Record the comprehension check: PR #510 second run scores Overall 5.88; refresh floor item 300
CI / tests (pull_request) Failing after 2m7s

This commit is contained in:
2026-11-12 19:44:07 +01:00
parent fba48f324c
commit 913accfe14
2 changed files with 54 additions and 3 deletions
+51
View File
@@ -3579,3 +3579,54 @@ Inherited architect, would restructure first:
- Locality: `bin/loop_claude/cycle/judge.py:196` `quotes_checked`: the judge's rules are strings coupled to CLAUDE.md's text
- Shape: `bin/rule_hook/rules.py:127` `check`: round-cap rules sit beside unrelated pin rules in 13 rules
- Self-sufficiency: `bin/loop_claude/routing.py:84` `next_route`: the reasons cite decision titles the reader cannot see
## 2026-11-12T18:43:58Z, PR #510 rerun at fba48f3
| Seat | Navigation | Locality | Shape | Self-sufficiency | Overall |
|---|---|---|---|---|---|
| Junior A | 6.5 | 5 | 5.5 | 4.5 | 5.5 |
| Mid A | 7 | 5.5 | 6.5 | 5 | 6 |
| Maintainability senior | 7 | 5.5 | 6 | 5 | 6 |
| Inherited architect | 7 | 6.5 | 6 | 5.5 | 6 |
| Mean | 6.88 | 5.63 | 6.00 | 5.00 | 5.88 |
Junior A, hardest first:
- Self-sufficiency, Locality: `skills/larv-review/SKILL.md:80` "Round cap": nested rules that point at CLAUDE.md, `standards/`, `rules/` and decision titles, so three documents stay open at once
- Locality, Shape: `bin/loop_claude/routing.py:93` `unfinished_route`: floor, cap, mark and unfinished count interact across `Route`, `Rung` and `escalation_mark`
- Locality: `bin/release_plan/release_standing.py:145` `next_release`: no tag, dated headings, renames and `named_releases` meet in one function
- Self-sufficiency, Shape: `bin/release_plan/ranking.py:271` `goal_weights`: paragraph-long docstrings carry the rules, and the constants cite a decision log
- Locality, Shape: `bin/loop_claude/cycle/run.py:154` `rule`: one function with four near-identically named archive helpers beside it
- Locality: `bin/loop_claude/cycle/judge.py:196` `quotes_checked`: ellipsis matching and a policy that only a misquoted evidence fails
- Shape: `bin/review_replay/main.py:225` `code_of`: guesses which code was reviewed from archive times and prompt text
Mid A, hardest first:
- Locality, Shape: `bin/release_plan/ranking.py:56` `rank`: every helper forks on `SHAPE` versus `OLD_SHAPE`
- Locality, Shape: `bin/release_plan/release_standing.py:145` `next_release`: three inputs and six `Pick` types
- Locality: `bin/loop_claude/routing.py:93` `unfinished_route`: the rule that a rung never falls spans several functions
- Locality: `bin/loop_claude/cycle/run.py:67` `run_cycle`: replaces `cycle.route` partway through its loop, out of sight of `transition`
- Locality: `bin/loop_claude/cycle/judge.py:196` `quotes_checked`: each check silently demotes the verdict's type
- Locality: `bin/review_rules/comprehension_history.py:240` `listings`: a Markdown format parsed by regex and shared with `larv_review` and `rank_todo`
- Locality: `bin/rule_hook/repeat_read.py:119` `shown_lines`: rebuilds the agent's context from Claude Code transcripts
- Self-sufficiency: `skills/larv-review/SKILL.md:80` "Round cap": needs `docs/decisions.md`, `rules/*` and `standards/*` open beside it
Maintainability senior, hardest first:
- Self-sufficiency, Locality: `skills/larv-review/SKILL.md:35` "Passes": a process spec in which nothing marks which sentences code enforces, and where
- Locality: `bin/loop_claude/routing.py:93` `unfinished_route`: rung state shared with `escalation_mark.py` and `model_routing/ladder.py`
- Locality: `bin/loop_claude/cycle/judge.py:196` `quotes_checked`: prompt strings are behaviour with no test-shaped boundary
- Locality, Shape: `bin/loop_claude/cycle/run.py:154` `rule`: the route lives in `Cycle` outside the state machine, and archive order is only commented
- Shape: `bin/release_plan/ranking.py:304` `score`: `OLD_SHAPE` exists only to read old history, and ranking reads a documentation file as data
- Shape: `bin/release_plan/release_standing.py:145` `next_release`: six `Pick` variants and layered tag cases
- Locality: `bin/larv_review/scoring_setup.py:65` `score_bullets`: parses SKILL.md's prose bullets and fails on a count change, so a prose edit is load-bearing
Inherited architect, would restructure first:
- Locality: `bin/review_rules/round_titles.py:59` `past_cap`: the round cap lives in four code places and in SKILL.md §3, and the hook counts commit titles, not launches
- Shape, Locality: `bin/release_plan/ranking.py:56` `rank`: `OLD_SHAPE` branches in six functions, and the module also parses goals and checks decision citations
- Locality: `bin/release_plan/release_standing.py:145` `next_release`: release standing is also read by `larv_review/plan.py`, `chunk_preflight` and `loop_claude/routing.py`
- Navigation, Shape: `README.md:96` `bin/`: about 85 entries at one level, with the launcher-to-package rule as the only map
- Shape: `bin/larv_review/main.py:173` `main`: a 145-line docstring doubles as help beside an elif chain
- Shape: `bin/rule_hook/rules.py:14` `RuleName`: a Literal that repeats the keys of `RULES`, as `ReviewedPass` repeats `PASS_AGENTS`
- Self-sufficiency: `bin/loop_claude/loop/chunk_start.py:83` `fetched_plan`: a comment cites a plan item that is deleted when finished
+3 -3
View File
@@ -36,7 +36,7 @@
| 273 | 0.11.0 | | 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 | 2.3 |
| 268 | 0.11.0 | | | **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 | 2.2 |
| 171 | 0.11.0 | | 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 | 2.0 |
| 300 | 0.11.0 | | owner | **Restructure the places the comprehension seats found hardest to follow, so the project reads at 7.0 or above on every dimension, Self-sufficiency first: today the comprehension floor run at 62faf32 scored Navigation 6.75, Locality 6.13, Shape 6.00, Self-sufficiency 5.00 and Overall 6.00.** | 4 | 2 | 3 | 7 | 8 | code health by 8 | 2.0 |
| 300 | 0.11.0 | | owner | **Restructure the places the comprehension seats found hardest to follow, so the project reads at 7.0 or above on every dimension, Self-sufficiency first: today the comprehension floor run at fba48f3 scored Navigation 6.88, Locality 5.63, Shape 6.00, Self-sufficiency 5.00 and Overall 5.88.** | 4 | 2 | 3 | 7 | 8 | code health by 8 | 2.0 |
| 264 | 0.11.0 | | | **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 | 2.0 |
| 323 | 0.11.0 | | | **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 | 2.0 |
| 342 | 0.11.0 | | | **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 | 2.0 |
@@ -242,9 +242,9 @@ Releases are the human's, and `CLAUDE.md` → "Working loop" already ends the lo
Raised by the goals audit of PR #296. `bin/routing_figures/calls.py` groups a chunk's review rounds by the rung its worker started on, and calls for a routing change when a lower rung took more of them. Since PR #296 the reviewers may run above the worker's rung, on the one their item's E + I picks, and no figure groups rounds by it, though the archived worker line names the E + I it follows from. A cheap worker on an item of high E + I gets stronger reviewers, who may raise more rounds, and a call could then blame the worker's rung for them: an interrupt of lilleman that settles nothing (goal 1.2).
### 300. Restructure the places the comprehension seats found hardest to follow, so the project reads at 7.0 or above on every dimension, Self-sufficiency first: today the comprehension floor run at 62faf32 scored Navigation 6.75, Locality 6.13, Shape 6.00, Self-sufficiency 5.00 and Overall 6.00.
### 300. Restructure the places the comprehension seats found hardest to follow, so the project reads at 7.0 or above on every dimension, Self-sufficiency first: today the comprehension floor run at fba48f3 scored Navigation 6.88, Locality 5.63, Shape 6.00, Self-sufficiency 5.00 and Overall 5.88.
Filed by the comprehension check of PR #473 at 13d1550 (`larv-review record-scoring`), which printed `Floor:` and `Next:`, and refreshed from the run of PR #510 at 62faf32. The lowest mean is Self-sufficiency, 5.00: all four seats name a reason that sits in `docs/decisions.md`, `CLAUDE.md`'s "Vocabulary" or `skills/larv-review/SKILL.md` rather than beside the code. Refresh this item's places and aim from the newest run before the chunk starts; do not file a second floor item.
Filed by the comprehension check of PR #473 at 13d1550 (`larv-review record-scoring`), which printed `Floor:` and `Next:`, and refreshed from the second run of PR #510 at fba48f3. The lowest mean is Self-sufficiency, 5.00: all four seats name a reason that sits in `docs/decisions.md`, `CLAUDE.md`'s "Vocabulary" or `skills/larv-review/SKILL.md` rather than beside the code. Refresh this item's places and aim from the newest run before the chunk starts; do not file a second floor item.
Aim: one ambitious refactor of the areas below, sized so every mean reaches 7.0 on the chunk's own scoring run. Where a place is already easier to read when the chunk starts, drop it.