Session summary

default

scored

afi / afi · cli reviewed proxy at 9b51f95e with Default profile / DeepSeek · v4 pro high on afi 0.30.0

Measurements

Unavailable values retain their exported state and reason

Quality

Recall 5%
Model-judged precision N/A
F1 N/A
Tier 1 recall 0%
Tier 2 recall 0%
Tier 3 recall 16.7%
Tier 4 recall 0%
Security recall 0%
Defect recall 7.7%
Maintainability recall 0%
Performance recall 0%
Median anchor distance 0
Worst anchor distance 0
Refusals a judge overturned Not recorded

Review outcomes

Distinct matched defects 1
Defects missed 19
Findings 1
Unkeyed findings 0
Intended findings 0
Carried findings Not recorded

Cost, usage, and speed

Total bill $0.1288
Review bill $0.1288
Judge bill N/A
Tokens 62873
Duration 4m 26s

Execution and identity

Lifecycle, reviewer, build, settings, and normalized execution limits

Lifecycle
completed
Lifecycle reason
Not recorded
Started
Finished
Reviewer
afi
Reviewer tool
afi · cli
Configuration
default / f8fe6f35adbe
Configuration ID
config-79001f276ea3730f
Build
afi 0.30.0 / b0f313c0b59a66ecc7612396dc8db0ea5da13a7a
Comparison
comparison-d1c302dcee5c202e
Build ID
build-4ceb7cbd44e9619b
Cohort ID
cohort-038e92fa426e379b
Harness
bench 1 / 10b3b2068100b7ba429855e062500eaf83b90120 dirty
Adapter
afi 1 / sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c
Exit code
0
Wall time
266
Deadline exceeded
No
Budget
$2.00
Billing limit
$2.00

Usage

Normalized reviewer-tool usage projection

Input tokens
62361
Output tokens
512
Cached input
12800
Reasoning tokens
6765
Requests
3
Models counted
Not recorded

Judge

Normalized assessment summary

Judge data is N/A for this run

Findings

Review text is escaped; normalized decisions follow each finding

Finding f1

maintainability

values()` returns `[sweep_bytes_reclaimed, sweep_blobs_removed]` in that order, but `COUNTERS` (lines 50-57) declares the names in the opposite order — `sweep_blobs_removed_total` then… values()` returns `[sweep_bytes_reclaimed, sweep_blobs_removed]` in that order, but `COUNTERS` (lines 50-57) declares the names in the opposite order — `sweep_blobs_removed_total` then `sweep_bytes_reclaimed_total`. The `render()` method zips `COUNTERS` with `values()` positionally, so the "blobs removed" counter will be rendered with the "bytes reclaimed" help text and value, and vice versa. Every Prometheus scrape will mislabel these two metrics.

maintainability
Category: maintainability Confidence: Not recorded

services/proxy/src/metrics.rs:94-95

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 13 (locality)

Source artifacts

Open a row to inspect or download evidence from this atomically published local run

findings present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

meta present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

record present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

result present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

spend present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

stderr present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

summary present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

traffic present

Open verified source artifact

Open this path at the exported commit

The artifact is present; its content is available through the verified source link

benchee benchee-dashboard-1 built from 10f4ec58 Static benchmark evidence ·