claude-code - 💡(How to fix) Fix [BUG] CLI returns empty responses: Model generates <thinking> block but output_tokens is 0 (Opus 4.7 & Sonnet 4.6) [2 comments, 2 participants]

{
  "type": "assistant",
  "uuid": "[REDACTED_UUID]",
  "timestamp": "2026-04-22T08:11:50.266Z",
  "entrypoint": "cli",
  "cwd": "/Users/[REDACTED_USER]/Workdir/[REDACTED_PROJECT_PATH]",
  "version": "2.1.117",
  "message": {
    "model": "claude-opus-4-7",
    "id": "msg_bdrk_[REDACTED_ID]",
    "type": "message",
    "role": "assistant",
    "content": [
      {
        "type": "thinking",
        "thinking": "[REDACTED_LONG_THINKING_PROCESS]",
        "signature": "[REDACTED_SIGNATURE]"
      }
    ],
    "stop_reason": null,
    "stop_sequence": null,
    "stop_details": null,
    "usage": {
      "input_tokens": 6,
      "cache_creation_input_tokens": 36412,
      "cache_read_input_tokens": 10477,
      "output_tokens": 0,
      "service_tier": "standard"
    }
  }
}

{
  "type": "assistant",
  "uuid": "[REDACTED_UUID]",
  "timestamp": "2026-04-22T08:15:12.705Z",
  "entrypoint": "cli",
  "cwd": "/Users/[REDACTED_USER]/Workdir/[REDACTED_PROJECT_PATH]",
  "version": "2.1.117",
  "message": {
    "model": "claude-sonnet-4-6",
    "id": "msg_bdrk_[REDACTED_ID]",
    "type": "message",
    "role": "assistant",
    "content": [
      {
        "type": "thinking",
        "thinking": "The user is frustrated because my responses keep getting cut off/interrupted... Looking back at the conversation, I can see several instances where my response shows \"(no content)\" - this means my response was empty/cut off... I should always include text alongside tool calls, and the instruction is clear that I need to state what I'm about to do before invoking anything... I was sending entirely tool-focused responses without any accompanying text, which would appear as silence to the user...",
        "signature": "[REDACTED_SIGNATURE]"
      }
    ],
    "stop_reason": null,
    "stop_sequence": null,
    "usage": {
      "input_tokens": 3,
      "cache_creation_input_tokens": 35117,
      "cache_read_input_tokens": 0,
      "output_tokens": 0
    }
  }
}