How-to guide

Understand tokens and budgets

The composer shows the current context size; expand its metrics to see Trace, Input, Output and Sum. Large values use k; hover for the fuller value and available counting detail.

Metric	Meaning
Context	The active model request's context, not the sum of every request
Input	Accumulated input usage; repeated context can be counted again on later calls
Output	Accumulated model output usage
Sum	Input plus output
Requests	Number of model requests included in the displayed turn's accounting
Elapsed	Time spent on the displayed turn, including tool work and waits

Provider-native counts are used when supported. Unsupported or unavailable counters remain approximate. Cached-input billing and total input tokens are different concepts; these pills are not a currency invoice. After compaction the active context can shrink while cumulative Input continues to rise.

Controls

In Settings → Budgets, Composer context tokens is a fallback when a model's measured window is unavailable. Output tokens per model call limits an individual reply; leave it blank for the native allowance. A smaller output budget may cut a useful reply short.

Max parallel agents limits simultaneous agents. Progress timeout is renewed by authoritative operation or workspace progress; it is not a fixed total duration for productive work. Document controls are explicitly labelled in characters and govern extraction, not model token accounting.

The compaction threshold is under Settings → LLM → Advanced → Compact context at (%). Compaction makes room by condensing older context and retaining access to the transcript and stored evidence. It is not a reset of the task or its usage totals. See Context and compaction.