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
A zsh plugin that shows Fish-style inline autosuggestions. As you type, it ranks your last 100 distinct history entries and displays the best match in grey after the cursor, for zsh 5.9+ users with a TypeSafe API key.
How it uses Jev
State holds typed_so_far plus ID-tagged candidates. A Choice over the IDs asks which entry the user is completing (its probability is the score); a Noul asks whether any candidate completes the input. Fuzzy mode gates on both signals; prefix mode always suggests the top candidate.
Primitives:choicenoul
Technique worth stealing
Ask one request with two questions: a Choice for the top candidate and a Noul for whether any candidate completes the input, then gate on both.
Try it
Clone the repo, npm install, export TYPESAFE_API_KEY, source zsh/jev-shell-history.plugin.zsh.
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 material0.94
- Shows a System One patternunclear0.42
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersunclear0.48
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 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 20 Sept 2026.