{
  "id": "23a31f35846dbc6687f18afa02fefba5c9989caadc5f73a9c6b6b2787ad6f592",
  "label": "estimate-tool-TaskOutput",
  "generatedAt": "2026-06-09T00:30:04.953Z",
  "url": "https://api.anthropic.com/v1/messages/count_tokens?beta=true",
  "headers": {
    "anthropic-beta": "claude-code-20250219,context-1m-2025-08-07,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,mid-conversation-system-2026-04-07,advisor-tool-2026-03-01,effort-2025-11-24,token-counting-2024-11-01",
    "anthropic-version": "2023-06-01",
    "content-type": "application/json",
    "x-api-key": "<redacted>"
  },
  "body": {
    "model": "claude-opus-4-8",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "<system-reminder>\nAs you answer the user's questions, you can use the following context:\n# currentDate\nToday's date is 2026-06-08.\n\n      IMPORTANT: this context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.\n</system-reminder>\n\n"
          },
          {
            "type": "text",
            "text": "say hi",
            "cache_control": {
              "type": "ephemeral"
            }
          },
          {
            "type": "text",
            "text": "{\"description\":\"DEPRECATED: Background tasks return their output file path in the tool result, and you receive a <task-notification> with the same path when the task completes.\\n- For bash tasks: prefer using the Read tool on that output file path — it contains stdout/stderr.\\n- For local_agent tasks: use the Agent tool result directly. Do NOT Read the .output file — it is a symlink to the full subagent conversation transcript (JSONL) and will overflow your context window.\\n- For remote_agent tasks: prefer using the Read tool on the output file path — it contains the streamed remote session output (same as bash).\\n\\n- Retrieves output from a running or completed task (background shell, agent, or remote session)\\n- Takes a task_id parameter identifying the task\\n- Returns the task output along with status information\\n- Use block=true (default) to wait for task completion\\n- Use block=false for non-blocking check of current status\\n- Task IDs can be found using the /tasks command\\n- Works with all task types: background shells, async agents, and remote sessions\",\"input_schema\":{\"$schema\":\"https://json-schema.org/draft/2020-12/schema\",\"additionalProperties\":false,\"properties\":{\"block\":{\"default\":true,\"description\":\"Whether to wait for completion\",\"type\":\"boolean\"},\"task_id\":{\"description\":\"The task ID to get output from\",\"type\":\"string\"},\"timeout\":{\"default\":30000,\"description\":\"Max wait time in ms\",\"maximum\":600000,\"minimum\":0,\"type\":\"number\"}},\"required\":[\"task_id\",\"block\",\"timeout\"],\"type\":\"object\"},\"name\":\"TaskOutput\"}"
          }
        ]
      },
      {
        "role": "system",
        "content": "The following skills are available for use with the Skill tool:\n\n- deep-research: \n- update-config: \n- keybindings-help: \n- verify: \n- code-review: \n- simplify: \n- fewer-permission-prompts: \n- loop: \n- claude-api: \n- run: \n- init: \n- review: \n- security-review: "
      }
    ],
    "thinking": {
      "type": "adaptive"
    },
    "output_config": {
      "effort": "high"
    },
    "system": [
      {
        "type": "text",
        "text": "x-anthropic-billing-header: cc_version=2.1.168.c27; cc_entrypoint=sdk-ts; cch=e5b75;"
      },
      {
        "type": "text",
        "text": "You are a Claude agent, built on Anthropic's Claude Agent SDK.",
        "cache_control": {
          "type": "ephemeral"
        }
      }
    ]
  },
  "bodyCanonicalSha256": "f2bf99de866a9ba68f3148962602d7936d7b089adac673d72093d317ef360704"
}