trpc-group · CongkeChen · Jul 7, 2026 · Jul 7, 2026 · Jul 7, 2026 · Jul 7, 2026
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -0,0 +1,54 @@
+name: Docs
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "docs/mkdocs/**"
+      - "mkdocs.yml"
+      - ".github/workflows/docs.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install MkDocs
+        run: python -m pip install --upgrade pip mkdocs
+
+      - name: Build documentation
+        run: mkdocs build
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: site
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4
diff --git a/docs/mkdocs/en/index.md b/docs/mkdocs/en/index.md
@@ -0,0 +1,21 @@
+# English Documentation
+
+Welcome to the English documentation for tRPC-Agent-Python.
+
+## Getting Started
+
+- [LLM Agent](./llm_agent.md): Build a general-purpose LLM-powered agent.
+- [Model Invocation](./model.md): Configure OpenAI, Anthropic, and LiteLLM models.
+- [Tools](./tool.md): Add function tools, file tools, MCP tools, and agent tools.
+- [Skills](./skill.md): Package reusable workflows with `SKILL.md`.
+- [Code Executor](./code_executor.md): Execute code through local or sandboxed runtimes.
+
+## Core Capabilities
+
+- [Session](./session.md): Manage conversation events and state.
+- [Memory](./memory.md): Store and retrieve long-term memories.
+- [Knowledge](./knowledge.md): Build RAG workflows with LangChain components.
+- [Multi-Agent](./multi_agents.md): Compose agents for complex workflows.
+- [Evaluation](./evaluation.md): Evaluate agent behavior and response quality.
+
+For source code and examples, see the [GitHub repository](https://github.com/trpc-group/trpc-agent-python).
diff --git a/docs/mkdocs/en/session.md b/docs/mkdocs/en/session.md
@@ -109,11 +109,18 @@ session = await session_service.get_session(
 
 **List Sessions**:
 ```python
+# Specify user_id: returns all sessions for that user (without events)
 session_list = await session_service.list_sessions(
     app_name="my_app",
     user_id="user_001"
 )
-# Returns ListSessionsResponse, containing all sessions for the user (without events)
+
+# user_id=None: returns sessions across all users for the app
+all_session_list = await session_service.list_sessions(
+    app_name="my_app",
+    user_id=None
+)
+# Returns ListSessionsResponse, containing matching sessions (without events)
 ```
 
 **Delete Session**:
@@ -128,7 +135,7 @@ await session_service.delete_session(
 **Implementation Logic** (`_base_session_service.py`):
 - `create_session`: Creates a session, separates and stores app/user/session state
 - `get_session`: Retrieves a session, merges app/user/session state, applies event filtering
-- `list_sessions`: Lists sessions (excludes events to reduce data transfer)
+- `list_sessions`: Lists sessions (excludes events to reduce data transfer); passing `user_id=None` returns sessions across all users for the app
 - `delete_session`: Deletes a session and its associated data
 
 ---
@@ -611,6 +618,7 @@ session = await session_service.get_session(
 )
 
 # List existing Sessions
+# Specify user_id to return that user's sessions; user_id=None returns sessions across all users for the app
 session_list = await session_service.list_sessions(
     app_name=app_name,
     user_id=user_id

diff --git a/docs/mkdocs/index.md b/docs/mkdocs/index.md
@@ -0,0 +1,23 @@
+# tRPC-Agent-Python Documentation
+
+tRPC-Agent-Python is a production-grade Agent framework deeply integrated with the Python AI ecosystem. It provides an end-to-end foundation for agent building, orchestration, tool integration, session and long-term memory, service deployment, and observability.
+
+Choose a language to get started:
+
+- [English Documentation](./en/)
+- [中文文档](./zh/)
+
+## Quick Links
+
+- [LLM Agent](./en/llm_agent.md)
+- [Model Invocation](./en/model.md)
+- [Tools](./en/tool.md)
+- [Skills](./en/skill.md)
+- [Code Executor](./en/code_executor.md)
+- [Session](./en/session.md)
+- [Memory](./en/memory.md)
+
+## Project
+
+- [GitHub Repository](https://github.com/trpc-group/trpc-agent-python)
+- [PyPI Package](https://pypi.org/project/trpc-agent-py/)
diff --git a/docs/mkdocs/zh/index.md b/docs/mkdocs/zh/index.md
@@ -0,0 +1,21 @@
+# 中文文档
+
+欢迎阅读 tRPC-Agent-Python 中文文档。
+
+## 快速开始
+
+- [LLM Agent](./llm_agent.md)：构建通用 LLM Agent。
+- [模型调用](./model.md)：配置 OpenAI、Anthropic 和 LiteLLM 模型。
+- [工具](./tool.md)：接入函数工具、文件工具、MCP 工具和 Agent 工具。
+- [Skills](./skill.md)：通过 `SKILL.md` 封装可复用工作流。
+- [代码执行器](./code_executor.md)：通过本地或沙箱运行时代码执行。
+
+## 核心能力
+
+- [Session](./session.md)：管理会话事件与状态。
+- [Memory](./memory.md)：存储和检索长期记忆。
+- [Knowledge](./knowledge.md)：基于 LangChain 组件构建 RAG 工作流。
+- [多 Agent](./multi_agents.md)：编排多个 Agent 完成复杂任务。
+- [Evaluation](./evaluation.md)：评测 Agent 行为和回复质量。
+
+源码与示例请参考 [GitHub 仓库](https://github.com/trpc-group/trpc-agent-python)。
diff --git a/docs/mkdocs/zh/session.md b/docs/mkdocs/zh/session.md
@@ -109,11 +109,18 @@ session = await session_service.get_session(
 
 **列出会话**：
 ```python
+# 指定 user_id：返回该用户的所有会话（不含 events）
 session_list = await session_service.list_sessions(
     app_name="my_app",
     user_id="user_001"
 )
-# 返回 ListSessionsResponse，包含该用户的所有会话（不含 events）
+
+# user_id 为 None：返回该 app 下所有用户的会话
+all_session_list = await session_service.list_sessions(
+    app_name="my_app",
+    user_id=None
+)
+# 返回 ListSessionsResponse，包含符合条件的所有会话（不含 events）
 ```
 
 **删除会话**：
@@ -128,7 +135,7 @@ await session_service.delete_session(
 **实现逻辑**（`_base_session_service.py`）：
 - `create_session`：创建会话，分离并存储 app/user/session 状态
 - `get_session`：获取会话，合并 app/user/session 状态，应用事件过滤
-- `list_sessions`：列出会话列表（不包含 events，减少数据传输）
+- `list_sessions`：列出会话列表（不包含 events，减少数据传输）；`user_id` 传 `None` 时返回该 app 下所有用户的会话
 - `delete_session`：删除会话及其关联数据
 
 ---
@@ -611,6 +618,7 @@ session = await session_service.get_session(
 )
 
 # 列出存在的 Session
+# 指定 user_id 返回该用户的会话；user_id=None 返回该 app 下所有用户的会话
 session_list = await session_service.list_sessions(
     app_name=app_name,
     user_id=user_id

diff --git a/examples/langgraph_agent/agent/agent.py b/examples/langgraph_agent/agent/agent.py
@@ -39,8 +39,9 @@ def build_calculator_subgraph():
     api_key, url, model_name = get_model_config()
     model = init_chat_model(
         model_name,
+        model_provider="openai",
         api_key=api_key,
-        api_base=url,
+        base_url=url,
     )
 
     tools = [calculate]
@@ -79,8 +80,9 @@ def build_graph_with_subgraph():
     api_key, url, model_name = get_model_config()
     model = init_chat_model(
         model_name,
+        model_provider="openai",
         api_key=api_key,
-        api_base=url,
+        base_url=url,
     )
 
     # Build calculator subgraph
@@ -126,8 +128,9 @@ def build_graph():
     api_key, url, model_name = get_model_config()
     model = init_chat_model(
         model_name,
+        model_provider="openai",
         api_key=api_key,
-        api_base=url,
+        base_url=url,
     )
 
     tools = [calculate]

diff --git a/examples/langgraph_agent_with_cancel/agent/agent.py b/examples/langgraph_agent_with_cancel/agent/agent.py
@@ -44,8 +44,9 @@ def build_graph():
     api_key, url, model_name = get_model_config()
     model = init_chat_model(
         model_name,
+        model_provider="openai",
         api_key=api_key,
-        api_base=url,
+        base_url=url,
     )
 
     tools = [calculate, analyze_data]

diff --git a/examples/langgraphagent_with_human_in_the_loop/agent/agent.py b/examples/langgraphagent_with_human_in_the_loop/agent/agent.py
@@ -53,8 +53,9 @@ def _build_graph():
     api_key, url, model_name = get_model_config()
     model = init_chat_model(
         model_name,
+        model_provider="openai",
         api_key=api_key,
-        api_base=url,
+        base_url=url,
     )
     tools = [execute_database_operation]
     llm_with_tools = model.bind_tools(tools)

diff --git a/examples/mem0_tools/agent/agent.py b/examples/mem0_tools/agent/agent.py
@@ -10,8 +10,8 @@
 from trpc_agent_sdk.agents import LlmAgent
 from trpc_agent_sdk.models import LLMModel
 from trpc_agent_sdk.models import OpenAIModel
-from trpc_agent_sdk.tools.mem0_tools import SaveMemoryTool
-from trpc_agent_sdk.tools.mem0_tools import SearchMemoryTool
+from trpc_agent_sdk.tools.mem0_tool import SaveMemoryTool
+from trpc_agent_sdk.tools.mem0_tool import SearchMemoryTool
 
 from .config import get_mem0_platform_config
 from .config import get_memory_config

diff --git a/mkdocs.yml b/mkdocs.yml
@@ -0,0 +1,105 @@
+site_name: tRPC-Agent-Python
+site_description: Python LLM agent framework with multi-model support, tool calling, session management, and service integrations.
+site_url: https://trpc-group.github.io/trpc-agent-python/
+repo_url: https://github.com/trpc-group/trpc-agent-python
+repo_name: trpc-group/trpc-agent-python
+docs_dir: docs/mkdocs
+site_dir: site
+
+theme:
+  name: readthedocs
+  locale: en
+
+markdown_extensions:
+  - admonition
+  - fenced_code
+  - tables
+  - toc:
+      permalink: true
+
+nav:
+  - Home: index.md
+  - English:
+      - Overview: en/index.md
+      - Agent:
+          - LLM Agent: en/llm_agent.md
+          - Custom Agent: en/custom_agent.md
+          - LangGraph Agent: en/langgraph_agent.md
+          - Claude Agent: en/claude_agent.md
+          - Multi-Agent: en/multi_agents.md
+          - Team: en/team.md
+          - Graph: en/graph.md
+          - Sub Agent: en/sub_agent.md
+      - Model: en/model.md
+      - Tools:
+          - Tool: en/tool.md
+          - Code Executor: en/code_executor.md
+          - Skills: en/skill.md
+      - Session & Memory:
+          - Session: en/session.md
+          - SQL Session: en/session_sql.md
+          - Redis Session: en/session_redis.md
+          - Session Summary: en/session_summary.md
+          - Memory: en/memory.md
+      - Knowledge:
+          - Knowledge: en/knowledge.md
+          - Document Loader: en/knowledge_document_loader.md
+          - Text Splitter: en/knowledge_text_splitter.md
+          - Embedder: en/knowledge_embedder.md
+          - Vector Store: en/knowledge_vectorstore.md
+          - Retrievers: en/knowledge_retrievers.md
+          - Prompt Template: en/knowledge_prompt_template.md
+          - Custom Components: en/knowledge_custom_components.md
+      - Evaluation & Optimization:
+          - Evaluation: en/evaluation.md
+          - Optimization: en/optimization.md
+      - Integrations:
+          - A2A: en/a2a.md
+          - AG-UI: en/agui.md
+          - OpenClaw: en/openclaw.md
+      - Runtime:
+          - Filter: en/filter.md
+          - Human in the Loop: en/human_in_the_loop.md
+          - Cancellation: en/cancel.md
+  - 中文:
+      - 概览: zh/index.md
+      - Agent:
+          - LLM Agent: zh/llm_agent.md
+          - 自定义 Agent: zh/custom_agent.md
+          - LangGraph Agent: zh/langgraph_agent.md
+          - Claude Agent: zh/claude_agent.md
+          - 多 Agent: zh/multi_agents.md
+          - Team: zh/team.md
+          - Graph: zh/graph.md
+          - Sub Agent: zh/sub_agent.md
+      - 模型: zh/model.md
+      - 工具:
+          - 工具: zh/tool.md
+          - 代码执行器: zh/code_executor.md
+          - Skills: zh/skill.md
+      - Session 与 Memory:
+          - Session: zh/session.md
+          - SQL Session: zh/session_sql.md
+          - Redis Session: zh/session_redis.md
+          - Session Summary: zh/session_summary.md
+          - Memory: zh/memory.md
+      - Knowledge:
+          - Knowledge: zh/knowledge.md
+          - 文档加载器: zh/knowledge_document_loader.md
+          - 文本切分: zh/knowledge_text_splitter.md
+          - Embedder: zh/knowledge_embedder.md
+          - Vector Store: zh/knowledge_vectorstore.md
+          - Retrievers: zh/knowledge_retrievers.md
+          - Prompt Template: zh/knowledge_prompt_template.md
+          - 自定义组件: zh/knowledge_custom_components.md
+      - 评测与优化:
+          - Evaluation: zh/evaluation.md
+          - Optimization: zh/optimization.md
+      - 集成:
+          - A2A: zh/a2a.md
+          - AG-UI: zh/agui.md
+          - OpenClaw: zh/openclaw.md
+      - 运行时:
+          - Filter: zh/filter.md
+          - Human in the Loop: zh/human_in_the_loop.md
+          - Cancellation: zh/cancel.md