Merge advancing master into feat/mcp-auto-reconnect

Master advanced from c757901957abdfd87f1cd7b11ecab16f3050e65d to 1ac6ee70bb24a566cca74d99bdfe5b1bbc092940 while retarget verification was running. Preserve the already validated c757901957 checkpoint and merge the new tip forward instead of rewriting that checkpoint. The newer master changes subagent output selection and removes the empty experimental package group. It merges cleanly with PR #2187, so no feature-resolution changes are required; this commit makes final mergeability and CI evaluate the branch against the live master tip.
2026-08-29 04:26:38 +00:00 · 2026-08-11 11:26:58 +08:00
parent 6d87182099 53c58e3914
commit 4952db971a
62 changed files with 613 additions and 208 deletions
@@ -1,33 +0,0 @@
-# Agent Note: Experimental and internal package group
-
-Status: implemented
-
-English | [中文](2026-07-28-experimental-plugin-package-group.zh.md)
-
-## Problem
-
-The [package hierarchy](../../../../packages/README.md) groups plugins by product role, but it cannot distinguish release packages from prototypes or internal-only packages. The team needs an obvious shared place for useful work that is not part of the official release.
-
-## Decision
-
-The subtree rules in [`packages/experimental/AGENTS.md`](../../../../packages/experimental/AGENTS.md) make `packages/experimental/<pkg>/` the required home for Cordis plugin packages whose whole public contract is experimental or internal-only. Package names remain `@deepseek-ai/dsh-<pkg>`.
-
-The group is the team's in-repository place to share engineering and product-manager prototypes: members can discover, run, review, and extend one another's work against the real plugin graph without implying product support.
-
-Official releases exclude this directory. A package enters a release only after moving to its product-role group; release packages cannot take runtime dependencies on packages here. Examples may use them, while any other runtime dependent also belongs here. Tests may use them as development dependencies.
-
-Experimental packages carry no stability, compatibility, migration, or support promise: they may change APIs, configuration, or data, or disappear without deprecation or migration. Internal-only packages may define narrower internal contracts but make no public release promise. Neither status relaxes engineering, security, documentation, lifecycle, testing, or snapshot requirements.
-
-The pending `@deepseek-ai/dsh-tui-session-changes` `/diff` viewer and `/btw` plugin are examples governed by this rule. Promotion into an official release requires explicit review of the public contract, limitations, test evidence, and a named owner accepting stable-package obligations.
-
-## Alternatives considered
-
-**Keep experimental and internal-only packages in product-role groups with README labels.** Labels are easy to miss and cannot enforce dependency boundaries.
-
-**Treat every package as experimental until the first tagged release.** This provides no durable incubation boundary.
-
-**Develop prototypes and internal packages elsewhere.** This loses the real plugin graph, examples, snapshots, and lifecycle checks needed to evaluate them.
-
-## Consequences
-
-The path makes release exclusion and dependency blast radius visible while retaining the real plugin graph for team sharing. It gives up product-role colocation and creates path churn on promotion, while the npm name remains stable. The subtree rules, repository [current-owner/current-need rule](../../../../packages/AGENTS.md), and unchanged engineering gates limit junk-drawer growth. Because official release tooling does not yet exist, contributor policy enforces the exclusion; when such tooling is added, the directory is its required exclusion boundary.
@@ -1,33 +0,0 @@
-# Agent Note: 实验性与内部专用包分组
-
-Status: implemented
-
-[English](2026-07-28-experimental-plugin-package-group.md) | 中文
-
-## 问题
-
-[包层级结构](../../../../packages/README.md)按产品角色对插件分组，但无法区分发布包、原型和内部专用包。团队需要一个明确的共享位置，存放不属于官方发布版本的有价值成果。
-
-## 决策
-
-[`packages/experimental/AGENTS.md`](../../../../packages/experimental/AGENTS.md) 中的子树规则要求所有公开约定整体处于实验状态或仅限内部使用的 Cordis 插件包位于 `packages/experimental/<pkg>/`。包名仍为 `@deepseek-ai/dsh-<pkg>`。
-
-该分组供团队在仓库内共享工程人员和产品经理制作的原型：成员可以基于真实插件图发现、运行、评审并扩展彼此的原型，但这不代表产品会提供支持。
-
-官方发布版本不包含此目录。包只有移入对应的产品角色分组后才会纳入发布版本；发布包不得在运行时依赖此处的包。示例可以使用这些包；其他任何运行时依赖方也必须位于此处。测试可以将它们用作开发依赖。
-
-实验性包不提供稳定性、兼容性、迁移或支持保证：其 API、配置或数据可以变更，包也可以移除，均不提供弃用期或迁移路径。内部专用包可以定义范围更窄的内部约定，但不作公开发布承诺。无论哪种状态，都不降低仓库对工程、安全、文档、生命周期、测试或快照的要求。
-
-尚待完成的 `@deepseek-ai/dsh-tui-session-changes` `/diff` 查看器和 `/btw` 插件都受这项规则约束。将包提升为稳定包并纳入官方发布版本，需要明确评审其公开约定、限制和测试证据，并指定一名愿意承担稳定包义务的负责人。
-
-## 考虑过的替代方案
-
-**将实验性和内部专用包留在产品角色分组中，并用 README 标注。** 标注容易被忽略，也无法强制执行依赖边界。
-
-**首个带标签的版本发布前，将所有包都视为实验性。** 这无法提供持久的孵化边界。
-
-**在其他位置开发原型和内部专用包。** 这会失去评估它们所需的真实插件图、示例、快照和生命周期检查。
-
-## 后果
-
-该路径明确标示不纳入发布版本的包及其依赖影响范围，同时保留供团队共享成果的真实插件图。代价是这些包无法与同产品角色的包共置，提升并纳入发布版本时还会产生路径变动，但 npm 包名保持稳定。子树规则、仓库已有的[「必须有当前负责人和实际需求」规则](../../../../packages/AGENTS.md)以及保持不变的工程门禁，可限制该分组无序膨胀。由于官方发布工具尚不存在，目前由贡献者政策执行这项排除规则；添加发布工具后，必须以该目录为排除边界。
@@ -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 .agents/notes/implemented/architecture/2026-07-29-package-regrouping.md
-2026-07-29-package-regrouping.md: 3c37bce05bacd6af800a76ac93fb691b896a6772
-2026-07-29-package-regrouping.zh.md: 68903ff1fad6a975c4445fe8971c8fe0dd40117f
+2026-07-29-package-regrouping.md: 30fc45a122263350b4a2ad1998850f631c20f9b8
+2026-07-29-package-regrouping.zh.md: a3a9a11ec71b7f894dcea7c733eb39a80b71ac50
@@ -58,7 +58,7 @@ The moves landed as pure `git mv` moves, so rename detection carries the history

 A group move did not touch: npm names, imports, `cordis.yml` configs, snapshot fixtures, the `pnpm-workspace.yaml`/`tsdown` globs (both `packages/*/*`), or the Python runtime manifest — all reference packages by npm name.

-`client/` and `host/` were out of scope and are unchanged. The `experimental/` group proposal (PR #844) is orthogonal — a release-boundary container, not a clustering decision.
+`client/` and `host/` were out of scope and are unchanged.

 ## Alternatives considered

@@ -58,7 +58,7 @@ Status: implemented

 组移动未触及：npm 包名、import、`cordis.yml` 配置、快照 fixture（测试前置数据）、`pnpm-workspace.yaml` 与 `tsdown` 的 glob（都是 `packages/*/*`），以及 Python 运行时 manifest（元数据清单）——它们全部按 npm 包名引用包。

-`client/` 与 `host/` 不在本次范围内，保持不变。`experimental/` 组提案（PR #844）与本案正交：它是发布边界容器，不是聚类决策。
+`client/` 与 `host/` 不在本次范围内，保持不变。

 ## Alternatives considered

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # 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 .agents/notes/implemented/architecture/2026-07-28-experimental-plugin-package-group.md
-2026-07-28-experimental-plugin-package-group.md: 1ebae5dbb16d4c966f94ffde69fb0cb9bc163d80
-2026-07-28-experimental-plugin-package-group.zh.md: 2d09451c5069a775906e5bc8748c334c29008164
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.md
+2026-08-10-subagent-empty-terminal-message-output.md: 693013f6810005ce02b08bd82f1f6a18511c40fb
+2026-08-10-subagent-empty-terminal-message-output.zh.md: 64d61af21f838ef3f515db8af116cbdd74e96179
@@ -0,0 +1,31 @@
+# Agent Note: One selection rule keeps subagent output past an empty terminal message
+
+Status: implemented
+
+English | [中文](2026-08-10-subagent-empty-terminal-message-output.zh.md)
+
+## Problem
+
+The agent loop appends an empty-content `assistant/message` when a `max-tokens` step assembled only tool-call blocks because `BlockAssembler.blocks()` drops truncated tool calls; the message records usage only. Three consumers selected the child's output independently and treated that usage record as output. The in-process driver's `readResult` and the continuable Activation's `subagent/end` capture selected the last `assistant/message` without filtering, while the SDK backend's observer let any `assistant/message` take precedence over accumulated text. In a multi-step turn cut off at max-tokens, the final empty message caused the real partial answer to be omitted from `SubagentResult.output`, the tool result, telemetry, and `subagent/end.lastAssistantMessage`. The in-process driver also lacked a streamed-text fallback, so a cancelled child whose only text existed in `assistant/chunk` events reported `[]`.
+
+## Decision
+
+`dsh-subagent` owns one canonical selection rule in `src/assistant-output.ts`: select the last non-empty assistant message; without one, select the accumulated `text-delta` stream; ignore empty-content messages. The incremental `AssistantOutputFold` implements the rule through `push(event)` for session-event transports, `pushText(text)` for chunk-only transports, and `collect()` for selection. `finalAssistantOutput(events)` applies it to a complete event suffix for the in-process `readResult` and Activation capture. The SDK backend folds notification events; the ACP backend exposes no complete assistant messages and folds raw chunk text. `SubagentResult.output` defines the result contract, and `subagent/end.lastAssistantMessage` uses the same rule. When a child produces neither form of output, the lifecycle field is absent rather than an empty array for both one-shot and continuable runs. A `max-tokens` or `aborted` result retains its actual stop reason.
+
+The foreground delegation tool uses the same selection. A non-`completed` result remains an `isError` tool result, but its message appends the child's partial text after the stop-reason headline so the parent model receives both the failure and available output.
+
+## Verification
+
+The keyless SDK backend test uses `FAKE_EMPTY_MESSAGE` to emit a usage-only terminal message. The `subagent-max-tokens-partial` ACP snapshot records a child that streams text and a tool call, ends at a tool-only max-tokens step with an empty usage message in its durable log, and returns the partial text through the parent's errored tool result. Unit coverage checks empty terminal messages, cancellation, message ordering, textless non-empty messages, and exclusion of tool-result content.
+
+## Alternatives considered
+
+**Fix each consumer in place without a shared helper.** Rejected: three independent selections had diverged, while observers of one run must agree on its output.
+
+**Stop the loop from appending the empty message.** Rejected: the message records usage and preserves the step in the durable log ("model-visible ⟺ logged"); changing session events to address output selection would affect every replay and projection consumer.
+
+**Treat empty-content messages as an error.** Rejected: the streamed text is the child's real partial answer, and the stop reason already tells the consumer the turn was cut short.
+
+## Consequences
+
+Multi-step children cut off at max-tokens report their earlier text; cancelled in-process children retain text streamed before the abort; one-shot and continuable `subagent/end` events agree with `SubagentResult.output`. A message whose content is non-empty but textless, such as reasoning-only content, is selected instead of streamed text because the rule tests content length rather than text presence. A non-empty message is also selected instead of text streamed after it: a child cancelled while streaming a later step reports its earlier complete message, while the stop reason records the truncation.
@@ -0,0 +1,31 @@
+# Agent Note: 用同一条选取规则在空终止消息后保留子代理输出
+
+Status: implemented
+
+[English](2026-08-10-subagent-empty-terminal-message-output.md) | 中文
+
+## 问题
+
+当 `max-tokens` 步骤只组装了工具调用块时，agent loop（智能体循环）会追加一条空内容的 `assistant/message`，因为 `BlockAssembler.blocks()` 会丢弃被截断的工具调用；这条消息仅记录 usage。三个消费方独立选取子 agent 的输出，并把这条 usage 记录当成输出。进程内驱动的 `readResult` 与 continuable Activation 的 `subagent/end` capture 不加过滤地选取最后一条 `assistant/message`，SDK 后端的观察器则让任何 `assistant/message` 优先于累积的文本。在被 max-tokens 截断的多步轮次中，最后那条空消息导致 `SubagentResult.output`、工具结果、遥测与 `subagent/end.lastAssistantMessage` 都漏掉真实的部分回答。进程内驱动也没有流式文本兜底，因此被取消的子 agent 若其唯一文本只存在于 `assistant/chunk` 事件中，也会报告 `[]`。
+
+## 决策
+
+`dsh-subagent` 在 `src/assistant-output.ts` 中拥有唯一的规范选取规则：选取最后一条非空 assistant 消息；没有时选取累积的 `text-delta` 流；忽略空内容消息。增量的 `AssistantOutputFold` 通过 `push(event)` 处理会话事件传输，通过 `pushText(text)` 处理仅分片传输，并通过 `collect()` 完成选取。`finalAssistantOutput(events)` 把规则应用于完整的事件后缀，供进程内 `readResult` 与 Activation capture 使用。SDK 后端折叠通知事件；ACP 后端不暴露完整的 assistant 消息，而是折叠原始分片文本。`SubagentResult.output` 定义结果约定，`subagent/end.lastAssistantMessage` 使用同一规则。子 agent 不产生这两种输出中的任何一种时，一次性与 continuable 运行的生命周期字段都会缺省，而不是空数组。`max-tokens` 或 `aborted` 结果保留实际的终止原因。
+
+前台委派工具使用同一选取规则。非 `completed` 的结果仍是 `isError` 工具结果，但其消息会在终止原因标题之后附上子 agent 的部分文本，让父模型同时接收失败信息与已有输出。
+
+## 验证
+
+无密钥 SDK 后端测试使用 `FAKE_EMPTY_MESSAGE` 发出一条仅记录 usage 的终止消息。`subagent-max-tokens-partial` ACP 快照记录一个子 agent：它流式输出文本与一次工具调用，结束于仅含工具调用的 max-tokens 步骤，持久化日志中含一条空的 usage 消息，并通过父侧的错误工具结果返回部分文本。单元覆盖检查空终止消息、取消、消息顺序、不含文本的非空消息，以及排除工具结果内容。
+
+## 考虑过的替代方案
+
+**各消费方就地修复、不抽共享辅助函数。** 之所以否决：三处独立选取已发生分歧，而同一次运行的观察方必须对其输出达成一致。
+
+**让 loop 不再追加空消息。** 之所以否决：这条消息记录 usage，并在持久化日志中保留该步骤（"model-visible ⟺ logged"）；为处理输出选取而改动会话事件，会影响所有 replay 与 projection 消费方。
+
+**把空内容消息视为错误。** 之所以否决：流式文本才是子代理真实的部分回答，且终止原因已经告诉消费方轮次被截断。
+
+## 后果
+
+被 max-tokens 截断的多步子 agent 会报告其更早的文本；被取消的进程内子 agent 保留中止前已流式的文本；一次性与 continuable 的 `subagent/end` 事件同 `SubagentResult.output` 一致。内容非空但不含文本的消息（例如仅含 reasoning 的内容）仍然优先于流式文本，因为规则检查内容长度，而不是文本是否存在。非空消息同样优先于其后才流式出的文本：子 agent 在流式输出后续步骤时被取消，报告的是更早那条完整消息，终止原因则记录该截断。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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 .agents/notes/implemented/simplification/2026-08-11-remove-empty-experimental-package-group.md
+2026-08-11-remove-empty-experimental-package-group.md: e5e81e3e3763f216921b3f3b74709b64be3dee37
+2026-08-11-remove-empty-experimental-package-group.zh.md: d44d0daaf346a5fea317f8c8c6a23f26eaa3cec0
@@ -0,0 +1,37 @@
+# Agent Note: Remove the empty experimental package group
+
+Status: implemented
+
+English | [中文](2026-08-11-remove-empty-experimental-package-group.zh.md)
+
+## Problem
+
+The package hierarchy reserves `packages/experimental/` for prototypes and internal-only plugins, but no package has used the group. The empty group adds placement, dependency, promotion, and release rules without a current package or release mechanism that needs them.
+
+The original group aimed to let the team share prototypes against the real plugin graph without implying product support. That need remains possible, but it does not justify a permanent repository category before a concrete package exists.
+
+## Decision
+
+The package hierarchy has no reserved experimental or internal-only group. Packages continue to live in groups selected for their current product role.
+
+A concrete package that needs different release, stability, or dependency treatment requires a decision based on its actual consumers and release mechanism. That decision may reintroduce a dedicated group when it can also define and enforce the exclusion rules.
+
+This note consolidates and supersedes the experimental-package-group decision, whose active triplet is removed with the empty directory.
+
+## Alternatives considered
+
+**Keep the empty group.** It provides an obvious future incubation location, but it also keeps repository rules with no current owner, package, or enforcement mechanism.
+
+**Move the experimental rules into the general package instructions.** This preserves the policy without an empty directory, but makes every package change carry rules for a hypothetical package class.
+
+**Put concrete experimental packages in product-role groups with README labels.** This preserves product-role colocation, but labels alone cannot enforce release and runtime-dependency rules. A future package can evaluate this option against its actual release mechanism.
+
+**Treat every package as experimental until the first tagged release.** This applies a broad temporary status without providing durable treatment for packages that remain experimental after releases begin.
+
+**Require prototypes to stay outside the repository.** This would lose access to the real plugin graph, examples, snapshots, and lifecycle checks. Removing the reserved group does not impose that restriction; a concrete prototype can establish the placement it needs.
+
+## Consequences
+
+The hierarchy loses an unused group and its special release and dependency policy. It also gives up a predeclared location for team discovery and a ready-made promotion path.
+
+The first package that needs experimental or internal-only treatment must define where it lives, how releases exclude it, which runtime dependencies are allowed, and what condition promotes or removes it. A dedicated group can return when those rules have a current consumer and enforceable mechanism.
@@ -0,0 +1,37 @@
+# Agent Note: 移除空的实验性包分组
+
+Status: implemented
+
+[English](2026-08-11-remove-empty-experimental-package-group.md) | 中文
+
+## 问题
+
+包层级结构预留 `packages/experimental/` 用于原型和内部专用插件，但从未有包使用该分组。这个空分组添加了放置、依赖、提升和发布规则，却没有需要这些规则的现有包或发布机制。
+
+原分组旨在让团队基于真实插件图共享原型，同时不暗示产品会提供支持。这项需求将来可能出现，但在具体包出现前，不足以支持一个永久的仓库类别。
+
+## 决策
+
+包层级结构不再预留实验性或内部专用分组。包继续按照当前产品职责放入对应分组。
+
+如果具体包需要不同的发布、稳定性或依赖处理，必须根据其实际消费方和发布机制做出决策。只要该决策同时定义并强制执行排除规则，就可以重新引入专用分组。
+
+本 Agent Note 整合并取代实验性包分组决策；该旧决策的活跃三文件组随空目录一并移除。
+
+## 考虑过的替代方案
+
+**保留空分组。** 它为未来孵化工作提供明确位置，但也会保留没有当前负责人、包或强制执行机制的仓库规则。
+
+**将实验性规则移入通用包指令。** 这可以在不保留空目录的情况下延续政策，但会让每次包变更都携带针对假设包类别的规则。
+
+**将具体实验性包放入产品职责分组，并用 README 标注。** 这会保持产品职责共置，但仅靠标注无法强制执行发布和运行时依赖规则。未来的包可以根据实际发布机制评估此选项。
+
+**在首个带标签的版本发布前，将每个包都视为实验性。** 这会施加宽泛的临时状态，却无法为发布开始后仍处于实验状态的包提供持久处理方式。
+
+**要求原型留在仓库外。** 这会失去真实插件图、示例、快照和生命周期检查。移除预留分组并不施加这项限制；具体原型可以建立自身所需的放置规则。
+
+## 后果
+
+包层级结构移除了未使用的分组及其特殊发布和依赖政策，同时也放弃了预先声明的团队发现位置和现成的提升路径。
+
+第一个需要实验性或内部专用处理的包必须定义其存放位置、发布版本如何排除它、允许哪些运行时依赖，以及包在何种条件下获得提升或被移除。当这些规则具有当前消费方和可强制执行的机制时，可以恢复专用分组。
@@ -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 docs/event-producer-consumer.md
-event-producer-consumer.md: 4e68c0e5e6262ec7f31f4ed2d146ee18d3faa02a
-event-producer-consumer.zh.md: 1879e74f3e8c01143292b82a1745f4438f64e0ac
+event-producer-consumer.md: 19e2e660e58101b54054091b3d55b362d25d29dc
+event-producer-consumer.zh.md: d29cab8974d206b74b8869057b8efcf7542c1161
@@ -37,10 +37,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `settings/document-updated` | `emit` | [`packages/settings/settings/src/index.ts:170`](../packages/settings/settings/src/index.ts) | [`settings`](../packages/settings/settings) (`events.dispatch`) | `apiproxy` |
 | `settings/updated` | `emit` | [`packages/settings/settings/src/index.ts:157`](../packages/settings/settings/src/index.ts) | [`settings`](../packages/settings/settings) (`events.dispatch`) | [`settings`](../packages/settings/settings) |
 | `skills/change` | `emit` | [`packages/skill/skill/src/index.ts:297`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`events.dispatch`) | - |
-| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:164`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), `server`, [`subagent`](../packages/subagent/subagent) |
-| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:138`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
-| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:144`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
-| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:155`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) |
+| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:165`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), `server`, [`subagent`](../packages/subagent/subagent) |
+| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:139`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
+| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:145`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
+| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:156`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) |
 | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:31`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) |
 | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:37`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
 | `telemetry/record` | `waterfall` | [`packages/session/session-telemetry/src/index.ts:43`](../packages/session/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/session/session-telemetry) (`waterfall`) | - |
@@ -39,10 +39,10 @@
 | `settings/document-updated` | `emit` | [`packages/settings/settings/src/index.ts:170`](../packages/settings/settings/src/index.ts) | [`settings`](../packages/settings/settings) (`events.dispatch`) | `apiproxy` |
 | `settings/updated` | `emit` | [`packages/settings/settings/src/index.ts:157`](../packages/settings/settings/src/index.ts) | [`settings`](../packages/settings/settings) (`events.dispatch`) | [`settings`](../packages/settings/settings) |
 | `skills/change` | `emit` | [`packages/skill/skill/src/index.ts:297`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`events.dispatch`) | - |
-| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:164`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), `server`, [`subagent`](../packages/subagent/subagent) |
-| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:138`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
-| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:144`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
-| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:155`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) |
+| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:165`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), `server`, [`subagent`](../packages/subagent/subagent) |
+| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:139`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
+| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:145`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`subagent`](../packages/subagent/subagent), [`tool-subagent`](../packages/subagent/tool-subagent) |
+| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:156`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) |
 | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:31`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) |
 | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:37`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
 | `telemetry/record` | `waterfall` | [`packages/session/session-telemetry/src/index.ts:43`](../packages/session/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/session/session-telemetry) (`waterfall`) | - |
@@ -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 docs/subsystems/subagent.md
-subagent.md: 220ecf493b2d3a84cede34c1cf72dbf0dcd80353
-subagent.zh.md: b0a0df5a778ed758421225e524c87cf8ef213c0b
+subagent.md: 42359215b2e21028e13734c2a4cd2488f86a07af
+subagent.zh.md: 0d1d4c42fa774867679ff248bfc99b0024b04257
@@ -293,7 +293,12 @@ The outcome of a one-shot run, resolved by `SubagentRun.result`. `structured` is
 * The terminal outcome of a subagent run, resolved by {@link SubagentRun.result}.
 */
 interface SubagentResult {
-  /** The child's final assistant output (the last assistant message's content). */
+  /**
+   * The child's final assistant output is the content of its last non-empty
+   * assistant message. Empty-content messages, including usage-only messages,
+   * are skipped. Without a non-empty message, the output is its accumulated
+   * assistant text stream, or `[]` when the child produced neither.
+   */
  readonly output: ContentBlock[]
  /**
   * The structured result after a requested `outputSchema` was successfully
@@ -614,7 +619,7 @@ async start(name: string, request: SubagentStartRequest): Promise<SubagentRun>

 Types: [Agent](core.md) · [ContentBlock](llm-streaming.md) · [MessageId](llm-streaming.md) · [SessionId](core.md)

-Source: [`packages/subagent/subagent/src/index.ts:169`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:170`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagent-events"></a>

@@ -640,7 +645,7 @@ A published child settled. Scope-filtered dispatch uses the same delegating pare

 Types: [Scoped](scope.md)

-Source: [`packages/subagent/subagent/src/index.ts:164`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:165`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagentprovider-added--emit"></a>

@@ -657,7 +662,7 @@ A provider became resolvable in the registry.
 'subagent/provider-added'(provider: SubagentProvider): void
 ```

-Source: [`packages/subagent/subagent/src/index.ts:138`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:139`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagentprovider-removed--emit"></a>

@@ -674,7 +679,7 @@ A provider left the registry. Accepted runs remain holder-owned.
 'subagent/provider-removed'(name: string): void
 ```

-Source: [`packages/subagent/subagent/src/index.ts:144`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:145`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagentstart--emit"></a>

@@ -698,5 +703,5 @@ A provider established a published child. For in-process providers, `ctx.agents.

 Types: [Scoped](scope.md)

-Source: [`packages/subagent/subagent/src/index.ts:155`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:156`](../../packages/subagent/subagent/src/index.ts)
 <!-- END GENERATED cordis-surface -->
@@ -293,7 +293,12 @@ type SubagentDescendantListEntry = SubagentListEntry & {
 * The terminal outcome of a subagent run, resolved by {@link SubagentRun.result}.
 */
 interface SubagentResult {
-  /** The child's final assistant output (the last assistant message's content). */
+  /**
+   * The child's final assistant output is the content of its last non-empty
+   * assistant message. Empty-content messages, including usage-only messages,
+   * are skipped. Without a non-empty message, the output is its accumulated
+   * assistant text stream, or `[]` when the child produced neither.
+   */
  readonly output: ContentBlock[]
  /**
   * The structured result after a requested `outputSchema` was successfully
@@ -616,7 +621,7 @@ async start(name: string, request: SubagentStartRequest): Promise<SubagentRun>

 Types: [Agent](core.md) · [ContentBlock](llm-streaming.md) · [MessageId](llm-streaming.md) · [SessionId](core.md)

-Source: [`packages/subagent/subagent/src/index.ts:169`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:170`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagent-events"></a>

@@ -642,7 +647,7 @@ A published child settled. Scope-filtered dispatch uses the same delegating pare

 Types: [Scoped](scope.md)

-Source: [`packages/subagent/subagent/src/index.ts:164`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:165`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagentprovider-added--emit"></a>

@@ -659,7 +664,7 @@ A provider became resolvable in the registry.
 'subagent/provider-added'(provider: SubagentProvider): void
 ```

-Source: [`packages/subagent/subagent/src/index.ts:138`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:139`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagentprovider-removed--emit"></a>

@@ -676,7 +681,7 @@ A provider left the registry. Accepted runs remain holder-owned.
 'subagent/provider-removed'(name: string): void
 ```

-Source: [`packages/subagent/subagent/src/index.ts:144`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:145`](../../packages/subagent/subagent/src/index.ts)

 <a id="subagentstart--emit"></a>

@@ -700,5 +705,5 @@ A provider established a published child. For in-process providers, `ctx.agents.

 Types: [Scoped](scope.md)

-Source: [`packages/subagent/subagent/src/index.ts:155`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:156`](../../packages/subagent/subagent/src/index.ts)
 <!-- END GENERATED cordis-surface -->
@@ -341,6 +341,10 @@ const SCENARIOS: Scenario[] = [
  // Windows bash process-tree kill is deferred with the Bash execution domain.
  { name: 'cancel-tool-calls', hasModelTurn: true, recorded: false, overridden: true, posixOnly: true },
  { name: 'subagent-spawn', hasModelTurn: true, recorded: true },
+  // Keyless authored scenario: the child ends at max-tokens with an empty
+  // usage-only assistant/message after earlier text and a tool call. The
+  // parent's tool result must retain that assistant output and stop reason.
+  { name: 'subagent-max-tokens-partial', hasModelTurn: true, recorded: false },
  { name: 'subagent-multi', hasModelTurn: true, recorded: true },
  { name: 'subagent-fork', hasModelTurn: true, recorded: true },
  { name: 'subagent-mixed', hasModelTurn: true, recorded: true },
@@ -0,0 +1,14 @@
+{
+  "steps": [
+    {
+      "op": "initialize"
+    },
+    {
+      "op": "newSession"
+    },
+    {
+      "op": "prompt",
+      "text": "Use the subagent tool exactly once to delegate this subtask: \"Write the words 'partial one', call todo_write once, then keep going until you are cut off.\" After the subagent returns, reply with the single word PARENT_DONE and stop."
+    }
+  ]
+}
@@ -0,0 +1,31 @@
+{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":2,"cwd":"{{cwd}}","parentSession":"11111111-1111-4111-8111-111111111111","origin":"subagent","delegationDepth":1}
+{"type":"approval/policy","seq":0,"time":1786373921809,"data":{"policy":"never","source":"delegation"}}
+{"type":"agent/inbox/spliced","seq":1,"time":1786373921809,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Write the words 'partial one', call todo_write once, then keep going until you are cut off."}],"source":{"kind":"user"},"role":"user","id":"dbf0670a-79cc-4e2c-a298-c4d804e6fe61"}]}}
+{"type":"turn/start","seq":2,"time":1786373921810,"data":{"turn":1}}
+{"type":"agent/inbox/spliced","seq":3,"time":1786373921810,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
+{"type":"subagent/descriptor","seq":4,"time":1786373921831,"data":{"version":2,"mode":"one-shot","provider":"spawn","label":"Truncated child"}}
+{"type":"step/start","seq":5,"time":1786373921836,"data":{"turn":1,"step":1}}
+{"type":"user/message","seq":6,"time":1786348800142,"data":{"content":[{"type":"text","text":"Write the words 'partial one', call todo_write once, then keep going until you are cut off."}],"source":{"kind":"user"},"role":"user","id":"dbf0670a-79cc-4e2c-a298-c4d804e6fe61"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":1786373921837,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"885ea744-63dd-4198-95be-267b9db94a57"},"surfaceOp":"append"}
+{"type":"session/title","seq":8,"time":1786373921837,"data":{"title":"Write the words 'partial one',","messageSeqs":[6],"source":{"kind":"fallback"}}}
+{"type":"request/header","seq":9,"time":1786348800142,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","seq":10,"time":1786348800142,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
+{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":12,"time":1786348800146,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"partial one"}}}}
+{"type":"assistant/chunk","seq":13,"time":1786348800146,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":14,"time":1786348800146,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_child_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"keep going\", \"status\": \"in_progress\"}]}"}}}}
+{"type":"assistant/chunk","seq":15,"time":1786348800146,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":9}}}}
+{"type":"assistant/chunk","seq":16,"time":1786348800146,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":17,"time":1786348800146,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"partial one"},{"type":"tool-call","id":"call_child_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"keep going\", \"status\": \"in_progress\"}]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"5e4d07b2-6ce2-4ab6-8be0-fbdf2d3af138"},"usage":{"inputTokens":20,"outputTokens":9}},"sourceEventSeqs":[11,12,13,14,15,16],"surfaceOp":"append"}
+{"type":"tool/call","seq":18,"time":1786348800146,"data":{"turn":1,"step":1,"callId":"call_child_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"keep going\", \"status\": \"in_progress\"}]}"}}
+{"type":"todo/write","seq":19,"time":1786348800150,"data":{"todos":[{"content":"keep going","status":"in_progress"}]}}
+{"type":"tool/result","seq":20,"time":1786348800151,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_child_1"},"content":[{"type":"tool-result","toolCallId":"call_child_1","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false}],"role":"user","id":"67efbbf3-ca1e-4d23-8f19-940cb391ff1e"}},"sourceEventSeqs":[18],"surfaceOp":"append"}
+{"type":"step/end","seq":21,"time":1786348800151,"data":{"turn":1,"step":1}}
+{"type":"step/start","seq":22,"time":1786348800156,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":23,"time":1786348800160,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":24,"time":1786348800160,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_child_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"keep going\", \"status\": \"completed\"}]}"}}}}
+{"type":"assistant/chunk","seq":25,"time":1786348800160,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}
+{"type":"assistant/chunk","seq":26,"time":1786348800160,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"max-tokens"}}}}
+{"type":"assistant/message","seq":27,"time":1786348800160,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"bb92e4ec-f260-4415-9782-b71147ea378d"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[23,24,25,26],"surfaceOp":"append"}
+{"type":"step/end","seq":28,"time":1786348800160,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":29,"time":1786348800160,"data":{"turn":1,"reason":{"kind":"max-tokens"}}}
@@ -0,0 +1,26 @@
+{"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1,"cwd":"{{cwd}}","delegationDepth":0}
+{"type":"agent/inbox/spliced","seq":0,"time":1786348800078,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask: \"Write the words 'partial one', call todo_write once, then keep going until you are cut off.\" After the subagent returns, reply with the single word PARENT_DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"8787ce07-4f1f-4368-bf58-18e30484ed44"}]}}
+{"type":"turn/start","seq":1,"time":1786348800079,"data":{"turn":1}}
+{"type":"agent/inbox/spliced","seq":2,"time":1786348800079,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
+{"type":"step/start","seq":3,"time":1786348800114,"data":{"turn":1,"step":1}}
+{"type":"user/message","seq":4,"time":1786348800114,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask: \"Write the words 'partial one', call todo_write once, then keep going until you are cut off.\" After the subagent returns, reply with the single word PARENT_DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"8787ce07-4f1f-4368-bf58-18e30484ed44"},"surfaceOp":"append"}
+{"type":"user/message","seq":5,"time":1786348800114,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"32a8b2ce-f1f9-411b-940d-c80f772561ac"},"surfaceOp":"append"}
+{"type":"session/title","seq":6,"time":1786348800114,"data":{"title":"Use the subagent tool exactly","messageSeqs":[4],"source":{"kind":"fallback"}}}
+{"type":"request/header","seq":7,"time":1786348800115,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","seq":8,"time":1786348800115,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
+{"type":"assistant/chunk","seq":9,"time":1786348800120,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":10,"time":1786348800120,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_parent_1","name":"subagent","arguments":"{\"description\": \"Truncated child\", \"prompt\": \"Write the words 'partial one', call todo_write once, then keep going until you are cut off.\"}"}}}}
+{"type":"assistant/chunk","seq":11,"time":1786348800120,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
+{"type":"assistant/chunk","seq":12,"time":1786348800120,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":13,"time":1786348800120,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_parent_1","name":"subagent","arguments":"{\"description\": \"Truncated child\", \"prompt\": \"Write the words 'partial one', call todo_write once, then keep going until you are cut off.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"f4269cd2-9132-4b68-8f9b-ff3a40321bc9"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
+{"type":"tool/call","seq":14,"time":1786348800121,"data":{"turn":1,"step":1,"callId":"call_parent_1","name":"subagent","arguments":"{\"description\": \"Truncated child\", \"prompt\": \"Write the words 'partial one', call todo_write once, then keep going until you are cut off.\"}"}}
+{"type":"tool/result","seq":15,"time":1786348800163,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_parent_1"},"content":[{"type":"tool-result","toolCallId":"call_parent_1","content":[{"type":"text","text":"Error: subagent run hit its token limit before finishing\nPartial output before the run ended:\npartial one"}],"isError":true}],"role":"user","id":"5dd34050-a533-4f1b-99ee-5fc62c6a4502"}},"sourceEventSeqs":[14],"surfaceOp":"append"}
+{"type":"step/end","seq":16,"time":1786348800163,"data":{"turn":1,"step":1}}
+{"type":"step/start","seq":17,"time":1786348800169,"data":{"turn":1,"step":2}}
+{"type":"assistant/chunk","seq":18,"time":1786348800173,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":19,"time":1786348800173,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PARENT_DONE"}}}}
+{"type":"assistant/chunk","seq":20,"time":1786348800173,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2}}}}
+{"type":"assistant/chunk","seq":21,"time":1786348800173,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":22,"time":1786348800173,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"PARENT_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"fb14560d-1d98-4b18-8736-b079de400315"},"usage":{"inputTokens":12,"outputTokens":2}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"}
+{"type":"step/end","seq":23,"time":1786348800173,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":24,"time":1786348800173,"data":{"turn":1,"reason":{"kind":"completed"}}}
@@ -0,0 +1,4 @@
+{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
+{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"PARENT_DONE"}}}}
+{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
@@ -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/README.md
-README.md: 19d6e5ba7b554f59bd66e213f8a53389761fc735
-README.zh.md: 17f58a2922e9019af054b0dccb6c4d9199fd1a9d
+README.md: eb7df95bde10dafd7afcb168d30c9dda90296687
+README.zh.md: 03cd02510267d3abdd414bed6ec1f42773d0811a
@@ -52,7 +52,6 @@ Groups hold `packages/<group>/<pkg>/`; names stay `@deepseek-ai/dsh-<pkg>`. **Gr
 | [`boot/`](boot/README.md) | Shared app-bin boot glue | Product — stable surface |
 | [`host/`](host/README.md) | Web-GUI host half: API gateway + HTTP route server | Product — stable surface |
 | [`client/`](client/README.md) | Web-GUI browser half: shell, wire, object services, slots, `ui-*` plugins | Product — stable surface |
-| [`experimental/`](experimental/README.md) | Prototypes and internal plugins | Unreleased |
 | [`examples/`](examples/README.md) | Demo bundles (agent-spine + CLI/ACP/JSON-RPC bins) leaves load | Support — example infra |
 | [`support/`](support/README.md) | Support infrastructure (testkits, invariants, replay, Loader smokes) | Support — lower compatibility expectations |
 | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (`Branded<B>`, Harness home/path helpers, timeout, retention) | Support — small, stable, harness-dep-free |
@@ -52,7 +52,6 @@ npm scope 为 `@deepseek-ai/dsh-*`；Cordis `Service` 子类和函数插件通
 | [`boot/`](boot/README.md) | 共享的 app bin 启动粘合层 | 产品：稳定接口 |
 | [`host/`](host/README.md) | web GUI 宿主半侧：API 网关 + HTTP 路由服务器 | 产品：稳定接口 |
 | [`client/`](client/README.md) | web GUI 浏览器半侧：shell、协议层、对象服务、slot、`ui-*` 插件 | 产品：稳定接口 |
-| [`experimental/`](experimental/README.md) | 原型和内部插件 | 未发布 |
 | [`examples/`](examples/README.md) | 演示组合包（agent-spine + CLI/ACP/JSON-RPC bin），由叶节点加载 | 支持：示例基础设施 |
 | [`support/`](support/README.md) | 支持基础设施（testkit、不变式、回放、Loader 冒烟测试） | 支持：兼容性预期较低 |
 | [`util/`](util/README.md) | 组间共享的低层零依赖工具（`Branded<B>`、Harness home／路径辅助函数、超时、保留策略） | 支持：小型、稳定、无 harness 依赖 |
@@ -1,11 +0,0 @@
-# AGENTS.md — Experimental and internal packages
-
-These rules supplement the [package rules](../AGENTS.md). The [experimental and internal package group decision](../../.agents/notes/implemented/architecture/2026-07-28-experimental-plugin-package-group.md) owns the rationale.
-
- All Cordis plugin packages whose full public contract is experimental or internal-only belong here. An experimental option inside an otherwise stable package stays in that package's product-role group.
- Use this directory to share engineering and product-manager prototypes across the team so others can discover, run, review, and extend them against the real plugin graph.
- Official releases exclude this directory. A package enters a release only after moving to its product-role group; do not add packages here to release manifests or bundles.
- Experimental packages carry no stability, compatibility, migration, or support promise. Internal-only packages may define contracts for a limited set of internal callers and callees but make no public release promise.
- Experimental or internal-only status never relaxes repository engineering, security, documentation, lifecycle, testing, or snapshot requirements.
- Release packages must not take runtime dependencies on packages here. Examples may; every other runtime dependent is also experimental or internal-only and belongs here. Tests may use them as development dependencies.
- Promotion moves a package to its product-role group without renaming its `@deepseek-ai/dsh-*` package. Require explicit review of its public contract, limitations, test evidence, and a named owner accepting stable-package obligations.
@@ -1,6 +0,0 @@
-# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
-# 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/experimental/README.md
-README.md: db39af8bb1b1bcfd257e16e4ad1dd112f604ffb1
-README.zh.md: fc5942190a354668164b41b99e83b52b14d88f18
@@ -1,7 +0,0 @@
-# experimental/ — experimental and internal packages
-
-English | [中文](README.zh.md)
-
-This group hosts team-shared engineering and product-manager prototypes plus internal-only Cordis plugins. It is excluded from official releases; packages move to their product-role group before release.
-
-No packages live here yet. The [subtree rules](AGENTS.md) define the no-warranty, dependency, and promotion boundaries.
@@ -1,7 +0,0 @@
-# experimental/：实验性与内部专用包
-
-[English](README.md) | 中文
-
-该分组容纳工程人员与产品经理在团队内共享的原型，以及内部专用 Cordis 插件。该分组不纳入官方发布版本；包在发布前移入对应的产品角色分组。
-
-该分组尚未包含任何包。[子树规则](AGENTS.md)界定不作保证、依赖关系和提升机制的边界。
@@ -26,6 +26,8 @@
 *   array; `FAKE_MESSAGE_WITHOUT_DATA`: assistant/message with no data
 *   member; `FAKE_MALFORMED_REASON`: `session.finished` reason is a bare
 *   string (wire-validation probes).
+ * - `FAKE_EMPTY_MESSAGE`: the turn streams a text chunk, then records an empty
+ *   assistant/message for a usage-only max-tokens step.
 * - `FAKE_HANG_INIT`: never answer `initialize` (mid-handshake cancel probe).
 * - `FAKE_INIT_READY` + `FAKE_INIT_GO`: touch the READY file when `initialize`
 *   arrives, then poll for the GO file before answering (deterministic
@@ -117,7 +119,9 @@ function runTurn(sessionId: string): void {
    message: {
      id: `fake-assistant-${seq}`,
      role: 'assistant',
-      content: [{ type: 'text', text }],
+      // Model the usage-only message recorded after a max-tokens step that
+      // assembled no output blocks.
+      content: env.FAKE_EMPTY_MESSAGE !== undefined ? [] : [{ type: 'text', text }],
      source: { kind: 'model', provider: 'fake', model: 'fake' },
    },
  })
@@ -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/scaffold/protocol/README.md
-README.md: 88a48957d0d44cec9f776d31eab7d25bd353de5f
-README.zh.md: 6618d8838a00f945c79d7ec24b1e7491df08a3f1
+README.md: 082a890454f900aec51df123669f28814d39d601
+README.zh.md: d9b8460e51b5313f4c3a8ac66471e8cd39142430
@@ -22,7 +22,7 @@ The shared wire protocol for the DeepSeek Harness SDK runtime: one newline-delim
 | server→client | `subagent.started` | `SubagentStartedNotification` |
 | server→client | `subagent.finished` | `SubagentFinishedNotification` (in-process runs only) |

-`HarnessSdkRequestMap` and `HarnessSdkNotificationMap` index these by method name. `SessionPromptResult.messageId` identifies the queued `UserMessage`; it does not identify a later assistant message, turn ending, or prompt result. Clients combine the open-ended `session.event` stream with agent-wide `session.status` according to their own activity ownership. `InitializeParams.maxTokens` is an optional positive safe integer that caps each conversation-model output for SDK-created agents and their in-process descendants; omission allows the selected adapter's exact-model default to apply, or otherwise preserves provider behavior. The notification payload types depend on `SessionEvent` (`dsh-session`), `ContentBlock` (`dsh-llm`), and `SubagentStopReason` (`dsh-subagent`) — the protocol streams full session-log envelopes, so the session vocabulary is part of the wire contract. `serverInfo.name` stays the wire-stable `deepseek-harness-sdk-runtime`.
+`HarnessSdkRequestMap` and `HarnessSdkNotificationMap` index these by method name. `SessionPromptResult.messageId` identifies the queued `UserMessage`; it does not identify a later assistant message, turn ending, or prompt result. Clients combine the open-ended `session.event` stream with agent-wide `session.status` according to their own activity ownership. `SubagentFinishedNotification.lastAssistantMessage` contains the child's last non-empty assistant message or, when no such message exists, its accumulated assistant text; the field is absent when the child produced neither. `InitializeParams.maxTokens` is an optional positive safe integer that caps each conversation-model output for SDK-created agents and their in-process descendants; omission allows the selected adapter's exact-model default to apply, or otherwise preserves provider behavior. The notification payload types depend on `SessionEvent` (`dsh-session`), `ContentBlock` (`dsh-llm`), and `SubagentStopReason` (`dsh-subagent`) — the protocol streams full session-log envelopes, so the session vocabulary is part of the wire contract. `serverInfo.name` stays the wire-stable `deepseek-harness-sdk-runtime`.

 ## Model Experience

@@ -22,7 +22,7 @@ DeepSeek Harness SDK 运行时的共享协议格式（wire format）：一个按
 | server→client | `subagent.started` | `SubagentStartedNotification` |
 | server→client | `subagent.finished` | `SubagentFinishedNotification`（仅进程内运行） |

-`HarnessSdkRequestMap` 与 `HarnessSdkNotificationMap` 按方法名索引这些类型。`SessionPromptResult.messageId` 标识已排队的 `UserMessage`；它不标识后续的助手消息、轮次结束或提示词结果。客户端根据自己对活动区间的所有权，组合持续开放的 `session.event` 流与 agent 级的 `session.status`。`InitializeParams.maxTokens` 是可选的正的安全整数，用于限制 SDK 创建的 agent 及其进程内后代的每次对话模型输出；省略时会应用所选适配器的确切模型默认值，否则提供方行为保持不变。通知载荷类型依赖 `SessionEvent`（`dsh-session`）、`ContentBlock`（`dsh-llm`）与 `SubagentStopReason`（`dsh-subagent`）——协议以完整会话日志封套进行流式传输，因此会话词汇是协议格式约定的一部分。`serverInfo.name` 的协议值固定为 `deepseek-harness-sdk-runtime`。
+`HarnessSdkRequestMap` 与 `HarnessSdkNotificationMap` 按方法名索引这些类型。`SessionPromptResult.messageId` 标识已排队的 `UserMessage`；它不标识后续的助手消息、轮次结束或提示词结果。客户端根据自己对活动区间的所有权，组合持续开放的 `session.event` 流与 agent 级的 `session.status`。`SubagentFinishedNotification.lastAssistantMessage` 包含子 agent 最后一条非空 assistant 消息；若不存在这类消息，则包含其累积的 assistant 文本；子 agent 两种输出均未产生时，该字段缺省。`InitializeParams.maxTokens` 是可选的正的安全整数，用于限制 SDK 创建的 agent 及其进程内后代的每次对话模型输出；省略时会应用所选适配器的确切模型默认值，否则提供方行为保持不变。通知载荷类型依赖 `SessionEvent`（`dsh-session`）、`ContentBlock`（`dsh-llm`）与 `SubagentStopReason`（`dsh-subagent`）——协议以完整会话日志封套进行流式传输，因此会话词汇是协议格式约定的一部分。`serverInfo.name` 的协议值固定为 `deepseek-harness-sdk-runtime`。

 ## 模型体验

@@ -85,7 +85,7 @@ export interface SubagentFinishedNotification {
  status: SdkRunStatus
  /** The provider-reported stop reason. */
  stopReason: SubagentStopReason
-  /** The child's final assistant message, when it produced one. */
+  /** The child's selected assistant output; absent when the child produced none. */
  lastAssistantMessage?: ContentBlock[]
 }

@@ -106,6 +106,8 @@ describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', (
    })

    expect(stderr).not.toContain('listener threw')
+    // A result without output omits lastAssistantMessage from the wire; it
+    // never sends `[]`.
    expect(JSON.parse(stdout) as unknown).toEqual([{
      method: 'subagent.finished',
      params: {
@@ -115,7 +117,6 @@ describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', (
        childSessionId: 'built-child',
        status: 'ok',
        stopReason: 'completed',
-        lastAssistantMessage: [],
      },
    }])
  })
@@ -736,6 +736,8 @@ describe('HarnessSdkServer', () => {
        stopReason: 'error',
      })

+      // A result without output omits lastAssistantMessage from the wire; it
+      // never sends `[]`.
      expect(transport.notifications).toContainEqual({
        method: 'subagent.finished',
        params: {
@@ -745,7 +747,6 @@ describe('HarnessSdkServer', () => {
          childSessionId: 'fallback-child-session',
          status: 'ok',
          stopReason: 'max-tokens',
-          lastAssistantMessage: [],
        },
      })
      expect(transport.notifications).toContainEqual({
@@ -24,6 +24,7 @@ import {
 } from '@agentclientprotocol/sdk'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import { SessionId } from '@deepseek-ai/dsh-session'
+import { AssistantOutputFold } from '@deepseek-ai/dsh-subagent'
 import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent'
 import type { SubprocessHandle, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess'

@@ -232,8 +233,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe
  let processDisposal: Promise<void> | undefined
  const disposeProcess = (): Promise<void> => (processDisposal ??= disposeAcpChild(child, spec.disposeEofGraceMs))

-  // Accumulate the child's streamed assistant text — the SubagentResult output.
-  const output: string[] = []
+  // ACP exposes no complete assistant messages, so the shared fold selects its
+  // accumulated assistant text.
+  const fold = new AssistantOutputFold()
  // Shared mutable state keeps cancellation visible across async closures.
  const flags = { cancelled: false }

@@ -241,7 +243,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe
    sessionUpdate(params: SessionNotification): Promise<void> {
      const update = params.update
      if (update.sessionUpdate === 'agent_message_chunk') {
-        output.push(acpContentText(update.content))
+        fold.pushText(acpContentText(update.content))
      }
      // Other updates (thoughts, tool calls, plans) are consumed but not
      // surfaced — the subagent returns only its final answer.
@@ -284,13 +286,8 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe
  const onAbort = (): void => { requestCancel() }
  request.signal.addEventListener('abort', onAbort, { once: true })

-  // The accumulated child text as harness ContentBlocks (empty array when the
-  // child streamed nothing). Read at every return so a partial answer survives
-  // a later cancel/error.
-  const collectOutput = (): ContentBlock[] => {
-    const text = output.join('')
-    return text.length > 0 ? [{ type: 'text', text }] : []
-  }
+  // Read at every return so a partial answer survives a later cancel/error.
+  const collectOutput = (): ContentBlock[] => fold.collect() ?? []

  // Establish the remote session before publishing a handle. Any failure owns
  // the still-private process and therefore reaps it before rejecting.
@@ -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/subagent/subagent-dsh-sdk/README.md
-README.md: 0bbcfa105ecf024a2492d39d3bf8d28956110050
-README.zh.md: 8c8551f85951aa8475ab2ce95771e4d54e0ed89a
+README.md: 493bb187d45c7654958cfb3dbbe1dee6bb21b368
+README.zh.md: 2e1d9b1e602f2180d20d43fe8c358163ec4ec024
@@ -10,7 +10,7 @@ The SDK provider runs each subagent as a complete DeepSeek Harness runtime in a

 The working directory resolves exactly like the ACP backend, through the seam's shared out-of-process helpers ([`dsh-subagent`](../subagent/README.md)): the configured `cwd` override when set (validated once at load), else the delegating parent session's cwd — never the server process's own cwd. The resolved path becomes the child process cwd and the workspace cwd of its SDK session.

-The returned run id is minted in the parent namespace; the child runtime's session id exists only inside the child process. After publication the provider owns one SDK activity and reads the child's answer from its session events: the last complete `assistant/message`, or the `text-delta` stream accumulated before the activity was cut short — a partial answer survives cancel and error paths.
+The returned run id is minted in the parent namespace; the child runtime's session id exists only inside the child process. After publication the provider owns one SDK activity and reads the child's answer from its session events: the last complete non-empty `assistant/message` (an empty-content message that records usage is skipped), or the accumulated `text-delta` stream when no such message exists. Partial output remains available after cancellation or an error.

 `dispose()` is idempotent: it settles the result locally as `aborted` (there is no wire-level prompt cancel), then closes the runtime — a bounded protocol `shutdown` request followed by the shared stdin-EOF → SIGTERM → SIGKILL ladder to actual exit.

@@ -10,7 +10,7 @@ SDK 提供方会在全新的子进程中把每个 subagent 作为完整的 DeepS

 工作目录的解析与 ACP 后端完全一致，并使用 seam 共享的进程外辅助工具（[`dsh-subagent`](../subagent/README.md)）：设置了 `cwd` 覆盖值时使用该值（加载时校验一次），否则使用发起委派的父会话 cwd，绝不使用服务器进程自身的 cwd。解析出的路径同时成为子进程 cwd 和其 SDK 会话的工作区 cwd。

-返回的 run id 在父级命名空间中生成；子运行时的会话 id 只存在于子进程内部。发布后，提供方拥有一段 SDK 活动，并从子会话事件中读取答案：最后一条完整的 `assistant/message`，或该活动中断前已经累积的 `text-delta` 流；部分答案在取消和错误路径上都得以保留。
+返回的 run id 在父级命名空间中生成；子运行时的会话 id 只存在于子进程内部。发布后，提供方拥有一段 SDK 活动，并从子会话事件中读取答案：最后一条完整且非空的 `assistant/message`（记录 usage 的空内容消息会被跳过）；若没有这类消息，则取累积的 `text-delta` 流。取消或发生错误后，部分输出仍然可用。

 `dispose()`（资源释放）是幂等的：先在本地把结果确定为 `aborted`（协议层面没有提示词取消机制），再关闭运行时，即先发出一次有界的协议 `shutdown` 请求，随后通过共享的 stdin-EOF → SIGTERM → SIGKILL 阶梯使进程实际退出。

@@ -16,7 +16,7 @@ import { DeepSeekHarness, type HarnessNotification } from '@deepseek-ai/dsh-sdk-
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
 import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent'
-import { settleRunResult, subprocessRunHandle } from '@deepseek-ai/dsh-subagent'
+import { AssistantOutputFold, settleRunResult, subprocessRunHandle } from '@deepseek-ai/dsh-subagent'
 import { scrubbedParentEnv } from '@deepseek-ai/dsh-subprocess'

 /** Resolved spawn spec for an SDK runtime child process (no defaults — see Config). */
@@ -163,24 +163,14 @@ export async function startSdkRun(request: SubagentStartRequest, spec: SdkRunSpe
  }

  const childSessionId = `session-${randomUUID().replaceAll('-', '')}`
-  // The child's final answer: the last complete assistant message when one
-  // exists, else the text streamed so far (a partial answer surviving cancel).
-  let lastMessage: ContentBlock[] | undefined
-  const partial: string[] = []
+  // The child's final answer under the seam's canonical selection rule
+  // (`AssistantOutputFold`); a partial answer survives cancel and error paths.
+  const fold = new AssistantOutputFold()
  const observe = (notification: HarnessNotification): void => {
    if (notification.method !== 'session.event' || notification.params.sessionId !== childSessionId) return
-    const event = notification.params.event as SessionEvent
-    if (event.type === 'assistant/chunk' && event.data.chunk.type === 'text-delta') {
-      partial.push(event.data.chunk.text)
-    } else if (event.type === 'assistant/message') {
-      lastMessage = event.data.message.content
-    }
-  }
-  const collectOutput = (): ContentBlock[] => {
-    if (lastMessage !== undefined) return lastMessage
-    const text = partial.join('')
-    return text.length > 0 ? [{ type: 'text', text }] : []
+    fold.push(notification.params.event as SessionEvent)
  }
+  const collectOutput = (): ContentBlock[] => fold.collect() ?? []

  // Race the child turn against local cancellation; the shared settlement
  // flattens failures under the seam's never-reject contract.
@@ -176,6 +176,20 @@ describe('dsh-subagent-dsh-sdk provider', () => {
    await ctx.fiber.dispose()
  })

+  it('keeps streamed text when the terminal message is an empty usage-only step', async () => {
+    // The child streams its answer, then emits an empty-content
+    // assistant/message (the harness loop appends one to host usage on a
+    // max-tokens step that assembled no text blocks). The empty message is
+    // not assistant output and must not erase the streamed answer.
+    const ctx = await setup({ FAKE_EMPTY_MESSAGE: '1', FAKE_REASON_KIND: 'max-tokens' })
+    const run = await ctx.subagents.start('dsh-sdk', request())
+    const result = await run.result
+    expect(result.stopReason).toBe('max-tokens')
+    expect(text(result.output)).toBe('hello from fake runtime')
+    await run.dispose()
+    await ctx.fiber.dispose()
+  })
+
  it('reports a settled-without-turn child as an error', async () => {
    const ctx = await setup({ FAKE_REASON_KIND: 'none', FAKE_STATUS: 'error' })
    const run = await ctx.subagents.start('dsh-sdk', request())
@@ -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/subagent/subagent-inprocess/README.md
-README.md: 209f1e9526ff4a01af6f4c96955068de4b2b06c0
-README.zh.md: 8623be4bc1ab39aa7718de204dd0507843b0ab14
+README.md: 69def8bf8f41e3685d017ac4b003b26a37f064ef
+README.zh.md: bf5e7cb5cc8517ee7020695ef10e3b58d613541b
@@ -14,7 +14,7 @@ The driver follows this sequence:
 2. Call `parent.ctx.agents.create` directly, passing the required request signal into the factory's creation transaction.
 3. During that transaction's unpublished setup window, install the requested persona, tool restriction, and structured-output runtime.
 4. Publish the child, retain the returned `AgentHandle`, and drive one task with `child.followup(prompt)` followed by `child.whenIdle()`.
-5. Read the child's own last assistant message and final durable turn reason from the complete owned child run, excluding any fork seed.
+5. Read the child's own output — its last non-empty assistant message (an empty-content message that records usage is skipped), or its accumulated assistant text when no such message exists — and the final durable turn reason from the complete owned child run, excluding any fork seed.

 The child gets the parent's working-directory/session lineage and inherits the parent provider, model, and output-token cap unless `request.agentOptions` overrides them. It gets a fresh flat registration scope: parent ownership does not import parent tool restrictions or establish an authority subset.

@@ -14,7 +14,7 @@
 2. 直接调用 `parent.ctx.agents.create`，把必需的请求信号传入工厂的创建事务。
 3. 在该事务未发布的设置窗口中，安装请求的 persona、工具限制和结构化输出运行时。
 4. 发布子 agent，保留返回的 `AgentHandle`，并通过先调用 `child.followup(prompt)`、再调用 `child.whenIdle()` 来驱动一项任务。
-5. 从完整的自有子运行中读取子 agent 自身最后一条 assistant 消息和最终持久化的轮次原因，并排除任何 fork 初始内容。
+5. 从完整的自有子运行中读取子 agent 自身的输出——最后一条非空 assistant 消息（记录 usage 的空内容消息会被跳过），若没有这类消息则取其累积的 assistant 文本——以及最终持久化的轮次原因，并排除任何 fork 初始内容。

 子 agent 会获得父 agent 的工作目录／会话谱系；除非 `request.agentOptions` 覆盖，否则还会继承父 agent 的提供方、模型和输出 token 上限。它获得全新的扁平注册作用域：父级所有权不会导入父 agent 的工具限制，也不会建立权限子集。

@@ -22,6 +22,7 @@ import {
  assertSubagentMaxDepth,
  captureDelegatedPolicyOverrides,
  childSessionMeta,
+  finalAssistantOutput,
  resolveChildAgentOptions,
  resolveChildDepth,
 } from '@deepseek-ai/dsh-subagent'
@@ -206,9 +207,9 @@ function readResult(
  structured?: { captured?: { value: unknown } | undefined },
 ): SubagentResult {
  const own = child.session.events.slice(boundary)
-  const lastMessage = own.findLast((event): event is SessionEvent<'assistant/message'> => event.type === 'assistant/message')
  const lastEnd = findLastMessageTurnEnd(own)
-  const output: ContentBlock[] = lastMessage?.data.message.content ?? []
+  // The seam's canonical selection rule; a partial answer survives cancel and truncation.
+  const output: ContentBlock[] = finalAssistantOutput(own) ?? []
  const recorded = toStopReason(lastEnd?.data.reason)
  // Disposal can tear the owner down before the loop records its ordinary
  // `aborted` end, yielding `disposed` instead.
@@ -1,4 +1,4 @@
-import { createUserMessage } from '@deepseek-ai/dsh-llm'
+import { CallId, createUserMessage } from '@deepseek-ai/dsh-llm'
 import { describe, expect, it } from 'vitest'
 import { Context } from '@deepseek-ai/cordis'
 import { type Agent, type AgentOptions } from '@deepseek-ai/dsh-agent'
@@ -10,7 +10,8 @@ import * as SessionInvariant from '@deepseek-ai/dsh-session/invariant'
 import * as AgentInvariant from '@deepseek-ai/dsh-agent/invariant'
 import * as AgentLoopInvariant from '@deepseek-ai/dsh-agent-loop/invariant'
 import SubagentService, { snapshotSubagentDescriptor } from '@deepseek-ai/dsh-subagent'
-import { maxTokensResponse, MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+import { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
+import { maxTokensResponse, MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
 import { startInProcessRun } from '../src/index.ts'

 type Script = ConstructorParameters<typeof MockAdapter>[0]
@@ -155,6 +156,31 @@ describe('startInProcessRun', () => {
    await run.dispose()
  })

+  it('keeps earlier streamed text when the final step appends an empty usage-only message', async () => {
+    // A tool-only max-tokens step records an empty assistant/message for
+    // usage. The result retains the preceding assistant output.
+    const { ctx, parent } = await setup([
+      toolCallResponse('t1', 'noop', {}, 'partial one'),
+      [
+        { type: 'block-start', index: 0, blockType: 'tool-call' },
+        { type: 'tool-call-delta', index: 0, id: CallId('t2'), name: 'noop', argumentsDelta: '{}' },
+        { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('t2'), name: 'noop', arguments: '{}' } },
+        { type: 'usage', usage: { inputTokens: 20, outputTokens: 5 } },
+        { type: 'finish', reason: { kind: 'max-tokens' } },
+      ],
+    ])
+    const disposeNoop = ctx.tools.register(defineContentToolFixture({
+      name: 'noop', description: 'probe', parameters: {},
+      execute() { return Promise.resolve([{ type: 'text', text: 'noop result' }]) },
+    }))
+    const run = await startInProcessRun(request(parent), {})
+    const result = await run.result
+    expect(result.stopReason).toBe('max-tokens')
+    expect(text(result.output)).toBe('partial one')
+    await run.dispose()
+    disposeNoop()
+  })
+
  it('seeds a forked child but reads only the child-owned output', async () => {
    const { ctx, parent } = await setup([textResponse('parent answer'), textResponse('child answer')])
    parent.followup(createUserMessage({ content: [{ type: 'text', text: 'parent question' }], source: { kind: 'user' } }))
@@ -278,7 +304,12 @@ describe('startInProcessRun', () => {
    const signalled = await startInProcessRun(request(parent, controller.signal), {})
    await new Promise(resolve => setTimeout(resolve, 30))
    controller.abort('stop child')
-    await expect(signalled.result).resolves.toMatchObject({ stopReason: 'aborted' })
+    // No step completed a message, so the text streamed before the abort is
+    // the cancelled run's output.
+    await expect(signalled.result).resolves.toEqual({
+      output: [{ type: 'text', text: 'partial' }],
+      stopReason: 'aborted',
+    })
    expect(adapter.requests[0]?.signal?.reason).toEqual({ kind: 'parent' })
    const child = parent.ctx.agents.get(signalled.id)
    const turnEnd = child?.session.events.findLast(event => event.type === 'turn/end')
@@ -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/subagent/subagent/README.md
-README.md: 42a10adeccb8e299e25ff0a5e0a918ef09b79617
-README.zh.md: 34e2ed6c1ca23df9b3158f3caea10cd19bafa841
+README.md: 28f649ef54bbf88feda24a9ce197c2c366f8349b
+README.zh.md: 595c5e5e7fffc367f2e3fd8142b779dc22fb3b79
@@ -64,7 +64,7 @@ Both in-process delegation paths fix the child's permission scope at the delegat

 `provider.start(request): Promise<SubagentRun>` is the ownership-transfer boundary; the delegation tool also uses it inside its one-shot Task-backed background path. Before fulfillment, the provider owns setup and must cancel, roll back, and quiesce unpublished resources on every failure. After fulfillment, the caller owns the run and must call `dispose()` on every path; remaining prompt and turn work belongs to `SubagentRun.result`.

-`SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for both result settlement and child-resource quiescence. A result rejection remains on `result`; `dispose()` rejects only for an independent resource-release failure.
+`SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for both result settlement and child-resource quiescence. A result rejection remains on `result`; `dispose()` rejects only for an independent resource-release failure. `output` and the `subagent/end` event's `lastAssistantMessage` use the exported `AssistantOutputFold`/`finalAssistantOutput` helpers to select the child's last non-empty assistant message, or its accumulated assistant text when no such message exists. `output` is `[]` and the event field is absent when the child produced neither ([`SubagentResult.output`](../../../docs/subsystems/subagent.md#the-terminal-result-subagentresult) owns the result contract).

 A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, exposes the exact child as `SubagentRun.localAgent`, records `request.parent.session.id` in the child's `parentSession` header, and appends the resolved descriptor inside its initial turn. Remote providers instead mint a parent-scoped lifecycle id and return `localAgent: undefined`; without a local child session, their one-shot runs are not part of trace-backed enumeration.

@@ -64,7 +64,7 @@ subagent seam 允许一个 agent（智能体）通过具名提供方把工作委

 `provider.start(request): Promise<SubagentRun>` 是所有权转移边界；委派工具也会在其由 Task 支撑的一次性后台路径中使用它。兑现前，提供方拥有设置过程，并且每次失败时都必须取消、回滚并使未发布资源完全停稳。兑现后，调用方拥有该运行，并且必须在每条路径上调用 `dispose()`；剩余提示词和轮次工作属于 `SubagentRun.result`。

-`SubagentRun.result` 兑现为 `{ output, structured?, stopReason }`。子 agent 级失败会以非 `completed` 原因兑现；只有 seam 无法表示的基础设施故障才可以拒绝。`dispose()` 是幂等的，会取消剩余工作，并等待结果结算以及子 agent 资源完全停稳。`result` 的 rejection 仍归 `result` 通道；只有独立的资源释放失败会使 `dispose()` 拒绝。
+`SubagentRun.result` 兑现为 `{ output, structured?, stopReason }`。子 agent 级失败会以非 `completed` 原因兑现；只有 seam 无法表示的基础设施故障才可以拒绝。`dispose()` 是幂等的，会取消剩余工作，并等待结果结算以及子 agent 资源完全停稳。`result` 的 rejection 仍归 `result` 通道；只有独立的资源释放失败会使 `dispose()` 拒绝。`output` 与 `subagent/end` 事件的 `lastAssistantMessage` 使用导出的 `AssistantOutputFold`／`finalAssistantOutput` 辅助函数选取子 agent 最后一条非空 assistant 消息；若没有这类消息，则选取其累积的 assistant 文本。子 agent 两种输出均未产生时，`output` 为 `[]`，该事件字段缺省（结果约定归 [`SubagentResult.output`](../../../docs/subsystems/subagent.md#the-terminal-result-subagentresult) 所有）。

 本地运行会在 `start()` 兑现前发布普通的子 agent／会话，把该共享会话 id 作为 `SubagentRun.id` 返回，以 `SubagentRun.localAgent` 公开准确的子 agent，把 `request.parent.session.id` 记录到子 agent 的 `parentSession` header，并在其初始轮次内追加已解析的描述符。远程提供方则生成 parent 作用域的生命周期 id，并返回 `localAgent: undefined`；由于没有本地 child 会话，其一次性运行不会进入基于追踪的枚举结果。

@@ -0,0 +1,74 @@
+/**
+ * Canonical selection of a child's final assistant output. Backend run results
+ * and `subagent/end.lastAssistantMessage` apply the same rule: select the last
+ * non-empty assistant message. An empty-content message records usage only
+ * when the loop appends it after a max-tokens step with no executable blocks,
+ * so it does not replace earlier output. If no non-empty message exists,
+ * select the accumulated assistant text. Selection is independent of the
+ * run's stop reason.
+ *
+ * @module @deepseek-ai/dsh-subagent/assistant-output
+ */
+
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+
+/**
+ * Incremental fold of the selection rule, for backends that observe a child's
+ * output as it streams: session-event backends {@link push} each event, and
+ * transports without session events (ACP content chunks) {@link pushText} raw
+ * text into the same streamed fallback.
+ */
+export class AssistantOutputFold {
+  private message: ContentBlock[] | undefined
+  private partial: string[] = []
+
+  /**
+   * Fold one session event: a non-empty assistant message becomes the
+   * candidate final answer, and a `text-delta` chunk extends the streamed
+   * fallback; every other event contributes nothing.
+   * @param event - the next observed session event.
+   */
+  push(event: SessionEvent): void {
+    if (event.type === 'assistant/message') {
+      const content = event.data.message.content
+      if (content.length > 0) this.message = content
+    } else if (event.type === 'assistant/chunk' && event.data.chunk.type === 'text-delta') {
+      this.pushText(event.data.chunk.text)
+    }
+  }
+
+  /**
+   * Extend the streamed fallback with text observed outside session events.
+   * @param text - the next streamed text piece (an empty piece is a no-op).
+   */
+  pushText(text: string): void {
+    if (text.length > 0) this.partial.push(text)
+  }
+
+  /**
+   * Select the final output folded so far.
+   * @returns the last non-empty assistant message, else the accumulated
+   *   streamed text, or `undefined` when the child produced neither.
+   */
+  collect(): ContentBlock[] | undefined {
+    if (this.message !== undefined) return this.message
+    const text = this.partial.join('')
+    return text.length > 0 ? [{ type: 'text', text }] : undefined
+  }
+}
+
+/**
+ * Apply the selection rule to one complete child-owned event suffix.
+ * @param events - the child-owned events (after any seed or epoch boundary).
+ * @returns the selected output, or `undefined` when the child produced none.
+ */
+export function finalAssistantOutput(events: readonly SessionEvent[]): ContentBlock[] | undefined {
+  // TODO: this folds the complete suffix once per run/epoch settlement. If a
+  // long continuable epoch ever profiles hot here, scan backward with early
+  // exit for the last non-empty message and fold text deltas only on the
+  // no-message fallback.
+  const fold = new AssistantOutputFold()
+  for (const event of events) fold.push(event)
+  return fold.collect()
+}
@@ -69,6 +69,7 @@ import { snapshotSubagentDescriptor } from './descriptor.ts'
 import { subagentIdentityProjectionDefinition, subagentTimingProjectionDefinition } from './projection.ts'

 export * from './out-of-process.ts'
+export { AssistantOutputFold, finalAssistantOutput } from './assistant-output.ts'
 export { SubagentRunId } from './types.ts'
 export type {
  ContinuableCreateRequest,
@@ -20,6 +20,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
 import { findLastMessageTurnEnd } from '@deepseek-ai/dsh-session'
 import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
+import { finalAssistantOutput } from './assistant-output.ts'
 import { SubagentRunId } from './types.ts'
 import type { SubagentResult, SubagentRun, SubagentRunEndInfo, SubagentRunInfo } from './types.ts'

@@ -128,7 +129,8 @@ export function observeRun(
      emit('subagent/end', {
        ...identity,
        stopReason: result.stopReason,
-        lastAssistantMessage: result.output,
+        // Omit the field when no output exists, matching continuable epochs.
+        ...result.output.length === 0 ? {} : { lastAssistantMessage: result.output },
      }, parent)
    },
    () => {
@@ -173,7 +175,7 @@ export function createActivationObserver(
    },
    capture: (child: Agent): void => {
      const own = child.session.events.slice(boundary)
-      const output = lastAssistantOutput(own)
+      const output = finalAssistantOutput(own)
      captured = {
        stopReason: epochStopReason(own),
        ...output === undefined ? {} : { output },
@@ -220,19 +222,6 @@ function epochStopReason(events: readonly SessionEvent[]): SubagentResult['stopR
  }
 }

-/**
- * The child's last assistant message content, for one Activation's terminal
- * lifecycle edge. Absent when no assistant message reached the log.
- * @param events - this epoch's own event suffix.
- * @returns its final assistant content, or `undefined` when it produced none.
- */
-function lastAssistantOutput(events: readonly SessionEvent[]): ContentBlock[] | undefined {
-  const message = events.findLast(
-    (event): event is SessionEvent<'assistant/message'> => event.type === 'assistant/message',
-  )
-  return message?.data.message.content
-}
-
 /** Render any listener-thrown value without letting coercion escape containment. */
 function renderThrown(value: unknown): string {
  try {
@@ -64,7 +64,11 @@ export interface SubagentRunEndInfo {
  readonly local: boolean
  /** The terminal stop reason. */
  readonly stopReason: SubagentResult['stopReason']
-  /** The child's final assistant output, absent on infrastructure rejection. */
+  /**
+   * The child's final assistant output, selected by the same rule as
+   * {@link SubagentResult.output}; absent on infrastructure rejection or when
+   * the child produced none.
+   */
  readonly lastAssistantMessage?: ContentBlock[]
 }

@@ -213,7 +217,12 @@ export type SubagentStopReason = SubagentStopReasonMap[keyof SubagentStopReasonM
 * The terminal outcome of a subagent run, resolved by {@link SubagentRun.result}.
 */
 export interface SubagentResult {
-  /** The child's final assistant output (the last assistant message's content). */
+  /**
+   * The child's final assistant output is the content of its last non-empty
+   * assistant message. Empty-content messages, including usage-only messages,
+   * are skipped. Without a non-empty message, the output is its accumulated
+   * assistant text stream, or `[]` when the child produced neither.
+   */
  readonly output: ContentBlock[]
  /**
   * The structured result after a requested `outputSchema` was successfully
@@ -0,0 +1,92 @@
+import { describe, expect, it } from 'vitest'
+import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { AssistantOutputFold, finalAssistantOutput } from '../src/assistant-output.ts'
+
+function message(content: ContentBlock[]): SessionEvent {
+  return { type: 'assistant/message', data: { message: { content } } } as SessionEvent
+}
+
+function textDelta(text: string): SessionEvent {
+  return { type: 'assistant/chunk', data: { chunk: { type: 'text-delta', text } } } as SessionEvent
+}
+
+function reasoningDelta(text: string): SessionEvent {
+  return { type: 'assistant/chunk', data: { chunk: { type: 'reasoning-delta', text } } } as SessionEvent
+}
+
+function toolResult(text: string): SessionEvent {
+  return {
+    type: 'tool/result',
+    data: {
+      message: {
+        content: [{
+          type: 'tool-result',
+          toolCallId: 'call-1',
+          content: [{ type: 'text', text }],
+          isError: false,
+        }],
+      },
+    },
+  } as SessionEvent
+}
+
+describe('finalAssistantOutput', () => {
+  it('selects the last non-empty message past a later empty usage-only message', () => {
+    const events = [
+      message([{ type: 'text', text: 'step one' }]),
+      message([{ type: 'text', text: 'step two' }]),
+      message([]),
+    ]
+    expect(finalAssistantOutput(events)).toEqual([{ type: 'text', text: 'step two' }])
+  })
+
+  it('prefers a non-empty message over text streamed before and after it', () => {
+    const events = [
+      textDelta('earlier partial'),
+      message([{ type: 'text', text: 'complete answer' }]),
+      textDelta('later partial'),
+      message([]),
+    ]
+    expect(finalAssistantOutput(events)).toEqual([{ type: 'text', text: 'complete answer' }])
+  })
+
+  it('treats textless assistant content as a non-empty message', () => {
+    const content: ContentBlock[] = [{ type: 'reasoning', text: 'complete reasoning' }]
+    expect(finalAssistantOutput([
+      textDelta('streamed text'),
+      message(content),
+      textDelta('later partial'),
+    ])).toEqual(content)
+  })
+
+  it('falls back to text deltas without including reasoning or tool-result content', () => {
+    const events = [
+      reasoningDelta('thinking'),
+      textDelta('partial '),
+      toolResult('tool output'),
+      textDelta('answer'),
+      message([]),
+    ]
+    expect(finalAssistantOutput(events)).toEqual([{ type: 'text', text: 'partial answer' }])
+  })
+
+  it('returns undefined when the child produced neither messages nor text', () => {
+    expect(finalAssistantOutput([])).toBeUndefined()
+    expect(finalAssistantOutput([reasoningDelta('thinking'), message([])])).toBeUndefined()
+  })
+})
+
+describe('AssistantOutputFold', () => {
+  it('folds raw text pieces into the same streamed fallback (ACP chunk transport)', () => {
+    const fold = new AssistantOutputFold()
+    fold.pushText('partial ')
+    fold.pushText('')
+    fold.pushText('answer')
+    expect(fold.collect()).toEqual([{ type: 'text', text: 'partial answer' }])
+  })
+
+  it('collects undefined until any output is folded', () => {
+    expect(new AssistantOutputFold().collect()).toBeUndefined()
+  })
+})
@@ -12,10 +12,10 @@ import JsonlSessionPersistence from '@deepseek-ai/dsh-session-persistence-jsonl'
 import * as SubagentSpawn from '@deepseek-ai/dsh-subagent-spawn'
 import * as SubagentFork from '@deepseek-ai/dsh-subagent-fork'
 import type { GenerateOptions, MessageId, StreamChunk } from '@deepseek-ai/dsh-llm'
-import { createUserMessage, LlmAdapter } from '@deepseek-ai/dsh-llm'
+import { CallId, createUserMessage, LlmAdapter } from '@deepseek-ai/dsh-llm'
 import { defineTool } from '@deepseek-ai/dsh-tools'
 import InvariantService from '@deepseek-ai/dsh-invariants'
-import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
+import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
 import SubagentService, {
  SubagentError,
  SUBAGENT_DESCRIPTOR_VERSION,
@@ -1200,6 +1200,44 @@ describe('continuable review regressions', () => {
    expect(ends[1]!.lastAssistantMessage).toEqual([{ type: 'text', text: 'second answer' }])
  })

+  it('keeps the epoch\'s earlier text past a final empty usage-only message', async () => {
+    // A tool-only max-tokens step records an empty assistant/message for
+    // usage. The terminal event retains the previous assistant content,
+    // including its tool call but not the intervening tool result.
+    const { ctx, parent } = await setup([
+      toolCallResponse('t1', 'noop', {}, 'partial one'),
+      [
+        { type: 'block-start', index: 0, blockType: 'tool-call' },
+        { type: 'tool-call-delta', index: 0, id: CallId('t2'), name: 'noop', argumentsDelta: '{}' },
+        { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('t2'), name: 'noop', arguments: '{}' } },
+        { type: 'usage', usage: { inputTokens: 20, outputTokens: 5 } },
+        { type: 'finish', reason: { kind: 'max-tokens' } },
+      ],
+    ])
+    ctx.tools.register(defineTool({
+      name: 'noop',
+      description: 'does nothing',
+      parameters: {},
+      output: {
+        schema: { type: 'object', additionalProperties: false, properties: {} },
+        render: () => [{ type: 'text', text: 'noop' }],
+      },
+      execute: () => Promise.resolve({}),
+    }))
+    const ends: SubagentRunEndInfo[] = []
+    ctx.on('subagent/end', (info) => { ends.push(info) })
+
+    const started = await ctx.subagents.startContinuable(startSpec(parent))
+    await waitNoActivation(ctx, started.childId)
+
+    await vi.waitFor(() => { expect(ends).toHaveLength(1) })
+    expect(ends[0]!.stopReason).toBe('max-tokens')
+    expect(ends[0]!.lastAssistantMessage).toEqual([
+      { type: 'text', text: 'partial one' },
+      { type: 'tool-call', id: 't1', name: 'noop', arguments: '{}' },
+    ])
+  })
+
  it('reports a resumed epoch that opened no turn without the previous answer', async () => {
    const { ctx, parent } = await setup([textResponse('first answer')])
    const started = await ctx.subagents.startContinuable(startSpec(parent))
@@ -15,6 +15,7 @@ import SubagentService, {
  type SubagentProvider,
  type SubagentResult,
  type SubagentRun,
+  type SubagentRunEndInfo,
  type SubagentStartRequest,
 } from '@deepseek-ai/dsh-subagent'
 import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
@@ -263,6 +264,17 @@ describe('SubagentService', () => {
      stopReason: 'completed',
    }))

+    // The lifecycle event omits lastAssistantMessage when output is empty,
+    // matching the continuable epoch event.
+    const silent = new StubProvider('silent', NO_CAPS, { output: [], stopReason: 'completed' })
+    subagents.registerProvider(silent)
+    const silentRun = await subagents.start('silent', baseRequest())
+    await silentRun.result
+    await Promise.resolve()
+    const silentEnd = ended.mock.calls.map(call => call[0] as SubagentRunEndInfo).find(info => info.provider === 'silent')
+    expect(silentEnd).toBeDefined()
+    expect('lastAssistantMessage' in silentEnd!).toBe(false)
+
    const failure = Promise.withResolvers<SubagentResult>()
    subagents.registerProvider({
      name: 'infra',
@@ -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/subagent/tool-subagent/README.md
-README.md: 6ec313b3b97f0ffa7488025d4314b1c6231a6f6a
-README.zh.md: 1fd88363b3ade9d57c194580f81295eed139ac50
+README.md: ac3ec0563cce9128608ca31860b034a103dc1a3a
+README.zh.md: d64831d7cf64800ad3307ce6cb7f294500a0a6f0
@@ -8,7 +8,7 @@ The model-facing delegation tool over one configured `ctx.subagents` provider. C

 Each plugin instance binds one `provider` to one `toolName`; the model receives no provider selector. Load another distinctly named instance to expose another transport. The tool registers only while its provider exists, avoiding sibling load-order and provider-reload dependencies. Its description follows `provider.inheritsParentContext`: fresh children require standalone prompts, while forked children already see completed parent turns.

-A foreground call passes the execution signal through startup and execution, awaits `run.result`, and always awaits `run.dispose()` before returning. Only `completed` returns the canonical `{ kind: 'foreground', runId, output: JsonValue[] }`, rendered as the same final text; abort, refusal, token limit, and other failures become errored tool results without partial output. If result collection and disposal both reject, the errored result preserves both diagnostics.
+A foreground call passes the execution signal through startup and execution, awaits `run.result`, and always awaits `run.dispose()` before returning. Only `completed` returns the canonical `{ kind: 'foreground', runId, output: JsonValue[] }`, rendered as the same final text; abort, refusal, token limit, and other failures become errored tool results whose message appends the child's preserved partial text (the `SubagentResult.output` selection) after the stop-reason headline, so a truncated answer is never reported as success yet never silently lost. If result collection and disposal both reject, the errored result preserves both diagnostics.

 With `run_in_background: true`, `backgroundMode` selects the route. `one-shot` registers a plain parent-owned Task and returns canonical `{ kind: 'background', taskId }`, rendered as `started background subagent task <id>`, even when the provider supports continuable children; generic task tools own its later status, collection, cancellation, and notices. `continuable` requires a provider with the `prepareContinuable` capability, calls `ctx.subagents.startContinuable()`, and returns `{ kind: 'continuable', subagentId }`, rendered as `started subagent <childId>`. The continuable route resolves at inbox acceptance: the child owns its own turns from there, so this call neither waits for nor collects a result, and the child does not report back — its transcript by that id is the source of its output, and the optional global `send_message` tool sends it more work. Starting continuable work does not require `send_message` to be loaded. See the [background subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md), the [continuable subagents Agent Note](../../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md), and the [merged-service Agent Note](../../../.agents/notes/implemented/simplification/2026-07-26-merge-subagent-control-service.md).

@@ -8,7 +8,7 @@

 每个插件实例把一个 `provider` 绑定到一个 `toolName`；模型不会收到提供方选择器。如需公开另一种传输，请加载另一个名称不同的实例。工具只在其提供方存在时注册，从而避免对同级加载顺序和提供方重新加载的依赖。工具描述遵循 `provider.inheritsParentContext`：新建子 agent（智能体）需要独立提示词，而 fork 子 agent 已能看到父级已完成轮次。

-前台调用会让执行信号贯穿启动和执行，等待 `run.result`，并且在返回前总会等待 `run.dispose()`。只有 `completed` 会返回规范值 `{ kind: 'foreground', runId, output: JsonValue[] }`，并渲染为相同的最终文本；中止、拒绝、token 上限和其他失败都会变成出错的工具结果，不包含局部输出。如果结果收集与 dispose（资源释放）都 reject，出错的结果会保留两项诊断信息。
+前台调用会让执行信号贯穿启动和执行，等待 `run.result`，并且在返回前总会等待 `run.dispose()`。只有 `completed` 会返回规范值 `{ kind: 'foreground', runId, output: JsonValue[] }`，并渲染为相同的最终文本；中止、拒绝、token 上限和其他失败都会变成出错的工具结果，其消息在终止原因标题之后附带子代理保留下来的部分文本（即 `SubagentResult.output` 的选取结果）——被截断的回答不会被报告为成功，也绝不会被悄悄丢弃。如果结果收集与 dispose（资源释放）都 reject，出错的结果会保留两项诊断信息。

 设置 `run_in_background: true` 后，`backgroundMode` 会选择路由。`one-shot` 会注册一个归父级所有的普通 Task，并返回规范值 `{ kind: 'background', taskId }`，渲染为 `started background subagent task <id>`，即使提供方支持可继续子 agent 也不例外；通用 Task 工具负责其后续状态、收集、取消和通知。`continuable` 要求提供方具备 `prepareContinuable` 能力，调用 `ctx.subagents.startContinuable()`，并返回 `{ kind: 'continuable', subagentId }`，渲染为 `started subagent <childId>`。可继续路由在 inbox 接受时结算：子 agent 自此拥有自己的轮次，因此该调用既不等待也不收集结果，而且子 agent 不会回报——通过该 id 查看其 transcript（文本记录）即是其输出来源，可选的全局 `send_message` 工具则向其发送更多工作。启动可继续工作不要求加载 `send_message`。见 [后台 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md)、[可继续的 subagent Agent Note](../../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md)和[服务合并 Agent Note](../../../.agents/notes/implemented/simplification/2026-07-26-merge-subagent-control-service.md)。

@@ -134,6 +134,21 @@ function stopReasonError(result: SubagentResult): string | undefined {
  }
 }

+/**
+ * Append the child's preserved partial answer to a stop-reason error so a
+ * truncated or cancelled child's real text still reaches the parent model.
+ * @param error - the stop-reason headline.
+ * @param output - the child's selected output (`SubagentResult.output`).
+ * @returns the headline, extended with the partial text when any exists.
+ */
+function withPartialText(error: string, output: ContentBlock[]): string {
+  const text = output
+    .filter((block): block is Extract<ContentBlock, { type: 'text' }> => block.type === 'text')
+    .map(block => block.text)
+    .join('')
+  return text.length === 0 ? error : `${error}\nPartial output before the run ended:\n${text}`
+}
+
 type ForegroundToolResult = {
  readonly kind: 'foreground'
  readonly runId: SubagentRun['id']
@@ -149,8 +164,9 @@ async function settleForegroundRun(run: SubagentRun): Promise<ForegroundToolResu
    run.result.then((result): ForegroundToolResult => {
      const error = stopReasonError(result)
      if (error !== undefined) {
-        // The registry converts this throw to isError; partial output is not success.
-        throw new Error(error)
+        // The registry converts this throw to isError; partial output is not
+        // success, but the preserved partial answer still reaches the parent.
+        throw new Error(withPartialText(error, result.output))
      }
      return {
        kind: 'foreground',
@@ -154,6 +154,9 @@ describe('dsh-tool-subagent', () => {
    const result = await callSubagent(ctx, { description: 'd', prompt: 'p' })
    expect(result.isError).toBe(true)
    expect(text(result)).toContain(fragment)
+    // The failure is not partial success, but the child's preserved partial
+    // answer still reaches the parent model inside the error result.
+    expect(text(result)).toContain('scripted subagent reply')
  })

  it('registers under a configurable toolName so multiple providers can coexist', async () => {