docs: refresh zh/en readme with concurrency, memory-ekg and streaming updates

This commit is contained in:
lpf
2026-03-04 14:10:03 +08:00
parent b007a403a1
commit 764fa94ced
2 changed files with 32 additions and 2 deletions

View File

@@ -19,13 +19,28 @@
## 并发调度(新)⚙️
- 🧩 一条复合消息会先自动拆成多个子任务(可配置上限)
- 🧩 一条复合消息会先自动拆成多个子任务
- 🔀 同一会话内:无资源冲突的子任务可并发执行
- 🔒 同一会话内:有资源冲突的子任务自动串行(避免互相踩)
- 🏷️ 默认会自动推断 `resource_keys`,无需手动填写
---
## 记忆与 EKG 增强(新)🧠
- 📚 每个子任务执行前会自动检索相关记忆(`memory_search`
- 🚨 会结合 EKG 与任务审计识别“重复错误签名”风险
- ⏱️ 高风险任务会自动附带重试退避建议,减少重复踩坑
---
## Telegram 流式渲染优化(新)💬
- 🧷 只在语法安全断点刷新流式内容(减少格式抖动)
- ✅ 结束时做一次最终收敛渲染,保证排版稳定
---
## 3 分钟上手 ⚡
### 1) 安装

View File

@@ -19,13 +19,28 @@ A long-running AI Agent written in Go: lightweight, auditable, and multi-channel
## Concurrency Scheduling (New) ⚙️
- 🧩 A composite message is auto-split into sub-tasks (configurable max)
- 🧩 A composite message is automatically split into sub-tasks
- 🔀 Within the same session: non-conflicting tasks run in parallel
- 🔒 Within the same session: conflicting tasks run serially (to avoid collisions)
- 🏷️ `resource_keys` are inferred automatically by default (no manual input needed)
---
## Memory + EKG Enhancements (New) 🧠
- 📚 Before each sub-task runs, related memory is fetched via `memory_search`
- 🚨 EKG + task-audit are used to detect repeated error-signature risks
- ⏱️ High-risk tasks include retry-backoff hints to reduce repeated failures
---
## Telegram Streaming Rendering (New) 💬
- 🧷 Stream flushes happen at syntax-safe boundaries to reduce formatting jitter
- ✅ A final convergence render is applied when streaming ends for stable layout
---
## 3-Minute Quick Start ⚡
### 1) Install