=== chat-max ===
--- INPUT  (POST chat, request.json) ---
{
  "model": "zai-org/GLM-5.3",
  "temperature": 0,
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK."
    }
  ],
  "max_tokens": 4096,
  "reasoning_effort": "max"
}

--- OUTPUT (HTTP 200, 0.8 s, pass=True) ---
{"id":"8e44ca457f9b4c708f0695ef48689082","choices":[{"index":0,"message":{"content":"OK","refusal":null,"role":"assistant","reasoning_content":"The user has asked me to reply with exactly \"OK\". This is a simple, clear instruction. There's nothing harmful or problematic about this request. I should just reply with \"OK\" and nothing else."},"finish_reason":"stop","logprobs":null}],"created":1792329991,"model":"zai-org/GLM-5.3","object":"chat.completion","usage":{"prompt_tokens":17,"completion_tokens":45,"total_tokens":62,"prompt_tokens_details":{"cached_tokens":0}}}