mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-06-17 02:05:22 -04:00
feat(ai): add OpenRouter and Ollama Cloud providers (#231)
Co-authored-by: Alex Kenley <Alex.Kenley@threatvectorsecurity.com>
This commit is contained in:
+69
-14
@@ -16,12 +16,60 @@ from core.database import SessionLocal, ModelEndpoint, Session as DbSession
|
||||
from core.middleware import require_admin
|
||||
from src.llm_core import _detect_provider, ANTHROPIC_MODELS
|
||||
from src.settings import load_settings as _load_settings, save_settings as _save_settings
|
||||
from src.endpoint_resolver import normalize_base as _normalize_base, build_chat_url, build_headers, _anthropic_api_root
|
||||
from src.endpoint_resolver import normalize_base as _normalize_base, build_chat_url
|
||||
from src.auth_helpers import owner_filter
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _anthropic_api_root(base: str) -> str:
|
||||
"""Return Anthropic's API root without duplicating /v1."""
|
||||
base = (base or "").strip().rstrip("/")
|
||||
host = urlparse(base).hostname or ""
|
||||
if host.endswith("anthropic.com") and base.endswith("/v1"):
|
||||
return base[:-3].rstrip("/")
|
||||
return base
|
||||
|
||||
|
||||
def _ollama_api_root(base: str) -> str:
|
||||
"""Return Ollama's native API root without depending on deferred imports."""
|
||||
base = (base or "").strip().rstrip("/")
|
||||
parsed = urlparse(base)
|
||||
host = parsed.hostname or ""
|
||||
path = (parsed.path or "").rstrip("/")
|
||||
if path.endswith("/api"):
|
||||
return base
|
||||
if host.endswith("ollama.com"):
|
||||
root = f"{parsed.scheme}://{parsed.netloc}" if parsed.scheme and parsed.netloc else "https://ollama.com"
|
||||
return root.rstrip("/") + "/api"
|
||||
return base
|
||||
|
||||
|
||||
def _models_url(base: str) -> str:
|
||||
"""Return provider-specific model-list URL for route-local probing."""
|
||||
provider = _detect_provider(base)
|
||||
host = urlparse(base).hostname or ""
|
||||
if provider == "anthropic" or host.endswith("anthropic.com"):
|
||||
return _anthropic_api_root(base) + "/v1/models"
|
||||
if provider == "ollama" or host.endswith("ollama.com"):
|
||||
return _ollama_api_root(base) + "/tags"
|
||||
return base.rstrip("/") + "/models"
|
||||
|
||||
|
||||
def _provider_headers(api_key: Optional[str], base: str) -> Dict[str, str]:
|
||||
"""Build provider auth headers without depending on import-time stubs."""
|
||||
if not api_key:
|
||||
return {}
|
||||
provider = _detect_provider(base)
|
||||
host = urlparse(base).hostname or ""
|
||||
if provider == "anthropic" or host.endswith("anthropic.com"):
|
||||
return {
|
||||
"x-api-key": api_key,
|
||||
"anthropic-version": "2023-06-01",
|
||||
}
|
||||
return {"Authorization": f"Bearer {api_key}"}
|
||||
|
||||
|
||||
# ── Curated model lists per provider ──
|
||||
# For cloud providers that return 100+ models, only show these by default.
|
||||
# A model ID matches if it starts with or equals a curated entry.
|
||||
@@ -87,6 +135,7 @@ _URL_TO_CURATED = {
|
||||
"generativelanguage.googleapis.com": "google",
|
||||
"api.x.ai": "xai",
|
||||
"openrouter.ai": "openrouter",
|
||||
"ollama.com": "ollama",
|
||||
}
|
||||
|
||||
|
||||
@@ -183,9 +232,15 @@ def _probe_single_model(base: str, api_key: str, model_id: str, timeout: int = 1
|
||||
payload = _build_anthropic_payload(model_id, messages, 0.0, 5)
|
||||
if _test_tools:
|
||||
payload["tools"] = [{"name": "test", "description": "Test tool", "input_schema": {"type": "object", "properties": {}}}]
|
||||
elif provider == "ollama":
|
||||
from src.llm_core import _build_ollama_payload
|
||||
target_url = build_chat_url(base)
|
||||
h = _provider_headers(api_key, base)
|
||||
h["Content-Type"] = "application/json"
|
||||
payload = _build_ollama_payload(model_id, messages, 0.0, 5, stream=False, tools=_test_tools)
|
||||
else:
|
||||
target_url = build_chat_url(base)
|
||||
h = build_headers(api_key, base)
|
||||
h = _provider_headers(api_key, base)
|
||||
h["Content-Type"] = "application/json"
|
||||
from src.llm_core import _uses_max_completion_tokens
|
||||
_max_key = "max_completion_tokens" if _uses_max_completion_tokens(model_id) else "max_tokens"
|
||||
@@ -276,10 +331,8 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
|
||||
return []
|
||||
logger.warning(f"Anthropic /v1/models failed, using hardcoded list: {e}")
|
||||
return list(ANTHROPIC_MODELS)
|
||||
url = base + "/models"
|
||||
headers = {}
|
||||
if api_key:
|
||||
headers["Authorization"] = f"Bearer {api_key}"
|
||||
url = _models_url(base)
|
||||
headers = _provider_headers(api_key, base)
|
||||
try:
|
||||
r = httpx.get(url, headers=headers, timeout=timeout)
|
||||
r.raise_for_status()
|
||||
@@ -494,10 +547,7 @@ def setup_model_routes(model_discovery):
|
||||
pass
|
||||
model_ids = [m for m in model_ids if m not in hidden]
|
||||
# Build correct URL based on provider
|
||||
if provider == "anthropic":
|
||||
chat_url = build_chat_url(base)
|
||||
else:
|
||||
chat_url = base + "/chat/completions"
|
||||
chat_url = build_chat_url(base)
|
||||
category = _classify_endpoint(base)
|
||||
|
||||
if model_ids:
|
||||
@@ -671,10 +721,8 @@ def setup_model_routes(model_discovery):
|
||||
entry["error"] = str(e)
|
||||
entry["model_count"] = 0
|
||||
else:
|
||||
url = base + "/models"
|
||||
headers = {}
|
||||
if ep.api_key:
|
||||
headers["Authorization"] = f"Bearer {ep.api_key}"
|
||||
url = _models_url(base)
|
||||
headers = _provider_headers(ep.api_key, base)
|
||||
try:
|
||||
t0 = _time.time()
|
||||
r = httpx.get(url, headers=headers, timeout=5)
|
||||
@@ -682,6 +730,12 @@ def setup_model_routes(model_discovery):
|
||||
r.raise_for_status()
|
||||
data = r.json()
|
||||
models = [m.get("id") for m in (data.get("data") or []) if m.get("id")]
|
||||
if not models:
|
||||
models = [
|
||||
m.get("name") or m.get("model")
|
||||
for m in (data.get("models") or [])
|
||||
if m.get("name") or m.get("model")
|
||||
]
|
||||
entry["status"] = "online"
|
||||
entry["model_count"] = len(models)
|
||||
except Exception as e:
|
||||
@@ -896,6 +950,7 @@ def setup_model_routes(model_discovery):
|
||||
for suffix in ["/models", "/chat/completions", "/completions", "/v1/messages"]:
|
||||
if base_url.endswith(suffix):
|
||||
base_url = base_url[:-len(suffix)].rstrip("/")
|
||||
base_url = _normalize_base(base_url)
|
||||
if not base_url:
|
||||
raise HTTPException(400, "Base URL is required")
|
||||
# Resolve hostname via Tailscale if DNS fails
|
||||
|
||||
Reference in New Issue
Block a user