Automated README summary
Automatically summarized from the README on 2 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
This project measures how well TypeSafe's Jev reviews pull requests, using SWR-Bench's 1,000 real GitHub PRs. It provides a CLI to assess live PRs and a benchmark runner for evaluation.
How it uses Jev
Jev answers four frozen questions: whether a reviewer would request changes, if there's a functional defect, the likely change category, and the likely file. The CLI reads a PR's title, description, and diff, then calls Jev to get probabilities. Results are printed or saved as JSON.
Primitives:choicescore
Technique worth stealing
Using a System One model to answer fixed questions with calibrated probabilities instead of generating text.
Try it
uv sync && export TYPESAFE_API_KEY=... && uv run s1cr review <PR_URL>
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.80
- Shows a System One patternnot found in the excerpt0.09
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.21
- Is a runnable toolFound in material0.78
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.72 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 2 Oct 2026.