feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)

Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)

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

src/atocore/main.py

@@ -0,0 +1,33 @@
+"""AtoCore — FastAPI application entry point."""
+
+from fastapi import FastAPI
+
+from atocore.api.routes import router
+from atocore.config import settings
+from atocore.models.database import init_db
+from atocore.observability.logger import setup_logging
+
+app = FastAPI(
+    title="AtoCore",
+    description="Personal Context Engine for LLM interactions",
+    version="0.1.0",
+)
+
+app.include_router(router)
+
+
+@app.on_event("startup")
+def startup():
+    setup_logging()
+    init_db()
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(
+        "atocore.main:app",
+        host=settings.host,
+        port=settings.port,
+        reload=True,
+    )