agents.base.types¶

Core type system for the Haive agent framework.

Defines type variables, constraints, and base protocols for type-safe agent design.

Classes¶

`Agent`	Complete agent protocol combining all capabilities.
`AgentInput`	Default input schema for agents.
`AgentOutput`	Default output schema for agents.
`AgentState`	Default state schema for agents.
`EngineProvider`	Protocol for objects that provide engines.
`GraphProvider`	Protocol for objects that provide graphs.
`GraphSegment`	Represents a segment of a graph that can be composed.
`HookContext`	Context passed to hooks.
`HookPoint`	Standard hook points in agent lifecycle.
`Invokable`	Protocol for objects that can be invoked.
`NodeConnection`	Represents a connection between nodes in a graph.
`StateProvider`	Protocol for objects that provide state schemas.

Module Contents¶

class agents.base.types.Agent¶

Bases: GraphProvider[TState], StateProvider[TState], Invokable[TInput, TOutput], EngineProvider[TEngine], Protocol[TEngine, TInput, TOutput, TState]

Complete agent protocol combining all capabilities.

class agents.base.types.AgentInput(/, **data)¶

Bases: pydantic.BaseModel

Default input schema for agents.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)

class agents.base.types.AgentOutput(/, **data)¶

Bases: pydantic.BaseModel

Default output schema for agents.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)

class agents.base.types.AgentState(/, **data)¶

Bases: pydantic.BaseModel

Default state schema for agents.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)

class agents.base.types.EngineProvider¶

Bases: Protocol[TEngine]

Protocol for objects that provide engines.

property engine: TEngine¶

Get the primary engine.

Return type:: TEngine

property engines: dict[str, haive.core.engine.base.Engine]¶

Get all engines.

Return type:: dict[str, haive.core.engine.base.Engine]

class agents.base.types.GraphProvider¶

Bases: Protocol[TState]

Protocol for objects that provide graphs.

build_graph()¶

Build and return the graph.

Return type:: Any

class agents.base.types.GraphSegment(/, **data)¶

Bases: pydantic.BaseModel, Generic[TState]

Represents a segment of a graph that can be composed.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)

class agents.base.types.HookContext(/, **data)¶

Bases: pydantic.BaseModel, Generic[TState]

Context passed to hooks.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)

class agents.base.types.HookPoint¶

Bases: str, enum.Enum

Standard hook points in agent lifecycle.

Initialize self. See help(type(self)) for accurate signature.

class agents.base.types.Invokable¶

Bases: Protocol[TInput, TOutput]

Protocol for objects that can be invoked.

async ainvoke(input_data, config=None)¶

Async invoke with input data.

Parameters:

input_data (TInput)
config (dict[str, Any] | None)

Return type:

TOutput

invoke(input_data, config=None)¶

Invoke with input data.

Parameters:

input_data (TInput)
config (dict[str, Any] | None)

Return type:

TOutput

class agents.base.types.NodeConnection(/, **data)¶

Bases: pydantic.BaseModel, Generic[TState]

Represents a connection between nodes in a graph.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)

class agents.base.types.StateProvider¶

Bases: Protocol[TState]

Protocol for objects that provide state schemas.

property state_schema: type[TState]¶

Get the state schema type.

Return type:: type[TState]