mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 22:14:25 +01:00
Garry Tanandcapy-ai[bot]
9cf105ccff
* feat(evals): Opus 5.5 is the paid gate's model under test; judge stays Fable (GSTA-49 TM1) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.140.0 chore: stamp TM1 (Opus 5.5 model under test) and CHANGELOG Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(evals): Codex host adapter, real Codex cost, two-arm weekly and monthly census (GSTA-49 TM2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: TM2 CHANGELOG under [Unreleased]; re-pin codex-host-runner in the harness manifest after the main merge Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci: retrigger PR workflows (base changed to main after open; no pull_request run fired) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.149.0 chore: stamp TM2 (Codex host, census arms) and CHANGELOG 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>
56 lines
7.8 KiB
JSON
56 lines
7.8 KiB
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":"95e1798e7e2495ace350d2624e59f83412f341bc","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-report.ts": {"blob":"f92c6bb723b158e328aa040fa5de6a0ee6d3916d","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/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":6},
|
|
"scripts/lib/shard-engine.ts": {"blob":"3cd0b1aaa84018b00bf9ea0ce48093f3c8492f66","since":6},
|
|
"scripts/test-paid-shards.ts": {"blob":"19c9b2376d09090aee1a8acacfe721d66f55b0fc","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/test-pr-profile.ts": {"blob":"579ca1bbd590f709c1ea3d6f28fa6c629688c79f","since":6,"nonBehavioral":"Classifies scripts/free-test-seed-allowlist.json as free-only; only the free seed ratchet reads it, so no verdict can change"},
|
|
"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":"20cc5894532873aa6145fc6617fdeec8cef94a2d","since":6},
|
|
"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":"ed8721f13d39f4ef62e0a1d814efbe9352da781a","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/hermetic-env.ts": {"blob":"cc072895461dc52ea317d1beff72121342420d30","since":6},
|
|
"test/helpers/llm-judge.ts": {"blob":"d0bc6bbbe9f478603d11a1ece95e66c812ad34e6","since":6},
|
|
"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":"53eb76e57c0558c00254366d6334a1c833126575","since":6},
|
|
"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":"884d1008b3349e8b16d6c38f9f0aa7ae514f0f37","since":6},
|
|
"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":"57fa44c31300754b00473276cf7b972d4e9e47d8","since":6},
|
|
"test/helpers/pty/runners/observation.ts": {"blob":"1c2b75fbb984708725abaa8939125f7cab969f9f","since":6},
|
|
"test/helpers/pty/screen.ts": {"blob":"ba7a80bb68b1959296ab2a827cfacdaa46f4ba2d","since":6},
|
|
"test/helpers/pty/session.ts": {"blob":"58533cea9d81cc87bb3b499bdfe0db8e3a8709c5","since":6},
|
|
"test/helpers/session-drain-policy.ts": {"blob":"6211239dd0485e6495a700b824a7e0e61d1bcd97","since":6},
|
|
"test/helpers/session-ledger.ts": {"blob":"425323284a368f5e77937e03884db4dea4e6134e","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/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":"b188064594eb4201a54a80ba1bc6f28e31d7f49e","since":6},
|
|
"test/helpers/test-selection.ts": {"blob":"51655f89f66be7a5ec487e2abfe4744300ebd5f6","since":6},
|
|
"test/helpers/touchfiles.ts": {"blob":"15f369056d41b9dc42dcd86f81f60c878074704c","since":6}
|
|
}
|
|
}
|