The checkout-owned full wrapper reads GSTACK_CAPY_MIN_WRAPPER through
gstack_support_env_get(gstack_source_root) and compares it with the
bootstrapper revision it was handed, so the rule can change without
recopying the Drive skill. The bootstrapper keeps only what a stale checkout
cannot do: clone, fetch, read the remote minimum, fast-forward, exec.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
docs/capy-install.md describes the three layers (Drive bootstrapper, full
wrapper, installer), the lazy install, the GSTACK_LAUNCH line, install
admission, baking gstack into a Capy snapshot, and that recovery after an
interrupted fast-forward completes or refuses the pending install stages
(checking out an older commit is not a rollback). docs/CHANGELOG_STYLE.md
(the release doc; there is no docs/RELEASING.md) says when
GSTACK_MIN_REVISION may be raised.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
capy/skill/gstack/ is the Drive skill's source of truth. scripts/install.sh
is a frozen bootstrapper: it prints gstack-capy-skill: wrapper <n> (<path>),
clones or fetches under .gstack-capy-install.lock, reads the remote
capy/support.env (FETCH_HEAD), fast-forwards a clean unpinned checkout below
GSTACK_MIN_REVISION (refusing dirty, diverged or pinned checkouts with the
exact commands; GSTACK_CAPY_AUTO_UPGRADE=0 disables), and execs the
checkout's own bin/gstack-capy-session with GSTACK_CAPY_LOCK_HELD=1 so the
held lock is never taken twice. Offline it says the remote minimum is
unknown. A Drive copy older than GSTACK_CAPY_MIN_WRAPPER prints an owner
action (CAPY_WRAPPER_STALE). SKILL.md: check at session start, install
lazily before the first workflow, the GSTACK_LAUNCH line, the trailer rule,
the subagent first-report line, gstack-pregate sealed before any push, and
the autoplan/DRIVER.md pointer. The context-budget fixture gains the skill's
entry.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
--check fetches and prints current|behind <installed> -> <remote> (<n>
commits); the default fast-forwards to the remote default branch tip and
reinstalls (bin/gstack-capy-install on a Capy install, else ./setup
--refresh-registered), completing a pending reinstall on the next run. It
refuses (UPGRADE_REFUSED, exit 3, nothing changed) a dirty tracked byte, a
diverged commit, a pinned checkout, the incoming Bun floor and a held
.setup-lock; never stashes or resets; an unreachable remote is
UPGRADE_FETCH_FAILED. Fetches are receipted (fail-open). The unattended
skill-end UPGRADE_AVAILABLE line is followed by UPGRADE_COMMAND naming it.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
B1a: an older run directory prints GSTACK_VERSION_CHANGED once and migrates legacy decision ids; a newer one refuses.
B1b: submit binds hand-run records (fence, table, severity list, No findings.), attested binds need --attempt,
--attempt is optional with one open attempt, --unavailable/--failed close an outside voice native_only, and submit
caches the plan-reality report by Implementation-plan hash.
B1c: revise reviews a revised plan in the same run as one recoverable transaction (reopen on hash drift plus Eng,
add newly in-scope phases, .r<rev>/.v<k> archives, gate_rev+1 at the gate); PLAN_SECTIONS_INVALID and next --scaffold;
PLAN_CHANGED / PLAN_SOURCE_CHANGED drift hints.
B2a/B2b: user challenges carry changes; agreeing voices with the same changes on a confirmed finding recommend b with
both remedies shown (or the reconcile proposal); accepted changes print APPLY and become pending amendments that next
and export refuse past until revise --incorporates names them or --withdraw drops one; all as-is; partial replies,
DECIDED block, carry-forward and rerun demotion.
Mutating verbs pass admission (GSTACK_CAPY install verdict; unattended Bun minimum; override recorded as a deviation).
Intentional pin rewrite: test/autoplan-answer-invalidation.test.ts reopen tests now revise --incorporates before rerun.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
RunState gains gstack_version, plan_input/heading, scope_flags, plan_revision, amendments and plan_reality; voices
record receipt kind and reviewed hash. New pure modules: Implementation-plan review hash, scaffold and drift lines
(B1c); gstack_version stamp and legacy decision-id migration (B1a); install-verdict and Bun-minimum admission
with a local verdict shim until lane A's lib/install-verdict.ts lands.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
bin/gstack-autoplan-snapshot.ts exports its section scanner and review projection, and initializes only a plan with
no section headings by wrapping it.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Findings and decisions carry the user challenge's `changes` value; decisions record recommended_basis, origin,
carried_from and chosen_text; validate refuses a complete run with an unsettled gate (ARTIFACT_GATE_UNSETTLED) and
prints attested=<n>. The gate reply grammar gains `all as-is` and resolves partial replies against prior answers
(field wave B2a/B2b).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Troubleshooting anchors for each and the regenerated doctor components table (field wave lane B-core).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The GSTACK_LAUNCH line carries PATH=<dir>:$PATH when the certified Bun is not
first on PATH, plus GSTACK_CAPY=1 and GSTACK_INSTALL_VERDICT, and
GSTACK_LAUNCH_PATH: <dir>; the doctor runs with that PATH. A supported Bun in
$BUN_INSTALL/bin is reused instead of downloaded again. Project pins are read
with bin/gstack-runtime-pins.ts (CI lanes included): when every exact pin is
gstack's verified version the archive is installed alongside a different PATH
Bun; any other exact pin is RUNTIME_PIN_CONFLICT. Both ./setup runs are
skipped when this HEAD was set up with the same hosts, model and browser flag
and the check passes (never after a fast-forward); a failed setup ends with
gstack: fail setup and is retried next run. --check certifies only;
GSTACK_CAPY_LOCK_HELD=1 accepts the bootstrapper's held lock; result anchors
come from the generated components table; REV_NOTE names bin/gstack-upgrade.
Intentional pin change: test/gstack-capy-install.test.ts --revision trailer
now names <root>/bin/gstack-upgrade (the old text named a command that never
existed).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
bin/gstack-install-verdict.sh (Bash) and lib/install-verdict.ts (TypeScript)
are the one reader of the install verdict gstack-capy-install writes to
<state root>/install-verdicts/<sha256(checkout realpath)>.json (checkout,
HEAD, workflow and required components, planning-only pins, trailer). The
source checkout and capy/support.env resolve through gstack_source_root /
sourceRoot, which follow an installed root's .source-path.
gstack-skill-start, after SESSION_KIND: an unattended session (any host)
refuses on a PATH Bun below the supported minimum; with GSTACK_CAPY=1 an
unattended or explicit spawned session also refuses without a passing
verdict for this checkout, HEAD and workflow (INSTALL_UNVERIFIED). A refusal
prints the INSTALL: row, an install-refused instruction block bound to its
SESSION_ID, GSTACK_RESULT ... status=refused run=- and exits 3. Ambient
spawned sessions warn; GSTACK_ALLOW_UNSUPPORTED_RUNTIME=1 admits and says so.
capy/support.env declares GSTACK_MIN_REVISION and GSTACK_CAPY_MIN_WRAPPER.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
gstack-doctor --check gains --min-revision <v>|unknown: below it the revision
row FAILs with REVISION_BELOW_MINIMUM naming the Capy wrapper or
bin/gstack-upgrade; unknown says so and never claims the minimum. The runtime
and pins rows name a supported Bun found in $BUN_INSTALL/bin (not on PATH)
with the export/GSTACK_LAUNCH fix (gstack_bun_launch_dir, one helper in
bin/gstack-bun-version.sh). --for a planning-only workflow (autoplan, the plan
reviews, office-hours) reports a repo test-pin mismatch as SKIP pins
(planning-only; ...). New result codes UPGRADE_REFUSED, UPGRADE_FETCH_FAILED,
REVISION_BELOW_MINIMUM, CAPY_WRAPPER_STALE, INSTALL_UNVERIFIED with
troubleshooting anchors; REVISION_UNMET's fix names bin/gstack-upgrade.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
autoplan/DRIVER.md (from autoplan/DRIVER.md.tmpl) is what a parent agent on any host
reads instead of autoplan/SKILL.md: phase order and scope flags, the next/submit/
answer/revise/export loop with the plan-specified submit --record/--attest/
--unavailable, revise --incorporates/--withdraw and next --scaffold, the reviewer
RESULT FORMAT, the gate grammar including all as-is, the run files, the result codes
and the coordinator contract, every list rendered from code (117 lines). gen:skill-docs
emits it as a Claude asset, so normal, out-dir and dry-run inventories and the
freshness check cover it. gstack-autoplan --help and the first next print
DRIVER: <root>/autoplan/DRIVER.md, resolved through an install root's recorded
.source-path (new lib/source-root.ts) (field wave item 13).
Intentional pin change: test/gen-skill-docs-checks.test.ts asset inventory gains
autoplan/DRIVER.md.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Each clause stating a measured quantity (a unit, or a number after measured/costs/
takes/took) needs its own receipt; misses print unreceipted_numbers=<n> and one
NUMBER_UNRECEIPTED: <clause> line each. A line claiming a decision rule must quote
it or link its file:line (unquoted=<n>). Either miss maps to the existing verdict
(incomplete unattended, repair otherwise). RECEIPT_RE accepts dot paths and needs
a hex letter or a commit/backtick context for a sha. New pure checkPlanReality(planText)
runs the same checks over plan prose for gstack-autoplan submit (field wave item 12).
The unreceipted= text token is now pinned as well as the JSON.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
UI scope reads the Implementation plan only and needs a rendered file path or a UI
term next to a visual noun; bare UI words stay weak evidence (sections load, no
Design phase). Scope records sources {ui,dx} (flag|marker|detected), --no-dx turns
DX off, a first-line <!-- gstack-autoplan-scope: ... --> marker is read and never
written, and the first next prints SCOPE: evidence plus a SCOPE_PIN hint. The
snapshot tool's scope output carries uiRequired from the same detector and
autoplan Step 2 uses it instead of a prose grep (field wave item 11).
Intentional pin change: test/review-checklists.test.ts Scope literal and the
source= line shape (source=ui:detected,dx:detected).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Gate item labels restart at every gate revision, but decision rows were minted
as <run>-<label>, so a second gate reused the first gate's ids and
gstack-artifact validate failed the export (ARTIFACT_DUPLICATE_ID). Revisions
after the first mint <run>-r<rev>-<label> through one decisionId helper, and
exported tasks block on the current gate's plan approval.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(codex): --effort <level> sets GSTACK_CODEX_EFFORT for one run
/codex review --effort medium (or --effort=medium) prefixes each
run-with-timeout dispatch with GSTACK_CODEX_EFFORT=<level>, which outranks
codex_effort and the per-mode default; --xhigh becomes shorthand for
--effort xhigh. The probe keeps owning validation. A missing value, a value
that is not one lowercase word, or conflicting flags stop instead of falling
back.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(codex): per-run effort prefix reaches the rendered /codex review dispatch
Runs the rendered review fence against the fake codex: no prefix uses
codex_effort, GSTACK_CODEX_EFFORT=medium|xhigh wins over it, an unknown level
never reaches codex. Step 1 check pins --effort tokens and the stop rule.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(codex): document codex_effort and --effort; Challenge runs at high, not xhigh
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(changelog): [Unreleased] entry for /codex --effort
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(codex): --effort reaches the probe as an allowlisted request level, parsed before the mode and checked before the paid probe
The level now travels as run-with-timeout --request-effort '<effort-level>'
(placeholder grammar ^[a-z]*$) instead of an agent-built env prefix, and the
probe names /codex --effort when it rejects one. Effort flags count only right
after /codex or its mode word and are removed before mode detection. Step 0.5
runs check-effort before probe-model, so a bad level makes no Codex call even
on a cold cache. Tests cover all five dispatch fences and the zero-call cases.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(codex): per-request --effort in model-policy, CHANGELOG behavior changes, TODOS follow-ups
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: stamp v1.91.93.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(codex): effort flags sit among /codex's leading flags; the probe names an unfilled '<effort-level>' placeholder
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(codex): per-request row in the effort precedence table, in-tool help names /codex --effort, late-flag notice
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(codex): binding tripwire sees the request-effort dispatch; valid and unfilled levels through Step 0.5 and every fence; doc accuracy
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: John Nunemaker <nunemaker@gmail.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>
Every outside-review gate, execution included, reads P0-P3 labels in label
position, table cells and severity words; an unreadable label is unverified
(unparsed_severity) and "Verdict: not ready" with no severity blocks with
FINDINGS: unspecified. The owned journal reader collapses Claude Code
2.1.293's post-compaction copies (equal apart from uuid, parentUuid and
message.usage), so /autoplan's guard no longer denies with tool_identity,
init_own or a false disarm. /plan-eng-review with writes forbidden ends DONE
with PERSISTED: no and a final PERSIST: line; /ship names it when no Eng
Review is saved.
Fixes#3105Fixes#3106Fixes#3107
Co-authored-by: Kolla Prakyath <177159691+kolla23@users.noreply.github.com>
Co-authored-by: Mr-B-1 <214900604+Mr-B-1@users.noreply.github.com>
.gitattributes pins nested bin/, hook shims, lib/cso/images and scripts/app
to LF, and setup rewrites copies an older checkout left with CRLF, leaving
locally edited files alone with a warning (#3110). The timeline Stop hook
reads the slug from gstack-slug's cache and hands a miss to a detached,
locked, negatively cached repair child (#3103). The /setup-gbrain smoke test
writes its page to a temp file instead of piping into gbrain put (#1675).
Co-authored-by: Mr-B-1 <214900604+Mr-B-1@users.noreply.github.com>
Co-authored-by: Andrei Bacu <63974644+Peaky8linders@users.noreply.github.com>
Co-authored-by: Elliot Drel <156480527+ElliotDrel@users.noreply.github.com>
Git Bash hands native Bun C:/ paths while gstack-hook-check looked them up as
/c/, so every TypeScript hook was refused and team-mode auto-update held every
release since 1.91.31. The checker maps Bun's paths back to the shell spelling,
the auto-updater lets the incoming release's own checker decide (installed
checker only as a fallback, hook-check-unavailable when neither verifies), and
docs/troubleshooting.md gives stuck installs one recovery command.
/gstack-upgrade and /spec guards use the --show-prefix root check, gstack-wtree
treats drive-letter --git-path answers as absolute, and setup refuses to
replace a runtime root that is or contains its own checkout, Kiro's in-place
root included (#3084), with --status suggesting the move. New sourced helper
bin/gstack-path-spelling.sh and TS twin lib/path-spelling.ts.
Co-authored-by: yuriysan <63948747+yuriysan@users.noreply.github.com>
Co-authored-by: y$un_ <3579304+szsunyuan@users.noreply.github.com>
Co-authored-by: Frederik Reventlow <267160539+dmfrede@users.noreply.github.com>
Co-authored-by: skleinbe-ny <226563731+skleinbe-ny@users.noreply.github.com>
Co-authored-by: bkermen <184220642+bkermen@users.noreply.github.com>
Co-authored-by: Drew Jankowski <3200063+andrewkjankowski@users.noreply.github.com>
#3097: on a managed gbrain 0.60 brain every transcript source was path-less,
so every managed import into it was refused (owner_unavailable). Each
transcript source is now bound to its own checkout under
<state root>/gbrain-transcript-sources/<id>/; path-less sources are migrated
on the next run and resumed checkpoints are admitted first; the checkout holds
one amended snapshot commit once every page has its file. Sources held by
another owner are left alone with the owner and commands named; nothing is
bound under an ephemeral state root. Classic brains are unchanged.
#1315: global-discover reads each Claude Code session's recorded cwd (whole
lines up to 1 MiB, longer lines skipped and counted) and resolves it through
git to its worktree root instead of decoding the project directory name.
Co-authored-by: Basim Rauf <22585821+Simba3696@users.noreply.github.com>
Co-authored-by: Akagilnc <12123308+Akagilnc@users.noreply.github.com>
The paid CSO producer gives `/cso` the Agent tool users have, so
independent review and repair verification can run in the evaluation. The
producer's receipt now counts subagent tokens.
browse resolves its proxy from --proxy, BROWSE_PROXY_URL, then HTTPS_PROXY,
HTTP_PROXY and ALL_PROXY (BROWSE_PROXY_URL=direct opts out), translates
NO_PROXY to Chromium bypass rules with loopback always kept, and hashes the
proxy and NO_PROXY rules into the daemon config so a differing environment is
refused with the variable named. Unparseable standard variables warn and go
direct; browse stop always stops (#915, supersedes #916).
Safe directories and targets resolve through one realpath
(fs.realpathSync.native), fixing Windows 8.3 temp paths (#3104). Bun children
get an empty private bunfig instead of --config=NUL, which panicked Bun
1.3.10 on Windows (#3085).
Co-authored-by: ningfeemic-dev <239259264+ningfeemic-dev@users.noreply.github.com>
/cso sets GIT_CONFIG_GLOBAL=/dev/null on every platform (Git for Windows 2.56
rejects NUL), shared by childEnvironment and the eval and producer Git
environments, with a Windows-safe test that `git config --global --list` is
empty. On macOS the local Docker socket resolves without opening it when Bun's
realpathSync throws EOPNOTSUPP; Linux admission and the local-Unix-only rule
are unchanged. /test-audit and /ship loop over file lists zsh does not
word-split, with a static test against `for x in $VAR` in generated bash.
/setup-deploy stops and writes nothing when nothing is deployed yet;
/land-and-deploy runs a recorded command trigger only with explicit approval
before claiming revision proof. TODOS.md records the open P2/P3 bugs by area,
the Wave 9 parked items and the feature themes.
Closes#3082. Adopts #3094, #3095, #3096 and #3109.
Co-authored-by: marcode <244097767+vilano93@users.noreply.github.com>
Co-authored-by: Nathan <196341+nathanshox@users.noreply.github.com>
Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com>
Co-authored-by: Andrey <95643518+Alfabit7@users.noreply.github.com>
* v1.91.79.0 feat(eval-plan): /eval-plan tier 1, lane-check, evidence verify, coordinator contract, owner brief, contributor-PR mode, banned terms (multi-agent wave PR E)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(spec,review): fail closed when the coordinator contract cannot be read; restore the omitted-Army sentence
The spec --execute spawn captures `gstack-autoplan contract` before piping
the archive, so a lane never starts without the contract; the C9 fixture
installs its gstack-like checkout (bin, lib, a contract stub) at every
host's global root. Review Step 5.8 keeps the pinned
'without claiming specialist coverage' wording.
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>
* v1.91.70.0 feat(unattended): artifact contract, unattended session kind, findings-derived review log, gate list
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.72.0 feat(autoplan): unattended runner next|submit, pluggable outside voice, review checklists, spec-loop cap
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(b-runner): atomic lock creation in spend-ledger, judge bundle skips runner-only sections, fixture env spelling
- lib/spend-ledger.ts: create the lock by linking a complete temp file so a
contender never reads an empty lock and breaks a live owner (CI admitted 20
of a cap of 8 under contention); unreadable locks break only by mtime age.
- test/helpers/workflow-judge-input.ts: exclude manifest runner_only sections
(the B4 checklists) from the judge bundle; the judge rates the interactive
workflow. test/workflow-judge-input.test.ts expects the same set.
- test/helpers/autoplan-run-fixture.ts: spell the runner's session kind
without the literal the free-suite environment scan rejects.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.74.0 feat(review): plan reality rows, sideways review and cso sweep, investigate recipes
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: register the investigate carve case and map Reality rows to real headings in the review checklists
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: pin the corrected Reality rows obligation rows
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(investigate): use allowlisted placeholders in the flake and polluter fences; select the investigate carve case on PTY changes
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>
* v1.91.77.0 feat(ship): two-stage gstack-pregate, gstack-regen registry, intent-based issue links (multi-agent wave C-pregate)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(pregate): keep the bin-driving pregate tests off the Windows subset; pin files are free-only for eval selection
The three C-pregate tests that spawn bin/gstack-regen, bin/gstack-pregate,
bin/gstack-issue-links and bin/gstack-ship-receipt do so through
test/helpers/pregate-fixture.ts runBin, so the Windows curation's source
scan of the test file never saw a bin/ spawn and shipped them to
windows-latest, where CreateProcess cannot exec a shebang (14 failures in
windows-free-shard 2 and 5). Each is now a KNOWN_WINDOWS_INCOMPATIBLE entry
with the precise reason. .gstack/generated.json and .gstack/pregate.json
join FREE_ONLY_PR_FILES: no paid case reads gstack's own pin files (the
tools read origin/<base> of the repo they run in, and paid cases run in
fixture repos), so touching them no longer restores every gate case.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(harness-version): record the FREE_ONLY_PR_FILES pin-file entries as non-behavioral
scripts/test-pr-profile.ts is a pinned shared-harness file; the two
.gstack pin-file entries change selection only, never a case verdict.
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>
Helper run IDs matched pii.phone.e164/pii.cc, so successful paid audits were
withheld and failed. Credential-class matches (and source env.kv values such
as a planted canary, quoted bare) still withhold and fail with rule IDs and
counts; helper identifiers are masked and other PII/legal spans are redacted
in place without changing status.
* v1.91.70.0 feat(unattended): artifact contract, unattended session kind, findings-derived review log, gate list
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.73.0 feat(ship): repo ship policy, gstack-restamp stamp-at-merge, tree receipt, evidence bundle, ship receipt
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ci): result-codes is selection data, receipt counts come from files, C-stamp tests leave the Windows subset
- scripts/pr-dependencies.ts: lib/result-codes.ts joins SELECTION_DATA_MODULES; its fix: prose names commands a person reruns, not files the module consumes (test/pr-dependencies.test.ts traced review cases through it to bin/gstack-next-version)
- ship/sections/pr-body.md.tmpl: gstack-ship-receipt write reads --gate/--ci from agent-written .gstack/tmp/ship-*.json files and --spend-usd from the allowlisted <spend-usd> placeholder (generated-bash lint: no free text in commands)
- scripts/lib/windows-curation.ts: the five C-stamp test files spawn bin/ shebang scripts through test/helpers/restamp-fixture.ts, which the source scan misses
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ship): the receipt step names where each input comes from
The workflow judge (eval-slices 3, median 3/4) found pr-body's gstack-ship-receipt command demanding a tree receipt, CI counts and a spend figure no earlier step produces, with RECEIPT_INVALID halting publication. The command now takes only Step 16 stage 4's lane counts (file-written JSON); --receipt is added only when Step 16 wrote .gstack/tmp/tree-receipt.json; RECEIPT_INVALID says to fix the named input file and rerun. The unused <spend-usd> allowlist entry is removed.
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>
* v1.91.70.0 feat(unattended): artifact contract, unattended session kind, findings-derived review log, gate list
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.72.0 feat(autoplan): unattended runner next|submit, pluggable outside voice, review checklists, spec-loop cap
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(b-runner): atomic lock creation in spend-ledger, judge bundle skips runner-only sections, fixture env spelling
- lib/spend-ledger.ts: create the lock by linking a complete temp file so a
contender never reads an empty lock and breaks a live owner (CI admitted 20
of a cap of 8 under contention); unreadable locks break only by mtime age.
- test/helpers/workflow-judge-input.ts: exclude manifest runner_only sections
(the B4 checklists) from the judge bundle; the judge rates the interactive
workflow. test/workflow-judge-input.test.ts expects the same set.
- test/helpers/autoplan-run-fixture.ts: spell the runner's session kind
without the literal the free-suite environment scan rejects.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(spend-ledger): accept Windows' status-only report of the killed child
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>
* docs(designs): multi-agent wave plan with autoplan review record and artifacts
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(designs): record owner approval of the multi-agent wave gate (all recommended options)
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 helper artifact path tripped the secret redactor: the run ID's
13-digit epoch reads as a phone number, some 32-hex IDs as wallets.
Validate paths against the helper layout; schema-shaped ID components
are accepted by shape, every other component still goes through redact
- the provider was killed at exactly --budget after cell start, before
the helper deadline (start + budget) and before finish; give it the
budget plus a 300 s reporting grace (evaluator graceSeconds)
- Claude producers stream events (stream-json --verbose
--include-partial-messages) and add usage per message, so a timed-out
receipt keeps tokens, cost, turns and the last text
- failed post-run checks name the check in the receipt reason
* v1.91.68.0 fix(cso-eval): failed receipts with usage for post-run integrity failures; Claude producers stop mutating the sealed source
Claude Code adds <dir>/.mcp.json as a sandbox deny path for every --add-dir.
The producer passed the sealed source as one, so bubblewrap left an empty
0444 .mcp.json mount point there that Claude Code cannot unlink from the 0555
directory, and the post-run source check failed with no receipt.
- claudeExecArgs no longer adds the source directory
- post-run integrity failures write status:failed receipts carrying the
check code/reason plus usage, tokens and estimated cost (no output or
artifacts)
- INVALID_PRODUCER_SOURCE / PRODUCER_CHANGED_SOURCE_MODE name the first
offending relative path and the rule it broke
* fix(cso-eval): run the trusted launcher outside Claude's sandbox; keep every other command sandboxed
Claude Code 2.1.263 forces every Bash command into its bubblewrap sandbox
while CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set, excludedCommands
notwithstanding. Inside it the launcher's owner check sees root as nobody
and the Docker socket is unreachable, so comprehensive cells degraded to
static-only results.
- drop CLAUDE_CODE_SUBPROCESS_ENV_SCRUB for producers; pass --settings with
sandbox enabled, failIfUnavailable, no unsandboxed fallback, no
auto-allow, and excludedCommands naming only the exact launcher path
- ClaudeAdapter.run refuses to start the agent
(CLAUDE_PRODUCER_SANDBOX_POLICY_MISMATCH) unless args and env carry
exactly that policy
- README containment note and CHANGELOG updated
* test(doctor): split the two multi-run doctor tests so each fits Windows' 30s per-test budget
On windows-latest each bin/gstack-doctor run costs ~4-5s. The cached/live probe test made 7 runs and the artifacts-sync test 5; both hit the 30s per-test timeout, which killed doctor mid-output ("no row codex probe") and then EBUSY on cleanup. Same failure on #3093 and the fix/runtime-root-source-guard PR. Every assertion is kept; each test now makes at most 4 runs.
* feat(hosts): Antigravity CLI (agy) host
Adds Google's Antigravity CLI as an experimental host through defineHost():
skills in ~/.gemini/antigravity-cli/skills/gstack-*, a runtime root with
.source-path for /gstack-upgrade, names equal to their gstack-<skill>
directories, name+description frontmatter with the 1024-char limit, the
Gemini overlay, and a preamble glossary mapping Claude tool names to
Antigravity's documented tools (run_command, view_file, write_to_file,
replace_file_content, grep_search, find_by_name, invoke_subagent,
ask_question).
Setup: ./setup --host agy (alias antigravity), --host auto on the agy
binary or ~/.gemini/antigravity-cli, never a Gemini-CLI-only ~/.gemini.
Registry tier, --status known roots, uninstall and team-init cover it.
Gemini CLI's ~/.gemini/skills and settings are never touched.
Co-authored-by: Shagun Prasad <109907086+0xshae@users.noreply.github.com>
Co-authored-by: ManchalaSashank <134257068+ManchalaSashank@users.noreply.github.com>
Co-authored-by: VoIP Expert <5742479+voipexpert@users.noreply.github.com>
Co-authored-by: Mattias Petersson <93470851+KiDDarn@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(agy): golden refresh after main merge; agy is recorded as an installed render host
* v1.91.67.0: CHANGELOG, version
---------
Co-authored-by: Shagun Prasad <109907086+0xshae@users.noreply.github.com>
Co-authored-by: ManchalaSashank <134257068+ManchalaSashank@users.noreply.github.com>
Co-authored-by: VoIP Expert <5742479+voipexpert@users.noreply.github.com>
Co-authored-by: Mattias Petersson <93470851+KiDDarn@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
