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:
@@ -1,4 +1,4 @@
|
||||
"""Tests for API-key provider support (z.ai/GLM, Kimi, MiniMax)."""
|
||||
"""Tests for API-key provider support (z.ai/GLM, Kimi, MiniMax, AI Gateway)."""
|
||||
|
||||
import os
|
||||
import sys
|
||||
@@ -37,6 +37,7 @@ class TestProviderRegistry:
|
||||
("kimi-coding", "Kimi / Moonshot", "api_key"),
|
||||
("minimax", "MiniMax", "api_key"),
|
||||
("minimax-cn", "MiniMax (China)", "api_key"),
|
||||
("ai-gateway", "AI Gateway", "api_key"),
|
||||
])
|
||||
def test_provider_registered(self, provider_id, name, auth_type):
|
||||
assert provider_id in PROVIDER_REGISTRY
|
||||
@@ -65,11 +66,17 @@ class TestProviderRegistry:
|
||||
assert pconfig.api_key_env_vars == ("MINIMAX_CN_API_KEY",)
|
||||
assert pconfig.base_url_env_var == "MINIMAX_CN_BASE_URL"
|
||||
|
||||
def test_ai_gateway_env_vars(self):
|
||||
pconfig = PROVIDER_REGISTRY["ai-gateway"]
|
||||
assert pconfig.api_key_env_vars == ("AI_GATEWAY_API_KEY",)
|
||||
assert pconfig.base_url_env_var == "AI_GATEWAY_BASE_URL"
|
||||
|
||||
def test_base_urls(self):
|
||||
assert PROVIDER_REGISTRY["zai"].inference_base_url == "https://api.z.ai/api/paas/v4"
|
||||
assert PROVIDER_REGISTRY["kimi-coding"].inference_base_url == "https://api.moonshot.ai/v1"
|
||||
assert PROVIDER_REGISTRY["minimax"].inference_base_url == "https://api.minimax.io/v1"
|
||||
assert PROVIDER_REGISTRY["minimax-cn"].inference_base_url == "https://api.minimaxi.com/v1"
|
||||
assert PROVIDER_REGISTRY["ai-gateway"].inference_base_url == "https://ai-gateway.vercel.sh/v1"
|
||||
|
||||
def test_oauth_providers_unchanged(self):
|
||||
"""Ensure we didn't break the existing OAuth providers."""
|
||||
@@ -87,6 +94,7 @@ PROVIDER_ENV_VARS = (
|
||||
"OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY",
|
||||
"GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY",
|
||||
"KIMI_API_KEY", "KIMI_BASE_URL", "MINIMAX_API_KEY", "MINIMAX_CN_API_KEY",
|
||||
"AI_GATEWAY_API_KEY", "AI_GATEWAY_BASE_URL",
|
||||
"OPENAI_BASE_URL",
|
||||
)
|
||||
|
||||
@@ -112,6 +120,9 @@ class TestResolveProvider:
|
||||
def test_explicit_minimax_cn(self):
|
||||
assert resolve_provider("minimax-cn") == "minimax-cn"
|
||||
|
||||
def test_explicit_ai_gateway(self):
|
||||
assert resolve_provider("ai-gateway") == "ai-gateway"
|
||||
|
||||
def test_alias_glm(self):
|
||||
assert resolve_provider("glm") == "zai"
|
||||
|
||||
@@ -130,6 +141,12 @@ class TestResolveProvider:
|
||||
def test_alias_minimax_underscore(self):
|
||||
assert resolve_provider("minimax_cn") == "minimax-cn"
|
||||
|
||||
def test_alias_aigateway(self):
|
||||
assert resolve_provider("aigateway") == "ai-gateway"
|
||||
|
||||
def test_alias_vercel(self):
|
||||
assert resolve_provider("vercel") == "ai-gateway"
|
||||
|
||||
def test_alias_case_insensitive(self):
|
||||
assert resolve_provider("GLM") == "zai"
|
||||
assert resolve_provider("Z-AI") == "zai"
|
||||
@@ -163,6 +180,10 @@ class TestResolveProvider:
|
||||
monkeypatch.setenv("MINIMAX_CN_API_KEY", "test-mm-cn-key")
|
||||
assert resolve_provider("auto") == "minimax-cn"
|
||||
|
||||
def test_auto_detects_ai_gateway_key(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_GATEWAY_API_KEY", "test-gw-key")
|
||||
assert resolve_provider("auto") == "ai-gateway"
|
||||
|
||||
def test_openrouter_takes_priority_over_glm(self, monkeypatch):
|
||||
"""OpenRouter API key should win over GLM in auto-detection."""
|
||||
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
|
||||
@@ -248,6 +269,13 @@ class TestResolveApiKeyProviderCredentials:
|
||||
assert creds["api_key"] == "mmcn-secret-key"
|
||||
assert creds["base_url"] == "https://api.minimaxi.com/v1"
|
||||
|
||||
def test_resolve_ai_gateway_with_key(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_GATEWAY_API_KEY", "gw-secret-key")
|
||||
creds = resolve_api_key_provider_credentials("ai-gateway")
|
||||
assert creds["provider"] == "ai-gateway"
|
||||
assert creds["api_key"] == "gw-secret-key"
|
||||
assert creds["base_url"] == "https://ai-gateway.vercel.sh/v1"
|
||||
|
||||
def test_resolve_with_custom_base_url(self, monkeypatch):
|
||||
monkeypatch.setenv("GLM_API_KEY", "glm-key")
|
||||
monkeypatch.setenv("GLM_BASE_URL", "https://custom.glm.example/v4")
|
||||
@@ -309,6 +337,15 @@ class TestRuntimeProviderResolution:
|
||||
assert result["provider"] == "minimax"
|
||||
assert result["api_key"] == "mm-key"
|
||||
|
||||
def test_runtime_ai_gateway(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_GATEWAY_API_KEY", "gw-key")
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
result = resolve_runtime_provider(requested="ai-gateway")
|
||||
assert result["provider"] == "ai-gateway"
|
||||
assert result["api_mode"] == "chat_completions"
|
||||
assert result["api_key"] == "gw-key"
|
||||
assert "ai-gateway.vercel.sh" in result["base_url"]
|
||||
|
||||
def test_runtime_auto_detects_api_key_provider(self, monkeypatch):
|
||||
monkeypatch.setenv("KIMI_API_KEY", "auto-kimi-key")
|
||||
from hermes_cli.runtime_provider import resolve_runtime_provider
|
||||
|
||||
@@ -137,6 +137,40 @@ class TestBuildApiKwargsOpenRouter:
|
||||
assert "codex_reasoning_items" in messages[1]
|
||||
|
||||
|
||||
class TestBuildApiKwargsAIGateway:
|
||||
def test_uses_chat_completions_format(self, monkeypatch):
|
||||
agent = _make_agent(monkeypatch, "ai-gateway", base_url="https://ai-gateway.vercel.sh/v1")
|
||||
messages = [{"role": "user", "content": "hi"}]
|
||||
kwargs = agent._build_api_kwargs(messages)
|
||||
assert "messages" in kwargs
|
||||
assert "model" in kwargs
|
||||
assert kwargs["messages"][-1]["content"] == "hi"
|
||||
|
||||
def test_no_responses_api_fields(self, monkeypatch):
|
||||
agent = _make_agent(monkeypatch, "ai-gateway", base_url="https://ai-gateway.vercel.sh/v1")
|
||||
messages = [{"role": "user", "content": "hi"}]
|
||||
kwargs = agent._build_api_kwargs(messages)
|
||||
assert "input" not in kwargs
|
||||
assert "instructions" not in kwargs
|
||||
assert "store" not in kwargs
|
||||
|
||||
def test_includes_reasoning_in_extra_body(self, monkeypatch):
|
||||
agent = _make_agent(monkeypatch, "ai-gateway", base_url="https://ai-gateway.vercel.sh/v1")
|
||||
messages = [{"role": "user", "content": "hi"}]
|
||||
kwargs = agent._build_api_kwargs(messages)
|
||||
extra = kwargs.get("extra_body", {})
|
||||
assert "reasoning" in extra
|
||||
assert extra["reasoning"]["enabled"] is True
|
||||
|
||||
def test_includes_tools(self, monkeypatch):
|
||||
agent = _make_agent(monkeypatch, "ai-gateway", base_url="https://ai-gateway.vercel.sh/v1")
|
||||
messages = [{"role": "user", "content": "hi"}]
|
||||
kwargs = agent._build_api_kwargs(messages)
|
||||
assert "tools" in kwargs
|
||||
tool_names = [t["function"]["name"] for t in kwargs["tools"]]
|
||||
assert "web_search" in tool_names
|
||||
|
||||
|
||||
class TestBuildApiKwargsNousPortal:
|
||||
def test_includes_nous_product_tags(self, monkeypatch):
|
||||
agent = _make_agent(monkeypatch, "nous", base_url="https://inference-api.nousresearch.com/v1")
|
||||
|
||||
@@ -26,6 +26,20 @@ def test_resolve_runtime_provider_codex(monkeypatch):
|
||||
assert resolved["requested_provider"] == "openai-codex"
|
||||
|
||||
|
||||
def test_resolve_runtime_provider_ai_gateway(monkeypatch):
|
||||
monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "ai-gateway")
|
||||
monkeypatch.setattr(rp, "_get_model_config", lambda: {})
|
||||
monkeypatch.setenv("AI_GATEWAY_API_KEY", "test-ai-gw-key")
|
||||
|
||||
resolved = rp.resolve_runtime_provider(requested="ai-gateway")
|
||||
|
||||
assert resolved["provider"] == "ai-gateway"
|
||||
assert resolved["api_mode"] == "chat_completions"
|
||||
assert resolved["base_url"] == "https://ai-gateway.vercel.sh/v1"
|
||||
assert resolved["api_key"] == "test-ai-gw-key"
|
||||
assert resolved["requested_provider"] == "ai-gateway"
|
||||
|
||||
|
||||
def test_resolve_runtime_provider_openrouter_explicit(monkeypatch):
|
||||
monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "openrouter")
|
||||
monkeypatch.setattr(rp, "_get_model_config", lambda: {})
|
||||
|
||||
Reference in New Issue
Block a user