- Replace Playwright-based browser emulation with CloakBrowser as default
- Update config to support CloakBrowser options and humanization presets
- Refactor browser helper to use CloakBrowser context and remove cf_clearance dependency
- Update Dockerfile, entrypoint, and update scripts to install CloakBrowser runtime
- Ensure CloakBrowser kernel is pre-installed during local setup and dependency updates
- Add tests for CloakBrowser integration and legacy compatibility
When a plugin requires a newer minor version of a non-core dependency
(e.g. sentry-sdk ~=2.59.0 while 2.58.0 is installed), the conflict
check now distinguishes upgrade-only conflicts from downgrade conflicts.
Non-core packages that only need upgrading are allowed through; the
runtime constraints file uses >= instead of == for non-core packages so
pip can satisfy the upgrade without risking a downgrade.
Core packages (fastapi, pydantic, sqlalchemy, etc.) remain strictly
pinned and any version mismatch is still rejected.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Route title and path lookups through the fallback-aware entrypoints so auxiliary matches can reuse pre-assist keywords without forcing image fetches in lightweight flows. Also reduce noisy agent shutdown logging during cleanup.
- 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
- Eliminate support for LLM_DISABLE_THINKING and LLM_REASONING_EFFORT in config, code, and tests
- Simplify LLM thinking level logic to rely solely on LLM_THINKING_LEVEL
- Refactor LLMHelper and related endpoints to remove legacy parameter handling
- Update system API and test utilities to match new configuration structure
- Minor code cleanup and formatting improvements
- Integrate voice message handling: detect and extract audio references from Telegram and WeChat messages, route to agent with voice reply preference.
- Add voice provider abstraction and OpenAI-based TTS/STT implementation.
- Implement agent tool `send_voice_message` for generating and sending voice replies, with fallback to text if voice is unavailable.
- Extend agent prompt and context to support voice reply instructions.
- Update notification and message schemas to support audio fields.
- Add Telegram and WeChat voice sending logic, including audio file conversion and temporary media upload for WeChat.
- Add tests for voice helper and agent voice routing.
