fix: deep audit round 2 — non-streaming mode config + ClarificationCard + settings restructure

HIGH fixes:
- H-NS-1: Non-streaming agent_chat now builds ChatModeConfig and calls
  send_message_with_chat_mode(), matching the streaming path
- H-FE-1: ClarificationCard component renders structured clarification
  questions with type badge, question text, and numbered options
- H-SEM-1: SemanticSkillRouter annotated as @reserved (Phase 3 wiring)

MEDIUM fixes:
- M-SETTINGS-1: Settings menu restructured with "高级" section separator;
  skills/audit/tasks/heartbeat/semantic-memory grouped under advanced
- M-MAN-1: LoopEvent→StreamChatEvent mapping completeness checklist
  added as documentation comment in agent_chat_stream loop
- M-ORPH-1: Deleted orphaned Automation/ and SkillMarket/ files,
  plus transitively orphaned types, hooks, and adapters

crates/zclaw-skills/src/semantic_router.rs

@@ -4,6 +4,10 @@
 //! 1. TF-IDF based text similarity (always available, no external deps)
 //! 2. Optional embedding similarity (when an Embedder is configured)
 //! 3. Optional LLM fallback for ambiguous cases
+//!
+//! **@reserved** — This module is fully implemented (719 lines, 200+ lines of tests)
+//! but NOT yet wired into the message pipeline. It will be activated in Phase 3
+//! when the "butler mode" semantic auto-routing feature is enabled. Do NOT delete.
 
 use std::collections::HashMap;
 use std::sync::Arc;