default

scored

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

Measurements

Unavailable values retain their exported state and reason

Quality

Recall 0%

Model-judged precision N/A

F1 N/A

Tier 1 recall 0%

Tier 2 recall 0%

Tier 3 recall 0%

Tier 4 recall 0%

Security recall 0%

Defect recall 0%

Maintainability recall 0%

Performance recall 0%

Median anchor distance N/A

Worst anchor distance N/A

Refusals a judge overturned Not recorded

Review outcomes

Distinct matched defects 0

Defects missed 20

Findings 2

Unkeyed findings 2

Intended findings 0

Carried findings Not recorded

Cost, usage, and speed

Total bill $0.0220

Review bill $0.0220

Judge bill N/A

Tokens 71896

Duration 4m 34s

Execution and identity

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

Lifecycle: completed
Lifecycle reason: Not recorded
Started: 31 Aug 2026, 11:41
Finished: 31 Aug 2026, 11:45
Reviewer: afi
Reviewer tool: afi · cli
Configuration: default / 42c620064e2e
Configuration ID: config-2734e64db3792db2
Build: afi 0.30.0 / b0f313c0b59a66ecc7612396dc8db0ea5da13a7a
Comparison: comparison-159153dbc75bc09b
Build ID: build-4ceb7cbd44e9619b
Cohort ID: cohort-cb1a53c602f2321a
Harness: bench 1 / 10b3b2068100b7ba429855e062500eaf83b90120 dirty
Adapter: afi 1 / sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c
Exit code: 0
Wall time: 274
Deadline exceeded: No
Budget: $2.00
Billing limit: $2.00

Usage

Normalized reviewer-tool usage projection

Input tokens: 70825
Output tokens: 1071
Cached input: 99328
Reasoning tokens: 32206
Requests: 6
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

bug

COUNTERS[4]` is `cairn_proxy_sweep_blobs_removed_total` and `COUNTERS[5]` is `cairn_proxy_sweep_bytes_reclaimed_total`, but `values()[4]` loads `self.sweep_bytes_reclaimed` while `values()[5]` loads… COUNTERS[4]` is `cairn_proxy_sweep_blobs_removed_total` and `COUNTERS[5]` is `cairn_proxy_sweep_bytes_reclaimed_total`, but `values()[4]` loads `self.sweep_bytes_reclaimed` while `values()[5]` loads `self.sweep_blobs_removed`. The `render()` method zips them positionally, so every metrics scrape would report the blob count under the "bytes reclaimed" metric name and the byte count under the "blobs removed" metric name — the two new counters are swapped.

bug

Category: bug Confidence: Not recorded

services/proxy/src/metrics.rs:88

Evidence quote

Not recorded

Suggested fix

Not recorded

rejectedNo keyed defect (scorer)

Finding f2

bug

the on-demand sweep route calls `app.sweeper.sweep(dry_run)` directly, which never acquires the `Sweeper::running` mutex. Only the background path (`Sweeper::run()`) locks that mutex. Two concurrent POSTs to `/v1/admin/cache/sweep`, or one concurrent with the background sweep, therefore execute `sweep()` simultaneously, each making independent removal decisions against a filesystem state the other is mutating — directly violating the "one sweep at a time" invariant documented in `sweep.rs:10-12`.

bug

Category: bug Confidence: Not recorded

services/proxy/src/admin.rs:76

Evidence quote

Not recorded

Suggested fix

Not recorded

rejectedNo keyed defect (scorer)

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