Files
gstack/test/fixtures/shard-cli-parity/results.json
Garry Tanandcapy-ai[bot] 95152e3c4c v1.91.163.0 feat(evals): the gate reruns failed cases once and reports a flaky green (GSTA-49 F1) (#3315)
* feat(evals): the gate reruns failed cases once and reports a flaky green (GSTA-49 F1)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* ci: retrigger after retargeting to main

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(evals): a case red twice stays a real red for the report, the run, reuse and the train verdict (GSTA-49 F1)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(evals): keep a lone rerun-plan artifact off the plan manifest (run 39363705692)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* chore: stamp v1.91.163.0

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>
2026-10-20 04:47:11 +00:00

867 lines
19 KiB
JSON

{
"recordedFrom": "96764e80 (pre-engine base runners); paid lane re-recorded at v1.91.12.0 for the marathon tier and the --slice-budget, --max-parallel, --case and --trials flags (PR 2999); free lane re-recorded for the --attribute-home flag (PR 3014) and the --files-from flag (fix wave 3, W2-A3)",
"free": [
{
"argv": [],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--dry-run",
"--list",
"--verbose"
],
"result": {
"ok": {
"dryRun": true,
"filesFrom": null,
"listOnly": true,
"recordDurations": false,
"windowsOnly": false,
"verbose": true,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--windows-only",
"--list"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": true,
"recordDurations": false,
"windowsOnly": true,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--record-durations"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": true,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--quick"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": true,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--shards",
"4",
"--shard",
"2"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 4,
"shardIndex": 2,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--wall-timeout",
"600"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 600000,
"wallTimeoutExplicit": true,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--ci-plan",
"plan.json",
"--shards",
"20"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": "plan.json",
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--ci-run",
"plan.json",
"--shard",
"1",
"--result",
"result.json"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": 1,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": "plan.json",
"ciVerify": null,
"result": "result.json",
"results": null
}
}
},
{
"argv": [
"--ci-verify",
"plan.json",
"--results",
"results"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": false,
"ciPlan": null,
"ciRun": null,
"ciVerify": "plan.json",
"result": null,
"results": "results"
}
}
},
{
"argv": [
"--bogus"
],
"result": {
"error": "Unknown argument: --bogus"
}
},
{
"argv": [
"--list",
"--bogus"
],
"result": {
"error": "Unknown argument: --bogus"
}
},
{
"argv": [
"--shards"
],
"result": {
"error": "Missing value for --shards"
}
},
{
"argv": [
"--shard"
],
"result": {
"error": "Missing value for --shard"
}
},
{
"argv": [
"--wall-timeout",
"0"
],
"result": {
"error": "--wall-timeout needs a positive integer (seconds)"
}
},
{
"argv": [
"--wall-timeout"
],
"result": {
"error": "--wall-timeout needs a positive integer (seconds)"
}
},
{
"argv": [
"--ci-plan"
],
"result": {
"error": "Missing path for --ci-plan"
}
},
{
"argv": [
"--ci-plan",
"--list"
],
"result": {
"error": "Missing path for --ci-plan"
}
},
{
"argv": [
"--ci-plan",
"a.json",
"--ci-run",
"b.json"
],
"result": {
"error": "CI modes cannot be combined with other selection modes"
}
},
{
"argv": [
"--ci-plan",
"a.json",
"--quick"
],
"result": {
"error": "CI modes cannot be combined with other selection modes"
}
},
{
"argv": [
"--ci-run",
"plan.json"
],
"result": {
"error": "--ci-run requires --shard and --result"
}
},
{
"argv": [
"--ci-verify",
"plan.json"
],
"result": {
"error": "--ci-verify requires --results"
}
},
{
"argv": [
"--quick",
"--shard",
"1"
],
"result": {
"error": "--quick cannot change recording, Windows or shard selection"
}
},
{
"argv": [
"--quick",
"--windows-only"
],
"result": {
"error": "--quick cannot change recording, Windows or shard selection"
}
},
{
"argv": [
"--attribute-home"
],
"result": {
"ok": {
"dryRun": false,
"filesFrom": null,
"listOnly": false,
"recordDurations": false,
"windowsOnly": false,
"verbose": false,
"shardCount": 20,
"shardIndex": null,
"wallTimeoutMs": 360000,
"wallTimeoutExplicit": false,
"quick": false,
"attributeHome": true,
"ciPlan": null,
"ciRun": null,
"ciVerify": null,
"result": null,
"results": null
}
}
},
{
"argv": [
"--ci-plan",
"a.json",
"--attribute-home"
],
"result": {
"error": "CI modes cannot be combined with other selection modes"
}
}
],
"paid": [
{
"argv": [],
"result": {
"ok": {
"tier": "gate",
"profile": "full",
"profileExplicit": false,
"listOnly": false,
"skipJudges": false,
"timeoutExplicit": false,
"timeoutMs": 1800000,
"jobs": 8,
"withinShardConcurrency": 2,
"maxFilesPerShard": 1,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": false,
"planPath": null,
"sliceIndex": null,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--list",
"--tier",
"periodic",
"--profile",
"full"
],
"result": {
"ok": {
"tier": "periodic",
"profile": "full",
"profileExplicit": true,
"listOnly": true,
"skipJudges": false,
"timeoutExplicit": false,
"timeoutMs": 1800000,
"jobs": 8,
"withinShardConcurrency": 2,
"maxFilesPerShard": 1,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": false,
"planPath": null,
"sliceIndex": null,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--tier",
"gate",
"--profile",
"pr",
"--list"
],
"result": {
"ok": {
"tier": "gate",
"profile": "pr",
"profileExplicit": true,
"listOnly": true,
"skipJudges": false,
"timeoutExplicit": false,
"timeoutMs": 1800000,
"jobs": 8,
"withinShardConcurrency": 2,
"maxFilesPerShard": 1,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": false,
"planPath": null,
"sliceIndex": null,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--timeout",
"600",
"--jobs",
"2",
"--files-per-shard",
"3"
],
"result": {
"ok": {
"tier": "gate",
"profile": "full",
"profileExplicit": false,
"listOnly": false,
"skipJudges": false,
"timeoutExplicit": true,
"timeoutMs": 600000,
"jobs": 2,
"withinShardConcurrency": 2,
"maxFilesPerShard": 3,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": true,
"planPath": null,
"sliceIndex": null,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--emit-plan",
"manifest.json",
"--slices",
"4",
"--skip-judges"
],
"result": {
"ok": {
"tier": "gate",
"profile": "full",
"profileExplicit": false,
"listOnly": false,
"skipJudges": true,
"timeoutExplicit": false,
"timeoutMs": 1800000,
"jobs": 8,
"withinShardConcurrency": 2,
"maxFilesPerShard": 1,
"emitPlanPath": "manifest.json",
"slices": 4,
"sliceBudgetMs": null,
"jobsExplicit": false,
"planPath": null,
"sliceIndex": null,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--plan",
"manifest.json",
"--slice",
"2"
],
"result": {
"ok": {
"tier": "gate",
"profile": "full",
"profileExplicit": false,
"listOnly": false,
"skipJudges": false,
"timeoutExplicit": false,
"timeoutMs": 1800000,
"jobs": 8,
"withinShardConcurrency": 2,
"maxFilesPerShard": 1,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": false,
"planPath": "manifest.json",
"sliceIndex": 2,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--report",
"reports",
"--write-durations"
],
"result": {
"ok": {
"tier": "gate",
"profile": "full",
"profileExplicit": false,
"listOnly": false,
"skipJudges": false,
"timeoutExplicit": false,
"timeoutMs": 1800000,
"jobs": 8,
"withinShardConcurrency": 2,
"maxFilesPerShard": 1,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": false,
"planPath": null,
"sliceIndex": null,
"reportDir": "reports",
"rerunPlanDir": null,
"writeDurations": true,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [],
"env": {
"EVALS_TIER": "periodic",
"EVALS_JOBS": "3",
"EVALS_CONCURRENCY": "5",
"EVALS_SHARD_TIMEOUT_MS": "1000",
"EVALS_PROFILE": "full"
},
"result": {
"ok": {
"tier": "periodic",
"profile": "full",
"profileExplicit": true,
"listOnly": false,
"skipJudges": false,
"timeoutExplicit": true,
"timeoutMs": 1000,
"jobs": 3,
"withinShardConcurrency": 5,
"maxFilesPerShard": 1,
"emitPlanPath": null,
"slices": 1,
"sliceBudgetMs": null,
"jobsExplicit": true,
"planPath": null,
"sliceIndex": null,
"reportDir": null,
"rerunPlanDir": null,
"writeDurations": false,
"maxParallel": null,
"caseId": null,
"trials": null
}
}
},
{
"argv": [
"--bogus"
],
"result": {
"error": "Unknown argument: --bogus"
}
},
{
"argv": [
"--list",
"--bogus"
],
"result": {
"error": "Unknown argument: --bogus"
}
},
{
"argv": [
"--tier",
"e2e"
],
"result": {
"error": "--tier must be gate, periodic or marathon. Received: e2e"
}
},
{
"argv": [
"--tier"
],
"result": {
"error": "--tier must be gate, periodic or marathon. Received: -"
}
},
{
"argv": [
"--profile"
],
"result": {
"error": "--profile needs pr or full"
}
},
{
"argv": [
"--profile",
"fast"
],
"result": {
"error": "--profile must be pr or full. Received: fast"
}
},
{
"argv": [
"--timeout",
"0"
],
"result": {
"error": "--timeout needs a positive integer. Received: 0"
}
},
{
"argv": [
"--jobs"
],
"result": {
"error": "--jobs needs a positive integer. Received: undefined"
}
},
{
"argv": [
"--emit-plan"
],
"result": {
"error": "--emit-plan needs a file path"
}
},
{
"argv": [
"--plan"
],
"result": {
"error": "--plan needs a manifest path"
}
},
{
"argv": [
"--report"
],
"result": {
"error": "--report needs a directory"
}
},
{
"argv": [
"--write-durations"
],
"result": {
"error": "--write-durations requires --report"
}
},
{
"argv": [
"--skip-judges"
],
"result": {
"error": "--skip-judges applies only to an emitted gate census plan"
}
},
{
"argv": [
"--profile",
"pr",
"--tier",
"periodic"
],
"result": {
"error": "PR profile requires gate tier"
}
},
{
"argv": [
"--profile",
"pr",
"--files-per-shard",
"2"
],
"result": {
"error": "PR profile requires one file per shard to preserve case accounting"
}
},
{
"argv": [],
"env": {
"EVALS_TIER": "e2e"
},
"result": {
"error": "EVALS_TIER must be gate, periodic or marathon. Received: e2e"
}
}
],
"unknownArgumentCli": {
"free": {
"status": 1,
"stderr": "[test:free] Unknown argument: --bogus"
},
"paid": {
"status": 1,
"stderr": "[test:paid] Unknown argument: --bogus"
}
}
}