default

scored

afi / afi · cli reviewed proxy at 9b51f95e with Default profile / Minimax · m3 high on afi 0.30.0

Measurements

Unavailable values retain their exported state and reason

Quality

Recall 20%

Model-judged precision N/A

F1 N/A

Tier 1 recall 0%

Tier 2 recall 28.6%

Tier 3 recall 33.3%

Tier 4 recall 0%

Security recall 0%

Defect recall 15.4%

Maintainability recall 0%

Performance recall 66.7%

Median anchor distance 0

Worst anchor distance 1

Refusals a judge overturned Not recorded

Review outcomes

Distinct matched defects 4

Defects missed 16

Findings 4

Unkeyed findings 0

Intended findings 0

Carried findings Not recorded

Cost, usage, and speed

Total bill $0.0849

Review bill $0.0849

Judge bill N/A

Tokens 81706

Duration 4m 53s

Execution and identity

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

Lifecycle: completed
Lifecycle reason: Not recorded
Started: 31 Aug 2026, 16:58
Finished: 31 Aug 2026, 17:03
Reviewer: afi
Reviewer tool: afi · cli
Configuration: default / 2116b14e41cc
Configuration ID: config-4ec1f072d60dba02
Build: afi 0.30.0 / b0f313c0b59a66ecc7612396dc8db0ea5da13a7a
Comparison: comparison-cf0749903d73090c
Build ID: build-5c6619f952748951
Cohort ID: cohort-fdab2adfb8a4bd39
Harness: bench 1 / c4bc25bc962489fe5de7f71b59f19b2f426564c0 dirty
Adapter: afi 1 / sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c
Exit code: 0
Wall time: 293
Deadline exceeded: No
Budget: $3.00
Billing limit: $3.00

Usage

Normalized reviewer-tool usage projection

Input tokens: 80579
Output tokens: 1127
Cached input: 139037
Reasoning tokens: 31203
Requests: 11
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

The `values()` array orders the two new counters as `[..., sweep_bytes_reclaimed, sweep_blobs_removed]`, but the `COUNTERS` table at line 33-58 lists them as `[..., sweep_blobs_removed_total,… The `values()` array orders the two new counters as `[..., sweep_bytes_reclaimed, sweep_blobs_removed]`, but the `COUNTERS` table at line 33-58 lists them as `[..., sweep_blobs_removed_total, sweep_bytes_reclaimed_total]`. `render()` pairs them positionally, so Prometheus sees blobs_removed reporting the bytes total and bytes_reclaimed reporting the blob count — exactly the swap the "Keeping the two side by side" comment is supposed to prevent.

bug

Category: bug Confidence: Not recorded

services/proxy/src/metrics.rs:88-95

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 13 (locality)

Finding f2

bug

forget(&index, &gone)` is invoked unconditionally at the end of `sweep`, and `gone` accumulates hex digests regardless of `dry_run` (line 137). The route is documented as `?dry_run=true` reports what a sweep would reclaim without removing anything, but a dry run still `unlink`s the index files via `forget`, leaving blobs on disk with no index entries and forcing a refetch on the next cache lookup.

bug

Category: bug Confidence: Not recorded

services/proxy/src/sweep.rs:140

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 12 (locality)

Finding f3

bug

reclaim` calls `app.sweeper.sweep(dry_run)` (the synchronous entry point at sweep.rs:90), bypassing the `tokio::sync::Mutex` that `Sweeper::run` (sweep.rs:82-85) acquires to honour the module's "One… reclaim` calls `app.sweeper.sweep(dry_run)` (the synchronous entry point at sweep.rs:90), bypassing the `tokio::sync::Mutex` that `Sweeper::run` (sweep.rs:82-85) acquires to honour the module's "One sweep at a time" promise. The background task and any number of concurrent admin requests can now run sweeps in parallel, each iterating candidates over a total the other is mutating.

bug

Category: bug Confidence: Not recorded

services/proxy/src/routes/admin.rs:76

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 6 (locality)

Finding f4

bug

tokio::time::interval(app.cfg.sweep_interval)` fires its first tick at t=0, but the surrounding doc comment on line 106-108 claims "The first tick is one interval away, which is what keeps a proxy… tokio::time::interval(app.cfg.sweep_interval)` fires its first tick at t=0, but the surrounding doc comment on line 106-108 claims "The first tick is one interval away, which is what keeps a proxy that has only just started from sweeping a cache it has not begun to fill." A fresh proxy sweeps an empty store immediately on startup; either the comment or the choice of constructor (`interval_at`) is wrong.

bug

Category: bug Confidence: Not recorded

services/proxy/src/main.rs:113

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 8 (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