@deepseek-ai/dsh-tool-ralph 0.1.2-rc.1 → 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 +3 -3
  3. package/README.zh.md +3 -3
  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/workflow/tool-ralph/README.md
5
- README.md: dcdaa1abf0da735c821fb805f584a0e3660417b9
6
- README.zh.md: 1d5f42f7416c74424ed6c4b13750ef3e8ef030d2
5
+ README.md: c32a04258f6ef399f2346fad0b11cc7417a209aa
6
+ README.zh.md: 5e5ddd2ef94d9622ea0e5428797201fbccfde383
package/README.md CHANGED
@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
9
9
 
10
10
  ## Summary
11
11
 
12
- `dsh-tool-ralph` gives the model the `ralph` tool: a fixed foreground workflow that hands one immutable objective to a sequence of fresh child agents, each starting with no conversation seed and carrying only the previous bounded report. It is a specialized orchestration policy built on the workflow and subagent capabilities — no Ralph mode is added to the agent loop, and the same-session goal domain stays independent. The call returns when a worker reports completion or a concrete blocker, or at the round limit; completion and blockers are worker reports, not independent certification. Use it only when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution; ordinary long-running objectives belong to goal tools, and bounded delegation belongs to subagents or workflows.
12
+ `ralph` runs a foreground sequence of fresh child agents against one immutable objective, with each round receiving only the previous bounded report and shared workspace state. It returns when a worker reports completion or a concrete blocker, or when the configured round limit is reached; those reports are not independently verified. Parent conversation and prior child sessions are never copied into a new round. Use it only when the direct human explicitly requests Ralph-style fresh-agent iteration; use goal tools for ordinary long-running work and subagents or workflows for bounded delegation.
13
13
 
14
14
  ## Table of Contents
15
15
 
@@ -58,7 +58,7 @@ This section explains the fixed-script design and the validation and lifecycle m
58
58
 
59
59
  ### Design concept
60
60
 
61
- The loop is a deployment-owned fixed script: the model supplies data only and cannot alter the loop, provider route, schema, or handoff validation. The tool is an ordinary plugin over `ctx.workflowEngine` and `ctx.subagents` — no Ralph mode or fresh-agent loop is added to `agent-loop`, and the same-session goal domain stays independent. The [Ralph Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md) owns the policy and deferred work.
61
+ The loop is a deployment-owned fixed script: the model supplies data only and cannot alter the loop, provider route, schema, or handoff validation. The tool is an ordinary plugin over `ctx.workflowEngine` and `ctx.subagents` — no Ralph mode or fresh-agent loop is added to `agent-loop`, and the same-session goal domain stays independent. The [harness-level goal-based execution Agent Note](../../../.agents/notes/implemented/feature/2026-07-16-harness-level-loop.md) owns the policy and deferred work.
62
62
 
63
63
  ### Fixed script and routing
64
64
 
@@ -97,7 +97,7 @@ Read these pages when the tool-level contract is not enough. They move from the
97
97
  - [Worker-thread engine](../workflow-worker-thread/README.md) — the engine that executes the fixed script.
98
98
  - [subagent seam](../../subagent/subagent/README.md) — the fresh-child provider contract.
99
99
  - [Goal group](../../goal/goal/README.md) — same-session goal tools for ordinary long-running objectives.
100
- - [Ralph tool Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md) — the policy, provider requirements, and deferred work.
100
+ - [Harness-level goal-based execution Agent Note](../../../.agents/notes/implemented/feature/2026-07-16-harness-level-loop.md) — the policy, provider requirements, and deferred work.
101
101
 
102
102
  -----
103
103
 
package/README.zh.md CHANGED
@@ -9,7 +9,7 @@ kind: "package-reference"
9
9
 
10
10
  ## 概述
11
11
 
12
- `dsh-tool-ralph` 把 `ralph` 工具交给模型：一个固定的前台工作流，把一个不可变目标依次交给多个全新子 agent（智能体），每个子 agent 都没有对话种子，只携带上一份有界报告。它是构建在工作流与 subagent 能力之上的专用编排策略——不会向 agent loop 添加 Ralph 模式，同会话的 goal 领域也保持独立。调用在 worker 报告完成或具体阻塞、或达到 Round 上限时返回；完成与阻塞都是 worker 报告，不是独立认证。仅当直接用户明确要求 Ralph 循环或全新 agent 迭代执行时使用它；普通的长期同会话目标属于 goal 工具，有界委派属于 subagent 或工作流。
12
+ `ralph` 针对一个不可变目标运行由多个全新子 agent（智能体）组成的前台序列，每个 Round 只接收上一份有界报告与共享工作区状态。它会在 worker 报告完成或具体阻塞，或达到配置的 Round 上限时返回；这些报告不会得到独立验证。父级对话与先前子 agent 会话绝不会复制到新的 Round。仅当直接用户明确要求 Ralph 式全新 agent 迭代时使用它；普通的长期工作请使用 goal 工具，有界委派请使用 subagent 或工作流。
13
13
 
14
14
  ## 目录
15
15
 
@@ -58,7 +58,7 @@ kind: "package-reference"
58
58
 
59
59
  ### 设计理念
60
60
 
61
- 循环是部署方拥有的固定脚本：模型只提供数据，无法改变循环、提供方路由、schema 或交接校验。该工具是基于 `ctx.workflowEngine` 与 `ctx.subagents` 的普通插件——不会向 `agent-loop` 添加 Ralph 模式或全新 agent loop，同会话的 goal 领域也保持独立。[Ralph Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md)拥有策略与暂缓事项。
61
+ 循环是部署方拥有的固定脚本：模型只提供数据，无法改变循环、提供方路由、schema 或交接校验。该工具是基于 `ctx.workflowEngine` 与 `ctx.subagents` 的普通插件——不会向 `agent-loop` 添加 Ralph 模式或全新 agent loop，同会话的 goal 领域也保持独立。[Harness 层目标式执行 Agent Note](../../../.agents/notes/implemented/feature/2026-07-16-harness-level-loop.zh.md)拥有策略与暂缓事项。
62
62
 
63
63
  ### 固定脚本与路由
64
64
 
@@ -97,7 +97,7 @@ kind: "package-reference"
97
97
  - [worker-thread 引擎](../workflow-worker-thread/README.zh.md)——执行固定脚本的引擎。
98
98
  - [subagent seam](../../subagent/subagent/README.zh.md)——全新子 agent 的提供方契约。
99
99
  - [goal 组](../../goal/goal/README.zh.md)——面向普通长期目标的同会话 goal 工具。
100
- - [Ralph 工具 Agent Note](../../../.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md)——策略、提供方要求与暂缓事项。
100
+ - [Harness 层目标式执行 Agent Note](../../../.agents/notes/implemented/feature/2026-07-16-harness-level-loop.zh.md)——策略、提供方要求与暂缓事项。
101
101
 
102
102
  -----
103
103
 
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@deepseek-ai/dsh-tool-ralph",
3
3
  "description": "Model-facing fresh-agent Ralph loop over the workflow and subagent seams",
4
- "version": "0.1.2-rc.1",
4
+ "version": "0.1.5-alpha.1",
5
5
  "publishConfig": {
6
6
  "access": "public"
7
7
  },
@@ -27,32 +27,32 @@
27
27
  ],
28
28
  "license": "MIT",
29
29
  "peerDependencies": {
30
- "@deepseek-ai/dsh-llm": "^0.1.2-rc.1",
31
- "@deepseek-ai/dsh-agent": "^0.1.2-rc.1",
32
- "@deepseek-ai/dsh-subagent": "^0.1.2-rc.1",
33
- "@deepseek-ai/dsh-system-prompt": "^0.1.2-rc.1",
34
- "@deepseek-ai/dsh-tools": "^0.1.2-rc.1",
35
- "@deepseek-ai/dsh-workflow": "^0.1.2-rc.1",
30
+ "@deepseek-ai/dsh-agent": "^0.1.5-alpha.1",
31
+ "@deepseek-ai/dsh-llm": "^0.1.5-alpha.1",
32
+ "@deepseek-ai/dsh-subagent": "^0.1.5-alpha.1",
33
+ "@deepseek-ai/dsh-tools": "^0.1.5-alpha.1",
34
+ "@deepseek-ai/dsh-workflow": "^0.1.5-alpha.1",
35
+ "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.1",
36
36
  "@deepseek-ai/cordis": "^4.0.2"
37
37
  },
38
38
  "dependencies": {
39
39
  "@deepseek-ai/schemastery": "^3.18.2"
40
40
  },
41
41
  "devDependencies": {
42
- "@deepseek-ai/dsh-agent": "^0.1.2-rc.1",
43
- "@deepseek-ai/dsh-agent-loop": "^0.1.2-rc.1",
44
- "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.2-rc.1",
45
- "@deepseek-ai/dsh-llm": "^0.1.2-rc.1",
46
42
  "@deepseek-ai/cordis-plugin-loader": "^1.0.3",
47
- "@deepseek-ai/dsh-subagent": "^0.1.2-rc.1",
48
- "@deepseek-ai/dsh-subagent-in-process-driver": "^0.1.2-rc.1",
49
- "@deepseek-ai/dsh-subagent-spawn-in-process": "^0.1.2-rc.1",
50
- "@deepseek-ai/dsh-system-prompt": "^0.1.2-rc.1",
51
- "@deepseek-ai/dsh-tools": "^0.1.2-rc.1",
52
- "@deepseek-ai/dsh-workflow": "^0.1.2-rc.1",
53
- "@deepseek-ai/dsh-session": "^0.1.2-rc.1",
54
- "@deepseek-ai/cordis": "^4.0.2",
55
- "@deepseek-ai/dsh-session-projection": "^0.1.2-rc.1",
56
- "@deepseek-ai/dsh-workflow-worker-thread": "^0.1.2-rc.1"
43
+ "@deepseek-ai/dsh-agent": "^0.1.5-alpha.1",
44
+ "@deepseek-ai/dsh-agent-loop": "^0.1.5-alpha.1",
45
+ "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.5-alpha.1",
46
+ "@deepseek-ai/dsh-llm": "^0.1.5-alpha.1",
47
+ "@deepseek-ai/dsh-session": "^0.1.5-alpha.1",
48
+ "@deepseek-ai/dsh-subagent": "^0.1.5-alpha.1",
49
+ "@deepseek-ai/dsh-subagent-in-process-driver": "^0.1.5-alpha.1",
50
+ "@deepseek-ai/dsh-subagent-spawn-in-process": "^0.1.5-alpha.1",
51
+ "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.1",
52
+ "@deepseek-ai/dsh-tools": "^0.1.5-alpha.1",
53
+ "@deepseek-ai/dsh-workflow": "^0.1.5-alpha.1",
54
+ "@deepseek-ai/dsh-workflow-worker-thread": "^0.1.5-alpha.1",
55
+ "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.1",
56
+ "@deepseek-ai/cordis": "^4.0.2"
57
57
  }
58
58
  }