Compare commits

...

1 Commits

Author SHA1 Message Date
lilleman 1eb93ef766 File item 466: review once more each prose fix that rewrites a checkable claim
CI / tests (pull_request) Successful in 2m49s
2026-11-20 02:18:51 +01:00
+16 -1
View File
@@ -6,7 +6,7 @@
`Bar = 0.1`
`Next ID = 466`
`Next ID = 467`
## Items
@@ -15,6 +15,7 @@
| 449 | 0.14.0 | | | **Record do-epic's repo picks and sub-task summaries in the team's own spelling, such as `core-4` and `core-4: Bygg …`, as its config sets them.** | 2 | 2 | 2 | 4 | 3 | 1.6 by 6 | 2.0 |
| 453 | 0.14.0 | | | **Make the issue types that do-epic and `todo-item add` file in Jira settings, since a Jira project such as TW has no Task type.** | 2 | 2 | 1 | 3 | 2 | 1.6 by 5 | 1.8 |
| 450 | 0.14.0 | | | **Add `do-epic <EPIC-KEY> --dry-run`, which prints every Jira write planning would make and each chunk that would start, and makes none of them.** | 2 | 2 | 2 | 4 | 3 | 1.6 by 5 | 1.6 |
| 466 | 0.14.0 | | | **Review once more each prose fix that rewrites a checkable claim, such as a claim about generated output, a number or a licence term, so no such rewrite reaches the merge unreviewed.** | 2 | 2 | 3 | 5 | 3 | 1.1 by 4 | 1.5 |
| 454 | 0.14.0 | | | **Start a do-epic chunk's issue as the team's board expects, by settings: assigned to the account do-epic works as, moved by a start transition and added to a board's active sprint.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 4 | 1.1 |
| 446 | 0.15.0 | | question | **Kill the process a stuck check names where its verdict is `stuck`, once the human says the recorded verdicts match what they would have done.** | 2 | 2 | 3 | 5 | 3 | 1.5 by 3 | 1.0 |
| 462 | 0.15.0 | | | **Run under `mutate-changes` the tests that today fail in mutmut's copy of the tree, so a mutant of a line only they cover is killed.** | 2 | 1 | 2 | 3 | 3 | code health by 3 | 4.7 |
@@ -129,6 +130,20 @@ Touches:
- `bin/do_epic/test_planning.py`
- `README.md`: `## Tools` (small)
### 466. Review once more each prose fix that rewrites a checkable claim, such as a claim about generated output, a number or a licence term, so no such rewrite reaches the merge unreviewed.
Today the prose pass runs one round per chunk, and a fix for a prose finding reruns no pass ("Re-entry"). So a rewrite of a factual claim merges unchecked. In one chunk the prose reviewer flagged a doc's claim about generated output as false; the rewrite was still false, and only the outside auto-reviewer caught it, after the PR was marked ready. In the same chunk a credit sentence left out parts the project's licence file lists for that source: a licence link and a notice of changes.
Two directions; the implementer picks the cheaper that fits what the rounds cost:
- let the prose pass re-enter once where a round's fix answers a finding that asserts something checkable;
- or have prose-reviewer check each claim a fix rewrites against a concrete counter-example, and against the source it names, such as the licence file's listed credit, before it accepts the rewrite.
Touches:
- `skills/larv-review/SKILL.md`: `## 3. Passes` (small), `### Prose` (small)
- `agents/prose-reviewer.md`: `## Checks, in priority order` (small)
### 454. Start a do-epic chunk's issue as the team's board expects, by settings: assigned to the account do-epic works as, moved by a start transition and added to a board's active sprint.
When a do-epic chunk starts, its issue stays as Jira holds it: unassigned, in New and outside the sprint. A team whose board shows who works on what, such as TW, where an issue being worked is assigned to the person, In Progress and in the active sprint, then sees nothing of the loop's work. Today each worker would have to do this by hand, from rules only some machines hold.