mirror of
https://github.com/stablyai/orca.git
synced 2026-10-02 16:02:15 +00:00
Jinwoo Hong
07dad6739a
* refactor(relay): sample fleet health inside the same-cap roll instead of a separate monitor run A same-cap wave no longer consumes a 15-minute monitor dry-run and its sealed, single-use, five-minute-fresh evidence. Each apply wave now samples fleet health itself right before isolation, with the monitor's evaluator, thresholds, and tolerances, for a window sized to the cell's host count (3/5/8 min), plus three lookback rules: no cell container exit in 10 min, no minute over 500 director 503s in 10 min, and director concurrency p99 within the monitor bar over 4 min. Removes the monitor-run inputs, the gate's consume/authorize steps, the break-glass override, and the same-cap-only authorization shapes in relay-monitor-evidence.mjs. The monitor workflow and the rehome enable path are unchanged. Claude-Session: ced32ebb-7155-4413-adad-1eccd14c2010 * fix(relay): bound the pre-drain sample overrun and keep the drain token fresh Review follow-ups: alternating tolerated readings could hold the sample open until its step timeout, so cap the overrun at three samples past the window; record why a read failed; mint a fresh admin ID token for the drain after the sample; raise the job timeout to 90 min so a long sample cannot cancel the job past the failsafe. Claude-Session: ced32ebb-7155-4413-adad-1eccd14c2010 * feat(relay): exempt the rolled cell and existing-only cells from the pre-drain crash rule The exit rule counted every relay container exit fleet-wide, so a cell that crashes every few hours (c25, 12 a week) blocked the very roll that fixes it, and existing-only legacy cells (c5, 15 a week) blocked rolls they take no part in. Exits are now grouped by instance, each instance is named by its own newest runtime-metrics log line, and only exits on general or migration-only cells other than the target count. An exit no configured cell can be named for trips the rule; a failed lookup is a failed read. relay-observability.tf joins the evidence-code set because the rule depends on its filter. Claude-Session: ced32ebb-7155-4413-adad-1eccd14c2010 * test(relay): cover re-asking for an unnamed exiting instance; note the boot-exit risk Claude-Session: ced32ebb-7155-4413-adad-1eccd14c2010
35 lines
4.8 KiB
JSON
35 lines
4.8 KiB
JSON
{
|
|
"name": "orca-cloud",
|
|
"private": true,
|
|
"version": "0.0.0",
|
|
"packageManager": "pnpm@10.24.0",
|
|
"engines": {
|
|
"node": ">=24 <27",
|
|
"pnpm": ">=10"
|
|
},
|
|
"scripts": {
|
|
"build": "pnpm -r build",
|
|
"dev": "pnpm --filter @orca-cloud/relay dev",
|
|
"incident:relay": "pnpm --filter @orca-cloud/relay-ops incident:monitor",
|
|
"incident:relay-preflight": "pnpm --filter @orca-cloud/relay-ops incident:preflight",
|
|
"incident:relay-pre-drain-sample": "pnpm --filter @orca-cloud/relay-ops incident:pre-drain-sample",
|
|
"infra:apply": "node dev/scripts/infra.mjs apply",
|
|
"infra:init": "node dev/scripts/infra.mjs init",
|
|
"infra:plan": "node dev/scripts/infra.mjs plan",
|
|
"lint": "pnpm -r lint",
|
|
"load:relay:controls": "node dev/scripts/load-relay-controls.mjs",
|
|
"load:relay:model": "node dev/scripts/run-relay-load-model.mjs",
|
|
"load:relay:recovery-gate": "node dev/scripts/run-relay-recovery-wave-gate.mjs",
|
|
"ops:relay": "pnpm --filter @orca-cloud/relay-ops dev",
|
|
"pretest": "node --test dev/scripts/capture-terraform-plan-baseline.test.mjs dev/scripts/operate-relay-asia-admission.test.mjs dev/scripts/prepare-relay-asia-director-cells.test.mjs dev/scripts/prepare-relay-asia-topology-input.test.mjs dev/scripts/production-cloud-sql-rollout-lock.test.mjs dev/scripts/read-relay-serving-regional-placement-version.test.mjs dev/scripts/relay-asia-rollout-evidence.test.mjs dev/scripts/relay-asia-topology-workflow.test.mjs dev/scripts/relay-cloud-sql-connection-budget.test.mjs dev/scripts/relay-load-reader-evidence.test.mjs dev/scripts/relay-lock-contention-alerts.test.mjs dev/scripts/relay-region-hint-metrics.test.mjs dev/scripts/relay-staging-deploy-identity.test.mjs dev/scripts/sanitize-relay-asia-admission-result.test.mjs dev/scripts/terraform-root-partition.test.mjs dev/scripts/validate-relay-asia-topology-plan.test.mjs ../.github/actions/cloud-sql-rollout-lease/action-contract.test.mjs ../.github/actions/cloud-sql-rollout-lease/storage-lease.test.mjs",
|
|
"test": "pnpm -r test && node --test dev/scripts/check-relay-same-cap-headroom.test.mjs dev/scripts/classify-relay-production-capacity-director.test.mjs dev/scripts/classify-relay-staging-bootstrap.test.mjs dev/scripts/deploy-relay-blue-green.test.mjs dev/scripts/deploy-relay-gce-candidate.test.mjs dev/scripts/deploy-relay-gce-multi-target.test.mjs dev/scripts/github-smoke-token.test.mjs dev/scripts/infra.test.mjs dev/scripts/operate-relay-regional-rehome.test.mjs dev/scripts/power-staging-relay.test.mjs dev/scripts/prepare-relay-capacity-canary.test.mjs dev/scripts/prepare-relay-production-capacity-canary.test.mjs dev/scripts/probe-relay-legacy-admission.test.mjs dev/scripts/probe-relay-rehome-trust.test.mjs dev/scripts/production-cell-image-digest-consistency.test.mjs dev/scripts/push-gateway-workflow.test.mjs dev/scripts/push-gateway-recovery.test.mjs dev/scripts/read-relay-production-capacity-identity.test.mjs dev/scripts/relay-admin-endpoint-retry-workflow.test.mjs dev/scripts/relay-admin-transient-retry.test.mjs dev/scripts/relay-admission-selector.test.mjs dev/scripts/relay-gce-terraform-fence.test.mjs dev/scripts/relay-load-connection-failure.test.mjs dev/scripts/relay-load-control-peer.test.mjs dev/scripts/relay-load-director-capacity-gate.test.mjs dev/scripts/relay-load-model.test.mjs dev/scripts/relay-load-phase-barrier.test.mjs dev/scripts/relay-load-placement-boundary.test.mjs dev/scripts/relay-load-profile.test.mjs dev/scripts/relay-load-rebind-boundary.test.mjs dev/scripts/relay-load-region-behavior.test.mjs dev/scripts/relay-load-request-unit-boundary.test.mjs dev/scripts/relay-load-run-lifecycle.test.mjs dev/scripts/relay-monitor-evidence.test.mjs dev/scripts/relay-production-capacity-wave.test.mjs dev/scripts/relay-production-capacity-workflow.test.mjs dev/scripts/relay-production-identity-boundaries.test.mjs dev/scripts/relay-production-same-cap-wave.test.mjs dev/scripts/relay-public-workflow-contract.test.mjs dev/scripts/relay-recovery-wave-gate.test.mjs dev/scripts/relay-region-observation-evidence.test.mjs dev/scripts/relay-rehome-aggregate-evidence.test.mjs dev/scripts/relay-repository.test.mjs dev/scripts/relay-same-cap-job-mode-conditions.test.mjs dev/scripts/relay-same-cap-script-census.test.mjs dev/scripts/relay-same-cap-shadow-gate.test.mjs dev/scripts/relay-staging-c4-refresh-workflow.test.mjs dev/scripts/relay-staging-capacity-identity.test.mjs dev/scripts/staging-relay-apply-guard.test.mjs dev/scripts/validate-relay-capacity-plan.test.mjs dev/scripts/verify-relay-capacity-transition.test.mjs dev/scripts/verify-relay-legacy-bootstrap.test.mjs dev/scripts/workload-identity-attribute-conditions.test.mjs",
|
|
"typecheck": "pnpm -r typecheck"
|
|
},
|
|
"devDependencies": {
|
|
"@types/node": "^24.10.0",
|
|
"tsx": "^4.23.15",
|
|
"typescript": "^5.9.3",
|
|
"vitest": "^4.1.11"
|
|
}
|
|
}
|