default

scored

afi / afi · cli reviewed proxy at 9b51f95e with Default profile / Z.AI · glm 5.2 high on afi 0.30.0

Measurements

Unavailable values retain their exported state and reason

Quality

Recall 15%

Model-judged precision N/A

F1 N/A

Tier 1 recall 0%

Tier 2 recall 14.3%

Tier 3 recall 16.7%

Tier 4 recall 25%

Security recall 0%

Defect recall 15.4%

Maintainability recall 0%

Performance recall 33.3%

Median anchor distance 0

Worst anchor distance 0

Refusals a judge overturned Not recorded

Review outcomes

Distinct matched defects 3

Defects missed 17

Findings 3

Unkeyed findings 0

Intended findings 0

Carried findings Not recorded

Cost, usage, and speed

Total bill $0.1978

Review bill $0.1978

Judge bill N/A

Tokens 75330

Duration 2m 56s

Execution and identity

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

Lifecycle: completed
Lifecycle reason: Not recorded
Started: 31 Aug 2026, 11:54
Finished: 31 Aug 2026, 11:57
Reviewer: afi
Reviewer tool: afi · cli
Configuration: default / 39fb05463232
Configuration ID: config-2e675e005d5c9c60
Build: afi 0.30.0 / b0f313c0b59a66ecc7612396dc8db0ea5da13a7a
Comparison: comparison-21fa35272c82669c
Build ID: build-4ceb7cbd44e9619b
Cohort ID: cohort-fe57f1fa72385a63
Harness: bench 1 / 10b3b2068100b7ba429855e062500eaf83b90120 dirty
Adapter: afi 1 / sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c
Exit code: 0
Wall time: 176
Deadline exceeded: No
Budget: $2.00
Billing limit: $2.00

Usage

Normalized reviewer-tool usage projection

Input tokens: 74111
Output tokens: 1219
Cached input: 307584
Reasoning tokens: 9813
Requests: 16
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 on-demand sweep calls `app.sweeper.sweep(dry_run)` directly instead of the locking `run()`, so an admin-triggered sweep runs concurrently with the background sweep. `Sweeper::sweep` (sweep.rs:90) takes no lock while `run` (sweep.rs:82-84) holds `running`; both walks compute `held` from the same files and each independently removes down to `cache_max_bytes`, so together they reclaim roughly twice the excess — exactly the "far below the ceiling" case the module doc at sweep.rs:10-12 says the mutex exists to prevent.

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 f2

bug

clear_partials` deletes every file in `incoming` with no age check and no exclusion of files being written, so a sweep that fires while a fetch is in progress `fs::remove_file`s that fetch's temp… clear_partials` deletes every file in `incoming` with no age check and no exclusion of files being written, so a sweep that fires while a fetch is in progress `fs::remove_file`s that fetch's temp file out from under its `BlobWriter`. On Unix the open fd keeps the writes alive, but `BlobWriter::commit`'s `fs::rename(&temp, &target)` (store.rs:259) then fails with `NotFound`, failing the in-flight download. The doc comment ("a file in `incoming` is a fetch that is not coming back") is only true for abandoned partials, not for the long-running 200 MiB fetches the cache is sized for.

bug

Category: bug Confidence: Not recorded

services/proxy/src/sweep.rs:230

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 17 (locality)

Finding f3

performance

sweep` performs the full walk (`read_dir`/`metadata`/`read`/`remove_file`) synchronously and is invoked from async contexts — the background task (main.rs:116 via `run`) and the admin handler… sweep` performs the full walk (`read_dir`/`metadata`/`read`/`remove_file`) synchronously and is invoked from async contexts — the background task (main.rs:116 via `run`) and the admin handler (admin.rs:76) — without `spawn_blocking`, so a store walk over the 32 GiB ceiling blocks a tokio worker thread for the whole pass and stalls every other request sharing that thread. The module's justification (sweep.rs:14-18) argues the std calls are cheaper than `tokio::fs` scheduling, but the cost at issue is blocking the runtime, not the syscall count. No findings.

performance

Category: performance Confidence: Not recorded

services/proxy/src/sweep.rs:90

Evidence quote

Not recorded

Suggested fix

Not recorded

matchedDefect 11 (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