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":"e0d18da4ea02ac443835a68992abeea2b47f22fc","since":6,"nonBehavioral":"the headline adds only streamed session cost; a billed session's cost is already in its collector total; cache writes without a 5m key fall back to the total minus 1h; cost fields only"},
    "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":"dd0ca92bcf8493fd5c1e9d399cc3bc74ec70c469","since":6,"nonBehavioral":"FREE_ONLY_PR_FILES gains USING_GBRAIN_WITH_GSTACK.md (a root guide no skill prompt or paid fixture reads); it changes only which PR paths select paid cases, never how a case runs or is judged (GST-1027)"},
    "scripts/test-strict-output.ts": {"blob":"01185d20dc9761b04b9b2f751ec98664fe0eaf93","since":6},
    "test/helpers/agent-sdk-runner.ts": {"blob":"d66dac458b8c13250973e550edf8087d4044cd0b","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets. Also: runAgentSdkTest now validates systemPrompt before starting; every live caller already passed the claude_code preset, so the prompt the model sees is unchanged and no verdict can change"},
    "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":"91996ff2bc303ee29f4e6f1705d1468b2536b32e","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets"},
    "test/helpers/eval-budgets.ts": {"blob":"667d0e09b20fe5d7366f57b77b5fb9b04baa37ef","since":6},
    "test/helpers/eval-store.ts": {"blob":"4085ad18cd99698f675deadad2a76a796427b693","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets"},
    "test/helpers/hermetic-env.ts": {"blob":"cc072895461dc52ea317d1beff72121342420d30","since":6},
    "test/helpers/llm-judge.ts": {"blob":"ff32d03f32e4af76c6c7314a79cd1b35263ed0dd","since":6,"nonBehavioral":"llm-judge.ts adds a pass-through byte counter (bytesReceived, lastByteMs) to the aborted-judge diagnostic; the request, response bytes, deadline and scoring are unchanged. GSTA-224 B2 (#3122): skill-fixture.ts follows review's renamed Step 2.5 heading so the review E2E cases extract the same section (now the skill's own reworded bytes); llm-judge.ts changes one bullet of the cross-skill consistency judge's intended architecture to name review-bot-history.md beside the older greptile-history.md name, so its calibration corpus (greptile-history inputs) stays valid. No other case's input or verdict can change; the cross-skill judge's judged files changed in this PR, so its owned inputs start its own series"},
    "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":"c09b69611fb22ddf093adb2baa83434494e5f8fa","since":6,"nonBehavioral":"Widens the two plan-eng-review boundary predicates' qid regex to also accept the optional ;signal=<key> hint suffix (#3442). Only a question carrying that suffix can change verdict, and only the changed question-tuning resolver asks for it; every case that runs a skill with that resolver owns its 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":"4f0731ef39bc3a6a7c5c592ce98690a24cb1ed7f","since":6,"nonBehavioral":"PTY transcript pricing finds the session by the caller's --session-id or the one new transcript for the launch cwd; the launcher adds no argument; native AUQ capture opts out; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"},
    "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":"a9938cb98f285474ebc4860cd61012504a36466e","since":6,"nonBehavioral":"The PTY floor and observation runners end a plan-mode turn at an idle prompt (the plan-mode footer without its running 'esc to interrupt' segment, after a 10 s settle) instead of waiting out the deadline. The floor runner exits as api_error only after the idle screen with its error panel held still for 10 s and every tick's question and assessment steps found nothing to credit (the transcript is re-read each tick), so a native or prose question already on screen is credited as before, even when its transcript line lands after the screen draws done (test/helpers/claude-pty-runner.runners.unit.test.ts, the prose-question-before-panel case). With no qualifying question an idle turn stays idle, so a trial that failed at the deadline as observer_timeout now fails earlier as api_error. An observation returns what the deadline would have returned. A running footer, extra footer text and a cut footer still wait for the deadline. No pass becomes a fail or a fail a pass. The session ledger may now record failure_cause api_error or refusal instead of observer_timeout or session_timeout for a plan-mode session whose last idle turn shows a panel; failure_class, the gate red class and pass rates are unchanged, so no pass-rate series resets"},
    "test/helpers/pty/runners/observation.ts": {"blob":"1c2b75fbb984708725abaa8939125f7cab969f9f","since":6},
    "test/helpers/pty/screen.ts": {"blob":"1384f765e48e511d5f843df2660b2ec70bbcb6b2","since":6,"nonBehavioral":"The PTY floor and observation runners end a plan-mode turn at an idle prompt (the plan-mode footer without its running 'esc to interrupt' segment, after a 10 s settle) instead of waiting out the deadline. The floor runner exits as api_error only after the idle screen with its error panel held still for 10 s and every tick's question and assessment steps found nothing to credit (the transcript is re-read each tick), so a native or prose question already on screen is credited as before, even when its transcript line lands after the screen draws done (test/helpers/claude-pty-runner.runners.unit.test.ts, the prose-question-before-panel case). With no qualifying question an idle turn stays idle, so a trial that failed at the deadline as observer_timeout now fails earlier as api_error. An observation returns what the deadline would have returned. A running footer, extra footer text and a cut footer still wait for the deadline. No pass becomes a fail or a fail a pass. The session ledger may now record failure_cause api_error or refusal instead of observer_timeout or session_timeout for a plan-mode session whose last idle turn shows a panel; failure_class, the gate red class and pass rates are unchanged, so no pass-rate series resets"},
    "test/helpers/pty/session.ts": {"blob":"8fd1749a62f24dc37ae186c8a21c2165f7f7645e","since":6,"nonBehavioral":"PTY sessions price their ledger row (streamed_cost_usd) from the session transcript found by the caller's --session-id or the one new transcript for the launch cwd; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"},
    "test/helpers/pty/transcript-cost.ts": {"blob":"08f7ccbdbd9d71a5dc86edd2f8fced423a78ad9a","since":6,"nonBehavioral":"PTY transcript pricing finds the session by the caller's --session-id or the one new transcript for the launch cwd; the launcher adds no argument; native AUQ capture opts out; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"},
    "test/helpers/session-drain-policy.ts": {"blob":"6211239dd0485e6495a700b824a7e0e61d1bcd97","since":6},
    "test/helpers/session-ledger.ts": {"blob":"c99baaaa0a77a5a72384493fd8a85a4253ecb05d","since":6,"nonBehavioral":"PTY sessions price their ledger row (streamed_cost_usd) from the session transcript found by the caller's --session-id or the one new transcript for the launch cwd; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"},
    "test/helpers/session-runner.ts": {"blob":"c73b2596d9eb5377530a6bf1d284e0b6ea1556a0","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets"},
    "test/helpers/skill-fixture.ts": {"blob":"ce7609eacc7a8265a4a211358d1b4fb49ea85bc5","since":6,"nonBehavioral":"GSTA-224 B2 (#3122): skill-fixture.ts follows review's renamed Step 2.5 heading ('Check for review bot comments') so the review E2E cases extract the same section, now the skill's own reworded bytes; llm-judge.ts updates only the cross-skill consistency judge's intended architecture to the renamed review-bot-history.md and its record helper. No other case's input or verdict can change; the cross-skill judge's judged files changed in this PR, so its owned inputs start its own new series"},
    "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":"e1b54ad5e3d3eadd8027de1b44e57554d6d99a41","since":6,"nonBehavioral":"selection only: fragment exemption narrowed to .md files directly in the fragments dir; changed-file lists include a rename's old path; no case prompt, fixture, judge or verdict logic changes (GST-400)"},
    "test/helpers/touchfiles.ts": {"blob":"15f369056d41b9dc42dcd86f81f60c878074704c","since":6}
  }
}