v3.0 开发验证完成,满足webui和最小数据管理需求, 任务模版目前偏简单,可以扩展一下,再release开放使用

This commit is contained in:
2025-12-30 17:29:50 +08:00
parent 7b89d60b3b
commit 6d3fefc7a6
30 changed files with 3764 additions and 16 deletions

View File

@@ -1,6 +1,7 @@
from __future__ import annotations
import os
import secrets
import threading
from typing import Any
@@ -12,7 +13,10 @@ from argus.ray.models import JobSpec, RayConfig
from .config import V2Config
from .db import Db
from .janitor import JobsJanitor
from .scheduler import Scheduler
from .sftpgo import SFTPGoAdminClient, SFTPGoError
from .ui import register_ui_routes
def _utc_now_iso() -> str:
@@ -38,11 +42,48 @@ def create_app(config_path: str) -> FastAPI:
db.init()
scheduler = Scheduler(db=db, ray_cfg=ray_cfg, v2_cfg=v2_cfg)
janitor = JobsJanitor(
db=db,
user_root=v2_cfg.data.user_root,
trash_after_days=v2_cfg.data.retention.jobs_trash_after_days,
purge_after_days=v2_cfg.data.retention.jobs_purge_after_days,
interval_s=v2_cfg.data.retention.janitor_interval_s,
)
stop_flag = threading.Event()
tool = scheduler.tool
app = FastAPI(title="mvp-v2", version="2.0")
def _user_home(user_id: str) -> str:
base = v2_cfg.data.user_root.rstrip("/")
return f"{base}/{user_id}"
def _ensure_user_dirs(user_id: str) -> None:
home = _user_home(user_id)
# Note: create a physical /common directory under each user's home so that
# SFTPGo WebClient shows a "common" entry at the root. The actual shared
# content is exposed via SFTPGo virtual folders under /common/{datasets,models}.
for rel in ("datasets", "models", "code", "jobs", "trash/jobs", "common"):
os.makedirs(f"{home}/{rel}", exist_ok=True)
def _sftpgo_enabled() -> bool:
return bool(v2_cfg.data.sftpgo.enabled)
def _sftpgo_client() -> SFTPGoAdminClient:
cfg = v2_cfg.data.sftpgo
if not cfg.admin_api_base:
raise HTTPException(status_code=500, detail="sftpgo enabled but data.sftpgo.admin_api_base is empty")
pw = os.environ.get(cfg.admin_password_env, "")
if not pw:
raise HTTPException(status_code=500, detail=f"missing env: {cfg.admin_password_env}")
shared_root = ray_cfg.shared_root.rstrip("/")
return SFTPGoAdminClient(
admin_api_base=str(cfg.admin_api_base),
admin_user=str(cfg.admin_user),
admin_password=pw,
common_root=f"{shared_root}/common",
)
def _auth(req: Request) -> dict[str, Any]:
token_env = v2_cfg.auth.token_env
admin_token = os.environ.get(token_env, "")
@@ -74,6 +115,9 @@ def create_app(config_path: str) -> FastAPI:
def _startup() -> None:
t = threading.Thread(target=scheduler.run_forever, args=(stop_flag,), daemon=True)
t.start()
if int(janitor.interval_s) > 0:
tj = threading.Thread(target=janitor.run_forever, args=(stop_flag,), daemon=True)
tj.start()
@app.on_event("shutdown")
def _shutdown() -> None:
@@ -93,7 +137,42 @@ def create_app(config_path: str) -> FastAPI:
row = db.create_user(user_id=user_id, display_name=str(display_name) if display_name is not None else None)
except Exception as e:
raise HTTPException(status_code=409, detail=f"user create failed: {e!r}")
return {"user_id": row.get("user_id", user_id), "state": row.get("state", "ACTIVE")}
# v3.0: create user dir structure (datasets/models/code/jobs/trash).
try:
_ensure_user_dirs(user_id)
except Exception as e:
raise HTTPException(status_code=500, detail=f"failed to create user dirs: {e!r}")
out: dict[str, Any] = {"user_id": row.get("user_id", user_id), "state": row.get("state", "ACTIVE")}
# v3.0: scheme A (password) SFTPGo integration.
if _sftpgo_enabled():
pw = secrets.token_urlsafe(12)
try:
_sftpgo_client().create_user(username=user_id, password=pw, home_dir=_user_home(user_id))
except SFTPGoError as e:
# Make create user idempotent for retries:
# If the user already exists in SFTPGo, reset password and enable it.
if "http error: 409" in str(e):
try:
_sftpgo_client().reset_password(username=user_id, new_password=pw, home_dir=_user_home(user_id))
_sftpgo_client().enable_user(username=user_id, home_dir=_user_home(user_id))
except Exception as e2:
raise HTTPException(status_code=502, detail=f"sftpgo upsert user failed: {e2!r}")
else:
raise HTTPException(status_code=502, detail=f"sftpgo create user failed: {e!r}")
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=502, detail=f"sftpgo create user failed: {e!r}")
out["sftp"] = {
"username": user_id,
"password": pw, # one-time return to admin; do not persist plaintext
"host": v2_cfg.data.sftpgo.host,
"port": int(v2_cfg.data.sftpgo.sftp_port),
}
return out
@app.post("/api/v2/users/{user_id}/tokens")
async def issue_token(user_id: str, req: Request) -> dict[str, Any]:
@@ -104,6 +183,12 @@ def create_app(config_path: str) -> FastAPI:
token = db.issue_token(user_id=user_id)
return {"user_id": user_id, "token": token}
@app.get("/api/v2/users")
async def list_users(req: Request, limit: int = 200) -> dict[str, Any]:
_require_admin(req)
lim = max(1, min(int(limit), 1000))
return {"users": db.list_users(limit=lim), "limit": lim}
@app.post("/api/v2/users/{user_id}:disable")
async def disable_user(user_id: str, req: Request) -> dict[str, Any]:
_require_admin(req)
@@ -111,8 +196,122 @@ def create_app(config_path: str) -> FastAPI:
if not u:
raise HTTPException(status_code=404, detail="user not found")
db.disable_user(user_id=user_id)
if _sftpgo_enabled():
try:
_sftpgo_client().disable_user(username=user_id, home_dir=_user_home(user_id))
except Exception:
# Best-effort: DB state is source of truth for API auth; SFTPGo sync can lag.
pass
return {"user_id": user_id, "state": "DISABLED"}
@app.post("/api/v2/users/{user_id}/sftp:reset_password")
async def reset_sftp_password(user_id: str, req: Request) -> dict[str, Any]:
_require_admin(req)
u = db.get_user(user_id)
if not u:
raise HTTPException(status_code=404, detail="user not found")
if not _sftpgo_enabled():
raise HTTPException(status_code=400, detail="sftpgo is not enabled")
pw = secrets.token_urlsafe(12)
try:
_sftpgo_client().reset_password(username=user_id, new_password=pw, home_dir=_user_home(user_id))
except HTTPException:
raise
except Exception as e:
raise HTTPException(status_code=502, detail=f"sftpgo reset password failed: {e!r}")
return {"user_id": user_id, "password": pw}
@app.post("/api/v2/me/sftp:reset_password")
async def reset_my_sftp_password(req: Request) -> dict[str, Any]:
"""
v3.0 WebUI: allow a user to rotate their own SFTPGo password and copy it.
Note: SFTPGo does not allow reading the current password, so this endpoint returns a new one-time password.
"""
subject = _auth(req)
user_id = str(subject["user_id"])
u = db.get_user(user_id)
if not u:
raise HTTPException(status_code=404, detail="user not found")
if not _sftpgo_enabled():
raise HTTPException(status_code=400, detail="sftpgo is not enabled")
pw = secrets.token_urlsafe(12)
try:
_sftpgo_client().reset_password(username=user_id, new_password=pw, home_dir=_user_home(user_id))
_sftpgo_client().enable_user(username=user_id, home_dir=_user_home(user_id))
except Exception as e:
raise HTTPException(status_code=502, detail=f"sftpgo reset password failed: {e!r}")
return {"user_id": user_id, "password": pw}
@app.get("/api/v2/me")
async def me(req: Request) -> dict[str, Any]:
subject = _auth(req)
user_id = str(subject["user_id"])
try:
_ensure_user_dirs(user_id)
except Exception:
# Best-effort: user may still be able to use API even if FS init fails.
pass
# Best-effort: reconcile SFTPGo user to include /common read-only mounts.
# This makes the virtual folders visible without requiring a password reset.
if _sftpgo_enabled() and not subject.get("is_admin"):
try:
_sftpgo_client().enable_user(username=user_id, home_dir=_user_home(user_id))
except Exception:
pass
home = _user_home(user_id)
out: dict[str, Any] = {
"user_id": user_id,
"is_admin": bool(subject.get("is_admin")),
"paths": {
"home": home,
"datasets": f"{home}/datasets",
"models": f"{home}/models",
"code": f"{home}/code",
"jobs": f"{home}/jobs",
"trash_jobs": f"{home}/trash/jobs",
},
"retention": {
"jobs_trash_after_days": int(v2_cfg.data.retention.jobs_trash_after_days),
"jobs_purge_after_days": int(v2_cfg.data.retention.jobs_purge_after_days),
},
}
if _sftpgo_enabled():
out["sftp"] = {
"host": v2_cfg.data.sftpgo.host,
"port": int(v2_cfg.data.sftpgo.sftp_port),
"username": user_id,
}
return out
@app.get("/api/v2/tasks")
async def list_tasks(req: Request, limit: int = 200, offset: int = 0, states: str | None = None) -> dict[str, Any]:
subject = _auth(req)
lim = max(1, min(int(limit), 1000))
off = max(0, int(offset))
state_list: list[str] | None = None
if states:
raw = [s.strip() for s in str(states).split(",") if s.strip()]
# Keep it strict to avoid typos silently returning empty results.
allowed = {
"QUEUED",
"PENDING_RESOURCES",
"SUBMITTING",
"SUBMITTED",
"RUNNING",
"SUCCEEDED",
"FAILED",
"CANCELED",
}
for s in raw:
if s not in allowed:
raise HTTPException(status_code=400, detail=f"invalid state: {s}")
state_list = raw or None
if subject.get("is_admin"):
tasks = db.list_tasks(user_id=None, states=state_list, limit=lim, offset=off)
else:
tasks = db.list_tasks(user_id=str(subject["user_id"]), states=state_list, limit=lim, offset=off)
return {"tasks": tasks, "limit": lim, "offset": off, "has_more": bool(len(tasks) == lim)}
@app.post("/api/v2/tasks")
async def submit_task(req: Request) -> dict[str, Any]:
subject = _auth(req)
@@ -126,13 +325,40 @@ def create_app(config_path: str) -> FastAPI:
except Exception as e:
raise HTTPException(status_code=400, detail=f"invalid jobspec: {e!r}")
# v2.5 constraint: training inputs must come from /private/common (dev/prod统一)。
common_prefix = ray_cfg.shared_root.rstrip("/") + "/common/"
for k, v in (("code_path", spec.code_path), ("train_file", spec.train_file), ("val_file", spec.val_file)):
# v3.0 path policy:
# - code_path: only allow /private/common/...
# - train/val: allow /private/common/datasets/... OR /private/users/<me>/datasets/...
# - model_id: if it looks like a local path (/private/...), allow only models dirs:
# /private/common/models/... OR /private/users/<me>/models/...
root = ray_cfg.shared_root.rstrip("/")
common_prefix = f"{root}/common/"
user_prefix = f"{root}/users/{str(subject['user_id']).strip()}/"
common_datasets_prefix = f"{common_prefix}datasets/"
user_datasets_prefix = f"{user_prefix}datasets/"
common_models_prefix = f"{common_prefix}models/"
user_models_prefix = f"{user_prefix}models/"
if not str(spec.code_path).startswith(common_prefix):
raise HTTPException(status_code=400, detail=f"code_path must start with {common_prefix}")
for k, v in (("train_file", spec.train_file), ("val_file", spec.val_file)):
if v is None:
continue
if not str(v).startswith(common_prefix):
raise HTTPException(status_code=400, detail=f"{k} must start with {common_prefix}")
sv = str(v)
if not (sv.startswith(common_datasets_prefix) or sv.startswith(user_datasets_prefix)):
raise HTTPException(
status_code=400,
detail=f"{k} must start with {common_datasets_prefix} or {user_datasets_prefix}",
)
model_id = str(spec.model_id)
if model_id.startswith(f"{root}/"):
if not (model_id.startswith(common_models_prefix) or model_id.startswith(user_models_prefix)):
raise HTTPException(
status_code=400,
detail=f"model_id local path must start with {common_models_prefix} or {user_models_prefix}",
)
task_id = new_task_id(spec.workload, user_id=str(subject["user_id"]))
db.create_task_v25(
@@ -257,4 +483,7 @@ def create_app(config_path: str) -> FastAPI:
return db.list_queue()
return db.list_queue(user_id=str(subject["user_id"]))
# v3.0: minimal WebUI (no server-side session; token stored in browser localStorage).
register_ui_routes(app)
return app