@deepseek-ai/dsh-schedule 0.1.3-alpha.2 → 0.1.5-alpha.2

package/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/schedule/schedule/README.md
-README.md: 6ed1cbdca15d74ced8a93d68ea218f71bdfa76d8
-README.zh.md: 8905abc7230415d1dbb6a201f1aca42517f7a4bd
+README.md: 7a8b14fcf1e335aab2c9a0c717e38ae08c81eb6c
+README.zh.md: c250ad5889fc92e9c47e23e32e0b87b9bd793901

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-`dsh-schedule` gives your session durable reminders: ask the model to remind you later, and the reminder comes back as an ordinary follow-up message in the same conversation. You can schedule a one-time reminder after a delay or at an absolute time, or a repeating reminder on a fixed interval, and you can list what is still pending or cancel a reminder. Reminders survive restarts: an already-live idle agent can deliver due work immediately, while a closed or cold session keeps it overdue until a future live root agent resumes the session. Delivery stays inside the session, with no email, SMS, or push notification. It is an opt-in Web capability; load the Schedule overlay to enable the reminder tools and read-only active-reminder catalog. Ordinary and search sidebar rows also show a non-interactive alarm when their best-effort list projection is known to be non-empty; the alarm does not promise a live runtime.
+Schedule lets you ask the model for durable reminders that return as ordinary follow-up messages in the same conversation. Create one-time reminders for a delay or absolute time, repeat them at fixed intervals, list pending reminders, and cancel them. Reminders survive restarts, but delivery requires a live root agent: closed sessions keep reminders overdue until resumed. Delivery never uses email, SMS, push, or browser notifications. Enable the Schedule overlay to expose the reminder tools and active-reminder catalog; sidebar alarms are best-effort indicators of known active reminders, not proof that reminder delivery is currently running.
 
 ## Table of Contents
 

package/README.zh.md

@@ -9,7 +9,7 @@ kind: "package-reference"
 
 ## 概述
 
-`dsh-schedule` 为你的会话提供持久的提醒：让模型稍后提醒你，提醒会作为同一会话中的普通 follow-up 消息返回。你可以安排延时后的一次性提醒、绝对时间的一次性提醒，或固定间隔的重复提醒，也可以列出仍待处理的提醒或取消提醒。提醒在重启后依然存在：已经 live 且空闲的 agent 可以立即交付到期工作，而已关闭或 cold 的会话会让提醒保持逾期，直到未来的 live 根 agent 恢复会话。交付只发生在会话内部，没有电子邮件、短信或推送通知。它是可选的 Web 能力；加载 Schedule overlay 即可启用提醒工具与只读活动提醒目录。普通与搜索侧边栏行还会在尽力而为的列表 projection 明确非空时显示不可交互的闹钟；该闹钟不保证 live runtime 存在。
+Schedule 让你向模型请求持久提醒；提醒会作为普通 follow-up 消息返回同一会话。你可以创建延时或绝对时间的一次性提醒、按固定间隔重复提醒、列出待处理提醒，也可以取消提醒。提醒在重启后仍然存在，但交付需要 live 根 agent：已关闭的会话会让提醒保持逾期，直到恢复。交付绝不会使用电子邮件、短信、推送或浏览器通知。启用 Schedule overlay 即可提供提醒工具和活动提醒目录；侧边栏闹钟只是已知活动提醒的尽力而为指示，不证明提醒交付当前正在运行。
 
 ## 目录
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-schedule",
   "description": "Agent-scoped durable after, at, and fixed-rate reminders over the session event log",
-  "version": "0.1.3-alpha.2",
+  "version": "0.1.5-alpha.2",
   "publishConfig": {
     "access": "public"
   },
@@ -37,33 +37,33 @@
   ],
   "license": "MIT",
   "peerDependencies": {
-    "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-brand": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-invariants": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session-persistence": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-tools": "^0.1.3-alpha.2",
-    "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2"
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-brand": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-invariants": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session-persistence": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-tools": "^0.1.5-alpha.2",
+    "@deepseek-ai/cordis": "^4.0.2"
   },
   "dependencies": {
     "zod": "^4.4.3"
   },
   "devDependencies": {
     "@deepseek-ai/cordis-plugin-loader": "^1.0.3",
-    "@deepseek-ai/dsh-agent-loop": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-invariants": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-brand": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session-persistence": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session-persistence-jsonl": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-system-prompt": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-tools": "^0.1.3-alpha.2",
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent-loop": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-brand": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-invariants": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session-persistence": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session-persistence-jsonl": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-tools": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.2",
     "@deepseek-ai/cordis": "^4.0.2"
   }
 }