feat: add Honcho AI-native memory integration

Opt-in persistent cross-session user modeling via Honcho. Reads
~/.honcho/config.json as single source of truth (shared with
Claude Code, Cursor, and other Honcho-enabled tools). Zero impact
when disabled or unconfigured.

- honcho_integration/ package (client, session manager, peer resolution)
- Host-based config resolution matching claude-honcho/cursor-honcho pattern
- Prefetch user context into system prompt per conversation turn
- Sync user/assistant messages to Honcho after each exchange
- query_user_context tool for mid-conversation dialectic reasoning
- Gated activation: requires ~/.honcho/config.json with enabled=true

gateway/run.py

@@ -1444,6 +1444,7 @@ class GatewayRunner:
                 session_id=session_id,
                 tool_progress_callback=progress_callback if tool_progress_enabled else None,
                 platform=platform_key,
+                honcho_session_key=session_key,
             )
             
             # Store agent reference for interrupt support