Documentation
¶
Overview ¶
Package responder implements an LLM-backed surrogate user that answers an interactive skill's follow-up questions during a multi-turn evaluation run.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Classifier ¶
type Classifier struct {
// contains filtered or unexported fields
}
Classifier maintains a persistent surrogate-user session and classifies each agent message into a Decision.
func New ¶
func New(exec Executor, cfg models.ResponderConfig, defaultModel string) *Classifier
New constructs a Classifier. defaultModel is used when cfg.Model is empty.
type Decision ¶
type Decision struct {
Kind DecisionKind
Answer string // set when Kind == DecisionReply
Reason string // set when Kind == DecisionAbstain
}
Decision is the outcome of classifying a single agent message.
type DecisionKind ¶
type DecisionKind int
DecisionKind enumerates the responder's possible classifications of an agent message.
const ( // DecisionReply means the responder answered the agent's question. DecisionReply DecisionKind = iota // DecisionStop means the agent is done and no further input is needed. DecisionStop // DecisionAbstain means the responder could not answer from its brief. DecisionAbstain )
type Executor ¶
type Executor interface {
Execute(ctx context.Context, req *execution.ExecutionRequest) (*execution.ExecutionResponse, error)
}
Executor is the narrow execution surface the responder needs. The concrete AgentEngine satisfies it, and tests supply a fake.
Source Files
Click to show internal directories.
Click to hide internal directories.