feat(honcho): async memory integration with prefetch pipeline and recallMode

Adds full Honcho memory integration to Hermes:

- Session manager with async background writes, memory modes (honcho/hybrid/local),
  and dialectic prefetch for first-turn context warming
- Agent integration: prefetch pipeline, tool surface gated by recallMode,
  system prompt context injection, SIGTERM/SIGINT flush handlers
- CLI commands: setup, status, mode, tokens, peer, identity, migrate
- recallMode setting (auto | context | tools) for A/B testing retrieval strategies
- Session strategies: per-session, per-repo (git tree root), per-directory, global
- Polymorphic memoryMode config: string shorthand or per-peer object overrides
- 97 tests covering async writes, client config, session resolution, and memory modes

cli.py

@@ -1440,7 +1440,7 @@ class HermesCLI:
                 platform="cli",
                 session_db=self._session_db,
                 clarify_callback=self._clarify_callback,
-                honcho_session_key=self.session_id,
+                honcho_session_key=None,  # resolved by run_agent via config sessions map / title
                 fallback_model=self._fallback_model,
                 thinking_callback=self._on_thinking,
                 checkpoints_enabled=self.checkpoints_enabled,
@@ -2573,6 +2573,26 @@ class HermesCLI:
                             try:
                                 if self._session_db.set_session_title(self.session_id, new_title):
                                     _cprint(f"  Session title set: {new_title}")
+                                    # Re-map Honcho session key to new title
+                                    if self.agent and getattr(self.agent, '_honcho', None):
+                                        try:
+                                            hcfg = self.agent._honcho_config
+                                            new_key = (
+                                                hcfg.resolve_session_name(
+                                                    session_title=new_title,
+                                                    session_id=self.agent.session_id,
+                                                )
+                                                if hcfg else new_title
+                                            )
+                                            if new_key and new_key != self.agent._honcho_session_key:
+                                                old_key = self.agent._honcho_session_key
+                                                self.agent._honcho.get_or_create(new_key)
+                                                self.agent._honcho_session_key = new_key
+                                                from tools.honcho_tools import set_session_context
+                                                set_session_context(self.agent._honcho, new_key)
+                                                _cprint(f"  Honcho session: {old_key} → {new_key}")
+                                        except Exception:
+                                            pass
                                 else:
                                     _cprint("  Session not found in database.")
                             except ValueError as e:
@@ -2886,6 +2906,12 @@ class HermesCLI:
                 f"  ✅ Compressed: {original_count} → {new_count} messages "
                 f"(~{approx_tokens:,} → ~{new_tokens:,} tokens)"
             )
+            # Flush Honcho async queue so queued messages land before context resets
+            if self.agent and getattr(self.agent, '_honcho', None):
+                try:
+                    self.agent._honcho.flush_all()
+                except Exception:
+                    pass
         except Exception as e:
             print(f"  ❌ Compression failed: {e}")
 
@@ -3322,7 +3348,8 @@ class HermesCLI:
                 if response and pending_message:
                     response = response + "\n\n---\n_[Interrupted - processing new message]_"
             
-            if response:
+            response_previewed = result.get("response_previewed", False) if result else False
+            if response and not response_previewed:
                 # Use a Rich Panel for the response box — adapts to terminal
                 # width at render time instead of hard-coding border length.
                 try:
@@ -3342,7 +3369,7 @@ class HermesCLI:
                     border_style=_resp_color,
                     padding=(1, 2),
                 ))
-            
+
             # Play terminal bell when agent finishes (if enabled).
             # Works over SSH — the bell propagates to the user's terminal.
             if self.bell_on_complete:
@@ -4254,6 +4281,12 @@ class HermesCLI:
             # Unregister terminal_tool callbacks to avoid dangling references
             set_sudo_password_callback(None)
             set_approval_callback(None)
+            # Flush + shut down Honcho async writer (drains queue before exit)
+            if self.agent and getattr(self.agent, '_honcho', None):
+                try:
+                    self.agent._honcho.shutdown()
+                except Exception:
+                    pass
             # Close session in SQLite
             if hasattr(self, '_session_db') and self._session_db and self.agent:
                 try: