Answer prose round 1: 0 🔴, 6 🟡; record the rename rule in the decision log, cut false and duplicate clauses, rewrite the help and rules bullets, file the sweep as item 190

This commit is contained in:
2026-10-18 09:56:53 +02:00
parent eae4ee9fb1
commit 63392cea66
11 changed files with 26 additions and 20 deletions
+1 -1
View File
@@ -4,7 +4,7 @@
- Each reviewer under `agents/` now writes its full report to a file that larv-review names in the reviewer's prompt, in a folder per chunk under `~/.local/state/larv-review/`. It returns only its verdict and one line per finding, so a review takes less of the worker's context. The worker reads a finding's full entry before it fixes or answers a 🔴 or 🟡. Each reviewer now holds Write. `rule-hook` refuses a reviewer's Edit and MultiEdit, and any Write outside `~/.local/state/larv-review/`; no override waives this rule. Each chunk's folder stays after the merge, so `stability-replay` can replay a round that reads an earlier round's report. It replays on a copy of the folder.
- `loop-claude` asks an interrupt's question on its own terminal and resumes the worker headless with your one-line answer, so the loop no longer waits for you to leave a claude session. Type `/talk` instead to open the worker's session in claude, as every interrupt did before, to read the diff or discuss first. A release ready to cut opens that session at once. Pressing Enter on an empty answer stops the loop, exit 2. Keys typed before the question shows are dropped, and a pasted answer keeps only its first line; type `/talk` for a longer one. The judge counts that answer as yours, like one typed in claude: the chunk stays open until the answer is recorded, where a later chunk could need it.
- `todo.md` may mark a renamed release in a `## Renamed` section, one line per rename, such as `- 0.2.1 renamed to 0.3.0`. `chunk-preflight` and `loop-claude` then skip that release when they pick the next one, and larv-review's scoring-run trigger calls no run for it. Without the mark, a release named since the last tag whose items all moved to other releases reads as finished: `chunk-preflight` says it is ready to cut and the loop stops for you, and the trigger calls a scoring run. `rank_todo.py` fails on a `## Renamed` line of another shape, and on an item filed under a release it marks. Before you move a project to this release, add the line to every project whose `todo.md` renamed a release since its last tag, or its loop stops for that release's cut.
- `todo.md` may mark a renamed release in a `## Renamed` section, one line per rename, such as `- 0.2.1 renamed to 0.3.0`. `chunk-preflight` and `loop-claude` then skip that release when they pick the next one, and larv-review's scoring-run trigger calls no run for it. Without the mark, a release named since the last tag whose items all moved to other releases reads as finished: `chunk-preflight` says it is ready to cut and the loop stops for you, and the trigger calls a scoring run. `rank_todo.py` fails on a `## Renamed` line of another shape, and on an item filed under a release it marks. Before you move a machine to this release, add the line to the `todo.md` of every project that renamed a release since its last tag, or its loop stops for that release's cut.
- When a worker's run ends with a question and a request for a higher rung, `loop-claude` now steps the worker one rung up as the judge interrupts, or as it answers the question with a quote from `README.md` or another file it may quote. The judge must quote a passage showing that the escalation trigger the run cites fired. Before, the step was lost for an answered question, and the worker carried on from the answer on its old rung. The step has the same limits as the step on an unfinished verdict, and no later ruling of that cycle carries a second escalation. The archive's interrupt and quoted-answer outcomes now name the worker's rung.
- A scoring run due because a release's items ran out costs four more seats: it is done twice on one head. `larv-review agreement` compares how often Mid A and the inherited architect vote alike in paired rulings with how often their overall scores move the same way between the two runs. After 10 such pairs it gives a verdict, and on `Assumption fails:` larv-review asks you whether to keep the paired ruling.
- `workflow-bench/bench.py` gives each run a fixed list of allowed tools. Before, it skipped every permission check. A run may launch agents, run `/security-review`, edit its clone (not the clone's `.git/` or `.claude/`) and its report, and read its clone and the copy of `~/.claude` it benches. For git it gets one command, `workflow-bench/review_git.py`, and no bare `git`. The wrapper runs `log`, `diff`, `show`, `status`, `ls-files`, `add` and `commit -m` on the run's clone, whatever the working directory. It allows only the options it lists for each, and refuses an argument that names a path outside the clone. git runs with no global or system config, hook, pager or editor. A run loads no settings or MCP servers from `~/.claude` or from the case's clone, so their hooks and extra directories do not apply to it. Every other call is denied. Expect a benched review that needs another git command, or to run a project's code or tests, to say in its report that it could not.
+1 -1
View File
@@ -97,7 +97,7 @@ def planned(todo: str | Failure, cut: LastCut, default: str) -> Plan | NoItem:
return NoItem(f"{where} files items under release {version(earliest)}, which is not after the last cut, {cut.tag}; ask the human which release they belong to.")
gap = f"{where} holds no item for the next release after the last cut, {cut.tag}, and"
if stands == "finished":
return NoItem(f"{gap} work has landed since, so that release is finished and ready to cut, and the working loop stops here. If todo.md renamed that release instead, add `- <old release> renamed to <new release>` under its `## Renamed`.")
return NoItem(f"{gap} work has landed since, so that release is finished and ready to cut, and the working loop stops here. If todo.md renamed that release instead, add `- <old release> renamed to <new release>` to todo.md's `## Renamed` section.")
if stands == "unplanned":
return NoItem(f"{gap} no work has landed since, so that release is to be planned first.")
if stands == "unknown":
+1 -2
View File
@@ -34,8 +34,7 @@ the checkout's todo.md, less the shipped items, and work has landed towards that
landed when the chunk ships one of the release's items, or when the release is the earliest the
default branch's todo.md names and the default branch has a commit after its newest v* tag, or has
no v* tag. A release the checkout's todo.md marks renamed in its ## Renamed section, as
`- 0.2.1 renamed to 0.3.0`, is due none; one whose items all moved to other releases unmarked was
deferred, and is due one.
`- 0.2.1 renamed to 0.3.0`, is due none.
A second scoring run of one head names itself `<PR or branch> rerun at <commit>`, so record-scoring
does not refuse it as a repeat of the first.
+2 -2
View File
@@ -9,7 +9,7 @@ from larv_review.git import landed_since_release
def scoring_run_due(before: list[Item], after: list[Item], ships: list[int], landed: bool, renamed: set[tuple[int, int, int]]) -> list[str] | Failure:
"""Why the plan calls a scoring run, empty when it does not. before is the default branch's plan, after the chunk's, ships the IDs it ships, landed whether the default branch holds a commit after its newest release tag, and renamed the releases the chunk's plan marks renamed.
A chunk that ships an item naming the floor is due one, so it can prove the floor met. So is a chunk that empties a release after work has landed towards it, so no release ends unmeasured, short of one renamed as below. Work has landed when the chunk ships one of the release's items, or when the release is the earliest one `before` names and `landed` holds. A release the chunk's plan marks renamed is due none; one whose last items moved to other releases unmarked was deferred, and is due one.
A chunk that ships an item naming the floor is due one, so it can prove the floor met. So is a chunk that empties a release after work has landed towards it, so no release ends unmeasured, short of one renamed as below. Work has landed when the chunk ships one of the release's items, or when the release is the earliest one `before` names and `landed` holds. A release the chunk's plan marks renamed is due none.
"""
plan = {item.id: item for item in before + after}
if unknown := sorted(set(ships) - set(plan)):
@@ -19,7 +19,7 @@ def scoring_run_due(before: list[Item], after: list[Item], ships: list[int], lan
next_release = min((item.release for item in before), default=None)
for release in emptied(before, after, shipped, renamed):
if any(item.release == release for item in shipped) or (release == next_release and landed):
# SKILL.md → "Second run" keys on this wording; a test pins both.
# SKILL.md → "Second run" keys on this wording.
reasons.append(f"leaves release {'.'.join(map(str, release))} with no plan item")
return reasons
+2 -2
View File
@@ -62,8 +62,8 @@ on the item chunk-preflight names, read from todo.md on the default branch as th
fetched it (todo_table.chunk_item). That item is the earliest release's top item that does not wait,
but only where that release is the next one: the earliest after the newest vX.Y.Z tag that todo.md
has named at that tag or since, skipping a release its ## Renamed section marks renamed, or, where
no tag names a version, the earliest release. Otherwise no item routes the chunk. An item waits while it is marked question, or while an
item that blocks it is still in the table. The item's L
no tag names a version, the earliest release. Otherwise no item routes the chunk. An item waits
while it is marked question, or while an item that blocks it is still in the table. The item's L
picks the worker's rung, stepping from the model's cheapest rung by WORKER_STEPS in
bin/model_routing/ladder.py, below it for a low L; without such an item, or with its L, E or I
unscored, the chunk runs on the model's cheapest rung. The
+4 -5
View File
@@ -59,16 +59,15 @@ A valid todo.md; ## Details and each item's detail are optional:
loop. An ID at or above Next ID fails; one below it that the table no longer holds was finished
or deleted, and is dropped.
- ## Items holds the table and nothing else: an order goes in the scores or the Blocked by column.
- ## Renamed is optional: one line `- 0.2.1 renamed to 0.3.0` per release the plan renamed. The tools
skip a marked release when they pick the next one, and call no scoring run for it; they read only
the old release, the new one is for the reader. No item may sit under a marked release. Delete a
line once a tag at or past its release is cut. A release whose items all moved to other releases
without a mark reads as finished, so the human cuts it.
- The table holds the columns above. One missing L, E or I fails, and so does one with a column this
version does not know, since writing it would drop that column.
- A table in the old shape, with C, A, G and Goals columns in place of L, E, I and Moves, still
ranks, by a formula over R, S, A, G and W and a | Goal | W | table that weighs every README goal, W
being the heaviest cited goal's weight; ranking it says to reshape it.
- ## Renamed is optional: one line `- 0.2.1 renamed to 0.3.0` per renamed release. chunk-preflight,
loop-claude and larv-review skip the line's first release, and ignore the second, which is for the
reader. No item may sit under a marked release, and a line goes once a tag at or past its first
release is cut. A release whose items all moved elsewhere without a line reads as finished.
Exit 1, saying why, on bad arguments, a file that cannot be read or written, a todo.md, README.md or
docs/decisions.md that breaks the rules above, an item that is not exempt scoring under the bar, or
-1
View File
@@ -498,7 +498,6 @@ class Standing(unittest.TestCase):
def test_fails_to_name_releases_when_the_newest_plan_marks_one_in_a_form_it_cannot_read(self):
plan = "## Items\n\n| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |\n|---|---|---|---|---|---|---|---|---|---|---|---|\n| 1 | 0.3.0 | | | **Do 1.** | 1 | 1 | 1 | 1 | 1 | 1 by 1 | 10.0 |\n"
self.assertIsInstance(todo_table.named_releases([plan, plan + "\n## Renamed\n\nsoon\n"]), Failure)
self.assertEqual(todo_table.named_releases([plan + "\n## Renamed\n\nsoon\n", plan]), {(0, 3, 0)})
class Main(unittest.TestCase):
+4 -3
View File
@@ -23,8 +23,9 @@ HEADER_START = "| ID | Release |"
Standing = typing.Literal["next", "cut", "finished", "unplanned", "unknown"]
# todo.md's ## Details section, its body the first group.
DETAILS = re.compile(r"^## Details\n(.*?)(?=^## |\Z)", re.M | re.S)
# One line of todo.md's ## Renamed section, the release it renamed and the one it became.
# A release's version, such as 0.2.1.
RELEASE = r"[0-9]+\.[0-9]+\.[0-9]+"
# One line of todo.md's ## Renamed section: the release it renamed and the one it became.
RENAME = re.compile(rf"- ({RELEASE}) renamed to ({RELEASE})")
# Each goal an item names, in its order, with how far the item moves it; None in OLD_SHAPE, whose Goals cell names no move.
Moves = tuple[tuple[str, int | None], ...]
@@ -206,7 +207,7 @@ def landed(cut: LastCut) -> int | Failure:
def named_releases(todos: list[str] | Failure) -> set[tuple[int, int, int]] | Failure:
"""Each release the todo.md texts, oldest first, file items under, leaving out one that a later text marks renamed, unless a text after that files items under it again. A text whose items do not parse names none; the newest text's marks failing to parse fails the whole, since a release left unmarked would read as finished."""
"""Each release the todo.md texts, oldest first, file items under. A release leaves the set when a text marks it renamed, and returns when a later text files items under it again. A text whose items or marks do not parse names none, except the newest: its marks failing to parse fails the whole, since the release they should have excluded would read as finished."""
if isinstance(todos, Failure):
return todos
if todos and isinstance(newest := renames(todos[-1]), Failure):
@@ -220,7 +221,7 @@ def named_releases(todos: list[str] | Failure) -> set[tuple[int, int, int]] | Fa
def renames(todo: str) -> set[tuple[int, int, int]] | Failure:
"""Each release todo.md's ## Renamed section says was renamed, as `- 0.2.1 renamed to 0.3.0`, so never finished; the new release is for the reader. Without such a line, a release whose items all moved to other releases reads as finished or deferred, and the human cuts it, so a forgotten mark costs one interrupt, never a silent skip. A panel of three readers seated as lilleman picked the spelling 3-0 over `- 0.2.1 → 0.3.0` and a `Renamed 0.2.1 = 0.3.0` line under ## Scoring."""
"""Each release todo.md's ## Renamed section says was renamed, as `- 0.2.1 renamed to 0.3.0`, so never finished; the tools read only the old release. `docs/decisions.md` → `todo.md: one table …` gives the rule and the spelling's pick."""
marked: set[tuple[int, int, int]] = set()
for body in sections(todo).get("Renamed", []):
for line in body.splitlines():
+3 -1
View File
@@ -80,7 +80,7 @@ Valid while the ladder orders its rungs by competence.
## review: the comprehension check records how hard a project is to read and blocks no merge: a paired ruling against the last measured commit where the architecture pass ran, and the four-seat scoring run, once when an item names the floor and twice on one head when a release's items run out
2026-10-08, lilleman. Serves goals 1.1 and 1.4. Two independent four-seat runs moved up to 0.4 on near-identical code, so a fall within that noise forced rounds that changed nothing (PR #224). A seat reading both versions judges the difference on the same material, so the noise the versions share cancels. No conventional significance level lets a sign test settle with four votes, so the human chose a lead of two votes over every other ruling, same included. Two seats that agree settle it, so a PR that leaves the reading as it was costs two seats. A third seat alone can never settle it, so the third and fourth launch together. The human chose the last measured commit on the architect's finding that with a merge base as the base, chunks without an architecture pass, and a suspended restructure's steps, could each lower comprehension unseen. Reading the default branch one merged change at a time keeps the rule working for merge commits and squash merges alike. The scoring run also runs on a chunk shipping an item that names the floor, so the chunk that lifts a project to the floor can prove it. A chunk that removes a release's last item without shipping it runs it too, so no release ends unmeasured, unless `todo.md` marks it renamed in a `## Renamed` section (`bin/todo_table.py` → `renames`). Valid while seats reading both versions agree more often than two absolute runs do.
2026-10-08, lilleman. Serves goals 1.1 and 1.4. Two independent four-seat runs moved up to 0.4 on near-identical code, so a fall within that noise forced rounds that changed nothing (PR #224). A seat reading both versions judges the difference on the same material, so the noise the versions share cancels. No conventional significance level lets a sign test settle with four votes, so the human chose a lead of two votes over every other ruling, same included. Two seats that agree settle it, so a PR that leaves the reading as it was costs two seats. A third seat alone can never settle it, so the third and fourth launch together. The human chose the last measured commit on the architect's finding that with a merge base as the base, chunks without an architecture pass, and a suspended restructure's steps, could each lower comprehension unseen. Reading the default branch one merged change at a time keeps the rule working for merge commits and squash merges alike. The scoring run also runs on a chunk shipping an item that names the floor, so the chunk that lifts a project to the floor can prove it. A chunk that removes a release's last item without shipping it runs the scoring run too, so no release ends unmeasured, unless `todo.md` marks that release renamed in a `## Renamed` section (`bin/todo_table.py` → `renames`). Valid while seats reading both versions agree more often than two absolute runs do.
2026-10-13, lilleman. No published study validates simulated reader panels as a measure of how easy code is to understand, and no test of whether the panel's signal beats its noise has run. So no ruling, score or floor blocks a merge. The runs go on, so the history keeps the scores and the places the seats found hard, for later measurement. The architect, the stability reviewer and a session filing an item read the newest places, since those places are what a chunk can improve. With nothing to block, the check runs once per chunk, on the branch as review left it, in place of a run in each architecture round and a rescore after later commits. A fallen dimension no longer calls the four scoring seats either: their scores only decided the block. The base is now the newest merged change that adds any ruling or scoring run: with worse rulings merging, a base left behind them would charge one chunk's ruling with earlier chunks' falls. The newest places are the newest scoring run's and each later ruling's places a seat voted worse, so they change with each ruling. A chunk that leaves a touched place as hard says why in its PR summary, not in a decline's record, which would outlive the place.
@@ -146,6 +146,8 @@ Valid while the ladder orders its rungs by competence.
2026-10-15, lilleman. Serves goal 1.4: loop-claude routes a chunk's first cycle on the item the chunk takes (`routing: a chunk's worker runs on the rung its item's L picks`). An item lists the items that must be done before it starts in a Blocked by column, and `rank_todo.py` ranks each blocker above every item it blocks. The table's order is `todo.md`'s only order: `rank_todo.py` fails on text beside the table under `## Items`, since a prose order there, "Release 0.3.0 takes items 125, 114 and 124 first", contradicted the table and loop-claude could not read it. A decision that wants an order sets the scores instead. An item waits while it is marked `question` or a blocker of it is still in the table, whatever the rows' order, so a release's first row that does not wait is the item a chunk takes. A blocker the table no longer holds was finished or deleted, and is dropped, so the cell shows what still blocks. A panel of three readers seated as lilleman picked the spelling: two ranked "Blocked by" first, as the cell lists only what still blocks, and all three chose bare IDs such as `12, 14` in a column right after Release, read before the tagline and kept apart from the scores. `rank_todo.py` adds the column to a table without it. The tools read cells by column name, so a later column leaves a reader on an older release working; `rank_todo.py`, which writes every column, fails on one it does not know rather than drop it.
2026-10-18, PR #312. Serves goals 1.5 and 1.1: adf-codec renamed its next release, 0.2.1, to 0.3.0, and `chunk-preflight` then called 0.2.1 finished and stopped the loop on every cycle. A change that moves a release's last items elsewhere reads the same whether it renamed the release or deferred its leftovers, so the plan says which: a `## Renamed` section holds one line `- 0.2.1 renamed to 0.3.0` per rename, which `bin/todo_table.py`'s `renames` reads. `chunk-preflight`, `loop-claude` and larv-review's scoring-run trigger skip a marked release; they read only the first version. A release whose items moved unmarked reads as finished: the loop stops, says so and names the fix, and the trigger calls a scoring run once work has landed. So a forgotten mark costs one interrupt and never lets a release end unmeasured. `rank_todo.py` fails on a line of another shape and on an item filed under a marked release, and a newest plan whose marks do not parse leaves the next release unknown. A line goes once a tag at or past its release is cut. Only a rename is marked, since an unmarked move is the deferral. A panel of three readers seated as lilleman picked the spelling 3-0 over `- 0.2.1 → 0.3.0` under `## Releases` and a `Renamed 0.2.1 = 0.3.0` line under `## Scoring`: plain words need no special character to type. Valid while a rename is the only move of a release's items that the tools must tell from finishing it.
## todo.md: only a session or subagent on the project's rung or above scores or reshapes the plan; one below it drafts new items and changes to filed ones for a subagent at or above that rung to apply and score, and removes finished ones
2026-10-15, lilleman. Serves goal 1.1: a cheaper rung writes worse scores, and a wrong score routes a chunk onto the wrong rung, ranks the plan wrong and drops an item under the bar that should stay. Below the project's rung, a session or subagent may not score an item, move it between releases, split a milestone, delete an item under the bar, or rewrite a filed item. It drafts each new item, and each change to a filed item, such as a refresh a rule asks for. Before the next commit, one subagent on the project's rung or above applies and scores the drafts. One launch covers all of a chunk's drafts (goal 1.4). A security finding gets that subagent at once, since it is filed the moment it is found. Removing a finished item closes work and plans none, so any rung does it. Scoring a delegated task's L runs on any rung too: a launch on the project's rung to score each delegation would cost more than the cheaper task saves (goal 1.4).
+1 -1
View File
@@ -5,7 +5,7 @@ paths:
# Todo items (`todo.md`)
- **`todo.md` is mandatory in every project, in the shape `rank_todo.py --help` shows**, which `~/.claude/bin/rank_todo.py` checks and ranks; its `--help` shows a valid file. `## Scoring` holds the formula and the bar; `## Items` is one table of every item; `## Details` holds each item's detail under its ID. `## Renamed`, when a release was renamed, holds one line `- 0.2.1 renamed to 0.3.0` per rename, no item under a marked release, and a line gone once a tag at or past its release is cut; a release whose items all moved elsewhere without that line reads as finished, ready to cut. Cite an item by its ID. The formula and bar are the project's own to tune.
- **`todo.md` is mandatory in every project, in the shape `rank_todo.py --help` shows**, which `~/.claude/bin/rank_todo.py` checks and ranks; its `--help` shows a valid file. `## Scoring` holds the formula and the bar; `## Items` is one table of every item; `## Details` holds each item's detail under its ID. `## Renamed` marks each renamed release with a line such as `- 0.2.1 renamed to 0.3.0`; `rank_todo.py --help` says what a mark does. Cite an item by its ID. The formula and bar are the project's own to tune.
- **Order items only by score and the Blocked by column.** An item's Blocked by cell lists the IDs of the items that must be done before it starts, such as `12, 14`; `rank_todo.py --help` says how it ranks them. No text in `todo.md` outside the table orders items: where an item must go first, score it so, and say why in its detail.
- **Plan only on the project's rung or above.** loop-claude's prompt tells you when you run below it. Below it, never score or re-score an item, move it between releases, split a milestone into items, delete an item under the bar, rewrite a filed item's tagline or detail, or choose or replace an item in `docs/score-anchors.md`. Draft each new item, each change to a filed item, and each change to the anchors, instead. Before your next commit, launch one subagent to apply the drafts, score them and set their release. Launch it on the rung `CLAUDE.md`'s delegation rule gives a subagent that files or scores items. Keep the scores and releases it writes. For a security finding, launch it at once. Any rung may remove a finished item's row and detail, and score a delegated task's L. A subagent launched for another task leaves `todo.md` alone.
- **An item's release allows the bump that semver read strictly asks for.** An item that changes what exists needs a major, or before 1.0.0 a minor. One that only adds needs a minor, and a fix a patch.
+7 -1
View File
@@ -6,7 +6,7 @@
`Bar = 0.1`
`Next ID = 188`
`Next ID = 191`
## Items
@@ -38,6 +38,7 @@
| 172 | 0.3.0 | | | **Name the project's rung `project` across `bin/loop_claude`, in place of `anchor`, as `bin/model_routing/ladder.py` names it.** | 2 | 1 | 3 | 4 | 3 | 1.1 by 3, 1.4 by 3 | 6.2 |
| 82 | 0.3.0 | | principle | **Sort `AGENTS.md`'s decision titles and `docs/decisions.md`'s entries by title.** | 2 | 2 | 1 | 3 | 4 | 1.1 by 4, 1.4 by 4 | 5.5 |
| 173 | 0.3.0 | | | **Have rule-hook's `todo-rank-check` run a worktree's own `bin/rank_todo.py` when the worktree is of this repo, so a branch that changes `todo.md`'s shape commits without an override.** | 2 | 1 | 3 | 4 | 2 | 1.1 by 2, 1.4 by 2 | 5.5 |
| 190 | 0.3.0 | | | **Rewrite the `docs/decisions.md` entries `todo.md: one table …` and `loop-claude: a judge decides …` as the current state, so a reader no longer replays superseded paragraphs to learn what holds.** | 2 | 2 | 1 | 3 | 3 | 1.1 by 3, 1.4 by 2 | 5.5 |
| 162 | 0.3.0 | | owner | **Script each step that 0.2.0's chunks repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 4, 1.5 by 4 | 4.9 |
| 175 | 0.3.0 | | | **Compare the first five chunks loop-claude starts with `chunk-preflight` against the five before them, and file an item where the preflight did not pay off.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3, 1.5 by 3 | 4.9 |
| 181 | 0.3.0 | | principle | **Have the test of a quoted answer's step-up assert the stepped rung's facts as literals, not through `prompts.rungs_held`.** | 1 | 1 | 1 | 1 | 1 | 1.1 by 2 | 4.4 |
@@ -109,6 +110,7 @@ Raised by PR #302's paired ruling, where two of four seats read the project as w
- `bin/todo_table.py` → `landed`: it counts ## Unreleased entries first, while `bin/larv_review/git.py` → `landed_since_release` counts commits only, two meanings of "work has landed"; give them one meaning or two names.
- `bin/loop_claude/loop/main.py` → `run_loop`: routing reads the plan as chunk-preflight's fetch left it, an order only a comment states.
- `bin/chunk_preflight/gathered.py`: the name covers the data, not the pure choices it also holds.
- `bin/chunk_preflight/gathered.py` → `planned`: the "finished and ready to cut" message cannot name the release that finished, which `standing` works out, so the human has to find it; let the pick's module return that release and the message name it.
### 159. Run each review pass on the lowest rung that a replay of its archived rounds shows finding every 🔴 and 🟡 the project's rung finds, even below the worker's rung.
@@ -212,6 +214,10 @@ The architecture pass of PR #296 found one rung under two names: `bin/model_rout
Raised by the overrides pass of PR #296. The hook imports the main checkout's `rank_todo.py`, so while a branch of this repo changes the table's shape, every commit touching `todo.md` needs a `todo-rank-check` override: 33 log lines across four branches, the score-outcomes, plan-136, plan-148 and item-146 ones. The hook then checks nothing, and the rule rests on the worker chaining the branch's own check. Run another repo's `bin/rank_todo.py` never: that would run its code before every commit.
### 190. Rewrite the `docs/decisions.md` entries `todo.md: one table …` and `loop-claude: a judge decides …` as the current state, so a reader no longer replays superseded paragraphs to learn what holds.
Found by the prose review of PR #312, which judged both entries to read as amendment logs, each paragraph correcting an earlier one. The rewrite keeps each paragraph's date and reason only where it still explains a rule that holds, and drops superseded states. It covers items 157 and 183, which reshape paragraphs of the same two entries.
### 162. Script each step that 0.2.0's chunks repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.
lilleman asked, on 2026-10-16, for a standing audit each release, so the loop keeps moving work a program does as well from the model to scripts (goals 1.4 and 1.5). Item 161 scripts the steps found before the first edit in item 140's chunk. This audit reads the archived transcripts of the chunks that shipped release 0.2.0 for every step repeated by hand across chunks whose answer a program computes the same way, before, during and after review: a lookup, a check, a prompt assembled for a reviewer, a cleanup. File one item per such step, with the time and tokens it cost, into the next release with items left. Leave a step that needs judgement with the model.