feat(ccip): matcher reads the incremental prototype store (#1317, m138 step 4)

match_image now sources character references from character_prototype via a
per-character in-process cache (_load_prototypes) that reloads ONLY the
characters whose ccip_prototype_state.updated_at advanced — no request-path
rebuild, so the per-accept ~4s stall is gone once the store is populated. Cold
start (store empty pre-first-refresh) falls back to the legacy on-the-fly
reference build, so character suggestions work immediately post-deploy and the
background refresh populates the store within ~15 min. Match math + grounding
are unchanged; existing tests exercise the legacy fallback, and a new test
covers matching from the populated prototype store.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM

tests/test_ccip.py

@@ -3,7 +3,13 @@ model needed, so it runs in CI with synthetic CCIP vectors."""
 import pytest
 from sqlalchemy import select
 
-from backend.app.models import ImageRecord, ImageRegion, TagKind
+from backend.app.models import (
+    CcipPrototypeState,
+    CharacterPrototype,
+    ImageRecord,
+    ImageRegion,
+    TagKind,
+)
 from backend.app.models.tag import image_tag
 from backend.app.services.ml.ccip import match_image
 from backend.app.services.tag_service import TagService
@@ -61,6 +67,24 @@ async def test_matches_same_character_across_images(db):
     assert m["grounding"]["kind"] == "figure"
 
 
+@pytest.mark.asyncio
+async def test_matches_from_prototype_store(db):
+    # Once the prototype store is populated (#1317), match_image reads it (the
+    # fast incremental path) instead of rebuilding references on the request —
+    # same match + grounding as the legacy build.
+    raven = await TagService(db).find_or_create("Raven", TagKind.character)
+    db.add(CharacterPrototype(tag_id=raven.id, ccip_embedding=_ccip(0)))
+    db.add(CcipPrototypeState(tag_id=raven.id, fingerprint="1:1"))
+    query = await _img(db, "n" * 64)
+    await _figure(db, query.id, _ccip(0))       # query figure matches the prototype
+    await db.commit()
+
+    matches = await match_image(db, query.id)
+    m = next(x for x in matches if x["tag_id"] == raven.id)
+    assert m["source"] == "ccip" and m["score"] > 0.9
+    assert m["grounding"]["kind"] == "figure"
+
+
 @pytest.mark.asyncio
 async def test_no_match_for_different_character(db):
     raven = await TagService(db).find_or_create("Raven", TagKind.character)