feat(backup): review a restore, run it as an Activity job, verify backups

- POST /restore/preview stages an upload in the library's folder and
  answers what it holds beside the live library, writing nothing live;
  DELETE discards it; at most two stages are held (429 too-large).
- POST /restore/apply rechecks the live fingerprint (409 plan-changed) and
  starts "Database restore": exclusive, not cancellable, indeterminate. It
  waits for request leases, publishes the exact staged bytes, swaps the
  database, prunes safety backups and logs counts, repairs and the backup.
- The legacy /restore runs the same stage and publish as an exclusive hold
  with its old response, so a restore and the health check, Move library
  and every other job refuse each other.
- JobRegistry.lease: Needs review decisions and maintenance and restore
  previews are refused while an exclusive job runs, and a restore waits
  for them before it switches the file.
- GET /backup holds a guarded slot, verifies a standalone snapshot before
  streaming it and removes the closed temp file; GET /backup/status lists
  the safety backups on disk and this session's verified download.
This commit is contained in:
Vito Sansevero
2026-10-25 06:20:12 -07:00
parent b9bafbbfa0
commit f193a3a1ce
11 changed files with 1656 additions and 241 deletions
-215
View File
@@ -3,14 +3,12 @@
import asyncio
import contextlib
from contextlib import closing
import datetime
import functools
import hashlib
import json
import math
import os
import sqlite3
import tempfile
import threading
import time
from pathlib import Path
@@ -27,7 +25,6 @@ from .jobs import (
DUPLICATE_CLEANUP_JOB_KIND,
DUPLICATES_JOB_KIND,
MAINTENANCE_JOB_KIND,
RESTORE_JOB_KIND,
JobBusy,
)
@@ -37,7 +34,6 @@ except ImportError:
from utils.parallel import map_parallel
try:
from ...database.operations import PromptDatabase
from ...database.pair_ingestion import ingest_resolved_pair
from ...utils.generation_params import (
PLACEHOLDERS,
@@ -48,7 +44,6 @@ try:
from ...utils.prompt_pair_resolver import resolve_prompt_pair
from ...utils.review_capture import reviewable
except ImportError:
from database.operations import PromptDatabase
from database.pair_ingestion import ingest_resolved_pair
from utils.generation_params import (
PLACEHOLDERS,
@@ -1236,216 +1231,6 @@ class AdminRoutesMixin:
"message": f"Found {len(issues)} consistency issues",
}
async def backup_database(self, request):
"""Download a consistent copy of the prompts database (WAL included)."""
try:
model = self.db.model
db_path = model.db_path
if not os.path.exists(db_path):
return web.json_response(
{"success": False, "error": "Database file not found"}, status=404
)
fd, temp_path = tempfile.mkstemp(suffix=".db")
os.close(fd)
try:
ok = await self._run_in_executor(model.backup_database, temp_path)
if not ok:
return web.json_response(
{"success": False, "error": "Failed to create database backup"},
status=500,
)
# Read once (the file is deleted right after) rather than
# streaming so the temp file never outlives the request.
with open(temp_path, "rb") as fh:
file_data = fh.read()
finally:
if os.path.exists(temp_path):
os.unlink(temp_path)
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"prompts_backup_{timestamp}.db"
return web.Response(
body=file_data,
content_type="application/octet-stream",
headers={
"Content-Disposition": f'attachment; filename="{filename}"',
"Content-Length": str(len(file_data)),
},
)
except Exception as e:
self.logger.error(f"Backup error: {e}", exc_info=True)
return web.json_response(
{
"success": False,
"error": f"Failed to backup database: {self._public_error(e)}",
},
status=500,
)
async def restore_database(self, request):
"""Restore the prompts database from an uploaded SQLite file.
The upload is streamed to a temp file. Free disk space decides how
large it may be (``maintenance.restore_room``), under a 64 GiB ceiling
(``restore_max_bytes``): a request whose Content-Length does not fit
is refused before anything is written, and one without is refused as
soon as its running size does not. The file is
verified with PromptModel.verify_database_file and only then copied
over the live database, which is backed up first. The whole request
holds the registry (records): it is refused while a scan or another
record-changing job runs, and those are refused while it runs.
"""
return await self._run_held(
RESTORE_JOB_KIND,
"Database restore (admin page)",
"records",
lambda: self._restore_database(request),
)
def _restore_refusal(self, size, ceiling, room, *, known):
"""``400 too-large`` past the ceiling, else ``507 insufficient-space``."""
from .maintenance import restore_space_message
if size > ceiling:
return web.json_response(
{
"success": False,
"code": "too-large",
"error": (
"File too large. Maximum size is "
f"{ceiling // (1024 * 1024)}MB"
),
},
status=400,
)
return web.json_response(
{
"success": False,
"code": "insufficient-space",
"error": restore_space_message(size, room, known=known),
},
status=507,
)
async def _restore_database(self, request):
from .maintenance import RESTORE_MAX_BYTES, restore_room
ceiling = getattr(self, "restore_max_bytes", RESTORE_MAX_BYTES)
temp_path = None
try:
# Free disk space decides how large a backup may be (#313): the
# upload, its staged copy and the swap must all fit.
room = await self._run_in_executor(restore_room, self.db.model.db_path)
max_bytes = min(ceiling, room)
length = request.content_length
if length is not None and length > max_bytes:
return self._restore_refusal(length, ceiling, room, known=True)
reader = await request.multipart()
field = await reader.next()
if not field or field.name != "database_file":
return web.json_response(
{
"success": False,
"error": (
"No database file uploaded. "
"Expected field name: database_file"
),
},
status=400,
)
fd, temp_path = tempfile.mkstemp(suffix=".db")
os.close(fd)
size = 0
with open(temp_path, "wb") as out:
while True:
chunk = await field.read_chunk()
if not chunk:
break
size += len(chunk)
if size > max_bytes:
return self._restore_refusal(size, ceiling, room, known=False)
out.write(chunk)
if size == 0:
return web.json_response(
{"success": False, "error": "Uploaded file is empty"}, status=400
)
model = self.db.model
ok, reason = await self._run_in_executor(
model.verify_database_file, temp_path
)
if ok:
reason = await self._run_in_executor(_inspect_restore_upload, temp_path)
ok = reason is None
if not ok:
return web.json_response(
{"success": False, "error": reason}, status=400
)
try:
backup_path = await self._run_in_executor(
model.restore_from_file, temp_path
)
except sqlite3.OperationalError as exc:
if (
getattr(exc, "_prompt_manager_restore_backup_created", False)
is True
):
try:
await self._run_in_executor(
_prune_safety_backups, model.db_path
)
except Exception:
self.logger.warning(
"Could not prune safety backups after failed restore"
)
raise
removed = await self._run_in_executor(_prune_safety_backups, model.db_path)
if removed:
self.logger.info(f"Removed {len(removed)} old safety backups")
previous = self.db
self.db = PromptDatabase(model.db_path)
self._database_replaced() # a health report described the old one
# Its connections would otherwise linger (a file lock on Windows)
previous.close_all()
prompt_count = self.db.model.get_database_info().get("total_prompts", 0)
return web.json_response(
{
"success": True,
"message": (
"Database restored successfully. "
f"Found {prompt_count} prompts."
),
"prompt_count": prompt_count,
"backup_created": (
self._public_path(backup_path) if backup_path else None
),
}
)
except Exception as e:
self.logger.error(f"Restore error: {e}", exc_info=True)
return web.json_response(
{
"success": False,
"error": f"Failed to restore database: {self._public_error(e)}",
},
status=500,
)
finally:
if temp_path:
for suffix in ("", "-wal", "-shm", "-journal"):
if os.path.exists(temp_path + suffix):
os.unlink(temp_path + suffix)
async def scan_images(self, request):
"""Scan ComfyUI output images for prompt metadata and add them to the database.