feat(metadata): add CivitAI AutoV3 hash support across all storage layers

- Three-state autov3 field (not-checked / checked-unavailable / 12-hex value)
  in .metadata.json sidecars, in-memory ModelHashIndex, and SQLite
  (models.autov3 column + autov3_index table) with column-presence migration
- Background self-terminating backfill for legacy rows: per-model-type
  concurrency guard, executor-offloaded I/O, Civitai-first resolution
  (SHA256-matched version file) falling back to the embedded safetensors
  header hash
- Civitai-first propagation on metadata refresh, scan, and download paths;
  reject the empty-string SHA256 placeholder and strip OneTrainer 0x prefix
- List API hash filters and hash index lookups accept 12-char AutoV3
- Cap safetensors header reads at 64 MiB to prevent crafted-file allocation
- Prevent stale AutoV3 mappings on file replacement while preserving them on
  same-file re-registration (lazy-hash completion)

py/services/autov3_backfill_service.py

@@ -0,0 +1,140 @@
+"""Backfill the AutoV3 checked state for models loaded from a persisted snapshot.
+
+The SQLite persistent cache predates the AutoV3 feature, so entries hydrated
+from it have a NULL ``autov3`` column (the "not checked yet" state). This
+service computes the embedded AutoV3 hash for each such model — once per
+process — and persists it through the scanner's single write path
+(:meth:`ModelScanner.update_autov3_for_model`), marking every visited row so a
+subsequent run finds nothing left to do.
+
+Three-state contract honored here:
+
+- ``NULL`` (sqlite) / absent (dict)  = not checked yet  → backfill computes it
+- ``''`` (sqlite/dict) / JSON null   = checked, no value available → never recompute
+- 12-char lowercase hex              = value → never recompute
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import logging
+import os
+import threading
+from typing import TYPE_CHECKING, Optional
+
+if TYPE_CHECKING:  # pragma: no cover - type-check only; runtime imports are local
+    from .model_scanner import ModelScanner
+
+logger = logging.getLogger(__name__)
+
+
+def _resolve_autov3(file_path: str) -> str:
+    """Resolve the AutoV3 hash for a model file.
+
+    Prefers the Civitai AutoV3 reported for the file whose SHA256 matches
+    (the authoritative value for recipe matching); falls back to the embedded
+    safetensors header hash. Returns ``''`` when neither is available.
+    """
+    try:
+        metadata_path = f"{os.path.splitext(file_path)[0]}.metadata.json"
+        if os.path.exists(metadata_path):
+            with open(metadata_path, "r", encoding="utf-8") as handle:
+                payload = json.load(handle)
+            if isinstance(payload, dict):
+                from ..utils.models import autov3_from_civitai_files  # local import avoids cycles
+
+                sha256 = (payload.get("sha256") or "").lower()
+                civitai_autov3 = autov3_from_civitai_files(payload.get("civitai"), sha256)
+                if civitai_autov3:
+                    return civitai_autov3
+    except Exception:
+        pass
+    from ..utils.file_utils import calculate_autov3  # local import avoids cycles
+
+    return calculate_autov3(file_path) or ""
+
+
+class Autov3BackfillService:
+    """Compute and persist AutoV3 hashes for models missing a checked state."""
+
+    _instance: Optional["Autov3BackfillService"] = None
+    _instance_lock = threading.Lock()
+
+    def __init__(self) -> None:
+        # Re-entrancy guard per model type: scanners for different model types
+        # initialize concurrently (lora_manager.py), so a global guard would
+        # silently skip every type but the first to start. Each model type
+        # runs its own backfill; a duplicate trigger for the same type no-ops.
+        self._running_types: set = set()
+
+    @classmethod
+    def get_instance(cls) -> "Autov3BackfillService":
+        """Return the process-wide singleton instance."""
+        if cls._instance is None:
+            with cls._instance_lock:
+                if cls._instance is None:
+                    cls._instance = cls()
+        return cls._instance
+
+    async def backfill(self, scanner: "ModelScanner") -> int:
+        """Compute AutoV3 for every un-checked model of ``scanner.model_type``.
+
+        Each candidate file is read once via :func:`~py.utils.file_utils.calculate_autov3`
+        (cheap: safetensors header only) and the result is persisted through
+        ``scanner.update_autov3_for_model``. Files that no longer exist on
+        disk are skipped — they are intentionally NOT marked, because scanner
+        cleanup removes the stale row later.
+
+        Returns:
+            The number of models successfully updated. Never raises; on any
+            failure a warning is logged and ``0`` is returned. A duplicate
+            trigger for a model type that is already being backfilled returns
+            ``0`` immediately; different model types run concurrently.
+        """
+        model_type = scanner.model_type
+        if model_type in self._running_types:
+            return 0
+        self._running_types.add(model_type)
+        try:
+            # Local imports avoid import cycles at module load time.
+            from .persistent_model_cache import get_persistent_cache
+            from ..utils.file_utils import calculate_autov3
+
+            persistent = getattr(scanner, "_persistent_cache", None) or get_persistent_cache()
+            paths = persistent.get_models_missing_autov3(model_type)
+
+            loop = asyncio.get_running_loop()
+            count = 0
+            for path in paths:
+                # A file that no longer exists must not be marked; scanner
+                # cleanup removes the stale row later. The existence check and
+                # hash resolution run in the executor so the loop stays
+                # responsive to API requests while the backfill iterates a
+                # large library.
+                if not await loop.run_in_executor(None, os.path.exists, path):
+                    continue
+                autov3 = await loop.run_in_executor(None, _resolve_autov3, path)
+                if await scanner.update_autov3_for_model(model_type, path, autov3):
+                    count += 1
+
+            if paths:
+                logger.info(
+                    "AutoV3 backfill: updated %d/%d models for %s",
+                    count,
+                    len(paths),
+                    model_type,
+                )
+            else:
+                # Steady state after the first run: nothing left to backfill.
+                logger.debug("AutoV3 backfill: nothing to process for %s", model_type)
+            return count
+        except Exception as exc:
+            logger.warning(
+                "AutoV3 backfill failed for %s: %s",
+                getattr(scanner, "model_type", "?"),
+                exc,
+            )
+            return 0
+        finally:
+            self._running_types.discard(model_type)

py/services/base_model_service.py

@@ -446,20 +446,31 @@ class BaseModelService(ABC):
     async def _apply_hash_filters(
         self, data: List[Dict], hash_filters: Dict
     ) -> List[Dict]:
-        """Apply hash-based filtering"""
+        """Apply hash-based filtering (SHA256 and AutoV3)."""
+
+        def matches_hash_set(item: Dict, hash_set: set) -> bool:
+            """Check whether an item matches any hash in the set.
+
+            Compares the item's ``sha256`` field and its non-empty ``autov3``
+            field, both case-insensitively.
+            """
+            if item.get("sha256", "").lower() in hash_set:
+                return True
+            autov3 = item.get("autov3", "")
+            return bool(autov3) and autov3.lower() in hash_set
+
         single_hash = hash_filters.get("single_hash")
         multiple_hashes = hash_filters.get("multiple_hashes")
 
         if single_hash:
-            # Filter by single hash
-            single_hash = single_hash.lower()
+            # Filter by single hash (SHA256 or AutoV3)
             return [
-                item for item in data if item.get("sha256", "").lower() == single_hash
+                item for item in data if matches_hash_set(item, {single_hash.lower()})
             ]
         elif multiple_hashes:
-            # Filter by multiple hashes
-            hash_set = set(hash.lower() for hash in multiple_hashes)
-            return [item for item in data if item.get("sha256", "").lower() in hash_set]
+            # Filter by multiple hashes (SHA256 or AutoV3)
+            hash_set = {hash.lower() for hash in multiple_hashes}
+            return [item for item in data if matches_hash_set(item, hash_set)]
 
         return data
 

py/services/cache_entry_validator.py

@@ -59,6 +59,7 @@ class CacheEntryValidator:
         'notes': ('', False),
         'usage_tips': ('', False),
         'hash_status': ('completed', False),
+        'autov3': (None, False),
     }
 
     @classmethod
@@ -119,8 +120,13 @@ class CacheEntryValidator:
                 if is_required:
                     errors.append(f"Required field '{field_name}' is missing or None")
                 if auto_repair:
-                    working_entry[field_name] = cls._get_default_copy(default_value)
-                    repaired = True
+                    # A missing optional field whose default is None is already
+                    # semantically equal to its default (e.g. autov3: absent
+                    # means "not checked") — writing None back is a no-op, not
+                    # a repair.
+                    if default_value is not None:
+                        working_entry[field_name] = cls._get_default_copy(default_value)
+                        repaired = True
                 continue
 
             # Validate field type and value
@@ -175,6 +181,15 @@ class CacheEntryValidator:
                     # that invalidates the entry, but we also don't mark it repaired.
                     pass
 
+        # Normalize autov3 to lowercase if needed (optional field, never stripped).
+        autov3 = working_entry.get('autov3')
+        if isinstance(autov3, str) and autov3:
+            normalized_autov3 = autov3.lower()
+            if normalized_autov3 != autov3:
+                if auto_repair:
+                    working_entry['autov3'] = normalized_autov3
+                    repaired = True
+
         # Determine if entry is valid
         # Entry is valid if no critical required field errors remain after repair
         # Critical fields are file_path and sha256
@@ -242,6 +257,19 @@ class CacheEntryValidator:
         """
         expected_type = type(default_value)
 
+        # Special case: autov3 is optional with a three-state contract.
+        # None = not checked, "" = checked but unavailable, otherwise a
+        # 12-character hex string (case-insensitive here; normalized to
+        # lowercase separately).
+        if field_name == 'autov3':
+            if value is None or value == "":
+                return None
+            if not isinstance(value, str):
+                return f"Field 'autov3' should be string or None, got {type(value).__name__}"
+            if len(value) != 12 or any(c not in '0123456789abcdefABCDEF' for c in value):
+                return "Field 'autov3' should be a 12-character hex string"
+            return None
+
         # Special handling for numeric types
         if expected_type == int:
             if not isinstance(value, (int, float)):

py/services/checkpoint_scanner.py

@@ -6,7 +6,7 @@ from datetime import datetime
 from typing import Any, Dict, List, Optional
 
 from ..utils.models import CheckpointMetadata
-from ..utils.file_utils import find_preview_file, normalize_path
+from ..utils.file_utils import find_preview_file, normalize_path, calculate_autov3
 from ..utils.metadata_manager import MetadataManager
 from ..config import config
 from .model_scanner import ModelScanner
@@ -62,6 +62,11 @@ class CheckpointScanner(ModelScanner):
             # Find preview image
             preview_url = find_preview_file(base_name, dir_path)
 
+            # AutoV3 reads only the safetensors header, so it is cheap even for
+            # large checkpoints; record the checked state at creation time ("" =
+            # checked but unavailable).
+            autov3 = calculate_autov3(real_path)
+
             # Create metadata WITHOUT calculating hash
             metadata = CheckpointMetadata(
                 file_name=base_name,
@@ -77,6 +82,7 @@ class CheckpointScanner(ModelScanner):
                 sub_type="checkpoint",
                 from_civitai=False,  # Mark as local model since no hash yet
                 hash_status="pending",  # Mark hash as pending
+                autov3=autov3 or "",
             )
 
             # Save the created metadata
@@ -120,7 +126,11 @@ class CheckpointScanner(ModelScanner):
                 # that queries get_hash_by_filename first) will miss on every
                 # lookup and keep calling back into this method, creating a
                 # tight loop that never populates the index.
-                self._hash_index.add_entry(metadata.sha256.lower(), file_path)
+                self._hash_index.add_entry(
+                    metadata.sha256.lower(),
+                    file_path,
+                    getattr(metadata, "autov3", None) or None,
+                )
                 return metadata.sha256
 
             async with self._hash_calculation_lock:
@@ -132,7 +142,11 @@ class CheckpointScanner(ModelScanner):
                     and metadata.hash_status == "completed"
                     and metadata.sha256
                 ):
-                    self._hash_index.add_entry(metadata.sha256.lower(), file_path)
+                    self._hash_index.add_entry(
+                        metadata.sha256.lower(),
+                        file_path,
+                        getattr(metadata, "autov3", None) or None,
+                    )
                     return metadata.sha256
 
                 task = self._hash_calculation_tasks.get(real_path)
@@ -185,7 +199,11 @@ class CheckpointScanner(ModelScanner):
             if metadata.hash_status == "completed" and metadata.sha256:
                 # Populate the in-memory hash index even for pre-computed
                 # hashes, mirroring the fix in calculate_hash_for_model.
-                self._hash_index.add_entry(metadata.sha256.lower(), file_path)
+                self._hash_index.add_entry(
+                    metadata.sha256.lower(),
+                    file_path,
+                    getattr(metadata, "autov3", None) or None,
+                )
                 return metadata.sha256
 
             # Update status to calculating
@@ -202,7 +220,11 @@ class CheckpointScanner(ModelScanner):
             await MetadataManager.save_metadata(file_path, metadata)
 
             # Update hash index
-            self._hash_index.add_entry(sha256.lower(), file_path)
+            self._hash_index.add_entry(
+                sha256.lower(),
+                file_path,
+                getattr(metadata, "autov3", None) or None,
+            )
 
             # Update the in-memory cache entry so that subsequent
             # _persist_current_cache / _save_persistent_cache calls

py/services/metadata_sync_service.py

@@ -11,6 +11,7 @@ from typing import Any, Awaitable, Callable, Dict, Iterable, Optional
 from ..services.settings_manager import SettingsManager
 from ..utils.civitai_utils import resolve_license_payload
 from ..utils.model_utils import determine_base_model
+from ..utils.models import autov3_from_civitai_files
 from .connectivity_guard import OFFLINE_FRIENDLY_MESSAGE, is_expected_offline_error
 from .errors import RateLimitError
 
@@ -152,6 +153,18 @@ class MetadataSyncService:
             civitai_metadata.get("baseModel")
         )
 
+        # Civitai-first AutoV3 propagation: the freshly fetched version
+        # metadata may report an AutoV3 for the file whose SHA256 matches the
+        # local model. Persist it now so recipe matching sees it immediately —
+        # no full rescan or restart required (the header is never re-read to
+        # upgrade the checked-unavailable '' state).
+        sha256_value = (local_metadata.get("sha256") or "").lower()
+        civitai_autov3 = autov3_from_civitai_files(
+            local_metadata.get("civitai"), sha256_value
+        )
+        if civitai_autov3:
+            local_metadata["autov3"] = civitai_autov3
+
         await self._preview_service.ensure_preview_for_metadata(
             metadata_path, local_metadata, civitai_metadata.get("images", [])
         )

py/services/model_hash_index.py

@@ -8,11 +8,12 @@ class ModelHashIndex:
         self._hash_to_path: Dict[str, str] = {}
         self._filename_to_hash: Dict[str, str] = {}
         self._autov2_to_path: Dict[str, str] = {}
+        self._autov3_to_path: Dict[str, str] = {}
         # New data structures for tracking duplicates
         self._duplicate_hashes: Dict[str, List[str]] = {}  # sha256 -> list of paths
         self._duplicate_filenames: Dict[str, List[str]] = {}  # filename -> list of paths
     
-    def add_entry(self, sha256: str, file_path: str) -> None:
+    def add_entry(self, sha256: str, file_path: str, autov3: Optional[str] = None) -> None:
         """Add or update hash index entry"""
         if not sha256 or not file_path:
             return
@@ -33,9 +34,13 @@ class ModelHashIndex:
                     self._duplicate_hashes.setdefault(sha256, []).append(file_path)
         
         # Track duplicates by filename - FIXED LOGIC
+        is_re_registration = False
         if filename in self._filename_to_hash:
             existing_hash = self._filename_to_hash[filename]
             existing_path = self._hash_to_path.get(existing_hash)
+            # Same path registered again (e.g. a file replaced in place with
+            # new content) — used below to drop its stale autov3 mapping.
+            is_re_registration = existing_path == file_path
             
             # If this is a different file with the same filename
             if existing_path and existing_path != file_path:
@@ -67,6 +72,30 @@ class ModelHashIndex:
         # AutoV2 = first 10 chars of SHA256
         if len(sha256) >= 10:
             self._autov2_to_path[sha256[:10]] = file_path
+        # AutoV3 is an independent hash (not derived from SHA256), stored as-is.
+        # Drop stale mappings for a path when it is re-registered with a NEW
+        # sha256 (file replaced in place) or with an explicit new autov3 value
+        # (correction). Re-registering the SAME file with the same sha256 and
+        # no autov3 (e.g. lazy-hash completion) must never clear its existing
+        # mapping. First-time registrations stay O(1).
+        if autov3:
+            autov3 = autov3.lower()
+        if is_re_registration and (existing_hash != sha256 or autov3):
+            stale_autov3_keys = [
+                key for key, mapped_path in self._autov3_to_path.items()
+                if mapped_path == file_path and key != autov3
+            ]
+            for key in stale_autov3_keys:
+                del self._autov3_to_path[key]
+        if autov3:
+            self._autov3_to_path[autov3] = file_path
+
+    def add_autov3(self, autov3: str, file_path: str) -> None:
+        """Add or update an AutoV3-only index entry (used when only AutoV3 is known)"""
+        if not autov3:
+            return
+        autov3 = autov3.lower()
+        self._autov3_to_path[autov3] = file_path
     
     def _get_filename_from_path(self, file_path: str) -> str:
         """Extract filename without extension from path"""
@@ -167,6 +196,11 @@ class ModelHashIndex:
         for k in autov2_keys_to_remove:
             del self._autov2_to_path[k]
 
+        # Remove from AutoV3 index
+        autov3_keys_to_remove = [k for k, v in self._autov3_to_path.items() if v == file_path]
+        for k in autov3_keys_to_remove:
+            del self._autov3_to_path[k]
+
     def remove_by_hash(self, sha256: str) -> None:
         """Remove entry by hash"""
         sha256 = sha256.lower()
@@ -189,6 +223,11 @@ class ModelHashIndex:
         autov2_key = sha256[:10]
         if autov2_key in self._autov2_to_path:
             del self._autov2_to_path[autov2_key]
+
+        # Remove AutoV3 entries pointing to any removed path
+        autov3_keys_to_remove = [k for k, v in self._autov3_to_path.items() if v in paths_to_remove]
+        for k in autov3_keys_to_remove:
+            del self._autov3_to_path[k]
         
         # Update filename-to-hash and duplicate filenames for all paths
         for path_to_remove in paths_to_remove:
@@ -209,22 +248,26 @@ class ModelHashIndex:
                     del self._duplicate_filenames[fname]
     
     def has_hash(self, hash_value: str) -> bool:
-        """Check if hash exists in index (SHA256 or AutoV2)"""
+        """Check if hash exists in index (SHA256, AutoV2, or AutoV3)"""
         normalized = hash_value.lower()
         if normalized in self._hash_to_path:
             return True
         if len(normalized) == 10:
             return normalized in self._autov2_to_path
+        if len(normalized) == 12:
+            return normalized in self._autov3_to_path
         return False
 
     def get_path(self, hash_value: str) -> Optional[str]:
-        """Get file path for a hash (SHA256 or AutoV2)"""
+        """Get file path for a hash (SHA256, AutoV2, or AutoV3)"""
         normalized = hash_value.lower()
         path = self._hash_to_path.get(normalized)
         if path is not None:
             return path
         if len(normalized) == 10:
             return self._autov2_to_path.get(normalized)
+        if len(normalized) == 12:
+            return self._autov3_to_path.get(normalized)
         return None
     
     def get_hash(self, file_path: str) -> Optional[str]:
@@ -243,6 +286,7 @@ class ModelHashIndex:
         self._hash_to_path.clear()
         self._filename_to_hash.clear()
         self._autov2_to_path.clear()
+        self._autov3_to_path.clear()
         self._duplicate_hashes.clear()
         self._duplicate_filenames.clear()
     
@@ -253,6 +297,10 @@ class ModelHashIndex:
     def get_all_filenames(self) -> Set[str]:
         """Get all filenames in the index"""
         return set(self._filename_to_hash.keys())
+
+    def get_all_autov3(self) -> Dict[str, str]:
+        """Get a snapshot of all AutoV3 hashes mapped to their file paths"""
+        return dict(self._autov3_to_path)
     
     def get_duplicate_hashes(self) -> Dict[str, List[str]]:
         """Get dictionary of duplicate hashes and their paths"""    

py/services/model_scanner.py

@@ -7,9 +7,9 @@ import shutil
 from dataclasses import dataclass
 from typing import Any, Awaitable, Callable, Dict, List, Mapping, Optional, Set, Type, Union
 
-from ..utils.models import BaseModelMetadata
+from ..utils.models import BaseModelMetadata, autov3_from_civitai_files
 from ..config import config
-from ..utils.file_utils import find_preview_file, get_preview_extension, calculate_sha256
+from ..utils.file_utils import find_preview_file, get_preview_extension, calculate_sha256, calculate_autov3
 from ..utils.metadata_manager import MetadataManager
 from ..utils.civitai_utils import resolve_license_info
 from .model_cache import ModelCache
@@ -86,6 +86,7 @@ class ModelScanner:
         self._persistent_cache = get_persistent_cache()
         self._name_display_mode = self._resolve_name_display_mode()
         self._cancel_requested = False  # Flag for cancellation
+        self._autov3_backfill_scheduled = False  # One-time AutoV3 backfill trigger per process
         try:
             loop = asyncio.get_running_loop()
         except RuntimeError:
@@ -225,6 +226,19 @@ class ModelScanner:
         if not isinstance(notes, str):
             notes = str(notes)
 
+        # AutoV3 three-state contract: absent key / None = "not checked yet",
+        # "" = "checked but unavailable" (never re-read the header), else the
+        # 12-char lowercase hex value. A metadata object already follows the
+        # contract and is passed through unchanged; a payload dict only carries
+        # an explicit checked state when the key is present.
+        if is_mapping:
+            if 'autov3' in source:
+                entry_autov3 = source['autov3'] or ''
+            else:
+                entry_autov3 = None
+        else:
+            entry_autov3 = get_value('autov3', None)
+
         entry: Dict[str, Any] = {
             'file_path': normalized_path,
             # file_name is always stored WITHOUT extension (e.g. "OWSMianne_ANIMA_V1",
@@ -238,6 +252,7 @@ class ModelScanner:
             'size': int(get_value('size', 0) or 0),
             'modified': float(get_value('modified', 0.0) or 0.0),
             'sha256': (get_value('sha256', '') or '').lower(),
+            'autov3': entry_autov3,
             'base_model': get_value('base_model', '') or '',
             'preview_url': preview_url,
             'preview_nsfw_level': int(get_value('preview_nsfw_level', 0) or 0),
@@ -473,6 +488,13 @@ class ModelScanner:
             if sha_value and path:
                 hash_index.add_entry(sha_value.lower(), path)
 
+        # Rebuild the AutoV3 index from the persisted autov3_index rows. These
+        # cover every known autov3 -> path mapping regardless of whether a
+        # sha256 row also exists for the same file.
+        for autov3_value, path in persisted.autov3_hash_rows:
+            if autov3_value and path:
+                hash_index.add_autov3(autov3_value.lower(), path)
+
         tags_count: Dict[str, int] = {}
         adjusted_raw_data: List[Dict[str, Any]] = []
         for item in persisted.raw_data:
@@ -541,8 +563,30 @@ class ModelScanner:
             'scanner_type': self.model_type,
             'pageType': page_type
         })
+
+        # Schedule the one-time AutoV3 backfill task (at most once per process)
+        # so entries loaded from a persisted snapshot that predates autov3 get
+        # their checked state computed in the background. The task never blocks
+        # or crashes the load path.
+        if not self._autov3_backfill_scheduled:
+            self._autov3_backfill_scheduled = True
+            try:
+                loop = asyncio.get_running_loop()
+            except RuntimeError:
+                loop = None
+            if loop is not None:
+                loop.create_task(self._run_autov3_backfill())
+
         return True
 
+    async def _run_autov3_backfill(self) -> None:
+        """Backfill autov3 for entries loaded from the persisted cache that lack it."""
+        try:
+            from ..services.autov3_backfill_service import Autov3BackfillService  # lazy import (module created by another unit)
+            await Autov3BackfillService.get_instance().backfill(self)
+        except Exception as exc:
+            logger.warning("AutoV3 backfill failed: %s", exc)
+
     async def _save_persistent_cache(self, scan_result: CacheBuildResult) -> None:
         if not scan_result or not getattr(self, '_persistent_cache', None):
             return
@@ -555,6 +599,7 @@ class ModelScanner:
             return
 
         hash_snapshot = self._build_hash_index_snapshot(scan_result.hash_index)
+        autov3_snapshot = self._build_autov3_index_snapshot(scan_result.hash_index)
         loop = asyncio.get_event_loop()
         try:
             await loop.run_in_executor(
@@ -563,7 +608,8 @@ class ModelScanner:
                 self.model_type,
                 list(scan_result.raw_data),
                 hash_snapshot,
-                list(scan_result.excluded_models)
+                list(scan_result.excluded_models),
+                autov3_snapshot,
             )
         except Exception as exc:
             logger.warning("%s Scanner: Failed to persist cache: %s", self.model_type.capitalize(), exc)
@@ -589,6 +635,20 @@ class ModelScanner:
                     bucket.append(path)
         return snapshot
 
+    def _build_autov3_index_snapshot(self, hash_index: Optional[ModelHashIndex]) -> Dict[str, List[str]]:
+        """Build the autov3 -> [paths] snapshot for the persisted cache."""
+        snapshot: Dict[str, List[str]] = {}
+        if not hash_index:
+            return snapshot
+
+        for autov3_value, path in hash_index.get_all_autov3().items():
+            if not autov3_value or not path:
+                continue
+            bucket = snapshot.setdefault(autov3_value.lower(), [])
+            if path not in bucket:
+                bucket.append(path)
+        return snapshot
+
     async def _persist_current_cache(self) -> None:
         if self._cache is None or not getattr(self, '_persistent_cache', None):
             return
@@ -880,7 +940,11 @@ class ModelScanner:
 
                                     # Update hash index if available
                                     if 'sha256' in model_data and 'file_path' in model_data:
-                                        self._hash_index.add_entry(model_data['sha256'].lower(), model_data['file_path'])
+                                        self._hash_index.add_entry(
+                                            model_data['sha256'].lower(),
+                                            model_data['file_path'],
+                                            model_data.get('autov3') or None
+                                        )
                                     
                                     # Update tags count
                                     if 'tags' in model_data and model_data['tags']:
@@ -1130,6 +1194,36 @@ class ModelScanner:
             except Exception as e:
                 logger.error(f"Failed to compute SHA256 for {file_path}: {e}")
 
+        # AutoV3 resolution: prefer the Civitai AutoV3 reported for the file
+        # whose SHA256 matches (authoritative for recipe matching), falling
+        # back to the embedded safetensors header hash only for models never
+        # checked before (autov3 is None). A checked-unavailable state ('')
+        # is only upgraded by Civitai data — the header is never re-read.
+        current_autov3 = model_data.get('autov3')
+        if current_autov3 in (None, ''):
+            try:
+                civitai_data = None
+                if isinstance(metadata, BaseModelMetadata):
+                    civitai_data = metadata.civitai
+                elif isinstance(metadata, dict):
+                    civitai_data = metadata.get("civitai")
+                autov3 = autov3_from_civitai_files(
+                    civitai_data, model_data.get("sha256") or ""
+                ) or ""
+                if not autov3 and current_autov3 is None:
+                    autov3 = (calculate_autov3(os.path.realpath(file_path)) or '').lower()
+                if autov3 != current_autov3:
+                    model_data['autov3'] = autov3
+                    if isinstance(metadata, BaseModelMetadata):
+                        metadata.autov3 = autov3
+                        await MetadataManager.save_metadata(file_path, metadata)
+                    elif isinstance(metadata, dict):
+                        # Dict payload: JSON null encodes the checked-unavailable state.
+                        metadata['autov3'] = autov3 or None
+                        await MetadataManager.save_metadata(file_path, metadata)
+            except Exception as e:
+                logger.error(f"Failed to resolve AutoV3 for {file_path}: {e}")
+
         # Skip excluded models
         if model_data.get('exclude', False):
             excluded_models.append(model_data['file_path'])
@@ -1322,7 +1416,7 @@ class ModelScanner:
                                 sha_value = result.get('sha256')
                                 model_path = result.get('file_path')
                                 if sha_value and model_path:
-                                    hash_index.add_entry(sha_value.lower(), model_path)
+                                    hash_index.add_entry(sha_value.lower(), model_path, result.get('autov3') or None)
 
                                 for tag in result.get('tags') or []:
                                     tags_count[tag] = tags_count.get(tag, 0) + 1
@@ -1391,7 +1485,11 @@ class ModelScanner:
             await self._cache.resort()
             
             # Update the hash index
-            self._hash_index.add_entry(metadata_dict['sha256'], metadata_dict['file_path'])
+            self._hash_index.add_entry(
+                metadata_dict['sha256'],
+                metadata_dict['file_path'],
+                metadata_dict.get('autov3') or None,
+            )
             await self._persist_current_cache()
             return True
         except Exception as e:
@@ -1578,7 +1676,11 @@ class ModelScanner:
 
             sha_value = cache_entry.get('sha256')
             if sha_value:
-                self._hash_index.add_entry(sha_value.lower(), normalized_new_path)
+                self._hash_index.add_entry(
+                    sha_value.lower(),
+                    normalized_new_path,
+                    cache_entry.get('autov3') or None,
+                )
 
             all_folders = set(item['folder'] for item in cache.raw_data)
             cache.folders = sorted(list(all_folders), key=lambda x: x.lower())
@@ -1736,7 +1838,11 @@ class ModelScanner:
             if old_sha:
                 self._hash_index.remove_by_path(file_path)
             if new_sha:
-                self._hash_index.add_entry(new_sha, file_path)
+                self._hash_index.add_entry(
+                    new_sha,
+                    file_path,
+                    desired_entry.get('autov3') or None,
+                )
 
         # ---- Incremental version index update ----
         new_civitai = desired_entry.get("civitai")
@@ -1787,6 +1893,74 @@ class ModelScanner:
 
         return True
 
+    async def update_autov3_for_model(self, model_type: str, file_path: str, autov3: str) -> bool:
+        """Persist an AutoV3 hash for a single model (single write path used by the backfill service).
+
+        Locates the in-memory cache entry by ``file_path`` and updates only its
+        ``autov3`` field: the in-memory hash index, the SQLite snapshot via
+        :meth:`PersistentModelCache.update_single_model`, and the
+        ``.metadata.json`` sidecar. sha256, tags, and every other field are
+        left untouched, so the persistent delta only ever differs in autov3.
+
+        Returns:
+            ``True`` when the entry was found and updated, ``False`` otherwise.
+            Never raises — failures are logged and swallowed.
+        """
+        try:
+            if self._cache is None:
+                return False
+
+            entry = next(
+                (item for item in self._cache.raw_data if item.get('file_path') == file_path),
+                None,
+            )
+            if entry is None:
+                return False
+
+            # Normalize once so the memory entry, sidecar, and SQLite row agree.
+            autov3 = (autov3 or "").lower()
+
+            # Capture the pre-mutation state so update_single_model only sees
+            # an autov3 delta between old and new.
+            old_item = dict(entry)
+
+            entry['autov3'] = autov3 or ''
+
+            # Prefer add_entry when a sha256 is known so the sha256 and autov3
+            # maps stay in sync; fall back to an autov3-only registration.
+            sha_value = entry.get('sha256')
+            checked_autov3 = entry.get('autov3') or None
+            if sha_value:
+                self._hash_index.add_entry(sha_value.lower(), file_path, checked_autov3)
+            elif checked_autov3:
+                self._hash_index.add_autov3(checked_autov3, file_path)
+
+            persistent = getattr(self, '_persistent_cache', None)
+            if persistent is not None:
+                await asyncio.get_event_loop().run_in_executor(
+                    None,
+                    persistent.update_single_model,
+                    model_type,
+                    entry,
+                    old_item,
+                )
+
+            # Sidecar write-back: JSON null encodes the checked-unavailable
+            # state. Skip silently when the sidecar does not exist.
+            metadata_path = f"{os.path.splitext(file_path)[0]}.metadata.json"
+            if os.path.exists(metadata_path):
+                with open(metadata_path, 'r', encoding='utf-8') as handle:
+                    payload = json.load(handle)
+                if not isinstance(payload, dict):
+                    payload = {}
+                payload['autov3'] = entry['autov3'] or None
+                await MetadataManager.save_metadata(metadata_path, payload)
+
+            return True
+        except Exception as exc:
+            logger.warning("Failed to update AutoV3 for %s: %s", file_path, exc)
+            return False
+
     @staticmethod
     def _cache_entries_differ(a: Dict[str, Any], b: Dict[str, Any]) -> bool:
         """Return ``True`` when two cache-entry dicts differ in any field.

py/services/persistent_model_cache.py

@@ -3,7 +3,7 @@ import logging
 import os
 import sqlite3
 import threading
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import Dict, List, Mapping, Optional, Sequence, Tuple
 
 from ..utils.cache_paths import CacheType, resolve_cache_path_with_migration
@@ -18,6 +18,7 @@ class PersistedCacheData:
     raw_data: List[Dict]
     hash_rows: List[Tuple[str, str]]
     excluded_models: List[str]
+    autov3_hash_rows: List[Tuple[str, str]] = field(default_factory=list)
 
 
 DEFAULT_LICENSE_FLAGS = 127  # 127 (0b1111111) encodes default CivitAI permissions with all commercial modes enabled.
@@ -36,6 +37,7 @@ class PersistentModelCache:
         "size",
         "modified",
         "sha256",
+        "autov3",
         "base_model",
         "preview_url",
         "preview_nsfw_level",
@@ -118,6 +120,10 @@ class PersistentModelCache:
                         "SELECT sha256, file_path FROM hash_index WHERE model_type = ?",
                         (model_type,),
                     ).fetchall()
+                    autov3_rows = conn.execute(
+                        "SELECT autov3, file_path FROM autov3_index WHERE model_type = ?",
+                        (model_type,),
+                    ).fetchall()
                     excluded = conn.execute(
                         "SELECT file_path FROM excluded_models WHERE model_type = ?",
                         (model_type,),
@@ -191,6 +197,8 @@ class PersistentModelCache:
                 "hash_status": row["hash_status"] or "completed",
                 "hf_url": row["hf_url"] or "",
             }
+            if row["autov3"] is not None:
+                item["autov3"] = (row["autov3"] or "").lower()
             raw_data.append(item)
 
         hash_pairs = [(entry["sha256"].lower(), entry["file_path"]) for entry in hash_rows if entry["sha256"]]
@@ -201,10 +209,21 @@ class PersistentModelCache:
                 if sha_value:
                     hash_pairs.append((sha_value.lower(), item["file_path"]))
 
-        excluded_paths = [row["file_path"] for row in excluded]
-        return PersistedCacheData(raw_data=raw_data, hash_rows=hash_pairs, excluded_models=excluded_paths)
+        autov3_pairs = [
+            (entry["autov3"].lower(), entry["file_path"])
+            for entry in autov3_rows
+            if entry["autov3"]
+        ]
 
-    def save_cache(self, model_type: str, raw_data: Sequence[Dict], hash_index: Dict[str, List[str]], excluded_models: Sequence[str]) -> None:
+        excluded_paths = [row["file_path"] for row in excluded]
+        return PersistedCacheData(
+            raw_data=raw_data,
+            hash_rows=hash_pairs,
+            excluded_models=excluded_paths,
+            autov3_hash_rows=autov3_pairs,
+        )
+
+    def save_cache(self, model_type: str, raw_data: Sequence[Dict], hash_index: Dict[str, List[str]], excluded_models: Sequence[str], autov3_hash_index: Optional[Dict[str, List[str]]] = None) -> None:
         if not self.is_enabled():
             return
         if not self._schema_initialized:
@@ -251,6 +270,10 @@ class PersistentModelCache:
                             "DELETE FROM hash_index WHERE model_type = ? AND file_path = ?",
                             to_remove_models,
                         )
+                        conn.executemany(
+                            "DELETE FROM autov3_index WHERE model_type = ? AND file_path = ?",
+                            to_remove_models,
+                        )
                         conn.executemany(
                             "DELETE FROM excluded_models WHERE model_type = ? AND file_path = ?",
                             to_remove_models,
@@ -373,6 +396,52 @@ class PersistentModelCache:
                             hash_inserts,
                         )
 
+                    if autov3_hash_index is not None:
+                        existing_autov3_rows = conn.execute(
+                            "SELECT autov3, file_path FROM autov3_index WHERE model_type = ?",
+                            (model_type,),
+                        ).fetchall()
+                        existing_autov3_map: Dict[str, set] = {}
+                        for row in existing_autov3_rows:
+                            autov3_value = (row["autov3"] or "").lower()
+                            if not autov3_value:
+                                continue
+                            existing_autov3_map.setdefault(autov3_value, set()).add(row["file_path"])
+
+                        new_autov3_map: Dict[str, set] = {}
+                        for autov3_value, paths in autov3_hash_index.items():
+                            normalized_autov3 = (autov3_value or "").lower()
+                            if not normalized_autov3:
+                                continue
+                            bucket = new_autov3_map.setdefault(normalized_autov3, set())
+                            for path in paths:
+                                if path:
+                                    bucket.add(path)
+
+                        autov3_inserts: List[Tuple[str, str, str]] = []
+                        autov3_deletes: List[Tuple[str, str, str]] = []
+
+                        all_autov3 = set(existing_autov3_map.keys()) | set(new_autov3_map.keys())
+                        for autov3_value in all_autov3:
+                            existing_paths = existing_autov3_map.get(autov3_value, set())
+                            new_paths = new_autov3_map.get(autov3_value, set())
+
+                            for path in existing_paths - new_paths:
+                                autov3_deletes.append((model_type, autov3_value, path))
+                            for path in new_paths - existing_paths:
+                                autov3_inserts.append((model_type, autov3_value, path))
+
+                        if autov3_deletes:
+                            conn.executemany(
+                                "DELETE FROM autov3_index WHERE model_type = ? AND autov3 = ? AND file_path = ?",
+                                autov3_deletes,
+                            )
+                        if autov3_inserts:
+                            conn.executemany(
+                                "INSERT OR IGNORE INTO autov3_index (model_type, autov3, file_path) VALUES (?, ?, ?)",
+                                autov3_inserts,
+                            )
+
                     existing_excluded_rows = conn.execute(
                         "SELECT file_path FROM excluded_models WHERE model_type = ?",
                         (model_type,),
@@ -435,6 +504,7 @@ class PersistentModelCache:
                             size INTEGER,
                             modified REAL,
                             sha256 TEXT,
+                            autov3 TEXT,
                             base_model TEXT,
                             preview_url TEXT,
                             preview_nsfw_level INTEGER,
@@ -472,6 +542,13 @@ class PersistentModelCache:
                             PRIMARY KEY (model_type, sha256, file_path)
                         );
 
+                        CREATE TABLE IF NOT EXISTS autov3_index (
+                            model_type TEXT NOT NULL,
+                            autov3 TEXT NOT NULL,
+                            file_path TEXT NOT NULL,
+                            PRIMARY KEY (model_type, autov3, file_path)
+                        );
+
                         CREATE TABLE IF NOT EXISTS excluded_models (
                             model_type TEXT NOT NULL,
                             file_path TEXT NOT NULL,
@@ -504,6 +581,7 @@ class PersistentModelCache:
             "license_flags": f"INTEGER DEFAULT {DEFAULT_LICENSE_FLAGS}",
             "hash_status": "TEXT DEFAULT 'completed'",
             "hf_url": "TEXT DEFAULT ''",
+            "autov3": "TEXT",
         }
 
         for column, definition in required_columns.items():
@@ -549,6 +627,12 @@ class PersistentModelCache:
         if license_flags is None:
             license_flags = DEFAULT_LICENSE_FLAGS
 
+        autov3_value = item.get("autov3")
+        if autov3_value is None:
+            autov3_column = None
+        else:
+            autov3_column = (autov3_value or "").lower()
+
         return (
             model_type,
             item.get("file_path"),
@@ -558,6 +642,7 @@ class PersistentModelCache:
             int(item.get("size") or 0),
             float(item.get("modified") or 0.0),
             (item.get("sha256") or "").lower() or None,
+            autov3_column,
             item.get("base_model") or "",
             item.get("preview_url") or "",
             int(item.get("preview_nsfw_level") or 0),
@@ -663,6 +748,25 @@ class PersistentModelCache:
                                 (model_type, new_sha, file_path),
                             )
 
+                    # --- autov3_index ---
+                    new_autov3: Optional[str] = new_item.get("autov3")
+                    if new_autov3 is not None:
+                        new_autov3 = (new_autov3 or "").lower()
+                    old_autov3: Optional[str] = (old_item.get("autov3") if old_item else None)
+                    if old_autov3 is not None:
+                        old_autov3 = (old_autov3 or "").lower()
+                    if new_autov3 != old_autov3:
+                        if old_autov3:
+                            conn.execute(
+                                "DELETE FROM autov3_index WHERE model_type = ? AND autov3 = ? AND file_path = ?",
+                                (model_type, old_autov3, file_path),
+                            )
+                        if new_autov3:
+                            conn.execute(
+                                "INSERT OR IGNORE INTO autov3_index (model_type, autov3, file_path) VALUES (?, ?, ?)",
+                                (model_type, new_autov3, file_path),
+                            )
+
                     conn.execute("COMMIT")
                 except Exception:
                     conn.execute("ROLLBACK")
@@ -676,6 +780,40 @@ class PersistentModelCache:
                 exc,
             )
 
+    def get_models_missing_autov3(self, model_type: str) -> List[str]:
+        """Return file paths whose models lack an AutoV3 checked state.
+
+        Only rows with a completed sha256 and a NULL autov3 column qualify —
+        rows with '' (checked-unavailable) or a value are never returned, so
+        the backfill query self-terminates.
+        """
+        if not self.is_enabled():
+            return []
+        if not self._schema_initialized:
+            self._initialize_schema()
+        if not self._schema_initialized:
+            return []
+        try:
+            with self._db_lock:
+                conn = self._connect(readonly=True)
+                try:
+                    rows = conn.execute(
+                        "SELECT file_path FROM models "
+                        "WHERE model_type = ? AND autov3 IS NULL "
+                        "AND sha256 IS NOT NULL AND sha256 != ''",
+                        (model_type,),
+                    ).fetchall()
+                finally:
+                    conn.close()
+            return [row["file_path"] for row in rows]
+        except Exception as exc:
+            logger.warning(
+                "Failed to query models missing autov3 for %s: %s",
+                model_type,
+                exc,
+            )
+            return []
+
     def _load_tags(self, conn: sqlite3.Connection, model_type: str) -> Dict[str, List[str]]:
         tag_rows = conn.execute(
             "SELECT file_path, tag FROM model_tags WHERE model_type = ?",