Add Nextcloud Talk bot integration (Inara)

- New routers/nextcloud_talk.py: webhook handler verifies incoming HMAC,
  calls LLM via BackgroundTasks, posts reply with correctly computed
  signature (random + message_text, not raw body)
- llm_client.py: read Claude OAuth token live from
  ~/.claude/.credentials.json to avoid stale systemd env tokens;
  strip conflicting ANTHROPIC_API_KEY
- config.py: add nextcloud_url, nextcloud_talk_bot_secret,
  nextcloud_talk_timeout settings
- main.py: register nextcloud_talk router, add logging setup
- docs/NEXTCLOUD_TALK_BOT.md: installation guide + HMAC signing gotcha

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

cortex/main.py

@@ -1,11 +1,14 @@
+import logging
 from contextlib import asynccontextmanager
 from fastapi import FastAPI
 from fastapi.staticfiles import StaticFiles
 from fastapi.responses import FileResponse
 import uvicorn
 
+logging.basicConfig(level=logging.INFO, format="%(levelname)s:%(name)s: %(message)s")
+
 from config import settings
-from routers import chat, google_chat
+from routers import chat, google_chat, nextcloud_talk
 
 
 @asynccontextmanager
@@ -19,6 +22,7 @@ app = FastAPI(title="Cortex Dispatcher", lifespan=lifespan)
 
 app.include_router(chat.router)
 app.include_router(google_chat.router)
+app.include_router(nextcloud_talk.router)
 app.mount("/static", StaticFiles(directory="static"), name="static")