Telemetry from ai_reviews
Pass-1 is the default diff review; pass-2 is an optional agentic re-review after pass-1 when enabled.
Final-pass input (code + security)
205.0k
Final-pass output (code + security)
27.9k
Pass-1 input (non-agentic)
36
Pass-1 output (non-agentic)
30.8k
Pass-2 tokens (agentic)
481.9k
Pass-1 share (of pass-1 + pass-2)
6%
Avg core IO tokens / PR
43.9k
Avg duration
1m 22s
Total duration (hours)
0.14h
Cache hit rate
100%
Est. cost
$3.12
Re-review rate
0%
Avg runs / PR
1
Activation rate
100%
Avg planner iterations
2.5
Avg context retrieved
52.0 KB
Planner token overhead
119.0k
Avg planner duration
19s
Activation rate
100%
Avg planner iterations
2.7
Avg context retrieved
52.1 KB
Planner token overhead
130.0k
Avg planner duration
29s
Avg cost to non-blocking: — across 0 resolved PR lifecycles.
Cache hit % is cache-read tokens divided by cache read plus cache-creation tokens, split by whether the review row is the first run on a PR or a later re-review run.
Cohort | Cache hit rate |
|---|---|
| First runsRun index 1 on each pull request | 100% |
| Re-runsRun index 2 and above on the same PR | — |