Omi 24h Health Report — Full Trace Edition

Generated: 2026-07-26T06:28:48.305151637Z | Window: 24h | Each log pattern includes up to 10 full entries for root cause tracing

CTO Triage Table

P Signal Tier Impact Code Entry Point
P0 GPU oversubscribed — 7 on 5 available critical Transcription/diarization degraded GKE autoscaler, parakeet-pool HPA
P1 Desktop-backend 5xx P99 90s timeout cascade user_facing Desktop users frozen for 90s Desktop-backend upstream call chain
P1 iOS crashes 4,080 (170/hr) critical 6.6x Android rate Crashlytics → http_pool_manager.dart
P2 WebSocket auth: 587x Token expired + cert errors user_facing Disconnected from transcription utils/other/endpoints.py:WebSocket auth
P2 Conversation finalization: 104x stale reconciliation user_facing Orphaned conversations services/conversation_finalization.py:135
P2 Sync pipeline: 30x upstream_error retrying user_facing Memory sync delays utils/sync/pipeline.py:sync_transcription_job

Service Health Matrix

Service Status Issues
desktop-backend CRITICAL No issues
backend-integration CRITICAL No issues
pusher DEGRADED No issues
backend-sync DEGRADED No issues
parakeet HEALTHY No issues
agent-proxy HEALTHY No issues
diarizer HEALTHY No issues
vad HEALTHY No issues
backend-listen HEALTHY No issues

Mobile Crashes (24h)

Platform Total Per Hour
iOS 4,080 170/hr
Android 618 26/hr

Per-Status Latency (Gap 1)

Service Status Count P50 P99 Analysis
desktop-backend2xx2,524336ms17.7sNormal
5xx5090.0s90.1sGateway timeout — 100% are 90s waits (5.1x vs 2xx)
backend2xx42,78639ms2.9sNormal
backend-sync2xx8481.2s54.2sNormal
backend-integration2xx1,30810ms799msNormal

GPU Capacity (Gap 3)

MetricValueStatus
GPU Allocation7 requested / 5 available (-2)CRITICAL
FailedScheduling (24h)1,168CRITICAL
VRAM (max)23.5%OK
Node (pool)VRAM %
vad-pool-v2-47a302d1-71u523.5%
diarizer-pool-037ee134-qt5h22.6%
parakeet-pool-c1f29adf-9lzh16.3%
parakeet-pool-c1f29adf-kwxz16.1%
nllb-translation-poo-bf276826-g5f65.1%

Top Error Endpoints

ServicePathCountTier
backend-integration/v1/mcp/sse34,121internal
backend-integration/v1/mcp/conversations?limit=329,413internal
backend-sync/v2/sync-local-files26,500user_facing
pusherhttps://audio.soundbrain.cc/webhook22,719known_noise
pusherhttps://omi-assist-api-prod.dakom.workers.dev/omi19,747known_noise
pusherhttps://omi.supermemory.ai/webhook10,390known_noise
backend-sync/v2/audio-merge-jobs/run6,707user_facing
backend-sync/v2/sync-jobs/run3,532user_facing
backend-sync/v2/sync-local-files2,426user_facing
backend-sync/v1/conversation-finalization-jobs/run2,092user_facing

Slowest Endpoints

ServicePathAvg LatencyCount
pusher/v1/trigger/listen17.7s47,482
parakeet/v2/transcribe3.6s90,840
parakeet/v3/stream12.0s3,856
parakeet/v1/transcribe298ms1,521

Abnormal Log Patterns — Full Trace (30 patterns, up to 10 logs each)

Each pattern shows up to 10 raw log entries with timestamps, pod names, and full text for code tracing. Click "Show logs" to expand.

#1 [CRITICAL] backend-listen — 587x in 24h
utils.other.endpoints
ERROR:utils.other.endpoints:WebSocket auth failed: code=4001 error=Token expired, <HEX> < <HEX>
Show 10 logs ▼
#2 [CRITICAL] backend-integration — 341x in 24h
Truncated response body. Usually implies that the request timed out or the application exited before the response was fi
Show 3 logs ▼
#3 [CRITICAL] backend-integration — 104x in 24h
services.conversation_finalization
ERROR:services.conversation_finalization:stale processing conversation reconciliation query failed
Show 10 logs ▼
#4 [CRITICAL] backend-integration — 104x in 24h
/app/services/conversation_finalization.py:135
Traceback (most recent call last):
Show 10 logs ▼
#5 [WARNING] backend-sync — 83x in 24h
/app/services/conversation_finalization.py:135
Traceback (most recent call last):
Show 10 logs ▼
#6 [WARNING] backend-sync — 83x in 24h
services.conversation_finalization
ERROR:services.conversation_finalization:stale processing conversation reconciliation query failed
Show 10 logs ▼
#7 [WARNING] pusher — 40x in 24h
utils.app_integrations
ERROR:utils.app_integrations:App 01KF1M5S7Y9QG9V6758W60TXFA is not proactive_notification or data invalid Nn38QjrnfQZAV9
Show 10 logs ▼
#8 [WARNING] backend-sync — 30x in 24h
utils.sync.pipeline
ERROR:utils.sync.pipeline:event=sync_transcription_job outcome=upstream_error status=retrying provider=unknown model=unk
Show 10 logs ▼
#9 [INFO] backend-listen — 19x in 24h
deepgram.clients.common.v1.abstract_sync_websocket
ERROR:deepgram.clients.common.v1.abstract_sync_websocket:WebSocketException in AbstractSyncWebSocketClient.start: server
Show 10 logs ▼
#10 [INFO] backend-listen — 19x in 24h
utils.stt.streaming
ERROR:utils.stt.streaming:Deepgram connection start() returned False — connection not established
Show 10 logs ▼
#11 [INFO] backend-listen — 19x in 24h
deepgram.clients.common.v1.abstract_sync_websocket
ERROR:deepgram.clients.common.v1.abstract_sync_websocket:WebSocketException in ListenWebSocketClient.start: server rejec
Show 10 logs ▼
#12 [INFO] backend-listen — 19x in 24h
WebSocketException in ListenWebSocketClient.start
WebSocketException in ListenWebSocketClient.start: server rejected WebSocket connection: HTTP 401
Show 10 logs ▼
#13 [INFO] backend-listen — 19x in 24h
WebSocketException in AbstractSyncWebSocketClient.start
WebSocketException in AbstractSyncWebSocketClient.start: server rejected WebSocket connection: HTTP 401
Show 10 logs ▼
#14 [INFO] backend-sync — 17x in 24h
utils.sync.pipeline
ERROR:utils.sync.pipeline:event=sync_transcription_job outcome=invalid_input status=failed provider=unknown model=unknow
Show 10 logs ▼
#15 [INFO] backend-listen — 17x in 24h
utils.stt.streaming
ERROR:utils.stt.streaming:Parakeet WS recv error: no close frame received or sent
Show 10 logs ▼
#16 [INFO] crashlytics — 16x in 24h
uid=<HEX> platform=ios device=iPhone17,2 version=1.0.544 package
uid=<HEX> platform=ios device=iPhone17,2 version=1.0.544 package:omi/backend/http/http_pool_manager.dart - HttpPoolManag
Show 3 logs ▼
#17 [INFO] crashlytics — 13x in 24h
uid=<HEX> platform=ios device=iPhone18,2 version=1.0.544 package
uid=<HEX> platform=ios device=iPhone18,2 version=1.0.544 package:omi/backend/http/http_pool_manager.dart - HttpPoolManag
Show 3 logs ▼
#18 [INFO] pusher — 11x in 24h
utils.app_integrations
ERROR:utils.app_integrations:App supermemory-for-omi-01JE0442S4S20TRAHVYAXGQ2RQ is not proactive_notification or data in
Show 10 logs ▼
#19 [INFO] backend-sync — 10x in 24h
utils.sync.pipeline
ERROR:utils.sync.pipeline:event=sync_transcription_job outcome=upstream_error status=failed provider=unknown model=unkno
Show 10 logs ▼
#20 [INFO] backend-sync — 10x in 24h
routers.sync
ERROR:routers.sync:event=sync_transcription_job outcome=upstream_error status=failed_final lane=backfill attempt=5 excep
Show 10 logs ▼
#21 [INFO] pusher — 9x in 24h
utils.webhooks
ERROR:utils.webhooks:Error sending audio bytes to developer webhook:
Show 10 logs ▼
#22 [INFO] backend-sync — 6x in 24h
utils.llm.conversation_processing
ERROR:utils.llm.conversation_processing:Error determining memory discard: Invalid json output: discard = False
Show 10 logs ▼
#23 [INFO] pusher — 6x in 24h
utils.app_integrations
ERROR:utils.app_integrations:App 01K8FRZA3XV2T4N1VD9CMTW8HV is not proactive_notification or data invalid CInQQMaPJvZfaP
Show 10 logs ▼
#24 [INFO] backend-listen — 6x in 24h
utils.stt.streaming
ERROR:utils.stt.streaming:Deepgram start() returned False on all 3 attempts — giving up
Show 10 logs ▼
#25 [INFO] backend-listen — 5x in 24h
utils.other.endpoints
ERROR:utils.other.endpoints:WebSocket auth failed: code=4001 error=Certificate for key id <HEX> not found.
Show 10 logs ▼
#26 [INFO] pusher — 5x in 24h
utils.app_integrations
ERROR:utils.app_integrations:App 01KF1M5S7Y9QG9V6758W60TXFA is not proactive_notification or data invalid 9l9OUOTgDnT3ZF
Show 10 logs ▼
#27 [INFO] backend-sync — 5x in 24h
utils.conversations.finalizer
ERROR:utils.conversations.finalizer:persisted conversation finalization failed uid=s14He2nS6ic2d1HIwKTbbLn81e02 conversa
Show 10 logs ▼
#28 [INFO] crashlytics — 5x in 24h
uid=<HEX> platform=ios device=iPhone8,1 version=1.0.544 package
uid=<HEX> platform=ios device=iPhone8,1 version=1.0.544 package:omi/backend/http/http_pool_manager.dart - HttpPoolManage
Show 3 logs ▼
#29 [INFO] backend-sync — 5x in 24h
utils.conversations.finalizer
ERROR:utils.conversations.finalizer:persisted conversation finalization failed uid=KsDfQaxJBAepV8W3FOB1HxtFqTx1 conversa
Show 10 logs ▼
#30 [INFO] pusher — 5x in 24h
utils.app_integrations
ERROR:utils.app_integrations:App supermemory-for-omi-01JE0442S4S20TRAHVYAXGQ2RQ is not proactive_notification or data in
Show 10 logs ▼

Infrastructure Health

CheckStatusDetails
Grafana AlertsCRITICAL73 alert instances, 7 firing, 3 pending
Cloud Run 5xxWARNING9390 total 5xx across 10 services
Pod LifecycleCRITICAL3095 events (Unhealthy: 1817, Started: 331, Created: 331)
AutoscalerWARNING1168 events (1168 FailedScheduling, 0 scale failures)
DeploysWARNING15 deploy runs, 2 failed
Node MaintOKno events
HPAOKno rescales

Signal Tier Classification (Gap 2)

TierWeightActive Signals
critical_user_facing3.0xGPU exhaustion, transcription pipeline
user_facing1.0xDesktop timeouts, sync 5xx, WebSocket auth, iOS crashes
internal0.3xMCP SSE 401s, Cloud Armor
known_noise0.1xPusher webhooks, firmware 404s

Detection Gap Coverage

GapStatusCoverage
1. Per-status latencyLIVEbeast --per-status + Grafana 5 panels + 2 alerts
2. Route tiersLIVEbeast --tier-filter + 19 route rules
3. GPU capacityLIVEbeast --gpu + Grafana 10 panels + 3 alerts

Sources: beast omi ops health-report --since 24h --drill-down | beast omi ops signal detect --per-status --gpu | Cloud Logging (GKE k8s_container) + BQ (Cloud Run stderr) for full trace logs
Patterns with full logs: 29/30 | Grafana dashboards: Per-Status-Code Latency + GPU Capacity & Health | 5 alert rules

- mon, by AI for @beastoin