Answer prose round 1: 0 🔴, 10 🟡; one claim per sentence in the CHANGELOG, the rule and Count, accurate comments, and a sorted Tools list
This commit is contained in:
+3
-2
@@ -2,8 +2,9 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
- Every `todo.md` item scores C, how hard the change is to get right, from 1 to 10, in a column after S. C stays out of the score. `rank_todo.py` fails on an items table without the column, and the rule hook then blocks committing that `todo.md`. Before a project's next loop run, add the column to its `todo.md` and score every item's C, as `rank_todo.py --help` shows.
|
||||
- The new `bin/score-outcomes` shows what finished chunks measured beside the R, S and C their items were guessed at: lines and files changed, review rounds, and 🔴 and 🟡 findings. It reads them from the default branch's merge commits, so a project that merges by squash or fast-forward shows none. Given a guess, it lists the 5 finished items guessed nearest, and for each score the median outcome at each guessed value, once 10 chunks of one item hold it: R against 🔴 findings, S against lines changed, C against review rounds past each pass's first. A session filing or editing an item runs it and scores R, S and C from what it shows. larv-review titles each round's commit with the round's 🔴 and 🟡 counts, `Answer stability round 1: 1 🔴, 2 🟡; …`, and the rule hook's new `round-title-counts` rule blocks a round title without them, so the findings count from now on.
|
||||
- Every `todo.md` item carries a C score, how hard the change is to get right, from 1 to 10, in a column after S. C stays out of the score. `rank_todo.py` fails on an items table without the column, and the rule hook then blocks committing that `todo.md`. Before the next commit that changes a project's `todo.md`, add the column and score every item's C, as `rank_todo.py --help` shows.
|
||||
- The new `bin/score-outcomes` shows what finished chunks measured beside the R, S and C their items were guessed at: lines and files changed, review rounds, and 🔴 and 🟡 findings. It reads them from the default branch's merge commits, so a project that merges by squash or fast-forward shows none. Given a guess, it lists the 5 finished items guessed nearest. It always reports, for each score, the median outcome at each guessed value, once 10 chunks that each shipped one item record it: R against 🔴 findings, S against lines changed, C against review rounds past each pass's first. A session filing or editing an item runs it and scores R, S and C from what it shows.
|
||||
- larv-review round commits now carry the round's 🔴 and 🟡 counts, `Answer stability round 1: 1 🔴, 2 🟡; …`, and the rule hook's new `round-title-counts` rule blocks a round title without them.
|
||||
- The stability reviewer mutation-tests the lines each change adds or modifies: it makes small changes to that code, such as flipping a comparison. For each test to add or strengthen, it reports one 🟡 naming the changes that test would catch. It uses the project's documented mutation command, or else cargo-mutants, Infection, mutmut or Stryker. The technical principles replace "Test coverage should not decline" with "Every mutant of a changed line fails a test, unless the mutant leaves behaviour unchanged", and say what a valuable test is: it checks behaviour through the unit's interface, and fails when that behaviour breaks. README → "Tools" gives the mutmut command for `bin/`. Expect longer stability passes and more 🟡s about tests. In a project whose README documents no mutation command, the reviewer picks and installs a tool on each run; document one there to make the runs consistent.
|
||||
- Each new `loop-claude` worker session's prompt now quotes the README's Goals and Audience. A line above them says that the chunk's `todo.md` items, or else the task, set its scope, and that the goals only choose how to deliver it. A session outside the loop reads Goals and Audience before starting a chunk, as `CLAUDE.md` now says.
|
||||
- A session no longer reads the technical principles before writing code. It writes the simplest change that solves its item, test first wherever a test can check the change, and reads a principle only when the item changes it, a finding names it, or a decision or `todo.md` item it writes cites it. larv-review's reviewers hold the change to the principles, and a finding against one names it. Expect more findings from the prose and stability reviewers, since sessions no longer load the rules for comments and READMEs.
|
||||
|
||||
@@ -72,8 +72,8 @@ Install puts only `loop-claude` on `PATH`; call the others by their path, such a
|
||||
- `metric-bench [history]` benches cheap static metrics of a project's Python against the places its comprehension history names as hardest; `metric-bench --help` states the metrics and the scores.
|
||||
- `rank_todo.py [--check] [todo.md]` scores and ranks a project's `todo.md`; `rank_todo.py --help` states the format.
|
||||
- `reading-cost [--reset] [record]` appends a figure for each chunk `loop-claude` finished to a project's `docs/reading-cost.md`, and says whether the figures rise; `reading-cost --help` states the measure.
|
||||
- `score-outcomes [R S C]` lists the finished items whose guessed R, S and C sit nearest the given scores, with what their chunks measured, and each score's median outcome; `score-outcomes --help` states the measures.
|
||||
- `rule-hook [overrides]` blocks a tool call that breaks a rule a program can check, unless the call overrides the rule; `settings.json` → `hooks` runs it before each Bash, Edit, MultiEdit and Write call, and `rule-hook --help` states the rules and the override.
|
||||
- `score-outcomes [R S C]` lists the finished items whose guessed R, S and C sit nearest the given scores, with what their chunks measured, and each score's median outcome; `score-outcomes --help` states the measures.
|
||||
- `statusline.py` renders Claude Code's status line; `settings.json` → `statusLine` runs it.
|
||||
|
||||
Test on the host, with `uv` on `PATH` to fetch mypy and the Python version Install names (`docs/decisions.md` → `bin/`): `python3 -m unittest discover -s bin -p 'test_*.py'`
|
||||
@@ -91,7 +91,7 @@ pytest_add_cli_args=-k
|
||||
|
||||
Then, in the copy: `uvx --with pytest 'mutmut>=3,<4' run && uvx --with pytest 'mutmut>=3,<4' results`, and `uvx --with pytest 'mutmut>=3,<4' show <mutant>` to see a mutant's change. The config keys are mutmut 3's.
|
||||
|
||||
`bin/` is the import root: each launcher puts it on `sys.path`, so a module imports another by its path under `bin/`, such as `from claude_code.entries import parse_entry`. Each tool's package holds its tests; `rank_todo.py` and `statusline.py` are tools of one file each, tested beside them, `rule_hook` imports `rank_todo.py`'s check, and `score_outcomes` the reading-cost record's path. The other non-test modules at `bin/`'s root, `claude_code/` and `transcript_archive/` serve more than one tool. `test_env.py` serves the tests, and `repo_checks/` tests the repo itself.
|
||||
`bin/` is the import root: each launcher puts it on `sys.path`, so a module imports another by its path under `bin/`, such as `from claude_code.entries import parse_entry`. Each tool's package holds its tests; `rank_todo.py` and `statusline.py` are tools of one file each, tested beside them, `rule_hook` imports `rank_todo.py`'s check, and `score_outcomes` imports `reading_cost`'s record path. The other non-test modules at `bin/`'s root, `claude_code/` and `transcript_archive/` serve more than one tool. `test_env.py` serves the tests, and `repo_checks/` tests the repo itself.
|
||||
|
||||
## Tracking a new file
|
||||
|
||||
|
||||
+1
-1
@@ -66,4 +66,4 @@ def full_history() -> Failure | None:
|
||||
shallow = git("rev-parse", "--is-shallow-repository")
|
||||
if isinstance(shallow, Failure):
|
||||
return shallow
|
||||
return Failure("a shallow clone lacks the history this reads; run `git fetch --unshallow origin`") if shallow.strip() == "true" else None
|
||||
return Failure("a shallow clone lacks the full history; run `git fetch --unshallow origin`") if shallow.strip() == "true" else None
|
||||
|
||||
+1
-1
@@ -187,7 +187,7 @@ def rank(text: str, readme: str, decisions: str) -> Ranked | Failure:
|
||||
def read_scoring(text: str, lines: list[str], readme: str) -> Scoring | Failure:
|
||||
if ITEMS_HEADER not in lines and "## Items" not in lines:
|
||||
return Failure("todo.md is not in the scored-table format; rank_todo.py --help shows a valid one")
|
||||
# A table without C fails, so no chunk starts on an unscored item; each project scores C before its next todo.md commit.
|
||||
# A table without C fails, so no chunk starts on an unscored item.
|
||||
if WITHOUT_C in lines:
|
||||
return Failure("todo.md's items table has no C column; add one after S, and score each item's C from 1 to 10 per rank_todo.py --help")
|
||||
goals = readme_goals(readme)
|
||||
|
||||
+2
-2
@@ -1,4 +1,4 @@
|
||||
"""The titles of larv-review's round commits, `Answer <pass> round <n>: <n> 🔴, <n> 🟡; <summary>`: each pass's round count, and the findings the rounds reported."""
|
||||
"""The titles of larv-review's round commits, `Answer <pass> round <n>: <k> 🔴, <m> 🟡; <summary>`: each pass's round count, and the findings the rounds reported."""
|
||||
import re
|
||||
|
||||
CAP = 3
|
||||
@@ -21,7 +21,7 @@ def round_counts(titles: list[str]) -> dict[str, int]:
|
||||
|
||||
|
||||
def lacks_counts(title: str) -> bool:
|
||||
"""Whether title is a round's, without the counts after its colon."""
|
||||
"""Whether title is a round title without the counts after its colon."""
|
||||
named = ROUND.match(title)
|
||||
return named is not None and not FINDINGS.match(title, named.end())
|
||||
|
||||
|
||||
@@ -38,7 +38,7 @@ RULES: dict[RuleName, Rule] = {
|
||||
"a git, gh or tea command, and any file written",
|
||||
),
|
||||
"round-title-counts": Rule(
|
||||
"a larv-review round's commit title gives the 🔴 and 🟡 findings the round reported, such as `Answer stability round 1: 1 🔴, 2 🟡; flag a deleted test`, since score-outcomes counts them",
|
||||
"a larv-review round's commit title gives the counts of 🔴 and 🟡 findings the round reported, such as `Answer stability round 1: 1 🔴, 2 🟡; flag a deleted test`, since score-outcomes counts them",
|
||||
"a git commit whose message opens `Answer <pass> round <n>:`",
|
||||
),
|
||||
"todo-rank-check": Rule(
|
||||
@@ -105,7 +105,7 @@ def command_breaches(command: str, simples: list[Simple], home: str) -> list[Bre
|
||||
elif len(commit.messages) > 1 or any("\n" in message.strip() for message in commit.messages):
|
||||
breaches.append(Breach("commit-one-line", "pass the message as one -m '<line>', with no heredoc, second -m or newline", commit.directory))
|
||||
if any(lacks_counts(message) for message in commit.messages):
|
||||
breaches.append(Breach("round-title-counts", "open the summary after the round's colon with `<n> 🔴, <n> 🟡;`", commit.directory))
|
||||
breaches.append(Breach("round-title-counts", "open the summary after the round's colon with `<k> 🔴, <m> 🟡;`", commit.directory))
|
||||
return breaches
|
||||
|
||||
|
||||
|
||||
@@ -9,14 +9,14 @@ reads origin as last fetched and says so on stderr.
|
||||
Git history is the record. A chunk is a merge commit on the default branch's first-parent line
|
||||
whose change removed items from todo.md, and changed more than todo.md and the records below; it
|
||||
shipped those items. Each item's guess is its R, S and C in the todo.md the merge's first parent
|
||||
held, when the chunk began; C only where that todo.md scored one. The chunk measures:
|
||||
held; C only where that todo.md scored one. The chunk measures:
|
||||
|
||||
- lines changed: lines added plus lines deleted against the first parent, leaving out todo.md and
|
||||
the records tools append to, docs/comprehension-history.md and docs/reading-cost.md;
|
||||
- files: the files those lines are in;
|
||||
- review rounds past each pass's first: among the branch's `Answer <pass> round <n>:` commit
|
||||
titles, each pass's rounds as `larv-review round-count` counts them, less one, summed;
|
||||
- 🔴 and 🟡 findings: summed over those titles, each opening `<n> 🔴, <n> 🟡` after the colon,
|
||||
- 🔴 and 🟡 findings: summed over those titles, each opening `<k> 🔴, <m> 🟡` after the colon,
|
||||
such as `Answer stability round 1: 1 🔴, 2 🟡; flag a deleted test`. Unknown where a round title
|
||||
lacks the counts, or the branch has no round.
|
||||
|
||||
@@ -99,7 +99,6 @@ def measure(merge: str, short: str, merged: str) -> list[Outcome] | Failure:
|
||||
if isinstance(after, Failure):
|
||||
return after
|
||||
items = shipped(before, after)
|
||||
# Most merges ship nothing; this spares them two more git calls.
|
||||
if not items:
|
||||
return []
|
||||
numstat = git("diff", "--numstat", f"{merge}^1", merge)
|
||||
|
||||
@@ -7,7 +7,7 @@ from todo_table import Item, items
|
||||
from reading_cost.figures import RECORD
|
||||
from round_titles import round_counts, round_findings
|
||||
|
||||
# Least to be measured before a score's medians show: the count the reading-cost trend waits for, which no published standard sets either.
|
||||
# Fewest single-item chunks a score needs before its medians print: the 10 figures the reading-cost trend waits for; no published standard sets either.
|
||||
ENOUGH = 10
|
||||
# The plan, and the records tools append to: none of their lines are the chunk's work.
|
||||
NOT_WORK = ("todo.md", HISTORY, RECORD)
|
||||
@@ -15,7 +15,7 @@ NOT_WORK = ("todo.md", HISTORY, RECORD)
|
||||
|
||||
@dataclasses.dataclass(frozen=True)
|
||||
class Outcome:
|
||||
"""What the merge that shipped an item measured. findings holds the 🔴 and 🟡 counts, None where a round title lacks them."""
|
||||
"""What the merge that shipped an item measured. findings holds the 🔴 and 🟡 counts, None where a round title lacks them or the branch has no round."""
|
||||
item: Item
|
||||
merge: str
|
||||
merged: str
|
||||
@@ -26,7 +26,7 @@ class Outcome:
|
||||
findings: tuple[int, int] | None
|
||||
|
||||
|
||||
# Each score, and the outcome it predicts. Each pass takes a first round whatever the change, so only the rounds after it measure how hard the change was to get right.
|
||||
# Each pass takes a first round whatever the change, so only the rounds after it measure how hard the change was to get right.
|
||||
MEASURES: dict[str, tuple[str, typing.Callable[[Outcome], int | None]]] = {
|
||||
"R": ("🔴 findings", lambda outcome: outcome.findings[0] if outcome.findings else None),
|
||||
"S": ("lines changed", lambda outcome: outcome.lines),
|
||||
|
||||
+1
-1
@@ -6,7 +6,7 @@ from failure import Failure
|
||||
EXEMPTIONS = ("", "decision", "defect", "principle", "question", "security")
|
||||
COLUMNS = ("ID", "Release", "Exempt", "Item", "R", "S", "C", "A", "G", "Goals", "Score")
|
||||
ITEMS_HEADER = "| " + " | ".join(COLUMNS) + " |"
|
||||
# A table may lack C alone: git history keeps tables written before C joined, which still read.
|
||||
# Tables in git history from before C joined lack it; items() still parses them, though rank_todo refuses one in a checkout.
|
||||
WITHOUT_C = "| " + " | ".join(column for column in COLUMNS if column != "C") + " |"
|
||||
|
||||
|
||||
|
||||
+1
-1
@@ -13,7 +13,7 @@ paths:
|
||||
- **C** — how hard the change is to get right: novel design, subtle invariants, many interacting parts. A huge rename is low C; a ten-line lock fix can be high. C stays out of the score.
|
||||
- **A** — its value to the audience in `README.md` → `## Audience`.
|
||||
- **G** — its value to the goals it cites in the Goals column; W is the weight of the heaviest of them.
|
||||
- **Score R, S and C from finished chunks wherever they hold a measurement.** Guess them, then run `~/.claude/bin/score-outcomes <R> <S> <C>` in the project. It lists the finished items guessed nearest and what their chunks measured, and the median outcome at each guessed value. Move each score to where items of a measured outcome like the one you expect sit. Keep a guess where none of the items it prints resembles yours.
|
||||
- **Check R, S and C against finished chunks.** Guess them, then run `~/.claude/bin/score-outcomes <R> <S> <C>` in the project. It lists the finished items guessed nearest, what their chunks measured, and the median outcome at each guessed value. Set each score to the value guessed for the finished items whose outcome matches what you expect of this one. Keep your guess when no listed item resembles the one you are scoring.
|
||||
- **An item scoring under the bar is deleted, with every item that needs it, and a finding under the bar is not filed.** The chunk's summary names each, with its score.
|
||||
- **The Exempt cell keeps an item whatever its score:** `security` for a security finding, `defect` for a 🔴 finding, `question` for a question only the human can answer, `decision` for an item `docs/decisions.md` cites, and, where no other reason fits, `principle` for a 🟡 finding against a file under `~/.claude/principles/`, whose item's detail names that principle. Every item `docs/decisions.md` cites carries one of these reasons.
|
||||
- **Unless the project has a reason to differ, weigh goals by position, the first heaviest.** When the weights stop listing the README's goals, `rank_todo.py` fails and prints those weights.
|
||||
|
||||
@@ -66,7 +66,7 @@ Give a reviewer without Bash the branch diff and `git ls-files`'s output in its
|
||||
- **Round.** A round is one launch of a pass's reviewer: the first, each re-entry, and the rerun after the architect returns Stage 0 questions ("Architecture" below). A rescore is a round only as "Architecture" → "Fresh" says.
|
||||
- **Architecture round.** The architecture pass's first round is the architect (unless skipped), the principles audit and the comprehension check, which "Opt-out" or "Architecture" → "Suspended" may skip. A later round relaunches each reviewer whose 🔴 or 🟡 the previous round's fixes answer, the comprehension check only as "Architecture" → "Fresh" says. Where those fixes carry an architectural decision, the architect and the principles audit run again.
|
||||
- **Auto-reviewer.** The external auto-reviewer (§4) is a pass of its own, each review it posts a round.
|
||||
- **Count.** Close each round with one commit that holds the round's fixes and is titled `Answer <pass> round <n>: <k> 🔴, <m> 🟡; …`, `<pass>` being the pass's name in lower case, such as `full scan`, and `<k>` and `<m>` the 🔴 and 🟡 findings the round's reviewers reported, summed, such as `Answer stability round 1: 1 🔴, 2 🟡; flag a deleted test`. `~/.claude/bin/score-outcomes` reads the counts to calibrate the plan's scores, and the rule hook blocks a round title without them. A round that changed nothing gets an empty commit (`git commit --allow-empty`). Push the commits when §4 runs next, where there is a remote. `~/.claude/bin/larv-review round-count` prints each pass's count and marks a pass at the cap. The auto-reviewer's count is the number of its reviews on the PR, less its reviews of a `Rescore:` commit.
|
||||
- **Count.** Close each round with one commit that holds the round's fixes. Title it `Answer <pass> round <n>: <k> 🔴, <m> 🟡; …`: `<pass>` is the pass's name in lower case, such as `full scan`, and `<k>` and `<m>` are the 🔴 and 🟡 findings all the round's reviewers reported. Example: `Answer stability round 1: 1 🔴, 2 🟡; flag a deleted test`. A round that changed nothing gets an empty commit (`git commit --allow-empty`). Push the commits when §4 runs next, where there is a remote. `~/.claude/bin/larv-review round-count` prints each pass's count and marks a pass at the cap. The auto-reviewer's count is the number of its reviews on the PR, less its reviews of a `Rescore:` commit.
|
||||
- **Later rounds.** A rerun pass reviews only what changed since it last reviewed: `git diff <the commit it last reviewed, or else the commit before this round's fixes> HEAD`, since the fixes may be unpushed. The comprehension check's seats still read the whole project. From round 2, prompt an agent under `~/.claude/agents/` with its own last round's findings verbatim too.
|
||||
- **Done.** A pass is done when its latest round leaves no 🔴 or 🟡 standing: none was reported, or each was shown factually wrong, declined, filed, or named under the bar per "Findings", or, for the prose pass, fixed. Resolve that round's 🟢s and ❓s per "Findings" too.
|
||||
- **Cap.** A pass takes at most three rounds per chunk. Instead of a fourth, list what is open and ask the user. For the auto-reviewer, ask before the push that would summon its fourth, and hold the fixes unpushed until the answer.
|
||||
|
||||
@@ -37,8 +37,8 @@
|
||||
| 92 | 0.2.0 | | **Have the worker route each subagent by its task's R + C, and delegate a task only when the worker needs just its conclusion.** | 2 | 2 | 5 | 5 | 6 | 1.4 | 19.0 |
|
||||
| 110 | 0.2.0 | | **Count, for each finished chunk, the later changes that fixed code it wrote, and show them beside its guessed R.** | 2 | 4 | 6 | 5 | 6 | 1.1, 1.4 | 18.9 |
|
||||
| 89 | 0.2.0 | | **Run the judge on the rung its chunk's R + C picks, once a replay of archived transcripts shows it returns the verdicts on record.** | 3 | 4 | 7 | 5 | 6 | 1.4 | 17.5 |
|
||||
| 115 | 0.2.0 | question | **Confirm or set how many finished chunks of one item `score-outcomes` waits for before it shows a score's medians, today 10.** | 1 | 1 | 2 | 4 | 5 | 1.2 | 16.6 |
|
||||
| 116 | 0.2.0 | | **Report R by the share of chunks with a 🔴, once 10 chunks of one item record finding counts and most record no 🔴.** | 1 | 2 | 2 | 4 | 5 | 1.1 | 16.4 |
|
||||
| 115 | 0.2.0 | question | **Confirm or set how many finished chunks that each shipped one item `score-outcomes` waits for before it shows a score's medians, today 10.** | 1 | 1 | 2 | 4 | 5 | 1.2 | 16.6 |
|
||||
| 116 | 0.2.0 | | **Report R by the share of chunks with a 🔴, once 10 chunks that each shipped one item record finding counts and most record no 🔴.** | 1 | 2 | 2 | 4 | 5 | 1.1 | 16.4 |
|
||||
| 111 | 0.2.0 | | **Measure the chunks of a project that merges by squash or fast-forward, which `score-outcomes` skips today.** | 3 | 3 | 5 | 4 | 5 | 1.3 | 13.9 |
|
||||
| 113 | 0.2.0 | | **Compute an item's S from the code it names, where it names any, and show it beside the finished items `score-outcomes` lists.** | 3 | 4 | 6 | 4 | 5 | 1.1, 1.4 | 13.9 |
|
||||
| 1 | 0.3.0 | question | **Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume.** | 3 | 5 | 2 | 8 | 9 | 3, 4 | 27.0 |
|
||||
@@ -58,7 +58,7 @@
|
||||
| 68 | 0.3.0 | principle | **Test `workflow-bench/compare.py`'s blinding and `bench.py`'s run plan.** | 2 | 4 | 4 | 3 | 5 | 1.1 | 12.9 |
|
||||
| 65 | 0.3.0 | | **Archive each judge reply the loop rejects.** | 3 | 4 | 3 | 4 | 5 | 3 | 12.5 |
|
||||
| 82 | 0.3.0 | principle | **Sort `AGENTS.md`'s decision titles and `docs/decisions.md`'s entries by title.** | 1 | 2 | 2 | 3 | 4 | 1.3 | 12.3 |
|
||||
| 114 | 0.3.0 | | **Run git through `git_repo.py` in `rule_hook`, `metric_bench` and `reading_cost`, keeping rule-hook's guards as an option, so one module owns how a tool runs git.** | 3 | 4 | 4 | 3 | 5 | 1.1 | 11.9 |
|
||||
| 114 | 0.3.0 | | **Run git through `git_repo.py` in `rule_hook`, `metric_bench`, `reading_cost` and `loop_claude`, keeping rule-hook's guards as an option, so one module owns how a tool runs git.** | 3 | 4 | 4 | 3 | 5 | 1.1 | 11.9 |
|
||||
| 73 | 0.3.0 | | **Have each reviewer write its full report to a file and return the worker only its findings' one-line summaries.** | 3 | 4 | 4 | 4 | 4 | 1.4 | 11.7 |
|
||||
| 6 | 0.3.0 | decision | **Move what `loop-claude` writes out of `~/.claude.json`, and ask the human about each write that must stay.** | 5 | 5 | 6 | 4 | 5 | 1.1 | 11.7 |
|
||||
| 51 | 0.3.0 | principle | **Hand loop-claude's terminal output to an injected effect, so no storage or retry function prints.** | 3 | 5 | 5 | 3 | 5 | 1.1 | 11.7 |
|
||||
@@ -133,7 +133,7 @@ Needs 88.
|
||||
|
||||
### 110. Count, for each finished chunk, the later changes that fixed code it wrote, and show them beside its guessed R.
|
||||
|
||||
`score-outcomes` measures R only by the 🔴 findings review caught. A serious bug review missed shows later, as a change that fixes code the chunk wrote. Item 98 asked for both; this is the second half.
|
||||
`score-outcomes` measures R only by the 🔴 findings review caught. A serious bug review missed shows later, as a change that fixes code the chunk wrote.
|
||||
|
||||
### 89. Run the judge on the rung its chunk's R + C picks, once a replay of archived transcripts shows it returns the verdicts on record.
|
||||
|
||||
@@ -141,11 +141,11 @@ loop-claude starts the judge itself (`bin/loop_claude/cycle/judge.py`), so it ro
|
||||
|
||||
Needs 88.
|
||||
|
||||
### 115. Confirm or set how many finished chunks of one item `score-outcomes` waits for before it shows a score's medians, today 10.
|
||||
### 115. Confirm or set how many finished chunks that each shipped one item `score-outcomes` waits for before it shows a score's medians, today 10.
|
||||
|
||||
`ENOUGH` in `bin/score_outcomes/outcomes.py` reuses the 10 figures the reading-cost trend waits for. No published standard sets either, and `CLAUDE.md` → "Web research" asks the human for a threshold a consumer relies on.
|
||||
`ENOUGH` in `bin/score_outcomes/outcomes.py` matches the 10 figures the reading-cost trend waits for. No published standard sets either, and `CLAUDE.md` → "Web research" asks the human for a threshold a consumer relies on.
|
||||
|
||||
### 116. Report R by the share of chunks with a 🔴, once 10 chunks of one item record finding counts and most record no 🔴.
|
||||
### 116. Report R by the share of chunks with a 🔴, once 10 chunks that each shipped one item record finding counts and most record no 🔴.
|
||||
|
||||
`score-outcomes` reports R as the median 🔴 count at each guessed R. Where most chunks have no 🔴, every median reads 0 and tells a scorer nothing. No round title held counts before PR #254, so how often a chunk has a 🔴 is not yet known.
|
||||
|
||||
@@ -155,7 +155,7 @@ Needs 88.
|
||||
|
||||
### 113. Compute an item's S from the code it names, where it names any, and show it beside the finished items `score-outcomes` lists.
|
||||
|
||||
Item 98 asked that a score computable from the code an item touches, such as the files it names, come from that computation. `score-outcomes` grounds R, S and C in finished chunks only. Where an item names files or units, their size bounds what the change can touch.
|
||||
`score-outcomes` grounds R, S and C in finished chunks only. Where an item names files or units, their size bounds what the change can touch.
|
||||
|
||||
### 1. Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume.
|
||||
|
||||
@@ -237,7 +237,7 @@ Goal 3, raised by the principles audit of PR #215: the judge runs with `--no-ses
|
||||
|
||||
"Deterministic order", in `principles/technical-principles.md`, raised by the principles audit of PR #224: their order carries no meaning, so two chunks adding a decision conflict at the end, and a reader cannot find a title by scanning.
|
||||
|
||||
### 114. Run git through `git_repo.py` in `rule_hook`, `metric_bench` and `reading_cost`, keeping rule-hook's guards as an option, so one module owns how a tool runs git.
|
||||
### 114. Run git through `git_repo.py` in `rule_hook`, `metric_bench`, `reading_cost` and `loop_claude`, keeping rule-hook's guards as an option, so one module owns how a tool runs git.
|
||||
|
||||
The comprehension seats on PR #254 found five git runners with different contracts: `git_repo.git`, `rule_hook/git.py`'s guarded one, `metric_bench/main.py`'s, `reading_cost/main.py`'s `located` and `loop_claude/effects.py`'s.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user