Monitoring Implementation Map
/monitoring is a thin shell (app/routes/monitoring._index.tsx →
app/pages/monitoring/MonitoringPage.tsx) hosting two independently-owned
panels selected by ?view=uptime|errors (defaults to uptime). navigation
mirrors it as view="monitoring" with monitoringView (plus
monitorId/errorIssueId when a row is open); each panel also writes richer
selection to the monitoring application-state key.
Uptime
- UI:
app/pages/monitoring/UptimePanel.tsx,app/pages/monitoring/uptime/**. - Server:
server/lib/uptime-monitors.ts(checks/alerting), sweep jobserver/jobs/uptime-monitors.ts, schedulerserver/plugins/uptime-monitor-jobs.ts, schemaserver/db/schema-monitoring.ts. - Actions:
list-monitors,get-monitor,save-monitor,run-monitor-check,delete-monitor. - Production serverless/Netlify-style runtimes skip the in-process interval scheduler and rely on the generated scheduled/background worker or external cron instead.
- Deep links: list
?view=uptime, detail?view=uptime&monitor=<id>, create?view=uptime&monitor=new, edit?view=uptime&monitor=<id>&edit=1. - See
docs/uptime-monitoring.md.
Status Pages
- UI:
app/pages/monitoring/uptime/status-pages/**, a config sub-view under Uptime that bundles chosen monitors under a public/status/<slug>page. - Server: owner-scoped CRUD and the sanitized public projection live in
server/lib/status-pages.tsoverserver/db/schema-monitoring.ts. - Actions:
list-status-pages,get-status-page,save-status-page,delete-status-page,add-status-page-monitor,remove-status-page-monitor,reorder-status-page-monitors, plus the unauthenticatedget-public-status-page. - Deep links: index
?view=uptime&statuspage=list, create?view=uptime&statuspage=new, edit?view=uptime&statuspage=<id>.
Errors
- UI:
app/pages/monitoring/ErrorsPanel.tsx,app/pages/monitoring/errors/**— first-party, Sentry-style exception triage grouped into issues by fingerprint. - Server: ingest/grouping in
server/lib/error-capture.tsoverserver/db/schema-errors.ts. - Browser exceptions arrive through
configureTracking()as$exceptionevents; servercaptureError()failures arrive through the shared tracking provider when the server Analytics key is configured and use the same grouped issue store. - Actions:
list-error-issues,get-error-issue,resolve-error-issue,capture-test-error,match-error-issues. - Browser capture uses the SDK from
@agent-native/core/client(captureException/captureMessage/addErrorBreadcrumb), auto-enabled byconfigureTrackingand transported through the first-party analytics ingest as a$exceptionevent. - Test identities (QA/E2E accounts,
isTestIdentity) keep their exceptions: occurrences are flaggedtestIdentity, never count toward users affected, and never alert. An issue only they have hit istestIdentityOnlyand hidden fromlist-error-issuesunlessincludeTestIdentities: true; the new-issue alert fires on its first real-user occurrence instead. Ingest decides from the identities an event carries (userId, email fields, its context), never from a sender'stest_identityflag, which any write-key holder could set. - Deep link:
?view=errors&issue=<id>. Issue detail includes recent frequency, parsed/raw stack traces, source code snippets when available, breadcrumbs, tags, occurrence history, and session replay links. - Agent lookup: call
list-error-issuesfirst, thenget-error-issuefor stack, occurrence, and replay detail. These are separate from the external Sentry action and do not require a Sentry credential. environmentonlist-error-issues(productionorbeta; omit for all) finds issues with a stored occurrence in that traffic: the occurrence's URL host decides, then its environment when it has no host, and with neither it counts as production.eventCountandusersAffectedstay across all environments. Each kind of traffic is sampled on its own, but an issue keeps only its latest stored occurrences, so an older rare beta occurrence of a noisy issue can be gone.- See
docs/error-capture.md.
Session Replay ↔ Errors
A recording's devtools Console error lines link to the grouped issue at
/monitoring?view=errors&issue=<id>, resolved by match-error-issues (exact
fingerprint match, no heuristics); issues link back to the originating
recording at /sessions/<recordingId>. The fingerprint includes the app, so
match-error-issues takes the recording's app and only matches issues filed
under it.
Related Skills
- session-replay — replay storage, capture, and the Dev Tools panel this feature links to.