Answer product-owner round 1: 0 🔴, 2 🟡 (0 misread); the changelog says what the wider run-heavy rule refuses and that loop-claude's prompts say plan, a bad value in a Jira issue's property names the property, and a Jira edit's refusal names the issue

This commit is contained in:
2026-11-16 16:48:05 +01:00
parent fde2718a97
commit 79e0f755e2
3 changed files with 10 additions and 7 deletions
+2 -1
View File
@@ -14,7 +14,7 @@
- A project's config may keep each of its five records on a Confluence Cloud page: set, for example, `decisions = "confluence:https://<site>/wiki/spaces/<space>/pages/<page ID>"`, with the credentials in the config's `env-file`. `decisions` and `comprehension-history` may name a page only where `plan` names a Jira epic. The loop reads and writes the page as markdown, so a save replaces a mention or a macro on it with plain text. It never overwrites a teammate's edit: where someone saved the page since the loop read it, `project-record save` refuses and the loop asks you.
- `todo-item add` files an item into a plan kept in a Jira epic: a Task under the epic, under the project's Fix Version for the release, labelled `security` for a security finding and linked to each item that blocks it. Editing an issue still happens in Jira.
- An item of the next release may predict the files and parts it will touch, under a `Touches:` line in its detail. `chunk-preflight` then names the items that may start chunks at once, and the new `touch-predictions record` keeps each prediction beside what the merged chunk touched, in the record a project's config places with `touch-predictions`.
- CLAUDE.md and the todo-items rule define the plan as a todo.md or a Jira epic, and say plan where todo.md was false for a Jira plan.
- CLAUDE.md, the todo-items rule, and loop-claude's worker and judge prompts and `--help` define the plan as a todo.md or a Jira epic, and say plan where todo.md was false for a Jira plan.
- Reviewers without a shell read the plan from a listing that larv-review writes into the review folder, whichever store holds it.
- A project's config may set `tooling-on-host = true`, so the loop runs a legacy project's language runtime, package manager, tests and task runner directly on the host.
- A project's config may set `readability-floor` to a number from 1 to 10: the comprehension score under which code health is very important. It is 7.0 where left out.
@@ -30,6 +30,7 @@
- In a client project, the loop reads the team's own `CLAUDE.md` and `AGENTS.md` and proposes each change that aligns them with this setup in a pull request of its own. Where the team declines or doesn't answer, the loop follows the team's rule unless it breaks a project goal, and records the conflict as a decision in the `decisions` record.
- The new `project-record open <record>` prints the file in which an agent reads and edits one of a project's five records (`decisions`, `score-anchors`, `comprehension-history`, `reading-cost` and `changelog`), and `project-record save <record>` stores the edit. Every tool now reads and writes a record the same one way, so that a later release can keep a record outside files. No config needs a change.
- `loop-inbox` is gone. loop-claude now asks its questions only on its own terminal. A line typed there answers a question, and `/talk` opens the worker's session. The DM still tells you a loop waits. To upgrade, quit any `loop-inbox` still open and remove your `~/.local/bin/loop-inbox` link.
- rule-hook's `run-heavy` rule also refuses a heavy command run through `uv run`, `poetry run`, `sudo` or `doas` outside `run-heavy`, such as `uv run mutmut run` or `sudo docker build`. Run it as `~/.claude/bin/run-heavy uv run mutmut run`.
- rule-hook refuses a Read or a Grep of `~/.claude/.env` or of the `env-file` any project's config names, and a Bash command that names either or searches a folder holding either with `ag`, `grep -r` or `rg`, unless the tool skips the file as hidden or ignored, so that a worker doesn't put a credential in its transcript in passing. A command that hides the path, such as behind a glob or a variable, still goes through.
- A project's config names the service for loop-claude's DMs: `notifier = "mattermost"` or `"slack"`, with the bot's token and the recipient in the `env-file`. To upgrade, move the Mattermost keys from `~/.claude/.env` into a file outside the checkout and the config's folder, such as `~/.claude-projects/<key>.env`, name it as `env-file` and add `notifier = "mattermost"`. A project with no `notifier` gets no DM, and `~/.claude/.env` is no longer read. A failure names each missing key and holds no token.
- `mattermost-dm` is now `notify`, which sends through the project's `notifier`; `notify --help` names the keys.
+4 -2
View File
@@ -347,7 +347,7 @@ def revision_of(issue: Issue, named: dict[str, str], detail: str | None, comment
if unfit := unfit_text(named.get("Item", ""), detail or ""):
return unfit
release = named.get("Release")
if isinstance(checked := item_fields({name: named[name] for name in ("Release", "Exempt") if name in named}, "the item"), Failure):
if isinstance(checked := item_fields({name: named[name] for name in ("Release", "Exempt") if name in named}, f"item {issue.key}"), Failure):
return checked
if any(name in named for name in SCORED):
texts = {name: str(value) for name, value in held.items()} | {name: named[name] for name in SCORED if name in named}
@@ -496,4 +496,6 @@ def earliest_release(names: tuple[str, ...]) -> Release | None:
def scores(key: str, held: dict[str, typing.Any]) -> ItemFields | Failure:
"""The scores, Moves and Exempt that an issue's PROPERTY value holds, each in the format the items table of a todo.md takes."""
named = {name: str(value) for name, value in held.items() if name in (*SHAPE.score_columns, MOVES, "Exempt")}
return item_fields(named, f"item {key}")
checked = item_fields(named, f"item {key}")
# Jira's screens don't show PROPERTY, so the message says where the value is.
return Failure(f"{checked.reason}; {key} holds it in its issue property {PROPERTY}") if isinstance(checked, Failure) else checked
+4 -4
View File
@@ -144,7 +144,7 @@ class JiraPlan(unittest.TestCase):
self.assertIn("ABC-34", failure.reason) # type: ignore[union-attr]
def test_an_exempt_out_of_format_fails_naming_the_reasons_it_may_hold(self):
self.assertEqual(self.read(issue("ABC-34", scores={"Exempt": "because"})), Failure("item ABC-34's Exempt 'because' is not empty or one of decision, defect, owner, principle, question, security"))
self.assertEqual(self.read(issue("ABC-34", scores={"Exempt": "because"})), Failure("item ABC-34's Exempt 'because' is not empty or one of decision, defect, owner, principle, question, security; ABC-34 holds it in its issue property plan-item"))
def test_reads_every_page(self):
self.pages = [{"issues": [issue("ABC-1")], "nextPageToken": "t1"}, {"issues": [issue("ABC-2")]}]
@@ -460,7 +460,7 @@ class Filing(unittest.TestCase):
for open_, reason in (
(filed("ABC-34", moves="3 by 1", s=2), "ABC-34 cites goal 3, which the goals file's ## Goals does not number"),
(issue("ABC-34", scores=unscored), "ABC-34 holds no S"),
(issue("ABC-34", scores=PROPERTY | {"L": 11}), "item ABC-34's L '11' is not a whole number from 1 to 4"),
(issue("ABC-34", scores=PROPERTY | {"L": 11}), "item ABC-34's L '11' is not a whole number from 1 to 4; ABC-34 holds it in its issue property plan-item"),
):
with self.subTest(reason=reason):
self.calls.clear()
@@ -597,8 +597,8 @@ class Editing(unittest.TestCase):
for fields, detail, reason in (
({"L": "9"}, None, "item ABC-34's L '9' is not a whole number from 1 to 4"),
({"Moves": "much"}, None, "item ABC-34's Moves 'much' is not"),
({"Exempt": "tired"}, None, f"the item's Exempt 'tired' is not empty or one of {', '.join(EXEMPTIONS[1:])}"),
({"Release": "soon"}, None, "the item's Release 'soon' is not a semver version, such as 1.2.0"),
({"Exempt": "tired"}, None, f"item ABC-34's Exempt 'tired' is not empty or one of {', '.join(EXEMPTIONS[1:])}"),
({"Release": "soon"}, None, "item ABC-34's Release 'soon' is not a semver version, such as 1.2.0"),
({"Tagline": " "}, None, "the item has no tagline"),
({"Tagline": "Count\nruns."}, None, "the tagline holds a line break; keep it on one line"),
({}, "## Why", "the detail holds a ## or ### heading"),