WIP
- OpenRouter model configuration registry - Model definition file for users to be able to control - Update instructions
This commit is contained in:
Fahad
@@ -2,13 +2,16 @@
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
from .base import (
|
||||
ModelCapabilities,
|
||||
ModelResponse,
|
||||
ProviderType,
|
||||
RangeTemperatureConstraint,
|
||||
)
|
||||
from .openai_compatible import OpenAICompatibleProvider
|
||||
from .openrouter_registry import OpenRouterModelRegistry
|
||||
|
||||
|
||||
class OpenRouterProvider(OpenAICompatibleProvider):
|
||||
@@ -26,6 +29,9 @@ class OpenRouterProvider(OpenAICompatibleProvider):
|
||||
"X-Title": os.getenv("OPENROUTER_TITLE", "Zen MCP Server"),
|
||||
}
|
||||
|
||||
# Model registry for managing configurations and aliases
|
||||
_registry: Optional[OpenRouterModelRegistry] = None
|
||||
|
||||
def __init__(self, api_key: str, **kwargs):
|
||||
"""Initialize OpenRouter provider.
|
||||
|
||||
@@ -36,49 +42,87 @@ class OpenRouterProvider(OpenAICompatibleProvider):
|
||||
# Always use OpenRouter's base URL
|
||||
super().__init__(api_key, base_url="https://openrouter.ai/api/v1", **kwargs)
|
||||
|
||||
# Log warning about model allow-list if not configured
|
||||
if not self.allowed_models:
|
||||
logging.warning(
|
||||
"OpenRouter provider initialized without model allow-list. "
|
||||
"Consider setting OPENROUTER_ALLOWED_MODELS environment variable "
|
||||
"to restrict model access and control costs."
|
||||
)
|
||||
# Initialize model registry
|
||||
if OpenRouterProvider._registry is None:
|
||||
OpenRouterProvider._registry = OpenRouterModelRegistry()
|
||||
|
||||
# Log loaded models and aliases
|
||||
models = self._registry.list_models()
|
||||
aliases = self._registry.list_aliases()
|
||||
logging.info(
|
||||
f"OpenRouter loaded {len(models)} models with {len(aliases)} aliases"
|
||||
)
|
||||
|
||||
def _parse_allowed_models(self) -> None:
|
||||
"""Override to disable environment-based allow-list.
|
||||
|
||||
OpenRouter model access is controlled via the OpenRouter dashboard,
|
||||
not through environment variables.
|
||||
"""
|
||||
return None
|
||||
|
||||
def _resolve_model_name(self, model_name: str) -> str:
|
||||
"""Resolve model aliases to OpenRouter model names.
|
||||
|
||||
Args:
|
||||
model_name: Input model name or alias
|
||||
|
||||
Returns:
|
||||
Resolved OpenRouter model name
|
||||
"""
|
||||
# Try to resolve through registry
|
||||
config = self._registry.resolve(model_name)
|
||||
|
||||
if config:
|
||||
if config.model_name != model_name:
|
||||
logging.info(f"Resolved model alias '{model_name}' to '{config.model_name}'")
|
||||
return config.model_name
|
||||
else:
|
||||
# If not found in registry, return as-is
|
||||
# This allows using models not in our config file
|
||||
logging.debug(f"Model '{model_name}' not found in registry, using as-is")
|
||||
return model_name
|
||||
|
||||
def get_capabilities(self, model_name: str) -> ModelCapabilities:
|
||||
"""Get capabilities for a model.
|
||||
|
||||
Since OpenRouter supports many models dynamically, we return
|
||||
generic capabilities with conservative defaults.
|
||||
|
||||
Args:
|
||||
model_name: Name of the model
|
||||
model_name: Name of the model (or alias)
|
||||
|
||||
Returns:
|
||||
Generic ModelCapabilities with warnings logged
|
||||
ModelCapabilities from registry or generic defaults
|
||||
"""
|
||||
logging.warning(
|
||||
f"Using generic capabilities for '{model_name}' via OpenRouter. "
|
||||
"Actual model capabilities may differ. Consider querying OpenRouter's "
|
||||
"/models endpoint for accurate information."
|
||||
)
|
||||
# Try to get from registry first
|
||||
capabilities = self._registry.get_capabilities(model_name)
|
||||
|
||||
# Create generic capabilities with conservative defaults
|
||||
capabilities = ModelCapabilities(
|
||||
provider=ProviderType.OPENROUTER,
|
||||
model_name=model_name,
|
||||
friendly_name=self.FRIENDLY_NAME,
|
||||
max_tokens=32_768, # Conservative default
|
||||
supports_extended_thinking=False, # Most models don't support this
|
||||
supports_system_prompts=True, # Most models support this
|
||||
supports_streaming=True,
|
||||
supports_function_calling=False, # Varies by model
|
||||
temperature_constraint=RangeTemperatureConstraint(0.0, 2.0, 1.0),
|
||||
)
|
||||
|
||||
# Mark as generic for validation purposes
|
||||
capabilities._is_generic = True
|
||||
|
||||
return capabilities
|
||||
if capabilities:
|
||||
return capabilities
|
||||
else:
|
||||
# Resolve any potential aliases and create generic capabilities
|
||||
resolved_name = self._resolve_model_name(model_name)
|
||||
|
||||
logging.debug(
|
||||
f"Using generic capabilities for '{resolved_name}' via OpenRouter. "
|
||||
"Consider adding to openrouter_models.json for specific capabilities."
|
||||
)
|
||||
|
||||
# Create generic capabilities with conservative defaults
|
||||
capabilities = ModelCapabilities(
|
||||
provider=ProviderType.OPENROUTER,
|
||||
model_name=resolved_name,
|
||||
friendly_name=self.FRIENDLY_NAME,
|
||||
max_tokens=32_768, # Conservative default context window
|
||||
supports_extended_thinking=False,
|
||||
supports_system_prompts=True,
|
||||
supports_streaming=True,
|
||||
supports_function_calling=False,
|
||||
temperature_constraint=RangeTemperatureConstraint(0.0, 2.0, 1.0),
|
||||
)
|
||||
|
||||
# Mark as generic for validation purposes
|
||||
capabilities._is_generic = True
|
||||
|
||||
return capabilities
|
||||
|
||||
def get_provider_type(self) -> ProviderType:
|
||||
"""Get the provider type."""
|
||||
@@ -87,23 +131,53 @@ class OpenRouterProvider(OpenAICompatibleProvider):
|
||||
def validate_model_name(self, model_name: str) -> bool:
|
||||
"""Validate if the model name is allowed.
|
||||
|
||||
For OpenRouter, we accept any model name unless an allow-list
|
||||
is configured via OPENROUTER_ALLOWED_MODELS environment variable.
|
||||
For OpenRouter, we accept any model name. OpenRouter will
|
||||
validate based on the API key's permissions.
|
||||
|
||||
Args:
|
||||
model_name: Model name to validate
|
||||
|
||||
Returns:
|
||||
True if model is allowed, False otherwise
|
||||
Always True - OpenRouter handles validation
|
||||
"""
|
||||
if self.allowed_models:
|
||||
# Case-insensitive validation against allow-list
|
||||
return model_name.lower() in self.allowed_models
|
||||
|
||||
# Accept any model if no allow-list configured
|
||||
# The API will return an error if the model doesn't exist
|
||||
# Accept any model name - OpenRouter will validate based on API key permissions
|
||||
return True
|
||||
|
||||
def generate_content(
|
||||
self,
|
||||
prompt: str,
|
||||
model_name: str,
|
||||
system_prompt: Optional[str] = None,
|
||||
temperature: float = 0.7,
|
||||
max_output_tokens: Optional[int] = None,
|
||||
**kwargs,
|
||||
) -> ModelResponse:
|
||||
"""Generate content using the OpenRouter API.
|
||||
|
||||
Args:
|
||||
prompt: User prompt to send to the model
|
||||
model_name: Name of the model (or alias) to use
|
||||
system_prompt: Optional system prompt for model behavior
|
||||
temperature: Sampling temperature
|
||||
max_output_tokens: Maximum tokens to generate
|
||||
**kwargs: Additional provider-specific parameters
|
||||
|
||||
Returns:
|
||||
ModelResponse with generated content and metadata
|
||||
"""
|
||||
# Resolve model alias to actual OpenRouter model name
|
||||
resolved_model = self._resolve_model_name(model_name)
|
||||
|
||||
# Call parent method with resolved model name
|
||||
return super().generate_content(
|
||||
prompt=prompt,
|
||||
model_name=resolved_model,
|
||||
system_prompt=system_prompt,
|
||||
temperature=temperature,
|
||||
max_output_tokens=max_output_tokens,
|
||||
**kwargs
|
||||
)
|
||||
|
||||
def supports_thinking_mode(self, model_name: str) -> bool:
|
||||
"""Check if the model supports extended thinking mode.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user