From ca543c9dbec6eb40376e361978b6ed0f22698dfa Mon Sep 17 00:00:00 2001 From: garrytan Date: Mon, 26 Oct 2026 15:17:49 +0000 Subject: [PATCH] fix(ci): record the paid-report.ts harness decision and keep ship-queue-train-cost.test.ts off the Windows subset scripts/lib/paid-report.ts is a pinned shared-harness file, so test/harness-version.test.ts wants a HARNESS_VERSION decision for its edit: non-behavioral, because a case shard's records are attributed to its one case for the trial's cost, class and error fields while no case's outcome, panel verdict or selection changes. test/ship-queue-train-cost.test.ts drives bin/gstack-ship-queue against the #!/bin/sh gh shim, which windows-latest cannot run (windows-free-shard 2 on #3478 at d5e6a7d), so it joins test/ship-queue-train.test.ts in the Windows exclusion list. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- scripts/harness-version.json | 2 +- scripts/lib/windows-curation.ts | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/scripts/harness-version.json b/scripts/harness-version.json index 0b7da8b49..368d96421 100644 --- a/scripts/harness-version.json +++ b/scripts/harness-version.json @@ -13,7 +13,7 @@ "files": { "scripts/lib/paid-cases.ts": {"blob":"f862cf5241580c7593b9ee62eacf5ef046248d26","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, "scripts/lib/paid-plan.ts": {"blob":"e8ce3cb98474dded38c5128a631d283b0ca35b63","since":6,"nonBehavioral":"F1 rule-16 flaky rerun: report aggregation, rerun planning and the gate slice exit code; no case's execution, trial outcome, trial record or panel verdict changes, so no pass-rate series resets"}, - "scripts/lib/paid-report.ts": {"blob":"19a87cb02bb3cd0f57da7719a5c30b7a4df81b2b","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, + "scripts/lib/paid-report.ts": {"blob":"224dc5e8ba23a3589a37bad94db72ed1ca3c7c77","since":6,"nonBehavioral":"a case shard's result records are attributed to its one case: the trial's cost_usd and cost_known come from them, and a failed trial's failure_class, exit_reason and error come from its record instead of a bare assertion with the JUnit message; no case's outcome, panel verdict or selection changes, so no pass-rate series resets"}, "scripts/lib/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":6}, "scripts/lib/shard-engine.ts": {"blob":"dc714d7d897aed185c0ec3d2c92ad22d954039e5","since":6,"nonBehavioral":"createShardSandbox drops the Capy launch markers (GSTACK_SESSION_KIND, GSTACK_CAPY, GSTACK_EPHEMERAL, GSTACK_INSTALL_VERDICT) from shard environments; CI never sets them, so no case's input or verdict changes there, and on a Capy machine fixtures now see the session kind they set themselves instead of the installer's"}, "scripts/test-paid-shards.ts": {"blob":"5439d0a8f6e1569fa7c924af20d67c30c81d5d30","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, diff --git a/scripts/lib/windows-curation.ts b/scripts/lib/windows-curation.ts index fe98f272f..e3d582379 100644 --- a/scripts/lib/windows-curation.ts +++ b/scripts/lib/windows-curation.ts @@ -287,6 +287,10 @@ export const KNOWN_WINDOWS_INCOMPATIBLE: Array<{ file: string; reason: string }> file: 'test/ship-queue-train.test.ts', reason: 'drives bin/gstack-ship-queue against the stateful #!/bin/sh gh shim in test/helpers/ship-queue-train-fixture.ts; on windows-latest spawnSync(\'gh\') resolves the runner\'s gh.exe instead of the shim (windows-free-shard run 39152702056)', }, + { + file: 'test/ship-queue-train-cost.test.ts', + reason: 'drives bin/gstack-ship-queue train verdict against the same #!/bin/sh gh shim in test/helpers/ship-queue-train-fixture.ts; on windows-latest spawnSync(\'gh\') resolves the runner\'s gh.exe instead of the shim (windows-free-shard 2 on #3478 at d5e6a7d)', + }, { file: 'test/ship-policy-compat.test.ts', reason: 'spawns bin/gstack-ship-policy, bin/gstack-restamp and bin/gstack-tree-receipt (shebangs) through test/helpers/restamp-fixture.ts',