@zq-silk/yui 1.0.0 → 1.1.0

package/docs/managed-turn-and-session-runtime.zh-CN.md

@@ -8,6 +8,11 @@ Provider binding，再结算执行占用。Global 停止证据保存为仅记录
 不触发新的原生输入。待投递通知不能重启已明确停止的 Session；普通 Host 脱离仍
 保留 active Session，可正常重连。部分切换失败后，仍须先结算旧输入再选择新会话。
 
+新建 global Operator 对话会按 Yui 当前配置时区请求原生标题
+`Yui · Operator · MMdd`。只有 Provider 返回新对话的确切身份后才执行该请求；
+恢复与重连路径不会重放。若 Provider 不支持创建后改名，已创建的 Session 仍保持
+可用，并留下诊断，而不会把元数据失败冒充为 Session 创建失败。
+
 ## 权威
 
 Task、WorkItem、Message、Decision、Artifact 和 Project Knowledge 保存持久工作。

package/docs/provider-runtime.md

@@ -143,6 +143,13 @@ Failure to drain remains a live ownership dependency, not false quiescence.
 This is OS process custody, not a Task workflow or a claim about unrelated
 external services.
 
+macOS has no child subreaper. The owner stops descendants it can still prove
+through ancestry or the original process group. If the Claude root forks,
+`setsid` and reparenting can hide a child from both checks; the owner therefore
+reports cleanup as unconfirmed instead of returning a successful exit. This
+also covers ordinary forked tools whose exit cannot be proven after the root
+is gone. A detached child may still need explicit inspection and termination.
+
 The dedicated process's PID/start identity is retained as engineering control
 data independently of AgentHost. Recovery never needs the old Host's in-memory
 connection. For Codex, a separate metadata/control client can inspect and stop

package/docs/provider-runtime.zh-CN.md

@@ -117,6 +117,11 @@ Task Session 终止首先取消其确切的未结算输入，并在向 Host 发
 一个活的所有权依赖，而不是虚假静止。这是 OS 进程托管，不是 Task 工作流，也不是关于
 无关外部服务的断言。
 
+macOS 没有子进程 subreaper。owner 会停止仍能通过父子关系或原进程组确认的后代。
+若 Claude 根进程曾 fork，子进程再执行 `setsid` 并被重新托管，就可能避开这两种检查；
+此时 owner 会报告清理未确认，而不会返回成功；普通工具进程曾 fork、但根进程退出后
+无法证明它们都已结束时，也适用这一保守结果。脱离的子进程可能仍需单独检查和终止。
+
 专用进程的 PID/start 身份作为工程控制数据独立于 AgentHost 保留。恢复从不需要旧 Host
 的内存连接。对 Codex，一个单独的元数据/控制客户端可以在不提交另一个 prompt 的情况下
 检查并停止已记录的原生执行；未知接受可以在实际原生静止之后被放弃，而不编造原生 Turn

package/docs/release-workflow.md

@@ -45,10 +45,16 @@ protection and valid exact-identity caches remain normal runtime behavior.
 
 Stable releases use npm `latest`; prereleases use `next`, never the stable
 default. The release workflow builds one runtime archive, verifies it across
-supported Node versions, publishes that exact archive to npm, then creates the
+supported Node versions on Linux x64, macOS x64 and macOS arm64, publishes that exact archive to npm, then creates the
 matching GitHub Release. Every release carries the runtime archive, checksum and
 provenance. A stable tag becomes GitHub latest; a prerelease does not.
 
+Platform jobs compile Yui's native helpers from the same source commit.
+The archive includes every supported helper under `dist/runtime/native/`;
+runtime selection uses the exact OS and architecture, without install scripts
+or downloading executable code on first use. Dependencies such as SQLite
+remain ordinary npm dependencies installed for the consumer's platform.
+
 The GitHub Release job uploads only missing assets to a draft, downloads and
 compares every asset against the tested artifact, and never overwrites a
 published asset. A retry accepts only byte-identical existing evidence. If npm

package/docs/task-delivery.md

@@ -35,9 +35,10 @@ isolation and acceptance checks remain enforced independently.
 
 Stable Project checkouts are read-only references. Task main is a logical
 multi-Project root with independent per-Project Git clones; WorkItem, Review and
-Integration worktrees belong to those Task repositories. For one Project, the Agent's
-normal cwd is its managed Git root; for multiple Projects, the root and native
-additional-directory mechanism expose the explicit Project set.
+Integration worktrees belong to those Task repositories. By default, a Task's native cwd is
+its managed root with zero, one, or multiple Projects. The native
+additional-directory mechanism exposes each bound Project. Binding another
+Project while the Task is active does not move the Task cwd.
 
 An isolated WorkItem has independent worktrees for writable Projects and
 Task-main context for the others. Write scope is explicit and can only be
@@ -367,7 +368,7 @@ This adds neither a retry worker nor another persistent ownership protocol.
 Current Resource records are read strictly: required safety fields, enum values,
 and every active reference must be valid. A malformed record or mismatched
 SQLite/payload identity is reported without supplying defaults, dropping refs,
-or rewriting stored evidence. This enforces the current storage 1.0 record contract.
+or rewriting stored evidence. This enforces the current storage 1.1 record contract.
 
 Failed preparation compensates only its unadopted resources. Standalone Task
 clones use exact clone identity/cleanliness checks before direct deletion;

package/docs/testing/verification-levels.md

@@ -50,13 +50,12 @@ is required.
 ## Permanent core smoke
 
 `npm test` and `npm run test:core` build the checkout and run the maintained suite.
-The stable suite owns only current storage 1.0 and future declared minor
-transitions. It contains no historical conversion implementation, fixture or
-compatibility test.
+The stable suite owns current storage 1.1 and its declared 1.0 minor
+transition. It contains no undeclared historical format compatibility path.
 
 Current coverage includes:
 
-1. Fresh storage 1.0, exact schema/record validation, no initialization over
+1. Fresh storage 1.1, exact schema/record validation, no initialization over
    unknown data, and rejection of old integer formats without mutation.
 2. Exact-version staging, mismatched-target refusal, same-major contiguous
    minor preflight, explicit maintenance-owner identity across handover, and
@@ -99,8 +98,9 @@ do not add prose-matching tests or claim model validation from static checks.
 
 ## CI and release
 
-`ci.yml` builds once and runs core plus one assembled-package normal-path smoke
-on every PR, without another lint or broad regression suite.
+`ci.yml` runs core plus one assembled-package normal-path smoke per supported
+platform (Linux x64, Mac Intel and Apple Silicon) on every PR, without another
+lint or broad regression suite.
 `node scripts/smoke-runtime-package.mjs --assembled .release-stage` exercises
 the actual CLI/Controller/Host/SQLite and isolated tmux, replacing only the
 external Provider with a deterministic fixture. It covers setup, durable input
@@ -111,7 +111,9 @@ and grouped viewers without affecting a similarly named neighboring session.
 The fixture owns a fresh Home and its PATH, installs cleanup before setup,
 and never calls an installed model Agent.
 
-`publish.yml` runs the same smoke against the freshly installed package through
+`publish.yml` builds one archive containing all three native targets and runs
+the same smoke on each platform and supported Node version against that exact
+freshly installed package through
 `YUI_INSTALLED_ROOT`, adding actual npm-bin, dependency, supported Node version,
 artifact and provenance boundaries. This validates runtime integration, not
 real-model behavior. Pure contract and safety tests remain in `test/core`;

package/i18n/README.zh-CN.md

@@ -5,7 +5,7 @@
 [![Core CI](https://github.com/zhangqian-silk/yui/actions/workflows/ci.yml/badge.svg?branch=master)](https://github.com/zhangqian-silk/yui/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](../LICENSE)
 ![Node](https://img.shields.io/badge/node-20%20%7C%2022%20%7C%2024-brightgreen.svg)
-![Platform](https://img.shields.io/badge/platform-Linux%20x64%20%28glibc%29-blue.svg)
+![Platform](https://img.shields.io/badge/platform-Linux%20x64%20%28glibc%29%20%7C%20macOS%20x64%2Farm64-blue.svg)
 [![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](#参与开发)
 
 让 Agent 持续推进你的任务，而不只是回答一轮对话。
@@ -30,16 +30,21 @@ Yui 是面向编程 Agent 的本地控制面。你只需用自然语言把目标
   Web 仅本地回环，包含只读视图和经认证的用户控制。
 - **默认隔离** —— 仓库改动发生在受管 Git worktree 中，稳定 checkout 保持只读。
 
-> **状态：** 1.0.0，采用纯净的存储 1.0 基线。默认更新只执行同一存储
+> **状态：** 1.1.0，当前存储版本为 1.1，已声明从 1.0 基线升级。默认更新只执行同一存储
 > 主版本内已声明的小版本升级；其他存储身份会在不修改 Home 的前提下被拒绝。
 
 [快速开始](#快速开始) · [通过对话管理工作](#通过对话管理工作) · [架构](#架构) · [设计原则](#设计原则)
 
 ## 快速开始
 
-需要 Linux x64 / glibc、Git、tmux，以及 Node.js `^20.17.0`、`^22.9.0` 或
-`^24.0.0`。最简单的方式是先安装 Codex CLI 或 Claude Code CLI，并确保它
-已经可以使用你自己的账号正常工作。Yui 负责协调 Agent，不提供模型访问额度。
+npm 包包含 Linux x64、Mac Intel 和 Apple Silicon 的 Yui 预编译程序。
+同一份包在三个平台验证后发布，运行时只选择对应平台的程序。
+
+需要 Linux x64 / glibc 或 macOS（x64 或 Apple Silicon）、Git、tmux，以及
+Node.js `^20.17.0`、`^22.9.0` 或 `^24.0.0`。macOS 上可用
+`brew install tmux` 安装 tmux。最简单的方式是先安装 Codex CLI 或 Claude
+Code CLI，并确保它已经可以使用你自己的账号正常工作。Yui 负责协调 Agent，
+不提供模型访问额度。
 
 Yui 传递 Claude 的认证环境并保留原生配置目录，由 Claude 自身按本地配置
 选择 API key 或登录方式。更换 Session 不会重置登录或初始化记录。首次运行时，
@@ -64,10 +69,18 @@ yui setup
 > 我已经安装了 Yui。请在交互式终端中帮我执行 `yui setup`，选择可用的
 > Agent，并用 `yui doctor` 检查结果。遇到账号或需要我决定的配置时问我。
 
-Setup 会配置与你对话的 Operator 和默认任务 Leader，并启动本地 Controller。
+Setup 会配置与你对话的 Operator 和默认任务 Leader，并启动本地 Controller，
+以及这些活跃 Role 需要的 Codex 共享 daemon。
 先用这两个角色即可开始，Worker、Reviewer 可以之后再配置。如果 Agent
 没有操作交互式终端的能力，就自己运行 setup；它只负责初始配置。
 
+之后启动时运行 `yui start`。它会按需启动 Controller；只有活跃 Role 使用
+Codex 时才会启动 Codex 共享 daemon。在 macOS 上，如果安装了 Codex App，
+它还会配置 App 下次启动时连接该 daemon。先运行 `yui start` 再打开 App；
+如果 App 已经打开，按 Yui 的提示退出并重新打开。`yui doctor` 可以检查
+实时连接。`yui controller start` 只启动 Controller。Linux 不需要 App 配置；
+没有活跃 Codex Role 时不会启动 Codex daemon。
+
 ### 3. 开始对话
 
 ```sh

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zq-silk/yui",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "description": "Local control plane for long-running native agent CLI sessions backed by tmux.",
   "license": "MIT",
   "private": false,
@@ -22,13 +22,12 @@
     "node": "^20.17.0 || ^22.9.0 || ^24.0.0"
   },
   "os": [
-    "linux"
+    "linux",
+    "darwin"
   ],
   "cpu": [
-    "x64"
-  ],
-  "libc": [
-    "glibc"
+    "x64",
+    "arm64"
   ],
   "keywords": [
     "yui",

package/skills/yui-leader/SKILL.md

@@ -69,6 +69,14 @@ The DB Brief is the current summary, not a full plan or a history of messages.
 After meaningful progress, use `task brief update` with only intended fields;
 read `task event list` before deliberately restoring an older value. Keep
 references to substantial plans, prototypes and reports in that summary.
+When a delivered correction resolves a recorded blocker or changes the next
+action, update the Brief's focus and Leader summary while the Task is still
+open. Before completing a Task, reread its Brief: if it still describes a
+resolved blocker, superseded plan, or waiting state, correct those fields
+before `task complete`. The completion summary is the terminal conclusion;
+do not copy it into Brief merely to create a second completion record. Brief
+maintenance is not a new completion gate, and routine unchanged steps do not
+need an update.
 Decisions contain the actual decision, reason and necessary boundaries, not
 the entire proposal. Label recommendations as recommendations, not user
 decisions.

package/skills/yui-leader/references/execution.md

@@ -409,7 +409,10 @@ Before ending authorized execution:
    with `yui task run show`, read each original result in full, and make the
    next decision.
 2. Persist actual WorkItem lifecycle and material Brief, Decision, Milestone,
-   Message, or Knowledge changes.
+   Message, or Knowledge changes. If an accepted result or authorized
+   correction has cleared a blocker still stated as current in Brief, update
+   that working summary before completing or yielding. Keep the original
+   failure and correction in their durable records.
 3. Choose one truthful outcome: continue through an owned native child, complete
    the Task, create a justified InputRequest, or leave the active Task waiting
    for a real durable event.

package/skills/yui-operator/SKILL.md

@@ -74,13 +74,30 @@ determine Task identity. They also do not determine WorkItem count. Let
 isolated workspaces and Integration handle independent Git changes.
 
 Keep the Task title concise and put detailed intent, constraints, and evidence
-in its description or routed Message. The examples below are separate
-operations, not an automatic create/submit/activate sequence. For creation-only
-intent, save the Task without starting planning. Discussion does not authorize
-delivery; follow the Leader's [planning and activation boundary](../yui-leader/references/planning.md)
-before activation. Queries, record-only input and discussion do not authorize
-reopening. An explicit request to continue the same completed result can authorize
-the necessary reopening; follow the delivery guidance below.
+in its description or routed Message.
+
+Treat Task creation and Task submission as separate user-authorized actions.
+When the user asks only to add, create, register, or record a Task, create the
+Draft and write all known requirements into its metadata, then stop. Do not
+submit a `discuss` or `develop` Message, request activation, start a Leader
+Session, or create execution resources. A detailed or immediately actionable
+requirement, or the user's desire for its eventual completion, is not permission
+to start it. Report that the Task is a Draft and has not started, and explain
+that the user can explicitly ask to discuss/plan it or to develop/implement it.
+
+Start the corresponding route only when the user's current request contains
+that additional intent: discussion or planning authorizes `discuss`;
+development, implementation, fixing, continuing execution, or immediate
+progress authorizes `develop` or the applicable lifecycle continuation. Do not
+weaken explicit intent merely because the request also says “create a Task.”
+The examples below are separate operations, never an automatic
+create/submit/activate sequence.
+
+Discussion does not authorize delivery; follow the Leader's
+[planning and activation boundary](../yui-leader/references/planning.md) before
+activation. Queries, record-only input and discussion do not authorize
+reopening. An explicit request to continue the same completed result can
+authorize the necessary reopening; follow the delivery guidance below.
 
 ```sh
 yui operator submit "<related request and delta>" --task <task-id> --intent discuss
@@ -94,14 +111,17 @@ Inspect an existing request before creating another. `task activate <task-id>`
 can adopt an eligible request in the foreground; it never activates a Draft
 without a recorded request and environment plan.
 
-Choose the submission intent explicitly; it is never inferred from the message
-text. `discuss` (the default) routes the Draft to
-planning; `record` saves the message without waking the Leader; `develop` asks an
-unplanned Draft to activate now, and reports the exact next step when it cannot
-(already planned → request activation explicitly; execution stopped → start it first). Pass
-`--request-id <key>` to make a submission idempotent: retrying the same key
-returns the original message and routing instead of creating a duplicate, and the
-same key with different text is refused as a conflict.
+After the user has authorized a submission, choose its intent explicitly; it is
+never inferred by the CLI from the message text. `discuss` (the CLI default when
+`operator submit` is already being invoked) routes the Draft to planning;
+`record` saves the message without waking the Leader; `develop` asks an unplanned
+Draft to activate now, and reports the exact next step when it cannot (already
+planned → request activation explicitly; execution stopped → start it first).
+The CLI default is not permission for the Operator to invoke submission after a
+creation-only request. Pass `--request-id <key>` to make a submission idempotent:
+retrying the same key returns the original message and routing instead of
+creating a duplicate, and the same key with different text is refused as a
+conflict.
 
 Resolve all known Projects before repository-backed execution. A stable Project
 checkout is read-only reference state, not the Task base authority. Yui records