ouyangbo/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity

Revert "remove Vercel AI Gateway and Vercel Sandbox (#33067)"

Browse Source 
This reverts commit febc4cfec0.
This commit is contained in:
Teknium
2026-07-29 18:16:17 -07:00
parent 0524eccdd8
commit ad12df6ba4
94 changed files with 4168 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hermes_cli/models.py
+214 -5
View File
@@ -98,6 +98,29 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
_openrouter_catalog_cache: list[tuple[str, str]] | None = None
# Fallback Vercel AI Gateway snapshot used when the live catalog is unavailable.
# OSS / open-weight models prioritized first, then closed-source by family.
# Slugs match Vercel's actual /v1/models catalog (e.g. alibaba/ for Qwen,
# zai/ and xai/ without hyphens).
VERCEL_AI_GATEWAY_MODELS: list[tuple[str, str]] = [
("moonshotai/kimi-k2.6", "recommended"),
("alibaba/qwen3.6-plus", ""),
("zai/glm-5.1", ""),
("minimax/minimax-m2.7", ""),
("anthropic/claude-sonnet-4.6", ""),
("anthropic/claude-opus-4.7", ""),
("anthropic/claude-opus-4.6", ""),
("anthropic/claude-haiku-4.5", ""),
("openai/gpt-5.4", ""),
("openai/gpt-5.4-mini", ""),
("openai/gpt-5.3-codex", ""),
("google/gemini-3.1-pro-preview", ""),
("google/gemini-3-flash", ""),
("google/gemini-3.1-flash-lite-preview", ""),
("xai/grok-4.20-reasoning", ""),
]
_ai_gateway_catalog_cache: list[tuple[str, str]] | None = None
def _codex_curated_models() -> list[str]:
@@ -582,6 +605,12 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
],
}
# Vercel AI Gateway: derive the bare-model-id catalog from the curated
# ``VERCEL_AI_GATEWAY_MODELS`` snapshot so both the picker (tuples with descriptions)
# and the static fallback catalog (bare ids) stay in sync from a single
# source of truth.
_PROVIDER_MODELS["ai-gateway"] = [mid for mid, _ in VERCEL_AI_GATEWAY_MODELS]
# ---------------------------------------------------------------------------
# Nous Portal free-model helper
# ---------------------------------------------------------------------------
@@ -1111,6 +1140,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
ProviderEntry("opencode-go", "OpenCode Go", "OpenCode Go (Open models subscription)"),
ProviderEntry("bedrock", "AWS Bedrock", "AWS Bedrock (Claude, Nova, Llama, DeepSeek; IAM or API key)"),
ProviderEntry("azure-foundry", "Azure Foundry", "Azure Foundry (OpenAI-style or Anthropic-style endpoint, your Azure AI deployment)"),
ProviderEntry("ai-gateway", "Vercel AI Gateway", "Vercel AI Gateway (Multi-model aggregator)"),
ProviderEntry("qwen-oauth", "Qwen OAuth (Portal)", "Qwen OAuth (Reuses local Qwen CLI login)"),
]
@@ -1284,6 +1314,9 @@ _PROVIDER_ALIASES = {
"zen": "opencode-zen",
"go": "opencode-go",
"opencode-go-sub": "opencode-go",
"aigateway": "ai-gateway",
"vercel": "ai-gateway",
"vercel-ai-gateway": "ai-gateway",
"kilo": "kilocode",
"kilo-code": "kilocode",
"kilo-gateway": "kilocode",
@@ -1553,6 +1586,95 @@ def get_curated_nous_model_ids() -> list[str]:
return list(_PROVIDER_MODELS.get("nous", []))
def _ai_gateway_model_is_free(pricing: Any) -> bool:
"""Return True if an AI Gateway model has $0 input AND output pricing."""
if not isinstance(pricing, dict):
return False
try:
return float(pricing.get("input", "0")) == 0 and float(pricing.get("output", "0")) == 0
except (TypeError, ValueError):
return False
def fetch_ai_gateway_models(
timeout: float = 8.0,
*,
force_refresh: bool = False,
) -> list[tuple[str, str]]:
"""Return the curated AI Gateway picker list, refreshed from the live catalog when possible."""
global _ai_gateway_catalog_cache
if _ai_gateway_catalog_cache is not None and not force_refresh:
return list(_ai_gateway_catalog_cache)
from hermes_constants import AI_GATEWAY_BASE_URL
fallback = list(VERCEL_AI_GATEWAY_MODELS)
preferred_ids = [mid for mid, _ in fallback]
try:
req = urllib.request.Request(
f"{AI_GATEWAY_BASE_URL.rstrip('/')}/models",
headers={"Accept": "application/json"},
)
with urllib.request.urlopen(req, timeout=timeout) as resp:
payload = json.loads(resp.read().decode())
except Exception:
return list(_ai_gateway_catalog_cache or fallback)
live_items = payload.get("data", [])
if not isinstance(live_items, list):
return list(_ai_gateway_catalog_cache or fallback)
live_by_id: dict[str, dict[str, Any]] = {}
for item in live_items:
if not isinstance(item, dict):
continue
mid = str(item.get("id") or "").strip()
if not mid:
continue
live_by_id[mid] = item
curated: list[tuple[str, str]] = []
for preferred_id in preferred_ids:
live_item = live_by_id.get(preferred_id)
if live_item is None:
continue
desc = "free" if _ai_gateway_model_is_free(live_item.get("pricing")) else ""
curated.append((preferred_id, desc))
if not curated:
return list(_ai_gateway_catalog_cache or fallback)
# If the live catalog offers a free Moonshot model, auto-promote it to
# position #1 as "recommended" — dynamic discovery without a PR.
free_moonshot = next(
(
mid
for mid, item in live_by_id.items()
if mid.startswith("moonshotai/")
and _ai_gateway_model_is_free(item.get("pricing"))
),
None,
)
if free_moonshot:
curated = [(mid, desc) for mid, desc in curated if mid != free_moonshot]
curated.insert(0, (free_moonshot, "recommended"))
else:
first_id, _ = curated[0]
curated[0] = (first_id, "recommended")
_ai_gateway_catalog_cache = curated
return list(curated)
def ai_gateway_model_ids(*, force_refresh: bool = False) -> list[str]:
"""Return just the AI Gateway model-id strings."""
return [mid for mid, _ in fetch_ai_gateway_models(force_refresh=force_refresh)]
# ---------------------------------------------------------------------------
# Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
# ---------------------------------------------------------------------------
@@ -1736,6 +1858,56 @@ def fetch_models_with_pricing(
return result
def fetch_ai_gateway_pricing(
timeout: float = 8.0,
*,
force_refresh: bool = False,
) -> dict[str, dict[str, str]]:
"""Fetch Vercel AI Gateway /v1/models and return hermes-shaped pricing.
Vercel uses ``input`` / ``output`` field names; hermes's picker expects
``prompt`` / ``completion``. This translates. Cache read/write field names
already match.
"""
from hermes_constants import AI_GATEWAY_BASE_URL
cache_key = AI_GATEWAY_BASE_URL.rstrip("/")
if not force_refresh and cache_key in _pricing_cache:
return _pricing_cache[cache_key]
try:
req = urllib.request.Request(
f"{cache_key}/models",
headers={"Accept": "application/json"},
)
with urllib.request.urlopen(req, timeout=timeout) as resp:
payload = json.loads(resp.read().decode())
except Exception:
_pricing_cache[cache_key] = {}
return {}
result: dict[str, dict[str, str]] = {}
for item in payload.get("data", []):
if not isinstance(item, dict):
continue
mid = item.get("id")
pricing = item.get("pricing")
if not (mid and isinstance(pricing, dict)):
continue
entry: dict[str, str] = {
"prompt": str(pricing.get("input", "")),
"completion": str(pricing.get("output", "")),
}
if pricing.get("input_cache_read"):
entry["input_cache_read"] = str(pricing["input_cache_read"])
if pricing.get("input_cache_write"):
entry["input_cache_write"] = str(pricing["input_cache_write"])
result[mid] = entry
_pricing_cache[cache_key] = result
return result
def _resolve_openrouter_api_key() -> str:
"""Best-effort OpenRouter API key for pricing fetch."""
return os.getenv("OPENROUTER_API_KEY", "").strip()
@@ -1790,7 +1962,7 @@ def _resolve_nous_pricing_credentials() -> tuple[str, str]:
def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> dict[str, dict[str, str]]:
"""Return live pricing for providers that support it (openrouter, nous, novita)."""
"""Return live pricing for providers that support it (openrouter, nous, ai-gateway, novita)."""
normalized = normalize_provider(provider)
if normalized == "openrouter":
return fetch_models_with_pricing(
@@ -1798,6 +1970,8 @@ def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> d
base_url="https://openrouter.ai/api",
force_refresh=force_refresh,
)
if normalized == "ai-gateway":
return fetch_ai_gateway_pricing(force_refresh=force_refresh)
if normalized == "novita":
return _fetch_novita_pricing(force_refresh=force_refresh)
if normalized == "deepinfra":
@@ -1882,8 +2056,9 @@ def _fetch_novita_pricing(
0.0001 USD. Convert them to the per-token strings used by the shared
pricing formatter.
Results are cached in ``_pricing_cache`` keyed on the resolved base URL —
without this, every menu render or pricing lookup re-hits the network.
Results are cached in ``_pricing_cache`` keyed on the resolved base URL,
matching the pattern used by ``fetch_ai_gateway_pricing`` — without this,
every menu render or pricing lookup re-hits the network.
"""
api_key = os.getenv("NOVITA_API_KEY", "").strip()
if not api_key:
@@ -2105,7 +2280,7 @@ def _model_in_provider_catalog(name_lower: str, providers: set[str]) -> bool:
_AGGREGATOR_PROVIDERS = frozenset(
{"nous", "openrouter", "copilot", "kilocode"}
{"nous", "openrouter", "ai-gateway", "copilot", "kilocode"}
)
# Subscription/OAuth providers whose catalogs RE-EXPOSE other vendors' models
@@ -2515,7 +2690,7 @@ def _resolve_copilot_catalog_api_key() -> str:
# - "nous": curated list and Portal /models endpoint are the source of
# truth for the subscription tier.
# Also excluded: providers that already have dedicated live-endpoint
# branches below (copilot, anthropic, ollama-cloud, custom,
# branches below (copilot, anthropic, ai-gateway, ollama-cloud, custom,
# stepfun, openai-codex) — those paths handle freshness themselves.
_MODELS_DEV_PREFERRED: frozenset[str] = frozenset({
"opencode-go",
@@ -2690,6 +2865,10 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
merged_lower.add(m.lower())
return merged
return list(_PROVIDER_MODELS.get("anthropic", []))
if normalized == "ai-gateway":
live = _fetch_ai_gateway_models()
if live:
return live
if normalized == "deepinfra":
# DeepInfra's generic /models endpoint mixes chat, image, video,
# speech, and embedding models. The tagged catalog helper is the only
@@ -4266,6 +4445,36 @@ def _fetch_deepinfra_pricing(
return result
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}",
"User-Agent": _HERMES_USER_AGENT,
}
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],