orchestration

What this skill does

# Orca Inter-Agent Orchestration

Orchestration is Orca's structured coordination layer for agent messages, task ownership, dispatch state, and worker completion tracking.

Use this skill when coordination state matters. For lightweight terminal prompts or basic worktree/terminal/built-in-browser control, use `orca-cli`.

## When To Use

- Send/reply/ask between agent terminals with persistent messages.
- Dispatch structured tasks to workers and wait for `worker_done` or `escalation`.
- Track task DAGs with dependencies.
- Run coordinator loops or decision gates.

## Preconditions

- `orca status --json` should show a running runtime.
- `orca` must be on PATH (`orca-ide` on Linux).
- The orchestration experimental feature must be enabled in Settings > Experimental.
- `orca orchestration` commands are RPC calls to the running Orca runtime.

## Ownership

Orchestration messages and tasks are runtime-global. Completion authority comes from the active dispatch context: `taskId` + `dispatchId` + assignee handle.

Classify inherited context before sending lifecycle messages:

- Coordinated subtask: a live coordinator owns the DAG and waits on this dispatch. Follow the preamble exactly, including `worker_done`, heartbeat/status, `ask`, and `escalation`.
- Full handoff: the original actor delegated ownership and is not monitoring. Finish in the current session. Create a new coordinator only when the user asks or you deliberately decompose fresh subtasks; if spawning workers, use your current-worktree coordinator handle and a selector such as `--worktree active`.

If unclear, inspect orchestration state before sending lifecycle messages:

```bash
orca orchestration task-list --json
orca terminal list --json
# If inherited context includes a task id:
orca orchestration dispatch-show --task <task_id> --json
```

## Messaging

```bash
orca orchestration send --to <handle|@group> --subject <text> [--from <handle>] [--body <text>] [--type <type>] [--priority <level>] [--thread-id <id>] [--payload <json>] [--json]
orca orchestration check [--terminal <handle>] [--unread] [--types <type,...>] [--inject] [--wait] [--timeout-ms <n>] [--json]
orca orchestration reply --id <msg_id> --body <text> [--from <handle>] [--json]
orca orchestration ask --to <handle> --question <text> [--options <csv>] [--timeout-ms <n>] [--from <handle>] [--json]
orca orchestration inbox [--limit <n>] [--json]
```

Rules:

- Omit `--from` unless impersonating another terminal; Orca auto-resolves it from the current terminal.
- While supervising workers manually, use `check --wait --types worker_done,escalation,decision_gate --timeout-ms <n>` instead of sleep/poll loops. Reply to `decision_gate` messages with `orca orchestration reply --id <msg_id> --body <answer> --json`, then keep waiting.
- Treat a `check --wait` timeout or `{count:0}` as a checkpoint, not a worker failure. Long coding tasks routinely run 15-60 minutes; keep using rolling waits unless you receive `worker_done`/`escalation`, the terminal exits or disappears, or the user explicitly asks you to stop.
- Heartbeats and visible terminal activity mean the worker is alive, not done. Do not stop, close, kill, or restart a worker just because it has not produced a completion message yet.
- Use `ask` when a worker needs a blocking answer from the coordinator; it waits for the reply and returns the answer directly.
- `check --wait` returns one message at a time. If N workers may finish together, loop N times and dispatch newly ready tasks after each completion.
- Group addresses include `@all`, `@idle`, `@claude`, `@codex`, `@opencode`, `@gemini`, `@droid`, and `@worktree:<id>`.
- Message types include `status`, `dispatch`, `worker_done`, `merge_ready`, `escalation`, `handoff`, `decision_gate`, and `heartbeat`.

## Tasks And Dispatch

A task is the work item, a dispatch assigns it to a terminal, and a gate blocks progress until a coordinator or user decision is recorded.

```bash
orca orchestration task-create --spec <text> [--deps <json_array>] [--parent <task_id>] [--json]
orca orchestration task-list [--status <status>] [--ready] [--json]
orca orchestration task-update --id <task_id> --status <status> [--result <json>] [--json]
orca orchestration dispatch --task <task_id> --to <handle> [--from <handle>] [--inject] [--json]
orca orchestration dispatch-show --task <task_id> [--json]
```

Task statuses: `pending`, `ready`, `dispatched`, `completed`, `failed`, `blocked`.

Dispatch rules:

- `--inject` sends the task spec plus preamble into a recognized agent CLI so it can report `worker_done`.
- If the target is a bare shell, omit `--inject`, dispatch for tracking if needed, then send the prompt manually with `orca terminal send --terminal <handle> --text <prompt> --enter --json`.
- After 3 consecutive failures on one task, the dispatch context circuit-breaks and the task is marked failed.

## Gates And Coordinator

```bash
orca orchestration gate-create --task <task_id> --question <text> [--options <json_array>] [--json]
orca orchestration gate-resolve --id <gate_id> --resolution <text> [--json]
orca orchestration gate-list [--task <task_id>] [--status <status>] [--json]
orca orchestration run --spec <text> [--from <handle>] [--poll-interval-ms <n>] [--max-concurrent <n>] [--worktree <selector>] [--json]
orca orchestration run-stop [--json]
```

`run` returns immediately with a run ID. Query progress with `task-list`. Use `ask` for worker-to-coordinator questions; it creates a `decision_gate` message that the coordinator answers with `reply`. Use `gate-create` only for coordinator-managed task DAG decisions, not for answering a worker's `ask`.

Recovery only: `orca orchestration reset --tasks|--messages|--all --json` clears runtime-global orchestration state. Do not run it during active coordination unless explicitly abandoning that state.

## Worker Terminals

For tracked orchestration work, create the worker without a prompt, wait for idle, then dispatch with `--inject`:

```bash
orca worktree create --name <task-name> --agent codex --json
orca terminal list --worktree id:<newWorktreeId> --json
orca terminal wait --terminal <handle> --for tui-idle --timeout-ms 60000 --json
orca orchestration dispatch --task <task_id> --to <handle> --inject --json
```

Read the new worktree id from `worktree create`, then use `terminal list` to get the agent terminal handle. Omit `--repo` only when running inside an Orca-managed worktree; otherwise pass `--repo <selector>`. `--agent` reveals the new worktree and launches the selected agent in its first terminal, so do not create a separate startup terminal. Use `--setup run|skip|inherit` when setup behavior matters, and `--no-parent` for independent work.

Use `orca worktree create --prompt ...` or `orca terminal send ...` only for untracked/lightweight prompts. Those paths do not attach `taskId`/`dispatchId`; the worker should not send lifecycle messages unless the prompt supplies a live orchestration preamble.

Other terminal commands coordinators often need:

```bash
orca terminal list [--worktree <selector>] [--json]
orca terminal create [--worktree <selector>] [--title <text>] [--command <cmd>] [--json]
orca terminal split --terminal <handle> [--direction horizontal|vertical] [--command <cmd>] [--json]
orca terminal wait --terminal <handle> --for tui-idle --timeout-ms <n> --json
orca terminal read --terminal <handle> --json
orca terminal send --terminal <handle> --text <text> --enter --json
```

If an older CLI rejects `worktree create --agent`, create the worktree normally, then run `orca terminal create --worktree <selector> --command "codex" --json` or `--command "claude"`.

Wait for `tui-idle` before dispatching. Always pass `--timeout-ms`; real coding tasks can take 15-60 minutes. During supervision, use rolling `check --wait` windows. If a window returns no matching message, inspect `task-list`, `terminal read`, or `terminal wait --for tui-idle` as a liveness checkpoint; if the terminal is