Run History
Every execution of an automation is recorded as a run. The run history page lists an automation's most recent runs so you can see at a glance what ran, when, with what outcome, and what it cost.
Open it with the Run history button on the automation detail page, or navigate to /automations/<automation-id>/runs.
The toolbar
Above the table, an at-a-glance stats row summarizes the runs currently in view — the numbers update as you filter:
| Stat | Meaning |
|---|---|
| Runs | How many runs match the current filters. |
| Completed | Runs that finished cleanly. |
| Failed | Runs with any non-clean outcome (failed, timed out, out of credits, or interrupted). |
| In progress | Runs still queued, running, or awaiting input. |
| Credits | Total credits consumed across the matching runs. |
| Avg duration | Average duration of the matching runs that actually ran. |
A filter row sits below the stats:
- Search — matches on run id, summary, or error text.
- Status — All statuses, In progress, Completed, or Failed. These roll up the detailed statuses below: "In progress" covers queued, running, and awaiting-input runs, and "Failed" covers failed, timed-out, out-of-credits, and interrupted runs.
- Trigger — All triggers, On demand, Scheduled, or Webhook.
- Time window — Any time, Last 24 hours, Last 7 days, or Last 30 days.
- Export CSV — downloads the currently-filtered runs as a CSV file.
The list also refreshes on its own every few seconds while any run is still in flight, and a Refresh button in the header re-loads it on demand.
The run table
The page fetches up to the 200 most recent runs and shows 50 at a time; a Show more button reveals the next 50. When the 200-run cap is reached, the footer count reads "200+ (most recent)". Rows are newest first.
| Column | Meaning |
|---|---|
| Status | The run's current or final state, as a colored badge (see below). |
| Started | When the run started (or when it was created, if it never started). Hover for the exact time. |
| Duration | How long the run took — the metered active time when available, otherwise the wall-clock span from start to finish. |
| Trigger | What launched it — On demand, Scheduled, or Webhook. |
| Tools | How many tool calls the run made. |
| Tokens | Total input + output tokens, compacted (for example, "12.4k"). Hover for the exact input / output split. |
| Credits | Credits consumed by the run. |
| Summary | The agent's summary, or — for a failed run — the error message. |
Click anywhere on a row (or focus it and press Enter/Space) to open its run detail page. There is no separate "View" column.
Run statuses
The status badge shows both the state and, by its color, the outcome:
| Status | Terminal? | Meaning |
|---|---|---|
| Queued | No | The run was accepted and is waiting to start. |
| Running | No | The run is in progress — open it to watch the live stream or interrupt it. |
| Awaiting input | No | The run is paused waiting for a human to approve a tool call. You should not normally see this today — with approvals switched off platform-wide, an approval pause is converted to a Failed run instead. See the note on the run detail page. |
| Completed | Yes | The run finished successfully. |
| Failed | Yes | The run ended with an error — open the run to read the error message. |
| Timed out | Yes | The run exceeded the automation's Max runtime and was terminated. |
| Out of credits | Yes | Either your balance was too low to start the run (in which case nothing was charged), or the run hit its Max credits per run cap mid-run and was wrapped up. |
| Interrupted | Yes | Someone stopped the run with the Interrupt button. |
| Skipped | Yes | A scheduled run was dropped before starting because every execution slot was busy when it fired. Nothing was reserved or charged, and the reason is in the run's summary — it is not a failure. A skipped run appears only under the All statuses filter (it counts as neither in progress, completed, nor failed). |
Failed, Timed out, Out of credits, and Interrupted render with a red badge; Completed is green; Queued and Running are blue; Awaiting input and Skipped are amber.
Empty and error states
- "No runs yet." — the automation has never run. The hint below adapts to the trigger: a scheduled or webhook automation is told its runs will appear once the schedule fires or the webhook is called.
- "No runs match the current filters." — with a Clear filters button — when a filter or search hides every run.
- Load failures show a typed alert with a Retry button:
SJ-AGENT-FORBIDDEN,SJ-AGENT-NOT-FOUND,SJ-AGENT-UNAVAILABLE, orSJ-AGENT-SERVER-ERROR.