* v1.91.79.0 feat(eval-plan): /eval-plan tier 1, lane-check, evidence verify, coordinator contract, owner brief, contributor-PR mode, banned terms (multi-agent wave PR E)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(spec,review): fail closed when the coordinator contract cannot be read; restore the omitted-Army sentence
The spec --execute spawn captures `gstack-autoplan contract` before piping
the archive, so a lane never starts without the contract; the C9 fixture
installs its gstack-like checkout (bin, lib, a contract stub) at every
host's global root. Review Step 5.8 keeps the pinned
'without claiming specialist coverage' wording.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.70.0 feat(unattended): artifact contract, unattended session kind, findings-derived review log, gate list
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.72.0 feat(autoplan): unattended runner next|submit, pluggable outside voice, review checklists, spec-loop cap
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(b-runner): atomic lock creation in spend-ledger, judge bundle skips runner-only sections, fixture env spelling
- lib/spend-ledger.ts: create the lock by linking a complete temp file so a
contender never reads an empty lock and breaks a live owner (CI admitted 20
of a cap of 8 under contention); unreadable locks break only by mtime age.
- test/helpers/workflow-judge-input.ts: exclude manifest runner_only sections
(the B4 checklists) from the judge bundle; the judge rates the interactive
workflow. test/workflow-judge-input.test.ts expects the same set.
- test/helpers/autoplan-run-fixture.ts: spell the runner's session kind
without the literal the free-suite environment scan rejects.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.74.0 feat(review): plan reality rows, sideways review and cso sweep, investigate recipes
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: register the investigate carve case and map Reality rows to real headings in the review checklists
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: pin the corrected Reality rows obligation rows
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(investigate): use allowlisted placeholders in the flake and polluter fences; select the investigate carve case on PTY changes
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.77.0 feat(ship): two-stage gstack-pregate, gstack-regen registry, intent-based issue links (multi-agent wave C-pregate)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(pregate): keep the bin-driving pregate tests off the Windows subset; pin files are free-only for eval selection
The three C-pregate tests that spawn bin/gstack-regen, bin/gstack-pregate,
bin/gstack-issue-links and bin/gstack-ship-receipt do so through
test/helpers/pregate-fixture.ts runBin, so the Windows curation's source
scan of the test file never saw a bin/ spawn and shipped them to
windows-latest, where CreateProcess cannot exec a shebang (14 failures in
windows-free-shard 2 and 5). Each is now a KNOWN_WINDOWS_INCOMPATIBLE entry
with the precise reason. .gstack/generated.json and .gstack/pregate.json
join FREE_ONLY_PR_FILES: no paid case reads gstack's own pin files (the
tools read origin/<base> of the repo they run in, and paid cases run in
fixture repos), so touching them no longer restores every gate case.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(harness-version): record the FREE_ONLY_PR_FILES pin-file entries as non-behavioral
scripts/test-pr-profile.ts is a pinned shared-harness file; the two
.gstack pin-file entries change selection only, never a case verdict.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.70.0 feat(unattended): artifact contract, unattended session kind, findings-derived review log, gate list
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.73.0 feat(ship): repo ship policy, gstack-restamp stamp-at-merge, tree receipt, evidence bundle, ship receipt
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ci): result-codes is selection data, receipt counts come from files, C-stamp tests leave the Windows subset
- scripts/pr-dependencies.ts: lib/result-codes.ts joins SELECTION_DATA_MODULES; its fix: prose names commands a person reruns, not files the module consumes (test/pr-dependencies.test.ts traced review cases through it to bin/gstack-next-version)
- ship/sections/pr-body.md.tmpl: gstack-ship-receipt write reads --gate/--ci from agent-written .gstack/tmp/ship-*.json files and --spend-usd from the allowlisted <spend-usd> placeholder (generated-bash lint: no free text in commands)
- scripts/lib/windows-curation.ts: the five C-stamp test files spawn bin/ shebang scripts through test/helpers/restamp-fixture.ts, which the source scan misses
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ship): the receipt step names where each input comes from
The workflow judge (eval-slices 3, median 3/4) found pr-body's gstack-ship-receipt command demanding a tree receipt, CI counts and a spend figure no earlier step produces, with RECEIPT_INVALID halting publication. The command now takes only Step 16 stage 4's lane counts (file-written JSON); --receipt is added only when Step 16 wrote .gstack/tmp/tree-receipt.json; RECEIPT_INVALID says to fix the named input file and rerun. The unused <spend-usd> allowlist entry is removed.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.70.0 feat(unattended): artifact contract, unattended session kind, findings-derived review log, gate list
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.72.0 feat(autoplan): unattended runner next|submit, pluggable outside voice, review checklists, spec-loop cap
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(b-runner): atomic lock creation in spend-ledger, judge bundle skips runner-only sections, fixture env spelling
- lib/spend-ledger.ts: create the lock by linking a complete temp file so a
contender never reads an empty lock and breaks a live owner (CI admitted 20
of a cap of 8 under contention); unreadable locks break only by mtime age.
- test/helpers/workflow-judge-input.ts: exclude manifest runner_only sections
(the B4 checklists) from the judge bundle; the judge rates the interactive
workflow. test/workflow-judge-input.test.ts expects the same set.
- test/helpers/autoplan-run-fixture.ts: spell the runner's session kind
without the literal the free-suite environment scan rejects.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(spend-ledger): accept Windows' status-only report of the killed child
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
