feat: brain service — self-contained second brain knowledge manager

Full backend service with:
- FastAPI REST API with CRUD, search, reprocess endpoints
- PostgreSQL + pgvector for items and semantic search
- Redis + RQ for background job processing
- Meilisearch for fast keyword/filter search
- Browserless/Chrome for JS rendering and screenshots
- OpenAI structured output for AI classification
- Local file storage with S3-ready abstraction
- Gateway auth via X-Gateway-User-Id header
- Own docker-compose stack (6 containers)

Classification: fixed folders (Home/Family/Work/Travel/Knowledge/Faith/Projects)
and fixed tags (28 predefined). AI assigns exactly 1 folder, 2-3 tags, title,
summary, and confidence score per item.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

gateway/config.py

@@ -59,6 +59,9 @@ OPENAI_MODEL = os.environ.get("OPENAI_MODEL", "gpt-5.2")
 
 # ── Session config ──
 SESSION_MAX_AGE = int(os.environ.get("SESSION_MAX_AGE", 30 * 86400))  # 30 days
+DEV_AUTO_LOGIN = os.environ.get("DEV_AUTO_LOGIN", "").lower() in {"1", "true", "yes", "on"}
+DEV_AUTO_LOGIN_USERNAME = os.environ.get("DEV_AUTO_LOGIN_USERNAME", "dev")
+DEV_AUTO_LOGIN_DISPLAY_NAME = os.environ.get("DEV_AUTO_LOGIN_DISPLAY_NAME", "Dev User")
 
 # ── Ensure data dir exists ──
 DATA_DIR.mkdir(parents=True, exist_ok=True)
@@ -66,4 +69,3 @@ DATA_DIR.mkdir(parents=True, exist_ok=True)
 # Note: All internal services use plain HTTP (Docker network).
 # No custom SSL context needed. External calls (OpenAI, SMTP2GO, Open Library)
 # use default TLS verification.
-