feat: add OpenAI Responses API support via per-model api_flavor

Route opted-in models to /v1/responses while keeping Chat Completions as
the default. The flavor is selected per-model in the catalog YAML and
threaded through ModelCapabilities (with a new reasoning_effort field).

- Translate chat-shaped messages/tools/structured-output into the
  Responses input / text.format / flattened-tool shapes at the provider
  boundary; stored history and intra-turn tool round-trips need no
  migration.
- Normalize the typed SSE event stream back into the existing handler
  contract (content / thought / tool-call chunks) so the streaming
  accumulator and OpenAI handler stay unchanged.
- Carry encrypted reasoning items across the in-turn tool loop
  (provider-local, keyed by call_id) for stateless reasoning continuity.
- OPENAI_RESPONSES_STORE opt-in enables server-side state and
  previous_response_id chaining across turns, persisted in message
  metadata.
- Set gpt-5.5 to api_flavor: responses, reasoning_effort: medium.
- Remove AzureOpenAILLM and the azure_openai provider/catalog.

tests/core/test_model_settings.py

@@ -37,7 +37,6 @@ class TestModelProvider:
         assert ModelProvider.SAGEMAKER == "sagemaker"
         assert ModelProvider.PREMAI == "premai"
         assert ModelProvider.LLAMA_CPP == "llama.cpp"
-        assert ModelProvider.AZURE_OPENAI == "azure_openai"
 
 
 class TestModelCapabilities: