quart.Response(icon_data, mimetype=mime_type)
 
+        @self.route('/github/releases', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            """Get releases from a GitHub repository URL"""
+            data = await quart.request.json
+            repo_url = data.get('repo_url', '')
+
+            # Parse GitHub repository URL to extract owner and repo
+            # Supports: https://github.com/owner/repo or github.com/owner/repo
+            pattern = r'github\.com/([^/]+)/([^/]+?)(?:\.git)?(?:/.*)?$'
+            match = re.search(pattern, repo_url)
+
+            if not match:
+                return self.http_status(400, -1, 'Invalid GitHub repository URL')
+
+            owner, repo = match.groups()
+
+            try:
+                # Fetch releases from GitHub API
+                url = f'https://api.github.com/repos/{owner}/{repo}/releases'
+                async with httpx.AsyncClient(
+                    trust_env=True,
+                    follow_redirects=True,
+                    timeout=10,
+                ) as client:
+                    response = await client.get(url)
+                    response.raise_for_status()
+                    releases = response.json()
+
+                # Format releases data for frontend
+                formatted_releases = []
+                for release in releases:
+                    formatted_releases.append(
+                        {
+                            'id': release['id'],
+                            'tag_name': release['tag_name'],
+                            'name': release['name'],
+                            'published_at': release['published_at'],
+                            'prerelease': release['prerelease'],
+                            'draft': release['draft'],
+                        }
+                    )
+
+                return self.success(data={'releases': formatted_releases, 'owner': owner, 'repo': repo})
+            except httpx.RequestError as e:
+                return self.http_status(500, -1, f'Failed to fetch releases: {str(e)}')
+
+        @self.route(
+            '/github/release-assets',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN,
+        )
+        async def _() -> str:
+            """Get assets from a specific GitHub release"""
+            data = await quart.request.json
+            owner = data.get('owner', '')
+            repo = data.get('repo', '')
+            release_id = data.get('release_id', '')
+
+            if not all([owner, repo, release_id]):
+                return self.http_status(400, -1, 'Missing required parameters')
+
+            try:
+                # Fetch release assets from GitHub API
+                url = f'https://api.github.com/repos/{owner}/{repo}/releases/{release_id}'
+                async with httpx.AsyncClient(
+                    trust_env=True,
+                    follow_redirects=True,
+                    timeout=10,
+                ) as client:
+                    response = await client.get(
+                        url,
+                    )
+                    response.raise_for_status()
+                    release = response.json()
+
+                # Format assets data for frontend
+                formatted_assets = []
+                for asset in release.get('assets', []):
+                    formatted_assets.append(
+                        {
+                            'id': asset['id'],
+                            'name': asset['name'],
+                            'size': asset['size'],
+                            'download_url': asset['browser_download_url'],
+                            'content_type': asset['content_type'],
+                        }
+                    )
+
+                # add zipball as a downloadable asset
+                # formatted_assets.append(
+                #     {
+                #         "id": 0,
+                #         "name": "Source code (zip)",
+                #         "size": -1,
+                #         "download_url": release["zipball_url"],
+                #         "content_type": "application/zip",
+                #     }
+                # )
+
+                return self.success(data={'assets': formatted_assets})
+            except httpx.RequestError as e:
+                return self.http_status(500, -1, f'Failed to fetch release assets: {str(e)}')
+
         @self.route('/install/github', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
+            """Install plugin from GitHub release asset"""
             data = await quart.request.json
+            asset_url = data.get('asset_url', '')
+            owner = data.get('owner', '')
+            repo = data.get('repo', '')
+            release_tag = data.get('release_tag', '')
+
+            if not asset_url:
+                return self.http_status(400, -1, 'Missing asset_url parameter')
 
             ctx = taskmgr.TaskContext.new()
-            short_source_str = data['source'][-8:]
+            install_info = {
+                'asset_url': asset_url,
+                'owner': owner,
+                'repo': repo,
+                'release_tag': release_tag,
+                'github_url': f'https://github.com/{owner}/{repo}',
+            }
+
             wrapper = self.ap.task_mgr.create_user_task(
-                self.ap.plugin_mgr.install_plugin(data['source'], task_context=ctx),
+                self.ap.plugin_connector.install_plugin(PluginInstallSource.GITHUB, install_info, task_context=ctx),
                 kind='plugin-operation',
                 name='plugin-install-github',
-                label=f'Installing plugin from github ...{short_source_str}',
+                label=f'Installing plugin from GitHub {owner}/{repo}@{release_tag}',
                 context=ctx,
             )
 
             return self.success(data={'task_id': wrapper.id})
 
-        @self.route('/install/marketplace', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route(
+            '/install/marketplace',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN,
+        )
         async def _() -> str:
             data = await quart.request.json
 
@@ -128,10 +257,8 @@ class PluginsRouterGroup(group.RouterGroup):
 
             file_bytes = file.read()
 
-            file_base64 = base64.b64encode(file_bytes).decode('utf-8')
-
             data = {
-                'plugin_file': file_base64,
+                'plugin_file': file_bytes,
             }
 
             ctx = taskmgr.TaskContext.new()
@@ -144,3 +271,39 @@ class PluginsRouterGroup(group.RouterGroup):
             )
 
             return self.success(data={'task_id': wrapper.id})
+
+        @self.route('/config-files', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            """Upload a file for plugin configuration"""
+            file = (await quart.request.files).get('file')
+            if file is None:
+                return self.http_status(400, -1, 'file is required')
+
+            # Check file size (10MB limit)
+            MAX_FILE_SIZE = 10 * 1024 * 1024  # 10MB
+            file_bytes = file.read()
+            if len(file_bytes) > MAX_FILE_SIZE:
+                return self.http_status(400, -1, 'file size exceeds 10MB limit')
+
+            # Generate unique file key with original extension
+            original_filename = file.filename
+            _, ext = os.path.splitext(original_filename)
+            file_key = f'plugin_config_{uuid.uuid4().hex}{ext}'
+
+            # Save file using storage manager
+            await self.ap.storage_mgr.storage_provider.save(file_key, file_bytes)
+
+            return self.success(data={'file_key': file_key})
+
+        @self.route('/config-files/<file_key>', methods=['DELETE'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(file_key: str) -> str:
+            """Delete a plugin configuration file"""
+            # Only allow deletion of files with plugin_config_ prefix for security
+            if not file_key.startswith('plugin_config_'):
+                return self.http_status(400, -1, 'invalid file key')
+
+            try:
+                await self.ap.storage_mgr.storage_provider.delete(file_key)
+                return self.success(data={'deleted': True})
+            except Exception as e:
+                return self.http_status(500, -1, f'failed to delete file: {str(e)}')

pkg/api/http/controller/groups/provider/models.py

@@ -6,7 +6,7 @@ from ... import group
 @group.group_class('models/llm', '/api/v1/provider/models/llm')
 class LLMModelsRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route('', methods=['GET', 'POST'])
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             if quart.request.method == 'GET':
                 return self.success(data={'models': await self.ap.llm_model_service.get_llm_models()})
@@ -17,7 +17,7 @@ class LLMModelsRouterGroup(group.RouterGroup):
 
                 return self.success(data={'uuid': model_uuid})
 
-        @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'])
+        @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(model_uuid: str) -> str:
             if quart.request.method == 'GET':
                 model = await self.ap.llm_model_service.get_llm_model(model_uuid)
@@ -37,7 +37,7 @@ class LLMModelsRouterGroup(group.RouterGroup):
 
                 return self.success()
 
-        @self.route('/<model_uuid>/test', methods=['POST'])
+        @self.route('/<model_uuid>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(model_uuid: str) -> str:
             json_data = await quart.request.json
 
@@ -49,7 +49,7 @@ class LLMModelsRouterGroup(group.RouterGroup):
 @group.group_class('models/embedding', '/api/v1/provider/models/embedding')
 class EmbeddingModelsRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route('', methods=['GET', 'POST'])
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             if quart.request.method == 'GET':
                 return self.success(data={'models': await self.ap.embedding_models_service.get_embedding_models()})
@@ -60,7 +60,7 @@ class EmbeddingModelsRouterGroup(group.RouterGroup):
 
                 return self.success(data={'uuid': model_uuid})
 
-        @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'])
+        @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(model_uuid: str) -> str:
             if quart.request.method == 'GET':
                 model = await self.ap.embedding_models_service.get_embedding_model(model_uuid)
@@ -80,7 +80,7 @@ class EmbeddingModelsRouterGroup(group.RouterGroup):
 
                 return self.success()
 
-        @self.route('/<model_uuid>/test', methods=['POST'])
+        @self.route('/<model_uuid>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(model_uuid: str) -> str:
             json_data = await quart.request.json
 

pkg/api/http/controller/groups/resources/mcp.py

@@ -0,0 +1,62 @@
+from __future__ import annotations
+
+import quart
+import traceback
+
+
+from ... import group
+
+
+@group.group_class('mcp', '/api/v1/mcp')
+class MCPRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('/servers', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            """获取MCP服务器列表"""
+            if quart.request.method == 'GET':
+                servers = await self.ap.mcp_service.get_mcp_servers(contain_runtime_info=True)
+
+                return self.success(data={'servers': servers})
+
+            elif quart.request.method == 'POST':
+                data = await quart.request.json
+
+                try:
+                    uuid = await self.ap.mcp_service.create_mcp_server(data)
+                    return self.success(data={'uuid': uuid})
+                except Exception as e:
+                    traceback.print_exc()
+                    return self.http_status(500, -1, f'Failed to create MCP server: {str(e)}')
+
+        @self.route('/servers/<server_name>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(server_name: str) -> str:
+            """获取、更新或删除MCP服务器配置"""
+
+            server_data = await self.ap.mcp_service.get_mcp_server_by_name(server_name)
+            if server_data is None:
+                return self.http_status(404, -1, 'Server not found')
+
+            if quart.request.method == 'GET':
+                return self.success(data={'server': server_data})
+
+            elif quart.request.method == 'PUT':
+                data = await quart.request.json
+                try:
+                    await self.ap.mcp_service.update_mcp_server(server_data['uuid'], data)
+                    return self.success()
+                except Exception as e:
+                    return self.http_status(500, -1, f'Failed to update MCP server: {str(e)}')
+
+            elif quart.request.method == 'DELETE':
+                try:
+                    await self.ap.mcp_service.delete_mcp_server(server_data['uuid'])
+                    return self.success()
+                except Exception as e:
+                    return self.http_status(500, -1, f'Failed to delete MCP server: {str(e)}')
+
+        @self.route('/servers/<server_name>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(server_name: str) -> str:
+            """测试MCP服务器连接"""
+            server_data = await quart.request.json
+            task_id = await self.ap.mcp_service.test_mcp_server(server_name=server_name, server_data=server_data)
+            return self.success(data={'task_id': task_id})

pkg/api/http/controller/groups/system.py

@@ -13,7 +13,6 @@ class SystemRouterGroup(group.RouterGroup):
                 data={
                     'version': constants.semantic_version,
                     'debug': constants.debug_mode,
-                    'enabled_platform_count': len(self.ap.platform_mgr.get_running_adapters()),
                     'enable_marketplace': self.ap.instance_config.data.get('plugin', {}).get(
                         'enable_marketplace', True
                     ),
@@ -91,3 +90,26 @@ class SystemRouterGroup(group.RouterGroup):
             )
 
             return self.success(data=resp)
+
+        @self.route(
+            '/status/plugin-system',
+            methods=['GET'],
+            auth_type=group.AuthType.USER_TOKEN,
+        )
+        async def _() -> str:
+            plugin_connector_error = 'ok'
+            is_connected = True
+
+            try:
+                await self.ap.plugin_connector.ping_plugin_runtime()
+            except Exception as e:
+                plugin_connector_error = str(e)
+                is_connected = False
+
+            return self.success(
+                data={
+                    'is_enable': self.ap.plugin_connector.is_enable_plugin,
+                    'is_connected': is_connected,
+                    'plugin_connector_error': plugin_connector_error,
+                }
+            )

pkg/api/http/controller/groups/webhooks.py

@@ -0,0 +1,49 @@
+import quart
+
+from .. import group
+
+
+@group.group_class('webhooks', '/api/v1/webhooks')
+class WebhooksRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET', 'POST'])
+        async def _() -> str:
+            if quart.request.method == 'GET':
+                webhooks = await self.ap.webhook_service.get_webhooks()
+                return self.success(data={'webhooks': webhooks})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                name = json_data.get('name', '')
+                url = json_data.get('url', '')
+                description = json_data.get('description', '')
+                enabled = json_data.get('enabled', True)
+
+                if not name:
+                    return self.http_status(400, -1, 'Name is required')
+                if not url:
+                    return self.http_status(400, -1, 'URL is required')
+
+                webhook = await self.ap.webhook_service.create_webhook(name, url, description, enabled)
+                return self.success(data={'webhook': webhook})
+
+        @self.route('/<int:webhook_id>', methods=['GET', 'PUT', 'DELETE'])
+        async def _(webhook_id: int) -> str:
+            if quart.request.method == 'GET':
+                webhook = await self.ap.webhook_service.get_webhook(webhook_id)
+                if webhook is None:
+                    return self.http_status(404, -1, 'Webhook not found')
+                return self.success(data={'webhook': webhook})
+
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                name = json_data.get('name')
+                url = json_data.get('url')
+                description = json_data.get('description')
+                enabled = json_data.get('enabled')
+
+                await self.ap.webhook_service.update_webhook(webhook_id, name, url, description, enabled)
+                return self.success()
+
+            elif quart.request.method == 'DELETE':
+                await self.ap.webhook_service.delete_webhook(webhook_id)
+                return self.success()

pkg/api/http/controller/main.py

@@ -5,6 +5,7 @@ import os
 
 import quart
 import quart_cors
+from werkzeug.exceptions import RequestEntityTooLarge
 
 from ....core import app, entities as core_entities
 from ....utils import importutil
@@ -15,12 +16,14 @@ from .groups import provider as groups_provider
 from .groups import platform as groups_platform
 from .groups import pipelines as groups_pipelines
 from .groups import knowledge as groups_knowledge
+from .groups import resources as groups_resources
 
 importutil.import_modules_in_pkg(groups)
 importutil.import_modules_in_pkg(groups_provider)
 importutil.import_modules_in_pkg(groups_platform)
 importutil.import_modules_in_pkg(groups_pipelines)
 importutil.import_modules_in_pkg(groups_knowledge)
+importutil.import_modules_in_pkg(groups_resources)
 
 
 class HTTPController:
@@ -33,7 +36,20 @@ class HTTPController:
         self.quart_app = quart.Quart(__name__)
         quart_cors.cors(self.quart_app, allow_origin='*')
 
+        # Set maximum content length to prevent large file uploads
+        self.quart_app.config['MAX_CONTENT_LENGTH'] = group.MAX_FILE_SIZE
+
     async def initialize(self) -> None:
+        # Register custom error handler for file size limit
+        @self.quart_app.errorhandler(RequestEntityTooLarge)
+        async def handle_request_entity_too_large(e):
+            return quart.jsonify(
+                {
+                    'code': 400,
+                    'msg': 'File size exceeds 10MB limit. Please split large files into smaller parts.',
+                }
+            ), 400
+
         await self.register_routes()
 
     async def run(self) -> None:

pkg/api/http/service/apikey.py

@@ -0,0 +1,79 @@
+from __future__ import annotations
+
+import secrets
+import sqlalchemy
+
+from ....core import app
+from ....entity.persistence import apikey
+
+
+class ApiKeyService:
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_api_keys(self) -> list[dict]:
+        """Get all API keys"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(apikey.ApiKey))
+
+        keys = result.all()
+        return [self.ap.persistence_mgr.serialize_model(apikey.ApiKey, key) for key in keys]
+
+    async def create_api_key(self, name: str, description: str = '') -> dict:
+        """Create a new API key"""
+        # Generate a secure random API key
+        key = f'lbk_{secrets.token_urlsafe(32)}'
+
+        key_data = {'name': name, 'key': key, 'description': description}
+
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(apikey.ApiKey).values(**key_data))
+
+        # Retrieve the created key
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(apikey.ApiKey).where(apikey.ApiKey.key == key)
+        )
+        created_key = result.first()
+
+        return self.ap.persistence_mgr.serialize_model(apikey.ApiKey, created_key)
+
+    async def get_api_key(self, key_id: int) -> dict | None:
+        """Get a specific API key by ID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(apikey.ApiKey).where(apikey.ApiKey.id == key_id)
+        )
+
+        key = result.first()
+
+        if key is None:
+            return None
+
+        return self.ap.persistence_mgr.serialize_model(apikey.ApiKey, key)
+
+    async def verify_api_key(self, key: str) -> bool:
+        """Verify if an API key is valid"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(apikey.ApiKey).where(apikey.ApiKey.key == key)
+        )
+
+        key_obj = result.first()
+        return key_obj is not None
+
+    async def delete_api_key(self, key_id: int) -> None:
+        """Delete an API key"""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(apikey.ApiKey).where(apikey.ApiKey.id == key_id)
+        )
+
+    async def update_api_key(self, key_id: int, name: str = None, description: str = None) -> None:
+        """Update an API key's metadata (name, description)"""
+        update_data = {}
+        if name is not None:
+            update_data['name'] = name
+        if description is not None:
+            update_data['description'] = description
+
+        if update_data:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(apikey.ApiKey).where(apikey.ApiKey.id == key_id).values(**update_data)
+            )

pkg/api/http/service/mcp.py

@@ -0,0 +1,158 @@
+from __future__ import annotations
+
+import sqlalchemy
+import uuid
+import asyncio
+
+from ....core import app
+from ....entity.persistence import mcp as persistence_mcp
+from ....core import taskmgr
+from ....provider.tools.loaders.mcp import RuntimeMCPSession, MCPSessionStatus
+
+
+class MCPService:
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_runtime_info(self, server_name: str) -> dict | None:
+        session = self.ap.tool_mgr.mcp_tool_loader.get_session(server_name)
+        if session:
+            return session.get_runtime_info_dict()
+        return None
+
+    async def get_mcp_servers(self, contain_runtime_info: bool = False) -> list[dict]:
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_mcp.MCPServer))
+
+        servers = result.all()
+        serialized_servers = [
+            self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, server) for server in servers
+        ]
+        if contain_runtime_info:
+            for server in serialized_servers:
+                runtime_info = await self.get_runtime_info(server['name'])
+
+                server['runtime_info'] = runtime_info if runtime_info else None
+
+        return serialized_servers
+
+    async def create_mcp_server(self, server_data: dict) -> str:
+        server_data['uuid'] = str(uuid.uuid4())
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_mcp.MCPServer).values(server_data))
+
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_data['uuid'])
+        )
+        server_entity = result.first()
+        if server_entity:
+            server_config = self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, server_entity)
+            if self.ap.tool_mgr.mcp_tool_loader:
+                task = asyncio.create_task(self.ap.tool_mgr.mcp_tool_loader.host_mcp_server(server_config))
+                self.ap.tool_mgr.mcp_tool_loader._hosted_mcp_tasks.append(task)
+
+        return server_data['uuid']
+
+    async def get_mcp_server_by_name(self, server_name: str) -> dict | None:
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.name == server_name)
+        )
+        server = result.first()
+        if server is None:
+            return None
+
+        runtime_info = await self.get_runtime_info(server.name)
+        server_data = self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, server)
+        server_data['runtime_info'] = runtime_info if runtime_info else None
+        return server_data
+
+    async def update_mcp_server(self, server_uuid: str, server_data: dict) -> None:
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_uuid)
+        )
+        old_server = result.first()
+        old_server_name = old_server.name if old_server else None
+        old_enable = old_server.enable if old_server else False
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_mcp.MCPServer)
+            .where(persistence_mcp.MCPServer.uuid == server_uuid)
+            .values(server_data)
+        )
+
+        if self.ap.tool_mgr.mcp_tool_loader:
+            new_enable = server_data.get('enable', False)
+
+            need_remove = old_server_name and old_server_name in self.ap.tool_mgr.mcp_tool_loader.sessions
+            need_start = new_enable
+
+            
+            if old_enable and not new_enable:
+                if need_remove:
+                    await self.ap.tool_mgr.mcp_tool_loader.remove_mcp_server(old_server_name)
+            
+            elif not old_enable and new_enable:
+                result = await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_uuid)
+                )
+                updated_server = result.first()
+                if updated_server:
+                    server_config = self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, updated_server)
+                    task = asyncio.create_task(self.ap.tool_mgr.mcp_tool_loader.host_mcp_server(server_config))
+                    self.ap.tool_mgr.mcp_tool_loader._hosted_mcp_tasks.append(task)
+            
+            elif old_enable and new_enable:
+                if need_remove:
+                    await self.ap.tool_mgr.mcp_tool_loader.remove_mcp_server(old_server_name)
+                result = await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_uuid)
+                )
+                updated_server = result.first()
+                if updated_server:
+                    server_config = self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, updated_server)
+                    task = asyncio.create_task(self.ap.tool_mgr.mcp_tool_loader.host_mcp_server(server_config))
+                    self.ap.tool_mgr.mcp_tool_loader._hosted_mcp_tasks.append(task)
+            
+
+    async def delete_mcp_server(self, server_uuid: str) -> None:
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_uuid)
+        )
+        server = result.first()
+        server_name = server.name if server else None
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_uuid)
+        )
+
+        if server_name and self.ap.tool_mgr.mcp_tool_loader:
+            if server_name in self.ap.tool_mgr.mcp_tool_loader.sessions:
+                await self.ap.tool_mgr.mcp_tool_loader.remove_mcp_server(server_name)
+
+    async def test_mcp_server(self, server_name: str, server_data: dict) -> int:
+        """测试 MCP 服务器连接并返回任务 ID"""
+
+        runtime_mcp_session: RuntimeMCPSession | None = None
+
+        if server_name != '_':
+            runtime_mcp_session = self.ap.tool_mgr.mcp_tool_loader.get_session(server_name)
+            if runtime_mcp_session is None:
+                raise ValueError(f'Server not found: {server_name}')
+
+            if runtime_mcp_session.status == MCPSessionStatus.ERROR:
+                coroutine = runtime_mcp_session.start()
+            else:
+                coroutine = runtime_mcp_session.refresh()
+        else:
+            runtime_mcp_session = await self.ap.tool_mgr.mcp_tool_loader.load_mcp_server(server_config=server_data)
+            coroutine = runtime_mcp_session.start()
+
+        ctx = taskmgr.TaskContext.new()
+        wrapper = self.ap.task_mgr.create_user_task(
+            coroutine,
+            kind='mcp-operation',
+            name=f'mcp-test-{server_name}',
+            label=f'Testing MCP server {server_name}',
+            context=ctx,
+        )
+        return wrapper.id

pkg/api/http/service/model.py

@@ -1,13 +1,14 @@
 from __future__ import annotations
 
 import uuid
+
 import sqlalchemy
+from langbot_plugin.api.entities.builtin.provider import message as provider_message
 
 from ....core import app
 from ....entity.persistence import model as persistence_model
 from ....entity.persistence import pipeline as persistence_pipeline
 from ....provider.modelmgr import requester as model_requester
-from langbot_plugin.api.entities.builtin.provider import message as provider_message
 
 
 class LLMModelsService:
@@ -104,12 +105,18 @@ class LLMModelsService:
         else:
             runtime_llm_model = await self.ap.model_mgr.init_runtime_llm_model(model_data)
 
+        # Mon Nov 10 2025: Commented for some providers may not support thinking parameter
+        # # 有些模型厂商默认开启了思考功能，测试容易延迟
+        # extra_args = model_data.get('extra_args', {})
+        # if not extra_args or 'thinking' not in extra_args:
+        #     extra_args['thinking'] = {'type': 'disabled'}
+
         await runtime_llm_model.requester.invoke_llm(
             query=None,
             model=runtime_llm_model,
-            messages=[provider_message.Message(role='user', content='Hello, world!')],
+            messages=[provider_message.Message(role='user', content='Hello, world! Please just reply a "Hello".')],
             funcs=[],
-            extra_args=model_data.get('extra_args', {}),
+            # extra_args=extra_args,
         )
 
 

pkg/api/http/service/pipeline.py

@@ -136,3 +136,33 @@ class PipelineService:
             )
         )
         await self.ap.pipeline_mgr.remove_pipeline(pipeline_uuid)
+
+    async def update_pipeline_extensions(self, pipeline_uuid: str, bound_plugins: list[dict], bound_mcp_servers: list[str] = None) -> None:
+        """Update the bound plugins and MCP servers for a pipeline"""
+        # Get current pipeline
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
+                persistence_pipeline.LegacyPipeline.uuid == pipeline_uuid
+            )
+        )
+        
+        pipeline = result.first()
+        if pipeline is None:
+            raise ValueError(f'Pipeline {pipeline_uuid} not found')
+        
+        # Update extensions_preferences
+        extensions_preferences = pipeline.extensions_preferences or {}
+        extensions_preferences['plugins'] = bound_plugins
+        if bound_mcp_servers is not None:
+            extensions_preferences['mcp_servers'] = bound_mcp_servers
+        
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+            .where(persistence_pipeline.LegacyPipeline.uuid == pipeline_uuid)
+            .values(extensions_preferences=extensions_preferences)
+        )
+        
+        # Reload pipeline to apply changes
+        await self.ap.pipeline_mgr.remove_pipeline(pipeline_uuid)
+        pipeline = await self.get_pipeline(pipeline_uuid)
+        await self.ap.pipeline_mgr.load_pipeline(pipeline)

pkg/api/http/service/webhook.py

@@ -0,0 +1,81 @@
+from __future__ import annotations
+
+import sqlalchemy
+
+from ....core import app
+from ....entity.persistence import webhook
+
+
+class WebhookService:
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_webhooks(self) -> list[dict]:
+        """Get all webhooks"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(webhook.Webhook))
+
+        webhooks = result.all()
+        return [self.ap.persistence_mgr.serialize_model(webhook.Webhook, wh) for wh in webhooks]
+
+    async def create_webhook(self, name: str, url: str, description: str = '', enabled: bool = True) -> dict:
+        """Create a new webhook"""
+        webhook_data = {'name': name, 'url': url, 'description': description, 'enabled': enabled}
+
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(webhook.Webhook).values(**webhook_data))
+
+        # Retrieve the created webhook
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(webhook.Webhook).where(webhook.Webhook.url == url).order_by(webhook.Webhook.id.desc())
+        )
+        created_webhook = result.first()
+
+        return self.ap.persistence_mgr.serialize_model(webhook.Webhook, created_webhook)
+
+    async def get_webhook(self, webhook_id: int) -> dict | None:
+        """Get a specific webhook by ID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(webhook.Webhook).where(webhook.Webhook.id == webhook_id)
+        )
+
+        wh = result.first()
+
+        if wh is None:
+            return None
+
+        return self.ap.persistence_mgr.serialize_model(webhook.Webhook, wh)
+
+    async def update_webhook(
+        self, webhook_id: int, name: str = None, url: str = None, description: str = None, enabled: bool = None
+    ) -> None:
+        """Update a webhook's metadata"""
+        update_data = {}
+        if name is not None:
+            update_data['name'] = name
+        if url is not None:
+            update_data['url'] = url
+        if description is not None:
+            update_data['description'] = description
+        if enabled is not None:
+            update_data['enabled'] = enabled
+
+        if update_data:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(webhook.Webhook).where(webhook.Webhook.id == webhook_id).values(**update_data)
+            )
+
+    async def delete_webhook(self, webhook_id: int) -> None:
+        """Delete a webhook"""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(webhook.Webhook).where(webhook.Webhook.id == webhook_id)
+        )
+
+    async def get_enabled_webhooks(self) -> list[dict]:
+        """Get all enabled webhooks"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(webhook.Webhook).where(webhook.Webhook.enabled == True)
+        )
+
+        webhooks = result.all()
+        return [self.ap.persistence_mgr.serialize_model(webhook.Webhook, wh) for wh in webhooks]

pkg/command/cmdmgr.py

@@ -59,14 +59,15 @@ class CommandManager:
         context: command_context.ExecuteContext,
         operator_list: list[operator.CommandOperator],
         operator: operator.CommandOperator = None,
+        bound_plugins: list[str] | None = None,
     ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """执行命令"""
 
-        command_list = await self.ap.plugin_connector.list_commands()
+        command_list = await self.ap.plugin_connector.list_commands(bound_plugins)
 
         for command in command_list:
             if command.metadata.name == context.command:
-                async for ret in self.ap.plugin_connector.execute_command(context):
+                async for ret in self.ap.plugin_connector.execute_command(context, bound_plugins):
                     yield ret
                 break
         else:
@@ -102,5 +103,8 @@ class CommandManager:
 
         ctx.shift()
 
-        async for ret in self._execute(ctx, self.cmd_list):
+        # Get bound plugins from query
+        bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+
+        async for ret in self._execute(ctx, self.cmd_list, bound_plugins=bound_plugins):
             yield ret

pkg/core/app.py

@@ -6,6 +6,7 @@ import traceback
 import os
 
 from ..platform import botmgr as im_mgr
+from ..platform.webhook_pusher import WebhookPusher
 from ..provider.session import sessionmgr as llm_session_mgr
 from ..provider.modelmgr import modelmgr as llm_model_mgr
 from ..provider.tools import toolmgr as llm_tool_mgr
@@ -22,6 +23,9 @@ from ..api.http.service import model as model_service
 from ..api.http.service import pipeline as pipeline_service
 from ..api.http.service import bot as bot_service
 from ..api.http.service import knowledge as knowledge_service
+from ..api.http.service import mcp as mcp_service
+from ..api.http.service import apikey as apikey_service
+from ..api.http.service import webhook as webhook_service
 from ..discover import engine as discover_engine
 from ..storage import mgr as storagemgr
 from ..utils import logcache
@@ -43,6 +47,8 @@ class Application:
 
     platform_mgr: im_mgr.PlatformManager = None
 
+    webhook_pusher: WebhookPusher = None
+
     cmd_mgr: cmdmgr.CommandManager = None
 
     sess_mgr: llm_session_mgr.SessionManager = None
@@ -119,6 +125,12 @@ class Application:
 
     knowledge_service: knowledge_service.KnowledgeService = None
 
+    mcp_service: mcp_service.MCPService = None
+
+    apikey_service: apikey_service.ApiKeyService = None
+
+    webhook_service: webhook_service.WebhookService = None
+
     def __init__(self):
         pass
 

pkg/core/bootutils/files.py

@@ -5,7 +5,6 @@ import shutil
 
 
 required_files = {
-    'plugins/__init__.py': 'templates/__init__.py',
     'data/config.yaml': 'templates/config.yaml',
 }
 
@@ -15,7 +14,6 @@ required_paths = [
     'data/metadata',
     'data/logs',
     'data/labels',
-    'plugins',
 ]
 
 

pkg/core/stages/build_app.py

@@ -12,6 +12,7 @@ from ...provider.modelmgr import modelmgr as llm_model_mgr
 from ...provider.tools import toolmgr as llm_tool_mgr
 from ...rag.knowledge import kbmgr as rag_mgr
 from ...platform import botmgr as im_mgr
+from ...platform.webhook_pusher import WebhookPusher
 from ...persistence import mgr as persistencemgr
 from ...api.http.controller import main as http_controller
 from ...api.http.service import user as user_service
@@ -19,6 +20,9 @@ from ...api.http.service import model as model_service
 from ...api.http.service import pipeline as pipeline_service
 from ...api.http.service import bot as bot_service
 from ...api.http.service import knowledge as knowledge_service
+from ...api.http.service import mcp as mcp_service
+from ...api.http.service import apikey as apikey_service
+from ...api.http.service import webhook as webhook_service
 from ...discover import engine as discover_engine
 from ...storage import mgr as storagemgr
 from ...utils import logcache
@@ -91,6 +95,10 @@ class BuildAppStage(stage.BootingStage):
         await im_mgr_inst.initialize()
         ap.platform_mgr = im_mgr_inst
 
+        # Initialize webhook pusher
+        webhook_pusher_inst = WebhookPusher(ap)
+        ap.webhook_pusher = webhook_pusher_inst
+
         pipeline_mgr = pipelinemgr.PipelineManager(ap)
         await pipeline_mgr.initialize()
         ap.pipeline_mgr = pipeline_mgr
@@ -126,5 +134,14 @@ class BuildAppStage(stage.BootingStage):
         knowledge_service_inst = knowledge_service.KnowledgeService(ap)
         ap.knowledge_service = knowledge_service_inst
 
+        mcp_service_inst = mcp_service.MCPService(ap)
+        ap.mcp_service = mcp_service_inst
+
+        apikey_service_inst = apikey_service.ApiKeyService(ap)
+        ap.apikey_service = apikey_service_inst
+
+        webhook_service_inst = webhook_service.WebhookService(ap)
+        ap.webhook_service = webhook_service_inst
+
         ctrl = controller.Controller(ap)
         ap.ctrl = ctrl

pkg/core/stages/load_config.py

@@ -1,11 +1,93 @@
 from __future__ import annotations
 
 import os
+from typing import Any
 
 from .. import stage, app
 from ..bootutils import config
 
 
+def _apply_env_overrides_to_config(cfg: dict) -> dict:
+    """Apply environment variable overrides to data/config.yaml
+
+    Environment variables should be uppercase and use __ (double underscore)
+    to represent nested keys. For example:
+    - CONCURRENCY__PIPELINE overrides concurrency.pipeline
+    - PLUGIN__RUNTIME_WS_URL overrides plugin.runtime_ws_url
+
+    Arrays and dict types are ignored.
+
+    Args:
+        cfg: Configuration dictionary
+
+    Returns:
+        Updated configuration dictionary
+    """
+
+    def convert_value(value: str, original_value: Any) -> Any:
+        """Convert string value to appropriate type based on original value
+
+        Args:
+            value: String value from environment variable
+            original_value: Original value to infer type from
+
+        Returns:
+            Converted value (falls back to string if conversion fails)
+        """
+        if isinstance(original_value, bool):
+            return value.lower() in ('true', '1', 'yes', 'on')
+        elif isinstance(original_value, int):
+            try:
+                return int(value)
+            except ValueError:
+                # If conversion fails, keep as string (user error, but non-breaking)
+                return value
+        elif isinstance(original_value, float):
+            try:
+                return float(value)
+            except ValueError:
+                # If conversion fails, keep as string (user error, but non-breaking)
+                return value
+        else:
+            return value
+
+    # Process environment variables
+    for env_key, env_value in os.environ.items():
+        # Check if the environment variable is uppercase and contains __
+        if not env_key.isupper():
+            continue
+        if '__' not in env_key:
+            continue
+
+        print(f'apply env overrides to config: env_key: {env_key}, env_value: {env_value}')
+
+        # Convert environment variable name to config path
+        # e.g., CONCURRENCY__PIPELINE -> ['concurrency', 'pipeline']
+        keys = [key.lower() for key in env_key.split('__')]
+
+        # Navigate to the target value and validate the path
+        current = cfg
+
+        for i, key in enumerate(keys):
+            if not isinstance(current, dict) or key not in current:
+                break
+
+            if i == len(keys) - 1:
+                # At the final key - check if it's a scalar value
+                if isinstance(current[key], (dict, list)):
+                    # Skip dict and list types
+                    pass
+                else:
+                    # Valid scalar value - convert and set it
+                    converted_value = convert_value(env_value, current[key])
+                    current[key] = converted_value
+            else:
+                # Navigate deeper
+                current = current[key]
+
+    return cfg
+
+
 @stage.stage_class('LoadConfigStage')
 class LoadConfigStage(stage.BootingStage):
     """Load config file stage"""
@@ -54,6 +136,10 @@ class LoadConfigStage(stage.BootingStage):
         ap.instance_config = await config.load_yaml_config(
             'data/config.yaml', 'templates/config.yaml', completion=False
         )
+
+        # Apply environment variable overrides to data/config.yaml
+        ap.instance_config.data = _apply_env_overrides_to_config(ap.instance_config.data)
+
         await ap.instance_config.dump_config()
 
         ap.sensitive_meta = await config.load_json_config(

pkg/core/taskmgr.py

@@ -156,7 +156,7 @@ class TaskWrapper:
                 'state': self.task._state,
                 'exception': self.assume_exception().__str__() if self.assume_exception() is not None else None,
                 'exception_traceback': exception_traceback,
-                'result': self.assume_result().__str__() if self.assume_result() is not None else None,
+                'result': self.assume_result() if self.assume_result() is not None else None,
             },
         }
 

pkg/entity/persistence/apikey.py

@@ -0,0 +1,21 @@
+import sqlalchemy
+
+from .base import Base
+
+
+class ApiKey(Base):
+    """API Key for external service authentication"""
+
+    __tablename__ = 'api_keys'
+
+    id = sqlalchemy.Column(sqlalchemy.Integer, primary_key=True, autoincrement=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    key = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, unique=True)
+    description = sqlalchemy.Column(sqlalchemy.String(512), nullable=True, default='')
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    updated_at = sqlalchemy.Column(
+        sqlalchemy.DateTime,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )

pkg/entity/persistence/mcp.py

@@ -0,0 +1,20 @@
+import sqlalchemy
+
+from .base import Base
+
+
+class MCPServer(Base):
+    __tablename__ = 'mcp_servers'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    enable = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
+    mode = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)  # stdio, sse
+    extra_args = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    updated_at = sqlalchemy.Column(
+        sqlalchemy.DateTime,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )

pkg/entity/persistence/metadata.py

@@ -1,12 +1,13 @@
 import sqlalchemy
 
 from .base import Base
+from ...utils import constants
 
 
 initial_metadata = [
     {
         'key': 'database_version',
-        'value': '0',
+        'value': str(constants.required_database_version),
     },
 ]
 

pkg/entity/persistence/pipeline.py

@@ -22,6 +22,7 @@ class LegacyPipeline(Base):
     is_default = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
     stages = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
     config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
+    extensions_preferences = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
 
 
 class PipelineRunRecord(Base):

pkg/entity/persistence/webhook.py

@@ -0,0 +1,22 @@
+import sqlalchemy
+
+from .base import Base
+
+
+class Webhook(Base):
+    """Webhook for pushing bot events to external systems"""
+
+    __tablename__ = 'webhooks'
+
+    id = sqlalchemy.Column(sqlalchemy.Integer, primary_key=True, autoincrement=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    url = sqlalchemy.Column(sqlalchemy.String(1024), nullable=False)
+    description = sqlalchemy.Column(sqlalchemy.String(512), nullable=True, default='')
+    enabled = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True)
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    updated_at = sqlalchemy.Column(
+        sqlalchemy.DateTime,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )

pkg/persistence/mgr.py

@@ -78,6 +78,8 @@ class PersistenceManager:
 
             self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
 
+        await self.write_default_pipeline()
+
     async def create_tables(self):
         # create tables
         async with self.get_db_engine().connect() as conn:
@@ -98,6 +100,7 @@ class PersistenceManager:
             if row is None:
                 await self.execute_async(sqlalchemy.insert(metadata.Metadata).values(item))
 
+    async def write_default_pipeline(self):
         # write default pipeline
         result = await self.execute_async(sqlalchemy.select(pipeline.LegacyPipeline))
         default_pipeline_uuid = None
@@ -115,6 +118,7 @@ class PersistenceManager:
                 'name': 'ChatPipeline',
                 'description': 'Default pipeline, new bots will be bound to this pipeline | 默认提供的流水线，您配置的机器人将自动绑定到此流水线',
                 'config': pipeline_config,
+                'extensions_preferences': {},
             }
 
             await self.execute_async(sqlalchemy.insert(pipeline.LegacyPipeline).values(pipeline_data))

pkg/persistence/migrations/dbm008_plugin_config.py

@@ -10,7 +10,9 @@ class DBMigratePluginConfig(migration.DBMigration):
 
         if 'plugin' not in self.ap.instance_config.data:
             self.ap.instance_config.data['plugin'] = {
-                'runtime_ws_url': 'ws://localhost:5400/control/ws',
+                'runtime_ws_url': 'ws://langbot_plugin_runtime:5400/control/ws',
+                'enable_marketplace': True,
+                'cloud_service_url': 'https://space.langbot.app',
             }
 
             await self.ap.instance_config.dump_config()

pkg/persistence/migrations/dbm009_pipeline_extension_preferences.py

@@ -0,0 +1,20 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(9)
+class DBMigratePipelineExtensionPreferences(migration.DBMigration):
+    """Pipeline extension preferences"""
+
+    async def upgrade(self):
+        """Upgrade"""
+
+        sql_text = sqlalchemy.text(
+            "ALTER TABLE legacy_pipelines ADD COLUMN extensions_preferences JSON NOT NULL DEFAULT '{}'"
+        )
+        await self.ap.persistence_mgr.execute_async(sql_text)
+
+    async def downgrade(self):
+        """Downgrade"""
+        sql_text = sqlalchemy.text('ALTER TABLE legacy_pipelines DROP COLUMN extensions_preferences')
+        await self.ap.persistence_mgr.execute_async(sql_text)

pkg/persistence/migrations/dbm010_pipeline_multi_knowledge_base.py

@@ -0,0 +1,88 @@
+from .. import migration
+
+import sqlalchemy
+
+from ...entity.persistence import pipeline as persistence_pipeline
+
+
+@migration.migration_class(10)
+class DBMigratePipelineMultiKnowledgeBase(migration.DBMigration):
+    """Pipeline support multiple knowledge base binding"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            # Convert knowledge-base from string to array
+            if 'local-agent' in config['ai']:
+                current_kb = config['ai']['local-agent'].get('knowledge-base', '')
+                
+                # If it's already a list, skip
+                if isinstance(current_kb, list):
+                    continue
+                
+                # Convert string to list
+                if current_kb and current_kb != '__none__':
+                    config['ai']['local-agent']['knowledge-bases'] = [current_kb]
+                else:
+                    config['ai']['local-agent']['knowledge-bases'] = []
+                
+                # Remove old field
+                if 'knowledge-base' in config['ai']['local-agent']:
+                    del config['ai']['local-agent']['knowledge-base']
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )
+
+    async def downgrade(self):
+        """Downgrade"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            # Convert knowledge-bases from array back to string
+            if 'local-agent' in config['ai']:
+                current_kbs = config['ai']['local-agent'].get('knowledge-bases', [])
+                
+                # If it's already a string, skip
+                if isinstance(current_kbs, str):
+                    continue
+                
+                # Convert list to string (take first one or empty)
+                if current_kbs and len(current_kbs) > 0:
+                    config['ai']['local-agent']['knowledge-base'] = current_kbs[0]
+                else:
+                    config['ai']['local-agent']['knowledge-base'] = ''
+                
+                # Remove new field
+                if 'knowledge-bases' in config['ai']['local-agent']:
+                    del config['ai']['local-agent']['knowledge-bases']
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )

pkg/persistence/migrations/dbm011_dify_base_prompt_config.py

@@ -0,0 +1,40 @@
+from .. import migration
+
+import sqlalchemy
+
+from ...entity.persistence import pipeline as persistence_pipeline
+
+
+@migration.migration_class(11)
+class DBMigrateDifyApiConfig(migration.DBMigration):
+    """Langflow API config"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            if 'base-prompt' not in config['ai']['dify-service-api']:
+                config['ai']['dify-service-api']['base-prompt'] = (
+                    'When the file content is readable, please read the content of this file. When the file is an image, describe the content of this image.',
+                )
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

pkg/pipeline/longtext/longtext.py

@@ -21,10 +21,15 @@ class LongTextProcessStage(stage.PipelineStage):
         - resp_message_chain
     """
 
-    strategy_impl: strategy.LongTextStrategy
+    strategy_impl: strategy.LongTextStrategy | None
 
     async def initialize(self, pipeline_config: dict):
         config = pipeline_config['output']['long-text-processing']
+
+        if config['strategy'] == 'none':
+            self.strategy_impl = None
+            return
+
         if config['strategy'] == 'image':
             use_font = config['font-path']
             try:
@@ -67,6 +72,10 @@ class LongTextProcessStage(stage.PipelineStage):
         await self.strategy_impl.initialize()
 
     async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
+        if self.strategy_impl is None:
+            self.ap.logger.debug('Long message processing strategy is not set, skip long message processing.')
+            return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
+
         # 检查是否包含非 Plain 组件
         contains_non_plain = False
 

pkg/pipeline/longtext/strategies/forward.py

@@ -26,7 +26,7 @@ class ForwardComponentStrategy(strategy_model.LongTextStrategy):
             platform_message.ForwardMessageNode(
                 sender_id=query.adapter.bot_account_id,
                 sender_name='User',
-                message_chain=platform_message.MessageChain([message]),
+                message_chain=platform_message.MessageChain([platform_message.Plain(text=message)]),
             )
         ]
 

pkg/pipeline/pipelinemgr.py

@@ -68,6 +68,12 @@ class RuntimePipeline:
 
     stage_containers: list[StageInstContainer]
     """阶段实例容器"""
+    
+    bound_plugins: list[str]
+    """绑定到此流水线的插件列表（格式：author/plugin_name）"""
+    
+    bound_mcp_servers: list[str]
+    """绑定到此流水线的MCP服务器列表（格式：uuid）"""
 
     def __init__(
         self,
@@ -78,9 +84,20 @@ class RuntimePipeline:
         self.ap = ap
         self.pipeline_entity = pipeline_entity
         self.stage_containers = stage_containers
+        
+        # Extract bound plugins and MCP servers from extensions_preferences
+        extensions_prefs = pipeline_entity.extensions_preferences or {}
+        plugin_list = extensions_prefs.get('plugins', [])
+        self.bound_plugins = [f"{p['author']}/{p['name']}" for p in plugin_list] if plugin_list else []
+        
+        mcp_server_list = extensions_prefs.get('mcp_servers', [])
+        self.bound_mcp_servers = mcp_server_list if mcp_server_list else []
 
     async def run(self, query: pipeline_query.Query):
         query.pipeline_config = self.pipeline_entity.config
+        # Store bound plugins and MCP servers in query for filtering
+        query.variables['_pipeline_bound_plugins'] = self.bound_plugins
+        query.variables['_pipeline_bound_mcp_servers'] = self.bound_mcp_servers
         await self.process_query(query)
 
     async def _check_output(self, query: pipeline_query.Query, result: pipeline_entities.StageProcessResult):
@@ -96,7 +113,7 @@ class RuntimePipeline:
             if query.pipeline_config['output']['misc']['at-sender'] and isinstance(
                 query.message_event, platform_events.GroupMessage
             ):
-                result.user_notice.insert(0, platform_message.At(query.message_event.sender.id))
+                result.user_notice.insert(0, platform_message.At(target=query.message_event.sender.id))
             if await query.adapter.is_stream_output_supported():
                 await query.adapter.reply_message_chunk(
                     message_source=query.message_event,
@@ -188,6 +205,9 @@ class RuntimePipeline:
     async def process_query(self, query: pipeline_query.Query):
         """处理请求"""
         try:
+            # Get bound plugins for this pipeline
+            bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+            
             # ======== 触发 MessageReceived 事件 ========
             event_type = (
                 events.PersonMessageReceived
@@ -203,7 +223,7 @@ class RuntimePipeline:
                 message_chain=query.message_chain,
             )
 
-            event_ctx = await self.ap.plugin_connector.emit_event(event_obj)
+            event_ctx = await self.ap.plugin_connector.emit_event(event_obj, bound_plugins)
 
             if event_ctx.is_prevented_default():
                 return
@@ -213,7 +233,7 @@ class RuntimePipeline:
             await self._execute_from_stage(0, query)
         except Exception as e:
             inst_name = query.current_stage_name if query.current_stage_name else 'unknown'
-            self.ap.logger.error(f'处理请求时出错 query_id={query.query_id} stage={inst_name} : {e}')
+            self.ap.logger.error(f'Error processing query {query.query_id} stage={inst_name} : {e}')
             self.ap.logger.error(f'Traceback: {traceback.format_exc()}')
         finally:
             self.ap.logger.debug(f'Query {query.query_id} processed')

pkg/pipeline/preproc/preproc.py

@@ -35,11 +35,17 @@ class PreProcessor(stage.PipelineStage):
         session = await self.ap.sess_mgr.get_session(query)
 
         # When not local-agent, llm_model is None
-        llm_model = (
+        try:
-            await self.ap.model_mgr.get_model_by_uuid(query.pipeline_config['ai']['local-agent']['model'])
+            llm_model = (
-            if selected_runner == 'local-agent'
+                await self.ap.model_mgr.get_model_by_uuid(query.pipeline_config['ai']['local-agent']['model'])
-            else None
+                if selected_runner == 'local-agent'
-        )
+                else None
+            )
+        except ValueError:
+            self.ap.logger.warning(
+                f'LLM model {query.pipeline_config["ai"]["local-agent"]["model"] + " "}not found or not configured'
+            )
+            llm_model = None
 
         conversation = await self.ap.sess_mgr.get_conversation(
             query,
@@ -54,12 +60,19 @@ class PreProcessor(stage.PipelineStage):
         query.prompt = conversation.prompt.copy()
         query.messages = conversation.messages.copy()
 
-        if selected_runner == 'local-agent':
+        if selected_runner == 'local-agent' and llm_model:
             query.use_funcs = []
             query.use_llm_model_uuid = llm_model.model_entity.uuid
 
             if llm_model.model_entity.abilities.__contains__('func_call'):
-                query.use_funcs = await self.ap.tool_mgr.get_all_tools()
+                # Get bound plugins and MCP servers for filtering tools
+                bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+                bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
+                query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
+
+                self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
+                self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
+                self.ap.logger.debug(f'Use funcs: {query.use_funcs}')
 
         variables = {
             'session_id': f'{query.session.launcher_type.value}_{query.session.launcher_id}',
@@ -72,7 +85,11 @@ class PreProcessor(stage.PipelineStage):
 
         # Check if this model supports vision, if not, remove all images
         # TODO this checking should be performed in runner, and in this stage, the image should be reserved
-        if selected_runner == 'local-agent' and not llm_model.model_entity.abilities.__contains__('vision'):
+        if (
+            selected_runner == 'local-agent'
+            and llm_model
+            and not llm_model.model_entity.abilities.__contains__('vision')
+        ):
             for msg in query.messages:
                 if isinstance(msg.content, list):
                     for me in msg.content:
@@ -89,15 +106,22 @@ class PreProcessor(stage.PipelineStage):
                 content_list.append(provider_message.ContentElement.from_text(me.text))
                 plain_text += me.text
             elif isinstance(me, platform_message.Image):
-                if selected_runner != 'local-agent' or llm_model.model_entity.abilities.__contains__('vision'):
+                if selected_runner != 'local-agent' or (
+                    llm_model and llm_model.model_entity.abilities.__contains__('vision')
+                ):
                     if me.base64 is not None:
                         content_list.append(provider_message.ContentElement.from_image_base64(me.base64))
+            elif isinstance(me, platform_message.File):
+                # if me.url is not None:
+                content_list.append(provider_message.ContentElement.from_file_url(me.url, me.name))
             elif isinstance(me, platform_message.Quote) and qoute_msg:
                 for msg in me.origin:
                     if isinstance(msg, platform_message.Plain):
                         content_list.append(provider_message.ContentElement.from_text(msg.text))
                     elif isinstance(msg, platform_message.Image):
-                        if selected_runner != 'local-agent' or llm_model.model_entity.abilities.__contains__('vision'):
+                        if selected_runner != 'local-agent' or (
+                            llm_model and llm_model.model_entity.abilities.__contains__('vision')
+                        ):
                             if msg.base64 is not None:
                                 content_list.append(provider_message.ContentElement.from_image_base64(msg.base64))
 
@@ -113,7 +137,9 @@ class PreProcessor(stage.PipelineStage):
             query=query,
         )
 
-        event_ctx = await self.ap.plugin_connector.emit_event(event)
+        # Get bound plugins for filtering
+        bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+        event_ctx = await self.ap.plugin_connector.emit_event(event, bound_plugins)
 
         query.prompt.messages = event_ctx.event.default_prompt
         query.messages = event_ctx.event.prompt

pkg/pipeline/process/handlers/chat.py

@@ -9,7 +9,6 @@ from .. import handler
 from ... import entities
 from ....provider import runner as runner_module
 
-import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.events as events
 from ....utils import importutil
 from ....provider import runners
@@ -44,21 +43,24 @@ class ChatMessageHandler(handler.MessageHandler):
             query=query,
         )
 
-        event_ctx = await self.ap.plugin_connector.emit_event(event)
+        # Get bound plugins for filtering
+        bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+        event_ctx = await self.ap.plugin_connector.emit_event(event, bound_plugins)
 
         is_create_card = False  # 判断下是否需要创建流式卡片
+
         if event_ctx.is_prevented_default():
-            if event_ctx.event.reply is not None:
+            if event_ctx.event.reply_message_chain is not None:
-                mc = platform_message.MessageChain(event_ctx.event.reply)
+                mc = event_ctx.event.reply_message_chain
                 query.resp_messages.append(mc)
 
                 yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
             else:
                 yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
         else:
-            if event_ctx.event.alter is not None:
+            if event_ctx.event.user_message_alter is not None:
                 # if isinstance(event_ctx.event, str):  # 现在暂时不考虑多模态alter
-                query.user_message.content = event_ctx.event.alter
+                query.user_message.content = event_ctx.event.user_message_alter
 
             text_length = 0
             try:

pkg/pipeline/process/handlers/command.py

@@ -5,7 +5,6 @@ import typing
 from .. import handler
 from ... import entities
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
-import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 import langbot_plugin.api.entities.events as events
@@ -46,11 +45,13 @@ class CommandHandler(handler.MessageHandler):
             query=query,
         )
 
-        event_ctx = await self.ap.plugin_connector.emit_event(event)
+        # Get bound plugins for filtering
+        bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+        event_ctx = await self.ap.plugin_connector.emit_event(event, bound_plugins)
 
         if event_ctx.is_prevented_default():
-            if event_ctx.event.reply is not None:
+            if event_ctx.event.reply_message_chain is not None:
-                mc = platform_message.MessageChain(event_ctx.event.reply)
+                mc = event_ctx.event.reply_message_chain
 
                 query.resp_messages.append(mc)
 
@@ -59,9 +60,6 @@ class CommandHandler(handler.MessageHandler):
                 yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
 
         else:
-            if event_ctx.event.alter is not None:
-                query.message_chain = platform_message.MessageChain([platform_message.Plain(event_ctx.event.alter)])
-
             session = await self.ap.sess_mgr.get_session(query)
 
             async for ret in self.ap.cmd_mgr.execute(
@@ -78,7 +76,12 @@ class CommandHandler(handler.MessageHandler):
                     self.ap.logger.info(f'Command({query.query_id}) error: {self.cut_str(str(ret.error))}')
 
                     yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
-                elif ret.text is not None or ret.image_url is not None or ret.image_base64 is not None:
+                elif (
+                    ret.text is not None
+                    or ret.image_url is not None
+                    or ret.image_base64 is not None
+                    or ret.file_url is not None
+                ):
                     content: list[provider_message.ContentElement] = []
 
                     if ret.text is not None:
@@ -90,6 +93,9 @@ class CommandHandler(handler.MessageHandler):
                     if ret.image_base64 is not None:
                         content.append(provider_message.ContentElement.from_image_base64(ret.image_base64))
 
+                    if ret.file_url is not None:
+                        # 此时为 file 类型
+                        content.append(provider_message.ContentElement.from_file_url(ret.file_url, ret.file_name))
                     query.resp_messages.append(
                         provider_message.Message(
                             role='command',

pkg/pipeline/respback/respback.py

@@ -33,7 +33,7 @@ class SendResponseBackStage(stage.PipelineStage):
         if query.pipeline_config['output']['misc']['at-sender'] and isinstance(
             query.message_event, platform_events.GroupMessage
         ):
-            query.resp_message_chain[-1].insert(0, platform_message.At(query.message_event.sender.id))
+            query.resp_message_chain[-1].insert(0, platform_message.At(target=query.message_event.sender.id))
 
         quote_origin = query.pipeline_config['output']['misc']['quote-origin']
 

pkg/pipeline/resprule/rules/atbot.py

@@ -16,26 +16,17 @@ class AtBotRule(rule_model.GroupRespondRule):
         rule_dict: dict,
         query: pipeline_query.Query,
     ) -> entities.RuleJudgeResult:
+        found = False
+
         def remove_at(message_chain: platform_message.MessageChain):
+            nonlocal found
             for component in message_chain.root:
-                if isinstance(component, platform_message.At) and component.target == query.adapter.bot_account_id:
+                if isinstance(component, platform_message.At) and str(component.target) == str(query.adapter.bot_account_id):
                     message_chain.remove(component)
+                    found = True
                     break
 
         remove_at(message_chain)
         remove_at(message_chain)  # 回复消息时会at两次，检查并删除重复的
 
-        # if message_chain.has(platform_message.At(query.adapter.bot_account_id)) and rule_dict['at']:
+        return entities.RuleJudgeResult(matching=found, replacement=message_chain)
-        #     message_chain.remove(platform_message.At(query.adapter.bot_account_id))
-
-        #     if message_chain.has(
-        #         platform_message.At(query.adapter.bot_account_id)
-        #     ):  # 回复消息时会at两次，检查并删除重复的
-        #         message_chain.remove(platform_message.At(query.adapter.bot_account_id))
-
-        #     return entities.RuleJudgeResult(
-        #         matching=True,
-        #         replacement=message_chain,
-        #     )
-
-        return entities.RuleJudgeResult(matching=False, replacement=message_chain)

pkg/pipeline/wrapper/wrapper.py

@@ -72,7 +72,9 @@ class ResponseWrapper(stage.PipelineStage):
                             query=query,
                         )
 
-                        event_ctx = await self.ap.plugin_connector.emit_event(event)
+                        # Get bound plugins for filtering
+                        bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+                        event_ctx = await self.ap.plugin_connector.emit_event(event, bound_plugins)
 
                         if event_ctx.is_prevented_default():
                             yield entities.StageProcessResult(
@@ -80,8 +82,8 @@ class ResponseWrapper(stage.PipelineStage):
                                 new_query=query,
                             )
                         else:
-                            if event_ctx.event.reply is not None:
+                            if event_ctx.event.reply_message_chain is not None:
-                                query.resp_message_chain.append(platform_message.MessageChain(event_ctx.event.reply))
+                                query.resp_message_chain.append(event_ctx.event.reply_message_chain)
 
                             else:
                                 query.resp_message_chain.append(result.get_content_platform_message_chain())
@@ -115,7 +117,9 @@ class ResponseWrapper(stage.PipelineStage):
                                 query=query,
                             )
 
-                            event_ctx = await self.ap.plugin_connector.emit_event(event)
+                            # Get bound plugins for filtering
+                            bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+                            event_ctx = await self.ap.plugin_connector.emit_event(event, bound_plugins)
 
                             if event_ctx.is_prevented_default():
                                 yield entities.StageProcessResult(
@@ -123,10 +127,8 @@ class ResponseWrapper(stage.PipelineStage):
                                     new_query=query,
                                 )
                             else:
-                                if event_ctx.event.reply is not None:
+                                if event_ctx.event.reply_message_chain is not None:
-                                    query.resp_message_chain.append(
+                                    query.resp_message_chain.append(event_ctx.event.reply_message_chain)
-                                        platform_message.MessageChain(text=event_ctx.event.reply)
-                                    )
 
                                 else:
                                     query.resp_message_chain.append(

pkg/platform/botmgr.py

@@ -13,6 +13,7 @@ from ..entity.persistence import bot as persistence_bot
 from ..entity.errors import platform as platform_errors
 
 from .logger import EventLogger
+from .webhook_pusher import WebhookPusher
 
 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
@@ -66,6 +67,14 @@ class RuntimeBot:
                 message_session_id=f'person_{event.sender.id}',
             )
 
+            # Push to webhooks
+            if hasattr(self.ap, 'webhook_pusher') and self.ap.webhook_pusher:
+                asyncio.create_task(
+                    self.ap.webhook_pusher.push_person_message(
+                        event, self.bot_entity.uuid, adapter.__class__.__name__
+                    )
+                )
+
             await self.ap.query_pool.add_query(
                 bot_uuid=self.bot_entity.uuid,
                 launcher_type=provider_session.LauncherTypes.PERSON,
@@ -91,6 +100,14 @@ class RuntimeBot:
                 message_session_id=f'group_{event.group.id}',
             )
 
+            # Push to webhooks
+            if hasattr(self.ap, 'webhook_pusher') and self.ap.webhook_pusher:
+                asyncio.create_task(
+                    self.ap.webhook_pusher.push_group_message(
+                        event, self.bot_entity.uuid, adapter.__class__.__name__
+                    )
+                )
+
             await self.ap.query_pool.add_query(
                 bot_uuid=self.bot_entity.uuid,
                 launcher_type=provider_session.LauncherTypes.GROUP,
@@ -157,6 +174,9 @@ class PlatformManager:
         self.adapter_dict = {}
 
     async def initialize(self):
+        # delete all bot log images
+        await self.ap.storage_mgr.storage_provider.delete_dir_recursive('bot_log_images')
+
         self.adapter_components = self.ap.discover.get_components_by_kind('MessagePlatformAdapter')
         adapter_dict: dict[str, type[abstract_platform_adapter.AbstractMessagePlatformAdapter]] = {}
         for component in self.adapter_components:

pkg/platform/logger.py

@@ -149,7 +149,7 @@ class EventLogger(abstract_platform_event_logger.AbstractEventLogger):
                 extension = mimetypes.guess_extension(mime_type)
                 if extension is None:
                     extension = '.jpg'
-                image_key = f'{message_session_id}-{uuid.uuid4()}{extension}'
+                image_key = f'bot_log_images/{message_session_id}-{uuid.uuid4()}{extension}'
                 await self.ap.storage_mgr.storage_provider.save(image_key, img_bytes)
                 image_keys.append(image_key)
 

pkg/platform/sources/dingtalk.py

@@ -1,3 +1,4 @@
+
 import traceback
 import typing
 from libs.dingtalk_api.dingtalkevent import DingTalkEvent
@@ -36,14 +37,31 @@ class DingTalkMessageConverter(abstract_platform_adapter.AbstractMessageConverte
             if atUser.dingtalk_id == event.incoming_message.chatbot_user_id:
                 yiri_msg_list.append(platform_message.At(target=bot_name))
 
-        if event.content:
+        if event.rich_content:
-            text_content = event.content.replace('@' + bot_name, '')
+            elements = event.rich_content.get("Elements")
-            yiri_msg_list.append(platform_message.Plain(text=text_content))
+            for element in elements:
-        if event.picture:
+                if element.get('Type') == 'text':
-            yiri_msg_list.append(platform_message.Image(base64=event.picture))
+                    text = element.get('Content', '').replace('@' + bot_name, '')
+                    if text.strip():
+                        yiri_msg_list.append(platform_message.Plain(text=text))
+                elif element.get('Type') == 'image' and element.get('Picture'):
+                    yiri_msg_list.append(platform_message.Image(base64=element['Picture']))
+        else:
+            # 回退到原有简单逻辑
+            if event.content:
+                text_content = event.content.replace('@' + bot_name, '')
+                yiri_msg_list.append(platform_message.Plain(text=text_content))
+            if event.picture:
+                yiri_msg_list.append(platform_message.Image(base64=event.picture))
+
+            # 处理其他类型消息（文件、音频等）
+        if event.file:
+            yiri_msg_list.append(platform_message.File(url=event.file, name=event.name))
         if event.audio:
             yiri_msg_list.append(platform_message.Voice(base64=event.audio))
 
+
+
         chain = platform_message.MessageChain(yiri_msg_list)
 
         return chain

pkg/platform/sources/discord.py

@@ -22,6 +22,7 @@ import langbot_plugin.api.definition.abstract.platform.event_logger as abstract_
 from ..logger import EventLogger
 
 
+
 # 语音功能相关异常定义
 class VoiceConnectionError(Exception):
     """语音连接基础异常"""

pkg/platform/sources/qqofficial.py

@@ -139,19 +139,15 @@ class QQOfficialAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter
     event_converter: QQOfficialEventConverter = QQOfficialEventConverter()
 
     def __init__(self, config: dict, logger: EventLogger):
-        self.config = config
+        bot = QQOfficialClient(
-        self.logger = logger
+            app_id=config['appid'], secret=config['secret'], token=config['token'], logger=logger
+        )
 
-        required_keys = [
+        super().__init__(
-            'appid',
+            config=config,
-            'secret',
+            logger=logger,
-        ]
+            bot=bot,
-        missing_keys = [key for key in required_keys if key not in config]
+            bot_account_id=config['appid'],
-        if missing_keys:
-            raise command_errors.ParamNotEnoughError('QQ官方机器人缺少相关配置项，请查看文档或联系管理员')
-
-        self.bot = QQOfficialClient(
-            app_id=config['appid'], secret=config['secret'], token=config['token'], logger=self.logger
         )
 
     async def reply_message(

pkg/platform/sources/telegram.py

@@ -102,7 +102,7 @@ class TelegramEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 sender=platform_entities.Friend(
                     id=event.effective_chat.id,
                     nickname=event.effective_chat.first_name,
-                    remark=event.effective_chat.id,
+                    remark=str(event.effective_chat.id),
                 ),
                 message_chain=lb_message,
                 time=event.message.date.timestamp(),

pkg/platform/sources/wechatpad.py

@@ -139,7 +139,7 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
             pattern = r'@\S{1,20}'
             content_no_preifx = re.sub(pattern, '', content_no_preifx)
 
-        return platform_message.MessageChain([platform_message.Plain(content_no_preifx)])
+        return platform_message.MessageChain([platform_message.Plain(text=content_no_preifx)])
 
     async def _handler_image(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
         """处理图像消息 (msg_type=3)"""
@@ -265,7 +265,7 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
             # 文本消息
             try:
                 if '<msg>' not in quote_data:
-                    quote_data_message_list.append(platform_message.Plain(quote_data))
+                    quote_data_message_list.append(platform_message.Plain(text=quote_data))
                 else:
                     # 引用消息展开
                     quote_data_xml = ET.fromstring(quote_data)
@@ -280,7 +280,7 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
                         quote_data_message_list.extend(await self._handler_compound(None, quote_data))
             except Exception as e:
                 self.logger.error(f'处理引用消息异常 expcetion:{e}')
-                quote_data_message_list.append(platform_message.Plain(quote_data))
+                quote_data_message_list.append(platform_message.Plain(text=quote_data))
             message_list.append(
                 platform_message.Quote(
                     sender_id=sender_id,
@@ -290,7 +290,7 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
             if len(user_data) > 0:
                 pattern = r'@\S{1,20}'
                 user_data = re.sub(pattern, '', user_data)
-                message_list.append(platform_message.Plain(user_data))
+                message_list.append(platform_message.Plain(text=user_data))
 
         return platform_message.MessageChain(message_list)
 
@@ -543,7 +543,6 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
     ] = {}
 
     def __init__(self, config: dict, logger: EventLogger):
-
         quart_app = quart.Quart(__name__)
 
         message_converter = WeChatPadMessageConverter(config, logger)
@@ -551,15 +550,14 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
         bot = WeChatPadClient(config['wechatpad_url'], config['token'])
         super().__init__(
             config=config,
-            logger = logger,
+            logger=logger,
-            quart_app = quart_app,
+            quart_app=quart_app,
-            message_converter =message_converter,
+            message_converter=message_converter,
-            event_converter = event_converter,
+            event_converter=event_converter,
             listeners={},
-            bot_account_id ='',
+            bot_account_id='',
-            name="WeChatPad",
+            name='WeChatPad',
             bot=bot,
-
         )
 
     async def ws_message(self, data):

pkg/platform/sources/wecombot.py

@@ -49,7 +49,7 @@ class WecomBotEventConverter(abstract_platform_adapter.AbstractEventConverter):
             return platform_events.FriendMessage(
                 sender=platform_entities.Friend(
                     id=event.userid,
-                    nickname='',
+                    nickname=event.username,
                     remark='',
                 ),
                 message_chain=message_chain,
@@ -61,10 +61,10 @@ class WecomBotEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 sender = platform_entities.GroupMember(
                     id=event.userid,
                     permission='MEMBER',
-                    member_name=event.userid,
+                    member_name=event.username,
                     group=platform_entities.Group(
                         id=str(event.chatid),
-                        name='',
+                        name=event.chatname,
                         permission=platform_entities.Permission.Member,
                     ),
                     special_title='',
@@ -117,6 +117,50 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         content = await self.message_converter.yiri2target(message)
         await self.bot.set_message(message_source.source_platform_object.message_id, content)
 
+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        """将流水线增量输出写入企业微信 stream 会话。
+
+        Args:
+            message_source: 流水线提供的原始消息事件。
+            bot_message: 当前片段对应的模型元信息（未使用）。
+            message: 需要回复的消息链。
+            quote_origin: 是否引用原消息（企业微信暂不支持）。
+            is_final: 标记当前片段是否为最终回复。
+
+        Returns:
+            dict: 包含 `stream` 键，标识写入是否成功。
+
+        Example:
+            在流水线 `reply_message_chunk` 调用中自动触发，无需手动调用。
+        """
+        # 转换为纯文本（智能机器人当前协议仅支持文本流）
+        content = await self.message_converter.yiri2target(message)
+        msg_id = message_source.source_platform_object.message_id
+
+        # 将片段推送到 WecomBotClient 中的队列，返回值用于判断是否走降级逻辑
+        success = await self.bot.push_stream_chunk(msg_id, content, is_final=is_final)
+        if not success and is_final:
+            # 未命中流式队列时使用旧有 set_message 兜底
+            await self.bot.set_message(msg_id, content)
+        return {'stream': success}
+
+    async def is_stream_output_supported(self) -> bool:
+        """智能机器人侧默认开启流式能力。
+
+        Returns:
+            bool: 恒定返回 True。
+
+        Example:
+            流水线执行阶段会调用此方法以确认是否启用流式。"""
+        return True
+
     async def send_message(self, target_type, target_id, message):
         pass
 

pkg/platform/webhook_pusher.py

@@ -0,0 +1,106 @@
+from __future__ import annotations
+
+import asyncio
+import logging
+import aiohttp
+import uuid
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from ..core import app
+
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
+
+
+class WebhookPusher:
+    """Push bot events to configured webhooks"""
+
+    ap: app.Application
+    logger: logging.Logger
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+        self.logger = self.ap.logger
+
+    async def push_person_message(self, event: platform_events.FriendMessage, bot_uuid: str, adapter_name: str) -> None:
+        """Push person message event to webhooks"""
+        try:
+            webhooks = await self.ap.webhook_service.get_enabled_webhooks()
+            if not webhooks:
+                return
+
+            # Build payload
+            payload = {
+                'uuid': str(uuid.uuid4()),  # unique id for the event
+                'event_type': 'bot.person_message',
+                'data': {
+                    'bot_uuid': bot_uuid,
+                    'adapter_name': adapter_name,
+                    'sender': {
+                        'id': str(event.sender.id),
+                        'name': getattr(event.sender, 'name', ''),
+                    },
+                    'message': event.message_chain.model_dump(),
+                    'timestamp': event.time if hasattr(event, 'time') else None,
+                },
+            }
+
+            # Push to all webhooks asynchronously
+            tasks = [self._push_to_webhook(webhook['url'], payload) for webhook in webhooks]
+            await asyncio.gather(*tasks, return_exceptions=True)
+
+        except Exception as e:
+            self.logger.error(f'Failed to push person message to webhooks: {e}')
+
+    async def push_group_message(self, event: platform_events.GroupMessage, bot_uuid: str, adapter_name: str) -> None:
+        """Push group message event to webhooks"""
+        try:
+            webhooks = await self.ap.webhook_service.get_enabled_webhooks()
+            if not webhooks:
+                return
+
+            # Build payload
+            payload = {
+                'uuid': str(uuid.uuid4()),  # unique id for the event
+                'event_type': 'bot.group_message',
+                'data': {
+                    'bot_uuid': bot_uuid,
+                    'adapter_name': adapter_name,
+                    'group': {
+                        'id': str(event.group.id),
+                        'name': getattr(event.group, 'name', ''),
+                    },
+                    'sender': {
+                        'id': str(event.sender.id),
+                        'name': getattr(event.sender, 'name', ''),
+                    },
+                    'message': event.message_chain.model_dump(),
+                    'timestamp': event.time if hasattr(event, 'time') else None,
+                },
+            }
+
+            # Push to all webhooks asynchronously
+            tasks = [self._push_to_webhook(webhook['url'], payload) for webhook in webhooks]
+            await asyncio.gather(*tasks, return_exceptions=True)
+
+        except Exception as e:
+            self.logger.error(f'Failed to push group message to webhooks: {e}')
+
+    async def _push_to_webhook(self, url: str, payload: dict) -> None:
+        """Push payload to a single webhook URL"""
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    url,
+                    json=payload,
+                    headers={'Content-Type': 'application/json'},
+                    timeout=aiohttp.ClientTimeout(total=15),
+                ) as response:
+                    if response.status >= 400:
+                        self.logger.warning(f'Webhook {url} returned status {response.status}')
+                    else:
+                        self.logger.debug(f'Successfully pushed to webhook {url}')
+        except asyncio.TimeoutError:
+            self.logger.warning(f'Timeout pushing to webhook {url}')
+        except Exception as e:
+            self.logger.warning(f'Error pushing to webhook {url}: {e}')

pkg/plugin/connector.py

@@ -6,19 +6,24 @@ from typing import Any
 import typing
 import os
 import sys
-
+import httpx
 from async_lru import alru_cache
 
 from ..core import app
 from . import handler
 from ..utils import platform
-from langbot_plugin.runtime.io.controllers.stdio import client as stdio_client_controller
+from langbot_plugin.runtime.io.controllers.stdio import (
+    client as stdio_client_controller,
+)
 from langbot_plugin.runtime.io.controllers.ws import client as ws_client_controller
 from langbot_plugin.api.entities import events
 from langbot_plugin.api.entities import context
 import langbot_plugin.runtime.io.connection as base_connection
 from langbot_plugin.api.definition.components.manifest import ComponentManifest
-from langbot_plugin.api.entities.builtin.command import context as command_context
+from langbot_plugin.api.entities.builtin.command import (
+    context as command_context,
+    errors as command_errors,
+)
 from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
 from ..core import taskmgr
 
@@ -32,14 +37,23 @@ class PluginRuntimeConnector:
 
     handler_task: asyncio.Task
 
+    heartbeat_task: asyncio.Task | None = None
+
     stdio_client_controller: stdio_client_controller.StdioClientController
 
     ctrl: stdio_client_controller.StdioClientController | ws_client_controller.WebSocketClientController
 
+    runtime_subprocess_on_windows: asyncio.subprocess.Process | None = None
+
+    runtime_subprocess_on_windows_task: asyncio.Task | None = None
+
     runtime_disconnect_callback: typing.Callable[
         [PluginRuntimeConnector], typing.Coroutine[typing.Any, typing.Any, None]
     ]
 
+    is_enable_plugin: bool = True
+    """Mark if the plugin system is enabled"""
+
     def __init__(
         self,
         ap: app.Application,
@@ -49,10 +63,26 @@ class PluginRuntimeConnector:
     ):
         self.ap = ap
         self.runtime_disconnect_callback = runtime_disconnect_callback
+        self.is_enable_plugin = self.ap.instance_config.data.get('plugin', {}).get('enable', True)
+
+    async def heartbeat_loop(self):
+        while True:
+            await asyncio.sleep(20)
+            try:
+                await self.ping_plugin_runtime()
+                self.ap.logger.debug('Heartbeat to plugin runtime success.')
+            except Exception as e:
+                self.ap.logger.debug(f'Failed to heartbeat to plugin runtime: {e}')
 
     async def initialize(self):
+        if not self.is_enable_plugin:
+            self.ap.logger.info('Plugin system is disabled.')
+            return
+
         async def new_connection_callback(connection: base_connection.Connection):
-            async def disconnect_callback(rchandler: handler.RuntimeConnectionHandler) -> bool:
+            async def disconnect_callback(
+                rchandler: handler.RuntimeConnectionHandler,
+            ) -> bool:
                 if platform.get_platform() == 'docker' or platform.use_websocket_to_connect_plugin_runtime():
                     self.ap.logger.error('Disconnected from plugin runtime, trying to reconnect...')
                     await self.runtime_disconnect_callback(self)
@@ -64,6 +94,7 @@ class PluginRuntimeConnector:
                     return False
 
             self.handler = handler.RuntimeConnectionHandler(connection, disconnect_callback, self.ap)
+
             self.handler_task = asyncio.create_task(self.handler.run())
             _ = await self.handler.ping()
             self.ap.logger.info('Connected to plugin runtime.')
@@ -77,8 +108,14 @@ class PluginRuntimeConnector:
                 'runtime_ws_url', 'ws://langbot_plugin_runtime:5400/control/ws'
             )
 
-            async def make_connection_failed_callback(ctrl: ws_client_controller.WebSocketClientController) -> None:
+            async def make_connection_failed_callback(
-                self.ap.logger.error('Failed to connect to plugin runtime, trying to reconnect...')
+                ctrl: ws_client_controller.WebSocketClientController,
+                exc: Exception = None,
+            ) -> None:
+                if exc is not None:
+                    self.ap.logger.error(f'Failed to connect to plugin runtime({ws_url}): {exc}')
+                else:
+                    self.ap.logger.error(f'Failed to connect to plugin runtime({ws_url}), trying to reconnect...')
                 await self.runtime_disconnect_callback(self)
 
             self.ctrl = ws_client_controller.WebSocketClientController(
@@ -86,6 +123,42 @@ class PluginRuntimeConnector:
                 make_connection_failed_callback=make_connection_failed_callback,
             )
             task = self.ctrl.run(new_connection_callback)
+        elif platform.get_platform() == 'win32':
+            # Due to Windows's lack of supports for both stdio and subprocess:
+            # See also: https://docs.python.org/zh-cn/3.13/library/asyncio-platforms.html
+            # We have to launch runtime via cmd but communicate via ws.
+            self.ap.logger.info('(windows) use cmd to launch plugin runtime and communicate via ws')
+            
+            if self.runtime_subprocess_on_windows is None:  # only launch once
+                python_path = sys.executable
+                env = os.environ.copy()
+                self.runtime_subprocess_on_windows = await asyncio.create_subprocess_exec(
+                    python_path,
+                    '-m', 'langbot_plugin.cli.__init__', 'rt',
+                    env=env,
+                )
+
+                # hold the process
+                self.runtime_subprocess_on_windows_task = asyncio.create_task(self.runtime_subprocess_on_windows.wait())
+
+            ws_url = 'ws://localhost:5400/control/ws'
+
+            async def make_connection_failed_callback(
+                ctrl: ws_client_controller.WebSocketClientController,
+                exc: Exception = None,
+            ) -> None:
+                if exc is not None:
+                    self.ap.logger.error(f'(windows) Failed to connect to plugin runtime({ws_url}): {exc}')
+                else:
+                    self.ap.logger.error(f'(windows) Failed to connect to plugin runtime({ws_url}), trying to reconnect...')
+                await self.runtime_disconnect_callback(self)
+            
+            self.ctrl = ws_client_controller.WebSocketClientController(
+                ws_url=ws_url,
+                make_connection_failed_callback=make_connection_failed_callback,
+            )
+            task = self.ctrl.run(new_connection_callback)
+
         else:  # stdio
             self.ap.logger.info('use stdio to connect to plugin runtime')
             # cmd: lbp rt -s
@@ -98,17 +171,53 @@ class PluginRuntimeConnector:
             )
             task = self.ctrl.run(new_connection_callback)
 
+        if self.heartbeat_task is None:
+            self.heartbeat_task = asyncio.create_task(self.heartbeat_loop())
+
         asyncio.create_task(task)
 
     async def initialize_plugins(self):
         pass
 
+    async def ping_plugin_runtime(self):
+        if not hasattr(self, 'handler'):
+            raise Exception('Plugin runtime is not connected')
+
+        return await self.handler.ping()
+
     async def install_plugin(
         self,
         install_source: PluginInstallSource,
         install_info: dict[str, Any],
         task_context: taskmgr.TaskContext | None = None,
     ):
+        if install_source == PluginInstallSource.LOCAL:
+            # transfer file before install
+            file_bytes = install_info['plugin_file']
+            file_key = await self.handler.send_file(file_bytes, 'lbpkg')
+            install_info['plugin_file_key'] = file_key
+            del install_info['plugin_file']
+            self.ap.logger.info(f'Transfered file {file_key} to plugin runtime')
+        elif install_source == PluginInstallSource.GITHUB:
+            # download and transfer file
+            try:
+                async with httpx.AsyncClient(
+                    trust_env=True,
+                    follow_redirects=True,
+                    timeout=20,
+                ) as client:
+                    response = await client.get(
+                        install_info['asset_url'],
+                    )
+                    response.raise_for_status()
+                    file_bytes = response.content
+                    file_key = await self.handler.send_file(file_bytes, 'lbpkg')
+                    install_info['plugin_file_key'] = file_key
+                    self.ap.logger.info(f'Transfered file {file_key} to plugin runtime')
+            except Exception as e:
+                self.ap.logger.error(f'Failed to download file from GitHub: {e}')
+                raise Exception(f'Failed to download file from GitHub: {e}')
+
         async for ret in self.handler.install_plugin(install_source.value, install_info):
             current_action = ret.get('current_action', None)
             if current_action is not None:
@@ -121,7 +230,10 @@ class PluginRuntimeConnector:
                     task_context.trace(trace)
 
     async def upgrade_plugin(
-        self, plugin_author: str, plugin_name: str, task_context: taskmgr.TaskContext | None = None
+        self,
+        plugin_author: str,
+        plugin_name: str,
+        task_context: taskmgr.TaskContext | None = None,
     ) -> dict[str, Any]:
         async for ret in self.handler.upgrade_plugin(plugin_author, plugin_name):
             current_action = ret.get('current_action', None)
@@ -135,7 +247,11 @@ class PluginRuntimeConnector:
                     task_context.trace(trace)
 
     async def delete_plugin(
-        self, plugin_author: str, plugin_name: str, task_context: taskmgr.TaskContext | None = None
+        self,
+        plugin_author: str,
+        plugin_name: str,
+        delete_data: bool = False,
+        task_context: taskmgr.TaskContext | None = None,
     ) -> dict[str, Any]:
         async for ret in self.handler.delete_plugin(plugin_author, plugin_name):
             current_action = ret.get('current_action', None)
@@ -148,7 +264,16 @@ class PluginRuntimeConnector:
                 if task_context is not None:
                     task_context.trace(trace)
 
+        # Clean up plugin settings and binary storage if requested
+        if delete_data:
+            if task_context is not None:
+                task_context.trace('Cleaning up plugin configuration and storage...')
+            await self.handler.cleanup_plugin_data(plugin_author, plugin_name)
+
     async def list_plugins(self) -> list[dict[str, Any]]:
+        if not self.is_enable_plugin:
+            return []
+
         return await self.handler.list_plugins()
 
     async def get_plugin_info(self, author: str, plugin_name: str) -> dict[str, Any]:
@@ -164,32 +289,62 @@ class PluginRuntimeConnector:
     async def emit_event(
         self,
         event: events.BaseEventModel,
+        bound_plugins: list[str] | None = None,
     ) -> context.EventContext:
         event_ctx = context.EventContext.from_event(event)
 
-        event_ctx_result = await self.handler.emit_event(event_ctx.model_dump(serialize_as_any=True))
+        if not self.is_enable_plugin:
+            return event_ctx
+
+        # Pass include_plugins to runtime for filtering
+        event_ctx_result = await self.handler.emit_event(
+            event_ctx.model_dump(serialize_as_any=False), include_plugins=bound_plugins
+        )
 
         event_ctx = context.EventContext.model_validate(event_ctx_result['event_context'])
 
         return event_ctx
 
-    async def list_tools(self) -> list[ComponentManifest]:
+    async def list_tools(self, bound_plugins: list[str] | None = None) -> list[ComponentManifest]:
-        list_tools_data = await self.handler.list_tools()
+        if not self.is_enable_plugin:
+            return []
 
-        return [ComponentManifest.model_validate(tool) for tool in list_tools_data]
+        # Pass include_plugins to runtime for filtering
+        list_tools_data = await self.handler.list_tools(include_plugins=bound_plugins)
 
-    async def call_tool(self, tool_name: str, parameters: dict[str, Any]) -> dict[str, Any]:
+        tools = [ComponentManifest.model_validate(tool) for tool in list_tools_data]
-        return await self.handler.call_tool(tool_name, parameters)
 
-    async def list_commands(self) -> list[ComponentManifest]:
+        return tools
-        list_commands_data = await self.handler.list_commands()
 
-        return [ComponentManifest.model_validate(command) for command in list_commands_data]
+    async def call_tool(
+        self, tool_name: str, parameters: dict[str, Any], bound_plugins: list[str] | None = None
+    ) -> dict[str, Any]:
+        if not self.is_enable_plugin:
+            return {'error': 'Tool not found: plugin system is disabled'}
+
+        # Pass include_plugins to runtime for validation
+        return await self.handler.call_tool(tool_name, parameters, include_plugins=bound_plugins)
+
+    async def list_commands(self, bound_plugins: list[str] | None = None) -> list[ComponentManifest]:
+        if not self.is_enable_plugin:
+            return []
+
+        # Pass include_plugins to runtime for filtering
+        list_commands_data = await self.handler.list_commands(include_plugins=bound_plugins)
+
+        commands = [ComponentManifest.model_validate(command) for command in list_commands_data]
+
+        return commands
 
     async def execute_command(
-        self, command_ctx: command_context.ExecuteContext
+        self, command_ctx: command_context.ExecuteContext, bound_plugins: list[str] | None = None
     ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
-        gen = self.handler.execute_command(command_ctx.model_dump(serialize_as_any=True))
+        if not self.is_enable_plugin:
+            yield command_context.CommandReturn(error=command_errors.CommandNotFoundError(command_ctx.command))
+            return
+
+        # Pass include_plugins to runtime for validation
+        gen = self.handler.execute_command(command_ctx.model_dump(serialize_as_any=True), include_plugins=bound_plugins)
 
         async for ret in gen:
             cmd_ret = command_context.CommandReturn.model_validate(ret)
@@ -197,6 +352,13 @@ class PluginRuntimeConnector:
             yield cmd_ret
 
     def dispose(self):
-        if isinstance(self.ctrl, stdio_client_controller.StdioClientController):
+        # No need to consider the shutdown on Windows
+        # for Windows can kill processes and subprocesses chainly
+
+        if self.is_enable_plugin and isinstance(self.ctrl, stdio_client_controller.StdioClientController):
             self.ap.logger.info('Terminating plugin runtime process...')
             self.ctrl.process.terminate()
+
+        if self.heartbeat_task is not None:
+            self.heartbeat_task.cancel()
+            self.heartbeat_task = None

pkg/plugin/handler.py

@@ -56,7 +56,9 @@ class RuntimeConnectionHandler(handler.Handler):
                     .where(persistence_plugin.PluginSetting.plugin_name == plugin_name)
                 )
 
-                if result.first() is not None:
+                setting = result.first()
+
+                if setting is not None:
                     # delete plugin setting
                     await self.ap.persistence_mgr.execute_async(
                         sqlalchemy.delete(persistence_plugin.PluginSetting)
@@ -71,6 +73,10 @@ class RuntimeConnectionHandler(handler.Handler):
                         plugin_name=plugin_name,
                         install_source=install_source,
                         install_info=install_info,
+                        # inherit from existing setting
+                        enabled=setting.enabled if setting is not None else True,
+                        priority=setting.priority if setting is not None else 0,
+                        config=setting.config if setting is not None else {},  # noqa: F821
                     )
                 )
 
@@ -292,7 +298,7 @@ class RuntimeConnectionHandler(handler.Handler):
         @self.action(PluginToRuntimeAction.GET_LLM_MODELS)
         async def get_llm_models(data: dict[str, Any]) -> handler.ActionResponse:
             """Get llm models"""
-            llm_models = await self.ap.model_service.get_llm_models(include_secret=False)
+            llm_models = await self.ap.llm_model_service.get_llm_models(include_secret=False)
             return handler.ActionResponse.success(
                 data={
                     'llm_models': llm_models,
@@ -430,6 +436,25 @@ class RuntimeConnectionHandler(handler.Handler):
                 },
             )
 
+        @self.action(RuntimeToLangBotAction.GET_CONFIG_FILE)
+        async def get_config_file(data: dict[str, Any]) -> handler.ActionResponse:
+            """Get a config file by file key"""
+            file_key = data['file_key']
+
+            try:
+                # Load file from storage
+                file_bytes = await self.ap.storage_mgr.storage_provider.load(file_key)
+
+                return handler.ActionResponse.success(
+                    data={
+                        'file_base64': base64.b64encode(file_bytes).decode('utf-8'),
+                    },
+                )
+            except Exception as e:
+                return handler.ActionResponse.error(
+                    message=f'Failed to load config file {file_key}: {e}',
+                )
+
     async def ping(self) -> dict[str, Any]:
         """Ping the runtime"""
         return await self.call_action(
@@ -529,24 +554,28 @@ class RuntimeConnectionHandler(handler.Handler):
     async def emit_event(
         self,
         event_context: dict[str, Any],
+        include_plugins: list[str] | None = None,
     ) -> dict[str, Any]:
         """Emit event"""
         result = await self.call_action(
             LangBotToRuntimeAction.EMIT_EVENT,
             {
                 'event_context': event_context,
+                'include_plugins': include_plugins,
             },
-            timeout=30,
+            timeout=60,
         )
 
         return result
 
-    async def list_tools(self) -> list[dict[str, Any]]:
+    async def list_tools(self, include_plugins: list[str] | None = None) -> list[dict[str, Any]]:
         """List tools"""
         result = await self.call_action(
             LangBotToRuntimeAction.LIST_TOOLS,
-            {},
+            {
-            timeout=10,
+                'include_plugins': include_plugins,
+            },
+            timeout=20,
         )
 
         return result['tools']
@@ -560,38 +589,74 @@ class RuntimeConnectionHandler(handler.Handler):
                 'plugin_name': plugin_name,
             },
         )
-        return result
 
-    async def call_tool(self, tool_name: str, parameters: dict[str, Any]) -> dict[str, Any]:
+        plugin_icon_file_key = result['plugin_icon_file_key']
+        mime_type = result['mime_type']
+
+        plugin_icon_bytes = await self.read_local_file(plugin_icon_file_key)
+
+        await self.delete_local_file(plugin_icon_file_key)
+
+        return {
+            'plugin_icon_base64': base64.b64encode(plugin_icon_bytes).decode('utf-8'),
+            'mime_type': mime_type,
+        }
+
+    async def cleanup_plugin_data(self, plugin_author: str, plugin_name: str) -> None:
+        """Cleanup plugin settings and binary storage"""
+        # Delete plugin settings
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_plugin.PluginSetting)
+            .where(persistence_plugin.PluginSetting.plugin_author == plugin_author)
+            .where(persistence_plugin.PluginSetting.plugin_name == plugin_name)
+        )
+
+        # Delete all binary storage for this plugin
+        owner = f'{plugin_author}/{plugin_name}'
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_bstorage.BinaryStorage)
+            .where(persistence_bstorage.BinaryStorage.owner_type == 'plugin')
+            .where(persistence_bstorage.BinaryStorage.owner == owner)
+        )
+
+    async def call_tool(
+        self, tool_name: str, parameters: dict[str, Any], include_plugins: list[str] | None = None
+    ) -> dict[str, Any]:
         """Call tool"""
         result = await self.call_action(
             LangBotToRuntimeAction.CALL_TOOL,
             {
                 'tool_name': tool_name,
                 'tool_parameters': parameters,
+                'include_plugins': include_plugins,
             },
-            timeout=30,
+            timeout=60,
         )
 
         return result['tool_response']
 
-    async def list_commands(self) -> list[dict[str, Any]]:
+    async def list_commands(self, include_plugins: list[str] | None = None) -> list[dict[str, Any]]:
         """List commands"""
         result = await self.call_action(
             LangBotToRuntimeAction.LIST_COMMANDS,
-            {},
+            {
+                'include_plugins': include_plugins,
+            },
             timeout=10,
         )
         return result['commands']
 
-    async def execute_command(self, command_context: dict[str, Any]) -> typing.AsyncGenerator[dict[str, Any], None]:
+    async def execute_command(
+        self, command_context: dict[str, Any], include_plugins: list[str] | None = None
+    ) -> typing.AsyncGenerator[dict[str, Any], None]:
         """Execute command"""
         gen = self.call_action_generator(
             LangBotToRuntimeAction.EXECUTE_COMMAND,
             {
                 'command_context': command_context,
+                'include_plugins': include_plugins,
             },
-            timeout=30,
+            timeout=60,
         )
 
         async for ret in gen:

pkg/provider/modelmgr/modelmgr.py

@@ -59,7 +59,7 @@ class ModelManager:
             try:
                 await self.load_llm_model(llm_model)
             except provider_errors.RequesterNotFoundError as e:
-                self.ap.logger.warning(f'Requester {e.requester_name} not found, skipping model {llm_model.uuid}')
+                self.ap.logger.warning(f'Requester {e.requester_name} not found, skipping llm model {llm_model.uuid}')
             except Exception as e:
                 self.ap.logger.error(f'Failed to load model {llm_model.uuid}: {e}\n{traceback.format_exc()}')
 
@@ -67,7 +67,14 @@ class ModelManager:
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.EmbeddingModel))
         embedding_models = result.all()
         for embedding_model in embedding_models:
-            await self.load_embedding_model(embedding_model)
+            try:
+                await self.load_embedding_model(embedding_model)
+            except provider_errors.RequesterNotFoundError as e:
+                self.ap.logger.warning(
+                    f'Requester {e.requester_name} not found, skipping embedding model {embedding_model.uuid}'
+                )
+            except Exception as e:
+                self.ap.logger.error(f'Failed to load model {embedding_model.uuid}: {e}\n{traceback.format_exc()}')
 
     async def init_runtime_llm_model(
         self,
@@ -107,6 +114,9 @@ class ModelManager:
         elif isinstance(model_info, dict):
             model_info = persistence_model.EmbeddingModel(**model_info)
 
+        if model_info.requester not in self.requester_dict:
+            raise provider_errors.RequesterNotFoundError(model_info.requester)
+
         requester_inst = self.requester_dict[model_info.requester](ap=self.ap, config=model_info.requester_config)
 
         await requester_inst.initialize()

pkg/provider/modelmgr/requesters/bailianchatcmpl.py

@@ -1,9 +1,14 @@
 from __future__ import annotations
 
 import typing
+import dashscope
 import openai
 
 from . import modelscopechatcmpl
+from .. import requester
+import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
 
 class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
@@ -15,3 +20,211 @@ class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
         'base_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
         'timeout': 120,
     }
+
+    async def _closure_stream(
+        self,
+        query: pipeline_query.Query,
+        req_messages: list[dict],
+        use_model: requester.RuntimeLLMModel,
+        use_funcs: list[resource_tool.LLMTool] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        is_use_dashscope_call = False   # 是否使用阿里原生库调用
+        is_enable_multi_model = True  # 是否支持多轮对话
+        use_time_num = 0 # 模型已调用次数，防止存在多文件时重复调用
+        use_time_ids = [] # 已调用的ID列表
+        message_id = 0  # 记录消息序号
+
+        for msg in messages:
+            # print(msg)
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+                    elif me['type'] == 'file_url' and '.' in me.get('file_name', ''):
+                        # 1. 视频文件推理
+                        # https://bailian.console.aliyun.com/?tab=doc#/doc/?type=model&url=2845871
+                        file_type = me.get('file_name').lower().split('.')[-1]
+                        if file_type in ['mp4', 'avi', 'mkv', 'mov', 'flv', 'wmv']:
+                            me['type'] = 'video_url'
+                            me['video_url'] = {'url': me['file_url']}
+                            del me['file_url']
+                            del me['file_name']
+                            use_time_num +=1
+                            use_time_ids.append(message_id)
+                            is_enable_multi_model = False
+                        # 2. 语音文件识别, 无法通过openai的audio字段传递，暂时不支持
+                        # https://bailian.console.aliyun.com/?tab=doc#/doc/?type=model&url=2979031
+                        elif file_type in ['aac', 'amr', 'aiff', 'flac', 'm4a',
+                                           'mp3', 'mpeg', 'ogg', 'opus', 'wav', 'webm', 'wma']:
+                            me['audio'] = me['file_url']
+                            me['type'] = 'audio'
+                            del me['file_url']
+                            del me['type']
+                            del me['file_name']
+                            is_use_dashscope_call = True
+                            use_time_num +=1
+                            use_time_ids.append(message_id)
+                            is_enable_multi_model = False
+            message_id += 1
+
+        # 使用列表推导式，保留不在 use_time_ids[:-1] 中的元素，仅保留最后一个多媒体消息
+        if not is_enable_multi_model and use_time_num > 1:
+            messages = [msg for idx, msg in enumerate(messages) if idx not in use_time_ids[:-1]]
+
+        if not is_enable_multi_model:
+            messages = [msg for msg in messages if 'resp_message_id' not in msg]
+
+        args['messages'] = messages
+        args['stream'] = True
+
+        # 流式处理状态
+        # tool_calls_map: dict[str, provider_message.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+
+        if is_use_dashscope_call:
+            response = dashscope.MultiModalConversation.call(
+                # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
+                api_key=use_model.token_mgr.get_token(),
+                model=use_model.model_entity.name,
+                messages=messages,
+                result_format="message",
+                asr_options={
+                    # "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
+                    "enable_lid": True,
+                    "enable_itn": False
+                },
+                stream=True
+            )
+            content_length_list = []
+            previous_length = 0  # 记录上一次的内容长度
+            for res in response:
+                chunk = res["output"]
+                # 解析 chunk 数据
+                if hasattr(chunk, 'choices') and chunk.choices:
+                    choice = chunk.choices[0]
+                    delta_content = choice["message"].content[0]["text"]
+                    finish_reason = choice["finish_reason"]
+                    content_length_list.append(len(delta_content))
+                else:
+                    delta_content = ""
+                    finish_reason = None
+
+                # 跳过空的第一个 chunk（只有 role 没有内容）
+                if chunk_idx == 0 and not delta_content:
+                    chunk_idx += 1
+                    continue
+
+                # 检查 content_length_list 是否有足够的数据
+                if len(content_length_list) >= 2:
+                    now_content = delta_content[previous_length: content_length_list[-1]]
+                    previous_length = content_length_list[-1]  # 更新上一次的长度
+                else:
+                    now_content = delta_content  # 第一次循环时直接使用 delta_content
+                    previous_length = len(delta_content)  # 更新上一次的长度
+
+                # 构建 MessageChunk - 只包含增量内容
+                chunk_data = {
+                    'role': role,
+                    'content': now_content if now_content else None,
+                    'is_final': bool(finish_reason) and finish_reason != "null",
+                }
+
+                # 移除 None 值
+                chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+                yield provider_message.MessageChunk(**chunk_data)
+                chunk_idx += 1
+        else:
+            async for chunk in self._req_stream(args, extra_body=extra_args):
+                # 解析 chunk 数据
+                if hasattr(chunk, 'choices') and chunk.choices:
+                    choice = chunk.choices[0]
+                    delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+                    finish_reason = getattr(choice, 'finish_reason', None)
+                else:
+                    delta = {}
+                    finish_reason = None
+
+                # 从第一个 chunk 获取 role，后续使用这个 role
+                if 'role' in delta and delta['role']:
+                    role = delta['role']
+
+                # 获取增量内容
+                delta_content = delta.get('content', '')
+                reasoning_content = delta.get('reasoning_content', '')
+
+                # 处理 reasoning_content
+                if reasoning_content:
+                    # accumulated_reasoning += reasoning_content
+                    # 如果设置了 remove_think，跳过 reasoning_content
+                    if remove_think:
+                        chunk_idx += 1
+                        continue
+
+                    # 第一次出现 reasoning_content，添加 <think> 开始标签
+                    if not thinking_started:
+                        thinking_started = True
+                        delta_content = '<think>\n' + reasoning_content
+                    else:
+                        # 继续输出 reasoning_content
+                        delta_content = reasoning_content
+                elif thinking_started and not thinking_ended and delta_content:
+                    # reasoning_content 结束，normal content 开始，添加 </think> 结束标签
+                    thinking_ended = True
+                    delta_content = '\n</think>\n' + delta_content
+
+                # 处理工具调用增量
+                if delta.get('tool_calls'):
+                    for tool_call in delta['tool_calls']:
+                        if tool_call['id'] != '':
+                            tool_id = tool_call['id']
+                        if tool_call['function']['name'] is not None:
+                            tool_name = tool_call['function']['name']
+
+                        if tool_call['type'] is None:
+                            tool_call['type'] = 'function'
+                        tool_call['id'] = tool_id
+                        tool_call['function']['name'] = tool_name
+                        tool_call['function']['arguments'] = (
+                            '' if tool_call['function']['arguments'] is None else tool_call['function']['arguments']
+                        )
+
+                # 跳过空的第一个 chunk（只有 role 没有内容）
+                if chunk_idx == 0 and not delta_content and not reasoning_content and not delta.get('tool_calls'):
+                    chunk_idx += 1
+                    continue
+
+                # 构建 MessageChunk - 只包含增量内容
+                chunk_data = {
+                    'role': role,
+                    'content': delta_content if delta_content else None,
+                    'tool_calls': delta.get('tool_calls'),
+                    'is_final': bool(finish_reason),
+                }
+
+                # 移除 None 值
+                chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+                yield provider_message.MessageChunk(**chunk_data)
+                chunk_idx += 1
+                # return

pkg/provider/modelmgr/requesters/jiekouaichatcmpl.py

@@ -0,0 +1,208 @@
+from __future__ import annotations
+
+import openai
+import typing
+
+from . import chatcmpl
+from .. import requester
+import openai.types.chat.chat_completion as chat_completion
+import re
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
+
+
+class JieKouAIChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """接口 AI ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': 'https://api.jiekou.ai/openai',
+        'timeout': 120,
+    }
+
+    is_think: bool = False
+
+    async def _make_msg(
+        self,
+        chat_completion: chat_completion.ChatCompletion,
+        remove_think: bool,
+    ) -> provider_message.Message:
+        chatcmpl_message = chat_completion.choices[0].message.model_dump()
+        # print(chatcmpl_message.keys(), chatcmpl_message.values())
+
+        # 确保 role 字段存在且不为 None
+        if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
+            chatcmpl_message['role'] = 'assistant'
+
+        reasoning_content = chatcmpl_message['reasoning_content'] if 'reasoning_content' in chatcmpl_message else None
+
+        # deepseek的reasoner模型
+        chatcmpl_message['content'] = await self._process_thinking_content(
+            chatcmpl_message['content'], reasoning_content, remove_think
+        )
+
+        # 移除 reasoning_content 字段，避免传递给 Message
+        if 'reasoning_content' in chatcmpl_message:
+            del chatcmpl_message['reasoning_content']
+
+        message = provider_message.Message(**chatcmpl_message)
+
+        return message
+
+    async def _process_thinking_content(
+        self,
+        content: str,
+        reasoning_content: str = None,
+        remove_think: bool = False,
+    ) -> tuple[str, str]:
+        """处理思维链内容
+
+        Args:
+            content: 原始内容
+            reasoning_content: reasoning_content 字段内容
+            remove_think: 是否移除思维链
+
+        Returns:
+            处理后的内容
+        """
+        if remove_think:
+            content = re.sub(r'<think>.*?</think>', '', content, flags=re.DOTALL)
+        else:
+            if reasoning_content is not None:
+                content = '<think>\n' + reasoning_content + '\n</think>\n' + content
+        return content
+
+    async def _make_msg_chunk(
+        self,
+        delta: dict[str, typing.Any],
+        idx: int,
+    ) -> provider_message.MessageChunk:
+        # 处理流式chunk和完整响应的差异
+        # print(chat_completion.choices[0])
+
+        # 确保 role 字段存在且不为 None
+        if 'role' not in delta or delta['role'] is None:
+            delta['role'] = 'assistant'
+
+        reasoning_content = delta['reasoning_content'] if 'reasoning_content' in delta else None
+
+        delta['content'] = '' if delta['content'] is None else delta['content']
+        # print(reasoning_content)
+
+        # deepseek的reasoner模型
+
+        if reasoning_content is not None:
+            delta['content'] += reasoning_content
+
+        message = provider_message.MessageChunk(**delta)
+
+        return message
+
+    async def _closure_stream(
+        self,
+        query: pipeline_query.Query,
+        req_messages: list[dict],
+        use_model: requester.RuntimeLLMModel,
+        use_funcs: list[resource_tool.LLMTool] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+
+        args['messages'] = messages
+        args['stream'] = True
+
+        # tool_calls_map: dict[str, provider_message.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        async for chunk in self._req_stream(args, extra_body=extra_args):
+            # 解析 chunk 数据
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+                finish_reason = getattr(choice, 'finish_reason', None)
+            else:
+                delta = {}
+                finish_reason = None
+
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            # reasoning_content = delta.get('reasoning_content', '')
+
+            if remove_think:
+                if delta['content'] is not None:
+                    if '<think>' in delta['content'] and not thinking_started and not thinking_ended:
+                        thinking_started = True
+                        continue
+                    elif delta['content'] == r'</think>' and not thinking_ended:
+                        thinking_ended = True
+                        continue
+                    elif thinking_ended and delta['content'] == '\n\n' and thinking_started:
+                        thinking_started = False
+                        continue
+                    elif thinking_started and not thinking_ended:
+                        continue
+
+            # delta_tool_calls = None
+            if delta.get('tool_calls'):
+                for tool_call in delta['tool_calls']:
+                    if tool_call['id'] and tool_call['function']['name']:
+                        tool_id = tool_call['id']
+                        tool_name = tool_call['function']['name']
+
+                    if tool_call['id'] is None:
+                        tool_call['id'] = tool_id
+                    if tool_call['function']['name'] is None:
+                        tool_call['function']['name'] = tool_name
+                    if tool_call['function']['arguments'] is None:
+                        tool_call['function']['arguments'] = ''
+                    if tool_call['type'] is None:
+                        tool_call['type'] = 'function'
+
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+
+            # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta.get('tool_calls'),
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield provider_message.MessageChunk(**chunk_data)
+            chunk_idx += 1

pkg/provider/modelmgr/requesters/jiekouaichatcmpl.yaml

@@ -0,0 +1,38 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: jiekouai-chat-completions
+  label:
+    en_US: JieKou AI
+    zh_Hans: 接口 AI
+  icon: jiekouai.png
+spec:
+  config:
+    - name: base_url
+      label:
+        en_US: Base URL
+        zh_Hans: 基础 URL
+      type: string
+      required: true
+      default: "https://api.jiekou.ai/openai"
+    - name: args
+      label:
+        en_US: Args
+        zh_Hans: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_Hans: 超时时间
+      type: int
+      required: true
+      default: 120
+  support_type:
+    - llm
+    - text-embedding
+execution:
+  python:
+    path: ./jiekouaichatcmpl.py
+    attr: JieKouAIChatCompletions

pkg/provider/modelmgr/requesters/tokenpony.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="450" height="280" viewBox="0 0 450 280" class="cursor-pointer h-24 flex-shrink-0 w-149"><g fill="none" fill-rule="nonzero"><path fill="#0005DE" d="M97.705 6.742c58.844 0 90.962 34.353 90.962 98.341v21.843c-15.118-2.479-30.297-6.573-45.558-12.3v-9.543c0-35.97-15.564-56.281-45.404-56.281s-45.404 20.31-45.404 56.281v72.48c0 36.117 15.65 56.818 45.404 56.818 26.78 0 42.133-16.768 44.936-46.452q22.397 6.473 44.905 9.356c-6.15 51.52-37.492 79.155-89.841 79.155-58.678 0-90.963-34.72-90.963-98.878v-72.479c0-63.988 32.119-98.34 90.963-98.34m253.627 0c58.844 0 90.963 34.353 90.963 98.341v72.48c0 64.157-32.285 98.877-90.963 98.877-52.438 0-83.797-27.729-89.874-79.415 15-2.026 29.965-5.252 44.887-9.67 2.658 30.042 18.036 47.026 44.987 47.026 29.755 0 45.404-20.7 45.404-56.819v-72.479c0-35.97-15.564-56.281-45.404-56.281s-45.403 20.31-45.403 56.281v8.778c-15.262 5.868-30.44 10.104-45.559 12.725v-21.503c0-63.988 32.118-98.34 90.962-98.34m-164.37 140.026.57.09.831.127-.83-.128a234.5 234.5 0 0 0 35.979 2.79q18.408.002 36.858-2.928l1.401-.226a242 242 0 0 0 1.45-.244l-1.037.175q.729-.12 1.458-.247l-.421.072 1.26-.219-.84.147a244 244 0 0 0 2.8-.5l-.792.144q.648-.117 1.298-.239l-.506.094q.66-.122 1.322-.248l-.816.154q.759-.142 1.518-.289l-.702.135a247 247 0 0 0 5.364-1.084l-.463.098a250 250 0 0 0 3.928-.864l-.785.178 1.45-.33-.665.152q.597-.137 1.193-.276l-.528.123a253 253 0 0 0 3.685-.882l-.254.063q.683-.168 1.366-.34l-1.112.277q.809-.2 1.618-.405l-.506.128q.818-.206 1.634-.417l-1.128.289q.71-.18 1.419-.365l1.506-.397a259 259 0 0 0 1.804-.488l-.433.119a261 261 0 0 0 3.751-1.053l-.681.196a264 264 0 0 0 1.735-.502l-1.054.306q.636-.184 1.272-.37l-.218.064 1.238-.366-1.02.302a266 266 0 0 0 2.936-.882l-1.026.312q.71-.214 1.42-.433l-.394.121q.675-.207 1.35-.418l-.955.297q.8-.246 1.6-.499l-.645.202q.86-.269 1.72-.543l-1.076.341q.666-.21 1.33-.423l-.254.082q.833-.266 1.665-.539l-1.41.457q.874-.28 1.75-.568l-.34.111q.702-.229 1.403-.462l-1.063.351q.818-.269 1.634-.542l-.571.19a276 276 0 0 0 4.038-1.378l-.735.256q.657-.228 1.315-.46l-.58.204q16.86-5.903 33.78-14.256l-7.114-12.453 42.909 6.553-13.148 45.541-7.734-13.537q-23.832 11.94-47.755 19.504l-.199.063a298 298 0 0 1-11.65 3.412 288 288 0 0 1-10.39 2.603 280 280 0 0 1-11.677 2.431 273 273 0 0 1-11.643 1.903 263.5 263.5 0 0 1-36.858 2.599q-17.437 0-34.844-2.323l-.227-.03q-.635-.085-1.27-.174l1.497.204a268 268 0 0 1-13.673-2.182 275 275 0 0 1-12.817-2.697 282 282 0 0 1-11.859-3.057 291 291 0 0 1-7.21-2.123c-17.23-5.314-34.43-12.334-51.59-21.051l-8.258 14.455-13.148-45.541 42.909-6.553-6.594 11.544q18.421 9.24 36.776 15.572l1.316.45 1.373.462-.831-.278q.795.267 1.589.53l-.758-.252q.632.211 1.264.419l-.506-.167q.642.212 1.284.42l-.778-.253a271 271 0 0 0 3.914 1.251l-.227-.07a267 267 0 0 0 3.428 1.046l-.194-.058 1.315.389-1.121-.331q.864.256 1.73.508l-.609-.177q.826.241 1.651.478l-1.043-.3 1.307.375-.264-.075q.802.228 1.603.452l-1.34-.377q1.034.294 2.067.58l-.727-.203q.713.2 1.426.394l-.699-.192q.62.171 1.237.338l-.538-.146a259 259 0 0 0 3.977 1.051l-.66-.17q.683.177 1.367.35l-.707-.18q.687.175 1.373.348l-.666-.168q.738.186 1.475.368l-.809-.2q.716.179 1.43.353l-.621-.153a253 253 0 0 0 3.766.898l-.308-.07q.735.17 1.472.336l-1.164-.266q.747.173 1.496.34l-.332-.074q.845.19 1.69.374l-1.358-.3q.932.21 1.864.41l-.505-.11q.726.159 1.452.313l-.947-.203q.72.156 1.44.307l-.493-.104q.684.144 1.368.286l-.875-.182q.743.155 1.485.306l-.61-.124q.932.192 1.864.376l-1.254-.252q.904.184 1.809.361l-.555-.109q.752.15 1.504.293l-.95-.184q.69.135 1.377.265l-.427-.081q.784.15 1.569.295l-1.142-.214q.717.136 1.434.268l-.292-.054a244 244 0 0 0 3.808.673l-.68-.116 1.063.18-.383-.064q1.076.18 2.152.352z"></path></g></svg>

pkg/provider/modelmgr/requesters/tokenpony.yaml

@@ -0,0 +1,31 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: tokenpony-chat-completions
+  label:
+    en_US: TokenPony
+    zh_Hans: 小马算力
+  icon: tokenpony.svg
+spec:
+  config:
+    - name: base_url
+      label:
+        en_US: Base URL
+        zh_Hans: 基础 URL
+      type: string
+      required: true
+      default: "https://api.tokenpony.cn/v1"
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_Hans: 超时时间
+      type: integer
+      required: true
+      default: 120
+  support_type:
+    - llm
+    - text-embedding
+execution:
+  python:
+    path: ./tokenponychatcmpl.py
+    attr: TokenPonyChatCompletions

pkg/provider/modelmgr/requesters/tokenponychatcmpl.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+import typing
+import openai
+
+from . import chatcmpl
+
+
+class TokenPonyChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """TokenPony ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': 'https://api.tokenpony.cn/v1',
+        'timeout': 120,
+    }

pkg/provider/runners/cozeapi.py

@@ -0,0 +1,313 @@
+from __future__ import annotations
+
+import typing
+import json
+import uuid
+import base64
+
+from .. import runner
+from ...core import app
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+from ...utils import image
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+from libs.coze_server_api.client import AsyncCozeAPIClient
+
+@runner.runner_class('coze-api')
+class CozeAPIRunner(runner.RequestRunner):
+    """Coze API 对话请求器"""
+
+    def __init__(self, ap: app.Application, pipeline_config: dict):
+        self.pipeline_config = pipeline_config
+        self.ap = ap
+        self.agent_token = pipeline_config["ai"]['coze-api']['api-key']
+        self.bot_id = pipeline_config["ai"]['coze-api'].get('bot-id')
+        self.chat_timeout = pipeline_config["ai"]['coze-api'].get('timeout')
+        self.auto_save_history = pipeline_config["ai"]['coze-api'].get('auto_save_history')
+        self.api_base = pipeline_config["ai"]['coze-api'].get('api-base')
+
+        self.coze = AsyncCozeAPIClient(
+            self.agent_token,
+            self.api_base
+        )
+    
+    def _process_thinking_content(
+        self,
+        content: str,
+    ) -> tuple[str, str]:
+        """处理思维链内容
+
+        Args:
+            content: 原始内容
+        Returns:
+            (处理后的内容, 提取的思维链内容)
+        """
+        remove_think = self.pipeline_config.get('output', {}).get('misc', {}).get('remove-think', False)
+        thinking_content = ''
+        # 从 content 中提取 <think> 标签内容
+        if content and '<think>' in content and '</think>' in content:
+            import re
+
+            think_pattern = r'<think>(.*?)</think>'
+            think_matches = re.findall(think_pattern, content, re.DOTALL)
+            if think_matches:
+                thinking_content = '\n'.join(think_matches)
+                # 移除 content 中的 <think> 标签
+                content = re.sub(think_pattern, '', content, flags=re.DOTALL).strip()
+
+        # 根据 remove_think 参数决定是否保留思维链
+        if remove_think:
+            return content, ''
+        else:
+            # 如果有思维链内容，将其以 <think> 格式添加到 content 开头
+            if thinking_content:
+                content = f'<think>\n{thinking_content}\n</think>\n{content}'.strip()
+            return content, thinking_content
+    
+    async def _preprocess_user_message(self, query: pipeline_query.Query) -> list[dict]:
+        """预处理用户消息，转换为Coze消息格式
+
+        Returns:
+            list[dict]: Coze消息列表
+        """
+        messages = []
+        
+        if isinstance(query.user_message.content, list):
+            # 多模态消息处理
+            content_parts = []
+            
+            for ce in query.user_message.content:
+                if ce.type == 'text':
+                    content_parts.append({"type": "text", "text": ce.text})
+                elif ce.type == 'image_base64':
+                    image_b64, image_format = await image.extract_b64_and_format(ce.image_base64)
+                    file_bytes = base64.b64decode(image_b64)
+                    file_id = await self._get_file_id(file_bytes)
+                    content_parts.append({"type": "image", "file_id": file_id})
+                elif ce.type == 'file':
+                    # 处理文件，上传到Coze
+                    file_id = await self._get_file_id(ce.file)
+                    content_parts.append({"type": "file", "file_id": file_id})
+            
+            # 创建多模态消息
+            if content_parts:
+                messages.append({
+                    "role": "user", 
+                    "content": json.dumps(content_parts),
+                    "content_type": "object_string", 
+                    "meta_data": None
+                })
+                
+        elif isinstance(query.user_message.content, str):
+            # 纯文本消息
+            messages.append({
+                "role": "user", 
+                "content": query.user_message.content,
+                "content_type": "text", 
+                "meta_data": None
+            })
+            
+        return messages
+    
+    async def _get_file_id(self, file) -> str:
+        """上传文件到Coze服务
+        Args:
+            file: 文件
+        Returns:
+            str: 文件ID
+        """
+        file_id = await self.coze.upload(file=file)
+        return file_id
+
+    async def _chat_messages(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """调用聊天助手（非流式）
+        
+        注意：由于cozepy没有提供非流式API，这里使用流式API并在结束后一次性返回完整内容
+        """
+        user_id = f'{query.launcher_id}_{query.sender_id}'
+        
+        # 预处理用户消息
+        additional_messages = await self._preprocess_user_message(query)
+        
+        # 获取会话ID
+        conversation_id = None
+        
+        # 收集完整内容
+        full_content = ''
+        full_reasoning = ''
+        
+        try:
+            # 调用Coze API流式接口
+            async for chunk in self.coze.chat_messages(
+                bot_id=self.bot_id,
+                user_id=user_id,
+                additional_messages=additional_messages,
+                conversation_id=conversation_id,
+                timeout=self.chat_timeout,
+                auto_save_history=self.auto_save_history,
+                stream=True
+            ):
+                self.ap.logger.debug(f'coze-chat-stream: {chunk}')
+                
+                event_type = chunk.get('event')
+                data = chunk.get('data', {})
+                # Removed debug print statement to avoid cluttering logs in production
+                
+                if event_type == 'conversation.message.delta':
+                    # 收集内容
+                    if 'content' in data:
+                        full_content += data.get('content', '')
+                    
+                    # 收集推理内容（如果有）
+                    if 'reasoning_content' in data:
+                        full_reasoning += data.get('reasoning_content', '')
+                
+                elif event_type.split(".")[-1]  == 'done' :  # 本地部署coze时，结束event不为done
+                    # 保存会话ID
+                    if 'conversation_id' in data:
+                        conversation_id = data.get('conversation_id')
+                
+                elif event_type == 'error':
+                    # 处理错误
+                    error_msg = f"Coze API错误: {data.get('message', '未知错误')}"
+                    yield provider_message.Message(
+                        role='assistant',
+                        content=error_msg,
+                    )
+                    return
+            
+            # 处理思维链内容
+            content, thinking_content = self._process_thinking_content(full_content)
+            if full_reasoning:
+                remove_think = self.pipeline_config.get('output', {}).get('misc', {}).get('remove-think', False)
+                if not remove_think:
+                    content = f'<think>\n{full_reasoning}\n</think>\n{content}'.strip()
+            
+            # 一次性返回完整内容
+            yield provider_message.Message(
+                role='assistant',
+                content=content,
+            )
+            
+            # 保存会话ID
+            if conversation_id and query.session.using_conversation:
+                query.session.using_conversation.uuid = conversation_id
+                
+        except Exception as e:
+            self.ap.logger.error(f'Coze API错误: {str(e)}')
+            yield provider_message.Message(
+                role='assistant',
+                content=f'Coze API调用失败: {str(e)}',
+            )
+
+
+    async def _chat_messages_chunk(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
+        """调用聊天助手（流式）"""
+        user_id = f'{query.launcher_id}_{query.sender_id}'
+
+        # 预处理用户消息
+        additional_messages = await self._preprocess_user_message(query)
+
+        # 获取会话ID
+        conversation_id = None
+
+        start_reasoning = False
+        stop_reasoning = False
+        message_idx = 1
+        is_final = False
+        full_content = ''
+        remove_think = self.pipeline_config.get('output', {}).get('misc', {}).get('remove-think', False)
+
+
+
+        try:
+            # 调用Coze API流式接口
+            async for chunk in self.coze.chat_messages(
+                bot_id=self.bot_id,
+                user_id=user_id,
+                additional_messages=additional_messages,
+                conversation_id=conversation_id,
+                timeout=self.chat_timeout,
+                auto_save_history=self.auto_save_history,
+                stream=True
+            ):
+                self.ap.logger.debug(f'coze-chat-stream-chunk: {chunk}')
+
+                event_type = chunk.get('event')
+                data = chunk.get('data', {})
+                content = ""
+                
+                if event_type == 'conversation.message.delta':
+                    message_idx += 1
+                    # 处理内容增量
+                    if "reasoning_content" in data and not remove_think:
+
+                        reasoning_content = data.get('reasoning_content', '')
+                        if reasoning_content and not start_reasoning:
+                            content = f"<think/>\n"
+                            start_reasoning = True
+                        content += reasoning_content
+
+                    if 'content' in data:
+                        if data.get('content', ''):
+                            content += data.get('content', '')
+                            if not stop_reasoning and start_reasoning:
+                                content = f"</think>\n{content}"
+                                stop_reasoning = True
+
+                
+                elif event_type.split(".")[-1]  == 'done' :  # 本地部署coze时，结束event不为done
+                    # 保存会话ID
+                    if 'conversation_id' in data:
+                        conversation_id = data.get('conversation_id')
+                        if query.session.using_conversation:
+                            query.session.using_conversation.uuid = conversation_id
+                    is_final = True
+
+                
+                elif event_type == 'error':
+                    # 处理错误
+                    error_msg = f"Coze API错误: {data.get('message', '未知错误')}"
+                    yield provider_message.MessageChunk(
+                        role='assistant',
+                        content=error_msg,
+                        finish_reason='error'
+                    )
+                    return
+                full_content += content
+                if message_idx % 8 == 0 or is_final:
+                    if full_content:
+                        yield provider_message.MessageChunk(
+                            role='assistant',
+                            content=full_content,
+                            is_final=is_final
+                        )
+                    
+        except Exception as e:
+            self.ap.logger.error(f'Coze API流式调用错误: {str(e)}')
+            yield provider_message.MessageChunk(
+                role='assistant',
+                content=f'Coze API流式调用失败: {str(e)}',
+                finish_reason='error'
+            )
+
+
+    async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """运行"""
+        msg_seq = 0
+        if await query.adapter.is_stream_output_supported():
+            async for msg in self._chat_messages_chunk(query):
+                if isinstance(msg, provider_message.MessageChunk):
+                    msg_seq += 1
+                    msg.msg_sequence = msg_seq
+                yield msg
+        else:
+            async for msg in self._chat_messages(query):
+                yield msg
+
+
+
+

pkg/provider/runners/difysvapi.py

@@ -14,6 +14,7 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 from libs.dify_service_api.v1 import client, errors
 
 
+
 @runner.runner_class('dify-service-api')
 class DifyServiceAPIRunner(runner.RequestRunner):
     """Dify Service API 对话请求器"""
@@ -77,7 +78,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
             tuple[str, list[str]]: 纯文本和图片的 Dify 服务图片 ID
         """
         plain_text = ''
-        image_ids = []
+        file_ids = []
 
         if isinstance(query.user_message.content, list):
             for ce in query.user_message.content:
@@ -92,11 +93,24 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                         f'{query.session.launcher_type.value}_{query.session.launcher_id}',
                     )
                     image_id = file_upload_resp['id']
-                    image_ids.append(image_id)
+                    file_ids.append(image_id)
+                # elif ce.type == "file_url":
+                #     file_bytes = base64.b64decode(ce.file_url)
+                #     file_upload_resp = await self.dify_client.upload_file(
+                #         file_bytes,
+                #         f'{query.session.launcher_type.value}_{query.session.launcher_id}',
+                #     )
+                #     file_id = file_upload_resp['id']
+                #     file_ids.append(file_id)
         elif isinstance(query.user_message.content, str):
             plain_text = query.user_message.content
+        # plain_text = "When the file content is readable, please read the content of this file. When the file is an image, describe the content of this image." if file_ids and not plain_text else plain_text
+        # plain_text = "The user message type cannot be parsed." if not file_ids and not plain_text else plain_text
+        # plain_text = plain_text if plain_text else "When the file content is readable, please read the content of this file. When the file is an image, describe the content of this image."
+        # print(self.pipeline_config['ai'])
+        plain_text = plain_text if plain_text else self.pipeline_config['ai']['dify-service-api']['base-prompt']
 
-        return plain_text, image_ids
+        return plain_text, file_ids
 
     async def _chat_messages(
         self, query: pipeline_query.Query
@@ -110,7 +124,6 @@ class DifyServiceAPIRunner(runner.RequestRunner):
         files = [
             {
                 'type': 'image',
-                'transfer_method': 'local_file',
                 'upload_file_id': image_id,
             }
             for image_id in image_ids

pkg/provider/runners/localagent.py

@@ -40,10 +40,14 @@ class LocalAgentRunner(runner.RequestRunner):
         """运行请求"""
         pending_tool_calls = []
 
-        kb_uuid = query.pipeline_config['ai']['local-agent']['knowledge-base']
+        # Get knowledge bases list (new field)
-
+        kb_uuids = query.pipeline_config['ai']['local-agent'].get('knowledge-bases', [])
-        if kb_uuid == '__none__':
+        
-            kb_uuid = None
+        # Fallback to old field for backward compatibility
+        if not kb_uuids:
+            old_kb_uuid = query.pipeline_config['ai']['local-agent'].get('knowledge-base', '')
+            if old_kb_uuid and old_kb_uuid != '__none__':
+                kb_uuids = [old_kb_uuid]
 
         user_message = copy.deepcopy(query.user_message)
 
@@ -57,21 +61,28 @@ class LocalAgentRunner(runner.RequestRunner):
                     user_message_text += ce.text
                     break
 
-        if kb_uuid and user_message_text:
+        if kb_uuids and user_message_text:
             # only support text for now
-            kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+            all_results = []
+            
+            # Retrieve from each knowledge base
+            for kb_uuid in kb_uuids:
+                kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
 
-            if not kb:
+                if not kb:
-                self.ap.logger.warning(f'Knowledge base {kb_uuid} not found')
+                    self.ap.logger.warning(f'Knowledge base {kb_uuid} not found, skipping')
-                raise ValueError(f'Knowledge base {kb_uuid} not found')
+                    continue
 
-            result = await kb.retrieve(user_message_text, kb.knowledge_base_entity.top_k)
+                result = await kb.retrieve(user_message_text, kb.knowledge_base_entity.top_k)
+                
+                if result:
+                    all_results.extend(result)
 
             final_user_message_text = ''
 
-            if result:
+            if all_results:
                 rag_context = '\n\n'.join(
-                    f'[{i + 1}] {entry.metadata.get("text", "")}' for i, entry in enumerate(result)
+                    f'[{i + 1}] {entry.metadata.get("text", "")}' for i, entry in enumerate(all_results)
                 )
                 final_user_message_text = rag_combined_prompt_template.format(
                     rag_context=rag_context, user_message=user_message_text

pkg/provider/runners/tboxapi.py

@@ -0,0 +1,205 @@
+from __future__ import annotations
+
+import typing
+import json
+import base64
+import tempfile
+import os
+
+from tboxsdk.tbox import TboxClient
+from tboxsdk.model.file import File, FileType
+
+from .. import runner
+from ...core import app
+from ...utils import image
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+
+
+class TboxAPIError(Exception):
+    """TBox API 请求失败"""
+
+    def __init__(self, message: str):
+        self.message = message
+        super().__init__(self.message)
+
+
+@runner.runner_class('tbox-app-api')
+class TboxAPIRunner(runner.RequestRunner):
+    "蚂蚁百宝箱API对话请求器"
+
+    # 运行器内部使用的配置
+    app_id: str  # 蚂蚁百宝箱平台中的应用ID
+    api_key: str  # 在蚂蚁百宝箱平台中申请的令牌
+
+    def __init__(self, ap: app.Application, pipeline_config: dict):
+        """初始化"""
+        self.ap = ap
+        self.pipeline_config = pipeline_config
+
+        # 初始化Tbox 参数配置
+        self.app_id = self.pipeline_config['ai']['tbox-app-api']['app-id']
+        self.api_key = self.pipeline_config['ai']['tbox-app-api']['api-key']
+
+        # 初始化Tbox client
+        self.tbox_client = TboxClient(authorization=self.api_key)
+
+    async def _preprocess_user_message(self, query: pipeline_query.Query) -> tuple[str, list[str]]:
+        """预处理用户消息，提取纯文本，并将图片上传到 Tbox 服务
+
+        Returns:
+            tuple[str, list[str]]: 纯文本和图片的 Tbox 文件ID
+        """
+        plain_text = ''
+        image_ids = []
+
+        if isinstance(query.user_message.content, list):
+            for ce in query.user_message.content:
+                if ce.type == 'text':
+                    plain_text += ce.text
+                elif ce.type == 'image_base64':
+                    image_b64, image_format = await image.extract_b64_and_format(ce.image_base64)
+                    # 创建临时文件
+                    file_bytes = base64.b64decode(image_b64)
+                    try:
+                        with tempfile.NamedTemporaryFile(suffix=f'.{image_format}', delete=False) as tmp_file:
+                            tmp_file.write(file_bytes)
+                            tmp_file_path = tmp_file.name
+                        file_upload_resp = self.tbox_client.upload_file(
+                            tmp_file_path
+                        )
+                        image_id = file_upload_resp.get("data", "")
+                        image_ids.append(image_id)
+                    finally:
+                        # 清理临时文件
+                        if os.path.exists(tmp_file_path):
+                            os.unlink(tmp_file_path)
+        elif isinstance(query.user_message.content, str):
+            plain_text = query.user_message.content
+
+        return plain_text, image_ids
+
+    async def _agent_messages(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """TBox 智能体对话请求"""
+
+        plain_text, image_ids = await self._preprocess_user_message(query)
+        remove_think = self.pipeline_config['output'].get('misc', {}).get('remove-think')
+
+        try:
+            is_stream = await query.adapter.is_stream_output_supported()
+        except AttributeError:
+            is_stream = False
+
+        # 获取Tbox的conversation_id
+        conversation_id = query.session.using_conversation.uuid or None
+
+        files = None
+        if image_ids:
+            files = [
+                File(file_id=image_id, type=FileType.IMAGE)
+                for image_id in image_ids
+            ]
+
+        # 发送对话请求
+        response = self.tbox_client.chat(
+            app_id=self.app_id,  # Tbox中智能体应用的ID
+            user_id=query.bot_uuid, # 用户ID
+            query=plain_text,  # 用户输入的文本信息
+            stream=is_stream,  # 是否流式输出
+            conversation_id=conversation_id,  # 会话ID，为None时Tbox会自动创建一个新会话
+            files=files,  # 图片内容
+        )
+
+        if is_stream:
+            # 解析Tbox流式输出内容，并发送给上游
+            for chunk in self._process_stream_message(response, query, remove_think):
+                yield chunk
+        else:
+            message = self._process_non_stream_message(response, query, remove_think)
+            yield provider_message.Message(
+                role='assistant',
+                content=message,
+            )
+
+    def _process_non_stream_message(self, response: typing.Dict, query: pipeline_query.Query, remove_think: bool):
+        if response.get('errorCode') != "0":
+            raise TboxAPIError(f'Tbox API 请求失败: {response.get("errorMsg", "")}')
+        payload = response.get('data', {})
+        conversation_id = payload.get('conversationId', '')
+        query.session.using_conversation.uuid = conversation_id
+        thinking_content = payload.get('reasoningContent', [])
+        result = ""
+        if thinking_content and not remove_think:
+            result += f'<think>\n{thinking_content[0].get("text", "")}\n</think>\n'
+        content = payload.get('result', [])
+        if content:
+            result += content[0].get('chunk', '')
+        return result
+
+    def _process_stream_message(self, response: typing.Generator[dict], query: pipeline_query.Query, remove_think: bool):
+        idx_msg = 0
+        pending_content = ''
+        conversation_id = None
+        think_start = False
+        think_end = False
+        for chunk in response:
+            if chunk.get('type', '') == 'chunk':
+                """
+                Tbox返回的消息内容chunk结构
+                {'lane': 'default', 'payload': {'conversationId': '20250918tBI947065406', 'messageId': '20250918TB1f53230954', 'text': '️'}, 'type': 'chunk'}
+                """
+                # 如果包含思考过程，拼接</think>
+                if think_start and not think_end:
+                    pending_content += '\n</think>\n'
+                    think_end = True
+
+                payload = chunk.get('payload', {})
+                if not conversation_id:
+                    conversation_id = payload.get('conversationId')
+                    query.session.using_conversation.uuid = conversation_id
+                if payload.get('text'):
+                    idx_msg += 1
+                    pending_content += payload.get('text')
+            elif chunk.get('type', '') == 'thinking' and not remove_think:
+                """
+                Tbox返回的思考过程chunk结构
+                {'payload': '{"ext_data":{"text":"日期"},"event":"flow.node.llm.thinking","entity":{"node_type":"text-completion","execute_id":"6","group_id":0,"parent_execute_id":"6","node_name":"模型推理","node_id":"TC_5u6gl0"}}', 'type': 'thinking'}
+                """
+                payload = json.loads(chunk.get('payload', '{}'))
+                if payload.get('ext_data', {}).get('text'):
+                    idx_msg += 1
+                    content = payload.get('ext_data', {}).get('text')   
+                    if not think_start:
+                        think_start = True
+                        pending_content += f'<think>\n{content}'
+                    else:
+                        pending_content += content
+            elif chunk.get('type', '') == 'error':
+                raise TboxAPIError(
+                    f'Tbox API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                )
+
+            if idx_msg % 8 == 0:
+                yield provider_message.MessageChunk(
+                    role='assistant',
+                    content=pending_content,
+                    is_final=False,
+                )
+
+        # Tbox不返回END事件，默认发一个最终消息
+        yield provider_message.MessageChunk(
+            role='assistant',
+            content=pending_content,
+            is_final=True,
+        )
+
+    async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """运行"""
+        msg_seq = 0
+        async for msg in self._agent_messages(query):
+            if isinstance(msg, provider_message.MessageChunk):
+                msg_seq += 1
+                msg.msg_sequence = msg_seq
+            yield msg

pkg/provider/tools/loader.py

@@ -35,7 +35,7 @@ class ToolLoader(abc.ABC):
         pass
 
     @abc.abstractmethod
-    async def get_tools(self) -> list[resource_tool.LLMTool]:
+    async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]:
         """获取所有工具"""
         pass
 

pkg/provider/tools/loaders/mcp.py

@@ -1,7 +1,11 @@
 from __future__ import annotations
 
+import enum
 import typing
 from contextlib import AsyncExitStack
+import traceback
+import sqlalchemy
+import asyncio
 
 from mcp import ClientSession, StdioServerParameters
 from mcp.client.stdio import stdio_client
@@ -10,6 +14,13 @@ from mcp.client.sse import sse_client
 from .. import loader
 from ....core import app
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
+from ....entity.persistence import mcp as persistence_mcp
+
+
+class MCPSessionStatus(enum.Enum):
+    CONNECTING = 'connecting'
+    CONNECTED = 'connected'
+    ERROR = 'error'
 
 
 class RuntimeMCPSession:
@@ -19,6 +30,8 @@ class RuntimeMCPSession:
 
     server_name: str
 
+    server_uuid: str
+
     server_config: dict
 
     session: ClientSession
@@ -27,16 +40,34 @@ class RuntimeMCPSession:
 
     functions: list[resource_tool.LLMTool] = []
 
-    def __init__(self, server_name: str, server_config: dict, ap: app.Application):
+    enable: bool
+
+    # connected: bool
+    status: MCPSessionStatus
+
+    _lifecycle_task: asyncio.Task | None
+
+    _shutdown_event: asyncio.Event
+
+    _ready_event: asyncio.Event
+
+    def __init__(self, server_name: str, server_config: dict, enable: bool, ap: app.Application):
         self.server_name = server_name
+        self.server_uuid = server_config.get('uuid', '')
         self.server_config = server_config
         self.ap = ap
-
+        self.enable = enable
         self.session = None
 
         self.exit_stack = AsyncExitStack()
         self.functions = []
 
+        self.status = MCPSessionStatus.CONNECTING
+
+        self._lifecycle_task = None
+        self._shutdown_event = asyncio.Event()
+        self._ready_event = asyncio.Event()
+
     async def _init_stdio_python_server(self):
         server_params = StdioServerParameters(
             command=self.server_config['command'],
@@ -58,6 +89,7 @@ class RuntimeMCPSession:
                 self.server_config['url'],
                 headers=self.server_config.get('headers', {}),
                 timeout=self.server_config.get('timeout', 10),
+                sse_read_timeout=self.server_config.get('ssereadtimeout', 30),
             )
         )
 
@@ -67,19 +99,65 @@ class RuntimeMCPSession:
 
         await self.session.initialize()
 
-    async def initialize(self):
+    async def _lifecycle_loop(self):
-        self.ap.logger.debug(f'初始化 MCP 会话: {self.server_name} {self.server_config}')
+        """在后台任务中管理整个MCP会话的生命周期"""
+        try:
+            if self.server_config['mode'] == 'stdio':
+                await self._init_stdio_python_server()
+            elif self.server_config['mode'] == 'sse':
+                await self._init_sse_server()
+            else:
+                raise ValueError(f'无法识别 MCP 服务器类型: {self.server_name}: {self.server_config}')
 
-        if self.server_config['mode'] == 'stdio':
+            await self.refresh()
-            await self._init_stdio_python_server()
+
-        elif self.server_config['mode'] == 'sse':
+            self.status = MCPSessionStatus.CONNECTED
-            await self._init_sse_server()
+
-        else:
+            # 通知start()方法连接已建立
-            raise ValueError(f'无法识别 MCP 服务器类型: {self.server_name}: {self.server_config}')
+            self._ready_event.set()
+
+            # 等待shutdown信号
+            await self._shutdown_event.wait()
+
+        except Exception as e:
+            self.status = MCPSessionStatus.ERROR
+            self.ap.logger.error(f'Error in MCP session lifecycle {self.server_name}: {e}\n{traceback.format_exc()}')
+            # 即使出错也要设置ready事件，让start()方法知道初始化已完成
+            self._ready_event.set()
+        finally:
+            # 在同一个任务中清理所有资源
+            try:
+                if self.exit_stack:
+                    await self.exit_stack.aclose()
+                self.functions.clear()
+                self.session = None
+            except Exception as e:
+                self.ap.logger.error(f'Error cleaning up MCP session {self.server_name}: {e}\n{traceback.format_exc()}')
+
+    async def start(self):
+        if not self.enable:
+            return
+
+        # 创建后台任务来管理生命周期
+        self._lifecycle_task = asyncio.create_task(self._lifecycle_loop())
+
+        # 等待连接建立或失败（带超时）
+        try:
+            await asyncio.wait_for(self._ready_event.wait(), timeout=30.0)
+        except asyncio.TimeoutError:
+            self.status = MCPSessionStatus.ERROR
+            raise Exception('Connection timeout after 30 seconds')
+
+        # 检查是否有错误
+        if self.status == MCPSessionStatus.ERROR:
+            raise Exception('Connection failed, please check URL')
+
+    async def refresh(self):
+        self.functions.clear()
 
         tools = await self.session.list_tools()
 
-        self.ap.logger.debug(f'获取 MCP 工具: {tools}')
+        self.ap.logger.debug(f'Refresh MCP tools: {tools}')
 
         for tool in tools.tools:
 
@@ -101,58 +179,220 @@ class RuntimeMCPSession:
                 )
             )
 
+    def get_tools(self) -> list[resource_tool.LLMTool]:
+        return self.functions
+
+    def get_runtime_info_dict(self) -> dict:
+        return {
+            'status': self.status.value,
+            'tool_count': len(self.get_tools()),
+            'tools': [
+                {
+                    'name': tool.name,
+                    'description': tool.description,
+                }
+                for tool in self.get_tools()
+            ],
+        }
+
     async def shutdown(self):
-        """关闭工具"""
+        """关闭会话并清理资源"""
-        await self.session._exit_stack.aclose()
+        try:
+            # 设置shutdown事件，通知lifecycle任务退出
+            self._shutdown_event.set()
+
+            # 等待lifecycle任务完成（带超时）
+            if self._lifecycle_task and not self._lifecycle_task.done():
+                try:
+                    await asyncio.wait_for(self._lifecycle_task, timeout=5.0)
+                except asyncio.TimeoutError:
+                    self.ap.logger.warning(f'MCP session {self.server_name} shutdown timeout, cancelling task')
+                    self._lifecycle_task.cancel()
+                    try:
+                        await self._lifecycle_task
+                    except asyncio.CancelledError:
+                        pass
+
+            self.ap.logger.info(f'MCP session {self.server_name} shutdown complete')
+        except Exception as e:
+            self.ap.logger.error(f'Error shutting down MCP session {self.server_name}: {e}\n{traceback.format_exc()}')
 
 
-@loader.loader_class('mcp')
+# @loader.loader_class('mcp')
 class MCPLoader(loader.ToolLoader):
     """MCP 工具加载器。
 
     在此加载器中管理所有与 MCP Server 的连接。
     """
 
-    sessions: dict[str, RuntimeMCPSession] = {}
+    sessions: dict[str, RuntimeMCPSession]
 
-    _last_listed_functions: list[resource_tool.LLMTool] = []
+    _last_listed_functions: list[resource_tool.LLMTool]
+
+    _hosted_mcp_tasks: list[asyncio.Task]
 
     def __init__(self, ap: app.Application):
         super().__init__(ap)
         self.sessions = {}
         self._last_listed_functions = []
+        self._hosted_mcp_tasks = []
 
     async def initialize(self):
-        for server_config in self.ap.instance_config.data.get('mcp', {}).get('servers', []):
+        await self.load_mcp_servers_from_db()
-            if not server_config['enable']:
-                continue
-            session = RuntimeMCPSession(server_config['name'], server_config, self.ap)
-            await session.initialize()
-            # self.ap.event_loop.create_task(session.initialize())
-            self.sessions[server_config['name']] = session
 
-    async def get_tools(self) -> list[resource_tool.LLMTool]:
+    async def load_mcp_servers_from_db(self):
+        self.ap.logger.info('Loading MCP servers from db...')
+
+        self.sessions = {}
+
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_mcp.MCPServer))
+        servers = result.all()
+
+        for server in servers:
+            config = self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, server)
+
+            task = asyncio.create_task(self.host_mcp_server(config))
+            self._hosted_mcp_tasks.append(task)
+
+    async def host_mcp_server(self, server_config: dict):
+        self.ap.logger.debug(f'Loading MCP server {server_config}')
+        try:
+            session = await self.load_mcp_server(server_config)
+            self.sessions[server_config['name']] = session
+        except Exception as e:
+            self.ap.logger.error(
+                f'Failed to load MCP server from db: {server_config["name"]}({server_config["uuid"]}): {e}\n{traceback.format_exc()}'
+            )
+            return
+
+        self.ap.logger.debug(f'Starting MCP server {server_config["name"]}({server_config["uuid"]})')
+        try:
+            await session.start()
+        except Exception as e:
+            self.ap.logger.error(
+                f'Failed to start MCP server {server_config["name"]}({server_config["uuid"]}): {e}\n{traceback.format_exc()}'
+            )
+            return
+
+        self.ap.logger.debug(f'Started MCP server {server_config["name"]}({server_config["uuid"]})')
+
+    async def load_mcp_server(self, server_config: dict) -> RuntimeMCPSession:
+        """加载 MCP 服务器到运行时
+
+        Args:
+            server_config: 服务器配置字典，必须包含:
+                - name: 服务器名称
+                - mode: 连接模式 (stdio/sse)
+                - enable: 是否启用
+                - extra_args: 额外的配置参数 (可选)
+        """
+
+        name = server_config['name']
+        uuid = server_config['uuid']
+        mode = server_config['mode']
+        enable = server_config['enable']
+        extra_args = server_config.get('extra_args', {})
+
+        mixed_config = {
+            'name': name,
+            'uuid': uuid,
+            'mode': mode,
+            'enable': enable,
+            **extra_args,
+        }
+
+        session = RuntimeMCPSession(name, mixed_config, enable, self.ap)
+
+        return session
+
+    async def get_tools(self, bound_mcp_servers: list[str] | None = None) -> list[resource_tool.LLMTool]:
         all_functions = []
 
         for session in self.sessions.values():
-            all_functions.extend(session.functions)
+            # If bound_mcp_servers is specified, only include tools from those servers
+            if bound_mcp_servers is not None:
+                if session.server_uuid in bound_mcp_servers:
+                    all_functions.extend(session.get_tools())
+            else:
+                # If no bound servers specified, include all tools
+                all_functions.extend(session.get_tools())
 
         self._last_listed_functions = all_functions
 
         return all_functions
 
     async def has_tool(self, name: str) -> bool:
-        return name in [f.name for f in self._last_listed_functions]
+        """检查工具是否存在"""
+        for session in self.sessions.values():
+            for function in session.get_tools():
+                if function.name == name:
+                    return True
+        return False
 
     async def invoke_tool(self, name: str, parameters: dict) -> typing.Any:
-        for server_name, session in self.sessions.items():
+        """执行工具调用"""
-            for function in session.functions:
+        for session in self.sessions.values():
+            for function in session.get_tools():
                 if function.name == name:
-                    return await function.func(**parameters)
+                    self.ap.logger.debug(f'Invoking MCP tool: {name} with parameters: {parameters}')
+                    try:
+                        result = await function.func(**parameters)
+                        self.ap.logger.debug(f'MCP tool {name} executed successfully')
+                        return result
+                    except Exception as e:
+                        self.ap.logger.error(f'Error invoking MCP tool {name}: {e}\n{traceback.format_exc()}')
+                        raise
 
-        raise ValueError(f'未找到工具: {name}')
+        raise ValueError(f'Tool not found: {name}')
+
+    async def remove_mcp_server(self, server_name: str):
+        """移除 MCP 服务器"""
+        if server_name not in self.sessions:
+            self.ap.logger.warning(f'MCP server {server_name} not found in sessions, skipping removal')
+            return
+
+        session = self.sessions.pop(server_name)
+        await session.shutdown()
+        self.ap.logger.info(f'Removed MCP server: {server_name}')
+
+    def get_session(self, server_name: str) -> RuntimeMCPSession | None:
+        """获取指定名称的 MCP 会话"""
+        return self.sessions.get(server_name)
+
+    def has_session(self, server_name: str) -> bool:
+        """检查是否存在指定名称的 MCP 会话"""
+        return server_name in self.sessions
+
+    def get_all_server_names(self) -> list[str]:
+        """获取所有已加载的 MCP 服务器名称"""
+        return list(self.sessions.keys())
+
+    def get_server_tool_count(self, server_name: str) -> int:
+        """获取指定服务器的工具数量"""
+        session = self.get_session(server_name)
+        return len(session.get_tools()) if session else 0
+
+    def get_all_servers_info(self) -> dict[str, dict]:
+        """获取所有服务器的信息"""
+        info = {}
+        for server_name, session in self.sessions.items():
+            info[server_name] = {
+                'name': server_name,
+                'mode': session.server_config.get('mode'),
+                'enable': session.enable,
+                'tools_count': len(session.get_tools()),
+                'tool_names': [f.name for f in session.get_tools()],
+            }
+        return info
 
     async def shutdown(self):
-        """关闭工具"""
+        """关闭所有工具"""
-        for session in self.sessions.values():
+        self.ap.logger.info('Shutting down all MCP sessions...')
-            await session.shutdown()
+        for server_name, session in list(self.sessions.items()):
+            try:
+                await session.shutdown()
+                self.ap.logger.debug(f'Shutdown MCP session: {server_name}')
+            except Exception as e:
+                self.ap.logger.error(f'Error shutting down MCP session {server_name}: {e}\n{traceback.format_exc()}')
+        self.sessions.clear()
+        self.ap.logger.info('All MCP sessions shutdown complete')

pkg/provider/tools/loaders/plugin.py

@@ -7,18 +7,18 @@ from .. import loader
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
 
 
-@loader.loader_class('plugin-tool-loader')
+# @loader.loader_class('plugin-tool-loader')
 class PluginToolLoader(loader.ToolLoader):
     """插件工具加载器。
 
     本加载器中不存储工具信息，仅负责从插件系统中获取工具信息。
     """
 
-    async def get_tools(self) -> list[resource_tool.LLMTool]:
+    async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]:
         # 从插件系统获取工具（内容函数）
         all_functions: list[resource_tool.LLMTool] = []
 
-        for tool in await self.ap.plugin_connector.list_tools():
+        for tool in await self.ap.plugin_connector.list_tools(bound_plugins):
             tool_obj = resource_tool.LLMTool(
                 name=tool.metadata.name,
                 human_desc=tool.metadata.description.en_US,

pkg/provider/tools/toolmgr.py

@@ -3,9 +3,9 @@ from __future__ import annotations
 import typing
 
 from ...core import app
-from . import loader as tools_loader
 from ...utils import importutil
 from . import loaders
+from .loaders import mcp as mcp_loader, plugin as plugin_loader
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
 
 importutil.import_modules_in_pkg(loaders)
@@ -16,25 +16,24 @@ class ToolManager:
 
     ap: app.Application
 
-    loaders: list[tools_loader.ToolLoader]
+    plugin_tool_loader: plugin_loader.PluginToolLoader
+    mcp_tool_loader: mcp_loader.MCPLoader
 
     def __init__(self, ap: app.Application):
         self.ap = ap
-        self.all_functions = []
-        self.loaders = []
 
     async def initialize(self):
-        for loader_cls in tools_loader.preregistered_loaders:
+        self.plugin_tool_loader = plugin_loader.PluginToolLoader(self.ap)
-            loader_inst = loader_cls(self.ap)
+        await self.plugin_tool_loader.initialize()
-            await loader_inst.initialize()
+        self.mcp_tool_loader = mcp_loader.MCPLoader(self.ap)
-            self.loaders.append(loader_inst)
+        await self.mcp_tool_loader.initialize()
 
-    async def get_all_tools(self) -> list[resource_tool.LLMTool]:
+    async def get_all_tools(self, bound_plugins: list[str] | None = None, bound_mcp_servers: list[str] | None = None) -> list[resource_tool.LLMTool]:
         """获取所有函数"""
         all_functions: list[resource_tool.LLMTool] = []
 
-        for loader in self.loaders:
+        all_functions.extend(await self.plugin_tool_loader.get_tools(bound_plugins))
-            all_functions.extend(await loader.get_tools())
+        all_functions.extend(await self.mcp_tool_loader.get_tools(bound_mcp_servers))
 
         return all_functions
 
@@ -93,13 +92,14 @@ class ToolManager:
     async def execute_func_call(self, name: str, parameters: dict) -> typing.Any:
         """执行函数调用"""
 
-        for loader in self.loaders:
+        if await self.plugin_tool_loader.has_tool(name):
-            if await loader.has_tool(name):
+            return await self.plugin_tool_loader.invoke_tool(name, parameters)
-                return await loader.invoke_tool(name, parameters)
+        elif await self.mcp_tool_loader.has_tool(name):
+            return await self.mcp_tool_loader.invoke_tool(name, parameters)
         else:
             raise ValueError(f'未找到工具: {name}')
 
     async def shutdown(self):
         """关闭所有工具"""
-        for loader in self.loaders:
+        await self.plugin_tool_loader.shutdown()
-            await loader.shutdown()
+        await self.mcp_tool_loader.shutdown()

pkg/rag/knowledge/services/chunker.py

@@ -4,6 +4,7 @@ import json
 from typing import List
 from pkg.rag.knowledge.services import base_service
 from pkg.core import app
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 
 
 class Chunker(base_service.BaseService):
@@ -27,21 +28,6 @@ class Chunker(base_service.BaseService):
         """
         if not text:
             return []
-        # words = text.split()
-        # chunks = []
-        # current_chunk = []
-
-        # for word in words:
-        #     current_chunk.append(word)
-        #     if len(current_chunk) > self.chunk_size:
-        #         chunks.append(" ".join(current_chunk[:self.chunk_size]))
-        #         current_chunk = current_chunk[self.chunk_size - self.chunk_overlap:]
-
-        # if current_chunk:
-        #     chunks.append(" ".join(current_chunk))
-
-        # A more robust chunking strategy (e.g., using recursive character text splitter)
-        from langchain.text_splitter import RecursiveCharacterTextSplitter
 
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=self.chunk_size,

pkg/storage/provider.py

@@ -42,3 +42,10 @@ class StorageProvider(abc.ABC):
         key: str,
     ):
         pass
+
+    @abc.abstractmethod
+    async def delete_dir_recursive(
+        self,
+        dir_path: str,
+    ):
+        pass

pkg/storage/providers/localstorage.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import os
 import aiofiles
+import shutil
 
 from ...core import app
 
@@ -22,6 +23,8 @@ class LocalStorageProvider(provider.StorageProvider):
         key: str,
         value: bytes,
     ):
+        if not os.path.exists(os.path.join(LOCAL_STORAGE_PATH, os.path.dirname(key))):
+            os.makedirs(os.path.join(LOCAL_STORAGE_PATH, os.path.dirname(key)))
         async with aiofiles.open(os.path.join(LOCAL_STORAGE_PATH, f'{key}'), 'wb') as f:
             await f.write(value)
 
@@ -43,3 +46,11 @@ class LocalStorageProvider(provider.StorageProvider):
         key: str,
     ):
         os.remove(os.path.join(LOCAL_STORAGE_PATH, f'{key}'))
+
+    async def delete_dir_recursive(
+        self,
+        dir_path: str,
+    ):
+        # 直接删除整个目录
+        if os.path.exists(os.path.join(LOCAL_STORAGE_PATH, dir_path)):
+            shutil.rmtree(os.path.join(LOCAL_STORAGE_PATH, dir_path))

pkg/utils/constants.py

@@ -1,6 +1,6 @@
-semantic_version = 'v4.3.1'
+semantic_version = 'v4.5.0'
 
-required_database_version = 8
+required_database_version = 11
 """Tag the version of the database schema, used to check if the database needs to be migrated"""
 
 debug_mode = False

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.3.1"
+version = "4.5.0"
 description = "Easy-to-use global IM bot platform designed for LLM era"
 readme = "README.md"
 requires-python = ">=3.10.1,<4.0"
@@ -60,11 +60,13 @@ dependencies = [
     "ebooklib>=0.18",
     "html2text>=2024.2.26",
     "langchain>=0.2.0",
+    "langchain-text-splitters>=0.0.1",
     "chromadb>=0.4.24",
     "qdrant-client (>=1.15.1,<2.0.0)",
-    "langbot-plugin==0.1.1",
+    "langbot-plugin==0.1.10",
     "asyncpg>=0.30.0",
-    "line-bot-sdk>=3.19.0"
+    "line-bot-sdk>=3.19.0",
+    "tboxsdk>=0.0.10",
 ]
 keywords = [
     "bot",
@@ -102,6 +104,7 @@ dev = [
     "pre-commit>=4.2.0",
     "pytest>=8.4.1",
     "pytest-asyncio>=1.0.0",
+    "pytest-cov>=7.0.0",
     "ruff>=0.11.9",
 ]
 

pytest.ini

@@ -0,0 +1,39 @@
+[pytest]
+# Test discovery patterns
+python_files = test_*.py
+python_classes = Test*
+python_functions = test_*
+
+# Test paths
+testpaths = tests
+
+# Asyncio configuration
+asyncio_mode = auto
+
+# Output options
+addopts =
+    -v
+    --strict-markers
+    --tb=short
+    --disable-warnings
+
+# Markers
+markers =
+    asyncio: mark test as async
+    unit: mark test as unit test
+    integration: mark test as integration test
+    slow: mark test as slow running
+
+# Coverage options (when using pytest-cov)
+[coverage:run]
+source = pkg
+omit =
+    */tests/*
+    */test_*.py
+    */__pycache__/*
+    */site-packages/*
+
+[coverage:report]
+precision = 2
+show_missing = True
+skip_covered = False

run_tests.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+# Script to run all unit tests
+# This script helps avoid circular import issues by setting up the environment properly
+
+set -e
+
+echo "Setting up test environment..."
+
+# Activate virtual environment if it exists
+if [ -d ".venv" ]; then
+    source .venv/bin/activate
+fi
+
+# Check if pytest is installed
+if ! command -v pytest &> /dev/null; then
+    echo "Installing test dependencies..."
+    pip install pytest pytest-asyncio pytest-cov
+fi
+
+echo "Running all unit tests..."
+
+# Run tests with coverage
+pytest tests/unit_tests/ -v --tb=short \
+    --cov=pkg \
+    --cov-report=xml \
+    "$@"
+
+echo ""
+echo "Test run complete!"
+echo "Coverage report saved to coverage.xml"

templates/config.yaml

@@ -10,8 +10,6 @@ command:
 concurrency:
     pipeline: 20
     session: 1
-mcp:
-    servers: []
 proxy:
     http: ''
     https: ''
@@ -38,6 +36,7 @@ vdb:
         port: 6333
         api_key: ''
 plugin:
+    enable: true
     runtime_ws_url: 'ws://langbot_plugin_runtime:5400/control/ws'
     enable_marketplace: true
-    cloud_service_url: 'https://space.langbot.app'
+    cloud_service_url: 'https://space.langbot.app'