> ## Documentation Index
> Fetch the complete documentation index at: https://docs.acmeagentsupply.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Recall

> Manual intervention and recovery CLI for AI agent fleets

# Recall

Recall is the operator's hand on the system — the CLI for direct intervention when automated systems are insufficient or you need immediate control over a running agent fleet.

```bash theme={null}
recall status          # fleet state snapshot
recall stall heike     # pause an agent immediately
recall wake heike      # resume
recall lockdown        # stop everything, now
```

## The Three Control Surfaces

Recall completes the operator control plane alongside two existing commands:

```
openclaw health    →  snapshot: what is the system's current state?
openclaw watch     →  live: what is changing right now?
recall             →  action: intervene directly
```

## The Three Operator Primitives

These three commands cover every coordination scenario:

| Command                | Effect                                      | When to Use                        |
| ---------------------- | ------------------------------------------- | ---------------------------------- |
| `recall stall <agent>` | Pause — agent stops acting, keeps listening | Almost always the right first move |
| `recall focus <agent>` | Leader — named agent acts, all others stall | Agents stepping on each other      |
| `recall stun <agent>`  | Reset — full intervention on a broken agent | Something is genuinely broken      |

**`stall` is the dominant operator command in real production.** Most incidents are coordination failures, not catastrophic failures. Stop the agent, investigate, then decide: `recall wake` (minor) or `recall stun` (broken).

## Full Command Reference

### System Commands

```bash theme={null}
recall lockdown          # global lockdown — no new model calls, tool calls, or sub-agent spawning
recall unlock            # lift lockdown
recall status            # fleet state snapshot
recall log [agent]       # intervention history
```

### Agent State

```bash theme={null}
recall freeze <agent>    # stop sub-agent spawning only (agent keeps working)
recall unfreeze <agent>
recall stall <agent>     # queue messages, agent stops processing
recall stall --all       # emergency brake — pauses everything
recall wake <agent>      # reverse stall or sleep
recall wake --all
recall sleep <agent>     # disconnect from channel(s)
recall stun <agent>      # full intervention (see below)
recall quarantine <agent> # isolate for inspection
```

### Recovery

```bash theme={null}
recall recover <agent>   # post-stun return-to-service wizard
recall reset             # safe gateway restart with triage + backup
recall focus <agent>     # single-leader mode — all others stall
recall unfocus           # return to normal multi-agent operation
```

## What Stun Actually Does

`recall stun` is not just a stop command. It runs a 7-step sequence:

1. Disconnect channel connections
2. Drain in-progress tool calls (max 10 seconds)
3. Kill all sub-agents
4. Archive the active session
5. Compact memory
6. Emit a control plane event (visible in `openclaw watch`)
7. Hold — agent offline until `recall recover` + operator confirmation

**Why step 4 matters:** A gateway restart doesn't fix a runaway agent. The bad state lives in the active session, active sub-agents, and memory files. Stun targets all three. Gateway restart misses all three.

## Standard Incident Response

```bash theme={null}
openclaw watch          # something looks odd
recall stall heike      # pause the agent immediately
radcheck risk           # assess
triage                  # capture proof bundle
agent911 diagnose       # classify the incident

# If minor:
recall wake heike

# If serious:
recall stun heike
recall recover heike
recall wake heike
```

## Reversibility

Every operation has a reversal:

| Operation  | Reversal                                |
| ---------- | --------------------------------------- |
| `lockdown` | `unlock`                                |
| `freeze`   | `unfreeze`                              |
| `stall`    | `wake` (queued messages delivered)      |
| `sleep`    | `wake`                                  |
| `stun`     | `wake` (after `recover` + confirmation) |

Session context is not restored after stun — by design. If the session caused the problem, restoring it restores the problem.

## Observability

Every Recall operation emits a structured event that flows into the reliability stack:

* Visible in `openclaw watch` incident timeline
* Ingested by RadCheck signal analysis
* Available in OCTriage proof bundles
* Read by Agent911 during incident diagnosis

<CardGroup cols={2}>
  <Card title="Agent911" icon="tower-broadcast" href="/products/agent911/overview">
    Recall calls Agent911 primitives. They share the same execution layer.
  </Card>

  <Card title="Triage" icon="stethoscope" href="/products/triage/overview">
    Run triage before stun to capture a proof bundle at the moment of intervention.
  </Card>
</CardGroup>