feat: 新增技能地址管理与开放问答接口,完善任务工作区

- 新增「技能地址管理」页面与 /api/skill-addresses 路由(扫描/预览/批量替换技能内地址)
- 完善 /api/open/chat 开放问答接口与模型工厂、网关配置
- 调整任务工作区、侧边栏与路由
- 将本地 0622/ 临时目录与 __pycache__/ 加入忽略,不提交

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
吉鑫升andClaude Opus 4.8 committed 2026-06-22 17:17:54 +08:00
1 parent 32476c7ad4
commit 6b480fdbe9
15 files changed
+1749 -40

No files matched your search

@@ -33,12 +33,16 @@
from __future__ import annotations
import asyncio
import json
import logging
import re
import uuid
from collections.abc import AsyncIterator
from typing import Any, Literal
from fastapi import APIRouter, HTTPException
from fastapi.responses import StreamingResponse
from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, SystemMessage
from pydantic import BaseModel, Field
@@ -167,15 +171,15 @@ def _extract_answer(result: Any, *, strip_think: bool) -> str:
return answer
@router.post("/chat", response_model=OpenChatResponse)
async def open_chat(body: OpenChatRequest) -> OpenChatResponse:
"""指定模型 + 智能体做一次问答(无状态、可关闭思考)。"""
lc_messages = _build_lc_messages(body)
# 流式响应每隔这么久没有真实事件就发一个 SSE 注释心跳,持续制造下行字节,
# 让前置反向代理(nginx proxy_read_timeout 默认 60s 等)不会把长任务判定成空闲超时。
_HEARTBEAT_SECONDS = 15.0
def _build_run_context(body: OpenChatRequest) -> tuple[dict[str, Any], str | None, str]:
"""把请求体翻译成 (config, agent_id, thread_id)。两个端点共用,确保关思考等行为一致。"""
agent_id = _resolve_agent_id(body.agent_id, body.agent_name)
thread_id = body.thread_id or f"open-{uuid.uuid4()}"
configurable: dict[str, Any] = {
"thread_id": thread_id,
"model_name": body.model_name,
@@ -187,8 +191,26 @@ async def open_chat(body: OpenChatRequest) -> OpenChatResponse:
}
if agent_id:
configurable["agent_id"] = agent_id
config: dict[str, Any] = {"configurable": configurable, "recursion_limit": body.recursion_limit}
return config, agent_id, thread_id
def _sse(event: str | None, data: Any) -> str:
"""序列化一条 SSE 消息。event=None 时只发 data 行。"""
payload = json.dumps(data, ensure_ascii=False)
head = f"event: {event}\n" if event else ""
return f"{head}data: {payload}\n\n"
@router.post("/chat", response_model=OpenChatResponse)
async def open_chat(body: OpenChatRequest) -> OpenChatResponse:
"""指定模型 + 智能体做一次问答(无状态、可关闭思考)。
同步阻塞版:整段调研跑完才返回。**长任务(联网调研)请改用 /chat/stream**——
本端点期间不产生任何下行字节,容易被前置反代的 proxy_read_timeout 掐成 504。
"""
lc_messages = _build_lc_messages(body)
config, agent_id, thread_id = _build_run_context(body)
try:
agent = make_lead_agent(config)
@@ -211,6 +233,103 @@ async def open_chat(body: OpenChatRequest) -> OpenChatResponse:
)
async def _open_chat_event_stream(body: OpenChatRequest) -> AsyncIterator[str]:
"""驱动智能体并产出 SSE 事件流。
- 边跑边转发 AI 文本增量(``event: delta``,仅供实时观看,客户端可忽略);
- 没有真实事件时每 ``_HEARTBEAT_SECONDS`` 发一个心跳注释行保活;
- 全部跑完后用 ``event: result`` 给出最终(已按需剥离 <think> 的)答案;
- 出错则 ``event: error``。
用「后台生产任务 + 队列 + 超时取队列」的方式把「智能体进度」与「定时心跳」解耦,
所以即便某次工具调用静默很久,心跳仍照常下行,连接不会被反代判空闲。
"""
lc_messages = _build_lc_messages(body)
config, agent_id, thread_id = _build_run_context(body)
strip_think = body.strip_think and not body.thinking_enabled
queue: asyncio.Queue[tuple[str, Any]] = asyncio.Queue()
final_state: dict[str, Any] = {}
async def produce() -> None:
nonlocal final_state
try:
agent = make_lead_agent(config)
async for mode, chunk in agent.astream({"messages": lc_messages}, config=config, stream_mode=["values", "messages"]):
if mode == "values" and isinstance(chunk, dict):
final_state = chunk
await queue.put(("progress", {"messages": len(chunk.get("messages") or [])}))
elif mode == "messages":
msg = chunk[0] if isinstance(chunk, tuple) and chunk else chunk
# 仅转发 AI 正文增量;DeepSeek 等把思考放在 additional_kwargs.reasoning_content,
# 不在 content 里,所以这里天然不会泄漏 <think>。
if isinstance(msg, AIMessage):
text = _extract_text(getattr(msg, "content", "")).strip()
if text:
await queue.put(("delta", {"text": text}))
except Exception as exc: # noqa: BLE001 — 开放接口需把内部错误归一成 error 事件
logger.exception("open_chat_stream 调用智能体失败 (model=%s, agent=%s)", body.model_name, agent_id)
await queue.put(("error", {"detail": f"智能体调用失败:{exc}"}))
finally:
await queue.put(("__end__", None))
task = asyncio.create_task(produce())
try:
while True:
try:
event, data = await asyncio.wait_for(queue.get(), timeout=_HEARTBEAT_SECONDS)
except asyncio.TimeoutError:
yield ": keepalive\n\n" # SSE 注释行,客户端忽略,仅用于保活
continue
if event == "__end__":
break
if event == "error":
yield _sse("error", data)
return
yield _sse(event, data)
answer = _extract_answer(final_state, strip_think=strip_think)
if not answer:
yield _sse("error", {"detail": "智能体未返回任何文本答案。"})
return
yield _sse(
"result",
{
"answer": answer,
"model_name": body.model_name,
"agent_name": body.agent_name,
"agent_id": agent_id,
"thinking_enabled": body.thinking_enabled,
"thread_id": thread_id,
},
)
finally:
if not task.done():
task.cancel()
@router.post("/chat/stream")
async def open_chat_stream(body: OpenChatRequest) -> StreamingResponse:
"""流式版 /chat:边跑边发心跳保活,跑完用 ``event: result`` 给最终答案。
解决两件事:(1) 长任务(联网调研、报告)同步阻塞会被前置反代 proxy_read_timeout
掐成 504;流式持续有字节下行,代理不再判定空闲超时。(2) 客户端只需读到
``event: result`` 解析 ``answer`` 即可,中间的 ``delta``/``progress``/心跳都可忽略。
"""
# 入参校验放在流外:非法请求直接抛 4xx,而不是开了流再报错。
_build_lc_messages(body)
return StreamingResponse(
_open_chat_event_stream(body),
media_type="text/event-stream",
headers={
"Cache-Control": "no-cache",
"Connection": "keep-alive",
# 关掉 nginx 对该响应的缓冲,确保 SSE/心跳实时下行(即便前置 nginx 默认开缓冲)。
"X-Accel-Buffering": "no",
},
)
@router.get("/agents")
async def open_list_agents() -> dict[str, Any]:
"""列出可用智能体的名称(方便知道 agent_name 该填什么)。"""