mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-06 00:44:07 +01:00
Merge remote-tracking branch 'origin/main' into capy/tm2-codex-host
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> # Conflicts: # CHANGELOG.md # VERSION # agents-digest/gstack-AGENTS.md # package.json # scripts/harness-version.json
This commit is contained in:
garrytan committed
commit
39b2148c93
63 files changed
+5330
-200
No files matched your search
@@ -180,7 +180,7 @@ function emptyArtifactInventory(): ProducerArtifactInventory {
|
||||
}
|
||||
|
||||
/** A whole path component that is one of the helper's own identifiers: `<epoch ms>-<hex>` run and replay IDs, retired runs, hex artifact IDs with an optional lowercase-word prefix (`gitleaks-<hex>-<hex>.json`), and dependency-closure files (`<finding id>-before|after-<plan hash>.json`). */
|
||||
const HELPER_ID_COMPONENT = /^(?:\d{13}-[a-f0-9]{16}|\.retired-\d{13}-[a-f0-9]{16}-[a-f0-9]{32}|(?:[a-z]+-)*[a-f0-9]{16,64}(?:-[a-f0-9]{16})*(?:\.[a-z]+)?|[a-f0-9]{64}-(?:before|after)-[a-f0-9]{16}\.json)$/;
|
||||
const HELPER_ID_COMPONENT = /^(?:\d{13}-[a-f0-9]{16}|\.retired-\d{13}-[a-f0-9]{16}-[a-f0-9]{32}|(?:[a-z]+-)*[a-f0-9]{16,64}(?:-[a-f0-9]{16})*(?:\.[a-z]+)?|(?:[a-f0-9]{32}){1,2}-(?:before|after)-[a-f0-9]{16}\.json)$/;
|
||||
|
||||
/**
|
||||
* Helper artifact paths are `<repoId>/<runId>/...` plus the helper's public-cache/ and legacy-imports/. Components that
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
"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",
|
||||
@@ -11,23 +10,22 @@
|
||||
"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) 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) 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) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
|
||||
"scripts/lib/paid-cases.ts": {"blob":"9bacd52446192a7ecf3dfaae901ea443cf9c9ae2","since":6},
|
||||
"scripts/lib/paid-plan.ts": {"blob":"45721ce128a112666a0caed6c13c66637b74ca54","since":6},
|
||||
"scripts/lib/paid-report.ts": {"blob":"b66c41237611ccecaaa7bd6a4d7b7aac8dc548cd","since":6},
|
||||
"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) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
|
||||
"scripts/test-paid-shards.ts": {"blob":"8ddee5f11ed7856876135520dd8025ab989e2db9","since":6},
|
||||
"scripts/test-pr-profile.ts": {"blob":"2029a89e14f511866cc91bebfee00b4fe9e7cf63","since":6},
|
||||
"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/codex-session-runner.ts": {"blob":"4eea35931a35a0afb006363402e3d4191e379737","since":6},
|
||||
"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) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
|
||||
"test/helpers/e2e-helpers.ts": {"blob":"2d4a2a53063cfc1f003db366d2c861ab1e379e6e","since":6},
|
||||
"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) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
|
||||
"test/helpers/eval-store.ts": {"blob":"609c6d099108ff2696eb014b47aa318a618dd2af","since":6},
|
||||
"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},
|
||||
@@ -41,13 +39,13 @@
|
||||
"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":"6faa013d55901f59ae7b7d1ef6f3a9ee6c9a3034","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) 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) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
|
||||
"test/helpers/session-ledger.ts": {"blob":"6e3c9e837e46f98addba2d12eaebff802da320bb","since":6},
|
||||
"test/helpers/session-runner.ts": {"blob":"d40eb29e8b8fdc0675b511693e4a90823b5963fc","since":6},
|
||||
"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}
|
||||
|
||||
@@ -226,7 +226,6 @@
|
||||
"test/helpers/hermetic-env.test.ts\tTS7053\tElement implicitly has an 'any' type because expression of type 'string' can't be used to index type '{ ... 6 more ...; EVALS_SELECTION_JSON: string; GITHUB_APP_PRIVATE_KEY: string; GITHUB_CLIENT_SECRET: string; GITHUB_PAT: string; GITHUB_PERSONAL_ACCESS_TOKEN: string; GITHUB_TOKEN: string; NODE_ENV?: string | undefined; TZ?: string | undefined; }'. No index signature with a parameter of type 'string' was found on type '{ ... 6 more ...; EVALS_SELECTION_JSON: string; GITHUB_APP_PRIVATE_KEY: string; GITHUB_CLIENT_SECRET: string; GITHUB_PAT: string; GITHUB_PERSONAL_ACCESS_TOKEN: string; GITHUB_TOKEN: string; NODE_ENV?: string | undefined; TZ?: string | undefined; }'.": 1,
|
||||
"test/helpers/office-hours-completion.ts\tTS18047\t'disposition' is possibly 'null'.": 2,
|
||||
"test/helpers/plan-count-file-permission.ts\tTS18048\t'event.input' is possibly 'undefined'.": 3,
|
||||
"test/helpers/plan-count-file-permission.ts\tTS18048\t'input' is possibly 'undefined'.": 12,
|
||||
"test/helpers/plan-review-decisions.ts\tTS2339\tProperty 'questions' does not exist on type 'AskUserQuestionFingerprint'.": 4,
|
||||
"test/helpers/plan-review-decisions.ts\tTS2339\tProperty 'selectedOptions' does not exist on type 'AskUserQuestionFingerprint'.": 4,
|
||||
"test/helpers/plan-review-decisions.ts\tTS2339\tProperty 'toolUseId' does not exist on type 'AskUserQuestionFingerprint'.": 8,
|
||||
|
||||
Reference in new issue
Block a user