多智能问答

This commit is contained in:
董宏凯 committed 2026-05-24 21:13:19 +08:00
1 parent 77db1a6297
commit 05815d9475
11 files changed
+2045 -727

No files matched your search

@@ -1,6 +1,7 @@
import logging
import mimetypes
import zipfile
from datetime import datetime, timezone
from pathlib import Path
from urllib.parse import quote
@@ -10,6 +11,8 @@ from pydantic import BaseModel
from app.gateway.authz import require_permission
from app.gateway.path_utils import resolve_thread_virtual_path
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
logger = logging.getLogger(__name__)
@@ -94,6 +97,61 @@ def _extract_file_from_skill_archive(zip_path: Path, internal_path: str) -> byte
return None
def collect_outputs_listing(outputs_dir: Path) -> list[dict]:
"""Walk an outputs directory and return artifact listing entries.
Each entry has ``path`` (virtual ``mnt/user-data/outputs/...``), ``name``,
``size_bytes``, ``mime_type``, and ``modified_at`` (ISO 8601 UTC). Symlinks
that escape the outputs root are dropped to keep the listing scoped to the
thread. The result is sorted by ``modified_at`` descending (newest first).
"""
if not outputs_dir.exists() or not outputs_dir.is_dir():
return []
outputs_root = outputs_dir.resolve()
files: list[dict] = []
for entry in outputs_root.rglob("*"):
if not entry.is_file():
continue
try:
resolved = entry.resolve()
resolved.relative_to(outputs_root)
except (OSError, ValueError):
continue
relative = resolved.relative_to(outputs_root).as_posix()
mime_type, _ = mimetypes.guess_type(resolved.name)
stat = resolved.stat()
files.append(
{
"path": f"mnt/user-data/outputs/{relative}",
"name": resolved.name,
"size_bytes": stat.st_size,
"mime_type": mime_type,
"modified_at": datetime.fromtimestamp(stat.st_mtime, tz=timezone.utc).isoformat(),
}
)
files.sort(key=lambda f: f["modified_at"], reverse=True)
return files
@router.get(
"/threads/{thread_id}/artifacts",
summary="List Artifact Files",
description="List all files under the thread's outputs directory (/mnt/user-data/outputs/). Returns an empty list if the thread has no outputs.",
)
@require_permission("threads", "read", owner_check=True)
async def list_artifacts(thread_id: str, request: Request) -> dict:
"""List artifact files generated by the agent under outputs/.
Walks ``backend/.deer-flow/users/{user_id}/threads/{thread_id}/user-data/outputs/``
recursively. Returns an empty list if the directory does not exist (e.g. the
thread has not produced any artifacts yet).
"""
outputs_dir = get_paths().sandbox_outputs_dir(thread_id, user_id=get_effective_user_id())
return {"thread_id": thread_id, "files": collect_outputs_listing(outputs_dir)}
@router.get(
"/threads/{thread_id}/artifacts/{path:path}",
summary="Get Artifact File",
@@ -27,6 +27,8 @@ from fastapi.responses import StreamingResponse
from app.gateway.routers.multi_agent import (
_auth_headers,
_create_thread,
_find_dispatch_message,
_find_trailing_ai_text,
_flatten_content,
_loopback_base,
_parse_last_messages,
@@ -59,7 +61,12 @@ async def init_intent(request: Request, payload: dict = Body(...)) -> dict[str,
"""
base = _loopback_base(request)
headers = _auth_headers(request)
async with httpx.AsyncClient(timeout=None) as client:
# trust_env=False: this client only talks to the same-process gateway at
# 127.0.0.1, so honoring HTTP_PROXY / HTTPS_PROXY env vars (set system-wide
# on the dev machine) makes httpx route loopback calls through an upstream
# proxy that can't reach 127.0.0.1, costing 40+ seconds of timeout per
# request before falling back. Symptom in logs: `headers_in=42.160s`.
async with httpx.AsyncClient(timeout=None, trust_env=False) as client:
thread_id = await _create_thread(client, base, headers)
return {
"status": "success",
@@ -93,7 +100,11 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
headers = _auth_headers(request)
async def stream_generator() -> AsyncIterator[str]:
async with httpx.AsyncClient(timeout=None) as client:
# trust_env=False: same-process loopback to 127.0.0.1 — honoring
# HTTP_PROXY / HTTPS_PROXY env vars (commonly set on dev machines)
# causes httpx to route loopback calls through an unreachable upstream
# proxy and wait ~40 seconds for timeout before falling back.
async with httpx.AsyncClient(timeout=None, trust_env=False) as client:
try:
body = _run_payload(
agent_name=INTENT_AGENT_ID,
@@ -119,16 +130,38 @@ async def stream_intent(request: Request, payload: dict = Body(...)) -> Streamin
captured = done
messages = _parse_last_messages(captured)
# Find the latest AIMessage's text content — that's what the
# frontend renders and what we scan for the handoff signal.
last_ai: dict[str, Any] = {}
for msg in reversed(messages):
if not isinstance(msg, dict):
continue
if (msg.get("type") or "").lower() in ("ai", "aimessage", "aimessagechunk"):
last_ai = msg
break
content = _flatten_content(last_ai.get("content", ""))
# Find the latest AIMessage with tool_calls (typically
# ask_clarification) — falls back to the latest plain
# AIMessage when the model produced no tool call.
dispatch_msg = _find_dispatch_message(messages)
content = _flatten_content(dispatch_msg.get("content", ""))
tool_calls = dispatch_msg.get("tool_calls") or []
# Clarification branch: the agent ended its run by calling
# ask_clarification. ClarificationMiddleware intercepts with
# Command(goto=END) and stashes the structured question in the
# tool_call args, so the AIMessage `content` is only the
# preamble ("下面我用几个问题确认:") and stops there. We splice
# the question back into the user-facing text so the frontend
# actually shows what the agent wants to ask.
clarification_call = next(
(tc for tc in tool_calls if (tc.get("name") or "").lower() == "ask_clarification"),
None,
)
if clarification_call is not None:
cargs = clarification_call.get("args") or {}
question = str(cargs.get("question") or "").strip()
follow_up = _find_trailing_ai_text(messages, exclude_text=content)
# Build a single content string the frontend can render
# as-is: preamble (if any) + the actual question.
parts: list[str] = []
if content.strip():
parts.append(content.strip())
if follow_up and follow_up != question:
parts.append(follow_up)
if question:
parts.append(question)
content = "\n\n".join(parts) if parts else content
summary: dict[str, Any] | None = None
match = _INTENT_READY_PATTERN.search(content)
@@ -285,7 +285,11 @@ async def init_multi_agent(request: Request, payload: dict = Body(...)) -> Strea
return f"data: {json.dumps(payload, ensure_ascii=False)}\n\n"
async def stream_generator() -> AsyncIterator[str]:
async with httpx.AsyncClient(timeout=None) as client:
# trust_env=False: same-process loopback to 127.0.0.1 — honoring
# HTTP_PROXY / HTTPS_PROXY env vars (commonly set on dev machines)
# causes httpx to route loopback calls through an unreachable upstream
# proxy and wait ~40 seconds for timeout before falling back.
async with httpx.AsyncClient(timeout=None, trust_env=False) as client:
try:
# Per-seat prepare task — same body as before, but we no longer
# await them with asyncio.gather. Instead, asyncio.as_completed
@@ -775,7 +779,11 @@ async def run_multi_agent_stream(request: Request, payload: dict = Body(...)) ->
headers = _auth_headers(request)
async def stream_generator() -> AsyncIterator[str]:
async with httpx.AsyncClient(timeout=None) as client:
# trust_env=False: same-process loopback to 127.0.0.1 — honoring
# HTTP_PROXY / HTTPS_PROXY env vars (commonly set on dev machines)
# causes httpx to route loopback calls through an unreachable upstream
# proxy and wait ~40 seconds for timeout before falling back.
async with httpx.AsyncClient(timeout=None, trust_env=False) as client:
try:
if agent_type == "leader":
gen = _leader_run(