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.

py/api/__init__.py

@@ -13,6 +13,7 @@ Split into domain-specific mixins for maintainability:
 - ReviewRecordingMixin: Needs review recording for the scan and the monitor
 - ReviewEventsMixin: the Needs review change stream an open page re-reads on
 - SystemRoutesMixin: System health check, Overview and usage statistics
+- MaintenanceRoutesMixin: reviewed maintenance plans (preview, apply)
 """
 
 import asyncio
@@ -46,6 +47,8 @@ from .job_routes import JobRoutesMixin
 from .image_tag_jobs import ImageTagJobsMixin
 from .thumbnail_jobs import ThumbnailJobsMixin
 from .system import SystemRoutesMixin
+from .maintenance import MaintenanceRoutesMixin
+from .maintenance_plans import PlanStore
 from .jobs import JobRegistry
 from .logging_routes import LoggingRoutesMixin
 from .autotag_routes import AutotagRoutesMixin
@@ -285,6 +288,7 @@ class PromptManagerAPI(
     ImageTagJobsMixin,
     ThumbnailJobsMixin,
     SystemRoutesMixin,
+    MaintenanceRoutesMixin,
     LoggingRoutesMixin,
     AutotagRoutesMixin,
     LoraIntegrationMixin,
@@ -348,6 +352,9 @@ class PromptManagerAPI(
         # (py/api/system.py).
         self._health_report = None
         self._db_generation = 0
+        # Reviewed maintenance plans under single-use tokens; a restart
+        # forgets them (py/api/maintenance.py).
+        self._maintenance_plans = PlanStore()
 
         # Run cleanup on initialization to remove any existing duplicates
         try:
@@ -508,6 +515,7 @@ class PromptManagerAPI(
         self._register_settings_routes(routes)
         self._register_job_routes(routes)
         self._register_system_routes(routes)
+        self._register_maintenance_routes(routes)
         self._register_logging_routes(routes)
         self._register_autotag_routes(routes)
         self._register_lora_routes(routes)

py/api/admin.py

@@ -1112,8 +1112,10 @@ class AdminRoutesMixin:
                 db.cleanup_duplicates(), "duplicate prompts"
             ),
             "vacuum": vacuum,
+            # Only under sources that can be read now (never an unmounted drive).
             "cleanup_orphaned_images": lambda: count_result(
-                db.cleanup_missing_images(), "orphaned image records"
+                db.cleanup_missing_images(self._health_roots()),
+                "orphaned image records",
             ),
             "check_hash_duplicates": lambda: self._hash_duplicates_result(
                 db.check_hash_duplicates()

py/api/maintenance.py

@@ -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"},
+        )

py/api/maintenance_plans.py

@@ -0,0 +1,138 @@
+"""The reviewed-plan store behind maintenance previews (#249 System S6).
+
+A preview issues a plan: its operation, the fingerprint of exactly what was
+reviewed, the payload an apply needs (target ids, the sources it judged) and
+the identity of the database it describes. Everything is held here, in
+server memory, under a single-use token (``secrets.token_urlsafe(32)``); the
+client only ever sees the token and the public plan. Plans expire after
+``ttl`` seconds and are gone after a restart.
+
+The store keeps at most ``max_plans`` plans and ``max_bytes`` of payload
+(measured as compact JSON). A plan larger than ``max_bytes`` is refused with
+``ScopeTooLarge``: it is never cut down to fit, since an apply must do
+exactly what was reviewed. A new plan that fits makes room by dropping the
+oldest ones, which then read as expired.
+
+A consumed token is remembered (the last ``MAX_USED``) with the job it
+started, so a second apply of it is told which job ran it.
+"""
+
+import json
+import secrets
+import time
+from collections import OrderedDict
+from dataclasses import dataclass, field
+
+
+class PlanExpired(Exception):
+    """No live plan has the token: unknown, expired, dropped or another operation's."""
+
+
+class PlanUsed(Exception):
+    """The token was already applied; ``job_id`` is the job that applied it."""
+
+    def __init__(self, job_id):
+        super().__init__("This plan was already applied")
+        self.job_id = job_id
+
+
+class ScopeTooLarge(Exception):
+    """The plan's payload exceeds the store's byte budget."""
+
+
+@dataclass
+class StoredPlan:
+    """One reviewed plan, as only the server sees it."""
+
+    operation: str
+    fingerprint: str
+    payload: dict
+    db_identity: tuple
+    expires_at: float  # wall-clock seconds since the epoch, for the response
+    deadline: float = field(repr=False)  # on the store's monotonic clock
+    size: int = field(repr=False)
+
+
+def _payload_size(payload):
+    return len(json.dumps(payload, separators=(",", ":"), default=str))
+
+
+class PlanStore:
+    """Reviewed maintenance plans under single-use tokens."""
+
+    MAX_USED = 64  # consumed tokens remembered for plan-used answers
+
+    def __init__(
+        self,
+        ttl=900,
+        max_plans=8,
+        max_bytes=16 * 2**20,
+        *,
+        clock=time.monotonic,
+        wall_clock=time.time,
+    ):
+        self.ttl = ttl
+        self.max_plans = max_plans
+        self.max_bytes = max_bytes
+        self._clock = clock
+        self._wall_clock = wall_clock
+        self._plans = OrderedDict()  # token -> StoredPlan, oldest first
+        self._used = OrderedDict()  # token -> job id, oldest first
+
+    def issue(self, operation, fingerprint, payload, db_identity) -> str:
+        """Hold a plan and return its token; ScopeTooLarge when it cannot fit."""
+        size = _payload_size(payload)
+        if size > self.max_bytes:
+            raise ScopeTooLarge(f"The plan needs {size} bytes")
+        self._drop_expired()
+        while self._plans and (
+            len(self._plans) >= self.max_plans
+            or self._held_bytes() + size > self.max_bytes
+        ):
+            self._plans.popitem(last=False)
+        token = secrets.token_urlsafe(32)
+        self._plans[token] = StoredPlan(
+            operation=operation,
+            fingerprint=fingerprint,
+            payload=payload,
+            db_identity=tuple(db_identity),
+            expires_at=self._wall_clock() + self.ttl,
+            deadline=self._clock() + self.ttl,
+            size=size,
+        )
+        return token
+
+    def peek(self, token, operation=None) -> StoredPlan:
+        """The live plan of ``token``, left in place; raises PlanUsed or PlanExpired."""
+        if not isinstance(token, str):
+            raise PlanExpired("No such plan")
+        if token in self._used:
+            raise PlanUsed(self._used[token])
+        plan = self._plans.get(token)
+        if plan is None or (operation is not None and plan.operation != operation):
+            raise PlanExpired("No such plan")
+        if self._clock() > plan.deadline:
+            del self._plans[token]
+            raise PlanExpired("The plan expired")
+        return plan
+
+    def consume(self, token, operation=None, *, job_id=None) -> StoredPlan:
+        """Take the plan of ``token`` once; later calls raise PlanUsed(job_id)."""
+        plan = self.peek(token, operation)
+        del self._plans[token]
+        self._used[token] = job_id
+        while len(self._used) > self.MAX_USED:
+            self._used.popitem(last=False)
+        return plan
+
+    def discard(self, token):
+        """Forget a plan that can no longer apply (its database was replaced)."""
+        self._plans.pop(token, None)
+
+    def _held_bytes(self):
+        return sum(plan.size for plan in self._plans.values())
+
+    def _drop_expired(self):
+        now = self._clock()
+        for token in [t for t, plan in self._plans.items() if now > plan.deadline]:
+            del self._plans[token]