Restore the code spans in items 307, 309 and 311's taglines
CI / tests (pull_request) Successful in 2m4s

This commit was merged in pull request #481.
This commit is contained in:
2026-11-11 14:52:51 +01:00
parent feb15e18fa
commit eae9a29553
+6 -6
View File
@@ -12,7 +12,7 @@
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 307 | 0.8.0 | | | **Distil the decisions lists into a few project principles, revisit them each time a decision is recorded, and ask the human before any change unless overwhelmingly certain.** | 3 | 2 | 3 | 6 | 5 | code health by 5, 1.2 by 3, 1.4 by 2 | 6.9 |
| 307 | 0.8.0 | | | **Distil the decisions `AGENTS.md` lists into a few project principles, revisit them each time a decision is recorded, and ask the human before any change unless overwhelmingly certain.** | 3 | 2 | 3 | 6 | 5 | code health by 5, 1.2 by 3, 1.4 by 2 | 6.9 |
| 303 | 0.8.0 | | 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 | 4.8 |
| 304 | 0.8.0 | 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 | 4.4 |
| 306 | 0.8.0 | | | **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 |
@@ -26,9 +26,9 @@
| 305 | 0.8.0 | | | **Record with each archived verdict the claude-config commit that ran it, the raw tokens each model spent by kind, and each choice of the worker's that the human reversed, so a change to the setup can be judged before and after.** | 3 | 2 | 3 | 6 | 5 | 1.4 by 4, 1.2 by 3 | 1.8 |
| 308 | 0.8.0 | 293 | | **Skip a stability round 2 whose every must-fix finding named a surviving mutant or a failing test that the pre-review gate now kills.** | 3 | 2 | 3 | 6 | 4 | 1.4 by 3, 1.5 by 2 | 1.6 |
| 295 | 0.8.0 | | | **Have `chunk-pr merge` wait for the forge's required checks itself, and give workers one command that waits for a background log or report file.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 2, 1.5 by 2 | 1.6 |
| 309 | 0.8.0 | | | **Run a scoring run's second pass on one head with two seats in place of four, once shows the seats agree with each other more than a run agrees with its rerun.** | 2 | 2 | 2 | 4 | 2 | 1.4 by 3 | 1.3 |
| 309 | 0.8.0 | | | **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 | 1.3 |
| 299 | 0.8.0 | | | **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 | 1.2 |
| 311 | 0.8.0 | | | **Hand each worker's claude a Bash output ceiling that saves longer output to a file, and refuse a Read of a session transcript under .** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3 | 1.2 |
| 311 | 0.8.0 | | | **Hand each worker's claude a Bash output ceiling that saves longer output to a file, and refuse a Read of a session transcript under `~/.claude/projects`.** | 2 | 2 | 3 | 5 | 3 | 1.4 by 3 | 1.2 |
| 310 | 0.8.0 | | | **Compact a waiting worker's session shortly before its prompt cache expires, only when the human has not answered an interrupt by then.** | 3 | 2 | 3 | 6 | 4 | 1.4 by 3 | 1.0 |
| 298 | 0.8.0 | 297 | | **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 | 1.0 |
| 313 | 0.8.0 | | | **Launch the first agent of each type in a parallel wave one message before the others of that type, so they read its prompt cache.** | 1 | 2 | 2 | 3 | 2 | 1.4 by 2 | 0.9 |
@@ -69,7 +69,7 @@
## Details
### 307. Distil the decisions lists into a few project principles, revisit them each time a decision is recorded, and ask the human before any change unless overwhelmingly certain.
### 307. Distil the decisions `AGENTS.md` lists into a few project principles, revisit them each time a decision is recorded, and ask the human before any change unless overwhelmingly certain.
lilleman, 2026-11-11: a principle covers many decisions and future ones too, so a few principles should make many decision lines redundant. `AGENTS.md` lists about 60 decision titles today, loaded into every thread.
@@ -163,7 +163,7 @@ Round 2 still matters elsewhere: 53 of 241 archived stability reports of round 2
In 0.7.0's 35 chunks, workers made 65 `tea api` calls in 26 chunks, mostly polling commit status and trying merge methods in turn, and ran 25 `until … sleep` loops that took 1,744 seconds. `chunk-pr merge` takes `--gate-passed` on the worker's word; waiting for the required checks itself makes that flag a fact, not a claim. This is the kind of step item 284 files, and can count as its first.
### 309. Run a scoring run's second pass on one head with two seats in place of four, once shows the seats agree with each other more than a run agrees with its rerun.
### 309. 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.
Seats cost $1,143 of the $9,154 measured from 2026-09-30 to 2026-11-11 (12.5%), scoring runs $470 of that. A scoring run today is four seats, run twice on one head: eight seat runs. Two seats on the second pass make it six, and two on both passes four.
@@ -175,7 +175,7 @@ Decide once `agreement` has its 10 commits scored twice. Keep four seats on any
The judge's verdict kind is the one judge decision that item 297 leaves an LLM. No single rule found so far separates interrupts: a "?" in the worker's final message appears in 48 interrupts and misses 66. A smaller LLM already failed the replay (`docs/decisions.md` → `routing: on a model judge-replay covered, …`: Sonnet returned another kind on 3 interrupts, Haiku missed 7). Untested are combined code rules, a decision table, and a small classifier trained and run on this machine on the archived verdicts (372 finished, 234 interrupt, 42 unfinished, 20 quoted). Run each offline, nothing sent to an outside service (goal 4), and count disagreements by kind; the bar is zero missed interrupts. A hosted decision model is out of scope, since it would send transcripts to an outside service.
### 311. Hand each worker's claude a Bash output ceiling that saves longer output to a file, and refuse a Read of a session transcript under .
### 311. Hand each worker's claude a Bash output ceiling that saves longer output to a file, and refuse a Read of a session transcript under `~/.claude/projects`.
Workers took 7,870 Bash results over 3,000 characters, $305 of carried context, against the reading rule in their prompt; stability reviewers another $145. `BASH_MAX_OUTPUT_LENGTH` (or `bashOutputMaxChars`) makes Claude Code save a longer result to a file and hand the model its path and the first 2,000 characters. loop-claude can hand it as it hands `CLAUDE_CODE_AUTO_COMPACT_WINDOW`. A ceiling of 6,000 characters would have removed $228 of carried output, 10,000 characters $122. Reads of old session transcripts cost $46; a rule-hook rule can refuse them.