79 Commits

Author SHA1 Message Date
lilleman 1559dcd6c9 Answer prose round 1: 0 🔴, 6 🟡 (0 misread); reword the help, docstrings, rule and item text 2026-11-18 16:35:03 +01:00
lilleman 83714f095c Refuse a Touches: list touch-predictions cannot read in todo-item add and edit, and in rank_todo.py --check 2026-11-18 16:17:23 +01:00
lilleman b6a53ef98b Answer prose round 1: 0 🔴, 7 🟡 (0 misread); say what an edit of a person's issue writes 2026-11-16 02:15:39 +01:00
lilleman 2e9d9dd714 Edit a Jira issue the loop filed, and score a teammate's with a comment saying why
CI / tests (pull_request) Successful in 1m48s
2026-11-16 01:55:57 +01:00
lilleman 4873ee9e74 Key project-record's copies per worktree
CI / tests (pull_request) Successful in 2m8s
2026-11-15 22:45:04 +01:00
lilleman b60d921427 Answer stability round 1: 1 🔴, 2 🟡 (0 misread); say in CLAUDE.md, the todo rule and the changelog that todo-item finishes an item in Jira, say that a move Jira didn't answer may have landed, and test a transition without a status category 2026-11-15 13:15:11 +01:00
lilleman 35f1f5e70f Answer stability round 1: 2 🔴, 2 🟡 (0 misread); count an item as filed once Jira holds it, try every link, say when a failed create may have filed, and drop README's stale sentence 2026-11-15 03:35:48 +01:00
lilleman 8e79cb7dc8 File a plan item as a child issue of the project's Jira epic 2026-11-15 03:16:11 +01:00
lilleman e171260c36 Answer stability round 1: 0 🔴, 6 🟡 (0 misread); leave blank lines and empty files out of what a chunk touched, spell a name that holds a backtick as Markdown does, pin two mutants, and sort a chunk's IDs 2026-11-15 03:03:49 +01:00
lilleman 3ea3d5427e Pick the chunks that may run at once by predicted parts, and record each prediction beside what the merged chunk touched
CI / tests (pull_request) Successful in 2m47s
2026-11-15 02:29:38 +01:00
lilleman 156d466703 Answer stability round 1: 0 🔴, 3 🟡 (0 misread); drop the caveat the plan listing outlived, name the listing in reviewer_header's docstring, shorten the help's new clause 2026-11-15 02:04:05 +01:00
lilleman 48e1e9dedc Define the plan as the store its config names and reword the lines that say todo.md where a Jira plan makes them false 2026-11-15 00:43:11 +01:00
lilleman 3a2d72a007 Answer stability round 1: 0 🔴, 4 🟡 (0 misread); keep goals in Jira to projects whose plan is there, test the reviewer header's Jira read, drop the repeated premises tests 2026-11-14 21:27:23 +01:00
lilleman 0cb2cbabcd Answer product-owner round 1: 0 🔴, 2 🟡 (0 misread); let the planner compare Scores in the file, name finish --no-changelog for a dropped item, name the plan's path in every refusal and exit 2 on a bad --release 2026-11-14 16:01:50 +01:00
lilleman 0ac8cad97f Route every read and write of the plan through plan_store and todo-item, which gains list, edit and move
CI / tests (pull_request) Failing after 2m13s
2026-11-14 15:15:25 +01:00
lilleman 9508838439 Answer prose round 1: 0 🔴, 9 🟡 (0 misread); name the five as project records, cut what CLAUDE.md already says, and reword the comments the round named
CI / tests (pull_request) Successful in 2m27s
2026-11-14 00:25:18 +01:00
lilleman 084bc74b1c Read and write each record through the store its config names, and open one for agents with project-record
CI / tests (pull_request) Successful in 2m14s
2026-11-13 23:54:04 +01:00
lilleman 7b6201cab6 Answer stability round 1: 0 🔴, 2 🟡 (0 misread); inject home into the goals file lookup and rename readme in ranking 2026-11-13 00:29:22 +01:00
lilleman eb61043c12 Read a project's goals and audience from the file its config names, in place of README.md
CI / tests (pull_request) Successful in 2m17s
2026-11-13 00:06:11 +01:00
lilleman c034c43259 Answer stability round 1: 0 🔴, 7 🟡 (0 misread); fail where the principles folder is missing or empty, say a reviewer without the header line reports it, fix the README and CHANGELOG lines the header made false, name the folder once as the config's principles folder 2026-11-12 23:40:35 +01:00
lilleman d96ea9ea3c Hand reviewers the technical principles from the folder a project's config names
CI / tests (pull_request) Failing after 2m11s
2026-11-12 23:21:31 +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 6d6876fbcf Answer prose round 1: 1 🔴, 7 🟡 (0 misread); state principle 6 as the code runs it, call them project principles, ask on every principle change
CI / tests (pull_request) Successful in 2m7s
2026-11-11 16:07:06 +01:00
lilleman c9a2c7b704 Propose a principle when a new decision shares its rule with decisions already listed
CI / tests (pull_request) Failing after 2m6s
2026-11-11 15:59:29 +01:00
lilleman 0c2f37d284 Distil 41 decision titles in AGENTS.md into seven principles, and say so where AGENTS.md's list is described 2026-11-11 15:57:43 +01:00
lilleman 118a7d22d3 Check each new decision against the project's principles, in rules/decisions.md and larv-review 2026-11-11 15:50:13 +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 02921d4174 Answer prose round 1: 0 🔴, 4 🟡 (0 misread); reword the help, todo-items rule and changelog; the ❓ on E and I is answered by item 116, which names L alone 2026-11-09 01:58:41 +01:00
lilleman f24a653a02 Answer prose round 1: 1 🔴, 2 🟡 (0 misread); the help fix went in the stability commit; say what finish does in CLAUDE.md, reword the changelog, README and rules lines 2026-11-09 01:51:27 +01:00
lilleman c47d65996e File and finish todo.md items with todo-item add and todo-item finish 2026-11-09 01:37:22 +01:00
lilleman 54b239d7f3 Answer prose round 1: 1 🔴, 10 🟡 (1 misread); give rule-hook's 30 seconds, reword the drop rule, its comments and the changelog, note in this title that three readers picked the Drop item spelling 3-0, rename two tests; the fork 🔀 went to the security pass, which ruled it below its bar 2026-11-09 01:19:34 +01:00
lilleman bd96cb7c03 Leave items a chunk drops by a 'Drop item' title out of score-outcomes, check this repo's branches with their own rank_todo.py, and test the replays' model, floor and checkout 2026-11-09 01:14:42 +01:00
lilleman 1a81b55925 Count each finished chunk's later fixes in score-outcomes and the routing figures 2026-10-28 19:27:09 +01:00
lilleman 453a8e3b94 Answer prose round 1: 0 🔴, 4 🟡; reword the contributor sentences 2026-10-21 22:26:19 +02:00
lilleman 2407689747 Make the contributor a standing member of every project's audience 2026-10-21 22:23:55 +02:00
lilleman fcf119ffec Answer prose round 1: 0 🔴, 11 🟡; make rank_todo.py's help and docstrings true for code health, define the overall before its use, split the changelog's upgrade steps into a list, retitle the todo.md decision so its bar attaches to the table, and fix the nits 2026-10-18 21:49:01 +02:00
lilleman eafcefe0da Answer stability round 1: 0 🔴, 6 🟡; pin the averaged overall with a second pair and a run with no Mean row, test a plan record-scoring reads but cannot rank, share rank_file between rank_todo.py and record-scoring, read the history path from HISTORY, make the comments and larv-review's help true 2026-10-18 21:12:19 +02:00
lilleman 390d1f1f83 Answer principles round 1: 0 🔴, 6 🟡; average the overall over the newest scored commit's runs, re-rank through rank_todo's functions and say not to record again, tie the help to UNDER_FLOOR and FLOOR, add code health to the working loop's premises, loop-claude's first prompt and two more agents, and fix items 114, 124 and 125's details 2026-10-18 20:29:19 +02:00
lilleman 8e0060be08 Answer architecture round 1: 1 🔴, 10 🟡; move FLOOR into comprehension_history, renumber the counter-signal item 198, void code health on a comprehension-check opt-out, add code health to every goal check, fail record-scoring on a failed re-rank, reuse overall_cells, and ease Scoring, parse_item and parse_moves 2026-10-18 20:04:36 +02:00
lilleman 2a961f267c State code health as every project's first achieve goal, weighed four times while the comprehension overall is under 7.0, unless a README voids it 2026-10-18 19:29:09 +02:00
lilleman 63392cea66 Answer prose round 1: 0 🔴, 6 🟡; record the rename rule in the decision log, cut false and duplicate clauses, rewrite the help and rules bullets, file the sweep as item 190 2026-10-18 09:56:53 +02:00
lilleman 1f0a046dd4 Answer stability round 1: 0 🔴, 2 🟡; name the rename fix in the finished message and the changelog, read a bad newest mark as unknown, refuse a self-rename, share the release parser, test the strip 2026-10-18 09:47:44 +02:00
lilleman 28a3f9c5e9 Answer architecture round 1: 0 🔴, 2 🟡; fail on a mark over a live release, pin the second run's reason wording, state the target is for the reader 2026-10-18 09:35:44 +02:00
lilleman ac33c733c7 Mark a renamed release in todo.md, so a release whose items moved unmarked reads as finished 2026-10-18 09:32:04 +02:00
lilleman 3f8f30ab2f Answer prose round 1: 0 🔴, 8 🟡; say every way the anchors are left out, name what a missing file shows, and untangle the scoring rule's lists 2026-10-16 20:08:14 +02:00
lilleman 1905ed5f2f Answer product-owner round 1: 0 🔴, 1 🟡; choose E and I anchors by the level's words, keep anchors to the project's rung, and pick anchors whose outcomes fit their level 2026-10-16 20:00:40 +02:00
lilleman 5d4f9d4c0b Anchor each level of L, E and I with shipped items, and have score-outcomes list them for a scorer to compare against 2026-10-16 19:37:55 +02:00
lilleman be855a7a03 Answer prose round 1: 0 🔴, 14 🟡; keep each routing reason in one entry, retitle the stability reviewer's decision, and say what each help line and comment means 2026-10-16 18:08:38 +02:00