Member Junction
    Preparing search index...

    Interface MJAIAgentRunStepEntity_AgentSkillInvocation

    One skill's involvement in an agent run step — the observability contract for skills. AIAgentRunStep.Skills holds a JSON array of these (or NULL when no skills are in play), so every step touched by a skill records WHICH skill, HOW it entered the run, and the PROVENANCE OF AUTHORITY that admitted it.

    Population rules (implemented in BaseAgent):

    • Skill steps record the activation(s) they performed (with Reason when agent-initiated).
    • Prompt steps record the full set of skills in effect for that turn.
    • Actions / Sub-Agent steps record the skill(s) through which the executed tool became available; NULL means the tool was a native agent grant.

    Runtime twin: MJAIAgentRunStepEntity_AgentSkillInvocation in @memberjunction/ai-core-plus (agent-types.ts) — keep the two in sync.

    interface MJAIAgentRunStepEntity_AgentSkillInvocation {
        ActivationType: "requested" | "auto";
        Provenance: MJAIAgentRunStepEntity_AgentSkillInvocationProvenance;
        Reason?: string;
        SkillID: string;
        SkillName: string;
    }
    Index

    Properties

    ActivationType Provenance Reason? SkillID SkillName

    Properties

    ActivationType: "requested" | "auto"

    How the skill entered the run: explicit user request (/skill mention) or agent self-activation.

    Provenance: MJAIAgentRunStepEntity_AgentSkillInvocationProvenance

    The gate values that admitted this skill — recorded so auditors see the configuration that allowed it.

    Reason?: string

    Agent-stated rationale (only for ActivationType='auto').

    SkillID: string

    ID of the activated skill (MJ: AI Skills.ID).

    SkillName: string

    Name of the activated skill at activation time.

    Settings

    Member Visibility

    On This Page

    Properties