[MOSH-2632]: Add OpenAPI support for judge max_tokens

openapi.yaml

@@ -12338,6 +12338,18 @@ components:
           minimum: 1
           description: "Number of concurrent workers for inference requests. Overrides the default concurrency for this model. Useful for tuning throughput when using proxy endpoints (e.g. OpenRouter) or rate-limited external APIs."
           example: 5
+        max_tokens:
+          type: integer
+          minimum: 1
+          description: "Maximum number of tokens the judge model can generate. Defaults to 32768. Increase for reasoning models (e.g. Gemini, o-series) that consume output token budget for chain-of-thought."
+          example: 8192
+        temperature:
+          type: number
+          format: float
+          minimum: 0
+          maximum: 2
+          description: "Sampling temperature for the judge model. Defaults to 0.05."
+          example: 0.0
 
     EvaluationModelOrString:
       oneOf: