feat: multi-instance support — agent_name and user_name configurable

All hardcoded "Inara"/"Scott" strings replaced with settings.agent_name
and settings.user_name, read from .env at startup:

- config.py: AGENT_NAME and USER_NAME settings (defaults: Inara / Scott)
- llm_client.py: conversation labels in prompt builder
- session_logger.py: **Name:** labels in session log markdown
- memory_distiller.py: distillation system prompts (mid + long)
- routers/nextcloud_talk.py: @mention prefix strip
- routers/google_chat.py: greeting message

Second instance scaffolding:
- holly/: identity directory with placeholder files (USER_NAME=Holly,
  AGENT_NAME to be chosen by Holly)
- cortex/.env.holly: config for Holly's instance on port 8001
- cortex-holly.service: systemd unit for the second instance

No behavioural change to the Inara/Scott instance — defaults unchanged.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cortex/llm_client.py

@@ -193,7 +193,7 @@ def _build_conversation(messages: list[dict]) -> str:
     if prior:
         history_lines = []
         for msg in prior:
-            label = "Scott" if msg["role"] == "user" else "Inara"
+            label = settings.user_name if msg["role"] == "user" else settings.agent_name
             history_lines.append(f"{label}: {msg['content']}")
         parts.append("<conversation>\n" + "\n\n".join(history_lines) + "\n</conversation>")
     parts.append(messages[-1]["content"] if messages else "")