@fitlab-ai/agent-infra 0.6.0 → 0.6.2-alpha.1

package/templates/.agents/skills/create-release-note/SKILL.en.md

@@ -156,31 +156,28 @@ Show the generated release notes to the user.
 
 Ask:
 1. Need any adjustments?
-2. Create a draft release?
+2. Write these notes onto the Release for this version?
 
-### 9. Create Draft Release (If Confirmed)
+### 9. Publish the Release Notes (If Confirmed)
 
-Create the draft release by following `.agents/rules/release-commands.md`.
+Write the notes by following the "Publish the Release Notes" command in `.agents/rules/release-commands.md` (it updates the Release already created and published by the release workflow, falling back to creating it if missing).
 
 Output:
 ```
-Draft Release created.
+Release notes updated.
 
-- URL: {draft-release-url}
+- URL: {release-url}
 - Version: v{version}
-- Status: Draft
+- Status: Published
 
-Please review and publish on the platform:
-1. Open the URL above
-2. Review the release notes
-3. Click "Publish release"
+The notes have been written to the Release. Edit further at the URL above if needed.
 ```
 
 ## Notes
 
 1. **Requires the platform CLI**: Must have the platform CLI installed and authenticated
 2. **Tags must exist**: Run the release skill first to create tags
-3. **Draft mode**: Creates a draft - won't auto-publish
+3. **Release auto-published**: the `v{version}` Release is created and published by the release workflow (the upload target for Homebrew bottles); this skill writes/refreshes the notes on that Release
 4. **Classification accuracy**: Auto-classification is based on title/scope/files; complex PRs may need manual adjustment
 
 ## Error Handling

package/templates/.agents/skills/create-release-note/SKILL.zh-CN.md

@@ -156,31 +156,28 @@ git log v<prev-version>..v<version> \
 
 询问：
 1. 需要调整吗？
-2. 是否创建 draft release？
+2. 是否把 notes 写入该版本的 Release？
 
-### 9. 创建 Draft Release（如确认）
+### 9. 发布 Release notes（如确认）
 
-按 `.agents/rules/release-commands.md` 的 Draft Release 创建命令执行。
+按 `.agents/rules/release-commands.md` 的「发布 Release notes」命令执行（写入已由 release 工作流自动创建/发布的 Release；不存在时兜底创建）。
 
 输出：
 ```
-Draft Release created.
+Release notes 已更新。
 
-- URL: {draft-release-url}
+- URL: {release-url}
 - Version: v{version}
-- Status: Draft
+- Status: Published
 
-Please review and publish on the platform:
-1. Open the URL above
-2. Review the release notes
-3. Click "Publish release"
+发布说明已写入该 Release。如需进一步调整，可在上面的 URL 直接编辑。
 ```
 
 ## 注意事项
 
 1. **需要 the platform CLI**：必须安装并认证 the platform CLI
 2. **标签必须存在**：先执行 release 技能创建标签
-3. **草稿模式**：创建草稿 —— 不会自动发布
+3. **Release 已自动发布**：`v{version}` 的 Release 由 release 工作流自动创建并发布（给 Homebrew bottle 提供上传落点）；本技能往该 Release 写入/刷新 notes
 4. **分类准确性**：自动分类基于标题/scope/文件；复杂的 PR 可能需要手动调整
 
 ## 错误处理

package/templates/.agents/skills/create-task/SKILL.en.md

@@ -20,6 +20,8 @@ The user's description is a **work item**, not an **instruction to execute immed
 
 After executing this skill, you **must** immediately update task status in task.md.
 
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
 ## Steps
 
 ### 1. Parse the User Description
@@ -74,12 +76,18 @@ workflow: feature-development|bug-fix|refactoring
 status: active
 created_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
 updated_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
+agent_infra_version: {agent_infra_version}
 created_by: human
+priority:                  # optional; Urgent | High | Medium | Low
+effort:                    # optional; High | Medium | Low
+start_date:                # optional; YYYY-MM-DD
+target_date:               # optional; YYYY-MM-DD
 current_step: requirement-analysis
 assigned_to: {current AI agent}
 ```
 
 Note: `created_by` is `human` because the task comes from the user's description.
+Optional Issue field metadata may be left empty at task creation; do not invent dates.
 
 ### 3. Update Task Status
 
@@ -93,6 +101,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 - `current_step`: requirement-analysis
 - `assigned_to`: {current AI agent}
 - `updated_at`: {current time}
+- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
 - `## Context` -> `- **Branch**:`: update it to the generated branch name
 - **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```

package/templates/.agents/skills/create-task/SKILL.zh-CN.md

@@ -20,6 +20,8 @@ description: "根据自然语言描述创建任务"
 
 执行本技能后，你**必须**立即更新 task.md 中的任务状态。
 
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
 ## 执行步骤
 
 ### 1. 解析用户描述
@@ -74,12 +76,18 @@ workflow: feature-development|bug-fix|refactoring
 status: active
 created_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
 updated_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
+agent_infra_version: {agent_infra_version}
 created_by: human
+priority:                  # 可选；Urgent | High | Medium | Low
+effort:                    # 可选；High | Medium | Low
+start_date:                # 可选；YYYY-MM-DD
+target_date:               # 可选；YYYY-MM-DD
 current_step: requirement-analysis
 assigned_to: {当前 AI 代理}
 ```
 
 注意：`created_by` 为 `human`，因为任务来源于用户的描述。
+可选 Issue 字段元数据在创建任务时可留空；不要臆测日期。
 
 ### 3. 更新任务状态
 
@@ -93,6 +101,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - `current_step`：requirement-analysis
 - `assigned_to`：{当前 AI 代理}
 - `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
 - `## 上下文` 中的 `- **分支**：`：更新为生成的分支名
 - **追加**到 `## Activity Log`（不要覆盖之前的记录）：
   ```

package/templates/.agents/skills/create-task/config/verify.json

@@ -10,6 +10,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],

package/templates/.agents/skills/implement-task/SKILL.en.md

@@ -14,6 +14,19 @@ Implement the approved task and produce `implementation.md` or `implementation-r
 - Create a new implementation artifact for each round and never overwrite an older one
 - After executing this skill, you **must** immediately update task.md
 
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
+## Common Rationalizations and Rebuttals
+
+Before implementing, stop if any of these thoughts appear. They are violations:
+
+| Rationalization | Rebuttal |
+|------|------|
+| "The code is too simple to need tests." | Simple code still regresses; without a failing-to-passing case there is no completion signal, so write a test that verifies business behavior first. |
+| "Writing code first and adding tests later is faster." | Tests added after implementation often mirror the implementation; goal-driven work defines the verifiable case first and then makes it pass. |
+| "This plan is flawed, so I will improve it as I go." | Deviations from `{plan-artifact}` must be recorded in the report; if the direction is questionable, stop and confirm instead of changing it silently. |
+| "The tests passed, so I can commit this too." | This skill never runs `git add` or `git commit`; committing is a separate step explicitly requested by the user. |
+
 ## Steps
 
 ### 1. Verify Prerequisites
@@ -62,7 +75,8 @@ Read `{plan-artifact}` carefully and extract:
 
 Follow `.agents/workflows/feature-development.yaml` and the plan in order.
 
-> Detailed implementation rules, testing discipline, and deviation handling live in `reference/implementation-rules.md`. Read `reference/implementation-rules.md` before executing this step.
+> Detailed implementation rules, the test execution loop, and deviation handling live in `reference/implementation-rules.md`. Read `reference/implementation-rules.md` before executing this step.
+> Test-writing discipline (RED-GREEN-REFACTOR and anti-patterns) lives in `.agents/rules/testing-discipline.md`; read it before adding or changing tests.
 
 ### 7. Run Test Verification
 
@@ -88,6 +102,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 - `current_step`: implementation
 - `assigned_to`: {current agent}
 - `updated_at`: {current time}
+- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
 - review the `## Requirements` section and only change items from `- [ ]` to `- [x]` when they are clearly satisfied by this round's implemented code and passing tests
 - record `{implementation-artifact}` for Round `{implementation-round}`
 - append:

package/templates/.agents/skills/implement-task/SKILL.zh-CN.md

@@ -14,6 +14,19 @@ description: "根据技术方案实施任务并输出报告"
 - 每轮实现都创建新的实现产物，不覆盖旧文件
 - 执行本技能后，你**必须**立即更新 task.md
 
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
+## 常见违规借口与反驳
+
+动手实现前，若冒出以下念头，先停下——它们都是违规借口：
+
+| 借口 | 反驳 |
+|------|------|
+| 「代码太简单，不需要测试」 | 简单代码也会回归；没有"失败→通过"的用例就没有完成标志，先写验证业务行为的测试。 |
+| 「先写代码再补测试更高效」 | 后补测试常沦为对实现的镜像；目标驱动应先定义可验证用例再让它通过。 |
+| 「方案这里不合理，顺手改更好」 | 偏离 `{plan-artifact}` 必须在报告中记录原因；有异议先停下确认，不擅自改方向。 |
+| 「测试过了，顺便提交一下」 | 本技能绝不执行 `git add`/`git commit`，提交是用户显式发起的独立步骤。 |
+
 ## 执行步骤
 
 ### 1. 验证前置条件
@@ -62,7 +75,8 @@ description: "根据技术方案实施任务并输出报告"
 
 按照 `.agents/workflows/feature-development.yaml` 和方案顺序实施。
 
-> 详细实现规则、测试纪律和偏离处理见 `reference/implementation-rules.md`。执行此步骤前，先读取 `reference/implementation-rules.md`。
+> 详细实现规则、测试执行循环和偏离处理见 `reference/implementation-rules.md`。执行此步骤前，先读取 `reference/implementation-rules.md`。
+> 测试编写纪律（RED-GREEN-REFACTOR 与反模式）见 `.agents/rules/testing-discipline.md`；新增或调整测试前先读取该文件。
 
 ### 7. 运行测试验证
 
@@ -88,6 +102,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - `current_step`：implementation
 - `assigned_to`：{当前代理}
 - `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
 - 审查 `## 需求` 段落，仅把本轮已由代码实现且有测试通过支撑的条目从 `- [ ]` 勾为 `- [x]`
 - 记录 Round `{implementation-round}` 的 `{implementation-artifact}`
 - 追加：

package/templates/.agents/skills/implement-task/config/verify.json

@@ -9,6 +9,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],
@@ -36,6 +37,7 @@
       "verify_comment_content": true,
       "verify_task_comment_content": true,
       "verify_issue_type": true,
+      "verify_issue_fields": false,
       "verify_milestone": true,
       "expected_status_label_key": "inProgress",
       "expected_comment_marker_key": "artifact"

package/templates/.agents/skills/import-codescan/config/verify.json

@@ -9,6 +9,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],

package/templates/.agents/skills/import-dependabot/config/verify.json

@@ -9,6 +9,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],

package/templates/.agents/skills/import-issue/SKILL.en.md

@@ -69,11 +69,18 @@ workflow: feature-development|bug-fix|refactoring
 status: active
 created_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
 updated_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
+agent_infra_version: {agent_infra_version}
 created_by: human
+priority:                  # optional; preserve source/frontmatter value when available
+effort:                    # optional; preserve source/frontmatter value when available
+start_date:                # optional; preserve explicit YYYY-MM-DD when available
+target_date:               # optional; preserve explicit YYYY-MM-DD when available
 current_step: requirement-analysis
 assigned_to: {current AI agent}
 ```
 
+Optional Issue field metadata should preserve recovered or explicit source values. If absent, leave it empty; do not invent dates.
+
 3.3 Append Activity Log entries.
 
 - Scenario B: append `Import Issue`
@@ -91,6 +98,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 - `current_step`: requirement-analysis
 - `assigned_to`: {current AI agent}
 - `updated_at`: {current time}
+- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
 - `## Context` -> `- **Branch**:`: update it to the generated branch name
 - **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```
@@ -162,6 +170,8 @@ Next step - run requirements analysis:
 
 After completing the checklist, **stop immediately**. Do not continue to later steps.
 
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
 ## Notes
 
 1. **Issue validation**: verify that the Issue exists before continuing

package/templates/.agents/skills/import-issue/SKILL.zh-CN.md

@@ -69,11 +69,18 @@ workflow: feature-development|bug-fix|refactoring
 status: active
 created_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
 updated_at: {YYYY-MM-DD HH:mm:ss±HH:MM}
+agent_infra_version: {agent_infra_version}
 created_by: human
+priority:                  # 可选；有来源/frontmatter 值时保留
+effort:                    # 可选；有来源/frontmatter 值时保留
+start_date:                # 可选；有明确 YYYY-MM-DD 时保留
+target_date:               # 可选；有明确 YYYY-MM-DD 时保留
 current_step: requirement-analysis
 assigned_to: {当前 AI 代理}
 ```
 
+可选 Issue 字段元数据应保留恢复得到或来源中明确给出的值。缺失时留空；不要臆测日期。
+
 3.3 追加 Activity Log。
 
 - 场景 B：追加 `Import Issue`
@@ -91,6 +98,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - `current_step`：requirement-analysis
 - `assigned_to`：{当前 AI 代理}
 - `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
 - `## 上下文` 中的 `- **分支**：`：更新为生成的分支名
 - **追加**到 `## Activity Log`（不要覆盖之前的记录）：
   ```
@@ -162,6 +170,8 @@ Issue #{number} 已导入。
 
 完成检查清单后，**立即停止**。不要继续执行后续步骤。
 
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
 ## 注意事项
 
 1. **Issue 验证**：在继续之前检查 Issue 是否存在

package/templates/.agents/skills/import-issue/config/verify.json

@@ -10,6 +10,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],

package/templates/.agents/skills/plan-task/SKILL.en.md

@@ -11,6 +11,8 @@ description: "Design a technical plan for a task"
 - This is a **mandatory human review checkpoint**; do not automatically proceed to implementation
 - After executing this skill, you **must** immediately update task status in task.md
 
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
 ## Steps
 
 ### 1. Verify Prerequisites
@@ -88,6 +90,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 - `current_step`: technical-design
 - `assigned_to`: {current AI agent}
 - `updated_at`: {current time}
+- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
 - Record the plan artifact for this round: `{plan-artifact}` (Round `{plan-round}`)
 - If the task template contains a `## Design` section, update it to link to `{plan-artifact}`
 - Mark technical-design as complete in workflow progress and include the actual round when the task template supports it

package/templates/.agents/skills/plan-task/SKILL.zh-CN.md

@@ -11,6 +11,8 @@ description: "为任务设计技术方案和实施计划"
 - 这是一个**强制性的人工审查检查点** —— 不要自动进入实现阶段
 - 执行本技能后，你**必须**立即更新 task.md 中的任务状态
 
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
 ## 执行步骤
 
 ### 1. 验证前置条件
@@ -88,6 +90,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - `current_step`：technical-design
 - `assigned_to`：{当前 AI 代理}
 - `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
 - 记录本轮方案产物：`{plan-artifact}`（Round `{plan-round}`）
 - 如任务模板包含 `## 设计` 段落，更新为指向 `{plan-artifact}` 的链接
 - 在工作流进度中标记 technical-design 为已完成，并注明实际轮次（如果任务模板支持）

package/templates/.agents/skills/plan-task/config/verify.json

@@ -9,6 +9,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],
@@ -38,6 +39,7 @@
       "verify_comment_content": true,
       "verify_task_comment_content": true,
       "verify_issue_type": true,
+      "verify_issue_fields": false,
       "verify_milestone": true,
       "expected_status_label_key": "pendingDesignWork",
       "expected_comment_marker_key": "artifact"

package/templates/.agents/skills/refine-task/SKILL.en.md

@@ -10,9 +10,20 @@ Fix review findings and produce `refinement.md` or `refinement-r{N}.md`.
 ## Boundary / Critical Rules
 
 - Fix only the issues documented in review artifacts
+- env-blocked findings are outside the repair scope: the refinement report must preserve them and record "outside AI repair scope (environment-blocked)" instead of making no-op edits to clear the report
 - Never auto-run `git add` or `git commit`
 - After executing this skill, you **must** immediately update task.md
 
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
+## Common Rationalizations and Rebuttals
+
+| Rationalization | Rebuttal |
+|------|------|
+| "This review comment is wrong, so I will ignore it." | If you disagree, record the reason under unresolved issues in the report; do not silently skip blocker or major findings. |
+| "I can clean up nearby code while I am here." | Scope is limited to review findings; changes outside that scope are out of bounds. |
+| "Clearing env-blocked items makes the report look better." | env-blocked findings are outside the repair scope; preserve and label them truthfully, and never use no-op edits to pad the fix count. |
+
 ## Steps
 
 ### 1. Verify Prerequisites
@@ -56,8 +67,11 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 Update task.md:
 - review the `## Requirements` section and only change items from `- [ ]` to `- [x]` when they are newly satisfied by this round's fixes and passing tests
+- preserve explicit optional Issue field metadata (`priority`, `effort`, `start_date`, `target_date`); only infer `priority` or `effort` from clear review context, and do not invent dates
 - append:
-  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Refinement (Round {N}, for {review-artifact})** by {agent} — Fixed {n} blockers, {n} major, {n} minor issues → {refinement-artifact}`
+  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Refinement (Round {N}, for {review-artifact})** by {agent} — Fixed {n} blockers, {n} major, {n} minor issues[, skipped {n} env-blocked] → {refinement-artifact}`
+
+Append `, skipped {n} env-blocked` when env-blocked > 0; omit it when env-blocked = 0.
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
 - Read `.agents/rules/issue-sync.md` before syncing, and complete upstream repository detection plus permission detection

package/templates/.agents/skills/refine-task/SKILL.zh-CN.md

@@ -10,9 +10,20 @@ description: "处理代码审查反馈并修复问题"
 ## 行为边界 / 关键规则
 
 - 只修复审查产物中记录的问题
+- env-blocked 项不在修复范围内：refinement 报告必须如实保留这些项并记录“不在 AI 修复范围（环境性遗留）”，不能为了清空报告做 no-op 改动
 - 绝不自动执行 `git add` 或 `git commit`
 - 执行本技能后，你**必须**立即更新 task.md
 
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
+## 常见违规借口与反驳
+
+| 借口 | 反驳 |
+|------|------|
+| 「这条审查意见不合理，直接忽略」 | 不同意要在报告的未解决问题中写明理由，不能静默跳过 blocker/major。 |
+| 「顺手把旁边也优化了」 | 范围严格限定在审查项内，范围外改动属于越界。 |
+| 「env-blocked 项清掉报告好看」 | env-blocked 不在修复范围，必须如实保留并标注，禁止 no-op 改动充数。 |
+
 ## 执行步骤
 
 ### 1. 验证前置条件
@@ -56,8 +67,11 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 更新 task.md：
 - 审查 `## 需求` 段落，仅把因本轮修复而新满足且有测试通过支撑的条目从 `- [ ]` 勾为 `- [x]`
+- 保留明确填写的可选 Issue 字段元数据（`priority`、`effort`、`start_date`、`target_date`）；仅在审查上下文非常明确时推断 `priority` 或 `effort`，不要臆测日期
 - 追加：
-  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Refinement (Round {N}, for {review-artifact})** by {agent} — Fixed {n} blockers, {n} major, {n} minor issues → {refinement-artifact}`
+  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Refinement (Round {N}, for {review-artifact})** by {agent} — Fixed {n} blockers, {n} major, {n} minor issues[, skipped {n} env-blocked] → {refinement-artifact}`
+
+env-blocked > 0 时附加 `, skipped {n} env-blocked`；env-blocked = 0 时省略。
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
 - 执行前先读取 `.agents/rules/issue-sync.md`，完成 upstream 仓库检测和权限检测

package/templates/.agents/skills/refine-task/config/verify.json

@@ -9,6 +9,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ]
@@ -32,6 +33,7 @@
       "verify_comment_content": true,
       "verify_task_comment_content": true,
       "verify_issue_type": true,
+      "verify_issue_fields": false,
       "verify_milestone": true,
       "expected_status_label_key": "inProgress",
       "expected_comment_marker_key": "artifact"

package/templates/.agents/skills/refine-task/reference/fix-workflow.en.md

@@ -20,6 +20,14 @@ Detailed priority rules:
 - Minor issues are optional only after Blockers and Majors are resolved
 - If you disagree with a finding, record that disagreement under unresolved issues instead of silently skipping it
 
+### Meta-category: env-blocked
+
+env-blocked findings are outside the repair scope. Handling rules:
+- do not write code changes for these findings
+- list them unchanged in the refinement report's "Environment-Blocked Handling" section and mark them "outside AI repair scope"
+- do not repeat them under unresolved issues, to avoid visually double-counting them
+- their destination is the PR description, where maintainers carry them as a "manual verification required" checklist
+
 ## Execute the Fixes
 
 For each fix:
@@ -51,6 +59,7 @@ Refinement status:
 - Blockers fixed: {fixed-blockers}/{total-blockers}
 - Major issues fixed: {fixed-majors}/{total-majors}
 - Minor issues fixed: {fixed-minors}/{total-minors}
+- [If env-blocked > 0] env-blocked skipped: {count}
 - All tests passing: {yes/no}
 - Review input: {review-artifact}
 - Refinement artifact: {refinement-artifact}

package/templates/.agents/skills/refine-task/reference/fix-workflow.zh-CN.md

@@ -20,6 +20,14 @@
 - 只有在 Blocker 和 Major 都解决后，Minor 才是可选项
 - 如果你不同意某条审查意见，不要静默跳过，而是把分歧记录到 unresolved issues
 
+### 元类目：env-blocked
+
+env-blocked 项不在修复范围。处理规则：
+- 不要为这些项编写代码改动
+- 在 refinement 报告的「环境性遗留处理」段落原样列出，标注「不在 AI 修复范围」
+- 不要在 unresolved 段落里重复列出（避免视觉计数翻倍）
+- 这些项的去向：维护者在 PR description 中以「待人工验证」清单承接
+
 ## 执行修复
 
 对每一项修复：
@@ -51,6 +59,7 @@
 - 阻塞项修复：{数量}/{总数}
 - 主要问题修复：{数量}/{总数}
 - 次要问题修复：{数量}/{总数}
+- [如 env-blocked > 0] 环境性遗留跳过：{数量}
 - 所有测试通过：{是/否}
 - 审查输入：{review-artifact}
 - 修复产物：{refinement-artifact}

package/templates/.agents/skills/refine-task/reference/report-template.en.md

@@ -29,6 +29,17 @@ Use this structure when writing `refinement.md` or `refinement-r{N}.md`.
 1. **{issue-title}**
    - **Fix**: {what changed}
 
+#### Environment-Blocked Handling
+
+> These findings are outside AI repair scope and do not count toward repair totals. Preserve them unchanged and identify the maintainer verification path.
+
+1. **{issue-title}**
+   - **Status**: skipped (outside AI repair scope)
+   - **Required Environment**: {e.g. Docker sandbox / macOS host / third-party account}
+   - **Maintainer Verification Steps**: {steps}
+
+> If this round has no env-blocked findings, keep the subsection heading and write "None".
+
 #### Unresolved Issues
 - {issue}: {reason}
 

package/templates/.agents/skills/refine-task/reference/report-template.zh-CN.md

@@ -29,6 +29,17 @@
 1. **{issue-title}**
    - **修复**: {what changed}
 
+#### 环境性遗留处理
+
+> 这些项不在 AI 修复范围；不计入修复总数。仅原样保留并指明维护者后续验证路径。
+
+1. **{issue-title}**
+   - **状态**：跳过（不在 AI 修复范围）
+   - **所需环境**：{e.g. Docker 沙箱 / macOS host / 第三方账号}
+   - **维护者验证步骤**：{steps}
+
+> 如本轮无 env-blocked 项，保留小节标题并写「（无）」。
+
 #### 未解决问题
 - {issue}: {reason}
 

package/templates/.agents/skills/restore-task/SKILL.en.md

@@ -14,6 +14,8 @@ Restore local task workspace files from platform Issue comments that contain syn
 - Stop immediately if the target directory already exists and ask the user to resolve the conflict first
 - After executing this skill, you **must** immediately update the restored `task.md`
 
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
 ## Steps
 
 ### 1. Verify Input and Environment
@@ -83,6 +85,7 @@ Update the restored `task.md`:
 - `status`: `active`
 - `assigned_to`: {current AI agent}
 - `updated_at`: {current time}
+- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
 
 Append an Activity Log entry indicating the task was restored from the platform Issue.
 

package/templates/.agents/skills/restore-task/SKILL.zh-CN.md

@@ -14,6 +14,8 @@ description: "从平台 Issue 评论还原本地任务文件"
 - 如果目标目录已存在，立即停止并提示用户先处理目录冲突
 - 执行本技能后，你**必须**立即更新恢复出的 `task.md`
 
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
 ## 执行步骤
 
 ### 1. 验证输入与环境
@@ -83,6 +85,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - `status`：`active`
 - `assigned_to`：{当前 AI 代理}
 - `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
 
 追加 Activity Log，说明任务已从平台 Issue 还原。
 

package/templates/.agents/skills/restore-task/config/verify.json

@@ -9,6 +9,7 @@
         "status",
         "created_at",
         "updated_at",
+        "agent_infra_version",
         "current_step",
         "assigned_to"
       ],