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

# Proactive Analyzer Configuration and Limitations

> Configuration keys, the manual trigger endpoint, and current known limitations for Proactive Analyzer.

<Warning>
  **Disabled by default.** Proactive Analyzer is off by default and requires the reactive [Query Analyzer](/corecapabilities/ai/query-analyzer/overview) to be enabled first. Contact your StarTree account team to have it enabled for your environment.
</Warning>

## Configuration

Proactive Analyzer lives behind its own configuration namespace and requires the reactive analyzer (`query-analyzer.enabled=true`) to be turned on first, since it reuses the same analysis engine.

| Setting                                             | Default         | Controls                                                     |
| --------------------------------------------------- | --------------- | ------------------------------------------------------------ |
| `enabled`                                           | `false`         | Master switch for the feature                                |
| `cron`                                              | `0 0 3 * * *`   | When the scan runs (daily at 03:00 by default)               |
| `lookback`                                          | `PT24H`         | How far back in the query log to rank queries                |
| `top-n`                                             | `5`             | How many query shapes are considered per run                 |
| `min-time-used-ms`                                  | `50`            | Minimum latency for a query shape to qualify                 |
| `max-analyses-per-run`                              | `3`             | Hard ceiling on analyses per run                             |
| `reanalyze-on-config-change-only`                   | `true`          | Skips analysis when table config is unchanged since last run |
| `notify.slack.enabled` / `notify.slack.webhook-url` | `false` / empty | Slack digest delivery                                        |

## Manual Trigger

`POST /api/query-analyzer/proactive/run` starts one scan immediately on a background thread, without waiting for the schedule. If a scan is already in progress, a manual trigger returns a conflict rather than starting a second overlapping run.

## Current Limitations

* **Recommendations are stored in memory by default** and reset when the service restarts.
* **Scans a single workspace on a single cluster per run.** Multi-cluster and multi-workspace scanning are not yet supported.
* **No automatic ticketing and no dedicated UI.** The digest points a human at the work; it does not file tickets or change any cluster setting on its own.
* **Email delivery is not yet available.** Slack and the log are the supported channels today.

## Related

<Card title="Proactive Analyzer Overview" icon="bell" href="/corecapabilities/ai/query-analyzer/proactive-analyzer/overview">
  What Proactive Analyzer does, how it works, and how it delivers results.
</Card>