Skip to content

Commit fcd036c

Browse files
committed
docs(readme): 补充分支相对官方版本的增强能力说明
1 parent b47c5fa commit fcd036c

1 file changed

Lines changed: 26 additions & 8 deletions

File tree

README.md

Lines changed: 26 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -36,17 +36,35 @@ English / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本
3636

3737
LangBot is an **open-source, production-grade platform** for building AI-powered instant messaging bots. It connects Large Language Models (LLMs) to any chat platform, enabling you to create intelligent agents that can converse, execute tasks, and integrate with your existing workflows.
3838

39-
## Enhancements in This Branch
39+
## 本分支相对官方版本增加 / 增强的能力
4040

41-
Compared with the upstream official branch, this maintained branch includes several practical enhancements focused on WeCom / WeChat operations and long-running session reliability:
41+
相比官方版本,`feat/wecom` 分支围绕**企微智能机器人、企业微信客服、企微应用接管微信客服、Dify 对话连续性、以及私有化部署稳定性**做了持续增强,主要包括以下能力:
4242

43-
- **WeCom Customer Service runtime enhancements** — Redis-backed scheduling, state persistence, retry handling, token cache, and sharded processing for more stable large-volume customer service workloads.
44-
- **WeCom app managed customer service adapter** — Added `wecom_kf_app` support for scenarios where customer service is managed through a WeCom application authorization model.
45-
- **Dify conversation persistence** — Persist Dify `conversation_id` bindings in Redis and clear them on explicit session resets, reducing context loss after runtime restarts.
46-
- **OpenClaw WeChat adapter support** — Added OpenClaw-based WeChat integration for additional WeChat connectivity scenarios.
47-
- **WeCom / WeChat integration hardening** — Additional fixes and runtime improvements around session isolation, callback handling, and customer-service message processing.
43+
1. **企微智能机器人增强**
44+
支持更细粒度的 **Pull / Webhook 流式配置****pending placeholder 开关与延迟控制**、以及 **Dify 流式输出节流配置**,同时补强拉流生命周期管理、websocket 兼容性与调试日志能力,适合对流式回复体验、稳定性和排障能力要求更高的企微机器人场景。
4845

49-
These enhancements are especially useful for teams running LangBot in private deployments with heavier WeCom / WeChat customer-service traffic and stronger context-continuity requirements.
46+
2. **企业微信客服运行时增强**
47+
在官方基础上补充了基于 **Redis Streams** 的调度机制,并增加 **游标检查点持久化、消息状态存储、失败重试、分片处理、token cache** 等能力,显著提升企业微信客服在高消息量、长时间运行、重启恢复等场景下的稳定性与可维护性。
48+
49+
3. **新增“企微应用接管微信客服”类型**
50+
新增 `wecom_kf_app` 适配器与对应配置,支持通过**企微应用授权方式**接管和管理微信客服能力,适配更多企业内部权限体系和组织接入模式。
51+
52+
4. **Dify 集成增强**
53+
修复 Dify 在 **workflow 流式结束、workflow 输出兼容、流式节流控制** 等方面的若干问题,并新增 **`conversation_id` Redis 持久化机制**,在显式 reset 场景下同步清理绑定,降低 LangBot 重启或会话重建后 Dify 上下文丢失的概率。
54+
55+
5. **企微 / 微信客服链路隔离与上下文保护增强**
56+
对 bot stream、pipeline session、客服消息处理链路做了进一步隔离和收口,减少多 bot、多流水线、长链路客服场景下的会话串扰与上下文错配问题。
57+
58+
6. **插件 / RAG / Pipeline 兼容增强**
59+
增强旧版 runtime sdk 兼容性,保留 RAG 检索链路中的 session context,并收敛部分 pipeline 异常处理策略,使复杂插件、知识库、老版本运行时共存时更稳定。
60+
61+
7. **检索能力增强**
62+
**Chroma** 增加全文检索与混合检索支持,提升向量检索之外的能力扩展空间,适合对知识检索效果有更高要求的场景。
63+
64+
8. **部署与运维增强**
65+
优化 Docker 镜像体积、构建缓存、Python 路径配置与 compose 镜像来源,并补充围绕 wecomcs 的 Redis 启动与运行文档,更适合长期私有化部署和运维。
66+
67+
如果你的主要使用场景是:**企微智能机器人、企业微信客服、企微应用接管微信客服、Dify 对话连续性、私有化部署稳定性**,那么这个分支相比官方版本会更贴近真实生产需求。
5068

5169
---
5270

0 commit comments

Comments
 (0)