@deepseek-ai/dsh-tool-goal 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/goal/tool-goal/README.md
-README.md: 4a63c19352bceb9776a3d2cec003db8d234f6b43
-README.zh.md: b44fcabc5567436348130b0456bc6103a6466d6f
+README.md: c40b9eb302ace23c2448114433eda364083a5293
+README.zh.md: fdd1b1a317bed56f18c9eb8cc107b448e2b85981

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-`dsh-tool-goal` gives the model three tools over the persisted goal service: `get_goal` reads the current goal, `create_goal` starts a new one, and `update_goal` edits, pauses, resumes, completes, or blocks it. The model may infer a long-running objective from a direct human request and create a goal; updates must carry the exact id and revision read beforehand. Authority is enforced at execution: create, edit, pause, and resume require a direct human turn on a top-level agent, while complete and blocked also accept the current goal round during automatic continuation. A configured threshold (default 3) bounds how soon an autonomous round may self-report `blocked`. Mount it with `dsh-goal` whenever the model should manage goals itself.
+`dsh-tool-goal` lets a model read persisted goals and infer and create a long-running goal from a direct human request. Creating, editing, pausing, or resuming requires that direct request in a top-level agent turn; completing or blocking also works in an autonomous goal round. Updates require the exact goal id and revision returned by a prior read. `resume` rearms active-but-disarmed or blocked goals, while users resume durable paused goals through Web or `/goal resume`. Autonomous blocking requires the same condition for a configurable threshold of three consecutive rounds by default.
 
 ## Table of Contents
 
@@ -52,7 +52,7 @@ The value must be a positive safe integer. It supplies both the hard lower bound
 
 ### Authority rules
 
-The tools execute only for the exact live calling agent inside its active driver with an open turn. `create`, `edit`, `pause`, and `resume` additionally require a direct human message in a runtime-root agent's current turn — a subagent or a non-human producer cannot create or edit goals. `complete` and `blocked` also accept the exact current goal round: a goal-sourced round may complete the goal immediately, but a blocked call is mechanically rejected until the configured number of consecutive rounds has passed — the model judges whether the same condition actually persisted and must describe it in `blocked_reason`. A direct human request may stop a goal immediately.
+The tools execute only for the exact live calling agent inside its active driver with an open turn. `create`, `edit`, `pause`, and `resume` additionally require a direct human message in a runtime-root agent's current turn — a subagent or a non-human producer cannot create or edit goals. `resume` rejects a durable paused goal before the goal service runs; that state belongs to the user-facing resume path. `complete` and `blocked` also accept the exact current goal round: a goal-sourced round may complete the goal immediately, but a blocked call is mechanically rejected until the configured number of consecutive rounds has passed — the model judges whether the same condition actually persisted and must describe it in `blocked_reason`. A direct human request may stop a goal immediately.
 
 An autonomous round that successfully reports `complete` or `blocked` also ends the physical turn after that step, and the model receives a closing instruction to write the final message to the user. Direct-human mutations never trigger that stop: the assistant may acknowledge the change and the loop keeps concurrent human steering available.
 
@@ -68,7 +68,7 @@ This section explains how the tools enforce authority and render output; the obs
 
 ### Design
 
-- **Authority at execution.** Every call resolves the exact live agent, its inherited `AgentRegistry` initiator, running status, and an open turn; `create`, `edit`, `pause`, and `resume` additionally require an accepted `{ kind: 'user' }` message or steering event in a runtime-root agent's current turn. Durable fork lineage does not demote a resumed root; live subagent ownership does.
+- **Authority at execution.** Every call resolves the exact live agent, its inherited `AgentRegistry` initiator, running status, and an open turn; `create`, `edit`, `pause`, and `resume` additionally require an accepted `{ kind: 'user' }` message or steering event in a runtime-root agent's current turn. A durable paused goal fails the `resume` action with `GOAL_TOOL_RESUME_PAUSED`; the user-facing command or Web control owns that transition. Durable fork lineage does not demote a resumed root; live subagent ownership does.
 - **Host attestation of human input.** `{ kind: 'user' }` is assigned by `Agent.followup()` and `steer()` when their caller omits a source, so plugins, schedulers, and other non-human producers must pass their own source rather than inheriting human authority.
 - **System-prompt guidance with the configured threshold.** The package registers one `tool:goal` system-prompt section whose fixed text interpolates `blockedAfterConsecutiveRounds`; the same value is the hard lower bound enforced at execution.
 - **Wrap-up context for terminal rounds.** A successful autonomous `complete` or `blocked` defers a closing `<goal_complete>` or `<goal_blocked>` instruction so the model addresses the user once before the turn ends; direct-human mutations never defer this context.
@@ -109,7 +109,7 @@ The tools are the model-facing half of the goal surface; read these pages for th
 
 #### What the model sees
 
-A fixed goal policy says when semantic human intent warrants creation, requires exact read-before-update refs, explains rearming after resume/fork, and limits completion/blocking claims. The configured threshold is interpolated into that guidance.
+A fixed goal policy says when semantic human intent warrants creation, requires exact read-before-update refs, explains rearming after resume/fork, and limits completion/blocking claims. Durable paused resume is rejected at execution with `GOAL_TOOL_RESUME_PAUSED`; the user-facing goal control owns that transition. The configured threshold is interpolated into that guidance.
 
 ##### Goal policy
 

package/README.zh.md

@@ -9,7 +9,7 @@ kind: "package-reference"
 
 ## 概述
 
-`dsh-tool-goal` 为模型提供基于持久 goal 服务的三个工具：`get_goal` 读取当前 goal，`create_goal` 创建新 goal，`update_goal` 编辑、暂停、恢复、完成或阻塞它。模型可以从人类直接请求中推断长期目标并创建 goal；更新必须携带先前读取到的精确 id 与 revision。权限在执行时强制：create、edit、pause 和 resume 要求顶层 agent 的当前轮次中存在人类直接消息；complete 和 blocked 在自动续行期间还接受当前 Goal Round。可配置的阈值（默认 3）约束自主 Round 多快可以自行报告 `blocked`。当模型需要自行管理 goal 时，与 `dsh-goal` 一起挂载它。
+`dsh-tool-goal` 让模型读取持久 goal，并根据人类直接请求推断和创建长期 goal。创建、编辑、暂停或恢复要求该直接请求出现在顶层 agent 轮次中；完成或阻塞也可以在自主 Goal Round 中执行。更新必须使用先前读取到的精确 goal id 和 revision。`resume` 会重新启用 active-but-disarmed 或 blocked 的 goal，而持久的 paused goal 由用户通过 Web 或 `/goal resume` 恢复。自主阻塞要求同一条件持续达到可配置阈值，默认是连续三个 Round。
 
 ## 目录
 
@@ -52,7 +52,7 @@ kind: "package-reference"
 
 ### 权限规则
 
-工具只为活跃驱动器内、处于开放轮次中的精确活跃调用 agent 执行。`create`、`edit`、`pause` 和 `resume` 还要求运行时根 agent（智能体）的当前轮次中存在人类直接消息——subagent 或非人类生产方不能创建或编辑 goal。`complete` 和 `blocked` 还接受完全一致的当前 Goal Round：来源为 goal 的 Round 可以立即完成 goal，但 blocked 调用在达到配置的连续 Round 数量之前会被机械拒绝——模型判断同一条件是否确实持续，并必须在 `blocked_reason` 中说明。人类直接请求可以立即停止 goal。
+工具只为活跃驱动器内、处于开放轮次中的精确活跃调用 agent 执行。`create`、`edit`、`pause` 和 `resume` 还要求运行时根 agent（智能体）的当前轮次中存在人类直接消息——subagent 或非人类生产方不能创建或编辑 goal。`resume` 会在 goal 服务执行前拒绝持久的 paused goal；该状态只属于面向用户的恢复路径。`complete` 和 `blocked` 还接受完全一致的当前 Goal Round：来源为 goal 的 Round 可以立即完成 goal，但 blocked 调用在达到配置的连续 Round 数量之前会被机械拒绝——模型判断同一条件是否确实持续，并必须在 `blocked_reason` 中说明。人类直接请求可以立即停止 goal。
 
 成功报告 `complete` 或 `blocked` 的自主 Round 还会在该步骤后结束物理轮次，模型会收到一条结束指令，要求向用户写出最终消息。人类直接变更绝不会触发这种停止：assistant 可以确认变更，循环仍可接收并发的人类 steering（中途引导）。
 
@@ -68,7 +68,7 @@ kind: "package-reference"
 
 ### 设计
 
-- **执行时权限。** 每次调用都解析精确活跃 agent、其继承的 `AgentRegistry` initiator、running 状态与开放轮次；`create`、`edit`、`pause` 和 `resume` 还要求运行时根 agent 的当前轮次中存在已接受的 `{ kind: 'user' }` 消息或 steering 事件。持久 fork 谱系不会降低已恢复根 agent 的等级；活跃 subagent 所有权会降低。
+- **执行时权限。** 每次调用都解析精确活跃 agent、其继承的 `AgentRegistry` initiator、running 状态与开放轮次；`create`、`edit`、`pause` 和 `resume` 还要求运行时根 agent 的当前轮次中存在已接受的 `{ kind: 'user' }` 消息或 steering 事件。持久的 paused goal 会让 `resume` 以 `GOAL_TOOL_RESUME_PAUSED` 失败；面向用户的命令或 Web 控件拥有该转换。持久 fork 谱系不会降低已恢复根 agent 的等级；活跃 subagent 所有权会降低。
 - **人类输入的宿主证明。** `Agent.followup()` 与 `steer()` 会在调用方省略 source 时分配 `{ kind: 'user' }`，因此插件、调度器与其他非人类生产方必须传入自己的 source，不能继承人类权限。
 - **带配置阈值的系统提示词指引。** 本包注册一个 `tool:goal` 系统提示词章节，其固定文本插入 `blockedAfterConsecutiveRounds`；同一数值就是执行时强制执行的硬下限。
 - **终局 Round 的结束上下文。** 成功的自主 `complete` 或 `blocked` 会延后一条 `<goal_complete>` 或 `<goal_blocked>` 结束指令，让模型在轮次结束前向用户做一次交代；人类直接变更绝不会延后该上下文。
@@ -109,7 +109,7 @@ kind: "package-reference"
 
 #### 模型看到的内容
 
-固定 goal 策略说明何种用户语义意图值得创建 goal，要求更新前先精确读取 ref，解释会话 resume／fork 后如何重新启用续行，并限制完成／阻塞声明。配置的阈值会插入该指引。
+固定 goal 策略说明何种用户语义意图值得创建 goal，要求更新前先精确读取 ref，解释会话 resume／fork 后如何重新启用续行，并限制完成／阻塞声明。持久 paused 的 resume 会在执行时以 `GOAL_TOOL_RESUME_PAUSED` 拒绝；面向用户的 goal 控件拥有该转换。配置的阈值会插入该指引。
 
 ##### Goal 策略
 

package/lib/index.js

@@ -348,6 +348,8 @@ function apply(ctx, config) {
 			if (args.action === "pause" || args.action === "resume") {
 				requireDirectHuman(ctx, execution);
 				if (hasText(args.objective) || hasRoundCap(args.max_goal_rounds) || hasText(args.blocked_reason)) throw new HarnessError("objective and max_goal_rounds are valid only with action edit; blocked_reason is valid only with action blocked", "GOAL_TOOL_INVALID_UPDATE");
+				const current = ctx.goals.get(execution.agent);
+				if (args.action === "resume" && current?.id === ref.id && current.revision === ref.revision && current.phase === "paused") throw new HarnessError("the model cannot resume a paused goal; the user must resume it", "GOAL_TOOL_RESUME_PAUSED");
 				const goal = args.action === "pause" ? ctx.goals.pause(execution.agent, ref) : ctx.goals.resume(execution.agent, ref);
 				return Promise.resolve(goalValue(goal));
 			}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-tool-goal",
   "description": "Model-facing same-session goal tools with execution-time authority checks",
-  "version": "0.1.3-alpha.2",
+  "version": "0.1.5-alpha.2",
   "publishConfig": {
     "access": "public"
   },
@@ -27,28 +27,29 @@
   ],
   "license": "MIT",
   "peerDependencies": {
-    "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-goal": "^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-system-prompt": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-tools": "^0.1.3-alpha.2",
+    "@deepseek-ai/dsh-goal": "^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-agent": "^0.1.5-alpha.2",
     "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2"
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-tools": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.2"
   },
   "dependencies": {
     "@deepseek-ai/schemastery": "^3.18.2"
   },
   "devDependencies": {
     "@deepseek-ai/cordis-plugin-loader": "^1.0.3",
-    "@deepseek-ai/dsh-agent": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-agent-loop": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-goal": "^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-tools": "^0.1.3-alpha.2",
+    "@deepseek-ai/dsh-agent": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent-loop-testkit": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-agent-loop": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-goal": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session": "^0.1.5-alpha.2",
     "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-session-projection": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-system-prompt": "^0.1.3-alpha.2"
+    "@deepseek-ai/dsh-tools": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-system-prompt": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-session-projection": "^0.1.5-alpha.2"
   }
 }