@wnlen/agent-execution-template 0.8.18 → 0.8.20

package/template/zh/ai/template/reconcile.md

@@ -1,16 +1,13 @@
 # AI 上下文整合
 
 不要总结这个文件。
-执行下面的上下文整合流程。
-
-你正在把新的权威资料吸收到现有 Agent Execution Template 项目上下文中。
-这不是重新引导，也不是全量覆盖。
+按下面流程把新权威资料吸收到现有项目上下文。不是重新引导，也不是全量覆盖。
 
 目标：合并新资料中的长期有效事实，修正过期或不准确的旧上下文，保留仍然正确的既有内容。
 
 ## 适用场景
 
-当项目已经使用一段时间后，出现更完整、更权威的业务、产品、架构或流程资料时，使用本流程。
+当出现更完整、更权威的业务、产品、架构或流程资料时，使用本流程。
 
 新资料默认放在：
 
@@ -18,10 +15,10 @@
 - `ai/project/inbox/raw/*.md`
 - `docs/**`
 
-`ai/project/inbox/` 是待吸收资料区。资料被整合确认后，统一移动到
-`ai/project/inbox/processed/`，用于追溯并避免后续重复整合。
-即使用户说“整合整个 inbox”，默认也只处理 `ai/project/inbox/*.md`
-和 `ai/project/inbox/raw/*.md`；不要递归读取 `processed/**` 或 `ideas/**`。
+`ai/project/inbox/` 是待吸收区。资料确认整合后移到 `ai/project/inbox/processed/`，
+用于追溯并避免重复整合。即使用户说“整合整个 inbox”，也默认只处理
+`ai/project/inbox/*.md` 和 `ai/project/inbox/raw/*.md`；不要递归读取
+`processed/**` 或 `ideas/**`。
 
 ## 先读
 
@@ -33,13 +30,13 @@
 6. 人类指定的新资料；未指定时，只读取 `ai/project/inbox/*.md`
    和 `ai/project/inbox/raw/*.md`
 
-不要默认读取 `ai/project/inbox/processed/**`、`ai/project/inbox/ideas/**`、
-`ai/project/archive/**`、源码、测试、配置或依赖文件，除非人类明确要求用它们核对事实。
+不要默认读取 `processed/**`、`ideas/**`、`archive/**`、源码、测试、配置或依赖；
+除非人类明确要求用它们核对事实。
 
 ## 整合原则
 
-- 不要直接覆盖整套文件。
-- 保留仍然正确的既有上下文。
+- 不整套覆盖。
+- 保留仍正确的既有上下文。
 - 将新资料拆分进合适位置：
   - 项目身份、用户、稳定约定 -> `ai/project/project.md`
   - 当前仍有效的执行上下文 -> `ai/project/runtime.md`
@@ -50,10 +47,9 @@
   - 命令 -> `ai/project/refs/commands.md`
   - 约束 -> `ai/project/refs/constraints.md`
   - 持久决策 -> `ai/project/refs/decisions.md`
-- 不要把 `refs/*` 写成原文堆砌；只吸收结构化、长期有效、可复用的内容。
-- 如果新资料会改变北极星、模块地图或路线图的方向性内容，只能建议创建
-  `strategy_update` 提案，不要在上下文整合中直接修改这些方向文件。
-- `task.md`、`result.json`、`result.md`、`metrics.json` 通常不参与业务上下文整合，除非人类明确要求吸收其中仍长期有效的事实。
+- `refs/*` 不堆原文；只吸收结构化、长期有效、可复用的内容。
+- 新资料若改变北极星、模块地图或路线图，只建议创建 `strategy_update`，不要直接改方向文件。
+- `task.md`、`result.json`、`result.md`、`metrics.json` 通常不参与整合；除非人类明确要求吸收其中的长期事实。
 
 ## 两阶段流程
 
@@ -70,13 +66,11 @@
 5. 需要人类确认的问题，最多 3 个
 6. 预计会更新的文件
 
-如果没有需要确认的问题，明确写“无需额外确认”。
-
-阶段 1 结束时必须停止，等待人类确认。
+无问题时写“无需额外确认”。阶段 1 结束必须停止，等待确认。
 
 ### 阶段 2：应用整合
 
-只有在人类明确确认整合计划后，才更新文件。
+只有人类确认整合计划后才更新文件。
 
 允许更新：
 
@@ -97,15 +91,14 @@
 - `ai/project/metrics.json`
 - `ai/project/archive/**`
 
-应用整合完成后，必须把本次已整合的 `ai/project/inbox/*.md` 和
-`ai/project/inbox/raw/*.md` 资料移动到 `ai/project/inbox/processed/`。保留相对路径：
-`ai/project/inbox/raw/file.md` 移动到 `ai/project/inbox/processed/raw/file.md`。
-如果文件名冲突，保留原文件名并添加日期或序号。不要移动
-`ai/project/inbox/ideas/**`；方向灵感应继续走 `strategy_update`。
+整合完成后，把本次已整合的 `ai/project/inbox/*.md` 和 `ai/project/inbox/raw/*.md`
+移到 `ai/project/inbox/processed/`，保留相对路径：`ai/project/inbox/raw/file.md` ->
+`ai/project/inbox/processed/raw/file.md`。文件名冲突时加日期或序号。不要移动 `ideas/**`；
+方向灵感继续走 `strategy_update`。
 
 ## 最终交接
 
-应用整合后，最终回复必须包含：
+应用后，最终回复包含：
 
 ```text
 上下文整合已完成。
@@ -142,4 +135,4 @@
 - 修正：<你要改的地方>
 ```
 
-不要让人类自己去文件管理器里寻找变化；文件路径只作为可追溯记录。
+不要让人类自己找变化；文件路径只作追溯。

package/template/zh/ai/template/rules/core.md

@@ -2,7 +2,7 @@
 
 ## 就绪门
 
-编辑代码前，检查 `ai/project/task.md` 是否清楚定义：
+编辑前，确认 `ai/project/task.md` 已清楚定义：
 
 - 目标
 - 范围
@@ -18,8 +18,8 @@
 
 ## 引导门
 
-如果 `ai/project/project.md` 为空、只有占位内容、不完整，或用户要求整理项目上下文，
-先执行 `ai/template/bootstrap.md`，再进入执行。
+若 `ai/project/project.md` 为空、占位、不完整，或用户要求整理上下文，先执行
+`ai/template/bootstrap.md`。
 
 引导模式只能写项目上下文文件：
 
@@ -32,14 +32,13 @@
 - `ai/project/refs/constraints.md`
 - `ai/project/refs/decisions.md`
 
-只有在人类同时提供当前任务目标时，引导模式才可以写 `ai/project/task.md`。
-此时只能起草任务契约，不能进入实现。
+只有人类同时提供当前任务目标时，引导模式才可写 `ai/project/task.md`；只能起草，不实现。
 
-引导模式不得编辑源码、测试、配置、依赖文件、生成文件、运行时文件、结果文件或指标文件。
+引导模式不得编辑源码、测试、配置、依赖、生成文件、运行时、结果或指标文件。
 
 写完引导草稿后，使用 `ai/template/bootstrap.md` 中的“引导后交接”停止。
 交接必须在聊天里给出可确认摘要和推荐下一步，不要只让人类打开文件检查。
-如果人类已经提供当前任务目标，可以同轮起草 `ai/project/task.md`，但仍必须停止等待确认，不能进入实现。
+若人类已提供任务目标，可同轮起草 `task.md`，但仍必须停止确认，不能实现。
 
 ## 引导读取范围
 
@@ -60,9 +59,8 @@
 
 ## 任务草稿门
 
-如果项目上下文已确认，但 `ai/project/task.md` 为空、只有占位内容、不完整，
-或人类提供了新的任务目标，根据已确认的项目上下文起草 `ai/project/task.md`，
-并在实现前停止等待人类确认。
+项目上下文已确认但 `task.md` 为空、占位、不完整，或人类提供新任务目标时，
+按已确认上下文起草 `task.md`，实现前停止确认。
 
 任务草稿模式只能写：
 
@@ -72,8 +70,8 @@
 
 ## 上下文整合门
 
-如果用户提供新的权威业务、产品、架构或流程资料，并希望合并到既有上下文，
-或说“整合 ai/project/inbox/ 里的新资料”，执行 `ai/template/reconcile.md`，
+用户提供新权威业务、产品、架构或流程资料并希望合并，或说
+“整合 ai/project/inbox/ 里的新资料”时，执行 `ai/template/reconcile.md`。
 不要重新 bootstrap，也不要全量覆盖。
 
 新资料优先放在：
@@ -84,7 +82,7 @@
 
 已整合资料统一移动到 `ai/project/inbox/processed/`，默认不再触发上下文整合。
 
-上下文整合必须先输出整合计划，等待人类确认后才更新文件。
+上下文整合必须先给计划，等确认后再更新文件。
 
 上下文整合默认只能更新：
 
@@ -92,8 +90,7 @@
 - `ai/project/runtime.md`
 - `ai/project/refs/*.md`
 
-如果新资料会改变北极星、模块地图或路线图的方向性内容，只能建议创建
-`strategy_update` 提案，不能在上下文整合中直接修改：
+新资料若改变北极星、模块地图或路线图，只能建议创建 `strategy_update`，不能直接改：
 
 - `ai/project/refs/final-shape.md`
 - `ai/project/refs/module-map.md`
@@ -103,27 +100,32 @@
 
 ## 边界内连续执行门
 
-每次执行前，AI 必须读取 `ai/template/execution-policy.md`，先做任务分解和风险判断，
-而不是等待用户显式说“启用连续执行”。
+每次执行前，AI 必须读取 `ai/template/execution-policy.md`，先分解任务并判断风险，
+不等用户说“启用连续执行”。
 
 硬门禁：
 
+- 只有 `task.md.readiness = ready_to_execute` 才能执行；本轮新建或重写 `task.md` 时必须停下确认。
+- L1 必须是可独立验收的垂直切片，不是机械步骤清单。
 - `execution_policy.task_tree` 必须记录 L1 清单和执行状态。
 - 每个任务节点必须有 Green / Yellow / Red 风险评级。
+- Yellow 只允许当前 L1/L2 内的局部低风险修正，不能改变公共接口、数据模型、
+  权限、安全、架构方向或验收标准。
 - 每个 Checkpoint 必须包含证据；不接受只有主观判断的 Green。
 - Red 必须停止等待人类确认。
-- 任何方向、核心架构、数据结构、安全、支付、账号、权限、大量删除、
-  核心重写或高成本方案取舍，都必须停止。
+- 涉及方向、核心架构、公共 API、持久化数据、安全、支付、账号、权限、大量删除、
+  核心重写或高成本取舍时，必须停止。
 - 需要扩大范围、权限、命令、网络或验收时，必须停止。
+- `task_tree` 写回应集中在 L1 开始/完成、Red、blocked、范围变化和最终收尾，
+  不要为每个微小 L3 操作写回。
 
 目标、范围、验收和权限由 AI 推断，但不能越过项目规则、显式用户限制、
 `permission.modify.denied`、安全边界或破坏性操作限制。
 
 ## 策略修订门
 
-如果用户要求更新项目北极星、最终形态、产品宪法、模块地图、路线图或项目方向，
-或 `ai/project/inbox/ideas/` 中存在 `.gitkeep` 之外的新灵感，执行
-`strategy_update`。
+用户要求更新北极星、最终形态、产品宪法、模块地图、路线图或项目方向，或
+`ai/project/inbox/ideas/` 有新灵感时，执行 `strategy_update`。
 
 `strategy_update` 只能：
 

package/template/zh/ai/template/rules/output.md

@@ -25,7 +25,9 @@
 
 ## 结果 Markdown
 
-`ai/project/result.md` 是给人看的摘要。保持简短：
+`ai/project/result.md` 是给人看的摘要。保持简短，并默认使用 `ai/template/LANG`
+指定的安装语言。中文模板下，标题和说明默认用中文；代码、命令、文件路径和协议字段
+保留原文。
 
 ```md
 ## 状态

package/test/selftest.js

@@ -54,6 +54,8 @@ function testInitUpdateDoctor() {
   assert(exists(cwd, "ai/template/execution-policy.md"), "init should create execution policy prompt");
   assert(exists(cwd, "ai/template/prompt.md"), "init should create template prompt");
   assert(exists(cwd, "ai/template/reconcile.md"), "init should create template reconcile prompt");
+  assert(exists(cwd, "ai/template/schemas/result.schema.json"), "init should create result schema");
+  assert(exists(cwd, "ai/template/schemas/metrics.schema.json"), "init should create metrics schema");
   assert(exists(cwd, "ai/project/inbox/.gitkeep"), "init should create inbox directory");
   assert(exists(cwd, "ai/project/project.md"), "init should create project.md");
   assert(exists(cwd, "ai/project/task.md"), "init should create task.md");
@@ -81,16 +83,29 @@ function testInitUpdateDoctor() {
   assert(read(cwd, "ai/template/prompt.md").includes("ai/template/execution-policy.md"), "execution prompt should read execution policy");
   assert(read(cwd, "ai/template/execution-policy.md").includes("风险分级"), "execution policy should include risk rubric");
   assert(read(cwd, "ai/template/execution-policy.md").includes("execution_policy.task_tree"), "execution policy should require task tree persistence");
-  assert(read(cwd, "ai/template/prompt.md").includes("默认也只处理 `ai/project/inbox/*.md`"), "execution prompt should narrow inbox reconciliation");
+  assert(read(cwd, "ai/template/prompt.md").includes("也默认只处理 `ai/project/inbox/*.md`"), "execution prompt should narrow inbox reconciliation");
   assert(read(cwd, "ai/template/protocol.md").includes("`bounded_continuous`"), "protocol should include bounded continuous execution");
   assert(read(cwd, "ai/template/execution-policy.md").includes("垂直切片"), "protocol should require vertical-slice progress for continuous execution");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("可独立验收的垂直切片"), "execution policy should define L1 granularity");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("不能边写草稿边执行"), "execution policy should block execution from draft tasks");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("不要为每个微小 L3 操作写回"), "execution policy should limit task tree write-back churn");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("公共接口、数据模型、权限、安全"), "execution policy should constrain Yellow corrections");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("用户可见输出"), "execution policy should define user-visible output rules");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("用户可见的计划"), "execution policy should keep user-visible planning in the installed language");
+  assert(read(cwd, "ai/template/rules/output.md").includes("默认使用 `ai/template/LANG`"), "output rules should keep human-readable results in the installed language");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("不要默认展示完整 L2/L3/L4"), "execution policy should avoid exposing full subtask trees by default");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("不要展示内部协议字段"), "execution policy should hide internal protocol details by default");
   assert(read(cwd, "ai/template/execution-policy.md").includes("L1 为 2 个或更多，自动启用"), "protocol should auto-enable continuous execution from L1 count");
   assert(read(cwd, "ai/template/execution-policy.md").includes("每个 Checkpoint 必须包含"), "protocol should require evidence-backed checkpoints");
   assert(read(cwd, "ai/template/rules/core.md").includes("边界内连续执行门"), "core rules should include bounded continuous execution gate");
+  assert(read(cwd, "ai/template/rules/core.md").includes("readiness = ready_to_execute"), "core rules should require ready task before execution");
+  assert(read(cwd, "ai/template/rules/core.md").includes("不是机械步骤清单"), "core rules should reject mechanical L1 task lists");
   assert(read(cwd, "ai/template/rules/core.md").includes("需要扩大范围、权限、命令、网络或验收时"), "core rules should stop continuous execution before boundary expansion");
   assert(read(cwd, "ai/project/task.md").includes("execution_policy:"), "task template should include execution policy");
   assert(read(cwd, "ai/project/task.md").includes("readiness:"), "task template should include readiness state");
   assert(read(cwd, "ai/project/task.md").includes("activation_rule: \"auto_enable_when_l1_count_gte_2\""), "task template should define automatic activation rule");
+  assert(read(cwd, "ai/project/task.md").includes("l1_granularity: \"independently_acceptable_vertical_slice\""), "task template should define L1 granularity");
+  assert(read(cwd, "ai/project/task.md").includes("write_back_policy: \"l1_start_done_red_blocked_scope_change_final\""), "task template should define task tree write-back policy");
   assert(read(cwd, "ai/project/task.md").includes("risk_gate:"), "task template should define risk gate");
   assert(read(cwd, "ai/project/task.md").includes("status: \"pending | running | done | blocked\""), "task template should define task tree node status");
   assert(read(cwd, "ai/project/task.md").includes("progress_unit: \"vertical_slice\""), "task template should define continuous progress unit");
@@ -99,10 +114,12 @@ function testInitUpdateDoctor() {
   assert(read(cwd, "ai/template/prompt.md").includes("不要重新 bootstrap"), "execution prompt should reconcile inbox material when project context already exists");
   assert(read(cwd, "ai/template/prompt.md").includes("整合 ai/project/inbox/ 里的新资料"), "execution prompt should route natural reconcile entry");
   assert(read(cwd, "ai/template/prompt.md").includes("继续推进这个项目"), "execution prompt should route natural continue entry");
+  assert(read(cwd, "ai/template/prompt.md").includes("草稿不能直接执行"), "execution prompt should stop after drafting a task");
+  assert(read(cwd, "ai/template/prompt.md").includes("用户可见输出"), "execution prompt should reference user-visible output rules");
   assert(read(cwd, "ai/template/prompt.md").includes("strategy_update"), "execution prompt should route strategy updates");
   assert(read(cwd, "ai/template/reconcile.md").includes("上下文整合"), "init should install reconcile prompt");
   assert(read(cwd, "ai/template/reconcile.md").includes("整合计划"), "reconcile prompt should require a plan first");
-  assert(read(cwd, "ai/template/reconcile.md").includes("不要递归读取 `processed/**` 或 `ideas/**`"), "reconcile prompt should exclude processed and ideas recursively");
+  assert(read(cwd, "ai/template/reconcile.md").includes("不要递归读取") && read(cwd, "ai/template/reconcile.md").includes("`processed/**` 或 `ideas/**`"), "reconcile prompt should exclude processed and ideas recursively");
   assert(read(cwd, "ai/template/reconcile.md").includes("ai/project/inbox/processed/raw/file.md"), "reconcile prompt should archive absorbed raw inbox material");
   assert(read(cwd, "ai/template/reconcile.md").includes("未吸收资料"), "reconcile handoff should audit unabsorbed material");
   assert(read(cwd, "ai/template/reconcile.md").includes("冲突处理"), "reconcile handoff should audit conflict handling");
@@ -140,7 +157,9 @@ function testInitUpdateDoctor() {
 
   const doctorOutput = run(["doctor"], cwd);
   assert(doctorOutput.includes("ai/project/result.json JSON"), "doctor should validate result JSON");
+  assert(doctorOutput.includes("ai/project/result.json schema"), "doctor should validate result schema");
   assert(doctorOutput.includes("ai/project/metrics.json JSON"), "doctor should validate metrics JSON");
+  assert(doctorOutput.includes("ai/project/metrics.json schema"), "doctor should validate metrics schema");
   assert(doctorOutput.includes("ai/project/task.md front matter"), "doctor should validate task front matter");
 }
 
@@ -150,6 +169,8 @@ function testEnglishInitUpdateDoctor() {
   const initOutput = run(["init", "--lang", "en"], cwd);
   assert(read(cwd, "ai/template/LANG") === "en\n", "init --lang en should install English template");
   assert(exists(cwd, "ai/template/execution-policy.md"), "English init should create execution policy prompt");
+  assert(exists(cwd, "ai/template/schemas/result.schema.json"), "English init should create result schema");
+  assert(exists(cwd, "ai/template/schemas/metrics.schema.json"), "English init should create metrics schema");
   assert(read(cwd, "ai/template/bootstrap.md").includes("Confirmation Dimensions"), "English init should install English bootstrap prompt");
   assert(read(cwd, "ai/template/bootstrap.md").includes("Do not summarize this file"), "English bootstrap prompt should prevent summary-only behavior");
   assert(read(cwd, "ai/template/bootstrap.md").includes("ai/project/refs/final-shape.md"), "English bootstrap prompt should initialize the North Star");
@@ -168,13 +189,26 @@ function testEnglishInitUpdateDoctor() {
   assert(read(cwd, "ai/template/prompt.md").includes("default to only `ai/project/inbox/*.md`"), "English execution prompt should narrow inbox reconciliation");
   assert(read(cwd, "ai/template/protocol.md").includes("`bounded_continuous`"), "English protocol should include bounded continuous execution");
   assert(read(cwd, "ai/template/execution-policy.md").includes("vertical"), "English protocol should require vertical-slice progress for continuous execution");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("independently acceptable vertical slice"), "English execution policy should define L1 granularity");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("executing from a draft"), "English execution policy should block execution from draft tasks");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("every tiny L3 operation"), "English execution policy should limit task tree write-back churn");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("public interfaces, data models, permissions"), "English execution policy should constrain Yellow corrections");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("User-Visible Output"), "English execution policy should define user-visible output rules");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("user-visible plans"), "English execution policy should keep user-visible planning in the installed language");
+  assert(read(cwd, "ai/template/rules/output.md").includes("installed language from `ai/template/LANG`"), "English output rules should keep human-readable results in the installed language");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("do not show full L2/L3/L4 by default"), "English execution policy should avoid exposing full subtask trees by default");
+  assert(read(cwd, "ai/template/execution-policy.md").includes("do not show internal protocol fields"), "English execution policy should hide internal protocol details by default");
   assert(read(cwd, "ai/template/execution-policy.md").includes("Automatically use `bounded_continuous`"), "English protocol should auto-enable continuous execution from L1 count");
   assert(read(cwd, "ai/template/execution-policy.md").includes("Every checkpoint must include"), "English protocol should require evidence-backed checkpoints");
   assert(read(cwd, "ai/template/rules/core.md").includes("Bounded Continuous Execution Gate"), "English core rules should include bounded continuous execution gate");
+  assert(read(cwd, "ai/template/rules/core.md").includes("readiness = ready_to_execute"), "English core rules should require ready task before execution");
+  assert(read(cwd, "ai/template/rules/core.md").includes("not a mechanical step"), "English core rules should reject mechanical L1 task lists");
   assert(read(cwd, "ai/template/rules/core.md").includes("expand scope, permission, commands, network access, or acceptance"), "English core rules should stop continuous execution before boundary expansion");
   assert(read(cwd, "ai/project/task.md").includes("execution_policy:"), "English task template should include execution policy");
   assert(read(cwd, "ai/project/task.md").includes("readiness:"), "English task template should include readiness state");
   assert(read(cwd, "ai/project/task.md").includes("activation_rule: \"auto_enable_when_l1_count_gte_2\""), "English task template should define automatic activation rule");
+  assert(read(cwd, "ai/project/task.md").includes("l1_granularity: \"independently_acceptable_vertical_slice\""), "English task template should define L1 granularity");
+  assert(read(cwd, "ai/project/task.md").includes("write_back_policy: \"l1_start_done_red_blocked_scope_change_final\""), "English task template should define task tree write-back policy");
   assert(read(cwd, "ai/project/task.md").includes("risk_gate:"), "English task template should define risk gate");
   assert(read(cwd, "ai/project/task.md").includes("status: \"pending | running | done | blocked\""), "English task template should define task tree node status");
   assert(read(cwd, "ai/project/task.md").includes("progress_unit: \"vertical_slice\""), "English task template should define continuous progress unit");
@@ -182,6 +216,8 @@ function testEnglishInitUpdateDoctor() {
   assert(read(cwd, "ai/template/prompt.md").includes("instead of bootstrapping again"), "English execution prompt should reconcile inbox material when project context already exists");
   assert(read(cwd, "ai/template/prompt.md").includes("Reconcile the new material in ai/project/inbox/"), "English execution prompt should route natural reconcile entry");
   assert(read(cwd, "ai/template/prompt.md").includes("Continue this project"), "English execution prompt should route natural continue entry");
+  assert(read(cwd, "ai/template/prompt.md").includes("do not execute while the\n   task is still a draft"), "English execution prompt should stop after drafting a task");
+  assert(read(cwd, "ai/template/prompt.md").includes("User-Visible Output"), "English execution prompt should reference user-visible output rules");
   assert(read(cwd, "ai/template/prompt.md").includes("strategy_update"), "English execution prompt should route strategy updates");
   assert(exists(cwd, "ai/project/refs/final-shape.md"), "English init should create project North Star");
   assert(exists(cwd, "ai/project/refs/module-map.md"), "English init should create module map");
@@ -215,6 +251,7 @@ function testEnglishInitUpdateDoctor() {
   const doctorOutput = run(["doctor"], cwd);
   assert(doctorOutput.includes("Template language: en"), "doctor should show installed English language");
   assert(doctorOutput.includes("ai/project/result.json JSON"), "English doctor should validate result JSON");
+  assert(doctorOutput.includes("ai/project/result.json schema"), "English doctor should validate result schema");
   assert(doctorOutput.includes("ai/project/task.md front matter"), "English doctor should validate task front matter");
   assert(doctorOutput.includes("[OK] Ready to run"), "doctor should use installed English language");
   const reconcileOutput = run(["reconcile"], cwd);
@@ -245,6 +282,60 @@ function testDoctorFailureAndWarning() {
   const invalidJsonOutput = run(["doctor"], invalidJsonCwd, 1);
   assert(invalidJsonOutput.includes("JSON 无效"), "doctor should fail invalid result JSON");
 
+  const invalidResultSchemaCwd = createTempProject("agent-execution-template-invalid-result-schema");
+  run(["init"], invalidResultSchemaCwd);
+  write(invalidResultSchemaCwd, "ai/project/result.json", JSON.stringify({
+    protocol_version: "0.8",
+    status: "success",
+    scope_followed: true,
+    files_read: [],
+    refs_read: [],
+    files_changed: [],
+    commands_run: [],
+    verification: {
+      level: "none",
+      passed: false,
+      evidence: []
+    },
+    assumptions: [],
+    issues: [],
+    next: [],
+    runtime_update: {
+      required: false,
+      changes: [],
+      reason: ""
+    }
+  }, null, 2));
+  const invalidResultSchemaOutput = run(["doctor"], invalidResultSchemaCwd, 1);
+  assert(invalidResultSchemaOutput.includes("不符合协议 schema"), "doctor should fail result schema violations");
+  assert(invalidResultSchemaOutput.includes("$.verification.passed must be true"), "doctor should enforce success verification");
+
+  const invalidMetricsSchemaCwd = createTempProject("agent-execution-template-invalid-metrics-schema");
+  run(["init"], invalidMetricsSchemaCwd);
+  write(invalidMetricsSchemaCwd, "ai/project/metrics.json", JSON.stringify({
+    protocol_version: "0.8",
+    task_id: "",
+    task_type: "",
+    model: "",
+    model_tier: "cheap",
+    escalated: true,
+    escalation_reason: "",
+    model_policy_followed: true,
+    escalation_trigger_hit: "",
+    strong_model_role: "",
+    input_tokens_estimated: 0,
+    output_tokens_estimated: 0,
+    duration_minutes: 0,
+    success: false,
+    human_fix_required: false,
+    failure_reason: "",
+    reuse_potential: "low",
+    notes: []
+  }, null, 2));
+  const invalidMetricsSchemaOutput = run(["doctor"], invalidMetricsSchemaCwd, 1);
+  assert(invalidMetricsSchemaOutput.includes("不符合协议 schema"), "doctor should fail metrics schema violations");
+  assert(invalidMetricsSchemaOutput.includes("$.escalation_reason must have length >= 1"), "doctor should enforce escalated metrics details");
+
   const taskWarnCwd = createTempProject("agent-execution-template-task-frontmatter");
   run(["init"], taskWarnCwd);
   write(taskWarnCwd, "ai/project/task.md", "# Task only\n");