fix(honcho): move context injection from system prompt to prefetch, fix honcho_context crash

- system_prompt_block() now returns static header only (matching ABC contract)
  All other providers already did this; Honcho was the only one baking live
  user data into system prompt, freezing it on turn 1 forever

- prefetch() assembles two layers:
  Layer 1: base context (representation + card) from peer.context(), cached
  and refreshed on context_cadence (not frozen)
  Layer 2: dialectic supplement, refreshed on dialectic_cadence

- Context and dialectic cadence now checked independently in queue_prefetch()
  Previously context refresh was gated behind dialectic cadence

- Fix honcho_context tool crash: Honcho SDK Message objects use .peer_id
  not .role — was silently returning 'No context available yet' due to
  AttributeError caught by broad except

plugins/memory/honcho/session.py

@@ -942,7 +942,7 @@ class HonchoSessionManager:
             if ctx.messages:
                 recent = ctx.messages[-10:]  # last 10 messages
                 result["recent_messages"] = [
-                    {"role": m.role, "content": m.content[:500]}
+                    {"role": getattr(m, "peer_id", "unknown"), "content": (m.content or "")[:500]}
                     for m in recent
                 ]