mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-02 22:02:13 +08:00
* refactor: extract shared skill installer and upload manager to harness Move duplicated business logic from Gateway routers and Client into shared harness modules, eliminating code duplication. New shared modules: - deerflow.skills.installer: 6 functions (zip security, extraction, install) - deerflow.uploads.manager: 7 functions (normalize, deduplicate, validate, list, delete, get_uploads_dir, ensure_uploads_dir) Key improvements: - SkillAlreadyExistsError replaces stringly-typed 409 status routing - normalize_filename rejects backslash-containing filenames - Read paths (list/delete) no longer mkdir via get_uploads_dir - Write paths use ensure_uploads_dir for explicit directory creation - list_files_in_dir does stat inside scandir context (no re-stat) - install_skill_from_archive uses single is_file() check (one syscall) - Fix agent config key not reset on update_mcp_config/update_skill Tests: 42 new (22 installer + 20 upload manager) + client hardening * refactor: centralize upload URL construction and clean up installer - Extract upload_virtual_path(), upload_artifact_url(), enrich_file_listing() into shared manager.py, eliminating 6 duplicated URL constructions across Gateway router and Client - Derive all upload URLs from VIRTUAL_PATH_PREFIX constant instead of hardcoded "mnt/user-data/uploads" strings - Eliminate TOCTOU pre-checks and double file read in installer — single ZipFile() open with exception handling replaces is_file() + is_zipfile() + ZipFile() sequence - Add missing re-exports: ensure_uploads_dir in uploads/__init__.py, SkillAlreadyExistsError in skills/__init__.py - Remove redundant .lower() on already-lowercase CONVERTIBLE_EXTENSIONS - Hoist sandbox_uploads_dir(thread_id) before loop in uploads router * fix: add input validation for thread_id and filename length - Reject thread_id containing unsafe filesystem characters (only allow alphanumeric, hyphens, underscores, dots) — prevents 500 on inputs like <script> or shell metacharacters - Reject filenames longer than 255 bytes (OS limit) in normalize_filename - Gateway upload router maps ValueError to 400 for invalid thread_id * fix: address PR review — symlink safety, input validation coverage, error ordering - list_files_in_dir: use follow_symlinks=False to prevent symlink metadata leakage; check is_dir() instead of exists() for non-directory paths - install_skill_from_archive: restore is_file() pre-check before extension validation so error messages match the documented exception contract - validate_thread_id: move from ensure_uploads_dir to get_uploads_dir so all entry points (upload/list/delete) are protected - delete_uploaded_file: catch ValueError from thread_id validation (was 500) - requires_llm marker: also skip when OPENAI_API_KEY is unset - e2e fixture: update TitleMiddleware exclusion comment (kept filtering — middleware triggers extra LLM calls that add non-determinism to tests) * chore: revert uv.lock to main — no dependency changes in this PR * fix: use monkeypatch for global config in e2e fixture to prevent test pollution The e2e_env fixture was calling set_title_config() and set_summarization_config() directly, which mutated global singletons without automatic cleanup. When pytest ran test_client_e2e.py before test_title_middleware_core_logic.py, the leaked enabled=False caused 5 title tests to fail in CI. Switched to monkeypatch.setattr on the module-level private variables so pytest restores the originals after each test. * fix: address code review — URL encoding, API consistency, test isolation - upload_artifact_url: percent-encode filename to handle spaces/#/? - deduplicate_filename: mutate seen set in place (caller no longer needs manual .add() — less error-prone API) - list_files_in_dir: document that size is int, enrich stringifies - e2e fixture: monkeypatch _app_config instead of set_app_config() to prevent global singleton pollution (same pattern as title/summarization fix) - _make_e2e_config: read LLM connection details from env vars so external contributors can override defaults - Update tests to match new deduplicate_filename contract * docs: rewrite RFC in English and add alternatives/breaking changes sections * fix: address code review feedback on PR #1202 - Rename deduplicate_filename to claim_unique_filename to make the in-place set mutation explicit in the function name - Replace PermissionError with PathTraversalError(ValueError) for path traversal detection — malformed input is 400, not 403 * fix: set _app_config_is_custom in e2e test fixture to prevent config.yaml lookup in CI --------- Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> Co-authored-by: DanielWalnut <45447813+hetaoBackend@users.noreply.github.com>
149 lines
5.0 KiB
Python
149 lines
5.0 KiB
Python
"""Upload router for handling file uploads."""
|
|
|
|
import logging
|
|
|
|
from fastapi import APIRouter, File, HTTPException, UploadFile
|
|
from pydantic import BaseModel
|
|
|
|
from deerflow.config.paths import get_paths
|
|
from deerflow.sandbox.sandbox_provider import get_sandbox_provider
|
|
from deerflow.uploads.manager import (
|
|
PathTraversalError,
|
|
delete_file_safe,
|
|
enrich_file_listing,
|
|
ensure_uploads_dir,
|
|
get_uploads_dir,
|
|
list_files_in_dir,
|
|
normalize_filename,
|
|
upload_artifact_url,
|
|
upload_virtual_path,
|
|
)
|
|
from deerflow.utils.file_conversion import CONVERTIBLE_EXTENSIONS, convert_file_to_markdown
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(prefix="/api/threads/{thread_id}/uploads", tags=["uploads"])
|
|
|
|
|
|
class UploadResponse(BaseModel):
|
|
"""Response model for file upload."""
|
|
|
|
success: bool
|
|
files: list[dict[str, str]]
|
|
message: str
|
|
|
|
|
|
|
|
|
|
@router.post("", response_model=UploadResponse)
|
|
async def upload_files(
|
|
thread_id: str,
|
|
files: list[UploadFile] = File(...),
|
|
) -> UploadResponse:
|
|
"""Upload multiple files to a thread's uploads directory."""
|
|
if not files:
|
|
raise HTTPException(status_code=400, detail="No files provided")
|
|
|
|
try:
|
|
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)
|
|
uploaded_files = []
|
|
|
|
sandbox_provider = get_sandbox_provider()
|
|
sandbox_id = sandbox_provider.acquire(thread_id)
|
|
sandbox = sandbox_provider.get(sandbox_id)
|
|
|
|
for file in files:
|
|
if not file.filename:
|
|
continue
|
|
|
|
try:
|
|
safe_filename = normalize_filename(file.filename)
|
|
except ValueError:
|
|
logger.warning(f"Skipping file with unsafe filename: {file.filename!r}")
|
|
continue
|
|
|
|
try:
|
|
content = await file.read()
|
|
file_path = uploads_dir / safe_filename
|
|
file_path.write_bytes(content)
|
|
|
|
virtual_path = upload_virtual_path(safe_filename)
|
|
|
|
if sandbox_id != "local":
|
|
sandbox.update_file(virtual_path, content)
|
|
|
|
file_info = {
|
|
"filename": safe_filename,
|
|
"size": str(len(content)),
|
|
"path": str(sandbox_uploads / safe_filename),
|
|
"virtual_path": virtual_path,
|
|
"artifact_url": upload_artifact_url(thread_id, safe_filename),
|
|
}
|
|
|
|
logger.info(f"Saved file: {safe_filename} ({len(content)} bytes) to {file_info['path']}")
|
|
|
|
file_ext = file_path.suffix.lower()
|
|
if file_ext in CONVERTIBLE_EXTENSIONS:
|
|
md_path = await convert_file_to_markdown(file_path)
|
|
if md_path:
|
|
md_virtual_path = upload_virtual_path(md_path.name)
|
|
|
|
if sandbox_id != "local":
|
|
sandbox.update_file(md_virtual_path, md_path.read_bytes())
|
|
|
|
file_info["markdown_file"] = md_path.name
|
|
file_info["markdown_path"] = str(sandbox_uploads / md_path.name)
|
|
file_info["markdown_virtual_path"] = md_virtual_path
|
|
file_info["markdown_artifact_url"] = upload_artifact_url(thread_id, md_path.name)
|
|
|
|
uploaded_files.append(file_info)
|
|
|
|
except Exception as e:
|
|
logger.error(f"Failed to upload {file.filename}: {e}")
|
|
raise HTTPException(status_code=500, detail=f"Failed to upload {file.filename}: {str(e)}")
|
|
|
|
return UploadResponse(
|
|
success=True,
|
|
files=uploaded_files,
|
|
message=f"Successfully uploaded {len(uploaded_files)} file(s)",
|
|
)
|
|
|
|
|
|
@router.get("/list", response_model=dict)
|
|
async def list_uploaded_files(thread_id: str) -> dict:
|
|
"""List all files in a thread's uploads directory."""
|
|
try:
|
|
uploads_dir = get_uploads_dir(thread_id)
|
|
except ValueError as e:
|
|
raise HTTPException(status_code=400, detail=str(e))
|
|
result = list_files_in_dir(uploads_dir)
|
|
enrich_file_listing(result, thread_id)
|
|
|
|
# Gateway additionally includes the sandbox-relative path.
|
|
sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id)
|
|
for f in result["files"]:
|
|
f["path"] = str(sandbox_uploads / f["filename"])
|
|
|
|
return result
|
|
|
|
|
|
@router.delete("/{filename}")
|
|
async def delete_uploaded_file(thread_id: str, filename: str) -> dict:
|
|
"""Delete a file from a thread's uploads directory."""
|
|
try:
|
|
uploads_dir = get_uploads_dir(thread_id)
|
|
except ValueError as e:
|
|
raise HTTPException(status_code=400, detail=str(e))
|
|
try:
|
|
return delete_file_safe(uploads_dir, filename, convertible_extensions=CONVERTIBLE_EXTENSIONS)
|
|
except FileNotFoundError:
|
|
raise HTTPException(status_code=404, detail=f"File not found: {filename}")
|
|
except PathTraversalError:
|
|
raise HTTPException(status_code=400, detail="Invalid path")
|
|
except Exception as e:
|
|
logger.error(f"Failed to delete {filename}: {e}")
|
|
raise HTTPException(status_code=500, detail=f"Failed to delete {filename}: {str(e)}")
|