Latency regression
app_write_file p95 slowed 127%
5.5 s now vs 2.4 s previously across 97 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
97
+185% vs previous 7d47 saved production turns
p50 latency
1.5 s
+118% vs previous 7d97 timed calls
p95 latency
5.5 s
+127% vs previous 7d97 timed calls
Tool failures
0.0%
No change vs previous 7d0 excluding NoResults
No result
0.0%
No change vs previous 7d0 product outcomes
Calls / turn
2.1
+9% vs previous 7d97.9% 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 |
|---|---|---|---|---|---|
| app_write_file | 97+185% vs prior | 1.5 s+118% vs prior | 5.5 s+127% vs prior | 0.0%No change 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.
app_write_fileHJC1.8 sOct 6, 8:10 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_bhH…
Turn sequence
18 of 29
Turn state
Completed
app_write_fileHJC1.7 sOct 6, 8:03 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_lRu…
Turn sequence
12 of 27
Turn state
Completed
app_write_fileHJC1.5 sOct 6, 7:09 PM UTC
Outcome
Success
Thread
dae0a154…
Tool call
call_2Kz…
Turn sequence
25 of 36
Turn state
Completed
app_write_fileHJC185 msOct 6, 7:10 PM UTC
Outcome
Success
Thread
dae0a154…
Tool call
call_xog…
Turn sequence
26 of 36
Turn state
Completed
app_write_fileHJC185 msOct 6, 7:10 PM UTC
Outcome
Success
Thread
dae0a154…
Tool call
call_FAE…
Turn sequence
27 of 36
Turn state
Completed
app_write_fileHJC337 msOct 6, 6:45 PM UTC
Outcome
Success
Thread
d41e378a…
Tool call
call_Ixe…
Turn sequence
17 of 29
Turn state
Completed
app_write_fileHJC382 msOct 6, 6:45 PM UTC
Outcome
Success
Thread
d41e378a…
Tool call
call_i1i…
Turn sequence
18 of 29
Turn state
Completed
app_write_fileHJC723 msOct 6, 6:45 PM UTC
Outcome
Success
Thread
d41e378a…
Tool call
call_YVq…
Turn sequence
19 of 29
Turn state
Completed
app_write_fileHJC5.7 sOct 6, 5:09 PM UTC
Outcome
Success
Thread
b9ce5727…
Tool call
call_LuR…
Turn sequence
17 of 39
Turn state
Completed
app_write_fileBidlo1.9 sOct 6, 4:22 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_6J4…
Turn sequence
20 of 40
Turn state
Completed
app_write_fileBidlo1.2 sOct 6, 4:22 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_ikA…
Turn sequence
21 of 40
Turn state
Completed
app_write_fileBidlo1.7 sOct 6, 4:25 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_FbP…
Turn sequence
28 of 40
Turn state
Completed
app_write_fileHJC1.7 sOct 6, 4:17 PM UTC
Outcome
Success
Thread
1a4e54dc…
Tool call
call_QVJ…
Turn sequence
5 of 28
Turn state
Completed
app_write_fileHJC1.5 sOct 6, 4:18 PM UTC
Outcome
Success
Thread
1a4e54dc…
Tool call
call_aas…
Turn sequence
21 of 28
Turn state
Completed
app_write_fileBidlo185 msOct 6, 4:12 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_VyK…
Turn sequence
17 of 23
Turn state
Completed
app_write_fileHJC1.9 sOct 6, 4:02 PM UTC
Outcome
Success
Thread
1a4e54dc…
Tool call
call_4FV…
Turn sequence
11 of 24
Turn state
Completed
app_write_fileHJC1.9 sOct 6, 3:57 PM UTC
Outcome
Success
Thread
1a4e54dc…
Tool call
call_meb…
Turn sequence
9 of 30
Turn state
Completed
app_write_fileBidlo1.7 sOct 6, 3:54 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_e15…
Turn sequence
19 of 28
Turn state
Completed
app_write_fileBidlo181 msOct 6, 3:55 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_hud…
Turn sequence
20 of 28
Turn state
Completed
app_write_fileBidlo605 msOct 6, 3:49 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_g1g…
Turn sequence
36 of 48
Turn state
Completed
app_write_fileBidlo491 msOct 6, 3:50 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_cSo…
Turn sequence
37 of 48
Turn state
Completed
app_write_fileBidlo163 msOct 6, 3:50 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_so5…
Turn sequence
41 of 48
Turn state
Completed
app_write_fileBidlo398 msOct 6, 3:50 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_8up…
Turn sequence
42 of 48
Turn state
Completed
app_write_fileBidlo167 msOct 6, 3:50 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_lbt…
Turn sequence
43 of 48
Turn state
Completed