The hurdles Braid put in front of its agents in runs 174-179 go (#407) #408
Loading…
Reference in a new issue
No description provided.
Delete branch "issue-407-run-hurdles"
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?
Closes nothing yet: braid#407 closes after the vLLM run named below.
Runs 174 to 179 took 621 agent minutes, apply 233 and the Visual check 168. Every transcript was read (
docs/design/measurements/2026-11-07-runs-174-179-efficiency.md); the minutes went to hurdles, not the work. The owner reviewed the proposals one by one; this is the kept set, as the OpenSpec changerun-hurdles-174-179.What changes
openspec.applystarts a session of its own; the build chain begins at it.window.__appnames, the start command and whether it reloads, the screenshots folder), and says to read no source outside the delta's files. 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(the server already runs isolated, so a close is a wipe); each person is opened in anisolatedContext.OSF_BRAID_CLOCK=0leaves it out). The motion probe steps and pauses it with the animations, so a frame holds however many turns a screenshot takes. An animation the specs name is judged from a filmstrip of five captioned frames (osf.engine.filmstrip).filland skips disabled controls.playfield issession(the console reads either); a source-level test holds the text to that and to a size ceiling.ban-checkis scoped to the run's lines, andagent.write-spec-testsand its three sim scenarios go.qwen3.8-27b's recommended output is 32,000, where production already is.node_modules/.binon theapptool's PATH;NODE_PATHfor$TMPDIRscripts; a glob from the run root into screenshots or tmp lands there; new files pasted into the code review's brief; the hook kept by the fix and review steps.Verified
./tools/test.shgreen: 501 backend tests, 42 journeys, 24 s. New tests for the lint, the guard, the app tool's PATH, the run env, the judge's facts, the browser server's init script, the filmstrip, the clock (journeys), and the briefs' wording and size../tools/sim.sh --smokeandjudge-requirement-by-namegreen;solo,apply-single,apply-single-no-progressandfree-forksrewritten for the fresh apply.After merge: one vLLM run, read for 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. Then archive and close braid#407.
🤖 Generated with Claude Code