feat: scaffold Brain of Reese — FastAPI RAG chat over Postgres 17 + pgvector

Foundation (phase 01, verified):
- FastAPI app: /api/health, /api/suggestions, /api/chat (placeholder),
  static frontend served locally (no CDN)
- Postgres 17 + pgvector via db/Containerfile + compose.yaml
  (podman compose up -d db), Alembic initial migration (documents,
  chunks with vector(768), query_log)
- LLM client targeting https://aipi.reeseapps.com/v1 (turbo/embed);
  scripts/llm_probe.py verified models + 768-dim embeddings live
- Conditional debugpy: imported only when DEBUGPY=1 (attach on demand,
  :5678); logging config for clean single-line logs
- Frontend shell: mobile-first chat + Sources pages, tokens, a11y baselines
- Tests: 24 unit+integration (99% coverage on app/), ruff + pyright clean,
  Playwright smoke E2E (3 tests) against a deterministic mock LLM
- Planning: .agent/PLAN.md (architecture + LOCKED decisions), AGENTS.md,
  6 user stories, 7 phase files (one story / one phase / one Playwright
  suite each)

app/core/logging.py

@@ -0,0 +1,26 @@
+"""Logging configuration.
+
+Human-readable, timestamped, single-line records on stdout. Every
+request-critical operation (retrieval, LLM calls, imports) logs key=value
+context at INFO level so a user is never left wondering what the system is
+doing — this pairs with the UI's loading/progress feedback (see PLAN §UI/UX).
+"""
+from __future__ import annotations
+
+import logging
+import sys
+
+_FORMAT = "%(asctime)s %(levelname)-8s %(name)s :: %(message)s"
+_DATEFMT = "%Y-%m-%d %H:%M:%S"
+
+
+def configure_logging(level: str = "INFO") -> None:
+    root = logging.getLogger()
+    root.setLevel(level.upper())
+    handler = logging.StreamHandler(sys.stdout)
+    handler.setFormatter(logging.Formatter(_FORMAT, _DATEFMT))
+    root.handlers = [handler]
+
+    # Keep third-party noise down while our own loggers stay verbose.
+    for noisy in ("httpx", "httpcore", "openai", "urllib3"):
+        logging.getLogger(noisy).setLevel(logging.WARNING)