mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-15 21:07:20 +01:00
v1.96.0.0
71
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Garry Tanandcapy-ai[bot]
|
796cceaeb0 |
ci: Trunk Dynamic CI observes free-suite and macOS regressions, learning only (GST-1400) (#4012)
* ci: Trunk Dynamic CI observes free-suite and macos-named-regressions, learning only (GST-1400) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog.d: Trunk Dynamic CI learning-only fragment (GST-1400) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the observer check red case and the required-check vote caveat (GST-1400 review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: a missing Trunk token skips the step, not the job (GST-1400 fix-check) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: secret guards catch lowercase, bracket and toJSON references; docs cite the pinned source (GST-1400 voices) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog.d: name job-start failures as the one red case (prose lint) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
55637db835 |
test: cut the last two behavior-guessing LLM judges; check review-bot history facts for free (GST-1403) (#4014)
* test: cut the qa anti-refusal and voice-tone judges; check review-bot history facts for free (GST-1403) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: count assertions follow the deleted judge file (GST-1403) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
ec1f2aa6a4 |
fix(redact): a short sha is not a phone number or a bc1 wallet; plan-reality receipt and pregate fixture flakes (#3998)
* fix(redact): a short sha is not a phone number or a bc1 wallet; plan-reality receipt and pregate fixture flakes (GSTA-279) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: the review_loop_grant sha exemption and the fixture origin's maintenance setting (GSTA-279) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): name the fragment for the branch and narrow its claim to the review_loop_grant position (GSTA-279) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
781f928ccf |
test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)
* test: remove the skill-prose clarity LLM judges (GST-1371) Removes the 21 eval cases where an LLM scored a skill's instruction text for clarity, completeness and actionability, with their registrations, input builders, response cache, calibration corpora, the cookie-workflow manual-review approval and scripts/judge-controls.ts. The three remaining skill-llm-eval judges keep their prompts, thresholds and samples; the file's supervision wall shrinks to fit them. Outcome judges are untouched. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: pin the retired judge-control script and cookie manual-review record as deleted (GST-1371) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: register the manual-review fixture as free (GST-1371) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: keep the orphaned clarity-judge calibration corpora for a follow-up deletion (GST-1371) Deleting the four corpus directories alone puts the diff over the /ship review ceiling; they serve no configuration now and go in a follow-up. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(todos): file the clarity-judge removal follow-ups (GST-1371) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: keep skill-bundle section paths POSIX so references dedupe on Windows (GST-1371) windows-scoped-shard (run 41918796523) failed 'cross-skill references retain complete bytes once': path.join gave the section entry a backslash path, so a reference to the same section was not recognized as already bundled. 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a73184629f |
ubi-runner: recovery bundles, recover, and a dormant results sink (GST-1220) (#3961)
* test: failing-first recovery bundle and results sink tests (GST-1220) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ubi-runner: encrypted recovery bundles, recover, --counted, and a dormant VM-side results sink (GST-1220) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ubi-runner: bind bundles to their VM and owner, stretch the bundle secret, keep the last good sink snapshot, stop the pusher before the final push (GST-1220 review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ubi-runner: keep command words after -- in the run record; tests for the run record, counted reattach and input guards (GST-1220) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: ubi-runner recovery troubleshooting covers counted reattach and tiered-verify reruns after SINK_FLUSH_FAILED (GST-1220) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: failing-first tests for the cross-family findings: runner-owned --pass names, a --sink-spelled option value, a corrupt bundle on counted reattach (GST-1220) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ubi-runner: forward only caller-exported --pass names, copy run-record words while parsing, open the bundle before a counted reattach (GST-1220 cross-family read) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: --pass forwards the caller-exported value, not a same-named runner local (opt, src, sink) (GST-1220 fix-check) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ubi-runner: --pass forwards the value captured from the caller environment at startup, never a live variable (GST-1220 fix-check) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: ubicloud skill says --pass forwards the exported value from runner start and never the recovery key or sink URL (GST-1220 docs audit 2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: changelog and TODOS 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> |
||
|
Garry Tanandcapy-ai[bot]
|
ade35bc813 |
v1.94.29.0 R56: everything in gstack earns its place (principle, evidence gates, inventory) (#3837)
* eval-plan: a no-gstack arm needs masking, install and audit lines prereg --check now refuses a loaded comparison whose ## No-gstack arm section lacks masking:, install: or audit:, or says none for one of them (PREREG_NO_GSTACK_ARM). On Capy, run agents inherit the instruction to load the user-drive gstack skill, so the arm hides both Capy drives, checks that no gstack is installed, and audits drive reads; an arm that read a gstack skill file is contaminated and gets zero credit (TESTING_INTERNALS.md #no-gstack-arm). The prereg template, /eval-plan, troubleshooting and the two passing prereg fixtures carry the new lines. eval-plan's paragraph was dieted to hold its context-budget ceiling. Evidence: safety: keeps the no-gstack control uncontaminated (Captain order, FOUN-32 via GGST-6) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: the R56 evidence ledger, gstack-inventory and skill-bill EVIDENCE docs/inventory/evidence.json holds one row per inventory key: the skill folders discoverTemplates() finds (root skill as gstack, symlinked folders excluded) plus seven shared parts, 71 keys. lib/inventory.ts validates each row by its status's own fields, with named codes (LEDGER_*), and joins the ledger with lib/context-bill.ts buildBill. bin/gstack-inventory writes docs/inventory.md, --check validates (exit 1 with codes), --json prints. Paid dispatches per run for /ship and /autoplan are quoted from their own docs and found by line, so a moved citation fails --check (INVENTORY_SOURCE_MISSING). Every current row is grandfathered and seeded from GEVA-2's table (org-gstack-gbrain/research/gstack-part-evidence.json): in-flight fair tests and proposed registry rows as plans, earlier unfair results under prior with why (stub, unmasked, ceiling, ...), five safety rows. gstack-skill-bill prints the skill's EVIDENCE line. Evidence: plan none (owner ruling R56, GST-914); the ledger itself is the measurement record Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ETHOS 9, Earn Its Place: factory, /write-skill and /autoplan carry it Garry, 2026-11-02: "Also work this principle of only include it if it is beneficial and good into gstack". ETHOS.md principle 9 states the rule, the fair test (claude_code preset, frontier models per R54, masked no-gstack arm), the R48 Why-null cycle, the safety exception, and measure biggest first, linking docs/inventory.md. factory.md item 8 cites it, trimmed elsewhere to 3,298 of 3,300 bytes with no rule dropped. /write-skill's edit ladder step 2 is the evidence rule and section 4 adds the Evidence: commit line. /autoplan's CEO phase lists each part a plan adds to gstack with its evidence or owned, dated plan; two redundant lines went to keep autoplan under its size pins (pins lowered by 17). CONTRIBUTING.md "Adding a new skill" and docs/skills.md point at the ledger. Skill-Size: 3273→3666 bytes (write-skill/SKILL.md.tmpl) Skill-Size: 12738→12721 bytes (autoplan/sections/ceo-phase.md) Evidence: plan none (owner ruling R56, GST-914); write-skill and autoplan rows stay grandfathered untested Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fixup! inventory: the R56 evidence ledger, gstack-inventory and skill-bill EVIDENCE Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: list the evidence table's other names and its unmapped rows Ledger rows carry aliases (the name GEVA-2's table uses where it differs from the key, such as upgrade for gstack-upgrade), and docs/inventory.md lists them beside the installed-name rule. Unmapped rows are labeled as evidence-table rows, and the ranking notes that a skill's on-demand files can also be a shared row's. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: the first inventory snapshot and the R56 changelog fragment docs/inventory.md is generated by bin/gstack-inventory at the previous commit: 71 parts ranked by load per run, 0 helps, 0 no-effect, 0 hurts, 16 untested with a plan (4 fair tests under way, 12 proposed), 50 untested with plan none, 5 safety. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: investigate's step procedure is a fair-test CUT-CANDIDATE (GST-814) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: the inventory snapshot after investigate's no-effect row Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: only the seeded backlog may be grandfathered, so a new part's row is checked (review fix) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: devex-review and retro name their GEVA-2 registry rows (R56-11, R56-12) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: the inventory snapshot after the review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: a concrete plan is a path, gstack-inventory never writes into a gstack install, and the ledger checks aliases, r48 and prior.why (review fixes) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * inventory: investigate's no-effect row notes that only Opus 5.5 was measured Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: the inventory snapshot after the review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: R56 counts after investigate's row; grandfathering and the install guard Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: register inventory-grandfathered.json as a free fixture free-suite (1) at |
||
|
Garry Tanandcapy-ai[bot]
|
a1da77e6d4 |
v1.94.20.0 test(review): one file per review and harness pin, so independent repins merge cleanly (GST-1084) (#3903)
* test(review): one file per review and harness pin, so independent repins merge cleanly (GST-1084)
The reviewer-brief pins move from the table in test/review-packets-removed.test.ts to
test/fixtures/review-pins/{files,replays,brief-bodies}/*.json, and the harness pins from
scripts/harness-version.json to scripts/harness-pins/<path>.json. Every entry is ported
unchanged. New tests prove a stale pin still fails and that two repins of different pins
merge cleanly with a real git merge-tree.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (GST-1084)
- unadmitted() and the specialist coverage use Object.hasOwn, so an inherited name such as toString is not an admitted replay
- MUST_PIN names every non-specialist reviewer source; deleting one of those pins now fails
- writeManifest writes the pins before the manifest head; pin parse errors name the file
- mergePinEdits removes its repository when setup throws, and the merge tests clean up every merge they made
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: name the changelog fragment for the branch (GST-1084)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: the harness guard pins one file per harness file (GST-1084)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ship-release): GST-1031 re-pin route reads per-file harness pins (GST-1084)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: GST-1031 route reads per-file harness pins
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(test-audit): harness guard pins 42 files
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(harness-version): a pin ahead of the manifest version counts as drift (GST-1084)
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>
|
||
|
Garry Tanandcapy-ai[bot]
|
f6d6215f4e |
v1.94.10.0 ci: run Windows checks by path (ship-90-90 plan D, GST-1135) (#3904)
* ci: run Windows checks by path (ship-90-90 plan D, GST-1135) Windows Setup E2E skips a version-only package.json change; a new Windows Scoped Tests workflow runs a PR's changed Windows-safe tests when it touches path, file-name or process code. windows-smoke is unchanged. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (round 2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: describe path-scoped Windows checks 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> |
||
|
Garry Tanandcapy-ai[bot]
|
4b43d4fd43 |
v1.93.14.0 ci: each free-suite job's timeout follows the plan's runner wall (#3850) (#3877)
* fix(free-tests): each free-suite job's timeout comes from the plan (runner wall + flaky retry + setup), not a fixed 20 minutes (#3850) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: free-suite job timeout follows the plan (#3850) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(free-tests): narrow the CI matrix in the #3850 wiring test; keep free-suite job names 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> |
||
|
Garry Tanandcapy-ai[bot]
|
daf661374f |
v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847)
* Attribute every paid trial's cost: bind label-named records by testName, price aborted SDK sessions from streamed usage, model-free cases cost $0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: case cost adds streamed sessions to record sums and keeps record cost_known
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: the paid report headline counts ledger-only session cost once
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: a cost-only record never sets the trial model
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: recordE2E writes cost_case_id only for a registered label-named case
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG for paid-report cost attribution (Unreleased)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: the headline adds only streamed session cost; cache writes without a 5m key
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: how the paid report prices a trial and what stays cost-unknown
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* Price PTY sessions from their transcripts: pin a session id, sum the session's and its subagents' usage into the ledger's streamed_cost_usd
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: transcript pricing never throws from a PTY ledger writer
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: pin transcript-cost.ts as non-behavioral at HARNESS_VERSION 6
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: recognise --session-id= and --resume= forms
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG for PTY transcript pricing (Unreleased)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: PTY sessions priced from their transcripts
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: price PTY transcripts without adding a launch argument; native AUQ capture opts out
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: harness notes and CHANGELOG match the transcript claim
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(flaky): gstack-flaky run reruns a failed JUnit test once and ledgers the flake (GSTA-158)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(flaky): stream output, keep unreported runner failures red, fail-closed duplicates and nonzero reruns
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes
gstack-flaky never greens an incomplete run: a targeted rerun needs the
runner's summary proving the first run complete, otherwise (and always for
generic runners) the rerun repeats the whole command. A rerun clears a test
only when it exits 0 and the test passes once on its first attempt. Killed
runners exit 3 (FLAKY_COMMAND_KILLED) and signals are forwarded. The first
report is restored at --junit with reruns kept beside it; ids are redacted at
every output; the ledger gets its own GSTACK_FLAKE_LEDGER_JUNIT; fixtures are
registered in FREE_FIXTURES.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: latch cancellation and check whole-command rerun reports
A cancel forwarded to a runner that traps the signal now counts as killed for
every later attempt, so a cancelled job is never rerun or greened. A
whole-command rerun clears nothing when its report has a failed test, misses a
first-run test, or its runner counted failures outside the report.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: whole-command rerun when coverage or runner-flaky tests can fail the run
A coverage threshold or a fail-on-flaky policy fails a run for a reason a
narrowed rerun cannot reproduce, so either forces a whole-command rerun.
--junit refuses an existing file that is not a JUnit report instead of
deleting it.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(flaky): rerun the whole command by default; targeted rerun is opt-in
A rerun counts only on the runner's own full green verdict: exit 0, no failed
or missing test, nothing counted outside the report. That covers every way a
run can fail, which a narrowed rerun cannot (a coverage threshold with an lcov
reporter, a fail-on-flaky policy, a test never reached). --rerun-scope test
reruns the failed test alone, with its preconditions documented and the
complete-run checks kept as a safety net. An unreadable existing --junit file
is a usage error, not a crash.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: gstack-flaky CHANGELOG entry and standalone-binaries row (GSTA-158)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(flaky): quarantine registry for repeat flakes (GSTA-158 P2)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(flaky): bound renewal dates; match non-ASCII paths in check --base
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(flaky): reword the FLAKY_QUARANTINE_BASE hint so the egress scanner does not read it as a network op
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(agent-sdk): every SDK caller passes the claude_code preset or names why not
The SDK's default system prompt is a bare stub that drops the line telling the
model to run /skill through the Skill tool. runAgentSdkTest now refuses a
missing, empty or bare-string prompt; non-preset callers name a reason; a free
tripwire scans test/ and scripts/ for the same mistake.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: record the SDK prompt guard as a non-behavioral harness change and baseline its tripwire
harness-version: runAgentSdkTest validates systemPrompt before starting; every
live caller already passed the claude_code preset, so no verdict can change.
test-of-test ratchet: the tripwire's subject is the eval harness by design.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: name the preset literal callers pass and the unnamed-prompt refusal
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(eval-plan): frontier models under test (R54)
Haiku and Sonnet are not models under test. dry-run refuses a plan whose every
arm is Haiku or Sonnet unless --tier-question names what it asks about that
tier, warns on a mix, and re-costs the plan on Opus 5.5 and GPT-6.1 Sol.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(eval-plan): trim R54 skill prose and raise the eval-plan context ceiling
The R54 paragraph and CHECK: frontier bullet were cut to the minimum; the
exemptions and verdict rule stay in docs/TESTING_INTERNALS.md. The remaining
growth is the feature, so only the eval-plan eager ceiling moves (4887 -> 5458,
the capture helper's value); other skills' ceilings are left as they were.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(eval-plan): pilot start keeps the R54 refusal; --tier-question rejects a flag
Review pass 1 (full depth) found the frontier refusal could be skipped by
starting a pilot on Haiku or Sonnet arms behind a dry run made on other arms,
or behind a dry-run.json written before the check existed. startPilot now
refuses a pilot whose every arm is Haiku or Sonnet unless its dry run recorded
a tier question. dry-run --tier-question no longer takes the next flag as its
answer. The testing doc now says the frontier re-cost is printed for
comparison with the brief cap, not enforced.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(support-tiers): Windows CI in the present tense now that windows-smoke is required (#3806)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: empty commit for a clean check set at the same tree (cancelled orphan free-suite check at
|
||
|
Garry Tanandcapy-ai[bot]
|
4bbad24221 |
v1.92.77.0 wave(github): #3724 #3771 #3833 (#3846)
* test-free-shards: --ci-run --jobs k sub-shards inside one CI job (k=1 default), per-file JUnit counts (GSTA-203 PR 2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ci): ship ffmpeg in the eval image so the marathon design-motion case can run (#3687) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * shard-jobs: serial sub-shard gets what is left of the shard wall; register shard-jobs.ts in ship-measure touchfiles Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * shard-jobs: validate every sub-shard summary, bounded JUnit read, stricter --ci-verify records, unique count paths, no serial launch without wall Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * shard-jobs tests: non-hex plan id fixture; harness-version: shard-jobs FREE_ONLY entry is non-behavioral Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(test:free): exact root-bound JUnit path matching; serial timeout text names the wall the parallel phase left Adversarial pass 2 (GSTA-203 PR 2): a plain relative path now matches a planned file exactly, and an absolute or ../-prefixed path matches only when its prefix is the child's root, so an unplanned browse/test/x.test.ts is never credited to test/x.test.ts. The serial sub-shard's FREE_SUBSHARD_TIMEOUT text says how much of the shard wall the parallel phase left it. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(testing): real-home tripwire covers --jobs k>1 parallel sub-shards (docs audit docs-203-1) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(free): per-shard sub-shard k in the CI plan (--shard-jobs), free_jobs and windows_jobs dispatch inputs (k=1 defaults) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(free-tests): 10 x ubicloud-standard-8 at 4 sub-shards per shard (GSTA-203 PR 3 A/B winner); Windows stays at k=1 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (changelog names main's 20 x standard-4 baseline and the unchanged 80 vCPUs) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(testing): sub-shard default is the plan's per-shard k (docs audit docs-pr3-2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(free): run the #3680/#3679 BSD-userland regression on macos-named-regressions Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: macos-named-regressions runs the BSD-userland ubi-runner regression (#3680) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: Windows k=1 applies to the nightly suite since #3806 (docs re-audit after the main merge) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
68195c372e |
v1.92.60.0 test-free-shards: --ci-run --jobs k sub-shards inside one CI job (k=1 default) (GSTA-203 PR 2) (#3730)
* test-free-shards: --ci-run --jobs k sub-shards inside one CI job (k=1 default), per-file JUnit counts (GSTA-203 PR 2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * shard-jobs: serial sub-shard gets what is left of the shard wall; register shard-jobs.ts in ship-measure touchfiles Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * shard-jobs: validate every sub-shard summary, bounded JUnit read, stricter --ci-verify records, unique count paths, no serial launch without wall Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * shard-jobs tests: non-hex plan id fixture; harness-version: shard-jobs FREE_ONLY entry is non-behavioral Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(test:free): exact root-bound JUnit path matching; serial timeout text names the wall the parallel phase left Adversarial pass 2 (GSTA-203 PR 2): a plain relative path now matches a planned file exactly, and an absolute or ../-prefixed path matches only when its prefix is the child's root, so an unplanned browse/test/x.test.ts is never credited to test/x.test.ts. The serial sub-shard's FREE_SUBSHARD_TIMEOUT text says how much of the shard wall the parallel phase left it. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(testing): real-home tripwire covers --jobs k>1 parallel sub-shards (docs audit docs-203-1) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
d7154dba13 |
test:health and factory scorecard: leave reused main pushes out of free-suite flake counts (#3725) (#3822)
A main push that reused its merged PR's verified run (#3709) runs no shards and uploads nothing, so both readers counted it as a zero-flake run and diluted real flake rates under the 5% bar. reuseChecker (scripts/lib/ci-history.ts) marks a run with no artifacts and a green reuse job; readCiFlakeLedgers leaves it out and refills the window, readFreeRetries leaves it out of the free-retry count. One capped job listing per artifact-less run (40 per read); past the cap or on a failed listing the run counts as before, with a note. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
|
693ee7132a |
v1.92.53.0 fix(ubicloud): reap destroys only the caller's own VMs (GST-573) (#3756)
* fix(ubicloud): pack and usage on macOS, empty projects (#3680, #3679, #3678) pack builds its archive in two tar passes plus gzip, which bsdtar and GNU tar both accept, with COPYFILE_DISABLE=1 so Apple's tar adds no ._* files. vm_rows skips the blank row Ubicloud returns for a project with no VMs. usage parenthesizes its ternary for the one-true-awk and exits 1 on an unreadable list or size; the quota preflight logs that and defers to the API. Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (usage skips a VM destroyed since the list; spawn timeout) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (quota wait retries an unreadable usage) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog fragment for the ubicloud macOS and empty-project fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: TESTING_INTERNALS notes the quota preflight's unreadable-usage path Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ubicloud): reap destroys only the caller's own VMs (GST-573) reap, which every up runs first, destroyed any VM in the project whose TTL had ended, whatever owner created it. That broke the owner-scoped cloud-deletes rule. It now destroys only the caller's own expired and old TTL-less VMs and logs a count of other owners' expired VMs. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(ubicloud): trim the owner-scoped reap prose back under the context budget Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: TESTING_INTERNALS says the TTL reaper covers only this owner's VMs Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(ubicloud): restore the expiry and reap conditions in the trimmed reap prose Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
Garry Tanandcapy-ai[bot]
|
a563f47679 |
v1.92.51.0 ci: windows-smoke is the required Windows check; the six-shard suite runs nightly (GSTA-203 PR 1) (#3806)
* ci: windows-smoke becomes the required Windows check; the six-shard Windows suite runs nightly on main (GSTA-203 PR 1, R50) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (dispatch-ci skips a workflow the branch predates; harness decision; changelog fragment) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CONTRIBUTING names windows-smoke; TODOS for the round-2 review notes 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> |
||
|
|
74836e41d6 |
v1.92.41.0 fix(ubicloud): pack and usage on macOS, reap and up on an empty project (#3680, #3679, #3678) (#3746)
* fix(ubicloud): pack and usage on macOS, empty projects (#3680, #3679, #3678) pack builds its archive in two tar passes plus gzip, which bsdtar and GNU tar both accept, with COPYFILE_DISABLE=1 so Apple's tar adds no ._* files. vm_rows skips the blank row Ubicloud returns for a project with no VMs. usage parenthesizes its ternary for the one-true-awk and exits 1 on an unreadable list or size; the quota preflight logs that and defers to the API. Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (usage skips a VM destroyed since the list; spawn timeout) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (quota wait retries an unreadable usage) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog fragment for the ubicloud macOS and empty-project fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: TESTING_INTERNALS notes the quota preflight's unreadable-usage path Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
Garry Tanandcapy-ai[bot]
|
1cac25cb8e |
v1.92.33.0 fix(flaky): 2026-10-31 flaky pass — paid detector gaps, Windows cold first launches, fixture races, ubicloud pack index copy (GSTA-199) (#3697)
* fix(flaky): 2026-10-31 flaky pass: paid detector gaps, Windows cold first launches, cleanup and settlement races, ubicloud pack index copy (GSTA-199) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(ship-budget): name the child-list probe timeout so the literals check reads the spawn timeout unchanged Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (Step 11): linear passive-pitch clause scan, tokenized grep operands, harness diagnostic reset and early stderr Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog fragment for the 2026-10-31 flaky pass Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore(harness): non-behavioral HARNESS_VERSION decision for the llm-judge byte counter Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog fragment path and count Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(testing): llm-judge-aborted lists bytesReceived and lastByteMs Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * revert(flaky): leave the cso-snapshot SIGCONT fix for after the SBOM generator re-pin (GST-495) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
83ae96e086 |
v1.92.30.0 test(free): split files over the 60 s seed ceiling and the Windows doctor file, then reseed (GSTA-151 A) (#3585)
* test(free): split files over the 60 s seed ceiling and the Windows doctor file Eight free test files the fresh recordings put over the seed ratchet's 60 s ceiling, and test/gstack-doctor.test.ts (343 s on Windows), are split by describe block or test with shared helpers moved to test/helpers/. Test bodies are unchanged. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(todos): note the GSTA-151 seed-ceiling splits Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(free): reseed both duration seeds at this head Recorded by free-durations-record.yml (open_pr=false) run 40818261447 at |
||
|
Garry Tanandcapy-ai[bot]
|
4eff47c5cf |
v1.92.2.0 evals: no-gstack arms for the model panel, arm-benchmark, safety and routing evals (#3708)
* feat(eval-plan): results --check refuses a results table without its no-gstack rows Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(model-panel): a <model>#no-gstack arm per model, identity-keyed cells, one campaign, results.md (GST-468) Each panel model also runs as <model>#no-gstack: the same fixture, ticket, tools, limits, route and reservation, with no skill folder and no routing line. The arm identity keys the ledger attempt, test name, row and summary; candidate folders are named after the fixture project and the seed commit has a neutral author. summarize reads one campaign (run id and PREREG.md sha256) and refuses a duplicate cell; suggestionLine reads the skill arms only, so the preregistered particle-1 line is unchanged. renderResults writes results.md, which passes gstack-eval-plan results --check against the new test/fixtures/model-panel/PREREG.md (supersedes GSTA-173 for later runs). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(arm-benchmark): no-gstack arm on a pinned model, 3 paired trials, both-order paired judge, spend ledger (GST-469) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): no-gstack arm for the safety-rule and router evals (GST-470) GSTACK_SAFETY_ARM and GSTACK_ROUTER_ARM take a third value, none: the same fixture, tools and user request with no skill excerpt, rule text, step file or installed skill. Under none every behavioral check is recorded as an observation (none-arm-observations.jsonl) and never fails the case or writes contract-violations.jsonl; harness preconditions still assert. The four safety prompt builders (ship-evidence, codex-boundary, codex-consult, design-risk) and the router fixtures move into helpers; the rule, removed, current and before prompts stay byte-identical, proven against reference copies of main's code. pair-agent and ios-demo refuse none with the reason (NO_NONE_ARM). GSTACK_ROUTER_ARM now throws on an unknown value instead of silently running current. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: changelog fragment for the no-gstack arms in existing evals Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(arm-benchmark): arm-pair paired-judge calibration run (bar met 6/6, $7.22) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(paid-shards): keep loop-named panel and arm-benchmark cases selectable by --case The lanes moved each cell's testName into helpers, so the static detector no longer saw a computed registration and B4 failed for all eight cases. Same runtime test names; the paid runs are unaffected. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(tests): keep FREE_FIXTURES and the placeholder allowlist current for the no-gstack arms scripts/judge-calibration.ts is now an arm-benchmark paid touchfile, so it can no longer be a free consumer of test/fixtures/judge-calibration/** (CI free-suite 8). The eval-plan Step 5 fence names <prereg-path> and <results-path>; allowlist both as PATH placeholders (CI free-suite 19). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(eval-plan): cover a complete table after a partial one, --json output and the results usage error Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(eval-plan): keep the Step 7 coverage test as reviewed Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: name the changelog fragment after the branch slug Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: arm-benchmark project folder names and the arm-pair calibration corpus Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: keep the judge-calibration fixture README as reviewed Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(skills): describe eval-plan results --check 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> |
||
|
Garry Tanandcapy-ai[bot]
|
ca7bd684b1 |
ci(free-tests): run the free suite on ubicloud-standard-4 (week-1 revert rule for #3617) (#3710)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> |
||
|
Garry Tanandcapy-ai[bot]
|
5ba425af4b |
v1.91.376.0 feat(ubicloud): reattach to a live verify VM and checkpoint tiers (GSTA-158 P3) (#3615)
* feat(ubicloud): reattach to a live verify VM and checkpoint tiers (GSTA-158 P3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ubicloud): replay on reattach, tear down TTL-less VMs on HUP, trim skill prose (GSTA-158 P3) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
0cd2b4a9f9 |
v1.91.373.0 feat(eval-plan): require a no-gstack arm in every head-to-head preregistration (#3690)
* feat(eval-plan): require a no-gstack arm in every head-to-head preregistration Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(eval-plan): lint loadout arms by their model; refuse arms sharing a ledger attempt 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> |
||
|
Garry Tanandcapy-ai[bot]
|
44eeeb3c9b |
v1.91.372.0 feat(flaky): gstack-flaky reruns a failed test command once and ledgers the flake (GSTA-158 P1) (#3612)
* feat(flaky): gstack-flaky run reruns a failed JUnit test once and ledgers the flake (GSTA-158) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(flaky): stream output, keep unreported runner failures red, fail-closed duplicates and nonzero reruns Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes gstack-flaky never greens an incomplete run: a targeted rerun needs the runner's summary proving the first run complete, otherwise (and always for generic runners) the rerun repeats the whole command. A rerun clears a test only when it exits 0 and the test passes once on its first attempt. Killed runners exit 3 (FLAKY_COMMAND_KILLED) and signals are forwarded. The first report is restored at --junit with reruns kept beside it; ids are redacted at every output; the ledger gets its own GSTACK_FLAKE_LEDGER_JUNIT; fixtures are registered in FREE_FIXTURES. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: latch cancellation and check whole-command rerun reports A cancel forwarded to a runner that traps the signal now counts as killed for every later attempt, so a cancelled job is never rerun or greened. A whole-command rerun clears nothing when its report has a failed test, misses a first-run test, or its runner counted failures outside the report. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: whole-command rerun when coverage or runner-flaky tests can fail the run A coverage threshold or a fail-on-flaky policy fails a run for a reason a narrowed rerun cannot reproduce, so either forces a whole-command rerun. --junit refuses an existing file that is not a JUnit report instead of deleting it. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(flaky): rerun the whole command by default; targeted rerun is opt-in A rerun counts only on the runner's own full green verdict: exit 0, no failed or missing test, nothing counted outside the report. That covers every way a run can fail, which a narrowed rerun cannot (a coverage threshold with an lcov reporter, a fail-on-flaky policy, a test never reached). --rerun-scope test reruns the failed test alone, with its preconditions documented and the complete-run checks kept as a safety net. An unreadable existing --junit file is a usage error, not a crash. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: gstack-flaky CHANGELOG entry and standalone-binaries row (GSTA-158) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
48599bb8ae |
v1.91.371.0 ci(evals): a pr-summary run skips the readiness wait it never used (#3609)
* ci(evals): a pr-summary run skips the readiness wait it never used Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: CHANGELOG [Unreleased] entry for the pr-summary readiness skip Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: move the CHANGELOG entry to changelog.d/capy-gsta149-pr-summary-wait.md (fragments policy since #3654) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
cae783e6f4 |
v1.91.370.0 ci(free-tests): run the free suite on ubicloud-standard-2 from one runner/shard constant (#3617)
* ci(free-tests): one runner and shard constant for every event, dispatch overrides for sizing, per-shard memory and disk peak Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(free-tests): type the refused dispatch overrides Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(free-tests): run the free suite on ubicloud-standard-2 at 20 shards Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(testing): the free-suite runner constant, sizing overrides and RESOURCES line Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: CHANGELOG [Unreleased] entry for the standard-2 free suite Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: move the CHANGELOG entry to changelog.d/capy-gsta149-free-runner.md (fragments policy since #3654) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
5532345a10 |
v1.91.341.0 fix(ubicloud): no zombie VMs: owner required, 3h TTL, legacy sweep, leftover line (GST-118) (#3652)
* fix(ubicloud): no zombie VMs — owner required, 3h TTL, legacy sweep, UBICLOUD left line (GST-118) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: extend ubicloud runner and pregate-remote coverage (legacy-hours override, --keep, leak exit status, missing left= line) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (TTL checks only on create, leftover line via UBI_LEFT_FILE, pregate TTL from its deadline) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name UBI_OWNER as a prerequisite for test:ubicloud and the keyed remote pregate Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: changelog for GST-118 (unreleased) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: give the left-file parser spawnSync a timeout (spawnsync tripwire) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ubicloud): legacy sweep reaps only the caller's own TTL-less VMs (GST-324) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.341.0 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a8d60be09f |
v1.91.322.0 feat: narrow PR screens leave hub files to the train gate (#3587)
* Narrow screens leave hub files to the train gate; map size-ledger baselines and the careful mask awk Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pull_request runs stay broad, deleted hubs, READY and summary previews) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG for narrow screens (Unreleased) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: TESTING_INTERNALS describes narrow and broad PR screen policy Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: record test-pr-profile.ts as non-behavioral at HARNESS_VERSION 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> |
||
|
Garry Tanandcapy-ai[bot]
|
043feff8b3 |
v1.91.309.0 fix(flaky): one rule each in the judged review and Eng prose; a cancelled judge names what it was waiting on (GSTA-139 S3) (#3544)
* fix(flaky): give the judged review and Eng prose one rule each, and name what a cancelled judge received (GSTA-139 S3)
- review: Step 5.8 records an unresolved non-gate defect as open, and a repeat
pass's reruns are revalidation that run after smoke expiry in the same
PROBE_DIR with materialize once on the final pass (every sample of #3527's
red panel 40617200857 and its rerun named one of these). Nearby prose trimmed
so union, skeleton and host pins do not grow.
- plan-eng-review: drop the Eng-only em-dash Voice variant so the shared Voice
hoists; the Scope gate's Format precedence names em dashes (5 of 6 samples of
40634787316 named the near-copy Voice). Host size pins lowered.
- llm-judge: a cancelled judge request prints llm-judge-aborted with timing,
429 waits and stream event counts (no content), so the next workflow-judge
deadline (train 35 gate 40660626349) names its cause.
- benchmark: the Phase 6 example no longer lazy-loads the hero image.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(review): earlier passes link checkpoints; only the final pass materializes (all 3 samples of the focused judge run at
|
||
|
Garry Tanandcapy-ai[bot]
|
766093df3e |
v1.91.300.0 test(flaky): 2026-10-28 free Linux timing pass: ubicloud fake ssh, coordinator clone, qa-fix-loop late clock (GSTA-139 S4) (#3543)
* test(flaky): ubicloud fake ssh dispatches on the remote command, not on a '-O' in the checkout name (GSTA-139) The fake ssh's *-O* arm, meant for 'ssh -O exit' (whose last argument is the host, so it never matched), caught any remote command whose path held '-O': dest work/ubi-run-O????? whenever mkdtemp's first random character was O. Sync then failed with exit 2 (tar child 141) or every phase exited 0, in about 1.3 s, before UBI_RUN_TIMEOUT could fire: Free Tests 40534568946 (:417, 2) and 40638411165 (:454, 0). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(flaky): the coordinator clone reads the fixture origin through git, not by copying its objects directory (GSTA-139) Every push into the fixture origin leaves a detached 'git maintenance run --auto' there (local transport drops the shard's GIT_CONFIG_COUNT backstop), which creates and deletes objects/maintenance.lock after the push returns. A local clone copies origin.git/objects entry by entry, so an entry appearing or vanishing mid-copy fails it; --no-local never lists that directory. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(flaky): qa-fix-loop late-timeout freezes its clock through setup and registers the outer budget (GSTA-139) The #3413 qa-only template: the late scenario's real setup ran inside its 1000 ms mocked work budget and a 1160 ms native deadline, so under load the attempt never started (0/10 under 24 busy loops, attempts length 0). The clock now stands still from the body's start until the capture begins, the capture gets exactly 1000 ms, and the native deadline is the registered 6080 ms outer budget. Gate edit: captureBudgetMs is asserted equal to 1000. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(flaky): keep run ids out of the coordinator-clone regression comment (GSTA-139) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (qa-fix-loop slow-setup keeps the setup-subtraction check the late clock freeze dropped) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: GSTA-139 S4 CHANGELOG entry and the local-push maintenance gap in TESTING_INTERNALS 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> |
||
|
Garry Tanandcapy-ai[bot]
|
415e343b52 |
v1.91.298.0 chore: remove Dia from gstack (cookie source and qualification harness) (#3551)
* chore: remove Dia from gstack (cookie source and qualification harness) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: pin the removed Dia harness so pregate selects a lane for its deleted scripts Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG names every doc the Dia removal touched 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> |
||
|
Garry Tanandcapy-ai[bot]
|
b3e94a3f8d |
v1.91.279.0 eval:select exemptions and ETHOS.md registration (#3499), below-floor review rulings (#3504, #3485), Windows curation, GSTA-121 follow-ups (#3515)
* Eval selection exemptions, review-floor rulings and the GSTA-121 follow-ups Release metadata (NOTICE.md, LICENSE, licenses/**) no longer restores the full paid gate and ETHOS.md is registered under the two prompts that read it (#3499). docs/review-policy.md records the six finding classes #3485 and #3504 ruled below the floor and the review army's lead judgment applies the table; the floor itself is unchanged. The Windows curation moves test/pregate-remote-stamp-only.test.ts to KNOWN_WINDOWS_INCOMPATIBLE (#3485). From GSTA-121: Blast radius in docs/skills.md and the merge-ask template, the 11-digit run-id exemption from pii.phone.e164 after a run word, relative string literals as import-graph edges, and a ubi-runner pack that never tars the live .git. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Red Team pass 1 (all below the floor): an 11-digit span with a leading 1 after a run word is a US or Chinese national number, not a run id, and reports again; ubi-runner pack removes its temporary repository when it fails and replays branch.* with remote.* so a branch's upstream resolves on the VM; the conservative-refusal example in docs/review-policy.md reads in the refusing direction; the touchfiles header names why ETHOS.md sits only under the two prompts that quote it. Step 6's selection found captain/templates/merge-ask.md as the one unknown dependency of this PR and registered captain/templates/** in FREE_ONLY_PR_FILES (#3499). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 2) The cmd_pack EXIT trap bakes the temp path in: a set -e failure unwinds the function before the trap runs and a local $tmp is unset there, so the old form leaked the snapshot. The leak test creates TMPDIR where the pack reads it and asserts the failure is the missing index. CHANGELOG examples no longer spell a full national number. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: adversarial review fixes The pack snapshot carries the index's staged blobs as a pack of their own, so a VM write-tree (gstack-wtree) can read a staged file the way the old .git tar allowed; git init runs with --template= and gc.auto=0 and a valueless remote/branch key replays as true. scripts/harness-version.json re-pins scripts/test-pr-profile.ts after the captain/templates/** entry. The run-id exemption reads the same way in the scanner and gstack-post: an 11-digit span after a run word is a run id (the leading-1 exclusion from the Red Team pass contradicted gstack-post's tested contract and the ruling that a run id is not a phone number), with the residual named in the comment, the docs and the CHANGELOG. The #3499 pins move to their own test so the boundary test stays under its default budget. Docs audit: TESTING_INTERNALS names RELEASE_METADATA_FILES and captain/templates/**, docs/captain.md names Blast radius. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 4) The pack's staged-blob list comes from the copied index, holds only blobs staged against HEAD (not every tracked blob), skips gitlinks whose commit the superproject lacks, and dies with its own message when pack-objects fails. The live-checkout test covers a gitlink entry and a valueless remote key replayed as true. CHANGELOG names the staged-blob carry. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (pass 5) The pack's blob list is the copied index's blobs that HEAD's tree lacks, so an intent-to-add entry's empty blob and the stages of an unmerged entry travel too (the HEAD-only diff list dropped both); gitlinks still skip. The live-checkout test adds an intent-to-add entry, which the VM fsck assertion covers. 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> |
||
|
Garry Tanandcapy-ai[bot]
|
1f246e3505 |
v1.91.278.0 fix(ship-queue): readiness takes dispatched Free Tests, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order (#3514)
* fix(ship-queue): readiness takes dispatched Free Tests, prose check reads key=value pairs, stamp paths accept tentative key versions, ready and train build read the base overlap, pr-wait --exclude, restamp prints the corrected order Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Pass 1 of /ship's review on #3514: the prose check skips a key: value pair's value whatever the whitespace, the restamp recompute keeps a merged-not-in-base predecessor and says to fetch, stampOnlyLine applies the version-width bound, pr-wait --exclude excludes nothing while the required checks are unreadable, baseOverlap reports a failed git read as unknown and gives no verdict at train build, readiness lets a pull_request run outrank a dispatched one, and the READY conflict refusal follows the crew template's rule 14 instead of a crew-local rule. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: stamp rule for tentative key versions, key=value prose claims, QUEUE_STALE merged-not-in-base fix 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a50cf58965 |
v1.91.265.0 docs: absorb four pstack principles into ETHOS.md, the observable-questions rule and candidate-side eval blinding (GSTA-124) (#3493)
* docs(ethos, plan-tune, eval-plan): absorb four pstack principles, the observable-questions rule and candidate-side blinding (GSTA-124) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Reword ETHOS sentences, scope the blinding rule, name the second candidate-visible root Review pass 1 (frozen scope, five INFORMATIONAL findings, all in-diff, none blocking): two ETHOS.md sentences in principles 6 and 7 were too close to the credited source and are reworded; the Credits line names both pstack sources (principle-* leaves and poteto-mode); eval-plan Step 1c rule 1 is scoped to what the preregistration controls and exempts the skill text an arm loads; the observable-questions rule in plan-tune and docs/proactive.md requires the observation to be local, read-only and free and points at the one-way-door rule; docs/TESTING_INTERNALS.md names skill-e2e-benchmark-* (test/skill-e2e- deploy.test.ts:293) as a second candidate-visible root and states the audit's matching method. SKILL.md regenerated for both unpinned skills. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: correct the candidate-visible root list and the one-way-door attribution The blinding audit paragraph in docs/TESTING_INTERNALS.md and the CHANGELOG entry claimed two candidate-visible temporary roots and that the other skill-e2e-<case>-* roots carry no listed word; test/skill-e2e-test-value.test.ts:131 (skill-e2e-<id>- with ids carrying 'test') and test/skill-e2e-health.test.ts:23 (gstack-health-eval-) show otherwise, so both now list the roots the mkdtemp scan found and say the list is not a proof of completeness. docs/proactive.md said the one-way-door rule already covers spend and third-party reach; it now says the new sentence extends that rule. The CHANGELOG bullet for the observable-questions rule names its local, read-only and free qualifier. 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> |
||
|
Garry Tanandcapy-ai[bot]
|
737ba3af40 |
v1.91.259.0 feat(ubicloud): /ubicloud skill with TTL-named VMs and a reaper, quota preflight, hang watchdog and one committed verify entry point (#3482)
* feat(ubicloud): /ubicloud skill with TTL-named VMs and a reaper, quota preflight, hang watchdog and one committed verify entry point
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CLAUDE.md names the ratcheted catalog ceiling
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: UBI_OWNER example is a literal value, not a free-text placeholder (INV-3 fence lint)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: the UBI_OWNER example is a neutral value (no thread codes in product prose)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: verify trusts the checkout only, watched commands keep stdin and end the remote session, quota and reap outcomes
verify: .gstack/ubicloud.json is repository content, so its setup script and
pull destinations must resolve inside --src (absolute, ~ and .. refused before
any API call) and a name it lists under pass is forwarded only when the command
line grants it (--pass NAME or --trust-config); --pass never forwards UBICLOUD_*
and refuses non-names. watched: the caller's stdin reaches the remote command,
a command that finished while the clock was read is not a timeout, a hung setup
exits 124, INT/TERM take the ssh session down, and the watchdog ends the
command's session on the VM (setsid + ~/.ubirun-<phase>.sid + pkill -s). Quota:
a cached refusal maximum is trusted for a day, the refusal names its source and
uses the 'vCPU quota exhausted' marker pregate-remote.sh retries on. reap:
returns 1 on a failed list or destroy; TTL suffixes read in base 10 and
UBI_TTL_HOURS takes 0-999. Tests: a fake API that creates plus a fake ssh run
'run' and 'verify' end to end.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: the remote session file is per runner invocation and setsid is optional on the image
Two watched commands on one VM wrote the same ~/.ubirun-<phase>.sid, so a cancel
could end the other's session; the file now carries the runner's pid and is
removed when the command ends. An image without setsid runs the command through
plain bash instead of failing with exit 127.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: pull destinations are rechecked at pull time, verify parses options by arity, a finished command keeps its status, the remote sid outlives the wrapper; docs audit
Pass-2 (Codex adversarial on the delta): an earlier pull could plant a symlink
where a later config pull lands, so under verify every destination is resolved
again (symlinks followed) right before its pull and a refused pull exits 1;
'--dest --trust-config' made an option value act as the trust flag, so verify
parses by arity; a command that finished in the instant before the watchdog's
kill exited 0 and was still reported as 124; the wrapper removed the sid file
while a background child kept the channel open, so the file now stays until
remote_cancel reads it. Docs audit (document-release, edit mode): TTL suffix and
owner rule in TESTING_INTERNALS, the reaper as the exception to 'no sweep', the
docs/skills.md transcript uses a neutral owner; CHANGELOG and the runner header
corrected on the two points it deferred.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: a refused pull destination creates no directory, inside or outside the checkout
inside_dir checked containment after mkdir -p, so a destination under a planted
symlink (escape/new/sub) created the outside directories before being refused.
The nearest existing ancestor is checked first; only an accepted destination is
created, and it is checked again after.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: bin/gstack-ubi has a test lane (it execs the runner and forwards arguments)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: pack ships a linked worktree with a self-contained .git
A worktree's .git is a gitdir pointer into the main repository; on the VM git
could not run, so the remote pregate refused with PREGATE_VM_TREE_MISMATCH
vm=unavailable. pack now replaces it with a bare --single-branch clone of the
checked-out branch (core.bare false, the worktree's index copied in), ~45 MB for
gstack; a detached worktree is refused with the fix named.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: take main's host-conformance C3 fix (#3479) so the remote gate can run on this tree
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* ubicloud: pack skips a split index (its shared half stays in the original git dir)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* CHANGELOG: restore main's released history under the [Unreleased] block (the merge resolution kept only the conflicted span)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.258.0 -> 1.91.259.0 (stamped; queue_mode=stamp-at-merge base=origin/main@7dc2f23192b7 policy=base origin/main@7dc2f23192b7:.gstack/ship-policy.json)
ship, next in queue at 1.91.259.0
STAMP_VERSION: 1.91.259.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.259.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.259.0)
stage stamp_paths: skipped (no stamp_paths in policy)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3c91fdaf8..e4f4d63ec 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [1.91.259.0] - 2026-10-26
**New `/ubicloud` skill: the Ubicloud runner moves into gstack with the discipline a shared vCPU quota needs.** Crews ran heavy suites on Ubicloud through a user-scope skill and per-lane wrappers, and paid for it in stray VMs after a machine slept, a project quota at 528 of 512 vCPUs when lanes verified in parallel, verifies that hung for an hour before anyone noticed, and a stale wrapper that skipped a service start. `scripts/ubicloud/ubi-runner.sh` now carries the fixes and `ubicloud/SKILL.md` (entry point `bin/gstack-ubi`) teaches the watched launch; `bun run test:ubicloud` and the remote pregate are unchanged.
diff --git a/VERSION b/VERSION
index c67e9e442..08528ff87 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.91.258.0
+1.91.259.0
diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md
index 4bd43c922..203312cf5 100644
--- a/agents-digest/gstack-AGENTS.md
+++ b/agents-digest/gstack-AGENTS.md
@@ -1,4 +1,4 @@
-# gstack digest v1.91.258.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.259.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
diff --git a/node_modules b/node_modules
new file mode 120000
index 000000000..c7990ad12
--- /dev/null
+++ b/node_modules
@@ -0,0 +1 @@
+/workspace/gstack-ubi/node_modules
\ No newline at end of file
diff --git a/package.json b/package.json
index 5e6d56827..0eca459a0 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "gstack",
- "version": "1.91.258",
+ "version": "1.91.259",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=76e86e08a851fb1a19bef9a947bdf0abeb87956d
next: NEW_VERSION=1.91.259.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head
|
||
|
Garry Tanandcapy-ai[bot]
|
b004c06dbc |
v1.91.255.0 fix(ship-queue): fill trains at 3 READY PRs or one hour, and price every case shard's trial (#3478)
* fix(ship-queue): fill trains at 3 READY PRs or one hour, and price every case shard's trial
The 5-PR / 3-hour fill left READY PRs waiting most of a day; .gstack/ship-policy.json
now fills at max_size 3 or fill_hours 1, whichever comes first (fillDue already
dispatches at either bound). train verdict printed cost=$24.41 for a train whose slice
report said cost $32.92 known + 54 of 136 trial(s) cost unknown: E2E records named by a
display label ("/benchmark workflow") were never attributed to their case id, so the
per-case sum was short. A case shard's records now belong to its one case; a multi-case
shard with display-labelled records keeps those trials unknown. The ATTEMPT: line names
how many cases have no cost instead of printing a partial sum as the total.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ci): record the paid-report.ts harness decision and keep ship-queue-train-cost.test.ts off the Windows subset
scripts/lib/paid-report.ts is a pinned shared-harness file, so test/harness-version.test.ts wants a HARNESS_VERSION decision for its edit: non-behavioral, because a case shard's records are attributed to its one case for the trial's cost, class and error fields while no case's outcome, panel verdict or selection changes.
test/ship-queue-train-cost.test.ts drives bin/gstack-ship-queue against the #!/bin/sh gh shim, which windows-latest cannot run (windows-free-shard 2 on #3478 at
|
||
|
Garry Tanandcapy-ai[bot]
|
9c7b4c81ca |
v1.91.183.0 fix(evals): a rejected API key is INFRA, never 131 assertion reds and reruns (#3361)
* 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> |
||
|
Garry Tanandcapy-ai[bot]
|
95152e3c4c |
v1.91.163.0 feat(evals): the gate reruns failed cases once and reports a flaky green (GSTA-49 F1) (#3315)
* 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> |
||
|
Garry Tanandcapy-ai[bot]
|
9665621d18 |
v1.91.148.0 ci(seed): seed PRs also dispatch Quality gate, and say which runs are their checks (#3297)
* ci(seed): seed PRs also dispatch Quality gate, and say which runs are their checks Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.148.0 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> |
||
|
Garry Tanandcapy-ai[bot]
|
e9dfcf64f0 |
v1.91.137.0 feat(evals): gate-cost replay and merge-train cost model (GSTA-49 T0) (#3271)
* feat(evals): gate-cost replay and merge-train cost model (GSTA-49 T0) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(gate-cost): build fixtures in a temp dir instead of tracked test/fixtures Tracked fixtures under test/fixtures need a FREE_FIXTURES entry, and test/helpers/free-fixtures-data.ts is a paid-runner input that selects every PR-profile case (57 cases + 24 judges, about 52 USD). The run tree is now written to a temporary directory and the l3 screen costs are inline. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: bump version and changelog (v1.91.137.0) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a2a6cabfa6 |
v1.91.134.0 feat(evals): readiness-gated paid dispatch (R1), verdict reuse (R2a/R2), receipt store that restores (#3262)
* feat(evals): readiness-gated paid dispatch (R1), restamp-only gate reuse (R2a), and a receipt store that restores Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(evals): R2 verdict reuse across main moves; review fixes (newer-run classification, receipt parser, manual acceptance) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): R2 own-diff signature covers release-output content and CHANGELOG deletions and preamble Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): R2 normalises release outputs by stamp pattern only; compares stamp-file modes; unreadable blobs refuse Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.134.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): autoplan-guard-pty actor continues through the phase boundary; name PHASE_BOUNDARY_STOP 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> |
||
|
Garry Tanandcapy-ai[bot]
|
dbf4a3c67e |
v1.91.130.0 feat(pr-selection): exercised-path consumer map in shadow mode, MAP_GAP and census refresh (#3259)
* 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
|
||
|
Garry Tanandcapy-ai[bot]
|
a669dafcb4 |
v1.91.129.0 fix(pr-selection): scan shebang and .ts imports, fail closed on scan errors, report cost per run (#3257)
* 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>
* 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
|
||
|
Garry Tanandcapy-ai[bot]
|
c5c2f28994 |
v1.91.128.0 ci(seed): weekly standing recorder for the Linux and Windows duration seeds (#3253)
* ci(seed): weekly standing recorder for the Linux and Windows duration seeds (W4) free-durations-record.yml runs Mondays 04:00 UTC (before test-health) and on dispatch. Linux records on ubicloud-standard-8, the free-suite shard runner, with scripts/ubicloud/setup-free-suite.sh; Windows records through windows-free-tests.yml's record_durations path (now also workflow_call). When either seed's file set drifts from main, the propose job force-updates bot/free-duration-seeds, opens or refreshes one seed PR stating the seed ratchet result and the files that failed while recording, and dispatches the free lanes on it. A red file keeps its duration; an interrupted recording uploads no seed (this also stops the Windows dispatch from uploading a stale copy), and more than 5 red files on either OS proposes nothing. The bot never edits the allowlist. open_pr=false on dispatch records and reports only. The workflow is classified free-lane only in scripts/test-pr-profile.ts, with a non-behavioral HARNESS_VERSION decision. Intentional pin change: test/windows-native-workflows.test.ts now expects workflow_call and the complete-recording guard on the Windows record job. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(seed): keep maintainer commits on the open seed PR, publish only from main, survive long ratchet reports /review on #3253 (gpt-6.1-sol): a refresh force-pushed over maintainer repairs on the seed PR, a dispatch from a feature branch would publish that branch's commits, and grep | head under pipefail could abort the step on a long ratchet report. The refresh now leaves an open seed PR alone when it holds any commit besides the bot's one refresh commit and pushes with an exact lease; only main publishes; the report is cut with sed. Each has a functional test that fails on the old workflow. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): unreleased entry for the weekly duration-seed recorder Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.128.0 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> |
||
|
Garry Tanandcapy-ai[bot]
|
a889ef9393 |
v1.91.105.0 fix(tests): the free suite stops needing its retry pass; test:health tells the truth (#3154) (#3212)
* test: turn git auto-maintenance off in free fixtures, with a runner backstop git 2.29+ starts a detached `git maintenance run --auto` after every commit; it creates and deletes .git/objects/maintenance.lock after the commit returns. Diagnosed on |
||
|
Garry Tanandcapy-ai[bot]
|
5d647455f2 |
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) (#3123)
* 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> |
||
|
+22Garry TanJim McKeeththearbajonartcapy-ai[bot]dependabot[bot]DanCanadianNader HelmyNader HelmyZee ZhengJack ThomasJayesh Betalatechcenter68Mattias PeterssonArno V0xDevNinjaBenjamin D. SmithBrian Majewskineallee2012Max Hoganmaxpetrusenkoagentkatlun-lgtmmikehasaBriacJackJinEmilianoU26frosimanuelTom LamYotamJinzheXianying TanBoyard EngelsJey2311 |
8bb6d65270 |
v1.91.66.0 fix: /autoplan without permission prompts after background reviewers, 34 contributor PRs from the backlog triage (#3087)
* docs: fix CONTRIBUTING.md test-tiers link in TESTING_INTERNALS The link resolved relative to docs/, pointing at a nonexistent docs/CONTRIBUTING.md. Adopts #3070. Co-authored-by: thearbajonart <334330110+thearbajonart@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci: refresh GitHub Actions SHA pins (setup-buildx 4.4.1, build-push 7.4.0, attest 4.2.2, setup-node 7.0.0) Rewrite of dependabot #2988. Every bumped `uses:` stays pinned to the full commit SHA (verified against the upstream tags) and now carries its exact version comment, including the lines that had none. setup-node 6.5.0 -> 7.0.0 is a major bump; its notes list an ESM migration, cache outputs and removal of a dummy NODE_AUTH_TOKEN export, none of which affect our node-version-only use. actionlint 1.7.11 (CI image) and 1.7.12 are clean. Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(openclaw): stop advising a per-spawn env for spawned sessions OpenClaw's sessions_spawn has no env argument (openclaw/openclaw#51654 was closed without adding one), so the documented env: { OPENCLAW_SESSION: "1" } silently did nothing. Point users at the ACP harness or Gateway environment instead and guard the old advice. Adopts #2749. Co-authored-by: DanCanadian <211164803+DanCanadian@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(benchmark): scope /benchmark routing to web page performance /benchmark claimed the bare words "benchmark" and "performance", so model and eval benchmark requests could route to the web performance skill instead of /benchmark-models. Narrow the description, Use-when list and triggers to web-specific phrases, point model/skill benchmarks at /benchmark-models, and split the root router line the same way. The catalog lead stays within the discovery budget ("Web performance ..."). Adopts #2302 and closes duplicate #2083 (rewritten on current main). Co-authored-by: Nader Helmy <31414549+creatornader@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(llms.txt): link skills by generated path, drop host-skipped skills gen-llms-txt built every skill link as <name>/SKILL.md, so the router pointed at a nonexistent gstack/SKILL.md (it is the root SKILL.md) and /claude-code pointed at a SKILL.md the Claude host never generates. Links now use the template's generated output path, and skills the Claude host skips are left out of the index. Adopts #2279. Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ci): install Bun from the SHA-256-verified release archive in GitLab CI and Ubicloud setup Rewrite of #1713. .gitlab-ci.yml's .setup-bun anchor and scripts/ubicloud/setup-free-suite.sh still piped https://bun.sh/install into bash. Both now download the bun-v$BUN_VERSION linux-x64 release zip, check it against the same SHA-256 Dockerfile.ci uses (#1706) before unzipping, install it to ~/.bun/bin and assert `bun --version`. test/ci-image-cli-pin.test.ts runs curlPipedToShell over both files and binds their hash and BUN_VERSION to Dockerfile.ci's amd64 arm and package.json's engines floor, so a Bun bump has to move all of them together. Verified by running the GitLab anchor in debian:stable-slim (bash and sh) and the Ubicloud block in a temp HOME. Co-authored-by: Zee Zheng <228040220+spacegeologist@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): viewport auto unpins a pinned viewport without a restart `viewport WxH` pinned the page with no way back short of `browse restart`, which also drops a headed /connect-chrome session. `viewport auto` (aliases `reset`, `unpin`) now undoes the pin: - headed: the context already launches with `viewport: null`, but Playwright cannot drop a page's emulated size (and re-applies it on new frame sessions), so the active tab gets a fresh page in the same context at the same URL or load-html content. Cookies and storage persist, the tab id and ownership stay, refs reset as on navigation, and the page follows the real window again. - headless: back to the 1280x720 launch default, tracked viewport included. `auto` with --scale is rejected. Fixes #1059. Adopts #2782 and #1881. Co-authored-by: Jack Thomas <17882510+loulanyue@users.noreply.github.com> Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): screenshot accepts --clip=x,y,w,h and --selector=<css> Agent-generated commands often use the GNU `--flag=value` form, which threw "Unknown screenshot flag". Both value flags now accept it, through the same validation and conflict checks as the space-separated form. Adopts #1563. Co-authored-by: techcenter68 <75930234+techcenter68@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(benchmark): price Codex cached input at the cache rate, stop calling Gemini OAuth ready Codex reports cached_input_tokens as a subset of input_tokens, but the adapter billed all of input_tokens at the full input rate. Split them into disjoint uncached and cached counts (what estimateCostUsd expects) and show new+cached input in the table and Markdown reports. A stored Gemini OAuth file alone is now reported as not ready, with a reason naming GEMINI_API_KEY; key-based auth stays ready. Adopts the focused subset of #2283; the capacity error code and stdin change are left out (no captured failure or reproduced hang). Co-authored-by: Mattias Petersson <mattias.petersson@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): catch loosened-input consumers and stale user-facing strings The Enum & Value Completeness check fired only on newly added values, so a diff that widens what a validator, parser or guard accepts, and breaks an unchanged downstream consumer outside the diff, was a blind spot. Widen the check's trigger (heading unchanged) and add a consumer-grep bullet. Teach the maintainability specialist to flag user-facing strings whose guarding condition changed while the text did not. Adopts #2141 (rewritten on current main; the section heading is kept). Co-authored-by: Arno V <38716+aversini@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(global-discover): bucket Codex sessions by originator Every Codex rollout counted as one undifferentiated codex bucket, so /retro global could not tell interactive Codex Desktop work from codex_exec runs or Claude Code-driven calls. Normalize session_meta.payload.originator into desktop, exec, claude_code or other (missing, unknown and non-string values), report the split per repo as codex_originators and globally as tools.codex.originators, and print it in the summary. Existing totals are unchanged. Adopts #1488. Refs #1315. Co-authored-by: 0xDevNinja <manmit0x@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(hook-check): cover skill frontmatter hooks, sourced helpers, conflict markers and the caller's tsconfig Rewrite of #3066. bin/gstack-hook-check only listed setup's hooks plus /autoplan's by name, so the /careful and /freeze PreToolUse checks (also run by /guard and /investigate), /plan-ceo-review's hand-off hook and the helpers they source were never parse-checked before Claude Code ran them. - The hook list is setup's _hook_command_path arguments plus every gstack path on a `command:` line in a generated */SKILL.md frontmatter (9 hooks, up from 6). The generated files are read rather than the .tmpl sources because the /autoplan and /plan-ceo-review commands come from resolvers. - Each shell hook's gstack-tree helpers (`.`/`source` lines, assignments and shellcheck source= directives, followed transitively) are parsed too: careful/bin/hook-extract.sh and bin/gstack-state-root.sh for /careful and /freeze. - The shim, its helpers, each TypeScript entry and every local module the bundle used (bun build --metafile; entry only when bun lacks it) are scanned for conflict-marker lines, which still parse inside heredocs, strings and template literals. - bun build runs from the gstack root, so the caller's broken tsconfig.json or bunfig.toml no longer fails every TypeScript hook. Lists are newline separated, so a root with spaces works. Tests in test/setup-hook-syntax-gate.test.ts cover each case; the gstack-doctor fixture now copies autoplan/SKILL.md, whose frontmatter registers the hook its hooks-row test breaks. docs/troubleshooting.md describes the wider check. Co-authored-by: Benjamin D. Smith <7134745+BenjaminDSmithy@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): extend defensive-security framing to the security specialist and Red Team The "authorized defensive-security review" framing and fixture summary mode lived only in the adversarial subagent prompt. The security specialist and the Red Team also reason adversarially over the full diff, so repos whose test corpus is attack payloads could still get those passes refused. Move both paragraphs into scripts/resolvers/defensive-review.ts (the adversarial render stays byte-identical), state them once in the specialist dispatch for the security specialist and the Red Team, and have the Red Team prompt start from them. Testing and the other specialists keep full fixture reads; the codex host still strips Review Army. Parity caps for ship and review rise by the measured 1,380 bytes each (carve-guards notes). Adopts #1921 (rewritten on current main). Co-authored-by: Brian Majewski <1693720+bmajewski@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(team-init): make the required-mode hook shell-neutral (node CommonJS, no shell variables) Rewrite of #2217. Required team mode wrote a bash check-gstack.sh and registered it as "$CLAUDE_PROJECT_DIR/.claude/hooks/check-gstack.sh", which only works when the hook runner is a POSIX shell. Under cmd.exe or PowerShell (Windows, Copilot CLI) the variable is not expanded and the .sh cannot run, so an intended allow or deny became a hook error. - The hook is now .claude/hooks/check-gstack.cjs: the same root search (GSTACK_ROOT, every host's global root, the migrated repo), with the home directory from HOME, then USERPROFILE, then os.homedir(). It prints {} when gstack resolves and the PreToolUse deny JSON with exit 2 when not. - The registered command is `node -e "require(require('path').resolve( process.env.CLAUDE_PROJECT_DIR || '.', '.claude', 'hooks', 'check-gstack.cjs'))"`: no `$` or `%`, so sh, cmd.exe and PowerShell all pass it through unchanged. - An existing check-gstack registration (matcher Skill or Skill|skill) is replaced in place; duplicates are dropped and unrelated hooks in the same entry kept. The legacy .sh is deleted only after the settings write succeeds (a tracked one joins the suggested git add), and is kept when bun is missing or the write fails, which now reports instead of claiming success. Tests: team-mode and the hook-schema test run the command as registered; test/team-init-hook-shell-neutral.test.ts runs it through the platform's default shell (cmd.exe on the Windows lane, which curates it in) and through PowerShell when installed (verified here in the pwsh 7 container). The routing-probe check for the bash `_GSTACK_ROOT` gate now pins the same contract in the .cjs: every host root probed, block only when none resolves. Co-authored-by: neallee2012 <1499497+neallee2012@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup-gbrain): register the gbrain MCP through bun.exe on Windows so no console window opens Rewrite of #2007, folding #1963's MCP notes. On Windows the local stdio registration stored the bun `gbrain` binstub; gbrain.exe starts bun in a new console, so every Claude Code session opened a visible terminal for the MCP (the contributor's process trees show it; bun.exe launched directly attaches to Claude Code's headless ConPTY). Under MINGW/MSYS/Cygwin the skill now resolves BUN_ROOT from BUN_INSTALL or ~/.bun and registers `$BUN_ROOT/bin/bun.exe <global node_modules gbrain/src/cli.ts> serve`. That path also covers a `bun link`ed clone, whose global node_modules entry links to it; gstack-gbrain-install records no other clone location. When bun.exe or the entry is missing it registers `$BUN_ROOT/bin/gbrain.exe` by its full name, because Claude Code does not apply PATHEXT to a stored path (#1963). POSIX keeps the binstub line. The skill also notes that `claude mcp list` can show "Failed to connect" while a live session holds a local PGLite brain's single-writer lock (#1963). test/setup-gbrain-windows-mcp.test.ts runs the generated fence under bash with stub uname/claude and a temp HOME for MINGW64, MSYS with BUN_INSTALL, a missing entry, and Linux. It is listed as Windows-incompatible (POSIX stubs); the console behavior needs a manual Windows check. Co-authored-by: Max Hogan <max@maxhogan.dev> Co-authored-by: maxpetrusenkoagent <280464918+maxpetrusenkoagent@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(hosts): rewrite every "Agent tool" phrasing for agent-runtime hosts The Agent-tool rewrite for hermes, gbrain, openclaw and factory keyed only on "use the Agent tool", but templates mostly say "via the Agent tool", "with the Agent tool", "multiple Agent tool calls" or "Use the Agent tool", so the Claude tool name leaked into those hosts' skills and sections. Add ordered rules after the existing key (possessive, "the Agent tool", then bare "Agent tool") mapping to sessions_spawn (gbrain/openclaw), delegate_task (hermes) and delegation (factory). No goldens change. Adopts #1935 (rewritten on current main, without the new goldens). Co-authored-by: katlun-lgtm <264247399+katlun-lgtm@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup-deploy): Vercel auto-deploys only when connected to the Git repo /setup-deploy stated that Vercel always deploys on push, which is false for CLI-only projects with no Git integration, and its nothing-detected path did not say why such a project is invisible to detection. Qualify the Vercel trigger (ask for and record the CLI deploy command otherwise) and note that `vercel link` creates .vercel/ so a re-run detects the project. Adopts the Vercel accuracy part of #2992 (rewritten on current main); the third-party bring-up tool pointer is not adopted. Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(retro): persist recommendations so the next retro detects follow-through /retro produced "3 Things to Improve" but never saved them in its JSON snapshot, so the next retro could not tell whether last week's recommendations were acted on. Step 13 now drafts the items before saving and always writes a `recommendations` array ({category, text}, [] when empty); Step 12 scores each prior recommendation addressed/partial/open against this window's commits, files and metrics and renders a follow-through line, skipping silently for snapshots without the key. The report format ties the items to the saved array. Global mode is unchanged. Adopts #1853 (rewritten on current main). Refs #1834. Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(global-discover): count the interactive Codex CLI (codex_cli_rs) in its own cli bucket * feat(developer-profile): --reconcile backfills office-hours tenure from timeline.jsonl sessions[] is written only at office-hours Phase 4.5, so runs that ended earlier never counted toward tenure and the tier undercounted. Add a manual `--reconcile` that scans projects/*/timeline.jsonl for office-hours `completed` events and appends a count-only row ({date, mode, project_slug, signal_count: 0, signals: [], backfilled: true}) for each run with no sessions[] entry for the same project within 60 minutes, extended back by a duration_s under 8h. It is idempotent, skips malformed lines, and leaves the file untouched on a no-op. `--read` counts backfilled rows for SESSION_COUNT and TIER but takes LAST_*, DESIGN_*, CROSS_PROJECT and the nudge from logged sessions only. Not wired into the preamble yet; the office-hours greeting guard for backfill-only profiles is left to the office-hours owner. Adopts #2668 (rewritten on current main). Closes part (b) of #2657. Co-authored-by: Briac <137724549+briacSck@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): the publication hook approves /autoplan's own Reads after the skill turn Claude Code applies a skill's allowed-tools only to the turn that invoked it. On 2.1.292 the default fork-subagent mode runs reviewers in the background, and the completion notice starts a new turn, so later Reads outside the working directory (the next phase's section file, the close packet) raised permission cards. Skill hooks stay registered for the session, and a PreToolUse "allow" skips the card (reproduced in a PTY on 2.1.292). autoplan/bin/owned-read.ts approves a parent Read only when the guard itself returned no output, and only for this installation's autoplan/sections/*.md (canonical path or the gbrain :user render) or an immutable phase artifact in <repo>/.gstack/tmp/autoplan/autoplan-<phase>-*/ whose repo is the session's project directory or contains it. Denials, unverified allows, child calls and every other path are unchanged. renderSectionBase and userRenderRoot move there with it. Tests that asserted a verified driver Read as {} now expect the approval; autoplan-owned-read covers the shipped shim, the close packet without a journal, verified artifacts through the guard, look-alikes (foreign install, writable copy, symlink alias, other repository, other names) and a guard denial staying a denial. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): restore point and phase artifacts live in the project's .gstack/tmp/autoplan/ Skill hooks do not run inside subagents, so a reviewer launched after a background completion notice raised a card for its own input (native-prompt.md under the state root). Step 1 now puts RESTORE_PATH in the repository's git-excluded .gstack/tmp/autoplan/ (added to .git/info/exclude, mode 700), and the snapshot tool writes every phase artifact beside it, so /autoplan and its reviewers read them from the working directory without a card. The guard's bindings are unchanged: they anchor on the restore point's directory. Step 1 still prints the slug, which the old RESTORE_PATH carried. A free test runs the generated Step 1 block twice from a repository subdirectory: the restore point lands in <repo>/.gstack/tmp/autoplan/, the exclude line is written once and git status stays clean. The autoplan parity cap rises by the measured bytes (115,270 / 101,979 = 1.1303). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): autoplan-guard-pty fails on any permission card after the reviewer's notice turn The scripted boundary now mirrors Step 1's layout (restore point and artifacts in the project's .gstack/tmp/autoplan/) and continues past the Phase 2 entry to dispatch the Phase 2 reviewer after the CEO reviewer's completion notice. The case asserts four verified guard allows, that the close packet Read, the Phase 2 section Read and the Phase 2 dispatch came after a task-notification turn, that the Phase 2 reviewer read its input, and that no permission card appeared at all. Still one trial on haiku, about 75-85 seconds. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): permission cards after a background reviewer, and where /autoplan keeps its files Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(outside-review): read a trailing '— Medium.' or '(High)' severity on a finding line, the shape Codex now writes * feat(design): honor OPENAI_BASE_URL for every design API call One resolver, openaiUrl() in design/src/auth.ts, now builds every OpenAI URL the design binary, its prototype and its live model check use. Setting OPENAI_BASE_URL sends image generation and screenshot analysis to an OpenAI-compatible gateway; unset or blank keeps api.openai.com. The prototype script now goes through receiptedFetch, so its egress is receipted like the rest, and receipts already record the gateway host. A source scan keeps any design file outside auth.ts from hardcoding an OpenAI API URL again, and a request-shape test proves the gateway reaches both the vision and image endpoints. Co-authored-by: JackJin <1037461232@qq.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: testing specialist treats negative assertions as decisions A new assertion that something is absent records a behavior removal and needs cited intent. A rename or removal in the diff can empty a standing negative assertion so it passes forever; the specialist now greps the suite for negative assertions naming the old value. Adopted from the testing-specialist part of a community PR; the scope-check hunk targeted text that no longer exists. Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: security specialist checks authorization a route-guard read misses Four access-control classes where the guard is correct and the object still leaks: error pages composed outside the guard, ownership surviving a role downgrade, list/detail/download paths checked as one, and a session mutated before the identity-switch callback is validated. Adopted to review/specialists/security.md only; the /cso hunk targeted a bullet list that is now an OWASP/ASVS table. Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: zero findings is valid; suppress six common false positives The checklist now says a clean diff may come back clean, and suppresses framework-owned error handling, long exhaustive switches, null derefs a type guard already narrows, N+1 on fixed-cardinality loops, hardcoded test fixture values and non-cryptographic Math.random(). The contributor's "missing input validation on an internal function" and "missing await on fire-and-forget" suppressions are left out: both can hide real bugs. Co-authored-by: frosimanuel <frosimanuel@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(todos): parked contributor ideas by theme; /autoplan permission follow-ups * design-review: capture code tokens before universal principles /design-review read only DESIGN.md and otherwise fell back to universal principles, so a project whose system lives in CSS custom properties, tailwind.config or a theme file got audited and mocked up against an invented aesthetic. The skill now reads code tokens before falling back, and the target-mockup brief reuses the captured colors, fonts, radii and spacing, changing layout only. The contributor's optional microcopy checks (domain vocabulary, human register) are not adopted here. Co-authored-by: Tom Lam <tomlam0811@berkeley.edu> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(sidebar): add a terminal text-size picker to the toolbar The sidebar terminal toolbar gets an XS-XL text-size picker beside Restart. SM (13px) stays the default, so nothing changes until a user picks a size; the choice persists in chrome.storage.local and applies to the live terminal, re-fitting xterm and re-sending the PTY size two frames later so the new character cell is measured first. A VM test runs the real sidepanel-terminal.js through one auto-connect and checks the creation size, the stored-size fallback, persistence and the live resize. Co-authored-by: Yotam <yotsurfing@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(design-shotgun): generate with Codex's built-in $imagegen on Codex On the Codex host, /design-shotgun now generates and edits mockups with Codex's documented $imagegen skill in its default built-in mode (the image_gen tool), so users signed in with ChatGPT need no OPENAI_API_KEY. The design binary stays for the local comparison board only, images are published with gstack-design-claim as before, and screenshot evolution loads the captured page with view_image before an $imagegen edit. Step 3c-3d moved into a DESIGN_SHOTGUN_GENERATION resolver that returns the existing design-binary text unchanged for every other host; the Claude output differs only in two host-neutral rewordings of the evolve-from-screenshot pointers. DESIGN_SETUP and the regenerate step of the board loop gain matching Codex-only text for design-shotgun. Co-authored-by: Jinzhe <hwang.phy@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * voice: ban the "load-bearing" stock phrase Models overuse "load-bearing"; it joins the AI-vocabulary ban line in both voice tiers. The tier-2 voice directive is also tightened (the meta "compressed for runtime" tag and the bounded closer's restated exemption clause) so the shared preamble shrinks by 163 bytes per tier-2+ skill, which also pays for the reply-language rule that follows. The ship goldens are refreshed for the new render. Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * voice: reply in the language of the user's latest message Every skill's voice directive now tells the agent to reply in the language of the user's latest message unless asked otherwise, so long English skill text no longer drags a Chinese (or any non-English) session into English. Mixed-language sessions follow the latest message. Code, commands, paths, identifiers and quoted output stay verbatim, and at tier 2+ so do the machine-read question markers (D<N>, option letters, (recommended)). The rule costs 205 bytes per tier-2+ skill and 144 per tier-1 skill. A further 25-byte cut to the bounded closer's exemption list leaves the net for this wave at +17 bytes per tier-2+ skill and +158 per tier-1 skill. review, qa and browse caps rise with measured notes; the ship goldens are refreshed. Co-authored-by: Xianying Tan <shrektan@126.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(redact-prepush): committed exact-span allowlist at .gstack-redact-allowlist The pre-push hook never fed the engine's allowlist option, so a reviewed, known-benign value (a public dev-compose URL, a documented sample key) warned or blocked every push, and the only ways out were a bypass or reshaping code until the detector stopped matching. The hook now reads the repo-root .gstack-redact-allowlist from each pushed commit (never the working tree), one exact matched span per line with # comments. Only a finding whose matched text equals an entry is suppressed: a password alone, a substring, or a different key still reports and still blocks, and engine.* unscanned findings are untouched. Every push that carries entries prints the entry count and each suppressed finding's rule and file line. Oversized files (over 64 KiB) are ignored. gstack.redact.allowEmail keeps working as before. Co-authored-by: Boyard Engels <boyard.engels@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(brain-sync): opt-in removal publishing with a bulk-removal valve gstack-brain-sync never published a removal: a deleted synced file, or the old directory after a project slug migration, stayed on the remote forever and gbrain indexed both copies. New setting artifacts_sync_removals (off by default). When on, each drain commits and pushes, receipted like every push, the removal of tracked files that are gone from disk and match the sync allowlist. Transcript pages are never removed here, and a decision log goes only together with its active snapshot. One valve: a drain that would remove more than 20 files at once publishes none and says so. `gstack-brain-sync --publish-removals` lists the pending removals and `--publish-removals --yes` publishes them on demand, whatever the setting. Co-authored-by: Jey2311 <5177215+Jey2311@users.noreply.github.com> * feat(windows): setup.ps1 checks prerequisites and runs ./setup in Git Bash A PowerShell entry point for Windows users. It checks that Git for Windows, Bun and Node.js are on PATH (printing the winget command for each missing one and changing nothing), finds Git Bash from git.exe rather than a PATH bash that may be WSL's, and runs ./setup from the checkout with every argument passed as its own argv entry to a constant bash script. No argument is interpolated into shell source. ./setup itself is unchanged. Co-authored-by: Jim McKeeth <jim@mckeeth.org> * v1.91.63.0: CHANGELOG, version * fix(ci): link bunx after the SHA-verified Bun install in GitLab CI and the Ubicloud setup * fix(redact-prepush): strip every parent column from combined-diff lines, so a merged release bump is exempt like any other * fix(hook-check): treat a Windows drive path as absolute (cygpath when present), so --list finds the skill hooks from a native caller * fix(windows): owned-read requires the read-only attribute on Windows; setup.ps1 passes arguments NUL-separated through a private file; Windows-only tests expect the owned-read approval * perf(hook-check): bundle every hook's TypeScript entries in one bun process instead of two bun starts per entry (seconds each on Windows) * perf(hook-check): read all skill frontmatter in one awk and scan conflict markers with one grep per hook (half the process starts) --------- Co-authored-by: thearbajonart <334330110+thearbajonart@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: DanCanadian <211164803+DanCanadian@users.noreply.github.com> Co-authored-by: Nader Helmy <31414549+creatornader@users.noreply.github.com> Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: Zee Zheng <228040220+spacegeologist@users.noreply.github.com> Co-authored-by: Jack Thomas <17882510+loulanyue@users.noreply.github.com> Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: techcenter68 <75930234+techcenter68@users.noreply.github.com> Co-authored-by: Mattias Petersson <mattias.petersson@gmail.com> Co-authored-by: Arno V <38716+aversini@users.noreply.github.com> Co-authored-by: 0xDevNinja <manmit0x@gmail.com> Co-authored-by: Benjamin D. Smith <7134745+BenjaminDSmithy@users.noreply.github.com> Co-authored-by: Brian Majewski <1693720+bmajewski@users.noreply.github.com> Co-authored-by: neallee2012 <1499497+neallee2012@users.noreply.github.com> Co-authored-by: Max Hogan <max@maxhogan.dev> Co-authored-by: maxpetrusenkoagent <280464918+maxpetrusenkoagent@users.noreply.github.com> Co-authored-by: katlun-lgtm <264247399+katlun-lgtm@users.noreply.github.com> Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com> Co-authored-by: Briac <137724549+briacSck@users.noreply.github.com> Co-authored-by: JackJin <1037461232@qq.com> Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: frosimanuel <frosimanuel@gmail.com> Co-authored-by: Tom Lam <tomlam0811@berkeley.edu> Co-authored-by: Yotam <yotsurfing@gmail.com> Co-authored-by: Jinzhe <hwang.phy@gmail.com> Co-authored-by: Xianying Tan <shrektan@126.com> Co-authored-by: Boyard Engels <boyard.engels@gmail.com> Co-authored-by: Jey2311 <5177215+Jey2311@users.noreply.github.com> Co-authored-by: Jim McKeeth <jim@mckeeth.org> |
||
|
Garry Tanandcapy-ai[bot]
|
c7edf46bcf |
v1.91.47.0 fix(careful,freeze): safety hooks cover PowerShell and NotebookEdit (#3077)
* fix(careful): check PowerShell tool commands and nested pwsh/cmd (#3067) /careful and /guard matched only the Bash tool, so on Windows, where Claude Code's PowerShell tool is the primary shell, the guard never ran. check-careful.sh also had no PowerShell or cmd patterns. - careful/guard register a PowerShell matcher beside Bash. - hook-extract.sh gains gstack_hook_extract_tool: one parser call reads tool_name with the field, so dispatch adds no fork. - check-careful.sh runs one PowerShell/cmd pattern table on PowerShell tool commands and on the tail of any Bash command that launches pwsh/powershell/cmd: Remove-Item and aliases with -Recurse/-Force prefixes, rd/rmdir/del/erase /s, Format-Volume, Clear-Disk, Clear-Content, [IO.Directory]/[IO.File]::Delete, and asks with an explanation for -EncodedCommand, iex, Start-Process of a shell and & $cmd. Command-position anchors keep Bash negative controls allowed. - /careful documents the coverage as best-effort and points to Claude Code permission deny rules. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(freeze): NotebookEdit respects the freeze boundary (#3067) NotebookEdit was in no freeze/guard/investigate matcher, and check-freeze.sh read only file_path, so notebook edits ignored /freeze on every platform. NotebookEdit carries tool_input.notebook_path. - freeze, guard and investigate register a NotebookEdit matcher beside Edit and Write. - check-freeze.sh reads file_path, then notebook_path, through the shared extractor; denials name the tool, the field, the boundary and /unfreeze. A helper without the combined reader denies as out of date. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: run hook-scripts on the Windows lane (#3067) The careful/freeze hooks are Windows coverage, but test/hook-scripts.test.ts was excluded from windows-free-tests by the raw /tmp/ pattern; its /tmp/ literals are payload strings that are never opened. Admit it by name and gate the three cases Windows runners cannot host: a symlink (no Developer Mode), a newline in a directory name, and a POSIX ':' PATH prefix. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore(evals): check-careful.sh is free-only for PR selection No paid fixture copies or runs careful/bin/check-careful.sh (the investigate boundary fixture copies hook-extract.sh and check-freeze.sh only); test/hook-scripts.test.ts covers it. As an unknown dependency it restored the full paid gate on every /careful hook change. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(careful): pin the #3067 Invoke-Sqlcmd DROP TABLE example on the PowerShell tool Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore(evals): record the check-careful.sh selection change as non-behavioral Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: /careful covers PowerShell (best-effort), /freeze covers NotebookEdit (#3067) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: release v1.91.37.0 (CHANGELOG, TODOS for deferred hook follow-ups) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: re-slot release to v1.91.39.0 (v1.91.37.0 and v1.91.38.0 claimed by #3075, #3076) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: re-slot release to v1.91.41.0 (merge-queue reservation) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(careful): hook payload reader survives Windows text-mode Python and backslash source paths windows-free-tests (run 37739845723) showed every PowerShell-tool case falling through: Python's text-mode stdout on Windows wrote tool_name as "PowerShell\r", so dispatch never matched, and freeze denials carried stray CRs. gstack_hook_extract_tool now reads and writes bytes. hook-extract.sh also located gstack-state-root.sh with ${BASH_SOURCE%/*}, which strips nothing when the file is sourced through a C:\... path, so gstack_hook_state_root vanished (state-root parity case on the same run). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): PR lane selects office-hours-auto-mode by its real test name The PR paid lane filters audited files with -t built from CASE_TEST_NAMES[id] ?? id. office-hours-auto-mode's Bun test is named 'AskUserQuestion surfaces when --disallowedTools AskUserQuestion is set', so the filter matched 0 tests and the shard failed (#3077 eval-slices (6), run 37741434771). Map the label, and check every audited PR-profile case is addressable by name. Recorded as non-behavioral for HARNESS_VERSION. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: CHANGELOG notes for the Windows CRLF and PR-lane name fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: re-slot release to v1.91.47.0 (merge-queue assignment) 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> |
||
|
Garry Tanandcapy-ai[bot]
|
db745675bd |
v1.91.33.0 feat(ship): measurement bar with explained-red and pooled decisions, weekly flaky-test sweep on main (#3059)
* refactor(eval-history): share pass-rate history loading as loadPassRateHistory() eval:pass-rates' main block loaded local dirs or the weekly trial-outcomes artifacts inline. Move that into an exported function returning records, scope and fetch errors, so the off-ship sweep reads the same history the same way. Behavior unchanged. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(ship-measure): the measurement bar and the weekly off-ship sweep CLI Decide each diagnostic measurement with one bar (scripts/lib/measure-bar.ts): MEETS at 9/10; MEETS-qualified at 8/10 when every red is a mechanical provider error, judge noise or a cited model miss; EXTEND at 7/10 (or an unqualified 8/10) for one more batch on identical inputs, decided once on the pooled 20; BELOW otherwise and for any timeout, hang, regression or fixable cause. Behavior uses 12 trials (11/10/9; 22/20 of 24); judge counts median-panel outputs. A batch with more than 30% provider-evidence failures is void and redispatched once. Below-strict reds nobody classified return needs-classify. ship-measure gains classify (append-only records; provider refused without evidence), decide and extend (refuses a changed identity, names the field, never a third batch), exit codes 5 and 6, and a pooling identity (frozen tree, runner, CLI, model, CI image, Bun, policy and harness versions). ship-measure sweep ranks main's gate cases by their cost to the all-green probability from eval:pass-rates history, measures the top K with the same runner and bar under a weekly cap shared with the last 7 days of sweep reports (ship_measure_sweep_cases, ship_measure_sweep_budget_usd), and writes a report with the predicted all-green probability before and after. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(ship): the measure loop decides by the bar's exit codes Step 4 branches on MEETS/MEETS-qualified, needs-classify (with the qualifying and fix-round classes), EXTEND once and BELOW; the rest of the loop prose is tightened to offset most of the growth. ship's union size cap moves from 1.495 to 1.4975 (measured 281,058 / 187,706 = 1.4973). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci: weekly eval-sweep workflow on main Mondays 12:00 UTC and on dispatch (k, cap_usd, dry_run): runs ship-measure sweep in the published CI image by digest with the census's paid-eval setup, downloads the last 7 days of sweep reports first so the weekly cap holds across runs, uploads the report and captures, and writes the job summary. Read-only grants; it never pushes or opens a pull request. One sweep at a time repository-wide, never cancelled mid-spend. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: the measurement bar table and the weekly sweep Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: v1.91.33.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(temp): run eval-sweep on push to this branch (K=2, $25) for end-to-end validation Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Revert "ci(temp): run eval-sweep on push to this branch (K=2, $25) for end-to-end validation" This reverts commit |
||
|
+8
|
28f1385eac |
v1.91.32.0 fix: Codex works from zsh, free text never enters shell commands, honest failures (#3057)
* fix: sourced helpers locate themselves under zsh (#3024) Skill blocks source bin/gstack-codex-probe and bin/gstack-egress-lib.sh into the host's shell. Under zsh (macOS default) BASH_SOURCE is empty, so Codex model selection resolved /../scripts/... and every outside pass reported CODEX_MODEL: invalid; the egress lib resolved to the caller's cwd. Resolve the file once at source time (BASH_SOURCE under bash, %x under zsh), and replace the bash-only ${!name} indirection in the auth probe. A free test derives every sourced helper from the generated skills and sources each under bash and zsh. Co-authored-by: marcosdetry <marcosdetry@users.noreply.github.com> Co-authored-by: akshaykalia <akshaykalia@users.noreply.github.com> Co-authored-by: scottgigante-hubflow <scottgigante-hubflow@users.noreply.github.com> Co-authored-by: woodsonl <woodsonl@users.noreply.github.com> Co-authored-by: bezdekt <bezdekt@users.noreply.github.com> * fix: reply and issue templates never pass untrusted text in double quotes (#3046) greptile-triage's reply APIs posted -f body="<reply text>" while the templates quote SHAs and diff code in backticks; in double quotes bash ran each span (replies posted as 'Fixed in .', and diff or reviewer text ran as a command). The pre-existing-failure issue template and /spec's issue title had the same shape. All three now go through quoted heredocs. The generated-bash lint gains untrusted-in-quotes and now also covers runtime reference docs in skill directories (review/greptile-triage.md). Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: a Codex usage limit is its own state, not 'inconclusive; proceeding' (#3051) The model probe matched only model and broken-install errors, so a usage or rate limit fell through to MODEL_PROBE_INCONCLUSIVE: Codex's own message (with the reset time) was dropped, the hint pointed at model config, and every later skill re-probed for 30 s. The probe now returns MODEL_QUOTA_EXHAUSTED (exit 4) on a failed, non-timeout call that names a usage limit, rate limit, insufficient_quota or 429, relays Codex's line verbatim and caches it for 15 minutes. Preflights map it to CODEX_MODE: quota_exhausted (missing coverage, no further Codex calls), and classifyOutsideReview reports a mid-run limit as unavailable (quota) with its own troubleshooting anchor. Co-authored-by: venkatareddyg <venkatareddyg@users.noreply.github.com> * test: record ship/review union sizes after the quota branch and issue template * fix: Codex watchdog freezes the command before reaping its children The bash-native watchdog (stock macOS, no timeout binary) ran pkill -P on the command's children and then killed the command. Between the two, the command continued past its killed child and printed output after its deadline. Stop it first. The test's minimal PATH also lacked pkill, which the watchdog uses to reap children (stock macOS ships it), so the orphaned child held stdout open and the capture waited out its sleep. * fix(autoplan): an oversize session journal is a hard too_large denial, not a retryable identity failure (#3050) The guard capped journal reads at 32 MiB and reported a longer journal as 'identity', which the hook treats as deny-and-retry. A journal only grows, so /autoplan could never enter Phase 1 in a long session, and the troubleshooting row sent people chasing symlinks. Oversize journals now report too_large as a hard cause that names the size and the supported fallback (run the reviews by hand or start a new session). Co-authored-by: venkatareddyg <venkatareddyg@users.noreply.github.com> * fix(deps): clear the weekly OSV findings (#3040) Raise overrides to fixed releases: ip-address 10.7.3 (our own pin was the vulnerable 10.3.1; reachable through socks in browse's proxy path), fast-uri 3.1.8, hono 4.13.13, proxy-addr 2.0.8, @modelcontextprotocol/sdk 1.31.0, sharp 0.35.5, and in lib/diagram-render dompurify 3.4.16 (bundled by mermaid) and source-map-js 1.2.2; the render page is rebuilt. Three advisories without a usable fix get justified, expiring ignores: braces (build-time only, excalidraw -> sass -> chokidar; a test checks the page carries no chokidar code), sprintf-js (roarr's constant-format logger) and katex (needs pre-existing prototype pollution; fix outside mermaid's range). osv-scanner with the repo config: no issues found. * fix(autoplan): name a shell-built snapshot init as the cause of the missing-evidence denial (#3045) The guard binds a phase entry only to a literal snapshot-init Bash call. When the model resolved the tool path into a variable, chained or piped the call, init ran and succeeded but the denial said 'Complete the existing snapshot init step', which reads as already done, so the run gave up. When no init binds but a Bash call looks like one, the denial now says the shape cannot be bound and prints the literal re-run (answers reused:true). The binding rule is unchanged, and the skill says to run init on its own. Co-authored-by: CharlesBerg85 <CharlesBerg85@users.noreply.github.com> * fix(browse): chain reads piped stdin synchronously, so Windows runs the flow (#3039) On Windows, an awaited Bun.stdin.text() inside the CLI's un-awaited main() let the process exit 0 before reading stdin: a replayed flow reported success with nothing sent to the daemon. Read fd 0 synchronously (skipped for a terminal); empty input now gets the server's usage error and a non-zero exit. Co-authored-by: VaibDeveloper <VaibDeveloper@users.noreply.github.com> * fix(browse): clearer config-mismatch refusal and a WebGL note for the macOS GPU flags (#3030) A plain call refused because another session started the daemon with --headed/--proxy was told to 'apply --proxy/--headed', flags it never passed. It now says who started the daemon and offers both remedies. The BROWSER.md env table notes that the default macOS GPU flags disable WebGL and that GSTACK_DISABLE_GPU=off restores it for WebGL QA. Co-authored-by: Hagetino <Hagetino@users.noreply.github.com> * fix(ship): skip Greptile triage when no PR exists yet (#3020) /ship's first run on a branch dispatched a triage subagent only to learn there was no PR. Step 10 now checks for a PR inline (gh's 'no pull requests found') and records that Greptile runs on the PR once it exists; other gh errors still dispatch so the child can report unavailable. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix(router): route only to loaded skills, and say when not to invoke (#3018) The root router listed every skill and ended 'When in doubt, invoke the skill'. Current Claude models follow that literally: they tried to invoke skills a user had turned off in Claude Code's skillOverrides (which gstack's own disabled_skills render cannot see), and borderline requests tipped into full workflows. The router now routes only to skills in the session's available-skills list and names when to answer directly; the CLAUDE.md routing block skill-start offers says the same. Co-authored-by: Rekin226 <Rekin226@users.noreply.github.com> * fix: spawned sessions never auto-grant consent or publish off the machine (#3016) Spawned sessions auto-choose the recommended option except for destructive or irreversible choices. Main already withholds the artifacts-sync consent prompt from spawned sessions; the remaining gap was any other prompt whose recommended option grants a consent or syncs data off the machine. Every spawned directive (skill-start's block, the escape sentence, the Conductor deny reason and the AUQ-error fallback) now names that as irreversible. A consent the user already gave interactively stays in force. Co-authored-by: ekson73 <ekson73@users.noreply.github.com> * test: fix the spawned-block slice and type the #3045 re-init events * fix(redact): TypeScript types and JSX expressions are code, not env.kv secrets (#3048) A credential-named parameter or prop with an unquoted code value (`session: SessionState,`, `key={turn.requestId + turn.role}`, `apiKey={settings.apiKey}`) cleared the entropy gate and blocked pushes as a MEDIUM env.kv finding. One rule replaces the PR's two keyword heuristics: a value that reads as a code name (no digits, word-like camelCase or dotted parts) with a code terminator, or a brace expression of such names with no quoted literal, is source syntax. Paired controls keep firing on quoted, brace-wrapped, concatenated, YAML-bare and random-letter literals. Co-authored-by: tianxchen <tianxchen@users.noreply.github.com> * fix(setup): refuse to register a hook that does not parse (#3032) Claude Code runs gstack's hook shims through /bin/sh; a shim that does not parse exits 2, which for a PreToolUse hook blocks the tool call in every session until someone finds the file. Before any hook registration is healed or written, setup now runs bash -n on each registered shim and a Bun parse of its TypeScript entry, and stops with the file, line and fix. A lean rewrite of the PR's idea (one gate block plus a test that runs it). Co-authored-by: BenjaminDSmithy <BenjaminDSmithy@users.noreply.github.com> * fix(browse): Windows runtime roots start the server from the source checkout's bundle (#3026) On Windows a host runtime root (~/.codex/skills/gstack and the other env-var hosts) holds file copies of browse/dist and no node_modules, so its server-node.mjs could not import playwright and every browser skill died (the module-scope server.ts half was fixed in v1.91.19.0). setup now records the source checkout in every runtime root's .source-path, and the CLI runs that checkout's bundle when the adjacent one cannot reach playwright. Verified by unit layout tests and the Windows CI lane, not live on Windows. Co-authored-by: ubay887 <ubay887@users.noreply.github.com> * fix(copilot): on Windows, run bash blocks in Git for Windows Bash (#3047) Copilot CLI on Windows ran gstack's extensionless helpers straight from PowerShell, which opened an app picker, and bare bash can resolve to WSL. The Copilot tool glossary (rendered into every Copilot skill) now says to run each bash block in Git for Windows Bash by its full path and never to translate a block into PowerShell. The PR's PowerShell repair skill and README section are not taken. Co-authored-by: nareshh74 <nareshh74@users.noreply.github.com> * test: record ship's union size after the Greptile no-PR check * fix: keep issue numbers out of model-read Copilot text; seed the new routing sentence in the autoplan fixture * docs: Oct 6 fix-wave plan, reviewed through /autoplan * fix(autoplan): every oversize-journal path reports too_large with a recovery that keeps the work Review follow-up to the #3050 fix. The summed batch read and the narrowed parent loop now report too_large with the real size instead of a plain error naming a hard-coded 32 MiB. The denial names the size and the cap, and gives the recovery that keeps work (/context-save, new session, /context-restore, /autoplan) with a docs anchor. A test seam that can only lower the cap replaces the 33 MiB fixture. * test(autoplan): negative controls and more shapes for the shell-built init denial * fix(redact): decide TS/JSX source syntax by file context, not by value shape Review follow-up to the #3048 fix. The word-shape heuristic also exempted real secrets made of words (API_KEY=VelvetRiverOrbitSunset; in a .env). The scanner now takes the file path (ScanOptions.sourcePath): the pre-push hook scans the pushed diff per file with its +++ b/ path, and gstack-redact --from-file passes its path. Only in a TypeScript/JSX file is an unquoted value after ':' or a JSX brace of names treated as source; the same line in .env/YAML, or with no path, is scanned as a literal, and the jwt pattern still fires in .ts files. Co-authored-by: tianxchen <tianxchen@users.noreply.github.com> * docs: gstack's own CLAUDE.md routing block matches the new router wording Live check (Claude Code 2.1.284): a skill set to "off" in skillOverrides is absent from the session's skill list while its sibling is listed, and both are listed without the override, so 'route only to skills in your available-skills list' holds. * fix(sync-gbrain): don't offer a call-graph build for a source with no code pages (#3029) Step 3.5 offered --dream for any source with pages, including one that holds only markdown (synced with gbrain's default strategy), where a build cannot help, and the injected CLAUDE.md guidance told future sessions to run --dream for any count: 0. On gbrain >= 0.60, code-def for an impossible symbol answers .status (probed live against gbrain 0.60.96: ready for a code source, out_of_scope for a markdown-only one). Step 3.5 now probes the pinned source first, reports the cause instead of asking on out_of_scope, and keeps today's offer when the probe is unknown (older gbrain, an error). gstack's own sync uses --strategy code, so the PR's soft-delete claim does not apply to gstack's path. Co-authored-by: syong <syong@users.noreply.github.com> * fix(setup): register the hooks that parse, refuse the rest with file:line (#3032) The landed gate stopped setup before any registration, so one unparseable hook left every other hook unregistered. On the Claude install the canonical root is the checkout Claude Code runs hooks from, so there is no staged swap to abort: setup now registers the hooks that parse, refuses the ones that do not with file and line, finishes the install and exits non-zero, saying it is a gstack bug and that a skipped hook keeps running from the checkout. bin/gstack-hook-check derives its list from setup's _hook_command_path calls plus the autoplan phase-publication hook (a test keeps them equal), parses each shim with its shebang's interpreter, and bundles each TypeScript entry with its local imports (packages external) into a temp dir, so a broken or missing import, or a missing entry, fails. Co-authored-by: BenjaminDSmithy <BenjaminDSmithy@users.noreply.github.com> * fix(auto-update): hold an update whose hooks do not parse, before the checkout moves bin/gstack-session-update fast-forwards the live checkout before setup runs, and Claude Code runs hooks straight from it, so setup's gate cannot protect an auto-update. After the Bun floor check the updater extracts the incoming revision with git archive and runs bin/gstack-hook-check on it; a failure holds the update like bun-too-old, records hook-does-not-parse with file:line in the update status, and the next session start says the current hooks keep running. Fixture-remote tests cover a broken shim, a broken imported module and a parseable control. Co-authored-by: BenjaminDSmithy <BenjaminDSmithy@users.noreply.github.com> * fix(browse): chain with no flow is a usage error before any daemon boots (#3039) Empty piped input, a terminal with no arguments, and a readFileSync(0) error (EAGAIN, EOF) now print the chain usage with the cause and its troubleshooting link and exit 1 before ensureServer(), instead of sending an empty argument to a daemon the CLI booted for it. Tests run the real CLI with no daemon and no browser, plus the stub-daemon flow. Co-authored-by: VaibDeveloper <VaibDeveloper@users.noreply.github.com> * fix(browse): refuse a runtime-root CLI and checkout server from different builds (#3026) A Windows runtime root runs the source checkout's Node server bundle through .source-path. When the root's CLI and the checkout's bundle carry different browse/dist/.version builds (the checkout was rebuilt without refreshing the root), the CLI now refuses to start the server with both builds, the ./setup fix and its troubleshooting anchor. Unversioned dev builds are not called skew. Co-authored-by: ubay887 <ubay887@users.noreply.github.com> * ci(windows): real isolated ./setup install, then a piped chain flow through the installed browse windows-setup-e2e built the checkout but never ran ./setup. It now installs the codex host into an isolated HOME (a runtime root copy with no node_modules), then from an unrelated directory pipes a two-command chain flow at a loopback page into the installed browse and asserts the page text, and that empty piped input exits 1 with the usage error. Covers the checkout-bundle path and the piped-stdin path end to end. * test(lint): free text never enters a generated command (structural rule) The generated-bash lint's untrusted-in-quotes rule (gh/glab/git/curl text flags in double quotes only) becomes free-text-placeholder: any <placeholder> anywhere in any command, in double, single or no quotes, and in heredoc bodies (quoted or not), unless it is on the reviewed identifier allowlist (test/helpers/placeholder-allowlist.ts) with the grammar a value must match. Quoted-only identifiers (URLs, selectors, paths printed by gstack) must sit inside quotes. Backslash-newline continuations now read as one command, so a flag and its value on separate lines are still seen together. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: reply, issue and spec text travel as agent-written files, never through a heredoc Replaces the quoted-heredoc bodies with CEO-12's file mechanism: a bash block creates a private mktemp file in the project's .gstack/tmp/ (kept out of git through .git/info/exclude), the agent writes the text with its file-write tool, and the next block posts with -F body=@file, --body-file or "$(cat file)". A heredoc ends early at any body line equal to its delimiter; a file has no such line. When the file was never written the block refuses with the path and the command to send it by hand, and it deletes the file after a successful post. - review/greptile-triage.md: replies; the fetched JSON moves from fixed /tmp/greptile_*.json paths to a mktemp directory; REPO and PR are re-derived per block instead of read from a previous shell. - Test-failure issues: title and body files, platform case on github/gitlab, assignee only when it is a valid login. - /spec: one draft file feeds the audit hash, every redaction scan, the issue and the archive; the archive no longer expands <title>/<body> inside an unquoted heredoc; the decision-log JSON is built by jq from files. Location verified against Claude Code 2.1.284 (Dockerfile.ci pin): project-local .gstack/tmp is writable under acceptEdits with no prompt and keeps mode 0600; $TMPDIR and the gstack state root prompt even under acceptEdits. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix(ship): Greptile triage runs only when a PR exists; every other case says why PR: unknown (gh missing, not logged in, a non-GitHub remote, or a failed lookup) used to dispatch the triage child anyway. The Step 10 check now tests gh, its login, the remote and the PR in that order, and every case but 'PR: exists' skips the dispatch and records 'Greptile: not run (<reason>); runs on the PR once it exists'. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: question-tuning commands carry no free text The question log took the summary in single quotes and the preference write took the user's own words; an apostrophe ended the quote and the rest ran as shell. The summary is now a kebab-case slug (an identifier with a grammar), and the optional free_text field is no longer passed from skills (the binary still accepts it). * fix(cso): Windows finds docker.exe only under known-folder roots and says transport is unsupported (#3028) On Windows /cso looked for docker only in Git's directory and System32, so Docker Desktop was never found and the gap read as 'not installed'. It now resolves Program Files, Program Files (x86) and the Windows directory through PowerShell's [Environment]::GetFolderPath (not the process environment), checks each candidate's real path against those roots and rejects reparse points. lib/cso/docker.ts admits only unix:/// endpoints, so a trusted docker.exe reports 'native Windows Docker transport is not supported yet; static assessment only'; one outside the roots is refused as outside the trusted install locations, not overridable. Both carry an anchor. Native named-pipe transport is not implemented. * fix: sourced helpers share one self-locate block and fail loudly when they cannot locate themselves (#3024 rework) The codex probe and the egress lib now carry one byte-identical block: BASH_SOURCE under bash or %x under zsh, made absolute with $PWD, else a set GSTACK_ROOT that holds the helper. Anything else (dash, sh, a shell that cannot name the file) prints "gstack: cannot locate <helper> (shell: ...)" with the docs/troubleshooting.md#sourced-helper-location URL and returns before any bash- or zsh-only syntax. The Claude-only default path and the $(pwd) fallback are gone. The generated Codex preflight dot-sources the probe and, when it cannot load, reports CODEX_MODE: helper_unavailable with the helper's own line instead of falling through to not_authed. The class guard enumerates nested sources, makes real resolver, auth, state-root and egress-home calls under bash and zsh (absolute, relative then cd, bare name via PATH), covers dash and an unknown shell, runs the full preflight, and lints BASH_SOURCE to the shared block plus other bash-only constructs. Co-authored-by: marcosdetry <marcosdetry@users.noreply.github.com> Co-authored-by: akshaykalia <akshaykalia@users.noreply.github.com> Co-authored-by: scottgigante-hubflow <scottgigante-hubflow@users.noreply.github.com> Co-authored-by: woodsonl <woodsonl@users.noreply.github.com> Co-authored-by: bezdekt <bezdekt@users.noreply.github.com> * fix(cso): a Maven or Gradle repository is Java, not Python (#3028) With no supported stack metadata, preparation defaulted to Python and asked a Java repository for requirements.txt. A root pom.xml, build.gradle or build.gradle.kts now names the stack as Java (unsupported for runtime preparation, so the prerequisite says so), and Python helper scripts or a root requirements.txt beside it no longer make it Python. * fix(browse): BROWSER.md says plainly how to enable WebGL; the mismatch refusal links Daemon discipline (#3030) The GSTACK_DISABLE_GPU row now states the effect and the switch: set GSTACK_DISABLE_GPU=off to enable WebGL (off is the only recognized value). The reworded config-mismatch refusal links BROWSER.md's Daemon discipline section. Free tests pin both. Co-authored-by: Hagetino <Hagetino@users.noreply.github.com> * test(windows): name the B2, B4, B5 and B12 tests in the curated Windows lane The runtime-root bundle tests lived in browse/test/config.test.ts and the Copilot glossary test in test/host-config.test.ts, both excluded from the Windows lane, so the two Windows-only fixes were never checked on Windows. Move each into its own Windows-safe file (unchanged assertions) and list it, the piped-stdin chain test and the /cso docker.exe discovery test as named Windows coverage in scripts/lib/windows-curation.ts. * fix: the free-text block exits loudly when mktemp fails; spec and redact tests follow the file mechanism The redact resolver test, the #2679 mktemp guard test, the /spec invariant and the spec secret-sink harness pinned the heredoc transport. They now pin the agent-written file: the harness runs the draft-file block, writes the draft the way the file-write tool would, then runs the real scan fence, with every HIGH/MEDIUM/scanner-failure assertion unchanged. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * test: hostile payloads through the generated posting blocks, identifier grammars, every quoting shape - The lint reads a whole command, so an unquoted multi-word placeholder is caught; negative controls cover double, single and no quotes, quoted and unquoted heredocs, continuation lines, and quoted-only identifiers used unquoted. - Every allowlisted grammar rejects quote-breaking characters (and shell operators and whitespace when used unquoted); git accepts 'fix;id' and 'fix`id`' as branch names, the ref grammar does not. - Greptile replies, test-failure issues (GitHub and GitLab) and /spec filing and archive run from the real generated text with stub gh/glab: a body with backticks, $(...), an apostrophe and lines equal to EOF and the old heredoc delimiters arrives byte for byte, nothing in it runs, and the temp file is gone. An unwritten file is refused with its path and the manual command, and nothing is sent. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * test(ship): the PR check precedes the Greptile dispatch, and each skip names its reason Runs Step 10's generated check against stub gh for gh missing, not logged in, a non-GitHub remote, no PR, a failed lookup and an existing PR. Fails on the previous text (which printed PR: unknown and dispatched). Co-authored-by: dgrant <dgrant@users.noreply.github.com> * feat(ship): ship-measure runner for the measure-then-fix loop (A6) scripts/ship-measure.ts owns /ship's diagnostic measurement of a red eval case: per-kind aggregation (rule trials; behavior panels of 3, each at its own 2 of 3 plus 90% of trials; judge outputs scored by 3-sample panels, standalone judge ids accepted), one artifact directory per baseline, repair round and trial, a diagnostic label with verdict null that refuses the eval history dir, an estimated admission budget that reserves every concurrent trial and reconciles actual cost, the ask-once rule, the repair-round limit, the unmeasured skip and the per-case PR table. Free-suite flakes (CEO-1): 'free' reruns one shard's exact file list N times, rerun 1 alone as the baseline and the rest in parallel at max(1, floor(cores / shard concurrency)), each with its own HOME, state root and flake ledger, GSTACK_FREE_RETRY_FLAKY=0, under a wall cap that reports a partial count. test:ubicloud --diagnostic runs the same on one VM with the retry off. bin/gstack-config gains the DX-7 keys with their CEO-9 defaults and rejecting validators. Free tests drive every kind, the budget stop, the unmeasured skip and the free reruns with fake runners. * fix: a Codex usage limit is quota_exhausted, a plain 429 is rate_limited, and only Codex's own error lines count (#3051 rework) The probe's quota signature used to treat any rate limit, "too many requests" or 429 as quota, and read the whole output, which echoes the prompt. Now only Codex's trailing ERROR: / stream error lines are read. A usage-limit or insufficient_quota line is MODEL_QUOTA_EXHAUSTED (exit 4, cached 15 minutes; quota wins over a 429 that names insufficient_quota); a plain 429 is MODEL_PROBE_RATE_LIMITED (exit 0, state rate_limited, never cached), reported as CODEX_MODE: unverified (rate_limited) so the review still runs and decides. The quota HINT says how many minutes gstack skips Codex and how to retry now (GSTACK_CODEX_PROBE_RETRY=1 skips the negative cache for that probe, or delete <state root>/.codex-model-probe), with the full troubleshooting URL. classifyOutsideReview reads the same trailing lines: a mid-review quota is unavailable (quota_exhausted), a mid-review 429 unavailable (rate_limited). New gate row rate_limited and docs anchor codex-rate-limited; the quota row documents the retry. Tests cover each line shape, the echoed prompt, exit 0, timeout, retry recovery, probe/classifier parity, and two fresh-shell preflight blocks where the second makes no paid Codex call. Co-authored-by: venkatareddyg <venkatareddyg@users.noreply.github.com> * ci: the eval image installs zsh, and the macOS lane sources the Codex probe from zsh Dockerfile.ci adds zsh so the sourced-helper guard runs (and fails loudly when zsh is missing) inside the eval container too. The macOS named regressions job sources bin/gstack-codex-probe from zsh in an unrelated directory and runs _gstack_codex_select_model exec (no paid call), then runs the sourced-helper guard on the macOS runner. A free test pins both lanes and runs the macOS step's script locally. * test: deterministic regression for the Codex watchdog freezing the command before reaping its children The existing stubborn-child test caught the reap-then-kill race only some of the time (2 of 3 runs on the pre-fix watchdog). A pkill that sleeps after reaping widens the window between reaping the children and killing the command, so a watchdog that does not SIGSTOP the command first always lets it print "late" after the deadline. Fails 3 of 3 on the pre-fix watchdog, passes 3 of 3 on the current one. * test: live codex smokes run codex in a private HOME and CODEX_HOME codex-resume-flag-semantics and codex-e2e-sol-scope probe the codex CLI (the latter at module load, in every free run), and every codex run writes $CODEX_HOME/tmp/arg0, so with a real codex on PATH they wrote into the developer's ~/.codex. Both now give codex a private HOME and CODEX_HOME and remove it afterwards. A free test runs each file against a stub codex that records HOME and CODEX_HOME and asserts neither is the caller's. * feat(ship): a red eval runs classify, measure, fix, re-measure, gate once (A6) Step 6 no longer stops at the first red paid eval: it reads the new lazily loaded measure section and runs the loop for each red case, and Step 5 measures a failed free-suite shard (diagnostic reruns, retry off) before the triage can call it pre-existing. The section states the diagnostic- not-verdict rule, the per-kind table, the ask-once and named-red stops, the unmeasured label and the honest-fix wording (observed k/n after fix at <cause>). A free test pins the steps and their order in the generated skill and checks every command and flag it names exists in the runner. Ship's parity cap rises to 1.455 (measured 272,944 / 187,706 = 1.4541). * docs(testing): diagnostic measurement is not a verdict; per-kind measure table (A6) * test(ship): seeded-flake paid case for the measure loop (A6, periodic, behavior) A fixture repo with no remote documents a single-case eval command and a gate command, both free local stubs. queue-priorities claims trial slots with atomic mkdir (reset per ship-measure round) and fails slots 2, 5 and 9 while src/priorities.js leaves its seed-shuffled list unsorted, printing failure_cause and failure_detail that name the line. The paid case gives /ship's generated Step 6 and measure section to a live session and asserts it measured the case alone, fixed the named line without touching the eval, re-measured at least 10 passing trials on the sorted file, and only then ran the gate once; any question other than the spend question is a contract violation. A free test measures the fixture through the real ship-measure CLI: 7/10 unsorted, 7/10 after an unrelated edit with the gate still red (ENG-13's negative control), 10/10 after the sort with the gate green. * test(cso): the missing-scanner case points Docker at a dead socket 'an optional scanner prerequisite does not turn completed manual coverage partial' assumed no usable Docker. On a machine with Docker and a pulled gitleaks image the scan completed and the test failed (also on main). The scan step now gets a DOCKER_HOST that cannot connect, which is the prerequisite-missing condition the test describes. * fix: Aside prompts travel as agent-written files, never inside the command The open-ended reading recipe (browse, devex-review), scrape's fuzzy-intent read and the shared web-research block put the model's question, query and reply format inside a double-quoted _aside_exec argument, where backticks and $(...) from page or repo text would run. The agent now writes the prompt into a private .gstack/tmp file; the send block rebuilds the path from the printed basename, refuses when the file is empty, and passes "$(cat "$PROMPT_FILE")". The fixed read-only sentence stays in the shell source. aside-driver pins move from the inline prompt to the file-based send block. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: design briefs and approval feedback travel as agent-written files Design briefs went into $D variants/generate/check as a double-quoted argument, and approval feedback was spliced into a single-quoted echo of JSON, so a quote, backtick or $(...) in either broke the command or ran. The agent now writes each brief into a private .gstack/tmp file and the block passes --brief "$(cat "$BRIEF_FILE")" (the CLI's --brief-file expects a JSON brief, so plain text uses --brief). variants and the later check reuse the same brief file. approved.json is built with jq -n from --arg values and --rawfile feedback, so the feedback is data. The office-hours mockup flow creates its brief and feedback files in one block. design-approval-flow now writes the feedback file (with quotes, backticks and $(...) in it) instead of substituting <FEEDBACK>, and checks the file is removed after the save. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: carve office-hours on every host to stay under the 160,000-byte ceiling With its brief, feedback and research prompts moved into files, the inlined office-hours render is 161,329 bytes on Codex and 160,302 on Factory, over SKILL_BYTE_CEILING, so gen-skill-docs --host all fails. Per the C4 policy (carve every skill whose external render exceeds the ceiling), office-hours joins ship and plan-ceo-review in CARVED_ON_EVERY_HOST. The Claude render is unchanged; external hosts read its sections relative to the installed skill. external-host-carve and qa-lazy-sections now include office-hours in their carved-skill lists. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * chore: regenerate after the free-text mktemp guard * fix(codex): prompts and review focus travel as agent-written files Co-authored-by: dgrant <dgrant@users.noreply.github.com> Challenge and consult prompts, and the /codex review focus text, are written by the agent into private .gstack/tmp files and fed to Codex on stdin or read back with cat; no heredoc carries them. Consult's new and resumed runs share one block (and one parser) so no placeholder stands in for the parser; a resumed run reads its session id from .context/codex-session-id and checks it. Adds the A3 group 2 placeholder allowlist block. * fix(benchmark-models): an inline prompt goes through a prompt file Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix(land-and-deploy): PR head repository and branch travel as data Co-authored-by: dgrant <dgrant@users.noreply.github.com> The branch check reads headRepository/headRefName from gh's JSON into quoted shell variables; ls-remote, the confirm-first delete and the local delete use those variables instead of model-substituted names. The postfail test now pins the variable form it replaces. * fix(office-hours): the reviewer receipt must match the receipt grammar before the check runs Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix(setup-gbrain): cleanup-orphans collects the PAT with read_secret_to_env Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix(ship): PR body drafts and rejected test paths are agent-written files Co-authored-by: dgrant <dgrant@users.noreply.github.com> The PR body is written into two private drafts (through ## Documentation, and from ## Test plan on); the scan block splices Step 14.5's section between them into the scanned temp file and deletes the drafts. Rejected test paths are read from a written list, and paths outside the repository are skipped. Tests that ran the old heredoc blocks now write the drafts and list first. * fix(sync-gbrain): orchestrator flags must match an allowlisted grammar Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: the gbrain page save and external-host placeholders pass the free-text rule The gbrain save block passed the whole page through a quoted heredoc inside --content; the agent now writes it to a mktemp file and gbrain put reads it on stdin. The Claude Code outside-voice runtime root and session mode, and the feature slug, join the allowlist with grammars; unused entries are dropped, and a test keeps every allowlisted placeholder tied to a real use. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: skill-specific Aside research queries travel as prompt files investigate, office-hours, plan-ceo-review, review, plan-eng-review, design-consultation Phase 2, the shared test bootstrap (B2) and QA's test bootstrap each carried their own _aside_exec call with the model-filled query inside a double-quoted argument. Skills that already carry the Web research block now give only the prompt-file text and use that block to create, write and send it; design-consultation, the shared bootstrap and QA create the file and send it with the new {{ASIDE_RESEARCH_SEND}} resolver, which is the same send block the research section uses (read-only sentence stays in the shell). aside-driver's B2 pin and qa-browser-preservation's bootstrap contract move from the inline call to the prompt file and the shared send resolver. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * fix: prose design commands pass briefs and feedback as data The DESIGN_SETUP command list taught `iterate --feedback "..."`, and design-consultation's late-change and plan-design-review's slop-regenerate lines showed `--feedback "<feedback>"` / `"..."`; design-shotgun's retry showed `generate --brief "<brief>"` and `evolve --brief "<brief>"`. Feedback now reads "$(cat "$FEEDBACK_FILE")" from an agent-written mktemp file (the setup note says how), and the shotgun retry reads the variant's own brief out of briefs.json with jq instead of retyping it. Co-authored-by: dgrant <dgrant@users.noreply.github.com> * test: record parity sizes after the free-text file mechanism; refresh ship goldens Measured union and skeleton sizes for ship, plan-eng-review, plan-design-review, office-hours, design-consultation, review, qa, browse and design-shotgun after every posting, prompt and brief site moved to agent-written mktemp files; the ship goldens pick up the question-tuning slug and the dropped free_text field. * test: parity caps for the combined wave head (rounded up past the measured ratio) * fix(plan-ceo-review): the mode handoff helper reminds the model to lead its chat with the line (#3038) Periodic run 37272185151's auto-decide-preserved red replays as the Step 0E handoff-line class: the model ran gstack-ceo-mode-handoff --auto, got the exact line, then opened its chat with a heading and a paraphrase, so the user never saw the auto-decide line (the terminal collapses tool output) and the detector saw no outcome. The helper now prints a one-line reminder on stderr beside the line; the detector accepts the line followed by that reminder and nothing else. The ship Greptile check test reads its template (test-of-test ratchet). * test: every troubleshooting link in shipped code resolves, relative or full URL * docs(todos): Oct 6 fix-wave follow-ups * v1.91.32.0 release notes: Codex works from zsh, free text never enters shell commands, honest failures * fix(plan-ceo-review): show the mode handoff line through a PostToolUse hook, not model compliance (#3038) The stderr reminder beside the handoff line measured 1/10 on auto-decide-preserved: the model still opened its chat with a paraphrase ('I've set review mode to HOLD SCOPE...'), so the user never saw the line and the detector saw no outcome. /plan-ceo-review now declares a Claude-only PostToolUse hook that shows the helper's exact line as a system message. Diagnostic measurement on this head: 10/10, the line visible in every trial while no trial's chat led with it. The reminder is reverted. * fix: type the handoff hook's line filter * fix: repairs from the integrated free suite - The self-locate markers looked like heredocs to the pipe-deadlock guard; they are plain comment fences now. - The spawned block keeps the canonical 'conservative non-destructive' phrase the cross-surface drift guard pins. - The free-text block's mktemp refusal says 'mktemp failed', as every /codex temp file must. - The batch transcript read reports sizes in MiB. - docs/TESTING_INTERNALS.md gets a real 'Ship measure' heading for its anchor. - The early-question harness admits /plan-ceo-review's handoff hook by its exact command (it only adds a system message); any other PostToolUse Bash hook is still refused. - Paid file count and the unconsumed-file example follow the new seeded case; ship goldens refreshed. - The CSO scanner test points Docker at a dead socket, so a machine with the pulled image does not scan. * test(cso): a host with no Docker binary is also a no-scan host The missing-image scan test failed on a Docker-less VM (docker is not installed in a trusted directory). Every accepted message is a reason the scan cannot run here; the not_assessed, helper-owned artifact assertions are unchanged. * ci: split the USERPROFILE assignment from export (SC2155) * fix(browse): Windows runtime roots read .source-path as a native path (#3026) The new windows-setup-e2e journey showed the installed browse could not start its server. setup runs under Git Bash and wrote .source-path as an MSYS path (/d/a/gstack); Node read it as \d\a\gstack on the current drive, found nothing, and fell back to the root's own bundle, which cannot import playwright. setup now writes cygpath -m, and the CLI maps an MSYS drive path for installs written by an older setup. The journey prints the daemon and startup logs when the chain fails. * fix(ship-measure): defects from the parallel #3034 plan review - A trial passes only with a JUnit testcase that executed and passed; a --case that selected nothing also exits 0. - measure runs a no-cost --list preflight that must plan the case's own file before any paid trial. - Diagnostic trials drop EVALS_CACHE_DIR/EVALS_CACHE_RUNTIME_ID, so they never reuse a stored judge pass or publish one the gate could reuse. - Gate once: when CI runs the gate on push, the push is the gate run; the skill no longer also starts eval:bg:pr (a second paid gate). - ubi-runner: down fails unless the VM is confirmed gone, and nothing sweeps other runners' VMs by default (UBI_GC_HOURS opt-in). * test(windows): the seeded-flake fixture drives a POSIX shell stub, so it stays off the Windows lane CreateProcess cannot exec the fixture's ./evals.sh shebang script (status null on windows-free-shard 6). The measure runner is covered on Windows by ship-measure.test.ts, which uses in-process fake runners. * fix: the free-text block refuses an unset temp dir instead of writing at / The rendered block ran mktemp "$_GT/..." with _GT unset in the portability test; on Linux that fails at /, but Git Bash on Windows can write to its install root, so the block went on (windows-free-shard 3). It now uses ${_GT:?}, so an unset directory always fails closed with the mktemp message. * test: pin the guarded ${_GT:?} temp-file form * test: the Greptile check's gh stub uses a portable shebang On Windows the absolute bash path has a space, so the stub never ran and every case read 'gh not logged in' (windows-free-shard 1). * test: the Greptile check runs with the native PATH and the gh stub first The PATH-only stub bin could not run its stub on Windows (every case read 'gh not logged in'). Stub cases now keep the real PATH with the stub first; only the no-gh case drops directories holding a real gh. --------- Co-authored-by: marcosdetry <marcosdetry@users.noreply.github.com> Co-authored-by: akshaykalia <akshaykalia@users.noreply.github.com> Co-authored-by: scottgigante-hubflow <scottgigante-hubflow@users.noreply.github.com> Co-authored-by: woodsonl <woodsonl@users.noreply.github.com> Co-authored-by: bezdekt <bezdekt@users.noreply.github.com> Co-authored-by: dgrant <dgrant@users.noreply.github.com> Co-authored-by: venkatareddyg <venkatareddyg@users.noreply.github.com> Co-authored-by: CharlesBerg85 <CharlesBerg85@users.noreply.github.com> Co-authored-by: VaibDeveloper <VaibDeveloper@users.noreply.github.com> Co-authored-by: Hagetino <Hagetino@users.noreply.github.com> Co-authored-by: Rekin226 <Rekin226@users.noreply.github.com> Co-authored-by: ekson73 <ekson73@users.noreply.github.com> Co-authored-by: tianxchen <tianxchen@users.noreply.github.com> Co-authored-by: BenjaminDSmithy <BenjaminDSmithy@users.noreply.github.com> Co-authored-by: ubay887 <ubay887@users.noreply.github.com> Co-authored-by: nareshh74 <nareshh74@users.noreply.github.com> Co-authored-by: syong <syong@users.noreply.github.com> |
||
|
Garry Tan
|
55f8151fbe |
v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033)
* docs: approved reliability follow-ups plan (Oct 2026)
* D1: score overlay wrong answers as comparison results (contract v4)
A completed answer that fails the fixture's output check is now a valid
measurement with taskCorrect false and answerError set, in either arm.
Only execution, scope and metric failures invalidate a trial. ON
correctness still gates the case, so an OFF wrong answer stays in the
comparison. OVERLAY_CONTRACT moves to v4; v3 verdicts are not
reinterpreted. Replays the 37198445662 sonnet trials (OFF-0 wrong).
* C4: score auq-matrix substance with a 3-sample judge panel
Each skill keeps one native capture in the same execution; the
recommendation-substance grader now runs as a JUDGE_PANEL_SAMPLES panel on
that capture and gates on the mean against the unchanged minimum of 4. A
failed sample fails the panel without resampling. Approved at the gate
2026-10-04 for censuses after this change.
* E1: one Bun version source; setup refuses below the 1.3.3 floor, updater checks before advancing
bin/gstack-bun-version.sh holds the security floor (1.3.3) and the tested
version (1.4.0, the CI pin and engines.bun). setup refuses Bun below the
floor before writing anything, warns between floor and tested, warns and
continues on an unparseable version, and prints a 1.4.0 install hint.
Prereleases sort below their release (semver).
gstack-session-update now fetches, reads the incoming release's floor and
checks the bun setup will run before fast-forwarding to that exact
revision; below it the update is held with reason bun-too-old and a
resume command, leaving the revision and installs untouched.
Fixture copies of setup (team-mode, claude-code migration) now include the
sourced file; the slow-git lock test sleeps on fetch, the updater's
network step.
* E3: record the owned Chromium's PID over CDP so the #2709 reap runs on Playwright 1.62
Playwright 1.62's Browser has no process(), so chromiumProcInfo was always
null and browse stop never reaped a surviving headless Chromium. The owned
headless launch now reads the browser PID from CDP SystemInfo.getProcessInfo
(bounded at 2s; a hung or failed call logs once and records nothing). The
reaper's start-time and cmdline identity checks are unchanged, so a recycled
PID or an externally owned browser is never signalled.
* A1: ship docs gate records post-child hashes with gstack-docs-candidate, saves each record once
Stored transcripts (37198445662 gate-census-2) show the parent's reads of
release files take ~1 s; the parent's own model time dominates (completion
268 s of 392 s, store ~270 s of 387 s), and 45-78 s of it is retyping hash
maps, child output and records into several artifacts after the child
returns. The child contract is unchanged.
* A2: /plan-ceo-review sends the mode handoff line before any other tool call
plan-ceo-mode-routing's HOLD SCOPE session spends its 240 s post-selection
window on model work: 37176837432 skipped the handoff helper and paraphrased
the mode, 37198445662 ran it, then wrote the plan, loaded sections and probed
Codex for 114 s before the posture chat. The handoff line is the posture.
* B3: accept wrapped unchanged rows in the cropped Edit preview
PR run 37176835584 timed out with the floor's owned Edit menu on screen:
unchanged diff rows soft-wrap under their gutter with a blank marker
column, and a trimmed empty unchanged row keeps only its number. The
parser accepted wrapped +/- rows only, so it never verified the owned
edit. Both forms are now parsed and still compared with the exact source
lines; the captured viewport is replayed with negative controls.
* A3: record per-phase headroom diagnosis for docsync, plan-mode-no-op, mode-routing and gate slice 11
* E4: /review Step 1 keeps going when the base fetch fails and reports stale base coverage
Under Codex's read-only .git, 'git fetch && merge-base && diff --stat'
stopped at the fetch, so the empty output read as 'Nothing to review'.
The fetch is now separate, prints BASE_REFRESH fresh or stale with the
local base revision, and the review states stale coverage.
* D2: reword the format-approach question prompt
Both plan-ceo-review-format-approach refusals in census 37195203538
(Fable 5.1 model_refusal_no_fallback, category reasoning_extraction:
"duplicating model outputs") were anchored on the session prompt, whose
capture instruction asked for the "verbatim" question and "the exact
prose you would have shown" in a "format-capture test". The approach
case now asks for the same question in the same file as the step's
output, without that wording. The other three plan-format cases keep
their unchanged prompt (no refusals in 72 trials).
* C2: /qa defines its outcome filename fields; QA report templates name the measured timing fields
Low judge samples in failing panels named both: qa workflow (37186854666)
'an undefined {user} in the outcome filename', and qa-only workflow
(37198445662) 'template asks for Duration / durationMs totals while
reporting.md mandates Probe budget and Guarded command time'. The qa
union stays under its 1.11 size ratio (93292 of 93294 bytes).
* 0.1: session ledger written by the claude -p, Agent SDK, PTY and Codex runners
Each armed model session appends one best-effort line to
$GSTACK_EVAL_DIR/session-ledger.jsonl: a stable session key, the timeout it
armed, monotonic elapsed time, its end reason (completed, session_timeout,
observer_timeout, api_error, refusal, aborted, error), one sanitized evidence
line and, for stream-JSON runners, a compact liveness summary (longest
in-request silence with nothing outstanding, last event kind, tool open at
end). Partial messages now stream for every claude -p session and for SDK
sessions without a custom query provider (runSharedInteractive opts in); their
rows feed only the summary, so transcripts keep their size unless
publicStreamDiagnostics is set. Structured refusal and API-error signals win
over phrases, and tool results are never read for them.
* 0.2: failure_cause beside failure_class, from runner facts and the session ledger
One pure failureCauseOf() beside failureClassOf() sets failure_cause
(contract > pre_turn_infra > api_error > refusal > provider_stall >
session_timeout > observer_timeout > assertion > unknown; no machine-set
'detector') with one bounded evidence line, and failureDetailOf() keeps a
Bun matcher's Expected/Received or a judge's failing dimensions in
failure_detail. Both record builders (classifyTrialShard, junitCensus) call
them and attach the trial's ledger sessions. failure_class, error and
TRIAL_ERROR_MAX are computed exactly as before; the new fields are optional,
bounded and validated only when present, and a frozen copy of the v1 reader
accepts every new record. A provider stall needs partial messages and
STALL_WINDOW_MS (120 s, eval-budgets.ts beside HEADROOM_WARN/FAIL) of
in-request silence with nothing outstanding; it stays a failure under
EVAL_POLICY v1.
* E4: fingerprint under a read-only .git via a private object dir owned by review-log
Codex's sandbox mounts .git read-only, so gstack-wtree's git add -A could not
write blobs and /review lost its start capture. gstack-review-log now creates
a private 0700 object directory under TMPDIR, passes it to gstack-wtree (which
writes new objects there with the common-dir object store, resolved before
exporting, as an alternate, so linked worktrees work), exposes it to the
bindReview/checkSharedLibsReuse consumers that read the tree and blobs, and
removes it on EXIT/INT/TERM after they finish. gstack-wtree prints one stderr
line and exits 1 on a failed write or unwritable TMPDIR instead of printing a
partial hash; review-log no longer swallows that line. Standalone gstack-wtree
keeps writing to the repository store so git diff between saved snapshots
(/ship) still works.
* 0.3: red lines name their values, evidence and an after-a-repair command; one published-text sanitizer
Each red line in the census report keeps its stored error and adds the
machine cause with its evidence, the failure_detail values (Expected/Received,
or each failing judge dimension with its mean, sample count and the sample
sentence naming it), the slice artifact and shard directory that hold the
transcript, a fetch command (eval:pass-rates --run <id> --case <id>), and
'after a repair:' with a command that selects only that case (E2E ids via
--case, judges via their selection and an exact test-name filter). A
session that completed and failed a check says so instead of 'assertion
(success)'. Report text that reaches a PR comment, issue or committed file
goes through scripts/lib/published-text.ts: control and bidi characters
stripped, credential-scan patterns redacted, mentions neutralized, HTML and
link brackets escaped inline, blocks in a fence longer than any backtick run,
length capped. Verdicts and collector verdict objects are unchanged.
* E2: one make-pdf resolver for readiness and every $P block on env-var hosts
make-pdf exported $P from its readiness block, which Codex and the other
env-var hosts lose between blocks. binaryAssignment gains 'make-pdf': the
MAKE-PDF SETUP readiness check and the runtime prelude both use it, so every
block that runs $P derives the same make-pdf/dist/pdf binary, with
MAKE_PDF_BIN (dev builds) winning when it is executable. Claude output keeps
its repo-local-first probe; only the false 'subsequent blocks' comment
changed. Root plus P=... fits the 400-byte prelude budget; the fixed
MAKE_PDF_OVERRIDE segment is the one exemption, named in runtime-root.ts and
the conformance test.
* 0.1: eval:pass-rates --headroom, --reds and --run report views; 85% headroom alarm in --gate
A new pure module, scripts/lib/eval-history.ts, reports per case the slowest
armed session against the timeout it armed (censored when it timed out,
insufficient below 3 samples, unknown without a session ledger, with the
case wall shown separately as an upper bound), the census critical path from
the slice jobs' timings, the verdict red ledger per census by failure class
and machine cause with shrunk per-case rates, and the all-green probability
(an approximation: the product of 1 - p_i, with an interval). --run <id>
lists one census's reds with their values and history and downloads only the
slice artifacts those reds name, reporting any over 64 MB instead of skipping
them. eval-flake-rank.ts only routes flags: --help works offline, an unknown
flag or case id exits 2 before any fetch, --case narrows the JSON and the
alarms, every view prints its run/branch scope, and --gate also alarms on a
session above HEADROOM_FAIL (85%) of its budget.
* E5: GSTACK_DESIGN_IMAGE_MODEL override; the live model check always tests the defaults
The image_generation tool model gains an env override validated against a
conservative gpt-image-<version> pattern; a bad value fails before any
request and the error names the variable. Pairing and rejection hints name
the tool model actually requested. design/scripts/live-model-check.ts now
ignores GSTACK_DESIGN_MODEL and GSTACK_DESIGN_IMAGE_MODEL (and says so), so
an override cannot mask a retirement of a default, and its exit 2 (no key)
says nothing was checked.
* C3: /deslop-shared-libs names a concrete risk for each recommendation, never 'none'
Both shared-libs-opportunity-judgment reds (37193478719 t3, 37195203538 t1)
failed adoption_and_risk because the top recommendation said 'Main risk:
none found inside the repo' / 'none in behavior'. The skill asked to 'name
the main risk or uncertainty' without saying what counts.
* B4: --case selects loop-registered cases; an unknown id exits before any process
caseSelection() resolves the one paid file that registers a case and how a
trial selects it: by its literal Bun test name, by the id a registration loop
names its test at runtime (coverage audits, TPA, journeys), or by running the
whole file when it registers no other case (plan-mode-no-op, whose test names
are not the id, so the old name pattern ran nothing). A whole-file case runs
one file shard per trial and is judged by shard status, as CI judges it.
--list prints the selection. Every E2E_TIERS id now resolves except
carve-section-loading, which fifteen files register (CI runs each as its own
shard) and which still fails with the owning files named.
* 0.3: after-a-repair runs the shard file when --case cannot resolve a case
A case that several files register (carve-section-loading) cannot be selected
by --case; its red line now prints the bun test command for the shard file
that went red, so every printed command selects exactly one case.
* C1: pre-register workflow-judge control bundles for qa, qa-only, review and setup-deploy
Positive (production bundle), negative (headings only) and one targeted
execution-blocking defect per judge, one 3-sample panel each, built with the
eval's own reader, prompt builder, options and floors.
* F: cost_known: a trial whose harness captured no billing says so; totals never hide it
cost_usd stays a finite number. Trial and eval records gain an optional
cost_known boolean (absent means known, so old records still parse; the
validator accepts only a boolean). Session-ledger rows record whether the
session's terminal result carried total_cost_usd; PTY and Codex sessions
never do, and SDK captures without a terminal result do not. A trial is
cost-known only when it has eval records and every record and session
captured billing, so JUnit-only PTY cases (125 of 298 trials in run
37198445662 recorded 0) now read cost unknown. The census headline prints the
known sum plus the unknown count, never a bare total over unknown costs, and
no total when every cost is unknown; the history import keeps the flag.
PTY transcripts are not priced: test/helpers/pricing.ts estimates exclude
cache writes, so they cannot give the billed cost.
* B1: replay corpora for the five repeat-offender cases
shared-libs-plan-callers, plan-ceo-section-loading, auto-decide-preserved,
plan-design-review-plan-mode and ship-docsync-late-result each get an
inventory of every wave census in scope (all artifacts still available)
and minimal, redacted detector or actor inputs replayed through the real
detector in the free suite: census passes, every distinct census red, and
derived negative controls labelled as derived. Fixed false reds stay as
expected passes with their history; the two genuine auto-decide product
failures (37176837432, 37179171083) stay refused. A contract test bounds
each entry at 64 KB, scans it for HIGH credentials, requires a pass and a
refusal per case, and reports entries whose series identity is stale.
Building the auto-decide corpus exposed a latent native detector misread:
a bold 'Mode application and rationale.' heading was parsed as a
withdrawn Mode field (37186854666). A field status now ends at its
sentence.
* B2: read approved stale-fill decisions from more valid ledger records
The structured ledger reader is authoritative before the prose fallback,
but it missed two valid approved records in passing censuses
(37186854666: a camelCase writeProfile subject; 37195203538: a
slash-joined 'D1 / STALE-FILL' row id), which then rested on the prose
detector that caused both historical reds. Both forms are accepted; an
unresolved row, an unrelated decision, the copied fixture plan and
non-write camelCase words stay refused.
* C1: record workflow-judge control results (negatives separated; qa and review miss a removed step)
* C2: record every low workflow-judge sample in the wave censuses with its disposition
* 0.3: published lines cannot break a fixed fence
evals.yml wraps collector-outcomes failures in a fixed three-backtick fence
for the PR comment, so those lines (and eval:pass-rates output meant for the
tracking issue) go through sanitizeFixedFenceLine: cleaned like every
published line, with backticks turned into quotes. Inline published text
also neutralizes backticks.
* A1: fit the post-child record wording under ship's 1.428 parity size cap
* E4: inline the Step 1 base refresh to fit review's 1.199 parity size cap
* B2: inventory of gate and periodic phrase-only detector checks
docs/evals/detector-inventory.md lists every pass/fail decision in gate
and periodic E2E cases that rests on phrases in model free text, with
its structured source (if any), whether the contract is user-visible,
and a disposition: already structured-first, convert candidate, phrase
witness required, or no structured source. Convert candidates are
ordered by census red history.
* 0.2: failureCauseOf takes the stall window instead of importing it; the PTY ledger never throws
eval-store.ts imported STALL_WINDOW_MS from eval-budgets.ts, which free tests
replace with mock.module stubs (review-finalization-budget, office-hours,
qa-fix-loop, qa-only), so loading eval-store failed there. failureCauseOf is
now dependency-free: the record builders pass STALL_WINDOW_MS. A PTY session
whose handle cannot show its text (test doubles) records no panel instead of
throwing from runPtySession's cleanup. The 37186854666 replay also runs
through classifyTrialShard.
* A2/auto-decide: the CEO handoff chat repeats the helper's printed line verbatim
Claude Code 2.1.284 collapses the helper's Bash output ('Ran 1 shell
command'), so the 'Auto-decided review mode → …' line reaches the user only
through chat. In lane D's auto-decide-preserved corpus every passing capture's
chat starts with that line, and the reds paraphrased it ('HOLD SCOPE was
auto-selected…', 'Mode decision done…', "I'm defaulting to HOLD SCOPE…").
The template now says verbatim and why.
* C2: record the judge panels rerun on the final ship and review wording
* integrate: touchfiles and module-size ratchet entries for the wave's new modules
GLOBAL_TOUCHFILES gains session-ledger.ts, published-text.ts and
auq-substance-panel.ts; bin/gstack-bun-version.sh joins every entry that
lists setup or the updater; auq-matrix stays a rule case with its C4
evidence beside E2E_KINDS; eval-history, published-text and session-ledger
are registered new modules.
* E1: BROWSE SETUP install hint pins the tested Bun (1.4.0)
* E2: quote "$P" in make-pdf commands so install paths with spaces work
* E1: /gstack-upgrade checks the incoming Bun floor before pulling
gstack_bun_incoming_hold (bin/gstack-bun-version.sh) is now the one
pre-advance check: the auto-updater calls it before its fast-forward and
/gstack-upgrade's git path calls it after fetching. Below the incoming
release's floor the upgrade stops with BUN_TOO_OLD and the checkout,
VERSION and installs stay untouched. Vendored installs were already safe:
setup refuses before writing and the swap restores the previous install.
* 0.3: only main posts or closes tracking issues; reports carry alarms, red ledger, headroom and all-green
A branch-dispatched periodic or marathon run writes its report to the step
summary and a report artifact; the upsert and close steps run only on
refs/heads/main. The periodic body now keeps every pass-rate alarm line (the
old grep kept only the header), adds the red ledger and session headroom read
with an explicit --branch, the all-green estimate and the triage guide link,
and routes report text through scripts/lib/published-text.ts. The marathon
lane gains the matching close-on-green step.
Migrated: evals-workflow-wiring pinned report-summary.md in the upsert step;
the body is now written by 'Write the census report'.
* C3: prosons neutral-posture detector ignores a negated "taste call"
Both plan-review-prosons-neutral-neg reds (37179171083 t3, 37193478719 t3)
recommended A and closed with "a coverage call, not a taste call"; the
old /taste call/i matched the negation. The detector moves to a helper so
the two census captures replay free as negatives, with positive controls.
* B2: credit the CEO mode handoff only when the chat shows its line
Claude Code 2.1.284 collapses the gstack-ceo-mode-handoff Bash result, so
the printed AUTO_DECIDE line is user-visible only when a later chat message
of the session begins with it. The native detector now requires that
witness; the helper's tool result locates it but no longer replaces it, and
a generic mode statement cannot stand in once a handoff ran. Census
37182865432 is relabelled a genuine miss (expected: refused): the chat said
"I'm defaulting to HOLD SCOPE…" and "Mode decided: HOLD SCOPE". Corpus
replay: 5 credited, 3 refused. ceo-mode-handoff tests migrated to the
witness rule (deliberate behavior change).
* test: baseline the wave's approved detector and harness replay tests
B1 corpora, B3, C3, C4 and D2 replay captures through paid-case detectors,
actors or fixtures (test code by design); each entry carries its reason.
* E6: live Codex multi-block periodic case in the host-run Codex job
test/codex-e2e-multiblock-live.test.ts runs ./setup --host codex once from the
job's checkout into a fresh HOME and CODEX_HOME (auth.json copied from the CI
login home), asserts codex debug prompt-input lists the gstack router as a
real file, seeds one learning, and runs /learn's Show recent block through
codex exec: that later block must root itself through its prelude, run the
installed gstack-learnings-search and print the seeded learning; no block may
report a missing install or an unresolved gstack helper path.
The file joins CODEX_CI_FILES so the planner gives it to the host-run Codex
job. paid-test-durations.json carries a 180 s packing estimate (refreshed by
--write-durations after the first census) so the plan keeps every slice
within max-parallel. Oracles live in test/helpers/codex-multiblock.ts with
free replays in test/codex-multiblock.test.ts. Registration (E2E_TOUCHFILES,
E2E_TIERS periodic, E2E_KINDS rule) is the integrator's.
* E5: design live-model check as a periodic case
test/skill-e2e-design-model-smoke.test.ts runs design/scripts/live-model-check.ts
(default models only) under a temp HOME. Without OPENAI_API_KEY the case is a
Bun skip that the census lists as SKIPPED with no coverage credit; with a key,
exit 0 passes and any other exit fails with the script output (exit 2 under a
present key fails as 'nothing was checked'). paid-test-durations.json carries
a 90 s packing estimate. Registration (E2E_TOUCHFILES, E2E_TIERS periodic,
E2E_KINDS rule) is the integrator's.
* A1: docsync parent points children at a saved interface file
The /ship docsync fixture saved its observation interface only in the
parent prompt and told the parent to copy it into every child prompt,
about 30-40 s of parent generation per session (lane S, 37198445662).
docsSessionOptions now writes it to <home>/fixture-interface.md (0600) and
the parent tells each child to Read that file first. Fault-actor prompts,
which prepare already writes to a file, are unchanged. Fixture-only.
* A3: a JUnit case's recorded wall is capped by its shard's wall
junitCensus summed a case's JUnit test times as duration_ms; for
plan-mode-no-op's concurrent PTY tests that is 346 s inside a 176 s shard
(the "432-613 s" history). The case wall headroom shows is now
min(sum, shard elapsed), a true upper bound. Session headroom already
used the ledger's per-session clocks.
* A3: refresh paid-test durations from census 37198445662
Recorded 2026-09-29 estimates under-packed gate slice 11 (17 files
estimated 1078 s ran 1353 s; plan-review-report 76 s -> 198 s,
plan-ceo-plan-mode 37 s -> 112 s, safety-codex-consult 83 s -> 150 s).
Refreshed both tiers with --report --write-durations from the latest
census's slice walls. Old plan re-costed with observed walls: worst slice
~677 s (slice 11); refreshed plan: every slice estimated <= 539 s.
* C2: Browser Quick gets a feasible budget; QA loop names its directory and stop path
Judge rationales on the qa-only panels (2 of the last 3) cited the 30 s
Browser Quick budget: homepage + 5 targets, each a checkpoint write and a
guarded command, left ~5 s per probe. Quick is now 180 s (method text: 3
minutes); the qa-only-no-fix paid check expects the same native deadline.
PROBE_DIR points at its source line, a stopped loop goes to the final
report steps (annotations, materialize, Markdown), and /review and /ship
say that after smoke expiry only plan checks rerun in revalidation.
* C2: name the flows judges found implicit in review resolvers
Structured outside review: MISSING COVERAGE asks no fix question and is
never reported clean (was "preserve the existing user decision flow").
/review's HIGH-impact plan gate: spawned or non-interactive runs report
REQUIREMENTS MISSING and continue, writing no TODOs. Value cards: the byte
clamp applies to card lines; JSON records you write keep full values.
* C1: a free test catches a removed workflow step, which the judges missed
C1 controls showed the qa workflow judge passing /qa without Phase 10 and
the review judge passing /review without Step 3. The new test pins every
step/phase heading of qa, qa-only, review, ship, plan-ceo-review,
plan-eng-review and setup-deploy (derived from the templates' step
headings) and names any that goes missing or out of order; new step
headings must be pinned. The judge rubric is unchanged (EVAL_POLICY).
* size: fit the wave's wording under ship, review and qa parity caps
Measured after all lane merges: ship -79, review -210, qa -68 bytes over.
Trimmed the added wording first (post-expiry rule, MISSING COVERAGE,
plan-gate default, value-card JSON, stop line) and folded /review's
redundant INFORMATIONAL sentence and findings bullet. ship 268,036 (room
8), review 130,118 (room 1). qa needed 11 more bytes: cap 1.11 -> 1.1102
with the measured 93,305 / 84,049 = 1.11013 and its reason beside it.
* docs: troubleshooting sections for the wave's new messages
Bun floor (setup, auto-update, /gstack-upgrade), /review stale base and
fingerprint temp-dir errors, the design image model override, the
unrecorded Chromium PID, and a contributor section for census report
lines (pass-rates flags, failure causes, headroom, cost unknown, overlay
v4, stale corpora, auq substance). A free test checks every
troubleshooting.md#anchor printed by setup or bin scripts exists.
* TODOS: reliability follow-ups deferrals; close the Bun floor, make-pdf $P and #2709 reap
* 0.4: 'A census went red' guide; docs for causes, session ledger, headroom and new messages
docs/evals/census-red.md walks one red line to a diagnosis: prerequisites, the
report fields, eval:pass-rates --run/--reds/--headroom with expected output,
what unknown/insufficient/unrecorded data means, free replay, and the single
'after a repair' paid run allowed by TESTING_INTERNALS. Linked from
CONTRIBUTING, TESTING_INTERNALS and both census reports.
TESTING_INTERNALS documents the failure_cause glossary (one row per
FAILURE_CAUSES value, diagnostic only under EVAL_POLICY v1), failure_detail,
sessions[], cost_known, the session ledger, the pass-rates views and the 85%
headroom alarm, main-only tracking issues, overlay contract v4, auq-matrix's
3-sample substance panel and the E5/E6 periodic cases. troubleshooting.md
gains #bun-too-old and an anchor per new user-facing message from lanes P, D
and F. README names GSTACK_DESIGN_IMAGE_MODEL. test/census-red-docs.test.ts
pins the glossary to FAILURE_CAUSES, parses every guide command and checks the
links.
* v1.91.20.0: CHANGELOG and version for the reliability follow-ups
* regen: SKILL.md and sections for all hosts, digest, context-budget fixture
bun run gen:skill-docs --host all; goldens and llms.txt re-rendered
unchanged; bun test/helpers/capture-context-budget.ts.
* integrate: register codex-multiblock-live and design-model-smoke (periodic, rule)
* 0.4: census report and eval:pass-rates views link the census-red guide
* test: cookie approval fixture reverses the Bun install-hint pin (E1)
The historical approved cookie-workflow prompt carried BUN_VERSION=1.3.10;
the regenerated install hint now pins 1.4.0, so the fixture's reversal
list gains that edit like the earlier waves' entries.
* test: release floor counts the two new periodic cases (E5, E6)
* fix: /freeze, /guard, /unfreeze and /investigate work on Codex and other env-var hosts
Templates quoted "$HOME/.claude/skills/gstack/...", which the env-var hosts'
rewrites turned into "$HOME/.agents/skills/gstack/..." on Codex (a path a
global install never has; same class on the other hosts), and setup's
runtime roots had no freeze/bin. Quoted runtime paths now use
{{RUNTIME_ROOT}}: $GSTACK_ROOT on env-var hosts (the fence gets the
runtime prelude), the unchanged $HOME path on Claude. _link_runtime_dists
links freeze/bin and the careful/bin helper it sources into every
env-var host's root. Also fixes the same guess in /benchmark-models,
/retro and /diagram. test/env-host-runtime-assets.test.ts fails on the
previous code: no fence guesses a $HOME/<dir>/skills/gstack path, every
$GSTACK_ROOT path a fence uses is in the host's runtime root, and the
installed Codex /freeze and /unfreeze fences run from a fresh shell.
Template-reading tests now read the Claude render or expect the
placeholder (deliberate change).
* CHANGELOG/TODOS: lane W's workflow, cases and guide; the env-var host freeze fix
* E6: a block that reads a SKILL.md is not a missing install
The first live codex-multiblock-live run passed its real check (the /learn
block found the install and printed the seeded learning) but the oracle
flagged a sed of the learn SKILL.md, whose prelude source quotes the
'gstack: no install found (tried $_r)' text. Only an emitted line that
starts with the message and names a real root counts now; free replay
negative added.
* test: qa-only fixture keeps its caller-set 30 s deadline
The qa-only-no-fix fixture tells the model to start the guard with 30 s
(a caller limit), so its deadline assertion's default stays 30 000 ms; the
product's Browser Quick default (180 s) does not apply to it. Reverts the
helper and its test to their base.
* C2: keep PROBE_DIR 'owned' (qa-functional-prompt pins it); qa measured 93,311
* test: paid file count and periodic floor include the two new periodic cases
* test: ship docs freshness pin checks meaning after A1's wording trim
The snapshot still hashes selected release paths (--select narrows them),
generated outputs and docs; the pin now checks that instead of the
pre-trim sentence.
* E3: reap the recorded Chromium only after the daemon has exited
With the PID now recorded (E3), browse stop reaped Chromium while the
daemon was still shutting down; the daemon read that as a crash, exited 1
and left its state file (chromium-profile-isolation's headless stop test
failed 3/3 locally, passes on base). The CLI waits up to 5 s for the daemon
to exit before reaping a survivor.
* regen: qa and qa-only exploratory sections (PROBE_DIR wording)
* B1: batching counter reads a target declared mid-line; replay corpus
GSTA-23's census 37228573062 failed plan-eng-multi-finding-batching with
reviewCount=0 after 975 s although D1-D10 were asked one per finding,
each with its saved decision-ledger record. The report wrote 'Report
destination requested by the user. Review target (fixed): `PLAN.md` ...'
and the counter read target fields only at a line start, so no brief
inherited the plan identity. A target field may now open any sentence of
its line; a mid-sentence mention or another file still gives no identity.
Floor (3), budget and kind unchanged. Corpus: 9 earlier passing censuses,
the red (now credited at D5), and a derived batching refusal; 975 s noted
in the headroom diagnosis.
* B1: shared-libs corpus labels its git path and covers the supported shape
Every census entry was recorded in CI's eval image (git 2.43), where
gstack-safe-git falls back because --no-lazy-fetch is rejected; each entry
now says so (git_path: fallback). Two synthetic supported-path entries
(HEAD and a history citation in the brief, as git >= 2.44 produces) keep
the 37193478719 pass and the 37195203538 refusal, and a test asserts both
shapes are covered and the actor reads no git-path-specific text.
* v1.91.21.0: move off v1.91.20.0 (claimed by #3031)
* test: settle nav-guard commands before asserting; make two new tests Windows-safe
navigation-guard: Bun's expect(promise).rejects slows each Playwright round-trip
to ~1s while it waits (50 page.evaluate: 43ms plain vs 46.6s inside the matcher),
so the click's 5s timeout expired before the guard saw the link-local request
(CI: 'click: Timeout 5000ms exceeded ... waiting for scheduled navigations').
Settle the command first, then assert on the refusal; a source check keeps it so.
env-host-runtime-assets: PROBE_FILES now matches either path separator.
detector-corpus ship-docsync-late-result: JSON-escape the <ROOT> substitution so a
Windows temp path's backslashes do not break JSON.parse.
* fix: CI run/job ids are not phone numbers; context-recovery fixture gets the full runtime bin
pii.phone.e164 redacted the run id in the published eval report's fetch command
(--run 37235771700), breaking the command it prints. Digit-only spans in a run/job
flag, gh run argument, actions/runs/ or /job/ URL segment, or run_id/job_id key are
now exempt; the same digits elsewhere still report.
context-recovery-artifacts: the fixture's ./bin/ lacked gstack-skill-start and
gstack-context-recovery (the preamble's runtime scripts since v1.71), so the agent
spent its 10 turns hunting for them and hit error_max_turns with no final message
(run 37235771700, 11 turns). Link the whole runtime bin; diagnostic rerun passed
in 6 turns.
* test: replay run 37237194905's late-result capture through the docs authority detector
The only failure was call 20's write to a mistyped shard root (3GanyY for 3GanyU),
which the model disclosed; the detector is correct and the A1 post-snapshot
--out under the fixture home stays permitted. Named red recorded in TODOS.
* test: keep docsync-authority in the Windows profile
The replay test's literal helper path tripped the Windows curator's shebang-spawn
pattern, dropping the whole file from the Windows profile (test-free-shards
invariant). The snapshot --out case is already covered by docsync-command-grammar,
so it is removed here, and the Linux-path replay skips on win32.
* fix: gstack-docs-candidate --help works; docs gate red lines name the denying tool failure
PR run 37239016858 ship-docsync-completion: the parent ran
'gstack-docs-candidate --help' (the helper's usage error points at --help, which
failed). That undeclared command made docsToolFailures non-empty, which denied
the atomic-replacement proof of the child's legitimate native Edit, so the red
line blamed the Edit's temp file. A replay of the capture proves the atomic
replace once --help is declared.
- the helper prints its usage for --help/-h and exits 0
- the fixture interface and command grammar admit the helper's bare --help
- the atomic-proof denial names its check and the tool failures behind it
(deny labels renumbered to their lines)
- replay with negative controls (undeclared command, temp left behind, renamed
elsewhere); diagnostic rerun of ship-docsync-completion passed
* test: retro-base-branch fixture uses main and a shallow report path
PR run 37241493377: the agent wrote retro-output.md one directory above the
requested <tmp>/retro-base/retro-output.md (it dropped the retro-base segment),
so the report check found nothing. The fixture also ran plain git init, which
makes master on CI's git while the prompt says the repo is on main; the agent
logged that mismatch as a learning. Init on main and use the temp dir itself as
the repo. Diagnostic rerun passed (18 turns, 203s).
* test: qa-quick sets a caller probe limit and drains past its session budget
C2 raised Browser Quick's native budget to 180 s. qa-quick is the only gate case
on the native budget, and its wall went 194 s (main periodic, pre-C2) -> 254 s and
274 s (this PR's runs) -> 300 s session timeout (run 37242691913): the agent now
probes every navigation target with a checkpoint, then needs ~80 s to report.
Like qa-only-no-fix, the eval now sets a caller probe limit (30 s), scopes the
fixture, and gives bun's outer timeout the session drain margin instead of racing
the 300 s session. The product's 180 s budget and the session budget are unchanged.
Diagnostic rerun passed in 195 s.
* review/ship: use main's post-expiry smoke sentence; v1.91.24.0
GSTA-23's measurement on the review workflow judge: main's 'Post-expiry smoke
rechecks are not-run.' passed 10/10; the C2 wording passed 6/10 and the
'..., even in 4c.' variant failed in PR run 37248650879. qa-probe-gates pins
main's sentence before step 4c.
* test: record the plan-design corpus test in the test-of-test baseline
#3031's ratchet now counts tests that slice a paid test file's source; the B1
plan-design-review-plan-mode replay corpus reads test/skill-e2e-design.test.ts
like its sibling corpora already listed.
* fix: --case no longer deadlocks importing the running CLI
runCaseDiagnosis loaded runPaidShards with a dynamic import of
scripts/test-paid-shards.ts; when that file is the entry it is still in its
top-level await, so the import never resolved and `--case` hung after its
first line (on main since #3031, found by the per-case measurement runs). The
CLI now passes its runner in; library callers keep the lazy import.
* test: name the in-flight file and the native error when bun dies before its summary (#3037)
* Bun 1.4.2 everywhere CI and setup pin the tested version
Bun 1.4.0 on Windows aborts about 3% of free-suite shards with native
bad-handle errors (main too; #3037); the same head on 1.4.2 had none in 180
shard runs. Every current 1.4.0 pin moves together, as bun-version-drift
requires: setup-bun in every workflow (CSO orchestration included), the eval
image (sha256 from bun-v1.4.2's SHASUMS256.txt, re-hashed locally), GitLab,
the Ubicloud free-suite setup, gstack-bun-version.sh's tested version,
engines.bun and @types/bun, the install hint in generated skills, the Dia and
cookie native-qualification pins, and docs and tests that state the current
pin. Recorded 1.4.0 observations, fixtures, CHANGELOG history and the CSO
images' oven/bun:1.3.10 base stay.
* fix: --case runs a single-case file whole
A session option naming the case (testName: 'office-hours-section-loading')
made caseSelection pick test-name mode, whose filter matched no Bun test, so
every trial would run hollow. A file that registers only this case now runs
whole before any name match is tried.
* fix(office-hours): reviewer returns a hash-bound receipt instead of echoing its verdict
The spec reviewer now Writes its verdict once, seals it with
gstack-office-hours-review seal (validates the saved JSON and prints
OFFICE_HOURS_VERDICT round=N sha256=<hash> path=<verdict>), and returns
only that line. check --receipt recomputes the hash and fails closed on a
missing, malformed, stale-round, wrong-path or mismatched receipt. The
saved file stays the sole findings inventory; validators bind the receipt
to the saved bytes and the judge reads those bytes.
* fix(office-hours): only blocking findings send a design back for another review round
Review findings carry severity blocking|minor (verdict schema v2). PASS when
no blocking findings remain; minor findings are recorded in Reviewer
Concerns and the Spec Review table, never a reason for another round.
CONVERGENCE needs a persisting blocking prior. A persisting or unverified
blocking prior cannot be relabeled minor. The 3-round cap is unchanged.
* fix(office-hours): rounds 2 and 3 are delta re-reviews of the captured design diff
prepare saves each reviewed design as round-N.design.md and gives later
reviewers the exact line diff since the previous round. A new later-round
blocking finding must cite (changed_text) an excerpt of a changed line;
seal, check and the validators verify it against the snapshots and fail
closed when a citation or snapshot is missing. Other new observations are
minor. Severity, anti-downgrade and CONVERGENCE rules are unchanged.
* test(office-hours): preservation judge accepts COMPLETED with recorded minor findings
* fix(office-hours): parent fixes only blocking findings; callers may set --max-rounds
Between rounds the parent edits for blocking findings only; minor findings
stay recorded. gstack-office-hours-review takes --max-rounds 1|2|3 (default
3) on every command; reaching it stops at MAX_ITERATIONS. The marathon
fixture sets 2 rounds so round 1 (full) and round 2 (delta) run live.
* docs(changelog): office-hours review loop changes in v1.91.28.0
* fix(cso): helper JSON keeps run URLs only in the validated workflow slot
The shared redactor now treats GitHub Actions run ids as CI metadata
(
|