AbstractOptionallogger: LDLoggerCreate a Runner for an agent AI Config.
Override in provider subclasses to return a configured Runner.
Default implementation returns undefined.
Optional_tools: ToolRegistryPromise resolving to a Runner, or undefined if this
provider does not support agent creation.
Create an AgentGraphRunner for an agent graph definition.
Override in provider subclasses to return a configured AgentGraphRunner.
Default implementation returns undefined.
Optional_tools: ToolRegistryPromise resolving to an AgentGraphRunner, or undefined if
this provider does not support graph execution.
Create a Runner for a completion or judge AI Config.
Override in provider subclasses to return a configured Runner.
Default implementation returns undefined.
Promise resolving to a Runner, or undefined if this
provider does not support model creation.
Abstract base class for AI providers.
An
AIProvideris a per-provider factory: it is instantiated once per provider package and is responsible for constructing focused runtime capability objects via createModel, createAgent, and createAgentGraph.Provider packages subclass
AIProviderand override the methods they support. The default implementations returnundefined, mirroring Python's base-class behaviour, so providers only need to implement the modes they actually support.