Commit Graph

565 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 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 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 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 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 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 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 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 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
lilleman 2db70062dc Keep omitClaudeMd on principles-auditor alone, the one pass that met the replay gate, record the gate's results and file item 340
CI / tests (pull_request) Successful in 2m51s
2026-11-12 07:45:23 +01:00
lilleman 2556fdace9 Answer prose round 1: 0 🔴, 7 🟡 (0 misread); the decision's scope, the changelog bullet and the prompts read once
CI / tests (pull_request) Successful in 2m30s
2026-11-12 05:30:15 +01:00
lilleman 66b9651d68 Bench the advisor tool on six archived L 1 and L 2 chunks: Sonnet alone passes as often as Opus at medium for less, so workers stay without it
CI / tests (pull_request) Successful in 2m18s
2026-11-12 04:27:48 +01:00
lilleman 7a7dc4b75d Answer prose round 1: 0 🔴, 6 🟡 (0 misread); the decision's judge rule stated once, in the present tense
CI / tests (pull_request) Successful in 2m34s
2026-11-12 03:08:01 +01:00
lilleman c61997f7b7 Run the judge of an Opus 5.5 project on Opus 5.5 at xhigh in every chunk
CI / tests (pull_request) Successful in 2m35s
2026-11-12 02:54:03 +01:00
lilleman 79f6334c7f Answer stability round 1: 0 🔴, 1 🟡 (0 misread); name the search's lowest rung a candidate 2026-11-12 01:55:46 +01:00
lilleman 042f48a0f4 Replay the judge on the Fable 5.2 rungs a review climbs to, and keep it on Opus 5.5 rungs after each missed an interrupt
CI / tests (pull_request) Failing after 2m52s
2026-11-12 01:40:34 +01:00
lilleman 6e67cc59fa Answer stability round 1: 0 🔴, 7 🟡 (0 misread); placeholder rungs in docstrings, rung-free test names, the decision note and changelog name every move 2026-11-12 00:20:18 +01:00
lilleman 8e46ef69b1 Rebuild the routing ladder for Fable 5.2 from the index read 2026-11-11
CI / tests (pull_request) Successful in 2m36s
2026-11-12 00:04:08 +01:00
lilleman 2ca4d0f8db Drop item 313
CI / tests (pull_request) Successful in 2m34s
2026-11-11 23:23:30 +01:00
lilleman aacfe7d3d3 Answer stability round 2: 0 🔴, 3 🟡 (0 misread); keep item 313 as a question for the human, restore the decision's expiry, and make the sweep list general
CI / tests (pull_request) Successful in 2m28s
2026-11-11 22:35:08 +01:00
lilleman f5201cb638 Answer prose round 1: 0 🔴, 9 🟡 (0 misread); record why item 313 was dropped, tighten the decision's evidence and reorder the changelog 2026-11-11 22:31:39 +01:00
lilleman b1037248a5 Items 270, 313, 317: the worker runs tests, static analysis and a docs sweep before each stability round; launch one agent of a type before the rest; one-line reviewer descriptions
CI / tests (pull_request) Successful in 2m24s
2026-11-11 22:22:06 +01:00
lilleman 6a803b168b Answer prose round 1: 0 🔴, 6 🟡 (0 misread); state the decision's evidence with its scope, and say the checks before review instead of a gate 2026-11-11 21:12:13 +01:00
lilleman 7afc59a9d7 Merge remote-tracking branch 'origin/main' into item-293
# Conflicts:
#	AGENTS.md
#	agents/stability-reviewer.md
#	docs/reading-cost.md
#	todo.md
2026-11-11 19:24:50 +01:00
lilleman a52ebb94bf Run mutation tests on a chunk's changed lines before review with bin/mutate-changes, and hand stability-reviewer the survivors
CI / tests (pull_request) Successful in 2m14s
2026-11-11 18:58:31 +01:00
lilleman e7128656b2 Answer stability round 1: 0 🔴, 4 🟡 (0 misread); ask for the Chunk items: line on resume too, split it on "and", and say on stderr why todo.md scores no item 2026-11-11 18:16:14 +01:00
lilleman daa3a54b90 Have loop-claude read the items a chunk takes from the worker's Chunk items: line, and keep the judge's escalation and release-ready fields, which code misread in replays
CI / tests (pull_request) Successful in 2m7s
2026-11-11 17:43:40 +01:00
lilleman d41dfd0401 Answer stability round 2: 0 🔴, 1 🟡 (0 misread); move this repo's working rules into the decision log, which the judge reads 2026-11-11 16:53:42 +01:00
lilleman dcb9abf644 Answer stability round 1: 1 🔴, 3 🟡 (0 misread); keep the global rules generic, and say in one always-loaded rule of this repo where AGENTS.md's parts went 2026-11-11 16:46:27 +01:00
lilleman 9b770e4893 Fold AGENTS.md into the decision log, .claude/rules/, README and the panel's seat prompts; load CLAUDE.md once in this repo
CI / tests (pull_request) Successful in 2m7s
2026-11-11 16:32:48 +01:00
lilleman 84d23fa95c Answer stability round 1: 2 🔴, 3 🟡 (0 misread); check AGENTS.md's remaining titles against the log, fix the citation, the prose-reviewer move rule and the worker decision 2026-11-11 16:07:06 +01:00
lilleman 47c10c4565 Answer prose round 1: 0 🔴, 5 🟡 (0 misread); reword the help paragraph, the changelog bullet and the decision, and restore the entry's old sentence 2026-11-11 14:19:48 +01:00
lilleman 3e289c95d9 Check the files a commit would commit against rule-hook's file rules, and sort .gitignore's allowlist block
CI / tests (pull_request) Failing after 2m2s
2026-11-11 14:07:34 +01:00
lilleman 09caf3576f Answer stability round 1: 0 🔴, 1 🟡 (0 misread); move the 2026-11-11 paragraph to the end of the entry 2026-11-11 13:46:27 +01:00
lilleman 7fb019914e Reword the blocks-no-merge decision titles to say no score blocks a merge
CI / tests (pull_request) Successful in 2m3s
2026-11-11 13:43:15 +01:00
lilleman 6440824f27 Drop item 52: obsolete 2026-11-10 23:03:05 +01:00
lilleman 70a1b95086 Answer architecture round 1: 0 🔴, 4 🟡 (0 misread); move the shared loop state out of loop_claude, split ranking and routing, give the reviewer rung one rule
CI / tests (pull_request) Successful in 2m14s
2026-11-10 22:03:16 +01:00
lilleman cfd3008615 Give the test commands their own README section 2026-11-10 11:24:44 +01:00
lilleman 034356f34b Answer prose round 1: 0 🔴, 2 🟡 (0 misread); the sentence says the 0.5 outweighs each achieve goal of fejkdata and names when to revisit it
CI / tests (pull_request) Successful in 2m14s
2026-11-10 10:04:15 +01:00
lilleman c638ad7aec Record that the maintain weight of 0.5 stays fixed until a project's ranking shows it distorted
CI / tests (pull_request) Successful in 2m35s
2026-11-10 10:02:25 +01:00
lilleman b58916ae71 Answer prose round 1: 0 🔴, 13 🟡 (0 misread); state the decision's figures as the trials ran them, fix item 289's tagline and wording and the scripts' docstrings and comments
CI / tests (pull_request) Successful in 2m3s
2026-11-09 22:51:02 +01:00
lilleman 3bf00dace7 Answer stability round 1: 0 🔴, 2 🟡 (0 misread); shorten the decision's title to the decision, and drop the log example, where both rules pick the same commit 2026-11-09 22:49:47 +01:00
lilleman b91c2ee84d Keep the reviewer-merge trials' method, results and scripts, and record that each pass keeps a reviewer of its own
CI / tests (pull_request) Successful in 2m16s
2026-11-09 22:43:47 +01:00
lilleman aebe45ef5e Answer stability round 1: 0 🔴, 2 🟡 (0 misread); give a maintain goal's weight one owner, weight_of, and fix the stale note on a README with no achieve goal 2026-11-09 12:04:30 +01:00
lilleman cef13bb354 Let an item name a maintain goal by the confidence a test, gate leg or probe adds, weighed 0.5 per point
CI / tests (pull_request) Successful in 2m7s
2026-11-09 11:59:07 +01:00
lilleman da4d376136 Answer prose round 1: 0 🔴, 7 🟡 (0 misread); define a subcommand word in command-patterns' help and split its table sentence, point the bin/ decision at the CI entry by name, leave ci.sh's pinned details to its header, say what a CI rule check needs, and split the two argument errors
CI / tests (pull_request) Successful in 2m47s
2026-11-09 03:09:41 +01:00
lilleman d62857f20e Answer product-owner round 1: 0 🔴, 1 🟡 (0 misread); name the checks main requires in the waiting line, give up after 30 minutes naming a required check that never passed, and match a required check as Gitea's glob; stability's branch-endpoint fix and prose's 'to the tag' ride along 2026-11-09 03:05:11 +01:00
lilleman a88f74f5ac Record CI and main's protection in the decisions, hold ci.sh's image to README's Python, and say so in README
CI / tests (pull_request) Successful in 3m10s
2026-11-09 02:50:26 +01:00
lilleman 823834da06 Answer stability round 1: 0 🔴, 2 🟡 (0 misread); state trigger 4's exception as one split, prose only, in CLAUDE.md, the decision's title, AGENTS.md and its routing paragraph, and say in §3 that a docstring is prose 2026-11-09 01:30:22 +01:00
lilleman ec7ee62b36 Let a worker fix a quality finding whose fix changes only prose on its own rung 2026-11-09 01:25:26 +01:00