feat: persist isolated vector snapshots and exact retrieval

backend/tests/test_vector_runtime.py

@@ -0,0 +1,91 @@
+"""Explicit opt-in: actual pinned model -> HTTP -> PostgreSQL -> HTTP process restart."""
+
+import os
+
+import pytest
+from sqlalchemy import text
+from test_runtime import server
+
+from app.services.embedding import SMALL_ZH
+
+
+@pytest.mark.skipif(
+    os.environ.get("RUN_LOCAL_EMBEDDING_TEST") != "1",
+    reason="requires optional CPU runtime and offline pinned model cache",
+)
+def test_real_local_model_vectors_retrieval_and_http_restart(migrated_database):
+    options = {
+        "EMBEDDING_ENABLED": "true",
+        "EMBEDDING_MODEL": "small",
+        "EMBEDDING_CACHE_DIR": os.environ["EMBEDDING_CACHE_DIR"],
+        "HF_HUB_OFFLINE": "1",
+        "HF_HUB_DISABLE_TELEMETRY": "1",
+        "HF_HUB_DISABLE_IMPLICIT_TOKEN": "1",
+        "TOKENIZERS_PARALLELISM": "false",
+    }
+    query = {"query": "合成测试中交通安排应查阅哪份资料？"}
+    with server(migrated_database, environment_overrides=options) as client:
+        ids = []
+        for topic, body in [
+            ("交通", "【合成测试】占位交通资料介绍测试公交线路与班次的查询入口。"),
+            ("住宿", "【合成测试】占位住宿资料介绍测试房型与入住须知。"),
+            ("审核", "【合成测试】占位审核资料说明测试出处核验流程。"),
+        ]:
+            item = client.post(
+                "/api/knowledge",
+                json={
+                    "title": f"{topic}合成测试",
+                    "content": body,
+                    "source_url": "https://example.com/",
+                    "collected_at": "2026-10-16T00:00:00Z",
+                },
+            ).json()
+            response = client.post(
+                f"/api/knowledge/{item['id']}/review",
+                json={
+                    "expected_version": item["version"],
+                    "verification_status": "verified",
+                    "reviewer": "test-reviewer",
+                    "verification_notes": "仅为模型/HTTP/数据库持久化测试，不是事实资料",
+                },
+            )
+            assert response.status_code == 200
+            ids.append(item["id"])
+        text_ = client.post("/api/indexes", json={"chunk_size": 200, "overlap": 20}).json()
+        assert (
+            client.post(
+                f"/api/indexes/{text_['id']}/publish", json={"expected_generation": 0}
+            ).status_code
+            == 200
+        )
+        built = client.post(
+            "/api/vector-indexes", json={"text_index_version_id": text_["id"]}, timeout=60
+        )
+        assert built.status_code == 201, built.text
+        version = built.json()
+        assert version["space_id"] == SMALL_ZH.space_id and version["dimension"] == 512
+        published = client.post(
+            f"/api/vector-indexes/{version['id']}/publish", json={"expected_generation": 0}
+        )
+        assert published.status_code == 200
+        active = published.json()
+        response = client.post("/api/retrieval/vector", json=query, timeout=60)
+        assert response.status_code == 200, response.text
+        first = response.json()
+        assert {h["knowledge_id"] for h in first["results"]} == set(ids)
+        assert all(-1 <= h["score"] <= 1 for h in first["results"])
+        assert first["config"]["space"]["spec"]["revision"] == SMALL_ZH.revision
+    with migrated_database.connect() as c:
+        assert (
+            c.scalar(
+                text("SELECT count(*) FROM chunk_vectors WHERE public.vector_dims(embedding)=512")
+            )
+            == 3
+        )
+        assert c.scalar(text("SELECT count(*) FROM vector_publications")) == 1
+    with server(migrated_database, environment_overrides=options) as client:
+        assert client.get("/api/vector-indexes/active").json() == active
+        assert client.get(f"/api/retrieval/runs/{first['run_id']}").json() == first
+        response = client.post("/api/retrieval/vector", json=query, timeout=60)
+        assert response.status_code == 200, response.text
+        assert response.json()["results"] == first["results"]