github garrytan/gstack v1.91.242.0
gstack v1.91.242.0

3 hours ago

gstack v1.91.242.0 (weekly release)

First tagged release: the 96 versions since v1.91.146.0 (the week before it), one line each; the full changelog has every earlier one.

Team-mode installs follow the stable branch, which now points here; gstack-config set update_channel main follows every merge instead (docs/releases.md).

  • 1.91.242.0 (2026-10-26): gstack-context-bill now bills a real install.
  • 1.91.241.0 (2026-10-26): The weekly OSV scan on main is green again, so the weekly release cut can run.
  • 1.91.240.0 (2026-10-26): Proactive skill suggestions default to the four core skills.
  • 1.91.239.0 (2026-10-26): BROWSER.md now says that gstack's own browser still trusts the compromised eMudhra intermediates, and how to check (#3338).
  • 1.91.238.0 (2026-10-26): Five /ship frictions the unattended lanes hit (GSTA-102).
  • 1.91.237.0 (2026-10-26): An unstamped PR can change a release output again (GSTA-96 on #3434).
  • 1.91.236.0 (2026-10-26): The merge queue now refuses a PR that never ran /ship.
  • 1.91.235.0 (2026-10-26): An issue we intend to fix later now stays open under the parked label instead of being closed.
  • 1.91.234.0 (2026-10-26): Weekly tagged releases, and a stable channel that team-mode auto-update follows by default.
  • 1.91.233.0 (2026-10-26): /plan-tune's inferred profile no longer pins at 1.0 after a few reviews, and it now records how many answers moved each dimension.
  • 1.91.232.0 (2026-10-26): The setup-browser-cookies workflow judge now has a preregistered calibration corpus, and its structured-output calibration is recorded as held, so the judge stays on today's request (GSTA-91).
  • 1.91.231.0 (2026-10-26): A fresh install is about 520 MB smaller: ./setup installs production dependencies only.
  • 1.91.230.0 (2026-10-26): see CHANGELOG.md
  • 1.91.229.0 (2026-10-26): The OpenSSF Scorecard workflow uploads its results with github/codeql-action/upload-sarif 4.39.0 (from 4.38.3), recreated from Dependabot's #3307.
  • 1.91.228.0 (2026-10-26): Skills start at once on Windows again: the workflow lease lock no longer depends on symlinks (#3330).
  • 1.91.227.0 (2026-10-26): Windows: gstack's record bins stop losing review, question, learning and timeline records when Git Bash path conversion is off (#3415).
  • 1.91.226.0 (2026-10-26): /review can re-review just its own fixes after a fixing pass, under the same rules as /ship (#3339).
  • 1.91.225.0 (2026-10-26): /design-html builds landing pages around one visitor action and pages that look finished, without inventing proof; adapted from Elaya's design skills (GSTA-92).
  • 1.91.224.0 (2026-10-25): /context-restore now says when commits landed after a checkpoint was saved, instead of offering finished steps as the plan.
  • 1.91.223.0 (2026-10-25): /plan-tune's inferred profile finally moves: a clicked answer is logged as the question's registered option key, not its label.
  • 1.91.222.0 (2026-10-25): Five flaky tests now fail only for real defects, and a judge reply that isn't valid JSON says so in its failure line (daily flaky-fix pass, GSTA-91).
  • 1.91.221.0 (2026-10-25): The session-start updater no longer skips because of its own session's workflow lease, and the autostash tests stop failing their first pass in Free Tests.
  • 1.91.220.0 (2026-10-25): A design doc edited in host plan mode no longer goes stale for the plan reviews (#542).
  • 1.91.219.0 (2026-10-25): Local paid runs from eval:bg now set EVALS_RUN_ID, so the native-capture cases start instead of failing in 0 seconds.
  • 1.91.218.0 (2026-10-25): gstack-team-init required now blocks skills when its gate can't run, instead of letting them through.
  • 1.91.217.0 (2026-10-25): Windows free tests now also run on every push to main.
  • 1.91.216.0 (2026-10-25): /sync-gbrain refuses an active autopilot before it touches the brain's source list (#3360, part 2; ported from #3362 by @exGeni).
  • 1.91.215.0 (2026-10-25): An unattended /ship leaves its receipt in a file the parent can read, and the parent is told to read that file (GSTA-88).
  • 1.91.214.0 (2026-10-25): gstack-brain-sync --publish-removals --yes no longer prints list: unbound variable when it finishes, and it now removes its temp list and releases the sync lock.
  • 1.91.213.0 (2026-10-25): The CI image and the Ubicloud free-suite VMs move off Node.js 22.20.0 to 22.23.4, and both now check the Node archive's SHA-256 before unpacking it (#3354, port of #3355 by @michael-sumner).
  • 1.91.212.0 (2026-10-25): /careful no longer asks about words inside a commit message (#1060; ported from #3221 by @Bhumika-1432006).
  • 1.91.211.0 (2026-10-25): gstack-diff-scope sees Python tests and nested test directories (#3335).
  • 1.91.210.0 (2026-10-25): /autoplan works when Claude Code's project directory is a subfolder of the repository (#3296).
  • 1.91.209.0 (2026-10-25): The free test suite no longer rewrites a contributor's global git pre-push hook (#3353).
  • 1.91.208.0 (2026-10-25): The Capy install guide says that the team-mode session-start updater also waits for live workflow leases.
  • 1.91.207.0 (2026-10-25): Per-repository session counts include sessions from removed Claude Code worktrees (ported from #3334 by @Shweta-Mishra-ai).
  • 1.91.206.0 (2026-10-25): A repo that keeps .gstack/ out of git can give pregate a policy, and name the CI lanes a local run satisfies (#3286).
  • 1.91.205.0 (2026-10-25): /ship's Step 9 can re-review just the fixes after a fixing pass, and a narrowed pass can never be the review that ships (#3339).
  • 1.91.204.0 (2026-10-25): An unattended run is told to end with GSTACK_RESULT only when its skill can write that line.
  • 1.91.203.0 (2026-10-25): Asking gstack to fix a failure no longer always opens /investigate (#3157, #3158).
  • 1.91.202.0 (2026-10-25): Team-mode session auto-update waits for live gstack sessions instead of moving the checkout under them (#3363).
  • 1.91.201.0 (2026-10-25): /ship's review army and /plan-eng-review now ask for one severity scale, CRITICAL or INFORMATIONAL, the same scale /review, the specialist JSON and the review checklist already use (#3349).
  • 1.91.200.0 (2026-10-25): /cso doctor no longer calls a Go repository "stack: python".
  • 1.91.199.0 (2026-10-25): When /sync-gbrain refuses because a gbrain autopilot is running, it now says which process it found and what to do.
  • 1.91.198.0 (2026-10-25): A second-opinion reviewer that says "not ready" is no longer reported as clean.
  • 1.91.197.0 (2026-10-25): Pregate gives touched Rust files a test lane, and runs a nested pnpm or vitest package with its own runner (#3344).
  • 1.91.196.0 (2026-10-25): /land-and-deploy no longer stops parallel PRs with a false "VERSION drift detected".
  • 1.91.195.0 (2026-10-25): Four skill prompts stop contradicting themselves or their code.
  • 1.91.194.0 (2026-10-25): A read-only repo can now opt in to Memorable recall, one remote at a time, and a corrupt policy store no longer turns the recall veto off.
  • 1.91.193.0 (2026-10-25): Windows: the browse terminal agent stops respawning every 60 seconds and stops flashing a console when Bun came from npm (#2295; ported from #3357 by @adammartin0087).
  • 1.91.192.0 (2026-10-25): Merge trains stop refusing correct heads and stop passing damaged CHANGELOGs.
  • 1.91.191.0 (2026-10-25): gstack-version-bump write --changelog moves the branch's [Unreleased] entry under the new version, and /ship Step 12 stops treating a provisional queue pick as a verified slot.
  • 1.91.190.0 (2026-10-25): The weekly model-policy freshness check reads OpenAI's deprecations page again (#3155).
  • 1.91.189.0 (2026-10-25): A stalled apt mirror can no longer hold a Free Tests shard for 20 minutes, PR runs now see main's branch layout, and gstack's install default moves to Bun 1.4.4.
  • 1.91.188.0 (2026-10-24): Pregate maps extensionless .jsx imports to their tests (#3340).
  • 1.91.187.0 (2026-10-24): Four docs now say what the code does: the unattended run contract, the gate reply grammar, the session-kind override and voice triggers.
  • 1.91.186.0 (2026-10-24): Approving an autoplan run no longer fails one time in ten because its run id looks like a card number.
  • 1.91.185.0 (2026-10-23): Three flaky paid eval cases get repairs: three harness gaps closed and one fixture rule moved to where the agent reads it.
  • 1.91.184.0 (2026-10-23): The office-hours attempt lifecycle test no longer races the wall clock.
  • 1.91.183.0 (2026-10-23): A rejected API key no longer turns a gate into 131 assertion reds and 131 reruns.
  • 1.91.182.0 (2026-10-23): gstack installs on a project that pins Bun 1.4.4 again.
  • 1.91.181.0 (2026-10-23): /cso can run its contained runtime checks.
  • 1.91.180.0 (2026-10-22): The /cso docs say what the qualified catalogs now allow.
  • 1.91.179.0 (2026-10-22): docsync-fault-interface fits its budgets under load again.
  • 1.91.178.0 (2026-10-22): A /qa run no longer gets a hint that another report root could change its verdict.
  • 1.91.177.0 (2026-10-22): The /cso runtime promotion workflow can finish.
  • 1.91.176.0 (2026-10-21): A qualified /cso runtime set can be released again after the S1 shebang change.
  • 1.91.175.0 (2026-10-21): A free-suite flake now keeps the assertion that failed.
  • 1.91.174.0 (2026-10-21): Two paid eval flakes from the 2026-10-20 trains are repaired at their cause, with no threshold, trial count or case kind changed.
  • 1.91.173.0 (2026-10-20): Merge trains can merge slot 2 onward.
  • 1.91.172.0 (2026-10-20): gstack now works the way Capy Captains run work: every decision goes to the Captain (or the person) in plain words, plan approvals arrive in a fixed before/after shape, each thread keeps a record of who approved what, and /ship's PR body shows before/after images of what changed.
  • 1.91.171.0 (2026-10-20): A restarted /ios-qa daemon resumes the device session instead of relaunching the app.
  • 1.91.170.0 (2026-10-20): /autoplan no longer stops a healthy run with a false "event order" or "init" denial when Claude Code is slow to write its session journal.
  • 1.91.169.0 (2026-10-20): The docs-sync fixture now accepts joined Git reads, for loops over literal file names and a pipe into tr as reads, and tells the actor that the Claude config dir is off-limits. The late-result fixture now says what its one repair corrects.
  • 1.91.168.0 (2026-10-20): Four QA paid cases stop failing on valid or unclear agent behavior: qa-only-no-fix accepts reads joined with its exact bookkeeping calls, and the QA-callers fixture says where the handoff check goes and stops counting the explicit plan check as a wasted rerun.
  • 1.91.167.0 (2026-10-20): Two paid detectors now accept the rewordings Opus 5.5 actually uses, with their negative controls kept (daily flaky-fix pass, GSTA-57).
  • 1.91.166.0 (2026-10-20): Two load-sensitive free tests from the flaky ledger now measure what they test.
  • 1.91.165.0 (2026-10-20): The Version Gate accepts an unstamped READY head under merge trains.
  • 1.91.164.0 (2026-10-19): Merge trains are on for gstack: .gstack/ship-policy.json now carries the train block.
  • 1.91.163.0 (2026-10-19): A gate red on one test now reruns that test once instead of the whole gate, and a pass is green with a flaky note.
  • 1.91.162.0 (2026-10-19): The evals workflow carries merge trains: a train's own gate publishes its record and the gstack/full-gate check, bisects run one executor per prefix, ready --screen dispatches a real screen, and a main backstop gates any tree no green train covered.
  • 1.91.161.0 (2026-10-19): gstack-pregate works on Django, Dart and Flutter repos, and on branches that only touch assets or tool config.
  • 1.91.160.0 (2026-10-19): Dart and Flutter projects get the right reviewers and the right test command.
  • 1.91.159.0 (2026-10-19): Security: the repository gstack runs in can no longer configure gstack's own programs.
  • 1.91.158.0 (2026-10-19): gstack-config set plan_mode_preamble off leaves the plan-mode preamble out of every installed skill, for people who never use plan mode.
  • 1.91.157.0 (2026-10-19): Claude SKILL.md files no longer carry a "When to invoke" body section, which saves about 20 KB across 56 skills.
  • 1.91.156.0 (2026-10-19): The weekly marathon's office-hours case can run its review formatter again, and its validator now checks cap fixes the way the formatter does.
  • 1.91.155.0 (2026-10-19): A busy page no longer locks up the browse daemon.
  • 1.91.154.0 (2026-10-19): /cso can verify Rails repairs in a read-only checkout, its retained Git history no longer brings back credential files the snapshot leaves out, a repair whose external assertions fail is now reported as ASSERTION_FAILED instead of a misleading INCOMPATIBLE_INPUT, and a security assertion can accept several safe rejection statuses while still requiring the secret to be absent.
  • 1.91.153.0 (2026-10-19): An outside review whose findings are untagged prose no longer reads clean because a "no issues" phrase appears somewhere in it, and a clean Codex review that says "no actionable regressions" no longer reads unverified.
  • 1.91.152.0 (2026-10-19): /cso now starts and finishes on ordinary repositories that hold a nested Git repository, a long patch history, or a Docker socket on macOS 27.
  • 1.91.151.0 (2026-10-19): Three contributor fixes: a saved "never ask" now sticks for /plan-eng-review's structure question, /context-save and /context-restore close three checkpoint gaps, and a new how-to covers the first production deploy.
  • 1.91.150.0 (2026-10-19): The paid evals that still pinned older models now run on the current generation, and two cases that went red on the move are repaired at their cause.
  • 1.91.149.0 (2026-10-19): Paid eval cases can now run on the Codex host, and the Monday census runs two arms: Claude Opus 5.5 and Codex gpt-6.1-sol.
  • 1.91.148.0 (2026-10-19): Weekly seed PRs now get the credential scan as well as the free suites.
  • 1.91.147.0 (2026-10-19): The free-suite duration seeds are current again.

Don't miss a new gstack release

NewReleases is sending notifications on new releases.