Merge pull request #1124 from willmiao/feature/centralized-sidecar-storage

feat: optional centralized storage for sidecar metadata and previews (#1045)
This commit is contained in:
pixelpaws
2026-09-26 19:15:07 +08:00
committed by GitHub
44 changed files with 3665 additions and 115 deletions
+3 -1
View File
@@ -27,6 +27,8 @@ import os
import threading
from typing import TYPE_CHECKING, Optional
from ..utils.sidecar_paths import get_metadata_path
if TYPE_CHECKING: # pragma: no cover - type-check only; runtime imports are local
from .model_scanner import ModelScanner
@@ -41,7 +43,7 @@ def _resolve_autov3(file_path: str) -> str:
safetensors header hash. Returns ``''`` when neither is available.
"""
try:
metadata_path = f"{os.path.splitext(file_path)[0]}.metadata.json"
metadata_path = get_metadata_path(file_path)
if os.path.exists(metadata_path):
with open(metadata_path, "r", encoding="utf-8") as handle:
payload = json.load(handle)
+7 -2
View File
@@ -12,6 +12,7 @@ from typing import Any, Dict, List, Optional
from ..utils.models import CheckpointMetadata
from ..utils.file_utils import find_preview_file, normalize_path, calculate_autov3
from ..utils.metadata_manager import MetadataManager
from ..utils.sidecar_paths import get_preview_dir, is_centralized
from ..config import config
from .model_scanner import ModelScanner, _is_excluded_dir
from .model_hash_index import ModelHashIndex
@@ -61,10 +62,9 @@ class CheckpointScanner(ModelScanner):
return None
base_name = os.path.splitext(os.path.basename(file_path))[0]
dir_path = os.path.dirname(file_path)
# Find preview image
preview_url = find_preview_file(base_name, dir_path)
preview_url = find_preview_file(base_name, get_preview_dir(file_path))
# AutoV3 reads only the safetensors header, so it is cheap even for
# large checkpoints; record the checked state at creation time ("" =
@@ -322,6 +322,11 @@ class CheckpointScanner(ModelScanner):
async def _find_pending_models_from_filesystem(self) -> List[Dict[str, Any]]:
"""Scan filesystem for checkpoint metadata files with pending hash status."""
# Centralized mode stores sidecars in the mirror tree, not next to the
# models; walk the mirror instead of the model folders.
if is_centralized():
return self._find_pending_models_in_sidecar_mirror()
pending_models = []
for root_path in self.get_model_roots():
+26 -10
View File
@@ -38,6 +38,7 @@ from ..utils.preview_selection import resolve_mature_threshold, select_preview_m
from ..utils.utils import calculate_filename_for_model, sanitize_folder_name
from ..utils.exif_utils import ExifUtils
from ..utils.metadata_manager import MetadataManager
from ..utils.sidecar_paths import get_metadata_path, get_preview_dir
from .service_registry import ServiceRegistry
from .download_routing import is_diffusion_model_download, resolve_other_download_sub_type
from .settings_manager import get_settings_manager
@@ -831,7 +832,7 @@ class DownloadManager:
)
for file_path in target_files:
metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(file_path)
deleted = await self._delete_file_with_retries(metadata_path)
if not deleted and os.path.exists(metadata_path):
logger.error(f"Error deleting metadata file: {metadata_path}")
@@ -2447,7 +2448,7 @@ class DownloadManager:
return {"success": False, "error": save_path}
part_path = save_path + ".part"
metadata_path = os.path.splitext(save_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(save_path)
pause_control = self._pause_events.get(download_id) if download_id else None
@@ -2464,6 +2465,10 @@ class DownloadManager:
# Download preview image if available
images = version_info.get("images", [])
if images:
# Centralized preview mirrors may not exist yet (unlike the
# model's own directory in alongside mode).
os.makedirs(get_preview_dir(save_path), exist_ok=True)
if progress_callback:
await progress_callback(
1
@@ -2503,7 +2508,10 @@ class DownloadManager:
if media_type == "video":
preview_ext = _extension_from_url(preview_url, ".mp4")
preview_path = os.path.splitext(save_path)[0] + preview_ext
preview_path = os.path.join(
get_preview_dir(save_path),
os.path.splitext(os.path.basename(save_path))[0] + preview_ext,
)
rewritten_url, rewritten = rewrite_preview_url(
preview_url, media_type="video"
)
@@ -2530,7 +2538,10 @@ class DownloadManager:
)
if rewritten and rewritten_url:
preview_ext = _extension_from_url(preview_url, ".png")
preview_path = os.path.splitext(save_path)[0] + preview_ext
preview_path = os.path.join(
get_preview_dir(save_path),
os.path.splitext(os.path.basename(save_path))[0] + preview_ext,
)
success, _ = await downloader.download_file(
rewritten_url, preview_path, use_auth=False
)
@@ -2557,8 +2568,9 @@ class DownloadManager:
temp_file_handle.write(
content if isinstance(content, bytes) else content.encode("utf-8")
)
preview_path = (
os.path.splitext(save_path)[0] + ".webp"
preview_path = os.path.join(
get_preview_dir(save_path),
os.path.splitext(os.path.basename(save_path))[0] + ".webp",
)
optimized_data, _ = ExifUtils.optimize_image(
@@ -2788,9 +2800,7 @@ class DownloadManager:
entry = cast(Any, adjusted_entry)
metadata_entries[index] = entry
metadata_file_path = (
os.path.splitext(entry.file_path)[0] + ".metadata.json"
)
metadata_file_path = get_metadata_path(entry.file_path)
metadata_files_for_cleanup.append(metadata_file_path)
await MetadataManager.save_metadata(entry.file_path, entry)
@@ -3049,7 +3059,11 @@ class DownloadManager:
extension = os.path.splitext(preview_path)[1] or ".webp"
targets = [
os.path.splitext(entry.file_path)[0] + extension for entry in entries
os.path.join(
get_preview_dir(entry.file_path),
os.path.splitext(os.path.basename(entry.file_path))[0] + extension,
)
for entry in entries
]
if not targets:
@@ -3057,10 +3071,12 @@ class DownloadManager:
first_target = targets[0]
if preview_path != first_target:
os.makedirs(os.path.dirname(first_target), exist_ok=True)
os.replace(preview_path, first_target)
source_path = first_target
for target in targets[1:]:
os.makedirs(os.path.dirname(target), exist_ok=True)
shutil.copyfile(source_path, target)
return targets
+6 -5
View File
@@ -12,6 +12,7 @@ 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 ..utils.sidecar_paths import get_metadata_path
from .connectivity_guard import OFFLINE_FRIENDLY_MESSAGE, is_expected_offline_error
from .errors import RateLimitError
from .model_sources import has_external_source
@@ -216,7 +217,7 @@ class MetadataSyncService:
logger.error(error)
return False, error
metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(file_path)
enable_archive = self._settings.get("enable_metadata_archive_db", False)
previous_source = model_data.get("metadata_source") or (model_data.get("civitai") or {}).get("source")
@@ -485,7 +486,7 @@ class MetadataSyncService:
+ (f" with version: {model_version_id}" if model_version_id else "")
)
metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(file_path)
await self.update_model_metadata(
metadata_path,
metadata,
@@ -505,7 +506,7 @@ class MetadataSyncService:
) -> Dict[str, Any]:
"""Apply metadata updates and persist to disk and cache."""
metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(file_path)
metadata = await metadata_loader(metadata_path)
for key, value in updates.items():
@@ -554,7 +555,7 @@ class MetadataSyncService:
}
expected_hash: Optional[str] = None
first_metadata_path = os.path.splitext(file_paths[0])[0] + ".metadata.json"
first_metadata_path = get_metadata_path(file_paths[0])
first_metadata = await metadata_loader(first_metadata_path)
if first_metadata and "sha256" in first_metadata:
expected_hash = first_metadata["sha256"].lower()
@@ -565,7 +566,7 @@ class MetadataSyncService:
try:
actual_hash = await hash_calculator(path)
metadata_path = os.path.splitext(path)[0] + ".metadata.json"
metadata_path = get_metadata_path(path)
metadata = await metadata_loader(metadata_path)
stored_hash = metadata.get("sha256", "").lower()
+16
View File
@@ -8,6 +8,7 @@ from abc import ABC, abstractmethod
from ..utils.utils import calculate_relative_path_for_model, remove_empty_dirs
from ..utils.constants import AUTO_ORGANIZE_BATCH_SIZE, MODEL_FILE_EXTENSIONS
from ..utils.sidecar_paths import is_centralized, resolve_centralized_dir_for_dir
from ..services.settings_manager import get_settings_manager
from ..services.model_lifecycle_service import _require_path_in_library_roots
from ..services.pending_delete_service import PENDING_DELETE_DIR_NAME
@@ -663,6 +664,21 @@ class ModelMoveService:
shutil.rmtree(absolute_path)
# Centralized mode: prune the folder's mirror subtree when it no
# longer holds any sidecar files (per-model deletes already
# removed their sidecars, so only empty directories are expected;
# a non-empty mirror keeps its orphan sidecars).
if is_centralized():
mirror_dir = resolve_centralized_dir_for_dir(absolute_path)
if mirror_dir and os.path.isdir(mirror_dir):
for root, _dirs, files in os.walk(mirror_dir, topdown=False):
if files:
continue
try:
os.rmdir(root)
except OSError: # pragma: no cover - best-effort cleanup
pass
await self._forget_folder(relative_folder)
return {
+33 -21
View File
@@ -11,6 +11,7 @@ from ..services.service_registry import ServiceRegistry
from ..services.pending_delete_service import get_pending_delete_service
from ..utils.constants import PREVIEW_EXTENSIONS
from ..utils.metadata_manager import MetadataManager
from ..utils.sidecar_paths import get_metadata_path, get_preview_dir, get_sidecar_dir
logger = logging.getLogger(__name__)
@@ -41,16 +42,22 @@ async def load_local_metadata(metadata_path: str) -> Dict[str, Any]:
async def delete_model_artifacts(
target_dir: str, file_name: str, main_extension: str | None = None
) -> List[str]:
"""Delete the primary model artefacts within ``target_dir``."""
"""Delete the primary model artefacts within ``target_dir``.
Sidecars and previews are taken from the model's sidecar directory — the
model's own directory in alongside mode, the centralized mirror otherwise.
"""
main_extension = ".safetensors" if main_extension is None else main_extension
main_file = f"{file_name}{main_extension}" if main_extension else file_name
patterns = [main_file, f"{file_name}.metadata.json"]
model_path = os.path.join(target_dir, main_file)
sidecar_dir = get_sidecar_dir(model_path)
patterns = [os.path.basename(get_metadata_path(model_path))]
for ext in PREVIEW_EXTENSIONS:
patterns.append(f"{file_name}{ext}")
deleted: List[str] = []
main_path = os.path.join(target_dir, main_file).replace(os.sep, "/")
main_path = model_path.replace(os.sep, "/")
if os.path.exists(main_path):
os.remove(main_path)
@@ -58,8 +65,8 @@ async def delete_model_artifacts(
else:
logger.warning("Model file not found: %s", main_file)
for pattern in patterns[1:]:
path = os.path.join(target_dir, pattern)
for pattern in patterns:
path = os.path.join(sidecar_dir, pattern)
if os.path.exists(path):
try:
os.remove(path)
@@ -260,7 +267,7 @@ class ModelLifecycleService:
_require_path_in_library_roots(file_path, self._scanner, label="File path")
metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(file_path)
metadata = await self._metadata_loader(metadata_path)
metadata["exclude"] = True
@@ -315,7 +322,7 @@ class ModelLifecycleService:
if not os.path.exists(file_path):
raise ValueError("Model file does not exist")
metadata_path = os.path.splitext(file_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(file_path)
metadata_payload = await self._metadata_loader(metadata_path)
metadata_payload["exclude"] = False
@@ -384,21 +391,26 @@ class ModelLifecycleService:
if os.path.exists(new_file_path):
raise ValueError("A file with this name already exists")
patterns = [
f"{old_file_name}{old_extension}",
f"{old_file_name}.metadata.json",
f"{old_file_name}.metadata.json.bak",
metadata_filename = os.path.basename(get_metadata_path(file_path))
# Sidecars/previews live in the sidecar dir (the model's own dir in
# alongside mode, the centralized mirror otherwise); the model file
# itself always stays in target_dir.
sidecar_dir = get_sidecar_dir(file_path)
patterns: List[tuple[str, str]] = [
(target_dir, f"{old_file_name}{old_extension}"),
(sidecar_dir, metadata_filename),
(sidecar_dir, f"{metadata_filename}.bak"),
]
for ext in PREVIEW_EXTENSIONS:
patterns.append(f"{old_file_name}{ext}")
patterns.append((sidecar_dir, f"{old_file_name}{ext}"))
existing_files: List[tuple[str, str]] = []
for pattern in patterns:
path = os.path.join(target_dir, pattern)
for pattern_dir, pattern in patterns:
path = os.path.join(pattern_dir, pattern)
if os.path.exists(path):
existing_files.append((path, pattern))
metadata_path = os.path.join(target_dir, f"{old_file_name}.metadata.json")
metadata_path = get_metadata_path(file_path)
metadata: Optional[Dict[str, object]] = None
hash_value: Optional[str] = None
@@ -413,9 +425,9 @@ class ModelLifecycleService:
for old_path, pattern in existing_files:
ext = self._get_multipart_ext(pattern)
new_path = os.path.join(target_dir, f"{new_file_name}{ext}").replace(
os.sep, "/"
)
new_path = os.path.join(
os.path.dirname(old_path), f"{new_file_name}{ext}"
).replace(os.sep, "/")
os.rename(old_path, new_path)
renamed_files.append(new_path)
@@ -432,9 +444,9 @@ class ModelLifecycleService:
if metadata.get("preview_url"):
old_preview = str(metadata["preview_url"])
ext = self._get_multipart_ext(old_preview)
new_preview = os.path.join(target_dir, f"{new_file_name}{ext}").replace(
os.sep, "/"
)
new_preview = os.path.join(
get_preview_dir(new_file_path), f"{new_file_name}{ext}"
).replace(os.sep, "/")
metadata["preview_url"] = new_preview
await self._metadata_manager.save_metadata(new_file_path, metadata)
+172 -27
View File
@@ -11,6 +11,13 @@ 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, calculate_autov3
from ..utils.metadata_manager import MetadataManager
from ..utils.sidecar_paths import (
get_metadata_path,
get_preview_dir,
get_sidecar_dir,
is_centralized,
resolve_centralized_dir_for_dir,
)
from ..utils.civitai_utils import resolve_license_info
from .model_cache import ModelCache
from .model_hash_index import ModelHashIndex
@@ -1613,6 +1620,25 @@ class ModelScanner:
old_abs_prefix = f"{str(previous_path).replace(chr(92), '/').rstrip('/')}/"
new_abs_prefix = f"{str(new_path).replace(chr(92), '/').rstrip('/')}/"
# Centralized sidecar mode: sidecars/previews live in the mirror tree,
# not under the renamed model directory, so the mirror subtree must
# move too and mirror-prefixed preview URLs need their own rekey.
old_mirror_dir: Optional[str] = None
new_mirror_dir: Optional[str] = None
if is_centralized():
old_mirror_dir = resolve_centralized_dir_for_dir(str(previous_path))
new_mirror_dir = resolve_centralized_dir_for_dir(str(new_path))
old_mirror_prefix = (
f"{old_mirror_dir.replace(chr(92), '/').rstrip('/')}/"
if old_mirror_dir
else ""
)
new_mirror_prefix = (
f"{new_mirror_dir.replace(chr(92), '/').rstrip('/')}/"
if new_mirror_dir
else ""
)
cache = self._cache
if cache is None:
return False
@@ -1670,8 +1696,24 @@ class ModelScanner:
item["preview_url"] = self._rekey_path(
item["preview_url"], old_abs_prefix, new_abs_prefix
)
if old_mirror_prefix:
item["preview_url"] = self._rekey_path(
item["preview_url"], old_mirror_prefix, new_mirror_prefix
)
touched.append(item)
if old_mirror_dir and new_mirror_dir and os.path.isdir(old_mirror_dir):
try:
os.makedirs(os.path.dirname(new_mirror_dir), exist_ok=True)
shutil.move(old_mirror_dir, new_mirror_dir)
except Exception as exc: # pragma: no cover - defensive
logger.warning(
"Failed to move centralized sidecar mirror %s -> %s: %s",
old_mirror_dir,
new_mirror_dir,
exc,
)
if touched:
changed = True
await self._rewrite_sidecar_paths(touched)
@@ -1700,7 +1742,9 @@ class ModelScanner:
async def _rewrite_sidecar_paths(self, entries: List[Dict[str, Any]]) -> None:
"""Point each model's metadata sidecar at its new location.
Sidecars travel with the renamed directory, so only the recorded
In alongside mode sidecars travel with the renamed directory; in
centralized mode the mirror subtree has already been moved by the
caller (:meth:`rename_known_folder`). Either way only the recorded
``file_path``/``preview_url`` inside them need rewriting. Failures are
logged and skipped — a stale sidecar is repaired by the next metadata
refresh, and must not abort the rename.
@@ -1709,7 +1753,7 @@ class ModelScanner:
file_path = item.get("file_path")
if not file_path:
continue
metadata_path = f"{os.path.splitext(file_path)[0]}.metadata.json"
metadata_path = get_metadata_path(file_path)
if not os.path.exists(metadata_path):
continue
try:
@@ -1719,6 +1763,94 @@ class ModelScanner:
"Failed to rewrite metadata sidecar %s: %s", metadata_path, exc
)
def _find_pending_models_in_sidecar_mirror(self) -> List[Dict[str, Any]]:
"""Mirror-tree counterpart of the alongside pending-hash filesystem scan.
Centralized mode stores ``.metadata.json`` sidecars in the mirror
tree, so walking the model folders finds nothing. Each mirror base is
resolved from a configured model root; a sidecar's recorded
``file_path`` locates its model, with a stem-based probe under the
mapped model root as fallback (mirror path components are sanitized,
so reverse mapping is best-effort). Orphan sidecars whose model file
no longer exists are skipped, matching the alongside scan.
"""
pending_models: List[Dict[str, Any]] = []
for root_path in self.get_model_roots():
mirror_base = resolve_centralized_dir_for_dir(root_path)
if not mirror_base or not os.path.isdir(mirror_base):
continue
for dirpath, dirnames, filenames in os.walk(mirror_base):
dirnames[:] = [d for d in dirnames if not _is_excluded_dir(d)]
for filename in filenames:
if not filename.endswith(".metadata.json"):
continue
metadata_path = os.path.join(dirpath, filename)
try:
with open(metadata_path, "r", encoding="utf-8") as f:
data = json.load(f)
# Check if hash is pending
hash_status = data.get("hash_status", "completed")
sha256 = data.get("sha256", "")
if hash_status != "completed" or not sha256:
# Find corresponding model file: prefer the
# sidecar's recorded path, then probe by stem
# under the mapped model root.
model_path = None
recorded_path = data.get("file_path")
if (
isinstance(recorded_path, str)
and recorded_path
and os.path.exists(recorded_path)
):
model_path = recorded_path
else:
model_name = filename.replace(".metadata.json", "")
rel_dir = os.path.relpath(dirpath, mirror_base)
candidate_dir = (
root_path
if rel_dir == os.curdir
else os.path.join(root_path, rel_dir)
)
for ext in self.file_extensions:
potential_path = os.path.join(
candidate_dir, model_name + ext
)
if os.path.exists(potential_path):
model_path = potential_path
break
if model_path:
pending_models.append(
{
"file_path": model_path.replace(os.sep, "/"),
"hash_status": hash_status,
"sha256": sha256,
**{
k: v
for k, v in data.items()
if k
not in [
"file_path",
"hash_status",
"sha256",
]
},
}
)
except (json.JSONDecodeError, Exception) as e:
logger.debug(
f"Error reading metadata file {metadata_path}: {e}"
)
continue
return pending_models
def _schedule_all_folders_backfill(self) -> None:
"""Kick off a one-shot background folder walk if none is running."""
if self._all_folders_backfill_running:
@@ -1889,7 +2021,7 @@ class ModelScanner:
file_info['name'] = os.path.basename(file_path)
metadata = cast(Any, self.model_class).from_civitai_info(version_info, file_info, file_path)
metadata.preview_url = find_preview_file(local_stem, os.path.dirname(file_path))
metadata.preview_url = find_preview_file(local_stem, get_preview_dir(file_path))
await MetadataManager.save_metadata(file_path, metadata)
logger.info(f"Created metadata from .civitai.info for {file_path} (Reason: .civitai.info was found but .metadata.json was missing)")
except Exception as e:
@@ -2326,38 +2458,51 @@ class ModelScanner:
# Move all associated files with the same base name
source_metadata = None
moved_metadata_path = None
# Find all files with the same base name in the source directory
# Associated files (sidecar metadata, previews) sit next to the
# model in alongside mode and in the mirror tree in centralized
# mode; collect from every directory that holds them.
source_sidecar_dir = get_sidecar_dir(source_path)
target_sidecar_dir = get_sidecar_dir(target_file)
associated_dirs = [(source_dir, target_path)]
if os.path.normpath(source_sidecar_dir) != os.path.normpath(source_dir):
associated_dirs.append((source_sidecar_dir, target_sidecar_dir))
# Find all files with the same base name in the source directories
files_to_move = []
try:
for file in os.listdir(source_dir):
if file.startswith(base_name + ".") and file != os.path.basename(source_path):
source_file_path = os.path.join(source_dir, file)
# Generate new filename with the same base name as the model file
file_suffix = file[len(base_name):] # Get the part after base_name (e.g., ".metadata.json", ".preview.png")
new_associated_filename = f"{final_base_name}{file_suffix}"
target_associated_path = os.path.join(target_path, new_associated_filename)
# Store metadata file path for special handling
if file == f"{base_name}.metadata.json":
source_metadata = source_file_path
moved_metadata_path = target_associated_path
else:
files_to_move.append((source_file_path, target_associated_path))
except Exception as e:
logger.error(f"Error listing files in {source_dir}: {e}")
metadata_filename = os.path.basename(get_metadata_path(source_path))
for assoc_source_dir, assoc_target_dir in associated_dirs:
try:
for file in os.listdir(assoc_source_dir):
if file.startswith(base_name + ".") and file != os.path.basename(source_path):
source_file_path = os.path.join(assoc_source_dir, file)
# Generate new filename with the same base name as the model file
file_suffix = file[len(base_name):] # Get the part after base_name (e.g., ".metadata.json", ".preview.png")
new_associated_filename = f"{final_base_name}{file_suffix}"
target_associated_path = os.path.join(assoc_target_dir, new_associated_filename)
# Store metadata file path for special handling
if file == metadata_filename:
source_metadata = source_file_path
moved_metadata_path = target_associated_path
else:
files_to_move.append((source_file_path, target_associated_path))
except Exception as e:
logger.error(f"Error listing files in {assoc_source_dir}: {e}")
# Move all associated files
metadata = None
for source_file, target_file_path in files_to_move:
try:
os.makedirs(os.path.dirname(target_file_path), exist_ok=True)
shutil.move(source_file, target_file_path)
except Exception as e:
logger.error(f"Error moving associated file {source_file}: {e}")
# Handle metadata file specially to update paths
if source_metadata and moved_metadata_path and os.path.exists(source_metadata):
try:
os.makedirs(os.path.dirname(moved_metadata_path), exist_ok=True)
shutil.move(source_metadata, moved_metadata_path)
metadata = await self._update_metadata_paths(moved_metadata_path, target_file)
except Exception as e:
@@ -2399,7 +2544,7 @@ class ModelScanner:
metadata['file_name'] = os.path.splitext(os.path.basename(model_path))[0]
if 'preview_url' in metadata and metadata['preview_url']:
preview_dir = os.path.dirname(model_path)
preview_dir = get_preview_dir(model_path)
# Update preview filename to match the new base name
new_base_name = os.path.splitext(os.path.basename(model_path))[0]
preview_ext = get_preview_extension(metadata['preview_url'])
@@ -2759,7 +2904,7 @@ class ModelScanner:
# 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"
metadata_path = get_metadata_path(file_path)
if os.path.exists(metadata_path):
with open(metadata_path, 'r', encoding='utf-8') as handle:
payload = json.load(handle)
@@ -2825,7 +2970,7 @@ class ModelScanner:
if not file_path:
return None
dir_path = os.path.dirname(file_path)
dir_path = get_preview_dir(file_path)
base_name = os.path.splitext(os.path.basename(file_path))[0]
preview_path = find_preview_file(base_name, dir_path)
if preview_path:
+7 -2
View File
@@ -12,6 +12,7 @@ from typing import Any, Dict, List, Optional
from ..utils.models import OtherModelMetadata
from ..utils.file_utils import find_preview_file, normalize_path, calculate_autov3
from ..utils.metadata_manager import MetadataManager
from ..utils.sidecar_paths import get_preview_dir, is_centralized
from ..config import config
from .model_scanner import ModelScanner, _is_excluded_dir
from .model_hash_index import ModelHashIndex
@@ -72,10 +73,9 @@ class OtherScanner(ModelScanner):
return None
base_name = os.path.splitext(os.path.basename(file_path))[0]
dir_path = os.path.dirname(file_path)
# Find preview image
preview_url = find_preview_file(base_name, dir_path)
preview_url = find_preview_file(base_name, get_preview_dir(file_path))
# AutoV3 reads only the safetensors header, so it is cheap even for
# large files; record the checked state at creation time ("" =
@@ -333,6 +333,11 @@ class OtherScanner(ModelScanner):
async def _find_pending_models_from_filesystem(self) -> List[Dict[str, Any]]:
"""Scan filesystem for other-model metadata files with pending hash status."""
# Centralized mode stores sidecars in the mirror tree, not next to the
# models; walk the mirror instead of the model folders.
if is_centralized():
return self._find_pending_models_in_sidecar_mirror()
pending_models = []
for root_path in self.get_model_roots():
+25 -9
View File
@@ -38,6 +38,7 @@ from typing import (
)
from ..utils.constants import PREVIEW_EXTENSIONS
from ..utils.sidecar_paths import get_metadata_path, get_sidecar_dir
from ..utils import settings_paths
logger = logging.getLogger(__name__)
@@ -669,13 +670,22 @@ class PendingDeleteService:
"""Enumerate existing artifacts exactly like delete_model_artifacts."""
main_extension = ".safetensors" if main_extension is None else main_extension
main_file = f"{file_name}{main_extension}" if main_extension else file_name
patterns = [main_file, f"{file_name}.metadata.json"]
model_path = os.path.join(target_dir, main_file)
artifacts: List[str] = []
main_path = os.path.abspath(model_path)
if os.path.exists(main_path):
artifacts.append(main_path)
# Sidecars/previews live in the sidecar dir (the model's own dir in
# alongside mode, the centralized mirror otherwise).
sidecar_dir = get_sidecar_dir(model_path)
patterns = [os.path.basename(get_metadata_path(model_path))]
for ext in PREVIEW_EXTENSIONS:
patterns.append(f"{file_name}{ext}")
artifacts: List[str] = []
for pattern in patterns:
path = os.path.abspath(os.path.join(target_dir, pattern))
path = os.path.abspath(os.path.join(sidecar_dir, pattern))
if os.path.exists(path):
artifacts.append(path)
return artifacts
@@ -694,7 +704,9 @@ class PendingDeleteService:
"""
for original_path in artifacts:
staged_path = os.path.join(batch_dir, os.path.basename(original_path))
os.rename(original_path, staged_path)
# EXDEV-tolerant: centralized sidecars may live on a different
# filesystem than the staging batch dir under the model root.
self._restore_file(original_path, staged_path)
staged_pairs.append(
{
"staged": os.path.abspath(staged_path),
@@ -736,13 +748,14 @@ class PendingDeleteService:
return staged_pairs
def _restore_file(self, staged_path: str, original_path: str) -> None:
"""Restore a staged file to its original path, tolerating EXDEV.
"""Move a file between staging and library paths, tolerating EXDEV.
``os.rename`` is atomic and preferred (model staging and most recipe
restores are same-volume). Recipe staging copies into the settings-dir
staging parent, which may live on a DIFFERENT filesystem than the
recipes dir; rename then raises EXDEV. Fall back to ``shutil.copy2`` +
``os.remove`` so the bytes are restored and the staged copy removed.
staging parent, and centralized sidecars live under the configured
sidecar root; both may live on a DIFFERENT filesystem than the target
dir, so rename can raise EXDEV. Fall back to ``shutil.copy2`` +
``os.remove`` so the bytes are moved and the source copy removed.
"""
try:
os.rename(staged_path, original_path)
@@ -764,7 +777,10 @@ class PendingDeleteService:
if not os.path.exists(staged_path):
continue
try:
os.rename(staged_path, original_path)
# EXDEV-tolerant: centralized sidecars may have been copied
# across filesystems into staging, so plain os.rename would
# fail here and strand the only copy.
self._restore_file(staged_path, original_path)
except OSError as exc: # pragma: no cover - best-effort rollback
logger.warning(
"Failed to roll back staged file %s -> %s: %s",
+9 -2
View File
@@ -10,6 +10,7 @@ from urllib.parse import urlparse
from ..utils.constants import CARD_PREVIEW_WIDTH, PREVIEW_EXTENSIONS
from ..utils.civitai_utils import rewrite_preview_url
from ..utils.preview_selection import resolve_mature_threshold, select_preview_media
from ..utils.sidecar_paths import get_metadata_path, get_preview_dir
from .settings_manager import get_settings_manager
logger = logging.getLogger(__name__)
@@ -63,6 +64,9 @@ class PreviewAssetService:
base_name = os.path.splitext(os.path.splitext(os.path.basename(metadata_path))[0])[0]
preview_dir = os.path.dirname(metadata_path)
# Centralized mirrors may not exist yet (unlike the model's own
# directory in alongside mode).
os.makedirs(preview_dir, exist_ok=True)
is_video = first_preview.get("type") == "video"
preview_url = first_preview.get("url")
@@ -159,7 +163,10 @@ class PreviewAssetService:
"""Replace an existing preview asset for a model."""
base_name = os.path.splitext(os.path.basename(model_path))[0]
folder = os.path.dirname(model_path)
folder = get_preview_dir(model_path)
# Centralized mirrors may not exist yet (unlike the model's own
# directory in alongside mode).
os.makedirs(folder, exist_ok=True)
extension, optimized_data = await self._convert_preview(
preview_data, content_type, original_filename
@@ -179,7 +186,7 @@ class PreviewAssetService:
with open(preview_path, "wb") as handle:
handle.write(optimized_data)
metadata_path = os.path.splitext(model_path)[0] + ".metadata.json"
metadata_path = get_metadata_path(model_path)
metadata = await metadata_loader(metadata_path)
metadata["preview_url"] = preview_path
metadata["preview_nsfw_level"] = nsfw_level
+30 -1
View File
@@ -99,6 +99,8 @@ DEFAULT_SETTINGS: Dict[str, Any] = {
"enable_other_models": False,
"enabled_other_sub_types": list(DEFAULT_ENABLED_OTHER_SUB_TYPES),
"recipes_path": "",
"sidecar_storage_mode": "alongside",
"sidecar_storage_path": "",
"base_model_path_mappings": {},
"download_path_templates": {},
"download_filename_templates": {},
@@ -1616,9 +1618,30 @@ class SettingsManager:
return os.path.abspath(os.path.normpath(os.path.expanduser(stripped)))
@staticmethod
def _normalize_sidecar_storage_mode(value: Any) -> str:
"""Return a valid sidecar storage mode, falling back to ``alongside``."""
if isinstance(value, str):
normalized = value.strip().lower()
if normalized in ("alongside", "centralized"):
return normalized
return "alongside"
def _refresh_sidecar_storage_config(self) -> None:
"""Rebuild dependent config state after sidecar storage settings change."""
try:
from ..config import config # Local import to avoid circular dependency
config.refresh_preview_roots()
except Exception as exc: # pragma: no cover - defensive logging
logger.debug(
"Failed to refresh config after sidecar storage change: %s", exc
)
def _get_effective_recipes_dir(self, recipes_path: Optional[str] = None) -> str:
"""Resolve the effective recipes directory for the active library."""
normalized_custom = self._normalize_recipes_path_value(
self.settings.get("recipes_path", "")
if recipes_path is None
@@ -1815,6 +1838,10 @@ class SettingsManager:
target_recipes_dir = self._get_effective_recipes_dir(value)
self._validate_recipes_storage_path(target_recipes_dir)
self._migrate_recipes_directory(current_recipes_dir, target_recipes_dir)
elif key == "sidecar_storage_mode":
value = self._normalize_sidecar_storage_mode(value)
elif key == "sidecar_storage_path":
value = self._normalize_recipes_path_value(value)
self.settings[key] = value
portable_switch_pending = False
if key == "use_portable_settings" and isinstance(value, bool):
@@ -1845,6 +1872,8 @@ class SettingsManager:
self._save_settings()
if key == "recipes_path":
self._notify_library_change(self.get_active_library_name())
if key in ("sidecar_storage_mode", "sidecar_storage_path"):
self._refresh_sidecar_storage_config()
if key in ("enable_other_models", "enabled_other_sub_types"):
self._apply_other_model_settings_change()
if portable_switch_pending:
+2 -4
View File
@@ -2,10 +2,9 @@
from __future__ import annotations
import os
from typing import Awaitable, Callable, Dict, List, Sequence, Tuple
from ..utils.sidecar_paths import get_metadata_path
from .auto_tag_service import extract_auto_tags
@@ -24,8 +23,7 @@ class TagUpdateService:
update_cache: Callable[[str, str, Dict[str, object]], Awaitable[bool]],
) -> Tuple[List[str], List[str]]:
"""Add tags to a metadata entry and return updated tags and auto_tags."""
base, _ = os.path.splitext(file_path)
metadata_path = f"{base}.metadata.json"
metadata_path = get_metadata_path(file_path)
metadata = await metadata_loader(metadata_path)
raw_tags = metadata.get("tags", [])
+6
View File
@@ -21,6 +21,10 @@ from .example_images import (
ImportExampleImagesValidationError,
)
from .filename_template_use_case import FilenameTemplateUseCase
from .sidecar_migration_use_case import (
SidecarMigrationProgressReporter,
SidecarMigrationUseCase,
)
__all__ = [
"AutoOrganizeInProgressError",
@@ -36,4 +40,6 @@ __all__ = [
"ImportExampleImagesUseCase",
"ImportExampleImagesValidationError",
"FilenameTemplateUseCase",
"SidecarMigrationProgressReporter",
"SidecarMigrationUseCase",
]
@@ -12,6 +12,7 @@ import os
from typing import Any, Awaitable, Callable, Dict, List, Optional, Sequence
from ...utils.constants import AUTO_ORGANIZE_BATCH_SIZE
from ...utils.sidecar_paths import get_metadata_path
from ...utils.utils import calculate_filename_for_model
from ..model_file_service import AutoOrganizeResult, ProgressCallback
from ..model_lifecycle_service import ModelLifecycleService, load_local_metadata
@@ -200,7 +201,7 @@ class FilenameTemplateUseCase:
sidecar or no ``original_file_name`` entry exists (models never
renamed, or renamed before the recording shipped).
"""
metadata_path = f"{os.path.splitext(file_path)[0]}.metadata.json"
metadata_path = get_metadata_path(file_path)
metadata = await self._metadata_loader(metadata_path)
original = metadata.get("original_file_name")
if not isinstance(original, str):
@@ -0,0 +1,685 @@
"""Use case migrating sidecar metadata and previews between storage layouts.
Two storage layouts exist (see :mod:`py.utils.sidecar_paths`):
- ``alongside``: ``<model_dir>/<name>.metadata.json`` and preview files live
next to the model file.
- ``centralized``: the same files live under the configured sidecar root,
mirroring the library-relative directory structure.
This use case moves the ``.metadata.json`` sidecar and preview files for every
known model from one layout to the other. Model files themselves NEVER move.
Paths inside the moved sidecar (``file_path``, ``file_name``, ``preview_url``)
are rewritten the same way :meth:`ModelScanner._update_metadata_paths` does.
After the move, scanner caches are reconciled so the list API immediately
serves the new preview locations instead of stale pre-migration URLs.
Intended flow (settings-first):
1. The user switches ``sidecar_storage_mode`` (and optionally
``sidecar_storage_path``) in settings.
2. The migration runs in the direction of the NEW mode with ``force=True``.
After the switch, files in the OLD layout are the source of truth; the
guard below would otherwise refuse to run because the active mode already
matches the migration target.
Both orderings work because all path computations are mode-independent: the
alongside location is derived from the model path directly, and the mirror
location is resolved via ``get_configured_sidecar_root()``, which ignores the
active mode.
Guards (pass ``force=True`` to bypass):
- ``migrate_to_centralized`` refuses when centralized storage is already the
active, resolvable mode.
- ``migrate_to_alongside`` refuses when the active mode is ``alongside``.
"""
from __future__ import annotations
import errno
import json
import logging
import os
import shutil
from typing import Any, Awaitable, Callable, Dict, List, Optional, Protocol, Sequence, Tuple
from ..service_registry import ServiceRegistry
from ..settings_manager import get_settings_manager
from ...utils.constants import PREVIEW_EXTENSIONS
from ...utils.file_utils import find_preview_file, get_preview_extension
from ...utils.metadata_manager import MetadataManager
from ...utils.sidecar_paths import (
METADATA_SUFFIX,
STORAGE_MODE_CENTRALIZED,
get_configured_sidecar_root,
get_sidecar_root,
get_storage_mode,
resolve_centralized_dir_for_dir,
)
class SidecarMigrationProgressReporter(Protocol):
"""Protocol for progress reporters used during sidecar migration."""
async def on_progress(self, payload: Dict[str, Any]) -> None:
"""Handle a sidecar migration progress update."""
ScannerFactory = Callable[[], Awaitable[Any]]
DIRECTION_TO_CENTRALIZED = "to_centralized"
DIRECTION_TO_ALONGSIDE = "to_alongside"
DIRECTION_RELOCATE_ROOT = "relocate_root"
# Same candidate set find_preview_file recognizes: every PREVIEW_EXTENSIONS
# suffix plus the legacy ".example.0.jpeg" (issue #225).
_PREVIEW_CANDIDATE_EXTENSIONS = tuple(PREVIEW_EXTENSIONS) + (".example.0.jpeg",)
def _enumerate_preview_names(directory: str, stem: str) -> List[str]:
"""Return preview filenames for ``stem`` present in ``directory``.
Case-insensitive full-name match against the preview candidate set, so
files like ``model.WEBP`` or ``model.Png`` placed by external tools are
migrated along with the exact-case variants.
"""
targets = {f"{stem.lower()}{ext}" for ext in _PREVIEW_CANDIDATE_EXTENSIONS}
try:
entries = os.listdir(directory)
except OSError:
return []
return [entry for entry in entries if entry.lower() in targets]
class SidecarMigrationUseCase:
"""Move sidecars and previews between alongside and centralized layouts."""
def __init__(
self,
*,
scanner_factories: Sequence[Tuple[str, ScannerFactory]] | None = None,
settings_service=None,
logger: Optional[logging.Logger] = None,
) -> None:
self._settings = settings_service or get_settings_manager()
self._scanner_factories: Tuple[Tuple[str, ScannerFactory], ...] = tuple(
scanner_factories
or (
("lora", ServiceRegistry.get_lora_scanner),
("checkpoint", ServiceRegistry.get_checkpoint_scanner),
("embedding", ServiceRegistry.get_embedding_scanner),
("other", ServiceRegistry.get_other_scanner),
)
)
self._logger = logger or logging.getLogger(__name__)
async def migrate_to_centralized(
self,
progress_cb: Optional[SidecarMigrationProgressReporter] = None,
*,
force: bool = False,
) -> Dict[str, Any]:
"""Move sidecars/previews from alongside the models into the mirror root."""
if (
not force
and get_storage_mode() == STORAGE_MODE_CENTRALIZED
and get_sidecar_root()
):
return self._refusal(
DIRECTION_TO_CENTRALIZED,
"sidecar storage is already centralized; pass force=true to migrate anyway",
)
return await self._migrate(
direction=DIRECTION_TO_CENTRALIZED,
to_centralized=True,
progress_cb=progress_cb,
)
async def migrate_to_alongside(
self,
progress_cb: Optional[SidecarMigrationProgressReporter] = None,
*,
force: bool = False,
) -> Dict[str, Any]:
"""Move sidecars/previews from the mirror root back next to the models."""
if not force and get_storage_mode() != STORAGE_MODE_CENTRALIZED:
return self._refusal(
DIRECTION_TO_ALONGSIDE,
"sidecar storage is already alongside; pass force=true to migrate anyway",
)
return await self._migrate(
direction=DIRECTION_TO_ALONGSIDE,
to_centralized=False,
progress_cb=progress_cb,
)
async def migrate_root(
self,
old_root: str,
progress_cb: Optional[SidecarMigrationProgressReporter] = None,
*,
force: bool = False,
) -> Dict[str, Any]:
"""Relocate the whole mirror tree from a previous root to the configured one.
Used after ``sidecar_storage_path`` changes while centralized storage
is active: without it, every asset under the old root would silently
disappear from the application. Moves every file keeping the
root-relative structure, rewrites the ``preview_url`` prefix inside
moved sidecars, reconciles scanner caches, and prunes the emptied old
tree. Keep-newer conflict resolution matches :meth:`_transfer`.
"""
if not force and get_storage_mode() != STORAGE_MODE_CENTRALIZED:
return self._refusal(
DIRECTION_RELOCATE_ROOT,
"sidecar storage is not centralized; pass force=true to relocate anyway",
)
new_root = get_configured_sidecar_root()
if not new_root:
return self._refusal(
DIRECTION_RELOCATE_ROOT,
"cannot resolve the centralized sidecar root",
)
old = (
os.path.abspath(os.path.expanduser(old_root.strip()))
if isinstance(old_root, str) and old_root.strip()
else ""
)
if not old:
return self._refusal(DIRECTION_RELOCATE_ROOT, "old_root is required")
if os.path.normpath(old) == os.path.normpath(new_root):
return self._refusal(
DIRECTION_RELOCATE_ROOT,
"old_root matches the configured sidecar root",
)
files: List[Tuple[str, str]] = []
if os.path.isdir(old):
for dirpath, _dirnames, filenames in os.walk(old):
rel = os.path.relpath(dirpath, old)
target_dir = new_root if rel == os.curdir else os.path.join(new_root, rel)
for filename in filenames:
files.append(
(os.path.join(dirpath, filename), os.path.join(target_dir, filename))
)
errors: List[Dict[str, str]] = []
counters: Dict[str, Any] = {"moved": 0, "conflicts": 0}
moved_sidecars: List[str] = []
async def emit(status: str, **extra: Any) -> None:
if progress_cb is None:
return
payload: Dict[str, Any] = {
"type": "sidecar_migration_progress",
"status": status,
"direction": DIRECTION_RELOCATE_ROOT,
"total": len(files),
"processed": extra.pop("processed", 0),
"moved": counters["moved"],
"skipped": 0,
"conflicts": counters["conflicts"],
"errors": len(errors),
}
payload.update(extra)
await progress_cb.on_progress(payload)
await emit("started")
for index, (src, dst) in enumerate(files, start=1):
try:
if self._transfer(src, dst, counters) and src.endswith(METADATA_SUFFIX):
moved_sidecars.append(dst)
except Exception as exc:
self._logger.error(
"Sidecar root relocation failed for %s: %s", src, exc, exc_info=True
)
errors.append({"model": os.path.basename(src), "error": str(exc)})
await emit("processing", processed=index, current=os.path.basename(src))
old_prefix = old.replace(os.sep, "/").rstrip("/") + "/"
new_prefix = new_root.replace(os.sep, "/").rstrip("/") + "/"
for sidecar in moved_sidecars:
self._rewrite_root_prefix(sidecar, old_prefix, new_prefix)
await self._reconcile_root_prefix(old_prefix, new_prefix)
# Prune the emptied old tree, best-effort.
if os.path.isdir(old):
for dirpath, dirnames, filenames in os.walk(old, topdown=False):
if filenames:
continue
for dirname in dirnames:
try:
os.rmdir(os.path.join(dirpath, dirname))
except OSError:
pass
try:
os.rmdir(dirpath)
except OSError:
pass
await emit("completed")
return {
"success": not errors,
"direction": DIRECTION_RELOCATE_ROOT,
"models_total": len(files),
"models_processed": len(files),
"models_moved": 0,
"moved": counters["moved"],
"skipped": 0,
"conflicts": counters["conflicts"],
"errors": errors,
"error_count": len(errors),
}
def _rewrite_root_prefix(
self, sidecar_path: str, old_prefix: str, new_prefix: str
) -> None:
"""Repoint preview_url inside a relocated sidecar from old to new root."""
try:
with open(sidecar_path, "r", encoding="utf-8") as handle:
metadata = json.load(handle)
except (OSError, json.JSONDecodeError) as exc:
self._logger.warning(
"Sidecar root relocation: cannot read %s: %s", sidecar_path, exc
)
return
preview_url = metadata.get("preview_url")
if not isinstance(preview_url, str) or not preview_url.startswith(old_prefix):
return
metadata["preview_url"] = new_prefix + preview_url[len(old_prefix):]
try:
with open(sidecar_path, "w", encoding="utf-8") as handle:
json.dump(metadata, handle, ensure_ascii=False, indent=2)
except OSError as exc:
self._logger.warning(
"Sidecar root relocation: cannot rewrite %s: %s", sidecar_path, exc
)
async def _reconcile_root_prefix(self, old_prefix: str, new_prefix: str) -> None:
"""Rewrite old-root preview URLs in every scanner cache after relocation."""
for model_type, factory in self._active_scanner_factories():
try:
scanner = await factory()
cache = await scanner.get_cached_data()
changed = False
for item in cache.raw_data:
preview_url = item.get("preview_url")
if (
isinstance(preview_url, str)
and preview_url.startswith(old_prefix)
):
item["preview_url"] = new_prefix + preview_url[len(old_prefix):]
changed = True
if changed and hasattr(scanner, "_persist_current_cache"):
await scanner._persist_current_cache()
except Exception as exc:
self._logger.error(
"Sidecar root relocation: failed to reconcile %s cache: %s",
model_type,
exc,
exc_info=True,
)
@staticmethod
def _refusal(direction: str, message: str) -> Dict[str, Any]:
return {
"success": False,
"error": message,
"direction": direction,
"models_total": 0,
"models_processed": 0,
"models_moved": 0,
"moved": 0,
"skipped": 0,
"conflicts": 0,
"errors": [],
"error_count": 0,
}
def _active_scanner_factories(self) -> Tuple[Tuple[str, ScannerFactory], ...]:
"""Drop the opt-in other scanner while Other Models is disabled."""
if self._settings.is_other_models_enabled():
return self._scanner_factories
return tuple(entry for entry in self._scanner_factories if entry[0] != "other")
async def _collect_model_paths(
self, errors: List[Dict[str, str]]
) -> List[Tuple[Any, List[str]]]:
"""Enumerate model file paths grouped by the scanner that owns them."""
groups: List[Tuple[Any, List[str]]] = []
for model_type, factory in self._active_scanner_factories():
try:
scanner = await factory()
cache = await scanner.get_cached_data()
except Exception as exc:
self._logger.error(
"Sidecar migration: failed to enumerate %s models: %s",
model_type,
exc,
)
errors.append({"model": model_type, "error": f"enumeration failed: {exc}"})
continue
paths = [
entry["file_path"]
for entry in cache.raw_data
if entry.get("file_path")
]
groups.append((scanner, paths))
return groups
@staticmethod
def _move_file(src: str, dst: str) -> None:
"""Move a file, tolerating EXDEV when the layouts span filesystems."""
os.makedirs(os.path.dirname(dst), exist_ok=True)
try:
os.rename(src, dst)
except OSError as exc:
if exc.errno != errno.EXDEV:
raise
shutil.copy2(src, dst)
os.remove(src)
async def _migrate(
self,
*,
direction: str,
to_centralized: bool,
progress_cb: Optional[SidecarMigrationProgressReporter],
) -> Dict[str, Any]:
root = get_configured_sidecar_root()
if not root:
return self._refusal(
direction,
"cannot resolve the centralized sidecar root",
)
errors: List[Dict[str, str]] = []
scanner_groups = await self._collect_model_paths(errors)
total = sum(len(paths) for _, paths in scanner_groups)
processed = 0
models_moved = 0
moved = 0
skipped = 0
conflicts = 0
# (file_path, final preview path at the destination layout), grouped
# by scanner so caches can be reconciled after the move.
preview_updates: List[Tuple[Any, List[Tuple[str, str]]]] = []
async def emit(status: str, **extra: Any) -> None:
if progress_cb is None:
return
payload: Dict[str, Any] = {
"type": "sidecar_migration_progress",
"status": status,
"direction": direction,
"total": total,
"processed": processed,
"moved": moved,
"skipped": skipped,
"conflicts": conflicts,
"errors": len(errors),
}
payload.update(extra)
await progress_cb.on_progress(payload)
await emit("started")
for scanner, model_paths in scanner_groups:
updates: List[Tuple[str, str]] = []
for model_path in model_paths:
processed += 1
current = os.path.basename(model_path)
try:
result = await self._migrate_model(
model_path,
root=root,
to_centralized=to_centralized,
)
moved += result["moved"]
conflicts += result["conflicts"]
if result["skipped"]:
skipped += 1
else:
updates.append((model_path, result["preview_url"]))
if result["moved"]:
models_moved += 1
except Exception as exc:
self._logger.error(
"Sidecar migration failed for %s: %s", model_path, exc, exc_info=True
)
errors.append({"model": current, "error": str(exc)})
await emit("processing", current=current)
preview_updates.append((scanner, updates))
await self._reconcile_scanner_caches(preview_updates)
await emit("completed")
return {
"success": not errors,
"direction": direction,
"models_total": total,
"models_processed": processed,
"models_moved": models_moved,
"moved": moved,
"skipped": skipped,
"conflicts": conflicts,
"errors": errors,
"error_count": len(errors),
}
async def _migrate_model(
self,
model_path: str,
*,
root: str,
to_centralized: bool,
) -> Dict[str, Any]:
"""Migrate one model's sidecar + previews; return per-model counters.
``preview_url`` in the result is the model's final preview path in the
destination layout ("" when none), used to reconcile scanner caches.
"""
result: Dict[str, Any] = {"moved": 0, "conflicts": 0, "skipped": 0, "preview_url": ""}
model_path = os.path.abspath(model_path)
if not os.path.exists(model_path):
self._logger.warning(
"Sidecar migration: model file missing, skipping: %s", model_path
)
result["skipped"] = 1
return result
model_dir = os.path.dirname(model_path)
mirror_dir = resolve_centralized_dir_for_dir(model_dir, sidecar_root=root)
if mirror_dir is None:
self._logger.warning(
"Sidecar migration: %s is outside configured model roots, skipping",
model_path,
)
result["skipped"] = 1
return result
if to_centralized:
src_dir, dst_dir = model_dir, mirror_dir
else:
src_dir, dst_dir = mirror_dir, model_dir
if os.path.normpath(src_dir) == os.path.normpath(dst_dir):
result["skipped"] = 1
return result
stem = os.path.splitext(os.path.basename(model_path))[0]
sidecar_name = stem + METADATA_SUFFIX
moved_previews: List[str] = []
for preview_name in _enumerate_preview_names(src_dir, stem):
src = os.path.join(src_dir, preview_name)
dst = os.path.join(dst_dir, preview_name)
if self._transfer(src, dst, result):
moved_previews.append(dst)
sidecar_src = os.path.join(src_dir, sidecar_name)
sidecar_moved = False
sidecar_dst = os.path.join(dst_dir, sidecar_name)
if os.path.exists(sidecar_src):
sidecar_moved = self._transfer(sidecar_src, sidecar_dst, result)
if sidecar_moved:
await self._rewrite_sidecar_paths(sidecar_dst, model_path, moved_previews)
# Ground truth from the destination directory: covers conflict-keep
# and partial moves, not just the previews transferred in this run.
final_preview = find_preview_file(stem, dst_dir)
if final_preview:
result["preview_url"] = final_preview.replace(os.sep, "/")
return result
async def _reconcile_scanner_caches(
self, preview_updates: List[Tuple[Any, List[Tuple[str, str]]]]
) -> None:
"""Point scanner cache entries at the post-migration preview locations.
Without this the list API keeps serving pre-migration ``preview_url``
values whose files no longer exist; hitting one triggers the preview
route's stale-URL cleanup, which would wipe the reference for good.
A failing scanner is logged and skipped — the on-disk migration has
already succeeded, and a full rescan repairs the cache.
"""
for scanner, updates in preview_updates:
if not updates:
continue
try:
cache = await scanner.get_cached_data()
changed = False
for file_path, preview_url in updates:
entry = next(
(item for item in cache.raw_data if item.get("file_path") == file_path),
None,
)
if entry is None:
continue
if entry.get("preview_url", "") == preview_url:
continue
if hasattr(cache, "update_preview_url"):
await cache.update_preview_url(
file_path,
preview_url,
entry.get("preview_nsfw_level", 0),
)
else: # pragma: no cover - minimal cache doubles
entry["preview_url"] = preview_url
changed = True
if changed and hasattr(scanner, "_persist_current_cache"):
await scanner._persist_current_cache()
except Exception as exc:
self._logger.error(
"Sidecar migration: failed to reconcile scanner cache: %s",
exc,
exc_info=True,
)
def _transfer(self, src: str, dst: str, result: Dict[str, Any]) -> bool:
"""Move ``src`` to ``dst`` with keep-newer conflict resolution.
Returns True when the file was actually moved to the destination. On a
conflict the newer file wins: a newer source replaces the destination;
a newer (or equal) destination is kept and the source is deleted.
"""
if os.path.exists(dst):
result["conflicts"] += 1
if os.path.getmtime(src) > os.path.getmtime(dst):
self._logger.info(
"Sidecar migration: conflict at %s; source is newer, replacing", dst
)
os.remove(dst)
else:
self._logger.info(
"Sidecar migration: conflict at %s; destination is newer, keeping it",
dst,
)
os.remove(src)
return False
self._move_file(src, dst)
result["moved"] += 1
return True
async def _rewrite_sidecar_paths(
self,
sidecar_path: str,
model_path: str,
moved_previews: List[str],
) -> None:
"""Update path fields inside a moved sidecar, mirroring ModelScanner."""
with open(sidecar_path, "r", encoding="utf-8") as handle:
metadata = json.load(handle)
stem = os.path.splitext(os.path.basename(model_path))[0]
metadata["file_path"] = model_path.replace(os.sep, "/")
metadata["file_name"] = stem
if moved_previews and metadata.get("preview_url"):
recorded_ext = get_preview_extension(metadata["preview_url"])
chosen = next(
(
path
for path in moved_previews
if get_preview_extension(path) == recorded_ext
),
moved_previews[0],
)
metadata["preview_url"] = chosen.replace(os.sep, "/")
await MetadataManager.save_metadata(sidecar_path, metadata)
async def execute_with_error_handling(
self,
*,
direction: str,
progress_cb: Optional[SidecarMigrationProgressReporter] = None,
force: bool = False,
old_root: Optional[str] = None,
) -> Dict[str, Any]:
"""Wrapper providing progress notification on unexpected failures."""
try:
if direction == DIRECTION_TO_CENTRALIZED:
return await self.migrate_to_centralized(progress_cb, force=force)
if direction == DIRECTION_TO_ALONGSIDE:
return await self.migrate_to_alongside(progress_cb, force=force)
if direction == DIRECTION_RELOCATE_ROOT:
return await self.migrate_root(old_root or "", progress_cb, force=force)
raise ValueError(
f"direction must be {DIRECTION_TO_CENTRALIZED!r}, "
f"{DIRECTION_TO_ALONGSIDE!r} or {DIRECTION_RELOCATE_ROOT!r}"
)
except Exception as exc:
if progress_cb is not None:
await progress_cb.on_progress(
{
"type": "sidecar_migration_progress",
"status": "error",
"direction": direction,
"error": str(exc),
}
)
raise