feat(reasoning): add max and ultra effort levels (#62650)

batch_runner.py

@@ -1192,7 +1192,7 @@ def main(
         providers_order (str): Comma-separated list of OpenRouter providers to try in order (e.g. "anthropic,openai,google")
         provider_sort (str): Sort providers by "price", "throughput", or "latency" (OpenRouter only)
         max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
-        reasoning_effort (str): OpenRouter reasoning effort level: "none", "minimal", "low", "medium", "high", "xhigh" (default: "medium")
+        reasoning_effort (str): Reasoning effort: "none", "minimal", "low", "medium", "high", "xhigh", "max", "ultra" (default: "medium")
         reasoning_disabled (bool): Completely disable reasoning/thinking tokens (default: False)
         prefill_messages_file (str): Path to JSON file containing prefill messages (list of {role, content} dicts)
         max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
@@ -1261,7 +1261,7 @@ def main(
         print("🧠 Reasoning: DISABLED (effort=none)")
     elif reasoning_effort:
         # Use specified effort level
-        valid_efforts = ["none", "minimal", "low", "medium", "high", "xhigh"]
+        valid_efforts = ["none", "minimal", "low", "medium", "high", "xhigh", "max", "ultra"]
         if reasoning_effort not in valid_efforts:
             print(f"❌ Error: --reasoning_effort must be one of: {', '.join(valid_efforts)}")
             return