fix(subagent): keep delegated result tool registration stable

[Grivn]

提交 PR 前请阅读贡献指南、Contributing Guide与开发和验证指南 / Development and Verification Guide。
Before opening a PR, read the Contributing Guide, 贡献指南, and the Development and Verification Guide / 开发和验证指南.
PR 标题和提交信息必须使用 Conventional Commits（type(scope): subject），且不得包含 emoji。 / PR titles and commits must use Conventional Commits (type(scope): subject) and must not contain emoji.
本仓库接受 Bug 修复、兼容性适配、现有能力增强、性能或体验优化和维护类 PR。全新能力、Provider、持久化格式或安全边界变更必须先提 Issue 并获得维护者确认。 / This repository accepts bug fixes, compatibility work, improvements to existing capabilities, performance or UX optimization, and maintenance. New capabilities, Providers, persistence formats, or security-boundary changes require prior maintainer approval in an Issue.
外部贡献者的仅文档类 PR 不直接接受；请先提 Issue 讨论。维护者的发布说明与文档维护不受此限制。 / Documentation-only PRs from external contributors are not accepted directly; open an Issue first. Maintainer release notes and documentation maintenance are exempt.

摘要 / Summary

Every delegated run registered a UUID result tool, changing model tool definitions on each write. Register one stable mnemon_subagent_result for the coordinator lifetime and pass a revocable { requestId, result } envelope while retaining per-operation validation, child ownership, and authoritative completion checks.

每次委派原先都会注册 UUID 结果工具，导致模型工具定义持续变化；现改为协调器生命周期内固定注册，并使用可撤销请求封装，同时保留操作专用 schema、子任务归属及权威完成事件校验。

关联 Issue 或背景 / Related Issue or Context

Fixes #239

涉及区域 / Affected Areas

• Host 激活、Headless 或 bundle / Host activation, Headless, or bundle
• 运行时记忆 / Runtime Memory
• 项目档案 / Project Documents
• 记忆空间或 Provider / Memory Spaces or Providers
• 子 Agent 或 Agent 工作流 / Subagent or Agent workflow
• Web UI 或对话交互 / Web UI or conversation interaction
• 设置、存储或安全 / Settings, storage, or security
• CLI、RPC、命令或工具 / CLI, RPC, commands, or tools
• 安装、更新或发布 / Installation, update, or release
• 测试、构建或文档 / Tests, build, or documentation
• 其他（请说明）/ Other (explain below)

PR 类型 / PR Type

• 面向用户的功能或行为变更 / User-facing feature or behavior change
• Bug 修复 / Bug fix
• 增强或优化 / Enhancement or optimization
• 兼容性适配 / Compatibility change
• 维护或重构 / Maintenance or refactor
• 测试或构建 / Tests or build

最新代码确认 / Latest Codebase Confirmation

• 我已基于最新 main 分支开发，或在提交前已 rebase 或合并最新 main。 / I developed from the latest main, or rebased or merged the latest main before submitting.

同步命令 / Sync command:

git fetch origin main; based on 1e19caf (latest origin/main).

AI 编码披露 / AI Coding Disclosure

• 完全 AI 编码：全部编程改动由 AI 产出，并由贡献者接受和审查。 / Fully AI-coded: AI produced all programming changes, which the contributor accepted and reviewed.
• 部分 AI 辅助：AI 帮助编写或修改了部分内容。 / Partially AI-assisted: AI helped write or modify part of the change.
• 未使用 AI 编码辅助。 / No AI coding assistance was used.

使用的 AI 模型 / AI model used:

GPT-6 Astra, max reasoning.

使用的编码 Agent 工具 / Coding Agent tool used:

Codex desktop with an isolated issue worktree.

仓库规范检查 / Repository Rules

• 未修改 DSH 官方源码，未让 tsconfig 指向 DSH 源码 checkout，仅使用正式的 @deepseek-ai/* NPM 契约。 / I did not modify DSH source or point tsconfig at a DSH source checkout, and used only published @deepseek-ai/* NPM contracts.
• Client 与 Host 边界仍以浏览器安全的 src/host/protocol.ts 为准，没有在两侧重复定义 wire DTO。 / The Client and Host boundary still uses browser-safe src/host/protocol.ts as the source for wire DTOs.
• 持久化格式、RPC 权限、路径或凭据处理的变更包含兼容或拒绝路径、安全分析和相应测试。 / Changes to persistence formats, RPC authority, paths, or credentials include compatibility or rejection paths, security analysis, and tests.
• 没有提交 token、密钥、私有记忆、未脱敏日志或生成的 lib/ 文件。 / I did not commit tokens, credentials, private memory, unredacted logs, or generated lib/ files.
• 用户可见文案和长期文档已同步维护中文与英文版本，命令、配置键和路径保持一致。 / User-facing copy and long-lived documentation are synchronized in Chinese and English, with matching commands, configuration keys, and paths.
• 会改变发布制品或其元数据的 PR 已添加 changeset；仅测试、CI 或站点文档变更可不添加。 / A PR that changes a published artifact or its metadata includes a changeset; test-only, CI-only, and site-documentation-only changes may omit one.
• 新增和修改的代码、注释、文档、提交信息不含 emoji。 / New and modified code, comments, documentation, and commits contain no emoji.

兼容性与数据安全 / Compatibility and Data Safety

Uses published DSH tool registration, execution, and disposal contracts; no configuration, Provider, persistence, RPC DTO, or stored-memory changes. The internal completion tool is now permanently visible, but root, foreign-child, unknown, duplicate, cancelled, disposed, and expired requests are rejected. Request IDs are revoked before asynchronous child cleanup; operation schemas remain enforced at submission and final receipt validation. Existing child tool allowlists, inherited parent context, and successful outer run_code fencing remain in force. Restart the plugin when upgrading or rolling back; no data conversion is needed.

仅变更内部结果协议；无配置、Provider、存储格式、RPC DTO 或存量记忆变更。固定工具拒绝父任务、其他子任务及未知、重复、取消、销毁、过期请求；异步清理前撤销请求，保留专用 schema、原有工具白名单、父上下文继承和外层 run_code 成功校验。升级或回滚需重启插件，无需数据迁移。

本地验证 / Local Validation

执行的命令 / Commands run:

pnpm run verify
node scripts/verify-plugin-artifacts.mjs --skip-build
MNEMON_NATIVE_TEST_CLI=/opt/homebrew/bin/mnemon pnpm --filter dsh-mnemon-source-memory-spaces exec vitest run tests/native-integration.spec.ts
pnpm run typecheck
pnpm run test:root
pnpm run verify:docs
git diff --check

结果摘要 / Result summary:

Passed the full verification pipeline (935 root tests, 5 expected live-model skips), all 16 independent plugin repositories and 17 packed artifacts, isolated Headless activation, package validation, and the real Mnemon 0.2.7 create/write/recall/forget test. The new registration regression failed on baseline 1e19caf. The final full verification pass also covers disposal during asynchronous workflow preparation, plus actual placement-tool rejection for write envelopes and ineligible Providers. Real WebUI ran before and after with all three Strategy enhancements and completed a runtime-memory write.

完整验证通过：根测试 935 项，5 项实时模型测试按预期跳过；16 个独立插件仓库、17 个发布包、Headless、包校验和真实 CLI 闭环通过。新增注册回归在基线失败；真实 WebUI 前后验证与热记忆写入成功。

用户可见变更证据 / Local Feature Evidence

证据 / Evidence:

Reproduction, exact fingerprints, and bilingual evidence

Two baseline child requests used different UUID result tools and different serialized tool-array hashes. Both fixed requests use mnemon_subagent_result and SHA256 b01c520da60b2e631963e1e8f4b8f0ba26026cd13b57e7a92ff17d20503dd28e; fixed parent inventories are also stable. This proves tool-prefix stability for the reproduced operations. No paid model, large-context cache-hit rate, or monetary saving was measured. The profile uses disposable storage and synthetic data.