Run 192: trial of apply groups side by side (braid#306) #484
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 this is: run 192 applies run 189's brief side by side (
parallel, at most 3 groups at once), from run 189's starting commit, on productionfb12307. It is the trial for braid#306. Repository:braid-testing/scratch-parallel-190, thorough, auto-approve, vLLM qwen3.8-27b. Runs 190 and 191 were stopped within seconds: I put the setting back before they had kept it.To measure against run 189 (660 min, apply groups 528 min):
Also checks braid#481 in a full run: browser tests run by the group that writes them, attempts lost to the now-blocking text-only rule, and the code review using helpers first.
Findings arrive below.
Run 192: result
Succeeded in 403.5 min against run 189's 660, with 446 agent minutes against 659, merged with no fix left. Lanes went red once on the lint, the Visual check failed 1 of 27 once, and round 3 passed 27 of 27.
styles.css), resolved by the agent in 4.9 minSide by side saved about 35 to 40 minutes: groups 1 and 2 ran inside group 3's 94 minutes, and group 3 ran about 18% slower while they did. Two agents gave about 1.6 times the work of one. Most of the 257 minutes saved came from elsewhere: a plan with less work in it, and no group 7 spending two hours on browser tests nobody had run. After group 3, the plan chained groups 4 to 7, so nothing more could overlap.
braid#481 in a full run
--list(below)openspec/linetested_bytested byentryProblems, worst first
const html = readFileSync(index.html); two others setconst html = renderRoom(...), and the rule treats everyhtmlin the file as file text. Two of round 1's three failures were false. The fix round moved them into the browser test (7.2 min, another lane round, a slower suite). Fix: judge the names a test reads within that test.code-reviewis missing fromDELEGATION_WHOLE, sohas_subagentis false and the "read the change throughreader" line never renders. That explains runs 189 and 192 using none. The #474 test replacedhas_subagentand hid it.brief_pathuses the worktree's parent plustmp, which for a group's worktree isgroups/tmp. 11 reads were refused across groups 3, 5, 6 and 7. Group 3 then tried to run Braid's package to learn the hand-over format. Fix: the run's owntmp.--listfor the task that writes the browser test. It read "NO task to run the whole suite" as overriding the new clause. Group 7 ran its tests anyway, because the apply brief says to.session.test.ts's "bot pacing" comparesDate.now()differences, and it failed once under load in group 1. The lint catches fixed waits but not timing assertions.game-table/Self-hosted faceswith "I looked" as the reason and failed at the end. The retry took 9 minutes, after reading the help file.pkill -f, which matches any such process the agents' user owns: a sibling group's or another run's (braid#201). The fixed port 4173 would also collide between groups.Runs 190 and 191 were stopped within seconds: I put the apply mode back before they had kept it.
The owner went through these one at a time. The approved fixes are filed as braid#485. Left out: checking the hand-over files when written, and refusing pkill. More side-by-side work waits for isolated environments (braid#201, braid#203).
Closing. Run 192 ended and the owner went through its findings (above). The approved fixes shipped as braid#485 and are on production (
f27905f).What is left of side by side stays on braid#306, paused until agents run in isolated environments (braid#203). The next full run measures the #485 fixes on its own findings issue.