feat(maintenance): reviewed, read-only maintenance plans

POST /prompt_manager/maintenance/preview reviews duplicate_prompts,
optimize, unused_components or missing_links on its own mode=ro snapshot
and answers a Plan (scope, protected reasons, backup policy, media, at most
50 detail rows). The fingerprint, targets and judged sources stay in a
server-side PlanStore under a single-use token (15 min, 8 plans, 16 MiB,
never truncated; a restart forgets them), bound to the database it read.

The previews reuse the legacy queries: duplicate groups and the merge are
shared with cleanup_duplicates, ORPHANED_PROMPTS_SQL is built from the
#239 protection predicates the plan reports, and missing links are judged
by the health check's link_states. Legacy /maintenance keeps its shape;
vacuum now reports success:false when VACUUM fails, and
cleanup_orphaned_images skips links under unavailable sources.
This commit is contained in:
Vito Sansevero
2026-10-23 17:16:00 -07:00
parent 6505d339aa
commit f09d2250df
12 changed files with 1684 additions and 113 deletions
+152
View File
@@ -0,0 +1,152 @@
"""Maintenance routes: reviewed, read-only plans (#249 System S6).
``POST /prompt_manager/maintenance/preview {operation, options:{}}`` reviews
one operation (``duplicate_prompts``, ``optimize``, ``unused_components`` or
``missing_links``; ``database/maintenance.py``) off the event loop and
answers a ``Plan``: ``{success, token, operation, expires_at, scope:{count,
label}, protected:{count, reasons}, backup:{policy, destination_label},
media:{deletes_files, label}, details:[≤50 {label, detail}]}``. The preview
writes nothing. The plan's fingerprint, its targets and the sources it judged
stay in the server's ``PlanStore`` under the token, bound to the database the
preview read (a restore that replaces it invalidates the plan).
The operation enum is strict, ``options`` must be an empty object and the
body is capped at ``PREVIEW_BODY_MAX`` bytes. Errors are ``{success:false,
code, error}`` with ``invalid-request`` (400), ``too-large`` (413: the body,
or a plan over the store's budget), ``storage-changed`` (409: the database
was replaced while the preview read it) or a null code (500); none carries a
server path or exception text.
"""
import datetime
import os
from aiohttp import web
from .maintenance_plans import ScopeTooLarge
try:
from ...database.maintenance import MAINTENANCE_OPERATIONS
except ImportError:
from database.maintenance import MAINTENANCE_OPERATIONS
PREVIEW_BODY_MAX = 4096
# The concept's Maintenance row titles, which name each operation's job.
MAINTENANCE_TITLES = {
"duplicate_prompts": "Duplicate prompt text",
"optimize": "Optimize database",
"unused_components": "Unused prompt components",
"missing_links": "Missing-file links",
}
_OPERATION_ERROR = "operation must be one of: " + ", ".join(MAINTENANCE_OPERATIONS)
def _failure(message, status, code=None, **extra):
return web.json_response(
{"success": False, "code": code, "error": message, **extra}, status=status
)
def _invalid(message):
return _failure(message, 400, "invalid-request")
def _iso(timestamp):
return datetime.datetime.fromtimestamp(timestamp, datetime.timezone.utc).isoformat()
class MaintenanceRoutesMixin:
"""Mixin providing the /prompt_manager/maintenance plan endpoints."""
def _register_maintenance_routes(self, routes):
@routes.post("/prompt_manager/maintenance/preview")
async def maintenance_preview_route(request):
return await self.preview_maintenance(request)
def _database_identity(self, db):
"""What binds a plan to one database: the swap generation and its file."""
path = os.path.normcase(os.path.realpath(db.model.db_path))
return (self._db_generation, path)
@staticmethod
def _safety_backup_policy():
"""``on`` or ``off``: whether an apply takes a safety backup first."""
return "on"
async def _read_maintenance_body(self, request, allowed):
"""``(data, None)`` for a capped JSON object with only ``allowed`` keys."""
data, error = await self._read_json_body(request, max_bytes=PREVIEW_BODY_MAX)
if error is not None:
if error.status == 413:
return None, _failure("Request body too large", 413, "too-large")
return None, _invalid("Request body must be a JSON object")
unknown = sorted(set(data) - set(allowed))
if unknown:
return None, _invalid("Unknown field: " + ", ".join(unknown)[:200])
return data, None
async def preview_maintenance(self, request):
data, error = await self._read_maintenance_body(
request, ("operation", "options")
)
if error is not None:
return error
operation = data.get("operation")
options = data.get("options", {})
if not isinstance(operation, str) or operation not in MAINTENANCE_OPERATIONS:
return _invalid(_OPERATION_ERROR)
if not isinstance(options, dict) or options:
return _invalid(f"{operation} takes no options")
db = self.db
identity = self._database_identity(db)
try:
roots = (
await self._run_in_executor(self._health_roots)
if operation == "missing_links"
else []
)
draft = await self._run_in_executor(
db.preview_maintenance, operation, roots
)
except Exception:
self.logger.exception(f"Maintenance preview of {operation} failed")
return _failure("Failed to review maintenance", 500)
if identity != self._database_identity(self.db):
return _failure(
"The database was replaced while it was reviewed. Review again.",
409,
"storage-changed",
)
policy = self._safety_backup_policy()
store = self._maintenance_plans
try:
token = store.issue(
operation,
draft.fingerprint,
{
"targets": draft.targets,
"roots": roots,
"protected": draft.protected["count"],
"backup": policy,
},
identity,
)
except ScopeTooLarge:
return _failure(
"This plan is too large to review at once.", 413, "too-large"
)
plan = store.peek(token, operation)
name = os.path.basename(db.model.db_path)
return web.json_response(
{
"success": True,
"token": token,
"expires_at": _iso(plan.expires_at),
**draft.public(),
"backup": {
"policy": policy,
"destination_label": f"{name}.backup_<date and time>",
},
},
headers={"Cache-Control": "no-store"},
)