File item 394 and move items 303, 306, 304, 287, 387, 338 and 288 into 0.12.0
CI / tests (pull_request) Successful in 3m21s

This commit was merged in pull request #565.
This commit is contained in:
2026-11-16 23:23:24 +01:00
parent ce98a50027
commit 5bb49dc623
+142 -56
View File
@@ -6,13 +6,21 @@
`Bar = 0.1`
`Next ID = 394`
`Next ID = 395`
## Items
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 303 | 0.12.0 | | defect | **Archive each judge run's prompt and json reply beside the verdict it gave, so judge cost, replays and backups cover the judge as they cover the worker.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3, 3 by 2 | 4.2 |
| 306 | 0.12.0 | | | **Set a strategy that keeps loop-claude's archive and larv-review's review folders backed up and small over the years, compressing older entries without losing any.** | 3 | 2 | 4 | 7 | 5 | 3 by 5 | 3.9 |
| 304 | 0.12.0 | 303 | defect | **Archive each review-replay and judge-replay run's transcript beside its result, so a replay that decided a rung can be checked and re-priced later.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 2, 3 by 2 | 3.8 |
| 287 | 0.12.0 | | | **Move the forge helpers `Forge`, `forge_of`, `runner`, `open_pull`, `merged_pull`, `pull_at`, `gitea`, `checks_passed` and `required_checks` into one module that `chunk_preflight`, `chunk_pr`, `deploy_release` and `larv_review` all import from, so no tool imports another tool's internals for them.** | 3 | 1 | 3 | 5 | 5 | code health by 3 | 2.9 |
| 387 | 0.12.0 | | | **Bind a project's rung to its ladder in one value, so the routing functions and `Cycle` take one argument for both.** | 3 | 1 | 3 | 5 | 5 | code health by 3 | 2.9 |
| 338 | 0.12.0 | | owner | **Script each step that 0.9.0's chunks repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3, 1.5 by 3 | 2.3 |
| 288 | 0.12.0 | | | **Point the two reading-cost decisions at code health and goal 1.4's counter-signal, in place of the goal 1.1 they cite.** | 1 | 2 | 1 | 2 | 1 | code health by 1, 1.4 by 1 | 2.2 |
| 391 | 0.12.0 | | | **Read and write a Jira epic issue's description and a Confluence record page through the lossless pair, so saving an unedited document leaves it unchanged.** | 3 | 2 | 3 | 6 | 5 | 1.6 by 6, 1.1 by 3 | 1.9 |
| 394 | 0.12.0 | | | **Write no changelog bullet for a plan kept in Jira: `todo-item finish` there needs neither --changelog nor --no-changelog and refuses --changelog, since the issues' history is the changelog.** | 2 | 2 | 3 | 5 | 3 | 1.6 by 4 | 1.3 |
| 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 |
@@ -31,13 +39,6 @@
| 368 | 0.13.0 | | | **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 |
| 366 | 0.13.0 | | | **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 |
| 367 | 0.13.0 | | | **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 |
| 303 | 0.14.0 | | defect | **Archive each judge run's prompt and json reply beside the verdict it gave, so judge cost, replays and backups cover the judge as they cover the worker.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3, 3 by 2 | 4.2 |
| 306 | 0.14.0 | | | **Set a strategy that keeps loop-claude's archive and larv-review's review folders backed up and small over the years, compressing older entries without losing any.** | 3 | 2 | 4 | 7 | 5 | 3 by 5 | 3.9 |
| 304 | 0.14.0 | 303 | defect | **Archive each review-replay and judge-replay run's transcript beside its result, so a replay that decided a rung can be checked and re-priced later.** | 2 | 2 | 2 | 4 | 3 | 1.4 by 2, 3 by 2 | 3.8 |
| 287 | 0.14.0 | | | **Move the forge helpers `Forge`, `forge_of`, `runner`, `open_pull`, `merged_pull`, `pull_at`, `gitea`, `checks_passed` and `required_checks` into one module that `chunk_preflight`, `chunk_pr`, `deploy_release` and `larv_review` all import from, so no tool imports another tool's internals for them.** | 3 | 1 | 3 | 5 | 5 | code health by 3 | 2.9 |
| 387 | 0.14.0 | | | **Bind a project's rung to its ladder in one value, so the routing functions and `Cycle` take one argument for both.** | 3 | 1 | 3 | 5 | 5 | code health by 3 | 2.9 |
| 338 | 0.14.0 | | owner | **Script each step that 0.9.0's chunks repeated by hand and a program can compute, filing one item per step, and file this audit again for the next release.** | 1 | 2 | 1 | 2 | 2 | 1.4 by 3, 1.5 by 3 | 2.3 |
| 288 | 0.14.0 | | | **Point the two reading-cost decisions at code health and goal 1.4's counter-signal, in place of the goal 1.1 they cite.** | 1 | 2 | 1 | 2 | 1 | code health by 1, 1.4 by 1 | 2.2 |
| 77 | 0.14.0 | | | **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 | 0.14.0 | | 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 | 0.14.0 | 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 |
@@ -77,12 +78,145 @@
## Details
### 303. Archive each judge run's prompt and json reply beside the verdict it gave, so judge cost, replays and backups cover the judge as they cover the worker.
Today no judge transcript reaches loop-claude's archive. `bin/claude_code/reply.py` runs every headless reply, the judge's included, with `--no-session-persistence`, so its runs stay out of the session picker; Claude Code then writes no session file for the archive to copy. No decision chose to leave the judge out: `loop-claude: the archive keeps the raw transcript` was written for the worker's `.jsonl`. Goal 3 asks for the transcripts of unattended runs to be backed up, and the judge is one. The gap also leaves the judge's spend measurable only from the `Judge cost:` lines, which older verdicts lack ($136 recorded over 2026-09-30 to 2026-11-11), and leaves `judge-replay` rebuilding each prompt from today's records: of the 39 verdicts it replayed on 2026-10-15, 8 may rest on records that had changed since.
The judge runs with no tools and one turn (`judge_args` in `bin/loop_claude/cycle/judge.py`), so its whole transcript is the prompt it read and the json reply. Recommended: keep `--no-session-persistence`, and have the archive write the prompt and the reply beside the outcomes entry of the verdict, interrupt or rejected reply they produced, deduplicated by content hash as the worker's copies are. A failed write stops the loop, as that decision says. Persisting the session and copying its file would also work, but fills the picker and needs a cleanup. The prompt repeats the worker's transcript, which the archive already holds: measure the size per cycle first, and if it outgrows "small enough to copy whole", keep the prompt without the transcript part and name the worker copy and entry range it held. Then let `judge-replay` read the archived prompt where one exists, and price the judge from the archived reply's usage. Update that decision entry to say the judge's runs are archived too.
Touches:
- `bin/loop_claude/cycle/judge.py`: `run_judge`, `judge_once`
- `bin/loop_claude/cycle/run.py`: `(module)` (small)
- `bin/transcript_archive/write.py`: `archive`, `copy_for`
- `bin/transcript_archive/location.py` (small)
- `bin/transcript_archive/test_transcript_archive.py`
- `bin/judge_replay/main.py`: `archived_cases`, `rule`
- `bin/judge_replay/replay.py`: `case_from`
- `bin/judge_replay/test_judge_replay.py`
### 306. Set a strategy that keeps loop-claude's archive and larv-review's review folders backed up and small over the years, compressing older entries without losing any.
Measured on 2026-11-11: loop-claude's archive is 6.3 GB (12,721 files from October alone, 0.84 GB older than 30 days), and `~/.local/state/larv-review/` is 997 MB, 984 MB of it under `code/`, with no pruning: `skills/larv-review/SKILL.md` → "Reports" keeps every folder after the merge, because `review-replay` replays rounds from them. The largest archived worker transcript, 23.4 MB, gzips to 9.1 MB at level 6. The disk holds 65 GB free today.
Write the strategy as a decision, then build it:
- **Backup.** Item 1 waits on ai-sandbox's data volume backup; check that both `~/.claude/loop-claude-transcripts` and `~/.local/state/larv-review` sit on that volume, since the review folders live outside `~/.claude`.
- **Retention.** Keep everything: the archive is the evidence every routing and replay decision rests on. Compress entries older than a threshold (such as 30 days, or once a chunk is finished and measured) with a format the tools read transparently, such as zstd. Compress, verify the round trip, then remove the original, never the reverse; a failure keeps the original and stops, as a failed archive does.
- **Readers.** `bin/transcript_archive`, `routing_figures`, `score-outcomes`, `review-replay`, `judge-replay` and `reading-cost` must read compressed entries; test each on one.
- Revise `loop-claude: the archive keeps the raw transcript`, whose validity is "while transcripts stay small enough to copy whole".
Touches:
- `bin/transcript_archive/read.py`: `read_threads`, `finished_chunks`, `chunk_outcomes`
- `bin/transcript_archive/write.py`: `copy_for`, `mirror`
- `bin/transcript_archive/test_transcript_archive.py`
- `bin/routing_figures/archive.py`
- `bin/reading_cost/main.py` (small)
- `bin/score_outcomes/reversals.py` (small)
- `bin/review_replay/rounds.py`
- `bin/judge_replay/main.py`: `archived_cases` (small)
- `skills/larv-review/SKILL.md`: `## 6. Wrap up` (small)
- `README.md`: `## Install` (small)
### 304. Archive each review-replay and judge-replay run's transcript beside its result, so a replay that decided a rung can be checked and re-priced later.
Today `review-replay` and `judge-replay` leave no transcript: both run claude through `claude_reply` in `bin/claude_code/reply.py`, whose `--no-session-persistence` makes Claude Code write no session file, as item 303 describes for the judge. A replay decides which rung a review pass or the judge may run on (`routing: a review pass runs below the project's rung only on a rung that a replay of its rounds shows…`, and the judge's rung on `JUDGE_REPLAYED`), so the runs behind a routing decision can't be read again, re-priced or re-scored once the decision is questioned. Goal 3 asks for the transcripts of unattended runs, the bench's included, to be backed up; `workflow-bench/bench.py` already keeps its claude stream in `logs/`.
Unlike the judge, a replayed reviewer uses tools over several turns, so its transcript is more than its prompt and reply. Recommended: have `claude_reply` take `--output-format stream-json --verbose` in place of `json`, keep `--no-session-persistence`, write the stream where the replay keeps its result, and read the reply from the stream's last `result` event. That also gives item 303 the judge's stream for free, so build on 303's archive layout and do both callers through the one runner.
Touches:
- `bin/claude_code/reply.py`: `claude_reply`
- `bin/claude_code/test_claude_code.py`
- `bin/review_replay/replay.py`: `reviewed_in`, `match`, `copy_reports`
- `bin/review_replay/test_review_replay.py`
- `bin/judge_replay/main.py`: `rule`
- `bin/judge_replay/test_judge_replay.py`
- `bin/loop_claude/cycle/judge.py`: `judge_args`, `run_judge` (small)
### 287. Move the forge helpers `Forge`, `forge_of`, `runner`, `open_pull`, `merged_pull`, `pull_at`, `gitea`, `checks_passed` and `required_checks` into one module that `chunk_preflight`, `chunk_pr`, `deploy_release` and `larv_review` all import from, so no tool imports another tool's internals for them.
Today the helpers live in two tools. `Forge` is defined in `bin/chunk_preflight/gathered.py` and imported by `bin/chunk_preflight/choices.py`, `bin/chunk_preflight/facts.py`, `bin/chunk_preflight/main.py` and `bin/chunk_pr/main.py`, and again through `choices` by `bin/deploy_release/forge.py`. `forge_of` lives in `choices.py`, which `bin/chunk_pr/main.py`, `bin/deploy_release/cut.py` and `bin/larv_review/reviewer_header.py` import. `open_pull`, `runner` and `gitea` live in `bin/deploy_release/forge.py`, which `bin/chunk_pr/main.py` and `bin/larv_review/reviewer_header.py` import. So `deploy_release` imports `chunk_preflight`, and `chunk_pr` and `larv_review` import both.
Both comprehension seats of PR #453's paired ruling (2026-11-09) named this web as a place that cost them time, and neither saw a reason for it: a second forge would need edits in `chunk_preflight`, `deploy_release`, `chunk_pr` and `larv_review`.
Put the seven helpers in a folder named by what it holds, such as `bin/forge/`, and import them from there. Keep each helper's behaviour and its tests. `chunk_preflight/choices.py` keeps `pulls_command`, which is preflight's own. Check `docs/decisions.md` for a mention of where a helper lives, and update it.
Touches:
- `bin/deploy_release/forge.py`
- `bin/chunk_preflight/gathered.py`: `Forge`
- `bin/chunk_preflight/choices.py`: `forge_of`, `(module)` (small)
- `bin/chunk_preflight/facts.py`: `(module)` (small)
- `bin/chunk_preflight/main.py`: `(module)` (small)
- `bin/chunk_pr/main.py`: `(module)` (small)
- `bin/chunk_pr/approval.py`: `(module)` (small)
- `bin/deploy_release/cut.py`: `(module)` (small)
- `bin/larv_review/reviewer_header.py`: `(module)` (small)
- `bin/chunk_pr/test_chunk_pr.py` (small)
- `bin/chunk_preflight/test_chunk_preflight.py` (small)
- `bin/deploy_release/test_deploy_release.py` (small)
### 387. Bind a project's rung to its ladder in one value, so the routing functions and `Cycle` take one argument for both.
Filed by PR #553, which made the routing ladder a file a project may replace. Its stability round 1 found two places the comprehension seats name as hard, touched and no easier to read: `bin/loop_claude/routing.py` `unfinished_route` took `ladder` as a fourth parameter, and `Cycle` in `bin/loop_claude/cycle/run.py` gained the field `ladder`. The patch threaded the ladder as an argument, since a wider change did not fit a patch cut during an outage.
12 functions in `routing.py` take `ladder` only to pass it on beside `project`, and 6 of `Ladder`'s methods in `bin/model_routing/ladder.py` take `project` first. One value that holds the project's rung with the ladder it stands on removes the extra argument from each, and gives `Cycle` back the field count it had. Make `unfinished_route` and `Cycle` easier to read while there: both are places the seats found hard.
Touches:
- `bin/model_routing/ladder.py`: `Ladder`
- `bin/loop_claude/routing.py`
- `bin/loop_claude/cycle/run.py`: `Cycle`
- `bin/loop_claude/loop/main.py` (small)
- `bin/loop_claude/cycle/prompts.py` (small)
- `bin/loop_claude/loop/chunk_start.py` (small)
- `bin/loop_claude/loop/close.py` (small)
- `bin/loop_claude/escalation_mark.py` (small)
- `bin/model_routing/review_choice.py` (small)
- `bin/rule_hook/reviewer_rung.py` (small)
- `bin/judge_replay/main.py` (small)
- `bin/loop_claude/test_loop_claude.py`
### 338. Script each step that 0.9.0'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). This audit reads the archived transcripts of the chunks that shipped release 0.9.0 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 0.9.0` first; its table names the patterns, and `read_threads` and `calls` in `bin/command_patterns/tally.py` open the calls of one pattern, or `command-patterns 0.9.0 --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.
The 0.8.0 audit filed four steps, items 334, 335, 336 and 337, and found most other repeated steps already covered by items 295, 312, 325, 326 and 327.
The chunk that ships this item files a copy of this audit in release 0.15.0, the release after this item's own, to audit releases 0.10.0 to 0.14.0, rewording "0.9.0" to them, and marks the copy `owner`, so the audit recurs each release until lilleman drops it.
### 288. Point the two reading-cost decisions at code health and goal 1.4's counter-signal, in place of the goal 1.1 they cite.
Both `docs/decisions.md` entries under `reading cost: a rise is …` and `reading cost: larv-review measures each finished chunk …` open "Serves goal 1.1: comprehension …". No goal says that any more: code health (`CLAUDE.md` → "Shared goal") holds comprehension, and since PR #455 a rising reading cost is goal 1.4's first counter-signal. Raised by the stability review of PR #455 as a 🟢 outside that change.
### 391. Read and write a Jira epic issue's description and a Confluence record page through the lossless pair, so saving an unedited document leaves it unchanged.
`plan_store/jira_epic.py` reads an issue's description and writes it back on an edit, and `record_store/confluence_page.py` reads a page and saves it back; both use the portable pair, which drops each block's `localId` and the empty paragraphs Jira uses for spacing. `record_store/jira_description.py` only reads, to show a person: it stays on the portable pair.
Open before building: the lossless markdown is less readable than the portable one (upstream larvit/adf-codec#185), and agents and the judge read the plan's details from it. Decide how a detail stays readable, for example by reading lossless and showing a person a portable view. Test that an unedited issue and page save back identical. The item ships alone because its R is above 5.
### 394. Write no changelog bullet for a plan kept in Jira: `todo-item finish` there needs neither --changelog nor --no-changelog and refuses --changelog, since the issues' history is the changelog.
The human ruled on 2026-11-16 that a project whose plan is a Jira epic keeps no changelog of its own: the issues' history in Jira already says what shipped. Today `todo-item finish` asks for `--changelog <bullet>` or `--no-changelog` whenever the configured changelog holds text, for a Jira plan too, and writes the bullet to `CHANGELOG.md` or the Confluence page.
Done when, for a plan kept in Jira:
- `todo-item finish <ID>` moves the issue without asking for either flag, and doesn't read or write the changelog;
- `todo-item finish <ID> --changelog <bullet>` refuses, writing nothing, and says the issues' history is the changelog;
- `--no-changelog` is still accepted, so `chunk-pr merge --finish <ID> --no-changelog` keeps working;
- `CLAUDE.md` → "Working loop" and larv-review §5 say a Jira plan takes no changelog bullet.
A plan kept as todo.md behaves as today. A client's own `CHANGELOG.md` stays the team's: the loop just stops adding to it.
Touches:
- `bin/todo_item/main.py`: `finish`, `(module)` (small)
- `bin/todo_item/test_todo_item.py`
- `bin/chunk_pr/main.py`: `(module)` (small)
- `CLAUDE.md`: `## Working loop` (small)
- `skills/larv-review/SKILL.md`: `## 5. Goal alignment, then merge` (small)
### 319. 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.
On SWE-bench Verified with Haiku 4.5 and Opus 4.7, handing the strong model the weak model's transcript solved 69.2% at $1.61 a task; starting the strong model fresh solved 79.2% at $0.90 (arXiv 2608.24358, The Handoff Tax). A model switch also rereads the whole context uncached (Claude Code prompt caching docs). A worker that steps from Sonnet 5.5 to Opus 5.5 by `--resume` is the raw handoff; an effort-only step within one model keeps the cache and isn't. The escalated subagent, which starts fresh with the trigger's evidence, already follows the pattern that won.
@@ -200,54 +334,6 @@ One of 0.13.0's history ports, per lilleman's call of 2026-11-12.
One of 0.13.0's history ports, per lilleman's call of 2026-11-12.
### 303. Archive each judge run's prompt and json reply beside the verdict it gave, so judge cost, replays and backups cover the judge as they cover the worker.
Today no judge transcript reaches loop-claude's archive. `bin/claude_code/reply.py` runs every headless reply, the judge's included, with `--no-session-persistence`, so its runs stay out of the session picker; Claude Code then writes no session file for the archive to copy. No decision chose to leave the judge out: `loop-claude: the archive keeps the raw transcript` was written for the worker's `.jsonl`. Goal 3 asks for the transcripts of unattended runs to be backed up, and the judge is one. The gap also leaves the judge's spend measurable only from the `Judge cost:` lines, which older verdicts lack ($136 recorded over 2026-09-30 to 2026-11-11), and leaves `judge-replay` rebuilding each prompt from today's records: of the 39 verdicts it replayed on 2026-10-15, 8 may rest on records that had changed since.
The judge runs with no tools and one turn (`judge_args` in `bin/loop_claude/cycle/judge.py`), so its whole transcript is the prompt it read and the json reply. Recommended: keep `--no-session-persistence`, and have the archive write the prompt and the reply beside the outcomes entry of the verdict, interrupt or rejected reply they produced, deduplicated by content hash as the worker's copies are. A failed write stops the loop, as that decision says. Persisting the session and copying its file would also work, but fills the picker and needs a cleanup. The prompt repeats the worker's transcript, which the archive already holds: measure the size per cycle first, and if it outgrows "small enough to copy whole", keep the prompt without the transcript part and name the worker copy and entry range it held. Then let `judge-replay` read the archived prompt where one exists, and price the judge from the archived reply's usage. Update that decision entry to say the judge's runs are archived too.
### 306. Set a strategy that keeps loop-claude's archive and larv-review's review folders backed up and small over the years, compressing older entries without losing any.
Measured on 2026-11-11: loop-claude's archive is 6.3 GB (12,721 files from October alone, 0.84 GB older than 30 days), and `~/.local/state/larv-review/` is 997 MB, 984 MB of it under `code/`, with no pruning: `skills/larv-review/SKILL.md` → "Reports" keeps every folder after the merge, because `review-replay` replays rounds from them. The largest archived worker transcript, 23.4 MB, gzips to 9.1 MB at level 6. The disk holds 65 GB free today.
Write the strategy as a decision, then build it:
- **Backup.** Item 1 waits on ai-sandbox's data volume backup; check that both `~/.claude/loop-claude-transcripts` and `~/.local/state/larv-review` sit on that volume, since the review folders live outside `~/.claude`.
- **Retention.** Keep everything: the archive is the evidence every routing and replay decision rests on. Compress entries older than a threshold (such as 30 days, or once a chunk is finished and measured) with a format the tools read transparently, such as zstd. Compress, verify the round trip, then remove the original, never the reverse; a failure keeps the original and stops, as a failed archive does.
- **Readers.** `bin/transcript_archive`, `routing_figures`, `score-outcomes`, `review-replay`, `judge-replay` and `reading-cost` must read compressed entries; test each on one.
- Revise `loop-claude: the archive keeps the raw transcript`, whose validity is "while transcripts stay small enough to copy whole".
### 304. Archive each review-replay and judge-replay run's transcript beside its result, so a replay that decided a rung can be checked and re-priced later.
Today `review-replay` and `judge-replay` leave no transcript: both run claude through `claude_reply` in `bin/claude_code/reply.py`, whose `--no-session-persistence` makes Claude Code write no session file, as item 303 describes for the judge. A replay decides which rung a review pass or the judge may run on (`routing: a review pass runs below the project's rung only on a rung that a replay of its rounds shows…`, and the judge's rung on `JUDGE_REPLAYED`), so the runs behind a routing decision can't be read again, re-priced or re-scored once the decision is questioned. Goal 3 asks for the transcripts of unattended runs, the bench's included, to be backed up; `workflow-bench/bench.py` already keeps its claude stream in `logs/`.
Unlike the judge, a replayed reviewer uses tools over several turns, so its transcript is more than its prompt and reply. Recommended: have `claude_reply` take `--output-format stream-json --verbose` in place of `json`, keep `--no-session-persistence`, write the stream where the replay keeps its result, and read the reply from the stream's last `result` event. That also gives item 303 the judge's stream for free, so build on 303's archive layout and do both callers through the one runner.
### 287. Move the forge helpers `Forge`, `forge_of`, `runner`, `open_pull`, `merged_pull`, `pull_at`, `gitea`, `checks_passed` and `required_checks` into one module that `chunk_preflight`, `chunk_pr`, `deploy_release` and `larv_review` all import from, so no tool imports another tool's internals for them.
Today the helpers live in two tools. `Forge` is defined in `bin/chunk_preflight/gathered.py` and imported by `bin/chunk_preflight/choices.py`, `bin/chunk_preflight/facts.py`, `bin/chunk_preflight/main.py` and `bin/chunk_pr/main.py`, and again through `choices` by `bin/deploy_release/forge.py`. `forge_of` lives in `choices.py`, which `bin/chunk_pr/main.py`, `bin/deploy_release/cut.py` and `bin/larv_review/reviewer_header.py` import. `open_pull`, `runner` and `gitea` live in `bin/deploy_release/forge.py`, which `bin/chunk_pr/main.py` and `bin/larv_review/reviewer_header.py` import. So `deploy_release` imports `chunk_preflight`, and `chunk_pr` and `larv_review` import both.
Both comprehension seats of PR #453's paired ruling (2026-11-09) named this web as a place that cost them time, and neither saw a reason for it: a second forge would need edits in `chunk_preflight`, `deploy_release`, `chunk_pr` and `larv_review`.
Put the seven helpers in a folder named by what it holds, such as `bin/forge/`, and import them from there. Keep each helper's behaviour and its tests. `chunk_preflight/choices.py` keeps `pulls_command`, which is preflight's own. Check `docs/decisions.md` for a mention of where a helper lives, and update it.
### 387. Bind a project's rung to its ladder in one value, so the routing functions and `Cycle` take one argument for both.
Filed by PR #553, which made the routing ladder a file a project may replace. Its stability round 1 found two places the comprehension seats name as hard, touched and no easier to read: `bin/loop_claude/routing.py` `unfinished_route` took `ladder` as a fourth parameter, and `Cycle` in `bin/loop_claude/cycle/run.py` gained the field `ladder`. The patch threaded the ladder as an argument, since a wider change did not fit a patch cut during an outage.
12 functions in `routing.py` take `ladder` only to pass it on beside `project`, and 6 of `Ladder`'s methods in `bin/model_routing/ladder.py` take `project` first. One value that holds the project's rung with the ladder it stands on removes the extra argument from each, and gives `Cycle` back the field count it had. Make `unfinished_route` and `Cycle` easier to read while there: both are places the seats found hard.
### 338. Script each step that 0.9.0'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). This audit reads the archived transcripts of the chunks that shipped release 0.9.0 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 0.9.0` first; its table names the patterns, and `read_threads` and `calls` in `bin/command_patterns/tally.py` open the calls of one pattern, or `command-patterns 0.9.0 --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.
The 0.8.0 audit filed four steps, items 334, 335, 336 and 337, and found most other repeated steps already covered by items 295, 312, 325, 326 and 327.
The chunk that ships this item files a copy of this audit in release 0.15.0, the release after this item's own, to audit releases 0.10.0 to 0.14.0, rewording "0.9.0" to them, and marks the copy `owner`, so the audit recurs each release until lilleman drops it.
### 288. Point the two reading-cost decisions at code health and goal 1.4's counter-signal, in place of the goal 1.1 they cite.
Both `docs/decisions.md` entries under `reading cost: a rise is …` and `reading cost: larv-review measures each finished chunk …` open "Serves goal 1.1: comprehension …". No goal says that any more: code health (`CLAUDE.md` → "Shared goal") holds comprehension, and since PR #455 a rising reading cost is goal 1.4's first counter-signal. Raised by the stability review of PR #455 as a 🟢 outside that change.
### 77. 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.
2026-10-08, lilleman: no metric enters review until a rerun on more data shows it tracking the panel.