Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A pi extension that sets pi's thinking level for each prompt. It runs for TUI and RPC (Relay) prompts, skipping commands, bash, steers, follow-ups queued behind a running turn, extension-injected text, subagent children, and non-reasoning models.
How it uses Jev
Jev scores the prompt on four rungs (low, medium, high, xhigh), reading it with the tail of the last assistant reply, and answers whether it is a short continuation whose difficulty depends on context. The most probable rung wins (ties go lower); an unsure continuation keeps the current level.
Primitives:choice
Technique worth stealing
Feed the tail of the last assistant reply as context so short continuations are scored against the conversation, not in isolation.
Try it
npm run probe
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 material0.82
- Shows a System One patternFound in material0.74
- Describes handling uncertaintyFound in material0.79
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalunclear0.47
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 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 13 Oct 2026.