# Resolve waits and control Runs

> Resolve human decisions, steer active work, and apply pause, resume, interrupt, cancel, Policy, rebind, truncate, or branch controls.

## Before you begin {#before-you-begin}

Open the exact namespace, Agent, session, and Run address. Inspect the authoritative status and pending waits before acting. Every mutation needs a caller-stable `eventId` or documented idempotency key and its specific Policy action. Repeating that identifier must return the recorded control outcome.

## Steps {#steps}

1. List open waits with `GET .../sessions/:session/waits`. Resolve one with `POST .../waits/:promiseId/resolve` and body `{ "eventId": "approval-42", "value": ... }`. The value must satisfy the schema pinned when Agent code called `ctx.await()`.
2. Add fresh operator or user direction through `POST .../sessions/:session/steers` with a bounded `eventId`, `text`, and optional `data`. Actor identity is derived from authentication, never accepted from the body.
3. Pause at a safe point with `POST .../runs/:run/pause`; continue through `/resume`. Resume requires an explicit `eventId`.
4. Interrupt with `/interrupt`. `safe-point` preserves the normal boundary; `abort` additionally requires `run:abort` and stops current work before continuing.
5. Cancel through `/cancel` when no future work should run. Committed facts and audit history remain.
6. Use `/policy` to change a Policy hash, turn limit, or micro-USD budget at a safe point. Use `/rebind` only when every new fixed binding satisfies the deployed contracts; scoped rebind derives assignments from accepted authority.
7. Use `/truncate` to move the same Run’s history to an earlier fact with required steering text. Use `/branch` when the original history must remain and a new Run should continue from the selected fact.

## Verify {#verify}

Read the control receipt and refresh Run detail. Confirm the journal records the authenticated actor, event id, operation, mode, payload hash, scheduler transition, and resulting status. When a Resource call has an unknown outcome, reconcile it according to the operation contract before resuming.

## Next steps {#next-steps}

Use [Inspect a Run](/docs/runs/operate.md) for journal paging and [Stream a Run](/docs/runs/stream.md) for reconnectable output. Review [Durable execution](/docs/sdk/durable-execution.md) for the Agent-side wait and handle contract.