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_custom_provider.py

@@ -1,10 +1,14 @@
-from types import SimpleNamespace
+"""Tests for OpenAICompatProvider handling custom/direct endpoints."""
 
-from nanobot.providers.custom_provider import CustomProvider
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
 
 
 def test_custom_provider_parse_handles_empty_choices() -> None:
-    provider = CustomProvider()
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
     response = SimpleNamespace(choices=[])
 
     result = provider._parse(response)