Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 248 Pull Requests 17 Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
13 changed files with 240 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
hermes_cli/auth.py
View File

@@ -212,6 +212,14 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
api_key_env_vars=("KILOCODE_API_KEY",),
base_url_env_var="KILOCODE_BASE_URL",
),
"huggingface": ProviderConfig(
id="huggingface",
name="Hugging Face",
auth_type="api_key",
inference_base_url="https://router.huggingface.co/v1",
api_key_env_vars=("HF_TOKEN",),
base_url_env_var="HF_BASE_URL",
),
}
@@ -685,6 +693,7 @@ def resolve_provider(
"github-copilot-acp": "copilot-acp", "copilot-acp-agent": "copilot-acp",
"aigateway": "ai-gateway", "vercel": "ai-gateway", "vercel-ai-gateway": "ai-gateway",
"opencode": "opencode-zen", "zen": "opencode-zen",
"hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
"go": "opencode-go", "opencode-go-sub": "opencode-go",
"kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
}

15
hermes_cli/config.py
View File

@@ -593,6 +593,21 @@ OPTIONAL_ENV_VARS = {
"category": "provider",
"advanced": True,
},
"HF_TOKEN": {
"description": "Hugging Face token for Inference Providers (20+ open models via router.huggingface.co)",
"prompt": "Hugging Face Token",
"url": "https://huggingface.co/settings/tokens",
"password": True,
"category": "provider",
},
"HF_BASE_URL": {
"description": "Hugging Face Inference Providers base URL override",
"prompt": "HF base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
# ── Tool API keys ──
"PARALLEL_API_KEY": {

27
hermes_cli/main.py
View File

@@ -795,6 +795,7 @@ def cmd_model(args):
"ai-gateway": "AI Gateway",
"kilocode": "Kilo Code",
"alibaba": "Alibaba Cloud (DashScope)",
"huggingface": "Hugging Face",
"custom": "Custom endpoint",
}
active_label = provider_labels.get(active, active)
@@ -821,6 +822,7 @@ def cmd_model(args):
("opencode-go", "OpenCode Go (open models, $10/month subscription)"),
("ai-gateway", "AI Gateway (Vercel — 200+ models, pay-per-use)"),
("alibaba", "Alibaba Cloud / DashScope (Qwen models, Anthropic-compatible)"),
("huggingface", "Hugging Face Inference Providers (20+ open models)"),
]
# Add user-defined custom providers from config.yaml
@@ -893,7 +895,7 @@ def cmd_model(args):
_model_flow_anthropic(config, current_model)
elif selected_provider == "kimi-coding":
_model_flow_kimi(config, current_model)
elif selected_provider in ("zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba"):
elif selected_provider in ("zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface"):
_model_flow_api_key_provider(config, selected_provider, current_model)
@@ -1502,6 +1504,27 @@ _PROVIDER_MODELS = {
"google/gemini-3-pro-preview",
"google/gemini-3-flash-preview",
],
# Curated model list sourced from https://models.dev (huggingface provider)
"huggingface": [
"Qwen/Qwen3.5-397B-A17B",
"Qwen/Qwen3-235B-A22B-Thinking-2507",
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
"Qwen/Qwen3-Coder-Next",
"Qwen/Qwen3-Next-80B-A3B-Instruct",
"Qwen/Qwen3-Next-80B-A3B-Thinking",
"deepseek-ai/DeepSeek-R1-0528",
"deepseek-ai/DeepSeek-V3.2",
"moonshotai/Kimi-K2-Instruct",
"moonshotai/Kimi-K2-Instruct-0905",
"moonshotai/Kimi-K2.5",
"moonshotai/Kimi-K2-Thinking",
"MiniMaxAI/MiniMax-M2.5",
"MiniMaxAI/MiniMax-M2.1",
"XiaomiMiMo/MiMo-V2-Flash",
"zai-org/GLM-5",
"zai-org/GLM-4.7",
"zai-org/GLM-4.7-Flash",
],
}
@@ -3122,7 +3145,7 @@ For more help on a command:
)
chat_parser.add_argument(
"--provider",
choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
default=None,
help="Inference provider (default: auto)"
)

28
hermes_cli/models.py
View File

@@ -217,6 +217,28 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
"qwen3.5-flash",
"qwen-vl-max",
],
# Curated model list for Hugging Face Inference Providers
# sourced from https://models.dev (huggingface provider)
"huggingface": [
"Qwen/Qwen3.5-397B-A17B",
"Qwen/Qwen3-235B-A22B-Thinking-2507",
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
"Qwen/Qwen3-Coder-Next",
"Qwen/Qwen3-Next-80B-A3B-Instruct",
"Qwen/Qwen3-Next-80B-A3B-Thinking",
"deepseek-ai/DeepSeek-R1-0528",
"deepseek-ai/DeepSeek-V3.2",
"moonshotai/Kimi-K2-Instruct",
"moonshotai/Kimi-K2-Instruct-0905",
"moonshotai/Kimi-K2.5",
"moonshotai/Kimi-K2-Thinking",
"MiniMaxAI/MiniMax-M2.5",
"MiniMaxAI/MiniMax-M2.1",
"XiaomiMiMo/MiMo-V2-Flash",
"zai-org/GLM-5",
"zai-org/GLM-4.7",
"zai-org/GLM-4.7-Flash",
],
}
_PROVIDER_LABELS = {
@@ -236,6 +258,7 @@ _PROVIDER_LABELS = {
"ai-gateway": "AI Gateway",
"kilocode": "Kilo Code",
"alibaba": "Alibaba Cloud (DashScope)",
"huggingface": "Hugging Face",
"custom": "Custom endpoint",
}
@@ -271,6 +294,9 @@ _PROVIDER_ALIASES = {
"aliyun": "alibaba",
"qwen": "alibaba",
"alibaba-cloud": "alibaba",
"hf": "huggingface",
"hugging-face": "huggingface",
"huggingface-hub": "huggingface",
}
@@ -304,7 +330,7 @@ def list_available_providers() -> list[dict[str, str]]:
# Canonical providers in display order
_PROVIDER_ORDER = [
"openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
"zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
"huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
"opencode-zen", "opencode-go",
"ai-gateway", "deepseek", "custom",
]

27
hermes_cli/setup.py
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: