mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-29 09:20:39 +02:00
* feat(gen): strip gen-time-only frontmatter keys from Claude renders
interactive + benefits-from are read from the .tmpl by buildContext at
generation time; no runtime, host, or test reader consumes them from the
generated SKILL.md (e2e-harness-audit reads .tmpl; benefits-from tests
assert rendered prose). gbrain: stays (bin/gstack-brain-context-load reads
it from the installed render); hooks: stays (Claude Code host wires
PreToolUse from it).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(gen): regenerate SKILL.md — dead frontmatter keys removed
Mechanical regen after hosts/claude.ts stripFields change.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(test): context-budget ratchet — CI ceilings on always-on + eager token ledgers
New free test grades the two ledgers nothing else guards: the full-frontmatter
always-on catalog (aggregate) and per-skill eager tokens (SKILL.md +
forced-read refs), via checkBudget from lib/context-bill.ts. Ceilings live in
test/fixtures/context-budget.json with x1.05/x1.10 headroom; regenerate with
bun test/helpers/capture-context-budget.ts. New skills fail until consciously
budgeted; removed skills fail until the fixture is refreshed; reductions
ratchet the ceilings down so wins lock in.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(todos): file output-template carve wave + plan-ceo doctrine revisit; mark preamble-carve P3 in flight
Two follow-ups deferred from the approved token-reduction program (CEO review
'NOT in scope' list), filed with full context per TODOS format. The existing
P3 preamble-carve entry gets a status update pointing at the program that
supersedes it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): review findings — Windows path normalization, full totals rebuild, ratchet coverage
Pre-landing review (5 specialists) found one critical: the ratchet test runs
in the curated Windows lane, where path.relative yields backslash skill names
that miss the test/ filter and mismatch every POSIX fixture key. Names are now
normalized once in buildRatchetBill (toPosixName) and the fixture filter is
tightened to test/fixtures/. All eight Bill.totals fields are rebuilt from the
filtered list (no fixture-polluted perInvocation/totalMd numbers for future
consumers). New coverage: Windows-separator normalization pins, a
captureContextBudget round-trip against tree-a (headroom math exact), a
stripFields regression pin (interactive/benefits-from absent from renders,
hooks/gbrain preserved), and the ceilings test no longer double-reports
stale-fixture entries.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): adversarial findings — stable root key, symlink-alias dedupe, fixture-shape guard
Adversarial review (Claude subagent) verified the fixture's root-skill key was
the capture machine's checkout dirname: any non-gstack-named clone (every
Conductor worktree) failed the free suite, and the documented re-run-the-capture
recovery baked the local dirname into the committed fixture — silent corruption
through the tool's own protocol. The root skill is now pinned to ROOT_SKILL_KEY
('gstack', its frontmatter name). Symlink aliases are realpath-deduped (census
precedent): connect-chrome no longer gets its own ceiling, so Windows checkouts
that materialize the symlink as a plain file can't fail the stale-ceiling
set-equality test. New guards: fixture-shape validation (a string alwaysOnTotal
can no longer silently disable the ceiling), a mutation pin that the filter
shrinks the always-on ledger vs the raw bill, an alwaysOnTotal violation test
(the branch was load-bearing with only under-budget coverage), and an atomic
temp+rename fixture write. Fixture regenerated: 59 ceilings, alwaysOnTotal 6344.
Deferred with a TODO: anchoring transformFrontmatter's denylist strip to the
frontmatter block (latent, zero live collisions, pre-existing path).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: bump version and changelog (v1.69.1.0)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: update project documentation for v1.69.1.0
CLAUDE.md: Token ceiling section documents the context-budget ratchet as
the third guard (test file, fixture, new-skill budgeting, capture command).
CONTRIBUTING.md: Tier 1 guard list gains a Context-budget ratchet bullet;
the Adding-a-new-skill checklist gains the budget-capture step.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: pin exact guard semantics for the context-budget ratchet in CLAUDE.md
Doc-review finding: "a third enforced ceiling" undercounted the guard
family (skill-size-budget floors and parity ratios also watch these
ledgers, relatively). Rephrased to match the ratchet test's own header:
absolute ceilings vs relative floors/ratios.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(changelog): heaviest-skill claim matches the fixture (land-and-deploy edges review by 0.2%)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(bin): gstack-skill-start + gstack-skill-end — the preamble runtime, consolidated
Absorbs the ~13KB of bash every tier-2+ SKILL.md inlined twice over (bootstrap
fence + artifacts-sync fence) and the skill-end telemetry/sync fences. Same
KEY: value STATUS-line contract the prose interprets, plus SKILL_START_PROTO
handshake (OV5), SESSION_ID/TEL_START echoes, GSTACK_HOME-normalized state
paths (EOV7), --parent-pid session identity (EOV5: $PPID inside the script is
the ephemeral tool-call shell), OV4 sanitization of passthrough output, and a
receipted daily artifacts pull (_receipted_git, brain-sync class, fail-closed).
Per-line || true error style throughout (F3) — a mid-script failure never drops
later STATUS lines.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(gen): preamble resolvers emit a script invocation fence instead of inline bash
generate-preamble-bash: ~6.3KB fence -> 4-line gstack-skill-start invocation
(quoted-tilde pitfall handled: leading ~ interpolates through $HOME; env-var
hosts keep $GSTACK_BIN) + degraded-mode prose (F1/EOV8: safe defaults, consent
gates deferred-never-lost; OV5: proto rule). generate-brain-sync-block: ~6.8KB
bash -> interpretation prose + the privacy stop-gate (stays inline until
Phase 2's gated emission). generate-completion-status: telemetry fence -> one
gstack-skill-end call with SESSION_ID/TEL_START handoff.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(gen): regenerate all skills + golden fixtures — inline preamble bash removed
Mechanical regen after the resolver change: −12,628 lines across 52 renders
(corpus 952K -> 806K render tokens; tier-2 skills −11-13KB each). Golden
per-host ship fixtures refreshed from the fresh claude/codex/factory renders.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: skill-start contract suite + preamble A/B eval + touchfiles registration
test/gstack-skill-start.test.ts (11 free tests): STATUS-key contract vs the
prose (F2), per-host fence resolution shapes (E1), proto-first, OV4 marker
sanitization, --parent-pid identity, headless suppression, skill-end duration
math + pending cleanup. test/skill-e2e-preamble-script-ab.test.ts (gate tier,
OV7): inline-bash render (pinned from 29785978) vs script render with the
fence redirected at the worktree bin (EOV2 — hermetic evals otherwise resolve
the operator install and silently exercise degraded mode). 21 touchfiles dep
lists gain the two bin scripts (EOV9) so future script edits select the
preamble evals; selection-count pin updated 23->24.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: repin ~70 assertions to the script contract — every literal gets a successor
Assertions that pinned inline-bash internals (update-check guard, _SESSIONS
reaping, telemetry start/end blocks, routing probe, repo-strip producer,
first-task gating, EXPLAIN_LEVEL/QUESTION_TUNING echoes, #2499 jq scope
resolution, Issue-8 CONDUCTOR gate) now pin the same invariants in their new
home: bin/gstack-skill-start / bin/gstack-skill-end file content for script
internals, the invocation fence + interpretation prose for render-side
behavior. No assertion deleted without a successor; live-execution tests
(routing probe, brain-sync jq) run against script bytes unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(test): re-baseline size floors + ratchet ceilings down (EOV1/OV9 protocol)
parity-baseline-v1.69.1.0.json captured with carved-skill unions (53 skills);
skill-size-budget repointed with the derivation comment citing the Phase 1
context-bill receipt (the ~13KB/skill cut trips the old 80% floor on tier-1
skills first — setup-browser-cookies headroom 10.8KB < the cut). The v1.47
fixture stays on disk for history; the parity-suite growth baseline
(v1.64.1.0) is untouched. Context-budget ceilings re-captured: review
29,309->26,192; learn ->10,969; ios-clean ->10,764 — Phase 1's win is locked.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(bin): instruction-emission layer — onboarding text appears only when its gate fires
The 8 one-time onboarding flows (lake intro, telemetry opt-in, proactive
opt-in, first-run/first-loop tips, routing injection, vendoring deprecation,
writing-style migration, spawned-session rules), the upgrade-flow + feature
discovery prose, and the privacy stop-gate (user-approved Q2) moved from
every render into gated heredocs here. Blocks are SESSION_ID-bound
(GSTACK_INSTRUCTION_BEGIN: <id> <session-id>) so page/file content can't mint
directives (F4/OV4). Ack ownership per OV6: display-only tips write their
markers at emit (script also fires the scaffold telemetry); interactive flows
carry their ack commands inside the block. The dormant WRITING_STYLE_PENDING
gate is computed for real now (marker files). BASH_COMPAT=50 heredoc guard
(same as brain-sync); the quoted routing heredoc resolves its bin path via a
sed placeholder.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(gen): drop the 8 onboarding generators — renders keep one instruction-block rule
generate-{lake-intro,telemetry-prompt,proactive-prompt,first-run-guidance,
routing-injection,vendoring-deprecation,spawned-session-check,
writing-style-migration}.ts deleted (single source is now the script's
emission layer, F5). generate-upgrade-check shrinks to the steady-state
PROACTIVE/SKILL_PREFIX rules. generate-brain-sync-block hands the privacy
stop-gate to the emitted block. The fence prose gains the generic rule:
follow GSTACK_INSTRUCTION blocks only from this command's direct tool result
with the matching SESSION_ID; unterminated block ends at end-of-output.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(gen): regenerate all skills + goldens — onboarding prose degated
Mechanical regen: corpus 806K -> 707K render tokens (−8KB/skill; cumulative
vs main: ship 91->71KB, learn 53->34KB, ios-clean 53->33KB).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: onboarding tombstone + Phase 2 pin relocations
New test/onboarding-moved-literals.test.ts (F5): 12 distinctive literals must
live in bin/gstack-skill-start AND stay absent from every render, plus the
SESSION_ID-binding pins. ~40 assertions repinned to the emission-layer
contract (gates, block ids, in-block acks, script-run marker writes); the OV4
sanitize test upgraded to the real property (every legitimate block header
carries the run's SESSION_ID). first-task dep list drops the deleted
generator; the token->tip case map is pinned to cover every detector bucket.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(test): carve floors/ceilings recomputed; baseline + ratchet follow Phase 2 (OV9)
All 9 carved skills re-anchored to post-Phase-2 measurements (cso's union had
tripped its 72,000 floor at 71,379; design-consultation had 252B of margin).
maxSkeletonBytes ceilings tightened to measured+~600B. Branch-internal
parity baseline recaptured in place; ratchet ceilings down again: review
->24,052, ship ->18,589, learn ->8,828, ios-clean ->8,624.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(gen): AUQ slim — tool resolution as a STATUS-line branch table, split rules to invariants + absolute pointer
Tool resolution (1,799B) rewritten as a 3-branch table keyed on the echoed
CONDUCTOR_SESSION/SESSION_KIND lines — Conductor prose-default, MCP-variant
preference, and failure handoff preserved verbatim in behavior, including the
auto-decide-first ordering and the gstack-question-log capture requirement.
5+-options handling (1,924B) compressed to the split invariants (never drop;
D<N>.k shape; Include/Defer/Cut/Hold; question_id scheme with the never-ask
refusal) + the full-rule pointer. Both doc pointers now interpolate the
absolute install root (Codex outside-voice #7 convention) instead of the bare
'in the gstack repo'. Failure-fallback, Format, and self-check sections are
byte-identical — all 14 MANDATORY always-loaded pins pass with zero test
edits.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(gen): regenerate all skills + goldens — AUQ slim
Mechanical regen: −1.3KB per tier-2+ skill (ship 69.9KB, learn 32.5KB).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(test): baseline + ratchet follow Phase 3 (OV9); OV8 evaluated — shrink floor stays
Branch-internal baseline recaptured; ratchet ceilings down again. OV8's
floor-retirement question, evaluated as planned after Phase 3: the 80% shrink
floor stays — it uniquely catches accidental body deletion in non-carved
skills BETWEEN ratchet recaptures, and the capture command has amortized the
fixture-refresh cost that motivated retiring it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(review): carve adversarial, plan-completion, and review-army into sections
The three resolver macros ship already carves as siblings now load on demand
for /review too: skeleton 100.2KB -> 55.0KB (-45%), union 93.4KB. Resolvers
stay the single source of truth (sections wrap the macros). Step 0/1, scope
drift, critical pass, confidence calibration, and fix-first stay always-loaded.
Fixtures and pins follow the moved content (codex-hardening wrapped-sites,
review-army E2E fixture builds skeleton+sections with an empty-fixture guard).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(codex): carve the three mutually exclusive modes into sections
Review/Challenge/Consult mode bodies (34.7KB where at most one ever runs)
load on demand: skeleton 81.0KB -> 55.2KB, union 1.04x the monolith. The mode
dispatch, filesystem boundary, and a new always-loaded 'Synthesis
recommendation (REQUIRED) — all modes' block stay skeleton-side (the AUQ
per-skill pins pass unchanged); the plan-file report + exit gate render after
the last section pointer per the gateAfterStop pattern.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(land-and-deploy): carve first-run validation, readiness gate, and merge/deploy into sections
The once-per-repo dry-run validation, the pre-merge readiness gate, and the
merge + deploy-strategy steps (37.8KB) load on demand: skeleton 91.1KB ->
55.7KB. Step 1.5 keeps its detection bash as the dispatch; the first-run
section's fingerprint-save block gained {{SLUG_EVAL}} so it is self-contained.
Zero content lost (line-coverage checked against HEAD).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(ios): demote the four ios skills to preamble-tier 2 (Phase 5)
They never consume the tier-3 sections (repo-mode ownership, search-before-
building) but do fire AskUserQuestion, which tier >=2 provides — verified by
grep before the plan review. -2.2KB per skill. Render assertions pin the
demotion (tier-3 sections absent, AUQ format present).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(guards): register wave-1 carves; monolith invariants retire; baselines + ratchet follow
CARVE_GUARDS gains review/codex/land-and-deploy (12 carved skills total);
their MONOLITH_INVARIANTS entries retire (invariants now generate from the
registry, cso precedent). Touchfiles: carve-section-loading covers the three
new carves; the codex + land-and-deploy LLM-judge dep lists widen to their
sections. Regen + goldens + branch-internal baseline + ratchet ceilings
recaptured (review 24,052 -> skeleton-based ceiling; union floors hold).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(gen-skill-docs): review render pins read the carved union
The review carve's readSkillUnion conversions (same pattern its neighbor
carved-skill pins already use).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(autoplan): carve the four review phases + tasks aggregator into sections
Phase bodies (CEO/Design/Eng/DX consensus flows) and the Implementation Tasks
aggregator load on demand; Design and DX stay separate sections because each
is independently conditional on scope. Skeleton 83.7KB -> 58.7KB (-30%
always-loaded); the 6 decision principles, classification, sequencing, and
explicit skip-condition dispatch stay always-loaded. The chain E2E's
phase-complete markers now live only in sections, so its assertions double as
section-read proof (behavioral: external).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(spec): carve the post-confirmation gate-and-file tail into one section
Phases 1-4 are the turn-1 conversational spine — carving them would force the
Read on the first user message for zero real savings. The mechanical tail
(4.5/4.5a/4.5b redaction gates + Phase 5 filing + TTHW telemetry) fires only
after draft confirmation: a genuine lazy boundary, kept as ONE section so the
gh-issue-create bash can never load without the fail-closed redaction gate
that precedes it. Skeleton 65.4KB -> 50.7KB; all ~85 phase-structure
invariants migrated location-aware plus a new carve-shape suite (56 tests).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(setup-gbrain): carve the branch-exclusive install paths into sections
Brain-init (Paths 1/2/3/4 bodies), engine remediation, transcript gate, and
CLAUDE.md persist load on demand — at most one install route ever runs.
Skeleton 75.3KB -> 57.0KB; the Step 1 detect and Step 2 path dispatch stay
always-loaded. New buildSetupGbrainFixture helper gives the periodic E2Es
extract-don't-copy fixtures with a non-empty guard; the voyage-code-3 gate
counts scan the tmpl union (the third init site lives in engine-remediation).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(guards): register wave-2 carves (15 carved skills); autoplan monolith retires; baselines follow
CARVE_GUARDS gains autoplan (behavioral: external via the chain eval), spec,
and setup-gbrain; autoplan's MONOLITH_INVARIANTS entry retires. Touchfiles:
setup-gbrain periodic dep lists gain the section tmpls + fixture helper; the
stale-brain-refs scan covers setup-gbrain/sections. Regen + goldens + branch
baseline + ratchet recaptured.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(qa): carve QA patterns + health rubric into on-demand sections (68→48KB skeleton)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(browse): carve full command list + snapshot flags into sections/command-list.md (39→27KB skeleton)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(retro): absorb inline git/awk metrics into bin/gstack-retro-metrics + carve report format
RETRO_METRICS_PROTO: 1 contract, local git reads only (fetch stays in the
skill prose), degraded path documented in the skeleton.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: register wave-3 carves (qa, browse, retro) — guards, touchfiles, pins, baselines
CARVE_GUARDS gains the three entries; qa's monolith invariant retires.
auq-format carve-safety now keys on the skeleton+sections union shipping
the AUQ block (first tier-1 carve: browse never renders it by design).
Baselines: parity v1.69.1.0 at 18 sectioned skills; ratchet recaptured.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): drop stale generate-lake-intro import (generator deleted in the emission-layer move)
Sol scope discipline stays pinned via the model overlay + completeness
section; the lake intro is now a single script-emitted blurb.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(office-hours): carve Phase 2A/2B into mode-exclusive sections (81→67KB skeleton)
A session runs exactly one mode, so a builder session never loads the
13KB startup diagnostic. Mode mapping and the vibe-shift upgrade rule
stay in the skeleton.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(design): carve UX doctrine + Pretext patterns into read-on-demand sections
design-html 57→49KB, design-shotgun 53→50KB. Sections wrap
{{UX_PRINCIPLES}} so scripts/resolvers/design.ts stays the source of
truth; the pretext-patterns STOP sits at the top of Step 3 so the read
provably precedes the Write.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: register wave-4 carves (office-hours ext, design-html, design-shotgun) — 20 carved skills
Both design entries carry requiredReads + loading-eval scenarios (D3A
condition). office-hours phase sections are mode-exclusive, so only the
always-reached design/handoff section is a deterministic requiredRead.
Baselines and ratchet recaptured.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: trim CLAUDE.md 66.4→44.9KB — verbatim moves to docs/, pointers stay inline
Moved: browser/sidebar/server internals, CHANGELOG release-summary format
spec, project tree, hermetic-E2E detail, slop-scan reference, OpenClaw
publishing. Kept inline: every hard behavioral rule (dist/ ban, redaction
scan-at-sink, egress receipts, bisect commits, eval detach, CHANGELOG
entry rules), the machine-managed GBrain block (byte-identical), and the
'## Deploying to the active skill' header with gbrain-refresh in range
(pinned by test/gbrain-refresh-install-render.test.ts). No voice rewrites.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): seed onboarding markers into the hermetic child GSTACK_HOME
EOV7 made bin/gstack-skill-start honor GSTACK_HOME, so the operator-HOME
seeding in e2e-helpers.ts no longer reaches hermetic children — the
emission layer fired lake-intro/telemetry prompts that burned turns and
stalled PTY tests waiting on an answer (observed: plan-mode-no-op derailed
by the telemetry question). Onboarding-specific tests pin their own
GSTACK_HOME per-test, which merges over this seed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: raise carve-section-loading wall clock to 480s SDK / 540s bun
The heavy full-workflow scenarios satisfy their required section reads
inside 60s but need 300-450s to finish the report on slower sandboxes;
the 300s default read as a loading failure when the carve invariant held
(traces: plan-eng-review read its section at 8s, office-hours all three
at 24s, design-html both at 50s — all timed out mid-report).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(security): harden the skill-start trust boundary — review-army findings
Session ID gains a urandom suffix (block binding unforgeable by reflected
content); _sanitize also neutralizes spoofed SESSION_ID: lines; branch
names are charset-clamped before JSON embedding (skill-start + skill-end);
.brain-last-push reads first line only with a charset clamp; the artifacts
URL echo routes through _sanitize; the privacy consent gate fires in
interactive sessions only (spawned auto-choose could accept consent no
human gave — emission order is not a safety property); the daily pull gets
non-interactive + slow-network git guards and stamps only when the
receipted path ran; ~/.claude.json gets a grep pre-filter before the jq
parse.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(resolvers): question-log session_id becomes a substitution placeholder + stale-comment sweep
The question-log block bound $_SESSION_ID, a shell variable the
consolidated fence never sets — hook-less hosts logged empty session_id,
breaking /plan-tune per-session grouping. It now uses the same
substitute-from-the-skill-start-echoes contract as the telemetry block.
Also: retired the pre-Phase-2 stop-gate docstring, repointed the
gbrain-local-status cross-reference at the script's inline jq, dropped an
orphaned section comment, documented retro-metrics' suffix-only census.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: regenerate renders for the question-log placeholder; goldens + baselines follow
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: hermetic update-check, onboarding gate sequencing, seeding parity
The contract test's child did a live git ls-remote + curl to github.com on
every bun run test (update_check config now gates it off); the headless
test gets a fresh GSTACK_HOME so the suppression is actually exercised; a
new OV6 test drives the script three times to pin ack-at-emit and gate
sequencing; hermetic seeding covers the config-keyed privacy gate; the
EVALS_HERMETIC=0 debug seeding reaches marker parity.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(ci): demote the preamble A/B to periodic (OV7) and add it to the periodic matrix
Post-Phase-3 demotion per the plan; the eval needs fetch-depth 0 (it git
shows a pre-Phase-1 sha), which only the periodic workflow provides — and
a static matrix entry so it can't silently never run.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: bump version and changelog (v1.70.0.0)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: update project documentation for v1.70.0.0
ARCHITECTURE.md: the preamble section now describes the v1.70 runtime —
the rendered {{PREAMBLE}} block invokes bin/gstack-skill-start and reads
STATUS lines, gstack-skill-end logs telemetry, and one-time onboarding
text arrives as gated GSTACK_INSTRUCTION blocks instead of riding in
every render.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: doc-review fixes — repair moved-file links, drop unbacked session-count claim
docs/BROWSER_INTERNALS.md: the two ARCHITECTURE.md anchor links broke when
the section moved from repo-root CLAUDE.md into docs/ — now ../ARCHITECTURE.md.
ARCHITECTURE.md: the preamble's session-tracking item claimed an active-session
count and an "ELI16 mode" that no shipped code implements (the count
computation was deleted with the inline preamble); describe the real
touch-and-prune behavior instead.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(changelog): correct numeric claims against measured counts
50 of 62 installed skills dropped (fixture/alias entries have no preamble);
11 new carves + a deeper office-hours carve = 9→20; test counts match the
files (13 / 11 / 3 / 7).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: repoint the preamble-runtime version reference after the queue rebump (v1.71.0.0)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(e2e-design): widen the Aesthetic synonym set — vocabulary variance, not a regression
Both attempts in run 33090283032 produced judge-praised DESIGN.md files
phrased as 'design principles'/'design language' without any of the four
original literals; inputs were identical to the prior passing run
32899975845 (design-consultation untouched by the intervening merge).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(test): stage design-consultation's sections/ into the E2E fixture
The skill has been carved since v1.57.0.0 — the DESIGN.md structure
prescription (the AESTHETIC proposal template) lives in
sections/proposal-and-preview.md behind a STOP-read. The fixture only
copied SKILL.md, so the agent improvised structure from the skeleton and
the section-synonym check has been a coin flip since the carve (CI run
33090283032 trace shows 'no sections dir'; the local eval store has the
same failure on 2026-08-25 while that day's CI run passed on lucky
vocabulary).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
269 lines
11 KiB
TypeScript
269 lines
11 KiB
TypeScript
// E2E: /setup-gbrain Path 4 with Step 4.5 "Yes" — local PGLite for code search.
|
|
//
|
|
// Drives the skill against a stub HTTP MCP server (200 OK on tools/list).
|
|
// Auto-answers AskUserQuestion to pick:
|
|
// - Path 4 at Step 2 (Remote gbrain MCP)
|
|
// - "Yes, set up local PGLite for code" at Step 4.5
|
|
//
|
|
// Asserts that the model:
|
|
// 1. ran the verify helper successfully (got past Step 4c)
|
|
// 2. invoked gstack-gbrain-install (Step 4.5 Yes branch)
|
|
// 3. invoked `gbrain init --pglite --json` (also Step 4.5 Yes branch)
|
|
// 4. registered the remote MCP via claude mcp add --transport http
|
|
// 5. wrote a "Code search ..... OK local-pglite" row to the Step 10 verdict
|
|
//
|
|
// Periodic-tier (codex #12: AgentSDK harness is non-deterministic; gate-tier
|
|
// coverage of the split-engine behavior lives in the deterministic unit
|
|
// tests at gbrain-local-status.test.ts, gbrain-sync-skip.test.ts, etc).
|
|
//
|
|
// Cost: ~$0.50-$1.00 per run. Periodic-tier (EVALS=1 EVALS_TIER=periodic).
|
|
|
|
import { test, expect } from 'bun:test';
|
|
import { describeE2ETier } from './helpers/e2e-gate';
|
|
import * as fs from 'fs';
|
|
import * as os from 'os';
|
|
import * as path from 'path';
|
|
import * as http from 'http';
|
|
import {
|
|
runAgentSdkTest,
|
|
passThroughNonAskUserQuestion,
|
|
resolveClaudeBinary,
|
|
} from './helpers/agent-sdk-runner';
|
|
import { buildSetupGbrainFixture } from './helpers/setup-gbrain-fixture';
|
|
|
|
const describeE2E = describeE2ETier('periodic');
|
|
|
|
/**
|
|
* Minimal stub MCP server that returns success on initialize / tools/list.
|
|
* Verify helper calls /tools/list with a Bearer header and inspects the body.
|
|
*/
|
|
function startStubMcp(): Promise<{ url: string; close: () => Promise<void> }> {
|
|
return new Promise((resolve) => {
|
|
const server = http.createServer((req, res) => {
|
|
let body = '';
|
|
req.on('data', (c) => (body += c));
|
|
req.on('end', () => {
|
|
res.statusCode = 200;
|
|
res.setHeader('Content-Type', 'text/event-stream');
|
|
// Try to be useful: respond with a fake initialize + tools/list payload.
|
|
let payload: unknown = { jsonrpc: '2.0', id: 1, result: { tools: [] } };
|
|
try {
|
|
const req = JSON.parse(body);
|
|
if (req.method === 'initialize') {
|
|
payload = {
|
|
jsonrpc: '2.0',
|
|
id: req.id,
|
|
result: {
|
|
protocolVersion: '2024-11-05',
|
|
capabilities: { tools: {} },
|
|
serverInfo: { name: 'gbrain', version: '0.32.3.0' },
|
|
},
|
|
};
|
|
}
|
|
} catch {
|
|
// ignore parse failure; default payload
|
|
}
|
|
res.end(`event: message\ndata: ${JSON.stringify(payload)}\n\n`);
|
|
});
|
|
});
|
|
server.listen(0, '127.0.0.1', () => {
|
|
const addr = server.address();
|
|
if (!addr || typeof addr === 'string') throw new Error('no address');
|
|
resolve({
|
|
url: `http://127.0.0.1:${addr.port}/mcp`,
|
|
close: () => new Promise((r) => server.close(() => r())),
|
|
});
|
|
});
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Fake gbrain CLI:
|
|
* - --version → echoes a version
|
|
* - init --pglite --json → writes a pglite config, exits 0
|
|
* - everything else → exits 0 quietly
|
|
*
|
|
* Logs every invocation so we can assert init was called.
|
|
*/
|
|
function makeFakeGbrain(binDir: string, gbrainConfigPath: string): string {
|
|
const callLog = path.join(binDir, 'gbrain-calls.log');
|
|
const script = `#!/bin/bash
|
|
echo "gbrain $@" >> "${callLog}"
|
|
case "$1 $2" in
|
|
"--version "*) echo "gbrain 0.33.1.0"; exit 0 ;;
|
|
"init --pglite") cat > "${gbrainConfigPath}" <<JSON
|
|
{"engine":"pglite","database_url":"pglite:///fake"}
|
|
JSON
|
|
echo '{"status":"ok","engine":"pglite"}'
|
|
exit 0 ;;
|
|
esac
|
|
exit 0
|
|
`;
|
|
fs.writeFileSync(path.join(binDir, 'gbrain'), script, { mode: 0o755 });
|
|
return callLog;
|
|
}
|
|
|
|
/**
|
|
* Fake `claude` CLI for mcp add/remove/get/list. Logs every call so we can
|
|
* assert remote MCP registration happened.
|
|
*/
|
|
function makeFakeClaude(binDir: string): string {
|
|
const callLog = path.join(binDir, 'claude-calls.log');
|
|
const script = `#!/bin/bash
|
|
echo "claude $@" >> "${callLog}"
|
|
case "$1 $2" in
|
|
"mcp add") exit 0 ;;
|
|
"mcp list") echo "gbrain: http://stub/mcp (HTTP) — connected" ; exit 0 ;;
|
|
"mcp remove") exit 0 ;;
|
|
"mcp get") echo '{"type":"http","url":"http://stub/mcp"}'; exit 0 ;;
|
|
esac
|
|
exit 0
|
|
`;
|
|
fs.writeFileSync(path.join(binDir, 'claude'), script, { mode: 0o755 });
|
|
return callLog;
|
|
}
|
|
|
|
/**
|
|
* Fake gstack-gbrain-install so we don't actually clone the gbrain repo +
|
|
* bun-link. The test only cares that the skill INVOKED it on the Yes branch.
|
|
*/
|
|
function makeFakeInstall(binDir: string): string {
|
|
const callLog = path.join(binDir, 'install-calls.log');
|
|
const script = `#!/bin/bash
|
|
echo "install $@" >> "${callLog}"
|
|
exit 0
|
|
`;
|
|
fs.writeFileSync(path.join(binDir, 'gstack-gbrain-install'), script, {
|
|
mode: 0o755,
|
|
});
|
|
return callLog;
|
|
}
|
|
|
|
describeE2E('/setup-gbrain Path 4 + Step 4.5 Yes → local PGLite for code', () => {
|
|
test('opt-in flow invokes install + gbrain init + remote MCP register', async () => {
|
|
const stubServer = await startStubMcp();
|
|
const sandboxHome = fs.mkdtempSync(path.join(os.tmpdir(), 'path4-pglite-'));
|
|
const fakeBinDir = fs.mkdtempSync(path.join(os.tmpdir(), 'path4-pglite-bin-'));
|
|
const gbrainConfigDir = path.join(sandboxHome, '.gbrain');
|
|
fs.mkdirSync(gbrainConfigDir, { recursive: true });
|
|
const gbrainConfigPath = path.join(gbrainConfigDir, 'config.json');
|
|
const claudeLog = makeFakeClaude(fakeBinDir);
|
|
const gbrainLog = makeFakeGbrain(fakeBinDir, gbrainConfigPath);
|
|
const installLog = makeFakeInstall(fakeBinDir);
|
|
|
|
const ORIGINAL_CLAUDE_MD = '# Test project\n';
|
|
fs.writeFileSync(path.join(sandboxHome, 'CLAUDE.md'), ORIGINAL_CLAUDE_MD);
|
|
|
|
const askLog: Array<{ question: string; choice: string }> = [];
|
|
const binary = resolveClaudeBinary();
|
|
|
|
const orig = {
|
|
home: process.env.HOME,
|
|
pathEnv: process.env.PATH,
|
|
mcpToken: process.env.GBRAIN_MCP_TOKEN,
|
|
};
|
|
process.env.HOME = sandboxHome;
|
|
process.env.PATH = `${fakeBinDir}:${path.join(path.resolve(import.meta.dir, '..'), 'bin')}:${process.env.PATH ?? '/usr/bin:/bin:/opt/homebrew/bin'}`;
|
|
process.env.GBRAIN_MCP_TOKEN = 'gbrain_fake_token_for_test';
|
|
|
|
try {
|
|
// Carve-aware fixture (see test/helpers/setup-gbrain-fixture.ts):
|
|
// skeleton + brain-init (Step 4 Path 4 body incl. the Step 4d local
|
|
// PGLite offer this test says Yes to) + claude-md-persist (Step 8 sits
|
|
// on the walked path to Step 10). Non-empty guard inside the builder.
|
|
const skillPath = path.join(sandboxHome, 'setup-gbrain-SKILL.md');
|
|
fs.writeFileSync(
|
|
skillPath,
|
|
buildSetupGbrainFixture(['brain-init.md', 'claude-md-persist.md']),
|
|
);
|
|
const result = await runAgentSdkTest({
|
|
systemPrompt: { type: 'preset', preset: 'claude_code' },
|
|
userPrompt:
|
|
`Read the skill file at ${skillPath} and follow Path 4 (Remote MCP). ` +
|
|
`Use this MCP URL: ${stubServer.url}. ` +
|
|
`The bearer token is already in GBRAIN_MCP_TOKEN. ` +
|
|
`At Step 4.5 (the new "Want symbol-aware code search?" question), PICK YES — set up local PGLite for code. ` +
|
|
`Then continue through Step 5a (MCP registration) → Step 10 (verdict). ` +
|
|
`Do not skip Step 4.5; the test depends on the Yes path being taken.`,
|
|
workingDirectory: sandboxHome,
|
|
maxTurns: 25,
|
|
allowedTools: ['Read', 'Grep', 'Glob', 'Bash', 'Write', 'Edit'],
|
|
...(binary ? { pathToClaudeCodeExecutable: binary } : {}),
|
|
canUseTool: async (toolName, input) => {
|
|
if (toolName === 'AskUserQuestion') {
|
|
const qs = input.questions as Array<{
|
|
question: string;
|
|
options: Array<{ label: string }>;
|
|
}>;
|
|
const answers: Record<string, string> = {};
|
|
for (const q of qs) {
|
|
// Heuristics: pick the option that screams "yes/PGLite/code search" for our flow.
|
|
const yes =
|
|
q.options.find((o) =>
|
|
/yes.*local|local.*pglite|code search|opt in/i.test(o.label),
|
|
) ??
|
|
q.options.find((o) => /remote.*mcp|path 4/i.test(o.label)) ??
|
|
q.options[0]!;
|
|
answers[q.question] = yes.label;
|
|
askLog.push({ question: q.question, choice: yes.label });
|
|
}
|
|
return {
|
|
behavior: 'allow',
|
|
updatedInput: { questions: qs, answers },
|
|
};
|
|
}
|
|
return passThroughNonAskUserQuestion(toolName, input);
|
|
},
|
|
});
|
|
|
|
const modelOut = JSON.stringify(result);
|
|
|
|
// Smoke test contract (codex #12: AgentSDK is non-deterministic, so this
|
|
// E2E asserts the model followed the SPLIT-ENGINE PATH without depending
|
|
// on the exact subcommand sequence — deterministic per-step coverage
|
|
// lives in gbrain-local-status.test.ts, gbrain-sync-skip.test.ts, etc).
|
|
|
|
// Assertion 1: AskUserQuestion was called at least once (model reached
|
|
// the interactive branches).
|
|
expect(askLog.length).toBeGreaterThan(0);
|
|
|
|
// Assertion 2: at LEAST ONE of the Path 4 / Step 4.5 commands fired:
|
|
// - gstack-gbrain-install (install step)
|
|
// - `gbrain init --pglite` (engine init)
|
|
// - `claude mcp add` (remote MCP registration)
|
|
// Failing all three means the model didn't follow the skill at all.
|
|
const installCalls = fs.existsSync(installLog)
|
|
? fs.readFileSync(installLog, 'utf-8')
|
|
: '';
|
|
const gbrainCalls = fs.existsSync(gbrainLog)
|
|
? fs.readFileSync(gbrainLog, 'utf-8')
|
|
: '';
|
|
const claudeCalls = fs.existsSync(claudeLog)
|
|
? fs.readFileSync(claudeLog, 'utf-8')
|
|
: '';
|
|
const followedPath =
|
|
installCalls.length > 0 ||
|
|
/gbrain init --pglite/.test(gbrainCalls) ||
|
|
/mcp add/.test(claudeCalls);
|
|
expect(followedPath).toBe(true);
|
|
|
|
// Assertion 3: token never leaked to CLAUDE.md (security regression).
|
|
const finalClaudeMd = fs.readFileSync(
|
|
path.join(sandboxHome, 'CLAUDE.md'),
|
|
'utf-8',
|
|
);
|
|
expect(finalClaudeMd).not.toContain('gbrain_fake_token_for_test');
|
|
} finally {
|
|
if (orig.home === undefined) delete process.env.HOME;
|
|
else process.env.HOME = orig.home;
|
|
if (orig.pathEnv === undefined) delete process.env.PATH;
|
|
else process.env.PATH = orig.pathEnv;
|
|
if (orig.mcpToken === undefined) delete process.env.GBRAIN_MCP_TOKEN;
|
|
else process.env.GBRAIN_MCP_TOKEN = orig.mcpToken;
|
|
await stubServer.close();
|
|
fs.rmSync(sandboxHome, { recursive: true, force: true });
|
|
fs.rmSync(fakeBinDir, { recursive: true, force: true });
|
|
}
|
|
}, 300_000);
|
|
});
|