Reliability regression
search_document failures increased
30.9% now vs 0.0% previously across 97 calls; ProviderError is the leading code.
Inspect recent failures, then check the tool handler and upstream dependency logs.
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
+52% vs previous 7d40 saved production turns
p50 latency
102 ms
-28% vs previous 7d97 timed calls
p95 latency
176 ms
-18% vs previous 7d97 timed calls
Tool failures
30.9%
+30.9 pts vs previous 7d30 excluding NoResults
No result
0.0%
No change vs previous 7d0 product outcomes
Calls / turn
2.4
-13% vs previous 7d90.0% 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 |
|---|---|---|---|---|---|
| search_document | 97+52% vs prior | 102 ms-28% vs prior | 176 ms-18% vs prior | 30.9%+30.9 pts vs prior | 0.0%No change vs prior |
Failure codes
Operational failures only; NoResults is excluded.
ProviderError30
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.
search_documentHJC141 msOct 6, 8:05 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_pej…
Turn sequence
5 of 29
Turn state
Completed
search_documentHJC175 msOct 6, 8:05 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_2qK…
Turn sequence
7 of 29
Turn state
Completed
search_documentHJC164 msOct 6, 7:54 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_5uP…
Turn sequence
2 of 31
Turn state
Completed
search_documentHJC176 msOct 6, 7:54 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
call_UKV…
Turn sequence
4 of 31
Turn state
Completed
search_documentHJC188 msOct 6, 7:48 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
chatcmpl…
Turn sequence
3 of 6
Turn state
Completed
search_documentHJC135 msOct 6, 7:48 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
chatcmpl…
Turn sequence
5 of 6
Turn state
Completed
search_documentHJC140 msOct 6, 7:49 PM UTC
Outcome
Success
Thread
ed7becf5…
Tool call
chatcmpl…
Turn sequence
6 of 6
Turn state
Completed
search_documentHJC165 msOct 6, 6:08 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_KUW…
Turn sequence
3 of 28
Turn state
Completed
search_documentHJC105 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_Xcn…
Turn sequence
7 of 13
Turn state
Completed
search_documentHJC108 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_Hx5…
Turn sequence
8 of 13
Turn state
Completed
search_documentHJC115 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_XkK…
Turn sequence
9 of 13
Turn state
Completed
search_documentHJC74 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_k1M…
Turn sequence
10 of 13
Turn state
Completed
search_documentHJC91 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_cE2…
Turn sequence
11 of 13
Turn state
Completed
search_documentHJC84 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_Tc1…
Turn sequence
12 of 13
Turn state
Completed
search_documentHJC127 msOct 6, 6:04 PM UTC
Outcome
Success
Thread
50ac87df…
Tool call
call_XAQ…
Turn sequence
13 of 13
Turn state
Completed
search_documentHJC123 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_YrI…
Turn sequence
8 of 15
Turn state
Completed
search_documentHJC126 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_P4P…
Turn sequence
9 of 15
Turn state
Completed
search_documentHJC128 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_bCp…
Turn sequence
10 of 15
Turn state
Completed
search_documentHJC134 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_t2b…
Turn sequence
11 of 15
Turn state
Completed
search_documentHJC76 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_YNR…
Turn sequence
12 of 15
Turn state
Completed
search_documentHJC129 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_zFg…
Turn sequence
13 of 15
Turn state
Completed
search_documentHJC153 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_BSR…
Turn sequence
14 of 15
Turn state
Completed
search_documentHJC164 msOct 6, 5:59 PM UTC
Outcome
Success
Thread
7839e632…
Tool call
call_PNp…
Turn sequence
15 of 15
Turn state
Completed
search_documentHJC103 msOct 6, 4:05 PM UTC
Outcome
Success
Thread
1a4e54dc…
Tool call
call_bxF…
Turn sequence
1 of 20
Turn state
Completed