Latency regression
apply_page_layout_ops p95 slowed 66%
736 ms now vs 443 ms previously across 5 calls.
Open the tool view and inspect the slowest recent calls for a repeatable bottleneck.
InvestigateBidlo Status Frontend
Chat tool telemetry
Find slow, failing, and repetitive agent tools without exposing prompts, arguments, or outputs.
Detailed production timing active
6101 of 6166 saved tool calls include execution duration.
Tool calls
5
-17% vs previous 7d4 saved production turns
p50 latency
470 ms
+23400% vs previous 7d5 timed calls
p95 latency
736 ms
+66% vs previous 7d5 timed calls
Tool failures
0.0%
-50.0 pts vs previous 7d0 excluding NoResults
No result
0.0%
No change vs previous 7d0 product outcomes
Calls / turn
1.3
-38% vs previous 7d25.0% of turns at 5+ calls
What changed
Material regressions ranked by severity and affected call volume.
Regression checks require at least 3 calls in both windows. Latency is flagged at +20%; failure and no-result rates are flagged at +1 and +3 points respectively.
Execution volume
Successful calls, no-results, and failures combined.
Calls
Oct 1Oct 4Oct 7
Payload pressure
How often results exceed the 20 KB inline cap.
5.0%
handle rows / all calls
309 stored handles in this period. This is a payload-size proxy, not a one-to-one call classification.
Tool comparison
Each change is measured against the previous equal window; latency appears only where detailed timing exists.
| Tool | Calls | p50 | p95 | Failures | No result |
|---|---|---|---|---|---|
| apply_page_layout_ops | 5-17% vs prior | 470 ms+23400% vs prior | 736 ms+66% vs prior | 0.0%-50.0 pts vs prior | 0.0%No change vs prior |
Failure codes
Operational failures only; NoResults is excluded.
No operational failures
in the selected view
Interpretation notes
The data has known edges that change what a chart means.
- Blocked loops are invisible
- Rate-limited and identical-argument calls are rejected before telemetry fires.
- NoResults is not downtime
- It remains a failed tool outcome, but is separated from runtime reliability here.
- Preview volume lives elsewhere
- Preview and threadless chats reach PostHog but are intentionally absent from Postgres.
- Latency is partially instrumented
- Saved tool parts provide production outcomes and volume; duration appears only on calls with detailed telemetry.
- Partial turns are retained
- They remain in volume counts but are excluded from failures and latency percentiles.
- Comparisons use equal windows
- Every delta compares the selected period with the immediately preceding period under the same tool and team filters.
Recent sanitized calls
Arguments, outputs, user IDs, and message content are never rendered.
apply_page_layout_opsHJC445 msOct 6, 7:00 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_CTa…
Turn sequence
1 of 1
Turn state
Completed
apply_page_layout_opsHJC736 msOct 4, 6:41 PM UTC
Outcome
Success
Thread
913d4f54…
Tool call
chatcmpl…
Turn sequence
1 of 1
Turn state
Completed
apply_page_layout_opsHJC521 msOct 4, 6:40 PM UTC
Outcome
Success
Thread
913d4f54…
Tool call
chatcmpl…
Turn sequence
3 of 4
Turn state
Completed
apply_page_layout_opsHJC423 msOct 4, 6:40 PM UTC
Outcome
Success
Thread
913d4f54…
Tool call
chatcmpl…
Turn sequence
4 of 4
Turn state
Completed
apply_page_layout_opsHJC470 msOct 4, 4:23 PM UTC
Outcome
Success
Thread
e1179f50…
Tool call
chatcmpl…
Turn sequence
12 of 12
Turn state
Completed