/goal

Type it and what “done” means, in plain language.

/goal every test in ~/budget passes

the checkable end state

Give it a condition the checker can see in the chat (“pytest reports 0 failed”, “the build prints no errors”). “Make it better” never becomes true.

The loop

How a /goal loop runs and endsYou set a goal with a condition. The model works on a turn. When the turn is finished, a separate evaluator model reads the chat since the goal was set and judges it. If the condition is not met, the reason it names becomes the next instruction and the model works again in the same run. The loop ends when the condition is met, when it is impossible, when the evaluator names the same missing piece four checks in a row, or when the round cap is reached. The plan time limit and running out of credit also end it.The goal endsnot met: try againYou type /goal and a conditionThe model works on a turn(same run, same tools)Evaluator model readsthe chat sincethe goal was setMetImpossibleStalledsame piece4 checksCapped25 roundsTime limitor no credit
After every turn a separate model judges the chat; only a verdict of not met sends the model round again.
Diagram as text
  1. You type /goal followed by a condition.
  2. The model works on the chat turn, in the same run and with the same tools as any other turn.
  3. When the turn is finished, an evaluator model reads the chat since the goal was set: up to the last 400 messages, cut to the last 16,000 characters.
  4. If the condition is not met, the reason the evaluator names becomes the next instruction, and the model works again.
  5. The goal ends as met when the evaluator finds the condition shown to be true.
  6. It ends as impossible when the chat shows a blocker the model cannot remove itself.
  7. It ends as stalled when the evaluator names the same missing piece four checks in a row.
  8. It ends as capped after 25 continuations by default; the operator can change that number.
  9. Separately, the time limit of your plan is checked every 15 seconds and can stop a turn that is still running. Running out of credit also ends the goal, with a notice.

The checker is a separate, small model. It cannot run anything; it judges only what the chat shows, such as a tool result or an exit code. A plan or a claim of success without a result behind it does not count. Each check is billed like any other model call and shows up in your usage as a goal check; in a free chat the free router does the checking.

The checker sees up to 400 messages since the goal was set, limited to the last 16,000 characters.

It reports impossible only when the model cannot remove the obstacle itself, such as an access right you need to grant. Slow progress does not count.

What does not interrupt it

the run

What you see

Every round shows up as a line in the chat.

Stop and resume

Stop pauses a goal instead of ending it. Writing the next message does not restart it. The goal bar says paused and shows a Resume button. Background goal runs ask for approval like the chat does. See Stop button.

With your own key the checker runs on your provider: helper and checking models.

Ceilings

Rounds default 25

Stalls after four checks in a row naming the same missing piece. Otherwise capped at 25 continuations; the operator can change that number.

Need the older, unattended kind instead? /jobgoal (/jg, /job) starts a background job with its own log under Jobs.

Time per run, by plan

A run lasts at most 4 hours on Mini, 8 on Pro and 12 on Max. Ultra has no limit. The Free plan has no autonomous runs. The clock starts when you set the goal; a new goal starts a new run. At the limit the goal ends with a notice in the chat. History and files stay.

Credit

With no credit left the goal ends with a notice; top up and set it again. If the checker itself cannot answer, the goal stays set and a message from you continues it.

Condition

Up to 4000 characters. Chats without an account cannot set a goal.

Plans and prices: Plans, Pricing. What else limits spending: Limits.

Overview of unattended runs and what limits them: /goal and /ultracode.

Time, credit and approvals

Standard limits are 4 hours per run on Mini, 8 on Pro and 12 on Max; Ultra has no plan time limit, and the Free plan has no autonomous runs. This is per run, not a monthly hours allowance. See current plans. Paid catalogue requests stop when credit is exhausted. A missing approval, provider error or stopped runtime can prevent progress; an unlimited plan is no guarantee of completion.

When you close the browser, the chat run and stored goal stay on the server. Files, conversation history and a separate terminal process have different lifetimes. See unattended runs, workspace persistence and terminal sessions.