Creates a new tracker for a fresh AI run. Each call mints a new runId (a UUIDv4) that LaunchDarkly uses to correlate the run's events in metrics views. Call this once per AI run; metrics from different runIds cannot be combined.
Whether the configuration is enabled.
Internal evaluatorEvaluator for this agent config. Populated at evaluation time. Not part of the flag value shape.
Optional instructionsInstructions for the agent.
Optional judgeJudge configuration for AI Configs being evaluated. References judge AI Configs that should evaluate this AI Config.
The key of the AI Config.
Optional modelOptional model configuration.
Optional providerOptional configuration for the provider.
Optional toolsRoot-level tools map keyed by tool name. Distinct from model.parameters.tools[].
Generated using TypeDoc
Agent-specific AI Config with instructions.