molecule-core/workspace-configs-templates/hermes/config.yaml
Hongming Wang 2e2261ab9c fix(hermes): align config.yaml required_env with executor (HERMES_API_KEY)
The hermes config required NOUS_API_KEY but the executor
(workspace-template/adapters/hermes/executor.py from PR #49) checks
HERMES_API_KEY and OPENROUTER_API_KEY. A workspace created from this
template would have the provisioner block on a missing NOUS_API_KEY
even when HERMES_API_KEY was set, or pass provisioning but fail at
executor init. .env.example already documents HERMES_API_KEY.

Fix: rename the required_env entry to HERMES_API_KEY and update the
comments to match the executor's actual fallback order (HERMES_API_KEY
first, OPENROUTER_API_KEY second).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-14 10:19:55 -07:00

39 lines
1.2 KiB
YAML

name: Hermes Agent
description: >-
NousResearch Hermes-3 agent workspace. Supports Nous Portal and
OpenRouter as inference providers. Compatible with Hermes-3 70B / 405B
and any Hermes-family fine-tune served through an OpenAI-compatible API.
version: 1.0.0
tier: 2
runtime: hermes
runtime_config:
# Model identifier — exact string depends on your provider:
# Nous Portal: nous-hermes-3-70b | nous-hermes-3-405b
# OpenRouter: nousresearch/hermes-3-llama-3.1-70b
# Override at runtime without editing this file by setting HERMES_MODEL env var.
model: nous-hermes-3-70b
# Authentication — supply ONE of these env vars (checked in order):
# HERMES_API_KEY — Nous Research portal key (https://portal.nousresearch.com)
# OPENROUTER_API_KEY — OpenRouter as a Hermes proxy (useful for dev / cost control)
# Both are checked by adapters/hermes/executor.py; at least one must be set.
required_env:
- HERMES_API_KEY
# 0 = no timeout; increase for long-running research tasks.
timeout: 0
skills: []
a2a:
port: 8000
streaming: true
push_notifications: true
delegation:
retry_attempts: 3
retry_delay: 5
timeout: 120
escalate: true