* refactor(resolvers): split review.ts into MECE resolver modules (pure move)
Move every function from scripts/resolvers/review.ts, unchanged, into:
- review-dashboard.ts: review dashboard, plan-file review report
- plan-gates.ts: approval check, exit-plan-mode gate, plan-file discovery,
plan-completion audit/gate (ship + review), plan verification exec
- spec-review.ts: both spec review loops, benefits-from, anti-shortcut clause
- outside-voice-steps.ts: Codex second opinion, adversarial step, Codex plan
review, Codex doc review, disabled-outside record
- review-scope.ts: scope drift, cross-review dedup, shared-code reuse
review.ts is deleted; index.ts imports the new modules. gen-skill-docs
output is byte-identical for every host (--host all). Test imports and
source-path references are re-pointed; the two source-text report/gate
tests in gen-skill-docs.test.ts become behavioral renders across every
consuming skill and host. All 46 touchfile entries that named review.ts
now name all five modules, guarded by a recorded selection golden.
* test(browse): black-box auth matrix for every server route and both surfaces
Drives buildFetchHandler fetchLocal/fetchTunnel with no token, wrong token,
root token, scoped token and the SSE cookie for all 33 routes, plus unmatched
paths and wrong methods. Denials assert today's exact status, body and content
type; allowed credentials assert the handler was reached. Written against the
unchanged if-chain server so the W3 route-table refactor must keep it green.
* refactor(shard-engine): move scripts/test-strict-output.ts to scripts/lib/shard-engine.ts
The shared shard engine grows from the existing strict-output module
(runShardChild, killProcessGroup, signal forwarding, strict classifier).
scripts/test-strict-output.ts stays as a re-export so existing importers,
mock.module paths and the strict-output/run-shard-child tests are unchanged.
The engine inherits the global touchfile entry; the free runner's CLI-routing
fixture copies the new module.
* refactor(resolvers): decompose the three >150-line review resolvers (output-neutral)
Split generateAdversarialStep, generateCodexPlanReview and
generatePlanCompletionAuditInner into per-section helpers whose template
literals are copied verbatim, so every function in the new modules is at
or under 150 lines. gen-skill-docs output is byte-identical for every host
(--host all, compared against 96764e80 with a fixed --link-root).
* refactor(resolvers): one outside-voice failure policy (deliberate prose unification)
outsideVoiceFailurePolicy(ctx, opts) in outside-voice.ts now renders the
auth / timeout / empty-response bullets for all four call sites that
hand-typed them (Codex second opinion, adversarial step, Codex plan
review, design outside voices). Options are explicit per site
(timeoutMinutes, onTimeout, stderrOnEmpty, fallback, escape) with no
defaults.
Deliberate generated-prose changes (every host):
- office-hours: 'Fall back to <native> subagent.' becomes
'Fall back to the <native> subagent below.'
- plan-devex-review: the plain 'Auth failure (stderr contains ...)'
bullets become the canonical bold bullets; auth also triggers on
'API key'; 'auth failed' becomes 'authentication failed'.
- review/ship adversarial: 'exceeded 9 minutes and was terminated'
becomes 'timed out after 9 minutes and was terminated'; the timeout
is still MISSING COVERAGE.
- design outside voices: unchanged.
Adds ratchet (d) (test/outside-voice-failure-policy.test.ts) with a
reasoned allowlist for /codex's own CLI errors, the MISSING COVERAGE
retention test, refreshed codex/factory ship goldens, and outside-voice.ts
in every touchfile entry of review.ts and design.ts (selection golden
extended).
* test(pty): fake PTY session driver with an injectable clock through the runner launch seam
The three plan-skill runners take an optional PtyDriver (launch, now,
monotonic, sleep); omitted, they use the real launcher and clocks exactly as
before. test/helpers/pty/fake-session.ts feeds scripted frames through that
seam, and claude-pty-runner.runners.unit.test.ts runs observation, counting
and floor for success, deadline timeout, permission prompt and plan-ready
outcomes with no CLI or real timers. These cases must stay green unchanged
through the W4 split and the runPtySession extraction.
Touchfiles: every entry that lists claude-pty-runner.ts or pty-screen.ts now
also lists test/helpers/pty/**.
* refactor(shard-engine): run both lanes on the shared engine; lane policy injected
Engine (scripts/lib/shard-engine.ts) gains the W2 primitives: per-shard
tmp/Chromium sandbox + async cleanup backstop, log-path allocation and
full-stream log capture, one duration-seed reader/writer with a lane
predicate, LanePolicy (seed predicate + zero-execution verdict),
strictShardStatus, and the shared CLI flag loop. runShardChild takes an
optional companion (signal/settle) and waits a bounded 250ms to reap a
wall-killed child.
Free lane stops spawning shards itself: runFreeShard uses runShardChild
with trackShardBrowser as the companion (win32 path unchanged: no process
group, no negative-pid kill). Its sync state-dir removal stays lane policy.
Paid lane uses the sandbox, log, seed, verdict and flag primitives; the
hollow-shard guard applies PAID_LANE_POLICY. Lane outcomes are unchanged
(free keeps >= 0 seeds and file-count zero-exec rule; paid keeps > 0 seeds,
warning under selection and passed-empty under EVALS_ALL).
paid-free-boundary's closure assertion now names the engine module, where
the strict classifier lives.
* test(shard-engine): engine unit tests, fixture-corpus equivalence, per-lane CLI parity
- test/shard-engine.test.ts: failing/unhandled/module-load output fails both
lanes, per-lane zero-execution and seed rules, whole-group kill on a wall
timeout (both lanes), mocked-win32 path with no negative-pid kill,
companion settle order, log capture, sandbox isolation, flag loop.
- test/shard-engine-equivalence.test.ts + test/fixtures/shard-equivalence:
seven outcome fixtures plus one real shard, run through both lanes and
compared with classifications recorded from the base runners (96764e80).
- test/shard-cli-parity.test.ts + test/fixtures/shard-cli-parity: flag set,
defaults, validation errors and the Unknown argument error per lane match
the base runners.
* refactor(shard-engine): decompose runFreeShard and runPaidShard to <= 150 lines
Output-neutral extraction under the fixture-corpus equivalence and runner
tests: captureFreeStream, explainFreeVerdict and logFreeRecovery (free);
paidShardCommand, settleShardSpool, settleBootstrapRetention and
printLogTail (paid). The bootstrap scope-creation block that
bootstrap-retention.test.ts evaluates stays verbatim.
* refactor(pty): split claude-pty-runner.ts into test/helpers/pty/* behind a barrel
Pure move: every line of the former 5,047-line runner lands verbatim in one
module (four private helpers gain `export` for cross-module use):
binary, screen (absorbs test/helpers/pty-screen.ts, which now re-exports it),
launch, session (PtyDriver), judge, classify, auq, plan-native, boundaries,
runners/{observation,counting,floor}. claude-pty-runner.ts re-exports the
original public surface by name; pty/ modules import siblings directly.
Tests that read the runner's source text:
- rewritten as behavioral: the unit test's model-pin tripwire (fake CLI argv:
fallback chain, --model before extraArgs, hermetic --strict-mcp-config),
pty-skill-seeding-wiring (runners through the fake driver; launcher through
a fake CLI reporting CLAUDE_CONFIG_DIR). The "three wrappers forward model"
grep is replaced by the runners' fake-driver launch assertions.
- pty-screen-session / pty-screen-supervision: stop copying runner source;
they mock.module the real pty/screen.ts (and the fixture cleanup) instead.
- re-pointed to the owning module (they execute a sliced runner body with
injected boundaries; no seam exists for those boundaries yet):
eng-seeded-completion-ai, plan-floor-permission, plan-create-prepublication,
plan-count-completion; hermetic-wiring's source guard now reads pty/launch.ts
and scans every pty/ module for raw process.env spreads.
- plan-count-timeout and pty-output-wake mock the viewport at pty/screen.ts.
* test(ratchet-c): enforcing module/function size ratchet and moved-code touchfile coverage
Ratchet (c) ships enforcing: test/helpers/module-size.ts counts file and
top-level function lengths by brace matching over masked source (strings,
comments, regex literals and template text masked; ${} expressions kept),
covering function declarations, arrow functions assigned to consts and
route-table handler properties, with no parser dependency. Its self-test
uses template literals and code-fence braces copied from
scripts/resolvers/review.ts and design.ts. test/fixtures/module-size-ratchet.json
binds scripts/lib/shard-engine.ts (<= 800 lines, <= 150 per function) and
records the residual runner sizes (free 2352, paid 1921) as non-growth caps;
allowlist entries are keyed on file plus matched text and need a reason.
Failure output lists file:line, the rule, Fix: and the allowlist path.
touchfiles.test.ts gains the moved-code superset check over
test/fixtures/touchfile-move-goldens/ (W2 golden recorded at 96764e80:
test-strict-output.ts and test-paid-shards.ts global, test-free-shards.ts none).
* refactor(browse): declared route table replaces the buildFetchHandler if-chain
The ~1,300-line if-chain in buildFetchHandler becomes a route table:
each entry declares method, path, auth kind and surfaces, and one auth
gate in browse/src/routes/table.ts returns the per-kind denial (root-bearer,
scoped, root-or-sse-cookie: 401 Unauthorized; root-token: 403 Root token
required; extension-origin: 403 Forbidden). Unmatched requests take the
declared fallthrough (root-bearer check, then plain-text 404). Handlers move
to browse/src/routes/{core,pairing,pty,tokens,tunnel,activity,commands,files,
inspector}.ts and receive a RouteContext with auth checks as functions
instead of closing over factory locals. Dispatch order is unchanged:
tunnel filter, beforeRoute overlay, gate, handler. TUNNEL_PATHS stays a
literal in server.ts.
Behavior-preserving: the black-box auth matrix from the previous commit
passes unchanged. /memory and /inspector/events are declared root-bearer
because the blanket check always ran before their SSE-cookie branch.
Source-text route tests are rewritten as behavioral tests through
buildFetchHandler or a route's real handler with a stub RouteContext
(browse/test/route-test-harness.ts). Checks with no runtime seam are
re-pointed to the route modules: Surface type, /inspector/events SSE
helper, sanitizeReplacer imports, /pty-inject-scan sidecar-client import,
and the ngrok config lookup and startTunnel wiring that stay in server.ts.
* test(browse): stubbed-handler auth matrix and route inventory for the route table
Every ROUTES entry runs through the real dispatcher and gate with stub
handlers on each declared surface and six credentials; denials assert the
exact status and body each auth kind returned at 96764e8, admitted
credentials assert the handler ran (with the gate's TokenInfo for scoped
routes). Also pins the reviewed route inventory (method, path, auth kind,
surfaces), that every entry declares auth and surfaces, that the table's
tunnel paths equal the TUNNEL_PATHS literal with GET /connect admitted, the
unmatched fallthrough, and that the root token is rejected on every tunnel
route through buildFetchHandler.
* test(browse): ratchet (b) keeps route dispatch inside the route table
Scans browse/src/server.ts and browse/src/routes/*.ts for pathname
comparisons; only the table matcher and the tunnel-surface filter are
allowed, listed with reasons in browse/test/fixtures/route-dispatch-allowlist.json
(keyed on file plus line text). Also checks every entry declares auth and
surfaces and that gstack registers no beforeRoute overlay itself. Self-tests
plant a violation and assert the file:line, Fix: and allowlist path in the
message, that a shifted line stays allowlisted, and that a reasonless entry
is rejected.
* test: touchfile superset check for modules moved out of browse/src/server.ts
Records the paid evals selected by touching browse/src/server.ts at 96764e80
(17 E2E, 1 LLM judge) and asserts every browse/src/routes/*.ts module selects
a superset. The test reads every golden in test/fixtures/moved-module-selection/
so other moved-code goldens can sit beside it.
* test(shard-engine): give non-timeout corpus fixtures CI headroom; keep the POSIX golden off the Windows lane
Only the wall-timeout fixture keeps a 3s wall; the rest get 60s so a loaded
host cannot turn a pass into a timeout. Base and branch runners still agree
on every classification under the new walls. The Windows exclusion entry
moves the free runner's ratchet (c) residual cap to 2356 lines.
* refactor(pty): one runPtySession loop drives observation, counting and floor
test/helpers/pty/session.ts owns launch -> start -> (poll -> tick)* ->
timeout and the failure contract the three runners each hand-rolled: the
run's own error wins over capture and close errors, close always runs, owned
fixture cleanup runs last (also when launch fails). Each runner now supplies a
PtySessionPlan: its boot/command step, poll cadence (2s observation/floor
sleep; counting's output wake + 250ms coalesce), tick policy (permission
handling, native identity, terminal rules stay per runner because they differ)
and capture hooks. The runner bodies are decomposed into top-level steps so no
function exceeds 150 lines; behavior is unchanged and the fake-driver cases
from the first W4 commit pass unmodified.
The counting capture step and the native completion-summary predicate are now
named functions (countingCapture, isNativeCompletionSummary), so
plan-create-prepublication and plan-count-completion call them directly
instead of executing sliced source. The two harnesses that still execute a
sliced runner body with injected boundaries (eng-seeded-completion-ai,
plan-floor-permission) pass the PtyDriver seam instead of overriding
Date/Bun.sleep.
* test(ratchet-c): register route modules, review resolver modules and server.ts residual cap
* refactor(pty): decompose launchClaudePty and engNumberedFindingAUQ under 150 lines
launchClaudePty (349 lines) becomes launch preparation (args, hermetic
child env, owned state roots), recorder creation, spawn, the trust-dialog
watcher, close, and the session handle over one PtyProcess state object. The
failure order is unchanged: abort the viewport, dispose any recorders created
so far, dispose the viewport, rethrow. The --model / --strict-mcp-config
ordering and seedSkills wiring stay pinned by the behavioral fake-CLI tests.
engNumberedFindingAUQ (345 lines) keeps its guards and dispatch; each
self-contained issue family (declared cache, library retry hooks, cache
owner, injected singleton, shared writers, injected export) moves verbatim
into its own function. Every pty/ module is now <= 800 lines and every
top-level function <= 150 lines.
* test(pty): split claude-pty-runner.unit.test.ts along the pty/ module seams
The 188 unit tests move verbatim into claude-pty-runner.{screen,classify,
auq,launch,plan-native,boundaries}.unit.test.ts (test names unchanged; each
file imports only what it uses from the barrel). The five files that no longer
read a SKILL.md template join the test-of-test ratchet baseline with a reason.
* test(touchfiles): moved PTY modules keep their paid-eval selection
test/fixtures/touchfile-selection/w4-pty.json records, at 96764e8, the paid
evals selected by touching test/helpers/claude-pty-runner.ts (20) and
test/helpers/pty-screen.ts (20). touchfiles.test.ts now asserts every .ts file
under test/helpers/pty/ (and pty/screen.ts for both sources) selects a
superset, reading every golden in that directory so later moves can add one;
a planted-violation case pins the report and its Fix line.
* fix(browse): unexchanged pair setup keys no longer authenticate bearer requests
validateToken accepted a gsk_setup_ key as a bearer on /command, /batch and
/file (found while building the W3 auth matrix). A setup key now only
authenticates the /connect exchange.
* W1: one state-root owner (lib/state-root.ts + bin/gstack-state-root.sh), gstack-paths --explain and fail-stop, parity tests
* W1: guarded migration of every executable state-root site; uninstall deletes only ~/.gstack
Bins, careful/freeze hooks, setup, upgrade migrations, browse/src, design,
ios-qa daemon, lib and scripts resolve the state root through
bin/gstack-state-root.sh (bash) or lib/state-root.ts (TS). Bins source the
twin and stop with a reinstall message when it is missing; hooks source it
and never spawn gstack-paths. browse/src/config.ts and lib/cso/state.ts
delegate to resolveStateRoot. Analytics writers and readers move together
so the usage log stays one file. gstack-uninstall deletes state only at
~/.gstack, refuses (exit 2) when it resolves to /, $HOME or an ancestor,
the checkout or the git root, and leaves any other resolved root in place
with the removal command. Fixtures that copy single bins now copy the twin.
* W1: privacy keys and trust-policy deny tiers merge across state roots; gstack-config reporting; test hermeticity
readConfigKey / gstack_read_config_key return the most restrictive
telemetry, memorable_recall, codex_reviews and update_check across the
resolved root and ~/.gstack; other keys read the resolved root only.
gstack-config set reports an overriding root with the exact override
command, list shows the winning root and a root-variable disagreement line.
gstack-gbrain-repo-policy get merges deny/read-only tiers. gstack-egress
reads through readConfigKey. test-setup.ts strips inherited
GSTACK_STATE_ROOT/GSTACK_STATE_DIR and redirects the legacy root.
* W1: shared hook logging helper (hosts/claude/hooks/hook-log.ts)
One hook-errors.log writer: root from resolveStateRoot, 0600 on every
append, opt-in rate limit used only by memorable-user-prompt. The five
hooks route through it.
* W1: docs/state-root.md and README troubleshooting pointer
Precedence table, a real --explain example, the move-your-state recipe,
merged privacy keys, the uninstall rule, the resolver-failure fix, and the
plugin-mode note (evidence gate: no official plugin distribution).
* W1b: template and resolver prose resolve state through guarded gstack-paths; ratchet (a)
Every gstack-paths eval in templates and resolvers carries the fail-stop
guard; executable ~/.gstack paths in bash blocks (context recovery preamble,
eureka log, analytics, project artifacts, upgrade snooze, setup-gbrain lock,
retro snapshots, ship consent marker) use $GSTACK_STATE_ROOT, and the writer
prose that pairs with them points at the printed PROJECT_DIR / RETRO_FILE.
ship drops export GSTACK_STATE_ROOT. SKILL.md regenerated (claude + codex),
ship goldens re-pinned, parity and context-budget caps raised to the measured
sizes with notes. test/state-root-ratchet.test.ts enforces the rule with a
reasoned allowlist; W1 touchfile entries plus a superset golden.
* refactor: apply W1 state-root edits in W2/W3/W5-owned files; one moved-code touchfile golden for all workstreams
* test: fold the moved-code touchfile golden into touchfiles.test.ts; fix integration fixture closure and caps
* v1.91.11.0: CHANGELOG, TODOS, docs and conventions for the refactor wave
* test: re-measure plan-ceo/design-consultation caps and ship goldens after the guarded plan-discovery and spec-review blocks; add the state-root twin to the workflow-boundaries fixture
* fix(windows): migrations resolve their directory with either path separator; state-root parity compares under the HOME Git Bash actually sees
* fix(review,ship): state plan-check timing after smoke expiry and test_stub Skip semantics (review workflow judge clarity)
* test(qa-eval): webhook fix eval asks for the fix loop's post-repair probes; eight-scenario coverage stays in the report-only case and the harness recheck
* test(qa-eval): re-pin the webhook prompt contract to the fix-loop stage; R29 coverage omissions stay bound by the report-only case
* fix(review,ship): plan checks publish a checkpoint before each probe; only the smoke expiry stop is skipped
* fix(qa): carry #2999's checkpoint receipt link, report-template line and full-revision placeholder (identical hunks)
* test(qa-callers): disable git auto maintenance in the caller fixture
Git 2.47+ runs auto maintenance detached after commit; on the CI runner's git
2.55 it rewrote .git/objects fan-out directories while the write observer was
running, which surfaced as unauthorized mutations. Same gc.auto=0 /
maintenance.auto=false guard the shared-libs fixture already uses.
* test(plan-mode-no-op): require prose evidence for the prose-fallback members so a spinner-frame judge verdict cannot end the run as asked
* test(ship-docsync): carry #2999's seeded-attempt docsync harness (identical files)
The doc-sync fault cases replayed attempt 1 before reaching their gate and ran
out of their 285s budget. The fixture now seeds attempt 1 and the parent starts
at the gate under test. Taken byte-identical from origin/capy/audit-fix-wave
(fb526898, e6ac813d, 6ce10ff7, d0c53577, 77cce3be). Local: stale-before,
recovery and late-result 6/6 PASS (97-164s); the whole file 12/12 PASS.
* feat: add shared call-time isConductor() helper
Single source of truth for Conductor host detection in TS consumers
(CONDUCTOR_WORKSPACE_PATH / CONDUCTOR_PORT). Reads the passed env at
call time, not a module-load snapshot, so unit tests can pin the env
inline without Bun --preload (esm-hoist-breaks-env-pin-bootstrap).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: harden question-preference-hook harness against ambient Conductor env
runHook copied all of process.env into the hook subprocess, so running the
suite inside Conductor (CONDUCTOR_WORKSPACE_PATH/PORT set) would leak those
markers. Strip them so the existing cases deterministically characterize
NON-Conductor behavior before the Conductor branch lands. Baseline: 15 pass.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: PreToolUse hook denies AskUserQuestion in Conductor, redirects to prose
Conductor disables native AskUserQuestion and routes through a flaky MCP
variant that returns '[Tool result missing due to internal error]'. The
hook now denies any AUQ call in a Conductor session and instructs the model
to render a prose decision brief instead (transport avoidance, not preference
enforcement) — firing for one-way doors too, with a typed-confirmation
requirement for destructive paths.
Precedence: never-ask auto-decide still wins (user already settled those);
Conductor prose is the fallback for everything else; non-Conductor behavior
is byte-for-byte unchanged. Restructured the per-question loop to compute
eligibility without early-returning so the Conductor branch can run as the
fallback while preserving memoryContext on every exit.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: Conductor renders AskUserQuestion decisions as prose by default
In Conductor, native AskUserQuestion is disabled and the MCP variant is
flaky, so skills now render every decision as a plain-text prose brief the
user answers by typing a letter — proactively, not as a failure reaction.
- Preamble emits CONDUCTOR_SESSION, gated on != headless so eval/CI inside
Conductor still BLOCKs instead of rendering prose to nobody.
- AskUserQuestion Format gains a Conductor-default-prose rule (auto-decide
preferences still apply first; prose decisions log via gstack-question-log
since PostToolUse never fires), a one-way/destructive typed-confirmation
rule, and a typed-reply continuation protocol for split chains.
- Regenerated all SKILL.md + ship golden fixtures; bumped affected carve
skeleton caps to absorb the always-loaded additions.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: deploy the Conductor AskUserQuestion hook (setup + upgrade migration)
The PreToolUse hook only delivers its Conductor-prose guarantee if it's
installed, but setup skips hook registration in non-interactive (conductor/CI)
setups. Two fixes so layer 3 actually deploys:
- setup: treat a Conductor workspace as an implicit opt-in for the PreToolUse
hook on the silent fall-through (never overriding an explicit opt-out).
- migration v1.58.0.0: re-register the hook for existing Conductor installs on
/gstack-upgrade, idempotent and respecting plan_tune_hooks=no.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: E2E for Conductor prose + fix auto-decide-preserved GSTACK_HOME bug
- New skill-e2e-conductor-prose (periodic): Conductor env + plan-eng-review
surfaces a prose decision brief, not a silent skip. Header documents this is
end-to-end behavior coverage; the deterministic Conductor guard is the
question-preference-hook unit test (the PTY harness can't register the MCP
variant — Codex #10).
- Fix the pre-existing bug in auto-decide-preserved: it seeded the never-ask
preference under GSTACK_HOME=tmpHome but never passed GSTACK_HOME into the
PTY run, so the spawned claude read the real ~/.gstack and the preference
was inert (Codex #9). Now passes GSTACK_HOME + CONDUCTOR_WORKSPACE_PATH to
prove auto-decide still wins over the Conductor prose redirect.
- Register both in touchfiles (periodic tier).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* v1.58.0.0 feat: Conductor renders AskUserQuestion decisions as prose
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: strip ambient Conductor env in memory-cache-injection hook harness
Same dev-in-Conductor leak fixed for question-preference-hook: this suite's
runHook copies process.env, so running it inside Conductor flipped the
defer-path memoryContext assertions into the [conductor] prose deny. Strip
CONDUCTOR_* so the cases characterize non-Conductor behavior. (CI is headless,
so this only bit local Conductor runs.)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: gstack-detach — run agent eval/bench jobs in their own session
Long agent-run jobs (30-60 min evals, benchmarks) die when the harness sends
SIGTERM to a background task's process group on turn boundaries / monitor
stops / interruptions (observed: 'script test:gate terminated by signal
SIGTERM'). gstack-detach runs the command in a fresh session (python3
os.setsid, or setsid on Linux, nohup fallback) so a group SIGTERM can't reach
it, and wraps it in caffeinate -i on macOS so idle-sleep can't kill it either.
Returns immediately; caller polls the logfile. Secrets stay in env, never argv.
The guard test pins the contract: the command runs in a different process
group than the caller and outlives the launching shell.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: eval:bg* scripts — detached eval runs for agents
Agent-facing convenience scripts that launch the eval suites through
gstack-detach so a harness SIGTERM can't kill a long run. eval:bg (diff-based),
eval:bg:all, eval:bg:gate, eval:bg:periodic — each returns immediately and
streams to /tmp/gstack-evals.log for polling. The plain test:evals / test:e2e
scripts stay foreground for humans.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: CLAUDE.md — agents must run long evals via gstack-detach
Codifies the detached-execution default: agent-launched eval/benchmark runs go
through bin/gstack-detach (or the eval:bg* scripts) so a harness SIGTERM or
macOS idle-sleep can't kill a 30-60 min run, then poll the log with a
death-aware watcher. Humans keep foreground scripts.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: harden gstack-detach against all four eval-infra killers
The basic bash detach fixed SIGTERM but a real run on a shared dev box hit
three more killers: cross-worktree API saturation (15-way concurrency x a
sibling worktree mass-timed-out the suite), a silent hang (periodic bun died
with no exit marker), and shared-/tmp log contamination (a concurrent
worktree's agent output bled into the log). Rewrite as a portable python3 tool
that bakes in all four fixes:
- fork + setsid: SIGTERM-proof (own session, survives harness polite-quit)
- caffeinate -i on macOS: no idle-sleep death
- --lock NAME (fcntl, machine-wide): concurrent worktrees SERIALIZE instead of
saturating the shared model API
- run-scoped default log (~/.gstack-dev/eval-runs/<label>-<slug>-<branch>-<ts>-<pid>):
no cross-worktree collision/contamination
- --timeout watchdog + a guaranteed '### gstack-detach EXIT=<code> ###' sentinel
on every terminal path: no silent hang, finished-vs-died always detectable
Guard test pins all four: detached pgid differs + outlives launcher, run-scoped
log path, watchdog EXIT=timeout, and lock serialization (second run WAITS).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: eval:bg* use run-scoped logs + machine lock + watchdog
Drop the shared /tmp/gstack-evals.log path (the cross-worktree collision that
contaminated a live run) for gstack-detach's run-scoped default, and add the
machine-wide gstack-evals lock (concurrent worktrees serialize, no API
saturation) plus per-tier watchdog timeouts (60/90/120 min). Each eval:bg*
prints its run-scoped log path to poll.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: wire detached-eval guidance into /ship + correct CLAUDE.md flags
- /ship eval step (sections/tests.md): long eval suites launch via gstack-detach
(own session, machine lock, EXIT sentinel) so a turn boundary can't kill a
30+ min run mid-ship — the exact failure observed during this branch's ship.
- CLAUDE.md: correct the now-stale /tmp reference; document the --lock (serialize
worktrees, no API saturation), --timeout watchdog, run-scoped log, and the
guaranteed EXIT sentinel the poller breaks on.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* refactor: extract pure promotedEnv() from conductor-env-shim
Single source of truth for GSTACK_* key promotion semantics. The ambient
promoteConductorEnv() becomes a wrapper; behavior-preserving. Needed by the
hermetic env builder which must not mutate process.env.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: hermetic child-env builder for E2E runners
Allowlist scrub (basics/network/named-auth kept; CONDUCTOR_*, CLAUDE_*,
GSTACK_*, MCP_*, GBRAIN_*, operator credentials dropped), per-runner
extraAllow, overrides merge last, EVALS_HERMETIC=0 byte-identical escape
hatch read at call time (ESM-hoist safe). Sync memoized singleton temp dirs
(<runRoot>/.claude keeps the extractPlanFilePath contract), seeded
.claude.json for non-interactive first run, pid-aware GC of crashed runs.
19 free unit tests.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: session-runner spawns hermetic children + isolation canaries
claude -p children now get the allowlist-scrubbed env and a gated
--strict-mcp-config (EVALS_HERMETIC=0 restores operator env AND args).
Two gate-tier canaries make the clean room falsifiable: hermetic-canary
asserts env redirect + scrub + zero MCP servers + nonzero API-key cost
from the Bash tool_result (never model prose); hermetic-sentinel plants a
poisoned operator config (user CLAUDE.md + MCP server) and proves the
child cannot see it. Empirically verified on claude 2.1.175: print mode
needs no seed config (the seed serves the PTY path); the child CLI sets
CLAUDECODE for its own tools, so that scrub is pinned in unit tests, not
E2E. hermetic-env.ts joins GLOBAL_TOUCHFILES.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: PTY runner spawns hermetic claude sessions
launchClaudePty children get the allowlist-scrubbed env, a gated
--strict-mcp-config, and the session exposes hermeticConfigDir for
forensics (hermetic plan files live under <dir>/plans/ and still match
extractPlanFilePath via the /.claude dir-name contract). Seeded trust
state covers repo-cwd sessions; the 15s trust-watcher stays as fallback.
Verified foreground via the plan-mode-no-op gate test.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: codex/gemini runners spawn hermetic children
Same allowlist scrub as the claude runners, with each provider's auth
surface re-admitted via extraAllow (codex: OPENAI_API_KEY/CODEX_* plus
its tempHome .codex copy; gemini: GEMINI_*/GOOGLE_* with real HOME for
~/.gemini auth). The gemini spawn previously inherited the full operator
env with no env property at all.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat: agent-sdk-runner spawns hermetic children via complete Options.env
The historical 'env: breaks SDK auth' failure was partial-env replacement:
Options.env replaces the child's entire environment, so objects lacking
ANTHROPIC_API_KEY killed auth. Passing the complete hermetic env (key +
PATH + redirected CLAUDE_CONFIG_DIR/GSTACK_HOME) works — validated live
via query() with a Bash tool call (success, real cost, Conductor vars
scrubbed). Per-test opts.env merges last; ambient key mutation still
works because the builder reads process.env at call time.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: static tripwire pins hermetic wiring in all five runners
Free-tier invariants: every runner builds child env via hermeticChildEnv,
no raw ...process.env spread at any spawn site, --strict-mcp-config gated
on isHermeticEnabled in both claude runners, and no test callsite passes
the operator env into a runner's override parameter (scoped to runner
calls — unit tests spawning gstack bin scripts directly are exempt).
Mirrors the terminal-agent-pid-identity / server-embedder-terminal-port
tripwire idiom.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test: refresh codex/factory ship goldens with detached-eval block
a38089aa added the gstack-detach guidance to the ship template and
updated the claude golden; the codex and factory goldens missed the same
16-line block. Regenerated via bun run gen:skill-docs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: hermetic local E2E is the default; retire stale SDK env warning
CLAUDE.md now documents the hermetic clean room (allowlist scrub, fresh
seeded CLAUDE_CONFIG_DIR, temp GSTACK_HOME, --strict-mcp-config),
EVALS_HERMETIC=0 as the debug escape hatch, and replaces the 'never pass
env: to runAgentSdkTest' rule with the verified mechanism (partial-env
replacement was the failure; complete env is safe).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: operational-learning fixture copies lib/jsonl-store.ts with the bin
gstack-learnings-log imports $SCRIPT_DIR/../lib/jsonl-store.ts (hasInjection,
v1.57.5.0) — copying only the bin scripts into the temp fixture broke the
script with exit 1 since then. Latent because diff-based selection rarely
runs this test; surfaced when hermetic-env.ts joined GLOBAL_TOUCHFILES and
selected everything. Reproduced outside the hermetic env to confirm blame.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: ios-qa daemon scenarios use unique pidfiles under --concurrent
All scenarios shared join(workDir, 'daemon.pid') through a module-scope
workDir binding that beforeEach reassigns mid-flight under bun --concurrent.
First daemon claims; siblings get already_running against the test process's
own always-alive pid and fail in milliseconds — the failure mode seen at
15-way gate concurrency. Per-claim unique pidfiles keep the single-instance
semantics under test.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: workflow judge re-appends body-carved sections after the marker slice
runWorkflowJudge appended sections/*.md before slicing startMarker..endMarker.
That handles skills that moved their MARKERS into sections (plan-eng,
plan-design) but not document-release, which keeps its markers in the
skeleton and carved the workflow BODY (Steps 2-9 -> sections/release-body.md)
AFTER the endMarker — so the slice dropped it and the judge scored
completeness 2 ('Steps 2-9 are in an external file'). Now any carved section
the marker window excluded is re-appended, so the judge sees the full
workflow the agent executes. document-release: completeness 2->5, clarity
3->4. ship/plan-ceo/plan-eng/plan-design judges unchanged (their section
content is already inside the slice, so the head-dedup skips re-append).
Pre-existing since the v1.57.0.0 carve (#1907); surfaced now because
hermetic-env.ts is a global touchfile that selects every llm-judge test.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* harden: hermetic temp-dir GC grace window + half-seed cleanup
Codex adversarial review (ship) flagged two temp-dir lifecycle edges:
- GC deleted any dead-pid dir; PID reuse could delete a freshly-created dir
whose original pid exited and was recycled to a live process. Now requires
BOTH a dead pid AND mtime older than a 1h floor.
- A seed-write failure after mkdir left an unseeded dir named with our live
pid that this process's GC skips, leaking until exit. Now the partial dir
is torn down before the (still loud) rethrow.
Two findings left as-is by design: HOME stays allowlisted (CLAUDE_CONFIG_DIR
wins for claude; codex/gemini need ~/.codex|~/.gemini auth; FS sandbox is
TODOS.md:454 scope; the hermetic-sentinel canary proves config isolation),
and PTY extraArgs --mcp-config is a deliberate caller opt-in like env overrides.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: document hermetic-by-default E2E + eval:bg detached runs in CONTRIBUTING
The Testing & evals section now tells contributors that local E2E runners
spawn children through a sealed clean room (allowlist-scrubbed env, seeded
CLAUDE_CONFIG_DIR, temp GSTACK_HOME, --strict-mcp-config) so local signal
matches CI, with EVALS_HERMETIC=0 as the escape hatch. The eval-tools list
gains the eval:bg* detached-run scripts (gstack-detach: SIGTERM-proof,
caffeinate-wrapped, machine-locked, run-scoped logs, EXIT= sentinel).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore: sync package.json to 1.58.1.0
The merge took main's package.json (1.58.0.0); gstack-version-bump repair
fixed the working tree but the change was left uncommitted. Without this the
committed tree disagrees with VERSION and CI's version-match test fails.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: regenerate diagram SKILL.md with Conductor prose preamble
The diagram skill (new from main) was missing the Conductor-session prose
AskUserQuestion blocks that gen-skill-docs propagates to every SKILL.md.
Pure generated output; reproduced by bun run gen:skill-docs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Garry Tan