diff --git a/app/WORK.md b/app/WORK.md index 184c2234..f3b1535b 100644 --- a/app/WORK.md +++ b/app/WORK.md @@ -626,12 +626,16 @@ refusal; hide closing an open conversation + deep-link `markOpened`; run Summary `Pipeline` row as a link; `Open repaired export` link + recovery attempts line. Template provenance on runs is a server gap (no template origin recorded). -## Micro-lane contract (supersedes earlier budgets) +## Lane sizing (contextual, task-sized) -Pipelines overrun because a lane still owns a whole behaviour. New unit: -ONE function or widget change, at most ONE source file plus its test, and a -prompt that names the exact web symbol/line and the exact expected result. -No refactors, no multi-file wiring, no screen redesign inside a lane. Split -plumbing (wiring, routes, providers) into separate manager edits. Target under -10 minutes of Code; if a lane exceeds 20 minutes it is cancelled and its tree -is landed or split, not retried. +A task is one outcome an operator can see or an API client can observe, with +its own regression. File count follows the task: one file is fine, and a task +that truly needs three files (widget + call site + fixture) is still one task. +The line is unrelated work: no refactors, redesigns or extra behaviours riding +along, and no second outcome that could ship on its own. + +Size by uncertainty, not file count: if the outcome needs the reviewer to judge +a look, mock or probe, keep it small and put the evidence expectation in the +prompt. Target tens of minutes, not hours; if a lane exceeds ~20 minutes with +nothing landed, cancel it and land or split the tree. Plumbing (routes, +providers, composition) stays a manager edit.