- 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
- Add tools for querying built-in and custom filter rules, and for adding, updating, and deleting custom rules and rule groups
- Refactor filter module to use shared builtin rule definitions
- Enhance rule group querying to include syntax guidance and usage references
- Add unittests for agent filter rule tools registration and parsing logic
- Add compatibility patch for langchain-openai responses API to ensure system messages are extracted as top-level instructions, addressing Codex endpoint requirements.
- Update provider list: add Alibaba, Volcengine, and Tencent TokenHub; adjust SiliconFlow and MiniMax endpoints; refine provider ordering and model list strategies.
- Extend models.dev-only listing logic for providers lacking stable models.list endpoints.
- Increase models.dev cache TTL for improved efficiency.
- Add tests for openai responses API and streaming compatibility patches.
- 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
- Implement batch AI re-organize endpoint for transfer history with progress tracking
- Add batch_manual_transfer_redo system task template and prompt generation
- Refactor agent_manager to support generic background prompt execution
- Add AIRecommendChain for search result recommendation using agent background prompt
- Update search endpoints to use new AIRecommendChain and remove legacy code
- Enhance test cases for batch manual transfer redo
- Minor code cleanup and style fixes
- Add structured runtime config files (AGENT_PROFILE.md, AGENT_WORKFLOW.md, AGENT_HOOKS.md, USER_PREFERENCES.md, SYSTEM_TASKS.md, CURRENT_PERSONA.md) for persona, workflow, hooks, and system tasks
- Implement agent_runtime_manager to load, validate, and render runtime config and system task prompts
- Refactor agent initialization to use runtime-managed directories for skills, jobs, memory, and activity logs
- Add AgentHooksMiddleware for structured pre/in/post hooks injection
- Replace hardcoded system task prompts with template-driven rendering from SYSTEM_TASKS.md
- Update tests to cover runtime config loading, migration, and system task prompt rendering
- Update .gitignore to exclude config/agent/
