Run history
What every run records — outcome, why it fired, and the full transcript of what an agent actually did.
Work that happens while you are away is the work you have the least reason to trust. So it is the work that has to be the most legible.
Every fire of every task is recorded — on the server, against your account, so the history covers every device you're signed in on. You can read one task's runs on its page, or All runs across every task at once. Both show the newest hundred.
What a run tells you#
Each run is two lines. On the first, a dot in the colour of the outcome, what happened, and how long it took; on the second, why it fired and when.
Whether it worked. succeeded; failed (exit 1); timed out; cancelled; errored — with
the message; skipped overlap when a previous run was still going; or skipped — with the reason
the daemon refused to fire it — the server was unreachable, the project wasn't open.
How long it took. Or unknown, honestly: a run whose end was only inferred — inferred at
restart or inferred from silence, not observed — has a last-seen time, not a finish time, and
those show as unknown rather than as a number that looks precise and is invented.
Why it fired — and this is the one people do not expect. Every run records its own cause, as
source · cause: trig · cron for a schedule, studio-events · event for an editor event, studio · manual for the button. A task that fired at a strange hour can be asked what started me, and it
answers from the record rather than from inference.
When it started, in your own clock.
Opening a run#
Click a run and it unfolds. For an agent or flow task, the tool activity comes first — one row per tool the agent called, with the tool's name and a glimpse of its input, still ticking if the run is live. Then the transcript, and last the output tail.
The transcript is the run's whole conversation, replayed. Not a log file — the same renderers that draw a live agent session. Each turn, each tool call, what it read and what it wrote, in the order it happened. One surface whether you are watching it live or opening it a week later.
This is the promise from About applied to unattended work: you can see what the model actually did, not a summary of what it claims to have done.
The output tail is the end of what the run printed — every kind of task keeps one, and a run that printed nothing says No output captured.
Note
A transcript is an enrichment; the printed output is the guarantee. Shell tasks have no conversation to show, and a transcript can also be unavailable for other reasons. When there is none, the panel simply shows the output. Absence here is normal, never an error.
Nothing, versus could not ask#
A small thing worth naming, because it is the difference between a tool you can reason with and one you cannot.
An empty run list and a run list that failed to load look identical if you are careless about it — both render as "no runs". Semantix treats them as different questions. No runs recorded yet means exactly that. If the history cannot be fetched, the panel says Run history unavailable and why — you're signed out, or the server is away. It will not show you a confident, empty, wrong history and let you conclude that your task has never fired.
The same instinct runs through the rest of the Task Manager: a fire the daemon refused is recorded as skipped with its reason rather than quietly dropped, and a duration that cannot be known is not invented.