Automated README summary
Automatically summarized from the README on 30 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code mod that picks a model·effort pair for each user turn, each subagent, and each ultracode workflow agent, aiming to save money. It is a fork of satviksinha/jev-model-router and supports TypeSafe's direct API and the Vercel AI Gateway.
How it uses Jev
At turn.start Jev is asked one Choice question, `route`, over allowed model·effort pairs, given the request, recent messages and files in play (or the request alone). Code sums probabilities per family, picks the cheapest family with at least half the probability, then its likeliest pair; the chosen model and effort are set on the turn. Subagents are asked once at spawn.
Primitives:choice
Technique worth stealing
Decide in code from Jev's probabilities: aggregate per family, apply a 50% confidence floor, then pick the likeliest pair within that family.
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 material0.77
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.81
- Top-10 learning shortlist signalunclear0.46
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.33 / 2
- About JevFound in material0.99
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 30 Oct 2026.