Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local TypeScript CLI for developers reviewing Pull Request / Merge Request diffs. It obtains structured decisions from JEV (TypeSafe) and applies a deterministic risk policy to the application code, separating model decisions from application decisions.
How it uses Jev
JEV answers structured questions about the diff state (files, additions, deletions, diff text plus inventory summary). Four scored axes (securityImpact, databaseChange, apiImpact, authenticationImpact) use the TypeSafe score primitive with a 0–9 rubric, converted to 0–100 impact. Advisory axes (breakingChange, needsHumanReview, riskLevel) do not enter the score. The app computes a weighted average and maps it to APPROVE / REVIEW / BLOCK.
Primitives:score
Technique worth stealing
Separate model decisions (impact + confidence) from application decisions (weighted average, risk level, action) via a deterministic policy JSON.
Try it
npm install && npm run build, then node bin/jev-pr-reviewer.mjs analyze fixtures/sample.diff --mock --json
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.95
- Shows a System One patternFound in material0.91
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalnot found in the excerpt0.37
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.78 / 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 4 Nov 2026.