Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Next.js chat demo for a school class forum: players type messages, and each is screened by Jev before it appears in the chat log, with blocked authors shown which rule categories were flagged.
How it uses Jev
On POST /api/moderate, the server sends Jev one request with state (game framing, the message, up to 10 context lines, room usernames) and questions: one Noul per each of nine game rules plus an off_limits exclusion. Code applies thresholds: off-limits removes the message; any reviewable category blocks but keeps it reviewable.
Primitives:noul
Technique worth stealing
One parallel request with a separate yes/no question per rule, so multiple categories can flag the same message.
Try it
npm install; cp .env.example .env.local; add TYPESAFE_API_KEY; npm run dev (http://localhost:4317).
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 material0.86
- Shows a System One patternnot found in the excerpt0.23
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.67
- Top-10 learning shortlist signalnot found in the excerpt0.34
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.24 / 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 19 Oct 2026.