fix(goal): stop terminal goal tool turns

docs/config-catalog.md

@@ -1110,7 +1110,7 @@ export interface Config {
 }
 ```
 
-Source: [`packages/goal/tool-goal/src/index.ts:25`](../packages/goal/tool-goal/src/index.ts)
+Source: [`packages/goal/tool-goal/src/index.ts:27`](../packages/goal/tool-goal/src/index.ts)
 
 ## `@deepseek-ai/dsh-tool-skill`
 

docs/event-producer-consumer.md

@@ -22,7 +22,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:165`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) |
 | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:252`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
 | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:288`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
-| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:298`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
+| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:298`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`tool-goal`](../packages/goal/tool-goal) |
 | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) |
 | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
 | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |

docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.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
-2026-07-19-model-facing-goal-tools.md: 7a207bbc73e13ca5111d73ee2c58cf05fbe6387e
-2026-07-19-model-facing-goal-tools.zh.md: 46ad7671e1ef2a6856df6d1ec893896aab9760b5
+2026-07-19-model-facing-goal-tools.md: cb823aa944d69228005884ac73cc99b67fa00dfb
+2026-07-19-model-facing-goal-tools.zh.md: f93ffa3a2eed602d8c7d98faccf09c9e46924f28

docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.md

@@ -22,6 +22,8 @@ The prompt tells the model that it may infer goal intent from a direct human req
 
 All three tools use exclusive execution so a model-ordered batch observes prior mutations and their new revisions. Results are compact JSON. ACP presentation is a pure function of arguments and uses generic read or mutation cards; activation is reported only as live observation and is never written into replay state.
 
+A successful update that leaves the goal stopped contributes the existing terminal `agent/turn-stop` decision for that physical turn, preventing an unnecessary follow-up request after pause, block, or completion. A later successful resume in the same turn removes that contribution.
+
 ### Execution authority
 
 Every call requires an `exec.agent` that is the exact running object in `AgentRegistry`, is the current inherited driver initiator, and has an open turn. These are execution-time checks and cannot be bypassed by prompt injection or hand-authored tool arguments.

docs/rfc/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md

@@ -22,6 +22,8 @@ Status: implemented
 
 三个工具都采用独占执行，使模型排序的批次可以观察此前变更及其新修订号。结果为紧凑 JSON。ACP 展示是参数的纯函数，使用通用读取或变更卡片；激活态仅作为实时观察返回，绝不会写入回放状态。
 
+成功更新后若目标处于停止状态，插件会为该物理轮次贡献现有的终止型 `agent/turn-stop` 决策，避免在暂停、阻塞或完成后再发起一次不必要的模型请求。同一轮次中后续成功的恢复会移除该贡献。
+
 ### 执行权限
 
 每次调用都要求存在 `exec.agent`，且它必须是 `AgentRegistry` 中完全相同的运行中对象、当前继承的驱动发起者，并处于开放轮次内。这些检查在执行时进行，不能通过提示词注入或手写工具参数绕过。

packages/goal/tool-goal/README.md

@@ -10,6 +10,8 @@ The model-facing control surface for [`ctx.goals`](../goal/README.md): `get_goal
 
 All calls are exclusive, so a model-ordered batch observes earlier mutations and their new revisions. ACP and other clients receive pure generic cards: read for `get_goal`, other for mutations.
 
+A successful mutation that leaves the goal stopped contributes the existing terminal `agent/turn-stop` decision for that physical turn. A later same-turn resume clears the contribution. This avoids an extra model request after pause, block, or completion without changing ordinary loop continuation.
+
 ## Authority
 
 Execution requires the exact live `exec.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.

packages/goal/tool-goal/src/index.ts

@@ -6,6 +6,7 @@
 
 import type { Context } from 'cordis'
 import z from 'schemastery'
+import type { Agent } from '@deepseek-ai/dsh-agent'
 import { GoalId } from '@deepseek-ai/dsh-goal'
 import type { GoalRef, GoalView } from '@deepseek-ai/dsh-goal'
 import { HarnessError } from '@deepseek-ai/dsh-llm'
@@ -17,6 +18,7 @@ import {
   goalToolExecution,
   requireDirectHuman,
 } from './authority.ts'
+import type { GoalToolExecution } from './authority.ts'
 
 export const name = 'tool-goal'
 export const inject = ['agents', 'goals', 'tools', 'systemPrompt']
@@ -105,9 +107,28 @@ function present(title: string, kind: 'read' | 'other', rawInput?: unknown): Gen
   return { card: 'generic', title, kind, ...rawInput === undefined ? {} : { rawInput } }
 }
 
+/** Remember whether one successful mutation makes this turn terminal. */
+function observeMutation(
+  terminalTurns: WeakMap<Agent, number>,
+  execution: GoalToolExecution,
+  goal: GoalView,
+): void {
+  if (goal.phase === 'active' && goal.activation === 'armed') {
+    terminalTurns.delete(execution.agent)
+    return
+  }
+  terminalTurns.set(execution.agent, execution.start.data.turn)
+}
+
 /** Register the three Codex-shaped goal tools and their shared policy section. */
 export function apply(ctx: Context, config: Config): void {
   const resolved = resolveConfig(config)
+  const terminalTurns = new WeakMap<Agent, number>()
+  ctx.on('agent/turn-stop', (agent, turn) => {
+    if (terminalTurns.get(agent) !== turn) return undefined
+    terminalTurns.delete(agent)
+    return { action: 'stop' }
+  })
   ctx.systemPrompt.section({
     name: 'tool:goal',
     order: 114,
@@ -149,6 +170,7 @@ export function apply(ctx: Context, config: Config): void {
         objective: args.objective,
         ...args.max_goal_rounds === undefined ? {} : { maxGoalRounds: args.max_goal_rounds },
       })
+      observeMutation(terminalTurns, execution, goal)
       return Promise.resolve([{ type: 'text', text: renderGoal(goal) }])
     },
     presentCall: args => present('Create goal', 'other', args.objective),
@@ -181,9 +203,11 @@ export function apply(ctx: Context, config: Config): void {
       }
       if (args.action === 'edit') {
         requireDirectHuman(ctx, execution)
+        const goal = ctx.goals.edit(execution.agent, ref, replacements)
+        observeMutation(terminalTurns, execution, goal)
         return Promise.resolve([{
           type: 'text',
-          text: renderGoal(ctx.goals.edit(execution.agent, ref, replacements)),
+          text: renderGoal(goal),
         }])
       }
       if (args.objective !== undefined || args.max_goal_rounds !== undefined) {
@@ -197,6 +221,7 @@ export function apply(ctx: Context, config: Config): void {
         const goal = args.action === 'pause'
           ? ctx.goals.pause(execution.agent, ref)
           : ctx.goals.resume(execution.agent, ref)
+        observeMutation(terminalTurns, execution, goal)
         return Promise.resolve([{ type: 'text', text: renderGoal(goal) }])
       }
       const authority = completionAuthority(ctx, execution)
@@ -211,6 +236,7 @@ export function apply(ctx: Context, config: Config): void {
       const goal = args.action === 'complete'
         ? ctx.goals.complete(execution.agent, ref)
         : ctx.goals.block(execution.agent, ref)
+      observeMutation(terminalTurns, execution, goal)
       return Promise.resolve([{ type: 'text', text: renderGoal(goal) }])
     },
     presentCall: args => present(

packages/goal/tool-goal/tests/tool-goal.spec.ts

@@ -287,6 +287,19 @@ describe('goal tool state transitions', () => {
       goal_id: goal['id'], revision: goal['revision'], action: 'resume',
     }, root.agent))
     expect(goal).toMatchObject({ phase: 'active', revision: 4 })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', 1)).toBeUndefined()
+  })
+
+  it('stops the current turn after a successful stopped-state mutation', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'pause cleanly' })
+    const paused = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'pause',
+    }, root.agent)
+    expect(resultGoal(paused)).toMatchObject({ phase: 'paused' })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', 1)).toEqual({ action: 'stop' })
+    expect(await agentEvents(ctx, root.agent).serial('agent/turn-stop', 1)).toBeUndefined()
   })
 
   it('rearms a restored active goal only after a new direct human prompt', async () => {