Wire AI features to Claude (claude-sonnet-5); fix key detection + retired model

The Anthropic path could never activate: it gated on
`not ANTHROPIC_API_KEY.startswith("sk-ant-")`, but real Anthropic keys start
with `sk-ant-`, so any real key was treated as a placeholder and every request
fell back to mock. It also targeted the retired `claude-3-haiku-20240307`.

- ai_translator.py: add `_real_key()` placeholder detection (rejects `sk-ant-...`,
  `changeme`, `your-`, etc. — accepts real secrets), centralize provider gating
  in `_ai_enabled()`, and point all three AI features (finding translation,
  security coach, attack-path narrative) at `claude-sonnet-5` with thinking
  disabled for fast structured output. OpenAI kept as a secondary provider.
- config.py / .env.example: default AI_PROVIDER to anthropic.

Mock mode still works with no key configured; dropping in a real
ANTHROPIC_API_KEY now actually enables live Claude.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

backend/app/core/config.py

@@ -16,7 +16,7 @@ class Settings(BaseSettings):
     CORS_ORIGINS: Optional[str] = None  # comma-separated extra allowed origins
     ACCESS_TOKEN_EXPIRE_MINUTES: int = 480
 
-    AI_PROVIDER: str = "openai"
+    AI_PROVIDER: str = "anthropic"
     OPENAI_API_KEY: Optional[str] = None
     ANTHROPIC_API_KEY: Optional[str] = None