Reliability regression
resolve_documents_by_name failures increased
8.3% now vs 0.0% previously across 60 calls; InvalidArguments is the leading code.
Inspect recent failures, then check the tool handler and upstream dependency logs.
InvestigateFind 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
60
p50 latency
215 ms
p95 latency
1.2 s
Tool failures
8.3%
No result
0.0%
Calls / turn
1.6
Material regressions ranked by severity and affected call volume.
Reliability regression
8.3% now vs 0.0% previously across 60 calls; InvalidArguments is the leading code.
Inspect recent failures, then check the tool handler and upstream dependency logs.
InvestigateLatency regression
1.2 s now vs 974 ms previously across 60 calls.
Open the tool view and inspect the slowest recent calls for a repeatable bottleneck.
InvestigateAgent loop pressure
97.4% now vs 87.5% previously (37 turns).
Inspect the affected turn sequences for repeated or avoidable tool selection.
InvestigateRegression 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.
Successful calls, no-results, and failures combined.
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.
Each change is measured against the previous equal window; latency appears only where detailed timing exists.
| Tool | Calls | p50 | p95 | Failures | No result |
|---|---|---|---|---|---|
| resolve_documents_by_name | 60+200% vs prior | 215 ms-42% vs prior | 1.2 s+23% vs prior | 8.3%+8.3 pts vs prior | 0.0%No change vs prior |
Operational failures only; NoResults is excluded.
The data has known edges that change what a chart means.
Arguments, outputs, user IDs, and message content are never rendered.
Outcome
Success
Thread
ed7becf5…
Tool call
call_Jz2…
Turn sequence
6 of 29
Turn state
Completed
Outcome
Success
Thread
b612fa70…
Tool call
call_e9A…
Turn sequence
10 of 24
Turn state
Completed
Outcome
Success
Thread
50ac87df…
Tool call
call_f4m…
Turn sequence
5 of 21
Turn state
Completed
Outcome
Success
Thread
50ac87df…
Tool call
call_x6w…
Turn sequence
6 of 21
Turn state
Completed
Outcome
Success
Thread
50ac87df…
Tool call
call_apa…
Turn sequence
8 of 21
Turn state
Completed
Outcome
Success
Thread
20a1bcaf…
Tool call
call_BmM…
Turn sequence
6 of 48
Turn state
Completed
Outcome
Success
Thread
8baa70ed…
Tool call
call_gO4…
Turn sequence
12 of 34
Turn state
Completed
Outcome
Success
Thread
8baa70ed…
Tool call
call_9W9…
Turn sequence
13 of 23
Turn state
Completed
Outcome
Success
Thread
8baa70ed…
Tool call
call_BGZ…
Turn sequence
3 of 14
Turn state
Completed
Outcome
Success
Thread
8baa70ed…
Tool call
call_nUz…
Turn sequence
3 of 5
Turn state
Completed
Outcome
Success
Thread
8baa70ed…
Tool call
call_OIQ…
Turn sequence
4 of 5
Turn state
Completed
Outcome
Success
Thread
bf677805…
Tool call
chatcmpl…
Turn sequence
18 of 20
Turn state
Completed
Outcome
Success
Thread
8baa70ed…
Tool call
call_nmQ…
Turn sequence
7 of 33
Turn state
Completed
Outcome
InvalidArguments
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
3 of 25
Turn state
Completed
Outcome
InvalidArguments
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
4 of 25
Turn state
Completed
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
5 of 25
Turn state
Completed
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
6 of 25
Turn state
Completed
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
7 of 25
Turn state
Completed
Outcome
Success
Thread
215345f3…
Tool call
chatcmpl…
Turn sequence
8 of 25
Turn state
Completed
Outcome
Success
Thread
464fa3c3…
Tool call
call_zwY…
Turn sequence
4 of 18
Turn state
Completed
Outcome
Success
Thread
913d4f54…
Tool call
chatcmpl…
Turn sequence
3 of 10
Turn state
Completed
Outcome
Success
Thread
e1179f50…
Tool call
call_dRH…
Turn sequence
6 of 16
Turn state
Completed
Outcome
Success
Thread
e1179f50…
Tool call
call_mMq…
Turn sequence
34 of 54
Turn state
Completed
Outcome
Success
Thread
c1a79eab…
Tool call
chatcmpl…
Turn sequence
12 of 28
Turn state
Completed