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
This commit is contained in:
@@ -5,11 +5,18 @@ image_tag AND to tag_allowlist; per-image removal/dismiss writes a rejection.
|
||||
from collections.abc import Sequence
|
||||
from dataclasses import dataclass
|
||||
|
||||
from sqlalchemy import delete, select
|
||||
from sqlalchemy import and_, delete, distinct, func, or_, select
|
||||
from sqlalchemy.dialects.postgresql import insert
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import MLSettings, Tag, TagAllowlist, TagSuggestionRejection
|
||||
from ...models import (
|
||||
ImagePrediction,
|
||||
MLSettings,
|
||||
Tag,
|
||||
TagAlias,
|
||||
TagAllowlist,
|
||||
TagSuggestionRejection,
|
||||
)
|
||||
from ...models.tag import image_tag
|
||||
from .aliases import AliasService
|
||||
|
||||
@@ -20,6 +27,8 @@ class AllowlistRow:
|
||||
tag_name: str
|
||||
tag_kind: str
|
||||
min_confidence: float
|
||||
applied_count: int # image_tag rows currently carrying this tag
|
||||
coverage_count: int # images a sweep WOULD cover at min_confidence
|
||||
|
||||
|
||||
class AllowlistService:
|
||||
@@ -116,6 +125,44 @@ class AllowlistService:
|
||||
delete(TagAllowlist).where(TagAllowlist.tag_id == tag_id)
|
||||
)
|
||||
|
||||
async def _coverage_match(self, tag: Tag):
|
||||
"""The predicate over image_prediction rows that resolve to `tag`,
|
||||
mirroring tasks.ml._confidence_for_tag's resolution: a prediction whose
|
||||
raw_name equals the tag name (any category), OR an alias maps
|
||||
(raw_name, category) -> this tag. Returns a SQLAlchemy boolean clause.
|
||||
"""
|
||||
alias_rows = (
|
||||
await self.session.execute(
|
||||
select(TagAlias.alias_string, TagAlias.alias_category).where(
|
||||
TagAlias.canonical_tag_id == tag.id
|
||||
)
|
||||
)
|
||||
).all()
|
||||
name_clause = ImagePrediction.raw_name == tag.name
|
||||
alias_clauses = [
|
||||
and_(
|
||||
ImagePrediction.raw_name == a,
|
||||
ImagePrediction.category == c,
|
||||
)
|
||||
for a, c in alias_rows
|
||||
]
|
||||
return or_(name_clause, *alias_clauses) if alias_clauses else name_clause
|
||||
|
||||
async def coverage(self, tag_id: int, threshold: float) -> int:
|
||||
"""How many distinct images a sweep WOULD cover for this tag at
|
||||
`threshold`: images with a resolving prediction scoring >= threshold.
|
||||
The gross candidate pool (NOT minus already-applied/rejected) — it's
|
||||
the tuning signal for "lower the threshold and ~N more images qualify".
|
||||
"""
|
||||
tag = await self.session.get(Tag, tag_id)
|
||||
if tag is None:
|
||||
return 0
|
||||
match = await self._coverage_match(tag)
|
||||
stmt = select(
|
||||
func.count(distinct(ImagePrediction.image_record_id))
|
||||
).where(ImagePrediction.score >= threshold, match)
|
||||
return (await self.session.execute(stmt)).scalar_one()
|
||||
|
||||
async def list_all(self) -> Sequence[AllowlistRow]:
|
||||
stmt = (
|
||||
select(
|
||||
@@ -128,12 +175,33 @@ class AllowlistService:
|
||||
.order_by(Tag.name.asc())
|
||||
)
|
||||
rows = (await self.session.execute(stmt)).all()
|
||||
return [
|
||||
AllowlistRow(
|
||||
tag_id=r[0],
|
||||
tag_name=r[1],
|
||||
tag_kind=r[2].value if hasattr(r[2], "value") else str(r[2]),
|
||||
min_confidence=r[3],
|
||||
tag_ids = [r[0] for r in rows]
|
||||
|
||||
# Applied counts in ONE grouped query (vs N per-row counts).
|
||||
applied: dict[int, int] = {}
|
||||
if tag_ids:
|
||||
applied = dict(
|
||||
(
|
||||
await self.session.execute(
|
||||
select(image_tag.c.tag_id, func.count())
|
||||
.where(image_tag.c.tag_id.in_(tag_ids))
|
||||
.group_by(image_tag.c.tag_id)
|
||||
)
|
||||
).all()
|
||||
)
|
||||
for r in rows
|
||||
]
|
||||
|
||||
result = []
|
||||
for r in rows:
|
||||
# Coverage is per-tag (alias set differs); allowlist is small.
|
||||
cov = await self.coverage(r[0], r[3])
|
||||
result.append(
|
||||
AllowlistRow(
|
||||
tag_id=r[0],
|
||||
tag_name=r[1],
|
||||
tag_kind=r[2].value if hasattr(r[2], "value") else str(r[2]),
|
||||
min_confidence=r[3],
|
||||
applied_count=applied.get(r[0], 0),
|
||||
coverage_count=cov,
|
||||
)
|
||||
)
|
||||
return result
|
||||
|
||||
Reference in New Issue
Block a user