feat: add Vercel AI Gateway provider (#1628)

* feat: add Vercel AI Gateway as a first-class provider

Adds AI Gateway (ai-gateway.vercel.sh) as a new inference provider
with AI_GATEWAY_API_KEY authentication, live model discovery, and
reasoning support via extra_body.reasoning.

Based on PR #1492 by jerilynzheng.

* feat: add AI Gateway to setup wizard, doctor, and fallback providers

* test: add AI Gateway to api_key_providers test suite

* feat: add AI Gateway to hermes model CLI and model metadata

Wire AI Gateway into the interactive model selection menu and add
context lengths for AI Gateway model IDs in model_metadata.py.

* feat: use claude-haiku-4.5 as AI Gateway auxiliary model

* revert: use gemini-3-flash as AI Gateway auxiliary model

* fix: move AI Gateway below established providers in selection order

---------

Co-authored-by: jerilynzheng <jerilynzheng@users.noreply.github.com>
Co-authored-by: jerilynzheng <zheng.jerilyn@gmail.com>
This commit is contained in:
Teknium
2026-03-17 00:12:16 -07:00
committed by GitHub
parent 4768ea624d
commit 3576f44a57
16 changed files with 223 additions and 9 deletions

View File

@@ -8,6 +8,7 @@ Add, remove, or reorder entries here — both `hermes setup` and
from __future__ import annotations
import json
import os
import urllib.request
import urllib.error
from difflib import get_close_matches
@@ -82,6 +83,20 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
"deepseek-chat",
"deepseek-reasoner",
],
"ai-gateway": [
"anthropic/claude-opus-4.6",
"anthropic/claude-sonnet-4.6",
"anthropic/claude-sonnet-4.5",
"anthropic/claude-haiku-4.5",
"openai/gpt-5",
"openai/gpt-4.1",
"openai/gpt-4.1-mini",
"google/gemini-3-pro-preview",
"google/gemini-3-flash",
"google/gemini-2.5-pro",
"google/gemini-2.5-flash",
"deepseek/deepseek-v3.2",
],
}
_PROVIDER_LABELS = {
@@ -94,6 +109,7 @@ _PROVIDER_LABELS = {
"minimax-cn": "MiniMax (China)",
"anthropic": "Anthropic",
"deepseek": "DeepSeek",
"ai-gateway": "AI Gateway",
"custom": "Custom endpoint",
}
@@ -109,6 +125,9 @@ _PROVIDER_ALIASES = {
"claude": "anthropic",
"claude-code": "anthropic",
"deep-seek": "deepseek",
"aigateway": "ai-gateway",
"vercel": "ai-gateway",
"vercel-ai-gateway": "ai-gateway",
}
@@ -142,7 +161,8 @@ def list_available_providers() -> list[dict[str, str]]:
# Canonical providers in display order
_PROVIDER_ORDER = [
"openrouter", "nous", "openai-codex",
"zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
"zai", "kimi-coding", "minimax", "minimax-cn", "anthropic",
"ai-gateway", "deepseek",
]
# Build reverse alias map
aliases_for: dict[str, list[str]] = {}
@@ -372,6 +392,10 @@ def provider_model_ids(provider: Optional[str]) -> list[str]:
live = _fetch_anthropic_models()
if live:
return live
if normalized == "ai-gateway":
live = _fetch_ai_gateway_models()
if live:
return live
return list(_PROVIDER_MODELS.get(normalized, []))
@@ -475,6 +499,33 @@ def probe_api_models(
}
def _fetch_ai_gateway_models(timeout: float = 5.0) -> Optional[list[str]]:
"""Fetch available language models with tool-use from AI Gateway."""
api_key = os.getenv("AI_GATEWAY_API_KEY", "").strip()
if not api_key:
return None
base_url = os.getenv("AI_GATEWAY_BASE_URL", "").strip()
if not base_url:
from hermes_constants import AI_GATEWAY_BASE_URL
base_url = AI_GATEWAY_BASE_URL
url = base_url.rstrip("/") + "/models"
headers: dict[str, str] = {"Authorization": f"Bearer {api_key}"}
req = urllib.request.Request(url, headers=headers)
try:
with urllib.request.urlopen(req, timeout=timeout) as resp:
data = json.loads(resp.read().decode())
return [
m["id"]
for m in data.get("data", [])
if m.get("id")
and m.get("type") == "language"
and "tool-use" in (m.get("tags") or [])
]
except Exception:
return None
def fetch_api_models(
api_key: Optional[str],
base_url: Optional[str],