Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 248 Pull Requests 14 Actions 1 Packages Projects Releases Wiki Activity

docs: list all supported fallback providers with env var names

Browse Source 
The config comment now shows the complete list of built-in providers
that the fallback system supports, each with the env var it reads
for the API key. Also clarifies that custom OpenAI-compatible endpoints
work via base_url + api_key_env.
This commit is contained in:
teknium1
2026-03-08 20:42:54 -07:00
parent 161436cfdd
commit 4cfb66bac2
1 changed files with 15 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
hermes_cli/config.py
View File

@@ -107,9 +107,22 @@ DEFAULT_CONFIG = {
# When the primary hits rate limits (429), overload (529), or service errors (503),
# Hermes will automatically switch to this model for the remainder of the session.
# Set to None / omit to disable fallback.
#
# Built-in providers (auto-resolve base_url and API key from env):
# openrouter (OPENROUTER_API_KEY) — best fallback, routes to any model
# openai (OPENAI_API_KEY) — GPT-4.1, o3, etc.
# nous (NOUS_API_KEY) — Nous inference API
# deepseek (DEEPSEEK_API_KEY) — DeepSeek models
# together (TOGETHER_API_KEY) — Together AI
# groq (GROQ_API_KEY) — Groq (fast inference)
# fireworks (FIREWORKS_API_KEY) — Fireworks AI
# mistral (MISTRAL_API_KEY) — Mistral models
# gemini (GEMINI_API_KEY) — Google Gemini
#
# For any other OpenAI-compatible endpoint, use base_url + api_key_env.
"fallback_model": {
"provider": "", # e.g. "openrouter", "openai", "nous", "deepseek", "together", "groq"
"model": "", # e.g. "anthropic/claude-sonnet-4", "gpt-4.1", "deepseek-chat"
"provider": "", # provider name from the list above
"model": "", # model slug, e.g. "anthropic/claude-sonnet-4", "gpt-4.1"
# Optional overrides (usually auto-resolved from provider):
# "base_url": "", # custom endpoint URL
# "api_key_env": "", # env var name for API key (e.g. "MY_CUSTOM_KEY")