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
14 commits sit in this repo's top risk tercile, which is 33% of the 42scored. 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 6.2 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 | 376fe89ftest: add comprehensive test suite | Yan Wang | 1y ago | +367 -0 | 98%Elevated | more lines added than baseline |
| 2 | c50983fdInitial import. | Yan Wang | 1y ago | +416 -0 | 98%Elevated | more lines added than baseline |
| 3 | ca71e84d[Cursor] Add screenshot verification functionality | Yan Wang | 1y ago | +355 -89 | 94%Elevated | more lines added than baseline |
| 4 | 77dcef9bEnvironment and Testing Updates (#17) | Ya Ge | 1y ago | +263 -70 | 92%Elevated | more lines added than baseline |
| 5 | 3c4187e8feat: enhance LLM and search engine capabilities (#12) | Jambo Hsu | 1y ago | +258 -57 | 89%Elevated | more lines added than baseline |
| 6 | 28d7e468Add tentative github copilot support (#59) | Yiming Paul Li | 1y ago | +107 -2 | 87%Elevated | more lines added than baseline |
| 7 | caf99052[Cursor] Add detailed step-by-step tutorial with screenshots (#67) | Ya Ge | 1y ago | +145 -0 | 85%Elevated | more lines added than baseline |
| 8 | e402fc40[Cursor] docs: Add multi-agent system documentation to README (#29) | Ya Ge | 1y ago | +51 -0 | 81%Elevated | more lines added than baseline |
| 9 | f9c796a5Add README.md and LICENSE | Yan Wang | 1y ago | +49 -0 | 81%Elevated | more lines added than baseline |
| 10 | e9571746feat(llm): add Azure OpenAI integration (#23) | Li Li | 1y ago | +58 -6 | 77%Elevated | more lines added than baseline |
| 11 | bda6437dfeat: Add Siliconflow API support (#96) | Yufeng Wang | 1y ago | +50 -4 | 75%Elevated | more lines added than baseline |
| 12 | 378daa28[Cursor] Update project configuration and documentation (#62) | Ya Ge | 1y ago | +49 -1 | 73%Elevated | more lines added than baseline |
| 13 | a2ed2bbadocs: add testing and setup instructions | Yan Wang | 1y ago | +33 -1 | 70%Elevated | more lines added than baseline |
| 14 | 69abe65fUpdate README.md (#34) | Ya Ge | 1y ago | +31 -110 | 68%Elevated | more lines added than baseline |
| 15 | 5930dcc1[Cursor] Update README to introduce cookiecutter template (#45) | Ya Ge | 1y ago | +28 -10 | 63%Typical | more lines added than baseline |
| 16 | 3d47100bUpgrade and improve DuckDuckGo search implementation (#28) | Ya Ge | 1y ago | +41 -82 | 63%Typical | more lines added than baseline |
| 17 | 142b7951fix: improve search engine reliability by using HTML backend | Yan Wang | 1y ago | +26 -17 | 63%Typical | more lines added than baseline |
| 18 | a582c5f4feat: add Google Gemini API support (#16) | Jambo Hsu | 1y ago | +32 -14 | 58%Typical | more lines added than baseline |
| 19 | da66e29fAdd OpenAI o1 model support with tests (#26) | Ya Ge | 1y ago | +28 -9 | 56%Typical | more lines added than baseline |
| 20 | 125eef3c[Cursor] fix: Resolve test failures on master branch (#131) | Ya Ge | 1y ago | +22 -8 | 54%Typical | more lines added than baseline |
| 21 | e6815741Add image reading capability to Gemini (#69) | Hamidreza Nasrabadi | 1y ago | +16 -1 | 51%Typical | more lines added than baseline |
| 22 | c27e876ffeat: add skip option for LLM tests when server not configured | Yan Wang | 1y ago | +21 -0 | 48%Typical | more lines added than baseline |
| 23 | dc7e1955Provide a reference implementation of the devcontainer.json for Windsurf. | Yan Wang | 1y ago | +16 -0 | 48%Typical | more lines added than baseline |
| 24 | e0976808Deepseek support (#15) | guoyongchang | 1y ago | +16 -3 | 44%Typical | more lines added than baseline |
| 25 | ac3f43cadocs: fix virtual environment inconsistency | Yan Wang | 1y ago | +13 -5 | 42%Typical | more lines added than baseline |
| 26 | 9adcce3c[Cursor] Fix requirements.txt formatting and add section headers | Yan Wang | 1y ago | +12 -1 | 39%Typical | more focused than baseline |
| 27 | 3086d03cfeat: Add user defined openai model provider (#124) (#125) | MiaoDX | 1y ago | +11 -7 | 37%Typical | more scattered than baseline |
| 28 | d30dd81f[Cursor] Use uv as the python package manager, #46 (#116) | Ya Ge | 1y ago | +9 -12 | 35%Typical | fewer lines added than baseline |
| 29 | 4e6e098cchore: venv (#20) | richard | 1y ago | +8 -8 | 32%Below typical | more scattered than baseline |
| 30 | e547c96fchore: Update activation commands in README.md (#18) | Jambo Hsu | 1y ago | +8 -5 | 30%Below typical | fewer lines added than baseline |
| 31 | 5aaf5d16Update .cursorrules (#42) | Chris | 1y ago | +6 -3 | 26%Below typical | fewer lines added than baseline |
| 32 | 5b9cc5e5docs: update .cursorrules with improvements | Yan Wang | 1y ago | +6 -1 | 26%Below typical | fewer lines added than baseline |
| 33 | c0a72387[Cursor] Add commit message files to gitignore (#30) | Ya Ge | 1y ago | +6 -10 | 23%Below typical | fewer lines added than baseline |
| 34 | 284b743cEmphasise Devin's consumption pricing (#137) | Erkin Alp Güney | 1y ago | +3 -3 | 18%Below typical | fewer lines added than baseline |
| 35 | 302d45e4[Cursor] Enhance LLM model versions and add current year rule for better performance and capabilities (#105) | Jambo Hsu | 1y ago | +4 -3 | 18%Below typical | fewer lines added than baseline |
| 36 | 9ea2811bfeat: add Google API key config and update .gitignore (#22) | Jambo Hsu | 1y ago | +4 -0 | 18%Below typical | fewer lines added than baseline |
| 37 | 7d10d1c1doc: update tutorial for new cursor UI (#114) | xxchan | 1y ago | +5 -11 | 13%Below typical | fewer lines added than baseline |
| 38 | 86186fddUpdate cursorrules with new instructions and tools (#27) | Ya Ge | 1y ago | +2 -3 | 11%Below typical | fewer lines added than baseline |
| 39 | c3ce4e5e[Cursor] Update README.md with Python version compatibility note (fixes #76, #81) (#83) | Ya Ge | 1y ago | +2 -0 | 7%Below typical | fewer lines added than baseline |
| 40 | 49f2ae2bchore: update Azure OpenAI API version to 2024-08-01-preview (#25) | Li Li | 1y ago | +2 -2 | 7%Below typical | fewer lines added than baseline |
| 41 | b116a795Update the README and requirements.txt to resolve a build failure when using python 3.13. Fix Issue #76. (#94) | Ya Ge | 1y ago | +1 -3 | 2%Below typical | fewer lines added than baseline |
| 42 | ba161edfchore: add requirements.txt | Yan Wang | 1y ago | +1 -0 | 2%Below typical | fewer lines added 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 42 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 9 files in nogl-prod/devin.cursorrules. No file in the repository changed in the last 90 days. Every commit is scored for change risk from its size, spread and the history of the files it touches.
