v2 restructure: Go client, Docker engine, release tooling

- Remove v1 Python CLI (src/kb_search/, tests/, root pyproject.toml, uv.lock, .venv)
- Add Go client with cross-platform build (client/)
- Add FastAPI engine with NVIDIA and multi-stage ROCm Dockerfiles (engine/)
- Add VERSION files for client and engine, wired into builds
- Add release.sh for automated build, tag, release, and Docker push
- Update README with build/release docs and ROCm migration note
- Clean up .gitignore for v2 project structure

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

engine/main.py

@@ -0,0 +1,69 @@
+"""Engine entry point — FastAPI server with eager model loading."""
+
+import asyncio
+import logging
+import os
+from contextlib import asynccontextmanager
+from pathlib import Path
+
+from fastapi import FastAPI
+
+_version_file = Path(__file__).parent / "VERSION"
+__version__ = _version_file.read_text().strip() if _version_file.exists() else "dev"
+
+from kb.config import cfg
+from kb.embeddings import load_model
+from kb.database import get_connection, init_schema
+from kb.worker import ingestion_worker
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger("kb.engine")
+
+# Track readiness for health endpoint
+ready = False
+worker_task: asyncio.Task | None = None
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    global ready, worker_task
+
+    # Set HF cache before any model imports
+    os.environ["HF_HOME"] = str(cfg.hf_cache)
+
+    log.info("Starting engine...")
+    cfg.ensure_dirs()
+
+    # Initialise database
+    conn = get_connection(cfg.db_path)
+    model_dim = load_model(cfg.model, cfg.device)
+    init_schema(conn, model_dim)
+    conn.close()
+
+    # Start background ingestion worker
+    worker_task = asyncio.create_task(ingestion_worker())
+
+    ready = True
+    log.info("Engine ready — model: %s, device: %s", cfg.model, cfg.device)
+
+    yield
+
+    # Shutdown
+    ready = False
+    if worker_task:
+        worker_task.cancel()
+        try:
+            await worker_task
+        except asyncio.CancelledError:
+            pass
+    log.info("Engine stopped.")
+
+
+app = FastAPI(title="kb-engine", version=__version__, lifespan=lifespan)
+
+# Import routes after app is created
+from kb.routes import health, search, jobs, documents, tags, status, reindex, auth  # noqa: E402, F401
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run("main:app", host=cfg.host, port=cfg.port, log_level="info")