Files
FabledCurator/tests/test_api_suggestions.py
T
bvandeusen e206778a5c
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 21s
CI / backend-lint-and-test (push) Successful in 26s
CI / integration (push) Failing after 3m24s
feat(allowlist): coverage projection + applied-count + post-accept projection (#7a/#7b)
Cluster B, milestone #99. Backend for the allowlist tuning dashboard.

#7a: AllowlistService.coverage(tag_id, threshold) counts distinct images with
a prediction resolving to the tag (raw_name==tag.name OR (raw_name,category) in
the tag's aliases) scoring >= threshold — the gross candidate pool, mirroring
tasks.ml._confidence_for_tag resolution. list_all now carries applied_count
(grouped image_tag count) + coverage_count (at the row's threshold). New
GET /api/tags/<id>/allowlist/coverage?threshold= for the live what-if number.

#7b: /suggestions/accept + /alias return {allowlisted, tag_id, tag_name,
projected_count} (projection at the tag's threshold) instead of 204, so the UI
can show a non-blocking 'auto-applying to ~N images' toast. Apply still runs
async via apply_allowlist_tags — projected_count is an estimate.

Tests: coverage by threshold (direct + alias-with-category), list applied vs
coverage, coverage route (explicit/default/bad threshold), accept/alias payload
(newly-allowlisted vs already-on-list).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XCUHUGQLrBrkgyk1t49kpX
2026-06-23 01:34:21 -04:00

169 lines
5.6 KiB
Python

import pytest
from backend.app.celery_app import celery
from backend.app.models import ImageRecord, TagKind
from backend.app.services.tag_service import TagService
pytestmark = pytest.mark.integration
@pytest.fixture(autouse=True)
def eager():
celery.conf.task_always_eager = True
yield
celery.conf.task_always_eager = False
async def _img(db, preds, sha="s" * 64):
from tests._prediction_helpers import seed_predictions
img = ImageRecord(
path=f"/images/{sha[:8]}.jpg", sha256=sha, size_bytes=1,
mime="image/jpeg", width=1, height=1,
origin="imported_filesystem", integrity_status="unknown",
)
db.add(img)
await db.commit()
await seed_predictions(db, img.id, preds)
await db.commit()
return img
@pytest.mark.asyncio
async def test_get_suggestions(client, db):
img = await _img(
db, {"sword": {"category": "general", "confidence": 0.97}}
)
resp = await client.get(f"/api/images/{img.id}/suggestions")
assert resp.status_code == 200
body = await resp.get_json()
assert "general" in body["by_category"]
@pytest.mark.asyncio
async def test_accept_requires_tag_id(client, db):
img = await _img(db, {})
resp = await client.post(
f"/api/images/{img.id}/suggestions/accept", json={}
)
assert resp.status_code == 400
@pytest.mark.asyncio
async def test_accept_then_applied(client, db):
img = await _img(db, {})
tag = await TagService(db).find_or_create("AcceptMe", TagKind.character)
await db.commit()
resp = await client.post(
f"/api/images/{img.id}/suggestions/accept", json={"tag_id": tag.id}
)
assert resp.status_code == 200
body = await resp.get_json()
# #7b: a fresh accept newly-allowlists → projection payload for the toast.
assert body["allowlisted"] is True
assert body["tag_id"] == tag.id
assert body["tag_name"] == "AcceptMe"
assert "projected_count" in body
@pytest.mark.asyncio
async def test_accept_already_allowlisted_reports_not_new(client, db):
img1 = await _img(db, {}, sha="c" * 64)
img2 = await _img(db, {}, sha="d" * 64)
tag = await TagService(db).find_or_create("Twice", TagKind.character)
await db.commit()
first = await client.post(
f"/api/images/{img1.id}/suggestions/accept", json={"tag_id": tag.id}
)
assert (await first.get_json())["allowlisted"] is True
second = await client.post(
f"/api/images/{img2.id}/suggestions/accept", json={"tag_id": tag.id}
)
body = await second.get_json()
assert body["allowlisted"] is False # already on the allowlist
assert "projected_count" not in body
@pytest.mark.asyncio
async def test_dismiss(client, db):
img = await _img(db, {})
tag = await TagService(db).find_or_create("DismissMe", TagKind.general)
await db.commit()
resp = await client.post(
f"/api/images/{img.id}/suggestions/dismiss", json={"tag_id": tag.id}
)
assert resp.status_code == 204
@pytest.mark.asyncio
async def test_alias_requires_fields(client, db):
img = await _img(db, {})
resp = await client.post(
f"/api/images/{img.id}/suggestions/alias", json={"alias_string": "x"}
)
assert resp.status_code == 400
async def _img_at(db, path, sha, preds):
from tests._prediction_helpers import seed_predictions
img = ImageRecord(
path=path, sha256=sha, size_bytes=1, mime="image/jpeg",
width=1, height=1, origin="imported_filesystem",
integrity_status="unknown",
)
db.add(img)
await db.commit()
await seed_predictions(db, img.id, preds)
await db.commit()
return img
@pytest.mark.asyncio
async def test_alias_roundtrip_resolves_by_raw_key(client, db):
"""Locks the modal-alias contract: the suggestion exposes the RAW model key,
an alias authored with that key resolves on a later image, and the resolved
suggestion is flagged via_alias. (Pre-fix the modal stored the normalized
display name, which never resolved.)"""
canonical = await TagService(db).find_or_create(
"Sasuke Uchiha", TagKind.character
)
await db.commit()
preds = {"uchiha_sasuke": {"category": "character", "confidence": 0.99}}
img_a = await _img_at(db, "/images/alias_a.jpg", "a" * 64, preds)
# (a) raw_name is exposed so the modal can author the alias with it; the
# raw prediction doesn't textually match the tag, so it'd otherwise be +new.
body = await (
await client.get(f"/api/images/{img_a.id}/suggestions")
).get_json()
sug = body["by_category"]["character"][0]
assert sug["raw_name"] == "uchiha_sasuke"
assert sug["via_alias"] is False
assert sug["creates_new_tag"] is True
# Author the alias keyed by the RAW key (what the frontend now sends).
resp = await client.post(
f"/api/images/{img_a.id}/suggestions/alias",
json={
"alias_string": sug["raw_name"],
"alias_category": "character",
"canonical_tag_id": canonical.id,
},
)
assert resp.status_code == 200
assert (await resp.get_json())["allowlisted"] is True
# (b) A DIFFERENT image with the same prediction now resolves via the alias
# (image A's tag is applied, so it's filtered there). Had the alias been
# stored under the display name, this would NOT resolve.
img_b = await _img_at(db, "/images/alias_b.jpg", "b" * 64, preds)
body_b = await (
await client.get(f"/api/images/{img_b.id}/suggestions")
).get_json()
sug_b = body_b["by_category"]["character"][0]
assert sug_b["canonical_tag_id"] == canonical.id
assert sug_b["via_alias"] is True
assert sug_b["creates_new_tag"] is False
assert sug_b["raw_name"] == "uchiha_sasuke"