- Add `has_audio_input` flag to agent message handling and propagate through processing pipeline
- Structure agent input payloads to include `input.mode` and `input.transcribed` for voice messages
- Update prompts and tool descriptions to clarify that `send_voice_message` and `ask_user_choice` are terminal tools and should not be followed by redundant text replies
- Enhance tests to cover voice input metadata propagation and prompt updates
- Add ChannelCapability.PROCESSING_STATUS and capability detection for supported channels
- Implement mark_message_processing_started/finished in Telegram, Slack, Discord, Feishu modules
- Telegram: manage typing lifecycle with max duration and explicit stop
- Slack: add/remove reaction as processing indicator
- Discord: start/stop typing indicator with async task management
- Feishu: add/remove reaction for processing status
- Refactor message chain to invoke processing status hooks for supported channels
- Ensure processing status is properly finished on sync and async message handling paths
- Add tests for processing status lifecycle and capability detection across channels
- Update stop_streaming logic to await inflight initial flush task, preventing duplicate message sends on stream stop
- Change message edit/delete methods to return Optional[bool] for clearer channel mismatch handling
- Refine Feishu logging to include message_id instead of full data object
- Suppress allowed_objects warnings in __init__.py
- Add test to verify stop_streaming waits for inflight flush before final edit
- Update .pylintrc to use 'E' for error enabling
- Refactor MoviePilotToolSelectorMiddleware to perform tool selection once per agent execution and cache the result in state, avoiding redundant LLM calls for each model round.
- Add abefore_agent to select tools at the start of agent execution and store selected tool names in state.
- Update awrap_model_call to reuse cached tool selection from state for subsequent model calls.
- Enhance test coverage for tool selection caching and reuse logic.
- Improve error logging in skill version extraction.
- Add mechanism to always include core tools (e.g., file operations, command execution) in LLMToolSelectorMiddleware
- Update MoviePilotToolFactory to provide filtered always-include tool names based on loaded tools
- Set default LLM_MAX_TOOLS to 30 in config
- Refactor agent initialization to support always_include parameter
- Enhance tests to cover always_include logic and async agent creation
- Move LLMHelper and related logic from app.helper.llm to app.agent.llm.helper
- Update all imports to reference new LLMHelper location
- Introduce app/agent/llm/__init__.py for internal LLM adapter exports
- Add llm.py API router with endpoints for model listing, provider auth, and test calls
- Remove legacy LLM endpoints from system.py
- Update requirements for langchain-anthropic and anthropic
- Refactor test_llm_helper_testcall.py for async LLMHelper usage and new import paths
