feat: add Hugging Face as a first-class inference provider (#3419)

Salvage of PR #1747 (original PR #1171 by @davanstrien) onto current main.

Registers Hugging Face Inference Providers (router.huggingface.co/v1) as a named provider:
- hermes chat --provider huggingface (or --provider hf)
- 18 curated open models via hermes model picker
- HF_TOKEN in ~/.hermes/.env
- OpenAI-compatible endpoint with automatic failover (Groq, Together, SambaNova, etc.)

Files: auth.py, models.py, main.py, setup.py, config.py, model_metadata.py, .env.example, 5 docs pages, 17 new tests.

Co-authored-by: Daniel van Strien <davanstrien@gmail.com>
This commit is contained in:
Teknium 2026-03-27 12:41:59 -07:00 committed by GitHub
parent f57ebf52e9
commit fd8c465e42
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 240 additions and 8 deletions

View file

@ -80,6 +80,11 @@ _DEFAULT_PROVIDER_MODELS = {
"minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
"ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
"kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
"huggingface": [
"Qwen/Qwen3.5-397B-A17B", "Qwen/Qwen3-235B-A22B-Thinking-2507",
"Qwen/Qwen3-Coder-480B-A35B-Instruct", "deepseek-ai/DeepSeek-R1-0528",
"deepseek-ai/DeepSeek-V3.2", "moonshotai/Kimi-K2.5",
],
}
@ -884,6 +889,7 @@ def setup_model_provider(config: dict):
"OpenCode Go (open models, $10/month subscription)",
"GitHub Copilot (uses GITHUB_TOKEN or gh auth token)",
"GitHub Copilot ACP (spawns `copilot --acp --stdio`)",
"Hugging Face Inference Providers (20+ open models)",
]
if keep_label:
provider_choices.append(keep_label)
@ -1528,7 +1534,26 @@ def setup_model_provider(config: dict):
_set_model_provider(config, "copilot-acp", pconfig.inference_base_url)
selected_base_url = pconfig.inference_base_url
# else: provider_idx == 16 (Keep current) — only shown when a provider already exists
elif provider_idx == 16: # Hugging Face Inference Providers
selected_provider = "huggingface"
print()
print_header("Hugging Face API Token")
pconfig = PROVIDER_REGISTRY["huggingface"]
print_info(f"Provider: {pconfig.name}")
print_info("Get your token at: https://huggingface.co/settings/tokens")
print_info("Required permission: 'Make calls to Inference Providers'")
print()
api_key = prompt(" HF Token", password=True)
if api_key:
save_env_value("HF_TOKEN", api_key)
# Clear OpenRouter env vars to prevent routing confusion
save_env_value("OPENAI_BASE_URL", "")
save_env_value("OPENAI_API_KEY", "")
_set_model_provider(config, "huggingface", pconfig.inference_base_url)
selected_base_url = pconfig.inference_base_url
# else: provider_idx == 17 (Keep current) — only shown when a provider already exists
# Normalize "keep current" to an explicit provider so downstream logic
# doesn't fall back to the generic OpenRouter/static-model path.
if selected_provider is None: