Xray
1h 6h 24h 48h 3d 5d 7d 14d 30d ‹
Last 1 hour▾
Ends now. Anything up to this cluster's 30-day retention.
Start and end times
Cancel
Interpreted in UTC (change it at the right of this bar). Earliest available: 2026-10-19 10:03:57.
› →|
updated 23h ago
Sample data. This database was generated by scripts/seed_dev_db.py — every service, deploy, person and figure on this page is synthetic. Names are sample.*@seed.invalid and image tags are prefixed SEED-. Nothing here happened.
← findings

chat-agent: p99 latency (ms) 15.00 s — 76.9× the fleet's usual 195 ms (also p95 latency (ms) 8.12 s)

info Service outlier test26 open impact 11 Owner: Sambasiva Bandarupalli (backup: Ahmed Aburaed) opened 76d ago · last observed 2d ago · observed 316× · #662 · 5c4a4717a8678b747be3

What happened template

chat-agent differs from the other 5 services on 2 measures over six hours: p99 latency (ms) 15.00 s against the peers' 195 ms (87.5 MADs above); p95 latency (ms) 8.12 s against the peers' 175 ms (61.7 MADs above). Peer comparison is structural more often than it is news — a service that does more work per request will sit here for as long as it does — which is why this is informational unless it is about failures.

A service unlike the rest of the fleet on one measure (robust z against its peers).

The facts

measures{'measure': 'p99 latency (ms)', 'value': 15000.0, 'value_fmt': '15.00 s', 'median': 195.06666666666672, 'median_fmt': '195 ms', 'mad': 169.11524000000026, 'z': 87.54346050263305, 'direction': 'above', 'peers': 5}, {'measure': 'p95 latency (ms)', 'value': 8125.0, 'value_fmt': '8.12 s', 'median': 175.33333333333331, 'median_fmt': '175 ms', 'mad': 128.8832416666667, 'z': 61.68115081421562, 'direction': 'above', 'peers': 5}
measurep99 latency (ms)
value15,000
value_fmt15.00 s
median195.07
median_fmt195 ms
z87.54
directionabove
peers5
rule{"min_score": 3.5, "min_relative_pct": 35, "warn_on": []}
discriminator
window2026-11-15 05:55:45 UTC → 2026-11-15 11:55:45 UTC

What is failing in chat-agent — the bad events, decomposed

“Bad events” are HTTP 5xx answers from chat-agent. In this finding's window (2026-11-15 05:55:45 UTC → 2026-11-15 11:55:45 UTC) there were 0; every line links to the grouped errors behind it.

The error shapes behind them

2× hitl_tool: pre-approval card generation failed since 2026-11-04 14:17:50 UTC

All chat-agent errors, grouped → · service page · its logs

History

  • 2026-11-15 03:26:54 UTCreopened x-ray · severity=info was=info title=chat-agent: p99 latency (ms) 24.60 s — 12.6× the fleet's usual 1.95 s level=low was_level=low finding={'id': 662, 'fingerprint': '5c4a4717a8678b747be3', 'kind': 'outlier.service', 'severity': 'info', 'cluster': 'test26', 'subject': 'chat-agent', 'title': "chat-agent: p99 latency (ms) 24.60 s — 12.6× the fleet's usual 1.95 s", 'facts': {'measures': [{'measure': 'p99 latency (ms)', 'value': 24600.000000000007, 'value_fmt': '24.60 s', 'median': 1947.333333333334, 'median_fmt': '1.95 s', 'mad': 2511.425560000002, 'z': 9.019843959327488, 'direction': 'above', 'peers': 7}], 'measure': 'p99 latency (ms)', 'value': 24600.000000000007, 'value_fmt': '24.60 s', 'median': 1947.333333333334, 'median_fmt': '1.95 s', 'z': 9.019843959327488, 'direction': 'above', 'peers': 7, 'window': [1794691614, 1794713214], 'recent_deploys': [], 'rule': {'min_score': 3.5, 'min_relative_pct': 35, 'warn_on': []}, 'discriminator': ''}, 'evidence': [{'label': 'Outliers', 'href': '/outliers?cluster=test26&from=1794691614&to=1794713214'}, {'label': 'chat-agent service page', 'href': '/service/chat-agent?cluster=test26&from=1794691614&to=1794713214'}, {'label': 'Tune this rule', 'href': '/alerts/system/outliers'}], 'provenance': {'source': 'rollup', 'collected_at': 1794713214, 'age_seconds': 1, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 5.3, 'status': 'open', 'first_seen': 1788417354, 'last_seen': 1794713214, 'resolved_at': None, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 259, 'narrative': "chat-agent differs from the other 8 services on 2 measures over six hours: p99 latency (ms) ≥ 2.0 min against the peers' 1.42 s (79.9 MADs above); p95 latency (ms) 25.30 s against the peers' 575 ms (44.7 MADs above). Peer comparison is structural more often than it is news — a service that does more work per request will sit here for as long as it does — which is why this is informational unless it is about failures.", 'narrative_kind': 'template', 'discriminator': '', 'level': 'low', 'told_level': None, 'episode_at': 1794713214, 'chat_thread': None, 'kind_label': 'Service outlier', 'group': 'Anomalies', 'age_s': 6295861, 'stale_s': 1}

Check it yourself

Every link carries the finding's own time window, so it shows tomorrow what it shows now.

Actions

Sign in (IAP) to acknowledge, snooze or resolve.

Where the numbers come from

sourcerollup
collected_at1794743745
age_seconds1
staleFalse
shownNone
totalNone
truncatedFalse
coverage_fromNone
retain_daysNone
noteNone
detectoroutliers