Responses API: Finish wiring up function tool calls

This finishes the plumbing for function tool call and adds a basic
verification test (that passes for me locally against Llama 4 Scout in
vllm).

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

docs/_static/llama-stack-spec.yaml

@@ -4833,11 +4833,40 @@ components:
       oneOf:
         - $ref: '#/components/schemas/OpenAIResponseMessage'
         - $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
+        - $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
       discriminator:
         propertyName: type
         mapping:
           message: '#/components/schemas/OpenAIResponseMessage'
           web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
+          function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
+    "OpenAIResponseOutputMessageFunctionToolCall":
+      type: object
+      properties:
+        arguments:
+          type: string
+        call_id:
+          type: string
+        name:
+          type: string
+        type:
+          type: string
+          const: function_call
+          default: function_call
+        id:
+          type: string
+        status:
+          type: string
+      additionalProperties: false
+      required:
+        - arguments
+        - call_id
+        - name
+        - type
+        - id
+        - status
+      title: >-
+        OpenAIResponseOutputMessageFunctionToolCall
     OpenAIResponseObjectStream:
       oneOf:
         - $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated'