Garry Tanandcapy-ai[bot] ff65fb0c48 runaway: warm-wait check-ins are not empty wakes (GST-1597) (#4069) ...

* runaway: warm-wait check-ins are not empty wakes (GST-1597)

lib/runaway.ts counted each 240-second warm-wait check-in (docs/captain.md,
#4060) as an empty wake, so /runaway-stopper could flag a lane that follows
the rule. A turn whose only call re-issues the wait on the same operation, or
a 240-second timer, within 30 minutes of the wait that started the run is
now left out of the rate.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fixes

Review-Finding: p1/specialist-batched#1 reader=red-team
Review-Finding: p1/specialist-batched#2 reader=testing
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: note the warm-wait exclusion in the /runaway-stopper summary; rewrap captain.md (GST-1597 docs audit)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* runaway: keep wait input in the skill collector; 240 s timers chain only on the run's operations; status reads keep the warm window (GST-1597)

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>

2026-11-06 13:40:49 +00:00

..

designs

…

evals

test: remove the AI scorer that grades skill prose for clarity (freeze repair, GST-1371) (#4009)

2026-11-04 22:19:08 +00:00

images

…

inventory

docs(inventory): record /review R56 HELPS with its unit and home-field caveats (GST-1370) (#4005)

2026-11-05 00:53:58 +00:00

spikes

…

ADDING_A_HOST.md

feat(hosts): /land-and-deploy and /modernize run only when typed on Claude Code and Cursor (C1) (#3808)

2026-11-04 03:33:48 +00:00

agent-ready-errors.md

…

askuserquestion-cjk.md

…

askuserquestion-split.md

…

autoplan-guard-troubleshooting.md

…

BROWSER_INTERNALS.md

…

captain.md

runaway: warm-wait check-ins are not empty wakes (GST-1597) (#4069)

2026-11-06 13:40:49 +00:00

capy-install.md

fix(ship): a second full preflight stops while this checkout's /ship run is open (GST-1204) (#3950)

2026-11-04 01:32:57 +00:00

CHANGELOG_STYLE.md

feat(release): versions at release under merge: direct (GSTA-258 L2 PR 2) (#3978)

2026-11-04 03:38:56 +00:00

CONTRIBUTOR_REFERENCE.md

feat: /runaway-stopper — detect, stop and prevent runaway threads and subagents (GST-1279) (#3975)

2026-11-04 02:59:50 +00:00

cso-release-qualification.md

…

cso-scanners.md

…

design-lint.md

…

domain-skills.md

…

eval-calls.md

v1.94.3.0 fix(ship-preflight): stop when origin's default branch can't be read (#3718 follow-up) (#3913)

2026-11-03 04:31:44 +00:00

eval-models.md

v1.94.3.0 fix(ship-preflight): stop when origin's default branch can't be read (#3718 follow-up) (#3913)

2026-11-03 04:31:44 +00:00

explanation-diataxis-in-gstack.md

…

flaky.md

…

gbrain-quick-tour.md

…

gbrain-sync-errors.md

…

gbrain-sync.md

…

gbrain-write-surfaces.md

fix(sync-gbrain): point curated-memory search at gstack-artifacts-<user> (#3810)

2026-11-04 03:15:35 +00:00

hosts.md

QM edition: three gstack skills QM loads on demand (GST-1492) (#4049)

2026-11-06 00:38:43 +00:00

howto-bring-up-a-first-deploy.md

…

howto-diagrams-and-formats.md

…

howto-document-a-shipped-feature.md

…

howto-ios-testing-with-gstack.md

v1.91.106.0 fix: the 2026-10-15 issue wave (#3209)

2026-10-16 22:00:32 +00:00

install.md

…

inventory.md

docs(inventory): record /review R56 HELPS with its unit and home-field caveats (GST-1370) (#4005)

2026-11-05 00:53:58 +00:00

loadouts.md

…

memorable-workflow-memory.md

…

model-policy.md

fix(ship): Steps 7 and 8 audits default to the owner's agent_model (GST-1449) (#4042)

2026-11-05 17:12:15 +00:00

ON_THE_LOC_CONTROVERSY.md

…

OPENCLAW_PUBLISHING.md

…

OPENCLAW.md

…

OVERLAY_BENCHMARK_CONTRACT.md

…

pregate.md

ship accept: record-ci bound from base ci_record_timeout_s; say when the final pregate ran tests here (GST-1606) (#4065)

2026-11-06 12:35:40 +00:00

privacy.md

…

proactive.md

…

PROJECT_STRUCTURE.md

test: cut the last two behavior-guessing LLM judges; check review-bot history facts for free (GST-1403) (#4014)

2026-11-05 02:30:04 +00:00

qa-without-a-webpage.md

…

recommended-harness.md

docs: on Capy, comment and request reviews only through tools.pr.comment / tools.pr.edit, never gh (GST-1417 follow-up) (#4027)

2026-11-05 05:16:39 +00:00

reference-qa-deadlines.md

…

releases.md

feat(release): versions at release under merge: direct (GSTA-258 L2 PR 2) (#3978)

2026-11-04 03:38:56 +00:00

REMOTE_BROWSER_ACCESS.md

…

review-policy.md

ship finish: FIX_CHECK names the grant that covers the fix-check (GST-1610) (#4070)

2026-11-06 13:06:50 +00:00

ship-budget.md

ship budget: count a Capy /ship helper's calls from the call log (GST-1585) (#4059)

2026-11-06 08:47:50 +00:00

ship-policy.md

ship accept: record-ci bound from base ci_record_timeout_s; say when the final pregate ran tests here (GST-1606) (#4065)

2026-11-06 12:35:40 +00:00

skill-gates.md

fix: skill gate hooks outlive the gate deadline, so a slow gate no longer fails open (#4072)

2026-11-06 13:22:18 +00:00

skill-routing-and-contracts.md

plan-ceo-review gate: hold the final stop until ranked Findings are written (GST-1461) (#4047)

2026-11-05 21:27:04 +00:00

skills.md

runaway: warm-wait check-ins are not empty wakes (GST-1597) (#4069)

2026-11-06 13:40:49 +00:00

SLOP_SCAN.md

…

standalone-binaries.md

v1.94.25.0 gstack-evidence: check a lane under the label it was recorded with (TRUT-7) (#3935)

2026-11-03 16:32:43 +00:00

state-root.md

…

support-tiers.md

docs: agents comment on GitHub only under a bot identity; email, chat and DMs to people stay banned (GST-1417) (#4022)

2026-11-05 04:54:26 +00:00

TEST_PORTFOLIO.md

test: cut the last two behavior-guessing LLM judges; check review-bot history facts for free (GST-1403) (#4014)

2026-11-05 02:30:04 +00:00

test-audit-2026-09.md

…

test-audit-2026-10.md

v1.94.20.0 test(review): one file per review and harness pin, so independent repins merge cleanly (GST-1084) (#3903)

2026-11-03 15:04:56 +00:00

test-impact.md

test-impact: tracer and reuse keys for free tests; pregate keeps main's always-run list (GST-167 PR 2, GST-233) (#3801)

2026-11-05 00:43:21 +00:00

test-value-bar.md

…

TESTING_INTERNALS.md

paid screens: narrow screens derive setup instead of running the full gate (GST-1575) (#4056)

2026-11-06 06:15:12 +00:00

triage.md

docs: on Capy, comment and request reviews only through tools.pr.comment / tools.pr.edit, never gh (GST-1417 follow-up) (#4027)

2026-11-05 05:16:39 +00:00

troubleshooting.md

ship-receipt write: the targeted record survives a main merge (GST-1593) (#4058)

2026-11-06 10:34:41 +00:00

tutorial-document-generate.md

…

unattended.md

docs: crew lanes keep context cheap (bounded warm waits, lane start card, names-only AGENTS.md index) (#4060)

2026-11-06 07:44:25 +00:00

uninstall.md

…

voice-input.md

…

why-gstack.md

…