Validation

Golden Flows

The 5 normative integration scenarios that every MPLP-conformant runtime is expected to pass. These flows serve as the 'integration tests' for the protocol.

Terminology Note

  • Flow-01~05 = Protocol Test Scenarios (defined in main repository)
  • LG-01~05 = Lifecycle Guarantees (Lab adjudication targets)

These are distinct naming spaces and should not be conflated. See Lifecycle Guarantees (LG-01~05) in Validation Lab →

Golden Flows are formally defined in the MPLP Protocol Specification.

See: governance/CONFORMANCE_MODEL.md for normative requirements.

flow-01

Single Agent – Happy Path

The baseline single-agent workflow. Agent receives context, generates a minimal 2-step plan, executes, and produces trace.

1

Context Creation

Context established with domain and environment.

2

Plan Generation

2-step plan created with deterministic UUIDs.

3

Task Execution

Steps executed in dependency order.

4

Trace Recording

All state transitions recorded.

5

Verification

Output validated against expected fixtures.

Normative Scope: Context · Plan · Trace

flow-02

Single Agent – Large Plan

Volumetric validation with 20+ steps. Tests protocol handling of large execution plans.

1

Large Context

Context framing batch processing scenario.

2

Multi-Step Plan

20-30 heterogeneous steps with dependencies.

3

Volumetric Execution

Steps processed with wildcard invariant validation.

4

Trace Verification

Events ordered correctly despite volume.

Normative Scope: Context · Plan · Trace

flow-03

Single Agent – With Tools

Tool integration via agent_role field. Validates protocol semantics for tool-enabled workflows.

1

Tool Context

Context for API testing workflow.

2

Tool Steps

Steps with agent_role: curl_executor, jq_processor.

3

Role-Based Execution

Each role handles specific tool type.

4

Result Capture

Tool outputs recorded in trace.

Normative Scope: Context · Plan · Trace · Extension

flow-04

Single Agent with LLM Enrichment

AEL (Action Execution Loop) integration. Validates LLM-enriched plan generation.

1

Initial Context

Context with high-level intent.

2

LLM Enrichment

AEL generates enriched plan from intent.

3

Plan Validation

Enriched plan passes schema validation.

4

Execution

Plan executed with full traceability.

Normative Scope: Context · Plan · Trace · Core

flow-05

Single Agent with Confirm Required

Multi-round approval workflow. Validates Confirm module integration.

1

Plan Creation

Plan requiring confirmation before execution.

2

Confirm Request

Confirmation request created with approver_role.

3

Approval/Rejection

Decision captured with timestamp and notes.

4

Conditional Execution

Plan proceeds only if approved.

Normative Scope: Context · Plan · Confirm · Trace

sa-flow-01

SA Basic Execution

Single-Agent (SA) profile baseline. Single-step execution with full lifecycle.

1

SA Initialize

SA profile initialization.

2

Load Context

Context loaded with SA-specific fields.

3

Execute Step

Single step executed with agent_role.

4

Complete

SA lifecycle completed cleanly.

Normative Scope: Context · Plan

sa-flow-02

SA Multi-Step Evaluation

SA profile with multi-step plan. Validates step sequencing in SA mode.

1

Multi-Step Plan

Plan with multiple ordered steps.

2

Sequential Execution

Steps processed by order_index.

3

State Tracking

Each step status updated correctly.

Normative Scope: Context · Plan

map-flow-01

MAP Turn-Taking Session

Multi-Agent Protocol with turn-taking. Two agents collaborate with role rotation.

1

Session Init

MAP session with round_robin mode.

2

Role Assignment

Agent A (planner), Agent B (reviewer).

3

Turn 1: Plan

Planner creates initial plan.

4

Turn 2: Review

Reviewer evaluates plan.

5

Turn 3: Revise

Planner revises based on feedback.

Normative Scope: Context · Plan · Collab · Role

map-flow-02

MAP Broadcast Fan-out

Multi-Agent Protocol with broadcast. Parallel dispatch to multiple agents.

1

Broadcast Init

MAP session with broadcast mode.

2

Multi-Participant

3+ agents registered.

3

Parallel Dispatch

Task broadcast to all participants.

4

Result Collection

Responses collected from all agents.

5

Aggregation

Results merged into final output.

Normative Scope: Context · Plan · Collab · Role

Normative

Protocol Conformance Boundary

Golden Flows define the minimum executable scenarios required for MPLP conformance. They are not examples, tutorials, or best practices.

Implementations may be evaluated against Golden Flows as described in the specification.

Canonical References

This website provides discovery and positioning content only. Normative requirements live in Docs; the ultimate source of truth is the Repository.

Next Steps

Evidence is evaluated through documentation-defined scenarios and replayable artifacts. This website does not certify or endorse implementations.

Positioning Notice: This website provides discovery and positioning content only. For formal protocol definitions, see docs.mplp.io. Source of truth: GitHub Repository.