lilleman
|
bfde3ffecb
|
Answer prose round 1: 0 🔴, 6 🟡 (0 misread); the comments, the presentation and the routing decision state the new steps
CI / tests (pull_request) Failing after 3m51s
|
2026-11-17 08:41:04 +01:00 |
|
lilleman
|
64ab847b0a
|
Bind a project's rung to its ladder in ProjectRung, and step an L 3 worker one rung up and an L 4 worker two up
CI / tests (pull_request) Failing after 3m48s
|
2026-11-17 08:12:16 +01:00 |
|
lilleman
|
f58250d0ce
|
Answer architecture round 1: 4 🔴, 5 🟡 (0 misread); one-way plan packages with a plan core and an Atlassian client, one parse and print of an item's cells, a pure chunk-start decision, a settings table, one plan read and one standing per pick, one config load in chunk-pr, notifier backends in notifier, and the bin regroup filed as item 392
|
2026-11-16 14:47:46 +01:00 |
|
lilleman
|
eecb0387ca
|
Run each chunk in its own tmux window, up to parallel-chunks at once, and mark a window that waits
CI / tests (pull_request) Failing after 2m56s
|
2026-11-16 11:59:45 +01:00 |
|
lilleman
|
bedd304479
|
Merge remote-tracking branch 'origin/main' into patch-0.10.1
# Conflicts:
# CHANGELOG.md
# README.md
# bin/loop_claude/loop/chunk_start.py
# bin/loop_claude/loop/close.py
# bin/loop_claude/loop/main.py
# bin/loop_claude/routing.py
# bin/loop_claude/test_loop_claude.py
# bin/project_config/main.py
# bin/project_config/test_project_config.py
# docs/decisions.md
|
2026-11-15 19:54:42 +01:00 |
|
lilleman
|
0a20b6d4f6
|
Read the routing ladder from routing-ladder.json, which a project replaces with a file of its own in its config's folder
CI / tests (pull_request) Successful in 2m37s
|
2026-11-15 18:51:59 +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
|
ade48c57b5
|
Answer stability round 1: 0 🔴, 6 🟡 (0 misread); test each failure path the review added, and return a Failure from prepare-scoring's reads
CI / tests (pull_request) Successful in 2m59s
|
2026-11-13 03:40:18 +01:00 |
|
lilleman
|
ee241646e7
|
Answer prose round 1: 0 🔴, 13 🟡 (0 misread); make each docstring say what its function now does, and sort the README's text_files bullet
|
2026-11-13 03:17:15 +01:00 |
|
lilleman
|
e1ca619e96
|
Name the four kinds of breach, the two level rules and the round title's spelling, and table the step-up rules
|
2026-11-13 02:45:35 +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
|
58517a0c54
|
Pick the judge's highest rung with highest()
CI / tests (pull_request) Successful in 2m33s
|
2026-11-12 02:59:50 +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
|
998e295ef9
|
Answer prose round 1: 0 🔴, 9 🟡 (0 misread); docstrings say what the code does, and each fact sits in one place
|
2026-11-10 22:32:49 +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
|
8d9a39de1c
|
Group bin's root modules into packages named by purpose, and make rank_todo.py a launcher of release_plan/ranking.py
|
2026-11-08 20:35:52 +01:00 |
|
lilleman
|
452a0c4271
|
Answer architecture round 1: 1 🔴, 12 🟡 (0 misread); route every verdict through next_route with one step-up writer, give a release one home in release.py and rename chunk_pick to release_standing, split loop/main.py, delete the unreachable lowered-pass code, render agent-followed Markdown from one list, refuse a round title naming no pass, and rename the clashing names
|
2026-11-04 22:57:30 +01:00 |
|
lilleman
|
dcdb8b5868
|
Answer architecture round 1: 0 🔴, 7 🟡 (0 misread); hold one lock per loop for its whole run, group the judge's readings of the items taken in, list them as given
|
2026-10-29 20:23:07 +01:00 |
|
lilleman
|
f781ac611b
|
Answer principles round 1: 0 🔴, 1 🟡; rename the module escalation_mark.py so it no longer shares the escalation field's name
|
2026-10-23 05:07:30 +02:00 |
|
lilleman
|
bf8b642ead
|
Answer architecture round 1: 0 🔴, 2 🟡; rename Step to StepUp and let escalation.py own the judge's step-line sentence
|
2026-10-23 04:54:45 +02:00 |
|
lilleman
|
f0e14f3fdf
|
Hold the escalation mark in one module, and carry a ruling's step through the cycle's states
|
2026-10-23 04:45:03 +02:00 |
|
lilleman
|
a4071f59ce
|
Answer prose round 1: 0 🔴, 1 🟡; state the help's step-up rule as the code holds it, and reword the docstrings and the changelog entry
|
2026-10-23 03:20:54 +02:00 |
|
lilleman
|
a81f878f92
|
Answer principles round 1: 0 🔴, 5 🟡; make the routing.py and prompts.py module docstrings true and short, drop the routing_check copy of the figures, rename judge_rung's local, and keep the help's 20
|
2026-10-23 03:10:31 +02:00 |
|
lilleman
|
3b69ced357
|
State each routing rule once in the docstring of the code that enforces it, cut loop-claude --help's routing paragraph, and name the project's rung project in bin/loop_claude
|
2026-10-22 22:42:01 +02:00 |
|
lilleman
|
f6594bc048
|
Answer principles round 1: 0 🔴, 2 🟡; block item 218 on item 170, name record_fields and RECORD_FIELDS, say an unreadable Worker line on stderr
|
2026-10-22 22:12:29 +02:00 |
|
lilleman
|
cb48719493
|
Answer architecture round 1: 0 🔴, 4 🟡; move verdicts out of cycle, derive RECORDED, type the archived worker as Record, drop stale help names
|
2026-10-22 22:00:09 +02:00 |
|
lilleman
|
851d7d7c79
|
Archive the route as a JSON record, hand routing the verdict, and name after_unfinished and the judge's highest levels taken in by what they do
|
2026-10-22 21:46:36 +02:00 |
|
lilleman
|
f0ece378c0
|
Give todo_table.items one way to say a plan has no items table
|
2026-10-22 00:32:30 +02:00 |
|
lilleman
|
5bc3247aec
|
Answer stability round 1: 1 🔴, 7 🟡; check an escalation against the worker's own lines after the mark, cover the escalated and capped steps
|
2026-10-18 14:08:16 +02:00 |
|
lilleman
|
2bba66ac0a
|
Answer architecture round 1: 0 🔴, 6 🟡; show the judge the mark, carry the entries read on the verdict, name the checked texts
|
2026-10-18 13:50:06 +02:00 |
|
lilleman
|
3a8e4e6f75
|
Accept an escalation quote only from transcript entries after the worker's last step-up
|
2026-10-18 13:24:05 +02:00 |
|
lilleman
|
e9cc88ed27
|
Answer principles round 1: 0 🔴, 4 🟡; one class per standing, cases in the table, test chunk_start's open session and the earlier-release case
|
2026-10-18 10:53:12 +02:00 |
|
lilleman
|
6cdace6ae3
|
Move the next chunk's pick into chunk_pick, so git_repo only runs git and todo_table only parses the plan
|
2026-10-18 10:33:36 +02:00 |
|
lilleman
|
5b536afdf9
|
Answer stability round 1: 0 🔴, 5 🟡; tell the resumed worker its stepped rung, rename the step for rulings, build NAMES_A_WORKER from the verdict constants, and test the capped answer and a failed interrupt archive
|
2026-10-17 22:37:11 +02:00 |
|
lilleman
|
602a5fac16
|
Answer principles round 1: 1 🔴, 2 🟡; name the worker's rung on an interrupt and archive its step-up at once, step from the taken-in item, drop every escalation after the first step of a cycle, and state stepped's rules once
|
2026-10-17 22:10:33 +02:00 |
|
lilleman
|
1c503e8818
|
Step the worker up as the judge interrupts when the run also cites an escalation trigger
|
2026-10-17 21:57:11 +02:00 |
|
lilleman
|
5ba8920dbf
|
Answer stability round 2: 0 🔴, 2 🟡; take the next release as the earliest todo.md has named since the last cut, so an emptied patch or a major jump stops the loop too, count work landed by the Unreleased entries before commits, read the default branch once, and test the emptied release and the stalled origin through real git
|
2026-10-17 02:34:15 +02:00 |
|
lilleman
|
4cf3c2bd8c
|
Answer architecture round 3: 0 🔴, 1 🟡; pick the next chunk's item in one function, todo_table.chunk_item, which routing and the preflight both call, so routing names no item where the release after the last cut has none
|
2026-10-17 02:19:11 +02:00 |
|
lilleman
|
f9615cb3b0
|
Run a preflight before each fresh worker and put its facts in the worker's prompt
|
2026-10-17 00:29:24 +02:00 |
|
lilleman
|
6df1833eb7
|
Answer architecture round 1: 0 🔴, 5 🟡; keep a taken-in E + I only where it lifts the reviewers, outside stepped, parse the archived line once, point the help at the code, and name the field one way
|
2026-10-16 23:45:11 +02:00 |
|
lilleman
|
8ffb1979ea
|
Route the judge and the reviewers on the highest E + I in their chunk, an item the worker takes in included
|
2026-10-16 23:36:39 +02:00 |
|
lilleman
|
886c864521
|
Answer principles round 1: 0 🔴, 9 🟡; drop a route handed under R + C, validate Route, rank old tables without C, settle item 166, file items 170 and 171
|
2026-10-16 12:49:32 +02:00 |
|
lilleman
|
12909f233d
|
Answer architecture round 1: 0 🔴, 8 🟡; read old routes' rungs, write R in rank_todo, route reviews through review_rungs, file item 168
|
2026-10-16 12:11:25 +02:00 |
|
lilleman
|
152972d84b
|
Score risk as L + E + I, and route a worker on its item's L and its reviewers on its E + I
|
2026-10-16 07:53:48 +02:00 |
|
lilleman
|
c28e72bfc2
|
Answer prose round 1: 0 🔴, 15 🟡; say a blocker ranks above every item it blocks, give each pronoun one referent, put the upgrade step first in the changelog, say does not wait throughout
|
2026-10-15 23:33:42 +02:00 |
|
lilleman
|
157ca50733
|
Answer architecture round 1: 3 🔴, 7 🟡; read the items table by column name, let an item wait while its blocker is held in any order, fill this plan's blockers, file the judge's bundled rung as item 153
|
2026-10-15 23:08:47 +02:00 |
|
lilleman
|
5b7da27a5a
|
Rank each todo.md blocker just above the first item it blocks, allow no other order in todo.md, and route loop-claude on the first item that waits on nothing
|
2026-10-15 22:54:47 +02:00 |
|
lilleman
|
10b0bca037
|
Mend ESCALATION_CAP's comment, which a prose fix left ending in a stray comma
|
2026-10-15 22:34:41 +02:00 |
|