@wnlen/agent-execution-template 0.8.14 → 0.8.15

package/docs/SPEC.md

@@ -22,7 +22,7 @@ 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@0.8.14
+Package: @wnlen/agent-execution-template@0.8.15
 中文安装: npx -y @wnlen/agent-execution-template init
 英文安装: npx -y @wnlen/agent-execution-template init --lang en
 ```
@@ -390,7 +390,7 @@ npx -y @wnlen/agent-execution-template doctor
 ```text
 Agent Execution Template 检查
 
-模板版本: 0.8.14
+模板版本: 0.8.15
 模板语言: zh
 
 [通过] ai/template/LANG

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wnlen/agent-execution-template",
-  "version": "0.8.14",
+  "version": "0.8.15",
   "description": "Low-friction AI execution protocol template for coding agents.",
   "bin": {
     "agent-execution-template": "bin/agent-execution-template.js"

package/template/en/ai/template/VERSION

@@ -1 +1 @@
-0.8.14
+0.8.15

package/template/en/ai/template/bootstrap.md

@@ -89,6 +89,14 @@ or acceptance.
 ## Output Rules
 
 - Mark unknown facts as `Unknown`; do not present guesses as facts.
+- If this bootstrap run absorbs `ai/project/inbox/*.md` or
+  `ai/project/inbox/raw/*.md`, move absorbed material to
+  `ai/project/inbox/processed/` after writing context. Preserve relative paths:
+  move `ai/project/inbox/raw/file.md` to
+  `ai/project/inbox/processed/raw/file.md`. If a filename conflicts, keep the
+  original filename and add a date or sequence number. Do not move
+  `ai/project/inbox/ideas/**`.
+- Leave unabsorbed material in place and explain why in the final response.
 - Initialization content in `final-shape.md`, `module-map.md`, and
   `roadmap.md` must cite evidence sources. If evidence is insufficient, keep
   placeholders or write `Unknown`; do not invent a vision.
@@ -144,6 +152,15 @@ Written:
 - ai/project/refs/constraints.md
 - ai/project/refs/decisions.md
 
+Absorbed material:
+- file; write "none" if there is none
+
+Unabsorbed material:
+- file: reason; write "none" if there is none
+
+Conflict handling:
+- conflict or tradeoff; write "none" if there is none
+
 Reply with:
 - Confirm, draft task 1
 - Confirm, but do: <one-sentence task>
@@ -184,6 +201,15 @@ Written:
 - ai/project/refs/decisions.md
 - ai/project/task.md
 
+Absorbed material:
+- file; write "none" if there is none
+
+Unabsorbed material:
+- file: reason; write "none" if there is none
+
+Conflict handling:
+- conflict or tradeoff; write "none" if there is none
+
 Reply with:
 - Confirm, execute
 - Correction: <what to change>

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

@@ -23,9 +23,12 @@ Then choose the mode:
   `proposed`, update it to `accepted` based on that explicit confirmation.
 - If the user says "Start initializing this project and absorb the material in ai/project/inbox/",
   or asks to initialize while also absorbing material from
-  `ai/project/inbox/`, follow `ai/template/bootstrap.md` and treat
-  `ai/project/inbox/*.md` and `ai/project/inbox/raw/*.md` as part of the
-  bootstrap input for this run; stop after project-context confirmation.
+  `ai/project/inbox/`, inspect `ai/project/project.md` first. If it already
+  exists and is not empty, placeholder-only, or clearly incomplete, follow
+  `ai/template/reconcile.md` instead of bootstrapping again. If it is empty,
+  placeholder-only, or clearly incomplete, follow `ai/template/bootstrap.md`
+  and treat `ai/project/inbox/*.md` and `ai/project/inbox/raw/*.md` as part of
+  the bootstrap input for this run; stop after project-context confirmation.
 - If the user says "Reconcile the new material in ai/project/inbox/", asks to
   reconcile, merge, absorb, update context, handle new material, mentions
   `reconcile` or `ai/project/inbox/`, or if `ai/project/inbox/` contains

package/template/en/ai/template/reconcile.md

@@ -98,8 +98,10 @@ Do not modify these unless the human explicitly asks:
 - `ai/project/metrics.json`
 - `ai/project/archive/**`
 
-After applying reconciliation, move the processed `ai/project/inbox/*.md`
-material into `ai/project/inbox/processed/`. If a filename conflicts, keep the
+After applying reconciliation, move the processed `ai/project/inbox/*.md` and
+`ai/project/inbox/raw/*.md` material into `ai/project/inbox/processed/`.
+Preserve relative paths: move `ai/project/inbox/raw/file.md` to
+`ai/project/inbox/processed/raw/file.md`. If a filename conflicts, keep the
 original name and add a date or sequence number. Do not move
 `ai/project/inbox/ideas/**`; direction ideas should continue through
 `strategy_update`.
@@ -117,11 +119,17 @@ Updated:
 Archived material:
 - ai/project/inbox/processed/file.md
 
+Unabsorbed material:
+- file: reason; write "none" if there is none
+
 Key changes:
 - Added:
 - Corrected:
 - Deprecated:
 
+Conflict handling:
+- conflict or tradeoff; write "none" if there is none
+
 Still uncertain:
 - Up to 3 items; write "none" if there are none
 

package/template/zh/ai/template/VERSION

@@ -1 +1 @@
-0.8.14
+0.8.15

package/template/zh/ai/template/bootstrap.md

@@ -80,6 +80,11 @@
 ## 输出规则
 
 - 未知事实标记为 `Unknown`；不要把猜测当成事实。
+- 如果本次引导吸收了 `ai/project/inbox/*.md` 或 `ai/project/inbox/raw/*.md`，
+  写入上下文后必须把已吸收资料移动到 `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/**`。
+- 未吸收资料必须留在原位置，并在最终回复中说明原因。
 - 对 `final-shape.md`、`module-map.md`、`roadmap.md` 的初始化内容必须标明证据来源；
   如果证据不足，保持占位或写 `Unknown`，不要编造愿景。
 - 有帮助时，在相关文件中记录证据来源。
@@ -131,6 +136,15 @@
 - ai/project/refs/constraints.md
 - ai/project/refs/decisions.md
 
+已吸收资料：
+- file；没有则写“无”
+
+未吸收资料：
+- file：原因；没有则写“无”
+
+冲突处理：
+- 冲突或取舍；没有则写“无”
+
 请直接回复：
 - 确认，按建议 1 起草任务
 - 确认，但改做：<一句话任务>
@@ -171,6 +185,15 @@
 - ai/project/refs/decisions.md
 - ai/project/task.md
 
+已吸收资料：
+- file；没有则写“无”
+
+未吸收资料：
+- file：原因；没有则写“无”
+
+冲突处理：
+- 冲突或取舍；没有则写“无”
+
 请直接回复：
 - 确认，执行
 - 修正：<你要改的地方>

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

@@ -20,8 +20,10 @@
   `apply_strategy_update` 起草或执行应用任务；如果 proposal 仍为
   `proposed`，先根据这次明确确认更新为 `accepted`。
 - 如果用户说“开始初始化这个项目，并吸收 ai/project/inbox/ 里的资料”，
-  或要求初始化时一并吸收 `ai/project/inbox/` 里的资料，执行
-  `ai/template/bootstrap.md`，并把 `ai/project/inbox/*.md` 与
+  或要求初始化时一并吸收 `ai/project/inbox/` 里的资料，先检查
+  `ai/project/project.md`。如果它已经存在且不是空文件、占位内容或明显不完整，
+  执行 `ai/template/reconcile.md`，不要重新 bootstrap；如果它为空、只有占位内容或
+  明显不完整，执行 `ai/template/bootstrap.md`，并把 `ai/project/inbox/*.md` 与
   `ai/project/inbox/raw/*.md` 视为本次引导输入的一部分；在项目上下文确认后停止。
 - 如果用户说“整合 ai/project/inbox/ 里的新资料”，要求整合/合并/吸收/
   更新上下文/处理新资料，提到 `reconcile` 或 `ai/project/inbox/`，

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

@@ -94,9 +94,11 @@
 - `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` 资料移动到
-`ai/project/inbox/processed/`。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`。
+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`。
 
 ## 最终交接
 
@@ -111,11 +113,17 @@
 已归档资料：
 - ai/project/inbox/processed/file.md
 
+未吸收资料：
+- file：原因；没有则写“无”
+
 关键变化：
 - 新增：
 - 修正：
 - 废弃：
 
+冲突处理：
+- 冲突或取舍；没有则写“无”
+
 仍不确定：
 - 最多 3 条；没有则写“无”
 

package/test/selftest.js

@@ -72,14 +72,22 @@ function testInitUpdateDoctor() {
   assert(read(cwd, "ai/template/bootstrap.md").includes("我建议下一步做"), "bootstrap prompt should recommend next steps");
   assert(read(cwd, "ai/template/bootstrap.md").includes("不要让人类主动去文件管理器里寻找问题"), "bootstrap prompt should not offload file inspection to humans");
   assert(read(cwd, "ai/template/bootstrap.md").includes("任务草稿摘要"), "bootstrap prompt should support task draft summary when a goal is provided");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("ai/project/inbox/processed/raw/file.md"), "bootstrap prompt should archive absorbed raw inbox material");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("已吸收资料"), "bootstrap handoff should audit absorbed material");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("未吸收资料"), "bootstrap handoff should audit unabsorbed material");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("冲突处理"), "bootstrap handoff should audit conflict handling");
   assert(read(cwd, "ai/template/prompt.md").includes("任务草稿交接"), "execution prompt should include task handoff");
   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");
   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("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("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");
   assert(read(cwd, "ai/template/protocol.md").includes("引导读取范围"), "init should install bootstrap protocol");
   assert(read(cwd, "ai/template/protocol.md").includes("推荐下一步最值得做的任务"), "protocol should require recommended next steps");
   assert(read(cwd, "ai/template/protocol.md").includes("上下文整合模式"), "protocol should include context reconcile mode");
@@ -129,8 +137,13 @@ function testEnglishInitUpdateDoctor() {
   assert(read(cwd, "ai/template/bootstrap.md").includes("ai/project/refs/roadmap.md"), "English bootstrap prompt should initialize roadmap");
   assert(read(cwd, "ai/template/bootstrap.md").includes("Recommended next step"), "English bootstrap prompt should recommend next steps");
   assert(read(cwd, "ai/template/bootstrap.md").includes("Do not make the human hunt through files"), "English bootstrap prompt should not offload file inspection to humans");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("ai/project/inbox/processed/raw/file.md"), "English bootstrap prompt should archive absorbed raw inbox material");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("Absorbed material"), "English bootstrap handoff should audit absorbed material");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("Unabsorbed material"), "English bootstrap handoff should audit unabsorbed material");
+  assert(read(cwd, "ai/template/bootstrap.md").includes("Conflict handling"), "English bootstrap handoff should audit conflict handling");
   assert(read(cwd, "ai/template/prompt.md").includes("Start initializing this project"), "English execution prompt should route natural bootstrap entry");
   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");
   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("strategy_update"), "English execution prompt should route strategy updates");
@@ -142,6 +155,9 @@ function testEnglishInitUpdateDoctor() {
   assert(read(cwd, "ai/project/proposals/final-shape-updates/_template.md").includes("`accepted`"), "English proposal template should describe accepted status");
   assert(read(cwd, "ai/template/reconcile.md").includes("Context Reconcile"), "English init should install English reconcile prompt");
   assert(read(cwd, "ai/template/reconcile.md").includes("reconciliation plan"), "English reconcile prompt should require a plan first");
+  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("[Initialize]"), "English init output should distinguish pre-bootstrap guidance");
   assert(initOutput.includes("Start initializing this project and absorb the material in ai/project/inbox/"), "English init output should explain bootstrap with existing material");