Cut release 0.14.0 with the judge's transcript fix, and move its open items to 0.15.0 #654

Merged
lilleman merged 2 commits from replan-0.14.0 into main 2026-11-20 09:01:06 +01:00
3 changed files with 64 additions and 64 deletions
+1 -1
View File
@@ -1,6 +1,6 @@
# Changelog
## Unreleased
## 0.14.0
- `loop-claude`'s judge stops, naming how much to cut the records by, rather than judge a prompt that leaves it less than the transcript's last 50,000 characters. A file the project's config names for two records is read once.
- Under `merge = "human"`, `loop-claude` and `chunk-preflight` pass over an item whose ready pull request awaits a person's merge, and `loop-claude` stops, naming those pull requests, once every item left awaits one.
+1 -1
View File
@@ -386,7 +386,7 @@ Valid while the later fixes per finished chunk, which `score-outcomes` and the r
- A file outside the checkout is read as it stands, never as the default branch held it: release standing, chunk-preflight and loop-claude's routing read such a plan or changelog from disk.
- chunk-preflight and loop-claude's routing learn that a release's items are all done from the plan's commits. A plan outside the checkout no longer names such a release, so the release after it reads as next, and only the last release of all gets a release review called due and is called ready to cut. Both tools say so on every run, and that the release reviews and the cuts are the human's to call (`bin/release_plan/release_standing.py`, `UNSEEN_RELEASES`).
Messages keep each file's usual name, such as `todo.md`, as its label, since the config keeps the names. Revisit at 0.15.0, which plans the support for `score-outcomes`, the routing figures, the release standing and the owed scoring run.
Messages keep each file's usual name, such as `todo.md`, as its label, since the config keeps the names. Revisit at 0.16.0, which plans the support for `score-outcomes`, the routing figures, the release standing and the owed scoring run.
## project config: `language` names the prose's language by its English name, and `commit-title`, `pull-request-title` and `branch` are brace templates over `{id}` and `{summary}`
+62 -62
View File
@@ -12,67 +12,67 @@
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 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 | | | **Have stability-reviewer check each parser that splits a field on a separator against a value that holds the separator.** | 1 | 2 | 2 | 3 | 2 | 1.1 by 3 | 1.2 |
| 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 |
| 77 | 0.15.0 | | | **Teach `bin/metric-bench` Go and TypeScript, rerun it once two projects' comprehension histories name places, and bring into review only a metric that tracks the panel.** | 4 | 2 | 1 | 5 | 6 | 1.1 by 7, 1.4 by 7 | 2.1 |
| 196 | 0.15.0 | | decision | **Replay the architecture, principles, overrides and product-owner passes with `review-replay` on Opus 5.5 projects, record each run in the review-replay routing decision, and, where a run qualifies a rung, add back the code that lowers a pass to it.** | 2 | 2 | 3 | 5 | 2 | 1.4 by 3 | 1.2 |
| 321 | 0.15.0 | 196 | decision | **Evaluate the review passes that run on a rung `review-replay` qualified, against the chunks before them, and revert any pass whose findings or later fixes worsened.** | 1 | 2 | 1 | 2 | 2 | 1.1 by 3, 1.4 by 2 | 2.0 |
| 273 | 0.15.0 | | decision | **Re-tune the E + I steps of `REVIEW_STEPS` for 6 to 8 once 10 finished chunks have scored an E + I of 6 or more, from how well E + I orders their review rounds and 🔴 findings.** | 1 | 2 | 2 | 3 | 2 | 1.1 by 2, 1.4 by 3 | 2.0 |
| 268 | 0.15.0 | | | **End a run whose release is ready to cut with a notice on loop-claude's terminal, in place of an interrupt that waits for an answer.** | 2 | 2 | 3 | 5 | 3 | 1 by 5 | 1.9 |
| 445 | 0.15.0 | | | **Refuse a plan that holds an item a `Finish item <ID>` commit already removed, so a merge resolution cannot bring a finished item back.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3, 1.1 by 2 | 1.8 |
| 171 | 0.15.0 | | decision | **Group the routing figures' review rounds by the reviewers' rung as well as the worker's, so a call blames a rung only for rounds its own reviews raised.** | 3 | 2 | 2 | 5 | 4 | 1.2 by 3, 1.4 by 3 | 1.8 |
| 300 | 0.15.0 | | owner | **Reach the comprehension floor: restructure the places the comprehension seats found hardest to follow, so the project reads at 7.0 or above on every dimension, Locality and Self-sufficiency first; today the scoring run at a357cc7b scored Navigation 7.00, Locality 6.00, Shape 6.13, Self-sufficiency 6.00 and Overall 6.38.** | 4 | 2 | 3 | 7 | 8 | code health by 8 | 1.7 |
| 264 | 0.15.0 | | | **Report the comprehension seats and the escalated subagents as subagent types of their own in `routing-figures.md`, with their dollars.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 5 | 1.7 |
| 323 | 0.15.0 | | | **Count a release review as landed once its pull request has merged, whatever its commits are titled.** | 3 | 2 | 3 | 6 | 3 | 1.4 by 3, 1.5 by 2 | 1.7 |
| 342 | 0.15.0 | | | **Research the tooling agents read, search and run commands with once more, and file an item for each tool that cuts tokens a replay shows keep quality.** | 1 | 2 | 1 | 2 | 3 | 1.4 by 3, 1.5 by 2 | 1.7 |
| 149 | 0.15.0 | | decision | **Fill each release by priority up to a capacity it states, in place of the bar, and move what does not fit to a later release.** | 4 | 2 | 3 | 7 | 5 | 1.1 by 7 | 1.6 |
| 165 | 0.15.0 | | | **Make this repo's tests assert the facts a prompt or help text carries in place of its sentences, and drop the tests that scan source or assert a constant.** | 3 | 2 | 1 | 4 | 5 | 1.1 by 4, 1.4 by 3 | 1.6 |
| 392 | 0.15.0 | | owner | **Group bin/'s packages by concern into seven folders (plan, records, integrations, loop, review, forge and host), so a newcomer finds a tool's neighbours in one place.** | 3 | 1 | 3 | 5 | 7 | code health by 4 | 1.6 |
| 456 | 0.15.0 | | | **Make the child-shell stop test pass under load, so a full test run doesn't fail on a race.** | 2 | 2 | 2 | 4 | 2 | 1.1 by 2, 1.5 by 2 | 1.6 |
| 151 | 0.15.0 | | decision | **Keep 10 to 20 settled decisions per project as its goals' test set, and rerun them after a goal changes.** | 3 | 2 | 2 | 5 | 5 | 1.2 by 7 | 1.6 |
| 68 | 0.15.0 | | principle | **Test `workflow-bench/compare.py`'s blinding and `bench.py`'s run plan.** | 2 | 1 | 1 | 2 | 4 | 1.1 by 5 | 1.5 |
| 102 | 0.15.0 | | | **Give loop-claude's retry delay, and the file it reads the machine's memory from, environment overrides, so the black-box test stops replacing `time.sleep` and `machine_load.memory.MEMINFO` through `sitecustomize`.** | 1 | 1 | 2 | 2 | 3 | 1.1 by 4 | 1.5 |
| 135 | 0.15.0 | | | **Fingerprint only the modules loop-claude imports, so editing another tool's code no longer reloads a running loop.** | 2 | 2 | 3 | 5 | 3 | 1.1 by 4 | 1.5 |
| 443 | 0.15.0 | | | **Measure whether compacting a waiting worker's session cut the cost of 20 chunks with an interrupt, with quality holding.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 4 | 1.4 |
| 5 | 0.15.0 | | decision | **Key a project on its checkout's full path, and refuse to start while another session uses that key.** | 4 | 2 | 3 | 7 | 5 | 1.1 by 6 | 1.4 |
| 291 | 0.15.0 | | owner | **Let `principles/technical-principles.md` → "Sane defaults" allow a library whose README goals ask that it work with no config to default the clock and randomness in its public constructor, where a documented option overrides each.** | 1 | 2 | 3 | 4 | 1 | 1.2 by 3 | 1.3 |
| 156 | 0.15.0 | | decision | **Drop `rank_todo.py`'s ranking of an old-shape table once no project under `~/code` holds one.** | 2 | 1 | 3 | 4 | 4 | 1.1 by 4 | 1.2 |
| 388 | 0.15.0 | | | **Refuse an agent's Write or Edit of a routing ladder file in rule-hook, since a change to the ladder is the human's.** | 1 | 1 | 3 | 3 | 2 | 1.2 by 3 | 1.2 |
| 365 | 0.15.0 | | | **Have `score-outcomes` read the finished and dropped items of a plan outside the checkout, from the project repo's history or from Jira's issue changelogs.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 2, 1.1 by 2 | 1.2 |
| 368 | 0.15.0 | | | **Call a release review due, call a release ready to cut, and tell whether a chunk owes a scoring run, for a plan outside the checkout, from the project repo's history or from Jira.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 2, 1.1 by 2 | 1.2 |
| 260 | 0.15.0 | | decision | **Compare the first 20 chunks whose worker got the reading rule with the 20 before them, on review rounds past each pass's first, unfinished verdicts, 🔴, 🟡 and misread findings, dollars and hours per chunk, and drop the rule where any rose.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3 | 1.2 |
| 309 | 0.15.0 | | | **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 |
| 51 | 0.15.0 | | principle | **Hand loop-claude's terminal output to an injected effect, so no storage or retry function prints.** | 2 | 1 | 3 | 4 | 5 | 1.1 by 5 | 1.1 |
| 419 | 0.15.0 | | | **Run the external auto-reviewer until its review of the PR's head has no findings, and answer each of its threads on the PR.** | 3 | 2 | 3 | 6 | 5 | 1.1 by 5 | 1.1 |
| 444 | 0.15.0 | | | **Rank an epic item that is split by repo, by the goals of each repo its sub-tasks name.** | 2 | 2 | 2 | 4 | 3 | 1 by 3 | 1.1 |
| 366 | 0.15.0 | | | **Count the chunks of a project whose plan sits outside the checkout in the routing figures, from the project repo's history or from Jira.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 2, 1.4 by 2 | 1.1 |
| 201 | 0.15.0 | | owner | **Save the human's tmux setups and restore them after a reboot, so work is up and running again quickly.** | 3 | 2 | 1 | 4 | 4 | 1.5 by 4 | 1.1 |
| 267 | 0.15.0 | | | **Keep waiting when an interrupt gets an empty answer, at the terminal or in the claude opened for it, in place of stopping the loop.** | 2 | 1 | 3 | 4 | 2 | 1.5 by 3 | 1.1 |
| 4 | 0.15.0 | | | **Name each chunk's archive folder by the chunk's start time, so `<key>/` lists chunks in the order they ran.** | 3 | 2 | 3 | 6 | 3 | 1.1 by 3 | 1.1 |
| 324 | 0.15.0 | | | **Count in the routing figures the finished chunks whose worker wrote no `Chunk items:` line.** | 2 | 2 | 1 | 3 | 3 | 1.1 by 2, 1.4 by 1 | 1.1 |
| 187 | 0.15.0 | | | **Count the tokens a worker spends reading reviewers' reports, so goal 1.4's signal shows whether report files lowered what a review costs the worker's context.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 3 | 1.0 |
| 266 | 0.15.0 | | | **Move the chunks archived under the key `home/lilleman/.claude` to the key `claude-config`, so the routing figures and `score-outcomes` count this repo's chunks as one project.** | 3 | 2 | 2 | 5 | 3 | 1.4 by 3 | 1.0 |
| 339 | 0.15.0 | | | **Lower the reading cost of the files a chunk reads most before its first commit.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 3 | 1.0 |
| 341 | 0.15.0 | | | **Hand each worker's claude a lower Read limit through `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS`, kept only where replays of the archived review rounds find what two unchanged replays find.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3 | 1.0 |
| 181 | 0.15.0 | | 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 | 0.9 |
| 193 | 0.15.0 | | | **Narrow `numbered`'s mark to `Mark` by a typed lookup in place of `typing.cast`, so a mark added to the regex but not the lookup fails at run time, and one added to the lookup but not `Mark` fails mypy.** | 1 | 1 | 3 | 3 | 1 | 1.1 by 2 | 0.9 |
| 194 | 0.15.0 | | | **Make `test_waits_out_a_usage_limit_which_ends_a_run_of_failures` expect a usage-limit wait independent of the wall-clock time that passes during the run.** | 1 | 1 | 1 | 1 | 1 | 1.1 by 2 | 0.9 |
| 298 | 0.15.0 | | | **Send the judge only the decision entries and the transcript tail a verdict needs, and keep the cut only where `judge-replay` changes no verdict kind.** | 3 | 3 | 3 | 7 | 4 | 1.4 by 2, 1.5 by 1 | 0.9 |
| 265 | 0.15.0 | | | **Archive each wait that costs a chunk wall time, for a usage limit, low memory, a failed worker start or a heavy slot, with its start and end stamps, so goal 1.5's hours split waiting from work.** | 3 | 2 | 2 | 5 | 4 | 1.5 by 3 | 0.8 |
| 395 | 0.15.0 | | decision | **Keep each block a save didn't change, with its localId, and the spacing paragraphs beside it as Jira or Confluence holds them.** | 3 | 2 | 2 | 5 | 5 | 1.6 by 4 | 0.8 |
| 425 | 0.15.0 | | | **Show on loop-claude's terminal why it doesn't start a chunk beside the next item, as chunk-preflight prints it.** | 1 | 1 | 2 | 2 | 2 | 1.5 by 2 | 0.7 |
| 169 | 0.15.0 | | | **Have rule-hook's `todo-rank-check` catch a `todo.md` that the same Bash call edits and then commits.** | 3 | 1 | 3 | 5 | 3 | 1.1 by 2 | 0.7 |
| 447 | 0.15.0 | | | **Stop a headless claude call that runs past a time limit, and report it as a failure, so a hung judge or stuck check can't hold the loop.** | 2 | 2 | 2 | 4 | 3 | 1.5 by 2 | 0.7 |
| 367 | 0.15.0 | | | **Check that every write to a Jira plan leaves it ranked, as rule-hook's `todo-rank-check` checks `todo.md` today.** | 2 | 2 | 3 | 5 | 3 | 1.6 by 2 | 0.7 |
| 423 | 0.15.0 | | | **Skip the judge's model call on a worker's final message that the offline classifier decides is finished.** | 3 | 3 | 3 | 7 | 5 | 1.4 by 2 | 0.4 |
| 197 | 0.15.0 | | | **Let the human edit what they type at loop-claude's terminal questions with the arrow keys, so Left moves the cursor in place of printing `^[[D`.** | 2 | 2 | 3 | 5 | 2 | 1.5 by 1 | 0.4 |
| 1 | 0.16.0 | | question | **Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume.** | 1 | 2 | 1 | 2 | 1 | | 0.0 |
| 397 | 0.16.0 | | owner | **Script each step that the chunks of releases 0.10.0 to 0.15.0 repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3, 1.5 by 3 | 2.3 |
| 449 | 0.15.0 | | | **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 | 0.15.0 | | | **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 | 0.15.0 | | | **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 | 0.15.0 | | | **Have stability-reviewer check each parser that splits a field on a separator against a value that holds the separator.** | 1 | 2 | 2 | 3 | 2 | 1.1 by 3 | 1.2 |
| 454 | 0.15.0 | | | **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 | 0.16.0 | | 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 | 0.16.0 | | | **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 |
| 77 | 0.16.0 | | | **Teach `bin/metric-bench` Go and TypeScript, rerun it once two projects' comprehension histories name places, and bring into review only a metric that tracks the panel.** | 4 | 2 | 1 | 5 | 6 | 1.1 by 7, 1.4 by 7 | 2.1 |
| 196 | 0.16.0 | | decision | **Replay the architecture, principles, overrides and product-owner passes with `review-replay` on Opus 5.5 projects, record each run in the review-replay routing decision, and, where a run qualifies a rung, add back the code that lowers a pass to it.** | 2 | 2 | 3 | 5 | 2 | 1.4 by 3 | 1.2 |
| 321 | 0.16.0 | 196 | decision | **Evaluate the review passes that run on a rung `review-replay` qualified, against the chunks before them, and revert any pass whose findings or later fixes worsened.** | 1 | 2 | 1 | 2 | 2 | 1.1 by 3, 1.4 by 2 | 2.0 |
| 273 | 0.16.0 | | decision | **Re-tune the E + I steps of `REVIEW_STEPS` for 6 to 8 once 10 finished chunks have scored an E + I of 6 or more, from how well E + I orders their review rounds and 🔴 findings.** | 1 | 2 | 2 | 3 | 2 | 1.1 by 2, 1.4 by 3 | 2.0 |
| 268 | 0.16.0 | | | **End a run whose release is ready to cut with a notice on loop-claude's terminal, in place of an interrupt that waits for an answer.** | 2 | 2 | 3 | 5 | 3 | 1 by 5 | 1.9 |
| 445 | 0.16.0 | | | **Refuse a plan that holds an item a `Finish item <ID>` commit already removed, so a merge resolution cannot bring a finished item back.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 3, 1.1 by 2 | 1.8 |
| 171 | 0.16.0 | | decision | **Group the routing figures' review rounds by the reviewers' rung as well as the worker's, so a call blames a rung only for rounds its own reviews raised.** | 3 | 2 | 2 | 5 | 4 | 1.2 by 3, 1.4 by 3 | 1.8 |
| 300 | 0.16.0 | | owner | **Reach the comprehension floor: restructure the places the comprehension seats found hardest to follow, so the project reads at 7.0 or above on every dimension, Locality and Self-sufficiency first; today the scoring run at a357cc7b scored Navigation 7.00, Locality 6.00, Shape 6.13, Self-sufficiency 6.00 and Overall 6.38.** | 4 | 2 | 3 | 7 | 8 | code health by 8 | 1.7 |
| 264 | 0.16.0 | | | **Report the comprehension seats and the escalated subagents as subagent types of their own in `routing-figures.md`, with their dollars.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 5 | 1.7 |
| 323 | 0.16.0 | | | **Count a release review as landed once its pull request has merged, whatever its commits are titled.** | 3 | 2 | 3 | 6 | 3 | 1.4 by 3, 1.5 by 2 | 1.7 |
| 342 | 0.16.0 | | | **Research the tooling agents read, search and run commands with once more, and file an item for each tool that cuts tokens a replay shows keep quality.** | 1 | 2 | 1 | 2 | 3 | 1.4 by 3, 1.5 by 2 | 1.7 |
| 149 | 0.16.0 | | decision | **Fill each release by priority up to a capacity it states, in place of the bar, and move what does not fit to a later release.** | 4 | 2 | 3 | 7 | 5 | 1.1 by 7 | 1.6 |
| 165 | 0.16.0 | | | **Make this repo's tests assert the facts a prompt or help text carries in place of its sentences, and drop the tests that scan source or assert a constant.** | 3 | 2 | 1 | 4 | 5 | 1.1 by 4, 1.4 by 3 | 1.6 |
| 392 | 0.16.0 | | owner | **Group bin/'s packages by concern into seven folders (plan, records, integrations, loop, review, forge and host), so a newcomer finds a tool's neighbours in one place.** | 3 | 1 | 3 | 5 | 7 | code health by 4 | 1.6 |
| 456 | 0.16.0 | | | **Make the child-shell stop test pass under load, so a full test run doesn't fail on a race.** | 2 | 2 | 2 | 4 | 2 | 1.1 by 2, 1.5 by 2 | 1.6 |
| 151 | 0.16.0 | | decision | **Keep 10 to 20 settled decisions per project as its goals' test set, and rerun them after a goal changes.** | 3 | 2 | 2 | 5 | 5 | 1.2 by 7 | 1.6 |
| 68 | 0.16.0 | | principle | **Test `workflow-bench/compare.py`'s blinding and `bench.py`'s run plan.** | 2 | 1 | 1 | 2 | 4 | 1.1 by 5 | 1.5 |
| 102 | 0.16.0 | | | **Give loop-claude's retry delay, and the file it reads the machine's memory from, environment overrides, so the black-box test stops replacing `time.sleep` and `machine_load.memory.MEMINFO` through `sitecustomize`.** | 1 | 1 | 2 | 2 | 3 | 1.1 by 4 | 1.5 |
| 135 | 0.16.0 | | | **Fingerprint only the modules loop-claude imports, so editing another tool's code no longer reloads a running loop.** | 2 | 2 | 3 | 5 | 3 | 1.1 by 4 | 1.5 |
| 443 | 0.16.0 | | | **Measure whether compacting a waiting worker's session cut the cost of 20 chunks with an interrupt, with quality holding.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 4 | 1.4 |
| 5 | 0.16.0 | | decision | **Key a project on its checkout's full path, and refuse to start while another session uses that key.** | 4 | 2 | 3 | 7 | 5 | 1.1 by 6 | 1.4 |
| 291 | 0.16.0 | | owner | **Let `principles/technical-principles.md` → "Sane defaults" allow a library whose README goals ask that it work with no config to default the clock and randomness in its public constructor, where a documented option overrides each.** | 1 | 2 | 3 | 4 | 1 | 1.2 by 3 | 1.3 |
| 156 | 0.16.0 | | decision | **Drop `rank_todo.py`'s ranking of an old-shape table once no project under `~/code` holds one.** | 2 | 1 | 3 | 4 | 4 | 1.1 by 4 | 1.2 |
| 388 | 0.16.0 | | | **Refuse an agent's Write or Edit of a routing ladder file in rule-hook, since a change to the ladder is the human's.** | 1 | 1 | 3 | 3 | 2 | 1.2 by 3 | 1.2 |
| 365 | 0.16.0 | | | **Have `score-outcomes` read the finished and dropped items of a plan outside the checkout, from the project repo's history or from Jira's issue changelogs.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 2, 1.1 by 2 | 1.2 |
| 368 | 0.16.0 | | | **Call a release review due, call a release ready to cut, and tell whether a chunk owes a scoring run, for a plan outside the checkout, from the project repo's history or from Jira.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 2, 1.1 by 2 | 1.2 |
| 260 | 0.16.0 | | decision | **Compare the first 20 chunks whose worker got the reading rule with the 20 before them, on review rounds past each pass's first, unfinished verdicts, 🔴, 🟡 and misread findings, dollars and hours per chunk, and drop the rule where any rose.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3 | 1.2 |
| 309 | 0.16.0 | | | **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 |
| 51 | 0.16.0 | | principle | **Hand loop-claude's terminal output to an injected effect, so no storage or retry function prints.** | 2 | 1 | 3 | 4 | 5 | 1.1 by 5 | 1.1 |
| 419 | 0.16.0 | | | **Run the external auto-reviewer until its review of the PR's head has no findings, and answer each of its threads on the PR.** | 3 | 2 | 3 | 6 | 5 | 1.1 by 5 | 1.1 |
| 444 | 0.16.0 | | | **Rank an epic item that is split by repo, by the goals of each repo its sub-tasks name.** | 2 | 2 | 2 | 4 | 3 | 1 by 3 | 1.1 |
| 366 | 0.16.0 | | | **Count the chunks of a project whose plan sits outside the checkout in the routing figures, from the project repo's history or from Jira.** | 3 | 2 | 2 | 5 | 4 | 1.6 by 2, 1.4 by 2 | 1.1 |
| 201 | 0.16.0 | | owner | **Save the human's tmux setups and restore them after a reboot, so work is up and running again quickly.** | 3 | 2 | 1 | 4 | 4 | 1.5 by 4 | 1.1 |
| 267 | 0.16.0 | | | **Keep waiting when an interrupt gets an empty answer, at the terminal or in the claude opened for it, in place of stopping the loop.** | 2 | 1 | 3 | 4 | 2 | 1.5 by 3 | 1.1 |
| 4 | 0.16.0 | | | **Name each chunk's archive folder by the chunk's start time, so `<key>/` lists chunks in the order they ran.** | 3 | 2 | 3 | 6 | 3 | 1.1 by 3 | 1.1 |
| 324 | 0.16.0 | | | **Count in the routing figures the finished chunks whose worker wrote no `Chunk items:` line.** | 2 | 2 | 1 | 3 | 3 | 1.1 by 2, 1.4 by 1 | 1.1 |
| 187 | 0.16.0 | | | **Count the tokens a worker spends reading reviewers' reports, so goal 1.4's signal shows whether report files lowered what a review costs the worker's context.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 3 | 1.0 |
| 266 | 0.16.0 | | | **Move the chunks archived under the key `home/lilleman/.claude` to the key `claude-config`, so the routing figures and `score-outcomes` count this repo's chunks as one project.** | 3 | 2 | 2 | 5 | 3 | 1.4 by 3 | 1.0 |
| 339 | 0.16.0 | | | **Lower the reading cost of the files a chunk reads most before its first commit.** | 2 | 2 | 1 | 3 | 3 | 1.4 by 3 | 1.0 |
| 341 | 0.16.0 | | | **Hand each worker's claude a lower Read limit through `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS`, kept only where replays of the archived review rounds find what two unchanged replays find.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3 | 1.0 |
| 181 | 0.16.0 | | 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 | 0.9 |
| 193 | 0.16.0 | | | **Narrow `numbered`'s mark to `Mark` by a typed lookup in place of `typing.cast`, so a mark added to the regex but not the lookup fails at run time, and one added to the lookup but not `Mark` fails mypy.** | 1 | 1 | 3 | 3 | 1 | 1.1 by 2 | 0.9 |
| 194 | 0.16.0 | | | **Make `test_waits_out_a_usage_limit_which_ends_a_run_of_failures` expect a usage-limit wait independent of the wall-clock time that passes during the run.** | 1 | 1 | 1 | 1 | 1 | 1.1 by 2 | 0.9 |
| 298 | 0.16.0 | | | **Send the judge only the decision entries and the transcript tail a verdict needs, and keep the cut only where `judge-replay` changes no verdict kind.** | 3 | 3 | 3 | 7 | 4 | 1.4 by 2, 1.5 by 1 | 0.9 |
| 265 | 0.16.0 | | | **Archive each wait that costs a chunk wall time, for a usage limit, low memory, a failed worker start or a heavy slot, with its start and end stamps, so goal 1.5's hours split waiting from work.** | 3 | 2 | 2 | 5 | 4 | 1.5 by 3 | 0.8 |
| 395 | 0.16.0 | | decision | **Keep each block a save didn't change, with its localId, and the spacing paragraphs beside it as Jira or Confluence holds them.** | 3 | 2 | 2 | 5 | 5 | 1.6 by 4 | 0.8 |
| 425 | 0.16.0 | | | **Show on loop-claude's terminal why it doesn't start a chunk beside the next item, as chunk-preflight prints it.** | 1 | 1 | 2 | 2 | 2 | 1.5 by 2 | 0.7 |
| 169 | 0.16.0 | | | **Have rule-hook's `todo-rank-check` catch a `todo.md` that the same Bash call edits and then commits.** | 3 | 1 | 3 | 5 | 3 | 1.1 by 2 | 0.7 |
| 447 | 0.16.0 | | | **Stop a headless claude call that runs past a time limit, and report it as a failure, so a hung judge or stuck check can't hold the loop.** | 2 | 2 | 2 | 4 | 3 | 1.5 by 2 | 0.7 |
| 367 | 0.16.0 | | | **Check that every write to a Jira plan leaves it ranked, as rule-hook's `todo-rank-check` checks `todo.md` today.** | 2 | 2 | 3 | 5 | 3 | 1.6 by 2 | 0.7 |
| 423 | 0.16.0 | | | **Skip the judge's model call on a worker's final message that the offline classifier decides is finished.** | 3 | 3 | 3 | 7 | 5 | 1.4 by 2 | 0.4 |
| 197 | 0.16.0 | | | **Let the human edit what they type at loop-claude's terminal questions with the arrow keys, so Left moves the cursor in place of printing `^[[D`.** | 2 | 2 | 3 | 5 | 2 | 1.5 by 1 | 0.4 |
| 1 | 0.17.0 | | question | **Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume.** | 1 | 2 | 1 | 2 | 1 | | 0.0 |
| 397 | 0.17.0 | | owner | **Script each step that the chunks of releases 0.10.0 to 0.16.0 repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3, 1.5 by 3 | 2.3 |
## Details
@@ -575,7 +575,7 @@ It lives under `~/.claude`, which `.gitignore` keeps from the remote, so a lost
The README line covers the bench's transcripts in `workflow-bench/logs/` too (goal 3).
### 397. Script each step that the chunks of releases 0.10.0 to 0.15.0 repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.
### 397. Script each step that the chunks of releases 0.10.0 to 0.16.0 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). This audit reads the archived transcripts of the chunks that shipped releases 0.10.0 to 0.14.0 for every step that chunks repeated by hand, before, during or after review. It keeps the steps whose answer a program computes the same way each time, such as 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. Run `command-patterns <version>` first for each of 0.10.0 to 0.14.0; each run's table is the audit's starting point. `read_threads` and `calls` in `bin/command_patterns/tally.py` open the calls of one pattern, or `command-patterns <version> --calls <file>` dumps them all as JSON lines. The 0.7.0 audit found that most steps its chunks repeated were already scripted by that release's own tools, so a step a shipped item already covers is not filed.