@deepseek-ai/dsh-plan-mode 0.1.3-alpha.2 → 0.1.5-alpha.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.i18n.yaml +2 -2
  2. package/README.md +1 -1
  3. package/README.zh.md +1 -1
  4. package/package.json +21 -21
package/README.i18n.yaml CHANGED
@@ -2,5 +2,5 @@
2
2
  # side as of the last confirmed-consistent state. Both languages carry equal authority;
3
3
  # after editing either side, bring the other along and re-record with:
4
4
  # pnpm run verify-translation-pairing --write packages/plan/plan-mode/README.md
5
- README.md: b9a86fe530923956365b17dbe5e0ececa28b3416
6
- README.zh.md: 5c1e21bac520dcd973c181d70139969abcff8b1b
5
+ README.md: 693273ab4bdfddebd6145046e8354a5a211c8b8b
6
+ README.zh.md: 39a7a65c29d3f11dfb9e9f4dc696d59082c82240
package/README.md CHANGED
@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
9
9
 
10
10
  ## Summary
11
11
 
12
- `dsh-plan-mode` adds plan mode to the agent: while it is active, the agent explores and designs before executing, guided by instructions the deployment writes, and presents the finished plan for your approval before carrying it out. You enter plan mode with `/plan`, optionally carrying a message and ordered image or file attachments, and leave it with `/plan off`; the finished plan arrives as a review where you can approve it or send the agent back to keep planning. Plan mode is guidance, not enforcement: every tool stays available, so sandbox mode and approval prompts remain the way to impose limits. Choose it when the agent should think before acting, and plan mode carries over when a session resumes or forks.
12
+ Plan mode asks an agent to explore and design before execution, then presents the finished plan for your approval. Enter it with `/plan`, optionally with a message or ordered image and file attachments; leave with `/plan off`, approve the review to continue, or return feedback for more planning. Deployment-defined guidance controls planning behavior, but every tool remains available, so use sandbox mode and approval prompts for enforced limits. The active state survives session resume and forks. Choose it when you want a reviewed plan before the agent acts.
13
13
 
14
14
  ## Table of Contents
15
15
 
package/README.zh.md CHANGED
@@ -9,7 +9,7 @@ kind: "package-reference"
9
9
 
10
10
  ## 概述
11
11
 
12
- `dsh-plan-mode` 为 agent（智能体）提供计划模式：激活期间，agent 先探索和设计再执行，遵循你的部署所写的引导行事，并在执行前把完成的计划呈交你批准。你可以用 `/plan` 进入计划模式，并随命令附带消息及有序的图片或文件附件；用 `/plan off` 离开。完成的计划会以评审形式呈现，你可以批准它，或让 agent 回去继续规划。计划模式是引导而非强制：每个工具仍然可用，因此沙箱模式与审批提示仍是施加限制的方式。当希望 agent 先思考再行动时选择它；会话恢复或 fork 后计划模式依然保持。
12
+ 计划模式要求 agent 先探索和设计再执行，然后把完成的计划呈交你批准。用 `/plan` 进入，并可附带一条消息或按顺序排列的图片与文件附件；用 `/plan off` 离开，批准评审以继续执行，或反馈意见以要求继续规划。部署方定义的引导控制规划行为，但每个工具仍然可用，因此请用沙箱模式与审批提示施加强制限制。激活状态会在会话恢复和 fork 后保留。当你希望 agent 行动前先提交一份经评审的计划时，选择计划模式。
13
13
 
14
14
  ## 目录
15
15
 
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@deepseek-ai/dsh-plan-mode",
3
3
  "description": "Logged per-agent plan mode with deployment guidance, a direct slash command, and a user-reviewed exit",
4
- "version": "0.1.3-alpha.2",
4
+ "version": "0.1.5-alpha.1",
5
5
  "publishConfig": {
6
6
  "access": "public"
7
7
  },
@@ -41,15 +41,15 @@
41
41
  ],
42
42
  "license": "MIT",
43
43
  "peerDependencies": {
44
- "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
45
- "@deepseek-ai/dsh-invariants": "^0.1.3-alpha.2",
46
- "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
47
- "@deepseek-ai/dsh-session": "^0.1.3-alpha.2",
48
- "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2",
49
- "@deepseek-ai/dsh-commands": "^0.1.3-alpha.2",
50
- "@deepseek-ai/dsh-system-prompt": "^0.1.3-alpha.2",
51
- "@deepseek-ai/dsh-tools": "^0.1.3-alpha.2",
52
- "@deepseek-ai/dsh-user-questions": "^0.1.3-alpha.2",
44
+ "@deepseek-ai/dsh-agent": "^0.1.5-alpha.1",
45
+ "@deepseek-ai/dsh-commands": "^0.1.5-alpha.1",
46
+ "@deepseek-ai/dsh-invariants": "^0.1.5-alpha.1",
47
+ "@deepseek-ai/dsh-llm": "^0.1.5-alpha.1",
48
+ "@deepseek-ai/dsh-session": "^0.1.5-alpha.1",
49
+ "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.1",
50
+ "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.1",
51
+ "@deepseek-ai/dsh-tools": "^0.1.5-alpha.1",
52
+ "@deepseek-ai/dsh-user-questions": "^0.1.5-alpha.1",
53
53
  "@deepseek-ai/cordis": "^4.0.2"
54
54
  },
55
55
  "peerDependenciesMeta": {
@@ -61,17 +61,17 @@
61
61
  "zod": "^4.4.3"
62
62
  },
63
63
  "devDependencies": {
64
- "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
65
- "@deepseek-ai/dsh-agent-loop": "^0.1.3-alpha.2",
66
- "@deepseek-ai/dsh-code-runtime": "^0.1.3-alpha.2",
67
- "@deepseek-ai/dsh-commands": "^0.1.3-alpha.2",
68
- "@deepseek-ai/dsh-invariants": "^0.1.3-alpha.2",
69
- "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
70
- "@deepseek-ai/dsh-session": "^0.1.3-alpha.2",
71
- "@deepseek-ai/dsh-system-prompt": "^0.1.3-alpha.2",
72
- "@deepseek-ai/dsh-tools": "^0.1.3-alpha.2",
73
- "@deepseek-ai/dsh-user-questions": "^0.1.3-alpha.2",
74
- "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2",
64
+ "@deepseek-ai/dsh-agent-loop": "^0.1.5-alpha.1",
65
+ "@deepseek-ai/dsh-code-runtime": "^0.1.5-alpha.1",
66
+ "@deepseek-ai/dsh-agent": "^0.1.5-alpha.1",
67
+ "@deepseek-ai/dsh-commands": "^0.1.5-alpha.1",
68
+ "@deepseek-ai/dsh-llm": "^0.1.5-alpha.1",
69
+ "@deepseek-ai/dsh-invariants": "^0.1.5-alpha.1",
70
+ "@deepseek-ai/dsh-session": "^0.1.5-alpha.1",
71
+ "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.1",
72
+ "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.1",
73
+ "@deepseek-ai/dsh-tools": "^0.1.5-alpha.1",
74
+ "@deepseek-ai/dsh-user-questions": "^0.1.5-alpha.1",
75
75
  "@deepseek-ai/cordis": "^4.0.2"
76
76
  }
77
77
  }