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
pydecide is a Python client that sends typed Choice, Score and Noul questions to seven backends (hosted Jev, OpenRouter, OpenAI Decisions, laya, laya-mlx, CrossEncoder, LLM fallback) behind one API, for developers routing, triaging and guarding with decision models.
How it uses Jev
Jev is one backend in an ordered chain. A Client sends the same typed questions to each backend; when a backend errors or answers a Choice or Noul question below its confidence threshold, the question escalates to the next backend. Score answers are never gated. Each response records the route taken in meta.route.
Primitives:choicescorenoul
Technique worth stealing
Confidence-gated fallback chain: a local model carries traffic and a hosted model sees only questions the local one could not answer confidently.
Try it
uv tool install "pydecide[mlx]" then decide ask "..." --noul "..." --choice good,bad
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 excerpt0.10
- Shows a System One patternFound in material0.82
- Describes handling uncertaintyFound in material0.91
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.59 / 2
- About JevFound in material0.97
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.