feat(ingest): resolve project labels with Jev

tests/transports/test_mcp_facet_label_promotion.py

@@ -0,0 +1,149 @@
+from datetime import UTC, datetime
+
+from gewu.adapters.openrouter_jev import JevAssessment
+from gewu.adapters.sqlite_facet_labels import SQLiteFacetLabelIndex
+from gewu.domain.contracts import (
+    FacetLabelProposal,
+    IngestReviewCreate,
+    JevFacetResolution,
+    JevFacetScore,
+    Locator,
+    ProjectFacetLabel,
+)
+from gewu.transports.mcp_server import _promote_jev_labels
+
+
+class _FixedEmbeddings:
+    dimensions = 3
+    model_id = "test-embedding-model"
+    artifact_sha256 = "a" * 64
+
+    def embed_queries(self, texts: tuple[str, ...]) -> tuple[tuple[float, ...], ...]:
+        return tuple((1.0, 0.0, 0.0) for _ in texts)
+
+    def embed_passages(self, texts: tuple[str, ...]) -> tuple[tuple[float, ...], ...]:
+        return tuple((1.0, 0.0, 0.0) for _ in texts)
+
+
+class _ProjectRegistry:
+    def __init__(self) -> None:
+        self.added: list[ProjectFacetLabel] = []
+
+    def add_facet_labels(self, project_id: str, labels: tuple[ProjectFacetLabel, ...]):
+        assert project_id == "dome-performance"
+        self.added.extend(labels)
+
+
+def _review(candidate: str = "immersive sound field") -> IngestReviewCreate:
+    return IngestReviewCreate(
+        review_id="review-facet-promotion-1",
+        project_id="dome-performance",
+        run_id="run-facet-promotion-1",
+        source_revision_id="source-revision-facet-promotion-1",
+        extraction_id="b" * 64,
+        locator=Locator(kind="text_span", block_id="block-1", start=0, end=5),
+        excerpt="quote",
+        lens="technical",
+        summary="A reusable spatial-audio technique",
+        relevance_rationale="This is a direct, reusable project technique.",
+        candidate_facet_labels=(
+            FacetLabelProposal(
+                facet="tags",
+                value=candidate,
+                definition="Audio techniques that render sound in immersive spatial fields.",
+            ),
+        ),
+    )
+
+
+def _assessment(
+    value: str = "immersive sound field",
+    *,
+    fit: float = 0.97,
+    new: float = 0.96,
+    confidence: float = 0.93,
+) -> JevAssessment:
+    return JevAssessment(
+        relation_probability=0.98,
+        lens="technical",
+        lens_confidence=0.99,
+        model="typesafe/jev-test",
+        facet_scores=(JevFacetScore(facet="tags", value=value, probability=fit),),
+        facet_resolutions=(
+            JevFacetResolution(
+                facet="tags",
+                value=value,
+                fit_probability=fit,
+                selected_new_label=True,
+                new_probability=new,
+                choice_confidence=confidence,
+                rank=1,
+            ),
+        ),
+    )
+
+
+def test_high_confidence_top_rank_new_label_is_added_and_embedded(
+    tmp_path, monkeypatch
+) -> None:
+    monkeypatch.setenv("GEWU_FACET_LABEL_FIT_THRESHOLD", "0.90")
+    monkeypatch.setenv("GEWU_FACET_LABEL_NEW_THRESHOLD", "0.90")
+    monkeypatch.setenv("GEWU_FACET_LABEL_CONFIDENCE_THRESHOLD", "0.80")
+    registry = _ProjectRegistry()
+    embeddings = _FixedEmbeddings()
+    label_index = SQLiteFacetLabelIndex(tmp_path / "labels.sqlite3")
+
+    resolutions = _promote_jev_labels(
+        item=_review(),
+        assessment=_assessment(),
+        project_id="dome-performance",
+        project_registry=registry,
+        facet_label_index=label_index,
+        embedding_provider=embeddings,
+        existing_catalog=(),
+        semantic_search_ready=True,
+    )
+
+    assert len(registry.added) == 1
+    assert registry.added[0].canonical_label == "immersive sound field"
+    assert resolutions[0].rank == 1
+    assert resolutions[0].added_to_project
+    cached = label_index.closest(
+        project_id="dome-performance",
+        facet="tags",
+        query="spatial audio rendering",
+        labels=tuple(registry.added),
+        embeddings=embeddings,
+        limit=1,
+    )
+    assert cached[0].canonical_label == "immersive sound field"
+
+
+def test_matching_existing_label_is_never_promoted_as_new(
+    tmp_path, monkeypatch
+) -> None:
+    monkeypatch.setenv("GEWU_FACET_LABEL_FIT_THRESHOLD", "0.90")
+    monkeypatch.setenv("GEWU_FACET_LABEL_NEW_THRESHOLD", "0.90")
+    monkeypatch.setenv("GEWU_FACET_LABEL_CONFIDENCE_THRESHOLD", "0.80")
+    registry = _ProjectRegistry()
+    existing = ProjectFacetLabel(
+        label_id="tag-spatial-audio",
+        facet="tags",
+        canonical_label="spatial audio",
+        definition="Audio techniques for placing or rendering sound spatially.",
+        created_at=datetime(2026, 1, 1, tzinfo=UTC),
+    )
+
+    resolutions = _promote_jev_labels(
+        item=_review("spatial audio"),
+        assessment=_assessment("spatial audio"),
+        project_id="dome-performance",
+        project_registry=registry,
+        facet_label_index=SQLiteFacetLabelIndex(tmp_path / "labels.sqlite3"),
+        embedding_provider=_FixedEmbeddings(),
+        existing_catalog=(existing,),
+        semantic_search_ready=True,
+    )
+
+    assert registry.added == []
+    assert not resolutions[0].added_to_project