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

# Manage a run

> Update concurrency, stop work, and resume or retry tasks.

Resume pending work with an optional concurrency override.

<CodeGroup>
  ```bash CLI theme={null}
  valkyrie run resume <run-id> --concurrency 20
  ```

  ```python Python SDK theme={null}
  await client.runs.resume(run_id, concurrency=20)
  ```
</CodeGroup>

Full syntax for each command below is in the [`run update`](/reference/cli/run#update), [`run stop`](/reference/cli/run#stop), [`run resume`](/reference/cli/run#resume), and [`run retry`](/reference/cli/run#retry) reference, and in [`client.runs.resume`](/reference/sdk/runs#resume) and [`client.runs.retry`](/reference/sdk/runs#retry) for Python.

## Update concurrency

```bash theme={null}
valkyrie run update <run-id> --concurrency 20
```

The tracker applies the persisted limit when it next refreshes the run. Increasing it admits more tasks. Decreasing it does not cancel in-flight work and pauses new admissions until usage falls below the limit.

The value must be positive. Completed, stopped, and failed runs cannot be updated. The limit is enforced independently by each `process_benchmark` executor, so overlapping executors can temporarily exceed the persisted value.

## Stop work

Stop a whole run, or name the tasks to stop:

```bash theme={null}
valkyrie run stop <run-id>
valkyrie run stop <run-id> --task-ids task-a,task-b
```

A plain stop does not interrupt work that already started. `--force` also deletes the sandboxes of in-progress and evaluating tasks and marks those tasks stopped:

```bash theme={null}
valkyrie run stop <run-id> --force
```

<Warning>
  Force-stopping deletes running sandboxes and cannot be undone. The CLI asks for confirmation first.
</Warning>

## Choose resume or retry

`resume` admits work that never ran. `retry` re-runs tasks that ended in `ERROR`:

```bash theme={null}
valkyrie run resume <run-id>
valkyrie run retry <run-id>
```

Either accepts a task subset, a concurrency override, and `--connect` to stream afterwards. Three overrides change what the retried work uses:

* `--update-agent` refreshes the frozen agent from its current S3 bundle, so a re-pushed agent takes effect.
* `--from-scratch` clears stored evaluation resume state, so a task is graded again from the beginning.
* `--benchmark-url` replaces the benchmark-service URL stored on the run, which a tunnelled service needs after its URL changes.

`-s` merges a secret mapping into the stored contract, which is how a rotated credential reaches resumed tasks.

For a terminal run, a selected valid task ID without an existing row is created as new `PENDING` work. An in-progress retry rejects selected IDs that do not already exist in `ERROR` state.

## Export benchmark task IDs

```bash theme={null}
valkyrie benchmark tasks swebench --dataset default --output tasks.txt
```

The output path is optional. Pass the file to `--task-ids-file` on start, stop, resume, or retry.