Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A single-file local pull-request reviewer for developers. Deterministic Python gathers diffs, triages, packages state, applies thresholds and composes verdicts; a system one model (e.g. TypeSafe Jev) makes every judgment. Ships with a golden-fixture evaluation harness.
How it uses Jev
For each change cluster, Jev answers three typed questions about the hunk state (explicit code_before_change / code_after_change lists): severity Score, true-positive Noul, and category Choice. Deletion-only clusters use an adapted removal-risk question set. Scores feed deterministic thresholds and verdict composition; all scores are logged to jsonl.
Primitives:choicescorenoul
Technique worth stealing
Send structured state (explicit before/after code lists) rather than raw diffs, and isolate changes into clusters so no change dilutes another.
Try it
Download the release script and SHA256SUMS, verify, install to PATH, set TYPESAFE_API_KEY, then run system-one-reviewer --repo PATH --range A..B.
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 projectnot found in the excerpt0.17
- Shows a System One patternnot found in the excerpt0.26
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.37
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalnot found in the excerpt0.24
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.88 / 2
- About JevFound in material0.96
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 21 Oct 2026.