fix(task-deeplink): 共享任务对话的 md/产物按对话创建者解析路径,修复切换账号后找不到文件

xdfx/rwfx/3qfx 任务深链对话按 metadata.taskId 全局共享、不区分用户,但生成的
md/artifacts 与上传文件物理存在 users/{user_id}/threads/{thread_id}/ 下,user_id
之前取当前登录账号。导致 A 账号生成的文件,B 账号打开同一共享对话时后端去
users/B/ 找 → 404「找不到」。

新增 deerflow/runtime/thread_paths.py(resolve_path_user_id /
aresolve_path_user_id):带 taskId 的共享对话统一解析到对话创建者
(threads_meta.user_id),个人对话仍走当前登录(行为不变)。在所有线程文件路径关口替换:
写入源 ThreadDataMiddleware、present_files、uploads(manager+middleware+router)、
产物读写(path_utils → artifacts/skills router)、嵌入式 client.get_artifact。
正向结果进程内缓存;无 DB/内存态/无行均安全回退到当前登录。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
AdministratorandClaude Opus 4.8 committed 2026-06-19 14:35:22 +08:00
1 parent 13ef1942f2
commit 23e6685977
11 files changed
+269 -99

No files matched your search

@@ -5,16 +5,21 @@ from pathlib import Path
from fastapi import HTTPException
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
from deerflow.runtime.thread_paths import aresolve_path_user_id, resolve_path_user_id
def resolve_thread_virtual_path(thread_id: str, virtual_path: str) -> Path:
def resolve_thread_virtual_path(thread_id: str, virtual_path: str, *, user_id: str | None = None) -> Path:
"""Resolve a virtual path to the actual filesystem path under thread user-data.
Args:
thread_id: The thread ID.
virtual_path: The virtual path as seen inside the sandbox
(e.g., /mnt/user-data/outputs/file.txt).
user_id: Pre-resolved canonical user bucket. When ``None`` it is
resolved synchronously via :func:`resolve_path_user_id` (the
thread creator for task-shared threads, else the current
login). Async callers should pass the result of
:func:`aresolve_path_user_id` to avoid a blocking DB read.
Returns:
The resolved filesystem path.
@@ -22,8 +27,21 @@ def resolve_thread_virtual_path(thread_id: str, virtual_path: str) -> Path:
Raises:
HTTPException: If the path is invalid or outside allowed directories.
"""
if user_id is None:
user_id = resolve_path_user_id(thread_id)
try:
return get_paths().resolve_virtual_path(thread_id, virtual_path, user_id=get_effective_user_id())
return get_paths().resolve_virtual_path(thread_id, virtual_path, user_id=user_id)
except ValueError as e:
status = 403 if "traversal" in str(e) else 400
raise HTTPException(status_code=status, detail=str(e))
async def aresolve_thread_virtual_path(thread_id: str, virtual_path: str) -> Path:
"""Async variant of :func:`resolve_thread_virtual_path` for FastAPI handlers.
Resolves the canonical user bucket without blocking the event loop, so a
task-shared thread's artifacts resolve to the thread creator's directory
regardless of which account is currently logged in.
"""
user_id = await aresolve_path_user_id(thread_id)
return resolve_thread_virtual_path(thread_id, virtual_path, user_id=user_id)
@@ -10,9 +10,9 @@ from fastapi.responses import FileResponse, PlainTextResponse, Response
from pydantic import BaseModel
from app.gateway.authz import require_permission
from app.gateway.path_utils import resolve_thread_virtual_path
from app.gateway.path_utils import aresolve_thread_virtual_path
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
from deerflow.runtime.thread_paths import aresolve_path_user_id
logger = logging.getLogger(__name__)
@@ -155,7 +155,7 @@ async def list_artifacts(thread_id: str, request: Request) -> dict:
返回 ``{ "thread_id", "files": [{ path, name, size_bytes, mime_type, modified_at }] }``,
目录不存在时 ``files`` 为空数组(非 404)。
"""
outputs_dir = get_paths().sandbox_outputs_dir(thread_id, user_id=get_effective_user_id())
outputs_dir = get_paths().sandbox_outputs_dir(thread_id, user_id=await aresolve_path_user_id(thread_id))
return {"thread_id": thread_id, "files": collect_outputs_listing(outputs_dir)}
@@ -206,7 +206,7 @@ async def get_artifact(thread_id: str, path: str, request: Request, download: bo
skill_file_path = path[: marker_pos + len(".skill")] # e.g., "mnt/user-data/outputs/my-skill.skill"
internal_path = path[marker_pos + len(skill_marker) :] # e.g., "SKILL.md"
actual_skill_path = resolve_thread_virtual_path(thread_id, skill_file_path)
actual_skill_path = await aresolve_thread_virtual_path(thread_id, skill_file_path)
if not actual_skill_path.exists():
raise HTTPException(status_code=404, detail=f"Skill file not found: {skill_file_path}")
@@ -236,7 +236,7 @@ async def get_artifact(thread_id: str, path: str, request: Request, download: bo
except UnicodeDecodeError:
return Response(content=content, media_type=mime_type or "application/octet-stream", headers=cache_headers)
actual_path = resolve_thread_virtual_path(thread_id, path)
actual_path = await aresolve_thread_virtual_path(thread_id, path)
logger.info(f"Resolving artifact path: thread_id={thread_id}, requested_path={path}, actual_path={actual_path}")
@@ -285,7 +285,7 @@ async def update_artifact(
if ".skill/" in path:
raise HTTPException(status_code=400, detail="Skill archive contents are read-only.")
actual_path = resolve_thread_virtual_path(thread_id, path)
actual_path = await aresolve_thread_virtual_path(thread_id, path)
logger.info(f"Updating artifact path: thread_id={thread_id}, requested_path={path}, actual_path={actual_path}")
if not actual_path.exists():
@@ -17,7 +17,7 @@ from pydantic import BaseModel, Field
from sqlalchemy import select
from app.gateway.deps import get_agent_store, get_config, get_skill_store, get_tag_store
from app.gateway.path_utils import resolve_thread_virtual_path
from app.gateway.path_utils import aresolve_thread_virtual_path
from deerflow.agents.lead_agent.prompt import refresh_skills_system_prompt_cache_async
from deerflow.config.app_config import AppConfig
from deerflow.config.extensions_config import ExtensionsConfig, SkillDisplayConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
@@ -1058,7 +1058,7 @@ async def install_skill(
target_category = body.target_category
if target_category == SkillCategory.PUBLIC and not is_admin:
raise HTTPException(status_code=403, detail="Only admin users can install skills to the public directory")
skill_file_path = resolve_thread_virtual_path(body.thread_id, body.path)
skill_file_path = await aresolve_thread_virtual_path(body.thread_id, body.path)
result = await get_or_new_skill_storage(app_config=config).ainstall_skill_from_archive(skill_file_path, target_category=target_category)
try:
from deerflow.skills.usage import mark_uploaded
@@ -11,7 +11,7 @@ from app.gateway.authz import require_permission
from app.gateway.deps import get_config
from deerflow.config.app_config import AppConfig
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
from deerflow.runtime.thread_paths import aresolve_path_user_id
from deerflow.sandbox.sandbox_provider import SandboxProvider, get_sandbox_provider
from deerflow.uploads.manager import (
PathTraversalError,
@@ -186,7 +186,7 @@ async def upload_files(
uploads_dir = ensure_uploads_dir(thread_id)
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=get_effective_user_id())
sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=await aresolve_path_user_id(thread_id))
uploaded_files = []
written_paths = []
sandbox_sync_targets = []
@@ -308,7 +308,7 @@ async def list_uploaded_files(thread_id: str, request: Request) -> dict:
enrich_file_listing(result, thread_id)
# Gateway additionally includes the sandbox-relative path.
sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=get_effective_user_id())
sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=await aresolve_path_user_id(thread_id))
for f in result["files"]:
f["path"] = str(sandbox_uploads / f["filename"])