Module: dialog

Dialog Module

Defines message format compatible with OpenAI/Anthropic, role semantics, and lifecycle management.

Status: Frozen

Usage Boundary: This page provides an evaluative summary and a canonical schema excerpt for convenience. The authoritative, versioned specification remains on docs.mplp.io. MPGC does not issue certifications, badges, or endorsements; adoption and conformance are self-assessed by the adopting organization.

Definition

Protocol Role

The normative responsibility of this module.

The Dialog module defines how messages are exchanged within an MPLP execution.

It provides the communication channel for agents, humans, and systems — without defining message semantics or driving execution decisions.

Dialog is a transport layer, not a decision layer.

Architecture

Interaction Model

Dependencies and event emissions.

Dependencies

  • Context: Dialog MUST reference a valid context_id.
  • Role: Participants are identified by their assigned Role.

Observability

  • Trace: All dialog events MUST be recorded.
  • Dialog does NOT directly affect Plan status.

Compliance

Key Constraints

Essential requirements for this module.

  1. Dialog entries MUST reference a valid context_id.
  2. All messages MUST be traceable.
  3. Unauthorized participants MUST NOT emit dialog events.

Specification

Canonical Schema

The normative JSON structure for this module.

{
  "required": [
    "meta",
    "dialog_id",
    "context_id",
    "status",
    "messages"
  ],
  "optional": [
    "thread_id",
    "started_at",
    "ended_at",
    "trace",
    "events",
    "governance"
  ],
  "messageObject": {
    "required": [
      "role",
      "content",
      "timestamp"
    ],
    "roleEnum": [
      "user",
      "assistant",
      "system",
      "agent"
    ]
  }
}

Behavior

Lifecycle

Valid states and transitions.

Status Enum

activepausedcompletedarchived

Evaluation Path

Governance → Compliance → Golden Flows → Adoption Signals