refactor: replace litellm with native openai + anthropic SDKs

- Remove litellm dependency entirely (supply chain risk mitigation)
- Add AnthropicProvider (native SDK) and OpenAICompatProvider (unified)
- Merge CustomProvider into OpenAICompatProvider, delete custom_provider.py
- Add ProviderSpec.backend field for declarative provider routing
- Remove _resolve_model, find_gateway, find_by_model (dead heuristics)
- Pass resolved spec directly into provider — zero internal lookups
- Stub out litellm-dependent model database (cli/models.py)
- Add anthropic>=0.45.0 to dependencies, remove litellm
- 593 tests passed, net -1034 lines

tests/providers/test_mistral_provider.py

@@ -17,6 +17,4 @@ def test_mistral_provider_in_registry():
 
     mistral = specs["mistral"]
     assert mistral.env_key == "MISTRAL_API_KEY"
-    assert mistral.litellm_prefix == "mistral"
     assert mistral.default_api_base == "https://api.mistral.ai/v1"
-    assert "mistral/" in mistral.skip_prefixes