qiaoqichaoandClaude Code
d56c699ce6
按 docs/v2/05-implementation-plan.md §1 候选迁移表与 claude_use/T00 白名单， 从 55e2cdb 抽取 224 个文件（2.48 MB）到独立目录 F:/mini-OpenClaw-v2。 - 排除：凭据(.env/server-deploy.conf/旧DELIVERY.md)、运行数据(xingbang_data 等 4 个 SQLite)、依赖(venv/node_modules 符号链接)、归档(_backup*/test-evidence/ ori_file)、Office 临时文件 - 目标目录独立 git 仓库，初始恢复点；Gitea 远程与分支待 OQ-06 Q2 定案 - 未部署、未启动服务、未调用模型 Co-Authored-By: Claude Code <noreply@anthropic.com>
275 lines
12 KiB
Python
275 lines
12 KiB
Python
"""AgentManager — Core Agent using LangChain create_agent API with DeepSeek."""
|
||
|
||
import os
|
||
from pathlib import Path
|
||
from typing import Any, AsyncGenerator
|
||
|
||
from langchain_core.messages import HumanMessage, AIMessage
|
||
|
||
from config import get_rag_mode
|
||
from graph.prompt_builder import build_system_prompt
|
||
from graph.session_manager import session_manager
|
||
from graph.chat_model_options import chat_model_options
|
||
from tools import get_all_tools
|
||
|
||
|
||
class AgentManager:
|
||
"""Manages the Agent lifecycle: initialization, streaming, invocation."""
|
||
|
||
def __init__(self) -> None:
|
||
self._base_dir: Path | None = None
|
||
self._tools: list = []
|
||
self._llm = None
|
||
self._raw_logs_dir: Path | None = None
|
||
|
||
def initialize(self, base_dir: Path) -> None:
|
||
"""Initialize LLM (DeepSeek) and tools. Called once at startup."""
|
||
self._base_dir = base_dir
|
||
self._tools = get_all_tools(base_dir)
|
||
|
||
# 初始化原始报文日志目录 (base_dir 已是 backend/ 目录)
|
||
self._raw_logs_dir = base_dir / "raw_logs"
|
||
self._raw_logs_dir.mkdir(exist_ok=True, parents=True)
|
||
|
||
# Use langchain-deepseek for native DeepSeek support
|
||
from langchain_deepseek import ChatDeepSeek
|
||
|
||
self._llm = ChatDeepSeek(
|
||
model=os.getenv("DEEPSEEK_MODEL", "deepseek-chat"),
|
||
api_key=os.getenv("DEEPSEEK_API_KEY"),
|
||
api_base=os.getenv("DEEPSEEK_BASE_URL", "https://api.deepseek.com"),
|
||
temperature=0.7,
|
||
streaming=True,
|
||
**chat_model_options(),
|
||
)
|
||
|
||
session_manager.initialize(base_dir)
|
||
print(f"🤖 Agent initialized with {len(self._tools)} tools (DeepSeek: {os.getenv('DEEPSEEK_MODEL', 'deepseek-chat')})")
|
||
|
||
def _build_agent(self):
|
||
"""Build a fresh agent with current system prompt (re-reads files each time)."""
|
||
assert self._base_dir is not None
|
||
assert self._llm is not None
|
||
|
||
rag_mode = get_rag_mode()
|
||
system_prompt = build_system_prompt(self._base_dir, rag_mode=rag_mode)
|
||
|
||
return self.build_task_agent(self._llm, self._tools, system_prompt)
|
||
|
||
def build_task_agent(self, model, tools: list, system_prompt: str):
|
||
"""Shared core factory. Scoped tasks supply explicit model, tools and prompt."""
|
||
from langchain.agents import create_agent
|
||
return create_agent(model=model, tools=tools, system_prompt=system_prompt)
|
||
|
||
def invoke_scoped(self, message: str, *, model, tools: list, system_prompt: str) -> dict:
|
||
"""Run an isolated task through the same core without shared chat memory.
|
||
|
||
No mutation of the default model/tools: concurrent projects cannot share state.
|
||
The caller stores the trace under its own authorization boundary.
|
||
"""
|
||
from langchain_core.messages import messages_to_dict
|
||
agent = self.build_task_agent(model, tools, system_prompt)
|
||
result = agent.invoke(
|
||
{"messages": self._build_messages(message, [])},
|
||
config={"recursion_limit": 16, "callbacks": []},
|
||
)
|
||
messages = result.get("messages", [])
|
||
if not messages or messages[-1].type != "ai" or getattr(messages[-1], "tool_calls", None):
|
||
raise ValueError("Agent 未完成工具调用循环")
|
||
content = messages[-1].content
|
||
if not isinstance(content, str):
|
||
content = "\n".join(b.get("text", "") for b in content if isinstance(b, dict) and b.get("type") == "text")
|
||
if not content.strip():
|
||
raise ValueError("Agent 未返回有效建议")
|
||
return {"text": content, "messages": messages_to_dict(messages), "engine": "mini-openclaw/AgentManager"}
|
||
|
||
def _build_messages(self, user_message: str, history: list[dict[str, Any]]) -> list:
|
||
"""Convert session history + new message into LangChain messages."""
|
||
messages = []
|
||
for msg in history:
|
||
role = msg.get("role", "")
|
||
content = msg.get("content", "")
|
||
if role == "user":
|
||
messages.append(HumanMessage(content=content))
|
||
elif role == "assistant":
|
||
messages.append(AIMessage(content=content))
|
||
messages.append(HumanMessage(content=user_message))
|
||
return messages
|
||
|
||
async def astream(
|
||
self, message: str, history: list[dict[str, Any]], session_id: str = "default"
|
||
) -> AsyncGenerator[dict[str, Any], None]:
|
||
"""Stream agent response with token-level and node-level events.
|
||
|
||
Yields events:
|
||
{"type": "retrieval", "query": "...", "results": [...]} (RAG mode only)
|
||
{"type": "token", "content": "..."}
|
||
{"type": "tool_start", "tool": "...", "input": "..."}
|
||
{"type": "tool_end", "tool": "...", "output": "..."}
|
||
{"type": "done", "content": "..."}
|
||
|
||
Also persists complete message flow to {session}.msgs.jsonl for trajectory.
|
||
"""
|
||
# RAG retrieval: inject memory context if enabled
|
||
rag_mode = get_rag_mode()
|
||
rag_context = ""
|
||
if rag_mode and self._base_dir:
|
||
from graph.memory_indexer import get_memory_indexer
|
||
|
||
indexer = get_memory_indexer(self._base_dir)
|
||
results = indexer.retrieve(message)
|
||
if results:
|
||
yield {
|
||
"type": "retrieval",
|
||
"query": message,
|
||
"results": results,
|
||
}
|
||
snippets = "\n\n".join(
|
||
f"[片段 {i+1}] (score: {r['score']})\n{r['text']}"
|
||
for i, r in enumerate(results)
|
||
)
|
||
rag_context = f"[记忆检索结果]\n{snippets}"
|
||
|
||
# 为当前 session 创建原始报文回调
|
||
from graph.raw_trace import RawTraceCallback
|
||
|
||
raw_callback = RawTraceCallback(session_id, self._raw_logs_dir)
|
||
|
||
# 消息流日志文件（记录完整的 human/assistant/tool 消息序列）
|
||
import json
|
||
import time
|
||
msgs_log_file = self._raw_logs_dir / f"{session_id}.msgs.jsonl"
|
||
|
||
# 记录 human 消息
|
||
def _append_msg(role: str, content: str, **kwargs):
|
||
"""追加一条消息到 msgs.jsonl"""
|
||
msg_record = {
|
||
"role": role,
|
||
"content": content,
|
||
"timestamp": time.time(),
|
||
**kwargs
|
||
}
|
||
with open(msgs_log_file, "a", encoding="utf-8") as f:
|
||
f.write(json.dumps(msg_record, ensure_ascii=False) + "\n")
|
||
|
||
_append_msg("human", message)
|
||
|
||
# 构建 agent 时传入 callback
|
||
agent = self._build_agent()
|
||
|
||
# Build messages with optional RAG context appended to history
|
||
augmented_history = list(history)
|
||
if rag_context:
|
||
augmented_history.append(
|
||
{"role": "assistant", "content": rag_context}
|
||
)
|
||
messages = self._build_messages(message, augmented_history)
|
||
|
||
full_response = ""
|
||
tools_just_finished = False
|
||
current_assistant_content = "" # 当前 assistant 消息累积
|
||
current_tool_calls = [] # 当前 assistant 的 tool_calls
|
||
|
||
async for event in agent.astream(
|
||
{"messages": messages},
|
||
stream_mode=["messages", "updates"],
|
||
config={"callbacks": [raw_callback]},
|
||
):
|
||
# event is a tuple of (stream_mode, data) when using multiple modes
|
||
if isinstance(event, tuple):
|
||
mode, data = event
|
||
else:
|
||
mode = "messages"
|
||
data = event
|
||
|
||
if mode == "messages":
|
||
# Token-level streaming from LLM
|
||
msg, metadata = data
|
||
if hasattr(msg, "content") and msg.content:
|
||
if msg.type == "AIMessageChunk" or msg.type == "ai":
|
||
if msg.content and not getattr(msg, "tool_calls", None):
|
||
# If tools just finished, signal a new response segment
|
||
if tools_just_finished:
|
||
yield {"type": "new_response"}
|
||
tools_just_finished = False
|
||
full_response += msg.content
|
||
current_assistant_content += msg.content
|
||
yield {"type": "token", "content": msg.content}
|
||
|
||
elif mode == "updates":
|
||
if isinstance(data, dict):
|
||
for node_name, node_data in data.items():
|
||
if node_name == "model" and "messages" in node_data:
|
||
# 模型节点：记录 assistant 消息和 tool_calls
|
||
for agent_msg in node_data["messages"]:
|
||
if hasattr(agent_msg, "tool_calls") and agent_msg.tool_calls:
|
||
# 记录 assistant 消息（带 tool_calls）
|
||
tool_calls_data = []
|
||
for tc in agent_msg.tool_calls:
|
||
tool_call_info = {
|
||
"name": tc["name"],
|
||
"args": tc.get("args", {})
|
||
}
|
||
tool_calls_data.append(tool_call_info)
|
||
current_tool_calls.append(tool_call_info)
|
||
yield {
|
||
"type": "tool_start",
|
||
"tool": tc["name"],
|
||
"input": str(tc.get("args", ""))[:1000],
|
||
}
|
||
|
||
# 记录带 tool_calls 的 assistant 消息
|
||
_append_msg(
|
||
"assistant",
|
||
agent_msg.content if hasattr(agent_msg, "content") else "",
|
||
tool_calls=tool_calls_data
|
||
)
|
||
|
||
elif node_name == "tools" and "messages" in node_data:
|
||
# 工具节点：记录每个 ToolMessage 的返回内容
|
||
for tool_msg in node_data["messages"]:
|
||
if hasattr(tool_msg, "name"):
|
||
tool_output = str(tool_msg.content)
|
||
# 记录 tool 消息（完整 content）
|
||
_append_msg(
|
||
"tool",
|
||
tool_output,
|
||
name=tool_msg.name,
|
||
tool_call_id=getattr(tool_msg, "tool_call_id", None)
|
||
)
|
||
yield {
|
||
"type": "tool_end",
|
||
"tool": tool_msg.name,
|
||
"output": tool_output[:2000], # yield 时截断，但完整内容已记录
|
||
}
|
||
# After all tool results, mark that tools finished
|
||
tools_just_finished = True
|
||
|
||
# 记录最终的 assistant 消息（纯回复，无 tool_calls）
|
||
if current_assistant_content and not current_tool_calls:
|
||
_append_msg("assistant", current_assistant_content)
|
||
elif current_assistant_content and current_tool_calls:
|
||
# 如果有 tool_calls，记录最后一轮的纯文本回复
|
||
_append_msg("assistant", current_assistant_content)
|
||
|
||
yield {"type": "done", "content": full_response}
|
||
|
||
async def ainvoke(self, message: str, session_id: str) -> str:
|
||
"""Non-streaming invocation (fallback)."""
|
||
history = session_manager.load_session(session_id)
|
||
agent = self._build_agent()
|
||
messages = self._build_messages(message, history)
|
||
result = await agent.ainvoke({"messages": messages})
|
||
|
||
final_messages = result.get("messages", [])
|
||
for msg in reversed(final_messages):
|
||
if hasattr(msg, "content") and msg.type == "ai" and msg.content:
|
||
response = msg.content
|
||
session_manager.save_message(session_id, "user", message)
|
||
session_manager.save_message(session_id, "assistant", response)
|
||
return response
|
||
return "No response generated."
|
||
|
||
|
||
agent_manager = AgentManager()
|