fastclaw-ai 1.1.0__tar.gz

fastclaw_ai-1.1.0/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: fastclaw-ai
+Version: 1.1.0
+Summary: FastClaw - AI Agent Framework with multi-channel support
+Author: kandada
+License: GPL-3.0
+Project-URL: Homepage, https://github.com/kandada/fastclaw
+Project-URL: Repository, https://github.com/kandada/fastclaw.git
+Project-URL: Issues, https://github.com/kandada/fastclaw/issues
+Project-URL: Documentation, https://github.com/kandada/fastclaw#readme
+Keywords: ai,agent,llm,chatbot,fastmind
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: fastmind>=0.1.9
+Requires-Dist: openai>=1.0.0
+Requires-Dist: websockets>=10.0
+Requires-Dist: fastapi>=0.100.0
+Requires-Dist: uvicorn[standard]>=0.35.0
+Requires-Dist: httpx>=0.23.0
+Requires-Dist: anyio>=4.5
+Requires-Dist: croniter>=6.2.0
+Requires-Dist: lark-oapi>=1.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+
+# FastClaw
+
+a python-based light but strong lobster
+
+## Design Philosophy
+
+FastClaw is built on the core concept of **event-driven agent orchestration**. Key design principles:
+
+- **Graph-based Agent**: Uses a directed graph to orchestrate agent behavior, supporting conditional branching between nodes (e.g., tool execution, response generation)
+- **Event Streaming**: Real-time streaming output of LLM responses for better user experience
+- **Tool System**: Extensible tool framework supporting Shell commands, skills, and custom integrations
+- **Session Management**: Persistent conversation history with multi-session support
+- **Cron Scheduling**: Built-in cron-style task scheduling for automated workflows
+
+## Quick Start
+
+### Installation
+
+```bash
+git clone https://github.com/kandada/fastclaw.git
+cd fastclaw
+pip install -r requirements.txt
+```
+
+### Start Server
+
+```bash
+python main.py start
+# or want it remaining in background:
+nohup python main.py start > fastclaw.log 2>&1 &
+```
+
+### Agent Configuration
+```bash
+vim workspace/data/agents/main_agent/metadata.json 
+# Edit the file to configure your LLM provider and API key
+# Currently supports OpenAI gateway models (DeepSeek, OpenAI, etc.), recommended: deepseek-chat
+# Default agent is main_agent. To switch, modify workspace/data/settings.json
+```
+
+Access at http://localhost:8765
+You can also select agents and enter API keys in the Settings page.
+API key must be provided for the agent to work properly.
+
+### CLI Usage
+
+```bash
+# Interactive chat
+python main.py chat
+
+# New session
+python main.py chat --new
+
+# Check status
+python main.py status
+```
+
+## Features
+
+- 🤖 **LLM-powered** - Built on  [FastMind](https://github.com/kandada/fastmind)  framework with streaming support
+- 🔧 **Tool Calling** - Execute Shell commands, skills, and more
+- ⏰ **Cron Jobs** - Schedule tasks with cron expressions
+- 💬 **Multi-channel** - Feishu, iMessage integrations
+- 🎨 **Extensible** - Easy to add custom skills and agents
+
+## License
+
+GPL-3.0
+
+## Acknowledgments
+
+Inspired by [OpenClaw](https://github.com/openclaw/openclaw). Special thanks to the open source community.
+
+---
+
+FastClaw is powerful, but its use depends entirely on the user - all responsibility lies with the user yourself.
+
+---
+
+Author：[xiefujin](https://github.com/kandada) email: 490021684@qq.com，welcome to contact me.

fastclaw_ai-1.1.0/fastclaw/README.md

@@ -0,0 +1,80 @@
+# FastClaw
+
+a python-based light but strong lobster
+
+## Design Philosophy
+
+FastClaw is built on the core concept of **event-driven agent orchestration**. Key design principles:
+
+- **Graph-based Agent**: Uses a directed graph to orchestrate agent behavior, supporting conditional branching between nodes (e.g., tool execution, response generation)
+- **Event Streaming**: Real-time streaming output of LLM responses for better user experience
+- **Tool System**: Extensible tool framework supporting Shell commands, skills, and custom integrations
+- **Session Management**: Persistent conversation history with multi-session support
+- **Cron Scheduling**: Built-in cron-style task scheduling for automated workflows
+
+## Quick Start
+
+### Installation
+
+```bash
+git clone https://github.com/kandada/fastclaw.git
+cd fastclaw
+pip install -r requirements.txt
+```
+
+### Start Server
+
+```bash
+python main.py start
+# or want it remaining in background:
+nohup python main.py start > fastclaw.log 2>&1 &
+```
+
+### Agent Configuration
+```bash
+vim workspace/data/agents/main_agent/metadata.json 
+# Edit the file to configure your LLM provider and API key
+# Currently supports OpenAI gateway models (DeepSeek, OpenAI, etc.), recommended: deepseek-chat
+# Default agent is main_agent. To switch, modify workspace/data/settings.json
+```
+
+Access at http://localhost:8765
+You can also select agents and enter API keys in the Settings page.
+API key must be provided for the agent to work properly.
+
+### CLI Usage
+
+```bash
+# Interactive chat
+python main.py chat
+
+# New session
+python main.py chat --new
+
+# Check status
+python main.py status
+```
+
+## Features
+
+- 🤖 **LLM-powered** - Built on  [FastMind](https://github.com/kandada/fastmind)  framework with streaming support
+- 🔧 **Tool Calling** - Execute Shell commands, skills, and more
+- ⏰ **Cron Jobs** - Schedule tasks with cron expressions
+- 💬 **Multi-channel** - Feishu, iMessage integrations
+- 🎨 **Extensible** - Easy to add custom skills and agents
+
+## License
+
+GPL-3.0
+
+## Acknowledgments
+
+Inspired by [OpenClaw](https://github.com/openclaw/openclaw). Special thanks to the open source community.
+
+---
+
+FastClaw is powerful, but its use depends entirely on the user - all responsibility lies with the user yourself.
+
+---
+
+Author：[xiefujin](https://github.com/kandada) email: 490021684@qq.com，welcome to contact me.

fastclaw_ai-1.1.0/fastclaw/__init__.py

@@ -0,0 +1,32 @@
+"""
+FastClaw - AI Agent Framework
+
+支持三种运行方式：
+1. 直接运行: cd fastclaw && python main.py
+2. 模块运行: python -m fastclaw
+3. pip 安装后: fastclaw start
+"""
+
+__version__ = "1.1.0"
+
+import os
+import sys
+from pathlib import Path
+
+# ===== 路径处理 =====
+
+_PKG_DIR = Path(__file__).resolve().parent
+_PROJECT_ROOT = _PKG_DIR.parent
+
+# 设置默认 FASTCLAW_WORKSPACE 环境变量
+# 优先级：已设置的环境变量 > 项目根目录的 workspace/ > ~/.fastclaw/workspace
+_default_workspace = _PROJECT_ROOT / "workspace"
+if os.environ.get("FASTCLAW_WORKSPACE") is None:
+    if _default_workspace.exists() and _default_workspace.is_dir():
+        os.environ["FASTCLAW_WORKSPACE"] = str(_default_workspace)
+    else:
+        os.environ["FASTCLAW_WORKSPACE"] = str(Path.home() / ".fastclaw" / "workspace")
+
+# 确保项目根目录在 sys.path（用于直接运行模式）
+if str(_PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(_PROJECT_ROOT))

fastclaw_ai-1.1.0/fastclaw/__main__.py

@@ -0,0 +1,18 @@
+"""
+支持 python -m fastclaw 运行
+"""
+
+import sys
+import asyncio
+from pathlib import Path
+
+_PKG_DIR = Path(__file__).resolve().parent
+_PROJECT_ROOT = _PKG_DIR.parent
+
+if str(_PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(_PROJECT_ROOT))
+
+from fastclaw.main import main as fastclaw_main
+
+if __name__ == "__main__":
+    asyncio.run(fastclaw_main())

fastclaw_ai-1.1.0/fastclaw/cli.py

@@ -0,0 +1,231 @@
+# cli.py
+"""FastClaw 命令行界面"""
+
+import asyncio
+import sys
+import logging
+import uuid
+from pathlib import Path
+
+try:
+    from termcolor import colored
+except ImportError:
+
+    def colored(text, color=None):
+        return text
+
+
+from fastmind import Event
+
+if __package__ in (None, ""):
+    from core.app import start
+    from gateway.channels.handlers import (
+        handle_channel_command,
+        load_sessions,
+        save_sessions,
+        get_last_session,
+    )
+else:
+    from .core.app import start
+    from .gateway.channels.handlers import (
+        handle_channel_command,
+        load_sessions,
+        save_sessions,
+        get_last_session,
+    )
+
+logging.disable(logging.WARNING)
+
+
+def create_cli_session():
+    """创建 CLI 会话并保存到 sessions.json"""
+    sessions = load_sessions()
+    new_session_id = f"cli_{uuid.uuid4().hex[:8]}"
+    sessions[new_session_id] = {
+        "session_id": new_session_id,
+        "agent_id": "main_agent",
+        "created_at": str(uuid.uuid4()),
+        "last_active_time": int(__import__("time").time()),
+    }
+    save_sessions(sessions)
+    return new_session_id
+
+
+async def chat(new_session=False, session_id=None):
+    """交互式对话"""
+    api = await start()
+    if session_id:
+        pass
+    elif new_session:
+        session_id = create_cli_session()
+    else:
+        last_session = get_last_session("cli")
+        if last_session:
+            session_id = last_session
+        else:
+            session_id = create_cli_session()
+
+    print("=" * 50)
+    print("FastClaw CLI (输入 'quit' 退出)")
+    print("支持命令: /new, /clear, /session <id>, /session_list")
+    print("=" * 50)
+
+    async def consume_stream():
+        """消费流式输出事件"""
+        buffer = ""
+        thinking_buffer = ""
+        thinking_shown = False
+        try:
+            async for event in api.stream_events(session_id):
+                if event.type == "stream.thinking":
+                    delta = event.payload.get("delta", "")
+                    delta_clean = delta.replace("\n", " ").replace("\r", " ")
+                    if not thinking_shown:
+                        thinking_shown = True
+                        thinking_buffer = ""
+                        print(f"{colored('[思考中...] ', 'cyan')}", end="", flush=True)
+                    thinking_buffer += delta_clean
+                    display_text = thinking_buffer[:200]
+                    print(
+                        f"\r{colored('[思考中...] ', 'cyan')}{display_text}",
+                        end="",
+                        flush=True,
+                    )
+                elif event.type == "stream.chunk":
+                    if thinking_shown:
+                        print("\r" + " " * 80, end="", flush=True)
+                        print("\r", end="", flush=True)
+                        thinking_shown = False
+                        thinking_buffer = ""
+                    delta = event.payload.get("delta", "")
+                    buffer += delta
+                    try:
+                        print(delta, end="", flush=True)
+                    except (UnicodeEncodeError, UnicodeDecodeError):
+                        safe_delta = delta.encode("utf-8", errors="replace").decode(
+                            "utf-8", errors="replace"
+                        )
+                        print(safe_delta, end="", flush=True)
+                elif event.type == "stream.fragment":
+                    if thinking_shown:
+                        print("\r" + " " * 80, end="", flush=True)
+                        print("\r", end="", flush=True)
+                        thinking_shown = False
+                        thinking_buffer = ""
+                    tool_calls = event.payload.get("tool_calls", [])
+                    if tool_calls:
+                        seen = set()
+                        unique_names = []
+                        for tc in tool_calls:
+                            name = tc.get("function", {}).get("name", "unknown")
+                            if name not in seen:
+                                seen.add(name)
+                                unique_names.append(name)
+                        print(f"[执行工具: {', '.join(unique_names)}]")
+                    content = event.payload.get("content", "")
+                    if content:
+                        pass
+                elif event.type == "stream.end":
+                    if thinking_shown:
+                        print("\r" + " " * 80, end="", flush=True)
+                        print("\r", end="", flush=True)
+                        thinking_shown = False
+                        thinking_buffer = ""
+                    print()
+                    return buffer
+                elif event.type == "stream.error":
+                    if thinking_shown:
+                        print("\r" + " " * 80, end="", flush=True)
+                        print("\r", end="", flush=True)
+                        thinking_shown = False
+                        thinking_buffer = ""
+                    print(f"\n[错误: {event.payload.get('error', '未知错误')}]")
+                    return None
+        except asyncio.CancelledError:
+            return buffer
+        except Exception as e:
+            print(f"\n[异常: {e}]")
+            return buffer
+
+    async def handle_cli_command(
+        text: str, current_session_id: str
+    ) -> tuple[bool, str]:
+        """处理 CLI 命令，返回 (是否已处理, 是否需要更新session_id, 新的session_id)"""
+        text = text.strip()
+        new_session_id = current_session_id
+
+        if text == "/new":
+            new_session_id = create_cli_session()
+            print(f"\n已创建新会话: {new_session_id}")
+            return True, new_session_id
+
+        elif text == "/clear":
+            from fastclaw.core.config import get_sessions_dir
+
+            session_dir = get_sessions_dir() / current_session_id
+            messages_file = session_dir / "messages.jsonl"
+            if messages_file.exists():
+                messages_file.unlink()
+            print(f"\n已清空当前会话 {current_session_id} 的聊天记录")
+            return True, current_session_id
+
+        elif text.startswith("/session "):
+            parts = text.split(" ", 1)
+            if len(parts) == 2:
+                target_id = parts[1].strip()
+                sessions = load_sessions()
+                if target_id in sessions:
+                    print(f"\n已切换到会话: {target_id}")
+                    new_session_id = target_id
+                else:
+                    print(f"\n未找到会话: {target_id}")
+                return True, current_session_id
+
+        elif text == "/session_list":
+            sessions = load_sessions()
+            if sessions:
+                print("\n当前所有会话:")
+                for sid, info in sessions.items():
+                    marker = " <-- 当前" if sid == current_session_id else ""
+                    agent = info.get("agent_id", "unknown")
+                    print(f"  - {sid} (agent: {agent}){marker}")
+            else:
+                print("\n当前没有会话")
+            return True, current_session_id
+
+        return False, current_session_id
+
+    while True:
+        try:
+            user_input = input(f"\n你 ({session_id}): ").strip()
+            if not user_input:
+                continue
+            if user_input.lower() == "quit":
+                break
+
+            is_command, new_session_id = await handle_cli_command(
+                user_input, session_id
+            )
+            session_id = new_session_id
+            if is_command:
+                continue
+
+            event = Event("user.message", {"text": user_input}, session_id)
+            await api.push_event(session_id, event)
+
+            await consume_stream()
+
+        except KeyboardInterrupt:
+            print("\n\n退出...")
+            break
+        except EOFError:
+            print("\n\n退出...")
+            break
+        except Exception as e:
+            print(f"\n错误: {e}")
+
+    await api.stop()
+
+
+if __name__ == "__main__":
+    asyncio.run(chat())

fastclaw_ai-1.1.0/fastclaw/core/__init__.py

@@ -0,0 +1,43 @@
+"""FastClaw 核心引擎"""
+
+import sys
+
+_IS_PACKAGE_MODE = __package__ and __package__.startswith("fastclaw.")
+
+if _IS_PACKAGE_MODE:
+    from .app import (
+        app,
+        start,
+        SKILLS,
+        load_skills,
+        load_agent_config,
+        load_settings,
+        calculate_tokens,
+        count_messages_tokens,
+    )
+    from .prompts import format_system_prompt, SYSTEM_PROMPT
+else:
+    from core.app import (
+        app,
+        start,
+        SKILLS,
+        load_skills,
+        load_agent_config,
+        load_settings,
+        calculate_tokens,
+        count_messages_tokens,
+    )
+    from core.prompts import format_system_prompt, SYSTEM_PROMPT
+
+__all__ = [
+    "app",
+    "start",
+    "SKILLS",
+    "load_skills",
+    "load_agent_config",
+    "load_settings",
+    "calculate_tokens",
+    "count_messages_tokens",
+    "format_system_prompt",
+    "SYSTEM_PROMPT",
+]