{
  "description": "Spawn subagents in isolated contexts; each gets its own conversation, terminal session, and toolset, and only its final summary returns to you. Pass every task in `tasks` — one entry spawns one subagent, several run in parallel (limit in the tasks description).\n\nSessions without a later-result consumer (including one-shot CLI and cron) join parallel children and return results in this tool call. Otherwise runs in the background: dispatch returns live transcript paths and results re-enter as a new message when subagents finish (one message per call). Background results are delivered only BETWEEN your turns: finish whatever does not depend on them, then give a one-line status and END YOUR TURN. Never wait or poll on transcripts, artifact files, or CI for a child. While children run, `action` (list/steer/stop) controls them live.\n\nUSE FOR: reasoning-heavy subtasks, work that would flood your context, or independent parallel workstreams.\nDO NOT USE FOR (use these instead):\n- Mechanical multi-step work with no reasoning needed -> execute_code\n- A single tool call -> call the tool directly\n- Tasks needing user interaction -> subagents cannot ask questions\n- Durable work that must survive this session -> cronjob or terminal(background=True, notify=True); /stop, /new, or process exit halts running subagents (whole tree); each returns an 'interrupted' completion with partial output.\n\nRULES:\n- Children know nothing of this conversation: pass everything needed via 'context', including any required output language, tone, or style (e.g. \"respond in Chinese\").\n- Child summaries are SELF-REPORTS, not verified facts: a child claiming \"uploaded successfully\" or \"file written\" may be wrong. For external side effects (uploads, remote writes, publishing), require a verifiable handle (URL, ID, absolute path) and verify it yourself before telling the user the operation succeeded.\n- Children cannot close tracked work: a child asked to close it returns findings instead; the parent applies the transition.\n- Children cannot call delegate_task, clarify, memory, or cronjob.\n- Children inherit the parent model unless pinned via delegation.provider / delegation.model in config.yaml.",
  "name": "delegate_task",
  "parameters": {
    "properties": {
      "action": {
        "description": "Default 'spawn'. Live control of running children: 'list' = ids/goals/status/transcripts; 'steer' = queue course-correction text into one child (subagent_id + message) without stopping it; 'stop' = end one child early (subagent_id; partial result still returns). Control actions return immediately; goal/tasks are ignored unless spawning.",
        "enum": [
          "spawn",
          "list",
          "steer",
          "stop"
        ],
        "type": "string"
      },
      "message": {
        "description": "For action='steer': the course correction, appended to the child's next tool result mid-run. Be directive and specific.",
        "type": "string"
      },
      "subagent_id": {
        "description": "Target for action='steer'/'stop' (ids from the spawn response or action='list').",
        "type": "string"
      },
      "tasks": {
        "description": "The task(s), up to 10 in parallel for this user (set via delegation.max_concurrent_children). Each entry spawns one subagent with isolated context and terminal session; a single task is a one-entry array. Required when spawning.",
        "items": {
          "properties": {
            "context": {
              "description": "Background THIS child needs: file paths, error messages, constraints. Each child sees only its own context — repeat shared background in every task that needs it.",
              "type": "string"
            },
            "goal": {
              "description": "What this subagent should accomplish. Be specific and self-contained — it knows nothing about your conversation history.",
              "type": "string"
            },
            "images": {
              "description": "Optional images this child must SEE (max 8): local file paths or http(s) URLs — e.g. a screenshot the user sent, a design mock, a chart. Vision-capable children receive the pixels on their first turn; non-vision children get path hints for vision_analyze. Text files do NOT belong here — put paths in 'context' instead.",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "output_schema": {
              "description": "Optional JSON Schema this child's final answer must validate against (told to the child up front; parent validates with one bounded correction retry; result gains schema_valid, plus schema_errors on failure — the child's raw text is still returned as summary, never discarded). Keep it forgiving — require only fields you will read.",
              "properties": {},
              "required": [],
              "type": "object"
            }
          },
          "required": [
            "goal"
          ],
          "type": "object"
        },
        "minItems": 1,
        "type": "array"
      }
    },
    "required": [],
    "type": "object"
  }
}