Fix migration workflow: upload as artifact instead of scp to practice EC2

apps/ai-service/tests/conftest.py

@@ -0,0 +1,28 @@
+"""Test-suite defaults that must be set before any test module is imported.
+
+`main.py` builds the entire runtime at module scope (`build_runtime(get_settings())`),
+and `tests/test_api.py` imports `main`. With the default `EMBEDDING_PROVIDER=cohere-v4`
+— or with a developer's `.env` selecting it — that construction opens a
+`QdrantClient` and calls `get_collections()` for the corpus-manifest check, so
+`pytest` fails during *collection* on any machine without a reachable Qdrant:
+
+    qdrant_client.http.exceptions.ResponseHandlingException:
+        [WinError 10061] No connection could be made ...
+    Interrupted: 1 error during collection
+
+No unit test needs a live datastore: every test injects its own doubles, and
+the one suite that does need real services (`test_live_datastores.py`) gates
+itself behind `RUN_INTEGRATION=1`. Forcing the disabled provider here makes
+`pytest tests -q` work out of the box instead of requiring an undocumented
+environment variable.
+
+`setdefault`, not assignment: a deliberate override (for example
+`EMBEDDING_PROVIDER=cohere-v4 pytest ...` against a local Qdrant) still wins.
+
+This runs at import time, before pytest collects any module, which is the only
+point early enough — `config.get_settings()` is `lru_cache`d, so a fixture
+would already be too late.
+"""
+import os
+
+os.environ.setdefault("EMBEDDING_PROVIDER", "disabled")

apps/ai-service/tests/test_qdrant_adapter.py

@@ -1,3 +1,5 @@
+from types import SimpleNamespace
+
 from adapters.qdrant import QdrantRetriever, _source_refs
 
 
@@ -24,6 +26,25 @@ class _FakeScrollClient:
         return [_FakePoint(p) for p in self._payloads], None
 
 
+class _FakeQueryPointsClient:
+    """Production qdrant-client shape (1.16+): no legacy `.search()`."""
+
+    def __init__(self, payloads: list[dict]) -> None:
+        self._payloads = payloads
+        self.kwargs = None
+
+    def query_points(self, **kwargs):
+        self.kwargs = kwargs
+        return SimpleNamespace(points=[_FakePoint(p) for p in self._payloads])
+
+
+class _FakeEmbedder:
+    dimensions = 3
+
+    def embed_query(self, text):  # noqa: ARG002
+        return [0.1, 0.2, 0.3]
+
+
 def _chi_dinh_payload(drug_id: str, text: str) -> dict:
     return {
         "chunk_id": f"{drug_id}__chi_dinh__0", "drug_id": drug_id,
@@ -91,6 +112,20 @@ def test_find_by_indication_matches_a_drug_that_names_the_symptom():
     assert [h.document.drug_id for h in hits] == ["paracetamol_acetaminophen"]
 
 
+def test_dense_indication_fallback_uses_modern_query_points_api():
+    client = _FakeQueryPointsClient([
+        _chi_dinh_payload("colchicin", "Điều trị đợt cấp bệnh gút."),
+    ])
+    retriever = QdrantRetriever(client, "duocthu_v1", _FakeEmbedder())
+
+    hits = retriever.search_indication("gút cấp", limit=4)
+
+    assert [hit.document.drug_id for hit in hits] == ["colchicin"]
+    assert client.kwargs["collection_name"] == "duocthu_v1"
+    assert client.kwargs["query"] == [0.1, 0.2, 0.3]
+    assert client.kwargs["limit"] == 16
+
+
 def test_find_by_indication_requires_the_whole_phrase_not_a_scattered_match():
     """"sốt xuất huyết" (dengue) must not match a chunk that only says "sốt"
     — the phrase itself has to appear, not just each of its words somewhere."""