group all server stores under storage.stores

llama_stack/distributions/ci-tests/run.yaml

@@ -220,17 +220,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models: []
 shields:
 - shield_id: llama-guard

llama_stack/distributions/dell/run-with-safety.yaml

@@ -97,17 +97,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/dell/run.yaml

@@ -93,17 +93,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml

@@ -110,17 +110,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/meta-reference-gpu/run.yaml

@@ -100,17 +100,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/nvidia/run-with-safety.yaml

@@ -99,17 +99,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/nvidia/run.yaml

@@ -88,17 +88,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models: []
 shields: []
 vector_dbs: []

llama_stack/distributions/open-benchmark/run.yaml

@@ -130,17 +130,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: gpt-4o

llama_stack/distributions/postgres-demo/run.yaml

@@ -75,17 +75,18 @@ storage:
       db: ${env.POSTGRES_DB:=llamastack}
       user: ${env.POSTGRES_USER:=llamastack}
       password: ${env.POSTGRES_PASSWORD:=llamastack}
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/starter-gpu/run.yaml

@@ -223,17 +223,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models: []
 shields:
 - shield_id: llama-guard

llama_stack/distributions/starter/run.yaml

@@ -220,17 +220,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models: []
 shields:
 - shield_id: llama-guard

llama_stack/distributions/template.py

@@ -188,6 +188,7 @@ class RunConfigSettings(BaseModel):
     default_benchmarks: list[BenchmarkInput] | None = None
     telemetry: TelemetryConfig = Field(default_factory=lambda: TelemetryConfig(enabled=True))
     storage_backends: dict[str, Any] | None = None
+    storage_stores: dict[str, Any] | None = None
 
     def run_config(
         self,
@@ -241,19 +242,25 @@ class RunConfigSettings(BaseModel):
             ),
         }
 
-        storage_config = dict(backends=storage_backends)
-        metadata_store = KVStoreReference(
-            backend="kv_default",
-            namespace="registry",
-        ).model_dump(exclude_none=True)
-        inference_store = InferenceStoreReference(
-            backend="sql_default",
-            table_name="inference_store",
-        ).model_dump(exclude_none=True)
-        conversations_store = SqlStoreReference(
-            backend="sql_default",
-            table_name="openai_conversations",
-        ).model_dump(exclude_none=True)
+        storage_stores = self.storage_stores or {
+            "metadata": KVStoreReference(
+                backend="kv_default",
+                namespace="registry",
+            ).model_dump(exclude_none=True),
+            "inference": InferenceStoreReference(
+                backend="sql_default",
+                table_name="inference_store",
+            ).model_dump(exclude_none=True),
+            "conversations": SqlStoreReference(
+                backend="sql_default",
+                table_name="openai_conversations",
+            ).model_dump(exclude_none=True),
+        }
+
+        storage_config = dict(
+            backends=storage_backends,
+            stores=storage_stores,
+        )
 
         # Return a dict that matches StackRunConfig structure
         return {
@@ -263,9 +270,6 @@ class RunConfigSettings(BaseModel):
             "apis": apis,
             "providers": provider_configs,
             "storage": storage_config,
-            "metadata_store": metadata_store,
-            "inference_store": inference_store,
-            "conversations_store": conversations_store,
             "models": [m.model_dump(exclude_none=True) for m in (self.default_models or [])],
             "shields": [s.model_dump(exclude_none=True) for s in (self.default_shields or [])],
             "vector_dbs": [],

llama_stack/distributions/watsonx/run.yaml

@@ -103,17 +103,18 @@ storage:
     sql_default:
       type: sql_sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/sql_store.db
-metadata_store:
-  namespace: registry
-  backend: kv_default
-inference_store:
-  table_name: inference_store
-  backend: sql_default
-  max_write_queue_size: 10000
-  num_writers: 4
-conversations_store:
-  table_name: openai_conversations
-  backend: sql_default
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
 models: []
 shields: []
 vector_dbs: []