---
title: "Observability"
description: "The live run view, logs and traces stitched by run ID, cost and token metrics, alerts that fire once, retention by plan, and the agent comparison report."
---

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

# Observability

Agents do the work, so the record of what they did has to be something an agent can read. Everything here is structured data first: JSON from the CLI, ordered events on a socket, notices that name the command to run. The web app shows the same data.

- [The live run view](/observability/live-run-view/): a run's events over a WebSocket from the project, with resume by sequence.
- [Logs and traces](/observability/logs-and-traces/): logs, spans and events stitched by run ID, with secrets redacted before anything is stored.
- [Cost and token metrics](/observability/metrics/): cost, tokens, tool calls, success and latency per agent, project, team, pull request and task, reconciled with metered usage.
- [Alerts and incidents](/observability/alerts/): spend caps, failing runs, stuck leases and a stale index, sent once per incident to email, Slack and Teams.
- [Retention by plan](/observability/retention/): how long telemetry is kept, and what no purge touches.
- [The agent comparison report](/observability/comparison/): the same task given to two agents, side by side, and evals that replay your merged pull requests.

```sh
overlane observe status
overlane observe trace --run run-12
overlane observe cost
overlane observe compare --task task-77
```

Command reference: [observe status](/cli/observe-status/), [observe logs](/cli/observe-logs/), [observe trace](/cli/observe-trace/), [observe cost](/cli/observe-cost/), [observe reconcile](/cli/observe-reconcile/), [observe compare](/cli/observe-compare/), [observe evals](/cli/observe-evals/), [observe alerts](/cli/observe-alerts/) and [observe retention](/cli/observe-retention/).

## No model in the measuring

Ordering, redaction, totals, reconciliation, alert conditions, the retention cut-off and every score are arithmetic over stored rows. The decision records of the optional decision models appear in `overlane observe status` as counts by outcome and use, with their mean latency; they are read from where they are already kept, not copied.

## Agent use and the override

An agent reports its own events, logs and cost with its token, reads the trace of a failed run, and sets its alert rules. A person can read the same views in the web app, change any rule, and run a purge. Ingest is a write, so a read-only role reads and cannot report.

Source: https://docs.overlane.app/observability/index.mdx