A generated skill that loads the shared preamble names sections/preamble.md
as a required asset before skill start, and a spawned document-release child
blocks on its absence, so docsync-spawned stayed red on every #3434 screen.
fixtureDocs now copies that file when the generated skill has it.
This single hunk is taken unchanged from gstack#3472 (head 2e3f7ba1,
GSTA-107), which trains ahead of #3434, so the train merge sees identical
lines. Nothing else from #3472 is included.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
skill-fixture.ts is a global touchfile pinned in scripts/harness-version.json
because it reshapes the skill content most E2E suites read, and it now
builds that content through test/helpers/skill-startup.ts. That helper was
in neither list, so a later edit to it would change fixture inputs without
the harness-version guard and select only 27 keys. It is now global and
pinned, recorded non-behavioral (its fixtures are byte-identical to the
pre-hoist output). ARCHITECTURE.md and the CHANGELOG stop calling the
pointer id a content id: it hashes the shared text before host rewrites.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The hoist moved about 22 KB out of every tier 2+ SKILL.md, which left
each hoisted maxSkeletonBytes cap and each eagerPerInvocation ceiling
roughly 22 KB / 5-6K tokens slack. The 20 hoisted skeleton caps now sit at
the post-hoist skeleton plus their pre-hoist headroom, and 42 context-budget
ceilings take the recaptured (lower) values. Nothing was raised: the four
ceilings the recapture would have raised keep their old values.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(capy): the launch environment is sourced from a 0600 file and no skill fence may print the environment (GSTA-104)
During GSTA-96's unattended /ship on #3425, the Step 14.5 docs-audit child
re-typed the GSTACK_LAUNCH assignments as `export $(...)`; the substitution
came back empty, the bare `export` printed the whole environment, and three
API key values landed in its tool output.
- bin/gstack-capy-install writes the assignments to <verdict>.env (mode 0600,
idempotent PATH prepend) and prints GSTACK_LAUNCH_FILE: <path>.
- ship Step 14.5 prompt, document-release's spawned note, autoplan/DRIVER.md
and gstack-skill-start's capy-asks block say: source the file; never
export $(...), env, printenv or bare set in a tool fence.
- test/launch-env-echo-ratchet.test.ts greps every generated SKILL.md,
sections, DRIVER.md, the Capy skill and bin/ shell helpers, with negative
controls under test/fixtures/launch-env-echo/.
- lib/redact-engine.ts: env.value (HIGH) finds the value of any *_KEY,
*_TOKEN, *_SECRET, *_PASSWORD variable in the writer's environment, so a
leaked value cannot reach a PR body, receipt, report or Drive file.
- scripts/lib/shard-engine.ts scrubs the Capy launch markers from shard
environments (GSTA-99's finding).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ci): DRIVER.md back to 159 lines; shard-engine recorded non-behavioral at HARNESS_VERSION 6; verdict-count test lists .json only
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: register test/fixtures/launch-env-echo as a free fixture
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(redact): env-value fixtures stay out of pregate's env.kv net
A credential-named assignment with an entropic literal on one line is what
the repo's own pregate secrets scan refuses in added lines, so the fixture
values move into plainly named constants and the scanned text is built from
them. The scan under test still sees the same values through processEnv.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(windows): the late-completion remote-caller case gives its second attempt a 2s budget (run 40263984171)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(redact): env.value trims the value, keeps a prefix value's longer match, hides the preview and skips PUBLIC names
/ship Step 9.4 review fixes for the GSTA-104 env-value scan:
- a value whose environment copy ends in a newline (a key read from a file)
is searched for trimmed, so its leaked form still matches (the length
check already trimmed; the search used the raw value);
- when one credential value is a prefix of another, the dedup key carries the
span length, so the longer value is redacted whole in either order instead
of leaving its tail in the text and dropping its finding;
- the env.value preview is a fixed mask instead of the first characters of a
live credential;
- framework-public names (NEXT_PUBLIC_*_KEY, *_PUBLIC_KEY) are not scanned,
since those values are committed on purpose;
- the header and the processEnv docstring state the name rule (KEY, TOKEN,
SECRET, PASSWORD, PASSWD, any case) and that process.env is the engine's
one ambient input.
Step 7 coverage extensions and a regression test for each fix in
test/redact-env-value.test.ts; docs/capy-install.md names the full rule.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* refactor(capy-install): write_launch_file quotes through shq; header names the launch file
Review finding: _sq duplicated shq() from the same file. The launch file's
assignments now go through shq, and the header comment describes the
GSTACK_LAUNCH_PATH and GSTACK_LAUNCH_FILE lines beside GSTACK_LAUNCH.
Step 7 coverage: the verdict test sources the launch file and runs --check;
the single-quote path test sources the file too; a new case makes the
launch-file directory unwritable and checks the run says so, prints no
GSTACK_LAUNCH_FILE line, leaves no temp file and keeps its exit code and
trailer (linux, non-root).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(preload): strip the Capy launch markers so a direct bun test matches the shard sandbox
Red Team finding: the launch-marker scrub lived only in createShardSandbox,
so a direct `bun test <file>` run under an unattended Capy session inherited
GSTACK_SESSION_KIND, GSTACK_CAPY, GSTACK_EPHEMERAL and GSTACK_INSTALL_VERDICT
(GSTA-99's symptom). The preload now deletes the same four names, and
test/shard-engine.test.ts imports CAPY_LAUNCH_MARKERS instead of re-typing them.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(ratchet): the launch-env echo scan catches backtick and $VAR exports, typeset -p, env flags and a set in any segment
Review findings 11 and 12: export-subst also trips on `export \`...\`` and
an unquoted `export $VAR` (both splat a NAME=value file; `export "$name"` is
one word and stays allowed); the export rule adds `typeset -p`; env trips
with only flags (`env -0`) and as `/usr/bin/env`; set is judged per segment
and with redirections, allowed only when piped straight into an anchored
grep filter. Quoted strings are blanked offset-preserving so a `#` inside
quotes no longer hides the rest of the line. The negative control covers
each new form on both sides.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(ship): Step 14.5 names where the launch-file placeholder comes from
The /document-release prompt line read `. <file>` with no word on what fills
it. It now says the placeholder is the GSTACK_LAUNCH_FILE: path the parent's
own install check printed. Worded to stay under the ship skill's pinned
parity size (313,279 of 313,281 union bytes).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(redact): env.value admits *_PASS, *_PAT, *_APIKEY and *_PWD, and skips path values and gstack's lock token
/ship Step 11 adversarial findings. The name rule also covers DB_PASS,
GITHUB_PAT, *_APIKEY and *_PWD (the shell's own PWD and OLDPWD stay out). A
credential-named variable whose value is a filesystem path (SSL_KEY=/etc/ssl/
private/x.key) names where the credential lives, so the path is no finding,
and GSTACK_BRAIN_LOCK_TOKEN (pid-random-epoch, written to the lock owner file)
is not a secret. Without these, an ordinary mention of that path or token in a
PR body, receipt or CSO report was a HIGH fail-closed blocker.
The adversarial pass also recommended an entropy floor so dev defaults such as
DB_PASSWORD=postgres stop matching prose; declined here on purpose, because the
scan's promise is to catch a leaked value whatever its shape, and a weak real
password is still a credential. Recorded as an open decision in the ship report.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(capy-install): a failed launch-file write removes only its own temp file
The failure path ran rm -f "$LAUNCH_FILE".tmp.*, which also deleted the temp
file a concurrent installer run (two threads on one machine, same verdict
path) was about to mv, so that run lost its launch file too. write_launch_file
now cleans up its own $tmp and returns 1; the caller only reports. The file's
comment no longer embeds the state-root path (a newline in GSTACK_STATE_ROOT
could have ended the comment).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: the launch markers come from one list, and the echo ratchet scans setup and scripts/*.sh
The preload imports CAPY_LAUNCH_MARKERS instead of re-typing the four names,
and the ratchet asserts the installer exports every name on that list, so a
fifth marker cannot be added to one place only. The shell scan also covers
./setup and the scripts/*.sh install scripts callers run first.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): the Unreleased entry states the review-fixed env.value rules, the ratchet forms and the one test-budget change
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(redact): the env.value path exemption asks whether the file exists instead of matching a shape
Second review cycle: a path-shaped rule also matched a base64 secret that
starts with "/" and holds another "/" (about 1 in 150 AWS-shaped keys), which
then went unscanned. The exemption now fires only when the value names a file
that exists on the scanning machine (SSL_KEY=/etc/ssl/private/x.key). The
module header names that stat as the engine's one filesystem read.
NON_SECRET_ENV_NAMES is exported so the test can prove bin/gstack-brain-lock.sh
still exports every name in it; the PWD/OLDPWD fixtures hold plain words so only
the name rule keeps them out.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: the installer's own-temp-file cleanup is exercised, and the ratchet coverage test names setup and scripts
An mv shim first on PATH refuses only the launch-file target, so the temp
file exists when the move fails: the run removes that file alone (a sibling
from a concurrent run survives), says so, prints no GSTACK_LAUNCH_FILE line
and keeps the earlier file, exit code and trailer. The ratchet coverage test
asserts setup, scripts/build.sh and scripts/sandbox-doctor.sh are scanned.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(redact): env.value has no path exemption and matches the value in normalized form
Second adversarial pass: the existence check let the scanned agent exempt
any "/"- or "~/"-prefixed secret by creating a path of that name, a silent
bypass of the one guard this branch adds, so the exemption is gone; a
path-valued SSL_KEY that must appear in a text goes through the allowlist.
The engine is back to no I/O. The value is now normalized the way the text
is before indexOf, so a credential NFKC rewrites (fullwidth digits) still
finds its leaked ASCII form.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(capy-install): the launch file is written only on a passing run; the ratchet checks the marker list both ways
A gstack: fail run no longer writes or announces a sourceable file whose PATH
prepend points at an unverified Bun. The ratchet also asserts every variable
the launch file exports is a CAPY_LAUNCH_MARKERS entry or GSTACK_STATE_ROOT,
so a sixth export cannot reach fixture children unstripped. The Capy skill's
prose no longer offers re-typing the assignments as an alternative to sourcing.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(capy-install): the launch file is part of the ok verdict
Third adversarial pass: a passing run whose launch file could not be
written still said gstack: ok with exit 0 and printed only the GSTACK_LAUNCH
line, leaving a shell-evaluating caller with the re-typing path the branch
exists to remove. The file is now written before the verdict is recorded;
a write failure on a passing run turns the run into
"gstack: fail launch-file — could not write the launch file <path>; fix: …
(LAUNCH_FILE_UNWRITABLE)" with exit 1 and an ok:false verdict, and every
failing run removes the launch file an earlier passing run left beside the
verdict. The two failure tests assert the new contract, the doctor-FAIL
tests assert no launch file is announced or left, and the docs, Capy skill
and CHANGELOG say the same.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(redact): the env.value allowlist and placeholder rules see the normalized value too
An allowlisted value in NFC did not suppress a match on its NFKC-composed
form, and a value that is a placeholder only after normalization was still
searched for. Fixture nits from the third review cycle: fixed directory
string instead of process.cwd(), the fullwidth assertion guards its own
vacuity, a zero-width-padded value under the floor is pinned, and the
ratchet comment names the one kept export and the PATH case line.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(capy-install): LAUNCH_FILE_UNWRITABLE is a registered result code; a kept profile verdict keeps its launch file
Fourth review cycle. The new trailer code now has its row in
lib/result-codes-capy.ts (the owner module is at its size cap) and its
docs/troubleshooting.md anchor, so the install-side code scan resolves it.
A failing profile check (--for review-voice) that keeps a fuller ok verdict
for this HEAD no longer deletes that verdict's launch file: the fail branch
removes the file only when the run rewrites the verdict, and setup_failed
removes it too. The docs say "a failing run that rewrites the verdict",
and that an unwritable directory keeps both the old file and the old
verdict. A new test runs a passing install, then a failing profile check,
and asserts the file and the ok verdict both survive.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(redact): the normalized allowlist and placeholder rules each have an assertion that fails without them
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(capy-install): a setup failure after a passing install removes the earlier launch file
Fifth review cycle: setup_failed's cleanup had no assertion. The setup
failure test now installs once (launch file present), commits a new HEAD so
setup runs again, fails that setup, and asserts the launch file is gone and
the verdict says ok:false before the next run sets up again and ends ok.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: state-root, contributor reference and capy-install follow the launch-file contract (Step 14.5 audit)
The /document-release audit (docs-3449-1792992068) corrected three authored
docs: docs/state-root.md shows the GSTACK_LAUNCH_FILE line and says to apply
it with ". <that file>" instead of prefixing or exporting the assignments;
docs/CONTRIBUTOR_REFERENCE.md names scan()'s one ambient input instead of
calling it pure; docs/capy-install.md's bun-shim bullet and exit table name
the launch file and the fail launch-file trailer.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(gate-diff): resolve the base to origin/<base> when no local branch exists; the no_base fix line fetches into the tracking ref
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(post): the repo's release versions and a receipt's tree hash / run ids are not pii.ip_public or pii.phone.e164
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evidence): parse the shard runner's and the remote pregate lane's test counts into tests_ran
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(restamp): CHANGELOG_DUPLICATE_HEADING refuses only duplicates the PR introduces
checkChangelog takes the base branch's CHANGELOG: a heading the base already
carries N times may appear N times on the PR (inherited released history), and
only a further copy is a duplicate. gstack-restamp passes origin/<base>'s
CHANGELOG at the plan's base sha, so a base like gbrain's master, which heads
one version twice, can be stamped; a duplicate the PR adds is still refused
with nothing written.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(restamp): the stamp-at-merge next: line no longer asks the lane to edit the CHANGELOG
Under a train the stamp commit may hold only restamp's own output: the train's
verify accepts the CHANGELOG only as the base's plus the PR's own entry
re-headed, and a lane that followed the old "write the CHANGELOG entry text"
prompt froze the queue. The claim-at-open wording is unchanged.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(ship-queue): require a current /ship receipt before READY, train build and train merge
Garry, 2026-10-25: use the gstack ship skill before merging PRs. ready printed
SHIP_RECEIPT: none as information and returned ok, so the pool was READY'd without
/ship. Now ready, train build (dry run included) and verify --train refuse with
QUEUE_RECEIPT_MISSING or QUEUE_RECEIPT_STALE from the PR body alone; verify accepts
the receipt written for the pinned head when the current head is its stamp commit.
gstack-ship-receipt result is /ship's terminal step (GSTACK_RESULT: skill=ship,
run dir with the head and receipt), unattended /ship may update an existing PR's
body, and INSTALL_UNVERIFIED with no verdict names the project directory to
install from (GSTA-85).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(ship): pin Step 22 in workflow-required-steps and tighten the ship skeleton
Gate edit: test/fixtures/workflow-required-steps.json pins the new
"## Step 22: Terminal line (every run)" heading (strengthens: a later
edit that drops the terminal line turns the required-steps test red).
Steps 14, 16, 18, 20 and 22 prose tightened so the carve-guards raise
shrinks to 81,600 / 1.6740 (measured skeleton 81,535, union 314,027).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (ready at the stamp commit, screen on a stale merge ref, ship-run.json)
- ready accepts the pin's receipt at a slot's stamp commit (plus the slot-2
merge of main), as verify --train already did; a real edit stays STALE
- ready --screen refuses QUEUE_SCREEN_STALE_REF when refs/pull/<n>/merge is
missing or merges an older head; a finished screen that planned 0 cases is
never followed, and train build seats that slot unscreened (GSTA-95 on #3431)
- gstack-ship-receipt result writes ship-run.json (a /ship record, not a run
v1 manifest), validates --head, and prints status=incomplete on gh failures
- bindReceipt takes an optional pr and renders one-line SHIP_RECEIPT lines
- tests for every state-matrix cell the review named; the train fixture's
merge ref is a real merge commit
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: cycle-2 review fixes (private screen scratch, no bare-merge receipt reuse, 12-hex --head, one receipt scrub) and align the unattended hook text with the GSTACK_RESULT writers (GSTA-91)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: adversarial-review fixes (result refuses an unpushed HEAD, resolves --out and reports unwritable records; ready names a failed merge-ref fetch; unattended /ship never runs gh pr ready)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: close review-cycle gaps (a stamp must change a stamp file, result requires a full --head and fails closed without headRefOid, digits-only --pr) with tests for every cycle-3 branch
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: give the fsck-rejected merge-ref spawns a timeout (spawnsync tripwire)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: detect a hollow screen from the plan it uploads (no paid-plan artifact or nothing planned), correct two troubleshooting facts, and normalise result --pr
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(hollow-screen): read manifest.json by name, list artifacts by name, say when the plan is unreadable; lowercase result --head
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(hollow-screen): expired and unreadable run rows, uppercase --head; docs name every SCREEN: literal
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(train build): say when the repository slug is unreadable instead of counting the screen silently
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: name an ls-remote failure in ready --screen, refuse result --pr with --body, cap echoed receipt errors, tell an unreadable install verdict from a missing one
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: ls-remote refusal, --pr with --body, capped receipt errors, unreadable slug and verdict (both twins); docs name the new literals
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: scrub Unicode line separators from receipt text, report an unreadable --body as incomplete, refuse unsupported verdict schemas in the bash twin
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(setup): install production dependencies only; contributors and CI keep the full install (GSTA-97)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): production-only install (GSTA-97)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (GSTA-97)
- setup/gstack-browser-ensure: Bun treats --production as frozen, so the
old fallback could never recover a stale lockfile; refresh it with
--lockfile-only, then install production-only again.
- gstack-browser-ensure failure line and the README tip no longer suggest a
full bun install to users.
- Tests: real-Bun stale-lockfile and keep-devDeps contracts, behavioral
browser-ensure install tests, relative-import closure scan, multi-line and
re-export negative controls; CHANGELOG matches.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes, pass 2 (GSTA-97)
- gstack-browser-ensure's failure line and the README tip suggest the
frozen production install (./setup skips the install when the build is
current, and a bare --production install is frozen anyway).
- setup install guard catches quoted and unquoted $BUN_CMD spellings.
- Replace the exact-text gstack-browser-ensure grep with an invariant: no
full bun install; behavior is covered by gstack-browser-ensure.test.ts.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(setup): keep a contributor checkout's dev packages on bun.lock's versions (GSTA-97)
/ship Step 11: a production install over a full install reports "no
changes" and leaves devDependencies at old versions after bun.lock moves,
so the session updater's ./setup left contributors on stale TypeScript,
Prettier and Agent SDK. A checkout with node_modules/typescript gets the
full frozen install. The import-closure scan now follows shipped code into
test/helpers (gstack-model-benchmark loads the providers).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes, ship invocation 2 (GSTA-97)
- Tests: contributor-branch failure row; bun.lock production closure never
reaches the dev-toolchain marker; real-Bun rows isolate HOME,
XDG_CONFIG_HOME and BUN_CONFIG_*; the import walker follows side-effect
imports; file header matches the two install branches.
- BROWSER.md quick start uses the frozen production install.
- CHANGELOG: the reclaim recipe also drops the Agent SDK's cache entries
(Bun hardlinks node_modules into its cache); Tests list is current.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): stub-bun wording matches what the fixtures check (GSTA-97)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.231.0 stamp
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(design-html): craft section and free craft check, adapted from Elaya design skills (GSTA-92)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(GSTA-92): restore the full CHANGELOG under the Unreleased entry; drop a $-digit literal from craft.md; count only craft-check executions in design-html-slop-gate
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(design-shotgun,design-html): carry the chosen archetype into approved.json; persist accepted craft exceptions in finalized.json (GSTA-92 phase 2)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(touchfiles): design-html-slop-gate selects on the craft check it runs (GSTA-92)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (GSTA-92)
A malformed or missing --accepted exceptions file now gets the full craft
check with nothing accepted, after a warning, still exiting 2. Before, it
printed nothing, and the craft section treats a missing CRAFT_RESULT as
'check unavailable', so one bad finalized.json switched the gate off
(found by both adversarial passes). The header comment and the craft
section now document the accepted-count suffix on CRAFT_RESULT. Tests
cover duplicate carried-forward exception ids and the slop-gate touchfiles
selection.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: scope --accepted to the same page; record current counts (GSTA-92)
The craft section passed --accepted whenever a finalized.json sat beside
the page, so a same-day Start fresh build inherited the old page's
exceptions. It now passes them only when evolving or rerunning a page it
finalized, records the count the check reports now, and writes [] when
nothing was accepted instead of the template's placeholder entry. A test
pins exit 2 for a clean page with a broken exceptions file.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: note the archetype handoff in the shotgun and design-html loops (GSTA-92)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
plan-ceo-review's parity cap moves 1.0999 -> 1.1006 for the approved COMPLETENESS IS
COVERAGE bullet (Garry 2026-10-25: "do it", parity caps to measured size; applied by
GStack Minder).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
- setup: follow a symlinked sections/ dir in the carved-pointer status check
- touchfiles: select preamble-hoist.ts alongside every preamble.ts entry
- section-manifest: exempt sections/preamble.md only for skills whose SKILL.md
carries the shared-preamble pointer
- skill-size-budget: growth ceiling measures SKILL.md plus its shared preamble
- host-conformance: tolerate a missing sections/ dir, as setup does
- skill-validation: read bin/gstack-skill-start directly
- skill-fixture: error messages and docblocks name the actual boundary
(harness-version non-behavioral note updated)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(design-html): craft section and free craft check, adapted from Elaya design skills (GSTA-92)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(GSTA-92): restore the full CHANGELOG under the Unreleased entry; drop a $-digit literal from craft.md; count only craft-check executions in design-html-slop-gate
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Every tier 2+ SKILL.md inlined the same ~23 KB preamble. It now renders once
per host into sections/preamble.md beside each tier 2+ SKILL.md; the SKILL.md
keeps a pointer that asks for the Read only when the file's id is not already
in context. Only sections byte-identical to the shared render move, so every
skill keeps exactly its pre-hoist paragraphs (verified across all 41 skills).
Parity caps for ten skills raised to their measured unions (owner-approved,
Garry 2026-10-25: "do it"); 63 size pins lowered and 26 deleted.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: flaky-fix pass — fragment-match reads the agent's report, ff-update reap counts its own sleepers, install-admission gets a measured timeout, judge parse errors name the judge (GSTA-91)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(qa-only): late scenarios freeze the fixture clock during setup and register their real outer budget (GSTA-91)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(harness): record the llm-judge parse-message change as non-behavioral (GSTA-91)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(land-and-deploy): Step 3.4 reads the ship policy and stops only on a real VERSION collision (#3318)
Under stamp-at-merge, verify the exact head stamp (base + one bump, changelog
headings bound to it) and ignore claims. Under claim-at-open, stop only when
another open PR holds the same VERSION or the base is at or above it. MICRO
bumps and versions below a sibling's claim pass.
Reported-by: Evgenii Lopatin (@exGeni)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(ship-policy): what /land-and-deploy Step 3.4 reads from the policy (#3318)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): Unreleased entry for #3318 /land-and-deploy Step 3.4
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(size): raise land-and-deploy size pins and parity cap for #3318 Step 3.4 (owner-approved)
Garry, 2026-10-24: "do it". Pins set to the measured sizes on 11 hosts
(+1,084 to +1,111 chars); maxSizeRatio 1.112 -> 1.125 (measured 1.1201).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(plan-design-review): say the design check uses OpenAI vision, not GPT-4o (#3350)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(health): compute the GBrain score in code so the rubric and formula can't disagree (#3351)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ios-qa): demo mode states its UI-only rule without overriding the skill's other rules (#3352)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(office-hours): diff against origin/HEAD, not a hard-coded origin/main with stderr hidden (#3347)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): #3347#3350#3351#3352 skill template fixes under [Unreleased]
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): plan-design focus rating in plain words, docsync own-call rule at the candidate --help, floor Create menu cropped at its rule (GSTA-65)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): floor actor answers Step 0D's focus menu in the template's own words (GSTA-65)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): floor actor identifies Step 0D's focus menu by its structure, not one wording (GSTA-65)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): GSTA-65 paid-side flaky repairs under [Unreleased]
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): the 0D focus picker moves into plan-design-finding-floor's owned fixture; no harness series reset (GSTA-65)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(evals): the 0D picker rows join the floor case's owner test (test-of-test ratchet)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.185.0 fix(evals): plan-design focus rating in plain words, docsync own-call rule, floor Create crop and 0D menu (GSTA-65) (#3358)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): a rejected API key is INFRA, never 131 assertion reds and reruns
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: register the credential-rejection fixture as free
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: keep the credential-rejection CLI replay off the Windows subset, like paid-rerun
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: name the Windows run in the curation reason
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.183.0 fix(evals): a rejected API key is INFRA, never 131 assertion reds and reruns (#3361)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(qa): materialize names the next write; fixture states the write boundary (GSTA-63)
qa-functional-webhook-fix (gate 39646086155) and qa-functional-cli-fix
(gate 39166935531) each wrote a stray placeholder beside the fixture
right after a fail verdict that read "final for this report root".
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.178.0 stamp
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(evals): the gate reruns failed cases once and reports a flaky green (GSTA-49 F1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ci: retrigger after retargeting to main
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(evals): a case red twice stays a real red for the report, the run, reuse and the train verdict (GSTA-49 F1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): keep a lone rerun-plan artifact off the plan manifest (run 39363705692)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: stamp v1.91.163.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(pregate): Dart import graph and test lanes (#3285)
Port of arlophoenix's #3285. The import graph reads Dart import/export/part
directives and resolves package: URIs through every tracked pubspec.yaml;
_test.dart files under test/ are tests. lanes runs each Dart package's
selected tests from its own root with flutter test or dart test (through fvm
when the package pins it). flutter/dart/melos/very_good CI jobs are lanes,
and run-step test paths resolve against working-directory and literal cd.
A missing Dart SDK or a .dart file outside any package leaves the lane
incomplete with a fix line; device tests (integration_test/, test_driver/)
are not unit lanes.
Co-authored-by: arlophoenix <arlo.phoenix@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(pregate): a --base that names a commit gets a branch fix, not an impossible fetch (#3269)
gstack-pregate --base <sha> refused with "fix: git fetch origin <sha>
--depth=1". That fetch can never create origin/<sha>: a short SHA fails
with "couldn't find remote ref", and a full SHA only reaches FETCH_HEAD.
A fork clone hits the same wall with --base upstream/main.
When origin/<base> does not resolve but <base> names a commit here and
no local branch (a SHA, a tag, another remote's ref), the refusal now
says --base takes a branch name on origin and suggests origin/HEAD's
branch. A local branch, or a name that resolves nowhere, keeps the
fetch fix: that is the unfetched or shallow checkout it repairs. Same
code, same exit 3, and pin files are still read only from the reviewed
origin/<base>.
Fixes#3269
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(pregate): Django, asset and tool-config lanes; init drafts from the repo (#3266, #3267, #3268)
- Django: settings modules, settings strings, include(), app migrations,
admin, templates, static files and project templates get framework edges
(lib/pregate/django.ts).
- Assets, stylesheets and dotfile tool config take a no-tests empty lane;
licence text under any name is documentation.
- gstack-pregate init drafts languages, runner notes and nearest-test
dependencies; never writes [].
- Review fixes on the #3285 port: untracked shell scopes leave a lane
unknown; Dart directives read to their semicolon; nested comments.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(pregate): init draft API is exercised directly, so init-draft.ts has a lane
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): restore the history a truncated rewrite dropped
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(pregate): outside-voice review fixes for the non-JS lanes
- Tool config is an allowlist: unknown dotfiles (.rspec, .husky hooks) and
stylesheets still need a lane; snapshot, golden and fixture trees and
.gstack/ are never inert.
- Django edges need Django evidence (manage.py or code importing django)
and settings assignments in code, not strings or comments.
- A cd after ||, &, control flow or braces leaves a lane unknown.
- Dart directives allow metadata and quoted semicolons.
- init drafts at most 256 dependencies (the schema limit); the rest are TODO.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(windows): pregate-dart and pregate-non-js join the POSIX-run pregate fixtures
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: release v1.91.161.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: arlophoenix <arlo.phoenix@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: y$un_ <forrest.sun527@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* security: isolate every gstack Bun entry point from the audited checkout's .env and bunfig.toml
Bun auto-loads .env, .env.local and .env.<NODE_ENV> from its cwd and runs a
cwd bunfig.toml preload before the program starts. gstack runs inside the repo
it audits, so a committed .env could steer state roots, the claude binary or
spend caps, and a bunfig preload ran arbitrary code in every bin and hook.
Every bun shebang, shell and skill caller, TypeScript spawn and compiled build
now disables both (--no-env-file --config=/dev/null, bunIsolationArgs(),
--no-compile-autoload-dotenv/bunfig), with a ratchet and hostile-fixture
regressions.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: name the directly executed scripts in the isolation ratchet
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: follow the isolation flags in touchfiles, copy lists, recipe assertions and the harness pin
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: keep browse/src/bun-child-config.ts unchanged so the native cookie qualification still binds
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(windows): the empty bunfig outlives its process so the timeline hook's detached repair child can read it
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.159.0 security: gstack's Bun entry points ignore the audited repo's .env and bunfig.toml (S1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: plan-mode render pattern accepts the isolation flags
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* perf(gen-skill-docs): stop emitting the "When to invoke" body section
The Claude catalog trim moved each skill's routing prose ("Use when...",
"Proactively invoke...", voice triggers) out of the frontmatter description
into a "## When to invoke this skill" section at the top of the body. Claude
Code reads only name + description to choose a skill and loads the body after
the skill is invoked, so that text cannot route anything and costs tokens on
every invocation. Keep the one-line trimmed description; drop the section.
The routing prose stays in each template's description, which
--catalog-mode=full and the other hosts still render. Tests that pinned the
section now assert its absence, or check the template instead.
(cherry picked from commit 707ccd6f38)
* feat(gen-skill-docs): keep voice triggers in the root routing block
The Claude catalog trim drops each skill's "Voice triggers (speech-to-text
aliases)" line from its description, and the body section that used to hold
it is gone. {{VOICE_TRIGGER_ROUTING}} renders them in the root router's
routing block instead: one "Voice trigger ... → invoke /<skill>" line per
skill, read from the templates' voice-triggers lists, so disabled-skill
filtering applies to them like any other routing line. Other hosts keep the
line in each description and render nothing here.
extractVoiceTriggers moves to the new resolver so the generator and the
resolver share one parser.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 645e75b1e8)
* chore: regenerate SKILL.md files without the "When to invoke" section
Output of `bun run gen:skill-docs --host all` after the previous commits.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit ff4c813337)
* test: refresh context-budget ceilings for the smaller skill bodies
`bun test/helpers/capture-context-budget.ts`. Against a recapture of the base
commit, 55 skills that lost the section get a lower ceiling and the root
gstack router rises by 532 tokens for the voice-trigger routing lines (5,369
tokens lower in total). devex-review and eval-plan differ from the committed
fixture only because it already lagged main. alwaysOnTotal is unchanged: the
catalog descriptions did not change.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit d886fcecc1)
* test: refresh the claude ship golden without the "When to invoke" section
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit f1789dca5c)
* test: lower the claude design-review size pin
The size guard (#3199) asks for it: claude/design-review shrank by 437 chars
without its "When to invoke" section.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 3a446fcc62)
* test: skip alias symlinks in the voice-routing check, keep unrelated budget ceilings, add #3129 CHANGELOG entry
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: rebuild the historical cookie approval with the dropped section, record the skill-fixture change as non-behavioral
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.157.0 perf(gen-skill-docs): drop the "When to invoke" body section from Claude SKILL.md files (port of #3129)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: thanhnguyentung95 <17350411+thanhnguyentung95@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: re-baseline old-model paid pins onto the current generation (TM3)
Repair the prosons capture prompt that tripped the reasoning_extraction
classifier, and restructure /setup-browser-cookies so the Aside probe,
decisions and target order are unambiguous.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG entry for the TM3 re-baseline under [Unreleased]
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: stamp v1.91.150.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.140.0 chore: stamp TM1 (Opus 5.5 model under test) and CHANGELOG
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(evals): Codex host adapter, real Codex cost, two-arm weekly and monthly census (GSTA-49 TM2)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: TM2 CHANGELOG under [Unreleased]; re-pin codex-host-runner in the harness manifest after the main merge
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ci: retrigger PR workflows (base changed to main after open; no pull_request run fired)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.149.0 chore: stamp TM2 (Codex host, census arms) and CHANGELOG
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): qa-only opts in to the read-only grammar; stderr-to-null forms accepted
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): qa-only checkpoint rule counts guarded "$B" stop as browser cleanup, like closetab
PR #3272's Opus gate 39217387697 (slice 8) failed qa-only-no-fix when the agent
stopped the browser inside the guard; the rule counted stop as a third probe
that needed a checkpoint. The prompt now names both cleanup children. A free
replay of the captured three guarded calls passes (and fails on the old rule);
stop before a probe, a disguised probe, stop --all and stop outside the guard
still fail.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(evals): register the qa-only stop-cleanup replay fixture in qa-only-no-fix touchfiles
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): docs-sync observer ignores an unexecuted candidate call that exited 127 at a missing path
PR #3295's gate (run 39223031058, slice 2) failed ship-docsync-current after Opus
called gstack-docs-candidate compare at a path missing the fixture-home segment,
got exit 127 (no such file or directory), and reran it at the declared path. The
observer now ignores such a call only when the absolute binary path does not
exist, the recorded result is exactly the shell's exit-127 not-found message for
that path, and a later call runs the same command at the declared path without
failing. A free replay of all 43 captured tool calls passes and fails on the
previous observer; negative controls cover an existing wrong-path binary, other
exits and messages, a missing/earlier/failing/changed retry, and non-candidate or
relative binaries. GStack Minder-approved.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.145.0 chore(release): stamp qa-only read-only opt-in, stderr forms, stop cleanup and docs-sync exit-127 exception
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.140.0 chore: stamp TM1 (Opus 5.5 model under test) and CHANGELOG
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): repair the five Opus gate reds from run 39161502626
- coverage audit: owned cd; followed by one && chain, wc -l on in-cwd files
- shared-libs: Claude Code 2.1.292 git --version probe, exact argv only
- ship hook: accept 'integrate the hook yourself' / 'combine ... by hand'
- qa-only: deadline starts only after the charter Write completes
- plan floor: tool-only parent session identifies the owned Create grant;
floor runner fails fast with PERMISSION_DIALOG_UNANSWERED
Each repair replays its captured run as a free regression with negative
controls. HARNESS_VERSION stays 6 (re-recorded from main's 5).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): ship hook manual-integration sentence rule; qa-only inspection uses Read/Glob; tool-only permission tests join their owner file
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): tpa-absent-linux accepts instructions the user follows themselves as the manual option
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): owned plan Edit menu binds to exactly one pending Edit, including unpublished ones
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): shared-libs read evidence counts a literal path loop whose output names each file
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: restamp to v1.91.142.0 (queue slot moved)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): investigate boundary fixture identifies the owner question by its continue/abort options
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): plan-design-with-ui focus check accepts the skill's design-completeness rating in the question body
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): phrasing sweep across the 108 gate rule cases; replay captured Opus paraphrases with negative controls
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): command-detector sweep — exact-count anchor, label slot, 2.1.292 worktree probe
- coverage audit (gate 39207508651 plan-eng-coverage-audit): output of exactly
known length (wc -l over literal in-cwd files) anchors the next owned read
at that line; a label's slot counts from the end and a later complete copy
voids the credit (review/specialists/testing.md prints '---')
- shared-libs-unsupported-git (39161502626): Claude Code 2.1.292's askPass-first
'worktree list --porcelain -z' cwd probe is Claude's own; the read-only Git
check is shared (repoGitRequests, isReadOnlyRepoGitRequest) and the free
regression replays every Git request of that capture
Each fix replays its captured command with negative controls. No threshold,
trial count, case kind or judge changed. HARNESS_VERSION stays 6.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): shared read-only command grammar for fixtures; docsync opts in (GSTA-49)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(evals): read-only grammar controls are POSIX-only; pin fail-closed on Windows (GSTA-49)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(evals): docsync grammar corpus forms run on POSIX only; Windows fails closed (GSTA-49)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): echo/printf join the read-only grammar; docsync literal reads stay inside the fixture home (GSTA-49)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): docsync keeps Git reads out of grammar lines; sed -n paging, composed-cat completed reads, config dir listable (GSTA-49)
Fable 5.1 (CI's eval model) read the grammar's 'Join them with ;, && or ||' as
covering Git reads: PR E2E 39186278010 failed 5 docsync cases on 21 joined
commands. The interface now says joins cover only the grammar's own reads and
Git, Preamble, lifecycle and candidate commands each run as their own Bash call.
- read-only grammar: sed -n with a line-range print script (file or pipe)
- docsync: a trailing ; on a declared read is a harmless wrapper; the completed-
read check credits a cat inside an accepted grammar line (not piped, no cd);
the Claude config dir is listable and settings.json readable while
.claude.json and every other config file stay denied
- focused Fable reruns: ship-docsync-missing-asset and ship-docsync-failure pass
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: stamp v1.91.143.0 (GSTA-49 shared read-only grammar)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(pr-selection): scan shebang and .ts imports, fail closed on scan errors, classify repo config safely
A1-1: strip a leading #! before scanImports at every site, treat bun/node
shebang scripts as code, pick the loader by extension (the TSX loader
misread 15 .ts files), and restore the full gate when any other import
scan fails. Broadens selection only: 0 (file, case) pairs lost vs main,
41 files move from no-consumer to consumed.
A1-2: FREE_ONLY_PR_FILES gains six repository-config files, capy/ is
derivable, and a full-gate file is labelled 'full-gate input' instead of
'real unknown dependency'. The replay MISS check honours the same audited
free-only exemptions as the selector.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(test-health): report gate cases and known cost per PR run, lead with cost per merged PR (A1-3)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(testing): correct the PR fallback section, document the lockfile decision (A1-3, A1-4)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(harness): record the A1 test-pr-profile.ts change as non-behavioral (selection only)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(pr-selection): exercised-path consumers and a shadow selection block (A2-1, A2-2, A2-3)
exercisedConsumers() unions touchfiles, the test-file import closure, executable
skill shell and the bins recorded trials ran (test/helpers/exercised-commands.json).
selectPrProfile reports what that map would select in prCoverage.shadow and never
changes the real selection; a map-only diff selects no paid case.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(exercised-map): union-only refresh with a fail-closed contract, census refresh, MAP_GAP and the replay receipt (A2-1, A2-4)
bun run test:exercised-map refreshes from a census run or local artifacts and
writes nothing on unavailable (exit 3) or partial (exit 4) input. The paid report
prints non-blocking MAP_GAP lines; --replay pins 0 misses over the 47 recorded
gate reds.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(test-health): report shadow savings as a lower bound and split red drops into activation misses and flaky drops (A2-3)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(testing): document the exercised-path map, its refresh contract and shadow metrics
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(harness): record the A2 test-pr-profile.ts and paid-report.ts changes as non-behavioral
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(fixtures): register the exercised-map replay fixture as free (read by scripts/exercised-map.ts --replay)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(release): v1.91.127.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* Revert "chore(release): v1.91.127.0"
This reverts commit 79e3ef6c63.
* chore(release): v1.91.130.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>