feat(open-chat): 新增 /api/open/chat 开放问答接口
- 无需登录(/api/open/ 加入 auth 白名单 + CSRF 豁免),供外部系统直接调用本项目智能体做问答 - 可指定模型(model_name)与智能体(agent_name 中文名称,扫描 agents/*/config.yaml 解析为运行 id);GET /api/open/agents 列出可选名称 - 只返回最终结果(answer = 最后一段 markdown),不含中间过程/工具调用 - 可靠关闭思考:thinking_enabled=false 时下发 thinking_force_disabled,经 create_chat_model(force_disable_thinking=True) 强制注入 enable_thinking=false(及 GLM thinking.type=disabled),覆盖只声明 supports_thinking 的内网 vLLM/Qwen 模型(与生成标题关思考一致) - 一次性问答设 is_scheduled_run 跳过自动起标题 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
593daa91ec
commit
2b6424b3ff
9 files changed
+337
-4
No files matched your search
@@ -50,6 +50,7 @@ from app.gateway.routers import (
|
||||
models,
|
||||
multi_agent,
|
||||
notifications,
|
||||
open_chat,
|
||||
parallel_agent_tasks,
|
||||
parallel_agents,
|
||||
positions,
|
||||
@@ -1454,6 +1455,9 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
|
||||
# Stateless Runs API (stream/wait without a pre-existing thread)
|
||||
app.include_router(runs.router)
|
||||
|
||||
# 开放问答接口 /api/open/chat —— 无需登录,指定模型 + 智能体做问答,可关闭思考模式
|
||||
app.include_router(open_chat.router)
|
||||
|
||||
# --- ?????????? /page/workspace/roundtable/planning?---
|
||||
# ??? app/gateway/routers/{multi_agent,intent,recommend}.py?
|
||||
# ??? frontend-web/docs/multi-agent-backend-dev.md
|
||||
|
||||
@@ -35,6 +35,9 @@ _PUBLIC_PATH_PREFIXES: tuple[str, ...] = (
|
||||
"/redoc",
|
||||
"/openapi.json",
|
||||
"/api/public/",
|
||||
# 开放问答接口:无需登录即可指定模型 + 智能体做问答(见 routers/open_chat.py)。
|
||||
# 以 "default" 用户桶运行,只暴露受控的问答能力。
|
||||
"/api/open/",
|
||||
)
|
||||
|
||||
# Exact auth paths that are public (login/register/status check).
|
||||
|
||||
@@ -52,6 +52,10 @@ def should_check_csrf(request: Request) -> bool:
|
||||
# PUT/POST returns 403 even though auth was bypassed earlier in the chain.
|
||||
if path.startswith("/api/public/"):
|
||||
return False
|
||||
# 开放问答接口同样是匿名、无会话的(见 auth_middleware._PUBLIC_PATH_PREFIXES),
|
||||
# 双提交 Cookie 既无 token 可比、也无会话可被伪造,豁免之。
|
||||
if path.startswith("/api/open/"):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,219 @@
|
||||
"""开放问答接口(无需登录)。
|
||||
|
||||
给外部系统一个最简单的 HTTP 入口来「调用本项目的智能体做问答」:
|
||||
|
||||
- 可指定 **模型**(``model_name``,对应 ``config.yaml`` 中 ``models[]`` 的 name)。
|
||||
- 可指定 **智能体**(``agent_id``,对应 ``.deer-flow/agents/<id>/``;留空 = 默认 lead agent)。
|
||||
- 可关闭 **大模型思考模式**(``thinking_enabled=false``,默认即关闭)。内网 vLLM/Qwen
|
||||
模型仅靠 ``thinking_enabled=False`` 往往关不掉思考(其 config 只声明
|
||||
``supports_thinking: true``),本接口在关闭思考时会把
|
||||
``thinking_force_disabled`` 一并下发,经
|
||||
``create_chat_model(force_disable_thinking=True)`` 强制注入
|
||||
``extra_body.chat_template_kwargs.enable_thinking=false``(及 GLM 的
|
||||
``thinking.type=disabled``)——与「生成标题」时关闭思考的做法一致。
|
||||
|
||||
该路由前缀 ``/api/open/`` 已在 ``auth_middleware`` 白名单里,**绕过登录鉴权**,
|
||||
以 ``"default"`` 用户桶运行,只暴露受控的问答能力(无文件/线程持久化)。
|
||||
|
||||
请求示例::
|
||||
|
||||
POST /api/open/chat
|
||||
{
|
||||
"message": "用一句话介绍一下你自己",
|
||||
"model_name": "deepseek-ai/DeepSeek-V4-Flash",
|
||||
"agent_id": null,
|
||||
"thinking_enabled": false
|
||||
}
|
||||
|
||||
返回::
|
||||
|
||||
{"answer": "...", "model_name": "...", "agent_id": null,
|
||||
"thinking_enabled": false, "thread_id": "open-...."}
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
import uuid
|
||||
from typing import Any, Literal
|
||||
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, SystemMessage
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from deerflow.agents.lead_agent.agent import make_lead_agent
|
||||
from deerflow.config.agents_config import list_custom_agents, validate_agent_id
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api/open", tags=["open"])
|
||||
|
||||
_THINK_TAG_RE = re.compile(r"<think>[\s\S]*?</think>", re.IGNORECASE)
|
||||
|
||||
|
||||
class OpenChatMessage(BaseModel):
|
||||
"""多轮历史中的一条消息。"""
|
||||
|
||||
role: Literal["user", "assistant", "system"] = "user"
|
||||
content: str
|
||||
|
||||
|
||||
class OpenChatRequest(BaseModel):
|
||||
"""开放问答请求体。
|
||||
|
||||
``message`` 与 ``messages`` 二选一:单轮直接传 ``message``;需要带上下文时传
|
||||
``messages``(完整历史,本接口本身无状态、不落库)。
|
||||
"""
|
||||
|
||||
message: str | None = Field(default=None, description="单轮问题文本;与 messages 二选一")
|
||||
messages: list[OpenChatMessage] | None = Field(default=None, description="多轮历史;与 message 二选一")
|
||||
model_name: str | None = Field(default=None, description="models[] 中的模型名;留空用默认模型")
|
||||
agent_name: str | None = Field(default=None, description="智能体名称(中文显示名);留空用默认 lead agent")
|
||||
agent_id: str | None = Field(default=None, description="智能体 id;一般不用,优先级高于 agent_name")
|
||||
thinking_enabled: bool = Field(default=False, description="是否开启思考;默认 False = 关闭思考(内网模型也会被强制关闭)")
|
||||
strip_think: bool = Field(default=True, description="关闭思考时,从答案里剥离残留的 <think>…</think> 块")
|
||||
thread_id: str | None = Field(default=None, description="可选;仅用于文件隔离,留空自动生成")
|
||||
recursion_limit: int = Field(default=100, ge=1, le=300, description="智能体单次问答的最大步数")
|
||||
|
||||
|
||||
class OpenChatResponse(BaseModel):
|
||||
answer: str
|
||||
model_name: str | None
|
||||
agent_name: str | None
|
||||
agent_id: str | None
|
||||
thinking_enabled: bool
|
||||
thread_id: str
|
||||
|
||||
|
||||
def _resolve_agent_id(agent_id: str | None, agent_name: str | None) -> str | None:
|
||||
"""把 agent_id / 中文名称 解析成运行 id。
|
||||
|
||||
优先级:显式 agent_id > agent_name(按 .deer-flow/agents/*/config.yaml 的 name 匹配)。
|
||||
都没传 = None(默认 lead agent)。名称匹配先精确、再忽略大小写/首尾空格。
|
||||
"""
|
||||
if agent_id and agent_id.strip():
|
||||
try:
|
||||
return validate_agent_id(agent_id)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(status_code=422, detail=f"非法的 agent_id:{exc}") from exc
|
||||
|
||||
if not agent_name or not agent_name.strip():
|
||||
return None
|
||||
|
||||
target = agent_name.strip()
|
||||
agents = list_custom_agents()
|
||||
for a in agents:
|
||||
if (a.name or "").strip() == target:
|
||||
return a.id
|
||||
lowered = target.lower()
|
||||
for a in agents:
|
||||
if (a.name or "").strip().lower() == lowered:
|
||||
return a.id
|
||||
raise HTTPException(status_code=404, detail=f"未找到名称为「{agent_name}」的智能体。")
|
||||
|
||||
|
||||
def _build_lc_messages(body: OpenChatRequest) -> list[BaseMessage]:
|
||||
"""把请求体转成 LangChain 消息列表。"""
|
||||
if body.messages:
|
||||
out: list[BaseMessage] = []
|
||||
for m in body.messages:
|
||||
text = (m.content or "").strip()
|
||||
if not text:
|
||||
continue
|
||||
if m.role == "assistant":
|
||||
out.append(AIMessage(content=m.content))
|
||||
elif m.role == "system":
|
||||
out.append(SystemMessage(content=m.content))
|
||||
else:
|
||||
out.append(HumanMessage(content=m.content))
|
||||
if out:
|
||||
return out
|
||||
if body.message and body.message.strip():
|
||||
return [HumanMessage(content=body.message)]
|
||||
raise HTTPException(status_code=422, detail="必须提供非空的 'message' 或 'messages'。")
|
||||
|
||||
|
||||
def _extract_text(content: Any) -> str:
|
||||
"""从 AIMessage.content(str 或 block 列表)抽取纯文本。"""
|
||||
if isinstance(content, str):
|
||||
return content
|
||||
if isinstance(content, list):
|
||||
parts: list[str] = []
|
||||
for block in content:
|
||||
if isinstance(block, str):
|
||||
parts.append(block)
|
||||
elif isinstance(block, dict):
|
||||
text_value = block.get("text")
|
||||
if isinstance(text_value, str):
|
||||
parts.append(text_value)
|
||||
return "".join(parts) if parts else ""
|
||||
return ""
|
||||
|
||||
|
||||
def _extract_answer(result: Any, *, strip_think: bool) -> str:
|
||||
"""从 ainvoke 的最终状态里取最后一条 AI 文本。"""
|
||||
messages = (result or {}).get("messages") if isinstance(result, dict) else None
|
||||
answer = ""
|
||||
if isinstance(messages, list):
|
||||
for msg in reversed(messages):
|
||||
if isinstance(msg, AIMessage):
|
||||
text = _extract_text(msg.content).strip()
|
||||
if text:
|
||||
answer = text
|
||||
break
|
||||
if strip_think and answer:
|
||||
answer = _THINK_TAG_RE.sub("", answer).strip()
|
||||
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)
|
||||
|
||||
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,
|
||||
"thinking_enabled": body.thinking_enabled,
|
||||
# 关闭思考时强制下发,确保内网模型也真的关掉(见模块 docstring)。
|
||||
"thinking_force_disabled": not body.thinking_enabled,
|
||||
# 一次性问答:跳过自动起标题(省一次 LLM 调用)、不挂定时任务工具。
|
||||
"is_scheduled_run": True,
|
||||
}
|
||||
if agent_id:
|
||||
configurable["agent_id"] = agent_id
|
||||
|
||||
config: dict[str, Any] = {"configurable": configurable, "recursion_limit": body.recursion_limit}
|
||||
|
||||
try:
|
||||
agent = make_lead_agent(config)
|
||||
result = await agent.ainvoke({"messages": lc_messages}, config=config)
|
||||
except Exception as exc: # noqa: BLE001 — 开放接口需把内部错误归一成 502
|
||||
logger.exception("open_chat 调用智能体失败 (model=%s, agent=%s)", body.model_name, agent_id)
|
||||
raise HTTPException(status_code=502, detail=f"智能体调用失败:{exc}") from exc
|
||||
|
||||
answer = _extract_answer(result, strip_think=body.strip_think and not body.thinking_enabled)
|
||||
if not answer:
|
||||
raise HTTPException(status_code=502, detail="智能体未返回任何文本答案。")
|
||||
|
||||
return OpenChatResponse(
|
||||
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,
|
||||
)
|
||||
|
||||
|
||||
@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)。"""
|
||||
agents = list_custom_agents()
|
||||
items = [{"name": a.name, "id": a.id} for a in agents if (a.name or "").strip()]
|
||||
return {"agents": items, "count": len(items)}
|
||||
@@ -222,6 +222,10 @@ _CONTEXT_CONFIGURABLE_KEYS: frozenset[str] = frozenset(
|
||||
"model_name",
|
||||
"mode",
|
||||
"thinking_enabled",
|
||||
# 强制关闭思考(内网 vLLM/Qwen 模型只声明 supports_thinking 时,单靠
|
||||
# thinking_enabled=False 不会注入 enable_thinking=false)。透传到 run config
|
||||
# 后由 lead agent 交给 create_chat_model(force_disable_thinking=...)。
|
||||
"thinking_force_disabled",
|
||||
"reasoning_effort",
|
||||
"rag_mode_enabled",
|
||||
"writing_mode",
|
||||
|
||||
Reference in new issue
Block a user