Files
FabledCurator/backend/app/api/system_backup.py
T
bvandeusenandClaude Opus 5.5 772482d794
CI and images / lint (push) Successful in 2s
CI and images / extension-version (push) Successful in 1s
CI and images / extension-test (push) Successful in 20s
CI and images / frontend-build (push) Successful in 23s
CI and images / backend-lint-and-test (push) Successful in 41s
CI and images / integration (push) Successful in 2m25s
CI and images / sign-extension (push) Successful in 2s
CI and images / build-agent (push) Successful in 5s
CI and images / build-web (push) Successful in 1m50s
CI and images / smoke-web (push) Successful in 49s
CI and images / promote (push) Successful in 2s
CI and images / refresh-dev (push) Skipped
CI and images / unattended-failure (push) Skipped
feat: with an off-site destination set up, database backups stream to it
The nightly database backup (and "Run DB backup now") now sends pg_dump's
output straight to the off-site bucket as a multipart upload, with no copy
staged on this server. The object is named database/fabledcurator-<UTC
time>.dump and appears only once pg_dump has exited cleanly and every part
has landed; a failed dump aborts the upload and records pg_dump's last line.
Without a destination, dumps are written to /images/_backups as before.

- backup_s3: Upload (start / add part / complete / abort), with a busy or
  silent bucket rested and asked again (15 s, 60 s, Retry-After obeyed), and
  a Pacer that holds uploads to the new bandwidth limit.
- Settings: "Upload limit (Mbit/s)" on the destination card, 200 by default,
  0 for none (migration 0120).
- pg_dump runs under nice (and ionice where installed), locally too.
- Backups card says where dumps go; the runs table gains "Saved to" and
  shows a failed run's error. Off-site rows have no restore/tag/delete here:
  restoring from the bucket is a later step (#6880).

Task #6878, milestone 586.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 21:11:12 -05:00

377 lines
14 KiB
Python

"""FC-3h: /api/system/backup — create/list/restore/delete/tag for
DB + image backups.
Read endpoints are public on FC (operator-facing internal API; same
posture as /api/system/activity). Write endpoints take a typed
`confirm` body field that must match a server-generated token for
that backup row, to prevent click-to-destroy by stale browser tabs
or accidental cURL.
"""
from __future__ import annotations
from quart import Blueprint, jsonify, request
from sqlalchemy import desc, select
from ..extensions import get_session
from ..models import BackupRun, ImportSettings
from ._responses import error_response as _bad
system_backup_bp = Blueprint(
"system_backup", __name__, url_prefix="/api/system/backup",
)
_KINDS = frozenset({"db", "images"})
_TAG_MAX_LEN = 64
_BACKUP_SETTINGS_FIELDS = (
"backup_db_nightly_enabled",
"backup_db_nightly_hour_utc",
"backup_db_keep_last_n",
"backup_images_keep_last_n",
)
def _row_to_dict(r: BackupRun) -> dict:
return {
"id": r.id,
"kind": r.kind,
"status": r.status,
"tag": r.tag,
"triggered_by": r.triggered_by,
"started_at": r.started_at.isoformat() if r.started_at else None,
"finished_at": r.finished_at.isoformat() if r.finished_at else None,
"duration_seconds": (
int((r.finished_at - r.started_at).total_seconds())
if r.finished_at and r.started_at else None
),
"sql_path": r.sql_path,
"tar_path": r.tar_path,
"size_bytes": r.size_bytes,
"error": r.error,
"restored_from_id": r.restored_from_id,
"manifest": r.manifest or {},
# Where an off-site dump went ({endpoint, bucket, key}); None for a
# backup kept on this server.
"offsite": (r.manifest or {}).get("offsite"),
}
def _validate_tag(tag):
if tag is None:
return None
if not isinstance(tag, str):
return _bad("invalid_tag", detail="tag must be string or null")
tag = tag.strip()
if not tag:
return None
if len(tag) > _TAG_MAX_LEN:
return _bad("invalid_tag", detail=f"tag too long (max {_TAG_MAX_LEN})")
return tag
def _validate_backup_settings_patch(body: dict):
if "backup_db_nightly_enabled" in body and not isinstance(
body["backup_db_nightly_enabled"], bool,
):
return _bad("invalid_value", detail="backup_db_nightly_enabled must be bool")
if "backup_db_nightly_hour_utc" in body:
v = body["backup_db_nightly_hour_utc"]
if not isinstance(v, int) or isinstance(v, bool) or not (0 <= v <= 23):
return _bad("invalid_value", detail="backup_db_nightly_hour_utc must be 0..23")
if "backup_db_keep_last_n" in body:
v = body["backup_db_keep_last_n"]
if not isinstance(v, int) or isinstance(v, bool) or not (1 <= v <= 365):
return _bad("invalid_value", detail="backup_db_keep_last_n must be 1..365")
if "backup_images_keep_last_n" in body:
v = body["backup_images_keep_last_n"]
if not isinstance(v, int) or isinstance(v, bool) or not (1 <= v <= 100):
return _bad("invalid_value", detail="backup_images_keep_last_n must be 1..100")
return None
@system_backup_bp.route("/db", methods=["POST"])
async def trigger_db_backup():
body = await request.get_json(silent=True) or {}
tag = _validate_tag(body.get("tag"))
if isinstance(tag, tuple):
return tag
from ..tasks.backup import backup_db_task
backup_db_task.delay(tag=tag, triggered_by="manual")
return jsonify({"status": "dispatched"}), 202
@system_backup_bp.route("/images", methods=["POST"])
async def trigger_images_backup():
body = await request.get_json(silent=True) or {}
tag = _validate_tag(body.get("tag"))
if isinstance(tag, tuple):
return tag
from ..tasks.backup import backup_images_task
backup_images_task.delay(tag=tag, triggered_by="manual")
return jsonify({"status": "dispatched"}), 202
@system_backup_bp.route("/runs", methods=["GET"])
async def list_runs():
try:
limit = min(int(request.args.get("limit", "50")), 200)
except ValueError:
return _bad("invalid_limit")
if limit < 1:
return _bad("invalid_limit")
kind = request.args.get("kind")
if kind is not None and kind not in _KINDS:
return _bad("invalid_kind", detail=f"kind must be one of {sorted(_KINDS)}")
before_id_raw = request.args.get("before_id")
before_id = int(before_id_raw) if before_id_raw else None
async with get_session() as session:
stmt = select(BackupRun).order_by(desc(BackupRun.id))
if kind:
stmt = stmt.where(BackupRun.kind == kind)
if before_id is not None:
stmt = stmt.where(BackupRun.id < before_id)
stmt = stmt.limit(limit + 1)
rows = (await session.execute(stmt)).scalars().all()
has_more = len(rows) > limit
rows = rows[:limit]
return jsonify({
"runs": [_row_to_dict(r) for r in rows],
"next_cursor": rows[-1].id if has_more and rows else None,
})
@system_backup_bp.route("/runs/<int:run_id>", methods=["GET"])
async def get_run(run_id: int):
async with get_session() as session:
row = await session.get(BackupRun, run_id)
if row is None:
return _bad("not_found", status=404)
return jsonify(_row_to_dict(row))
@system_backup_bp.route("/runs/<int:run_id>", methods=["PATCH"])
async def patch_run(run_id: int):
body = await request.get_json(silent=True) or {}
if "tag" not in body:
return _bad("invalid_body", detail="tag required")
tag = _validate_tag(body["tag"])
if isinstance(tag, tuple):
return tag
async with get_session() as session:
row = await session.get(BackupRun, run_id)
if row is None:
return _bad("not_found", status=404)
row.tag = tag
await session.commit()
await session.refresh(row)
return jsonify(_row_to_dict(row))
@system_backup_bp.route("/runs/<int:run_id>/restore", methods=["POST"])
async def trigger_restore(run_id: int):
body = await request.get_json(silent=True) or {}
supplied = body.get("confirm", "")
async with get_session() as session:
row = await session.get(BackupRun, run_id)
if row is None:
return _bad("not_found", status=404)
if row.status != "ok":
return _bad(
"not_restorable",
detail=f"source backup status={row.status!r}; only 'ok' rows are restorable",
)
if (row.manifest or {}).get("offsite"):
return _bad(
"not_restorable",
detail=("this dump is kept in the off-site bucket, not on this server, "
"so it can't be restored from here"),
)
expected = f"restore-{row.kind}-{row.id}"
if supplied != expected:
return _bad(
"confirm_mismatch",
detail=f"confirm must equal {expected!r}",
expected=expected,
)
kind = row.kind
if kind == "db":
from ..tasks.backup import restore_db_task
restore_db_task.delay(source_backup_run_id=run_id)
else: # 'images' (the only other value _KINDS allows via the trigger path)
from ..tasks.backup import restore_images_task
restore_images_task.delay(source_backup_run_id=run_id)
return jsonify({"status": "dispatched", "kind": kind}), 202
@system_backup_bp.route("/runs/<int:run_id>", methods=["DELETE"])
async def delete_run(run_id: int):
body = await request.get_json(silent=True) or {}
supplied = body.get("confirm", "")
async with get_session() as session:
row = await session.get(BackupRun, run_id)
if row is None:
return _bad("not_found", status=404)
expected = f"delete-{row.kind}-{row.id}"
if supplied != expected:
return _bad(
"confirm_mismatch",
detail=f"confirm must equal {expected!r}",
expected=expected,
)
from ..services import backup_service
backup_service.unlink_artifact_files(
sql_path=row.sql_path, tar_path=row.tar_path,
manifest_path=(row.manifest or {}).get("manifest_path"),
)
await session.delete(row)
await session.commit()
return "", 204
@system_backup_bp.route("/settings", methods=["GET"])
async def get_settings():
async with get_session() as session:
row = await ImportSettings.load(session)
return jsonify({
"backup_db_nightly_enabled": row.backup_db_nightly_enabled,
"backup_db_nightly_hour_utc": row.backup_db_nightly_hour_utc,
"backup_db_keep_last_n": row.backup_db_keep_last_n,
"backup_images_keep_last_n": row.backup_images_keep_last_n,
})
@system_backup_bp.route("/destination", methods=["GET"])
async def get_destination():
"""The off-site destination as the settings screen shows it. The secret
key is never returned, only whether one is saved."""
from ..services import backup_destination as dest
async with get_session() as session:
row = await ImportSettings.load(session)
return jsonify(dest.describe(row))
@system_backup_bp.route("/destination", methods=["PATCH"])
async def patch_destination():
"""Save the destination. Body {endpoint, bucket, access_key, region,
secret_key, upload_limit_mbps}; an empty field clears it, and a missing
upload_limit_mbps keeps the saved limit. A missing or empty secret_key
keeps the saved one, so the screen can save the other fields without the
secret being typed again."""
from ..services import backup_destination as dest
body = await request.get_json(silent=True)
if not isinstance(body, dict):
return _bad("invalid_body", detail="body must be a JSON object")
fields, why = dest.clean_fields(body)
if fields is None:
return _bad("invalid_destination", detail=why)
secret = body.get("secret_key")
if secret is not None and not isinstance(secret, str):
return _bad("invalid_destination", detail="secret_key must be text")
limit = body.get("upload_limit_mbps")
if limit is not None and (
not isinstance(limit, int) or isinstance(limit, bool) or not 0 <= limit <= 100_000
):
return _bad("invalid_destination",
detail="upload_limit_mbps must be a whole number from 0 (no limit) up")
async with get_session() as session:
row = await ImportSettings.load(session)
if limit is not None:
row.backup_upload_limit_mbps = limit
row.backup_s3_endpoint = fields.endpoint
row.backup_s3_bucket = fields.bucket
row.backup_s3_access_key = fields.access_key
row.backup_s3_region = fields.region
if secret and secret.strip():
row.backup_s3_secret_sealed = dest.seal(secret.strip())
await session.commit()
return jsonify(dest.describe(row))
@system_backup_bp.route("/destination", methods=["DELETE"])
async def delete_destination():
"""Forget the destination, secret included. What was already sent stays in
the bucket: FabledCurator never deletes there."""
from ..services import backup_destination as dest
async with get_session() as session:
row = await ImportSettings.load(session)
row.backup_s3_endpoint = None
row.backup_s3_bucket = None
row.backup_s3_access_key = None
row.backup_s3_secret_sealed = None
row.backup_s3_region = dest.DEFAULT_REGION
await session.commit()
return jsonify(dest.describe(row))
@system_backup_bp.route("/destination/test", methods=["POST"])
async def try_destination():
"""Reach the bucket with the fields in the body (the form as typed, saved
or not); a missing secret_key uses the saved one. Lists the bucket and
writes nothing. Answers {ok, message} either way: a destination that
can't be reached is a result to show, not an API error."""
import asyncio
from ..services import backup_destination as dest
from ..services.backup_s3 import S3Error
from ..services.credential_crypto import InvalidCredentialBlob
body = await request.get_json(silent=True) or {}
if not isinstance(body, dict):
return _bad("invalid_body", detail="body must be a JSON object")
fields, why = dest.clean_fields(body)
if fields is None:
return jsonify({"ok": False, "message": f"Not tested: {why}."})
secret = body.get("secret_key")
secret = secret.strip() if isinstance(secret, str) else ""
if not secret:
async with get_session() as session:
row = await ImportSettings.load(session)
sealed = row.backup_s3_secret_sealed
if sealed:
try:
secret = dest.unseal(sealed)
except InvalidCredentialBlob:
return jsonify({"ok": False, "message": (
"Not tested: the saved secret key can't be opened on this server. "
"Enter the secret key again."
)})
target = dest.target_for(fields, secret or None)
if target is None:
missing = [name for name, v in (
("address", fields.endpoint), ("bucket", fields.bucket),
("access key", fields.access_key), ("secret key", secret),
) if not v]
return jsonify({"ok": False, "message": f"Not tested: fill in the {', '.join(missing)}."})
try:
return jsonify(await asyncio.to_thread(dest.check_target, target))
except S3Error as exc:
return jsonify({"ok": False, "message": str(exc)})
@system_backup_bp.route("/settings", methods=["PATCH"])
async def patch_settings():
body = await request.get_json(silent=True)
if not isinstance(body, dict):
return _bad("invalid_body", detail="body must be a JSON object")
err = _validate_backup_settings_patch(body)
if err is not None:
return err
async with get_session() as session:
row = await ImportSettings.load(session)
for field in _BACKUP_SETTINGS_FIELDS:
if field in body:
setattr(row, field, body[field])
await session.commit()
return await get_settings()