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.
Single Agent – Happy Path
The baseline single-agent workflow. Agent receives context, generates a minimal 2-step plan, executes, and produces trace.
Context Creation
Plan Generation
Task Execution
Trace Recording
Verification
Context Creation
Context established with domain and environment.
Plan Generation
2-step plan created with deterministic UUIDs.
Task Execution
Steps executed in dependency order.
Trace Recording
All state transitions recorded.
Verification
Output validated against expected fixtures.
Evaluated Scope: Context · Plan · Trace
Single Agent – Large Plan
Volumetric validation with 20+ steps. Tests protocol handling of large execution plans.
Large Context
Multi-Step Plan
Volumetric Execution
Trace Verification
Large Context
Context framing batch processing scenario.
Multi-Step Plan
20-30 heterogeneous steps with dependencies.
Volumetric Execution
Steps processed with wildcard invariant validation.
Trace Verification
Events ordered correctly despite volume.
Evaluated Scope: Context · Plan · Trace
Single Agent – With Tools
Tool integration via agent_role field. Validates protocol semantics for tool-enabled workflows.
Tool Context
Tool Steps
Role-Based Execution
Result Capture
Tool Context
Context for API testing workflow.
Tool Steps
Steps with agent_role: curl_executor, jq_processor.
Role-Based Execution
Each role handles specific tool type.
Result Capture
Tool outputs recorded in trace.
Evaluated Scope: Context · Plan · Trace · Extension
Single Agent with LLM Enrichment
AEL (Action Execution Loop) integration. Validates LLM-enriched plan generation.
Initial Context
LLM Enrichment
Plan Validation
Execution
Initial Context
Context with high-level intent.
LLM Enrichment
AEL generates enriched plan from intent.
Plan Validation
Enriched plan passes schema validation.
Execution
Plan executed with full traceability.
Evaluated Scope: Context · Plan · Trace · Core
Single Agent with Confirm Required
Multi-round approval workflow. Validates Confirm module integration.
Plan Creation
Confirm Request
Approval/Rejection
Conditional Execution
Plan Creation
Plan requiring confirmation before execution.
Confirm Request
Confirmation request created with approver_role.
Approval/Rejection
Decision captured with timestamp and notes.
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 Basic Execution
Single-Agent (SA) profile baseline. Single-step execution with full lifecycle.
SA Initialize
Load Context
Execute Step
Complete
SA Initialize
SA profile initialization.
Load Context
Context loaded with SA-specific fields.
Execute Step
Single step executed with agent_role.
Complete
SA lifecycle completed cleanly.
Evaluated Scope: Context · Plan
SA Multi-Step Evaluation
SA profile with multi-step plan. Validates step sequencing in SA mode.
Multi-Step Plan
Sequential Execution
State Tracking
Multi-Step Plan
Plan with multiple ordered steps.
Sequential Execution
Steps processed by order_index.
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 Turn-Taking Session
Multi-Agent Protocol with turn-taking. Two agents collaborate with role rotation.
Session Init
Role Assignment
Turn 1: Plan
Turn 2: Review
Turn 3: Revise
Session Init
MAP session with round_robin mode.
Role Assignment
Agent A (planner), Agent B (reviewer).
Turn 1: Plan
Planner creates initial plan.
Turn 2: Review
Reviewer evaluates plan.
Turn 3: Revise
Planner revises based on feedback.
Evaluated Scope: Context · Plan · Collab · Role
MAP Broadcast Fan-out
Multi-Agent Protocol with broadcast. Parallel dispatch to multiple agents.
Broadcast Init
Multi-Participant
Parallel Dispatch
Result Collection
Aggregation
Broadcast Init
MAP session with broadcast mode.
Multi-Participant
3+ agents registered.
Parallel Dispatch
Task broadcast to all participants.
Result Collection
Responses collected from all agents.
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.
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.
Evidence is evaluated through documentation-defined scenarios and replayable artifacts. This website does not certify or endorse implementations.