refactor(llm): route all tiers via OpenRouter, drop Anthropic SDK

Tutti i tier (S/A/B/C/D) ora passano per OpenRouter via OpenAI SDK.
Modelli Anthropic raggiungibili via prefisso `anthropic/...`.

- pyproject: rimosso `anthropic>=0.39` da deps + uv.lock
- config: rimosso `anthropic_api_key` field
- LLMClient: dispatch unico, single client OpenAI con base_url OpenRouter
- defaults S/A/B → `anthropic/claude-{opus-4-7,sonnet-4-6}`
- retry exceptions: solo openai.* (drop anthropic.*)
- test rinominati e adattati: tier S/A/B mockano OpenAI con prefisso `anthropic/`
- rimosso test `tier_S_without_anthropic_key_raises` (non più rilevante)

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

.env.example

@@ -4,17 +4,16 @@ CERBERO_TESTNET_TOKEN=
 CERBERO_MAINNET_TOKEN=
 CERBERO_BOT_TAG=swarm-poc-phase1
 
-# LLM providers
+# LLM provider (single endpoint via OpenRouter — supports anthropic/openai/qwen/llama models)
 OPENROUTER_API_KEY=
-ANTHROPIC_API_KEY=
+OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
 
-# LLM models (override Phase 1 defaults if needed)
-LLM_MODEL_TIER_S=claude-opus-4-7
-LLM_MODEL_TIER_A=claude-sonnet-4-6
-LLM_MODEL_TIER_B=claude-sonnet-4-6
+# Models per tier (override Phase 1 defaults if needed)
+LLM_MODEL_TIER_S=anthropic/claude-opus-4-7
+LLM_MODEL_TIER_A=anthropic/claude-sonnet-4-6
+LLM_MODEL_TIER_B=anthropic/claude-sonnet-4-6
 LLM_MODEL_TIER_C=qwen/qwen-2.5-72b-instruct
 LLM_MODEL_TIER_D=meta-llama/llama-3.3-70b-instruct
-OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
 
 # Run config
 RUN_NAME=phase1-spike-001