Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A FastAPI service that reads a user query, picks the owning intent, and routes it to the correct worker agent over the A2A protocol. For developers building agent routers who want typed, calibrated classification instead of a generative LLM.
How it uses Jev
JevClient builds a System One request from data/intents.yaml: the query as state, a Choice over intents, and a Noul for needs-human-review. Jev returns probabilities and confidence in one parallel pass. IntentClassifier.classify returns Classification(intent, confidence, probabilities, needs_human); RouterAgent gates on confidence and Noul probability before A2A dispatch.
Primitives:choicenoul
Technique worth stealing
Dual-gate routing: confidence below CONFIDENCE_THRESHOLD or Noul probability above HUMAN_REVIEW_THRESHOLD sends the query to the fallback worker.
Try it
CLASSIFIER_BACKEND=mock uvicorn src.app:app --port 8080, then POST /classify or /route.
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 material0.95
- Shows a System One patternFound in material0.90
- Describes handling uncertaintynot found in the excerpt0.16
- Reports measured numbersunclear0.51
- Is a runnable toolunclear0.56
- Top-10 learning shortlist signalunclear0.59
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 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 1 Oct 2026.