- Refactored model fetching logic to support various authentication methods for OpenAI-compatible APIs.
- Introduced new data models for LLM service requests and responses to standardize interactions across layers.
- Added an adapter base class for unified request execution across different providers.
- Implemented utility functions for building OpenAI-compatible client configurations and request overrides.
- Removed UniversalMessageSender from group_generator.py and private_generator.py.
- Updated PlatformIOManager to manage legacy send drivers and ensure send pipeline readiness.
- Enhanced LegacyPlatformDriver to utilize prepared messages for sending.
- Refactored send_service to unify message sending logic and integrate with Platform IO.
- Added regression tests for Platform IO legacy driver and send service functionality.
- Introduced a built-in NapCat adapter plugin for MVP message forwarding.
- Implemented core functionalities for connecting to NapCat/OneBot v11 WebSocket service.
- Added message serialization capabilities for WebUI chat routes.
- Enhanced the RegisterPluginPayload to include optional adapter declarations.
- Implemented methods for handling external messages and adapter declarations in the PluginRunner.
- Improved the send_service to inherit platform IO route metadata for outgoing messages.
- Remove get_bot_account("qq") fallback from all 4 sender paths
(plan L108/L208/L449: unknown platform = no account, never substitute QQ)
- Sender paths now error immediately if platform bot account is not configured
- Add detailed comments on filter_bot legacy fallback explaining why
global user_id match is needed (plan contingency L528 insufficient for
platform-tagged legacy rows like telegram+qq_account)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Updated imports and references from ChatStream to BotChatSession across multiple files.
- Adjusted method signatures and internal logic to accommodate the new session management.
- Ensured compatibility with existing functionality while improving code clarity and maintainability.
