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/.env.example

@@ -8,10 +8,12 @@ SYNC_DATABASE_URL=postgresql://trustos:trustos_dev@postgres:5432/trustos
 SECRET_KEY=changeme-use-openssl-rand-hex-32-in-production
 ACCESS_TOKEN_EXPIRE_MINUTES=480
 
-# AI
-OPENAI_API_KEY=sk-...
+# AI — defaults to Anthropic/Claude (model: claude-sonnet-5).
+# Leave the placeholders as-is to run in mock mode (all AI features return
+# canned demo responses). Drop in a real key to enable live AI.
+AI_PROVIDER=anthropic
 ANTHROPIC_API_KEY=sk-ant-...
-AI_PROVIDER=openai
+OPENAI_API_KEY=sk-...
 
 # External APIs
 HIBP_API_KEY=