Set how hard the agent thinks

Agents: claude, codex, opencode · On: phone, desktop

Effort is the reasoning dial: how long the agent is willing to think before it answers. Set it with the button under the composer, or with /effort.

Why you would use it

Mechanical edits do not need the model's deepest pass and you pay for it in time and tokens. Debugging does. The dial is per tab, so a tab kept for reviews can sit on high while another sits on low.

How to use it

Tap the effort button (#effortpick) in the row under the composer, right of the model. It shows the value, or auto.
The slash panel opens on Models, with the Effort slider above the search bar. Drag along it or tap a stop to choose an effort. Tap the effort button again to close the panel. Your draft stays as you wrote it.

The model button opens this panel too. On a model with effort levels, an Effort slider sits over the search bar when the panel shows Models: auto at the left end, then the model's levels. Drag along it or tap a stop. The effort is set when you let go, and the panel stays open so you can pick a model next. A model with no levels shows no slider. On a model with fast mode, the Fast switch sits under the slider: see fast-mode. Star the current model after setting its effort to save both, with the harness, in Favourites. You can save the same model at several efforts. Each favourite shows its effort on the right as a word and a five-bar meter, grey to red. If the button is enabled but there are no slider stops, it opens the effort list so you can choose auto.

Or type /effort and the menu becomes the same list of efforts as soon as the word is finished (no space needed), filtering as you type. It works at the end of a message already written too: picking an effort there sets it and takes /effort out of the draft, leaving the message. Send /effort on its own to see the current value, or /effort high to set it directly.

What you see

The button's label is the value itself, dimmed and reading auto when unset.
The tooltip is Effort: high, or Effort: let the agent decide when nothing is set.
On a model with no effort levels (claude's Haiku, some opencode models) the button is disabled and its tooltip is This model has no effort variants.
/effort with no argument answers with a toast: effort: high, or effort: default.
With nothing set the tick is on auto. Unlike the model, no agent reports an effort back, so the tick only ever follows what you set.

Options and settings

The levels are the ones the agent's CLI lists for the model this tab runs, plus default (auto: let the agent decide). With the model on auto, the menu lists every level any of the agent's models has. On opencode, which takes an effort only for a model it knows, a tab on auto offers auto alone.

Agent	Where the levels come from
claude	The effort levels the CLI lists per model: `low` to `max` on Opus, Fable and Sonnet today, none on Haiku
codex	The reasoning efforts the CLI lists per model, which can include `ultra`
opencode	The variants opencode lists for the model, applied as `model/variant`

The lists refresh with the models: see update-from-a-tab.

Limits and known gaps

On claude, effort is a session flag, so changing it restarts the agent process. The next start resumes the same vendor session, so nothing is lost.
On codex, effort rides on turn/start and lands on the next message with no restart.
On opencode, choosing a variant the model does not have is refused before it is sent: model <id> does not support effort xhigh; supported: auto, low, high. If opencode itself rejects it, the error gains ; choose auto or another effort supported by this model.
A model with no effort levels disables the button, with the tooltip This model has no effort variants. A new tab drops an effort its model has no levels for.
A change made mid-turn applies from the next turn.
The button is disabled with no tab open.
Changing the model can change which efforts exist, which is why the model button sits to the left of this one.