Bidlo Status Frontend

Chat tool telemetry

Find slow, failing, and repetitive agent tools without exposing prompts, arguments, or outputs.

Detailed production timing active

6056 of 6122 saved tool calls include execution duration.

98.9% timing coverage

Tool calls

1

New activity vs previous 7d1 saved production turns

p50 latency

75 ms

Timing not instrumented1 timed calls

p95 latency

75 ms

Timing not instrumented1 timed calls

Tool failures

100.0%

+100.0 pts vs previous 7d1 excluding NoResults

No result

0.0%

No change vs previous 7d0 product outcomes

Calls / turn

1.0

New activity vs previous 7d100.0% of turns at 5+ calls

What changed

Material regressions ranked by severity and affected call volume.

Current 7 days compared with the previous equal window

Agent loop pressure

More turns are using five or more tools

100.0% now vs — previously (1 turns).

Inspect the affected turn sequences for repeated or avoidable tool selection.

Investigate

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
1 calls on 2026-10-06
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.

Sorted by current p95 latency
ToolCallsp50p95FailuresNo result
update_pdf_layers1No prior data75 msNo prior timing75 msNo prior timing100.0%No prior data0.0%No prior data

Failure codes

Operational failures only; NoResults is excluded.

InvalidArguments1

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.

Privacy safe
update_pdf_layersHJC75 msOct 6, 6:54 PM UTC

Outcome

InvalidArguments

Thread

50ac87df…

Tool call

call_0nO…

Turn sequence

1 of 5

Turn state

Completed

Source: Production chat_messages.tool_results (saved tool parts and detailed telemetry) Tool execution time starts after approval gates.