sync update from LAN repo (source master-nj @ 067eb808)

This commit is contained in:
gozeros committed 2026-11-10 14:04:09 +08:00
1 parent 1244fb1f2f
commit 1d5dd8fc90
182 files changed
+18973 -769

No files matched your search

@@ -152,6 +152,18 @@ def _list_export_manifests(mapping_id: str, *, limit: int) -> list[dict[str, Any
def _delete_base_package_files(base_id: str, import_job_ids: list[str]) -> None:
"""Delete package artifacts owned by one assistant base only."""
import shutil
from app.gateway.assistant_file_ingest import file_job_dir
for job_id in import_job_ids:
# UUID validation confines cleanup to exactly one job directory.
try:
directory = file_job_dir(job_id)
except ValueError:
continue
if directory.is_dir() and not directory.is_symlink():
shutil.rmtree(directory)
root = _package_root()
if not root.is_dir():
return
@@ -448,10 +460,71 @@ async def import_skills(request: Request, _body: SkillImportRequest) -> dict[str
raise HTTPException(status_code=410, detail="不支持技能直接归纳到助手知识库,请先归纳到 WeKnora 普通知识库后再导入助手知识库")
@router.post("/imports/files", status_code=410)
async def import_files(request: Request) -> dict[str, Any]:
@router.post("/imports/files", status_code=202)
async def import_files(
request: Request,
file: UploadFile = File(...),
assistant_base_id: str | None = Form(default=None),
) -> dict[str, Any]:
import hashlib
from app.gateway.assistant_file_ingest import ALLOWED_EXTENSIONS, MAX_FILE_BYTES, file_job_dir, save_json, start_file_job
actor = await _actor(request, admin=True)
filename = (file.filename or "document").replace("\\", "/").rsplit("/", 1)[-1][:240]
extension = Path(filename).suffix.lower()
if extension not in ALLOWED_EXTENSIONS:
await file.close()
raise HTTPException(status_code=415, detail="支持 Markdown、TXT、CSV、PDF、Word、Excel、PowerPoint 文件")
job = await _store(request).create_queued_import_job(
source_type="file", source_key=f"file-upload:{uuid4()}", source_name=filename,
trigger="local_file_upload", created_by=actor, base_id=assistant_base_id,
metadata={"type": "file", "filename": filename}, phase="uploading",
)
root = file_job_dir(job["id"])
await asyncio.to_thread(root.mkdir, parents=True, exist_ok=True)
path = root / f"original{extension}"
size, digest = 0, hashlib.sha256()
try:
with path.open("wb") as handle:
while chunk := await file.read(1024 * 1024):
size += len(chunk)
if size > MAX_FILE_BYTES:
raise HTTPException(status_code=413, detail="单个文件最大 100 MB,请拆分后上传")
digest.update(chunk)
await asyncio.to_thread(handle.write, chunk)
if not size:
raise HTTPException(status_code=422, detail="上传文件为空")
await asyncio.to_thread(save_json, root / "manifest.json", {
"filename": filename, "stored_name": path.name, "digest": digest.hexdigest(), "actor": actor,
})
job = await _store(request).update_import_job(job["id"], phase="queued", counts={"uploaded_bytes": size})
start_file_job(request.app, job["id"])
return job
except Exception as exc:
await _store(request).update_import_job(job["id"], status="failed", phase="upload_failed", error=str(getattr(exc, "detail", exc)), completed=True)
await asyncio.to_thread(path.unlink, missing_ok=True)
raise
finally:
await file.close()
@router.post("/import-jobs/{job_id}/retry-file", status_code=202)
async def retry_file_import(request: Request, job_id: str) -> dict[str, Any]:
from app.gateway.assistant_file_ingest import file_job_dir, retry_file_job
await _actor(request, admin=True)
raise HTTPException(status_code=410, detail="助手知识库不支持导入任意本地文件,请从 WeKnora 普通知识库导出后导入")
store = _store(request)
job = await store.get_job(job_id)
if not job or job.get("trigger") != "local_file_upload":
raise HTTPException(status_code=404, detail="文件处理任务不存在")
if job["status"] == "completed":
raise HTTPException(status_code=409, detail="文件已处理完成")
if not (file_job_dir(job_id) / "manifest.json").exists():
raise HTTPException(status_code=409, detail="文件上传未完成,请重新上传")
if not await retry_file_job(request.app, job_id):
raise HTTPException(status_code=409, detail="文件仍在处理中")
return await store.get_job(job_id)
@router.post("/imports/weknora-package", status_code=202)
@@ -748,8 +821,16 @@ async def _ensure_local_wiki_vectors_for_export(
) -> None:
mapping_id = str(mapping.get("id") or mapping.get("knowledge_base_id") or "")
service = getattr(request.app.state, "llmwiki_sync_service", None)
if service is None or not mapping_id:
if not mapping_id:
raise RuntimeError("请先配置 Wiki 编码模型并启用本地向量索引,再生成向量数据包")
if service is None:
# Exporting an existing snapshot does not require an encoder. The
# snapshot already records its model fingerprint and dimensions, so a
# deployment that encoded online (or later disabled the encoder) can
# still package those vectors without silently re-encoding them.
if await _has_local_wiki_vectors_for_export(request, mapping_id):
return
raise RuntimeError("当前知识库没有可导出的本地 Wiki 向量;请先完成向量同步")
# Refresh remote metadata/content hashes even when the previous generation
# was complete. Unchanged articles reuse their existing vectors.
sync_mapping = dict(mapping)