跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

jev-model-routing

Use to pick the cheapest good-enough model or effort for a turn or a delegated task (lanes small to escalate), to decide continue/retry/verify/escalate/complete after each cycle, or to tune routing.

kerpopule · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add kerpopule/hermes-jev-skills --skill jev-model-routing

技能说明


name: jev-model-routing description: Use to pick the cheapest good-enough model or effort for a turn or a delegated task (lanes small to escalate), to decide continue/retry/verify/escalate/complete after each cycle, or to tune routing. version: 0.2.0 license: MIT metadata: hermes: tags: [jev, typesafe, model-routing, cost]

Model routing with Jev

Jev reads a turn and answers three questions in one ~0.4 s request: how hard is it, what kind of work is it, and would a mistake be costly. Code then walks your pool for that tier and specialty and takes the first model that fits (images, context size). You do not pick models by feel; you ask.

On Hermes it is automatic

With the hermes-jev plugin enabled, each fresh user turn is routed once, before the first model call. Tool-loop follow-ups reuse that decision. Switches, per profile:

/jev                    status
/jev routing shadow     decide and log, but do not switch (start here)
/jev routing on         switch models
/jev routing off
/jev notice on          show "[Jev] medium · coding → kimi-k2.7-code · confidence 0.97" on routed replies

A plugin can swap the model, not the provider connection. On OpenRouter that still means every vendor (DeepSeek, GLM, Kimi, MiniMax, Grok, Qwen, Gemini, GPT). If you run /model yourself, your choice wins and Jev stays out of the way.

For a Hermes custom provider, the plugin cannot infer the backing models.dev provider. It now keeps the current model and logs custom provider needs an explicit provider_aliases.custom instead of blaming an unrelated pool. If and only if that endpoint actually serves the pool's models, set "provider_aliases": {"custom": "venice"} (replace venice with the real pool prefix) in routing.json. Check the endpoint and every pool model before enabling routing; an alias is an operator assertion, not cross-provider discovery. This does not edit any live routing mode.

Asking directly (any agent)

Before delegating a task or spawning a sub-agent, ask which model should get it:

jev route --prompt "<the task, in the person's words>" --current "<provider:model you are on>"

Use model_id from the reply. routed: false means stay where you are; reason says why. Relay notice if the person likes to see routing.

Lanes: delegating a task, and every step after it

For work you hand to a sub-agent or worker, finish with the smallest model and lowest effort that still gets it right. Jev decides; it never writes code, patches or designs.

jev lane classify --task "<the work, in the person's words>"        # first lane + model/effort
jev lane step --task "..." --lane <lane> --attempt <n> \
    --run "<test cmd>" --run "<lint/typecheck cmd>" --scope "<path glob>"   # after each cycle
LaneClaude Code (subagent)Hermes Kanban card (default map)
smalljev-lane-small: Haiku, lowgpt-5.6-luna, medium
mediumjev-lane-medium: Sonnet, mediumgpt-6-sol, medium (today's default)
highjev-lane-high: Opus, mediumgpt-6-sol, medium
escalatejev-lane-escalate: Opus, highgpt-6-astra, high

jev lane targets --host hermes shows the map in force; <hermes root>/jev/lanes.json (or ~/.config/jev/lanes.json) overrides any field. The Hermes map was calibrated on one fleet's own history (see docs/lanes.md); re-measure yours with jev lane replay-build / replay-report.

  • One request, all questions. classify asks the lane (with an other escape: work a person should see first), security sensitivity and underspecification together. Code applies the thresholds: a small pick needs 0.7 confidence; a medium pick below 0.5 goes to high; security ≥ 0.7 is at least high. keep_current means keep the model you had (do it yourself, or ask).
  • Code first. A model the person named, two failed attempts, or your own security-path check decide without asking Jev.
  • Deterministic checks first. step runs the tests, compiler, type checker and linter you name and reads git diff. A failing check is retry (and escalate once the same lane failed twice); files outside --scope are retry; unrun checks are verify; security files changed on small/medium are escalate. Jev is asked only what is left: is it implemented, is it in scope, what next.
  • Escalate one lane at a time, on evidence only. escalate from the top lane returns person.
  • Complete is earned. complete is refused (becomes verify, with complete_refused) unless the checks ran and passed and the diff stayed in scope. Say when a check failed; never hide it.
  • Only the tail of each long check output goes to Jev. Never compact or filter the agent's own reasoning.
  • Jev down: classify keeps the current model, step says verify.
  • Make --run a script, not a one-liner. It runs under a shell, so pipes and && work, but the evidence prints the command cut short and a reader cannot tell what passed. A small script that checks the exact commit and each exit code, and prints ok:/FAIL: per gate, keeps the evidence legible. Make sure it reads only this cycle's results: an earlier failed attempt left in the same log will fail (or pass) the wrong run.
  • Read-only work: --no-changes-expected. For a review or report, say so; otherwise an empty diff reads as nothing done.
  • escalate with a decision still open means person. After a review whose facts are verified but which leaves the owner a choice (a risk to accept, an approach to pick), a stronger model cannot settle it. Put the decision to the person rather than re-running the work a lane up.

On Hermes, jev lane shadow (from cron) classifies new Kanban cards and logs what it would choose; /jev lanes shadow|on|off is the switch and <hermes root>/jev/LANES_OFF wins. on sets the card's model and effort before dispatch; turn it on only after jev lane shadow-report shows fewer tokens at the same

阅读完整来源 ↗