mesh-wrapper

Agent Mesh Wrapper v3.0 (A2A-Enhanced)

Purpose

Enable lateral agent communication with full A2A protocol semantics — for all tier levels.

v3.0 Key Additions:

• DELEGATE — any agent can directly task a peer (same tier or below only)
• SUBSCRIBE/NOTIFY — agents register for events; peers fire notifications when ready
• CACHE — agents broadcast learned data (selectors, schemas, patterns) to all peers
• Tier-1 activation — mesh now available for ANY task, not just Tier-2+

Original innovation preserved: Agents communicate directly without orchestrator bottleneck, achieving 2-10x speedup on large tasks through parallel execution and knowledge sharing.

When to Use

• AUTO-ENABLED (Tier-2+): Tasks with 2+ packets — full mesh with heartbeats
• ON-DEMAND (Tier-1): Single-packet tasks use A2A lightweight mode (DELEGATE, SUBSCRIBE, CACHE) without full mesh infrastructure
• Parallel feature work across multiple agents
• Knowledge sharing between agents (dependencies, conflicts, optimizations, learned selectors)
• Direct task delegation without conductor round-trip
• Event-driven pipelines (forge notifies a peer when a batch is ready)

Why All Tiers:

• A2A DELEGATE/CACHE messages are lightweight — no heartbeat overhead needed
• A single agent needing peer validation mid-work shouldn't require a Tier-2 mesh spin-up
• Full mesh (heartbeats, state.json, rate limiting) still only activates at Tier-2+

Protocol

Step 1: Mesh Participation Check

From packet assignment:

• Count total packets
• If packets >= 2 → Enable full mesh mode (heartbeats, state.json, rate limiting)
• If packets < 2 → Enable A2A lightweight mode (DELEGATE/SUBSCRIBE/CACHE only, no heartbeats)

def get_mesh_mode(packet_count):
    """Determine mesh activation level based on packet count."""
    if packet_count >= 2:
        return "full"        # Heartbeats, state.json, full rate limiting
    else:
        return "a2a_lite"    # DELEGATE/SUBSCRIBE/CACHE only, no overhead