Replace custom provider abstraction with litellm

Drops the src/providers/ package (base class, AnthropicProvider,
OpenAIProvider, factory) in favour of a single src/llm.py that calls
litellm.completion() directly. litellm handles provider routing,
authentication, and SDK differences for 100+ providers without any
code we need to maintain.

Changes:
- Delete src/providers/ entirely
- Add src/llm.py — one complete() function wrapping litellm
- src/agent/core.py: EmailAgent takes model: str instead of LLMProvider
- src/config.py: ai_provider + api key fields → single ai_model string
  in litellm format (e.g. "anthropic/claude-opus-4-6")
- main.py: remove provider factory wiring; pass config.ai_model to agent
- .env.example: simplify AI section, show litellm model string examples
- pyproject.toml: replace anthropic + openai deps with litellm>=1.0.0
- uv.lock: regenerated

https://claude.ai/code/session_01HaUFs7SaLD5SoiuGCY27Tw

pyproject.toml

@@ -4,10 +4,8 @@ version = "0.1.0"
 description = "AI-powered conversational registration agent for Spielgruppe Pumuckl"
 requires-python = ">=3.13"
 dependencies = [
-    # At least one AI provider SDK is required; both are included so the
-    # operator can choose at runtime via the AI_PROVIDER env variable.
-    "anthropic>=0.40.0",
-    "openai>=1.50.0",
+    # LLM access — supports any provider (Anthropic, OpenAI, Gemini, …)
+    "litellm>=1.0.0",
     # Configuration
     "python-dotenv>=1.0.0",
     # Registration schema validation