feat(assets): align local API with cloud spec (#12863)

* feat(assets): align local API with cloud spec

Unify response models, add missing fields, and align input schemas with
the cloud OpenAPI spec at cloud.comfy.org/openapi.

- Replace AssetSummary/AssetDetail/AssetUpdated with single Asset model
- Add is_immutable, metadata (system_metadata), prompt_id fields
- Support mime_type and preview_id in update endpoint
- Make CreateFromHashBody.name optional, add mime_type, require >=1 tag
- Add id/mime_type/preview_id to upload, relax tags to optional
- Rename total_tags → tags in tag add/remove responses
- Add GET /api/assets/tags/refine histogram endpoint
- Add DB migration for system_metadata and prompt_id columns

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Fix review issues: tags validation, size nullability, type annotation, hash mismatch check, and add tag histogram tests

- Remove contradictory min_length=1 from CreateFromHashBody.tags default
- Restore size field to int|None=None for proper null semantics
- Add Union type annotation to _build_asset_response result param
- Add hash mismatch validation on idempotent upload path (409 HASH_MISMATCH)
- Add unit tests for list_tag_histogram service function

Amp-Thread-ID: https://ampcode.com/threads/T-019cd993-f43c-704e-b3d7-6cfc3d4d4a80
Co-authored-by: Amp <amp@ampcode.com>

* Add preview_url to /assets API response using /api/view endpoint

For input and output assets, generate a preview_url pointing to the
existing /api/view endpoint using the asset's filename and tag-derived
type (input/output). Handles subdirectories via subfolder param and
URL-encodes filenames with spaces, unicode, and special characters.

This aligns the OSS backend response with the frontend AssetCard
expectation for thumbnail rendering.

Amp-Thread-ID: https://ampcode.com/threads/T-019cda3f-5c2c-751a-a906-ac6c9153ac5c
Co-authored-by: Amp <amp@ampcode.com>

* chore: remove unused imports from asset_reference queries

Amp-Thread-ID: https://ampcode.com/threads/T-019cda7d-cb21-77b4-a51b-b965af60208c
Co-authored-by: Amp <amp@ampcode.com>

* feat: resolve blake3 hashes in /view endpoint via asset database

Amp-Thread-ID: https://ampcode.com/threads/T-019cda7d-cb21-77b4-a51b-b965af60208c
Co-authored-by: Amp <amp@ampcode.com>

* Register uploaded images in asset database when --enable-assets is set

Add register_file_in_place() service function to ingest module for
registering already-saved files without moving them. Call it from the
/upload/image endpoint to return asset metadata in the response.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce023-3384-7560-bacf-de40b0de0dd2
Co-authored-by: Amp <amp@ampcode.com>

* Exclude None fields from asset API JSON responses

Add exclude_none=True to model_dump() calls across asset routes to
keep response payloads clean by omitting unset optional fields.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce023-3384-7560-bacf-de40b0de0dd2
Co-authored-by: Amp <amp@ampcode.com>

* Add comment explaining why /view resolves blake3 hashes

Amp-Thread-ID: https://ampcode.com/threads/T-019ce023-3384-7560-bacf-de40b0de0dd2
Co-authored-by: Amp <amp@ampcode.com>

* Move blake3 hash resolution to asset_management service

Extract resolve_hash_to_path() into asset_management.py and remove
_resolve_blake3_to_path from server.py. Also revert loopback origin
check to original logic.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce023-3384-7560-bacf-de40b0de0dd2
Co-authored-by: Amp <amp@ampcode.com>

* Require at least one tag in UploadAssetSpec

Enforce non-empty tags at the Pydantic validation layer so uploads
with no tags are rejected with a 400 before reaching ingest. Adds
test_upload_empty_tags_rejected to cover this case.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce377-8bde-7048-bc28-a9df063409f9
Co-authored-by: Amp <amp@ampcode.com>

* Add owner_id check to resolve_hash_to_path

Filter asset references by owner visibility so the /view endpoint
only resolves hashes for assets the requesting user can access.
Adds table-driven tests for owner visibility cases.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce377-8bde-7048-bc28-a9df063409f9
Co-authored-by: Amp <amp@ampcode.com>

* Make ReferenceData.created_at and updated_at required

Remove None defaults and type: ignore comments. Move fields before
optional fields to satisfy dataclass ordering.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce377-8bde-7048-bc28-a9df063409f9
Co-authored-by: Amp <amp@ampcode.com>

* Fix double commit in create_from_hash

Move mime_type update into _register_existing_asset so it shares a
single transaction with reference creation. Log a warning when the
hash is not found instead of silently returning None.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce377-8bde-7048-bc28-a9df063409f9
Co-authored-by: Amp <amp@ampcode.com>

* Add exclude_none=True to create/upload responses

Align with get/update/list endpoints for consistent JSON output.

Amp-Thread-ID: https://ampcode.com/threads/T-019ce377-8bde-7048-bc28-a9df063409f9
Co-authored-by: Amp <amp@ampcode.com>

* Change preview_id to reference asset by reference ID, not content ID

Clients receive preview_id in API responses but could not dereference it
through public routes (which use reference IDs). Now preview_id is a
self-referential FK to asset_references.id so the value is directly
usable in the public API.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Filter soft-deleted and missing refs from visibility queries

list_references_by_asset_id and list_tags_with_usage were not filtering
out deleted_at/is_missing refs, allowing /view?filename=blake3:... to
serve files through hidden references and inflating tag usage counts.
Add list_all_file_paths_by_asset_id for orphan cleanup which
intentionally needs unfiltered access.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Pass preview_id and mime_type through all asset creation fast paths

The duplicate-content upload path and hash-based creation paths were
silently dropping preview_id and mime_type. This wires both fields
through _register_existing_asset, create_from_hash, and all route
call sites so behavior is consistent regardless of whether the asset
content already exists.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Remove unimplemented client-provided ID from upload API

The `id` field on UploadAssetSpec was advertised for idempotent creation
but never actually honored when creating new references. Remove it
rather than implementing the feature.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Make asset mime_type immutable after first ingest

Prevents cross-tenant metadata mutation when multiple references share
the same content-addressed Asset row. mime_type can now only be set when
NULL (first ingest); subsequent attempts to change it are silently ignored.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Use resolved content_type from asset lookup in /view endpoint

The /view endpoint was discarding the content_type computed by
resolve_hash_to_path() and re-guessing from the filename, which
produced wrong results for extensionless files or mismatched extensions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Merge system+user metadata into filter projection

Extract rebuild_metadata_projection() to build AssetReferenceMeta rows
from {**system_metadata, **user_metadata}, so system-generated metadata
is queryable via metadata_filter and user keys override system keys.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Standardize tag ordering to alphabetical across all endpoints

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Derive subfolder tags from path in register_file_in_place

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Reject client-provided id, fix preview URLs, rename tags→total_tags

- Reject 'id' field in multipart upload with 400 UNSUPPORTED_FIELD
  instead of silently ignoring it
- Build preview URL from the preview asset's own metadata rather than
  the parent asset's
- Rename 'tags' to 'total_tags' in TagsAdd/TagsRemove response schemas
  for clarity

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: SQLite migration 0003 FK drop fails on file-backed DBs (MB-2)

Add naming_convention to Base.metadata so Alembic batch-mode reflection
can match unnamed FK constraints created by migration 0002. Pass
naming_convention and render_as_batch=True through env.py online config.

Add migration roundtrip tests (upgrade/downgrade/cycle from baseline).

Amp-Thread-ID: https://ampcode.com/threads/T-019ce466-1683-7471-b6e1-bb078223cda0
Co-authored-by: Amp <amp@ampcode.com>

* Fix missing tag count for is_missing references and update test for total_tags field

- Allow is_missing=True references to be counted in list_tags_with_usage
  when the tag is 'missing', so the missing tag count reflects all
  references that have been tagged as missing
- Add update_is_missing_by_asset_id query helper for bulk updates by asset
- Update test_add_and_remove_tags to use 'total_tags' matching the API schema

Amp-Thread-ID: https://ampcode.com/threads/T-019ce482-05e7-7324-a1b0-a56a929cc7ef
Co-authored-by: Amp <amp@ampcode.com>

* Remove unused imports in scanner.py

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Rename prompt_id to job_id on asset_references

Rename the column in the DB model, migration, and service schemas.
The API response emits both job_id and prompt_id (deprecated alias)
for backward compatibility with the cloud API.

Amp-Thread-ID: https://ampcode.com/threads/T-019cef41-60b0-752a-aa3c-ed7f20fda2f7
Co-authored-by: Amp <amp@ampcode.com>

* Add index on asset_references.preview_id for FK cascade performance

Amp-Thread-ID: https://ampcode.com/threads/T-019cef45-a4d2-7548-86d2-d46bcd3db419
Co-authored-by: Amp <amp@ampcode.com>

* Add clarifying comments for Asset/AssetReference naming and preview_id

Amp-Thread-ID: https://ampcode.com/threads/T-019cef49-f94e-7348-bf23-9a19ebf65e0d
Co-authored-by: Amp <amp@ampcode.com>

* Disallow all-null meta rows: add CHECK constraint, skip null values on write

- convert_metadata_to_rows returns [] for None values instead of an all-null row
- Remove dead None branch from _scalar_to_row
- Simplify null filter in common.py to just check for row absence
- Add CHECK constraint ck_asset_reference_meta_has_value to model and migration 0003

Amp-Thread-ID: https://ampcode.com/threads/T-019cef4e-5240-7749-bb25-1f17fcf9c09c
Co-authored-by: Amp <amp@ampcode.com>

* Remove dead None guards on result.asset in upload handler

register_file_in_place guarantees a non-None asset, so the
'if result.asset else None' checks were unreachable.

Amp-Thread-ID: https://ampcode.com/threads/T-019cef5b-4cf8-723c-8a98-8fb8f333c133
Co-authored-by: Amp <amp@ampcode.com>

* Remove mime_type from asset update API

Clients can no longer modify mime_type after asset creation via the
PUT /api/assets/{id} endpoint. This reduces the risk of mime_type
spoofing. The internal update_asset_hash_and_mime function remains
available for server-side use (e.g., enrichment).

Amp-Thread-ID: https://ampcode.com/threads/T-019cef5d-8d61-75cc-a1c6-2841ac395648
Co-authored-by: Amp <amp@ampcode.com>

* Fix migration constraint naming double-prefix and NULL in mixed metadata lists

- Use fully-rendered constraint names in migration 0003 to avoid the
  naming convention doubling the ck_ prefix on batch operations.
- Add table_args to downgrade so SQLite batch mode can find the CHECK
  constraint (not exposed by SQLite reflection).
- Fix model CheckConstraint name to use bare 'has_value' (convention
  auto-prefixes).
- Skip None items when converting metadata lists to rows, preventing
  all-NULL rows that violate the has_value check constraint.

Amp-Thread-ID: https://ampcode.com/threads/T-019cef87-94f9-7172-a6af-c6282290ce4f
Co-authored-by: Amp <amp@ampcode.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Amp <amp@ampcode.com>
This commit is contained in:
Luke Mino-Altherr
2026-03-16 15:34:04 -04:00
committed by GitHub
parent 593be209a4
commit 2bd4d82b4f
27 changed files with 1218 additions and 330 deletions

View File

@ -0,0 +1,57 @@
"""Test that Alembic migrations run cleanly on a file-backed SQLite DB.
This catches problems like unnamed FK constraints that prevent batch-mode
drop_constraint from working on real SQLite files (see MB-2).
Migrations 0001 and 0002 are already shipped, so we only exercise
upgrade/downgrade for 0003+.
"""
import os
import pytest
from alembic import command
from alembic.config import Config
# Oldest shipped revision — we upgrade to here as a baseline and never
# downgrade past it.
_BASELINE = "0002_merge_to_asset_references"
def _make_config(db_path: str) -> Config:
root = os.path.join(os.path.dirname(__file__), "../..")
config_path = os.path.abspath(os.path.join(root, "alembic.ini"))
scripts_path = os.path.abspath(os.path.join(root, "alembic_db"))
cfg = Config(config_path)
cfg.set_main_option("script_location", scripts_path)
cfg.set_main_option("sqlalchemy.url", f"sqlite:///{db_path}")
return cfg
@pytest.fixture
def migration_db(tmp_path):
"""Yield an alembic Config pre-upgraded to the baseline revision."""
db_path = str(tmp_path / "test_migration.db")
cfg = _make_config(db_path)
command.upgrade(cfg, _BASELINE)
yield cfg
def test_upgrade_to_head(migration_db):
"""Upgrade from baseline to head must succeed on a file-backed DB."""
command.upgrade(migration_db, "head")
def test_downgrade_to_baseline(migration_db):
"""Upgrade to head then downgrade back to baseline."""
command.upgrade(migration_db, "head")
command.downgrade(migration_db, _BASELINE)
def test_upgrade_downgrade_cycle(migration_db):
"""Full cycle: upgrade → downgrade → upgrade again."""
command.upgrade(migration_db, "head")
command.downgrade(migration_db, _BASELINE)
command.upgrade(migration_db, "head")

View File

@ -10,6 +10,7 @@ from app.assets.database.queries import (
get_asset_by_hash,
upsert_asset,
bulk_insert_assets,
update_asset_hash_and_mime,
)
@ -142,3 +143,45 @@ class TestBulkInsertAssets:
session.commit()
assert session.query(Asset).count() == 200
class TestMimeTypeImmutability:
"""mime_type on Asset is write-once: set on first ingest, never overwritten."""
@pytest.mark.parametrize(
"initial_mime,second_mime,expected_mime",
[
("image/png", "image/jpeg", "image/png"),
(None, "image/png", "image/png"),
],
ids=["preserves_existing", "fills_null"],
)
def test_upsert_mime_immutability(self, session: Session, initial_mime, second_mime, expected_mime):
h = f"blake3:upsert_{initial_mime}_{second_mime}"
upsert_asset(session, asset_hash=h, size_bytes=100, mime_type=initial_mime)
session.commit()
asset, created, _ = upsert_asset(session, asset_hash=h, size_bytes=100, mime_type=second_mime)
assert created is False
assert asset.mime_type == expected_mime
@pytest.mark.parametrize(
"initial_mime,update_mime,update_hash,expected_mime,expected_hash",
[
(None, "image/png", None, "image/png", "blake3:upd0"),
("image/png", "image/jpeg", None, "image/png", "blake3:upd1"),
("image/png", "image/jpeg", "blake3:upd2_new", "image/png", "blake3:upd2_new"),
],
ids=["fills_null", "preserves_existing", "hash_updates_mime_locked"],
)
def test_update_asset_hash_and_mime_immutability(
self, session: Session, initial_mime, update_mime, update_hash, expected_mime, expected_hash,
):
h = expected_hash.removesuffix("_new")
asset = Asset(hash=h, size_bytes=100, mime_type=initial_mime)
session.add(asset)
session.flush()
update_asset_hash_and_mime(session, asset_id=asset.id, mime_type=update_mime, asset_hash=update_hash)
assert asset.mime_type == expected_mime
assert asset.hash == expected_hash

View File

@ -242,22 +242,24 @@ class TestSetReferencePreview:
asset = _make_asset(session, "hash1")
preview_asset = _make_asset(session, "preview_hash")
ref = _make_reference(session, asset)
preview_ref = _make_reference(session, preview_asset, name="preview.png")
session.commit()
set_reference_preview(session, reference_id=ref.id, preview_asset_id=preview_asset.id)
set_reference_preview(session, reference_id=ref.id, preview_reference_id=preview_ref.id)
session.commit()
session.refresh(ref)
assert ref.preview_id == preview_asset.id
assert ref.preview_id == preview_ref.id
def test_clears_preview(self, session: Session):
asset = _make_asset(session, "hash1")
preview_asset = _make_asset(session, "preview_hash")
ref = _make_reference(session, asset)
ref.preview_id = preview_asset.id
preview_ref = _make_reference(session, preview_asset, name="preview.png")
ref.preview_id = preview_ref.id
session.commit()
set_reference_preview(session, reference_id=ref.id, preview_asset_id=None)
set_reference_preview(session, reference_id=ref.id, preview_reference_id=None)
session.commit()
session.refresh(ref)
@ -265,15 +267,15 @@ class TestSetReferencePreview:
def test_raises_for_nonexistent_reference(self, session: Session):
with pytest.raises(ValueError, match="not found"):
set_reference_preview(session, reference_id="nonexistent", preview_asset_id=None)
set_reference_preview(session, reference_id="nonexistent", preview_reference_id=None)
def test_raises_for_nonexistent_preview(self, session: Session):
asset = _make_asset(session, "hash1")
ref = _make_reference(session, asset)
session.commit()
with pytest.raises(ValueError, match="Preview Asset"):
set_reference_preview(session, reference_id=ref.id, preview_asset_id="nonexistent")
with pytest.raises(ValueError, match="Preview AssetReference"):
set_reference_preview(session, reference_id=ref.id, preview_reference_id="nonexistent")
class TestInsertReference:
@ -351,13 +353,14 @@ class TestUpdateReferenceTimestamps:
asset = _make_asset(session, "hash1")
preview_asset = _make_asset(session, "preview_hash")
ref = _make_reference(session, asset)
preview_ref = _make_reference(session, preview_asset, name="preview.png")
session.commit()
update_reference_timestamps(session, ref, preview_id=preview_asset.id)
update_reference_timestamps(session, ref, preview_id=preview_ref.id)
session.commit()
session.refresh(ref)
assert ref.preview_id == preview_asset.id
assert ref.preview_id == preview_ref.id
class TestSetReferenceMetadata:

View File

@ -20,6 +20,7 @@ def _make_reference(
asset: Asset,
name: str,
metadata: dict | None = None,
system_metadata: dict | None = None,
) -> AssetReference:
now = get_utc_now()
ref = AssetReference(
@ -27,6 +28,7 @@ def _make_reference(
name=name,
asset_id=asset.id,
user_metadata=metadata,
system_metadata=system_metadata,
created_at=now,
updated_at=now,
last_access_time=now,
@ -34,8 +36,10 @@ def _make_reference(
session.add(ref)
session.flush()
if metadata:
for key, val in metadata.items():
# Build merged projection: {**system_metadata, **user_metadata}
merged = {**(system_metadata or {}), **(metadata or {})}
if merged:
for key, val in merged.items():
for row in convert_metadata_to_rows(key, val):
meta_row = AssetReferenceMeta(
asset_reference_id=ref.id,
@ -182,3 +186,46 @@ class TestMetadataFilterEmptyDict:
refs, _, total = list_references_page(session, metadata_filter={})
assert total == 2
class TestSystemMetadataProjection:
"""Tests for system_metadata merging into the filter projection."""
def test_system_metadata_keys_are_filterable(self, session: Session):
"""system_metadata keys should appear in the merged projection."""
asset = _make_asset(session, "hash1")
_make_reference(
session, asset, "with_sys",
system_metadata={"source": "scanner"},
)
_make_reference(session, asset, "without_sys")
session.commit()
refs, _, total = list_references_page(
session, metadata_filter={"source": "scanner"}
)
assert total == 1
assert refs[0].name == "with_sys"
def test_user_metadata_overrides_system_metadata(self, session: Session):
"""user_metadata should win when both have the same key."""
asset = _make_asset(session, "hash1")
_make_reference(
session, asset, "overridden",
metadata={"origin": "user_upload"},
system_metadata={"origin": "auto_scan"},
)
session.commit()
# Should match the user value, not the system value
refs, _, total = list_references_page(
session, metadata_filter={"origin": "user_upload"}
)
assert total == 1
assert refs[0].name == "overridden"
# Should NOT match the system value (it was overridden)
refs, _, total = list_references_page(
session, metadata_filter={"origin": "auto_scan"}
)
assert total == 0

View File

@ -11,6 +11,7 @@ from app.assets.services import (
delete_asset_reference,
set_asset_preview,
)
from app.assets.services.asset_management import resolve_hash_to_path
def _make_asset(session: Session, hash_val: str = "blake3:test", size: int = 1024) -> Asset:
@ -219,31 +220,33 @@ class TestSetAssetPreview:
asset = _make_asset(session, hash_val="blake3:main")
preview_asset = _make_asset(session, hash_val="blake3:preview")
ref = _make_reference(session, asset)
preview_ref = _make_reference(session, preview_asset, name="preview.png")
ref_id = ref.id
preview_id = preview_asset.id
preview_ref_id = preview_ref.id
session.commit()
set_asset_preview(
reference_id=ref_id,
preview_asset_id=preview_id,
preview_reference_id=preview_ref_id,
)
# Verify by re-fetching from DB
session.expire_all()
updated_ref = session.get(AssetReference, ref_id)
assert updated_ref.preview_id == preview_id
assert updated_ref.preview_id == preview_ref_id
def test_clears_preview(self, mock_create_session, session: Session):
asset = _make_asset(session)
preview_asset = _make_asset(session, hash_val="blake3:preview")
ref = _make_reference(session, asset)
ref.preview_id = preview_asset.id
preview_ref = _make_reference(session, preview_asset, name="preview.png")
ref.preview_id = preview_ref.id
ref_id = ref.id
session.commit()
set_asset_preview(
reference_id=ref_id,
preview_asset_id=None,
preview_reference_id=None,
)
# Verify by re-fetching from DB
@ -263,6 +266,45 @@ class TestSetAssetPreview:
with pytest.raises(PermissionError, match="not owner"):
set_asset_preview(
reference_id=ref.id,
preview_asset_id=None,
preview_reference_id=None,
owner_id="user2",
)
class TestResolveHashToPath:
def test_returns_none_for_unknown_hash(self, mock_create_session):
result = resolve_hash_to_path("blake3:" + "a" * 64)
assert result is None
@pytest.mark.parametrize(
"ref_owner, query_owner, expect_found",
[
("user1", "user1", True),
("user1", "user2", False),
("", "anyone", True),
("", "", True),
],
ids=[
"owner_sees_own_ref",
"other_owner_blocked",
"ownerless_visible_to_anyone",
"ownerless_visible_to_empty",
],
)
def test_owner_visibility(
self, ref_owner, query_owner, expect_found,
mock_create_session, session: Session, temp_dir,
):
f = temp_dir / "file.bin"
f.write_bytes(b"data")
asset = _make_asset(session, hash_val="blake3:" + "b" * 64)
ref = _make_reference(session, asset, name="file.bin", owner_id=ref_owner)
ref.file_path = str(f)
session.commit()
result = resolve_hash_to_path(asset.hash, owner_id=query_owner)
if expect_found:
assert result is not None
assert result.abs_path == str(f)
else:
assert result is None

View File

@ -113,11 +113,19 @@ class TestIngestFileFromPath:
file_path = temp_dir / "with_preview.bin"
file_path.write_bytes(b"data")
# Create a preview asset first
# Create a preview asset and reference
preview_asset = Asset(hash="blake3:preview", size_bytes=100)
session.add(preview_asset)
session.flush()
from app.assets.helpers import get_utc_now
now = get_utc_now()
preview_ref = AssetReference(
asset_id=preview_asset.id, name="preview.png", owner_id="",
created_at=now, updated_at=now, last_access_time=now,
)
session.add(preview_ref)
session.commit()
preview_id = preview_asset.id
preview_id = preview_ref.id
result = _ingest_file_from_path(
abs_path=str(file_path),

View File

@ -0,0 +1,123 @@
"""Tests for list_tag_histogram service function."""
from sqlalchemy.orm import Session
from app.assets.database.models import Asset, AssetReference
from app.assets.database.queries import ensure_tags_exist, add_tags_to_reference
from app.assets.helpers import get_utc_now
from app.assets.services.tagging import list_tag_histogram
def _make_asset(session: Session, hash_val: str = "blake3:test") -> Asset:
asset = Asset(hash=hash_val, size_bytes=1024)
session.add(asset)
session.flush()
return asset
def _make_reference(
session: Session,
asset: Asset,
name: str = "test",
owner_id: str = "",
) -> AssetReference:
now = get_utc_now()
ref = AssetReference(
owner_id=owner_id,
name=name,
asset_id=asset.id,
created_at=now,
updated_at=now,
last_access_time=now,
)
session.add(ref)
session.flush()
return ref
class TestListTagHistogram:
def test_returns_counts_for_all_tags(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["alpha", "beta"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="r1")
add_tags_to_reference(session, reference_id=r1.id, tags=["alpha", "beta"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="r2")
add_tags_to_reference(session, reference_id=r2.id, tags=["alpha"])
session.commit()
result = list_tag_histogram()
assert result["alpha"] == 2
assert result["beta"] == 1
def test_empty_when_no_assets(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["unused"])
session.commit()
result = list_tag_histogram()
assert result == {}
def test_include_tags_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["models", "loras", "input"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="r1")
add_tags_to_reference(session, reference_id=r1.id, tags=["models", "loras"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="r2")
add_tags_to_reference(session, reference_id=r2.id, tags=["input"])
session.commit()
result = list_tag_histogram(include_tags=["models"])
# Only r1 has "models", so only its tags appear
assert "models" in result
assert "loras" in result
assert "input" not in result
def test_exclude_tags_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["models", "loras", "input"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="r1")
add_tags_to_reference(session, reference_id=r1.id, tags=["models", "loras"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="r2")
add_tags_to_reference(session, reference_id=r2.id, tags=["input"])
session.commit()
result = list_tag_histogram(exclude_tags=["models"])
# r1 excluded, only r2's tags remain
assert "input" in result
assert "loras" not in result
def test_name_contains_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["alpha", "beta"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="my_model.safetensors")
add_tags_to_reference(session, reference_id=r1.id, tags=["alpha"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="picture.png")
add_tags_to_reference(session, reference_id=r2.id, tags=["beta"])
session.commit()
result = list_tag_histogram(name_contains="model")
assert "alpha" in result
assert "beta" not in result
def test_limit_caps_results(self, mock_create_session, session: Session):
tags = [f"tag{i}" for i in range(10)]
ensure_tags_exist(session, tags)
a = _make_asset(session, "blake3:aaa")
r = _make_reference(session, a, name="r1")
add_tags_to_reference(session, reference_id=r.id, tags=tags)
session.commit()
result = list_tag_histogram(limit=3)
assert len(result) == 3

View File

@ -243,6 +243,15 @@ def test_upload_tags_traversal_guard(http: requests.Session, api_base: str):
assert body["error"]["code"] in ("BAD_REQUEST", "INVALID_BODY")
def test_upload_empty_tags_rejected(http: requests.Session, api_base: str):
files = {"file": ("notags.bin", b"A" * 64, "application/octet-stream")}
form = {"tags": json.dumps([]), "name": "notags.bin", "user_metadata": json.dumps({})}
r = http.post(api_base + "/api/assets", data=form, files=files, timeout=120)
body = r.json()
assert r.status_code == 400
assert body["error"]["code"] == "INVALID_BODY"
@pytest.mark.parametrize("root", ["input", "output"])
def test_duplicate_upload_same_display_name_does_not_clobber(
root: str,