Implement the 'max_tool_calls' parameter for the Responses API

Test max_tool_calls with builtin and mcp tools

Update input prompt for more consistent tool calling

Resolve merge conflicts

Update integration test

Handle review comments

docs/static/llama-stack-spec.yaml

@@ -6166,6 +6166,11 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) Max number of total calls to built-in tools that can be processed
+            in a response
         input:
           type: array
           items:
@@ -6524,6 +6529,11 @@ components:
             (Optional) Additional fields to include in the response.
         max_infer_iters:
           type: integer
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) Max number of total calls to built-in tools that can be processed
+            in a response.
       additionalProperties: false
       required:
         - input
@@ -6605,6 +6615,11 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) Max number of total calls to built-in tools that can be processed
+            in a response
       additionalProperties: false
       required:
         - created_at

docs/static/stainless-llama-stack-spec.yaml

@@ -6882,6 +6882,11 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) Max number of total calls to built-in tools that can be processed
+            in a response
         input:
           type: array
           items:
@@ -7240,6 +7245,11 @@ components:
             (Optional) Additional fields to include in the response.
         max_infer_iters:
           type: integer
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) Max number of total calls to built-in tools that can be processed
+            in a response.
       additionalProperties: false
       required:
         - input
@@ -7321,6 +7331,11 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_tool_calls:
+          type: integer
+          description: >-
+            (Optional) Max number of total calls to built-in tools that can be processed
+            in a response
       additionalProperties: false
       required:
         - created_at