* feat: context compressor
Co-authored-by: kawayiYokami <289104862@qq.com>
* Add comprehensive tests for ContextManager and ContextTruncator
- Implemented a full test suite for ContextManager covering initialization, message processing, token-based compression, and error handling.
- Added tests for ContextTruncator focusing on message fixing, truncation by turns, dropping oldest turns, and halving.
- Ensured that both test suites validate edge cases and maintain expected behavior with various message types, including system and tool messages.
* feat: add MockProvider for LLM compression tests
* chore: remove lock
* ruff fix
* fix
* perf
* feat: enhance context compression with token tracking and logging
* feat: update logging for context compression trigger
* feat: implement context compression logic with dynamic threshold and token tracking
* fix: reorder import statements for consistency
* feat: add token_usage tracking to conversations and update related processing logic
---------
Co-authored-by: kawayiYokami <289104862@qq.com>
- Added support for template schemas in the configuration editor, allowing users to define and manage additional parameters like temperature, top_p, and max_tokens.
- Improved UI components in ProviderModelsPanel and ObjectEditor for better user interaction, including new configuration buttons and enhanced input handling.
- Updated localization files to include new configuration options.
* feat: 添加模板列表配置支持，包含验证和编辑功能
* refactor(dashboard): extract ConfigItemRenderer to eliminate code duplication
- Create ConfigItemRenderer.vue to centralize rendering logic for various config types (string, int, bool, selectors, etc.)
- Refactor TemplateListEditor.vue to use the new renderer for entry fields
- Refactor AstrBotConfig.vue and AstrBotConfigV4.vue to simplify metadata-driven rendering
- Resolve circular dependency by decoupling TemplateListEditor from the base renderer
* ruff format
* refactor: improve config validation and fix unidirection data flow
- Frontend: Fix one-way data flow in TemplateListEditor.vue by cloning entries before applying defaults and emitting updates instead of in-place modification.
- Frontend: Remove unused TemplateListEditor import in ConfigItemRenderer.vue.
- Backend: Refactor validate_config in config.py by extracting _expect_type and _validate_template_list helpers to reduce nesting and complexity.
* perf: support extended thinking for Anthropic, DeepSeek reasoning mode, and Gemini text part thought signatures to improve multi-turn reasoning performance.
* chore: remove verbose
* perf
* refactor: remove special tools handling for deepseek-reasoner model in openai source
* fix: improve error handling and logging in InternalAgentSubStage processing
* refactor: remove unused reasoning content from Gemini source processing
* refactor: enhance modality determination logic in useProviderSources
Co-authored-by: kawayiYokami <289104862@qq.com>
* feat: supports thinking level of google gemini
- Updated google-genai version to >=1.56.0 in pyproject.toml and requirements.txt.
- Changed model configuration from "gemini-1.5-flash" to "gemini-3-flash-preview" in default.py.
- Enhanced thinking configuration handling in gemini_source.py to support new parameters for Gemini 3 models.
* fix: standardize thinking level configuration in default.py and gemini_source.py
- Updated the thinking level values in default.py to uppercase for consistency.
- Enhanced gemini_source.py to validate the thinking level and default to "HIGH" if an invalid value is provided.
- Renamed "QQ 个人号(OneBot v11)" to "OneBot v11" in the configuration.
- Added a new logo for OneBot in the dashboard assets.
- Updated platform icon retrieval logic to include the new OneBot logo.
- Added icons for 'modelstack', 'tokenpony', and 'compshare' in providerUtils.js.
- Updated ProviderPage.vue to display the correct count of displayed provider sources.
- Enhanced the logic for displaying provider sources to include placeholders for unselected templates.
- Improved the display name for provider sources to show template keys for placeholders.
- Adjusted styles for better layout and overflow handling in provider source list and cards.
- Refactored source selection logic to handle placeholder sources correctly.
- Updated error handling in provider testing to provide clearer messages.
* feat: segment reply supports segmentation words
* chore: ruff format
* feat: enhance segmented reply processing by refining word extraction logic
* ruff format
* feat: add image caption provider configuration for group chat
- Introduced `image_caption_provider_id` to allow separate configuration for group chat image understanding.
- Updated metadata and hints in English and Chinese for clarity on new settings.
- Adjusted logic in long term memory to utilize the new provider ID for image captioning.
* fix: format
* Fix logic for image caption and active reply settings
* Fix indentation and formatting in long_term_memory.py
* chore: ruff format
---------
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
Co-authored-by: Soulter <905617992@qq.com>
Update the configuration hint for `words_count_threshold` to explicitly state that it acts as a maximum limit for segmentation, preventing user confusion about it being a minimum trigger.
