Reconcile the reasoning-passthrough change (#2520) with the Responses API
work: dedupe the shared reasoning_effort capability, keep upstream's
upstream_model_id YAML plumbing and the _apply_reasoning_effort chat path,
and run the Responses branch ahead of it so responses-flavor models skip
the chat-only top-level reasoning_effort injection.
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.
* fixes setup scripts
fixes to env handling in setup script plus other minor fixes
* Remove var declarations
Declarations such as `LLM_PROVIDER=$LLM_PROVIDER` override .env variables in compose
Similar issue is present in the frontend - need to choose either to switch to separate frontend env or keep as is.
* Manage apikeys in settings
1. More pydantic management of api keys.
2. Clean up of variable declarations from docker compose files, used to block .env imports. Now should be managed ether by settings.py defaults or .env
* feat: Implement model registry and capabilities for multi-provider support
- Added ModelRegistry to manage available models and their capabilities.
- Introduced ModelProvider enum for different LLM providers.
- Created ModelCapabilities dataclass to define model features.
- Implemented methods to load models based on API keys and settings.
- Added utility functions for model management in model_utils.py.
- Updated settings.py to include provider-specific API keys.
- Refactored LLM classes (Anthropic, OpenAI, Google, etc.) to utilize new model registry.
- Enhanced utility functions to handle token limits and model validation.
- Improved code structure and logging for better maintainability.
* feat: Add model selection feature with API integration and UI component
* feat: Add model selection and default model functionality in agent management
* test: Update assertions and formatting in stream processing tests
* refactor(llm): Standardize model identifier to model_id
* fix tests
---------
Co-authored-by: Alex <a@tushynski.me>
Alex