* fix(preamble): completeness means complete coverage with minimal code (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96)
Every tier 2+ SKILL.md inlined the same ~23 KB preamble. It now renders once
per host into sections/preamble.md beside each tier 2+ SKILL.md; the SKILL.md
keeps a pointer that asks for the Read only when the file's id is not already
in context. Only sections byte-identical to the shared render move, so every
skill keeps exactly its pre-hoist paragraphs (verified across all 41 skills).
Parity caps for ten skills raised to their measured unions (owner-approved,
Garry 2026-10-25: "do it"); 63 size pins lowered and 26 deleted.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(paid-select): a generated sections/preamble.md takes its skill template's identity in the PR planner (GSTA-96)
screen-summary failed on #3434 with 'PR profile requires full validation' for nine
skills whose only paid coverage is periodic: their new sections/preamble.md had no
dependency identity, while the SKILL.md beside it inherits its template's.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(section-manifest): the shared sections/preamble.md renders from the hoist resolver, not a section template (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (CHANGELOG says 3 characters shorter; model-overlays guards the coverage half)
The completeness section shrank by 3 characters (5 bytes), matching the 89 pins lowered by 3. The default-copy test pinned only the minimal-code half; an expectMentions check now fails if the full-coverage or never-excuses-a-gap clause is dropped.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (model-overlays binds smaller diff to equal coverage)
The default-copy check now also fails if 'on equal coverage' is dropped from the smaller-diff rule (which would tell models to prefer the smaller diff unconditionally) or if the no-impossible-state-checks clause is removed.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG lists the model-overlays coverage checks
The [Unreleased] Tests bullet now says the default-copy test checks both halves of the rule (full coverage of the requirement; smaller diff only at equal coverage; no impossible-state checks; never excuses a gap), matching 88e3cc0 and 44eacaf.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: plan-ceo-review and ETHOS say completeness means coverage, not more code
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (CEO bullet bounds code by accepted scope; tests bind each completeness rule)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: cover the shared-preamble hoist (ship Step 7)
Adds test/preamble-hoist.test.ts (tier 1 unchanged; tier 2+ SKILL.md plus
sections/preamble.md reproduces the pre-hoist preamble; pointer position and id)
and two gen-skill-docs-checks cases (one shared preamble per host, beside every
pointer and named by its id; preamble artifact kind).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (ship Step 9.4)
- setup: follow a symlinked sections/ dir in the carved-pointer status check
- touchfiles: select preamble-hoist.ts alongside every preamble.ts entry
- section-manifest: exempt sections/preamble.md only for skills whose SKILL.md
carries the shared-preamble pointer
- skill-size-budget: growth ceiling measures SKILL.md plus its shared preamble
- host-conformance: tolerate a missing sections/ dir, as setup does
- skill-validation: read bin/gstack-skill-start directly
- skill-fixture: error messages and docblocks name the actual boundary
(harness-version non-behavioral note updated)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: describe the size-budget growth check's startup measure (ship Step 9.4, pass 2)
The growth ceiling now measures SKILL.md plus the shared preamble, the same
measure as the shrink floor; the docblock said SKILL.md only.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG says simplification.md quotes the old rule and CLAUDE.md restates the new one
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG lists the hoist tests and the growth-ceiling measure (ship Step 9.4)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: cover the symlinked sections/ status check and the ETHOS house-rule quote (ship Step 7)
host-conformance: --status still finds a broken bare sections/ pointer when a
carved Claude skill's installed sections/ is a directory symlink (fails at the
pre-repair 0e5d11fd9). gen-skill-docs: the house rule review/specialists/
simplification.md quotes from ETHOS.md still appears in ETHOS.md.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: describe the shared preamble file (ship Step 14.5 docs audit)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: the shared-preamble skip needs the skill's own Read; digest and first-run intro say complete coverage, minimal code (GSTA-96)
The pointer skipped the shared file when any text carrying its id was in context, so a
page or file with that heading could stand in for the anti-spoofing rules (security,
red team and adversarial review, ship run 2). It now requires the skill's own earlier
Read. The digest's Boil the Ocean bullet and the first-run intro still said 'AI makes
completeness cheap, so do the complete thing' (docs audit blocker); both now carry
Garry's 'complete coverage, minimal code' (2026-10-25: '1/ yes fix this').
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: pin the shared-preamble provenance skip and the new Boil the Ocean wording (ship Step 7)
preamble-hoist: on every host, tier and render option the pointer allows the
skip only when the skill's own Read is in context. agents-digest and
gstack-skill-start: the digest bullet and the lake intro say complete
coverage, minimal code, never the retired phrasing. Each fails at 9af36d010.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: describe the provenance skip where the docs still described the id-only one (ship Step 9.4)
The preamble-hoist.ts docblock and ARCHITECTURE.md still said the shared
preamble is re-read only when its id is absent; since 2acf1a44a the pointer
requires the skill's own earlier Read of the file.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG lists the provenance-pointer and Boil the Ocean wording tests (ship Step 13)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* revert(digest): keep the agents digest at main's bytes; an unstamped head cannot change a release output (GSTA-96)
CI 'Check VERSION is not stale vs queue' classified #3434 as stamped because it touched
agents-digest/gstack-AGENTS.md (a release_outputs path), while regenerating only the
generator fails the digest freshness test. The first-run intro rewording stays.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: voice judge reads the hoisted preamble; register ETHOS.md on its reader cases
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: refresh the claude ship golden the main merge took from main (ship Step 5 preflight)
The 1a4dcaf07 merge resolved test/fixtures/golden/claude-ship-SKILL.md to
main's pre-hoist bytes. The golden is a copy of ship/SKILL.md; regenerated
with bun scripts/gen-ship-goldens.ts (pregate regen: REGEN_STALE).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: pr-dependencies' unplaceable-file example uses SECURITY.md now that ETHOS.md is mapped
6183ca8ae registered ETHOS.md on its reader cases in touchfiles-data.ts, so a
PR touching only ETHOS.md plans in pr mode and no longer restores the full gate.
The fail-closed test and the real-unknown label check now use SECURITY.md, which
is tracked and unmapped; the assertions are unchanged. CHANGELOG names the
third test file. (CI free shard 7 at 7c21720ac; remote pregate shard 6.)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: host path-leak checks read the moved shared preamble too; name SHARED_PREAMBLE_FILE (ship review pass 2)
The external-host path-leak assertions in gen-skill-docs.test.ts (Codex,
Factory) and host-config.test.ts (Copilot, Antigravity) read SKILL.md
alone, so a Claude path that moved into sections/preamble.md with the
hoist went unchecked. They now read the skill's startup text through
readSkillStartup. workflow-judge-input and host-conformance use the
SHARED_PREAMBLE_FILE constant instead of a bare 'preamble.md' literal,
and preamble.ts's header describes the hoisted composition.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG token savings name the per-skill skip and the autoplan follow-up (ship review pass 2)
The pointer's skip is bound to the skill's own copy of sections/preamble.md,
so "every later one saves about 5,800" holds per skill, not per session, and
/autoplan's skip list and the inline /office-hours loader do not yet skip the
pointer section. The entry now says so instead of claiming the full /autoplan
saving. Adding the skip entry grows size-pinned skills, so it is a follow-up.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: corpus budget measures startup bytes; carve-safety counts shared preamble as uncarved (ship review pass 2)
skill-size-budget's growth ceiling and shrink floor already measured
SKILL.md plus sections/preamble.md, but the total-corpus check still summed
hoisted SKILL.md bytes against the pre-hoist baseline, hiding about 0.9 MB
of headroom. It now sums the same startup bytes (3,114,885 -> 2,590,484,
x0.832); the unreachable SKILL.md-missing fallback is gone.
auq-format-always-loaded's carve-safety guard treated any sections/ dir as
carved, so every skill with only the shared preamble ran it and its sanity
check passed on preamble.md. It now uses setup --status's rule: a section
other than the shared preamble. Those skills keep the per-skill checks.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: remaining SKILL.md-only negatives read the shared preamble too (ship review pass 3)
The parameterized external-host path-leak smoke test, the two Codex
.claude path checks and both vestigial-handshake negatives read SKILL.md
alone, so text that moved into sections/preamble.md went unchecked. They
now read readSkillStartup. preamble.ts's header no longer says tier 1
renders through generatePreamble().
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: ratchet skeleton caps and eager context ceilings down after the hoist (ship review pass 3)
The hoist moved about 22 KB out of every tier 2+ SKILL.md, which left
each hoisted maxSkeletonBytes cap and each eagerPerInvocation ceiling
roughly 22 KB / 5-6K tokens slack. The 20 hoisted skeleton caps now sit at
the post-hoist skeleton plus their pre-hoist headroom, and 42 context-budget
ceilings take the recaptured (lower) values. Nothing was raised: the four
ceilings the recapture would have raised keep their old values.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: preamble-hoist's section splitter closes a fence only on a bare delimiter (ship Step 11)
Inside an open fence, a line such as "```bash" is content in CommonMark,
but splitSections treated it as the closing fence, so a later "## " line in
the same block could split a section mid-code-block and hoist half of it.
A closing delimiter now needs nothing but whitespace after it. Every host's
render is unchanged (gen-skill-docs --dry-run FRESH on all twelve hosts).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: skill-startup.ts is a global, pinned harness file like skill-fixture.ts (ship review pass 3)
skill-fixture.ts is a global touchfile pinned in scripts/harness-version.json
because it reshapes the skill content most E2E suites read, and it now
builds that content through test/helpers/skill-startup.ts. That helper was
in neither list, so a later edit to it would change fixture inputs without
the harness-version guard and select only 27 keys. It is now global and
pinned, recorded non-behavioral (its fixtures are byte-identical to the
pre-hoist output). ARCHITECTURE.md and the CHANGELOG stop calling the
pointer id a content id: it hashes the shared text before host rewrites.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG matches the merged skip lists and the baseline diff (ship review, run 4)
The headline still called the autoplan and inline /office-hours skip
entries a follow-up, but the main merge added them; it now says the loaded
skills skip their shared Read. The #3451 sentence is dropped, because that
fix shipped in v1.91.237.0 and is recorded there. The typecheck baseline
line says the TS2769 entry was re-keyed for the 'preamble' artifact kind
with its count unchanged, not fixed and lowered.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: pin the pointer entry in the loader skip lists; drop a carve-safety tautology (ship review, run 4)
A new INVOKE_SKILL test checks that plan-ceo-review's inline /office-hours
skip list and autoplan's section skip list both name the shared-preamble
pointer heading, and that office-hours and the four plan reviews carry it.
The carve-safety "sanity" assertion repeated the predicate discoverSkills()
now uses to set sectionsDir, so it could never fail; it is removed.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: gstack-doctor finds the Codex model patch in the hoisted shared preamble (ship Step 11, run 4)
The doctor's patch row grepped only the Codex review SKILL.md for the
"Model-Specific Behavioral Patch (" heading. The hoist moves that section
into sections/preamble.md, so the required row (for ship, review, the plan
reviews, office-hours, investigate and more) would fail on every correct
post-hoist Codex install and block install.sh's "gstack: ok". It now checks
the SKILL.md and then its shared preamble and names the file it found. A
new doctor test covers a hoisted render.
preamble-hoist's variantSubsections also returns null when no subsection
differs, instead of emitting a replacing heading with no subsections.
Every host's render is unchanged.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(docsync): fixtureDocs installs the generated sections/preamble.md (hunk taken from #3472)
A generated skill that loads the shared preamble names sections/preamble.md
as a required asset before skill start, and a spawned document-release child
blocks on its absence, so docsync-spawned stayed red on every #3434 screen.
fixtureDocs now copies that file when the generated skill has it.
This single hunk is taken unchanged from gstack#3472 (head 2e3f7ba1,
GSTA-107), which trains ahead of #3434, so the train merge sees identical
lines. Nothing else from #3472 is included.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG notes the docsync fixture hunk taken from #3472
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CHANGELOG names the post-merge context-budget ratchet (captain hoisted)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(auq): planted skill fixtures resolve the shared preamble like an install (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(plan-format): mode menu delivers its question without output-harvesting wording (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): record the v1.91.270.0 merge values (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(auq): parallel-capture contract expects the planted skill with its sections path mapped (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): record the v1.91.273.0 merge re-measurements (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): restore the released entries the previous commit truncated (GSTA-96)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): end two sentences the prose gate flags (GSTA-96)
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>
* security: isolate every gstack Bun entry point from the audited checkout's .env and bunfig.toml
Bun auto-loads .env, .env.local and .env.<NODE_ENV> from its cwd and runs a
cwd bunfig.toml preload before the program starts. gstack runs inside the repo
it audits, so a committed .env could steer state roots, the claude binary or
spend caps, and a bunfig preload ran arbitrary code in every bin and hook.
Every bun shebang, shell and skill caller, TypeScript spawn and compiled build
now disables both (--no-env-file --config=/dev/null, bunIsolationArgs(),
--no-compile-autoload-dotenv/bunfig), with a ratchet and hostile-fixture
regressions.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: name the directly executed scripts in the isolation ratchet
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: follow the isolation flags in touchfiles, copy lists, recipe assertions and the harness pin
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: keep browse/src/bun-child-config.ts unchanged so the native cookie qualification still binds
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(windows): the empty bunfig outlives its process so the timeline hook's detached repair child can read it
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.159.0 security: gstack's Bun entry points ignore the audited repo's .env and bunfig.toml (S1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: plan-mode render pattern accepts the isolation flags
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(autoplan): eng review always runs last — the gate reviews the final amended plan
Reorder the pipeline to CEO -> Design (if UI scope) -> DX (if developer-facing
scope) -> Eng. The old order (CEO -> Design -> Eng -> DX) let DX findings land
AFTER the required gate signed off, so eng validated a stale plan.
Accept-all semantics made explicit: every AskUserQuestion resolves to the
recommended option; premises no longer pause the pipeline mid-run (clearly-wrong
ones queue as User-Challenge items at the single Final Approval Gate). Eng's
Codex voice now sees the DX consensus summary. New free static test pins the
order; the chain E2E gains DX-between and Eng-terminal assertions.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(review): simplification specialist — advisory over-engineering lens with ponytail's tag vocabulary
New 8th Review Army specialist (DIFF_LINES > 100, --simplification force flag)
hunting unrequested STRUCTURE only: delete/stdlib/native/speculative/shrink
closed tags, one-line findings, lines_removable field. speculative: replaces
ponytail's yagni: tag — we import the lens, not the posture; coverage stays
sacred (Completeness Gaps owns it, suppressions inlined, shrink needs >=5 lines).
Advisory carve-out in the merge step: advisory findings are excluded from
quality_score and the findings-count header, render with an [ADVISORY] label,
and are ASK-only in Fix-First. Zero-findings case prints the lens-scoped
'Simplification: lean already — nothing to cut.' from the PARENT (the
specialist keeps the exact NO FINDINGS contract); with findings, the parent
prints 'net: -N lines possible' summed from lines_removable.
Tests: static pins for the carve-out + early-out contract (gen-skill-docs),
two periodic e2e cases with planted fixtures — activation (over-build traps:
hand-rolled Intl, one-impl abstract, dead config) and false-flag precision
(a lean ETHOS 'choose A' diff must yield NO FINDINGS).
Inspired by dietrichgebert/ponytail's /ponytail-review.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(preamble): reuse ladder in Search Before Building — rungs 2-5 of ponytail's ladder, completeness kept
Tier-3+ skills gain a per-edit reflex the section only stated as research
discipline: before writing new code, stop at the first rung that holds —
repo helper, stdlib, native platform feature, installed dependency — then
build the COMPLETE version of what remains. The closing clause is the
explicit reconciliation with Boil the Ocean: the ladder governs structure,
never coverage. Rungs 1/6/7 (YAGNI / one line / minimum that works) are
deliberately NOT imported.
Also ports ponytail's root-cause rule: one guard in the shared function
beats a guard in every caller.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(preamble): bounded-closer output rule for tier-2+ skills
After completing work, skills report in a few short lines — what changed,
what was skipped, what to watch — and cut any explanation that outgrows the
change. Explicit exemptions protect every mandated output: decision briefs,
completion-status blocks, user-requested explanations, and report-shaped
skills' report formats (the report IS the work in /qa-only, /plan-*-review,
/retro, /document-generate).
Rationale is signal-to-noise, not tokens: ponytail's own benchmark shows
terse prose alone doesn't cut cost (caveman arm: -20% LOC, +7% tokens), and
independent replications found its 'skipped on purpose' essays ate the code
savings. Includes a good/bad closer example pair per the model-overlay
guidance that a positive example beats a 'don't be verbose' instruction.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(resolvers): terse-mode savings claim matches measurement — 2.6KB, not 3-5KB
Measured on the v1.71 render: --explain-level=terse saves exactly 2,611 bytes
per tier-2+ skill. The old ~3-5KB claim predated the preamble restructuring.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(retro,preamble): gstack-shortcut debt ledger — accepted shortcuts leave a joined trail
When the user accepts an option that is BOTH Completeness <= 7 AND a
durable-scope call, the decision ledger entry (gstack-decision-log, ceiling +
upgrade trigger in the rationale) is the source of truth, and the agent marks
each cut corner in code with gstack-shortcut(dec-<id>): <ceiling>, upgrade
when <trigger> — same edit, no follow-up question, never agent-initiated.
/retro Step 11.5 harvests markers into a debt ledger (grep || true — zero
matches is the healthy case; skill installs and docs excluded), joins on the
decision id so nothing double-counts, tags unlinked and no-trigger rot risks,
and closes with 'N markers, M with no trigger.'
/review suppressions: a marker with ceiling+trigger downgrades a would-be
Completeness Gaps finding to acknowledged debt. Redaction test pins that the
marker ships untouched (the ledger is the point) — it does not match the
TODO(owner) hygiene shape.
Format from dietrichgebert/ponytail's ponytail-debt; store inverted to gstack's
existing decision ledger.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: refresh golden ship baselines after preamble additions (reuse ladder + bounded closer)
The golden-file regression test pins the rendered ship skill byte-for-byte;
the WS3/WS7 preamble sections are deliberate changes, so the baselines
re-capture per the goldens' own update protocol.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(hosts): instruction-only tier — a 2KB committed rules digest any agent host can read
New agents-digest/gstack-AGENTS.md (1,765 bytes, hard 2,048-byte budget):
gstack's ethos one-liners, the reuse ladder, and voice rules for hosts with
no install arm — Zed, Amp, Jules, or any AGENTS.md-reading agent. Generated
by scripts/gen-agents-digest.ts, auto-refreshed by gen:skill-docs, committed
like llms.txt so setup's explainer arms can point at it before any toolchain
exists. First line carries the gstack version as its own staleness nudge.
Delivery is print-path + user-performed copy ONLY: setup never writes or
overwrites a user's AGENTS.md (a test pins this — no cp/ln/mv/redirect into
AGENTS.md anywhere in setup). openclaw and hermes explainer arms print the
path; slate keeps routing to the full Claude install and gbrain ships from
its own repo. HostConfig gains the optional install.instructionTier slot,
declared by both instruction-tier hosts. README host table now matches what
setup actually does.
Inspired by dietrichgebert/ponytail's instruction-tier AGENTS.md fallback —
one generated source, never per-host hand copies.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(preamble): AskUserQuestion repetition cut — gated, passed NOT-WORSE A/B
Removes the duplicate statements v1.71's compaction left in the
AskUserQuestion Format section: the completeness rule restated in the prose
triad, the auto-decide marker syntax stated twice, the Conductor-flakiness
explanation stated twice, and the self-check's full triad restatement. Every
verbosity floor and all 14 format pins stay (Layer 0 green).
The gate this decision rested on ran before landing (new periodic
skill-e2e-auq-repetition-cut-ab.test.ts, pre-cut ref 3263fffe vs this
render, same harness as auq-verbose-vs-carved-ab): POST 7/7 format elements,
substance 5 — identical to PRE. No degradation; the load-bearing-repetition
hypothesis did not hold for these duplicates.
Net: -236 bytes per tier-2+ skill (~9.7KB corpus). Golden ship baselines
re-captured for the deliberate change.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(evals): with-skill vs without-skill arm benchmark — measures whether gstack's behavioral layer earns its tokens
Ponytail's honest-benchmark method pointed at gstack itself: 3 build-shaped
tasks (native-platform over-build trap, CRUD endpoint, bug fix with planted
decoys) x 2 arms, real claude -p sessions, scored on the git diff left
behind. A research instrument, not a release gate — no assertion compares
arm scores.
Arms use the PROVEN project-scope pattern: the with-arm installs a
build-discipline skill (extracted reuse-ladder + bounded-closer content, not
whole-file copies) into the fixture's .claude/skills/ with a CLAUDE.md
routing line and an explicit invocation; a live spike confirmed claude -p
discovers and invokes project-scope skills via the Skill tool (3 turns,
exact-output probe). Fixtures are git init + local bare origin; diff capture
is three lines of git, no worktree machinery.
Failure taxonomy: zero-diff arms are VALID scored cells (deterministic
0/none, no API call), harvest failures record harvest:null, judge_error
cells are excluded from aggregates but named in the report — nothing drops
silently. armJudge: fixed sonnet judge, 0-3 unrequested-structure rubric,
must name the construct or say none, bounded retry-on-malformed; callJudge
gains optional temperature/max_tokens (defaults unchanged). recordE2E now
populates tokens_used for every E2E. Eval schema v2: harvest gains
{insertions, deletions, net}, tolerant reads keep v1 runs comparable.
Registered periodic in E2E_TIERS + touchfiles (with the auq-repetition-cut
A/B); periodic detach timeout raised to the new shard-census floor. Free
selftest (8 tests, zero API) pins fixtures, extraction, arm asymmetry, diff
capture, judge plumbing, and the retry bound.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: absorb the ponytail-import wave into the guard fixtures — ceilings, schema pin, triad phrasing
Skeleton ceilings re-captured for the 17 carved skills the wave deliberately
grew (reuse ladder + bounded closer + shortcut trail, net of the gated -236B
AUQ cut), each with its measured size in the comment per the carve-guards
protocol. eval-store schema pin updated to v2 (harvest gains
insertions/deletions/net). The AUQ prose-triad keeps its pinned per-choice
phrasing ('explicit on EACH choice') while still deferring the score scale to
the canonical Format rule — the shipped cut is strictly closer to the pre-cut
text than the render that already passed the NOT-WORSE gate. Autoplan carve
anchors follow the Phase 2.5 renumbering. Golden ship baselines re-captured.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: observability partial-file pin follows eval-store schema v2
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(test-runner): GSTACK_FREE_JOBS + opt-in flaky-retry pass for syscall-supervised sandboxes
GSTACK_FREE_JOBS overrides the computed shard count (the free runner's
analogue of the paid runner's EVALS_JOBS). On Vercel sandboxes, PID 1
installs a seccomp filter whose supervisor spuriously fails access(2) for
busy processes — measured: 200/200 git-init probes fail 'Cannot access work
tree: Permission denied' while the suite runs at 6 shards, 0/200 idle;
statx succeeds while access fails on the same path in the same process.
One serial mega-shard maximizes per-process pressure and fails too; 2
shards is the measured sweet spot.
GSTACK_FREE_RETRY_FLAKY=1 (default OFF — dev boxes should see flakes)
re-runs attributed failures once, serially, capped at 5 files; a clean
retry downgrades to a loud FLAKY-PASS naming the offenders, a repeat
failure stays red, timeouts and unattributed failures never retry.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(browse): portable temp paths — TEMP_DIRS allowlist, tmpdir()-based test files
Local path validation now accepts os.tmpdir() alongside the classic /tmp
(new TEMP_DIRS in platform.ts): on macOS os.tmpdir() is /var/folders/...,
and TMPDIR-honoring CI/sandbox environments point it elsewhere entirely —
both are legitimate scratch space. Remote file serving (TEMP_ONLY) stays
pinned to TEMP_DIR alone; no change to the exfil boundary.
commands.test.ts drops 41 hardcoded /tmp literals for a tmpp() helper on
os.tmpdir() (two message assertions now reference the same variable), and
path-validation's symlink-escape test targets /etc/hosts instead of
/etc/crontab — the target must EXIST for realpath to resolve the link (a
dangling target falls back to the link's own path and passes vacuously),
and /etc/crontab is absent on Amazon Linux.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(config): portable sha256 — Linux ships sha256sum, not shasum
resolve-user-slug and endpoint hashing exited 127 on Amazon Linux (shasum
is a macOS/perl tool). New _sha256_hex helper prefers sha256sum and falls
back to shasum, matching gstack-verify-gate's existing pattern; both call
sites converted.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(next-version): only trust ls-remote when origin is actually configured
Without the guard, git DWIMs the literal 'origin' as an ssh host/path; on
hosts whose transport launders exit codes the probe 'succeeds' with zero
branches and the allocator silently sees an empty queue — the exact
duplicate-allocation failure (#2545) fetchGitClaimed exists to prevent.
git remote get-url origin gates the probe; absence falls through to the
existing local-refs path with its staleness warning.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(testing): sandbox-doctor — one command makes a cloud sandbox run the suite green
Measured failure taxonomy for Vercel/Conductor sandboxes (missing /dev/fd,
64M /dev/shm, seccomp-supervisor access(2) EACCES under load, uid-1000
processes with FULL capabilities defeating chmod-denial tests, no X server,
no git identity, Conductor git-shim exit-code laundering) plus the
idempotent script that treats all of it and seeds the run recipe.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(config): converge on main's self-contained sha8_of — its tests extract the function standalone
The merge kept a branch-local _sha256_hex helper; main's v1.72 landed the
same portability fix inline WITH tests that extract sha8_of()'s text and run
it under a shim-only PATH — a helper call can't satisfy that shape. Adopt
the landed implementation at both hash sites.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: coverage for GSTACK_FREE_JOBS override and failingFiles attribution
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: coverage for TEMP_DIRS widening and remote-serving TEMP_ONLY asymmetry
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: coverage for gstack-shortcut marker grammar and retro harvest joint
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: coverage for sandbox-doctor shell syntax and idempotency guards
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test-runner): empty-shard outcome carries failingFiles; harden flaky-retry list
The empty-shard early return omitted the (required) failingFiles field —
tsc TS2741 — feeding undefined into the flaky-retry flatMap. Also drop the
dead 'else if (worst !== 0)' guard (the enclosing if already pins it).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(release): version-bump write regenerates the version-stamped agents digest
agents-digest/gstack-AGENTS.md embeds VERSION in its first line and is
byte-freshness-gated (test/agents-digest.test.ts + Skill Docs Freshness CI),
but nothing in the release path regenerated it — every version-bumping ship
of this repo would land red. write now spawns the repo's own generator when
present (agentsDigest true/false/null in the output JSON), and ship's
evidence gate allow-lists the digest alongside VERSION/package.json.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(setup): instruction-tier explainer prints the script-anchored digest path
$(pwd) printed a nonexistent path when setup ran from any other directory;
both arms now share one print_instruction_tier() using SOURCE_GSTACK_DIR.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(digest): broaden AGENTS.md writer tripwire; pin digest-resolver ladder lockstep
The print-path-only guard now catches tee/install/rsync/dd/truncate, >>
appends, and laundered variable-destination writes. New test ties the
digest's hand-rendered reuse-ladder text to the preamble resolver so an
edit to either fails CI instead of shipping drift.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(retro): shortcut harvest drops placeholder markers and convention docs
The Step 11.5 grep matched documentation mentions (dec-<id>, dec-*) in
checklists, resolver sources, and convention tests, reporting phantom debt
rows on gstack itself. A trailing filter kills placeholder forms; prose
tells the agent to discard convention-quoting hits.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(review): advisory findings count in per-specialist stats
Without this, simplification (all-advisory by construction) would log
findings:0 every run and auto-gate itself into permanent silence after 10
dispatches. The advisory carve-out governs score and header only.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(evals): arm-benchmark harvest and judge hardening
- Harvest diffs against the recorded seed SHA (origin/main is movable by an
agent that commits AND pushes; a recorded SHA is not).
- Fixtures get a node_modules .gitignore and the git wrapper a 64MB
maxBuffer, so a vendored-dependency arm is scored instead of killing the
cell.
- The judge diff cap is a named constant with loud truncation (log +
judge_reasoning suffix).
- Judge prompt block markers carry a per-call random sentinel, so a diff
containing a faked closing marker cannot escape the data block.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(evals): AUQ A/B vendored pre-cut arm + judge-error inconclusive taxonomy
- The PRE arm read a branch-local SHA (3263fffe) that becomes unreachable on
fresh clones after the squash-merge; the pre-cut render is now a vendored
fixture.
- A judge failure on one side no longer coerces substance to 0 (which
fabricated DEGRADATION on POST-side failures and masked regressions on
PRE-side failures): null substance = inconclusive, format still gates.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: regression pin for the originConfigured guard vs laundering git shims
On healthy hosts the guarded and unguarded paths behave identically, so a
revert passes the suite; only a shim that makes 'git ls-remote' exit 0 with
empty output (the Conductor wrapper's observed behavior) exposes it. Pins
that the empty 'successful' probe is never trusted as an empty queue.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sandbox-doctor): missing /dev/shm no longer aborts the doctor under set -eu
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(touchfiles): close dep-list gaps for the new evals
- arm-benchmark entries gain ship/SKILL.md (buildBehavioralSkill extracts
sections from the rendered ship skill)
- review-army-simplification entries gain their planted fixtures + test file
- auq-repetition-cut-ab gains llm-judge.ts and the vendored PRE fixture
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: re-capture context-budget fixture — lock the WS6-3 reduction and Step 9 deltas
Per the ratchet protocol: the AUQ repetition cut shrank per-skill eager
tokens but the fixture was never re-captured, leaving the win unlocked.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(release): digest regen is an explicit --regen-digest opt-in, not presence-sniffed code exec
Review (security) caught the cycle-1 fix executing any repo's
scripts/gen-agents-digest.ts on plain 'write' — arbitrary code exec from a
hostile clone on a routine bump, contradicting the binary's own containment
posture. The regen still runs the TARGET repo's generator (a 'trusted' copy
beside the binary would false-red the freshness gate on version drift), but
only under the flag: /ship passes it deliberately, in a repo whose code the
operator already executes (its test suite). Plain write is side-effect-free
again. Also: uniform output shape (agentsDigest: null on the JSON-manifest
branch), a REAL generator round-trip test replacing the misnamed lockstep
check, and land-and-deploy's evidence gate gets the same digest allow-path
as ship so the two grading surfaces agree.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test-runner): flaky-retry vetoes on ANY unattributable failure evidence
The gate equated 'some failure attributed' with 'all failures attributed': a
shard with one attributed failure plus a headerless failure, an unhandled
error between tests, or a truncated run (no terminal summary) qualified for
retry — re-running only failingFiles and masking the rest as FLAKY-PASS,
re-opening the silent-truncation hole the strict classifier closes.
FreeShardOutcome now carries unattributedFailures; nonzero vetoes the retry.
Pins: mixed shard, truncated-with-attributed shard, empty-shard field values.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(next-version): a configured origin advertising zero heads is never trusted
The originConfigured guard covered only the no-origin laundering case. With
origin configured (the normal Conductor worktree state), the laundering shim
makes a failed ls-remote exit 0 with empty stdout — read as 'the queue is
empty', the exact duplicate-allocation bug (#2545) one layer up. A reachable
remote always advertises at least its default branch, so an exit-0 zero-head
probe now falls back to local refs/remotes/origin with a laundering-specific
warning. Regression test shims git for both configurations.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sandbox-doctor): loud on git-shim patch drift; document the retry-contract override
- The /conductor/bin/git patch was a silent no-op if the shim's bytes drift
from the exact pattern — now warns that laundering is NOT fixed.
- The bashrc block documents why GSTACK_FREE_RETRY_FLAKY=1 deliberately
overrides the runner's default-OFF contract on this sandbox, and how to
undo it.
- Test pins the guarded shm form (missing /dev/shm must not abort set -eu).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(digest): pin the script-anchored explainer path; catch declaration-prefixed writers
- Asserts $SOURCE_GSTACK_DIR/agents-digest path and forbids $(pwd)/agents-digest
(the cycle-1 fix was revertible without failing anything).
- The laundered-assignment arm now matches local/export/declare/readonly/typeset
prefixed assignments — the likeliest in-function writer shape in setup.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor(evals): arm-benchmark selftest runs FREE on every PR
The selftest lived inside the paid skill-e2e-* file, so fixture-integrity
and plumbing pins executed weekly at best — a broken fixture would ship past
every gating check and be discovered when the periodic run burned money on a
dead instrument. Harness extracted to test/helpers/arm-benchmark-harness.ts,
selftest to test/arm-benchmark-selftest.test.ts (free suite). Touchfiles:
harness added to the three benchmark dep lists; the auq-repetition-cut-ab
tier comment now states the MANUAL re-run obligation honestly (periodic runs
force EVALS_ALL, so dep lists cannot auto-trigger it).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: re-capture context-budget fixture after cycle-2 template deltas
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sandbox-doctor): keep both heredoc bodies under the 512B pipe-deadlock window
The cycle-2 additions pushed the python-patch and bashrc heredocs into the
512-65536B window test/heredoc-pipe-deadlock.test.ts guards (sh scripts get
no BASH_COMPAT escape hatch). Same content, tighter prose; the drift warning
now reuses the patch pattern variable instead of a second literal.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(review): a gstack-shortcut marker only suppresses findings when its decision id resolves in the ledger
Cross-model catch (Claude adversarial + Codex agreed): any diff author could
fabricate a marker and silence Completeness review of that gap. Reviewers
now resolve the dec-id via gstack-decision-search; an orphan marker is
reported as a forged suppression, not honored as debt.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(autoplan): define the B2 gate path — accepted premise challenges amend the plan and re-run Eng
The final gate offered B2 (respond to User Challenges) but the option
handler table omitted it, leaving accepted challenges with no amendment or
Eng re-review path. B2 now walks challenges one at a time; an accepted one
amends the plan and re-runs Eng (the gate always reviews the final plan),
sharing D's 3-cycle cap.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(evals): arm benchmark runs each fixture's functional oracle — correctness before LOC
The plan's metric order is diff-quality FIRST, but cells never ran the
fixtures' own run-tests.js, so a refusal, a broken implementation, and
working code were indistinguishable in aggregates (Codex adversarial catch).
Tasks with an oracle declare checkCmd; every cell records checks=pass|fail|none
in the report line and eval store. Selftest pins the oracle declarations and
that the planted bug fails its own check pre-fix.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(ship): check the bump's agentsDigest result; state the --regen-digest trust envelope honestly
A failed digest regen warned and moved on — ship now instructs re-running
the generator and staging the digest with the bump (the freshness check
stays red otherwise). The 'no-op everywhere else' phrasing oversold safety:
the step now names what executes and why that is inside the envelope Step 5
already opened (the repo's own test suite).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test-runner): GSTACK_FREE_JOBS accepts digits only — parseInt truncation defeated the loud-failure contract
'2abc' silently became 2 and '3.7' became 3 despite the error text claiming
a positive-integer requirement. Strict /^\d+$/ pre-check; both shapes pinned.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sandbox-doctor): atomic git-shim patch, :99-socket Xvfb check, dnf gate, non-interactive sudo
- The /conductor/bin/git patch writes tmp-then-rename with a .orig backup —
a concurrently spawned git can never exec a truncated shim.
- Xvfb running-check looks for the :99 socket, not any-display pgrep.
- Xvfb install is dnf-gated so non-dnf distros degrade to a warning instead
of aborting the remaining fixes under set -eu.
- The bashrc /dev/fd restore uses sudo -n || true — no password prompt at
every shell start on non-passwordless machines.
- BASH_COMPAT=50 keeps heredoc bodies off the bash pipe window.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(build): a failed agents-digest regen fails gen-skill-docs instead of deferring the red to CI
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(browse): an untrustable TMPDIR (/, $HOME, a cwd ancestor) never widens the local allowlist
TEMP_DIRS honors os.tmpdir() at daemon start; a daemon launched with
TMPDIR=/ would have trusted the whole filesystem for local path validation
for its lifetime. Subprocess pins cover /, $HOME, cwd-ancestor rejection and
that a benign distinct TMPDIR (the sandbox recipe's $HOME/tmp) stays honored.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: zero-heads warning names the benign cause too; digest path declaration made load-bearing; ratchet re-capture
- The ls-remote zero-heads warning no longer accuses an empty remote of
running a laundering shim.
- instructionTier.rulesFile now must equal the generator's DIGEST_RELPATH
(and setup must print it) — the declaration fails with the real path
instead of lying silently.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: file ship-time follow-ups in TODOS
skillify HOME-override gate red (pre-existing, proven on main), the
auq-verbose-vs-carved-ab branch-local ref, eval-store harvest union,
evidence digest allow-path scoping, and the WS6-2 dead-frontmatter live-host
verification deferral.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* v1.73.0.0 chore: version bump + CHANGELOG — ponytail import wave
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: raise ship skeleton parity ceiling — measured 75,592 after the v1.73 release-step prose
The --regen-digest trust-envelope paragraph (Step 12) and the evidence-gate
digest note (Step 16) grew the ship skeleton past the previous 75,420
ceiling. Re-measured per the deliberate-change protocol.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: update project documentation for v1.73.0.0
- README.md, docs/skills.md, AGENTS.md: /autoplan phase order corrected to
CEO → design → DX → eng (eng always last); /review rows note the advisory
simplification lens
- docs/PROJECT_STRUCTURE.md: add agents-digest/, gen-agents-digest.ts,
sandbox-doctor.sh, test-free-shards.ts to the annotated tree
- CONTRIBUTING.md: document GSTACK_FREE_JOBS, GSTACK_FREE_RETRY_FLAKY, and
the sandbox-doctor one-command fixer in the Tier 1 test section
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: apply cross-model doc-review fixes for v1.73.0.0
- README.md: host table gains the OpenClaw explainer arm row (setup has the
arm; the table claimed to match setup)
- docs/skills.md: /review completeness-gaps section documents the
gstack-shortcut(dec-<id>) acknowledged-debt suppression and orphan-marker
flagging; /autoplan deep-dive states the recommended-option default with
the 6 principles as tie-breakers
- CONTRIBUTING.md: host count 8 -> 10 (Hermes, GBrain), supported-hosts list
completed
- docs/TESTING_INTERNALS.md: sandbox recipe says to source ~/.bashrc after
the doctor seeds it; GSTACK_FREE_JOBS wording fixed from "caps" to
"overrides in either direction" (matches the un-clamped runner)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): temp-dirs asymmetry pins are topology-aware; TMPDIR probes are POSIX-only
CI exposed two wrong assumptions in the new temp-dirs tests, neither a
product bug:
- The remote-serving asymmetry test assumed a distinct os.tmpdir() lies
OUTSIDE TEMP_DIR, but the free-shard runner nests each child's TMPDIR
inside /tmp on CI — a file there is under TEMP_DIR, so serving it
remotely is legitimate. The test now pins the actual exfil boundary on
every topology (a cwd project file is locally readable, never remotely
servable) and branches the os.tmpdir() case on nested-vs-outside.
Reproduced locally with TMPDIR=/tmp/nested-tmp before fixing.
- The untrustable-TMPDIR subprocess probes set TMPDIR, which Windows
os.tmpdir() ignores (reads TEMP/TMP) — and on Windows TEMP_DIR is
DEFINED as os.tmpdir(), so the fixed+movable two-dir topology the guard
filters does not exist there. Probes now skip on Windows with that
rationale; the benign-TMPDIR assertion compares realpaths.
Verified under all three POSIX topologies: TMPDIR=$HOME/tmp (outside),
TMPDIR=/tmp/nested-tmp (CI shard shape), TMPDIR unset (identical).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(build): DIGEST_RELPATH is a forward-slash literal on every platform
path.join built it with backslashes on Windows, so the wiring test's
string comparisons against setup and hosts/*.ts (which carry the
forward-slash literal) could never match there — windows-free-tests red.
path.join(root, DIGEST_RELPATH) at the write site normalizes fine.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sandbox-doctor): bashrc block re-heals the /dev/shm remount on sandbox restart
The 4G remount does not survive restarts; a reverted 64M shm made the
multi-tab browse handoff test fail consistently under suite concurrency
(observed live: two consecutive full-run failures, green in isolation,
green again after remounting). Same guarded arithmetic as the doctor body.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): close the cross-shard porcelain race that failed Windows CI
Two-part fix for the gen-skill-docs-out-dir isolation-pin failure:
- cookie-import-browser built its scratch cookie DBs inside the TRACKED
browse/test/fixtures/ dir (created in beforeAll, deleted in afterAll), so
they flash as untracked files mid-run — a concurrent shard's porcelain
snapshot caught the window on Windows. The DBs now live in a per-run
tmpdir; zero source-tree writes.
- gen-skill-docs-out-dir is the free suite's only LIVE porcelain-snapshot
test, so it joins TREE_MUTATING (the serial quiet window): any concurrent
transient tree-write can race it, and its own spawned render rewrites
llms.txt/agents-digest in place (idempotent on a fresh tree).
The race is pre-existing; this branch's +5 test files reshuffled shard
composition and exposed it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* v1.75.0.0 chore: queue-advance rebump — perth-v2 landed v1.74.0.0 on main
The v1.73.0.0 slot this branch claimed was superseded when #2721 merged;
same MINOR level relative to main per the versioning invariant. CHANGELOG
entry renumbered (1.73.0.0 was branch-internal and never landed on main),
digest restamped via --regen-digest.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test-runner): duration-packed walls keep the per-file floor — predictions don't transfer across machines
The committed duration seed is recorded on fast CI; a syscall-supervised
sandbox replays the same files 2-4x slower. Observed post-merge: a 253-file
shard predicted ~242s was wall-killed at its predicted-x3 725s wall while
genuinely progressing (the old count heuristic guaranteed 1265s). Packed
walls may be looser than the count floor, never tighter.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
