refactor: split gateway and pi-qmem extension into modules

- gateway: separate config, models, state, audit, guardrail, embeddings,
  store, metrics, cleanup and routes; keep main.py as FastAPI bootstrap
- extension: split client/config, six tools, config command and rules;
  preserve jiti entrypoint and registrations
- Dockerfile copies the complete gateway module set
- tests: update monkeypatch boundaries for modular config/state

gateway/config.py

@@ -0,0 +1,43 @@
+"""Configurazione statica del Memory Gateway letta dall'ambiente."""
+from __future__ import annotations
+
+import logging
+import os
+from collections import Counter
+from typing import Any
+
+QDRANT_URL = os.environ.get("QDRANT_URL", "http://127.0.0.1:6333")
+QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY", "")
+EMBED_API = os.environ.get("EMBED_API", "ollama")
+EMBED_URL = os.environ.get("EMBED_URL", os.environ.get("OLLAMA_URL", "http://127.0.0.1:11434"))
+EMBED_MODEL = os.environ.get("EMBED_MODEL", "bge-m3")
+EMBED_API_KEY = os.environ.get("EMBED_API_KEY", "")
+EMBED_DIM = int(os.environ.get("EMBED_DIM", "1024"))
+COLLECTION = os.environ.get("COLLECTION", "memories")
+API_KEYS: set[str] = {k.strip() for k in os.environ.get("API_KEYS", "").split(",") if k.strip()}
+RATE_LIMIT_PER_MIN = int(os.environ.get("RATE_LIMIT_PER_MIN", "120"))
+MAX_TEXT_LEN = int(os.environ.get("MAX_TEXT_LEN", "8000"))
+
+GUARDRAIL_ENABLED = os.environ.get("GUARDRAIL_ENABLED", "true").lower() == "true"
+GUARDRAIL_BLOCK_THRESHOLD = float(os.environ.get("GUARDRAIL_BLOCK_THRESHOLD", "0.85"))
+GUARDRAIL_WARN_THRESHOLD = float(os.environ.get("GUARDRAIL_WARN_THRESHOLD", "0.70"))
+GUARDRAIL_VERSION = "similarity-v1"
+GIT_COMMIT = os.environ.get("GIT_COMMIT", "unknown").strip()
+GATEWAY_VERSION = os.environ.get("GATEWAY_VERSION", "2.8.0").strip()
+
+VM_PUSH_URL = os.environ.get("VM_PUSH_URL", "http://host.docker.internal:8428/api/v1/import/prometheus")
+VM_PUSH_INTERVAL = int(os.environ.get("VM_PUSH_INTERVAL", "30"))
+METRICS_ENABLED = os.environ.get("METRICS_ENABLED", "true").lower() == "true"
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+log = logging.getLogger("memory-gateway")
+
+SPARSE_VECTOR_NAME = "bm25"
+_metrics: dict[str, Any] = {
+    "requests": Counter(),
+    "duration_sum": Counter(),
+    "duration_count": Counter(),
+    "errors": Counter(),
+    "search_queries": 0,
+    "search_hits": 0,
+}