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.

database/health.py

@@ -189,6 +189,33 @@ def _image_owner(image_path, file_path, prefixes):
     return owner
 
 
+def readable_roots(roots):
+    """Whether each source can be read now (an unmounted drive cannot)."""
+    return [_readable(root) for root in roots]
+
+
+def link_states(rows, roots, readable):
+    """``(row, owner, state)`` for each image row ``(id, image_path, filename,
+    file_path)``: ``owner`` is the index of the source it lies under (None
+    outside every source) and ``state`` is ``missing``, ``present``,
+    ``unavailable`` (its source cannot be read, so the file is not looked at)
+    or ``outside``. ``readable`` is ``readable_roots(roots)``. The health
+    check's ``missing_files`` and the maintenance missing-link plan both
+    judge links this way, so their counts agree.
+    """
+    prefixes = [_root_prefix(root) for root in roots]
+    for row in rows:
+        owner = _image_owner(row[1], row[3], prefixes)
+        if owner is None:
+            yield row, None, "outside"
+        elif not readable[owner]:
+            yield row, owner, "unavailable"
+        elif os.path.exists(row[1]):
+            yield row, owner, "present"
+        else:
+            yield row, owner, "missing"
+
+
 def _unavailable_line(unavailable, *, partial):
     noun = "source is" if unavailable == 1 else "sources are"
     effect = "its files were" if unavailable == 1 else "their files were"
@@ -224,7 +251,7 @@ def _missing_files(conn, roots):
 
 def _check_files(rows, roots):
     """The ``missing_files`` result of the image *rows*, from the file system."""
-    readable = [_readable(root) for root in roots]
+    readable = readable_roots(roots)
     sources = [
         {
             "name": _source_name(root, index),
@@ -239,13 +266,12 @@ def _check_files(rows, roots):
             None, [_unavailable_line(unavailable, partial=False)], status="unavailable"
         )
         return {**result, "partial": False, "sources": sources}
-    prefixes = [_root_prefix(root) for root in roots]
     outside, missing = 0, []
-    for image_id, image_path, filename, file_path in rows:
-        owner = _image_owner(image_path, file_path, prefixes)
-        if owner is None:
+    for row, owner, state in link_states(rows, roots, readable):
+        if state == "outside":
             outside += 1
-        elif readable[owner] and not os.path.exists(image_path):
+        elif state == "missing":
+            image_id, image_path, filename, _file_path = row
             sources[owner]["count"] += 1
             if len(missing) < MAX_DETAIL:
                 name = filename or os.path.basename(image_path)

database/maintenance.py

@@ -0,0 +1,550 @@
+"""Reviewed maintenance plans: read-only previews and their exact apply (#249 S6).
+
+Four operations, each the native owner of a legacy ``/maintenance`` one and
+built on the same queries, so a preview counts what the legacy cleanup would
+change:
+
+- ``duplicate_prompts``: prompts whose text is equal ignoring case and outer
+  spaces (``DUPLICATE_PROMPTS_SQL``, legacy ``cleanup_duplicates``); each
+  group keeps its oldest prompt, which takes over the others' images and
+  metadata. A group with a member in a saved pair is kept whole.
+- ``optimize``: VACUUM (legacy ``vacuum``).
+- ``unused_components``: prompts nothing references (``ORPHANED_PROMPTS_SQL``,
+  legacy ``prune_orphaned_prompts``, with the #239 protections).
+- ``missing_links``: image rows whose file is gone (legacy
+  ``cleanup_orphaned_images``), counted only under a source that can be read
+  now, as the health check's ``missing_files`` judges them
+  (``health.link_states``). It deletes database rows only, never a file.
+
+``preview_maintenance`` reads one snapshot on its own ``mode=ro`` connection
+(``health.readonly_uri``) and closes it in ``finally``; files are looked at
+after the snapshot ended. It returns a ``MaintenanceDraft``: the public plan
+fields, the targets an apply needs and the fingerprint of exactly what was
+reviewed (ids, text hashes, metadata, tags, Library state and pair refs of
+every prompt involved, or each link's row and source). The fingerprint never
+leaves the server.
+
+``apply_maintenance`` recomputes that fingerprint on the write connection
+inside ``BEGIN IMMEDIATE`` and raises ``PlanChanged`` before writing anything
+when it differs; otherwise it applies the reviewed targets in batches of
+``ID_BATCH`` in that one transaction. VACUUM cannot run in a transaction, so
+``optimize`` binds to its database only (the caller checks that).
+"""
+
+import hashlib
+import json
+import os
+import shutil
+import sqlite3
+from dataclasses import dataclass, field
+from pathlib import Path
+
+from .execution_contexts import LIVE_HINT_CTES
+from .health import BATCH_ROWS, link_states, readable_roots, readonly_uri
+from .pairs import PairDependencyError
+
+MAINTENANCE_OPERATIONS = (
+    "duplicate_prompts",
+    "optimize",
+    "unused_components",
+    "missing_links",
+)
+MAX_DETAILS = 50  # detail rows a plan lists
+EXCERPT_CHARS = 80
+# Ids bound per statement: the pair-reference read binds each id twice, which
+# stays under SQLite's historical 999-variable limit.
+ID_BATCH = 400
+
+# Why a prompt no image links to is kept (#239): predicates on ``p``, in the
+# order the plan names them. ORPHANED_PROMPTS_SQL is built from them, so the
+# reasons a plan lists are exactly the rules the prune applies.
+PROTECTIONS = (
+    (
+        "EXISTS (SELECT 1 FROM prompt_pairs pp "
+        "WHERE pp.positive_prompt_id = p.id OR pp.negative_prompt_id = p.id)",
+        "in saved pairs",
+        "in a saved pair",
+    ),
+    (
+        "EXISTS (SELECT 1 FROM prompt_tags pt JOIN tags t ON pt.tag_id = t.id "
+        "WHERE pt.prompt_id = p.id AND t.name = '__protected__')",
+        "tagged __protected__",
+        "tagged __protected__",
+    ),
+    (
+        "EXISTS (SELECT 1 FROM prompt_library_state ls WHERE ls.prompt_id = p.id)",
+        "with Library state (a title or an explicit parent)",
+        "with Library state (a title or an explicit parent)",
+    ),
+    (
+        "p.id IN (SELECT prompt_id FROM live_hint_prompts)",
+        "used by recorded runs",
+        "used by a recorded run",
+    ),
+)
+
+# Exempt references: images, pairs, the __protected__ tag, Library parent
+# state, and live recorded-run hints (computed once, see LIVE_HINT_CTES).
+ORPHANED_PROMPTS_SQL = (
+    "WITH "
+    + LIVE_HINT_CTES
+    + " SELECT p.id FROM prompts p"
+    + " LEFT JOIN generated_images gi ON p.id = gi.prompt_id"
+    + " WHERE gi.prompt_id IS NULL"
+    + "".join(f" AND NOT ({predicate})" for predicate, _many, _one in PROTECTIONS)
+)
+# The prompts no image links to, with which protections keep each one.
+_UNLINKED_PROTECTIONS_SQL = (
+    "WITH "
+    + LIVE_HINT_CTES
+    + " SELECT "
+    + ", ".join(
+        f"COALESCE(SUM({predicate}), 0)" for predicate, _many, _one in PROTECTIONS
+    )
+    + ", COALESCE(SUM("
+    + " OR ".join(f"({predicate})" for predicate, _many, _one in PROTECTIONS)
+    + "), 0) FROM prompts p WHERE NOT EXISTS "
+    "(SELECT 1 FROM generated_images gi WHERE gi.prompt_id = p.id)"
+)
+
+# Duplicate prompt groups, as the legacy cleanup finds them (case-insensitive
+# text; GROUP_CONCAT order is sorted by created_at afterwards).
+DUPLICATE_PROMPTS_SQL = """
+    SELECT LOWER(TRIM(text)) as normalized_text, COUNT(*) as count,
+           GROUP_CONCAT(id) as ids,
+           GROUP_CONCAT(created_at) as created_dates
+    FROM prompts
+    GROUP BY LOWER(TRIM(text))
+    HAVING COUNT(*) > 1
+"""
+
+_LINK_ROWS_SQL = (
+    "SELECT id, image_path, filename, file_path FROM generated_images ORDER BY id"
+)
+
+# What a prompt's fingerprint covers, per batch of ids.
+_PROMPT_STATE_SQL = (
+    "SELECT id, hash, text, category, rating, notes, created_at, updated_at "
+    "FROM prompts WHERE id IN ({marks}) ORDER BY id",
+    "SELECT prompt_id, tag_id FROM prompt_tags WHERE prompt_id IN ({marks}) "
+    "ORDER BY prompt_id, tag_id",
+    "SELECT * FROM prompt_library_state WHERE prompt_id IN ({marks}) "
+    "ORDER BY prompt_id",
+    "SELECT id, positive_prompt_id, negative_prompt_id FROM prompt_pairs "
+    "WHERE positive_prompt_id IN ({marks}) OR negative_prompt_id IN ({marks}) "
+    "ORDER BY id",
+)
+
+NO_FILES_DELETED = "No image file is deleted."
+LINKS_ONLY = "Database links only; no image file is deleted."
+UNUSED_DETAIL = "No image, saved pair, Library state or recorded run uses it"
+
+
+class PlanChanged(Exception):
+    """What a plan was reviewed on changed before it was applied."""
+
+
+@dataclass
+class MaintenanceDraft:
+    """A preview: the public plan fields plus what only the server keeps."""
+
+    operation: str
+    fingerprint: str
+    targets: list
+    scope: dict
+    protected: dict
+    media: dict
+    details: list = field(default_factory=list)
+
+    def public(self):
+        """The plan fields a response may carry (no fingerprint, no targets)."""
+        return {
+            "operation": self.operation,
+            "scope": dict(self.scope),
+            "protected": {
+                "count": self.protected["count"],
+                "reasons": list(self.protected["reasons"]),
+            },
+            "media": dict(self.media),
+            "details": [dict(row) for row in self.details],
+        }
+
+
+def _plural(count, one, many=None):
+    return f"{count:,} {one if count == 1 else (many or one + 's')}"
+
+
+def _excerpt(text):
+    text = " ".join(str(text or "").split())
+    if len(text) <= EXCERPT_CHARS:
+        return text
+    return text[: EXCERPT_CHARS - 1].rstrip() + "…"
+
+
+def _megabytes(size):
+    return f"{size / 2**20:,.1f} MB"
+
+
+class _Fingerprint:
+    """A streaming sha256 over JSON-encoded parts."""
+
+    def __init__(self, operation):
+        self._hash = hashlib.sha256()
+        self.add(operation)
+
+    def add(self, part):
+        encoded = json.dumps(part, separators=(",", ":"), default=str)
+        self._hash.update(encoded.encode("utf-8") + b"\n")
+
+    def hexdigest(self):
+        return "sha256:" + self._hash.hexdigest()
+
+
+def _batches(ids):
+    ids = list(ids)
+    for start in range(0, len(ids), ID_BATCH):
+        yield ids[start : start + ID_BATCH]
+
+
+def _marks(batch):
+    return ",".join("?" for _ in batch)
+
+
+def _add_prompt_state(fingerprint, conn, ids):
+    """Fold every reviewed fact about the prompts ``ids`` into ``fingerprint``."""
+    for batch in _batches(sorted(ids)):
+        marks = _marks(batch)
+        for sql in _PROMPT_STATE_SQL:
+            params = batch * sql.count("{marks}")
+            for row in conn.execute(sql.format(marks=marks), params):
+                fingerprint.add(list(row))
+
+
+def _texts(conn, ids):
+    """``{id: text}`` of at most MAX_DETAILS prompts, for detail rows."""
+    ids = list(ids)[:MAX_DETAILS]
+    if not ids:
+        return {}
+    rows = conn.execute(
+        f"SELECT id, text FROM prompts WHERE id IN ({_marks(ids)})", ids
+    )
+    return {row[0]: row[1] for row in rows}
+
+
+def _orphaned_ids(conn):
+    return sorted(row[0] for row in conn.execute(ORPHANED_PROMPTS_SQL))
+
+
+def _delete_ids(conn, table, ids):
+    """Delete ``table`` rows by id in batches; returns the rows removed."""
+    if table not in ("prompts", "generated_images"):
+        raise ValueError(f"Unsupported table {table!r}")
+    removed = 0
+    for batch in _batches(ids):
+        cursor = conn.execute(
+            f"DELETE FROM {table} WHERE id IN ({_marks(batch)})",  # nosec B608
+            batch,
+        )
+        removed += cursor.rowcount
+    return removed
+
+
+def _read_snapshot(db_path, read):
+    """``read(conn)`` on one ``mode=ro`` snapshot; the connection always closes."""
+    conn = sqlite3.connect(readonly_uri(db_path), uri=True)
+    try:
+        conn.row_factory = sqlite3.Row
+        conn.execute("BEGIN")  # one read snapshot for the whole plan
+        return read(conn)
+    finally:
+        conn.close()
+
+
+def _relative(image_path, root):
+    try:
+        return Path(os.path.relpath(image_path, root)).as_posix()
+    except ValueError:  # another drive (Windows)
+        return os.path.basename(image_path)
+
+
+def _source_name(root, index):
+    return os.path.basename(str(root).rstrip("\\/")) or f"Source {index + 1}"
+
+
+class MaintenanceOperations:
+    """Mixin for PromptDatabase: maintenance previews and their apply."""
+
+    # ── shared with the legacy cleanup ───────────────────────────────
+
+    def _duplicate_groups(self, conn):
+        """``(groups, paired)``: duplicate id groups, oldest first.
+
+        ``paired`` are the groups with a member in a saved pair, which the
+        cleanup keeps whole.
+        """
+        groups, paired = [], []
+        for duplicate in conn.execute(DUPLICATE_PROMPTS_SQL).fetchall():
+            ids = duplicate["ids"].split(",")
+            created_dates = duplicate["created_dates"].split(",")
+            # Sort IDs by created_at date to keep the oldest
+            id_date_pairs = list(zip(ids, created_dates))
+            id_date_pairs.sort(key=lambda x: x[1])
+            sorted_ids = [int(pair[0]) for pair in id_date_pairs]
+            try:
+                self._ensure_prompts_unpaired(conn, sorted_ids)
+            except PairDependencyError:
+                paired.append(sorted_ids)
+                continue
+            groups.append(sorted_ids)
+        return groups, paired
+
+    def _merge_duplicate_group(self, conn, sorted_ids):
+        """Keep the oldest prompt of a group; returns (removed, images moved)."""
+        primary_id, duplicate_ids = sorted_ids[0], sorted_ids[1:]
+        self.logger.debug(
+            f"Merging duplicates: keeping {primary_id}, removing {duplicate_ids}"
+        )
+        primary = conn.execute(
+            "SELECT * FROM prompts WHERE id = ?", (primary_id,)
+        ).fetchone()
+        if not primary:
+            return 0, 0
+        merged_metadata = self._merge_duplicate_metadata(
+            conn, primary_id, duplicate_ids
+        )
+        moved = self._transfer_images_to_primary(conn, primary_id, duplicate_ids)
+        if merged_metadata:
+            self._update_primary_with_merged_metadata(conn, primary_id, merged_metadata)
+        removed = 0
+        for duplicate_id in duplicate_ids:
+            conn.execute("DELETE FROM prompts WHERE id = ?", (duplicate_id,))
+            removed += 1
+            self.logger.debug(f"Removed duplicate prompt {duplicate_id}")
+        return removed, moved
+
+    @staticmethod
+    def _missing_link_ids(rows, roots):
+        """Ids of the ``rows`` whose file is gone under a readable source."""
+        readable = readable_roots(roots)
+        return [
+            row[0]
+            for row, _owner, state in link_states(rows, roots, readable)
+            if state == "missing"
+        ]
+
+    # ── previews ──────────────────────────────────────────────────────
+
+    def preview_maintenance(self, operation, roots=()) -> MaintenanceDraft:
+        """The reviewed plan of ``operation``; writes nothing (blocking).
+
+        ``roots`` are the sources missing links are judged under (the health
+        check's: the effective sources plus configured ones that are gone).
+        """
+        if operation not in MAINTENANCE_OPERATIONS:
+            raise ValueError(f"Unknown maintenance operation {operation!r}")
+        roots = [str(root) for root in roots]
+        if operation == "optimize":
+            return self._plan_optimize()
+        if operation == "missing_links":
+            rows = _read_snapshot(self.model.db_path, self._link_rows)
+            return self._plan_missing_links(rows, roots)
+        reader = (
+            self._plan_duplicate_prompts
+            if operation == "duplicate_prompts"
+            else self._plan_unused_components
+        )
+        return _read_snapshot(self.model.db_path, reader)
+
+    @staticmethod
+    def _link_rows(conn):
+        rows = []
+        cursor = conn.execute(_LINK_ROWS_SQL)
+        while batch := cursor.fetchmany(BATCH_ROWS):
+            rows.extend(tuple(row) for row in batch)
+        return rows
+
+    def _duplicates_fingerprint(self, conn):
+        groups, paired = self._duplicate_groups(conn)
+        fingerprint = _Fingerprint("duplicate_prompts")
+        fingerprint.add({"groups": groups, "paired": paired})
+        _add_prompt_state(fingerprint, conn, [i for group in groups for i in group])
+        return groups, paired, fingerprint.hexdigest()
+
+    def _plan_duplicate_prompts(self, conn):
+        groups, paired, fingerprint = self._duplicates_fingerprint(conn)
+        removed = sum(len(group) - 1 for group in groups)
+        texts = _texts(conn, [group[0] for group in (groups + paired)])
+        details = [
+            {
+                "label": _excerpt(texts.get(group[0])),
+                "detail": f"Keeps the oldest of {len(group)} copies",
+            }
+            for group in groups
+        ] + [
+            {
+                "label": _excerpt(texts.get(group[0])),
+                "detail": "Kept: belongs to a saved pair",
+            }
+            for group in paired
+        ]
+        if groups:
+            label = (
+                f"{_plural(removed, 'duplicate prompt')} in "
+                f"{_plural(len(groups), 'group')}"
+            )
+        else:
+            label = "No duplicate prompt text"
+        reasons = []
+        if len(paired) == 1:
+            reasons.append("1 group belongs to a saved pair")
+        elif paired:
+            reasons.append(f"{len(paired):,} groups belong to saved pairs")
+        return MaintenanceDraft(
+            operation="duplicate_prompts",
+            fingerprint=fingerprint,
+            targets=groups,
+            scope={"count": removed, "label": label},
+            protected={
+                "count": sum(len(group) for group in paired),
+                "reasons": reasons,
+            },
+            media={"deletes_files": False, "label": NO_FILES_DELETED},
+            details=details[:MAX_DETAILS],
+        )
+
+    def _unused_fingerprint(self, conn):
+        ids = _orphaned_ids(conn)
+        fingerprint = _Fingerprint("unused_components")
+        fingerprint.add(ids)
+        _add_prompt_state(fingerprint, conn, ids)
+        return ids, fingerprint.hexdigest()
+
+    def _plan_unused_components(self, conn):
+        ids, fingerprint = self._unused_fingerprint(conn)
+        *by_reason, kept = conn.execute(_UNLINKED_PROTECTIONS_SQL).fetchone()
+        reasons = [
+            f"{count:,} {many if count != 1 else one}"
+            for count, (_predicate, many, one) in zip(by_reason, PROTECTIONS)
+            if count
+        ]
+        texts = _texts(conn, ids)
+        count = len(ids)
+        return MaintenanceDraft(
+            operation="unused_components",
+            fingerprint=fingerprint,
+            targets=ids,
+            scope={
+                "count": count,
+                "label": (
+                    _plural(count, "unused prompt component")
+                    if count
+                    else "No unused prompt components"
+                ),
+            },
+            protected={"count": kept, "reasons": reasons},
+            media={"deletes_files": False, "label": NO_FILES_DELETED},
+            details=[
+                {"label": _excerpt(texts.get(prompt_id)), "detail": UNUSED_DETAIL}
+                for prompt_id in ids[:MAX_DETAILS]
+            ],
+        )
+
+    @staticmethod
+    def _links_fingerprint(candidates):
+        fingerprint = _Fingerprint("missing_links")
+        for row, owner in candidates:
+            fingerprint.add([row[0], row[1], row[3], owner])
+        return fingerprint.hexdigest()
+
+    def _plan_missing_links(self, rows, roots):
+        readable = readable_roots(roots)
+        candidates, unavailable, outside = [], 0, 0
+        for row, owner, state in link_states(rows, roots, readable):
+            if state == "missing":
+                candidates.append((row, owner))
+            elif state == "unavailable":
+                unavailable += 1
+            elif state == "outside":
+                outside += 1
+        reasons = []
+        if unavailable:
+            reasons.append(
+                _plural(
+                    unavailable,
+                    "link under an unavailable source",
+                    "links under unavailable sources",
+                )
+            )
+        if outside:
+            reasons.append(
+                _plural(
+                    outside,
+                    "link outside the image sources",
+                    "links outside the image sources",
+                )
+            )
+        count = len(candidates)
+        return MaintenanceDraft(
+            operation="missing_links",
+            fingerprint=self._links_fingerprint(candidates),
+            targets=[row[0] for row, _owner in candidates],
+            scope={
+                "count": count,
+                "label": (
+                    _plural(count, "link to a missing file", "links to missing files")
+                    if count
+                    else "No links to missing files"
+                ),
+            },
+            protected={"count": unavailable + outside, "reasons": reasons},
+            media={"deletes_files": False, "label": LINKS_ONLY},
+            details=[
+                {
+                    "label": _relative(row[1], roots[owner]),
+                    "detail": (
+                        f"{_source_name(roots[owner], owner)} · the file is missing"
+                    ),
+                }
+                for row, owner in candidates[:MAX_DETAILS]
+            ],
+        )
+
+    def _plan_optimize(self):
+        def read(conn):
+            return [
+                conn.execute(f"PRAGMA {name}").fetchone()[0]
+                for name in ("page_size", "page_count", "freelist_count")
+            ]
+
+        page_size, page_count, free_pages = _read_snapshot(self.model.db_path, read)
+        db_path = self.model.db_path
+        wal = db_path + "-wal"
+        size = page_size * page_count
+        wal_size = os.path.getsize(wal) if os.path.exists(wal) else 0
+        free = shutil.disk_usage(os.path.dirname(os.path.abspath(db_path))).free
+        # VACUUM writes the rebuilt database through the WAL beside it.
+        return MaintenanceDraft(
+            operation="optimize",
+            fingerprint=_Fingerprint("optimize").hexdigest(),
+            targets=[],
+            scope={"count": 1, "label": "The whole database"},
+            protected={"count": 0, "reasons": []},
+            media={"deletes_files": False, "label": NO_FILES_DELETED},
+            details=[
+                {
+                    "label": "Database file",
+                    "detail": f"{_megabytes(size)}, plus {_megabytes(wal_size)} "
+                    "not yet checkpointed",
+                },
+                {
+                    "label": "Free pages",
+                    "detail": f"About {_megabytes(free_pages * page_size)} "
+                    "can be reclaimed",
+                },
+                {
+                    "label": "Free space needed",
+                    "detail": f"About {_megabytes(size)} in the database folder; "
+                    f"{_megabytes(free)} available",
+                },
+            ],
+        )

database/models.py

@@ -941,6 +941,10 @@ class PromptModel:
 
         Reclaims unused space and defragments the database file,
         improving query performance and reducing file size.
+
+        Raises:
+            Exception: whatever stopped VACUUM (logged first); the database is
+            then unchanged.
         """
         try:
             with closing(sqlite3.connect(self.db_path)) as conn:
@@ -948,6 +952,7 @@ class PromptModel:
                 conn.commit()
         except Exception as e:
             self.logger.error(f"Error vacuuming database: {e}")
+            raise
 
     def get_database_info(self) -> dict:
         """

database/operations.py

@@ -10,7 +10,7 @@ import os
 from typing import Optional, List, Dict, Any, Set, Tuple
 
 from .models import PromptModel, normalize_image_path, utc_now_iso
-from .pairs import PairDependencyError, PairOperations
+from .pairs import PairDependencyError, PairOperations  # noqa: F401 (re-exported)
 from .library import LibraryOperations, titled
 from .image_favorites import ImageFavoriteOperations
 from .annotations import AnnotationOperations
@@ -20,10 +20,17 @@ from .saved_views import SavedViewOperations
 from .library_commands import LibraryCommandOperations
 from .vocabulary import VocabularyOperations
 from .execution_history import ExecutionHistoryOperations
-from .execution_contexts import ExecutionContextOperations, LIVE_HINT_CTES
+from .execution_contexts import ExecutionContextOperations
 from .execution_outputs import ExecutionOutputOperations
 from .history_reads import HistoryReadOperations
 from .health import HealthOperations, iter_consistency_issues
+from .maintenance import (  # noqa: F401  (ORPHANED_PROMPTS_SQL is re-exported)
+    ORPHANED_PROMPTS_SQL,
+    _LINK_ROWS_SQL,
+    MaintenanceOperations,
+    _delete_ids,
+    _orphaned_ids,
+)
 
 # Import logging system
 try:
@@ -166,28 +173,6 @@ def _coerce_file_info(metadata: Any) -> tuple:
     )
 
 
-# Exempt references: images, pairs, the __protected__ tag, Library parent
-# state, and live recorded-run hints (computed once, see LIVE_HINT_CTES).
-ORPHANED_PROMPTS_SQL = "WITH " + LIVE_HINT_CTES + """
-SELECT p.id FROM prompts p
-LEFT JOIN generated_images gi ON p.id = gi.prompt_id
-WHERE gi.prompt_id IS NULL
-AND NOT EXISTS (
-    SELECT 1 FROM prompt_pairs pp
-    WHERE pp.positive_prompt_id = p.id OR pp.negative_prompt_id = p.id
-)
-AND NOT EXISTS (
-    SELECT 1 FROM prompt_tags pt
-    JOIN tags t ON pt.tag_id = t.id
-    WHERE pt.prompt_id = p.id AND t.name = '__protected__'
-)
-AND NOT EXISTS (
-    SELECT 1 FROM prompt_library_state ls WHERE ls.prompt_id = p.id
-)
-AND p.id NOT IN (SELECT prompt_id FROM live_hint_prompts)
-"""
-
-
 # The scan's known set (#249 Activity-2): every image row, with its stored file
 # size and whether its pair link is resolved: exactly one distinct pair, the rule
 # _LINK_SUMMARY_SQL and get_image_prompt_info use. A file is known and resolved
@@ -351,6 +336,7 @@ class PromptDatabase(
     ReviewDecisionOperations,
     SavedViewOperations,
     HealthOperations,
+    MaintenanceOperations,
 ):
     """Database operations class for managing prompts."""
 
@@ -1541,80 +1527,14 @@ class PromptDatabase(
         self.logger.info("Starting duplicate cleanup process with image preservation")
         try:
             with self._pair_transaction() as conn:
-                # Find duplicates by text content (case-insensitive)
-                # Note: Removed ORDER BY from GROUP_CONCAT for SQLite compatibility
-                # We'll sort the IDs manually after fetching
-                cursor = conn.execute("""
-                    SELECT LOWER(TRIM(text)) as normalized_text, COUNT(*) as count,
-                           GROUP_CONCAT(id) as ids,
-                           GROUP_CONCAT(created_at) as created_dates
-                    FROM prompts
-                    GROUP BY LOWER(TRIM(text))
-                    HAVING COUNT(*) > 1
-                """)
-
-                duplicates = cursor.fetchall()
-                self.logger.debug(
-                    f"Found {len(duplicates)} groups of duplicate prompts"
-                )
+                groups, _paired = self._duplicate_groups(conn)
+                self.logger.debug(f"Found {len(groups)} groups of duplicate prompts")
                 total_removed = 0
                 total_images_transferred = 0
-
-                for duplicate in duplicates:
-                    ids = duplicate["ids"].split(",")
-                    created_dates = duplicate["created_dates"].split(",")
-
-                    # Sort IDs by created_at date to keep the oldest
-                    id_date_pairs = list(zip(ids, created_dates))
-                    id_date_pairs.sort(key=lambda x: x[1])  # Sort by date
-                    sorted_ids = [int(pair[0]) for pair in id_date_pairs]
-
-                    try:
-                        self._ensure_prompts_unpaired(conn, sorted_ids)
-                    except PairDependencyError:
-                        continue
-
-                    # Keep the oldest one (first), merge and delete the rest
-                    primary_id = sorted_ids[0]  # Keep the oldest
-                    duplicate_ids = sorted_ids[1:]
-
-                    self.logger.debug(
-                        f"Merging duplicates: keeping {primary_id}, removing "
-                        f"{duplicate_ids}"
-                    )
-
-                    # Get primary prompt details
-                    cursor = conn.execute(
-                        "SELECT * FROM prompts WHERE id = ?", (primary_id,)
-                    )
-                    primary_prompt = cursor.fetchone()
-                    if not primary_prompt:
-                        continue
-
-                    # Collect and merge metadata from all duplicates
-                    merged_metadata = self._merge_duplicate_metadata(
-                        conn, primary_id, duplicate_ids
-                    )
-
-                    # Transfer all images from duplicates to primary prompt
-                    images_transferred = self._transfer_images_to_primary(
-                        conn, primary_id, duplicate_ids
-                    )
-                    total_images_transferred += images_transferred
-
-                    # Update primary prompt with merged metadata
-                    if merged_metadata:
-                        self._update_primary_with_merged_metadata(
-                            conn, primary_id, merged_metadata
-                        )
-
-                    # Delete duplicate prompts (images already transferred)
-                    for duplicate_id in duplicate_ids:
-                        conn.execute(
-                            "DELETE FROM prompts WHERE id = ?", (duplicate_id,)
-                        )
-                        total_removed += 1
-                        self.logger.debug(f"Removed duplicate prompt {duplicate_id}")
+                for sorted_ids in groups:
+                    removed, moved = self._merge_duplicate_group(conn, sorted_ids)
+                    total_removed += removed
+                    total_images_transferred += moved
 
                 conn.commit()
 
@@ -1879,13 +1799,30 @@ class PromptDatabase(
             conn.commit()
             return cursor.rowcount > 0
 
-    def cleanup_missing_images(self) -> int:
+    def cleanup_missing_images(self, roots=None) -> int:
         """
         Remove image records where the actual file no longer exists.
 
+        Args:
+            roots: The image sources links are judged under (the health
+                check's). When given, only a link under a source that can be
+                read now is removed: a link under an unavailable source (an
+                unmounted drive) or outside every source is kept. None keeps
+                the old rule: every link whose file does not exist.
+
         Returns:
             int: Number of orphaned records removed
         """
+        if roots is not None:
+            with self.model.get_connection() as conn:
+                rows = [tuple(row) for row in conn.execute(_LINK_ROWS_SQL)]
+            # Files are looked at before the write transaction starts.
+            ids = self._missing_link_ids(rows, [str(root) for root in roots])
+            if not ids:
+                return 0
+            with self._pair_transaction() as conn:
+                return _delete_ids(conn, "generated_images", ids)
+
         removed_count = 0
 
         with self.model.get_connection() as conn:
@@ -2567,16 +2504,12 @@ class PromptDatabase(
         Returns number of prompts removed.
         """
         with self._pair_transaction() as conn:
-            cursor = conn.execute(ORPHANED_PROMPTS_SQL)
-            orphaned = [row["id"] for row in cursor.fetchall()]
+            orphaned = _orphaned_ids(conn)
             if not orphaned:
                 return 0
-            placeholders = ",".join(["?"] * len(orphaned))
-            cursor = conn.execute(
-                f"DELETE FROM prompts WHERE id IN ({placeholders})", orphaned
-            )
+            removed = _delete_ids(conn, "prompts", orphaned)
             conn.commit()
-            return cursor.rowcount
+            return removed
 
     def check_consistency(self) -> List[str]:
         """Run consistency checks and return a list of issue descriptions.