Validation

Golden Flows

Website summary of 9 published MPLP flow scenarios. FLOW-01~05 form the core v1.0 published boundary; SA-FLOW-01~02 and MAP-FLOW-01~02 are profile-level reference scenarios.

Terminology Note

  • FLOW-01~05 = Core published-boundary scenarios
  • SA-FLOW / MAP-FLOW = profile-level reference scenarios
  • LG-01~05 = Validation Lab lifecycle guarantees

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

Website Source Model

This page renders the Website aggregate projection layer for Golden Flows. It is not a protocol-truth registry.

Upstream provenance: IDs, titles, and core-boundary classification are governed in tests/golden/flows/registry.ts; per-flow scenario detail is summarized from the upstream repo assets under tests/golden/flows/*. Docs remains the secondary reference projection at Golden Flow Registry.

Core Conformance Boundary

FLOW-01~05 define the published v1.0 core boundary. These are the primary protocol-side scenarios implementations are expected to satisfy.

flow-01
Core Boundary

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.

Evaluated Scope: Context · Plan · Trace

flow-02
Core Boundary

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.

Evaluated Scope: Context · Plan · Trace

flow-03
Core Boundary

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.

Evaluated Scope: Context · Plan · Trace · Extension

flow-04
Core Boundary

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.

Evaluated Scope: Context · Plan · Trace · Core

flow-05
Core Boundary

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.

Evaluated Scope: Context · Plan · Confirm · Trace

SA Profile Reference Flows

SA-FLOW-01~02 are profile-level reference scenarios. They inform Single-Agent profile evaluation, but they do not expand the core v1.0 published boundary.

sa-flow-01
Profile Reference

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.

Evaluated Scope: Context · Plan

sa-flow-02
Profile Reference

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.

Evaluated Scope: Context · Plan

MAP Profile Reference Flows

MAP-FLOW-01~02 are profile-level reference scenarios for multi-agent coordination modes. They are reference flows, not additional core-boundary scenarios.

map-flow-01
Profile Reference

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.

Evaluated Scope: Context · Plan · Collab · Role

map-flow-02
Profile Reference

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.

Evaluated Scope: Context · Plan · Collab · Role

Boundary

How To Read This Page

Website summarizes the published flow set, but it does not replace the upstream registry, per-flow repo assets, or Docs verification reference pages.

Read FLOW-01~05 as the core published boundary. Read SA/MAP flows as profile-level reference scenarios that remain upstream-governed by the same verified asset chain.

Canonical References

This website provides discovery and positioning content only. The canonical website definition anchor is /what-is-mplp. Documentation and Repository provide the authoritative documentation chain.

Next Steps

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