This commit was merged in pull request #545.
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
- An item of the next release may predict the files and parts it will touch, under a `Touches:` line in its detail. `chunk-preflight` then names the items that may start chunks at once, and the new `touch-predictions record` keeps each prediction beside what the merged chunk touched, in the record a project's config places with `touch-predictions`.
|
||||
- CLAUDE.md and the todo-items rule define the plan as a todo.md or a Jira epic, and say plan where todo.md was false for a Jira plan.
|
||||
- Reviewers without a shell read the plan from a listing that larv-review writes into the review folder, whichever store holds it.
|
||||
- A project's config may set `tooling-on-host = true`, so the loop runs a legacy project's language runtime, package manager, tests and task runner directly on the host.
|
||||
|
||||
@@ -17,9 +17,8 @@
|
||||
| 356 | 0.11.0 | | | **Hand reviewers the review standards from the folder a project's config names, in place of `~/.claude/skills/larv-review/standards/`.** | 2 | 2 | 3 | 5 | 2 | 1.6 by 3 | 1.1 |
|
||||
| 372 | 0.11.0 | | | **Key loop-claude's session, archive, routing state and config-folder commits per chunk, so two chunks of one project run side by side without touching each other's state.** | 3 | 2 | 3 | 6 | 6 | 1.5 by 3 | 0.4 |
|
||||
| 374 | 0.11.0 | 372 | decision | **Merge open chunks one at a time: rebase, finish the item in todo.md and CHANGELOG.md, rerun the gate and the paired ruling, and keep a chunk waiting for approval in the queue without blocking the next.** | 4 | 2 | 3 | 7 | 6 | 1.5 by 4, 1.6 by 3 | 1.0 |
|
||||
| 373 | 0.11.0 | | | **Pick the next release's chunks that may run at once by the files and the parts of files each is predicted to touch, and record the prediction beside what each merged chunk touched.** | 4 | 2 | 2 | 6 | 6 | 1.5 by 4, 1.4 by 2 | 0.8 |
|
||||
| 359 | 0.11.0 | | | **Tie a project's releases to what its config names: semver tags, Jira Fix Versions, sprints, or none.** | 3 | 2 | 3 | 6 | 4 | 1.6 by 3 | 0.8 |
|
||||
| 375 | 0.11.0 | 372, 373, 374 | decision | **Run up to the project's configured number of chunks at once, each in its own window of one tmux session named for the project, mark a window whose chunk waits for the human, and refuse to start without tmux at the needed version.** | 4 | 2 | 3 | 7 | 7 | 1.5 by 7 | 0.6 |
|
||||
| 375 | 0.11.0 | 372, 374 | decision | **Run up to the project's configured number of chunks at once, each in its own window of one tmux session named for the project, mark a window whose chunk waits for the human, and refuse to start without tmux at the needed version.** | 4 | 2 | 3 | 7 | 7 | 1.5 by 7 | 0.6 |
|
||||
| 319 | 0.12.0 | | | **Start a fresh session with a brief of the chunk when a rung step changes the worker's model, in place of resuming the old session.** | 3 | 2 | 3 | 6 | 4 | 1.1 by 2, 1.4 by 2 | 1.2 |
|
||||
| 309 | 0.12.0 | | | **Run a scoring run's second pass on one head with two seats in place of four, once `larv-review agreement` shows the seats agree with each other more than a run agrees with its rerun.** | 2 | 2 | 2 | 4 | 2 | 1.4 by 3 | 1.2 |
|
||||
| 299 | 0.12.0 | | | **Replay the archived judge verdicts through code rules and a classifier trained locally on the archive, and file an item for each verdict kind one of them decides with no missed interrupt.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3 | 1.0 |
|
||||
@@ -107,16 +106,6 @@ Where the rebase conflicts, the chunk's worker resolves it, and only the review
|
||||
|
||||
`bin/chunk_preflight/choices.py:80` `forge_of` is a place the comprehension seats found hard: forge code split across tools. Where this item touches it, build on item 287's forge module if that has shipped.
|
||||
|
||||
### 373. Pick the next release's chunks that may run at once by the files and the parts of files each is predicted to touch, and record the prediction beside what each merged chunk touched.
|
||||
|
||||
lilleman's call, 2026-11-13, splitting item 361. A planning pass, on the project's rung or above, predicts for each item of the next release the files it will touch and, within each file, the parts: a function, a class, a section heading, a table row. It writes the prediction into the item's detail, where `chunk-preflight` reads it. Two chunks may run together where their predicted parts don't overlap, even in one file. `todo.md` and `CHANGELOG.md` don't count, since item 374 writes them at merge time.
|
||||
|
||||
A conflict is not a catastrophe; lilleman expects projects where wall-clock time matters most and tokens spent per hour don't, while tokens per delivered chunk still do (goals 1.4 and 1.5). So the pass picks the set that keeps the most chunks running within the project's parallel limit, item 375's config key, and takes an overlap only where it predicts a small change to the same part. The rules for a chunk hold as today: a chunk takes every item that can share its review, an item with R above 5 forms its own chunk, an item waits while an item that blocks it is still in the plan, and only the next release's items start.
|
||||
|
||||
Record each chunk's predicted parts beside the parts its merged diff touched, so a later item can measure how often the predictions miss and tune the pass. Name the source of each part's boundaries per language, such as the Python `ast` module, or say where the pass falls back to line ranges.
|
||||
|
||||
Re-scored 2026-11-15 from L 3 and S 5, after a read of the code: it adds a new package that maps a diff to parts, changes chunk-preflight, and adds a record writer that reads todo.md's history, so several components, a new tool and S 6, which is L 4.
|
||||
|
||||
### 359. Tie a project's releases to what its config names: semver tags, Jira Fix Versions, sprints, or none.
|
||||
|
||||
lilleman's call, 2026-11-12: what a release is differs per client. With none, items name no release, and the architecture and principles passes the release review runs need another trigger, which this item settles and records. Readers: `rank_todo.py`'s release order, chunk-preflight's next release, loop-claude's "release ready to cut", larv-review's release review, `CLAUDE.md` → "Working loop". Cutting a release stays the human's.
|
||||
|
||||
Reference in New Issue
Block a user