Merge branch 'main' into add-mcp-authentication-param

tests/integration/inference/test_openai_completion.py

@@ -54,6 +54,7 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
         # {"error":{"message":"Unknown request URL: GET /openai/v1/completions. Please check the URL for typos,
         # or see the docs at https://console.groq.com/docs/","type":"invalid_request_error","code":"unknown_url"}}
         "remote::groq",
+        "remote::oci",
         "remote::gemini",  # https://generativelanguage.googleapis.com/v1beta/openai/completions -> 404
         "remote::anthropic",  # at least claude-3-{5,7}-{haiku,sonnet}-* / claude-{sonnet,opus}-4-* are not supported
         "remote::azure",  # {'error': {'code': 'OperationNotSupported', 'message': 'The completion operation

tests/integration/inference/test_openai_embeddings.py

@@ -138,6 +138,7 @@ def skip_if_model_doesnt_support_openai_embeddings(client, model_id):
         "remote::runpod",
         "remote::sambanova",
         "remote::tgi",
+        "remote::oci",
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI embeddings.")
 

tests/integration/vector_io/test_openai_vector_stores.py

@@ -907,16 +907,16 @@ def test_openai_vector_store_retrieve_file_contents(
     )
 
     assert file_contents is not None
-    assert len(file_contents.content) == 1
-    content = file_contents.content[0]
+    assert file_contents.object == "vector_store.file_content.page"
+    assert len(file_contents.data) == 1
+    content = file_contents.data[0]
 
     # llama-stack-client returns a model, openai-python is a badboy and returns a dict
     if not isinstance(content, dict):
         content = content.model_dump()
     assert content["type"] == "text"
     assert content["text"] == test_content.decode("utf-8")
-    assert file_contents.filename == file_name
-    assert file_contents.attributes == attributes
+    assert file_contents.has_more is False
 
 
 @vector_provider_wrapper
@@ -1483,14 +1483,12 @@ def test_openai_vector_store_file_batch_retrieve_contents(
         )
 
         assert file_contents is not None
-        assert file_contents.filename == file_data[i][0]
-        assert len(file_contents.content) > 0
+        assert file_contents.object == "vector_store.file_content.page"
+        assert len(file_contents.data) > 0
 
         # Verify the content matches what we uploaded
         content_text = (
-            file_contents.content[0].text
-            if hasattr(file_contents.content[0], "text")
-            else file_contents.content[0]["text"]
+            file_contents.data[0].text if hasattr(file_contents.data[0], "text") else file_contents.data[0]["text"]
         )
         assert file_data[i][1].decode("utf-8") in content_text
 

tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py

@@ -92,6 +92,99 @@ async def test_persistence_across_adapter_restarts(vector_io_adapter):
     await vector_io_adapter.shutdown()
 
 
+async def test_vector_store_lazy_loading_from_kvstore(vector_io_adapter):
+    """
+    Test that vector stores can be lazy-loaded from KV store when not in cache.
+
+    Verifies that clearing the cache doesn't break vector store access - they
+    can be loaded on-demand from persistent storage.
+    """
+    await vector_io_adapter.initialize()
+
+    vector_store_id = f"lazy_load_test_{np.random.randint(1e6)}"
+    vector_store = VectorStore(
+        identifier=vector_store_id,
+        provider_id="test_provider",
+        embedding_model="test_model",
+        embedding_dimension=128,
+    )
+    await vector_io_adapter.register_vector_store(vector_store)
+    assert vector_store_id in vector_io_adapter.cache
+
+    vector_io_adapter.cache.clear()
+    assert vector_store_id not in vector_io_adapter.cache
+
+    loaded_index = await vector_io_adapter._get_and_cache_vector_store_index(vector_store_id)
+    assert loaded_index is not None
+    assert loaded_index.vector_store.identifier == vector_store_id
+    assert vector_store_id in vector_io_adapter.cache
+
+    cached_index = await vector_io_adapter._get_and_cache_vector_store_index(vector_store_id)
+    assert cached_index is loaded_index
+
+    await vector_io_adapter.shutdown()
+
+
+async def test_vector_store_preloading_on_initialization(vector_io_adapter):
+    """
+    Test that vector stores are preloaded from KV store during initialization.
+
+    Verifies that after restart, all vector stores are automatically loaded into
+    cache and immediately accessible without requiring lazy loading.
+    """
+    await vector_io_adapter.initialize()
+
+    vector_store_ids = [f"preload_test_{i}_{np.random.randint(1e6)}" for i in range(3)]
+    for vs_id in vector_store_ids:
+        vector_store = VectorStore(
+            identifier=vs_id,
+            provider_id="test_provider",
+            embedding_model="test_model",
+            embedding_dimension=128,
+        )
+        await vector_io_adapter.register_vector_store(vector_store)
+
+    for vs_id in vector_store_ids:
+        assert vs_id in vector_io_adapter.cache
+
+    await vector_io_adapter.shutdown()
+    await vector_io_adapter.initialize()
+
+    for vs_id in vector_store_ids:
+        assert vs_id in vector_io_adapter.cache
+
+    for vs_id in vector_store_ids:
+        loaded_index = await vector_io_adapter._get_and_cache_vector_store_index(vs_id)
+        assert loaded_index is not None
+        assert loaded_index.vector_store.identifier == vs_id
+
+    await vector_io_adapter.shutdown()
+
+
+async def test_kvstore_none_raises_runtime_error(vector_io_adapter):
+    """
+    Test that accessing vector stores with uninitialized kvstore raises RuntimeError.
+
+    Verifies proper RuntimeError is raised instead of assertions when kvstore is None.
+    """
+    await vector_io_adapter.initialize()
+
+    vector_store_id = f"kvstore_none_test_{np.random.randint(1e6)}"
+    vector_store = VectorStore(
+        identifier=vector_store_id,
+        provider_id="test_provider",
+        embedding_model="test_model",
+        embedding_dimension=128,
+    )
+    await vector_io_adapter.register_vector_store(vector_store)
+
+    vector_io_adapter.cache.clear()
+    vector_io_adapter.kvstore = None
+
+    with pytest.raises(RuntimeError, match="KVStore not initialized"):
+        await vector_io_adapter._get_and_cache_vector_store_index(vector_store_id)
+
+
 async def test_register_and_unregister_vector_store(vector_io_adapter):
     unique_id = f"foo_db_{np.random.randint(1e6)}"
     dummy = VectorStore(