Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
2 commits sit in this repo's top risk tercile, which is 29% of the 7scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 9.1 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
Consistently feature-driven across its history.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 8c88c668feat:Scheduler | amithathreya | 1mo ago | +457 -11 | 93%Elevated | more lines added than baseline |
| 2 | 5805ad02feat: Streaming response | amith | 2mo ago | +432 -0 | 79%Elevated | more lines added than baseline |
| 3 | bbacfd73llama cpp python rewrite | amithathreya | 1mo ago | +135 -192 | 64%Typical | more lines added than baseline |
| 4 | b053213efeat:ctx_check and admission policy | amithathreya | 1mo ago | +53 -10 | 50%Typical | more lines added than baseline |
| 5 | 054bec2efeat:RLock | amithathreya | 1mo ago | +51 -29 | 36%Typical | more lines added than baseline |
| 6 | 7b8a60ebskeleton for admission check | amithathreya | 1mo ago | +33 -9 | 21%Below typical | more lines added than baseline |
| 7 | 05d7ace3Update README | amith | 2mo ago | +10 -77 | 7%Below typical | more focused than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 7 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
Repowise tracks change history across 11 files in amithathreya/inference_layer. In the last 90 days 11 files were touched, 15 times in total, most often kvcache.py. Every commit is scored for change risk from its size, spread and the history of the files it touches.
