gstack/scripts/harness-version.json

{
  "version": 6,
  "patterns": [
    "test/helpers/agent-sdk-runner.ts",
    "test/helpers/codex-session-runner.ts",
    "test/helpers/codex-host-runner.ts",
    "test/helpers/claude-pty-runner.ts",
    "test/helpers/pty/**",
    "test/helpers/pty-screen.ts",
    "test/helpers/e2e-gate.ts",
    "test/helpers/llm-judge.ts"
  ],
  "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":"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, so a red whose record says infra or timeout is classed by that record (INFRA instead of VERDICT: rerun and bisect eligibility, not a pass rate); no case's outcome or selection changes and pass rates count outcomes only, 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"},
    "scripts/test-pr-profile.ts": {"blob":"a80de69f1923afed67127640d68c99e1a8528c5b","since":6,"nonBehavioral":"classify the new weekly-release.yml workflow and scripts/release-cut.ts as free-lane only PR files: the release cut runs on a cron and manual dispatch after merge and inside no case, so no case's selection on a PR, input or verdict changes"},
    "scripts/test-strict-output.ts": {"blob":"01185d20dc9761b04b9b2f751ec98664fe0eaf93","since":6},
    "test/helpers/agent-sdk-runner.ts": {"blob":"210bba92d241a90df578b2c7fc943ac5755d0025","since":6},
    "test/helpers/auq-substance-panel.ts": {"blob":"4881260ef793668e4963a062db6d06a5e1f7a40f","since":6},
    "test/helpers/claude-pty-runner.ts": {"blob":"ce7a5eaa66e502a052ea9c53348dd2ab25db6148","since":6,"nonBehavioral":"Removes the plan-design 0D focus picker from the shared harness; floor.ts gains an optional pickSetupChoice hook that no other caller passes, so no other case's input or verdict can change. plan-design-finding-floor, the only case whose seed raises that menu, passes the picker from its owned fixture test/fixtures/design-floor-focus-picker.ts, so its owned bytes start its own new series."},
    "test/helpers/codex-host-runner.ts": {"blob":"bff225017e235f0be6ece29f04971ac04b95b544","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"},
    "test/helpers/codex-session-runner.ts": {"blob":"c040ebbfa815b8cce19ef80c6133bd5a5474149a","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"},
    "test/helpers/e2e-gate.ts": {"blob":"efb7e197dd5f66c3ad0e34074b14e640754f7a45","since":6},
    "test/helpers/e2e-helpers.ts": {"blob":"6ee6937e6c3ca081c77131b5a755278c7b714834","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"},
    "test/helpers/eval-budgets.ts": {"blob":"667d0e09b20fe5d7366f57b77b5fb9b04baa37ef","since":6},
    "test/helpers/eval-store.ts": {"blob":"a50ea2c28f508ad9f35ea9353dd2f502ee0dcfc2","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"},
    "test/helpers/hermetic-env.ts": {"blob":"cc072895461dc52ea317d1beff72121342420d30","since":6},
    "test/helpers/llm-judge.ts": {"blob":"a3177665b662932ce485ccc976c2b36a1531a0bb","since":6,"nonBehavioral":"callJudge rewrites only the message of a JSON parse failure (names the judge output, stop reason, length and the retained llm-judge-response-parse-error event); it still throws a SyntaxError before any score is parsed, the request is unchanged, and no case's pass or fail changes"},
    "test/helpers/paid-test-set.ts": {"blob":"ff9bfe43c43ec2bdd11114f7b8ec7c5736116f75","since":6},
    "test/helpers/pty-screen.ts": {"blob":"4f77569f9ce11f9cee9f347216e468cd7c956820","since":6},
    "test/helpers/pty/auq.ts": {"blob":"16e5ea2bb5b9f28f44808a1a09024dbd3e6f28c4","since":6},
    "test/helpers/pty/binary.ts": {"blob":"404d7515076d5c00804f89e23ea69296312c00e1","since":6},
    "test/helpers/pty/boundaries.ts": {"blob":"c5520118da36f96f60a3c9720751bb57a669865c","since":6,"nonBehavioral":"Widens the plan-eng-review first-review severity annotation from [P0-3] to [P0-3|CRITICAL|INFORMATIONAL] (#3349). Only a question carrying the new labels can change verdict, and only the changed plan-eng-review prompt asks for them; every case that runs it owns that generated SKILL.md, which this change also edits, so those cases already start their own series. No other case's input or verdict can change."},
    "test/helpers/pty/classify.ts": {"blob":"3f2daa12ff6484f96b8d28d910a50231c4bb3ae8","since":6},
    "test/helpers/pty/fake-session.ts": {"blob":"554e064ef259b8444280eddfe9b0db93c66a8202","since":6},
    "test/helpers/pty/judge.ts": {"blob":"81c5bb4c48ab928aca2f186a1ade9df7169d7fbe","since":6},
    "test/helpers/pty/launch.ts": {"blob":"e4413de380b799659170e7da248d51afda3b0e3f","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"},
    "test/helpers/pty/plan-native.ts": {"blob":"ddba9cb68c7c0da935cff7c1cea258dee2dff740","since":6},
    "test/helpers/pty/runners/counting.ts": {"blob":"8c5c05e54abf961259d34d9c3d77db67138d7794","since":6},
    "test/helpers/pty/runners/floor.ts": {"blob":"54e2145832bb98913644d10ff303792d67f9362e","since":6,"nonBehavioral":"Removes the plan-design 0D focus picker from the shared harness; floor.ts gains an optional pickSetupChoice hook that no other caller passes, so no other case's input or verdict can change. plan-design-finding-floor, the only case whose seed raises that menu, passes the picker from its owned fixture test/fixtures/design-floor-focus-picker.ts, so its owned bytes start its own new series."},
    "test/helpers/pty/runners/observation.ts": {"blob":"1c2b75fbb984708725abaa8939125f7cab969f9f","since":6},
    "test/helpers/pty/screen.ts": {"blob":"f3743152fc9bb7a8e8c70002f75bf45914f260d5","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"},
    "test/helpers/pty/session.ts": {"blob":"54fe04b61d953e4e55e2fc251532c04a49fab66f","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"},
    "test/helpers/session-drain-policy.ts": {"blob":"6211239dd0485e6495a700b824a7e0e61d1bcd97","since":6},
    "test/helpers/session-ledger.ts": {"blob":"a10bf28bf100f135b93c73818670dd147253cdd3","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"},
    "test/helpers/session-runner.ts": {"blob":"cc65a66adafa9c053e3da3c6f17b5ac86c0eade7","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"},
    "test/helpers/skill-fixture.ts": {"blob":"8a654dae6b0a396d839b02179119ae3e3bb13f69","since":6,"nonBehavioral":"extractSkillBody and extractSkillSections follow the shared-preamble hoist (pointer plus sections/preamble.md); every fixture they build is byte-identical to the pre-hoist output (compared for 8 body and 4 section extractions), so no case's input or verdict changes; the /ship review then reworded only comments and two error messages, so no fixture byte changes"},
    "test/helpers/skill-startup.ts": {"blob":"a8d21e3817c3f35a1d06af325c92fde7d420e377","since":6,"nonBehavioral":"readSkillEffective also appends a variant's added ### subsections (office-hours' Open-ended questions); readSkillStartup, readSharedSections and readSkillEffective return bytes identical to the pinned helper for every tier 2+ render without added subsections (735 across all hosts) and for office-hours' SKILL.md before this PR, so office-hours' fixture input changes only because its prompt changed in this PR, not because the helper did"},
    "test/helpers/test-selection.ts": {"blob":"51655f89f66be7a5ec487e2abfe4744300ebd5f6","since":6},
    "test/helpers/touchfiles.ts": {"blob":"15f369056d41b9dc42dcd86f81f60c878074704c","since":6}
  }
}