Updates to server.py to clean up streaming vs non-streaming stuff

Also make sure agent turn create is correctly marked

llama_stack/providers/datatypes.py

@@ -41,6 +41,9 @@ class ProviderSpec(BaseModel):
         description="Higher-level API surfaces may depend on other providers to provide their functionality",
     )
 
+    # used internally by the resolver; this is a hack for now
+    deps__: List[str] = Field(default_factory=list)
+
 
 class RoutingTable(Protocol):
     def get_provider_impl(self, routing_key: str) -> Any: ...

llama_stack/providers/impls/meta_reference/agents/agent_instance.py

@@ -144,6 +144,8 @@ class ChatAgent(ShieldRunnerMixin):
     async def create_and_execute_turn(
         self, request: AgentTurnCreateRequest
     ) -> AsyncGenerator:
+        assert request.stream is True, "Non-streaming not supported"
+
         session_info = await self.storage.get_session_info(request.session_id)
         if session_info is None:
             raise ValueError(f"Session {request.session_id} not found")
@@ -635,14 +637,13 @@ class ChatAgent(ShieldRunnerMixin):
             raise ValueError(f"Session {session_id} not found")
 
         if session_info.memory_bank_id is None:
-            memory_bank = await self.memory_api.create_memory_bank(
-                name=f"memory_bank_{session_id}",
-                config=VectorMemoryBankConfig(
-                    embedding_model="all-MiniLM-L6-v2",
-                    chunk_size_in_tokens=512,
-                ),
+            bank_id = f"memory_bank_{session_id}"
+            memory_bank = VectorMemoryBankDef(
+                identifier=bank_id,
+                embedding_model="all-MiniLM-L6-v2",
+                chunk_size_in_tokens=512,
             )
-            bank_id = memory_bank.bank_id
+            await self.memory_api.register_memory_bank(memory_bank)
             await self.storage.add_memory_bank_to_session(session_id, bank_id)
         else:
             bank_id = session_info.memory_bank_id

llama_stack/providers/impls/meta_reference/agents/agents.py

@@ -100,7 +100,7 @@ class MetaReferenceAgentsImpl(Agents):
             session_id=session_id,
         )
 
-    async def create_agent_turn(
+    def create_agent_turn(
         self,
         agent_id: str,
         session_id: str,
@@ -113,16 +113,22 @@ class MetaReferenceAgentsImpl(Agents):
         attachments: Optional[List[Attachment]] = None,
         stream: Optional[bool] = False,
     ) -> AsyncGenerator:
-        agent = await self.get_agent(agent_id)
-
-        # wrapper request to make it easier to pass around (internal only, not exposed to API)
         request = AgentTurnCreateRequest(
             agent_id=agent_id,
             session_id=session_id,
             messages=messages,
             attachments=attachments,
-            stream=stream,
+            stream=True,
         )
+        if stream:
+            return self._create_agent_turn_streaming(request)
+        else:
+            raise NotImplementedError("Non-streaming agent turns not yet implemented")
 
+    async def _create_agent_turn_streaming(
+        self,
+        request: AgentTurnCreateRequest,
+    ) -> AsyncGenerator:
+        agent = await self.get_agent(request.agent_id)
         async for event in agent.create_and_execute_turn(request):
             yield event

llama_stack/providers/tests/agents/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.