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

# Running missions

> Execute, analyze, and manage runs with env run, env stats, and env cache.

## `env run`

Executes a project's mission phase-by-phase, logging every tick and running the
LLM judge at the end for a verdict.

```bash theme={null}
cadenza env run rescue-dog --headless
```

<Warning>
  `env run` requires the **`gym`** extra (MuJoCo). Install with
  `pip install -e ".[gym]"`.
</Warning>

### Flags

| Flag           | Default         | Description                                                                                                                                      |
| -------------- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| `--headless`   | viewer shown    | Run without the MuJoCo viewer. Works on any Python (no `mjpython` needed). Use this in scripts/CI.                                               |
| `--policy <p>` | `scripted`      | Driver. `scripted` parses each phase's `goal_prompt` into actions. `lora` drives with your fine-tuned LoRA action head (needs the `lora` extra). |
| `--xml <path>` | project default | Override the MuJoCo scene XML.                                                                                                                   |

```bash theme={null}
cadenza env run rescue-dog --headless --policy lora
```

### Output

Each run writes two files under `<project>/.cadenza-env/`:

| File                      | Contents                                                                        |
| ------------------------- | ------------------------------------------------------------------------------- |
| `<run-id>.log.jsonl`      | One record per executed action: phase, reward, observation summary.             |
| `<run-id>.finetune.jsonl` | `(prompt, action, reward, …)` rows rendered via `vla_finetune.prompt_template`. |

The scripted driver exercises the full loop and emits fine-tune records but is
**not** a learned policy. To drive the same mission with your own model, see
[Custom environments](/sdk/custom-environments).

## `env stats`

Aggregate motion and reward analytics across a project's cached runs.

```bash theme={null}
cadenza env stats rescue-dog
```

Reports per-phase success, reward breakdowns, and motion summaries, so you can
see whether edits to your reward shaping or policy actually helped.

## `env cache`

Show or prune the per-project `.cadenza-env/` run directory to manage disk.

```bash theme={null}
cadenza env cache rescue-dog                    # show what's cached
cadenza env cache rescue-dog --keep-last 5      # keep only the 5 newest runs
cadenza env cache rescue-dog --older-than 7d    # drop runs older than 7 days
cadenza env cache rescue-dog --clear            # remove all cached runs
```

| Flag                 | Description                                           |
| -------------------- | ----------------------------------------------------- |
| `--keep-last <n>`    | Keep the `n` most recent runs, delete the rest.       |
| `--older-than <dur>` | Delete runs older than a duration (e.g. `7d`, `24h`). |
| `--clear`            | Delete all cached runs for the project.               |