feat: Add max_output_tokens to Response API

OpenAI Responses and Completions have a max_output_tokens field.
It is currently missing from the create and response object in Responses API.

This PR fixes it.

fixes: #3562
Signed-off-by: Abhishek Bongale <abhishekbongale@outlook.com>

docs/static/llama-stack-spec.yaml

@@ -6164,6 +6164,10 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) Upper bound for response tokens generation.
         input:
           type: array
           items:
@@ -6522,6 +6526,10 @@ components:
             (Optional) Additional fields to include in the response.
         max_infer_iters:
           type: integer
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) Maximum tokens generated in a response.
       additionalProperties: false
       required:
         - input
@@ -6603,6 +6611,10 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) Upper bound for response tokens generation.
       additionalProperties: false
       required:
         - created_at

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

@@ -6880,6 +6880,10 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) Upper bound for response tokens generation.
         input:
           type: array
           items:
@@ -7238,6 +7242,10 @@ components:
             (Optional) Additional fields to include in the response.
         max_infer_iters:
           type: integer
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) Maximum tokens generated in a response.
       additionalProperties: false
       required:
         - input
@@ -7319,6 +7327,10 @@ components:
           type: string
           description: >-
             (Optional) System message inserted into the model's context
+        max_output_tokens:
+          type: integer
+          description: >-
+            (Optional) Upper bound for response tokens generation.
       additionalProperties: false
       required:
         - created_at