Fold AGENTS.md into the decision log, .claude/rules/, README and the panel's seat prompts; load CLAUDE.md once in this repo
CI / tests (pull_request) Successful in 2m7s
CI / tests (pull_request) Successful in 2m7s
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
---
|
||||
paths:
|
||||
- "todo.md"
|
||||
---
|
||||
|
||||
# Routing calls: file them in the plan
|
||||
|
||||
`routing-calls-raised.md` sits at the root of loop-claude's archive (`$LOOP_CLAUDE_TRANSCRIPTS`, default `~/.claude/loop-claude-transcripts`). Each of its lines is a call or a `Reset`, with a stamp. A call is new when it is stamped after the latest `Reset` and after the latest stamp that `todo.md` or `docs/decisions.md` → `routing:` cites.
|
||||
|
||||
When there are new calls, file one `todo.md` item to settle them, or refresh the item already filed. Its detail quotes those calls with their stamps, and the routed-chunks table of `routing-figures.md` beside it, never the project names its other tables hold.
|
||||
|
||||
A change to the ladder, its steps or the delegation rule is the human's. The chunk that settles the calls cites the latest stamp it settled in `docs/decisions.md` → `routing:`, whatever the human decided, so they are not filed again. Once a chunk that changes the ladder, its steps or the delegation rule has merged, append `- <UTC time> Reset` to `routing-calls-raised.md`: the figures then count only chunks finished after it, and its calls may be raised again.
|
||||
@@ -1,3 +1,4 @@
|
||||
{
|
||||
"model": "claude-opus-5-5"
|
||||
"model": "claude-opus-5-5",
|
||||
"claudeMdExcludes": ["**/.claude/CLAUDE.md"]
|
||||
}
|
||||
|
||||
+2
-1
@@ -6,7 +6,6 @@
|
||||
|
||||
!.gitattributes
|
||||
!.gitignore
|
||||
!AGENTS.md
|
||||
!CHANGELOG.md
|
||||
!CLAUDE.md
|
||||
!README.md
|
||||
@@ -15,6 +14,8 @@
|
||||
!todo.md
|
||||
|
||||
!.claude/
|
||||
!.claude/rules/
|
||||
!.claude/rules/*.md
|
||||
!.claude/settings.json
|
||||
!.gitea/
|
||||
!.gitea/workflows/
|
||||
|
||||
@@ -1,52 +0,0 @@
|
||||
# Working here
|
||||
|
||||
## Project principles
|
||||
|
||||
Each project principle states one rule that the decisions in `docs/decisions.md` apply; the entries there hold the specifics and the evidence. The numbers name the principles, and don't rank them.
|
||||
|
||||
1. **Cut cost only where a measurement of archived chunks shows quality holds.** Chunk bundling, the round cap, which fixes rerun a pass, a reviewer of its own for each pass, the review a branch changing only Markdown no agent follows gets, the passes kept for the release review, review opt-outs, the security pass, compaction and the routing ladder all apply it.
|
||||
2. **A measurement files or ranks work, and never blocks a merge.** The comprehension floor and check, and a reading-cost rise, apply it. A merge waits on a scoring run the plan calls for only until the run is recorded, whatever it scores.
|
||||
3. **Each file has one writer.** `~/.claude/loop-claude-models.json` is loop-claude's, `~/.claude.json` is Claude Code's, and `~/.claude` moves only through `deploy-release`. The exception is `~/.claude/settings.json`, which Claude Code writes from any session. Git's clean filter `bin/settings_filter.py` keeps each machine's model and Claude Code's key order out of every commit, and the working rule on `~/.claude/settings.json` below carries its other changes into this repo.
|
||||
4. **A rule a program can check is enforced by a program, and reviewers rule on the rest.** rule-hook and its overrides, `docker-run-memory`, the refused writes of reviewers under `agents/`, and CI with `main`'s branch protection apply it.
|
||||
5. **A chunk can't vouch for itself.** What a chunk writes is approved by a review pass, by the human, or by a precedent the repo held before the chunk began. So an unanswered ask leaves the PR unmerged, the human approves the premises chunk and runs `deploy-release --cut`, and the judge holds a chunk open while an answer the human typed isn't recorded anywhere.
|
||||
6. **An unattended run never waits on a prompt, and a lasting failure stops it.** Every claude loop-claude starts bypasses permissions inside its sandbox, each claude it or loop-inbox opens on a terminal has `CLAUDE_CODE_SANDBOXED` set, and interactive sessions run in auto mode with the dangerous-mode prompt skipped. A failed archive stops the loop, while a `claude` that cannot start, as during an update, is retried.
|
||||
7. **One word names one thing, and one rule has one home.** In `bin/`, an outcome is an entry of a `.outcomes.md` file in loop-claude's archive, a record is a document tools or people keep entries in, and a place is what a comprehension seat names. `CLAUDE.md` holds only the rules no path can scope, and each `rules/` file loads by its `paths:`.
|
||||
|
||||
## Decisions no project principle covers
|
||||
|
||||
- bin/: the tools run on the host's Python, with no container, and so do their tests outside CI
|
||||
- bin/: the tools support only the latest stable Python, and the tests, written in plain unittest, run on it in four pytest-xdist workers
|
||||
- loop-claude: one session per project, its id derived from the checkout's path relative to `~/code`, or to `/` outside it
|
||||
- loop-inbox: a loop-claude lists itself while it runs, and its waiting question, as files per session under `~/.local/state/loop-claude/`, and takes the first answer, from its terminal or from loop-inbox, that names that question
|
||||
- machine load: a heavy command waits for one of the machine's heavy slots, one for every 4 CPUs, which every session shares, and loop-claude starts a worker only while at least a quarter of the machine's memory is available
|
||||
- principles: about seven things per level, four or five where they act on each other, more where a reader finds them by name; crossing a limit asks for a grouping or a recorded reason
|
||||
- review: a release review fixes its findings in the release it reviews, and files under that release only a finding that needs a human answer, adds a feature or outlasts its five rounds
|
||||
- review: a reviewer or comprehension seat that rules the work below standard may ask to rerun once, one rung up, in the same round; the ruling that stands is an escalation trigger for the worker unless the fix changes only prose, and never for the judge
|
||||
- review: a reviewer under `agents/` marks a 🔴 or 🟡 `[misread]` where the implementer misread code that had already shipped, each round title counts the marked findings, and `score-outcomes` lists them per chunk
|
||||
- review: stability and product-owner report only a defect, a broken requirement of the plan or the goals, a breach of a technical principle, or for stability a hard place the change touches; each architect finding names a later change the PR makes harder; prose runs only on a chunk that changes prose
|
||||
- review: the stability pass mutation-tests the lines a chunk changes, in place of measuring test coverage
|
||||
- routing: a worker delegates a task only where it needs just the task's conclusion, and each subagent runs on the rung its task's L picks from the project's rung, never below the project's rung when it files or scores todo.md items
|
||||
- routing: a worker hands a task one rung up on each escalation trigger, up to two rungs above the rung its item picks unless the human agrees, and opens the subagent's prompt with the trigger so the routing figures count it
|
||||
- routing: a worker whose run ends asking for a higher rung, citing an escalation trigger the judge finds in the transcript, steps one rung up as the judge interrupts or quotes an answer, or next cycle, up to two rungs above the rung its item picks
|
||||
- routing: the worker changes rung only as a chunk starts, after every second unfinished verdict, or when the judge reports a taken-in item that picks a higher rung or an escalation trigger the worker cites
|
||||
- tests: each test earns its keep as the technical principles' test bullet says, and the worker takes a test's expected values from its item, never from the code
|
||||
- the repo may name bender, bender-infra and ai-sandbox
|
||||
- todo.md: one table of items, scored by the formula it states, held to its bar and ranked by `bin/rank_todo.py`, which ranks each blocker above the items it blocks; each achieve goal weighs by its position, code health first and four times as heavy while the comprehension panel's overall is under 7.0 or unmeasured, then README.md's goals, and a maintain goal weighs 0.5 per point of the confidence an item's test, gate leg or probe adds to it; the table's order is the plan's only order
|
||||
- todo.md: only a session or subagent on the project's rung or above scores or reshapes the plan; one below it drafts new items and changes to filed ones for a subagent at or above that rung to apply and score, and removes finished ones
|
||||
- worker: a chunk's worker writes the simplest change that solves its item, test first wherever a test can check the change, and reads a technical principle only where the item, a finding or its own record names it; larv-review's reviewers hold the change to the principles and to the standards in `skills/larv-review/standards/`
|
||||
- workflow-bench/: the remote may show the bench cases' names and commit SHAs
|
||||
|
||||
## Working rules
|
||||
|
||||
- `routing-calls-raised.md` sits at the root of loop-claude's archive (`$LOOP_CLAUDE_TRANSCRIPTS`, default `~/.claude/loop-claude-transcripts`). Each of its lines is a call or a `Reset`, with a stamp. A call is new when it is stamped after the latest `Reset` and after the latest stamp that `todo.md` or `docs/decisions.md` → `routing:` cites. When there are new calls, file one `todo.md` item to settle them, or refresh the item already filed. Its detail quotes those calls with their stamps, and the routed-chunks table of `routing-figures.md` beside it, never the project names its other tables hold. A change to the ladder, its steps or the delegation rule is the human's. The chunk that settles the calls cites the latest stamp it settled in `docs/decisions.md` → `routing:`, whatever the human decided, so they are not filed again. Once a chunk that changes the ladder, its steps or the delegation rule has merged, append `- <UTC time> Reset` to `routing-calls-raised.md`: the figures then count only chunks finished after it, and its calls may be raised again.
|
||||
- When `~/.claude/settings.json` has uncommitted changes, carry them into `~/code/claude-config` on a branch of their own and merge them through a PR: Claude Code writes that file from any session, and `deploy-release` refuses to move `~/.claude` until a release holds them. Read their diff first: `git -C ~/.claude diff HEAD -- settings.json`. An empty diff means only the model or the key order changed, which `deploy-release` takes as no change. When the diff holds a credential, such as a token in `env` or `mcpServers`, ask the human to move it out of the file, and commit only once it is gone. A token in `env` moves to the shell profile; a server in `mcpServers` moves to `~/.claude.json` with `claude mcp add --scope user`.
|
||||
|
||||
## Scoring run
|
||||
|
||||
The project values for `skills/comprehension-panel/seat-prompts.md`:
|
||||
|
||||
- `{language}`: Python
|
||||
- `{kind}`: a Claude Code configuration with an agent loop and review skills
|
||||
- `{domain}`: driving headless Claude Code sessions, agent review workflows
|
||||
- `{domain docs}`: the Claude Code documentation
|
||||
- `{3am question}`: a loop-claude run exits 1 overnight after the judge returned a verdict the loop rejected, or a larv-review run looped a reviewer a third time
|
||||
+2
-1
@@ -2,7 +2,8 @@
|
||||
|
||||
## Unreleased
|
||||
|
||||
- `AGENTS.md` groups most decision titles into seven project principles, and each new decision is checked against them: a principle covers it, it breaks one, or it suggests a new one for you to approve.
|
||||
- `~/.claude` holds no `AGENTS.md` any more, so every session in another project starts about 3,600 tokens smaller. In `~/code/claude-config`, only the clone's `CLAUDE.md` loads, not the release's as well. This repo's working rules load from its `.claude/rules/`, and its scoring-run values sit in `skills/comprehension-panel/seat-prompts.md`.
|
||||
- The head of `docs/decisions.md` groups most decision titles into seven project principles, and each new decision is checked against them: a principle covers it, it breaks one, or it suggests a new one for you to approve.
|
||||
- The prose reviewer now holds prose to the negation rule: write `doesn't cost anything`, never `costs nothing`, after any verb or its preposition.
|
||||
- `rule-hook` now checks files at `git commit`: each file that differs from HEAD or is untracked and not ignored, even one the commit leaves out. It holds each to `action-pin`, `image-pin`, `ignorefile-sorted` and `no-ai-attribution`, so a file a Bash command wrote is checked as an Edit or Write is. A `# rule-override` line in the file or the command overrides a breach.
|
||||
- `chunk-pr merge` now refuses while a scoring run the plan calls is unrecorded on the branch, and `larv-review needs-scoring-run` calls one after a release is cut with none.
|
||||
|
||||
@@ -10,9 +10,9 @@ How work proceeds in any repo, unless the repo's `AGENTS.md` says otherwise. The
|
||||
- **When the next release has no items left and work has landed towards it, its release review is the chunk** (`larv-review` §3 → "Release review"). **Once that has merged and the release holds no item, the release is finished: stop.** Report what it holds and that it is ready to cut. Under `/loop`, this ends the loop. Until the human cuts it, only a security fix, or an item its release review filed, lands, into that release; never start a later release's items or plan a new one.
|
||||
- **Open every chunk with one line:** the last version cut, how many changes are unreleased (the entries under `CHANGELOG.md` → `## Unreleased`, or else the commits since the last tag), and the release this chunk ships into. A repo that doesn't publish anything says so once.
|
||||
- **Read the README's `## Goals` and `## Audience` before starting a chunk, unless your prompt quotes them.** The chunk's items set its scope. The goals choose between ways to deliver those items, and never add to them.
|
||||
- **Read the plan and the decisions only as far as the chunk needs.** Where your prompt quotes `chunk-preflight`'s facts, they hold the next item's L, E + I, tagline and detail, and each item that may join it with its L, E + I, S, tagline and detail; open `todo.md` only for what they leave out. Otherwise run `grep -n '^## Details' todo.md`, then read `todo.md` with the Read tool up to the line it prints, or whole when it prints none. Then read the details of only the items the chunk takes. `AGENTS.md` lists the project principles and the title of each decision no project principle covers. Read an entry in `docs/decisions.md` only where the project principle or the title leaves open what the chunk or the review needs.
|
||||
- **Read the plan and the decisions only as far as the chunk needs.** Where your prompt quotes `chunk-preflight`'s facts, they hold the next item's L, E + I, tagline and detail, and each item that may join it with its L, E + I, S, tagline and detail; open `todo.md` only for what they leave out. Otherwise run `grep -n '^## Details' todo.md`, then read `todo.md` with the Read tool up to the line it prints, or whole when it prints none. Then read the details of only the items the chunk takes. `AGENTS.md`, or the head of `docs/decisions.md` in a project that keeps no `AGENTS.md`, lists the project principles and the title of each decision no project principle covers. Read an entry in `docs/decisions.md` only where the project principle or the title leaves open what the chunk or the review needs.
|
||||
- **Work one chunk at a time, and put every item that can share its review into it.** Every review has a fixed cost, so a chunk takes the next plan item plus every other item for which three things hold: they name one release; they fire the same review passes (`larv-review` §3); and no item outside the chunk blocks one of them. The items need not share a purpose. An item whose risk R, in `todo.md`, is above 5 ships alone: it joins no chunk, and none joins it. The next plan item is the first that does not wait: an item waits while it is marked `question`, until the human answers, or while an item that blocks it is still in the plan. Tiny items, a few lines of change each, need not fire the same passes: bundle up to ten that name one release, and that no item outside the chunk blocks, into one chunk. Split a milestone into items in `todo.md` before starting it. Fix a finding in the chunk's own change within the chunk. File a finding about anything else in `todo.md`.
|
||||
- **Ask, don't guess.** Three choices are always the human's: a goal; a release, meaning the items planned into it and when it is cut; and a change to loop-claude's routing ladder, its rungs included. Any other rule that asks the human's approval reserves that choice too. Ask about a reserved choice. For any other choice, first check whether the goals already answer it. If they nearly do, propose a change to the goals and show how it answers this case: an answer settles one question, a goal settles every question like it. Otherwise take the option you would recommend, and record it with its reason: in the item's detail, or, where it governs later work, as the next sentence says. A recommendation you can give a reason for is not a guess. Ask only where you have no recommendation. Write every answer once, where it belongs, never only in chat: a goal in `README.md`, a working rule in `AGENTS.md`, a standing choice in a comment at the one place it governs, or in `docs/decisions.md` once made in more than one place. When an answer holds a goal and a choice, write the goal in the README, and record as a choice only what the goal leaves open.
|
||||
- **Ask, don't guess.** Three choices are always the human's: a goal; a release, meaning the items planned into it and when it is cut; and a change to loop-claude's routing ladder, its rungs included. Any other rule that asks the human's approval reserves that choice too. Ask about a reserved choice. For any other choice, first check whether the goals already answer it. If they nearly do, propose a change to the goals and show how it answers this case: an answer settles one question, a goal settles every question like it. Otherwise take the option you would recommend, and record it with its reason: in the item's detail, or, where it governs later work, as the next sentence says. A recommendation you can give a reason for is not a guess. Ask only where you have no recommendation. Write every answer once, where it belongs, never only in chat: a goal in `README.md`, a working rule in `AGENTS.md`, or in the `.claude/rules/` file its paths scope where the project keeps no `AGENTS.md`, a standing choice in a comment at the one place it governs, or in `docs/decisions.md` once made in more than one place. When an answer holds a goal and a choice, write the goal in the README, and record as a choice only what the goal leaves open.
|
||||
- **Bench a syntax with the people who write it.** Before a new or changed spelling of something users read or write ships — markdown, HTML, a config key, a CLI flag — a panel of fresh-context readers, seated as those users from the README's `## Audience`, picks it.
|
||||
- **Implement the simplest change that solves the item, and ship it with `/larv-review`.** Whenever a test can check the change, write that test first and see it fail. Take its expected values from the item, never from the code. larv-review's reviewers hold the change to the technical principles, and a finding against one names it. Read a file under `~/.claude/principles/` only when the item changes it, a finding or a record you write names it, or you decline a finding.
|
||||
- **Remove a finished item's row and detail from `todo.md`, and revise any decision that cites it.** If the repo publishes something others consume — a package, an image, an API — reword the item for them and move it to `CHANGELOG.md` under `## Unreleased`. A changelog is for the public, never for the next agent. Otherwise delete it; git history is the record. `~/.claude/bin/todo-item finish <ID>` removes the row and detail, and adds the bullet you pass with `--changelog <bullet>`; it refuses while a decision cites the item.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Claude Code configuration
|
||||
|
||||
My personal `~/.claude`, version controlled: `CLAUDE.md`, `AGENTS.md` and `rules/` for instructions, the words under `CLAUDE.md` → "Vocabulary"; `agents/` and `skills/`; `principles/` and `skills/larv-review/standards/` for what the reviewer agents hold projects to; `docs/` for decisions and the comprehension history; `settings.json` for the harness and `.claude/settings.json` for the harness inside this repo; `CHANGELOG.md` and `todo.md`; the tools in `bin/`; `workflow-bench/`, the scripts and prompts of the 2026-09-30 bench of larv-review; `reviewer-merge-trials/`, the 2026-11-09 trials of merging reviewers, with their method, results and scripts; and `presentation/`, a page that explains this setup to newcomers, with the script that prints it to PDF.
|
||||
My personal `~/.claude`, version controlled: `CLAUDE.md` and `rules/` for instructions, the words under `CLAUDE.md` → "Vocabulary"; `.claude/rules/` for the working rules of this repo alone; `agents/` and `skills/`; `principles/` and `skills/larv-review/standards/` for what the reviewer agents hold projects to; `docs/` for decisions and the comprehension history; `settings.json` for the harness and `.claude/settings.json` for the harness inside this repo; `CHANGELOG.md` and `todo.md`; the tools in `bin/`; `workflow-bench/`, the scripts and prompts of the 2026-09-30 bench of larv-review; `reviewer-merge-trials/`, the 2026-11-09 trials of merging reviewers, with their method, results and scripts; and `presentation/`, a page that explains this setup to newcomers, with the script that prints it to PDF.
|
||||
|
||||
## Goals
|
||||
|
||||
@@ -77,7 +77,11 @@ Move `~/.claude` to the newest release:
|
||||
~/code/claude-config/bin/deploy-release
|
||||
```
|
||||
|
||||
It refuses while a file `~/.claude` tracks has an uncommitted change, such as a hook Claude Code wrote into `settings.json`: merge that per `AGENTS.md` → "Working rules", then cut a release. A model picked with `/model` is no such change. It prints `CHANGELOG.md`'s section for each version it moved past: do what each asks, such as a new step under Install. `deploy-release --help` says what else it checks.
|
||||
It refuses while a file `~/.claude` tracks has an uncommitted change, such as a hook Claude Code wrote into `settings.json`. Merge that into `~/code/claude-config` on a branch of its own, through a PR, then cut a release. A model picked with `/model` is no such change.
|
||||
|
||||
For `~/.claude/settings.json`, which Claude Code writes from any session, read the diff first: `git -C ~/.claude diff HEAD -- settings.json`. An empty diff means only the model or the key order changed, which `deploy-release` takes as no change. When the diff holds a credential, such as a token in `env` or `mcpServers`, move it out of the file, and commit only once it is gone: a token in `env` moves to the shell profile, and a server in `mcpServers` moves to `~/.claude.json` with `claude mcp add --scope user`.
|
||||
|
||||
It prints `CHANGELOG.md`'s section for each version it moved past: do what each asks, such as a new step under Install. `deploy-release --help` says what else it checks.
|
||||
|
||||
## Release
|
||||
|
||||
|
||||
@@ -63,7 +63,7 @@ def raise_calls(root: pathlib.Path, new: list[Call], rung: Rung, loop: Loop) ->
|
||||
unstarted = hand_over(ClaudeCommand(claude_args(rung, [prompt]), str(loop.paths.config_clone), {}), loop.effects)
|
||||
if unstarted:
|
||||
return Stop(1, f"could not start claude for the routing calls in {loop.paths.config_clone}, the setup's development clone: {unstarted.reason}")
|
||||
# Raised once the human has seen them, answered or not: an unanswered call reaches the plan through AGENTS.md, so it is not asked twice.
|
||||
# Raised once the human has seen them, answered or not: an unanswered call reaches the plan through .claude/rules/routing-calls.md, so it is not asked twice.
|
||||
if unmarked := state.mark_raised(root, new, utc(loop.effects.now())):
|
||||
say(f"routing figures: {unmarked.reason}", loop.effects)
|
||||
return None
|
||||
|
||||
@@ -50,11 +50,14 @@ class Citations(unittest.TestCase):
|
||||
def test_every_folder_the_judge_reads_rules_from_exists(self):
|
||||
self.assertEqual([folder for folder in HUMAN_RULE_DIRS if not (ROOT / folder).is_dir()], [])
|
||||
|
||||
def test_every_decision_title_agents_md_lists_is_a_title_in_the_decision_log(self):
|
||||
listed = LISTED_TITLE.findall((ROOT / "AGENTS.md").read_text().split("## Decisions no project principle covers\n\n")[1].split("\n\n")[0])
|
||||
def test_every_decision_title_the_log_lists_at_its_head_is_a_title_in_it(self):
|
||||
log = (ROOT / "docs/decisions.md").read_text()
|
||||
listed = LISTED_TITLE.findall(log.split("# Decisions no project principle covers\n\n")[1].split("\n\n")[0])
|
||||
self.assertTrue(listed)
|
||||
titles = set(DECISION_TITLE.findall((ROOT / "docs/decisions.md").read_text()))
|
||||
self.assertEqual([title for title in listed if title not in titles], [])
|
||||
self.assertEqual([title for title in listed if title not in set(DECISION_TITLE.findall(log))], [])
|
||||
|
||||
def test_the_repo_keeps_no_agents_md_since_claude_code_would_load_the_releases_copy_into_every_project(self):
|
||||
self.assertFalse((ROOT / "AGENTS.md").exists())
|
||||
|
||||
def test_every_todo_citation_of_a_decision_names_a_title(self):
|
||||
titles = DECISION_TITLE.findall((ROOT / "docs/decisions.md").read_text())
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""What loop-claude keeps at the archive's root between measurements: docs/decisions.md → `routing: loop-claude measures review rounds…`.
|
||||
|
||||
STATE holds, as fields loop-claude reads back, the cycle it last measured at and each call it raised. RAISED lists the raised calls for the human to read. A chunk appends a reset to RAISED by hand, as AGENTS.md says, and loop-claude reads the resets from there."""
|
||||
STATE holds, as fields loop-claude reads back, the cycle it last measured at and each call it raised. RAISED lists the raised calls for the human to read. A chunk appends a reset to RAISED by hand, as .claude/rules/routing-calls.md says, and loop-claude reads the resets from there."""
|
||||
import dataclasses
|
||||
import json
|
||||
import pathlib
|
||||
|
||||
+40
-2
@@ -1,3 +1,41 @@
|
||||
# Project principles
|
||||
|
||||
This repo keeps no `AGENTS.md`: `~/.claude` is a checkout of it, and Claude Code would load an `AGENTS.md` there into every other project's sessions. So its project principles, and the title of each decision no project principle covers, head its decision log.
|
||||
|
||||
Each project principle states one rule that the decisions below apply; their entries hold the specifics and the evidence. The numbers name the principles, and don't rank them.
|
||||
|
||||
1. **Cut cost only where a measurement of archived chunks shows quality holds.** Chunk bundling, the round cap, which fixes rerun a pass, a reviewer of its own for each pass, the review a branch changing only Markdown no agent follows gets, the passes kept for the release review, review opt-outs, the security pass, compaction and the routing ladder all apply it.
|
||||
2. **A measurement files or ranks work, and never blocks a merge.** The comprehension floor and check, and a reading-cost rise, apply it. A merge waits on a scoring run the plan calls for only until the run is recorded, whatever it scores.
|
||||
3. **Each file has one writer.** `~/.claude/loop-claude-models.json` is loop-claude's, `~/.claude.json` is Claude Code's, and `~/.claude` moves only through `deploy-release`. The exception is `~/.claude/settings.json`, which Claude Code writes from any session. Git's clean filter `bin/settings_filter.py` keeps each machine's model and Claude Code's key order out of every commit, and `README.md` → "Update" carries its other changes into this repo.
|
||||
4. **A rule a program can check is enforced by a program, and reviewers rule on the rest.** rule-hook and its overrides, `docker-run-memory`, the refused writes of reviewers under `agents/`, and CI with `main`'s branch protection apply it.
|
||||
5. **A chunk can't vouch for itself.** What a chunk writes is approved by a review pass, by the human, or by a precedent the repo held before the chunk began. So an unanswered ask leaves the PR unmerged, the human approves the premises chunk and runs `deploy-release --cut`, and the judge holds a chunk open while an answer the human typed isn't recorded anywhere.
|
||||
6. **An unattended run never waits on a prompt, and a lasting failure stops it.** Every claude loop-claude starts bypasses permissions inside its sandbox, each claude it or loop-inbox opens on a terminal has `CLAUDE_CODE_SANDBOXED` set, and interactive sessions run in auto mode with the dangerous-mode prompt skipped. A failed archive stops the loop, while a `claude` that cannot start, as during an update, is retried.
|
||||
7. **One word names one thing, and one rule has one home.** In `bin/`, an outcome is an entry of a `.outcomes.md` file in loop-claude's archive, a record is a document tools or people keep entries in, and a place is what a comprehension seat names. `CLAUDE.md` holds only the rules no path can scope, and each `rules/` file loads by its `paths:`. This repo's own working rules sit in `.claude/rules/`, which loads only in this repo.
|
||||
|
||||
# Decisions no project principle covers
|
||||
|
||||
- bin/: the tools run on the host's Python, with no container, and so do their tests outside CI
|
||||
- bin/: the tools support only the latest stable Python, and the tests, written in plain unittest, run on it in four pytest-xdist workers
|
||||
- loop-claude: one session per project, its id derived from the checkout's path relative to `~/code`, or to `/` outside it
|
||||
- loop-inbox: a loop-claude lists itself while it runs, and its waiting question, as files per session under `~/.local/state/loop-claude/`, and takes the first answer, from its terminal or from loop-inbox, that names that question
|
||||
- machine load: a heavy command waits for one of the machine's heavy slots, one for every 4 CPUs, which every session shares, and loop-claude starts a worker only while at least a quarter of the machine's memory is available
|
||||
- principles: about seven things per level, four or five where they act on each other, more where a reader finds them by name; crossing a limit asks for a grouping or a recorded reason
|
||||
- review: a release review fixes its findings in the release it reviews, and files under that release only a finding that needs a human answer, adds a feature or outlasts its five rounds
|
||||
- review: a reviewer or comprehension seat that rules the work below standard may ask to rerun once, one rung up, in the same round; the ruling that stands is an escalation trigger for the worker unless the fix changes only prose, and never for the judge
|
||||
- review: a reviewer under `agents/` marks a 🔴 or 🟡 `[misread]` where the implementer misread code that had already shipped, each round title counts the marked findings, and `score-outcomes` lists them per chunk
|
||||
- review: stability and product-owner report only a defect, a broken requirement of the plan or the goals, a breach of a technical principle, or for stability a hard place the change touches; each architect finding names a later change the PR makes harder; prose runs only on a chunk that changes prose
|
||||
- review: the stability pass mutation-tests the lines a chunk changes, in place of measuring test coverage
|
||||
- routing: a worker delegates a task only where it needs just the task's conclusion, and each subagent runs on the rung its task's L picks from the project's rung, never below the project's rung when it files or scores todo.md items
|
||||
- routing: a worker hands a task one rung up on each escalation trigger, up to two rungs above the rung its item picks unless the human agrees, and opens the subagent's prompt with the trigger so the routing figures count it
|
||||
- routing: a worker whose run ends asking for a higher rung, citing an escalation trigger the judge finds in the transcript, steps one rung up as the judge interrupts or quotes an answer, or next cycle, up to two rungs above the rung its item picks
|
||||
- routing: the worker changes rung only as a chunk starts, after every second unfinished verdict, or when the judge reports a taken-in item that picks a higher rung or an escalation trigger the worker cites
|
||||
- tests: each test earns its keep as the technical principles' test bullet says, and the worker takes a test's expected values from its item, never from the code
|
||||
- the repo may name bender, bender-infra and ai-sandbox
|
||||
- todo.md: one table of items, scored by the formula it states, held to its bar and ranked by `bin/rank_todo.py`, which ranks each blocker above the items it blocks; each achieve goal weighs by its position, code health first and four times as heavy while the comprehension panel's overall is under 7.0 or unmeasured, then README.md's goals, and a maintain goal weighs 0.5 per point of the confidence an item's test, gate leg or probe adds to it; the table's order is the plan's only order
|
||||
- todo.md: only a session or subagent on the project's rung or above scores or reshapes the plan; one below it drafts new items and changes to filed ones for a subagent at or above that rung to apply and score, and removes finished ones
|
||||
- worker: a chunk's worker writes the simplest change that solves its item, test first wherever a test can check the change, and reads a technical principle only where the item, a finding or its own record names it; larv-review's reviewers hold the change to the principles and to the standards in `skills/larv-review/standards/`
|
||||
- workflow-bench/: the remote may show the bench cases' names and commit SHAs
|
||||
|
||||
# Decisions
|
||||
|
||||
## bin/: an outcome is an entry of a `.outcomes.md` file in loop-claude's archive, a record is a document tools or people keep entries in, and a place is what a comprehension seat names
|
||||
@@ -103,7 +141,7 @@ The trials: four stability rounds and five principles rounds archived on 2026-10
|
||||
- A cap on tool results. Claude Code caps a Bash result at about 30k characters already. A PostToolUse hook capping it at 12k, which `updatedToolOutput` allows, left the stability reviewers 3 of 6 findings, two lost in one round. Read results, 59.9M characters in subagents' threads with 58% of their characters in results over 12k, are out of such a hook's reach. Not worth an item.
|
||||
- A scout: Haiku 5.5 reading raw content, whole files or long output, and returning facts as path:line and the ranges worth reading, so the agent's own context holds the summary and the chosen lines. In session, as an agent under `agents/`, its first request writes 37k tokens, $0.005, and a read of a 38KB file costs $0.008 in 8 seconds. As a slim headless `claude -p` with its own system prompt, no setting sources and no dynamic sections, which keeps the subscription login, it starts at 6k tokens and $0.0003 in 3 to 5 seconds, its prefix cached across calls, and the same read costs $0.004 in 7 seconds; a direct API call and `claude --bare` need an API key, so they are out. Stability reviewers with the agent scout found 5 of 6 findings and read 29% fewer characters at 6% less cost and 14% more time; with the CLI scout 4 of 6, 38% fewer, 17% less and 39% more; the auditors with the agent scout 3 of 6, the 🔴 among the lost, at the same cost and twice the time. Workers offered the scout never called it.
|
||||
- What a reviewer reads: the auditors read the project whole by design. Of their 🔴 and 🟡 findings since the reset, 47% named a file the chunk edited and 51% another file, so reading only the change would drop half of them (`review: the principles audit runs only in the release review, and reads the project whole with one auditor checking the goals and every principles file that applies`).
|
||||
- The base context: every thread starts with `~/.claude/CLAUDE.md` (19k characters), `~/.claude/AGENTS.md` (11k, this repo's decisions, which Claude Code loads as user instructions into every project's sessions), the project's `AGENTS.md`, and, for the worker and general-purpose subagents, the skill listing (18k) and the agent listing (12k). Subagents' first messages wrote $97 of it. Trimming the listings would save about $20, 2%, and is not worth an item: `disableBundledSkills` would also drop `/security-review`, the security pass of record.
|
||||
- The base context: every thread starts with `~/.claude/CLAUDE.md` (19k characters), `~/.claude/AGENTS.md` (11k, this repo's decisions, which Claude Code loaded as user instructions into every project's sessions until 2026-11-11, when they moved into this log), the project's `AGENTS.md`, and, for the worker and general-purpose subagents, the skill listing (18k) and the agent listing (12k). Subagents' first messages wrote $97 of it. Trimming the listings would save about $20, 2%, and is not worth an item: `disableBundledSkills` would also drop `/security-review`, the security pass of record.
|
||||
|
||||
Quality. Under the 200k window, every figure's mean per chunk fell. Measured on 2026-11-04, the first 20 chunks whose worker started under it, from 2026-10-28, took a mean 4.0 review rounds past each pass's first against 5.8 for the 20 before them, from 2026-10-23 to 2026-10-26; 0.20 unfinished verdicts against 0.30; 1.15 🔴 against 1.90; 11.9 🟡 against 19.4; 0.11 misread findings against 0.25; $22 against $34; and 9.6 hours against 42. Only the median dollars went up, $15.17 against $11.72: the 20 before held four chunks of $94 to $167, and the 20 after none above $76. This decision weighs all spend, so the mean is the figure that counts. The two groups also differ in projects and routing, so how much of the fall the window caused is unknown. Before the window, 19 chunks compacted between 2026-10-10 and 2026-10-22, at the compaction points Claude Code set then, 214k to 972k tokens. Per 100 worker messages they took a median 3.6 review rounds past each pass's first against 4.0 for the 68 uncompacted chunks of 100 messages or more, and 13.9 🔴 and 🟡 findings against 16.6. 4 of 19 had an unfinished verdict against 3 of 68, each 8 to 10 hours after the compaction and followed by a finished verdict within minutes; in those four verdicts the judge quoted the worker's own passages and the human's typed answers, never a summary. One cause was possible and is closed here: Claude Code writes the summary as a user entry, which `bin/claude_code/entries.py` read as the human's words, so the judge would see a `[human]` line of thousands of words and `/talk` would count it as typed; it now reads as Claude Code's. Two summaries read whole kept the chunk's intent, files, errors and next step in 12k to 20k characters, and the worker resumed without re-reading.
|
||||
|
||||
@@ -502,7 +540,7 @@ Three places carry the rule. `rules/todo-items.md` states it and loads with `tod
|
||||
|
||||
2026-10-13, lilleman through todo item 104, implemented by claude. Serves goals 1.4 and 1.5. Like red, green, refactor: the worker makes the item work, and the review passes raise it to the bar. A loop-claude worker loaded `CLAUDE.md` and every file under `rules/`, 4,247 words, and `CLAUDE.md` told it to read `technical-principles.md` too, 2,426 words more. The reviewers read the principles anyway, and a finding against one names it.
|
||||
|
||||
The worker keeps what it needs to write its own work. Each project's decision titles stay in its `AGENTS.md`, since a worker that misses a decision builds the wrong behaviour. 2026-11-11, lilleman: a project principle in `AGENTS.md` now stands in for the titles of the decisions it covers. A core of "Prose" stays in `CLAUDE.md`, since no reviewer reads the worker's chat. lilleman chose both on 2026-10-13. The rules for writing Goals and Audience, `todo.md` items and decisions stay in `rules/`, since writing those is the worker's job. `bin/rule-hook` stays: it blocks what a program can check, at no context cost. "Quality", the rules for comments and READMEs, and the examples behind "Prose" moved to `skills/larv-review/standards/`, which no path loads. loop-claude's judge and the prose reviewer read them, and the stability reviewer reads "Quality". They sit beside larv-review, whose passes apply them; `principles/` stays where it is, since the principles auditor reads it per file.
|
||||
The worker keeps what it needs to write its own work. Each project's decision titles stay in its `AGENTS.md`, since a worker that misses a decision builds the wrong behaviour. This repo's head its decision log instead, since `~/.claude` is its checkout and an `AGENTS.md` there would load into every other project's sessions. 2026-11-11, lilleman: a project principle in `AGENTS.md` now stands in for the titles of the decisions it covers. A core of "Prose" stays in `CLAUDE.md`, since no reviewer reads the worker's chat. lilleman chose both on 2026-10-13. The rules for writing Goals and Audience, `todo.md` items and decisions stay in `rules/`, since writing those is the worker's job. `bin/rule-hook` stays: it blocks what a program can check, at no context cost. "Quality", the rules for comments and READMEs, and the examples behind "Prose" moved to `skills/larv-review/standards/`, which no path loads. loop-claude's judge and the prose reviewer read them, and the stability reviewer reads "Quality". They sit beside larv-review, whose passes apply them; `principles/` stays where it is, since the principles auditor reads it per file.
|
||||
|
||||
A finding against a principle names it, so the worker reads only that one when it fixes or declines the finding. The worker still writes a failing test first wherever a test can check the change, since no reviewer can make a test come first. On 2026-10-13 lilleman widened it from code changes to anything there is to test. A chunk that changes no code, config or test, such as one that only plans, meets no principles review; the chunk that implements its items does. The prose reviewer checks that a doc sorts a list whose order carries no meaning.
|
||||
|
||||
|
||||
@@ -1570,3 +1570,16 @@ Read most (opens and searches):
|
||||
- `bin/rule_hook/call.py` 2
|
||||
- `docs/decisions.md` 2
|
||||
- `AGENTS.md` 1
|
||||
|
||||
## Reading cost, chunk 667832515e57, finished 2026-11-11T15:26:47Z
|
||||
|
||||
59123 new input tokens before the first commit.
|
||||
|
||||
Read most (opens and searches):
|
||||
|
||||
- `skills/larv-review/SKILL.md` 5
|
||||
- `todo.md` 4
|
||||
- `docs/decisions.md` 2
|
||||
- `AGENTS.md` 1
|
||||
- `rules/decisions.md` 1
|
||||
- `skills/larv-review/standards/comments.md` 1
|
||||
|
||||
+2
-2
@@ -6,8 +6,8 @@ paths:
|
||||
|
||||
# Decisions: one home, each linked to a goal or a technical principle
|
||||
|
||||
**The decision log has one home: `docs/decisions.md`**. A title states the whole decision in one line: what holds at the commit it ships in, in words a reader finds in the code or the plan. `AGENTS.md` lists the project principles and the title of each decision no project principle covers, so a session works by the decisions without loading their background. The entry holds the background: its date, who made it, the reasoning, and the premise it rests on ("valid while X") so it can expire honestly when that premise dies.
|
||||
**The decision log has one home: `docs/decisions.md`**. A title states the whole decision in one line: what holds at the commit it ships in, in words a reader finds in the code or the plan. `AGENTS.md`, or the head of `docs/decisions.md` in a project that keeps no `AGENTS.md`, lists the project principles and the title of each decision no project principle covers, so a session works by the decisions without loading their background. The entry holds the background: its date, who made it, the reasoning, and the premise it rests on ("valid while X") so it can expire honestly when that premise dies.
|
||||
|
||||
**Every decision links to a goal or a technical principle.** An entry names the goal it serves or the technical principle under `~/.claude/principles/` it applies; one that can do neither is a missing goal, and an entry already in the repo with neither behind it is a finding. Propose the goal, never a reason of your own — `~/.claude/CLAUDE.md` → "Working loop", "Ask, don't guess" says how. An entry working against a goal or a technical principle stands only while it names the `todo.md` item that ends it.
|
||||
|
||||
**Check each new decision against the project's principles.** A project principle, listed in the project's `AGENTS.md` under `## Project principles`, states one rule that several decisions apply. Each time a decision is recorded, ask three things. Does a project principle already cover it? Then it adds no title to `AGENTS.md`, and needs no ask. Does it break one? Then either the principle or the decision is wrong. Does it apply the same rule as decisions already listed? Then that rule is a new project principle, which covers those decisions too. A break, a new project principle or a change to one is the human's: ask, with your recommendation, and leave the project principles as they are until the human answers. Once the human approves a new one, the titles it covers leave `AGENTS.md`.
|
||||
**Check each new decision against the project's principles.** A project principle, listed under `Project principles` in the project's `AGENTS.md`, or else at the head of `docs/decisions.md`, states one rule that several decisions apply. Each time a decision is recorded, ask three things. Does a project principle already cover it? Then it adds no title to the list of decisions no project principle covers, and needs no ask. Does it break one? Then either the principle or the decision is wrong. Does it apply the same rule as decisions already listed? Then that rule is a new project principle, which covers those decisions too. A break, a new project principle or a change to one is the human's: ask, with your recommendation, and leave the project principles as they are until the human answers. Once the human approves a new one, the titles it covers leave that list.
|
||||
|
||||
@@ -96,7 +96,7 @@ the end. Tell everyone not to manufacture confusion.
|
||||
A scoring run needs four seats — Junior A, Mid A, the maintainability senior and the inherited
|
||||
architect — plus the calibration seat ("The score") when more than one project is in play. Build
|
||||
the four seats' prompts from `seat-prompts.md`, filled in from the project's `AGENTS.md` → "Scoring
|
||||
run". Change neither between runs, or the scores are not comparable. A project without that
|
||||
run", or the values `seat-prompts.md` names for a project without one. Change neither between runs, or the scores are not comparable. A project without that
|
||||
section gets it at its first scoring run or paired ruling.
|
||||
|
||||
## The paired ruling
|
||||
|
||||
@@ -9,7 +9,7 @@ A scoring-run seat's prompt is the opening, the seat's background, the shared br
|
||||
- `{files}`: every tracked file in `git -C {checkout} ls-files`, except test files and those `{forbidden}` names. Give one recursive glob per top-level source directory, say which test files it leaves out, and list each file no glob matches. Example: `bin/**/*.py` except `test_*.py`, plus launchers such as `bin/loop-claude`.
|
||||
- `{preloaded}`: the files the harness pre-loads into a seat, found per `SKILL.md` → "What makes the result trustworthy".
|
||||
- `{anchors}` and `{dimensions}`: the six anchor bullets and the four dimension bullets in `SKILL.md` → "The score", verbatim, without bold and each on one line.
|
||||
- `{language}`, `{kind}`, `{domain}`, `{domain docs}` and `{3am question}`: the project's `AGENTS.md` → "Scoring run".
|
||||
- `{language}`, `{kind}`, `{domain}`, `{domain docs}` and `{3am question}`: the project's `AGENTS.md` → "Scoring run", or for claude-config, which keeps no `AGENTS.md`, "claude-config's values" below.
|
||||
|
||||
## Opening
|
||||
|
||||
@@ -93,3 +93,11 @@ Report, in this shape:
|
||||
2. The places that decided them, most decisive first. Each opens with the names from your rulings line that it moves, joined by ", " and followed by ": ", such as `Locality, Shape: `. Then `path:line` and the unit's name, each in backticks, in the version the place is in, and one or two sentences on what reads easier or harder there than in the other version. A dimension's ruling that no place opens with counts as same, and the overall ruling does unless you name a place.
|
||||
3. Where a place you name backs a worse ruling and you want a more capable reader to check that ruling, the line `Rerun one rung up`.
|
||||
```
|
||||
|
||||
## claude-config's values
|
||||
|
||||
- `{language}`: Python
|
||||
- `{kind}`: a Claude Code configuration with an agent loop and review skills
|
||||
- `{domain}`: driving headless Claude Code sessions, agent review workflows
|
||||
- `{domain docs}`: the Claude Code documentation
|
||||
- `{3am question}`: a loop-claude run exits 1 overnight after the judge returned a verdict the loop rejected, or a larv-review run looped a reviewer a third time
|
||||
|
||||
@@ -6,13 +6,12 @@
|
||||
|
||||
`Bar = 0.1`
|
||||
|
||||
`Next ID = 322`
|
||||
`Next ID = 323`
|
||||
|
||||
## Items
|
||||
|
||||
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|
||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||
| 314 | 0.8.0 | | | **Fold this repo's `AGENTS.md` into the files where each part fits, so `~/.claude` holds none, and load `CLAUDE.md` once in this repo's clone.** | 3 | 2 | 3 | 6 | 4 | 1.4 by 6, code health by 3 | 6.5 |
|
||||
| 297 | 0.8.0 | | | **Have loop-claude compute the judge's taken-in items, release-ready and escalation fields from `chunk-preflight`, git and the worker's structured lines, and leave the judge only the verdict kind.** | 3 | 2 | 3 | 6 | 4 | 1.4 by 2, code health by 2 | 3.7 |
|
||||
| 293 | 0.8.0 | | | **Run mutation tests on a chunk's changed lines in the worker's pre-review gate, through one command that picks the tool by language, and hand stability-reviewer the surviving mutants.** | 3 | 2 | 3 | 6 | 5 | 1.1 by 5, 1.4 by 4, 1.5 by 2 | 2.8 |
|
||||
| 284 | 0.8.0 | | owner | **Script each step that 0.7.0'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 | 2.6 |
|
||||
@@ -62,6 +61,7 @@
|
||||
| 201 | 0.9.0 | | 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 | 1.3 |
|
||||
| 267 | 0.9.0 | | | **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 | 1.3 |
|
||||
| 4 | 0.9.0 | | | **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 | 1.3 |
|
||||
| 322 | 0.9.0 | | | **Have loop-claude's judge read a project's `.claude/rules/*.md` as records, and count a write there as a recorded answer.** | 2 | 2 | 3 | 5 | 3 | 1.2 by 3 | 1.2 |
|
||||
| 187 | 0.9.0 | | | **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 | 1.2 |
|
||||
| 266 | 0.9.0 | | | **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 | 1.2 |
|
||||
| 181 | 0.9.0 | | 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 | 1.0 |
|
||||
@@ -75,12 +75,6 @@
|
||||
|
||||
## Details
|
||||
|
||||
### 314. Fold this repo's `AGENTS.md` into the files where each part fits, so `~/.claude` holds none, and load `CLAUDE.md` once in this repo's clone.
|
||||
|
||||
`~/.claude` is a checkout of this repo, so its `AGENTS.md`, 14.4 KB of this repo's decision titles and working rules, loads into every session and subagent of every other project, while this repo's own sessions don't load it, since the repo root has a `CLAUDE.md`. Each 1,000 tokens every thread starts with cost $68.60 of the $9,154 measured from 2026-09-30 to 2026-11-11, so the file costs about 2.1% of spend, and puts irrelevant rules in front of every other project. In `~/code/claude-config`, `CLAUDE.md` loads twice, the release's copy and the clone's: about 0.9%.
|
||||
|
||||
lilleman, 2026-11-11: keep the name `AGENTS.md` for projects, since the setup must stay portable to other harnesses and models, but drop this repo's from `~/.claude`. Move each part where it fits: decision titles and the project principles to `docs/decisions.md` or wherever this repo's principles fit; each working rule to the `rules/` file its paths scope, or the skill or tool it governs; the scoring-run values to `skills/comprehension-panel`. Revise `CLAUDE.md` → "Working loop", which says `AGENTS.md` lists every decision's title, for this repo. For the double `CLAUDE.md`, try `claudeMdExcludes` for the release copy in this repo's `.claude/settings.json`; a chunk then runs under the rules it is changing. Check: a first request in another project is about 3,600 tokens smaller and holds no `Contents of /home/lilleman/.claude/AGENTS.md`.
|
||||
|
||||
### 297. Have loop-claude compute the judge's taken-in items, release-ready and escalation fields from `chunk-preflight`, git and the worker's structured lines, and leave the judge only the verdict kind.
|
||||
|
||||
`bin/loop_claude/cycle/judge.py` already checks quotes in code (`quotes_checked`, `grounded`, `re_ask_checked`). The `Reply` fields `items_taken_in`, `release_ready` and `escalation` state facts the plan and git already hold, so code can derive them with certainty, and the judge's prompt shrinks to what needs judgement. Before switching, recompute each field for the 668 archived verdicts offline and count where code and judge disagree; read each disagreement and keep the judge for a field where code is wrong. Seats found `quotes_checked` hard to read (PR #397's scoring run: the misquote rule is split across `judge.py` and `escalation_mark.py`); make it easier to read where the change touches it.
|
||||
@@ -396,6 +390,10 @@ Weigh the widely used tmux-resurrect and tmux-continuum plugins against a script
|
||||
|
||||
Today the folder is the SHA-256 of the transcript's first timestamped line, which tells the human nothing; that line carries the start time. Drop the fallback to the first line, which every chunk of a project shares, and give the tests' fake transcripts ISO timestamps. `bin/reading-cost` takes a chunk's id from the folder's first 12 characters and skips a chunk whose id `docs/reading-cost.md` holds, so give it a way to match a figure written under the old name.
|
||||
|
||||
### 322. Have loop-claude's judge read a project's `.claude/rules/*.md` as records, and count a write there as a recorded answer.
|
||||
|
||||
`CLAUDE.md` → "Working loop", "Ask, don't guess" records a working rule in the `.claude/rules/` file its paths scope where a project keeps no `AGENTS.md`, as this repo now does. The judge reads only `AGENTS.md` and `docs/decisions.md` of the project (`bin/loop_claude/project/records.py` → `RECORD_FILES`), and `ANSWER_DESTINATIONS` in `bin/loop_claude/cycle/prompts.py` lists the same. So an answer recorded as such a rule leaves the judge holding the chunk open, or asking again. Add the project's `.claude/rules/*.md` to both, and to the records `bin/loop_claude/loop/usage.py` names.
|
||||
|
||||
### 187. 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.
|
||||
|
||||
Before PR #310, reports reached the worker as the Agent call's result, a median 19k tokens per chunk (2026-10-08, 68 archived transcripts). Now a reviewer returns its verdict and one line per finding, and the worker reads a 🔴 or 🟡 finding's entry from the report file. `reading-cost` counts only tracked files (`bin/reading_cost/measure.py`), and `routing-figures` counts only the Agent call's result (`bin/routing_figures/chunk.py`), so neither sees the report reads. Found by the architecture review of PR #310.
|
||||
|
||||
Reference in New Issue
Block a user