Delegate several tasks to Luna workers
delegate_tasksDelegate a batch of bounded tasks to an AI worker for autonomous implementation, verification, and integration. Use sequential for dependencies or parallel for independent scopes.
Instructions
Delegate a batch intended for two or more owned seams to gpt-5.6-luna; one task remains accepted for compatibility, but prefer delegate_task when no scheduling is needed. Use sequential for dependencies/shared workspace state and parallel only for genuinely independent disjoint declared scopes. Do not create artificial seams. At most 12 tasks are accepted and at most 3 run concurrently; the rest queue. Each task needs a self-contained contract and a concise activityLabel when a safe label exists. The parent owns architecture/interfaces and exceptional judgement; Luna owns exploration, implementation, verification, and repair. automaticRepair is one bounded task-local turn.
Parallel same-file edits prevent automatic integration. allowOverlappingScopes:true only accepts the declared overlap; it is not a write sandbox and does not permit same-file integration. integrate=false skips copying and retention follows operator policy. Partial outcomes remain visible. automaticRecovery defaults true: at most one evidence-eligible timeout continuation or exact process-exit retry; a counter alone never authorizes retry. Repair precedes recovery and neither nests. Successes, cancellation, scope/security/evidence failures, refused checks, discrepancies, and conflicts are never retried. Successful streams survive sibling failure.
After integration, deterministic code reruns the deduplicated union of declared checks in the final workspace. completionState=verified-complete means all seams, integration, and final checks passed; the default text-only handoff then tells the parent to finish without rereading files or rerunning checks. Any failure/refusal/conflict returns rich evidence for targeted diagnosis. resultDetail is one batch-level compatibility choice. More workers are not automatically cheaper; raw tokens are not credit cost and savings depend on the parent and task mix. While pending with no meaningful new state, remain silent; do not narrate waiting or polling. Report only a result, error, cancellation, timeout, or actionable state change.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | ||
| tasks | Yes | ||
| integrate | No | ||
| resultDetail | No | handoff | |
| computePolicy | No | Optional per-call compute envelope. Narrows this installation's operator-owned baseline only and can never widen it. Omit to use the baseline. | |
| routingPreflight | No | Optional advisory routing declaration. Solo advice never blocks execution; declarations gate: every surface refuses empty seams, parallel also refuses mutable sharedState, shared-core coreOverlap, or tasks > seams. "unknown" biases advice solo, never refuses. | |
| workingDirectory | No | ||
| automaticRecovery | No | ||
| allowOverlappingScopes | No |