AgentContext class

A window of information injected into every LLM prompt.

The LLMCore compresses this context to fit within the token budget.

Constructors

AgentContext({required AgentGoal goal, List<AgentTask>? activeTasks, List<AgentObservation>? recentObservations, List<String>? workspaceConcepts, List<String>? retrievedMemories, Map<String, dynamic>? environment, int iterationNumber = 0})

Properties

activeTasks → List<AgentTask>
Tasks currently in the plan.
final
environment → Map<String, dynamic>
Key-value pairs describing the external environment state.
final
goal → AgentGoal
The goal being pursued.
final
hashCode → int
The hash code for this object.
no setterinherited
iterationNumber → int
How many agent-loop cycles have completed.
final
recentObservations → List<AgentObservation>
The most recent observations (tool results, sensor data).
final
retrievedMemories → List<String>
Memory snippets relevant to the goal (retrieved by the memory system).
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
workspaceConcepts → List<String>
Active concepts from the consciousness workspace.
final

Methods

copyWith({List<AgentTask>? activeTasks, List<AgentObservation>? recentObservations, List<String>? workspaceConcepts, List<String>? retrievedMemories, Map<String, dynamic>? environment, int? iterationNumber}) → AgentContext
Returns a copy with updated fields.
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toString() → String
A string representation of this object.
override

Operators

operator ==(Object other) → bool
The equality operator.
inherited