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

# Dashboard

> Real-time action feed and policy analytics at localhost:8765

## Launch

```bash theme={null}
pip install "plyra-guard[sidecar]"
plyra-guard serve
# → http://localhost:8765
```

Or start from code:

```python theme={null}
guard.serve(host="0.0.0.0", port=8080)
```

<Note>
  The default sidecar port in config is `8080`. The CLI command `plyra-guard serve`
  uses port `8765`. You can override both via the `sidecar` section in your YAML config.
</Note>

## What you can see

* **Live action feed** — every tool call as it happens, with verdict and latency
* **Policy hit rates** — which rules fire most
* **Session replay** — reconstruct any agent session from the audit log
* **Block details** — full context on every blocked call: action type, intent,
  matched rule, and reason

<Warning>
  The default CORS setting (`allow_origins=["*"]`) is fine for local
  development. Lock it down before exposing the dashboard beyond localhost.
</Warning>

<Note>
  Run `plyra-guard serve` to launch the dashboard at
  [localhost:8765](http://localhost:8765). The dashboard shows a live
  action feed, policy hit rates, session replay, and full block context
  — no configuration required beyond the sidecar install.
</Note>

## Query the audit log

```python theme={null}
from plyra_guard import AuditFilter, Verdict

# Get the 20 most recent blocked actions
entries = guard.get_audit_log(AuditFilter(
    verdict=Verdict.BLOCK,
    limit=20,
))

for entry in entries:
    print(f"{entry.action_type} | {entry.verdict.value} | {entry.duration_ms}ms")
```

### AuditFilter fields

| Field         | Type               | Default | Description            |
| ------------- | ------------------ | ------- | ---------------------- |
| `agent_id`    | `str \| None`      | `None`  | Filter by agent        |
| `task_id`     | `str \| None`      | `None`  | Filter by task         |
| `verdict`     | `Verdict \| None`  | `None`  | Filter by verdict type |
| `action_type` | `str \| None`      | `None`  | Filter by action type  |
| `from_time`   | `datetime \| None` | `None`  | Start of time range    |
| `to_time`     | `datetime \| None` | `None`  | End of time range      |
| `limit`       | `int`              | `100`   | Max entries to return  |

## Explain a decision

```python theme={null}
from plyra_guard import ActionIntent

intent = ActionIntent(
    action_type="file.delete",
    tool_name="delete_file",
    parameters={"path": "/etc/passwd"},
    agent_id="default",
)

explanation = guard.explain(intent)
print(explanation)
# Human-readable description of which evaluators ran,
# which rule matched, and why the verdict was reached
```

## Metrics snapshot

```python theme={null}
metrics = guard.get_metrics()
print(f"Total: {metrics.total_actions}")
print(f"Blocked: {metrics.blocked_actions}")
print(f"Avg risk: {metrics.avg_risk_score:.2f}")
print(f"Avg latency: {metrics.avg_duration_ms:.1f}ms")
```

Export as Prometheus text format:

```python theme={null}
print(metrics.to_prometheus())
```