qwen_agent/agent
autobee-sparticle 18bf296aa0
feat: move enable_thinking control from docker-compose to request body (#21)
* add page number

* feat: add skill feature memory

添加 skill 功能的 feature memory,记录技能包管理服务和 Hook 系统的核心信息。

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(skill): add feature memory with changelog and decisions

添加 skill 功能的完整记忆文档:

Changelog:
- 2025-Q4: 初始实现 (GRPC 层 + 内置 skills)
- 2026-Q1: API 完善 (REST API + Hook 系统)

Design Decisions:
- 001: Skill 架构设计 (目录结构、Hook 系统)
- 002: 上传安全措施 (ZipSlip、路径遍历防护)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* soffice sharp 支持

* shell_env support

* feat: move enable_thinking control from docker-compose to request body

Remove DEFAULT_THINKING_ENABLE environment variable from docker-compose
and settings.py. The enable_thinking flag is now solely controlled via
request body (default: false), as felo-mygpt already passes this config
from RobotConfig database.

Closes sparticleinc/felo-mygpt#2473

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: 朱潮 <zhuchaowe@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: zhuchao <zhuchaowe@163.com>
2026-03-26 20:12:39 +09:00
..
__init__.py 新增agent文件夹,修改import引用,增加custom_mcp_manager 2025-11-26 17:23:02 +08:00
agent_config.py 增加取消推理 2026-03-16 22:22:39 +08:00
agent_memory_cache.py 修改balance资源配置 2025-12-23 23:11:24 +08:00
chat_history_manager.py db_pool 2026-01-19 23:39:04 +08:00
checkpoint_manager.py db_pool 2026-01-19 23:39:04 +08:00
checkpoint_utils.py refactor: migrate from Memori to Mem0 for long-term memory 2026-01-20 21:15:30 +08:00
config_cache.py 修改general_agent提示词 2025-12-03 17:53:18 +08:00
custom_filesystem_middleware.py skill.md文件长度限制解除 2026-03-02 12:55:39 +08:00
db_pool_manager.py refactor(mem0): optimize connection pool and async memory handling 2026-01-22 19:39:12 +08:00
deep_assistant.py shell_env支持 2026-03-16 13:31:59 +08:00
guideline_middleware.py rename general agent 2026-02-06 17:05:17 +08:00
logging_handler.py on_tool_start 长度调整 2026-02-15 18:12:22 +08:00
mem0_config.py patch 2026-01-21 13:23:11 +08:00
mem0_manager.py 🐛 fix: 修复 Mem0 连接池耗尽和 LLM 参数透传问题 2026-03-04 10:11:44 +08:00
mem0_middleware.py bug fix 2026-03-04 14:30:44 +08:00
plugin_hook_loader.py feat: 实现 Claude Plugins 模式的 Hook 机制 2026-02-06 20:15:54 +08:00
prompt_loader.py feat: move enable_thinking control from docker-compose to request body (#21) 2026-03-26 20:12:39 +09:00
summarization_middleware.py update summary 2026-02-04 15:31:41 +08:00
tool_output_length_middleware.py 修改确保 max_length 永远不会是 None 2026-03-04 14:08:26 +08:00
tool_use_cleanup_middleware.py 修复完成。主要改动: 1. 新增 _clean_content_blocks 方法:专门处理 content 字段的清理 - 当 content 是列表格式时,过滤掉 type: 'tool_use' 的块(如果 id 不在 valid_tool_call_ids 中) - 返回清理后的 content 和是否有文本内容的标志 2. 更新 _cleanup_tool_use_messages 方法: - 调用 _clean_content_blocks 来清理 content - 使用清理后的 cleaned_content 创建新的 AIMessage 问题根源:之前的代码只清空了 tool_calls=[],但没有从 content 列表中移除 type: 'tool_use' 的块。Anthropic API 会检查这两个地方,导致报错。 2025-12-23 19:11:27 +08:00