Commit Graph

2770 Commits

Author SHA1 Message Date
lilleman 08d4be4bae Answer stability round 1: 0 🔴, 1 🟡 (0 misread); print each round's opening line, not a label read off it, and sort the allowlist entries 2026-11-12 11:53:55 +01:00
lilleman b2ddebce7a Answer security round 1: 0 🔴, 0 🟡 (0 misread); un-ignore stability-skip-count/, which the allowlist left out
CI / tests (pull_request) Successful in 2m39s
2026-11-12 11:40:57 +01:00
lilleman a61afc567d Commit the stability skip count that item 308's decision rests on
CI / tests (pull_request) Successful in 2m38s
2026-11-12 11:40:07 +01:00
lilleman b03bfab121 Answer stability round 2: 0 🔴, 0 🟡 (0 misread); no finding
CI / tests (pull_request) Successful in 2m36s
2026-11-12 11:35:10 +01:00
lilleman 2294916343 Answer prose round 1: 0 🔴, 6 🟡 (0 misread); fixed in the stability answer: the changelog bullet, the decision's title and count, the rule's sentences, the re-entry pointer and Done's clause 2026-11-12 11:33:53 +01:00
lilleman c010b12c5a Answer product-owner round 1: 0 🔴, 3 🟡 (0 misread); fixed in the stability answer: a run that fails is fixed again, a round needs a 🔴, the findings ask only for a kill or a pass, and the answer commit records the clean run 2026-11-12 11:33:53 +01:00
lilleman 6ff139f67c Answer stability round 1: 1 🔴, 2 🟡 (0 misread); require every 🔴 and 🟡 to be mechanical, keep the named test as found, recount the archive, and say which passes still rerun 2026-11-12 11:33:53 +01:00
lilleman 7b0e428eec Answer security round 1: 0 🔴, 0 🟡 (0 misread); no finding 2026-11-12 11:28:34 +01:00
lilleman dd7e9b9929 Skip a stability round 2 whose every 🔴 named a surviving mutant or a failing test
CI / tests (pull_request) Successful in 2m12s
2026-11-12 11:27:46 +01:00
lilleman 02bde923e5 Answer prose round 1: 0 🔴, 9 🟡 (0 misread); fixed in the stability answer: the decision's margin figures, title and actors, the help's bar clause, and item 321's detail
CI / tests (pull_request) Successful in 2m37s
2026-11-12 11:21:27 +01:00
lilleman 87ffd81d21 Answer product-owner round 1: 0 🔴, 2 🟡 (0 misread); fixed in the stability answer: whole counts in the report, and the help says a replay fails 2026-11-12 11:21:27 +01:00
lilleman 2770de2744 Answer stability round 1: 0 🔴, 7 🟡 (0 misread); hold a rung to a whole count of findings, tell a 🔴 by its opening mark, test the second reference replay failing alone, and share the candidate rungs 2026-11-12 11:21:19 +01:00
lilleman 058f4ca7aa Test the reference replays apart, a round one of them failed on and a reference that found nothing; drop share's dead guard 2026-11-12 11:01:49 +01:00
lilleman d55b1e4ad5 Answer security round 1: 0 🔴, 0 🟡 (0 misread); no finding 2026-11-12 10:54:38 +01:00
lilleman 4fc822c346 Record the prose replay under the new bar, which qualified no rung, and finish item 318
CI / tests (pull_request) Failing after 2m39s
2026-11-12 10:54:01 +01:00
lilleman cbe99537e2 Qualify a review-replay rung by the project's rung's own recall, trying the project's model at lower efforts first 2026-11-12 10:39:40 +01:00
lilleman fa54ed46b1 Answer prose round 1: 0 🔴, 7 🟡 (0 misread); rename Record to Annotation, and reword the decision, the help and the changelog
CI / tests (pull_request) Successful in 2m37s
2026-11-12 10:25:30 +01:00
lilleman 72d9a9f652 Answer product-owner round 1: 0 🔴, 2 🟡 (0 misread); print the report before exiting 1 on an unreadable archive, naming the file 2026-11-12 10:25:30 +01:00
lilleman d449c552c6 Answer stability round 1: 0 🔴, 2 🟡 (0 misread); keep the whole typed answer that holds the judge's quote of a reversal, and test a failing rev-parse 2026-11-12 10:25:30 +01:00
lilleman 67e272d5ef Answer security round 1: 0 🔴, 0 🟡 (0 misread); no finding 2026-11-12 10:10:29 +01:00
lilleman ec0b17b03f Sort the new modules' imports, and test a reversal count where every chunk holds one 2026-11-12 10:09:19 +01:00
lilleman 1fc7bf0f52 Kill the surviving mutants of the spend, the setup version and the reversal count, and keep a subagent's type on one line 2026-11-12 10:03:47 +01:00
lilleman 3c4cedd389 Record with each archived verdict the setup that ran it, what each model spent by kind, and the human's reversals
CI / tests (pull_request) Failing after 2m12s
2026-11-12 09:57:56 +01:00
lilleman 8dc82fcf95 Finish items 325, 326, 336, 295, 332 and 334
CI / tests (pull_request) Successful in 2m36s
2026-11-12 09:35:12 +01:00
lilleman 1f8b33d485 Answer stability round 2: 0 🔴, 4 🟡 (0 misread); claudeMdExcludes is read from the user's settings too and covers rule files, and the mutants it names are killed 2026-11-12 09:34:49 +01:00
lilleman 1d1172098f Kill the surviving mutants of claudeMdExcludes and wait-for's half-line cut
CI / tests (pull_request) Successful in 2m11s
2026-11-12 09:20:11 +01:00
lilleman 58133e69fe Answer stability round 1: 1 🔴, 12 🟡 (0 misread); wait-for waits out a half-written line, prepare-scoring honours claudeMdExcludes, and a merge by another method waits for the checks
CI / tests (pull_request) Successful in 2m38s
2026-11-12 09:13:37 +01:00
lilleman 37f19d1677 Kill the surviving mutants of run-tests and wait-for, and name a file wait-for cannot read
CI / tests (pull_request) Successful in 2m38s
2026-11-12 09:04:32 +01:00
lilleman 22942308f6 Answer prose round 1: 0 🔴, 9 🟡 (0 misread); the pin comment, run-heavy's background line and the panel's setup sentence read once 2026-11-12 09:04:32 +01:00
lilleman eaa67bfcd9 Answer product-owner round 1: 0 🔴, 5 🟡 (0 misread); merge allows a minute for checks to report, prepare-scoring replaces a stale setup, and the skill runs merge in the background 2026-11-12 09:04:28 +01:00
lilleman c04864b6f0 Sort the new imports, narrow prepare-scoring's git results, and take run-tests' worker count from the heavy slot
CI / tests (pull_request) Successful in 2m20s
2026-11-12 08:56:39 +01:00
lilleman 90773cfa5f Add larv-review prepare-scoring, which sets up a scoring run's worktree and seat prompts that record-scoring then removes
CI / tests (pull_request) Failing after 2m38s
2026-11-12 08:53:23 +01:00
lilleman f299bf332b Let deploy-release move a settings.json that differs only by a model pick or key order 2026-11-12 08:47:04 +01:00
lilleman 876e0afb45 Reuse deploy-release's checks wait in chunk-pr merge 2026-11-12 08:46:19 +01:00
lilleman 6e2656d83d Have chunk-pr merge wait for the required checks, and name sync, ready's title and wait-for in the docs 2026-11-12 08:45:10 +01:00
lilleman 2ab44beca2 Add chunk-pr sync and wait-for 2026-11-12 08:43:14 +01:00
lilleman 0d32cab386 Let chunk-pr ready take the pull request's final title 2026-11-12 08:41:20 +01:00
lilleman e86a0cbc0c Print each failing test's error lines, which pytest-xdist leaves out of the short summary 2026-11-12 08:41:13 +01:00
lilleman e4e3d8cff0 Add run-tests, which runs the suite as README → Test says and saves the whole log 2026-11-12 08:39:35 +01:00
lilleman b19ecc459e Record the reading-cost figures 2026-11-12 08:37:59 +01:00
lilleman afba2d0bbb Kill the surviving non-UTF-8 mutant of todo-item show
CI / tests (pull_request) Successful in 2m33s
2026-11-12 08:29:05 +01:00
lilleman bf0f0c5ecf Answer product-owner round 1: 0 🔴, 0 🟡 (0 misread); item 338's detail names the shipped flag, and --calls=<file> stays refused
CI / tests (pull_request) Successful in 2m16s
2026-11-12 08:23:35 +01:00
lilleman 9efcdab4f8 Answer prose round 1: 0 🔴, 6 🟡 (0 misread); the docstrings and the CLAUDE.md bullet read once, in order 2026-11-12 08:23:35 +01:00
lilleman 9439d7ec5c Answer stability round 1: 0 🔴, 2 🟡 (0 misread); show reuses item_details and reads todo.md alone, and the --calls file is owner-only 2026-11-12 08:23:35 +01:00
lilleman 0ca23f5612 Warn that a --calls file may carry a secret
CI / tests (pull_request) Successful in 2m32s
2026-11-12 08:17:42 +01:00
lilleman 7b93108618 File the tooling research round's items, and finish items 312, 335 and 337
CI / tests (pull_request) Successful in 2m14s
2026-11-12 08:14:33 +01:00
lilleman ed914030f8 Kill the surviving mutants of todo-item show 2026-11-12 08:12:29 +01:00
lilleman 34689413ac Show an item with todo-item show, and save each call with command-patterns --calls 2026-11-12 08:06:53 +01:00
lilleman 5ccb51f763 Finish item 315
CI / tests (pull_request) Successful in 2m32s
2026-11-12 07:58:30 +01:00
lilleman 4132d8cf18 Answer prose round 1: 0 🔴, 6 🟡 (0 misread); the decision's figures match its table and the hook's sentences read once 2026-11-12 07:57:04 +01:00