114 Commits

Author SHA1 Message Date
lilleman ad11c72016 Distil each task-bench run into a digest and gather plan items from it
CI / tests (pull_request) Failing after 4m49s
2026-11-21 03:56:18 +01:00
lilleman 089e9b683b Add task-bench, which has Haiku fix planted bugs at a base and a head and prints what each side took
CI / tests (pull_request) Failing after 4m9s
2026-11-21 01:05:50 +01:00
lilleman b8595db647 Answer architecture round 1: 0 🔴, 36 🟡 (0 misread); chunk_driver holds what both drivers share, and Jira and review-state reads have one home each
CI / tests (pull_request) Successful in 5m11s
2026-11-19 11:14:44 +01:00
lilleman 2b8dd5a72e Run do-epic end to end against a sandbox Jira epic with do-epic-e2e 2026-11-19 02:47:00 +01:00
lilleman b769916928 Ship the do-epic launcher, keep its transcripts out of the repo and in the backup list 2026-11-18 22:36:02 +01:00
lilleman 54fc339fb0 Move loop-claude's cycle, judge, interrupt, tmux and routing into agent_cycle
CI / tests (pull_request) Failing after 3m50s
2026-11-18 16:21:35 +01:00
lilleman 30648af4d3 Merge remote-tracking branch 'origin/main' into add-license
CI / tests (pull_request) Successful in 3m26s
2026-11-18 10:56:32 +01:00
lilleman 0018508657 Add MIT license for Larv IT AB
CI / tests (pull_request) Successful in 2m51s
2026-11-18 10:50:47 +01:00
lilleman 6b07e19c34 Read and file an epic's child issues and sub-tasks through a do-epic backend interface
CI / tests (pull_request) Failing after 3m21s
2026-11-18 09:54:35 +01:00
lilleman d051c4ffe8 Print one section of a markdown file, picked by a fragment of its heading, with markdown-section
CI / tests (pull_request) Successful in 4m23s
2026-11-17 09:16:46 +01:00
lilleman 242be1db34 Merge remote-tracking branch 'origin/main' into item-319
CI / tests (pull_request) Successful in 3m24s
# Conflicts:
#	todo.md
2026-11-17 04:01:42 +01:00
lilleman e42eb5b288 Bench a model step's handoff: resume, compact or a fresh session with a brief 2026-11-17 02:57:22 +01:00
lilleman b9876c17fe Gzip loop-claude's archive and the review folders 30 days after each file was last written, and read gzipped files by their plain name
CI / tests (pull_request) Failing after 2m59s
2026-11-17 02:00:32 +01:00
lilleman 73600d7288 Move the forge helpers into bin/forge/, which chunk_preflight, chunk_pr, deploy_release and larv_review import
CI / tests (pull_request) Successful in 3m9s
2026-11-16 23:42:01 +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 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 c5acadf8d3 Keep the shipped routing ladder beside the module that reads it, so a copy of bin/ carries it 2026-11-15 18:59:23 +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 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 6a553b9574 Name each project's notifier in its config, with Mattermost and Slack as backends
CI / tests (pull_request) Successful in 2m3s
2026-11-14 22:53:00 +01:00
lilleman 8ee67ed2b7 Answer stability round 1: 0 🔴, 10 🟡 (0 misread); share one REST client and env-file reader, read each issue into a checked value, convert descriptions last, and simplify the hard places the change touched 2026-11-14 19:40:36 +01:00
lilleman 18dbf7b3d8 Track the adf_codec package, which the allowlist ignored
CI / tests (pull_request) Successful in 2m13s
2026-11-14 16:27:40 +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 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 c1924e51ef Remove loop-inbox, so an interrupt is answered at loop-claude's terminal only
CI / tests (pull_request) Successful in 2m18s
2026-11-13 23:22:49 +01:00
lilleman 64eb8fc7d7 Name the text-file helpers for what they hold, and keep what counts as a quote beside the judge 2026-11-13 02:49:07 +01:00
lilleman 4840683a26 Read a project's settings from the config that names its checkout, ~/.claude-projects/<key>/config.toml
CI / tests (pull_request) Successful in 2m46s
2026-11-12 22:55:09 +01:00
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 2ab44beca2 Add chunk-pr sync and wait-for 2026-11-12 08:43:14 +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 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 5588270e43 DM the human on Mattermost for each question, release ready to cut and exit 1 of loop-claude
CI / tests (pull_request) Successful in 2m32s
2026-11-11 22:24:06 +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 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 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 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 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 c2792f684a Answer stability round 1: 0 🔴, 4 🟡 (0 misread); count chunks and projects as the archive holds them, date the 876 commits, fail the print when a font fails to load, build the image under run-heavy, and print from Python 2026-11-09 23:13:08 +01:00
lilleman 46fc4dde7c Keep the presentation of loop-claude, with the script that prints it to PDF and what writing it settled
CI / tests (pull_request) Successful in 2m15s
2026-11-09 23:05:33 +01:00
lilleman a0ceffa2a5 Answer security round 1: 0 🔴, 0 🟡 (0 misread); track only the trials' cases, scripts, merged reviewers and README 2026-11-09 22:45:41 +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 73d77a0cf8 Print a release's shell command patterns with command-patterns 2026-11-09 02:48:36 +01:00
lilleman 547a9505fd Run the suite in a pinned container with ci.sh 2026-11-09 02:41:29 +01:00
lilleman 4d25e43c5e Open, mark ready and merge a chunk's pull request with chunk-pr, which picks tea or gh from the remote 2026-11-09 02:03:34 +01:00
lilleman 0c5ea295f1 Track bin/todo-item and its package 2026-11-09 01:37:52 +01:00
lilleman 268200de23 Pass the judge a Brief, decide read_seats from its inputs and return a failed bench run as a line 2026-11-08 22:51:27 +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