Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A DeepSeek Harness plugin that compacts old context without lossy summaries. Instead of asking an LLM to rewrite history, it scores each tool call and result and keeps what matters byte-for-byte.
How it uses Jev
Jev receives the whole compacted region as state (tool results replaced by short notes) and answers two noul questions per non-pinned call: should the call stay, and should the result stay verbatim. Probabilities are compared against keepThreshold to keep both, truncate the result, or drop the call.
Primitives:noul
Technique worth stealing
Score each tool call and result separately with calibrated probabilities, then keep, truncate, or drop — never rewriting kept content.
Try it
Mount the plugin via an agent preset patch, set TYPESAFE_API_KEY, restart DSH, then run /compact.
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 material0.91
- Shows a System One patternunclear0.46
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.80
- Top-10 learning shortlist signalnot found in the excerpt0.37
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.10 / 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 3 Oct 2026.