Latency regression
run_subagents p95 slowed 142%
1.4 min now vs 35 s previously across 65 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
6035 of 6100 saved tool calls include execution duration.
Tool calls
65
+171% vs previous 7d37 saved production turns
p50 latency
28 s
+80% vs previous 7d65 timed calls
p95 latency
1.4 min
+142% vs previous 7d65 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
1.8
-27% vs previous 7d83.8% 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
307 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 |
|---|---|---|---|---|---|
| run_subagents | 65+171% vs prior | 28 s+80% vs prior | 1.4 min+142% 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.
run_subagentsHJC18 sOct 6, 8:04 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_CS0…
Turn sequence
3 of 29
Turn state
Completed
run_subagentsHJC2.6 minOct 6, 8:09 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_74S…
Turn sequence
11 of 29
Turn state
Completed
run_subagentsHJC60 sOct 6, 8:10 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_iwb…
Turn sequence
12 of 29
Turn state
Completed
run_subagentsHJC24 sOct 6, 8:12 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_tVD…
Turn sequence
26 of 29
Turn state
Completed
run_subagentsHJC13 sOct 6, 7:13 PM UTC
Outcome
Success
Thread
3d7ad6cb…
Tool call
chatcmpl…
Turn sequence
1 of 1
Turn state
Completed
run_subagentsBidlo20 sOct 6, 4:20 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_Kkw…
Turn sequence
14 of 40
Turn state
Completed
run_subagentsBidlo21 sOct 6, 4:10 PM UTC
Outcome
Success
Thread
20a1bcaf…
Tool call
call_BqT…
Turn sequence
4 of 23
Turn state
Completed
run_subagentsHJC5.1 sOct 5, 9:40 PM UTC
Outcome
Success
Thread
8baa70ed…
Tool call
call_1xC…
Turn sequence
20 of 24
Turn state
Completed
run_subagentsHJC25 sOct 5, 8:19 PM UTC
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
11 of 25
Turn state
Completed
run_subagentsHJC28 sOct 5, 8:20 PM UTC
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
13 of 25
Turn state
Completed
run_subagentsHJC12 sOct 5, 8:05 PM UTC
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
4 of 38
Turn state
Completed
run_subagentsHJC1.8 sOct 5, 7:45 PM UTC
Outcome
Success
Thread
8baa70ed…
Tool call
call_VIT…
Turn sequence
15 of 31
Turn state
Completed
run_subagentsHJC18 sOct 5, 7:31 PM UTC
Outcome
Success
Thread
10f9fa7b…
Tool call
call_Ct2…
Turn sequence
7 of 11
Turn state
Completed
run_subagentsHJC23 sOct 5, 7:29 PM UTC
Outcome
Success
Thread
22e6d03b…
Tool call
call_lUC…
Turn sequence
7 of 8
Turn state
Completed
run_subagentsHJC15 sOct 5, 7:27 PM UTC
Outcome
Success
Thread
05b735d6…
Tool call
call_UVv…
Turn sequence
1 of 8
Turn state
Completed
run_subagentsHJC29 sOct 5, 7:27 PM UTC
Outcome
Success
Thread
05b735d6…
Tool call
call_5w9…
Turn sequence
4 of 8
Turn state
Completed
run_subagentsHJC19 sOct 5, 2:09 PM UTC
Outcome
Success
Thread
921b777f…
Tool call
chatcmpl…
Turn sequence
1 of 1
Turn state
Completed
run_subagentsHJC29 sOct 4, 4:46 PM UTC
Outcome
Success
Thread
e1179f50…
Tool call
call_WC1…
Turn sequence
10 of 32
Turn state
Completed
run_subagentsHJC24 sOct 4, 4:46 PM UTC
Outcome
Success
Thread
e1179f50…
Tool call
call_9hA…
Turn sequence
24 of 32
Turn state
Completed
run_subagentsHJC12 sOct 4, 4:47 PM UTC
Outcome
Success
Thread
e1179f50…
Tool call
call_9SR…
Turn sequence
29 of 32
Turn state
Completed
run_subagentsHJC22 sOct 2, 7:59 PM UTC
Outcome
Success
Thread
c1a79eab…
Tool call
chatcmpl…
Turn sequence
26 of 28
Turn state
Completed
run_subagentsBidlo35 sOct 2, 6:54 PM UTC
Outcome
Success
Thread
ba0363bd…
Tool call
call_Vld…
Turn sequence
4 of 33
Turn state
Completed
run_subagentsBidlo51 sOct 2, 6:56 PM UTC
Outcome
Success
Thread
ba0363bd…
Tool call
call_Dyz…
Turn sequence
7 of 33
Turn state
Completed
run_subagentsBidlo34 sOct 2, 6:57 PM UTC
Outcome
Success
Thread
ba0363bd…
Tool call
call_cgj…
Turn sequence
17 of 33
Turn state
Completed