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/config.py

@@ -0,0 +1,64 @@
+"""Application settings.
+
+Every setting can be overridden with an environment variable prefixed
+``BOR_`` (or a local gitignored ``.env`` file — see ``.env.example``).
+"""
+from __future__ import annotations
+
+import os
+from functools import lru_cache
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        env_prefix="BOR_",
+        extra="ignore",
+    )
+
+    # --- App ---
+    app_name: str = "Brain of Reese"
+    app_version: str = "0.1.0"
+    environment: str = "development"
+    log_level: str = "INFO"
+    static_dir: str = "frontend"
+
+    # --- Database (PostgreSQL 17 + pgvector) ---
+    database_url: str = "postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese"
+
+    # --- LLM (self-hosted, OpenAI-compatible "aipi" endpoint) ---
+    llm_base_url: str = "https://aipi.reeseapps.com/v1"
+    llm_api_key: str = ""
+    llm_chat_model: str = "turbo"
+    llm_embed_model: str = "embed"
+
+    # --- RAG tuning ---
+    embedding_dim: int = 768  # verified against aipi /v1 (embed model)
+    top_k_chunks: int = 4
+    top_n_docs: int = 2
+    relevance_threshold: float = 0.30
+    max_context_chars: int = 24_000
+    chunk_target_chars: int = 2_000
+    chunk_overlap_chars: int = 200
+    embed_batch_size: int = 16
+
+    # Suggested questions (onboarding + empty state).
+    suggestions: list[str] = [
+        "How is my Kubernetes cluster set up?",
+        "What's my backup strategy?",
+        "How do I deploy a new service?",
+        "What's currently running in the homelab?",
+    ]
+
+    @property
+    def effective_api_key(self) -> str:
+        """API key for aipi: explicit setting, then $AIPI_KEY, then a placeholder."""
+        return self.llm_api_key or os.environ.get("AIPI_KEY", "") or "not-needed"
+
+
+@lru_cache
+def get_settings() -> Settings:
+    return Settings()