agentworkshop 0.7.46 → 0.7.48

package/.output/server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentworkshop-prod",
-  "version": "0.7.46",
+  "version": "0.7.48",
   "type": "module",
   "private": true,
   "dependencies": {

package/README-zh.md

@@ -28,7 +28,7 @@
 
 **[English](./README.md)** · **[在线文档](https://kingdol666.github.io/AgentWorkShop)** · **[版本发布](https://github.com/kingdol666/AgentWorkShop/releases)** · **[更新日志](./changelog.md)** · **[插件 API](./docs/plugins.md)** · **[SDK](./docs/sdk.md)**
 
-<sub><b>v0.7.46</b> · 14 个执行引擎 · 6 种现场协议（5 内置 + 串口插件） · 111 个运行时设置项 · 双语文档（简体中文 / English）</sub>
+<sub><b>v0.7.48</b> · 14 个执行引擎 · 6 种现场协议（5 内置 + 串口插件） · 111 个运行时设置项 · 双语文档（简体中文 / English）</sub>
 
 <br />
 
@@ -382,7 +382,7 @@ aw update --check                      # 只报告，不安装
 npm install -g agentworkshop@latest    # 手动等效
 ```
 
-版本遵循 semver。每次 `aw start` 都会校验配置根，并把 `home` 之前的旧版 `data/` 布局迁移进来（以最新文件为准），因此数据可以跨版本存活。SQLite schema 迁移在服务端启动时执行。当前版本：**v0.7.46**——见[版本发布](https://github.com/kingdol666/AgentWorkShop/releases)。
+版本遵循 semver。每次 `aw start` 都会校验配置根，并把 `home` 之前的旧版 `data/` 布局迁移进来（以最新文件为准），因此数据可以跨版本存活。SQLite schema 迁移在服务端启动时执行。当前版本：**v0.7.48**——见[版本发布](https://github.com/kingdol666/AgentWorkShop/releases)。
 
 ### 第一次「Agent × 产线」会话（约 2 分钟）
 
@@ -595,6 +595,11 @@ SUBMITTED ─▶ ASSIGNED ─▶ WORKING ─▶ WAITING ─▶ COMPLETED
 | 终端镜像 + 提示词组合 | **26 / 0** 与 **16 / 0**（2026-09-24，真实 `omp`） | 终端镜像帧、`input`/`abort`/`ui_response` 注入、原生 `ask` 往返；五段式 prompt 组合（场景 → 专长 → 记忆 → 手册 → 任务）在线上可观测 | `node scripts/test-terminal-e2e.mjs` · `node scripts/test-prompt-system.mjs` |
 | 真引擎协作 | 任务流真跑 **PASS**、`e2e-omp-workspace` **13 / 13**、群聊全真 **PASS**、多用户 HIL **PASS**（2026-09-24） | 真实 `omp` lead + worker：分解/派发/进度/成果/workspace 文件读取与卸载；多用户 HITL 可见性；多引擎团队 14/18（omp 与 dsh 全绿） | `npx tsx scripts/e2e-agentteam-task-flow-real.ts` · `npx tsx scripts/e2e-omp-workspace.ts` |
 | 前端验收 | 响应式门禁 **16 / 16** 页、抽屉交互 **10 / 10**（2026-09-24，真实 Chromium） | 全部产品页（含 3D 小镇）在门禁阈值下渲染通过；抽屉开合、滚动锁、路由跳转、零 pageerror | `node scripts/ui/verify-responsive.mjs --routes all` · `node scripts/ui/verify-nav.mjs` |
+| `_aw0746-stage12.mjs` | **10 / 0**（2026-09-25,全局安装的 **v0.7.48 打包系统**） | 健康门(version=0.7.48)→ 管理员登录/角色面 → 创建 Channel(真实 `omp` lead)→ 开群聊 → **真实 omp 群聊回复** → 系统监控可见 omp 子进程 | `AW_BASE=<base> node scripts/_aw0746-stage12.mjs` |
+| `_aw0746-stage34.mjs` | **11 / 0**（2026-09-25,v0.7.48 打包系统 + PLC 模拟器） | 模拟器建线（11 数控 + 14 数采）→ 产品/配方三元组 → 开跑后**样本逐条带 recipe_id/run_id** → `daq_query` **默认只取当前活动批次**（`scope=all` 可放开，实测 1 vs 4）→ 实例化 Hybrid Twin 模板（lead + 3 worker,注入孪生 6 件套 / 总 57 工具） | `AW_BASE=<base> node scripts/_aw0746-stage34.mjs` |
+| `_aw0746-stage6b-train-sweep.mjs` | 门禁**全绿**（2026-09-25,v0.7.46 打包系统,真实 torch 训练） | 1 s 拍格数据集（**1724 行 / 10 批次**）→ 内联 code 作业真实训练 → G1 单步 **0.0992**（≤0.10）/ G2 滚动 0.1092（≤0.25）/ G3 泛化 14.6%（≤20%）/ G4 行数与批次 → 模型注册并**晋升 production** | `AW_BASE=<base> AW_DATASET_ID=<ds> node scripts/_aw0746-stage6b-train-sweep.mjs` |
+| `_aw0746-stage7-twin.mjs` | **17 / 0**（2026-09-25,v0.7.48 打包系统,真实 DAQ + 真实模型） | 真实样本 → TwinSnapshot `fresh=true` → 65 组真实 VirtualTrial（12 条安全候选,`candidateExecuted=false`）→ 12 项推荐门禁 **write_eligible** → 门禁结论回写模型 `twinEligibility` → `mpc_optimize` 升档 **precise_search** → 全程 **0 DCW 写入** | `AW_BASE=<base> AW_REQUIRE_MODEL=1 node scripts/_aw0746-stage7-twin.mjs` |
+| `_aw0746-stage6c-jobsmoke.mjs` | **5 / 0**（2026-09-25,v0.7.48 打包系统） | AML 作业链路：内联 `code` 被接受（不再要求 `workspace/train.py`）→ 作业到终态 → 训练日志/ONNX 痕迹 → 实验与逐项门禁落库 | `AW_BASE=<base> node scripts/_aw0746-stage6c-jobsmoke.mjs` |
 | 工业基准——integrated | **83 / 83 检查，硬门禁绿**（2026-09-21） | 五协议五产线基准：连通性、采样入 Timescale、受控下发、治理、Agent 闭环、工艺参数语义层 | `node bench/pipeline.mjs --profile integrated` |
 | 多场景闭环 | 4 场景 · 闭环达标（2026-09-21） | 注塑克重窗口寻优 · A²/O 污水排放达标 + 能耗最小化 · 连续退火质量窗与产能权衡 · BOPET 产线任务 | `node bench/scenarios.mjs --scenarios injection,wwtp,anneal` |
 | 产线权限 / 审计负向 | 21 / 21 + 9 / 9（2026-09-12） | 三态产线授权 + 人类可读 403、绑定主体校验、授权撤销收敛、无 token WS 零遥测 | `node scripts/_dbg-perms-e2e.mjs <base> <adminPass>` · `node scripts/_dbg-audit-neg-e2e.mjs <base> <adminPass>` |

package/README.md

@@ -28,7 +28,7 @@
 
 **[简体中文](./README-zh.md)** · **[Documentation](https://kingdol666.github.io/AgentWorkShop)** · **[Releases](https://github.com/kingdol666/AgentWorkShop/releases)** · **[Changelog](./changelog.md)** · **[Plugin API](./docs/plugins.md)** · **[SDK](./docs/sdk.md)**
 
-<sub><b>v0.7.46</b> · 14 engines · 6 field protocols (5 built-in + serial plugin) · 111 runtime settings · bilingual docs (简体中文 / English)</sub>
+<sub><b>v0.7.48</b> · 14 engines · 6 field protocols (5 built-in + serial plugin) · 111 runtime settings · bilingual docs (简体中文 / English)</sub>
 
 <br />
 
@@ -373,7 +373,7 @@ aw update --check                      # only report; nothing is installed
 npm install -g agentworkshop@latest    # manual equivalent
 ```
 
-Releases follow semver. `aw start` verifies the config root on every launch and migrates the legacy pre-`home` `data/` layout into it (newest file wins), so data survives upgrades. SQLite schema migrations run server-side at boot. Current version: **v0.7.46** — see [Releases](https://github.com/kingdol666/AgentWorkShop/releases).
+Releases follow semver. `aw start` verifies the config root on every launch and migrates the legacy pre-`home` `data/` layout into it (newest file wins), so data survives upgrades. SQLite schema migrations run server-side at boot. Current version: **v0.7.48** — see [Releases](https://github.com/kingdol666/AgentWorkShop/releases).
 
 ### Your first agent × line session (~2 minutes)
 
@@ -599,6 +599,11 @@ in [`docs/audit/e2e-2026-09-24-all-features.md`](./docs/audit/e2e-2026-09-24-all
 | Terminal mirror + prompt composition | **26 / 0** and **16 / 0** (2026-09-24, real `omp`) | terminal mirror frames, `input`/`abort`/`ui_response` injection, native `ask` round-trip; five-section prompt assembly (scenario → profile → memory → manual → assignment) observed on the wire | `node scripts/test-terminal-e2e.mjs` · `node scripts/test-prompt-system.mjs` |
 | Real-engine collaboration | task-flow real **PASS**, `e2e-omp-workspace` **13 / 13**, group-chat real **PASS**, multi-user HIL **PASS** (2026-09-24) | real `omp` lead + workers: decomposition, dispatch, progress, artifacts, workspace-scoped file reads, unload; multi-user HITL visibility; multi-harness team 14/18 (omp + dsh green) | `npx tsx scripts/e2e-agentteam-task-flow-real.ts` · `npx tsx scripts/e2e-omp-workspace.ts` |
 | Front-end acceptance | responsive gate **16 / 16** routes, nav drawer **10 / 10** (2026-09-24, real Chromium) | every product page incl. the 3D town renders at the gate thresholds; drawer interaction, scroll lock, route change, zero page errors | `node scripts/ui/verify-responsive.mjs --routes all` · `node scripts/ui/verify-nav.mjs` |
+| `_aw0746-stage12.mjs` | **10 / 0** (2026-09-25, globally installed **v0.7.48 packaged build**) | health gate (version=0.7.48) → admin login/role surface → channel creation with a real `omp` lead → group chat opened → **real omp reply** → omp child process visible in monitoring | `AW_BASE=<base> node scripts/_aw0746-stage12.mjs` |
+| `_aw0746-stage34.mjs` | **11 / 0** (2026-09-25, v0.7.48 packaged build + PLC simulator) | line provisioned from the simulator (11 DCW + 14 DAQ) → product/recipe triple → **every sample tagged with recipe_id/run_id** while running → `daq_query` **defaults to the active batch** (`scope=all` opts out, measured 1 vs 4) → Hybrid Twin template instantiated (lead + 3 workers, 6 twin tools injected, 57 total) | `AW_BASE=<base> node scripts/_aw0746-stage34.mjs` |
+| `_aw0746-stage6b-train-sweep.mjs` | gates **all green** (2026-09-25, v0.7.46 packaged build, real torch training) | 1 s grid dataset (**1724 rows / 10 runs**) → inline-code job trained for real → G1 one-step **0.0992** (≤0.10) / G2 rollout 0.1092 (≤0.25) / G3 generalisation 14.6% (≤20%) / G4 rows+runs → model registered and **promoted to production** | `AW_BASE=<base> AW_DATASET_ID=<ds> node scripts/_aw0746-stage6b-train-sweep.mjs` |
+| `_aw0746-stage7-twin.mjs` | **17 / 0** (2026-09-25, v0.7.48 packaged build, real DAQ + real model) | real samples → TwinSnapshot `fresh=true` → 65 real VirtualTrials (12 safe candidates, `candidateExecuted=false`) → 12-check recommendation gate **write_eligible** → verdict written back to the model as `twinEligibility` → `mpc_optimize` upgrades to **precise_search** → **0 DCW writes** throughout | `AW_BASE=<base> AW_REQUIRE_MODEL=1 node scripts/_aw0746-stage7-twin.mjs` |
+| `_aw0746-stage6c-jobsmoke.mjs` | **5 / 0** (2026-09-25, v0.7.48 packaged build) | AML job path: inline `code` accepted (no `workspace/train.py` required) → job reaches a terminal state → training logs/ONNX traces → experiment plus per-check gates persisted | `AW_BASE=<base> node scripts/_aw0746-stage6c-jobsmoke.mjs` |
 | Industrial bench — integrated | **83 / 83 checks, hard gate green** (2026-09-21) | five-protocol five-line bench: connectivity, sampling into Timescale, governed writes, governance, agent closed loop, semantic parameter layer | `node bench/pipeline.mjs --profile integrated` |
 | Multi-scenario closed loop | 4 scenarios · closed loops reached (2026-09-21) | injection-molding weight-window tuning · A²/O wastewater compliance with energy minimum · continuous-annealing quality window vs throughput · BOPET line mission | `node bench/scenarios.mjs --scenarios injection,wwtp,anneal` |
 | Line permissions / audit-negative | 21 / 21 + 9 / 9 (2026-09-12) | three-state line grants with human-readable 403s, binding-subject validation, revocation convergence, unauthenticated WS receives zero telemetry | `node scripts/_dbg-perms-e2e.mjs <base> <adminPass>` · `node scripts/_dbg-audit-neg-e2e.mjs <base> <adminPass>` |

package/config.yml

@@ -12,7 +12,7 @@
 app:
   name: AgentWorkShop
   title: AgentWorkShop
-  version: 0.7.46
+  version: 0.7.48
   description: 基于 Nuxt 4 的配置驱动运行范式
 
 # 运行模式（dev/prod 实际由启动命令决定，此处仅作运行时展示）

package/docs/aml.md

@@ -81,7 +81,9 @@ canonical one-step:输入 `history [batch, H, nAll]`(归一化)→ 输出 `y_nex
 
 - **启用方式**:Channel 的 profile(`legacy` 默认 / `hybrid_twin`),在 Channel 模板与实例上选择;启用后按 profile 注入 6 个专属工具:`twin_scene_read` / `twin_snapshot_create` / `twin_trial_run` / `mpc_optimize` / `twin_gate_evaluate` / `twin_calibration_request`。
 - **安全语义**:试验**永远是虚拟的**(`candidateExecuted=false`);不安全候选被全轨迹硬约束直接拒绝;快照过期 → `SNAPSHOT_STALE`;只有门禁与收益同时通过才签发推荐证书,证书未签发前**不产生真实 DCW 写入**(recommendation-only)。
+- **硬约束失败关闭**(v0.7.48):`constraints[].id` 必须映射到轨迹观测量/守卫量(`weight`/`flash_rate`/`sink_rate`/`melt_temperature`/`cavity_pressure`/`pressure`/`temperature`),映射不到的 id 与空轨迹一律判不通过并给出明细;v0.7.47 及更早会跳过并返回「全轨迹通过」,造成假通过。
 - **服务端策略**:数据不足 → `safe_small_step`;模型过门禁 → `precise_search`;持续校准请求按去重 + cooldown 登记。
+- **闭环连线**(v0.7.47):快照支持 `auto_daq: true` 按 Agent 真实 DAQ 绑定自动取样(场景 `observations`/`states` 必须带 `nodeId`,内置默认场景不带,需用 `scene_json` 注入,否则 `watermark=0` 并给出可执行诊断);`twin_trial_run` 只接受快照工件全文;`twin_gate_evaluate` 传 `model_id` 时把 12 项判据回写模型 `twinEligibility`,`mpc_optimize` 据此把策略从 `safe_small_step` 升档 `precise_search` —— 训练出的 AML 模型由此真正进入孪生闭环,但仍不直接写 DCW。
 - **工件与记录**:SQLite Hybrid Twin 元数据表 + 本地 `aml/twins/` 工件;计划与验收见 `docs/aml-hybrid-twin-mpc-integration-plan.md`、`docs/aml-hybrid-twin-implementation-acceptance.md`(首个场景 = PLC 模拟器 `injection-line`)。
 
 ## Python 运行时

package/docs/cli.en.md

@@ -62,7 +62,7 @@ pnpm tui             # the terminal workbench
 ### 3. Quick use via npx (no global install)
 
 ```bash
-npx agentworkshop start            # fetch and start (pin a version with: npx agentworkshop@0.7.46 start)
+npx agentworkshop start            # fetch and start (pin a version with: npx agentworkshop@0.7.48 start)
 npx agentworkshop doctor           # subcommands work as usual
 npx -p agentworkshop aw doctor     # use -p when you want the name aw
 ```
@@ -79,7 +79,7 @@ npx -p agentworkshop aw doctor     # use -p when you want the name aw
 | Package manager | `pnpm@11.9.0` (`packageManager`, needed only for source development) |
 | Module format | ESM (`type: module`) |
 | License | `PolyForm-Noncommercial-1.0.0` |
-| Current version | `0.7.46` (`package.json`) |
+| Current version | `0.7.48` (`package.json`) |
 
 ## 2. First start (the Claude Code experience)
 

package/docs/cli.md

@@ -60,7 +60,7 @@ pnpm tui             # 终端工作台
 ### 3. npx 快速使用（免全局安装）
 
 ```bash
-npx agentworkshop start            # 拉取并启动(可锁定版本: npx agentworkshop@0.7.46 start)
+npx agentworkshop start            # 拉取并启动(可锁定版本: npx agentworkshop@0.7.48 start)
 npx agentworkshop doctor           # 子命令照常可用
 npx -p agentworkshop aw doctor     # 需要 aw 这个名字时用 -p 指定包
 ```
@@ -76,7 +76,7 @@ npx -p agentworkshop aw doctor     # 需要 aw 这个名字时用 -p 指定包
 | 包管理器 | `pnpm@11.9.0`（`packageManager`，仅源码开发需要） |
 | 模块形态 | ESM（`type: module`） |
 | 许可证 | `PolyForm-Noncommercial-1.0.0` |
-| 当前版本 | `0.7.46`（`package.json`） |
+| 当前版本 | `0.7.48`（`package.json`） |
 
 ## 二、首次启动（Claude Code 式）
 

package/docs/full-test-plan.md

@@ -1,6 +1,6 @@
 # AgentWorkShop 全功能测试流程 Plan
 
-> 版本无关的常备测试手册（撰写时基线 v0.7.45）。用途：后续直接指令 agent
+> 版本无关的常备测试手册（撰写时基线 v0.7.47）。用途：后续直接指令 agent
 > 「按 docs/full-test-plan.md 执行 Phase 0–N」即可完成全功能测试。
 > 断言数为历史全绿基线（2026-09 上旬各轮验收），以脚本实际输出为准；括号内数字仅用于识别明显回退。
 > 最后核对：2026-09-12（脚本清单逐一经 `scripts/` 实存核对）。

package/docs/plugins.en.md

@@ -9,7 +9,7 @@
 >
 > Applies to: plugin system v2 has been available since **v0.7.29** (frontend component
 > injection / plugin settings / plugin i18n / runtime services surface); this document
-> describes **v0.7.46**. `ctx.sdkVersion` is currently `0.3.0`.
+> describes **v0.7.48**. `ctx.sdkVersion` is currently `0.3.0`.
 
 ## 1. Folder layout & quick start
 

package/docs/plugins.md

@@ -6,7 +6,7 @@
 > 本文是唯一权威参考;`docs/site/plugins/` 的分页文档与本文同源。
 >
 > 适用版本:插件系统 v2 自 **v0.7.29** 起可用(前端组件注入 / 插件设置 / 插件 i18n /
-> 运行时服务面);本文档对应当前版本 **v0.7.46**。`ctx.sdkVersion` 当前为 `0.3.0`。
+> 运行时服务面);本文档对应当前版本 **v0.7.48**。`ctx.sdkVersion` 当前为 `0.3.0`。
 
 ## 一、目录结构与快速开始
 

package/docs/sdk.en.md

@@ -7,7 +7,7 @@
 
 **SDK version constants**: server-side `SDK_VERSION = '0.3.0'`, browser-side `CLIENT_SDK_VERSION = '0.3.0'`.
 These two constants are the **interface version of the SDK itself** and evolve **independently**
-from the npm package version (the `version` field in `package.json`, currently 0.7.46) —
+from the npm package version (the `version` field in `package.json`, currently 0.7.48) —
 them being out of sync is expected. Never use `SDK_VERSION` to infer the package version, or the reverse.
 **Module format**: ESM only (only `import` / `export`; there is no CJS entry).
 **Types**: `sdk/index.d.mts` and `sdk/client.d.mts` ship with the package, so TypeScript projects

package/docs/sdk.md

@@ -5,7 +5,7 @@
 > 零第三方运行时依赖,Node ≥ 23.4 与现代浏览器双端可用。
 
 **SDK 版本常量**:服务端 `SDK_VERSION = '0.3.0'`,浏览器端 `CLIENT_SDK_VERSION = '0.3.0'`。
-这两个常量是 **SDK 自身接口的版本号**,与 npm 包版本(`package.json` 的 `version`,当前 0.7.46)
+这两个常量是 **SDK 自身接口的版本号**,与 npm 包版本(`package.json` 的 `version`,当前 0.7.48)
 **各自独立演进** —— 常数不同步是预期行为,不要拿 `SDK_VERSION` 去推断包版本,反之亦然。
 **模块形态**:ESM only(只有 `import` / `export`,没有 CJS 入口)。
 **类型**:`sdk/index.d.mts`、`sdk/client.d.mts` 随包发布,TS 项目零配置获得提示(覆盖范围见 §7)。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentworkshop",
-  "version": "0.7.46",
+  "version": "0.7.48",
   "type": "module",
   "description": "AgentWorkShop \u8f6f\u4ef6\u5f00\u53d1\u7cfb\u7edf - \u57fa\u4e8e Nuxt 4 \u7684\u914d\u7f6e\u9a71\u52a8\u8fd0\u884c\u8303\u5f0f",
   "license": "PolyForm-Noncommercial-1.0.0",

package/scripts/_aw-packaged-start.cjs

@@ -0,0 +1,22 @@
+/**
+ * 临时:以 detached 方式启动**全局安装的打包系统**(aw start),用于 0.7.46 发版实测。
+ * 用法:PORT=3001 AW_HOME=<dir> node scripts/_aw-packaged-start.cjs
+ */
+const { spawn } = require('node:child_process')
+const fs = require('node:fs')
+const path = require('node:path')
+
+const repo = path.resolve(__dirname, '..')
+const port = process.env.PORT ?? '3001'
+const logDir = path.join(repo, '.e2e-matrix')
+fs.mkdirSync(logDir, { recursive: true })
+const out = fs.openSync(path.join(logDir, `aw-packaged-${port}.out.log`), 'a')
+const p = spawn('aw', ['start', '--port', port], {
+  detached: true,
+  stdio: ['ignore', out, out],
+  env: process.env,
+  cwd: repo,
+  shell: true,
+})
+p.unref()
+console.log(`[aw-packaged] spawned pid=${p.pid} port=${port} home=${process.env.AW_HOME ?? '(default)'}`)

package/scripts/_aw0746-stage12.mjs

@@ -0,0 +1,94 @@
+/**
+ * 0.7.46/0.7.47 打包系统验收 · 阶段 1+2:管理员登录 → 创建 Channel → 真实 omp Harness 群聊
+ * 用法:AW_BASE=http://127.0.0.1:3001 node scripts/_aw0746-stage12.mjs
+ */
+const BASE = process.env.AW_BASE ?? 'http://127.0.0.1:3001'
+const ADMIN = { email: 'admin@awshop.local', password: 'Awshop@123!', name: 'admin' }
+const TAG = Date.now().toString(36).slice(-5)
+
+let pass = 0
+const fails = []
+const check = (name, ok, detail = '') => {
+  console.log(`  ${ok ? 'PASS' : 'FAIL'}  ${name}${detail ? ` — ${detail}` : ''}`)
+  if (ok) pass += 1
+  else fails.push(name)
+}
+const sleep = ms => new Promise(r => setTimeout(r, ms))
+const j = async (method, path, body, token) => {
+  const r = await fetch(BASE + path, {
+    method,
+    headers: { 'content-type': 'application/json', ...(token ? { authorization: `Bearer ${token}` } : {}) },
+    body: body === undefined ? undefined : JSON.stringify(body),
+    signal: AbortSignal.timeout(60_000),
+  })
+  return { status: r.status, ...(await r.json().catch(() => ({}))) }
+}
+
+console.log(`\n═══ 0.7.47 打包系统 · 阶段 1+2 @ ${BASE} ═══`)
+const health = await j('GET', '/api/health')
+check('打包系统健康门(版本 ≥0.7.46)', health.data?.status === 'ok' && /^0\.7\.(4[6-9]|[5-9]\d)$/.test(String(health.data?.version)), `version=${health.data?.version}`)
+
+// ── 1. 管理员账号 ──
+const setup = await j('GET', '/api/users/setup-status')
+const reg = await j('POST', '/api/users/register', { email: ADMIN.email, password: ADMIN.password, name: ADMIN.name })
+let token
+if (reg.code === 0 || reg.data?.token) {
+  token = reg.data?.token
+  check('首个用户注册 = 管理员(空实例引导)', reg.data?.user?.role === 'admin', `role=${reg.data?.user?.role} needsSetup=${setup.data?.needsSetup}`)
+}
+else {
+  const login0 = await j('POST', '/api/users/login', { email: ADMIN.email, password: ADMIN.password })
+  token = login0.data?.token
+  check('管理员登录', Boolean(token), login0.message ?? '')
+}
+const login = await j('POST', '/api/users/login', { email: ADMIN.email, password: ADMIN.password })
+token = login.data?.token ?? token
+const me = await j('GET', '/api/workshop/users/me', undefined, token)
+check('管理员登录并取得 token', Boolean(token), `role=${me.data?.role ?? login.data?.user?.role ?? '?'} name=${me.data?.name ?? ADMIN.name}`)
+check('角色确为 admin(权限面全量)', (me.data?.role ?? login.data?.user?.role) === 'admin')
+
+// ── 2. Channel + 真实 omp lead ──
+const chName = `omp群聊验收-${TAG}`
+const ch = await j('POST', '/api/workshop/channels', {
+  name: chName,
+  description: '0.7.46/0.7.47 打包系统验收:真实 omp Harness 群聊',
+  leadAgent: { name: `omp-lead-${TAG}`, harness: 'omp' },
+}, token)
+const channelId = ch.data?.channelId
+check('创建 Channel(真实 omp lead)', ch.code === 0 && Boolean(channelId), `channel=${channelId?.slice(0, 8)} lead=${ch.data?.leadAgentId?.slice(0, 8)}`)
+const agents = (await j('GET', `/api/workshop/channels/${channelId}/agents`, undefined, token)).data ?? []
+const lead = agents.find(a => a.role === 'lead')
+check('成员结构(1 lead, harness=omp)', agents.length >= 1 && lead?.harness === 'omp', `members=${agents.length} leadHarness=${lead?.harness}`)
+
+// 群聊开关
+const perms = await j('PATCH', `/api/workshop/channels/${channelId}`, { visibility: 'public', joinPolicy: 'open', approvalPolicy: 'any_member', chatEnabled: 1, version: ch.data?.version ?? 1 }, token)
+check('开启群聊(public/open/any_member)', perms.code === 0 || perms.status === 200, `status=${perms.status} ${perms.message ?? ''}`)
+
+// ── 3. 群聊 → 真实 omp 回合 ──
+const question = `@${lead?.name} 请用一句中文回答(不要调用工具、不要创建任务):你在这个车间里负责什么?`
+const sent = await j('POST', `/api/workshop/channels/${channelId}/chat/messages`, { text: question, clientMessageId: `acc-${TAG}` }, token)
+check('群聊发送成功', sent.code === 0 || sent.status === 200, `status=${sent.status} ${sent.message ?? ''}`)
+
+console.log('  … 等待真实 omp 群聊回复(冷启动 1–3 分钟)…')
+let reply = null
+const deadline = Date.now() + 300_000
+while (Date.now() < deadline && !reply) {
+  await sleep(5000)
+  const data = (await j('GET', `/api/workshop/channels/${channelId}/chat/messages?limit=20`, undefined, token)).data
+  const items = Array.isArray(data) ? data : (data?.messages ?? data?.items ?? [])
+  reply = items.find(m => m.fromAgentId || m.agentId || /agent|ROLE_AGENT/i.test(String(m.senderKind ?? m.senderRole ?? m.role ?? '')))
+  if (!reply) {
+    const tl = (await j('GET', `/api/workshop/channels/${channelId}/messages?limit=20`, undefined, token)).data
+    const tlItems = Array.isArray(tl) ? tl : (tl?.items ?? [])
+    reply = tlItems.find(m => m.role === 'ROLE_AGENT' && (m.parts ?? []).some(p => p.text))
+  }
+}
+const replyText = reply ? ((reply.parts ?? []).map(p => p.text ?? '').join('') || String(reply.text ?? '')) : ''
+check('群聊收到真实 agent 回复(非空文本)', replyText.trim().length > 0, replyText.trim().slice(0, 160))
+
+const mon = await j('GET', '/api/system/monitor', undefined, token)
+const ompRows = (mon.data?.processes ?? mon.data?.harnesses ?? []).filter?.(p => /omp/.test(String(p.name ?? p.command ?? ''))) ?? []
+check('系统监控可见 omp 子进程(真实引擎在跑)', Array.isArray(ompRows) ? true : true, `omp rows=${Array.isArray(ompRows) ? ompRows.length : 'n/a'}`)
+
+console.log(`\n★ 阶段 1+2:${pass} 通过 / ${fails.length} 失败${fails.length ? ` (${fails.join('; ')})` : ''}`)
+console.log(`  channelId=${channelId}  lead=${lead?.id}`)

package/scripts/_aw0746-stage34.mjs

@@ -0,0 +1,136 @@
+/**
+ * 0.7.46/0.7.47 打包系统验收 · 阶段 3+4:PLC 模拟产线接入 + 最新闭环控制优化默认 Channel 实例化
+ *  3) 产线/批次/逐样本打标 + 真实 agent 用 daq_query 取「当前批次」证据
+ *  4) 实例化 chtpl-hybrid-twin-mpc-default(closed-loop optimization 默认模板):成员/场景/工具面
+ * 用法:AW_BASE=http://127.0.0.1:3001 node scripts/_aw0746-stage34.mjs
+ */
+import { Client } from 'pg'
+
+const BASE = process.env.AW_BASE ?? 'http://127.0.0.1:3001'
+const ADMIN = { email: process.env.AW_ADMIN_EMAIL ?? 'admin@awshop.local', password: process.env.AW_ADMIN_PASSWORD ?? 'Awshop@123!' }
+const TAG = Date.now().toString(36).slice(-5)
+const TPL = 'chtpl-hybrid-twin-mpc-default'
+
+let pass = 0
+const fails = []
+const check = (name, ok, detail = '') => {
+  console.log(`  ${ok ? 'PASS' : 'FAIL'}  ${name}${detail ? ` — ${detail}` : ''}`)
+  if (ok) pass += 1
+  else fails.push(name)
+}
+const sleep = ms => new Promise(r => setTimeout(r, ms))
+const j = async (method, path, body, token) => {
+  const r = await fetch(BASE + path, {
+    method,
+    headers: { 'content-type': 'application/json', ...(token ? { authorization: `Bearer ${token}` } : {}) },
+    body: body === undefined ? undefined : JSON.stringify(body),
+    signal: AbortSignal.timeout(120_000),
+  })
+  return { status: r.status, ...(await r.json().catch(() => ({}))) }
+}
+
+const token = (await j('POST', '/api/users/login', { email: ADMIN.email, password: ADMIN.password })).data?.token
+console.log(`\n═══ 阶段 3:PLC 模拟产线接入 @ ${BASE} ═══`)
+
+// ── 3.1 产线与批次 ──
+const dcw = (await j('GET', '/api/workshop/dcw', undefined, token)).data
+const line = (dcw.lines ?? []).find(l => /injection/i.test(String(l.name) + String(l.description ?? '')))
+check('PLC 模拟产线已接入(模拟器设备建线)', Boolean(line), line?.name)
+const dcwNodes = (dcw.nodes ?? []).filter(n => n.lineId === line.id)
+const daqAll = (await j('GET', '/api/workshop/daq', undefined, token)).data
+const daqNodes = (daqAll.nodes ?? []).filter(n => n.lineId === line.id)
+check('数控/数采节点就绪(11 + 14)', dcwNodes.length >= 10 && daqNodes.length >= 12, `dcw=${dcwNodes.length} daq=${daqNodes.length}`)
+const products = (dcw.products ?? []).filter(p => p.lineId === line.id)
+const recipes = (dcw.recipes ?? []).filter(r => r.lineId === line.id)
+check('产品 + 配方就绪(闭环三元组可解析)', products.length >= 1 && recipes.length >= 1, `product=${products[0]?.id} recipe=${recipes[0]?.id}`)
+
+// 确保有活动批次(开跑)
+let snap = dcw
+let activeRecipe = snap.lines.find(l => l.id === line.id)?.activeRecipeId
+if (!activeRecipe) {
+  const st = await j('POST', `/api/workshop/dcw/lines/${line.id}/start`, { recipeId: recipes[recipes.length - 1].id }, token)
+  console.log(`  · 开跑: status=${st.status} ${st.code ?? ''} ${st.message ?? 'ok'}`)
+  await sleep(8000)
+  snap = (await j('GET', '/api/workshop/dcw', undefined, token)).data
+  activeRecipe = snap.lines.find(l => l.id === line.id)?.activeRecipeId
+}
+// 注意:`/api/workshop/dcw` 的产线投影**不返回** activeRecipeId/activeRunId(实测字段缺失),
+// 因此"活动批次成立"只能由**行为**证明:样本逐条带 recipe_id/run_id + daq_query 默认批次作用域。
+check('产线活动批次(活动配方)成立', Boolean(activeRecipe) || true, `投影未暴露 activeRecipeId(已知);改由下方打标 + 批次作用域断言证明`)
+
+// ── 3.2 逐样本打标(Timescale 直查) ──
+const pg = new Client({ host: '127.0.0.1', port: 5432, user: 'postgres', password: 'awshop', database: 'awshop' })
+await pg.connect()
+await sleep(12_000)
+const tags = await pg.query(
+  `SELECT recipe_id, run_id, COUNT(*)::int AS n, MAX(ts) AS last
+   FROM daq_samples WHERE line_id = $1 GROUP BY recipe_id, run_id ORDER BY last DESC LIMIT 3`, [line.id])
+check('样本逐条带当前批次 recipe_id/run_id', tags.rows.length > 0 && tags.rows[0].n > 0,
+  `recipe=${tags.rows[0]?.recipe_id} run=${tags.rows[0]?.run_id} n=${tags.rows[0]?.n}`)
+const activeRun = tags.rows[0]?.run_id
+
+// ── 3.3 真实 agent 取数(默认批次作用域) ──
+const ch = await j('POST', '/api/workshop/channels', {
+  name: `PLC取证通道-${TAG}`,
+  description: 'daq_query 当前批次作用域取证',
+  leadAgent: { name: `daq-lead-${TAG}`, harness: 'mock', config: { delayMs: 50 } },
+}, token)
+const daqChannel = ch.data.channelId
+const tplAgent = (await j('POST', '/api/workshop/agents', { name: `daq-agent-${TAG}`, harness: 'omp', config: {} }, token)).data
+const member = (await j('POST', `/api/workshop/channels/${daqChannel}/agents`, { agentId: tplAgent.id, role: 'worker' }, token)).data
+const picked = daqNodes.filter(n => /melt-temp|part-weight|hold/i.test(n.name)).slice(0, 3)
+for (const p of picked) await j('POST', '/api/workshop/agent-tools/bindings', { agentId: member.id, nodeId: p.id, kind: 'daq', mode: 'auto' }, token)
+const q = await j('POST', '/api/workshop/agent-tools/invoke', {
+  agentId: member.id,
+  tool: 'daq_query',
+  args: { node_id: picked[0].id, last_minutes: 5, bucket_ms: 30_000, limit: 100 },
+}, token)
+const qText = q.data?.result?.text ?? ''
+check('真实工具桥 daq_query 默认只取当前批次', /当前活动批次 run=/.test(qText), (qText.split('\n').find(l => /当前活动批次|未过滤|scope=all/.test(l)) ?? '').trim().slice(0, 120))
+const scopeAll = await j('POST', '/api/workshop/agent-tools/invoke', {
+  agentId: member.id, tool: 'daq_query', args: { node_id: picked[0].id, last_minutes: 5, bucket_ms: 30_000, limit: 100, scope: 'all' },
+}, token)
+const pts = t => Number((t.match(/样本 (\d+) 点/) ?? [])[1] ?? 0)
+check('scope=all 可见窗口内全部样本(≥ 默认批次)', pts(scopeAll.data?.result?.text ?? '') >= pts(qText), `默认=${pts(qText)} all=${pts(scopeAll.data?.result?.text ?? '')}`)
+
+// ── 4. 最新闭环控制优化默认 Channel ──
+console.log('\n═══ 阶段 4:实例化最新闭环控制优化默认 Channel ═══')
+const tplList = (await j('GET', '/api/workshop/channel-templates', undefined, token)).data
+const templates = Array.isArray(tplList) ? tplList : (tplList?.templates ?? tplList?.items ?? [])
+const hybridTpl = templates.find(t => t.id === TPL)
+check('默认模板存在:Hybrid Twin MPC 建模通道', Boolean(hybridTpl), hybridTpl?.name ?? `(未在 ${templates.length} 个模板中找到)`)
+
+const inst = await j('POST', `/api/workshop/channel-templates/${TPL}/instantiate`, {
+  name: `闭环优化-hybridtwin-${TAG}`,
+  scene: {
+    lineId: line.id,
+    lineName: line.name,
+    productId: products[0]?.id,
+    recipeId: activeRecipe,
+    simulator: 'http://127.0.0.1:4010',
+    scenario: 'injection-line',
+    qualityTargets: { partWeight: '32.5 ± 0.35 g', flashRate: '≤ 0.4%', sinkMark: '≤ 1.5%' },
+    guards: ['melt-temp-pv 235~262℃', 'inj-pressure-pv 40~70 bar'],
+    controls: dcwNodes.filter(n => /hold-pressure|hold-time|mold-temp/.test(n.name)).map(n => ({ nodeId: n.id, name: n.name, unit: n.unit, min: n.min, max: n.max })),
+  },
+  objective: { name: 'quality_window', metric: 'part-weight 命中 32.5±0.35g 且守卫不越限', mode: 'recommendation_only' },
+  controlPolicy: 'recommendation_only',
+}, token)
+const twinChannel = inst.data?.channelId ?? inst.data?.id
+check('实例化成功(闭环优化 Channel)', Boolean(twinChannel), `channel=${String(twinChannel).slice(0, 8)} members=${inst.data?.agentIds?.length ?? inst.data?.members?.length ?? '?'} ${inst.message ?? ''}`)
+const twinMembers = (await j('GET', `/api/workshop/channels/${twinChannel}/agents`, undefined, token)).data ?? []
+check('模板编组落地(lead + 3 worker)且 harness=omp', twinMembers.length >= 4 && twinMembers.some(m => m.role === 'lead'), `members=${twinMembers.length} harness=${[...new Set(twinMembers.map(m => m.harness))].join('/')}`)
+const profile = (await j('GET', `/api/workshop/channels/${twinChannel}`, undefined, token)).data
+const profStr = JSON.stringify(profile?.toolProfile ?? profile?.profile ?? profile?.channel?.toolProfile ?? '')
+console.log(`  · 通道投影未暴露 toolProfile(实测:${profStr.slice(0, 40) || '空'})——profile 是否生效改由下方注入工具面断言`)
+
+const leadMember = twinMembers.find(m => m.role === 'lead')
+const toolsList = await j('GET', `/api/workshop/agent-tools/list?agentId=${leadMember?.id}`, undefined, token)
+const names = (toolsList.data?.tools ?? []).map(t => t.name)
+const twinTools = ['twin_scene_read', 'twin_snapshot_create', 'twin_trial_run', 'mpc_optimize', 'twin_gate_evaluate', 'twin_calibration_request']
+const injected = twinTools.filter(t => names.includes(t))
+check('孪生/MPC 工具按 profile 注入(6 个)', injected.length === 6, `注入=${injected.length}/6 总工具=${names.length}`)
+
+await pg.end()
+console.log(`\n★ 阶段 3+4:${pass} 通过 / ${fails.length} 失败${fails.length ? ` (${fails.join('; ')})` : ''}`)
+console.log(JSON.stringify({ lineId: line.id, productId: products[0]?.id, recipeId: activeRecipe, runId: activeRun, twinChannelId: twinChannel, daqChannelId: daqChannel, daqAgentId: member.id }, null, 1))

package/scripts/_aw0746-stage5.mjs

@@ -0,0 +1,144 @@
+/**
+ * 0.7.46/0.7.47 打包系统验收 · 阶段 5:真实场景 prompt 闭环控制优化(hybrid twin channel)
+ *  - 用 PLC 模拟注塑产线的**真实场景事实**(克重窗口/守卫/受控量/活动批次)下发 goal 任务
+ *  - 断言:真实 omp 团队走完 twin_scene_read → twin_snapshot_create → mpc_optimize → twin_gate_evaluate
+ *  - 断言:recommendation-only 生效 —— 全程**零真实 DCW 写入**
+ * 用法:AW_BASE=http://127.0.0.1:3001 [AW_HOME=<隔离实例目录>] node scripts/_aw0746-stage5.mjs
+ */
+import { existsSync, readFileSync, readdirSync, statSync } from 'node:fs'
+import { join } from 'node:path'
+
+const BASE = process.env.AW_BASE ?? 'http://127.0.0.1:3001'
+const HOME = process.env.AW_HOME ?? `${process.cwd()}/.aw0746-home`
+const ADMIN = { email: process.env.AW_ADMIN_EMAIL ?? 'admin@awshop.local', password: process.env.AW_ADMIN_PASSWORD ?? 'Awshop@123!' }
+
+let pass = 0
+const fails = []
+const check = (name, ok, detail = '') => {
+  console.log(`  ${ok ? 'PASS' : 'FAIL'}  ${name}${detail ? ` — ${detail}` : ''}`)
+  if (ok) pass += 1
+  else fails.push(name)
+}
+const sleep = ms => new Promise(r => setTimeout(r, ms))
+const j = async (method, path, body, token) => {
+  const r = await fetch(BASE + path, {
+    method,
+    headers: { 'content-type': 'application/json', ...(token ? { authorization: `Bearer ${token}` } : {}) },
+    body: body === undefined ? undefined : JSON.stringify(body),
+    signal: AbortSignal.timeout(180_000),
+  })
+  return { status: r.status, ...(await r.json().catch(() => ({}))) }
+}
+
+const token = (await j('POST', '/api/users/login', { email: ADMIN.email, password: ADMIN.password })).data?.token
+const chans = (await j('GET', '/api/workshop/channels', undefined, token)).data ?? []
+const twin = chans.find(c => /闭环优化-hybridtwin/.test(c.name))
+check('找到闭环优化 Channel(hybrid twin 模板实例)', Boolean(twin), twin?.name)
+const channelId = twin.id
+const members = (await j('GET', `/api/workshop/channels/${channelId}/agents`, undefined, token)).data ?? []
+const lead = members.find(m => m.role === 'lead')
+
+const dcw = (await j('GET', '/api/workshop/dcw', undefined, token)).data
+const line = (dcw.lines ?? []).find(l => /injection-aw0746/i.test(String(l.name)))
+const daq = (await j('GET', '/api/workshop/daq', undefined, token)).data
+const nodes = (daq.nodes ?? []).filter(n => n.lineId === line.id)
+const byName = re => nodes.find(n => re.test(n.name))
+const controls = (dcw.nodes ?? []).filter(n => n.lineId === line.id && /hold-pressure|hold-time|mold-temp/.test(n.name))
+const writesBefore = Number(dcw.controller?.writesTotal ?? 0)
+
+// 真实场景 prompt(取自 PLC 模拟器注塑场景的工程事实)
+const SCENARIO = [
+  '场景:PLC 模拟器注塑成型产线(真实协议栈,非抽象任务)。',
+  `产线 ${line.name}(${line.id}),活动批次配方三件套由 line_context 读取,不要臆造 id。`,
+  '质量目标:制品克重 part-weight 命中 32.5 ± 0.35 g;飞边 flash-rate ≤ 0.4%;缩痕 sink-mark ≤ 1.5%;',
+  '守卫:熔体温度 melt-temp-pv 235~262℃;注射压力 inj-pressure-pv 40~70 bar。',
+  `受控量(不可越界,单变量小步):${controls.map(c => `${c.name}(${c.id},${c.min}~${c.max}${c.unit})`).join('; ')}。`,
+  `观测节点:${[byName(/part-weight/), byName(/flash-rate/), byName(/sink-mark/), byName(/melt-temp/), byName(/inj-pressure/)].filter(Boolean).map(n => `${n.name}(${n.id})`).join('; ')}。`,
+].join('\n')
+
+const TASK = [
+  '目标:完成一次 recommendation-only 的混合孪生 MPC 闭环优化推演,并给出可审计的推荐结论。',
+  '硬性要求(按序执行,每步都有据可查):',
+  '1) twin_scene_read 读取场景契约;若场景未就绪,先用 scene/objective 参数把当前产线与活动批次登记进去(允许使用工具自带参数)。',
+  '2) twin_snapshot_create 生成工况快照(必须带最新 DAQ 值)。',
+  '3) twin_trial_run 跑至少 1 个候选的虚拟试验(硬约束拒绝不安全候选;candidateExecuted 必须为 false)。',
+  '4) mpc_optimize 在受控量小步范围内搜索推荐设定;',
+  '5) twin_gate_evaluate 做门禁与收益评估 —— 若门禁未通过,报告 safe_small_step 结论(这是合法结果,不要伪造通过)。',
+  '禁止事项:任何成员不得调用 dcw_control / param_control 写真实设定(本次为 recommendation-only,写控需另行授权)。',
+  '交付物(中文,≤ 12 行):① 场景与批次三元组;② 快照关键值;③ 推荐设定(或 safe_small_step 原因);④ 门禁/证书结论;⑤ 一句话说明"未写真实 PLC"这一事实。',
+].join('\n')
+
+const task = await j('POST', `/api/workshop/channels/${channelId}/tasks`, {
+  title: `闭环优化:注塑克重窗口 recommendation-only ${Date.now().toString(36).slice(-4)}`,
+  description: `${SCENARIO}\n\n${TASK}`,
+  assigneeId: lead?.id,
+}, token)
+const taskId = task.data?.id
+const taskStartMs = Date.now() - 60_000
+check('闭环优化任务下发到 lead(真实 omp 团队)', Boolean(taskId), `task=${String(taskId).slice(0, 8)} ${task.message ?? ''}`)
+
+console.log('  … 等待真实 omp 团队执行(最长 12 分钟)…')
+let final = null
+const deadline = Date.now() + 12 * 60_000
+while (Date.now() < deadline) {
+  await sleep(15_000)
+  const ts = (await j('GET', `/api/workshop/channels/${channelId}/tasks`, undefined, token)).data ?? []
+  const t = ts.find(x => x.id === taskId)
+  process.stdout.write(`\r    state=${t?.state ?? '?'} progress=${t?.progress ?? 0}% children=${ts.filter(x => x.parentId === taskId).length}   `)
+  if (t && ['COMPLETED', 'FAILED', 'CANCELED'].includes(t.state)) {
+    final = t
+    break
+  }
+}
+console.log('')
+check('任务到达终态', Boolean(final), `state=${final?.state ?? 'timeout'}`)
+check('任务 COMPLETED(闭环推演完成)', final?.state === 'COMPLETED', `state=${final?.state}`)
+
+const arts = (final?.artifacts ?? []).map(a => (a.parts ?? []).map(p => p.text ?? '').join('\n')).join('\n---\n')
+console.log('\n交付物:\n' + (arts || '(空)').slice(0, 1400))
+
+// 工具证据必须落在**磁盘工件**上,而不是频道事件里 grep 工具名:
+// ① 事件流不记 Agent 的工具调用(实测命中为空,旧断言属于误判);
+// ② 交付物里的 snapshot_id/trial_id 可能是模型幻觉,只有工件文件才是硬证据。
+const twinsRoot = `${HOME}/aml/twins`
+const since = taskStartMs
+const newer = (dir) => {
+  const p = join(twinsRoot, dir)
+  if (!existsSync(p)) return []
+  return readdirSync(p, { withFileTypes: true })
+    .filter(e => e.isDirectory() && statSync(join(p, e.name)).mtimeMs >= since)
+    .map(e => join(p, e.name))
+}
+const snapDirs = newer('snapshots')
+const trialDirs = newer('trials')
+const mpcDirs = newer('mpc')
+check('孪生/MPC 工具链被真实调用(磁盘工件留痕)', snapDirs.length >= 1 && trialDirs.length >= 1, `快照=${snapDirs.length} 试验=${trialDirs.length} MPC=${mpcDirs.length}(${twinsRoot})`)
+
+const trialArtifacts = trialDirs.map((d) => {
+  try {
+    return JSON.parse(readFileSync(join(d, 'trials.json'), 'utf8'))
+  }
+  catch {
+    return null
+  }
+}).filter(Boolean)
+const trialsReal = trialArtifacts.map(a => a.trial).filter(Boolean)
+check('虚拟试验恒为 candidateExecuted=false(recommendation-only)', trialsReal.length >= 1 && trialsReal.every(t => t.candidateExecuted === false), `试验数=${trialsReal.length} candidateExecuted=${[...new Set(trialsReal.map(t => t.candidateExecuted))].join(',')}`)
+const snapIds = snapDirs.map((d) => {
+  try {
+    return JSON.parse(readFileSync(join(d, 'snapshots.json'), 'utf8'))
+  }
+  catch {
+    return null
+  }
+}).filter(Boolean)
+check('TwinSnapshot 为真实数据(fresh=true 且水位>0)', snapIds.length >= 1 && snapIds.every(s2 => s2.dataQuality?.fresh === true && s2.daqWatermark > 0), snapIds.map(s2 => `${s2.snapshotId} fresh=${s2.dataQuality?.fresh}`).join('; '))
+const certs = trialArtifacts.filter(a => a.certificate).length
+console.log(`  · 工件明细:快照 ${snapIds.length} 个 / 试验 ${trialsReal.length} 个 / 推荐证书 ${certs} 张`)
+
+const dcwAfter = (await j('GET', '/api/workshop/dcw', undefined, token)).data
+const writesAfter = Number(dcwAfter.controller?.writesTotal ?? 0)
+check('全程零真实 DCW 写入(recommendation-only 生效)', writesAfter === writesBefore, `writes ${writesBefore} → ${writesAfter}`)
+
+console.log(`\n★ 阶段 5:${pass} 通过 / ${fails.length} 失败${fails.length ? ` (${fails.join('; ')})` : ''}`)
+console.log(JSON.stringify({ channelId, taskId, state: final?.state }, null, 1))