Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An opt-in Pi extension that filters older messages from model requests while preserving the original session history. It is for Pi users running long sessions who want to keep useful context without deleting history.
How it uses Jev
Jev judges which older eligible messages are still useful. Candidates include complete text-only tool call/result pairs, assistant text, readable thinking, and user shell history. A candidate stays when its keep probability is greater than the threshold (default 0.8). Low-scoring content is hidden from future model requests, not deleted.
Primitives:score
Technique worth stealing
Branch-aware caching of Jev relevance judgments so only new or changed candidates are rejudged.
Try it
pi install npm:pi-jev-context, restart Pi or run /reload, then /login typesafe and /jev on.
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 patternnot found in the excerpt0.22
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 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 20 Sept 2026.