Section 4 now says what the pipeline does: a cycle is a verdict with
blocking findings followed by a return to the author, so a green verdict
consumes nothing — the case that cost #225 an arbitration after a failed
merge forced a rebase and a third attempt.
The canon also separates the two quantities the verdict line carries. The
attempt number names the review document, because two runs sharing a
number would overwrite each other's artefact; the budget counts blocking
cycles only. That is why the document threshold in the process gate sits
above the cycle limit, and why the guard reports a recount of review-4
rather than removing the label itself.
Issue: #227
User-Visible: no
The reviewer prompt was identical for every round, and the canon said
nothing about the scope of a repeat pass, so r2 re-derived the product
framing and re-checked acceptance criteria the fix never touched: the r2
pass on #150 cost a full pipeline run over one line in a test fixture.
From the second cycle on, the subject is the delta against the SHA the
previous verdict was given on: each earlier finding must be shown closed
by a line of code or text, only the criteria the delta can reach are
re-verified, and whatever is carried over is listed with the round and SHA
it came from. Cheap gates still run every round.
The scope shrinks, the strictness does not. A fix can break a criterion an
earlier round accepted — that is how regression #102 happened — so the
boundary is the findings plus everything the delta can reach, and a
non-local delta (a rebase onto a moved dev, a behaviour contract change, a
new subsystem) still gets the full pass.
Issue: #214
User-Visible: no
Filing and servicing a separate issue costs far more than fixing a small
problem in place — the owner's call of 2026-08-19 (#202). A Medium finding
inside the task's scope no longer becomes its own issue: with no High
findings the verdict is yellow, the author fixes it and the fix passes
another review cycle. Only an out-of-scope Medium is still filed
separately, because foreign scope is never patched from a task branch.
Applied to the canon (PROCESS.md), the reviewer prompt in process.yml and
AGENTS.md; the verdict format now writes "Medium: N -> in-task | #NN".
Issue: #202
User-Visible: no
The analyst used to ask the owner to confirm every estimate and waited for an
answer on each point. Most issues are unambiguous, and most of that waiting
changed nothing — the owner's own measure is that seven issues in ten should
travel from S1-new to a finished spec without a single question.
Section 2.2 flips the default. Estimates, type, priority and track go on as
labels immediately; the analysis comment is a notification, not a request —
the owner's silence is consent, his disagreement is a label edit, and neither
stops the work. The analyst moves the issue to S3-spec himself. The only
questions that ever reach the owner are product questions, asked at the spec
stage in one batch with defaults and blocked, and only when the spec cannot be
written without the answer; anything that can wait for the spec waits, anything
that does not block it becomes a recorded assumption instead. The one full stop
left in analysis is a genuine SCOPE conflict, where the analyst proposes
rejection and the owner decides.
Issue: #114
User-Visible: no
Three lines of section 10.4 and the trailing newline went missing in transit.
The lost paragraph is the one that says a label which did not change means the
run failed rather than the work — the sentence that tells a waiting author to
read the logs instead of polling for another forty-five minutes. Losing exactly
that one while copying a document about silent failures is a joke the situation
made on its own.
Caught by the byte comparison that follows every publish, which is the whole
reason it follows every publish.
Issue: #139
User-Visible: no
The owner stopped using GitHub Projects. Most of this is wording, but one part
was not: release-prerelease.mjs talked to the Project in code. finishIssues
looked up the project id, listed its items and its Status=Done option, and threw
when an issue was missing from the board — so the first release that closed an
issue would have died on a step with nothing to do with publishing. Found by
reading rather than by releasing, which was luck.
Closing issues stays, and now strips the status label first. That order is not
cosmetic: the invariant that a closed issue carries no status label has broken
twice already, both times because a manual step did it the other way round. The
close-merged job already does it in this order.
The documents now say labels and only labels. The explicit "no longer used"
lines are kept on purpose, in PROCESS.md and next to the code that used to sync:
a decision that vanishes quietly gets reintroduced a month later by someone who
never knew it was made.
Issue: #139
User-Visible: no
The owner's report: the process works but every stage takes a long time even on
simple bugs. Two causes, and neither was the one that first comes to mind.
The reviewer ran everything regardless. On #89 it installed Chromium, ran all 127
smoke files and a full golden capture — right for a task rated 10/10 for
complexity, absurd for a bug about a room divider. Full suites are the pre-beta
gate; the review now runs typecheck, unit and build always, and smokes, golden,
pytest or performance only where the diff and the AC call for them. The price of
narrowing it is honesty: the reviewer must list which gates it ran, which it did
not, and why, so a skipped gate is a visible decision rather than a silent one.
The reviewer also built its own environment out of model turns, with no npm cache
and no browser cache, paid for from the same forty-five minutes. The workflow now
installs dependencies and Chromium as ordinary cached steps, after switching to
the task branch so the lockfile is the branch's own.
Second, ceremony did not scale down. The light track makes a spec cheap; the new
trivial track does without one — S2-analysis straight to S5-ready, no spec review,
AC in the issue body. It is deliberately hard to qualify for: a bug on one surface,
no new UX contract, no migration, no i18n, no perf or touch effect, three checkable
AC at most, and expected behaviour already on record. Nothing left to decide is the
criterion that holds the whole thing up, and it cannot be met by feeling sure.
Code review is never skipped on either track. It is what stands in for testing
here, so it is the one stage speed may not buy.
Issue: #127
Issue: #128
User-Visible: no
The guard refused to review any issue the owner had not filed himself. The rule
was meant to keep malformed outside reports out of the pipeline, but it checked at
every step instead of at the entrance, and it duplicated a guarantee the platform
already gives: only someone with write access can apply a label. Applying the
first status label is the owner's explicit decision, and it is the only place the
question belongs.
So the author check is gone. While an issue carries no status label it sits
outside the process and the invariants do not apply; once labelled, the task is in
flight and who filed it stops mattering.
The old rule also cost real work. On #123 an outside bug report had been analysed
and specified before the guard turned it away in nine seconds, and the remedy on
offer was to refile the same thing as the owner's own issue.
Issue: #114
User-Visible: no
The implementation loop runs typecheck, unit and build. Golden, browser smokes,
performance and the full HA harness run before a beta — after the code review has
passed and the issue already sits in S8-merged. Some defects cannot surface any
earlier, and until now the process had nothing to say about them, so the honest
reading was a second full review cycle at the most expensive possible moment.
The owner's decision: fix it, re-run what failed, and a green run carries the
release on. The gate named the defect precisely and the same gate proves the fix,
so the check is objective and depends on nobody's judgement.
The boundary is written down with it, because "the gate found something" could
otherwise absorb an arbitrary amount of new work. A fix that changes a behaviour
contract, reaches an untouched subsystem or rivals the task in size goes through
the normal flow. Editing a test so it stops failing is concealment rather than
repair — the exception is a defect proven to be in the fixture, as on #89.
The rule also records what it costs: the author judges his own work here, which
the process refuses everywhere else. That is the price of speed at the one point
where a review cycle is dearest, and the compensation is that the re-run command
and its result are written into the issue where the release manager reads them.
Issue: #114
User-Visible: no
A review run always moves the label. The rule is written down because its absence
cost a real stall: a green code review whose merge conflicted left the label alone,
the waiting author polled thirty times and reported the limit as exhausted, and a
verdict that existed reached nobody.
Both documents now say what S6-in-progress means when the verdict was green and
only the merge failed — rebase, not rework, and the verdict still stands. They also
say that a label which did not change means the run failed rather than the work, so
the answer is logs and the owner, not more polling. Cycles are counted per stage.
Issue: #114
User-Visible: no
Section 10.1 promised pre-push as the blocking gate that replaces pull requests.
The hook did not exist, so the document promised a check that was not there —
worse than saying nothing, because a promise like that gets relied on. Until now
process-gate ran only as the catch-up job in CI, which reports after the code is
already in dev.
The hook skips branch deletions and tags, and for a branch the remote has not
seen it measures from the merge-base with dev rather than from the root, or every
violation committed before the gate existed would make it impossible to pass. A
missing script does not block a push: old checkouts and worktrees have to stay
usable.
gh is optional on purpose. Reading issue status needs the network, and a hook
that cannot work on a train is a hook people switch off; offline it runs what it
can and CI does the strict pass.
The executable bit is the quiet part. Git skips a hook without +x and says
nothing — the gate reports success by being absent. Measured on a real push:
mode 644 produces zero lines from the gate and the push goes through, 755 stops
it. The API cannot set the bit, so install-hooks restores it on every install.
Issue: #121
User-Visible: no
The canon moved into the repository in #112 and then stood still while the
process kept moving. A document that lags is worse than no document: an agent
reading it as truth acts on rules that no longer exist. It promised a pre-push
hook that was never written, named labels in Russian that the repository has
never used, listed a status set the gate no longer applies, and said nothing at
all about the event-driven pipeline — the largest mechanism the process has.
Label names are now English throughout and S8-merged is documented. Section 1
covers the configuration files the gate kept reporting as unclassified, and
records that D beats A where paths overlap, since the built bundle lives inside
custom_components/houseplan/frontend/. Section 10.1 admits that pre-push does
not exist. Section 10.2 matches ALLOWED_STATUS in scripts/process-gate.mjs,
including the two caveats that only surfaced once the pipeline ran. Section 10.4
is new and documents the four silent-failure traps that cost a working day each.
The source-of-truth order now says that actual automation outranks its own
description — this document included.
Issue: #119
User-Visible: no
Publishes the 538-line process canon into the repository, replacing the
51-line provenance stub that pointed at a non-existent .agents/PROTOCOL.md.
Rewrites AGENTS.md: product context first, labels as the canonical status,
rule #1 with the status check, change classes, trailers, push cadence,
Codex/Claude roles and review cycle limits.
Issue: #112
User-Visible: no
Matysh