feat(config): pydantic settings loader from .env

Aggiunge Settings (BaseSettings) che carica configurazione da
variabili d'ambiente / file .env, con validazione obbligatoria
dei segreti Cerbero testnet e OpenRouter.

Test:
- test_settings_loads_from_env: happy path via monkeypatch.setenv
- test_settings_requires_tokens: ValidationError quando token
  obbligatori mancano (forza _env_file=None per isolare il test
  da eventuale .env locale popolato).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/multi_swarm/config.py

@@ -0,0 +1,37 @@
+"""Pydantic settings loader for Multi_Swarm_Coevolutive.
+
+Loads configuration from environment variables and an optional ``.env`` file
+in the project root. Required secrets are validated at instantiation time.
+"""
+
+from pathlib import Path
+
+from pydantic import Field, SecretStr
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        extra="ignore",
+        case_sensitive=False,
+    )
+
+    cerbero_base_url: str = "http://localhost:9000"
+    cerbero_testnet_token: SecretStr
+    cerbero_mainnet_token: SecretStr | None = None
+    cerbero_bot_tag: str = "swarm-poc-phase1"
+
+    openrouter_api_key: SecretStr
+    anthropic_api_key: SecretStr | None = None
+
+    run_name: str = "phase1-spike-001"
+    data_dir: Path = Field(default=Path("./data"))
+    series_dir: Path = Field(default=Path("./series"))
+    db_path: Path = Field(default=Path("./runs.db"))
+
+
+def load_settings() -> Settings:
+    # Required fields are populated from environment / .env, not init kwargs.
+    return Settings()  # type: ignore[call-arg]