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

# Alerts

> Threshold rules on cost, latency, errors, and eval scores.

**Alerts** are threshold rules evaluated continuously against a rolling window
of your traffic. When a metric breaches its threshold the rule starts
**firing** and sends an email; when it recovers it returns to **ok** and sends a
resolve email. A rule that stays firing re-notifies on a cooldown.

## Anatomy of a rule

| Field         | Description                                               |
| ------------- | --------------------------------------------------------- |
| **Name**      | A label for the rule (1–200 chars).                       |
| **Metric**    | What to measure — see the table below.                    |
| **Condition** | Comparison operator: `>`, `≥`, `<`, `≤`.                  |
| **Threshold** | The number the metric is compared against.                |
| **Window**    | The rolling lookback: 5 min, 15 min, 1 hour, or 24 hours. |
| **Filters**   | Optional — narrow to a `modelId` and/or `agentName`.      |
| **Notify**    | An email address to notify.                               |
| **Enabled**   | Toggle the rule on/off without deleting it.               |

## Metrics

| Metric                                        | Meaning                                              |
| --------------------------------------------- | ---------------------------------------------------- |
| `cost`                                        | Total cost (USD) over the window.                    |
| `latency_p50` / `latency_p95` / `latency_p99` | Step-latency quantiles (ms).                         |
| `ttft_p95`                                    | Time-to-first-token, p95 (ms).                       |
| `error_rate`                                  | Fraction of spans that errored (0–1).                |
| `token_usage`                                 | Total tokens over the window.                        |
| `request_count`                               | Span count over the window.                          |
| `eval_avg_score`                              | Average score for a chosen [eval](/dashboard/evals). |
| `eval_pass_rate`                              | Pass ratio (0–1) for a chosen eval.                  |

<Note>
  The two `eval_*` metrics require selecting a specific eval — the rule scores
  against that eval's results rather than raw span metrics.
</Note>

## How evaluation works

A background evaluator sweeps every enabled rule on an interval
(`ALERT_EVAL_INTERVAL_MS`, default 60s). For each rule it queries the metric
over the window and compares it to the threshold:

* **ok → firing** — threshold breached. Records a `fired` event (with the
  observed value and threshold) and emails the channel.
* **firing → ok** — metric recovered. Records a `resolved` event and emails.
* **still firing** — re-notifies at most once per `ALERT_RENOTIFY_MS`
  (default 1 hour) so you aren't paged every minute.

Each transition is stored as an alert event, giving every rule an auditable
history of when it fired and resolved.

<Warning>
  Alert emails require email to be configured on the deployment
  (`RESEND_API_KEY`). Without it, rules still evaluate and change state, but no
  notifications are sent. See [self-hosting configuration](/self-hosting/configuration#email-optional).
</Warning>

## List view

The Alerts page lists every rule with its metric, condition, threshold, window,
current status (an **ok** or **firing** badge), and an inline enable switch.
Plans cap how many rules an org can create; the [Usage](/dashboard/account#usage)
panel shows your current count against the limit.