OpenAI Responses - image support and multi-turn tool calling

Signed-off-by: Ben Browning <bbrownin@redhat.com>

llama_stack/templates/remote-vllm/build.yaml

@@ -24,6 +24,8 @@ distribution_spec:
     - inline::braintrust
     telemetry:
     - inline::meta-reference
+    openai_responses:
+    - inline::openai-responses
     tool_runtime:
     - remote::brave-search
     - remote::tavily-search
@@ -31,6 +33,4 @@ distribution_spec:
     - inline::rag-runtime
     - remote::model-context-protocol
     - remote::wolfram-alpha
-    openai_responses:
-    - inline::openai-responses
 image_type: conda

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -92,6 +92,14 @@ providers:
       service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
+  openai_responses:
+  - provider_id: openai-responses
+    provider_type: inline::openai-responses
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/openai_responses.db
   tool_runtime:
   - provider_id: brave-search
     provider_type: remote::brave-search
@@ -116,14 +124,6 @@ providers:
     provider_type: remote::wolfram-alpha
     config:
       api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
-  openai_responses:
-  - provider_id: openai-responses
-    provider_type: inline::openai-responses
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/openai_responses.db
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db

llama_stack/templates/remote-vllm/run.yaml

@@ -85,6 +85,14 @@ providers:
       service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
+  openai_responses:
+  - provider_id: openai-responses
+    provider_type: inline::openai-responses
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/openai_responses.db
   tool_runtime:
   - provider_id: brave-search
     provider_type: remote::brave-search
@@ -109,14 +117,6 @@ providers:
     provider_type: remote::wolfram-alpha
     config:
       api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
-  openai_responses:
-  - provider_id: openai-responses
-    provider_type: inline::openai-responses
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/openai_responses.db
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db

llama_stack/templates/remote-vllm/vllm.py

@@ -31,6 +31,7 @@ def get_distribution_template() -> DistributionTemplate:
         "datasetio": ["remote::huggingface", "inline::localfs"],
         "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
         "telemetry": ["inline::meta-reference"],
+        "openai_responses": ["inline::openai-responses"],
         "tool_runtime": [
             "remote::brave-search",
             "remote::tavily-search",
@@ -39,7 +40,6 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::model-context-protocol",
             "remote::wolfram-alpha",
         ],
-        "openai_responses": ["inline::openai-responses"],
     }
     name = "remote-vllm"
     inference_provider = Provider(