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
reasoning-router is a router for coding agents that asks a classifier how much reasoning each step needs, so one strong model handles quick edits and hard debugging without manual effort switching. It works in OpenCode, Pi, Codex CLI, and any client that can talk to a local proxy.
How it uses Jev
For each primary request, the router sends a bounded summary of recent conversation to the classifier, which picks a reasoning effort (for example low for a rename, high for a failing test). Jev is the default classifier; its answer is added to the outgoing request as an OpenAI configuration_update item or an Anthropic effort-only system message, keeping the prompt prefix cacheable.
Technique worth stealing
Adds the chosen effort as a configuration_update item or effort-only system message so earlier updates stay in place and the prompt prefix remains cacheable.
Try it
Set REASONING_ROUTER_CLASSIFIER=jev and REASONING_ROUTER_CLASSIFIER_API_KEY, then run reasoning-router.
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 projectnot found in the excerpt0.20
- Shows a System One patternFound in material0.61
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.17
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.28
- Is a replica of the modelnot found in the excerpt0.21
- Solves a common problem (0–2)score on a 0–2 scale1.35 / 2
- About JevFound in material0.94
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.