This commit was merged in pull request #607.
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
- `todo-item add` and `todo-item edit --detail` refuse a detail whose `Touches:` list touch-predictions cannot read, and `rank_todo.py --check` fails on each item holding one, so rule-hook refuses a commit of such a plan: after updating, run `~/.claude/bin/rank_todo.py --check` in each project and fix each list it names.
|
||||
- loop-claude hands each worker's claude a Bash output ceiling of 6,000 characters that saves a longer result to a file, rule-hook refuses a Read of a session transcript under ~/.claude/projects, and review-replay takes --bash-ceiling and --read-limit to test such a limit against archived review rounds.
|
||||
- do-epic picks each epic item's repo, or that it is Claude's work or a human task, by repo-rule.md and a headless claude call, records the pick as a label on the issue and reads it back without a new call; where the rule leaves it unclear it returns a question for the human. The epic backends gain a label write.
|
||||
- judge-replay <model> --offline replays every archived verdict through a "?" rule, a decision table and a classifier trained on the archive, with no judge call, and counts the interrupts each misses.
|
||||
|
||||
@@ -27,7 +27,6 @@
|
||||
| 414 | 0.12.0 | 410 | | **DM the human through the notifier when a human-task issue blocks the epic's next item, and poll until it closes.** | 2 | 2 | 2 | 4 | 3 | 1 by 5 | 1.9 |
|
||||
| 417 | 0.12.0 | 410 | | **Run do-epic end to end against a sandbox epic on a real Jira site with a command of its own, outside `run-tests`.** | 2 | 1 | 1 | 2 | 3 | 1 by 5 | 1.9 |
|
||||
| 421 | 0.12.0 | | | **Refuse in rule-hook a Bash or Monitor wait that has no end: a loop without a time or count cap, and a `pgrep -f` or `pkill -f` whose pattern the same command line contains.** | 2 | 2 | 3 | 5 | 3 | 1.5 by 4 | 1.3 |
|
||||
| 424 | 0.12.0 | | | **Refuse a `Touches:` list touch-predictions cannot read in todo-item add and edit, and in rank_todo.py --check.** | 2 | 2 | 3 | 5 | 3 | 1.5 by 4 | 1.3 |
|
||||
| 316 | 0.12.0 | | | **Launch comprehension seats as an agent type of their own under `agents/`, without `CLAUDE.md` and the skill and agent listings a general-purpose subagent carries.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3 | 1.0 |
|
||||
| 310 | 0.12.0 | | | **Compact a waiting worker's session shortly before its prompt cache expires, only when the human has not answered an interrupt by then.** | 3 | 2 | 3 | 6 | 4 | 1.4 by 3 | 0.9 |
|
||||
| 422 | 0.12.0 | 401, 420 | | **Check every 5 minutes whether a tmux window of the loop looks stuck by other signs than a lingering worker, investigate it with a headless claude, and kill only the process the investigation names.** | 3 | 2 | 3 | 6 | 5 | 1.5 by 4 | 0.8 |
|
||||
@@ -269,25 +268,6 @@ Touches:
|
||||
- `bin/rule_hook/test_rule_hook.py`: `CommandBreaches` (small)
|
||||
- `settings.json`
|
||||
|
||||
### 424. Refuse a `Touches:` list touch-predictions cannot read in todo-item add and edit, and in rank_todo.py --check.
|
||||
|
||||
On 2026-11-18 six items (400, 401, 416, 420, 421 and 422) held `Touches:` lists that touch-predictions cannot read, such as ``- `bin/judge_replay/main.py` (small)`` and ``- `README.md`: loop-claude's section (small)``. loop-claude reads the lists before it starts chunks beside the next item, so it didn't start any chunk beside item 401, and didn't say why; slots sat idle for over an hour. The same mistake had been fixed by hand on 2026-11-16 (commit 4b508615). Nothing checked a list when it was written.
|
||||
|
||||
Both checks call `predicted`, touch-predictions' parser, so they cannot drift from it, and the spelling it reads stays as it is. The parser moves from `bin/touch_predictions/prediction.py` to `bin/plan/touches.py`, with its tests, since touch_predictions imports plan_store and plan_store's check needs the parser. `todo-item add` and `edit --detail` refuse such a detail, writing nothing, in main.py before the plan's backend gets it, so a plan in Jira is held to it too. `rank_todo.py --check` fails on any item in todo.md whose list it cannot read, naming the item and the reason. Moves 1.5 (delivery speed): idle chunk slots are what the mistake cost.
|
||||
|
||||
Touches:
|
||||
|
||||
- `bin/todo_item/main.py`: `main` (small), `edit` (small)
|
||||
- `bin/todo_item/test_todo_item.py`
|
||||
- `bin/plan_store/todo_md.py`: `FilePlan.check`
|
||||
- `bin/test_rank_todo.py`
|
||||
- `bin/rank_todo.py`: `(module)` (small)
|
||||
- `bin/plan/touches.py`
|
||||
- `bin/plan/test_touches.py`
|
||||
- `bin/touch_predictions/prediction.py`
|
||||
- `bin/touch_predictions/test_touch_predictions.py`
|
||||
- `rules/todo-items.md`: `` # Todo items (`todo.md`) `` (small)
|
||||
|
||||
### 316. Launch comprehension seats as an agent type of their own under `agents/`, without `CLAUDE.md` and the skill and agent listings a general-purpose subagent carries.
|
||||
|
||||
Seats run as general-purpose subagents, so each starts with the skill and agent listings, about 7,500 tokens, at $9.00 per 1,000 prefix tokens over the archive measured from 2026-09-30 to 2026-11-11: about 1.3% of spend. An agent under `agents/` with Read, Grep, Glob and Bash, `omitClaudeMd: true`, and the seat's persona in its prompt drops both; a seat reads the project as a newcomer does, which is what it simulates. Keep each seat's prompt from `skills/comprehension-panel/seat-prompts.md`. Check that a scoring run's scores on one head stay within the spread two runs of today's seats show. lilleman approved on 2026-11-11.
|
||||
|
||||
Reference in New Issue
Block a user