feat(heartbeat): add process memory and backup health checks

This commit is contained in:
William Valentin
2026-02-16 13:50:39 -08:00
parent 8684c3a07d
commit 07340ff0af
11 changed files with 282 additions and 8 deletions
+7 -3
View File
@@ -7,16 +7,20 @@
"status": "completed",
"date": "2026-02-16",
"updated": "2026-02-16",
"summary": "Added first-class automation presets and scheduling upgrades: `automation.daily_briefing` now auto-registers an opinionated cron job for morning briefings, and backup scheduling now supports cron expressions via `backup.schedule` plus optional `backup.run_on_start` while preserving interval fallback. Added `BackupScheduler` with `backup.notify` channel alerts, configurable `backup.failure_threshold`, and recovery notifications (`backup.notify_recovery`) so backup failures/recoveries proactively notify operators.",
"summary": "Added first-class automation presets and scheduling upgrades: `automation.daily_briefing` now auto-registers an opinionated cron job for morning briefings, and backup scheduling now supports cron expressions via `backup.schedule` plus optional `backup.run_on_start` while preserving interval fallback. Added `BackupScheduler` with `backup.notify` channel alerts, configurable `backup.failure_threshold`, and recovery notifications (`backup.notify_recovery`) so backup failures/recoveries proactively notify operators. Extended heartbeat monitoring with `process_memory` and `backup` checks (with thresholds) so high RSS usage and backup failure streaks proactively trigger health alerts.",
"files_modified": [
"src/config/schema.ts",
"src/config/schema.test.ts",
"src/automation/index.ts",
"src/automation/presets.ts",
"src/automation/presets.test.ts",
"src/automation/heartbeat.ts",
"src/automation/heartbeat.test.ts",
"src/backup/index.ts",
"src/backup/scheduler.ts",
"src/backup/scheduler.test.ts",
"src/backup/status.ts",
"src/backup/status.test.ts",
"src/daemon/channels.ts",
"src/daemon/channels.test.ts",
"src/daemon/index.ts",
@@ -25,7 +29,7 @@
"config/default.yaml",
"README.md"
],
"test_status": "pnpm test:run src/automation/presets.test.ts src/backup/scheduler.test.ts src/config/schema.test.ts src/daemon/channels.test.ts src/gateway/handlers/services.test.ts + pnpm typecheck passing"
"test_status": "pnpm test:run src/automation/presets.test.ts src/automation/heartbeat.test.ts src/backup/scheduler.test.ts src/backup/status.test.ts src/config/schema.test.ts src/daemon/channels.test.ts src/gateway/handlers/services.test.ts + pnpm typecheck passing"
},
"backup-session-summary-audit-trail": {
"status": "completed",
@@ -3311,7 +3315,7 @@
}
},
"overall_progress": {
"total_test_count": 1825,
"total_test_count": 1830,
"all_tests_passing": true,
"p0_completion": "3/3 (100%)",
"p1_completion": "4/4 (100%)",