Description

✅ Added

• Complete SkillsBench automated evaluation tool, supporting benchmark data preparation, batch task execution, automatic result verification and pass rate statistics / 完整的SkillsBench自动化评测工具，支持基准数据准备、批量任务执行、自动结果验证、通过率统计
• Locomo evaluation result statistics script, automatically generates accuracy, time cost, token consumption report / locomo评测结果统计脚本，自动生成准确率、耗时、Token消耗报告
• Long-running task progress notification capability, Feishu channel dynamically displays processing emoji feedback / 长任务进度提示能力，飞书端动态展示处理中表情反馈
• VikingAddResourceTool supporting both URL resources (images, Git repositories) and local file addition / VikingAddResourceTool工具，支持URL资源（图片、Git仓库）和本地文件添加
• Channel-level memory sharing mode configuration, supporting memory isolation/sharing switching / 频道级内存共享模式配置，支持内存隔离/共享切换
• CLI chat command --config/-c parameter, supporting custom configuration file path / CLI chat命令--config/-c参数，支持自定义配置文件路径
• Memory search performance logging for performance troubleshooting / 内存搜索性能日志，便于性能问题排查

🔄 Changed

• Locomo evaluation script optimization: supports resume evaluation, writes results to independent output file, --token changed to required parameter, updated default judge model / Locomo评测脚本优化：支持断点续评、结果写入独立输出文件、--token改为必填参数、更新默认评分模型
• Single-turn request timeout increased from 300s to 3000s to adapt to long-running evaluation tasks / 单轮请求超时从300s延长至3000s，适配长耗时评测任务
• Resource search/Grep tool logic optimized to adapt to the latest OV server API / 资源搜索/Grep工具逻辑优化，适配最新OV服务端接口
• Feishu channel message processing logic refactored, prioritizes processing of generic metadata actions / 飞书频道消息处理逻辑重构，优先处理通用元数据动作
• Configuration loading logic optimized to support custom configuration path input / 配置加载逻辑优化，支持自定义配置路径传入

🐛 Fixed

• Fixed null pointer exception when fieldnames is None during CSV reading / 修复CSV读取时fieldnames为None的空指针异常
• Fixed Feishu thread message reply logic, uses thread ID only in thread mode / 修复飞书线程消息回复逻辑，仅在线程模式下使用线程ID
• Fixed non-standard JSON parsing failure issue, uses strict=False for compatible processing / 修复非标准JSON解析失败问题，使用strict=False兼容处理
• Fixed AddResource timeout exception issue, returns task submission success prompt even on timeout / 修复AddResource超时异常问题，超时仍返回任务提交成功提示

❌ Removed

• Removed redundant custom JSON preprocessing logic in run_eval.py / 移除run_eval.py中冗余的自定义JSON预处理逻辑
• Removed built-in @mention parsing logic in Feishu channel / 移除飞书频道内置的@提及解析逻辑
• Removed deprecated target_path and wait parameters in AddResource tool / 移除AddResource工具中废弃的target_path和wait参数
• Removed logic that directly modifies input files in judge.py, changed to write to independent output file / 移除jduge.py中直接修改输入文件的逻辑，改为写入独立输出文件

Related Issue

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update

Changes Made

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

Additional Notes