refactor: retire repository-local release machinery

This commit is contained in:
codex-bot-andresmgsl 2026-07-23 13:45:08 +00:00
parent 1c3d873bf2
commit b0d4aff964
12 changed files with 99 additions and 2697 deletions

2
.github/labels.conf vendored
View file

@ -1,4 +1,4 @@
panel=claude-bot-andresmgsl codex-bot-andresmgsl grok-bot-andresmgsl panel=claude-bot-andresmgsl codex-bot-andresmgsl grok-bot-andresmgsl kimi-bot-andresmgsl
triage-actors=dan-claude-bot triage-actors=dan-claude-bot
scope:cli|C5DEF5|bin/box — the command surface scope:cli|C5DEF5|bin/box — the command surface
scope:installer|C5DEF5|install.sh, versioned installs, upgrade/uninstall scope:installer|C5DEF5|install.sh, versioned installs, upgrade/uninstall

View file

@ -1,145 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
# changelog-armed.sh [<changelog>] [<version-file>] — assert that
# CHANGELOG.md is ARMED: that there is a heading for the next PR's entry to
# land under, and that it is the right one for the state this tree is in.
#
# The failure it exists to catch (#108, heavy-duty/rig#66) leaves no trace:
# the ceremony PR stamps '## Unreleased' into '## X.Y.Z — DATE' by hand, and
# nothing puts the heading back. A PR authored BEFORE the release wrote its
# entry under '## Unreleased'; that heading is gone by the time it merges, so
# git lands the entry under whatever heading now occupies that position — the
# just-shipped section — CLEANLY, with no conflict. The one signal an author
# would trust ("git told me to look") is absent exactly when the result is
# wrong, and the drift is only ever discovered by reading the file.
#
# The rule, keyed on VERSION, because the two states are genuinely different:
#
# VERSION ends in -dev -> the top section MUST be '## Unreleased'
# VERSION is bare -> the top section may be '## Unreleased' (armed,
# the ceremony's own re-arm) or the stamped
# section for exactly that VERSION — AND the
# section for that VERSION must exist and carry
# prose, because it is the one about to ship
#
# Keying on VERSION is the whole design, and the reason this is not simply
# "require '## Unreleased'". That unconditional form is what rig#44 and
# heavy-duty/cast#108 had to REVERT: it is false by construction on the
# ceremony PR's own tree, which makes the release unshippable through a green
# CI. Anyone tempted to simplify this back should read those two first.
#
# The consequence worth stating plainly: a ceremony PR that stamps and forgets
# to re-arm still passes here — its VERSION is bare, and a bare tree is
# allowed to be stamped. It goes red the moment the '-dev' bump lands on main,
# which release.yml does automatically in the same job as the publish. So the
# guard does not block the release; it refuses to let main SIT disarmed, which
# is the window a late PR can fall into.
#
# A file of its own (not inlined in ci.yml) so test/release.sh can drive it
# against constructed trees for both states — the same discipline as
# release-notes.sh.
changelog="${1:-CHANGELOG.md}"
version_file="${2:-VERSION}"
# release-notes.sh lives beside this script; the bare-VERSION branch runs it
# rather than re-implementing the extraction, so the guard and the publisher
# cannot disagree about what a section is or when one counts as empty.
here="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
[ -f "$changelog" ] || { echo "changelog-armed: no such file: $changelog" >&2; exit 1; }
[ -f "$version_file" ] || { echo "changelog-armed: no such file: $version_file" >&2; exit 1; }
ver="$(tr -d '[:space:]' < "$version_file")"
[ -n "$ver" ] || { echo "changelog-armed: $version_file is empty" >&2; exit 1; }
# The TOP section: the first '## ' heading in the file. Everything above it is
# the changelog's own preamble and belongs to no section.
top="$(grep -m1 '^## ' "$changelog" || true)"
[ -n "$top" ] || {
echo "changelog-armed: $changelog has no '## ' section at all — nothing for a PR entry to land under" >&2
exit 1
}
# '## 0.7.0 — 2026-07-19' -> '0.7.0'. Split on whitespace, same shape
# release-notes.sh matches on, so the two cannot disagree about what a
# section header is.
top_ver="$(printf '%s\n' "$top" | awk '{ print $2 }')"
case "$ver" in
*-dev)
if [ "$top_ver" != "Unreleased" ]; then
cat >&2 <<EOF
changelog-armed: VERSION is '$ver' (a development tree) but the top section of
$changelog is:
$top
A -dev tree MUST carry '## Unreleased' at the top. Without it, a PR that
wrote its entry under '## Unreleased' before the release merges CLEANLY into
the section above — the one that already shipped — and the changelog quietly
misattributes it (#108, heavy-duty/rig#66).
The fix is to re-arm: add an empty '## Unreleased' immediately above
'$top'. The release ceremony is supposed to do this in the same edit that
stamps the version — see CONTRIBUTING.md, "Releases".
EOF
exit 1
fi
;;
*)
# A bare VERSION is the ceremony tree and the merge commit that publishes
# it. Both arrangements are legal there: re-armed ('## Unreleased' back on
# top, above the section just stamped) or not yet re-armed (the stamped
# section still on top). What is NOT legal is a stamped top section naming
# some OTHER version — that is a ceremony that stamped the wrong number,
# and release.yml would publish a body that is not this release's.
if [ "$top_ver" != "Unreleased" ] && [ "$top_ver" != "$ver" ]; then
cat >&2 <<EOF
changelog-armed: VERSION is '$ver' but the top section of $changelog is:
$top
A bare VERSION means this tree is a release. Its top section must be either
'## Unreleased' (re-armed after stamping) or the stamped section for '$ver'
itself. A stamped section naming a different version means the ceremony
stamped the wrong number, and the published release body would come from
the wrong section.
EOF
exit 1
fi
# The top heading is deliberately left UNCONSTRAINED above — both ceremony
# shapes must stay legal, which is the #44 / cast#108 lesson and is not
# negotiable. That asymmetry leaves a gap of its own, the HALF-ceremony
# tree: VERSION bumped to the release, a populated '## Unreleased' still on
# top, and no stamped section for the version anywhere. The test above is
# false on its first clause, short-circuits, and passes. Nothing else
# refuses until release.yml extracts the notes — which happens AFTER the
# merge, on main, and publishes a release with an empty body, the worst
# place for this to land. So make the same assert one step earlier by
# running the very script release.yml runs (heavy-duty/rig#67).
if ! bash "$here/release-notes.sh" "$ver" "$changelog" >/dev/null 2>&1; then
cat >&2 <<EOF
changelog-armed: VERSION is '$ver' but $changelog has no non-empty section for
'$ver'. The top section is:
$top
This is a HALF-DONE ceremony: the version was bumped but its section was
never stamped — the stamp is MISSING, not misnumbered. A bare VERSION means
this tree is a release, and the section it is about to publish has to exist
and have prose in it. Left alone, this passes CI, merges, and only then does
release.yml refuse to extract the notes — on main, after the fact, with the
release already half-shipped.
The fix is the ceremony's first edit (CONTRIBUTING.md, "Releases"): stamp
'## Unreleased' into '## $ver — DATE', then put an empty '## Unreleased'
back above it.
EOF
exit 1
fi
;;
esac
echo "changelog-armed: VERSION '$ver' agrees with the top section ($top_ver)"

View file

@ -1,225 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
# changelog-monotonic.sh [<base-ref>] [<changelog>] — assert that no SHIPPED
# release heading was DELETED by this branch: the set of '^## X.Y.Z' headings
# on HEAD must be a SUPERSET of the set at the merge base.
#
# The failure it exists to catch (#122, caught in review of #118) leaves no
# trace either. An author adding an entry under '## Unreleased' REPLACES the
# line below it instead of inserting above it:
#
# -## 0.8.0 — 2026-07-19
# +## Unreleased
# +
# +### Fixed
# +
# +- **An entry**
#
# git merges that cleanly — it is a one-line edit inside a file nobody has
# touched concurrently — and the shipped section's whole body is silently
# absorbed into '## Unreleased'. 0.8.0 no longer HAS a section; the notes
# anchor release-notes.sh extracts by is gone, and the next release cut from
# that state republishes 0.8.0's prose as if it were new.
#
# changelog-armed.sh is green on exactly that tree, correctly: it asks only
# whether the TOP section agrees with VERSION, and deleting '## 0.8.0' leaves
# '## Unreleased' on top. It is not wrong, it is narrow — it guards ONE
# heading, the one a PR is about to write under. This guards the REST of the
# file, the part no single tree can be asked about at all, because "a heading
# disappeared" is not a property of a tree — it is a property of a DIFF.
#
# The rule, and why it needs no tuning: release headings are APPEND-ONLY. The
# ceremony (#96) adds one and never removes one; nothing else in the documented
# flow (CONTRIBUTING.md, "Releases") touches them. So SUPERSET is exact — it
# has no legitimate violation to carve an exception for. The stamp is covered
# for free: rewriting '## Unreleased' -> '## X.Y.Z — DATE' ADDS X.Y.Z and
# removes no X.Y.Z heading, because 'Unreleased' is not one. '## Unreleased'
# is deliberately NOT in the set this guards — changelog-armed.sh owns that
# heading, keyed on VERSION, and the ceremony legitimately consumes it.
#
# A file of its own, NOT a clause inside changelog-armed.sh, for three
# reasons. Its input is different (a git history, not two files). Its
# degradation is different (no base ref is a SKIP, not a failure). And
# changelog-armed.sh is driven by test/release.sh against constructed
# two-file trees that are not git repos at all — folding a git-dependent
# assert into it would make every one of those cases either skip or lie.
# Same discipline as release-notes.sh: its own file so a test can drive it.
base_ref="${1:-${CHANGELOG_MONOTONIC_BASE:-origin/main}}"
changelog="${2:-CHANGELOG.md}"
# Fail-closed switch: CI sets it, so a SKIP that would be a sensible local
# degradation becomes a red run there instead. A guard that can silently
# stop guarding is the failure shape this whole family of checks exists to
# refuse, so the skip path is loud and CI refuses to take it at all.
strict="${CHANGELOG_MONOTONIC_STRICT:-0}"
skip() {
if [ "$strict" = "1" ]; then
echo "changelog-monotonic: $* — and CHANGELOG_MONOTONIC_STRICT=1, so this is a FAILURE, not a skip." >&2
echo " CI sets STRICT because a guard that quietly stops guarding is worse than no guard." >&2
echo " (Uniqueness on HEAD already passed; it is containment that cannot run.)" >&2
echo " Fix the checkout, not this script: the base ref must be fetched (fetch-depth: 0)." >&2
exit 1
fi
echo "changelog-monotonic: containment SKIPPED — $*"
echo " (Uniqueness on HEAD already ran and passed — only the deleted-heading"
echo " half needs the history. In CI this same condition is a hard failure.)"
exit 0
}
[ -f "$changelog" ] || { echo "changelog-monotonic: no such file: $changelog" >&2; exit 1; }
# The set of RELEASE headings: '## <token> ...' where <token> looks like a
# version. Field $2, the same split changelog-armed.sh and release-notes.sh
# use, so the three cannot disagree about what a section header is.
# 'Unreleased' fails the shape and is excluded by construction.
headings_raw() {
awk '
/^## / && $2 ~ /^[0-9]+\.[0-9]+\.[0-9]+/ { print $2 }
'
}
headings() { headings_raw | sort -u; }
# --- uniqueness on HEAD (the #118 class) -------------------------------------
# Containment catches a DELETED heading. It cannot catch a DUPLICATED one: the
# duplicate is head-side SURPLUS, and `comm -23` (base minus head) is blind to
# extras on the head side — with or without `sort -u`, base {0.8.0} minus head
# {0.8.0, 0.8.0} is empty. Multiset comparison does not close it either, for
# the same reason. The assert that does is uniqueness of version headings ON
# HEAD, kept alongside containment rather than replacing it.
#
# This is the shape #118's bad rebase actually produced: two
# `## 0.8.0 — 2026-07-19` headings with the incoming entry between them. Every
# other guard stayed green — markers absent, changelog-armed.sh happy (the top
# section was still right), tests and shellcheck clean — while
# release-notes.sh re-armed its grab on the second heading and folded post-cut
# prose into the shipped release body.
#
# Nothing legitimate repeats a version heading: the ceremony stamps a NEW
# version, and 'Unreleased' fails the version shape and never reaches here.
dupes="$(headings_raw < "$changelog" | sort | uniq -d)"
if [ -n "$dupes" ]; then
{
echo "changelog-monotonic: $changelog has DUPLICATE release heading(s):"
echo
printf '%s\n' "$dupes" | sed 's/^/ ## /'
echo
cat <<EOF
Each version heading must appear exactly once. A repeat splits one release
into two same-named sections, and release-notes.sh re-arms its extraction on
every matching '## ' line — so the published body for that version absorbs
whatever sits between the copies, and an entry stranded there is dropped from
the NEXT release's notes as well.
This is the #118 shape: an entry meant for '## Unreleased' was inserted after
a shipped heading, and the heading re-added below it. The fix is one heading,
with the entry above it under '## Unreleased':
## Unreleased
### Fixed
- **Your entry**
## $(printf '%s\n' "$dupes" | head -1) — DATE <- exactly once
Quick check on any changelog-touching rebase:
diff <(git show origin/main:$changelog | grep '^## ') <(grep '^## ' $changelog)
EOF
} >&2
exit 1
fi
# --- everything below needs the HISTORY ------------------------------------
# Uniqueness is settled. What follows is containment, which compares HEAD
# against the merge base and therefore genuinely depends on the base ref, the
# merge base, and the base blob. Each of those can be unavailable for reasons
# that are not the author's fault (a shallow clone, a fork checkout without
# the upstream remote, the commit that first adds the changelog), so each
# degrades rather than failing — which is exactly why the uniqueness half must
# NOT live down here (#143). It asks nothing of the history, and gating it
# behind these conditions let a duplicate exit 0 on a message about deletion.
git rev-parse --is-inside-work-tree >/dev/null 2>&1 \
|| skip "not inside a git work tree, so there is no history to compare against"
git rev-parse --verify --quiet "$base_ref^{commit}" >/dev/null \
|| skip "base ref '$base_ref' does not resolve here (a shallow clone, or a fork checkout without the upstream remote)"
merge_base="$(git merge-base "$base_ref" HEAD 2>/dev/null || true)"
[ -n "$merge_base" ] \
|| skip "no merge base between '$base_ref' and HEAD (unrelated histories, or a clone too shallow to reach one)"
# The changelog may not exist at the merge base at all (the commit that adds
# it). Nothing to have deleted, so nothing to assert.
base_file="$(git show "$merge_base:$changelog" 2>/dev/null || true)"
[ -n "$base_file" ] || {
echo "changelog-monotonic: $changelog does not exist at the merge base ($(git rev-parse --short "$merge_base")) — nothing could have been deleted (uniqueness on HEAD already passed)."
exit 0
}
base_headings="$(printf '%s\n' "$base_file" | headings)"
head_headings="$(headings < "$changelog")"
# comm -23: lines in the base set that are NOT in the head set — exactly the
# headings this branch removed.
missing="$(comm -23 <(printf '%s\n' "$base_headings") <(printf '%s\n' "$head_headings"))"
if [ -n "$missing" ]; then
{
echo "changelog-monotonic: this branch DELETES release heading(s) from $changelog:"
echo
printf '%s\n' "$missing" | sed 's/^/ ## /'
echo
cat <<EOF
Present at the merge base ($(git rev-parse --short "$merge_base")), absent on HEAD.
Release headings are APPEND-ONLY. The ceremony adds one (#96); nothing ever
legitimately removes one. So this is not a judgement call — it is a defect,
and almost always the same one (#122, caught in review of #118): an entry
written under '## Unreleased' REPLACED the heading below it instead of being
inserted ABOVE it. The shipped section's body is now sitting under
'## Unreleased', and the version it belonged to has no section at all.
Nothing else will say so. git merges that edit cleanly — no conflict, no
signal — and changelog-armed.sh stays green, because the TOP section is
still the right one for this VERSION. The damage surfaces at the NEXT
release, when release-notes.sh cannot find the section it extracts by
heading, or worse, republishes the absorbed prose as if it were new.
The fix is to put the heading back and INSERT above it, never over it:
## Unreleased
### Fixed
- **Your entry**
## $(printf '%s\n' "$missing" | head -1) — DATE <- untouched, still here
If you are genuinely renaming a released version, that is a rewrite of
history this guard is meant to stop; say so in the PR and change the guard
deliberately, in its own commit.
EOF
} >&2
exit 1
fi
count="$(printf '%s\n' "$base_headings" | grep -c . || true)"
head_count="$(printf '%s\n' "$head_headings" | grep -c . || true)"
# The success line has two honest forms, because this step now runs on two
# shapes of event. On a push to main the merge base IS HEAD: containment
# compared the file against itself and asserted nothing, and deletion is
# undetectable on that event by construction. Reporting "all N still present"
# there would be the same dishonesty the skip messages were fixed for — a log
# claiming a check that did no work. Uniqueness is the half that actually ran,
# so that is the half the line names.
if [ "$merge_base" = "$(git rev-parse HEAD)" ]; then
echo "changelog-monotonic: containment vacuous (the merge base IS HEAD, so nothing could have been deleted between them) — uniqueness on HEAD checked $head_count release heading(s)."
else
echo "changelog-monotonic: all $count release heading(s) at the merge base ($(git rev-parse --short "$merge_base")) are still present in $changelog"
fi

View file

@ -1,125 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
# drill-recorded.sh [<drills-dir>] [<version-file>] — assert that a RELEASE
# tree carries a drill record: that the full real-hardware drill this repo
# says a release rests on was actually run for this version, and written
# down as drills/<version>.md.
#
# CONTRIBUTING.md has said since #96 that "this PR is where the release
# ritual hangs: the full drill on real hardware, recorded". No release ever
# did it. #95, #114 and #148 all shipped as a VERSION bump plus a
# CHANGELOG.md stamp and nothing else. That is three releases through the
# same gap, because the gate was a sentence in a document and the only thing
# standing on it was a reviewer remembering to ask. A reviewer finally did —
# which is the point: the ONE time it was caught is the time somebody
# happened to look, and that is not a gate, it is luck with good manners.
#
# So the rule moves into CI, where it fires on every release PR whether or
# not anyone is paying attention. It is keyed on VERSION for the same reason
# changelog-armed.sh is — the two states are genuinely different:
#
# VERSION ends in -dev -> PASS. A development tree ships nothing, so
# there is nothing for it to have proven. Almost
# every PR in this repo is this case, and a guard
# that nagged all of them would be turned off.
# VERSION is bare -> the ceremony tree, the one about to ship.
# <drills-dir>/<version>.md MUST exist and carry
# at least one non-whitespace character.
#
# ONE FILE PER VERSION, and that is the whole design. Records used to be
# sections sharing drill/RUNS.md, and every hard edge this script used to
# have existed only because of that sharing: em-dash field matching, an
# optional ' — DATE' tail, whole-version comparison so '0.9.0-rc1' could not
# satisfy '0.9.0', avoiding '\x' escapes because CI runs mawk not gawk, and a
# non-blank body rule to tell an empty section from a filled one. Two
# separate defects were found in review because of that complexity — a
# `sed '/./,$!d'` whitespace bypass, and heading-grammar drift from the
# sibling repos. Splitting the file makes almost all of it UNREPRESENTABLE:
# '0.9.0.md' and '0.9.0-rc1.md' are simply different files, so whole-version
# matching is free rather than a trap, and there is no grammar left to drift.
#
# The directory is plain 'drills', NOT '.drills'. A dot-directory is
# invisible to a glob without dotglob, which is exactly what caused #116 and
# #118 in this repo; evidence a sweep cannot see is evidence that goes
# missing quietly.
#
# drills/ is RELEASE EVIDENCE, one file per shipped version. It is NOT
# drill/RUNS.md, which stays exactly as it is: the harness's own run log,
# traps table and lore, a different artifact with a different purpose. This
# guard reads drills/ and never looks at drill/RUNS.md.
#
# What this guard asserts is a RECORD, deliberately — not a passing drill.
# CI cannot run the drill: it wants real hardware, a real Incus, and the
# better part of an hour (see ci.yml, which says exactly this about the
# rehearsal job it runs instead). What CI can do is refuse to let a release
# claim a ritual it left no evidence of. That also leaves the maintainer
# waiver intact and honest: a release that must ship without a full drill
# records WHY in its own file, which is a deliberate, reviewable commit in
# the diff — rather than the silent skip that got us here.
#
# A file of its own (not inlined in ci.yml) so test/release.sh can drive it
# against constructed trees for both states — the same discipline as
# changelog-armed.sh and release-notes.sh.
drills="${1:-drills}"
version_file="${2:-VERSION}"
# A missing or empty version file is an ERROR, never a silent pass. A guard
# that cannot read the version cannot know whether this tree is its business,
# and "could not tell" must not resolve to "allowed".
[ -f "$version_file" ] || { echo "drill-recorded: no such file: $version_file" >&2; exit 1; }
ver="$(tr -d '[:space:]' < "$version_file")"
[ -n "$ver" ] || { echo "drill-recorded: $version_file is empty" >&2; exit 1; }
case "$ver" in
*-dev)
# Nothing to assert, and saying so is the point: the operator reading a
# green log should be able to tell "the guard passed" from "the guard
# decided this tree was not its business".
echo "drill-recorded: VERSION '$ver' is a development tree — nothing to assert; only ceremony trees ship"
exit 0
;;
esac
record="$drills/$ver.md"
# The one rule that survives the rewrite, and it survives because it was
# never really about heading parsing: a file of only spaces, tabs and
# newlines is NOT a record. The first cut of the old guard extracted with
# `sed '/./,$!d'`, where `.` matches a space — so a record whose body was one
# tab satisfied a guard that promised "at least one non-blank line". An
# evidence-free release for the price of an invisible character, on the one
# check whose entire job is to demand evidence. Existence alone is a weaker
# claim than `touch` can defeat, so existence alone is not the test.
if [ ! -f "$record" ] || ! grep -q '[^[:space:]]' "$record"; then
cat >&2 <<EOF
drill-recorded: VERSION is '$ver' — a release — and there is no drill record
for it. The file this looks for is:
$record
...with something written in it. Either the file is absent entirely, or it
is present and blank; both mean the same thing, which is that this release
is asserting a ritual it has left no evidence of.
The unblock is to RUN THE DRILL (drill/drill.sh, on real hardware) and
record it at that path — what it measured, what it found, what it cost.
See $drills/README.md for what a record should contain. CI cannot run the
drill for you; it can only refuse a release that never ran one.
(drill/RUNS.md is a different artifact — the harness's own run log and
traps. Appending there does not satisfy this guard, and is not meant to.)
If this release must ship without a full drill, that is a maintainer's call
to make and it is still recorded: create the same file and say plainly that
the drill was WAIVED and why. The guard requires a record, not a passing
result — so a skip is a visible, reviewable file in the diff rather than
the silent gap that let #95, #114 and #148 all ship unproven. See
CONTRIBUTING.md, "Releases".
EOF
exit 1
fi
echo "drill-recorded: VERSION '$ver' has a drill record at $record"

View file

@ -1,486 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
# labels-reconcile.sh — the automation LABELS.md promises: state labels are
# written by machinery, never by hand. Every run derives each open PR's
# state:* from GitHub's own facts (draft flag, requested reviewers, submitted
# reviews) and converges the labels to it, so a killed run or a hand-moved
# label heals on the next pass. Stale is judged from real activity — commits,
# comments, reviews — never from label churn, or the sweep would un-stale its
# own mark every tick.
#
# The verdict contract (CONTRIBUTING.md): reviews end in approve or
# request-changes. Some live bots are comment-only and post agreement as a
# COMMENTED review — a non-verdict this machine refuses to guess about (body
# parsing is a heuristic, and a wrong guess promotes an unapproved PR). The
# judgment call belongs to the PR AUTHOR, who reads the round and escalates
# by requesting the human's review — an explicit request is a fact, and it is
# the one this machine trusts (see decide_state's top precedence). The
# machine auto-requests the human only in the no-judgment-needed case: three
# formal head-current approvals. Any approval that counts must be bound to
# the CURRENT head SHA: GitHub keeps approvals alive across pushes, and a
# stale approval must never promote unreviewed code to the human.
#
# DRY_RUN=1 narrates every mutation instead of performing it (how this script
# is rehearsed against the live repo). A workflow_dispatch run also bootstraps
# the taxonomy (label create --force) — that heal is dispatch-only; the cron
# sweep tolerates a missing label rather than recreating it.
#
# The state machine below is pure (globals in, state out) and covered by
# fixture tests in test/labels-reconcile.sh.
HUMAN="${HUMAN_REVIEWER:-danmt}"
BOTS=(claude-bot-andresmgsl codex-bot-andresmgsl grok-bot-andresmgsl)
STATES=(state:building state:bots-reviewing state:addressing state:needs-human)
BLOCKERS=(blocker:conflict blocker:ci-red blocker:unrequested)
# Labels this machine used to own and no longer does. Cleared on sight so a
# retirement heals the board instead of stranding a label nothing recomputes.
RETIRED=(state:needs-rebase)
STALE_AFTER=$((48 * 3600))
log() { printf 'labels: %s\n' "$*"; }
run() { # every mutation goes through here — DRY_RUN=1 logs instead of doing
if [ -n "${DRY_RUN:-}" ]; then log "DRY_RUN: $*"; else "$@"; fi
}
# ---------------------------------------------------------------------------
# The state machine. Pure functions over four globals, set per PR:
# DRAFT true|false
# HEAD_SHA the PR's current head commit
# REQUESTED newline-separated logins with a review currently requested
# REVIEWS_JSON JSON array of submitted (non-PENDING) reviews
# MERGEABLE MERGEABLE | CONFLICTING | UNKNOWN (GitHub's own verdict)
# CHECKS SUCCESS | FAILURE | PENDING | NONE (the check rollup)
# ---------------------------------------------------------------------------
requested() { grep -qxF "$1" <<<"$REQUESTED"; }
checks_state() { # rollup JSON on stdin → SUCCESS | FAILURE | PENDING | NONE | UNREADABLE
# UNREADABLE is the absence of the key itself, which is what a failed fetch
# leaves behind — distinct from a present-but-empty rollup, which honestly
# means this PR has no checks. Collapsing the two let an API hiccup present
# as "nothing is failing", i.e. as mergeable-by-a-human: the same
# unknown-certified-as-green shape as the bug this machine exists to stop.
# The caller skips the PR entirely rather than labelling on facts it did not
# read; blocking on it instead would flap the whole board on one bad call.
# The rollup mixes two node types with two different closed enums: CheckRun
# carries `conclusion` (CheckConclusionState), StatusContext carries `state`
# (StatusState). Rather than list the outcomes that block — the version that
# shipped in this PR's first round listed four, and ERROR, CANCELLED and
# STALE fell through its `else` into SUCCESS — this lists the outcomes that
# DON'T, and treats everything else as blocking.
#
# That direction is the point. An outcome we do not recognise is one we
# cannot certify as mergeable, and certifying the unrecognised as green is
# the exact shape of #136. The cost of being wrong is symmetric in form and
# not in consequence: a false FAILURE parks the PR on the agent, who looks;
# a false SUCCESS invites a human to merge a tree that will not merge.
jq -r '
if (has("statusCheckRollup") | not) then "UNREADABLE" else
# NEUTRAL and SKIPPED satisfy branch protection — a skipped required check
# is not a failed one, and path-filtered jobs skip constantly here.
["SUCCESS", "NEUTRAL", "SKIPPED"] as $passing
# "" covers a StatusContext still reported with no state at all.
| ["", "PENDING", "IN_PROGRESS", "QUEUED", "WAITING", "REQUESTED", "EXPECTED"] as $waiting
# A re-run does not evict the run it superseded — the rollup keeps both.
# This PR proved it: its own tip carried a CANCELLED `scope` (15:19:39)
# beside the SUCCESS `scope` (15:19:45) that replaced it, same workflow.
# Once CANCELLED blocks, judging every entry would strand this very PR in
# needs-rebase forever, so collapse each context to its newest entry first.
# Key on workflow + name because a bare job name is only unique within its
# workflow.
#
# Dating a run is the subtle part, and getting it wrong restores the bug.
# A run still in flight has no completion, but `gh` does not omit the
# field: its Go struct marshals the zero time as "0001-01-01T00:00:00Z",
# which is a string, so `//` will not fall through it. Ordering on
# completion therefore sorted the LIVE re-run to the bottom and let `last`
# pick the very run it superseded — reporting the old SUCCESS while a
# replacement was still running, which is #136 again.
#
# So: date a run by when it BEGAN, discarding both spellings of absent
# (null, and the zero sentinel) and falling back only if it never recorded
# a beginning. NOT by the newest stamp of any kind: `max` compares the
# completion of a finished run against the start of a live one, which are
# different quantities and not an ordering on runs. A run cancelled by the
# concurrency group does not stop the instant its replacement starts — the
# runner has to wind down — so predecessor.completedAt > successor.startedAt
# is the ordinary case, and `max` dated the dead predecessor newer than the
# live run that replaced it, narrowing both failures above without closing
# them. The list is already in preference order, so `first` IS that rule.
#
# An entry that carries no usable timestamp at all sorts LAST rather than
# first — something we cannot date is most likely the thing just created,
# and treating it as newest keeps an undateable in-flight run from being
# discarded in favour of a stale success. Every ambiguity resolves toward
# "not settled".
| [ (.statusCheckRollup // [])[]
| { ctx: [.workflowName // "", .name // .context // ""],
at: ([.startedAt, .createdAt, .completedAt]
| map(select(type == "string" and . != ""
and (startswith("0001-01-01") | not)))
| first // ""),
outcome: ((.conclusion // .state // "") | ascii_upcase) } ]
| group_by(.ctx)
| map(sort_by([(.at == ""), .at]) | last | .outcome) as $latest
| if ($latest | length) == 0 then "NONE"
elif (($latest - $passing - $waiting) | length) > 0 then "FAILURE"
elif (($latest - $passing) | length) > 0 then "PENDING"
else "SUCCESS" end
end'
}
bot_verdict() { # $1 = login → MISSING | BLOCK | APPROVE | STALE | FEEDBACK
local review state commit
review="$(jq -c --arg u "$1" \
'[.[] | select(.user.login == $u)] | sort_by(.submitted_at) | last // empty' \
<<<"$REVIEWS_JSON")"
if [ -z "$review" ]; then echo MISSING; return; fi
state="$(jq -r '.state' <<<"$review")"
commit="$(jq -r '.commit_id' <<<"$review")"
case "$state" in
CHANGES_REQUESTED)
# blocks at ANY head — GitHub's own semantic: only a newer review
# from the same reviewer clears it
echo BLOCK ;;
APPROVED)
if [ "$commit" = "$HEAD_SHA" ]; then echo APPROVE; else echo STALE; fi ;;
*)
# COMMENTED and anything else: a non-verdict. The machine does not
# read bodies — if the comment is really an agreement, the AUTHOR
# says so by requesting the human's review.
echo FEEDBACK ;;
esac
}
human_request_needed() { # 0 when needs-human requires a FRESH human request
# already requested → the handoff is live; head-current human approval →
# nothing left to ask. Anything else (never reviewed, an old comment, an
# approval of an older head) stalls the handoff unless we request —
# guarding on "has the human ever reviewed" wedged exactly that way.
if requested "$HUMAN"; then return 1; fi
if [ "$(bot_verdict "$HUMAN")" = APPROVE ]; then return 1; fi
return 0
}
blockers() { # → the blocker:* labels this PR should carry, one per line
# The second axis. These are FACTS ABOUT THE BRANCH, and they are mutually
# independent — a PR can be conflicted and red and unasked at once — so they
# are a set, not an ordering. That is the whole point of splitting them out
# of state:*: every precedence bug this machine has had (needs-human
# surviving a conflict, MISSING swallowing STALE) came from projecting
# independent facts onto one totally-ordered label. A set has no precedence
# to get wrong.
#
# UNKNOWN mergeability is deliberately NOT a conflict: GitHub reports it for
# about a minute after every merge while it recomputes, and flapping every
# open PR on each merge would be worse than the bug. Same for a failed read
# of either fact — both default to the "do not know" value, which blocks
# nothing. An unset global (an older fixture, a failed fetch) must never
# invent a verdict it did not read.
case "${MERGEABLE:-UNKNOWN}" in CONFLICTING) echo blocker:conflict ;; esac
case "${CHECKS:-NONE}" in FAILURE) echo blocker:ci-red ;; esac
# Nobody is on the hook for a verdict somebody still owes. Distinct from
# bots-reviewing, which says a request is live and an answer is coming:
# here the round is stalled because no one was ever asked, and the board
# said "waiting on the bots" for the 48h it took `stale` to notice.
# A draft is exempt (the bots ignore drafts by design), and so is an
# explicit human request — a maintainer claiming a PR early is deliberate,
# not a dropped ball.
if [ "$DRAFT" != true ] && ! requested "$HUMAN"; then
local b v owed=false any_requested=false
for b in "${BOTS[@]}"; do
requested "$b" && any_requested=true
# MISSING and STALE are both verdicts this head does not have: nobody
# reviewed it, or everybody reviewed something else. The agent owes an
# ask either way — the stale round is if anything the worse of the two,
# since it has approvals on the page that no longer describe the tree.
v="$(bot_verdict "$b")"
case "$v" in MISSING | STALE) owed=true ;; esac
done
if [ "$owed" = true ] && [ "$any_requested" = false ]; then
echo blocker:unrequested
fi
fi
}
decide_state() { # → the one state:* label this PR should carry
if [ "$DRAFT" = true ]; then echo state:building; return; fi
local s
s="$(round_state)"
# The one rule joining the two axes: state:needs-human means a human could
# merge this RIGHT NOW, so it requires a clear branch. Any blocker at all
# means the work is the agent's — whatever the review round says — and the
# blocker label says which work it is. Nothing else in this function reads
# the branch, which is what keeps the ordering below purely about reviews.
if [ "$s" = state:needs-human ] && [ -n "$(blockers)" ]; then
echo state:addressing; return
fi
echo "$s"
}
round_state() { # → the state the REVIEW ROUND alone implies; knows no branch facts
local b verdicts=""
for b in "${BOTS[@]}"; do
if requested "$b"; then echo state:bots-reviewing; return; fi
done
# Collect the WHOLE round before applying any precedence. Deciding inside
# the loop let BOTS order pick the winner: a MISSING returned immediately,
# so a STALE belonging to a later bot was never even read, and the mixed
# round (one approval staled by a push, another bot yet to review) came out
# needs-human — the #136 headline shape, with zero reviews bound to the head.
for b in "${BOTS[@]}"; do
verdicts="$verdicts $(bot_verdict "$b")"
done
case "$verdicts" in
# STALE = a verdict for an older head. Unlike MISSING, this outranks the
# human request: every approval it covers was invalidated by a push, so
# NOBODY has reviewed this tree. Handing that to the human is the #136 case
# where everything reads green — mergeable, CI passing, "waiting on the
# human" — over code no reviewer has seen. The agent owes a re-request.
# Checked before MISSING because "unfinished" must not swallow "and also
# stale": a round that is both is a push that outran the re-requests, not
# a maintainer deliberately claiming the PR early.
*STALE*) echo state:addressing; return ;;
esac
case "$verdicts" in
# No verdict at all from some bot, and nothing staled. An explicit human
# request still outranks an unfinished round — a maintainer pulling a PR
# to themselves early is a deliberate act, and the original precedence.
#
# Otherwise it is the AGENT's ball, not the bots'. The loop above already
# returned for every live bot request, so reaching here with a MISSING
# means somebody owes a verdict and nobody was asked for one — the round
# is not running. Calling that bots-reviewing was the lie that let a
# forgotten PR read "waiting on the reviewers" for the 48h it took the
# stale sweep to notice. blocker:unrequested says why.
*MISSING*)
if requested "$HUMAN"; then echo state:needs-human; return; fi
echo state:addressing; return ;;
esac
# an explicit human request outranks the remaining bot outcomes — it is the
# final gate, and a maintainer pulling a PR to themselves early counts too
if requested "$HUMAN"; then echo state:needs-human; return; fi
case "$verdicts" in
# FEEDBACK = a comment with no verdict → the agent owes the round-reply.
*BLOCK* | *FEEDBACK*) echo state:addressing; return ;;
esac
# the bots all approve — but if the human's standing word is
# changes-requested (and nobody re-requested them yet), the agent owes
# fixes, not the human a nag
if [ "$(bot_verdict "$HUMAN")" = BLOCK ]; then
echo state:addressing
else
echo state:needs-human
fi
}
# ---------------------------------------------------------------------------
# The sweep: fetch facts, decide, converge. One PR's failure never aborts the
# others — each PR reconciles in a subshell and a failure just logs.
# ---------------------------------------------------------------------------
bootstrap_labels() { # dispatch-only: ~20 upserts is too chatty for every cron tick
while IFS='|' read -r name color desc; do
[ -n "$name" ] || continue
run gh label create "$name" -R "$REPO" --color "$color" --description "$desc" --force
done <<'EOF'
state:building|FBCA04|PR is a draft — the coding agent is still building
state:bots-reviewing|1D76DB|Waiting on the bot reviewers to finish the round
state:addressing|D93F0B|All bots reviewed — coding agent owes the single reply + fixes
state:needs-human|8250DF|No blockers, all bots approve — waiting on the human reviewer
blocker:conflict|B60205|Does not merge — the branch conflicts and the agent owes a rebase
blocker:ci-red|B60205|A check is failing — the agent owes a fix (not a rebase)
blocker:unrequested|E99695|Somebody still owes a verdict and nobody was asked for one
merge-next|0E8A16|Head of the merge queue — merge this one next (set by hand/agent, cleared here)
stale|B60205|No activity for 48h — needs a poke (sweep-managed)
blocked|6A737D|Waiting on another PR or issue to land first
release|0E8A16|Release flow and version/packaging work
scope:cli|C5DEF5|bin/box — the command surface
scope:installer|C5DEF5|install.sh, versioned installs, upgrade/uninstall
scope:host|C5DEF5|host/ — setup, teardown, firewall, isolation stack
scope:tiers|C5DEF5|restricted tier — grant/revoke, multi-user
scope:templates|C5DEF5|templates/ — the box seeds
scope:drill|C5DEF5|drill/ — rehearsals, doctor, RUNS.md
EOF
}
has_label() { grep -qxF "$1" <<<"$LABELS"; }
reconcile_pr() { # $1 = PR number; relies on the globals set from its fetch
local n="$1" desired remove s args last_activity age
desired="$(decide_state)"
# encode the runbook's last step for the no-judgment case: three formal
# head-current approvals → the human is asked, once. The guard asks whether
# a FRESH human review is needed for THIS head — never "has the human ever
# reviewed", which wedged the handoff after any earlier human comment.
# Idempotent (a live request suppresses it); race-free via the shared
# concurrency group in labels.yml. With a comment-only bot on the panel
# this path stays cold and the AUTHOR requests the human.
if [ "$desired" = state:needs-human ] && human_request_needed; then
run gh api "repos/$REPO/pulls/$n/requested_reviewers" -f "reviewers[]=$HUMAN" --silent
log "#$n: requested $HUMAN (round passed)"
fi
# ---- converge both axes ----
# state:* is exclusive (everything but $desired comes off); blocker:* is a
# set (each one on or off on its own); RETIRED always comes off. One edit
# call for all of it, so a PR never flickers through a half-applied board.
local want_blockers add=""
want_blockers="$(blockers)"
remove=""
for s in "${STATES[@]}"; do
if [ "$s" != "$desired" ] && has_label "$s"; then remove="$remove,$s"; fi
done
for s in "${RETIRED[@]}"; do
if has_label "$s"; then remove="$remove,$s"; fi
done
for s in "${BLOCKERS[@]}"; do
if grep -qxF "$s" <<<"$want_blockers"; then
has_label "$s" || add="$add,$s"
else
has_label "$s" && remove="$remove,$s"
fi
done
add="${add#,}"
remove="${remove#,}"
# Never NAME a label the repo does not have. `gh issue edit --add-label`
# rejects the WHOLE call on one unknown name — nothing is applied — so a
# single missing blocker would take the state convergence down with it, on
# exactly the PRs this change exists to fix, surfacing only as a log line.
# Batching state and blockers into one edit for anti-flicker is what widened
# that blast radius; filtering the add side is what closes it again.
# Removals need no filter: they are built from has_label, so the label
# provably exists. REPO_LABELS unreadable means no filtering rather than
# filtering everything out — a failed read must not silently strip the board.
local skip_edit=false
if [ -n "${REPO_LABELS:-}" ]; then
local kept="" missing="" want
for want in ${add//,/ }; do
if grep -qxF "$want" <<<"$REPO_LABELS"; then kept="$kept,$want"
else missing="$missing $want"; fi
done
add="${kept#,}"
# A missing STATE label skips only the EDIT — never the rest of this
# function. Everything below is independent of the state:* taxonomy, and
# returning here stranded it: `merge-next` kept claiming "merge this one
# next" on a PR the board had moved to the agent, and the stale sweep
# stopped running. That is the original false-invitation bug, reintroduced
# in the very fix meant to survive a cold-start repo — and a regression
# against the old behaviour, which failed the edit and fell through.
if ! grep -qxF "$desired" <<<"$REPO_LABELS"; then
log "#$n: WARNING: state label '$desired' does not exist — skipping the label edit; dispatch the workflow to bootstrap"
skip_edit=true
elif [ -n "$missing" ]; then
log "#$n: WARNING: missing label(s)$missing — state still converged; dispatch the workflow to bootstrap"
fi
fi
if [ "$skip_edit" = false ] && { ! has_label "$desired" || [ -n "$remove" ] || [ -n "$add" ]; }; then
args=(--add-label "$desired${add:+,$add}")
[ -n "$remove" ] && args+=(--remove-label "$remove")
if run gh issue edit "$n" -R "$REPO" "${args[@]}" >/dev/null; then
log "#$n: state -> $desired${add:+ +$add}${remove:+ (cleared $remove)}"
else
# a deleted label must not wedge the sweep — dispatch heals the taxonomy
log "#$n: WARNING: label edit failed (missing label? run the workflow manually to bootstrap)"
fi
fi
# ---- merge-next: cleared, never set ----------------------------------
# Queue order is INTENT — which PR should land first is a judgement about
# conflicts and dependencies that GitHub knows nothing about, so the
# reconciler must not guess it (LABELS.md's rule for `blocked`/`release`).
# What it CAN do is stop the label going stale the way needs-human did:
# the moment the PR is no longer the thing a human should merge next, the
# claim is removed. Setting it stays with whoever owns the queue.
if has_label merge-next && [ "$desired" != state:needs-human ]; then
run gh issue edit "$n" -R "$REPO" --remove-label merge-next >/dev/null
log "#$n: cleared merge-next (state is $desired, not mergeable-by-a-human)"
fi
# ---- stale: real activity only, and blocked is legitimately quiet ----
last_activity="$(
{
jq -r '.created_at' <<<"$PR_JSON"
jq -r '.[].submitted_at' <<<"$REVIEWS_JSON"
gh api --paginate "repos/$REPO/issues/$n/comments" --jq '.[].created_at'
gh api --paginate "repos/$REPO/pulls/$n/comments" --jq '.[].created_at'
gh api --paginate "repos/$REPO/pulls/$n/commits" --jq '.[].commit.committer.date'
} | sort | tail -n1
)"
age=$((NOW - $(date -d "$last_activity" +%s)))
if has_label blocked || [ "$age" -le "$STALE_AFTER" ]; then
if has_label stale; then
run gh issue edit "$n" -R "$REPO" --remove-label stale >/dev/null
log "#$n: unstale"
fi
elif ! has_label stale; then
run gh issue edit "$n" -R "$REPO" --add-label stale >/dev/null
log "#$n: stale ($((age / 3600))h quiet)"
fi
}
main() {
REPO="${REPO:?set REPO to owner/name}"
NOW="$(date +%s)"
if [ "${GITHUB_EVENT_NAME:-}" = workflow_dispatch ]; then
log "workflow_dispatch: bootstrapping the taxonomy"
bootstrap_labels
fi
# The repo's label set, read ONCE per sweep — reconcile_pr filters every
# add against it, because one unknown name fails the whole edit call.
REPO_LABELS="$(gh label list -R "$REPO" --limit 200 --json name --jq '.[].name' 2>/dev/null || echo "")"
[ -z "$REPO_LABELS" ] && log "WARNING: could not read the label set — applying labels unfiltered"
local n
for n in $(gh pr list -R "$REPO" --state open --limit 100 --json number --jq '.[].number'); do
(
PR_JSON="$(gh api "repos/$REPO/pulls/$n")"
DRAFT="$(jq -r '.draft' <<<"$PR_JSON")"
HEAD_SHA="$(jq -r '.head.sha' <<<"$PR_JSON")"
LABELS="$(jq -r '.labels[].name' <<<"$PR_JSON")"
REQUESTED="$(jq -r '.requested_reviewers[].login' <<<"$PR_JSON")"
# PENDING reviews are unsubmitted drafts in someone's browser — not a verdict
REVIEWS_JSON="$(gh api --paginate "repos/$REPO/pulls/$n/reviews" --jq '.[]' \
| jq -s '[.[] | select(.state != "PENDING")]')"
# mergeability + the check rollup, the two facts the state machine was
# blind to (#136). `gh pr view` rather than the REST PR object: the API's
# `mergeable` is a tri-state boolean that GitHub computes lazily, while
# this returns the same MERGEABLE/CONFLICTING/UNKNOWN string the UI shows.
# Failure to read them is NOT fatal and NOT treated as broken — an API
# hiccup must never flap every PR into needs-rebase, so both degrade to
# the "do not know" value that triggers nothing.
GH_VIEW="$(gh pr view "$n" -R "$REPO" --json mergeable,statusCheckRollup 2>/dev/null || echo '{}')"
MERGEABLE="$(jq -r '.mergeable // "UNKNOWN"' <<<"$GH_VIEW")"
CHECKS="$(checks_state <<<"$GH_VIEW")"
# Read failed: leave this PR exactly as it is. Recomputing on facts we
# did not read is how an API hiccup turns into a false "merge me" —
# and the next tick is 15 minutes away, not 15 hours.
if [ "$CHECKS" = UNREADABLE ]; then
log "#$n: could not read mergeability/checks — left alone this pass"
exit 0
fi
reconcile_pr "$n"
) || log "#$n: reconcile failed — continuing with the remaining PRs"
done
log "reconciled."
}
# sourced by test/labels-reconcile.sh for the fixture tests; executed in CI
if [ "${BASH_SOURCE[0]}" = "$0" ]; then
main "$@"
fi

View file

@ -1,30 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
# release-notes.sh <version> [<changelog>] — print exactly <version>'s
# section of the changelog: every line between its '## <version> — <date>'
# header and the next '## '. This is what release.yml hands to
# 'gh release create', so the release notes are the curated prose we wrote,
# not the PR list GitHub would generate (#83). Fails loudly when the section
# is missing or empty — a tag without its changelog section is a release
# ritual skipped, and an empty release body would paper over it.
#
# A file of its own (not inlined in release.yml) so test/release.sh drives
# the same extraction against fixtures and the real CHANGELOG.md.
ver="${1:-}"
changelog="${2:-CHANGELOG.md}"
[ -n "$ver" ] || { echo "usage: release-notes.sh <version> [<changelog>]" >&2; exit 2; }
[ -f "$changelog" ] || { echo "release-notes: no such file: $changelog" >&2; exit 1; }
# $2 of a section header ('## 0.6.0 — 2026-07-18') is the bare version —
# compared WHOLE, so 0.6.0 can never match a 0.6.0-rc1 section (or vice
# versa), and no regex-escaping of dots. sed drops the blank padding under
# the header; the command substitution eats the trailing blanks.
notes="$(awk -v ver="$ver" '
/^## / { grab = ($2 == ver); next }
grab { print }
' "$changelog" | sed '/./,$!d')"
[ -n "$notes" ] || { echo "release-notes: $changelog has no section for '$ver' — the release PR stamps the Unreleased section with version + date BEFORE the tag (#83)" >&2; exit 1; }
printf '%s\n' "$notes"

View file

@ -5,6 +5,10 @@ which records not just what changed but what each drill run proved.
## Unreleased ## Unreleased
### Changed
- Release and repository governance now use the shared ceremony pinned at `0.1.0` (heavy-duty/ceremony#14)
### Added ### Added
- `kimi-box` template — the Moonshot Kimi CLI agent seed (#158; rig#109's tenant) - `kimi-box` template — the Moonshot Kimi CLI agent seed (#158; rig#109's tenant)

View file

@ -1,313 +1,83 @@
# Contributing # Contributing
How change lands in this repo. The short version: PRs are born as drafts, This repository is governed by
three reviewer bots take the first rounds, a human takes the last word — and [heavy-duty/ceremony](https://github.com/heavy-duty/ceremony). Agents read
labels tell you where everything is without opening anything. [`.ceremony/AGENTS.md`](.ceremony/AGENTS.md) first, then the role file it
selects. The files under `.ceremony/` are machine-managed and must never be
edited in place.
## The PR loop Only triage mints issues. Everyone else opens or extends a discussion when
they find work outside an existing issue contract. Only humans merge.
1. **Fork and branch.** Contributors work from forks; upstream branches are ## Review panel
for maintainers. Title the PR conventionally (`feat:`, `fix:`, `docs:`),
and include a `CHANGELOG.md` entry under `## Unreleased` when the change
deserves one.
2. **Open as a draft** while you build. Drafts are invisible to the reviewer
bots on purpose.
3. **When it's ready**: mark ready-for-review and request all three bots —
`claude-bot-andresmgsl`, `codex-bot-andresmgsl`, `grok-bot-andresmgsl`.
They poll roughly every 15 minutes.
4. **Rounds are answered whole.** Wait until all three have reviewed, then
answer the entire round in a **single reply**, push the fixes, and
re-request the bots that didn't approve. Prefer verification over
argument: a test settles what a comment thread can't.
5. **Reviews end in a verdict.** A reviewer — bot or human — either
**approves** or **requests changes**, never a bare comment. A
comment-only review is a non-verdict: it doesn't say whether the round
passed, and the state machine (and anyone scanning the board) has to
guess. The verdict carries *blockingness only*, the body carries the
feedback: non-blocking nits ride an **approval** and the author addresses
them at their discretion; anything blocking — including a question that
gates the verdict — is **request changes**, saying what unblocks it. The
reconciler treats a comment-only review as not-approved, so commenting
without a verdict only stalls the PR. The machine never reads review
bodies: when a comment-only reviewer's line is really an agreement, that
judgment belongs to the **author** — escalate by requesting the
maintainer's review (step 6), and the reconciler flips the label on that
request, because an explicit request is a fact it can trust.
6. **When the round passes, the author hands the PR to the maintainer** in
three acts, in this order: post the tagged round summary, request the
maintainer's review, then set `state:needs-human` yourself — removing the
state label it replaces. The review request is what *earns* the label,
provided the PR carries **no `blocker:*` label**. A blocker means the work
is still yours whatever the round said, so on a conflicted or red PR
neither the request nor your own label write will stick — the sweep takes
it straight back off. With three formal head-current approvals the labels
workflow requests the maintainer automatically; when part of the panel is
comment-only, reading their agreement is the author's judgment, so the
author makes the request.
Writing the label by hand is an **optimistic write, not a transfer of The review panel is:
ownership**. The machine stays the authority — but because the workflow
wakes on `labeled`, the author's own write fires the sweep that validates
it, and a handoff that had not earned the label is corrected seconds later.
Forgetting the write is not a failure either; it only means the label waits
for the cron, which is the lag this replaced.
7. **Checks must be green**: `shellcheck` and `bash test/cli.sh` locally
mirror what CI runs; the multi-user rehearsal runs in CI on a real Incus.
## Changelog entries - `claude-bot-andresmgsl`
- `codex-bot-andresmgsl`
- `grok-bot-andresmgsl`
- `kimi-bot-andresmgsl`
Every PR that changes behaviour adds **one line** to `## Unreleased`. One line Every PR needs a current-head verdict from the whole panel minus its author.
is the whole rule — if it wraps more than twice in your editor, cut it down. `dan-claude-bot` is triage-only and is never a reviewer. Draft PRs remain
invisible to the panel; when ready, request every eligible reviewer.
- **Say what changed, and stop.** Why it was wrong, how it was found, what it ## Code and verification
cost, what it implies — that belongs in the PR body and the commit message,
which is where anyone chasing the reasoning already goes. This file answers
one question: what is different in this version.
- **Any word that can be removed, is removed.**
- **Lead with the surface, not the mechanism.** "`state:needs-human` is set at
handoff" beats "the labels workflow now also wakes on `labeled`".
- **Cite the issue or PR**`(#141)` — and let the reader follow it for the
rest.
- **Mark a breaking change** with a leading `BREAKING:`.
- Group under `### Added` / `### Changed` / `### Fixed` / `### Removed`.
- No bold run-in headings, no sub-paragraphs, no code blocks, no prose essays.
Good: - Bash executables use `set -euo pipefail`; test harnesses use `set -u`
because they assert failing commands.
- Keep shellcheck clean. Run `bash test/cli.sh` and `bash test/release.sh`;
CI also runs the Incus multi-user rehearsal.
- Match whole versions: `0.7.0` must never match `0.7.0-rc1`.
- Comments preserve the incident that bought a rule, including its issue
number.
```markdown ## Changelog
- `state:needs-human` is set at handoff, not by the cron (#141)
- An unreadable check rollup no longer reads as "nothing is failing" (#136)
- BREAKING: `--class human|server` is now `--root-door closed|open` (#77)
```
Not an entry — that is a PR body: Every behavior-changing PR adds one concise line under `## Unreleased`,
above the shipped heading below it. Cite the issue or PR. Never replace or
```markdown duplicate a shipped heading; the shared armed and monotonic guards enforce
- **`state:needs-human` no longer waits on the cron to become true** (#141) — both halves of this rule.
the labels workflow now also wakes on `pull_request_target: labeled` and
`unlabeled`, and the author sets it themselves when handing a PR over. A
review landing was never a trigger. There is no `pull_request_review_target`,
and on fork PRs — which is all of them here — ...
```
## Releases ## Releases
A release is a PR, and merging it ships it The release ceremony, merge and tag doors, version stamps, guard semantics,
([#96](https://github.com/heavy-duty/box/issues/96), building on and recovery paths are defined by
[#83](https://github.com/heavy-duty/box/issues/83)): [heavy-duty/ceremony](https://github.com/heavy-duty/ceremony/blob/0.1.0/README.md).
Box pins the shared machinery and doctrine at `0.1.0`.
1. **The release PR**`release: X.Y.Z`, labeled `release` — bumps `VERSION` Box uses the `file` version backend and has no artifact hook: for this
from `X.Y.Z-dev` and stamps the `## Unreleased` section with version + pure-Bash tree, GitHubs source tarball for the tag is the package, and
date (feature PRs land their changelog entry as part of the PR, so the `install.sh` downloads exactly that. `VERSION`, `CHANGELOG.md`, and
section is already written). `drills/<version>.md` remain box-owned release inputs.
**Stamping is two edits, not one — the second is re-arming.** After ### What a box drill proves
rewriting `## Unreleased` into `## X.Y.Z — DATE`, put an **empty
`## Unreleased` back at the top**, immediately above the section you just
stamped:
```markdown The box drill is the 85-probe VM isolation contract: it exercises the trust
## Unreleased boundary on real hardware. The lighter Incus container rehearsal in CI proves
the tier mechanics but cannot substitute for that boundary measurement. The
record format and operating procedure live in [drills/README.md](drills/README.md).
## 0.7.1 — 2026-07-19 `drills/<version>.md` and [`drill/RUNS.md`](drill/RUNS.md) are deliberately
different artifacts. The former is per-release evidence read by the release
guard; the latter is the harnesss ongoing run log and lore. Updating one
never satisfies the purpose of the other.
### Fixed The family drills are independent and may run in any order. Each pins the
... same fixed candidate refs: rigs drill uses the candidate box ref, while
``` boxs drill mints with the candidate rig ref. Static refs dissolve the
box↔rig runtime recursion; no repository needs to release first.
Not cosmetic, and not deferrable to the next PR that happens to need it. A known gap remains from box#81: released box templates still default
Between the stamp and the next re-creation of that heading, `main` has no `RIG_REF` to `main`, so a later mint may consume a rig revision other than
`## Unreleased`. A PR authored *before* the release wrote its entry under the one drilled. This conversion does not change that behavior or claim the
that heading; with the heading gone, git lands the entry under whatever gap is closed.
now occupies the position — **the section that just shipped** — and it
merges **cleanly**, no conflict, no signal. The changelog then credits a
released version with a change it does not contain, and nothing but a
human reading the file will ever say so
([#108](https://github.com/heavy-duty/box/issues/108); confirmed in the
sibling repo as
[heavy-duty/rig#66](https://github.com/heavy-duty/rig/issues/66)).
CI enforces the arming rule with ## Scope labels
[.github/scripts/changelog-armed.sh](.github/scripts/changelog-armed.sh),
keyed on `VERSION`: a `-dev` tree must carry `## Unreleased` on top; a
bare-`VERSION` tree (the ceremony PR, and the merge that publishes it) may
carry either `## Unreleased` or its own stamped section. That is why the
guard cannot simply demand `## Unreleased` unconditionally — the
unconditional form is false on the ceremony PR's own tree and makes the
release unshippable, which is why rig and cast both reverted it. The
practical consequence: forgetting to re-arm does **not** block the release
PR, it turns `main` red on the very next push — the automatic `-dev` bump
the release itself makes. Do it in the ceremony PR and main is never
disarmed at all.
**Release headings are append-only.** When you add your entry under - `scope:cli``bin/box`, the command surface
`## Unreleased`, *insert above* the heading below it — never type over - `scope:installer``install.sh`, versioned installs, upgrade/uninstall
that line. Replacing `## 0.8.0 — 2026-07-19` with your own `## Unreleased` - `scope:host` — host setup, teardown, firewall, and isolation stack
block deletes a shipped section: its prose is absorbed into `Unreleased`, - `scope:tiers` — grant/revoke and multi-user boundaries
`release-notes.sh` can no longer find the version it extracts by heading, - `scope:templates` — template and profile seeds
and the next release republishes the absorbed prose as if it were new. git - `scope:drill` — rehearsals, doctor, and run evidence
merges that edit cleanly and `changelog-armed.sh` stays green on it — the
top section is still the right one — so
[.github/scripts/changelog-monotonic.sh](.github/scripts/changelog-monotonic.sh)
asserts the other half on every PR: the set of `## X.Y.Z` headings on your
branch must be a **superset** of the set at the merge base
([#122](https://github.com/heavy-duty/box/issues/122), caught in review of
[#118](https://github.com/heavy-duty/box/pull/118)). The ceremony's own
stamp passes it by construction — rewriting `## Unreleased` into
`## X.Y.Z — DATE` adds a heading and removes none.
**The drill gates the release, and CI enforces it.** The release PR's
flow is: draft → ready → bot round → **drill**`state:needs-human`
maintainer merge (which *is* the release). CI proves the tier's semantics
on every PR; the drill is what proves the VM trust boundary, and it wants
real hardware and the better part of an hour, so it runs on the release
PR's branch and nowhere else.
Record it in its own file, named exactly for the version:
```
drills/X.Y.Z.md
```
...with the run in it — what it measured, what it found, what it cost.
See [drills/README.md](drills/README.md) for the shape.
[.github/scripts/drill-recorded.sh](.github/scripts/drill-recorded.sh)
asserts exactly that on every tree with a bare `VERSION`, which is every
`release` PR and the merge that publishes it; a `-dev` tree passes with
nothing to assert. It is **no longer a thing a reviewer has to remember**.
**`drills/` is release evidence; [`drill/RUNS.md`](drill/RUNS.md) is the
harness's own log.** Two artifacts, two purposes. `drill/RUNS.md` keeps
being what it has always been — every run of the harness, the traps table,
the lore — and is not release-scoped. `drills/X.Y.Z.md` is the per-release
record the gate reads. Appending to `drill/RUNS.md` does not satisfy the
gate, and is not meant to.
One file per version is also why the guard is short. When records shared a
file it had to match em-dash heading fields, tolerate an optional date
tail, and compare versions *whole* so `0.9.0-rc1` could not satisfy
`0.9.0` — and two separate defects were found in review because of that
complexity. Now `0.9.0.md` and `0.9.0-rc1.md` are simply different files
and none of it is representable.
It became CI's job because remembering did not work. The sentence this
paragraph replaces described a step **no release had ever performed**
there was no drill record anywhere in the repo — and #95, #114 and #148
all shipped through the gap as a `VERSION` bump plus a `CHANGELOG.md`
stamp. The one time it was caught was the one time somebody happened to
look, which is not a gate.
**The three drills are INDEPENDENT — there is no fixed order.** box, rig
and cast each drill separately, in any order, on any schedule, in separate
sittings if you like. What makes that safe is not sequencing, it is that
every drill **pins the same fixed set of candidate refs**: rig's drill
runs `--host yes` with `BOX_REF=release/<box-version>`, so it exercises the
box that will actually ship; box's drill mints with
`RIG_REF=release/<rig-version>`, so it exercises the rig that will actually
ship. Both measure the same pair.
That is what dissolves the box↔rig recursion. box and rig really are
**mutually recursive** — rig sits *below* box as the host-builder
(`rig bootstrap --host yes` installs box and runs `setup-host`) and
*above* it as the guest-converger (a `box new` seed's cloud-init curls
rig's installer and runs `rig bootstrap <tenant>-box`); box's own source
says as much, the seeds "invert the rig→box install edge (rig#28: rig
installs box on hosts; now box guests install rig)". A cycle at *runtime*
becomes two independent tests against one fixed pair, because the refs are
**static identifiers that exist as soon as the release branches do**, long
before any drill runs. Nothing has to be released, or drilled, first.
Within a single drill you of course bring the substrate up before probing
it — a host before a guest. That is how you run a drill; it is not an
ordering rule between repos.
Each repo drills in a **different way** and asserts a different thing: box
asserts the **isolation contract** (the 85-probe VM trust boundary), rig
asserts **convergence** (a machine reaches its role, idempotently), cast
asserts **promotion** (A→B reproduces, the diff is idempotent). Three
different exercises sharing a substrate — not three phases of one script,
which is exactly why the records are per-repo.
It drills **candidate refs, not released artifacts.** `RIG_REPO` and
`RIG_REF` are mint-time environment variables (defaults
`heavy-duty/rig` and `main`, `bin/box`), so a run pins the exact commits
under test. That dissolves the chicken-and-egg: **no repo has to be
released before another can be drilled.** And drilling the candidate *is*
drilling the release — a release PR's diff is `VERSION` plus
`CHANGELOG.md` and nothing else, so no executable byte differs between
the tree that was drilled and the tree that ships.
The drills of a release set share **one run ID**. Each repo records its own
legs in its own `drills/X.Y.Z.md`, citing that run ID and the other two
repos' commit SHAs, so the three records reconcile afterwards. The guard
reads only this repo's file — it asserts box's record exists, never the
other two.
If a defect shows up only in the combination: **patch, re-drill,
re-record.** The three releases converge on a set that holds together;
they are not required to be right in one pass.
**A known gap, and box is where it belongs.** A *released* box still
defaults `RIG_REF` to `main`, so what a user mints a week after a drill is
not the combination that was drilled — the guest converges against
whatever rig's main has become since. Pinning `RIG_REF` to a released rig
tag in the templates is the outstanding step from
[#81](https://github.com/heavy-duty/box/issues/81) (rig#32 step 5), and it
is what would make a drilled combination reproducible for users. This PR
does not fix it; box's source already says the two directions "track main
unpinned today, said honestly ... until a release flow exists".
A maintainer **waiver** is possible, and it is still written down. The
guard requires a *record*, not a passing result, so a release that must
ship without a full drill creates `drills/X.Y.Z.md` anyway and says plainly
that the drill was waived and why. Skipping then costs a deliberate,
reviewable file in the diff — which is precisely what the three silent
skips above did not.
2. **The maintainer's merge IS the release.**
[release.yml](.github/workflows/release.yml) fires on the merged,
`release`-labeled PR and asserts before creating anything: `VERSION` at
the merge commit is non-`-dev` **and changed in this PR** (the `-dev`
interlock — a mislabeled ordinary PR fails loudly and creates nothing),
the version's `CHANGELOG.md` section extracts non-empty, and no tag or
release exists for it yet. Then, in the same job, it tags the merge
commit bare `X.Y.Z` (no `v` prefix, the `0.6.0` precedent) and publishes
the GitHub release with that section as the body. No assets — the source
tarball for the tag is the package, and `install.sh` downloads exactly
that.
*Manual fallback/backfill*: the tag-push path stays. Tagging the merge
commit bare `X.Y.Z` by hand and pushing the tag still publishes the same
way (release.yml asserts the tag names the tree's own `VERSION`) — for
backfills, or the day the merge path is red.
3. **The release re-arms main itself**: the same workflow run bumps
`VERSION` to `X.Y.(Z+1)-dev` and pushes the commit straight to main —
no follow-up PR (it opens one only if branch protection refuses the
direct push, and says so loudly). Not cosmetic — the versioned layout
names install trees after `VERSION`, so a `main` install without the
bump would land in `versions/X.Y.Z` and impersonate the release just
cut. On the *manual* tag path the bump stays yours: open the one-line
PR after publishing.
## Labels — who sets what
The full taxonomy lives in [LABELS.md](LABELS.md). What matters day to day is
who sets each kind — most of it is machinery, and hand-moving a
machine-owned label just gets corrected on the next pass:
| Labels | Set by |
|---|---|
| `state:*` | the labels workflow ([.github/workflows/labels.yml](.github/workflows/labels.yml)) — recomputed from GitHub's own facts on PR events (label changes included) and every 15 minutes. Machine-owned, with one exception: the author sets `state:needs-human` at handoff (step 6) and the workflow reconciles it. Otherwise never by hand. Exactly one per PR: *whose ball is it.* |
| `blocker:*` | the same workflow, from the same facts — *what is in the way.* Any number per PR, or none. Never by hand: applying one does not stop a merge, and removing one does not unblock anything. Fix the thing and the next sweep drops the label. |
| `stale` | the same workflow — 48h without commits, comments, or reviews. `blocked` PRs are exempt: they are quiet legitimately. |
| `scope:*` on PRs | actions/labeler, from the changed paths ([.github/labeler.yml](.github/labeler.yml)). Additive — you may add more, the machine won't remove them. |
| `scope:*` on issues | you, when opening or triaging — issues have no paths to derive from. |
| `blocked`, `release` | you — automation never guesses intent. |
| `merge-next` | you or the agent owning the queue. Which PR lands first is a judgement about how they conflict, so the workflow never sets it — it only **clears** it, the moment the PR stops being something a human could merge. |
| `bug` / `enhancement` / `documentation` | you, on issues only — a PR's type already lives in its title. |
## Issues
Give issues the same care as PR titles: say the surface in the title, apply a
`scope:` label and a type label (`bug` / `enhancement` / `documentation`) when
you open one, and `blocked` when it waits on something — that is what keeps
the board navigable as the issue count grows.

181
LABELS.md
View file

@ -1,181 +0,0 @@
# Labels
How this repo uses GitHub labels. The taxonomy is shared across the
heavy-duty repos (box, rig, cast) — only the `scope:` set differs per repo,
because it names this repo's actual surfaces.
## State — who is the ball with? (PRs, exactly one)
Every open PR carries exactly one `state:` label, and it answers the only
question a board scan actually asks: *who is this PR waiting on?* The states
mirror the review loop this repo runs — PRs open as drafts, three reviewer
bots pick up ready PRs with reviews requested, each round is answered in a
single reply, and a human takes the final review.
| Label | Color | Waiting on | Enters when | Leaves when |
|---|---|---|---|---|
| `state:building` | `#FBCA04` | the coding agent, still building | PR opened as draft | marked ready + bot reviews requested |
| `state:bots-reviewing` | `#1D76DB` | the reviewer bots to finish the round | ready with reviews requested, or fixes pushed and reviews re-requested | all three bots have reviewed the round |
| `state:addressing` | `#D93F0B` | the coding agent to reply, fix, or ask | all bots reviewed and not all approved; or nobody was asked; or a blocker is up | the round-reply is posted and fixes pushed — and any blocker named alongside is cleared |
| `state:needs-human` | `#8250DF` | the human reviewer | the PR **could be merged right now**: no blockers, three formal head-current approvals — and the human review is requested | merged — or changes requested, which cycles back to `state:addressing` |
`bots-reviewing` and `addressing` are deliberately distinct: staleness in the
first means *poke the bots*, staleness in the second means *the agent dropped
the ball*. Collapsing them loses exactly the information a sweep needs.
`bots-reviewing` therefore means strictly *a request is live and an answer is
coming* — a PR nobody was asked to review is the agent's ball, not the bots'.
## The second axis: `blocker:*`
State answers *whose ball is it*. Blockers answer *what is in the way*, and
unlike states they are *facts about the branch* — mutually independent, so a
PR carries as many as apply.
| Label | Color | Means | Clears when |
|---|---|---|---|
| `blocker:conflict` | `#B60205` | GitHub says `CONFLICTING` — the agent owes a **rebase** | it merges cleanly |
| `blocker:ci-red` | `#B60205` | a check failed — the agent owes a **fix**, which a rebase will not provide | checks are green |
| `blocker:unrequested` | `#E99695` | this head has no verdict from somebody — never reviewed, or staled by a push — and **nobody was asked** for one | reviews are requested |
| `blocker:drill-pending` | `#B60205` | a `release` PR whose version has no drill record at [`drills/X.Y.Z.md`](drills/README.md) — the ceremony is **correct but unevidenced** | the drill is run and recorded (or a waiver is recorded) at `drills/X.Y.Z.md` |
`blocker:drill-pending` is the one blocker that says the diff is *fine*. The
version is stamped, the changelog is right, CI's other guards are green — what
is missing is the evidence that the release was proven on real hardware, which
[.github/scripts/drill-recorded.sh](.github/scripts/drill-recorded.sh) refuses
to let a release ship without (CONTRIBUTING.md, "Releases"). Naming it
separately from `blocker:ci-red` matters because the two owe different work: a
red check is a fix in the branch, a pending drill is an hour on a real host.
It must be **created by a maintainer account** — the bot account gets a `403`
creating labels, so the labels workflow's bootstrap dispatch cannot mint it.
Until it exists in the repo, `blocked` stands in: it is the closest true thing
(the PR is waiting on something outside itself) and, usefully, the staleness
sweep already skips it, so a release parked overnight on a drill does not
collect a `stale`.
One rule joins the axes: **`state:needs-human` requires zero blockers.** Any
blocker means the work is the agent's, whatever the review round says.
This split exists because the single-label version kept lying. Independent
facts were projected onto one totally-ordered label, so one always had to win
and the losers vanished off the board: a PR that was *both* conflicted and red
could only say one of them, and `needs-rebase` told an agent to rebase when
what it actually owed was a bug fix. Precedence between two blockers is not a
question a set has to answer, which is why every ordering bug this machine has
had — `needs-human` surviving a conflict, `MISSING` swallowing `STALE` — lived
on the axis that had to be totally ordered.
`state:needs-rebase` was the first attempt at this and is **retired**; the
reconciler strips it on sight so no PR is left carrying a label nothing
recomputes.
**`state:needs-human` means one thing: a human could merge this right now.**
The label is the only signal a maintainer scanning the board (or a phone)
actually reads, and one that says "your turn" on an unmergeable PR is worse
than no label at all. So beyond the blockers, one review fact also outranks an
explicit human request:
- **nobody reviewed *this* head** — every approval staled by a push → `state:addressing`,
because the agent owes a re-request
That case is more dangerous than any blocker: a blocked PR at least shows an X
or a disabled merge button, while a staled-approval PR reads green, mergeable
and "waiting on the human" over code no reviewer has seen.
`UNKNOWN` mergeability is deliberately **not** treated as a conflict. GitHub
reports it for about a minute after every merge while it recomputes, and
flapping every open PR through `blocker:conflict` on each merge would be worse
than the bug this fixes. A failed read of either branch fact degrades to the
same "do not know" value, for the same reason.
An *unfinished* round still yields to an explicit human request — a maintainer
pulling a PR to themselves early is a deliberate act. `MISSING` (nobody has
reviewed yet) and `STALE` (everyone reviewed something else) are different
facts and are treated differently.
## Cross-cutting (PRs and issues)
| Label | Color | Meaning |
|---|---|---|
| `stale` | `#B60205` | No activity for 48h. Sweep-managed, never hand-applied. `state:building` + `stale` is precisely a forgotten draft. |
| `blocked` | `#6A737D` | Waiting on another PR or issue to land first. Quiet *legitimately* — the staleness sweep skips it. |
| `release` | `#0E8A16` | Release flow, versioning, and packaging work. |
| `merge-next` | `#0E8A16` | Head of the merge queue — **merge this one next**. Queue order is *intent* (which PR lands first, given how they conflict), so the reconciler never sets it: you or the agent maintaining the queue do. The reconciler only **clears** it, the moment the PR stops being something a human could merge — so it cannot go stale the way `state:needs-human` did. |
## Scope — which surface? (PRs and issues, any number)
All scopes share one calm color, `#C5DEF5` — scopes locate, states alert.
| Label | Covers |
|---|---|
| `scope:cli` | `bin/box` — the command surface itself |
| `scope:installer` | `install.sh`, the versioned install layout, upgrade/uninstall |
| `scope:host` | `host/` — setup-host, teardown, the firewall and isolation stack |
| `scope:tiers` | the restricted tier — grant/revoke, multi-user semantics |
| `scope:templates` | `templates/` — the box seeds |
| `scope:drill` | `drill/` — the rehearsals, doctor, RUNS.md |
## Issue types
`bug`, `enhancement`, `documentation` — issues only. PRs carry their type in
the conventional title (`feat:`, `fix:`, `docs:`), so typing a PR with a label
would just say the same thing twice, drifting apart eventually.
## Maintenance
State labels are machine-owned, with exactly one exception. Every state above
is derivable from GitHub's own facts — the draft flag, requested reviewers,
review states, push timestamps — so the labels workflow
([.github/workflows/labels.yml](.github/workflows/labels.yml)) recomputes the
state and reconciles labels statelessly, on PR events (label changes included)
plus a 15-minute cron. A hand-moved label is a lie waiting to happen; the
workflow asserts the effective state instead.
The exception is `state:needs-human`, which the author sets at handoff
([CONTRIBUTING.md](CONTRIBUTING.md), step 6). That is an optimistic write, not
a transfer of ownership: because `pull_request_target: labeled` wakes the
workflow, the author's own label write fires the sweep that validates it, and
a handoff that had not earned the label is corrected within seconds.
It exists because the wake signal was missing. There is no
`pull_request_review_target` — on fork PRs, which is all of them here,
`pull_request_review` runs read-only and cannot label anything — so the moment
the label becomes true, the third approval landing, fired nothing at all. What
was left was the `*/15` cron, and GitHub deprioritises short intervals hard
enough that the delivered rate is closer to hourly. The label could therefore
lag the round it described by hours, worst on the quietest repo: every sweep
reconciles the whole board, so a busy repo stays fresh by piggybacking on
unrelated PR events, while a quiet one depends on the cron most and receives
it least. `scope:` labels on PRs are applied from the changed
paths by actions/labeler ([.github/labeler.yml](.github/labeler.yml));
[CONTRIBUTING.md](CONTRIBUTING.md) says who sets what.
The same workflow bootstraps the taxonomy: a manual dispatch creates any
missing label idempotently. To create them by hand (needs push access):
```sh
gh label create "state:building" --color FBCA04 --description "PR is a draft — the coding agent is still building" --force
gh label create "state:bots-reviewing" --color 1D76DB --description "Waiting on the bot reviewers to finish the round" --force
gh label create "state:addressing" --color D93F0B --description "All bots reviewed — coding agent owes the single reply + fixes" --force
gh label create "blocker:conflict" --color B60205 --description "Does not merge — the branch conflicts and the agent owes a rebase" --force
gh label create "blocker:ci-red" --color B60205 --description "A check is failing — the agent owes a fix (not a rebase)" --force
gh label create "blocker:unrequested" --color E99695 --description "Somebody still owes a verdict and nobody was asked for one" --force
# retired — the reconciler strips it; delete it once no PR carries it
# gh label delete "state:needs-rebase"
gh label create "state:needs-human" --color 8250DF --description "No blockers, all bots approve — waiting on the human reviewer" --force
gh label create "merge-next" --color 0E8A16 --description "Head of the merge queue — merge this one next (set by hand/agent, cleared here)" --force
gh label create "stale" --color B60205 --description "No activity for 48h — needs a poke (sweep-managed)" --force
gh label create "blocked" --color 6A737D --description "Waiting on another PR or issue to land first" --force
gh label create "release" --color 0E8A16 --description "Release flow and version/packaging work" --force
gh label create "scope:cli" --color C5DEF5 --description "bin/box — the command surface" --force
gh label create "scope:installer" --color C5DEF5 --description "install.sh, versioned installs, upgrade/uninstall" --force
gh label create "scope:host" --color C5DEF5 --description "host/ — setup, teardown, firewall, isolation stack" --force
gh label create "scope:tiers" --color C5DEF5 --description "restricted tier — grant/revoke, multi-user" --force
gh label create "scope:templates" --color C5DEF5 --description "templates/ — the box seeds" --force
gh label create "scope:drill" --color C5DEF5 --description "drill/ — rehearsals, doctor, RUNS.md" --force
# delete is not an upsert: a label that is already gone exits non-zero. Swallow
# that, so this block converges on re-run instead of erroring after first success.
for L in duplicate invalid question wontfix "help wanted" "good first issue"; do
gh label delete "$L" --yes 2>/dev/null || true
done
```

View file

@ -9,7 +9,7 @@ drills/0.9.0-rc1.md
``` ```
The name must match the contents of `VERSION` exactly. The name must match the contents of `VERSION` exactly.
[.github/scripts/drill-recorded.sh](../.github/scripts/drill-recorded.sh) [the pinned ceremony drill-recorded action](https://github.com/heavy-duty/ceremony/tree/0.1.0/actions/drill-recorded)
refuses any tree with a bare `VERSION` that has no such file, or whose file is refuses any tree with a bare `VERSION` that has no such file, or whose file is
blank. A `-dev` tree passes with nothing to assert. blank. A `-dev` tree passes with nothing to assert.

View file

@ -1,416 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
# Fixture tests for the labels-reconcile state machine: a comment is a
# non-verdict whatever its body says (the AUTHOR escalates by requesting the
# human), a stale approval does not promote unreviewed code, and an explicit
# human request outranks everything.
# Dependency-free beyond jq; no network, no daemon — pure decide_state.
cd "$(dirname "$0")/.."
# shellcheck source=.github/scripts/labels-reconcile.sh
. .github/scripts/labels-reconcile.sh
# The DRAFT/HEAD_SHA/REQUESTED/REVIEWS_JSON assignments below are the state
# machine's inputs, consumed inside the sourced decide_state — not unused.
# shellcheck disable=SC2034
BOT1="${BOTS[0]}" BOT2="${BOTS[1]}" BOT3="${BOTS[2]}"
pass=0 fail=0
expect() { # $1 = description, $2 = want, $3 = got
if [ "$2" = "$3" ]; then
pass=$((pass + 1))
else
fail=$((fail + 1))
printf 'FAIL: %s — want %s, got %s\n' "$1" "$2" "$3"
fi
}
rev() { # $1=login $2=state $3=commit $4=body $5=submitted_at → one review object
jq -n --arg u "$1" --arg s "$2" --arg c "$3" --arg b "$4" --arg t "$5" \
'{user: {login: $u}, state: $s, commit_id: $c, body: $b, submitted_at: $t}'
}
reviews() { jq -s '.' <<<"$*"; } # collect review objects into an array
# -- drafts are building, whoever is requested --------------------------------
DRAFT=true HEAD_SHA=head1 REQUESTED="" REVIEWS_JSON='[]'
expect "draft PR is building" state:building "$(decide_state)"
# -- fresh ready PR with bots requested ---------------------------------------
DRAFT=false REQUESTED="$BOT1
$BOT2
$BOT3" REVIEWS_JSON='[]'
expect "requested bots mean bots-reviewing" state:bots-reviewing "$(decide_state)"
# -- a bot that never reviewed keeps the round open ---------------------------
# With a live request that is the bots' ball; with NO request outstanding it
# is the agent's, because nothing is coming until somebody asks.
REQUESTED="$BOT3" REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)")"
expect "a missing bot WITH a live request is bots-reviewing" state:bots-reviewing "$(decide_state)"
REQUESTED=""
expect "...but with nobody asked it is the agent's ball" state:addressing "$(decide_state)"
expect "...and the blocker names the stall" blocker:unrequested "$(blockers)"
# -- a comment is a non-verdict, agreement body or not: the author escalates --
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" COMMENTED head1 "✅ **Reviewed — I agree with everything.**" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "comment-only agreement still parks on the author" state:addressing "$(decide_state)"
# ...and the author's escalation — requesting the human — flips it
REQUESTED="$HUMAN"
expect "author escalation flips to needs-human" state:needs-human "$(decide_state)"
REQUESTED=""
# -- three formal approvals need no author judgment ---------------------------
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "three formal approvals reach needs-human" state:needs-human "$(decide_state)"
# -- a comment WITHOUT a verdict parks the PR on the agent --------------------
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" COMMENTED head1 "🔧 Reviewed — I agree with most; feedback below." t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "comment without verdict is addressing" state:addressing "$(decide_state)"
# -- changes requested blocks, at any head ------------------------------------
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" CHANGES_REQUESTED old1 "blockers below" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "changes-requested blocks even from an old head" state:addressing "$(decide_state)"
# -- a stale approval must not promote unreviewed code ------------------------
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED old1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "stale approval is addressing (agent owes re-request)" state:addressing "$(decide_state)"
# -- a re-requested bot reopens the round even with an old approval on file ---
REQUESTED="$BOT1"
expect "re-requested bot means bots-reviewing" state:bots-reviewing "$(decide_state)"
REQUESTED=""
# -- only the LATEST review per bot counts ------------------------------------
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" CHANGES_REQUESTED head1 "blockers" t1)" \
"$(rev "$BOT1" APPROVED head1 "" t2)" \
"$(rev "$BOT2" APPROVED head1 "" t3)" \
"$(rev "$BOT3" APPROVED head1 "" t4)")"
expect "later approval supersedes earlier block" state:needs-human "$(decide_state)"
# -- an explicit human request outranks the bot rounds ------------------------
REQUESTED="$HUMAN" REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" COMMENTED head1 "feedback, no verdict" t1)")"
expect "human requested outranks bots" state:needs-human "$(decide_state)"
REQUESTED=""
# -- human CHANGES_REQUESTED puts the ball back on the agent ------------------
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)" \
"$(rev "$HUMAN" CHANGES_REQUESTED head1 "not yet" t4)")"
expect "human block with bots approving is addressing" state:addressing "$(decide_state)"
# ...and re-requesting the human hands it back to them
REQUESTED="$HUMAN"
expect "re-requested human is needs-human again" state:needs-human "$(decide_state)"
REQUESTED=""
# -- an old human comment must not wedge the handoff (codex, #85 round 3) -----
REVIEWS_JSON="$(reviews \
"$(rev "$HUMAN" COMMENTED old1 "early thoughts" t0)" \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "old human comment + three approvals is needs-human" state:needs-human "$(decide_state)"
expect "old human comment still needs a fresh request" needed "$(human_request_needed && echo needed || echo not-needed)"
# ...a stale human APPROVAL likewise needs a re-request for the new head
REVIEWS_JSON="$(reviews \
"$(rev "$HUMAN" APPROVED old1 "" t0)" \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "stale human approval needs a fresh request" needed "$(human_request_needed && echo needed || echo not-needed)"
# ...a HEAD-CURRENT human approval needs nothing more
REVIEWS_JSON="$(reviews \
"$(rev "$HUMAN" APPROVED head1 "" t0)" \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
expect "head-current human approval needs no request" not-needed "$(human_request_needed && echo needed || echo not-needed)"
# ...and a live request suppresses re-requesting
REQUESTED="$HUMAN"
expect "live human request suppresses re-request" not-needed "$(human_request_needed && echo needed || echo not-needed)"
REQUESTED=""
# ---------------------------------------------------------------------------
# #136: state:needs-human must mean "a human could merge this RIGHT NOW".
# Both cases below were observed live in this repo on 2026-07-20, and both
# showed state:needs-human while being unmergeable in different ways.
# ---------------------------------------------------------------------------
ALL_APPROVE="$(reviews \
"$(rev "$BOT1" APPROVED head1 "" t1)" \
"$(rev "$BOT2" APPROVED head1 "" t2)" \
"$(rev "$BOT3" APPROVED head1 "" t3)")"
# -- flavour 1: not mergeable. The merge button is disabled, yet the board
# said "your turn" on #119/#120/#127 for hours. The branch fact now rides
# the blocker axis; the state says whose ball it is, which is the agent's.
DRAFT=false HEAD_SHA=head1 REQUESTED="" REVIEWS_JSON="$ALL_APPROVE" MERGEABLE=CONFLICTING CHECKS=SUCCESS
expect "a CONFLICTING PR is the agent's, not the human's" state:addressing "$(decide_state)"
expect "...and says WHY on the blocker axis" blocker:conflict "$(blockers)"
REQUESTED="$HUMAN"
expect "...even with the human explicitly requested" state:addressing "$(decide_state)"
# -- red CI is the same claim, but NOT the same work: a rebase does not fix a
# failing test. Collapsing both into one needs-rebase label told the agent
# to do the wrong thing, which is why the axis split exists.
REQUESTED="" MERGEABLE=MERGEABLE CHECKS=FAILURE
expect "a red PR is the agent's" state:addressing "$(decide_state)"
expect "...and is distinguishable from a conflict" blocker:ci-red "$(blockers)"
REQUESTED="$HUMAN"
expect "...and a human request does not override red CI" state:addressing "$(decide_state)"
# -- both at once. The single-axis design could not say this at all: one label
# had to win, and the loser silently vanished off the board.
REQUESTED="" MERGEABLE=CONFLICTING CHECKS=FAILURE
expect "a conflicted AND red PR reports both blockers" "blocker:conflict
blocker:ci-red" "$(blockers)"
expect "...and is still just the agent's ball" state:addressing "$(decide_state)"
# -- UNKNOWN is NOT unmergeable. GitHub reports it for ~a minute after every
# merge while it recomputes; treating it as broken would flap every open PR
# on each merge — worse than the bug being fixed.
REQUESTED="" MERGEABLE=UNKNOWN CHECKS=PENDING
expect "UNKNOWN mergeability blocks nothing" state:needs-human "$(decide_state)"
expect "...and raises no blocker" "" "$(blockers)"
# -- blocker:unrequested — the stalled round. Nobody owes an answer because
# nobody was ever asked, yet the board read "waiting on the bots" until
# `stale` noticed 48h later.
MERGEABLE=MERGEABLE CHECKS=SUCCESS REQUESTED="" REVIEWS_JSON='[]'
expect "ready, nobody asked, nothing reviewed raises unrequested" blocker:unrequested "$(blockers)"
# ...the partial case is equally stalled: one verdict in, nobody asked for the rest
REVIEWS_JSON="$(reviews "$(rev "$BOT1" APPROVED head1 "" t1)")"
expect "one bot in, none requested is still unrequested" blocker:unrequested "$(blockers)"
# ...a STALE round with nobody asked is the same debt, and arguably worse: the
# page carries approvals that no longer describe the tree. Guarding on
# MISSING alone let this one through with no blocker at all.
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED oldhead "" t1)" \
"$(rev "$BOT2" APPROVED oldhead "" t2)" \
"$(rev "$BOT3" APPROVED oldhead "" t3)")"
expect "a stale round with nobody asked is unrequested too" blocker:unrequested "$(blockers)"
expect "...and is still the agent's ball" state:addressing "$(decide_state)"
# ...but a live request means an answer IS coming
REVIEWS_JSON="$(reviews "$(rev "$BOT1" APPROVED head1 "" t1)")"
REQUESTED="$BOT2"
expect "a live bot request is not a stalled round" "" "$(blockers)"
# ...and a draft is exempt: the bots ignore drafts by design
DRAFT=true REQUESTED="" REVIEWS_JSON='[]'
expect "a draft with nobody asked is not stalled" "" "$(blockers)"
# ...as is an explicit human request — claiming a PR early is deliberate
DRAFT=false REQUESTED="$HUMAN"
expect "an early human claim is not a stalled round" "" "$(blockers)"
REQUESTED="" REVIEWS_JSON="$ALL_APPROVE" MERGEABLE=MERGEABLE CHECKS=SUCCESS
# -- flavour 2 (the dangerous one): mergeable, green, human requested, and
# NOBODY has reviewed this head. Observed on #119 after a rebase: every
# signal read "merge me" and nothing on the page contradicted it.
MERGEABLE=MERGEABLE CHECKS=SUCCESS REQUESTED="$HUMAN"
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED oldhead "" t1)" \
"$(rev "$BOT2" APPROVED oldhead "" t2)" \
"$(rev "$BOT3" APPROVED oldhead "" t3)")"
expect "stale approvals outrank the human request (nobody reviewed this tree)" state:addressing "$(decide_state)"
# -- ...and a round that is BOTH unfinished and staled is still the agent's.
# Deciding inside the bot loop made this depend on BOTS order: the MISSING
# returned before any later bot's STALE was read, so the mixed round came
# out needs-human with nothing bound to the head. Pinned at both ends of
# the array, because the whole failure was one of ordering.
MERGEABLE=MERGEABLE CHECKS=SUCCESS REQUESTED="$HUMAN"
REVIEWS_JSON="$(reviews \
"$(rev "$BOT1" APPROVED oldhead "" t1)" \
"$(rev "$BOT2" APPROVED oldhead "" t2)")"
expect "stale approvals + a bot yet to review is addressing, not needs-human" \
state:addressing "$(decide_state)"
REVIEWS_JSON="$(reviews "$(rev "$BOT3" APPROVED oldhead "" t3)")"
expect "...and the same when the stale verdict is the LAST bot in BOTS" \
state:addressing "$(decide_state)"
# -- but an UNFINISHED round still yields to an explicit human request: a
# maintainer pulling a PR to themselves early is deliberate, and was the
# original precedence. MISSING differs from STALE — nobody has reviewed
# YET, versus everyone reviewed something else.
REVIEWS_JSON="$(reviews "$(rev "$BOT1" APPROVED head1 "" t1)")"
expect "an unfinished round still yields to an explicit human request" state:needs-human "$(decide_state)"
REQUESTED=""
expect "...and without that request the agent owes the ask" state:addressing "$(decide_state)"
# ---------------------------------------------------------------------------
# checks_state: the rollup classifier. It lived inline in main() for the first
# round of this PR, which is why nothing here caught it calling ERROR,
# CANCELLED and STALE green. Extracted so the enum can be pinned down.
# ---------------------------------------------------------------------------
rollup() { jq -n --argjson c "$1" '{statusCheckRollup: $c}'; }
run_() { jq -n --arg n "$1" --arg o "$2" --arg t "${3:-2026-07-20T15:00:00Z}" \
'{__typename:"CheckRun", workflowName:"ci", name:$n, conclusion:$o, completedAt:$t}'; }
ctx_() { jq -n --arg n "$1" --arg s "$2" --arg t "${3:-2026-07-20T15:00:00Z}" \
'{__typename:"StatusContext", context:$n, state:$s, createdAt:$t}'; }
expect "no checks at all is NONE" NONE "$(rollup '[]' | checks_state)"
# A failed fetch leaves no rollup KEY; a PR with no checks leaves an empty
# ARRAY. Collapsing the two let an API hiccup read as "nothing is failing" —
# the same unknown-certified-as-green shape as #136, in the one place that
# fix did not look. The caller skips an UNREADABLE PR rather than relabelling.
expect "a failed read is UNREADABLE, not NONE" UNREADABLE "$(echo '{}' | checks_state)"
expect "...and a real empty rollup is still NONE" NONE \
"$(echo '{"mergeable":"MERGEABLE","statusCheckRollup":[]}' | checks_state)"
expect "all green is SUCCESS" SUCCESS \
"$(rollup "[$(run_ a SUCCESS),$(run_ b SUCCESS)]" | checks_state)"
expect "a queued run is PENDING" PENDING \
"$(rollup "[$(run_ a SUCCESS),$(run_ b QUEUED)]" | checks_state)"
expect "a plain failure is FAILURE" FAILURE \
"$(rollup "[$(run_ a SUCCESS),$(run_ b FAILURE)]" | checks_state)"
# -- the round-1 gap: outcomes that are neither success nor pending, and that
# leave a required check unsatisfied. All three reached the old `else`.
expect "a commit status ERROR blocks" FAILURE \
"$(rollup "[$(run_ a SUCCESS),$(ctx_ lint ERROR)]" | checks_state)"
expect "a CANCELLED run blocks" FAILURE \
"$(rollup "[$(run_ a SUCCESS),$(run_ b CANCELLED)]" | checks_state)"
expect "a STALE run blocks" FAILURE \
"$(rollup "[$(run_ a SUCCESS),$(run_ b STALE)]" | checks_state)"
expect "an outcome the enum does not know blocks, it does not pass" FAILURE \
"$(rollup "[$(run_ a SUCCESS),$(run_ b SOME_FUTURE_STATE)]" | checks_state)"
# -- NEUTRAL and SKIPPED satisfy branch protection; path-filtered jobs skip
# constantly, and calling that red would park every PR on the agent.
expect "NEUTRAL and SKIPPED are not failures" SUCCESS \
"$(rollup "[$(run_ a SUCCESS),$(run_ b NEUTRAL),$(run_ c SKIPPED)]" | checks_state)"
# -- latest-wins. The rollup keeps superseded runs, so this PR's own tip
# carried a CANCELLED `scope` beside the SUCCESS `scope` that replaced it.
# Without collapsing, making CANCELLED block would strand it forever.
expect "a re-run supersedes the cancelled original" SUCCESS \
"$(rollup "[$(run_ scope CANCELLED 2026-07-20T15:19:39Z),\
$(run_ scope SUCCESS 2026-07-20T15:19:45Z)]" | checks_state)"
expect "...and the reverse order is not a re-run passing, it is one failing" FAILURE \
"$(rollup "[$(run_ scope SUCCESS 2026-07-20T15:19:39Z),\
$(run_ scope CANCELLED 2026-07-20T15:19:45Z)]" | checks_state)"
# same job name in a different workflow is a different context, not a re-run
expect "same name in another workflow does not supersede" FAILURE \
"$(rollup "[$(jq -n '{__typename:"CheckRun",workflowName:"labels",name:"scope",conclusion:"FAILURE",completedAt:"2026-07-20T15:00:00Z"}'),\
$(run_ scope SUCCESS 2026-07-20T15:19:45Z)]" | checks_state)"
# -- a run still IN FLIGHT. `run_()` cannot express this: it always carries a
# real completedAt, which is exactly why the supersede rule shipped dating
# runs by completion and nothing caught it. Both spellings of "no
# completion" are pinned, because `gh` emits the zero sentinel (a string,
# which `//` does not fall through) while the API emits null.
inflight_() { jq -n --arg n "$1" --arg t "$2" --arg c "${3:-0001-01-01T00:00:00Z}" \
'{__typename:"CheckRun", workflowName:"ci", name:$n, status:"IN_PROGRESS",
conclusion:"", startedAt:$t, completedAt:(if $c == "null" then null else $c end)}'; }
expect "a re-run in flight beats the success it superseded (zero sentinel)" PENDING \
"$(rollup "[$(run_ build SUCCESS 2026-07-20T15:00:00Z),\
$(inflight_ build 2026-07-20T15:10:00Z)]" | checks_state)"
expect "...and the same when the absent completion is null" PENDING \
"$(rollup "[$(run_ build SUCCESS 2026-07-20T15:00:00Z),\
$(inflight_ build 2026-07-20T15:10:00Z null)]" | checks_state)"
expect "a replacement in flight for a CANCELLED run is pending, not failed" PENDING \
"$(rollup "[$(run_ build CANCELLED 2026-07-20T15:00:00Z),\
$(inflight_ build 2026-07-20T15:10:00Z)]" | checks_state)"
# an entry carrying no usable timestamp is treated as newest, not oldest —
# ambiguity resolves toward "not settled" rather than toward a stale success.
# Guarded by the sort tiebreak rather than the dating expression: reverting
# only `at:` leaves this passing, so the two changes are separately pinned.
expect "an undateable in-flight run is not discarded for a stale success" PENDING \
"$(rollup "[$(run_ build SUCCESS 2026-07-20T15:00:00Z),\
$(jq -n '{__typename:"CheckRun",workflowName:"ci",name:"build",conclusion:"",startedAt:null,completedAt:null}')]" \
| checks_state)"
# ...and the reverse direction, which stops "in flight sorts last" being
# widened into "in flight always wins": a run that FINISHED after an earlier
# in-flight entry is the newer word, and the context is settled.
expect "a finished re-run supersedes an earlier in-flight run" SUCCESS \
"$(rollup "[$(inflight_ build 2026-07-20T15:19:00Z),\
$(run_ build SUCCESS 2026-07-20T15:19:45Z)]" | checks_state)"
# -- the wind-down window. A predecessor cancelled by the concurrency group
# does not stop the instant its replacement starts, so its completion
# routinely lands AFTER the successor's start — on box's aa5a6ba the
# replacement started 15:19:38 and the run it cancelled finished 15:19:51.
# Dating by "newest stamp of any kind" compares the dead run's completion
# against the live run's start, which is not an ordering on runs, and the
# predecessor wins. Every fixture above spaces completion before start, so
# none of them can see it. run_() cannot express the overlap either — it
# carries no startedAt — hence the explicit payloads.
overlap_() { jq -n --arg n "$1" --arg o "$2" --arg s "$3" --arg c "$4" \
'{__typename:"CheckRun", workflowName:"ci", name:$n, conclusion:$o,
startedAt:$s, completedAt:$c}'; }
expect "a predecessor finishing after its replacement started is still older (CANCELLED)" PENDING \
"$(rollup "[$(overlap_ scope CANCELLED 2026-07-20T15:19:00Z 2026-07-20T15:19:51Z),\
$(inflight_ scope 2026-07-20T15:19:38Z)]" | checks_state)"
expect "...and the same when it finished green — mid-flight is not mergeable" PENDING \
"$(rollup "[$(overlap_ build SUCCESS 2026-07-20T15:19:00Z 2026-07-20T15:19:51Z),\
$(inflight_ build 2026-07-20T15:19:38Z)]" | checks_state)"
# -- the classifier feeds the state machine: a cancelled required check must
# take the PR off the human's plate, which is the whole point of #136.
DRAFT=false HEAD_SHA=head1 REQUESTED="$HUMAN" REVIEWS_JSON="$ALL_APPROVE" MERGEABLE=MERGEABLE
CHECKS="$(rollup "[$(run_ a SUCCESS),$(run_ b CANCELLED)]" | checks_state)"
expect "a cancelled check reaches decide_state as the agent's ball" state:addressing "$(decide_state)"
expect "...via blocker:ci-red, not a conflict" blocker:ci-red "$(blockers)"
# -- the happy path survives all of the above.
REVIEWS_JSON="$ALL_APPROVE" MERGEABLE=MERGEABLE CHECKS=SUCCESS REQUESTED=""
expect "mergeable + green + three head-current approvals is needs-human" state:needs-human "$(decide_state)"
# -- and a draft outranks everything, including a conflict.
DRAFT=true MERGEABLE=CONFLICTING
expect "a draft is building even when conflicted" state:building "$(decide_state)"
DRAFT=false MERGEABLE=MERGEABLE CHECKS=SUCCESS REQUESTED="" REVIEWS_JSON='[]'
# ---------------------------------------------------------------------------
# reconcile_pr's cold-start path. Everything above tests pure functions, which
# is exactly why a per-PR `return` in the label pre-flight got through review:
# the fixtures could not reach it. A missing state:* label must skip the label
# EDIT only — merge-next clearing and the stale sweep are independent of the
# taxonomy, and stranding them reintroduced the false-invitation bug (a
# `merge-next` claim surviving on a PR the board had moved to the agent).
# ---------------------------------------------------------------------------
reconcile_probe() { # $1 = REPO_LABELS content → the log lines reconcile_pr emits
(
REPO_LABELS="$1" REPO=owner/repo NOW="$(date +%s)"
LABELS="merge-next" # the PR carries a queue claim
DRAFT=false HEAD_SHA=head1 REQUESTED="" REVIEWS_JSON='[]'
MERGEABLE=MERGEABLE CHECKS=SUCCESS
PR_JSON='{"created_at":"2020-01-01T00:00:00Z"}'
run() { :; } # swallow mutations
gh() { :; } # no network
reconcile_pr 777 2>&1
)
}
cold="$(reconcile_probe "merge-next")" # state:* labels absent entirely
expect "a cold-start repo still clears merge-next" \
yes "$(grep -q 'cleared merge-next' <<<"$cold" && echo yes || echo no)"
expect "...and still runs the stale sweep" \
yes "$(grep -q 'stale (' <<<"$cold" && echo yes || echo no)"
expect "...while warning that the state label is missing" \
yes "$(grep -q "state label 'state:addressing' does not exist" <<<"$cold" && echo yes || echo no)"
warm="$(reconcile_probe "$(printf 'state:addressing\nmerge-next\nstale\nblocker:unrequested')")"
expect "a bootstrapped repo converges the state as well" \
yes "$(grep -q 'state -> state:addressing' <<<"$warm" && echo yes || echo no)"
printf 'labels-reconcile tests: %d passed, %d failed\n' "$pass" "$fail"
[ "$fail" -eq 0 ]

View file

@ -1,22 +1,10 @@
#!/usr/bin/env bash #!/usr/bin/env bash
# The release flow (#83), proven offline. Run: bash test/release.sh # Box-specific release-channel coverage. Shared release/guard machinery lives
# # in heavy-duty/ceremony and is tested there; this file drives real install.sh.
# Three surfaces: the changelog-section extraction release.yml publishes
# (.github/scripts/release-notes.sh, driven against fixtures AND the real
# CHANGELOG.md so the header format cannot drift under it), the
# latest-release tag resolution install.sh defaults to (the extracted
# function, driven against a shim curl serving canned redirects), and the
# three install channels — REAL install.sh runs against throwaway roots,
# with the shim curl standing in for GitHub. Nothing here touches the
# network; the same discipline as test/cli.sh. Deliberately no `set -e` —
# the harness asserts on failing commands.
set -u set -u
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
PASS=0 FAIL=0 PASS=0 FAIL=0
# check <desc> <want_exit> <want_substr> <cmd...>
# Runs cmd, asserts exit code and (if non-empty) that combined output
# contains want_substr.
check() { check() {
local desc="$1" want="$2" substr="$3"; shift 3 local desc="$1" want="$2" substr="$3"; shift 3
local out rc local out rc
@ -34,741 +22,17 @@ check() {
echo "ok: $desc"; PASS=$((PASS + 1)) echo "ok: $desc"; PASS=$((PASS + 1))
} }
NOTES="$ROOT/.github/scripts/release-notes.sh"
WORK="$(mktemp -d)" WORK="$(mktemp -d)"
# ---------------------------------------------------------------------------
# release-notes.sh — the extraction, against a fixture changelog that carries
# every boundary: an Unreleased section that must never leak into a release,
# two adjacent versions, a version that prefixes another (0.7.0 vs
# 0.7.0-rc1), and a stamped-but-empty section that must refuse.
# ---------------------------------------------------------------------------
check "release-notes: runnable bash" 0 "" bash -n "$NOTES"
FIX="$WORK/CHANGELOG.md"
cat > "$FIX" <<'EOF'
# Changelog
Intro prose that belongs to no section.
## Unreleased
- **Not yet released** — must never appear in a release body.
## 0.7.0 — 2026-07-20
### Added
- **The seven-oh entry** — prose for 0.7.0, and only 0.7.0.
## 0.7.0-rc1 — 2026-07-19
- **The rc entry** — must not ride along with 0.7.0.
## 0.6.0 — 2026-07-18
- **The six-oh entry** — the previous release's prose.
## 0.5.0 — 2026-07-15
EOF
check "extract: prints the asked-for version's prose" 0 "The seven-oh entry" bash "$NOTES" 0.7.0 "$FIX"
check "extract: keeps the section's own subheaders" 0 "### Added" bash "$NOTES" 0.7.0 "$FIX"
# shellcheck disable=SC2016 # $1/$2 expand in the child shell, by design
check "extract: stops at the NEXT section" 1 "" bash -c 'bash "$1" 0.7.0 "$2" | grep -q "rc entry"' _ "$NOTES" "$FIX"
# shellcheck disable=SC2016 # $1/$2 expand in the child shell, by design
check "extract: never leaks Unreleased into a release" 1 "" bash -c 'bash "$1" 0.7.0 "$2" | grep -q "Not yet released"' _ "$NOTES" "$FIX"
# shellcheck disable=SC2016 # $1/$2 expand in the child shell, by design
check "extract: never prints the header itself" 1 "" bash -c 'bash "$1" 0.7.0 "$2" | grep -q "^## "' _ "$NOTES" "$FIX"
check "extract: the version is matched WHOLE (rc1 is its own section)" \
0 "The rc entry" bash "$NOTES" 0.7.0-rc1 "$FIX"
check "extract: an adjacent older version still resolves" 0 "six-oh" bash "$NOTES" 0.6.0 "$FIX"
check "extract: a missing version refuses by name" 1 "no section for '9.9.9'" bash "$NOTES" 9.9.9 "$FIX"
check "extract: ...and names the ritual that was skipped" 1 "#83" bash "$NOTES" 9.9.9 "$FIX"
check "extract: a stamped-but-EMPTY section refuses" 1 "no section for '0.5.0'" bash "$NOTES" 0.5.0 "$FIX"
check "extract: no version argument is a usage error" 2 "usage:" bash "$NOTES"
check "extract: a missing changelog refuses by path" 1 "no such file" bash "$NOTES" 1.0.0 "$WORK/nope.md"
# The REAL changelog: released sections must keep extracting, or release.yml
# breaks the day it runs — this is the guard against header-format drift.
check "extract: the real 0.6.0 section extracts" 0 "restricted tier" bash "$NOTES" 0.6.0 "$ROOT/CHANGELOG.md"
check "extract: the real 0.5.0 section extracts" 0 "" bash "$NOTES" 0.5.0 "$ROOT/CHANGELOG.md"
# ---------------------------------------------------------------------------
# release.yml — a daemon-free run cannot push a tag, so the wiring is
# grepped, fail-closed (the house discipline): the VERSION assertion, the
# shared extraction script, and that the tag is verified before creation.
# ---------------------------------------------------------------------------
RY="$ROOT/.github/workflows/release.yml"
check "release.yml: exists" 0 "" test -f "$RY"
# shellcheck disable=SC2016 # the $-string is a literal in the target file
check "release.yml: asserts tag == VERSION before creating anything" 0 "" \
grep -qF 'GITHUB_REF_NAME" != "$ver"' "$RY"
check "release.yml: the mismatch creates NOTHING (exit 1)" 0 "" \
grep -qF 'creating nothing' "$RY"
check "release.yml: the body comes from the shared extraction script" 0 "" \
grep -qF '.github/scripts/release-notes.sh' "$RY"
check "release.yml: the release is bound to the pushed tag (--verify-tag)" 0 "" \
grep -qF -- '--verify-tag' "$RY"
# ---------------------------------------------------------------------------
# release.yml, the merge door (#96) — merging the release-labeled PR IS the
# release. Same daemon-free discipline: the gate, the four asserts, and the
# same-job tag+publish are grep-pinned, fail-closed.
# ---------------------------------------------------------------------------
check "release.yml: the tag-push trigger is still present (manual fallback)" 0 "" \
grep -qF 'tags: ["**"]' "$RY"
# The merge door rides pushes to MAIN, not pull_request events: a fork PR
# run gets a read-only GITHUB_TOKEN (permissions: cannot raise it), and
# every ceremony PR this org merges is cross-repo from the bot fork — the
# tag create would 403 after green asserts (#97 round 1). The label — the
# operator's intent — is read via the API off the merge commit's PR.
check "release.yml: the merge door rides pushes to main (fork-token-proof)" 0 "" \
grep -qF 'branches: [main]' "$RY"
check "release.yml: the doors split on the ref — tags to the tag door..." 0 "" \
grep -qF "startsWith(github.ref, 'refs/tags/')" "$RY"
check "release.yml: ...main to the merge door" 0 "" \
grep -qF "github.ref == 'refs/heads/main'" "$RY"
# shellcheck disable=SC2016 # the $-string is a literal in the target file
check "release.yml: the release label is read via the API off the merge commit" 0 "" \
grep -qF 'commits/$GITHUB_SHA/pulls' "$RY"
check "release.yml: a transition without a labeled PR refuses" 0 "" \
grep -qF "no merged, release-labeled PR is behind this commit" "$RY"
check "release.yml: assert — VERSION at the merge commit is non--dev" 0 "" \
grep -qF '*-dev)' "$RY"
check "release.yml: assert — VERSION changed IN THIS PR (first parent vs merge)" 0 "" \
grep -qF 'git show HEAD^1:VERSION' "$RY"
check "release.yml: assert — no existing tag for the version" 0 "" \
grep -qF 'git/ref/tags/' "$RY"
check "release.yml: assert — no existing release for the version" 0 "" \
grep -qF 'gh release view' "$RY"
check "release.yml: BOTH doors extract notes via the shared script" 0 "2" \
grep -cF 'bash .github/scripts/release-notes.sh' "$RY"
check "release.yml: every failing assert creates NOTHING (both doors)" 0 "5" \
grep -cF 'creating nothing' "$RY"
check "release.yml: the merge door creates the tag ref via the API..." 0 "" \
grep -qF 'ref=refs/tags/' "$RY"
# shellcheck disable=SC2016 # the $-string is a literal in the target file
check "release.yml: ...at the MERGE commit" 0 "" \
grep -qF 'sha=$MERGE_SHA' "$RY"
check "release.yml: BOTH doors publish bound to an existing tag (--verify-tag)" 0 "2" \
grep -cF -- '--verify-tag' "$RY"
check "release.yml: tag + publish share one job (the anti-recursion shape)" 0 "" \
grep -qF 'anti-recursion' "$RY"
# The decide step tells the label's two meanings apart (LABELS.md gives
# `release` to release-flow WORK as well as to the ceremony PR — the PR
# that added the merge door included): work under the label no-ops GREEN —
# in the -dev steady state and in the post-release window (bare, unchanged,
# already released) — while every half-ceremony refuses. Pin each verdict
# and the gating output.
check "release.yml: decide — dev-tree work no-ops green (not a red run per infra PR)" 0 "" \
grep -qF "release-flow work under the release label, not a ceremony" "$RY"
check "release.yml: decide — a -dev endstate is always work (the bump PR no-ops green)" 0 "" \
grep -qF "a dev tree is by definition not a release" "$RY"
check "release.yml: decide — post-release-window work no-ops green" 0 "" \
grep -qF "release-flow work merged in the post-release window" "$RY"
check "release.yml: decide — bare, unchanged, never released refuses to guess" 0 "" \
grep -qF "Refusing to guess" "$RY"
check "release.yml: decide gates every later merge-door step on ceremony=yes" 0 "4" \
grep -cF "if: steps.decide.outputs.ceremony == 'yes'" "$RY"
# The release re-arms main itself: the post-release -dev bump is arithmetic,
# not judgment, so it rides the same job — direct push, PR fallback.
check "release.yml: the release bumps main to the next -dev itself" 0 "" \
grep -qF "bump main to the next -dev" "$RY"
check "release.yml: ...with a PR fallback when the direct push is refused" 0 "" \
grep -qF "opening the bump PR instead" "$RY"
# ---------------------------------------------------------------------------
# changelog-armed.sh (#108) — the changelog has a heading for the NEXT entry.
#
# The drift this catches produces no conflict and no error: the ceremony
# stamps '## Unreleased' away, and a PR authored before the release merges its
# entry cleanly into the section that just shipped. box has no top-section
# guard at all today — the two checks above pin only that the 0.6.0 and 0.5.0
# sections still extract, which a disarmed main passes happily.
#
# BOTH states are constructed as real trees and the real script is run against
# them, because the failure mode of the naive fix is precisely a state
# mismatch: an unconditional '## Unreleased' requirement is green on main and
# false on the ceremony PR's own tree, which is why rig#44 and
# heavy-duty/cast#108 both had to revert one. A test that only drives the
# -dev state would have shipped that bug again.
# ---------------------------------------------------------------------------
ARMED="$ROOT/.github/scripts/changelog-armed.sh"
check "changelog-armed: runnable bash" 0 "" bash -n "$ARMED"
# tree <dir> <version> <changelog-body...> — a two-file tree to run against
tree() {
local d="$WORK/$1" v="$2"; shift 2
mkdir -p "$d"
printf '%s\n' "$v" > "$d/VERSION"
{ echo "# Changelog"; echo; printf '%s\n' "$@"; } > "$d/CHANGELOG.md"
echo "$d"
}
armed() { bash "$ARMED" "$1/CHANGELOG.md" "$1/VERSION"; }
# --- the -dev steady state: armed is the only legal shape ------------------
T="$(tree dev-armed 0.7.1-dev '## Unreleased' '' '- **A pending entry**' '' '## 0.7.0 — 2026-07-19' '' '- **Shipped**')"
check "armed: a -dev tree with '## Unreleased' on top passes" 0 "agrees" armed "$T"
T="$(tree dev-disarmed 0.7.1-dev '## 0.7.0 — 2026-07-19' '' '- **Shipped**')"
check "armed: a -dev tree WITHOUT it fails — the #108 drift, caught" 1 "MUST carry" armed "$T"
check "armed: ...and the failure says how to fix it (re-arm)" 1 "re-arm" armed "$T"
check "armed: ...naming the issue and its origin" 1 "heavy-duty/rig#66" armed "$T"
# --- the ceremony PR: bare VERSION, BOTH arrangements legal ----------------
# This is the pair that the reverted guards got wrong. Neither may fail, or
# the release PR cannot go green and the ceremony is unshippable.
T="$(tree rel-stamped 0.7.1 '## 0.7.1 — 2026-07-19' '' '- **This release**')"
check "armed: a bare VERSION with its OWN stamped section on top passes" 0 "agrees" armed "$T"
T="$(tree rel-rearmed 0.7.1 '## Unreleased' '' '## 0.7.1 — 2026-07-19' '' '- **This release**')"
check "armed: ...and so does the RE-ARMED ceremony tree (the shape #108 asks for)" \
0 "agrees" armed "$T"
# The one bare-VERSION arrangement that is wrong: a stamp naming another
# version. release.yml would publish a body that is not this release's.
T="$(tree rel-wrong 0.7.1 '## 0.7.0 — 2026-07-19' '' '- **Some other release**')"
check "armed: a bare VERSION under someone ELSE's stamped section fails" 1 "wrong number" armed "$T"
# --- the HALF-ceremony: the gap the two bare-VERSION clauses leave ---------
# VERSION bumped to the release, '## Unreleased' still populated on top, and
# the section for that version never stamped at all. The wrong-number test
# above is false on its FIRST clause here and short-circuits, so before
# heavy-duty/rig#67's rule this tree passed the guard and was refused instead
# by release.yml — at publish time, after the merge, on main, with the release
# already half-shipped. Caught here one step earlier, by running the same
# extraction release.yml runs.
T="$(tree rel-half 0.8.0 '## Unreleased' '' '- **A pending entry**' '' '## 0.7.0 — 2026-07-19' '' '- **Shipped**')"
check "armed: a bare VERSION whose section was never stamped fails (half-ceremony)" \
1 "no non-empty section" armed "$T"
check "armed: ...and names the stamp as MISSING, not misnumbered" \
1 "MISSING, not misnumbered" armed "$T"
# The wording is the whole point of the separate branch: an operator sent to
# fix a version number that is already correct will not find the real problem.
not_wrong_number() { ! armed "$1" 2>&1 | grep -qF 'wrong number'; }
check "armed: ...and not as the wrong-number case, which has a different fix" \
0 "" not_wrong_number "$T"
# A section that exists but carries no prose is the same failure: release.yml
# would publish an empty body, which is what release-notes.sh already refuses.
T="$(tree rel-empty 0.7.1 '## 0.7.1 — 2026-07-19' '' '## 0.7.0 — 2026-07-19' '' '- **Shipped**')"
check "armed: a bare VERSION whose section is stamped but EMPTY fails" \
1 "no non-empty section" armed "$T"
# --- degenerate trees refuse rather than pass by accident ------------------
T="$(tree no-sections 0.7.1-dev 'Prose and no headings at all.')"
check "armed: a changelog with no '## ' section at all fails" 1 "no '## ' section at all" armed "$T"
check "armed: a missing changelog refuses by path" 1 "no such file" \
bash "$ARMED" "$WORK/nope.md" "$ROOT/VERSION"
check "armed: a missing VERSION refuses by path" 1 "no such file" \
bash "$ARMED" "$ROOT/CHANGELOG.md" "$WORK/nope-version"
mkdir -p "$WORK/empty-ver"; : > "$WORK/empty-ver/VERSION"
check "armed: an empty VERSION refuses" 1 "is empty" \
bash "$ARMED" "$ROOT/CHANGELOG.md" "$WORK/empty-ver/VERSION"
# --- and the tree under test, which is the assertion that actually fires ---
check "armed: THIS tree's VERSION and CHANGELOG.md agree" 0 "agrees" \
bash "$ARMED" "$ROOT/CHANGELOG.md" "$ROOT/VERSION"
# The guard is only a guard if CI runs it, and the ceremony is only re-armed
# if the ceremony step says so. Fail-closed pins on both, since a guard nobody
# invokes and a step nobody wrote are the two ways this reverts silently.
check "ci.yml: runs the changelog-armed guard" 0 "" \
grep -qF 'changelog-armed.sh' "$ROOT/.github/workflows/ci.yml"
check "CONTRIBUTING: the ceremony re-arms '## Unreleased' after stamping" 0 "" \
grep -qF 'Stamping is two edits, not one' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and names the guard that enforces it" 0 "" \
grep -qF 'changelog-armed.sh' "$ROOT/CONTRIBUTING.md"
# ---------------------------------------------------------------------------
# drill-recorded.sh — a RELEASE tree has a drill record at drills/<ver>.md.
#
# The gap this closes is not a drift or a race; it is a rule that was only
# ever a sentence. CONTRIBUTING.md has said since #96 that the release PR is
# where the full real-hardware drill hangs — and #95, #114 and #148 all
# shipped without one, because nothing but a reviewer's memory stood on it.
#
# Both states are constructed as real trees, same discipline as the armed
# block above, and for a sharper reason here: the -dev pass is not a
# convenience, it is what keeps the guard installable. A version of this rule
# that fired on every tree would be red on every ordinary PR in the repo and
# would be switched off inside a day.
#
# Every fixture carries its OWN VERSION and its OWN drills/ dir. Reaching for
# $ROOT/VERSION instead is exactly the coupling #146 had to fix: the suite
# then passes or fails on whichever state the repo happens to be in, so it
# goes red on the ceremony tree — the one tree where the release suite most
# needs to be trustworthy.
#
# Records are now ONE FILE PER VERSION, which is why this block is shorter
# than the one it replaces. The heading-parsing cases are gone because there
# is no heading to parse: em-dash fields, the optional ' — DATE' tail, and
# "an empty section must not borrow a neighbour's prose" were all artifacts
# of records sharing drill/RUNS.md. Deleting a test is only safe when the
# failure it described became unrepresentable, and that is the case here —
# except for the whitespace rule, which was never about headings and is
# pinned harder below.
# ---------------------------------------------------------------------------
DRILLED="$ROOT/.github/scripts/drill-recorded.sh"
check "drill-recorded: runnable bash" 0 "" bash -n "$DRILLED"
check "drill-recorded: executable" 0 "" test -x "$DRILLED"
# dtree <dir> <version> [<record-version> <record-body...>] — a self-contained
# tree: its own VERSION, and its own drills/ dir created only when asked for.
# With 2 args there is NO drills/ dir at all, which is a case in its own right.
dtree() {
local d="$WORK/$1" v="$2"; shift 2
mkdir -p "$d"
printf '%s\n' "$v" > "$d/VERSION"
if [ "$#" -gt 0 ]; then
local rec="$1"; shift
mkdir -p "$d/drills"
printf '%s\n' "$@" > "$d/drills/$rec.md"
fi
echo "$d"
}
drilled() { bash "$DRILLED" "$1/drills" "$1/VERSION"; }
# --- the -dev steady state: nothing to assert ------------------------------
# No record at all, and that must PASS. This is the case that makes the guard
# survivable on an ordinary PR.
T="$(dtree drill-dev 0.8.1-dev)"
check "drill-recorded: a -dev tree with NO drills dir at all passes" 0 "nothing to assert" drilled "$T"
check "drill-recorded: ...and says why it declined to judge" 0 "development tree" drilled "$T"
# --- the ceremony tree: a record is required and must not be blank ---------
T="$(dtree drill-ok 0.9.0 0.9.0 '# Release drill — 0.9.0' '' '- 47/47 on real hardware')"
check "drill-recorded: a bare VERSION with a non-empty record for it passes" \
0 "has a drill record" drilled "$T"
# No drills/ dir AT ALL is the commonest way to fail this: the release branch
# was cut and nobody ran anything. It must fail loudly, not error out on a
# missing directory in some way that reads like a broken guard.
T="$(dtree drill-nodir 0.9.0)"
check "drill-recorded: a bare VERSION with NO drills dir fails" 1 "no drill record" drilled "$T"
check "drill-recorded: ...and the failure names the version" 1 "VERSION is '0.9.0'" drilled "$T"
# The dir exists — some other release left its record here — but this version
# has none. A directory listing is not evidence about a particular version.
T="$(dtree drill-otherver 0.9.0 0.8.0 '# Release drill — 0.8.0' '' '- the previous release')"
check "drill-recorded: a drills dir with no file for THIS version fails" \
1 "no drill record" drilled "$T"
check "drill-recorded: ...and names the unblock — run the drill and record it" \
1 "RUN THE DRILL" drilled "$T"
check "drill-recorded: ...and names the path it wanted" 1 "drills/0.9.0.md" drilled "$T"
check "drill-recorded: ...and offers the recorded maintainer waiver as the other way out" \
1 "WAIVED" drilled "$T"
check "drill-recorded: ...and names the three releases that shipped through the gap" \
1 "#95, #114 and #148" drilled "$T"
# A file that exists and says nothing is the same failure as no file: the
# ceremony created the shape and never wrote the evidence. `touch` must not
# be able to satisfy a gate whose entire job is to demand evidence.
mkdir -p "$WORK/drill-emptyfile/drills"
printf '0.9.0\n' > "$WORK/drill-emptyfile/VERSION"
: > "$WORK/drill-emptyfile/drills/0.9.0.md"
check "drill-recorded: a record file that is present but EMPTY fails" \
1 "no drill record" drilled "$WORK/drill-emptyfile"
# ...and WHITESPACE is not evidence either. This is the ONE rule carried over
# from the heading-parsing guard, because it was never a heading problem. The
# first cut extracted with `sed '/./,$!d'`, where `.` matches a space — so a
# record whose body was one tab passed a guard that promised "at least one
# non-blank line". An evidence-free release for the price of an invisible
# character. All three reviewers on #149 found it independently, which is the
# level of scrutiny it deserved and not a level it should ever need again.
# Splitting the file per version removed the parsing; it did not remove this.
mkdir -p "$WORK/drill-blank/drills"
printf '0.9.0\n' > "$WORK/drill-blank/VERSION"
printf ' \n\t\n\n' > "$WORK/drill-blank/drills/0.9.0.md"
check "drill-recorded: a record of only spaces, tabs and newlines fails (#149)" \
1 "no drill record" drilled "$WORK/drill-blank"
# --- the version is matched WHOLE, both directions -------------------------
# Under the old scheme this took deliberate field-matching against a heading,
# and getting it wrong would have let a release-candidate drill stand in for
# the release it was a candidate for — the one thing an rc drill by
# definition did not measure. One file per version makes it free: these are
# simply different paths. Pinned anyway, in both directions, so that a future
# rewrite reaching for a prefix or glob match cannot quietly reintroduce it.
T="$(dtree drill-rc-only 0.9.0 0.9.0-rc1 '# Release drill — 0.9.0-rc1' '' '- the rc drill')"
check "drill-recorded: a 0.9.0-rc1.md record does NOT satisfy 0.9.0" 1 "no drill record" drilled "$T"
T="$(dtree drill-rel-only 0.9.0-rc1 0.9.0 '# Release drill — 0.9.0' '' '- the release drill')"
check "drill-recorded: ...and a 0.9.0.md record does NOT satisfy 0.9.0-rc1" 1 "no drill record" drilled "$T"
# --- degenerate trees refuse rather than pass by accident ------------------
# A guard that cannot read the version cannot know whether this tree is its
# business, and "could not tell" must never resolve to "allowed".
check "drill-recorded: a missing VERSION refuses by path" 1 "no such file" \
bash "$DRILLED" "$WORK/drill-ok/drills" "$WORK/nope-version"
mkdir -p "$WORK/drill-empty-ver"; : > "$WORK/drill-empty-ver/VERSION"
check "drill-recorded: an empty VERSION refuses" 1 "is empty" \
bash "$DRILLED" "$WORK/drill-ok/drills" "$WORK/drill-empty-ver/VERSION"
# The drills dir is only consulted once the tree is a release — a -dev tree
# must not be refused for a directory it has no business reading.
check "drill-recorded: a -dev tree does not even look for the drills dir" 0 "nothing to assert" \
bash "$DRILLED" "$WORK/nope-drills" "$WORK/drill-dev/VERSION"
# --- and the tree under test ----------------------------------------------
# The property is that the guard's VERDICT IS CORRECT FOR THIS TREE — not that
# it always passes. Those come apart on a ceremony tree, and demanding success
# is wrong there in a way that took a red release PR to notice.
#
# A -dev tree is vacuous, so it must pass. A ceremony tree passes only once a
# human has run the drill and written the record — which is the entire point of
# the gate. Asserting exit 0 unconditionally therefore made test/release.sh
# UN-GREENABLE on every release branch before its drill, and reported it as a
# `release-flow tests` failure rather than as the gate doing its job: the same
# noise-and-misattribution shape as #146, where a fixture read the repo's real
# VERSION and only misbehaved on the ceremony tree.
#
# So: assert the verdict that this tree's own state entails. Green in all three
# states — dev, ceremony-without-record, ceremony-with-record — and still red if
# the guard ever disagrees with the tree in front of it.
THIS_VER="$(tr -d '[:space:]' < "$ROOT/VERSION")"
case "$THIS_VER" in
*-dev)
check "drill-recorded: THIS tree is -dev, and the guard is vacuous on it" 0 "nothing to assert" \
bash "$DRILLED" "$ROOT/drills" "$ROOT/VERSION" ;;
*)
if [ -s "$ROOT/drills/$THIS_VER.md" ]; then
check "drill-recorded: THIS ceremony tree HAS its record, and the guard accepts it" 0 "" \
bash "$DRILLED" "$ROOT/drills" "$ROOT/VERSION"
else
check "drill-recorded: THIS ceremony tree has NO record yet, and the guard refuses it" 1 "no drill record" \
bash "$DRILLED" "$ROOT/drills" "$ROOT/VERSION"
fi ;;
esac
# drills/ is release evidence and drill/RUNS.md is the harness's own log. The
# rewrite is only coherent if both keep existing and the docs say which is
# which; a reader who appends to the wrong one gets a red gate and no clue.
check "drills/: the directory documents itself" 0 "" test -f "$ROOT/drills/README.md"
check "drills/: ...and is plain, not a dot-directory invisible to globs (#116)" 1 "" \
test -d "$ROOT/.drills"
check "drills/: ...and distinguishes itself from the harness log" 0 "" \
grep -qF 'drill/RUNS.md' "$ROOT/drills/README.md"
check "drills/: ...and its worked example uses a version that can never ship" 0 "" \
grep -qF '9.9.9' "$ROOT/drills/README.md"
check "drill/RUNS.md: the harness log is untouched and still present" 0 "" \
test -f "$ROOT/drill/RUNS.md"
# No real record may be invented to make the suite green. The repo is
# 0.8.1-dev; fabricating drills/0.8.1.md would defeat the whole gate.
check "drills/: no fabricated record for an unshipped version" 1 "" \
test -f "$ROOT/drills/0.8.1.md"
# The guard is only a guard if CI runs it, and only a rule if the document
# that used to carry the rule now points at it.
check "ci.yml: runs the drill-recorded guard" 0 "" \
grep -qF 'drill-recorded.sh' "$ROOT/.github/workflows/ci.yml"
check "CONTRIBUTING: names the guard that enforces the drill" 0 "" \
grep -qF 'drill-recorded.sh' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: documents the drill record's path" 0 "" \
grep -qF 'drills/X.Y.Z.md' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and distinguishes it from the harness's own log" 0 "" \
grep -qF "harness's own log" "$ROOT/CONTRIBUTING.md"
# The three drills are INDEPENDENT. An earlier draft of this section said the
# drill was "ONE orchestrated run over the whole stack", which over-constrains
# it into a fixed sequence the repos cannot satisfy. Pinning the corrected
# claim, and negatively pinning the fixed-order language, because "surely you
# drill rig before box" is exactly the simplification a future editor makes.
check "CONTRIBUTING: the three drills are independent, in any order" 0 "" \
grep -qF 'The three drills are INDEPENDENT' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and no fixed-order framing survives" 1 "" \
grep -qF 'ONE orchestrated run' "$ROOT/CONTRIBUTING.md"
# The load-bearing correction: box and rig are mutually recursive, so a
# "release A before you can drill B" rule is not merely bureaucratic, it is
# unsatisfiable in principle. What dissolves it is that every drill pins the
# same fixed candidate refs — static identifiers that exist as soon as the
# release branches do — turning a runtime cycle into two independent tests.
check "CONTRIBUTING: ...drilling candidate refs, not released artifacts" 0 "" \
grep -qF 'candidate refs, not released artifacts' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and the same fixed refs are what dissolve the recursion" 0 "" \
grep -qF 'pins the same fixed set of candidate refs' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and each repo asserts a different thing" 0 "" \
grep -qF 'isolation contract' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and a combination defect means patch, re-drill, re-record" 0 "" \
grep -qF 're-drill' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING: ...and the RIG_REF gap is stated as outstanding (#81)" 0 "" \
grep -qF 'RIG_REF' "$ROOT/CONTRIBUTING.md"
check "LABELS: documents blocker:drill-pending" 0 "" \
grep -qF 'blocker:drill-pending' "$ROOT/LABELS.md"
check "LABELS: ...and points at the per-version record, not the harness log" 0 "" \
grep -qF 'drills/X.Y.Z.md' "$ROOT/LABELS.md"
# ---------------------------------------------------------------------------
# changelog-monotonic.sh (#122) — no SHIPPED release heading may be DELETED.
#
# The complement of the guard above, and the reason it is a separate script:
# changelog-armed.sh asks about ONE tree ("does the top section agree with
# VERSION?"), which is exactly why it was green on #118's broken branch — the
# top section was still '## Unreleased'. "A heading disappeared" is not a
# property of a tree at all; it is a property of a DIFF. So these cases are
# driven against real, constructed GIT REPOS with a base commit and a branch
# commit, not the two-file trees above — a fixture without history cannot
# express the failure being guarded.
#
# The #118 shape is reconstructed verbatim as the first case: the line
# '## 0.8.0 — 2026-07-19' replaced by an entry written under '## Unreleased'.
# The ceremony's own stamp is driven right beside it, because a rule that
# fires on the stamp is unshippable for the same reason rig#44 and cast#108
# were — that pair, not the failing case alone, is what makes this a design.
# ---------------------------------------------------------------------------
MONO="$ROOT/.github/scripts/changelog-monotonic.sh"
check "changelog-monotonic: runnable bash" 0 "" bash -n "$MONO"
# grepo <name> <base-changelog-lines...> — a git repo whose `main` carries the
# given changelog, left checked out on a branch `pr` off it. Prints the dir.
#
# It carries its own VERSION, like tree() above, so the checks that run
# changelog-armed.sh against these fixtures read a version that belongs to the
# FIXTURE. Reaching for the repo's real VERSION instead makes those checks pass
# or fail on what box happens to be versioned at today: bare (the release
# ceremony's own tree) sends changelog-armed.sh down its bare branch, where it
# demands a section for THAT version in a fixture changelog that has never
# heard of it. `-dev` here because every one of these fixtures tops out at
# '## Unreleased', which is what a development tree is required to carry.
grepo() {
local d="$WORK/$1"; shift
mkdir -p "$d"
git -C "$d" init -q -b main
git -C "$d" config user.email test@example.invalid
git -C "$d" config user.name test
printf '%s\n' '0.8.1-dev' > "$d/VERSION"
{ echo "# Changelog"; echo; printf '%s\n' "$@"; } > "$d/CHANGELOG.md"
git -C "$d" add CHANGELOG.md VERSION
git -C "$d" commit -qm base
git -C "$d" checkout -q -b pr
echo "$d"
}
# head_changelog <dir> <lines...> — the PR branch's version of the file
head_changelog() {
local d="$1"; shift
{ echo "# Changelog"; echo; printf '%s\n' "$@"; } > "$d/CHANGELOG.md"
git -C "$d" commit -qam head
}
mono() { local d="$1"; shift; ( cd "$d" && bash "$MONO" "$@" ); }
mono_strict() { local d="$1"; shift; ( cd "$d" && CHANGELOG_MONOTONIC_STRICT=1 bash "$MONO" "$@" ); }
# --- the #118 incident, reconstructed --------------------------------------
G="$(grepo mono-118 '## Unreleased' '' '## 0.8.0 — 2026-07-19' '' '### Added' '' '- **Shipped prose**')"
head_changelog "$G" '## Unreleased' '' '### Fixed' '' '- **An entry**' '' '### Added' '' '- **Shipped prose**'
check "monotonic: a DELETED release heading fails (the #118 near-miss)" 1 "DELETES release heading" mono "$G" main
check "monotonic: ...and names the heading that vanished" 1 "## 0.8.0" mono "$G" main
check "monotonic: ...and the shape of the mistake (replaced, not inserted)" 1 "instead of being" mono "$G" main
check "monotonic: ...and why nothing else says so (git merges it cleanly)" 1 "git merges that edit cleanly" mono "$G" main
# The whole point of the issue: the OTHER guard is green on this same tree.
# Pinned here so a future 'just widen changelog-armed.sh' cannot quietly
# delete the reason this script exists.
check "monotonic: ...on a tree changelog-armed.sh calls FINE (the #122 gap)" 0 "agrees" \
bash "$ARMED" "$G/CHANGELOG.md" "$G/VERSION"
# --- the #118 incident as it ACTUALLY happened: a DUPLICATED heading -------
# The deletion case above is the near-miss. What the bad rebase really produced
# was two '## 0.8.0 — 2026-07-19' headings with the incoming entry stranded
# between them. Containment cannot see this: the duplicate is head-side
# SURPLUS, and `comm -23` (base minus head) is blind to extras on the head side
# — with or without `sort -u`, and multiset comparison does not close it for
# the same reason. Uniqueness on HEAD is the assert that does.
G="$(grepo mono-dup '## Unreleased' '' '## 0.8.0 — 2026-07-19' '' '### Added' '' '- **Shipped prose**')"
head_changelog "$G" '## Unreleased' '' '## 0.8.0 — 2026-07-19' '' '### Fixed' '' '- **An entry**' '' '## 0.8.0 — 2026-07-19' '' '### Added' '' '- **Shipped prose**'
check "monotonic: a DUPLICATED release heading fails (the #118 shape)" 1 "DUPLICATE release heading" mono "$G" main
check "monotonic: ...and names the repeated heading" 1 "## 0.8.0" mono "$G" main
check "monotonic: ...and says what a repeat does to release-notes extraction" 1 "re-arms its extraction" mono "$G" main
# Containment alone is green on this exact tree — nothing was deleted. Pinned
# so a future simplification cannot collapse the two asserts into one.
# shellcheck disable=SC2016 # $1/$2 are the inner shell's positionals, not ours
check "monotonic: ...on a tree where NOTHING was deleted (containment is blind)" 1 "" \
bash -c 'cd "$1" && bash "$2" main 2>&1 | grep -q "DELETES release heading"' _ "$G" "$MONO"
# And, as with the deletion case, the other guard calls this tree fine.
check "monotonic: ...on a tree changelog-armed.sh calls FINE" 0 "agrees" \
bash "$ARMED" "$G/CHANGELOG.md" "$G/VERSION"
# --- the release ceremony's stamp: an ADD, never a removal -----------------
# '## Unreleased' -> '## 0.8.1 — DATE' adds 0.8.1 and removes no X.Y.Z
# heading, because 'Unreleased' is not one. A false positive here would make
# every release unshippable — the rig#44 / cast#108 failure, one guard over.
G="$(grepo mono-stamp '## Unreleased' '' '- **Pending**' '' '## 0.8.0 — 2026-07-19' '' '- **Shipped**')"
head_changelog "$G" '## Unreleased' '' '## 0.8.1 — 2026-07-20' '' '- **Pending**' '' '## 0.8.0 — 2026-07-19' '' '- **Shipped**'
check "monotonic: the ceremony stamp passes (adds a heading, removes none)" 0 "still present" mono "$G" main
# --- the ordinary entry, done right ----------------------------------------
G="$(grepo mono-ok '## Unreleased' '' '## 0.8.0 — 2026-07-19' '' '- **Shipped**')"
head_changelog "$G" '## Unreleased' '' '### Fixed' '' '- **An entry**' '' '## 0.8.0 — 2026-07-19' '' '- **Shipped**'
check "monotonic: an entry INSERTED above the top section passes" 0 "still present" mono "$G" main
check "monotonic: ...and counts what it actually checked" 0 "all 1 release heading" mono "$G" main
# --- deletion is caught anywhere in the file, not just at the top ----------
G="$(grepo mono-mid '## 0.8.0 — 2026-07-19' '' '- **a**' '' '## 0.7.0 — 2026-07-18' '' '- **b**' '' '## 0.6.0 — 2026-07-17' '' '- **c**')"
head_changelog "$G" '## 0.8.0 — 2026-07-19' '' '- **a**' '' '- **b**' '' '## 0.6.0 — 2026-07-17' '' '- **c**'
check "monotonic: a heading deleted MID-FILE is caught too" 1 "## 0.7.0" mono "$G" main
# ...and only the deleted one is named, so the message points at the edit.
notes_only_070() { ! mono "$1" main 2>&1 | grep -qE '^ ## 0\.(6|8)\.0$'; }
check "monotonic: ...naming only the heading that went missing" 0 "" notes_only_070 "$G"
# --- a rewritten Unreleased is NOT a violation (changelog-armed owns it) ---
G="$(grepo mono-unrel '## Unreleased' '' '- **Pending**' '' '## 0.8.0 — 2026-07-19' '' '- **Shipped**')"
head_changelog "$G" '## 0.8.0 — 2026-07-19' '' '- **Shipped**'
check "monotonic: a deleted '## Unreleased' is NOT this guard's business" 0 "still present" mono "$G" main
# --- a changelog that did not exist at the base ----------------------------
G="$(grepo mono-new 'No sections yet.')"
head_changelog "$G" '## 0.1.0 — 2026-07-20' '' '- **First**'
check "monotonic: a base with no release headings passes (nothing to delete)" 0 "all 0 release heading" mono "$G" main
# --- degradation: no base to compare against -------------------------------
# A local run may genuinely have no base ref. That must SKIP loudly, not fail
# spuriously (which would make the script un-runnable off CI) and not pass
# silently (which is the failure shape this repo keeps refusing). CI closes
# the hole from the other side with STRICT.
G="$(grepo mono-nobase '## 0.8.0 — 2026-07-19' '' '- **Shipped**')"
check "monotonic: an unresolvable base ref SKIPS containment" 0 "containment SKIPPED" mono "$G" no-such-ref
check "monotonic: ...and says uniqueness already ran, not that nothing did" 0 "already ran" mono "$G" no-such-ref
check "monotonic: ...naming the base ref it could not resolve" 0 "no-such-ref" mono "$G" no-such-ref
check "monotonic: ...and warning that CI treats it as a failure" 0 "hard failure" mono "$G" no-such-ref
check "monotonic: STRICT turns that skip into a red run" 1 "is a FAILURE, not a skip" mono_strict "$G" no-such-ref
check "monotonic: ...and points at the checkout, not the script" 1 "fetch-depth: 0" mono_strict "$G" no-such-ref
# Outside a work tree at all (a tarball, an unpacked release).
mkdir -p "$WORK/mono-nogit"
printf '%s\n' '# Changelog' '' '## 0.8.0 — 2026-07-19' > "$WORK/mono-nogit/CHANGELOG.md"
check "monotonic: outside a git work tree it skips containment, not everything" 0 "containment SKIPPED" \
mono "$WORK/mono-nogit" main
check "monotonic: a missing changelog refuses by path (never a skip)" 1 "no such file" \
bash "$MONO" main "$WORK/nope.md"
# --- #143: uniqueness is a property of HEAD, so nothing base-side may gate it -
# Containment needs the merge base. Uniqueness needs only the file in front of
# it. Before #143 the duplicate check sat downstream of the base-ref, merge-base
# and base-blob conditions, so each of the three degradation paths below exited
# 0 on a tree with a duplicate in plain sight — the base-blob one not even via
# skip(), but a bare `exit 0` that STRICT could not reach. These cases pin the
# ORDER, which is the actual invariant; asserting the exit code alone is what
# let the original ship (the base-absent case below was green before and after).
grepo_nocl() { # a repo whose main has NO changelog at all
local d="$WORK/$1"
mkdir -p "$d"
git -C "$d" init -q -b main
git -C "$d" config user.email test@example.invalid
git -C "$d" config user.name test
echo seed > "$d/README.md"
git -C "$d" add README.md
git -C "$d" commit -qm base
git -C "$d" checkout -q -b pr
echo "$d"
}
add_changelog() { # <dir> <lines...> — the PR introduces the file
local d="$1"; shift
{ echo "# Changelog"; echo; printf '%s\n' "$@"; } > "$d/CHANGELOG.md"
git -C "$d" add CHANGELOG.md
git -C "$d" commit -qm head
}
# The changelog is absent at the merge base AND the PR introduces a duplicate.
G="$(grepo_nocl mono-143-newdup)"
add_changelog "$G" '## Unreleased' '' '## 0.8.0 — 2026-07-19' '' '- **a**' '' '## 0.8.0 — 2026-07-19' '' '- **stranded**'
check "monotonic: a duplicate introduced where the base had no changelog is CAUGHT (#143)" 1 "DUPLICATE release heading" mono "$G" main
check "monotonic: ...and STRICT does not change that (it was never a skip)" 1 "DUPLICATE release heading" mono_strict "$G" main
# ...and the clean counterpart still exits 0, now saying uniqueness did run.
G="$(grepo_nocl mono-143-newok)"
add_changelog "$G" '## Unreleased' '' '## 0.8.0 — 2026-07-19' '' '- **a**'
check "monotonic: ...while a CLEAN introduced changelog still passes" 0 "nothing could have been deleted" mono "$G" main
check "monotonic: ...saying uniqueness was checked, not that nothing was" 0 "uniqueness on HEAD already passed" mono "$G" main
# No git at all: uniqueness still has everything it needs.
mkdir -p "$WORK/mono-143-nogit"
printf '%s\n' '# Changelog' '' '## 0.8.0 — 2026-07-19' '' '## 0.8.0 — 2026-07-19' > "$WORK/mono-143-nogit/CHANGELOG.md"
check "monotonic: a duplicate OUTSIDE a git work tree is caught (#143)" 1 "DUPLICATE release heading" \
mono "$WORK/mono-143-nogit" main
# Unresolvable base ref: same — the skip is containment's, not the script's.
G="$(grepo mono-143-nobase '## 0.8.0 — 2026-07-19' '' '- **Shipped**')"
head_changelog "$G" '## 0.8.0 — 2026-07-19' '' '- **a**' '' '## 0.8.0 — 2026-07-19' '' '- **b**'
check "monotonic: a duplicate is caught even when the base ref will not resolve (#143)" 1 "DUPLICATE release heading" mono "$G" no-such-ref
# --- the push-to-main shape: containment vacuous, uniqueness real ----------
# With the pull_request gate gone (#143), merge_base == HEAD is a ROUTINE path,
# not a degradation. Containment compares the file against itself and asserts
# nothing, so a line reading "all N still present" would claim a check that did
# no work — the same dishonesty the skip messages were fixed for. The success
# line therefore has two forms, and this pins which one each event gets.
G="$(grepo mono-vacuous '## 0.8.0 — 2026-07-19' '' '- **Shipped**')"
check "monotonic: HEAD as its own base reports containment VACUOUS, not verified" 0 "containment vacuous" mono "$G" HEAD
check "monotonic: ...and names uniqueness as the half that actually ran" 0 "uniqueness on HEAD checked" mono "$G" HEAD
# shellcheck disable=SC2016 # $1/$2 expand in the child shell, by design
check "monotonic: ...and does NOT claim headings were still present" 1 "" \
bash -c 'cd "$1" && bash "$2" HEAD | grep -q "are still present"' _ "$G" "$MONO"
# The PR shape keeps the containment wording — the two must not collapse.
head_changelog "$G" '## 0.8.0 — 2026-07-19' '' '- **Shipped**' '' '## 0.9.0 — 2026-07-20' '' '- **New**'
check "monotonic: a real base still reports containment, naming the count" 0 "still present" mono "$G" main
# --- and the real tree, through the real script ----------------------------
# HEAD as its own base: the merge base is HEAD, so the sets are identical by
# construction. Proves the script runs against the actual CHANGELOG.md and
# parses its real headings, without depending on an `origin/main` that a
# fresh clone or a detached CI checkout may not have.
# HEAD as its own base is now the VACUOUS-containment path (#143), so the
# assertion moved to uniqueness's count — which is the stronger proof of the
# original intent anyway: it says the parser read the REAL CHANGELOG.md and
# found real headings in it, rather than that a self-comparison came out equal.
check "monotonic: THIS tree passes against itself (the parser meets reality)" 0 "uniqueness on HEAD checked" \
mono "$ROOT" HEAD
# The guard is only a guard if CI runs it — and only if CI runs it with the
# history it needs. Fail-closed pins on all three, since a depth-1 checkout
# would silently downgrade every run to the SKIP path.
check "ci.yml: runs the changelog-monotonic guard" 0 "" \
grep -qF 'changelog-monotonic.sh' "$ROOT/.github/workflows/ci.yml"
check "ci.yml: ...with full history, or the merge base is unreachable" 0 "" \
grep -qF 'fetch-depth: 0' "$ROOT/.github/workflows/ci.yml"
check "ci.yml: ...and STRICT, so a skip is a red run and not a green one" 0 "" \
grep -qF 'CHANGELOG_MONOTONIC_STRICT' "$ROOT/.github/workflows/ci.yml"
# #143: the step must NOT be pull-request-only — duplication is vacuous on no
# tree — and dropping that gate is only safe with the base-ref fallback, since
# `github.base_ref` is empty on a push and a bare `origin/` under STRICT is a
# hard failure on every push to main.
# Scoped to the step's OWN block, deliberately. A file-wide negative would
# forbid any FUTURE step in ci.yml from being pull_request-gated and would fail
# citing #143 when one legitimately is — #143 constrains this step, not the file.
# Terminates on a new STEP or a new JOB. The job boundary is not optional: the
# monotonic step is the LAST step of `check`, so stopping only at the next
# `- name:` runs the block into the `rehearsal` job below and swallows its
# job-level `if:`. That reintroduces the very bug the scoping fixed — an
# unrelated edit failing while citing #143 — just moved from "any step in the
# file" to "this step plus the head of the next job".
mono_step_block() {
awk '/^ - name: no shipped changelog heading/ {f=1; print; next}
f && (/^ - / || /^ [^ ]/) {exit}
f {print}' "$ROOT/.github/workflows/ci.yml"
}
# Anchored: an `if:` appearing inside a `run:` line is not a step condition.
mono_step_gated() { mono_step_block | grep -q '^ if:'; }
check "ci.yml: the monotonic step itself is not pull_request-gated (#143)" 1 "" mono_step_gated
check "ci.yml: ...and the block was actually found (guards the awk above)" 0 "changelog-monotonic" mono_step_block
check "ci.yml: ...and falls back to ref_name, so a push has a base to resolve" 0 "" \
grep -qF 'github.base_ref || github.ref_name' "$ROOT/.github/workflows/ci.yml"
check "CONTRIBUTING: names the append-only rule for release headings" 0 "" \
grep -qF 'changelog-monotonic.sh' "$ROOT/CONTRIBUTING.md"
# ---------------------------------------------------------------------------
# latest_release_tag — extracted from install.sh (the source-the-pure-function
# trick) and driven against a shim curl. The shim serves the ONE seam the
# function uses: -w '%{redirect_url}' on the releases/latest probe.
# ---------------------------------------------------------------------------
SHIMDIR="$WORK/shim"; mkdir -p "$SHIMDIR" SHIMDIR="$WORK/shim"; mkdir -p "$SHIMDIR"
cat > "$SHIMDIR/curl" <<'SHIM' cat > "$SHIMDIR/curl" <<'SHIM'
#!/usr/bin/env bash #!/usr/bin/env bash
# Fake curl for the release drills: answers the releases/latest probe with
# $FAKE_REDIRECT on stdout (the -w '%{redirect_url}' seam) — or fails with
# $FAKE_CURL_RC (network down) — and serves downloads (-o <file>) by copying
# $FAKE_TARBALL when the URL is $FAKE_SERVE_URL, else exit 22 (curl's own
# 404-under--f code). Every URL is appended to $FAKE_CURL_LOG so a test can
# assert exactly what was asked for, and in what order.
url="" out="" url="" out=""
while [ $# -gt 0 ]; do while [ $# -gt 0 ]; do
case "$1" in case "$1" in
-o|--output) out="$2"; shift 2 ;; -o|--output) out="$2"; shift 2 ;;
-w|--write-out) shift 2 ;; -w|--write-out) shift 2 ;;
-*) shift ;; -*) shift ;;
*) url="$1"; shift ;; *) url="$1"; shift ;;
esac esac
done done
[ -n "${FAKE_CURL_LOG:-}" ] && printf '%s\n' "$url" >> "$FAKE_CURL_LOG" [ -n "${FAKE_CURL_LOG:-}" ] && printf '%s\n' "$url" >> "$FAKE_CURL_LOG"
@ -787,105 +51,77 @@ chmod +x "$SHIMDIR/curl"
TAGFN="$(mktemp)" TAGFN="$(mktemp)"
awk '/^latest_release_tag\(\) \{/,/^\}/' "$ROOT/install.sh" > "$TAGFN" awk '/^latest_release_tag\(\) \{/,/^\}/' "$ROOT/install.sh" > "$TAGFN"
check "latest_release_tag: extracted from install.sh (guards the awk)" 0 "releases/latest" cat "$TAGFN" check "latest_release_tag: extracted from install.sh" 0 "releases/latest" cat "$TAGFN"
check "latest_release_tag: the extracted function is valid bash" 0 "" bash -n "$TAGFN" check "latest_release_tag: extracted function is valid bash" 0 "" bash -n "$TAGFN"
ltag() { # ltag <redirect_url> [curl_rc] ltag() {
FAKE_REDIRECT="$1" FAKE_CURL_RC="${2:-0}" REPO=heavy-duty/box \ FAKE_REDIRECT="$1" FAKE_CURL_RC="${2:-0}" REPO=heavy-duty/box \
PATH="$SHIMDIR:$PATH" bash -c ". '$TAGFN'; latest_release_tag" PATH="$SHIMDIR:$PATH" bash -c ". '$TAGFN'; latest_release_tag"
} }
check "resolve: reads the tag off the redirect" 0 "0.6.0" \ check "resolve: reads the tag off the redirect" 0 "0.6.0" \
ltag "https://github.com/heavy-duty/box/releases/tag/0.6.0" ltag "https://github.com/heavy-duty/box/releases/tag/0.6.0"
check "resolve: a -dev-style tag survives verbatim" 0 "0.7.0-rc1" \ check "resolve: a pre-release tag survives verbatim" 0 "0.7.0-rc1" \
ltag "https://github.com/heavy-duty/box/releases/tag/0.7.0-rc1" ltag "https://github.com/heavy-duty/box/releases/tag/0.7.0-rc1"
check "resolve: a repo with NO releases (redirect to /releases) fails" 1 "" \ check "resolve: a repo with no releases fails" 1 "" \
ltag "https://github.com/heavy-duty/box/releases" ltag "https://github.com/heavy-duty/box/releases"
check "resolve: no redirect at all fails" 1 "" ltag "" check "resolve: no redirect fails" 1 "" ltag ""
check "resolve: a curl failure (network down) fails, never hangs on prose" 1 "" \ check "resolve: a curl failure fails" 1 "" \
ltag "https://github.com/heavy-duty/box/releases/tag/0.6.0" 6 ltag "https://github.com/heavy-duty/box/releases/tag/0.6.0" 6
rm -f "$TAGFN"
# ---------------------------------------------------------------------------
# The three channels, driven through REAL install.sh runs (#83): default =
# latest release, BOX_REF=<tag> = pinned, BOX_REF=<branch> = dev. The shim
# curl serves a fabricated release tarball shaped exactly like GitHub's (one
# top-level directory), and its log proves WHICH URLs the installer asked
# for. FAKE_TARBALL carries VERSION 9.9.9 so nothing collides with the tree
# under test.
# ---------------------------------------------------------------------------
FAKEHOME="$WORK/home"; mkdir -p "$FAKEHOME" FAKEHOME="$WORK/home"; mkdir -p "$FAKEHOME"
SRC="$WORK/box-9.9.9"; mkdir -p "$SRC/bin" SRC="$WORK/box-9.9.9"; mkdir -p "$SRC/bin"
cp "$ROOT/bin/box" "$SRC/bin/box"; chmod +x "$SRC/bin/box" cp "$ROOT/bin/box" "$SRC/bin/box"; chmod +x "$SRC/bin/box"
echo "9.9.9" > "$SRC/VERSION" printf '9.9.9\n' > "$SRC/VERSION"
tar -C "$WORK" -czf "$WORK/gh.tar.gz" box-9.9.9 tar -C "$WORK" -czf "$WORK/gh.tar.gz" box-9.9.9
ninst() { # ninst <box_home> <box_bin> [VAR=val ...] — install.sh, shim network ninst() {
local h="$1" b="$2"; shift 2 local h="$1" b="$2"; shift 2
env HOME="$FAKEHOME" PATH="$SHIMDIR:$PATH" \ env HOME="$FAKEHOME" PATH="$SHIMDIR:$PATH" \
BOX_HOME="$h" BOX_BIN="$b" BOX_YES=1 BOX_SKIP_SETUP_HOST=1 \ BOX_HOME="$h" BOX_BIN="$b" BOX_YES=1 BOX_SKIP_SETUP_HOST=1 \
FAKE_TARBALL="$WORK/gh.tar.gz" "$@" bash "$ROOT/install.sh" FAKE_TARBALL="$WORK/gh.tar.gz" "$@" bash "$ROOT/install.sh"
} }
# --- channel 1: the default is the latest RELEASE ---------------------------
H1="$WORK/h1"; B1="$WORK/b1"; L1="$WORK/c1.log" H1="$WORK/h1"; B1="$WORK/b1"; L1="$WORK/c1.log"
check "default channel: resolves and installs the latest release" 0 "latest release: 9.9.9" \ check "default channel: installs the latest release" 0 "latest release: 9.9.9" \
ninst "$H1" "$B1" FAKE_CURL_LOG="$L1" \ ninst "$H1" "$B1" FAKE_CURL_LOG="$L1" \
FAKE_REDIRECT="https://github.com/heavy-duty/box/releases/tag/9.9.9" \ FAKE_REDIRECT="https://github.com/heavy-duty/box/releases/tag/9.9.9" \
FAKE_SERVE_URL="https://github.com/heavy-duty/box/archive/refs/tags/9.9.9.tar.gz" FAKE_SERVE_URL="https://github.com/heavy-duty/box/archive/refs/tags/9.9.9.tar.gz"
check "default channel: the download is the TAG tarball" 0 "" \ check "default channel: downloads the tag tarball" 0 "" \
grep -qF "archive/refs/tags/9.9.9.tar.gz" "$L1" grep -qF "archive/refs/tags/9.9.9.tar.gz" "$L1"
check "default channel: it never asked for a branch" 1 "" \ check "default channel: never asks for a branch" 1 "" grep -q "refs/heads" "$L1"
grep -q "refs/heads" "$L1" check "default channel: records the resolved tag" 0 "heavy-duty/box@9.9.9" \
check "default channel: INSTALLED_FROM records the RESOLVED tag" 0 "heavy-duty/box@9.9.9" \
cat "$H1/versions/9.9.9/INSTALLED_FROM" cat "$H1/versions/9.9.9/INSTALLED_FROM"
check "default channel: the install answers through the chain" 0 "box 9.9.9" \ check "default channel: installed binary answers" 0 "box 9.9.9" \
env HOME="$FAKEHOME" "$B1/box" --version env HOME="$FAKEHOME" "$B1/box" --version
# --- channel 2: BOX_REF=<tag> pins a release --------------------------------
H2="$WORK/h2"; B2="$WORK/b2"; L2="$WORK/c2.log" H2="$WORK/h2"; B2="$WORK/b2"; L2="$WORK/c2.log"
check "pinned channel: BOX_REF=<tag> installs that tag" 0 "done" \ check "pinned channel: installs the requested tag" 0 "done" \
ninst "$H2" "$B2" BOX_REF=9.9.9 FAKE_CURL_LOG="$L2" \ ninst "$H2" "$B2" BOX_REF=9.9.9 FAKE_CURL_LOG="$L2" \
FAKE_SERVE_URL="https://github.com/heavy-duty/box/archive/refs/tags/9.9.9.tar.gz" FAKE_SERVE_URL="https://github.com/heavy-duty/box/archive/refs/tags/9.9.9.tar.gz"
check "pinned channel: no releases/latest probe (a pin resolves nothing)" 1 "" \ check "pinned channel: skips latest-release resolution" 1 "" \
grep -q "releases/latest" "$L2" grep -q "releases/latest" "$L2"
# --- channel 3: BOX_REF=<branch> is the dev channel -------------------------
H3="$WORK/h3"; B3="$WORK/b3"; L3="$WORK/c3.log" H3="$WORK/h3"; B3="$WORK/b3"; L3="$WORK/c3.log"
check "dev channel: BOX_REF=main falls back tag -> branch" 0 "trying it as a branch" \ check "dev channel: falls back from tag to branch" 0 "trying it as a branch" \
ninst "$H3" "$B3" BOX_REF=main FAKE_CURL_LOG="$L3" \ ninst "$H3" "$B3" BOX_REF=main FAKE_CURL_LOG="$L3" \
FAKE_SERVE_URL="https://github.com/heavy-duty/box/archive/refs/heads/main.tar.gz" FAKE_SERVE_URL="https://github.com/heavy-duty/box/archive/refs/heads/main.tar.gz"
check "dev channel: the tag was tried FIRST" 0 "refs/tags/main.tar.gz" \ check "dev channel: tries the tag first" 0 "refs/tags/main.tar.gz" head -1 "$L3"
head -1 "$L3" check "dev channel: then downloads the branch" 0 "" \
check "dev channel: then the branch" 0 "" \
grep -qF "archive/refs/heads/main.tar.gz" "$L3" grep -qF "archive/refs/heads/main.tar.gz" "$L3"
# --- the failure is LOUD, never a silent fall-through to main ---------------
H4="$WORK/h4"; B4="$WORK/b4"; L4="$WORK/c4.log" H4="$WORK/h4"; B4="$WORK/b4"; L4="$WORK/c4.log"
check "resolution failure: REFUSES, naming the probe URL" 1 "could not resolve the latest release" \ check "resolution failure: names the latest-release probe" 1 "could not resolve the latest release" \
ninst "$H4" "$B4" FAKE_CURL_RC=6 FAKE_CURL_LOG="$L4" ninst "$H4" "$B4" FAKE_CURL_RC=6 FAKE_CURL_LOG="$L4"
check "resolution failure: ...and the way out (BOX_REF)" 1 "BOX_REF" \ check "resolution failure: names BOX_REF as the override" 1 "BOX_REF" \
ninst "$H4" "$B4" FAKE_CURL_RC=6 ninst "$H4" "$B4" FAKE_CURL_RC=6
check "resolution failure: downloaded NOTHING (no silent main)" 1 "" \ check "resolution failure: downloads nothing" 1 "" grep -q "archive/" "$L4"
grep -q "archive/" "$L4" check "resolution failure: installs nothing" 1 "" test -e "$H4/versions"
check "resolution failure: nothing was installed" 1 "" test -e "$H4/versions" check "unknown ref names both attempted channels" 1 "neither a tag nor a branch" \
check "a ref that is neither tag nor branch dies naming both" 1 "neither a tag nor a branch" \
ninst "$H4" "$B4" BOX_REF=no-such-ref ninst "$H4" "$B4" BOX_REF=no-such-ref
# --------------------------------------------------------------------------- check "README documents the latest-release channel" 0 "" grep -qF 'latest release' "$ROOT/README.md"
# The -dev convention (#83): main's VERSION carries -dev between releases, so check "README documents the pinned channel" 0 "" grep -qF 'BOX_REF=0.6.0' "$ROOT/README.md"
# a dev install lands beside releases in versions/ instead of impersonating check "README documents the dev channel" 0 "" grep -qF 'BOX_REF=main' "$ROOT/README.md"
# one — and the docs keep the promises this PR makes.
# ---------------------------------------------------------------------------
check "CONTRIBUTING documents the post-release -dev bump" 0 "" \
grep -q -- '-dev' "$ROOT/CONTRIBUTING.md"
check "CONTRIBUTING documents the release ritual (tag == VERSION)" 0 "" \
grep -qi 'release' "$ROOT/CONTRIBUTING.md"
check "README documents the default (latest release) channel" 0 "" \
grep -qF 'latest release' "$ROOT/README.md"
check "README documents the pinned channel" 0 "" \
grep -qF 'BOX_REF=0.6.0' "$ROOT/README.md"
check "README documents the dev channel" 0 "" \
grep -qF 'BOX_REF=main' "$ROOT/README.md"
echo "---" echo "---"
echo "$PASS passed, $FAIL failed" echo "$PASS passed, $FAIL failed"