Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A DeepSeek Harness bundle for Harness users that picks the model tier and reasoning effort for every turn and subagent, instead of using one model for everything. It includes a composer chip, three configurable tiers, and per-turn records.
How it uses Jev
A configurable decision model, with a ready-made jev profile, is asked once per turn to answer two questions: task difficulty (fast/balanced/deep) and thinking effort (low/medium/high). The bundle applies that answer to the live request; when the judge does not answer, the route is held rather than made cheaper.
Primitives:choice
Technique worth stealing
Ask the judge once per turn and reuse its answer across all tool calls, holding the route when the judge is unavailable.
Try it
Clone the repo, install it as a bundle via install-bundle, then enable it and configure tiers in the Model Router panel.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 projectnot found in the excerpt0.31
- Shows a System One patternFound in material0.67
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelnot found in the excerpt0.29
- Solves a common problem (0–2)score on a 0–2 scale1.37 / 2
- About JevFound in material0.81
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 Nov 2026.