20 lines
1.5 KiB
YAML
20 lines
1.5 KiB
YAML
name: evalroute
|
|
repo: https://github.com/keppy/hermes-plugin-evalroute
|
|
sha: 684c6a871787870519b41b8cef0a152334fbf8ee
|
|
description: "Route a task to the right (model, reasoning effort) arm before you start. Classifies the task into a lane, prints a provenance-carrying route card, and installs per-model reasoning-effort defaults. Strong rules run locally; weak-signal classification calls the host LLM and consumes tokens. The separate harness and shim can make paid provider calls when explicitly run; no plugin-owned credentials. Disclosure — weak-signal task classification sends the task text to your active Hermes model via the host LLM facade (token cost). The model-callable tool, /route, /rate and observed /model and /reasoning commands append task text and command args to a local ledger at <HERMES_HOME>/evalroute/labels.jsonl. \"hermes evalroute install-routes\" rewrites agent.reasoning_overrides in config.yaml when you run it. The bundled harness and Hermes shim are never run by the plugin. When run by hand they make paid provider calls, execute model-generated code on the host via shell checkers, and run hermes -z with approvals bypassed."
|
|
maintainer: keppy
|
|
tier: community
|
|
category: tools
|
|
requires_hermes: ">=0.21"
|
|
version: "0.3.3"
|
|
docs_url: https://github.com/keppy/hermes-plugin-evalroute#readme
|
|
capabilities:
|
|
provides_tools:
|
|
- evalroute_route
|
|
provides_hooks:
|
|
- pre_llm_call
|
|
- pre_command
|
|
- post_llm_call
|
|
provides_middleware: []
|
|
requires_env: []
|