Automated README summary
Automatically summarized from the README on 4 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Accepts TypeSafe /v1/systemone requests and returns TypeSafe-shaped decisions using a remotely served decider-4b GGUF model in llama.cpp. For developers integrating TypeSafe-compatible decision endpoints.
How it uses Jev
Evaluates Choice, Noul, and Score questions (including mixed) from a state. Uses pinned Decider preparation, per-type calibration, upstream assembly, and llama.cpp /completion. Returns calibrated probabilities and maps native token counters to usage.input_tokens and usage.output_tokens.
Primitives:choicescorenoul
Technique worth stealing
Bounded coverage recovery retries missing option token IDs from 256 with doubled probability coverage.
Try it
uv sync --python 3.12.5 --locked; uv run decider-service --validate-config; uv run decider-service
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 material0.83
- Shows a System One patternFound in material0.74
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalnot found in the excerpt0.20
- Is a replica of the modelunclear0.54
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 2
- About JevFound in material0.95
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 Oct 2026.