@wnlen/agent-execution-template 0.8.21 → 0.8.23

package/README.md

@@ -181,6 +181,12 @@ acceptable vertical slice, not a mechanical step checklist:
 - [ ] L1-3 Export entrypoint Yellow
 ```
 
+Simple tasks are not buried under a full process form. A single-L1, Green,
+low-risk task uses a compact task contract with only the goal, scope,
+acceptance, permissions, verification commands, and minimal `task_tree`.
+Multi-L1, Yellow/Red, cross-module, continuously executed, or highly uncertain
+tasks use an expanded task contract.
+
 Because there are two or more L1 tasks, the protocol automatically uses bounded
 continuous execution. Before each L1, the AI plans naturally derived L2/L3 work.
 After completing an L1, it checks and strikes the item. `task_tree` is written

package/README.zh-CN.md

@@ -188,6 +188,10 @@ AI 会在执行前先拆 L1 任务。L1 必须是可独立验收的垂直切片
 - [ ] L1-3 导出入口 Yellow
 ```
 
+简单任务不会被完整流程表单淹没。单 L1、Green、低风险任务使用 compact task
+contract，只保留目标、范围、验收、权限、验证命令和最小 `task_tree`。多 L1、
+Yellow/Red、跨模块、连续执行或高不确定任务才使用 expanded task contract。
+
 因为 L1 有两个以上，协议会自动使用边界内连续执行。执行每个 L1 前，AI 再规划
 自然衍生的 L2/L3；完成一个 L1 后，在清单中打勾并划掉。`task_tree` 只在
 L1 开始/完成、Red/blocked、范围变化或最终收尾时写回，避免为微小步骤反复改文件。

package/bin/agent-execution-template.js

@@ -52,11 +52,7 @@ const TASK_HEALTH_PATTERNS = [
   /^readiness:\s*/m,
   /^execution_policy:/m,
   /^\s+mode:\s*/m,
-  /^\s+activation_rule:\s*/m,
   /^\s+task_tree:/m,
-  /^\s+risk_gate:/m,
-  /^\s+evidence_required:\s*/m,
-  /^model_policy:/m,
   /^refs:/m,
   /^permission:/m
 ];
@@ -77,33 +73,31 @@ const TEXT = {
 `,
     unknown: "未知",
     sourceMissing: "找不到模板来源",
-    ready: "Agent Execution Template 协议已安装。项目上下文尚未初始化。",
-    initGuide: `[下一步：让 AI 初始化项目上下文]
-已安装根目录 AI 兼容入口: AGENTS.md / CLAUDE.md
-
-1. 无额外资料
-   对 AI 说: 开始初始化这个项目
-2. 有已确定资料
-   先放到: ai/project/inbox/
-   对 AI 说: 开始初始化这个项目，并吸收 ai/project/inbox/ 里的资料
-
-[后续]
-1. 继续推进
-   对 AI 说: 继续推进这个项目
-2. 吸收新资料
-   先放到: ai/project/inbox/
-   对 AI 说: 整合 ai/project/inbox/ 里的新资料
-3. 优化上下文
-   运行命令: npx -y @wnlen/agent-execution-template refresh
-4. 评估方向
-   先放到: ai/project/inbox/ideas/
-   对 AI 说: 把 ai/project/inbox/ideas/ 里的新灵感生成方向修订提案
-5. 查看下一步
-   运行命令: npx -y @wnlen/agent-execution-template next
-
-[区分标准]
-  资料 = 已确定的事实、文档、流程、接口、业务规则
-  方向 = 还没决定的新想法、产品策略、架构调整、路线变化`,
+    ready: "Agent Execution Template 已安装。",
+    initGuide: `你现在可以这样用:
+
+1. 第一次整理项目上下文
+   【发给 AI】
+
+     开始初始化这个项目
+
+2. 已有 README、PRD、架构文档或业务规则
+   先放到 ai/project/inbox/
+   【发给 AI】
+
+     开始初始化这个项目，并吸收 ai/project/inbox/ 里的资料
+
+3. 后续有新资料要合并
+   放到 ai/project/inbox/
+   【发给 AI】
+
+     整合 ai/project/inbox/ 里的新资料
+
+4. 有还没确定的新想法、产品方向或架构调整
+   放到 ai/project/inbox/ideas/
+   【发给 AI】
+
+     把 ai/project/inbox/ideas/ 里的新灵感生成方向修订提案`,
     start: "开始:",
     startPrompt: "开始初始化这个项目",
     then: "然后:",
@@ -112,8 +106,8 @@ const TEXT = {
     confirmTask: "需要吸收新资料时，先放入 ai/project/inbox/，然后说:",
     executePrompt: "整合 ai/project/inbox/ 里的新资料",
     strategyHint: "需要修订方向时，先放入 ai/project/inbox/ideas/，然后生成 strategy_update 提案。",
-    files: "文件",
-    check: "检查",
+    files: "文件已就绪",
+    check: "检查安装",
     details: "详情:",
     refreshTitle: "Agent Execution Template 项目上下文重整",
     improveContextTitle: "Agent Execution Template 上下文总结优化",
@@ -191,33 +185,31 @@ Usage:
 `,
     unknown: "unknown",
     sourceMissing: "Template source not found",
-    ready: "Agent Execution Template protocol installed. Project context is not initialized yet.",
-    initGuide: `[Next: ask the AI to initialize project context]
-Installed root AI compatibility entrypoints: AGENTS.md / CLAUDE.md
-
-1. Without extra material
-   Tell the AI: Start initializing this project
-2. With confirmed material
-   Put it in: ai/project/inbox/
-   Tell the AI: Start initializing this project and absorb the material in ai/project/inbox/
-
-[Follow-up]
-1. Continue work
-   Tell the AI: Continue this project
-2. Absorb new material
-   Put it in: ai/project/inbox/
-   Tell the AI: Reconcile the new material in ai/project/inbox/
-3. Improve context
-   Run: npx -y @wnlen/agent-execution-template refresh
-4. Evaluate direction
-   Put it in: ai/project/inbox/ideas/
-   Tell the AI: Generate a direction amendment proposal from ai/project/inbox/ideas/
-5. Show next step
-   Run: npx -y @wnlen/agent-execution-template next
-
-[Rule of thumb]
-  Material = confirmed facts, docs, workflows, APIs, or business rules
-  Direction = undecided ideas, product strategy, architecture changes, or roadmap changes`,
+    ready: "Agent Execution Template installed.",
+    initGuide: `You can use it like this:
+
+1. Set up project context for the first time
+   [Send to AI]
+
+     Start initializing this project
+
+2. You already have a README, PRD, architecture doc, or business rules
+   Put them in ai/project/inbox/
+   [Send to AI]
+
+     Start initializing this project and absorb the material in ai/project/inbox/
+
+3. Later, you have new material to merge
+   Put it in ai/project/inbox/
+   [Send to AI]
+
+     Reconcile the new material in ai/project/inbox/
+
+4. You have an undecided idea, product direction, or architecture change
+   Put it in ai/project/inbox/ideas/
+   [Send to AI]
+
+     Generate a direction amendment proposal from ai/project/inbox/ideas/`,
     start: "Start:",
     startPrompt: "Start initializing this project",
     then: "Then:",
@@ -226,8 +218,8 @@ Installed root AI compatibility entrypoints: AGENTS.md / CLAUDE.md
     confirmTask: "When you need to absorb new material, put it in ai/project/inbox/, then say:",
     executePrompt: "Reconcile the new material in ai/project/inbox/",
     strategyHint: "When direction changes, put ideas in ai/project/inbox/ideas/ and produce a strategy_update proposal.",
-    files: "Files",
-    check: "Check",
+    files: "Files ready",
+    check: "Check install",
     details: "Details:",
     refreshTitle: "Agent Execution Template project context refresh",
     improveContextTitle: "Agent Execution Template project context improvement",
@@ -604,17 +596,16 @@ function init({ lang = DEFAULT_LANG, verbose = false, quiet = false, manageEntry
   }
 
   if (!quiet) {
-    const sourceNotice = isSourceCheckout() ? `${text.sourceCheckoutNotice}\n\n` : "";
+    const sourceNotice = isSourceCheckout() ? `\n${text.sourceCheckoutNotice}` : "";
     console.log(`${text.ready}
 
-${text.initGuide}
+${text.initGuide}${sourceNotice}
 
-${sourceNotice}
-${text.files}: ${summarizeChanges(changes, lang)}
 ${text.check}: ${commandHint("doctor")}
 `);
 
     if (verbose) {
+      console.log(`${text.files}: ${summarizeChanges(changes, lang)}`);
       printChanges(text.details, changes, lang);
     }
   }

package/docs/SPEC.md

@@ -24,7 +24,7 @@ npx 安装协议 -> AI 整理项目上下文 -> 人类确认 -> AI 生成任务
 
 ```text
 Protocol: v0.8
-Package: @wnlen/agent-execution-template@0.8.21
+Package: @wnlen/agent-execution-template@0.8.23
 中文安装: npx -y @wnlen/agent-execution-template init
 英文安装: npx -y @wnlen/agent-execution-template init --lang en
 ```
@@ -420,7 +420,7 @@ npx -y @wnlen/agent-execution-template doctor
 ```text
 Agent Execution Template 检查
 
-模板版本: 0.8.21
+模板版本: 0.8.23
 模板语言: zh
 
 [通过] ai/template/LANG
@@ -697,6 +697,16 @@ ai/project/task.md.execution_policy
 ai/template/execution-policy.md
 ```
 
+`ai/project/task.md` 支持两种契约形态：
+
+- compact task contract：用于单 L1、Green、低风险任务，只写目标、范围、验收、权限、
+  验证命令和最小 `execution_policy.task_tree`。
+- expanded task contract：用于多 L1、Yellow/Red、跨模块、连续执行、高不确定或高风险任务，
+  可按需展开 checkpoint、模型策略、风险门和更完整的任务树字段。
+
+默认优先 compact。完整默认策略保存在 `ai/template/execution-policy.md`，简单任务不应把
+`checkpoint_budget`、`model_policy` 等内部控制字段机械复制进 `task.md`。
+
 默认模式是 `auto`。AI 每次执行前先做任务分解和风险判断，再决定使用
 `normal` 还是 `bounded_continuous`，不依赖用户口令。
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wnlen/agent-execution-template",
-  "version": "0.8.21",
+  "version": "0.8.23",
   "description": "Low-friction AI execution protocol template for coding agents.",
   "bin": {
     "agent-execution-template": "bin/agent-execution-template.js"

package/template/en/ai/project/task.md

@@ -7,61 +7,11 @@ readiness: "draft_for_confirmation | ready_to_execute | blocked"
 depends_on_previous_result: false
 execution_policy:
   mode: "auto | normal | bounded_continuous"
-  activation_rule: "auto_enable_when_l1_count_gte_2"
-  max_depth: 3
-  allow_depth_4_when_needed: true
-  progress_unit: "vertical_slice"
-  l1_granularity: "independently_acceptable_vertical_slice"
-  write_back_policy: "l1_start_done_red_blocked_scope_change_final"
   task_tree:
     - id: "L1-1"
       title: ""
       risk: "Green | Yellow | Red"
       status: "pending | running | done | blocked"
-      scope:
-        allowed: []
-        denied: []
-      acceptance: []
-      evidence: []
-      children: []
-  checkpoint_budget:
-    l1: 0
-    l2: 0
-    l3: 0
-    l4: 0
-  checkpoint_triggers:
-    - before_crossing_boundary
-    - after_vertical_slice
-    - before_final_review
-  auto_continue:
-    green: true
-    yellow: "low_risk_only"
-    red: false
-  risk_gate:
-    green: "continue"
-    yellow: "continue_with_local_fix"
-    red: "stop_for_human"
-  evidence_required: true
-model_policy:
-  default_tier: "cheap"
-  allowed_tiers:
-    - cheap
-    - standard
-    - strong
-  escalation_allowed: true
-  escalation_triggers:
-    - ambiguous_goal
-    - ambiguous_acceptance
-    - high_risk_change
-    - architecture_boundary
-    - repeated_failure
-    - verification_dispute
-  strong_model_roles:
-    - planning
-    - risk_judgment
-    - architecture_review
-    - failure_review
-    - acceptance_judgment
 refs:
   required: []
   optional: []
@@ -92,6 +42,13 @@ If this run creates or rewrites the task contract, keep
 `readiness = draft_for_confirmation` by default and stop at the handoff. Enter
 execution only when an existing task is explicitly `ready_to_execute`.
 
+Default to a compact task contract. A single-L1, Green, low-risk task should
+write only the goal, scope, acceptance, permissions, verification commands, and
+minimal `execution_policy.task_tree`. Multi-L1, Yellow/Red, cross-module,
+continuously executed, or highly uncertain tasks may expand checkpoint, model
+policy, risk gate, and fuller task-tree fields as needed. The complete default
+rules live in `ai/template/execution-policy.md`.
+
 ## Goal
 
 Describe the exact goal of this task. If generated from a short human request,
@@ -135,7 +92,8 @@ The task is complete when:
 Default to `auto`. The AI decides during pre-execution planning whether to use
 continuous execution; it does not wait for a human keyword. If planning finds
 fewer than 2 L1 tasks, use `normal`; if it finds 2 or more L1 tasks, use
-`bounded_continuous` automatically.
+`bounded_continuous` automatically. Each L1 must be an independently acceptable
+vertical slice.
 
 `bounded_continuous` means bounded continuous execution:
 
@@ -167,8 +125,10 @@ fewer than 2 L1 tasks, use `normal`; if it finds 2 or more L1 tasks, use
   architecture direction, or acceptance.
 - `progress_unit` defaults to `vertical_slice`: each work loop should produce
   a reviewable increment.
-- `checkpoint_budget` is the maximum checkpoint budget, not a required count;
-  do not report just to spend the budget.
+- Compact tasks should not expand internal control fields such as
+  `checkpoint_budget` or `model_policy`.
+- Expanded tasks may add checkpoint budgets, model policy, risk gates, and
+  fuller node fields as needed.
 - Emit checkpoints only when risk changes from Green to Yellow/Red, scope or
   permission is about to expand, an L1 vertical slice is complete, verification
   failed but execution is about to continue, or final wrap-up is about to start.

package/template/en/ai/template/VERSION

@@ -1 +1 @@
-0.8.21
+0.8.23

package/template/en/ai/template/execution-policy.md

@@ -3,6 +3,22 @@
 Do not summarize this file.
 During task execution, use this file to choose `normal` or `bounded_continuous`.
 
+## Task Contract Shapes
+
+`ai/project/task.md` has two valid shapes:
+
+- Compact task contract: for single-L1, Green, low-risk tasks. Write only the
+  goal, scope, acceptance, permissions, verification commands, and minimal
+  `execution_policy.task_tree`; do not expand internal control fields such as
+  `checkpoint_budget` or `model_policy`.
+- Expanded task contract: for multi-L1, Yellow/Red, cross-module, continuously
+  executed, highly uncertain, or high-risk tasks. Expand checkpoint, model
+  policy, risk gate, and fuller task-tree fields only when needed.
+
+Prefer compact by default. Upgrade to expanded only when complexity, risk, or
+auditability makes the extra structure worthwhile. The complete execution rules
+live in this file and do not need to be repeated in every task draft.
+
 ## Default Policy
 
 The default execution policy is `auto`: before each execution, the AI first
@@ -25,6 +41,8 @@ Pre-execution planning must:
 - Stop for human confirmation first if any L1 is Red; Green and Yellow do not
   block startup.
 - Write the task tree to `execution_policy.task_tree` in `ai/project/task.md`.
+  Simple tasks should write only minimal L1 nodes; complex tasks can add
+  `scope`, `acceptance`, `evidence`, `children`, and related fields.
 
 ## Task Tree
 
@@ -48,7 +66,16 @@ Execute the task tree in L1 -> L2 -> L3 order.
 - During execution, use `pending`, `running`, `done`, or `blocked` for node
   status.
 
-Recommended node shape:
+Minimal node shape:
+
+```yaml
+id: "L1-1"
+title: ""
+risk: "Green | Yellow | Red"
+status: "pending | running | done | blocked"
+```
+
+Recommended node shape for complex tasks:
 
 ```yaml
 id: "L1-1"

package/template/en/ai/template/prompt.md

@@ -67,11 +67,17 @@ In Task Draft Mode:
 2. Infer goal, scope, acceptance, permissions, verification method, and initial
    risk from the user's current goal, project context, and repository facts; do
    not require the human to provide each field upfront.
-3. Draft `ai/project/task.md` and set `execution_policy.mode` to `auto`.
+3. Draft `ai/project/task.md`. For a single-L1, Green, low-risk task, default to
+   a compact task contract: write only the goal, scope, acceptance, permissions,
+   verification commands, and minimal `execution_policy.task_tree`. Use an
+   expanded task contract only for multi-L1, Yellow/Red, cross-module,
+   continuously executed, or highly uncertain tasks.
 4. Before execution, list the L1 checklist, mark each L1 Green / Yellow / Red,
    and write it to `execution_policy.task_tree`. Use `normal` if there are
    fewer than 2 L1 tasks; automatically use `bounded_continuous` if there are 2
-   or more L1 tasks.
+   or more L1 tasks. The complete default rules live in
+   `ai/template/execution-policy.md`; do not mechanically copy internal control
+   fields such as `checkpoint_budget` or `model_policy` into simple task drafts.
 5. If this run creates or rewrites `ai/project/task.md`, set `readiness` to
    `draft_for_confirmation` and stop at the handoff; do not execute while the
    task is still a draft.

package/template/en/ai/template/protocol.md

@@ -67,6 +67,13 @@ rewrites the task contract, stop at the confirmation handoff. Only Red stops for
 human confirmation, and Yellow only permits local low-risk correction inside the
 current L1/L2.
 
+Task contracts are layered by complexity. A single-L1, Green, low-risk task uses
+a compact task contract with only the goal, scope, acceptance, permissions,
+verification commands, and minimal `execution_policy.task_tree`. Multi-L1,
+Yellow/Red, cross-module, continuously executed, or highly uncertain tasks use
+an expanded task contract and may include checkpoint, model policy, and fuller
+task-tree fields as needed.
+
 Task tree, risk rubric, checkpoint evidence, and `task_tree` write-back rules
 are defined in `ai/template/execution-policy.md`.
 

package/template/zh/ai/project/task.md

@@ -7,61 +7,11 @@ readiness: "draft_for_confirmation | ready_to_execute | blocked"
 depends_on_previous_result: false
 execution_policy:
   mode: "auto | normal | bounded_continuous"
-  activation_rule: "auto_enable_when_l1_count_gte_2"
-  max_depth: 3
-  allow_depth_4_when_needed: true
-  progress_unit: "vertical_slice"
-  l1_granularity: "independently_acceptable_vertical_slice"
-  write_back_policy: "l1_start_done_red_blocked_scope_change_final"
   task_tree:
     - id: "L1-1"
       title: ""
       risk: "Green | Yellow | Red"
       status: "pending | running | done | blocked"
-      scope:
-        allowed: []
-        denied: []
-      acceptance: []
-      evidence: []
-      children: []
-  checkpoint_budget:
-    l1: 0
-    l2: 0
-    l3: 0
-    l4: 0
-  checkpoint_triggers:
-    - before_crossing_boundary
-    - after_vertical_slice
-    - before_final_review
-  auto_continue:
-    green: true
-    yellow: "low_risk_only"
-    red: false
-  risk_gate:
-    green: "continue"
-    yellow: "continue_with_local_fix"
-    red: "stop_for_human"
-  evidence_required: true
-model_policy:
-  default_tier: "cheap"
-  allowed_tiers:
-    - cheap
-    - standard
-    - strong
-  escalation_allowed: true
-  escalation_triggers:
-    - ambiguous_goal
-    - ambiguous_acceptance
-    - high_risk_change
-    - architecture_boundary
-    - repeated_failure
-    - verification_dispute
-  strong_model_roles:
-    - planning
-    - risk_judgment
-    - architecture_review
-    - failure_review
-    - acceptance_judgment
 refs:
   required: []
   optional: []
@@ -86,6 +36,11 @@ permission:
 `Red`，等待确认。本轮新建或重写任务契约时，默认保持 `draft_for_confirmation` 并停下交接；
 只有既有任务为 `ready_to_execute` 时才执行。
 
+默认使用 compact task contract。单 L1、Green、低风险任务只写目标、范围、验收、
+权限、验证命令和最小 `execution_policy.task_tree`。多 L1、Yellow/Red、跨模块、
+连续执行或高不确定任务才按需展开 checkpoint、模型策略、风险门和更完整任务树字段。
+完整默认规则见 `ai/template/execution-policy.md`。
+
 ## 目标
 
 描述这个任务的准确目标。如果由简短人类请求生成，保留用户意图并明确写出假设。
@@ -124,7 +79,7 @@ permission:
 ## 执行策略
 
 默认 `auto`：AI 执行前规划并决定是否连续执行，不等用户口令。L1 < 2 用 `normal`；
-L1 >= 2 自动用 `bounded_continuous`。
+L1 >= 2 自动用 `bounded_continuous`。L1 必须是可独立验收的垂直切片。
 
 `bounded_continuous` 表示边界内连续执行：
 
@@ -143,7 +98,8 @@ L1 >= 2 自动用 `bounded_continuous`。
 - 只有 Red 停下来让人类确认；Green 自动继续，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。
 - `progress_unit` 默认为 `vertical_slice`：每轮都应产生可检查增量。
-- `checkpoint_budget` 是上限，不是必须用完；不要为消耗预算而汇报。
+- compact 任务不要展开 `checkpoint_budget`、`model_policy` 等内部控制字段。
+- expanded 任务可以按需增加 checkpoint 预算、模型策略、风险门和更完整节点字段。
 - 只有在风险从 Green 变 Yellow/Red、即将扩大范围或权限、完成 L1 垂直切片、
   验证失败后准备继续、准备最终收尾时才输出 Checkpoint。
 - 每个 Checkpoint 必须包含证据：已改文件、已运行命令、验证结果或无法验证的原因。

package/template/zh/ai/template/VERSION

@@ -1 +1 @@
-0.8.21
+0.8.23

package/template/zh/ai/template/execution-policy.md

@@ -3,6 +3,19 @@
 不要总结这个文件。
 任务执行时按本文件选择 `normal` 或 `bounded_continuous`。
 
+## 任务契约形态
+
+`ai/project/task.md` 有两种合法形态：
+
+- compact task contract：用于单 L1、Green、低风险任务。只写目标、范围、验收、
+  权限、验证命令和最小 `execution_policy.task_tree`；不要展开
+  `checkpoint_budget`、`model_policy` 等内部控制字段。
+- expanded task contract：用于多 L1、Yellow/Red、跨模块、连续执行、高不确定或
+  高风险任务。需要时可展开 checkpoint、模型策略、风险门和更完整的任务树字段。
+
+默认优先 compact。只有复杂度、风险或审计需要证明它有价值时，才升级到 expanded。
+完整执行规则由本文件承载，不需要在每个任务草稿里重复。
+
 ## 默认策略
 
 默认执行策略是 `auto`：AI 在每次执行前先做任务分解和风险判断，再决定使用
@@ -19,7 +32,8 @@
 - 如果 L1 少于 2 个，使用 `normal`。
 - 如果 L1 为 2 个或更多，自动启用 `bounded_continuous`。
 - 如果任一 L1 为 Red，先停止并让人类确认；Green 和 Yellow 不阻塞启动。
-- 将任务树写入 `ai/project/task.md` 的 `execution_policy.task_tree`。
+- 将任务树写入 `ai/project/task.md` 的 `execution_policy.task_tree`。简单任务只写最小
+  L1 节点；复杂任务再补充 scope、acceptance、evidence、children 等字段。
 
 ## 任务树
 
@@ -37,7 +51,16 @@
   出现 Red、blocked、范围变化或最终收尾时立即写回。不要为每个微小 L3 操作写回。
 - 执行中使用 `pending`、`running`、`done` 或 `blocked` 表示节点状态。
 
-推荐节点结构：
+最小节点结构：
+
+```yaml
+id: "L1-1"
+title: ""
+risk: "Green | Yellow | Red"
+status: "pending | running | done | blocked"
+```
+
+复杂任务推荐节点结构：
 
 ```yaml
 id: "L1-1"

package/template/zh/ai/template/prompt.md

@@ -45,9 +45,13 @@
 1. 读取已确认的 `ai/project/project.md` 和相关 `ai/project/refs/*.md`。
 2. 根据用户目标、项目上下文和仓库事实推断目标、范围、验收、权限、验证方式和初始风险；
    不要求用户逐项提供。
-3. 起草 `ai/project/task.md`，并将 `execution_policy.mode` 设为 `auto`。
+3. 起草 `ai/project/task.md`。单 L1、Green、低风险任务默认使用 compact task contract：
+   只写目标、范围、验收、权限、验证命令和最小 `execution_policy.task_tree`。
+   多 L1、Yellow/Red、跨模块、连续执行或高不确定任务才使用 expanded task contract。
 4. 执行前列出 L1 清单并标注 Green / Yellow / Red，写入 `execution_policy.task_tree`。
-   L1 < 2 用 `normal`；L1 >= 2 自动用 `bounded_continuous`。
+   L1 < 2 用 `normal`；L1 >= 2 自动用 `bounded_continuous`。完整默认规则由
+   `ai/template/execution-policy.md` 承载，不要把 `checkpoint_budget`、`model_policy`
+   等内部控制字段机械复制到简单任务草稿里。
 5. 本轮新建或重写 `task.md` 时，将 `readiness` 设为 `draft_for_confirmation` 并停止；
    草稿不能直接执行。
 6. 只有既有任务为 `ready_to_execute` 且无 Red 预检项，才进入执行；否则设为 `blocked`。

package/template/zh/ai/template/protocol.md

@@ -53,6 +53,11 @@ ai/project/task.md             = 当前执行契约
 L1 必须是可独立验收的垂直切片。只有既有任务 `readiness = ready_to_execute` 才能执行；
 本轮新建或重写任务契约时先停下确认。Red 停止确认，Yellow 只允许当前 L1/L2 内的局部低风险修正。
 
+任务契约默认按复杂度分层。单 L1、Green、低风险任务使用 compact task contract，只保留
+目标、范围、验收、权限、验证命令和最小 `execution_policy.task_tree`。多 L1、Yellow/Red、
+跨模块、连续执行或高不确定任务才使用 expanded task contract，按需展开 checkpoint、
+模型策略和更完整的任务树字段。
+
 任务树、风险分级、Checkpoint 证据和 `task_tree` 写回规则由
 `ai/template/execution-policy.md` 定义。
 

package/test/selftest.js

@@ -126,12 +126,12 @@ function testInitUpdateDoctor() {
   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("compact task contract"), "task template should default to compact contracts");
+  assert(read(cwd, "ai/project/task.md").includes("expanded 任务"), "task template should explain when to expand task contracts");
+  assert(!read(cwd, "ai/project/task.md").includes("activation_rule: \"auto_enable_when_l1_count_gte_2\""), "task template should not default to expanded activation metadata");
+  assert(!read(cwd, "ai/project/task.md").includes("checkpoint_budget:"), "task template should not default to checkpoint budget fields");
+  assert(!read(cwd, "ai/project/task.md").includes("model_policy:"), "task template should not default to model policy fields");
   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");
   assert(read(cwd, "ai/template/prompt.md").includes("开始初始化这个项目"), "execution prompt should route natural bootstrap entry");
   assert(read(cwd, "ai/template/prompt.md").includes("开始初始化这个项目，并吸收 ai/project/inbox/ 里的资料"), "execution prompt should route bootstrap with inbox material");
   assert(read(cwd, "ai/template/prompt.md").includes("不要重新 bootstrap"), "execution prompt should reconcile inbox material when project context already exists");
@@ -154,22 +154,33 @@ function testInitUpdateDoctor() {
   assert(read(cwd, "ai/template/rules/core.md").includes("ai/project/refs/final-shape.md"), "core rules should route direction refs");
   assert(read(cwd, "ai/project/proposals/final-shape-updates/_template.md").includes("`accepted`"), "proposal template should describe accepted status");
   const initOutput = run(["init"], cwd);
-  assert(initOutput.includes("开始初始化这个项目"), "init output should provide compact natural bootstrap prompt");
-  assert(initOutput.includes("根目录 AI 兼容入口: AGENTS.md / CLAUDE.md"), "init output should mention root AI compatibility entrypoints");
-  assert(initOutput.includes("协议已安装。项目上下文尚未初始化"), "init output should distinguish protocol install from project context bootstrap");
-  assert(initOutput.includes("[下一步：让 AI 初始化项目上下文]"), "init output should guide the AI bootstrap as the next step");
+  assert(initOutput.includes("Agent Execution Template 已安装。"), "init output should confirm installation");
+  assert(initOutput.includes("你现在可以这样用:"), "init output should introduce scenario-based usage");
+  assert(initOutput.includes("1. 第一次整理项目上下文"), "init output should cover first-time project context setup");
+  assert(initOutput.includes("【发给 AI】\n\n     开始初始化这个项目"), "init output should make the bootstrap prompt visually prominent");
+  assert(initOutput.includes("2. 已有 README、PRD、架构文档或业务规则"), "init output should cover initialization with existing material");
   assert(initOutput.includes("开始初始化这个项目，并吸收 ai/project/inbox/ 里的资料"), "init output should explain bootstrap with existing material");
-  assert(initOutput.includes("整合 ai/project/inbox/ 里的新资料"), "init output should provide compact natural reconcile prompt");
-  assert(initOutput.includes("优化上下文"), "init output should expose project context refresh in user language");
-  assert(initOutput.includes("把 ai/project/inbox/ideas/ 里的新灵感生成方向修订提案"), "init output should provide natural strategy prompt");
-  assert(initOutput.includes("agent-execution-template next"), "init output should tell users how to recover the next step");
-  assert(initOutput.includes("文件:"), "init output should summarize file changes");
+  assert(initOutput.includes("3. 后续有新资料要合并"), "init output should cover later material reconciliation");
+  assert(initOutput.includes("整合 ai/project/inbox/ 里的新资料"), "init output should show the reconcile prompt");
+  assert(initOutput.includes("4. 有还没确定的新想法、产品方向或架构调整"), "init output should cover undecided ideas");
+  assert(initOutput.includes("把 ai/project/inbox/ideas/ 里的新灵感生成方向修订提案"), "init output should show the strategy proposal prompt");
+  assert(!initOutput.includes("项目上下文尚未初始化"), "init output should not state the obvious uninitialized context");
+  assert(!initOutput.includes("忘了下一步时运行"), "init output should not show next as the default fallback");
+  assert(!initOutput.includes("根目录 AI 入口"), "init output should not mention root AI entrypoint implementation details");
+  assert(!initOutput.includes("资料路径:"), "init output should not show abstract material path categories");
+  assert(!initOutput.includes("已确定资料:"), "init output should not show abstract confirmed material path categories");
+  assert(!initOutput.includes("未决定的新想法:"), "init output should not show abstract idea path categories");
+  assert(!initOutput.includes("agent-execution-template next"), "init output should not tell users to remember the next command");
+  assert(!initOutput.includes("文件已就绪:"), "init output should hide file change summaries by default");
+  assert(initOutput.includes("检查安装:"), "init output should show install check command");
   assert(!initOutput.includes("维护者提示"), "init output should not show source checkout guidance in user projects");
   assert(!initOutput.includes("[已更新]"), "init output should hide detailed file changes by default");
   assert(!initOutput.includes("Read ai/template/bootstrap.md"), "init output should not use weak Read bootstrap command");
   assert(countOccurrences(read(cwd, "AGENTS.md"), "agent-execution-template:start") === 1, "init should not duplicate AGENTS.md managed blocks");
   assert(countOccurrences(read(cwd, "CLAUDE.md"), "agent-execution-template:start") === 1, "init should not duplicate CLAUDE.md managed blocks");
-  assert(run(["init", "--verbose"], cwd).includes("[已更新] ai/template/VERSION"), "init --verbose should show detailed file changes");
+  const verboseInitOutput = run(["init", "--verbose"], cwd);
+  assert(verboseInitOutput.includes("文件已就绪:"), "init --verbose should summarize file changes");
+  assert(verboseInitOutput.includes("[已更新] ai/template/VERSION"), "init --verbose should show detailed file changes");
   assert(countOccurrences(read(cwd, "AGENTS.md"), "agent-execution-template:start") === 1, "re-running init should keep one AGENTS.md managed block");
   assert(countOccurrences(read(cwd, "CLAUDE.md"), "agent-execution-template:start") === 1, "re-running init should keep one CLAUDE.md managed block");
   const reconcileOutput = run(["reconcile"], cwd);
@@ -248,12 +259,12 @@ function testEnglishInitUpdateDoctor() {
   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("compact task contract"), "English task template should default to compact contracts");
+  assert(read(cwd, "ai/project/task.md").includes("Expanded tasks"), "English task template should explain when to expand task contracts");
+  assert(!read(cwd, "ai/project/task.md").includes("activation_rule: \"auto_enable_when_l1_count_gte_2\""), "English task template should not default to expanded activation metadata");
+  assert(!read(cwd, "ai/project/task.md").includes("checkpoint_budget:"), "English task template should not default to checkpoint budget fields");
+  assert(!read(cwd, "ai/project/task.md").includes("model_policy:"), "English task template should not default to model policy fields");
   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");
   assert(read(cwd, "ai/template/prompt.md").includes("Start initializing this project and absorb the material in ai/project/inbox/"), "English execution prompt should route bootstrap with inbox material");
   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");
@@ -273,16 +284,25 @@ function testEnglishInitUpdateDoctor() {
   assert(read(cwd, "ai/template/reconcile.md").includes("ai/project/inbox/processed/raw/file.md"), "English reconcile prompt should archive absorbed raw inbox material");
   assert(read(cwd, "ai/template/reconcile.md").includes("Unabsorbed material"), "English reconcile handoff should audit unabsorbed material");
   assert(read(cwd, "ai/template/reconcile.md").includes("Conflict handling"), "English reconcile handoff should audit conflict handling");
-  assert(initOutput.includes("Start initializing this project"), "English init output should provide English bootstrap prompt");
-  assert(initOutput.includes("root AI compatibility entrypoints: AGENTS.md / CLAUDE.md"), "English init output should mention root AI compatibility entrypoints");
-  assert(initOutput.includes("protocol installed. Project context is not initialized yet"), "English init output should distinguish protocol install from project context bootstrap");
-  assert(initOutput.includes("[Next: ask the AI to initialize project context]"), "English init output should guide the AI bootstrap as the next step");
+  assert(initOutput.includes("Agent Execution Template installed."), "English init output should confirm installation");
+  assert(initOutput.includes("You can use it like this:"), "English init output should introduce scenario-based usage");
+  assert(initOutput.includes("1. Set up project context for the first time"), "English init output should cover first-time project context setup");
+  assert(initOutput.includes("[Send to AI]\n\n     Start initializing this project"), "English init output should make the bootstrap prompt visually prominent");
+  assert(initOutput.includes("2. You already have a README, PRD, architecture doc, or business rules"), "English init output should cover initialization with existing material");
   assert(initOutput.includes("Start initializing this project and absorb the material in ai/project/inbox/"), "English init output should explain bootstrap with existing material");
-  assert(initOutput.includes("Reconcile the new material in ai/project/inbox/"), "English init output should provide English reconcile prompt");
-  assert(initOutput.includes("Improve context"), "English init output should expose context refresh in user language");
-  assert(initOutput.includes("Generate a direction amendment proposal from ai/project/inbox/ideas/"), "English init output should provide natural strategy prompt");
-  assert(initOutput.includes("agent-execution-template next"), "English init output should tell users how to recover the next step");
-  assert(initOutput.includes("Files:"), "English init output should summarize file changes");
+  assert(initOutput.includes("3. Later, you have new material to merge"), "English init output should cover later material reconciliation");
+  assert(initOutput.includes("Reconcile the new material in ai/project/inbox/"), "English init output should show the reconcile prompt");
+  assert(initOutput.includes("4. You have an undecided idea, product direction, or architecture change"), "English init output should cover undecided ideas");
+  assert(initOutput.includes("Generate a direction amendment proposal from ai/project/inbox/ideas/"), "English init output should show the strategy proposal prompt");
+  assert(!initOutput.includes("Project context is not initialized yet"), "English init output should not state the obvious uninitialized context");
+  assert(!initOutput.includes("If you forget the next step"), "English init output should not show next as the default fallback");
+  assert(!initOutput.includes("Root AI entrypoints"), "English init output should not mention root AI entrypoint implementation details");
+  assert(!initOutput.includes("Material paths:"), "English init output should not show abstract material path categories");
+  assert(!initOutput.includes("Confirmed material:"), "English init output should not show abstract confirmed material path categories");
+  assert(!initOutput.includes("Undecided ideas:"), "English init output should not show abstract idea path categories");
+  assert(!initOutput.includes("agent-execution-template next"), "English init output should not tell users to remember the next command");
+  assert(!initOutput.includes("Files ready:"), "English init output should hide file change summaries by default");
+  assert(initOutput.includes("Check install:"), "English init output should show install check command");
   assert(!initOutput.includes("Maintainer note"), "English init output should not show source checkout guidance in user projects");
   assert(!initOutput.includes("[UPDATED]"), "English init output should hide detailed file changes by default");
   assert(run(["init", "--lang=en", "--verbose"], cwd).includes("[UPDATED] ai/template/VERSION"), "English init --verbose should show detailed file changes");