Add enterprise SLA uptime monitor

README.md

@@ -1,2 +1,6 @@
 # deepevents.ai
 deepevents.ai main codebase
+
+## Enterprise tooling slices
+
+- [`enterprise-sla-uptime-monitor`](enterprise-sla-uptime-monitor/) — deterministic SLA, uptime, webhook reliability, and export-evidence guardrail for SCIBASE Enterprise Tooling issue #19.

enterprise-sla-uptime-monitor/README.md

@@ -0,0 +1,46 @@
+# Enterprise SLA Uptime Monitor
+
+A self-contained Enterprise Tooling slice for SCIBASE issue #19. It converts synthetic uptime checks, incident records, webhook delivery outcomes, and export jobs into a deterministic admin review packet for institutional reliability governance.
+
+This module is intentionally narrow: it does **not** replace the existing admin-dashboard, export, trust-center, data-residency, identity-drift, legal-hold, webhook-replay, or grant-compliance submissions. It focuses only on service-level commitments, error-budget posture, webhook reliability notices, and whether SLA evidence can be exported safely.
+
+## What it does
+
+- Computes per-service uptime against tenant SLA targets.
+- Tracks unplanned downtime, planned maintenance, MTTR, incident counts, and error-budget remaining minutes.
+- Flags `breach`, `watch`, and `within_sla` service states.
+- Reviews webhook destinations with elevated failure rates or dependencies on breached services.
+- Blocks evidence exports that would report on a breached service before an admin review.
+- Produces a SHA-256 evidence digest over the deterministic packet for audit trails.
+
+## Files
+
+- `src/sla-uptime-monitor.js` — local evaluator and helper functions.
+- `data/sample-sla-input.json` — synthetic tenant/service/incidents/webhook/export data.
+- `scripts/demo.js` — terminal demo that prints the admin metrics and action queue.
+- `test/sla-uptime-monitor.test.js` — Node test suite covering breach/watch/ready decisions and deterministic digests.
+- `docs/requirement-map.md` — mapping back to issue #19 Enterprise Tooling requirements.
+- `docs/demo.svg` — static dashboard-style preview.
+
+## Run locally
+
+```bash
+npm run check
+npm test
+npm run demo
+```
+
+Expected demo summary:
+
+```text
+SCIBASE Enterprise SLA Uptime Monitor
+Services: 3
+Breaches: 1
+Watch: 1
+Blocked exports: 1
+Queued actions: 4
+```
+
+## Safety and privacy
+
+The module uses only synthetic data and Node built-ins. It performs no network calls, requires no account credentials, and stores no secrets. It is suitable for offline review and CI.

enterprise-sla-uptime-monitor/data/sample-sla-input.json

@@ -0,0 +1,126 @@
+{
+  "generatedAt": "2026-05-16T12:00:00Z",
+  "windowMinutes": 43200,
+  "tenants": [
+    {
+      "id": "northbridge-university",
+      "name": "Northbridge University Research Office",
+      "contractTier": "enterprise",
+      "defaultSlaTarget": 0.995
+    },
+    {
+      "id": "helios-rd",
+      "name": "Helios R&D Lab",
+      "contractTier": "enterprise-plus",
+      "defaultSlaTarget": 0.999
+    }
+  ],
+  "services": [
+    {
+      "id": "api-core",
+      "name": "SCIBASE API Core",
+      "tenantId": "northbridge-university",
+      "slaTarget": 0.995,
+      "observedChecks": 8640,
+      "failedChecks": 31,
+      "plannedMaintenanceMinutes": 20,
+      "unplannedDowntimeMinutes": 265,
+      "owner": "platform-ops"
+    },
+    {
+      "id": "webhook-dispatcher",
+      "name": "Webhook Dispatcher",
+      "tenantId": "northbridge-university",
+      "slaTarget": 0.995,
+      "observedChecks": 8640,
+      "failedChecks": 12,
+      "plannedMaintenanceMinutes": 30,
+      "unplannedDowntimeMinutes": 180,
+      "owner": "integrations"
+    },
+    {
+      "id": "export-pipeline",
+      "name": "Enterprise Export Pipeline",
+      "tenantId": "helios-rd",
+      "slaTarget": 0.999,
+      "observedChecks": 8640,
+      "failedChecks": 7,
+      "plannedMaintenanceMinutes": 15,
+      "unplannedDowntimeMinutes": 23,
+      "owner": "data-platform"
+    }
+  ],
+  "incidents": [
+    {
+      "id": "INC-1042",
+      "serviceId": "api-core",
+      "tenantId": "northbridge-university",
+      "severity": "sev2",
+      "startedAt": "2026-05-08T11:10:00Z",
+      "resolvedAt": "2026-05-08T13:55:00Z",
+      "customerVisible": true,
+      "rootCause": "database connection pool exhaustion",
+      "followUp": "increase pool alert lead time"
+    },
+    {
+      "id": "INC-1047",
+      "serviceId": "webhook-dispatcher",
+      "tenantId": "northbridge-university",
+      "severity": "sev3",
+      "startedAt": "2026-05-12T09:00:00Z",
+      "resolvedAt": "2026-05-12T10:26:00Z",
+      "customerVisible": true,
+      "rootCause": "downstream retry queue backpressure",
+      "followUp": "add tenant-specific delivery throttle"
+    },
+    {
+      "id": "INC-1051",
+      "serviceId": "export-pipeline",
+      "tenantId": "helios-rd",
+      "severity": "sev4",
+      "startedAt": "2026-05-13T20:00:00Z",
+      "resolvedAt": "2026-05-13T20:23:00Z",
+      "customerVisible": false,
+      "rootCause": "scheduled worker recycle",
+      "followUp": "none"
+    }
+  ],
+  "webhookDeliveries": [
+    {
+      "destinationId": "dspace-sync",
+      "tenantId": "northbridge-university",
+      "serviceId": "webhook-dispatcher",
+      "attempts": 1250,
+      "failures": 38,
+      "lastFailureAt": "2026-05-15T18:42:00Z",
+      "requiresNotice": true
+    },
+    {
+      "destinationId": "orcid-sync",
+      "tenantId": "helios-rd",
+      "serviceId": "export-pipeline",
+      "attempts": 2200,
+      "failures": 3,
+      "lastFailureAt": "2026-05-10T07:15:00Z",
+      "requiresNotice": false
+    }
+  ],
+  "exportJobs": [
+    {
+      "id": "EXP-991",
+      "tenantId": "northbridge-university",
+      "serviceId": "api-core",
+      "target": "institutional-admin-dashboard",
+      "containsSlaEvidence": true,
+      "requestedBy": "research-office-admin"
+    },
+    {
+      "id": "EXP-992",
+      "tenantId": "helios-rd",
+      "serviceId": "export-pipeline",
+      "target": "funder-quarterly-pack",
+      "containsSlaEvidence": true,
+      "requestedBy": "compliance-ops"
+    }
+  ]
+}

enterprise-sla-uptime-monitor/docs/requirement-map.md

@@ -0,0 +1,19 @@
+# Requirement map — Enterprise SLA uptime monitor
+
+This module targets issue #19, **Enterprise Tooling**, with a distinct service-level reliability slice that is not another admin dashboard, export package, trust center, data-residency guard, webhook replay ledger, identity drift checker, or grant compliance packet.
+
+| Issue #19 capability | Module coverage |
+| --- | --- |
+| Admin dashboards | Emits tenant-level service health, breach counts, MTTR, error-budget remaining minutes, and queueable admin actions. |
+| API & webhooks | Evaluates webhook delivery failure rates, notice requirements, and destination-specific reliability actions. |
+| Export pipelines | Marks SLA evidence exports ready or blocked based on service reliability posture and attached evidence. |
+| Compliance tracking | Produces auditable SLA summaries, SHA-256 evidence digests, incident follow-ups, and customer-notice recommendations. |
+| Institutional use case | Gives research offices a deterministic readout for uptime obligations before reporting to funders or internal governance. |
+
+## Non-overlap
+
+Live gate search found existing #19 submissions for broad tooling, export operations, trust centers, audit routers, webhook replay, identity drift, data residency, retention/legal hold, and grant compliance. This slice is limited to SLA/uptime/error-budget governance and does not claim to manage those adjacent workflows.
+
+## Local-first guardrail
+
+All data is synthetic. The demo runs offline, performs no network calls, stores no credentials, and does not publish or send notifications.

enterprise-sla-uptime-monitor/package.json

@@ -0,0 +1,13 @@
+{
+  "name": "enterprise-sla-uptime-monitor",
+  "version": "1.0.0",
+  "description": "Self-contained enterprise SLA and uptime monitoring slice for SCIBASE Enterprise Tooling.",
+  "type": "module",
+  "private": true,
+  "scripts": {
+    "check": "node --check src/sla-uptime-monitor.js && node --check scripts/demo.js && node --check test/sla-uptime-monitor.test.js",
+    "test": "node --test test/sla-uptime-monitor.test.js",
+    "demo": "node scripts/demo.js"
+  },
+  "license": "MIT"
+}

enterprise-sla-uptime-monitor/scripts/demo.js

@@ -0,0 +1,23 @@
+import { readFile } from 'node:fs/promises';
+import { fileURLToPath } from 'node:url';
+import { dirname, join } from 'node:path';
+
+import { evaluateSlaPortfolio } from '../src/sla-uptime-monitor.js';
+
+const here = dirname(fileURLToPath(import.meta.url));
+const samplePath = join(here, '..', 'data', 'sample-sla-input.json');
+const input = JSON.parse(await readFile(samplePath, 'utf8'));
+const report = evaluateSlaPortfolio(input);
+
+console.log('SCIBASE Enterprise SLA Uptime Monitor');
+console.log(`Window: ${report.windowMinutes} minutes`);
+console.log(`Services: ${report.adminMetrics.serviceCount}`);
+console.log(`Breaches: ${report.adminMetrics.breachedServices}`);
+console.log(`Watch: ${report.adminMetrics.watchServices}`);
+console.log(`Blocked exports: ${report.adminMetrics.exportsBlocked}`);
+console.log(`Queued actions: ${report.adminMetrics.queuedActions}`);
+console.log(`Evidence digest: ${report.evidenceDigest}`);
+console.log('\nAction queue:');
+for (const action of report.actionQueue) {
+  console.log(`- [${action.priority}] ${action.type}: ${action.summary}`);
+}