Commit Graph

3180 Commits

Author SHA1 Message Date
lilleman ce98a50027 Cut release 0.11.0
CI / tests (pull_request) Successful in 3m5s
v0.11.0
2026-11-16 21:30:33 +01:00
lilleman 3c85562bb9 Answer prose round 1: 0 🔴, 4 🟡 (0 misread); the entry says what OTLP is and sends, the archive traces each cycle, and both lists keep their order
CI / tests (pull_request) Successful in 3m5s
2026-11-16 21:25:46 +01:00
lilleman 242f87a9b3 Record that the tools send no OTLP traces, logs or metrics, and loop-claude's archive is the trace of each cycle
CI / tests (pull_request) Successful in 3m7s
2026-11-16 21:23:54 +01:00
lilleman 8d24f73971 Record the comprehension check: paired ruling better at 31da587 against 64454f8, both seats voting better overall
CI / tests (pull_request) Successful in 3m8s
2026-11-16 16:57:45 +01:00
lilleman 2fc9f7212c Point Gathered.plan and CarriedOver at where plan_name and the moved items live now, and name next_chunk.py in the README 2026-11-16 16:57:25 +01:00
lilleman 31da587415 Answer stability round 1: 0 🔴, 14 🟡 (0 misread); tests that kill the surviving mutants, with a versioned MemoryStore and appended_to, plan/named_paths.py, TakenIn's docstring and the run-heavy rule naming LAUNCHERS; three places left to item 300
CI / tests (pull_request) Successful in 3m10s
2026-11-16 16:53:36 +01:00
lilleman 79e0f755e2 Answer product-owner round 1: 0 🔴, 2 🟡 (0 misread); the changelog says what the wider run-heavy rule refuses and that loop-claude's prompts say plan, a bad value in a Jira issue's property names the property, and a Jira edit's refusal names the issue 2026-11-16 16:48:05 +01:00
lilleman fde2718a97 Answer prose round 1: 0 🔴, 9 🟡 (0 misread); each 🟡 and 🟢 rewritten as the report asks, items 392 and 393 included, and item 300's quoted places left for its next refresh 2026-11-16 16:48:04 +01:00
lilleman a06a6dec22 Say in project-record's help that a save refuses after a teammate's save since the last save too
CI / tests (pull_request) Successful in 2m45s
2026-11-16 16:24:06 +01:00
lilleman 8deef3b4ac Answer overrides round 2: 0 🔴, 0 🟡 (0 misread); the todo-rank-check override on ba21a1ef stands, and those on two empty commits are moot 2026-11-16 16:23:45 +01:00
lilleman ba0356adae Answer principles round 2: 0 🔴, 1 🟡 (0 misread); start_window fails only where it cannot mark a new session as the checkout's, so a started chunk never reads as one that didn't start 2026-11-16 16:23:45 +01:00
lilleman a7a6640ea1 Answer architecture round 3: 0 🔴, 2 🟡 (0 misread); a record write names its version, even None, in every backend, and the unreleased section is read through markdown_text.section by one title pattern 2026-11-16 16:17:12 +01:00
lilleman 50ce373c40 Answer overrides round 1: 0 🔴, 0 🟡 (0 misread); both todo-rank-check overrides stand
CI / tests (pull_request) Successful in 2m44s
2026-11-16 16:12:36 +01:00
lilleman fda61ac06e Answer security round 1: 0 🔴, 0 🟡 (0 misread); security-review found nothing, and the full scan could not run in a subagent 2026-11-16 16:12:36 +01:00
lilleman ba21a1efcd Answer principles round 1: 2 🔴, 9 🟡 (0 misread); explicit record versions in place of the Confluence store's hidden state, the routing ruling filed as item 393 for 0.12.0, rule-hook catching heavy runs through uv, poetry, sudo and doas, one unreleased heading, one owner of the no-item message, typed Jira issues, a turn that gives its failure as a value, outcome tests for the Atlassian client, an Emptied reason type, an injected clock and git in touch-predictions, and paired record names 2026-11-16 16:12:36 +01:00
lilleman a60bfdbc1c Answer architecture round 2: 0 🔴, 1 🟡 (0 misread); the answer destinations and the help say the plan, and the notice of releases a plan outside the checkout hides prints once per chunk 2026-11-16 14:54:27 +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 3f7d85c48e Release review of 0.11.0
CI / tests (pull_request) Successful in 2m47s
2026-11-16 13:55:47 +01:00
lilleman 64454f86a8 Merge remote-tracking branch 'origin/main' into adf-lossless
CI / tests (pull_request) Successful in 2m48s
# Conflicts:
#	todo.md
2026-11-16 13:32:34 +01:00
lilleman b62dea42fc Answer stability round 1: 0 🔴, 0 🟡 (0 misread); approved
CI / tests (pull_request) Successful in 1m46s
2026-11-16 13:16:54 +01:00
lilleman d01d0d421e Answer overrides round 2: 0 🔴, 0 🟡 (0 misread); the todo-rank-check override on finishing item 375 stands
CI / tests (pull_request) Successful in 2m56s
2026-11-16 13:16:54 +01:00
lilleman f2b7eb7fd2 Answer prose round 1: 0 🔴, 6 🟡 (0 misread); say each pair's use once in the module docstring, name what the changelog entry keeps, and make item 391 stand alone 2026-11-16 13:16:50 +01:00
lilleman a921b08207 Finish item 375
CI / tests (pull_request) Successful in 2m54s
2026-11-16 13:16:19 +01:00
lilleman e2c4e94cb2 Answer overrides round 1: 0 🔴, 0 🟡 (0 misread); the todo-rank-check override stands
CI / tests (pull_request) Successful in 2m57s
2026-11-16 13:15:32 +01:00
lilleman 251b0e8f02 Record the comprehension check: two scoring runs at 55235a0, overall 6.50 each, and refresh floor item 300
CI / tests (pull_request) Successful in 2m58s
2026-11-16 13:14:42 +01:00
lilleman bac9cf9756 Answer overrides round 1: 0 🔴, 0 🟡 (0 misread); the override stands 2026-11-16 13:08:38 +01:00
lilleman 880d0c6342 Answer security round 1: 0 🔴, 0 🟡 (0 misread); no finding 2026-11-16 13:08:38 +01:00
lilleman 068ab77ce3 Record reading cost 2026-11-16 13:07:39 +01:00
lilleman 4985e6a2a9 Convert ADF to markdown and back through adf-codec's lossless pair
CI / tests (pull_request) Successful in 1m47s
2026-11-16 13:07:30 +01:00
lilleman 55235a07d8 Answer stability round 2: 0 🔴, 0 🟡 (0 misread); no finding
CI / tests (pull_request) Successful in 2m56s
2026-11-16 13:05:18 +01:00
lilleman 96e1b364f1 Clamp the room for new chunks at 0, and test the held-items wording and the session option's target 2026-11-16 12:55:17 +01:00
lilleman 30b0e9e0a7 Target the tmux session as =<session>: for its @loop-root option, which set-option and show-options read as a pane's target
CI / tests (pull_request) Successful in 2m57s
2026-11-16 12:47:28 +01:00
lilleman 255d5f7bb1 Answer prose round 1: 0 🔴, 12 🟡 (0 misread); name the tmux and claude sessions apart, say parallel-chunks is a most, and put the fakes and keywords in order 2026-11-16 12:46:08 +01:00
lilleman 986697ab52 Answer product-owner round 1: 0 🔴, 4 🟡 (0 misread); leave a stopped chunk to the human, name the task that didn't start, refuse another checkout's session and ask to stop old loops before upgrading 2026-11-16 12:46:07 +01:00
lilleman fa9d487afd Answer stability round 1: 1 🔴, 4 🟡 (0 misread); check a new chunk's Touches against every held item, keep a stopped chunk's items, test the fetch and fold the slot loop back 2026-11-16 12:46:07 +01:00
lilleman fbd1b5e99d Check what start_chunks hands next_plan and tmux, keep other chunks' dead windows, and drop item_of's redundant re.ASCII 2026-11-16 12:20:43 +01:00
lilleman f3eaf19f62 Test the window loop, the window starts, --item and the tmux effects in process; drop the Ctrl-C check every stop's reason already makes 2026-11-16 12:12:18 +01:00
lilleman 4e02971bfe Sort the added imports and type the parallel-chunks value for mypy 2026-11-16 12:02:41 +01:00
lilleman 3fd7e15255 Answer security round 1: 0 🔴, 0 🟡 (0 misread); no finding 2026-11-16 12:00:57 +01:00
lilleman 2de1e7e74e Cite no open item in the tmux windows decision 2026-11-16 12:00:15 +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 7fc64d860a Finish item 384
CI / tests (pull_request) Successful in 2m7s
2026-11-16 03:08:52 +01:00
lilleman 00c1dd2480 Answer prose round 1: 0 🔴, 7 🟡 (0 misread); say who made each call, split the README paragraph and correct the rank's help
CI / tests (pull_request) Successful in 3m10s
2026-11-16 03:07:39 +01:00
lilleman f768ef3272 Answer product-owner round 1: 0 🔴, 2 🟡 (1 misread); rank a question first, as todo.md does, and parse the formula on load 2026-11-16 03:07:39 +01:00
lilleman cf1180734c Answer stability round 1: 0 🔴, 7 🟡 (0 misread); parse the formula on load, require the scoring, share the bar rule and split add 2026-11-16 03:07:39 +01:00
lilleman 727ed70ecb Kill the surviving mutants of the scoring and ranking 2026-11-16 02:50:37 +01:00
lilleman 9d9c5a3352 Answer security round 1: 0 🔴, 0 🟡 (0 misread); no finding 2026-11-16 02:42:27 +01:00
lilleman 2db4759c2a Rank an issue the loop files in Jira by its score among the issues the loop filed, a security finding first
CI / tests (pull_request) Successful in 2m8s
2026-11-16 02:41:43 +01:00
lilleman 9d685c52b3 Answer overrides round 2: 0 🔴, 0 🟡 (0 misread); the second override of the rank check is accepted
CI / tests (pull_request) Successful in 1m44s
2026-11-16 02:17:16 +01:00
lilleman c56b3166a0 Finish item 382
CI / tests (pull_request) Successful in 1m48s
2026-11-16 02:15:54 +01:00