Runs 174-179: the hurdles Braid puts in front of its agents, in one change #407
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
What happens. Runs 174 to 179 took 621 agent minutes: apply 233, Visual check 168. Reading every transcript (
docs/design/measurements/2026-11-07-runs-174-179-efficiency.md) shows the time goes to hurdles Braid puts in the way, not to the work: a session forked at 82-134k that restarts fresh, a judge that reads 15 files to learn what Braid could tell it, a contrast probe that fails every card face, one browser profile shared by every step and person, screenshots reported at a pathreadcannot open, a lint that fails an attempt over tag placement, and briefs that say "game" and "play" to a project that is neither.Fix, one change, reviewed proposal by proposal with the owner on 2026-11-07:
openspec.applystarts fresh, not forked from revise: the brief already carries everything.window.__appsettled: the code review keeps it, the proposal template asks for it.fill, skip disabled elements; a glyph the screenshot shows plainly passes.docs/design/measurements/work/runs-174-179/brief-sweep.md, and the judge'splayfield becomessession..../animation-judging.md).// spec:tag is documentation: accepted on the test, its describe or the file top; B6 stops blocking; the write-spec-tests fan-out goes; B1, B2 and B8 stay (relates to #268).efforts:map goes.node_modules/.binon theapptool's PATH;$TMPDIRscripts can find modules; the path guard allowsglobon the run folder it names; pasted code in the write-spec-tests and code-review briefs.Done when
./tools/test.shand./tools/sim.sh --smokeare green, a scripted replay of run 174's judge and apply steps shows the hurdles gone, and one vLLM run shows: apply starting under 20k, no screenshot path hunting, no probe entries on a card face, a round-1 judge of a change off the main flow not going through a whole session, and a filmstrip in a judge report.Shipped in PR #408 (merge
14a3a2db), archived as2026-11-07-run-hurdles-174-179.What shipped
openspec.applystarts a session of its own; the build chain begins at it.window.__appnames and their file, the start command and whether it reloads, the screenshots folder) and reads no source outside the delta. Round 1 goes through a whole session only for a change on the app's main flow; round 2 replays only for a file round 1's session evidence named.browser_close; each person is anisolatedContext.osf.engine.filmstrip).filland skips disabled controls.playfield issession.ban-check --base, noagent.write-spec-tests.qwen3.8-27brecommended output 32,000 (production raised the same day).node_modules/.binon theapptool's PATH,NODE_PATHfor$TMPDIRscripts, run-root globs land in screenshots or tmp, new files pasted into the code review's brief, the hook kept by fix and review.Evidence from the laptop
./tools/test.shgreen (501 backend tests, 42 journeys); new tests for the lint, the guard, PATH, the run env, the judge's facts, the init script, the filmstrip, the clock, and the briefs' wording and size, each failing before its fix../tools/sim.sh --smokeand the judge scenario green; four scenarios rewritten for the fresh apply.The next thorough run on vLLM is read for the five signs in Done when; anything it exposes is a new issue.
browsercheck takes 5 to 7 minutes #419