@fitlab-ai/agent-infra 0.6.2-alpha.1 → 0.6.3

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

@@ -22,6 +22,20 @@ description: "审查任务实现并输出代码审查报告"
 | 「大体没问题，给个 Approved」 | 结论必须由 blocker/major/minor 计数支撑，每个问题引用文件:行号，不能凭印象放行。 |
 | 「测试改动看着合理，跳过细看」 | 审查测试变更前必须逐条核对 `.agents/rules/testing-discipline.md`（见步骤 4 门禁）。 |
 
+## 第 0 步：状态核对（执行前硬约束）
+
+在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
+
+运行以下命令，并把原文粘贴到回复正文和本轮产物的 `## 状态核对` 段：
+
+```bash
+git status -s
+ls -la .agents/workspace/active/{task-id}/
+tail .agents/workspace/active/{task-id}/task.md
+```
+
+状态核对完成前，禁止任何关于外部状态的断言（例如“代码没变”“测试已通过”“没有其他引用”），包括思考阶段。本门禁只提供结构下限；逐条证据配对和真实性仍需按报告模板与审查要求核对。
+
 ## 执行步骤
 
 ### 1. 验证前置条件

package/templates/.agents/skills/review-task/config/verify.en.json

@@ -0,0 +1,50 @@
+{
+  "skill": "review-task",
+  "checks": {
+    "task-meta": {
+      "required_fields": [
+        "id",
+        "type",
+        "workflow",
+        "status",
+        "created_at",
+        "updated_at",
+        "agent_infra_version",
+        "current_step",
+        "assigned_to"
+      ]
+    },
+    "artifact": {
+      "file_pattern": "review.md|review-r{N}.md",
+      "required_sections": [
+        "Review Summary",
+        "Findings",
+        "Environment-Blocked Findings",
+        "Conclusion and Recommendation",
+        "State Check",
+        "Evidence"
+      ],
+      "required_patterns": [
+        "^### Approval Decision$",
+        "^\\$ "
+      ],
+      "freshness_minutes": 30
+    },
+    "activity-log": {
+      "expected_action_pattern": "Code Review \\(Round \\d+\\)",
+      "freshness_minutes": 30
+    },
+    "platform-sync": {
+      "when": "issue_number_exists",
+      "expected_status_label": "status: in-progress",
+      "expected_comment_marker": "<!-- sync-issue:{task-id}:{artifact-stem} -->",
+      "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/review-task/config/{verify.json → verify.zh-CN.json}

@@ -20,10 +20,13 @@
         "审查摘要",
         "问题清单",
         "环境性遗留",
-        "结论与建议"
+        "结论与建议",
+        "状态核对",
+        "证据原文"
       ],
       "required_patterns": [
-        "^### 审查决定$"
+        "^### 审查决定$",
+        "^\\$ "
       ],
       "freshness_minutes": 30
     },

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

@@ -13,6 +13,10 @@ Use this template when writing `review.md` or `review-r{N}.md`.
   - `{implementation-artifact}`
   - `{refinement-artifact}` (if present)
 
+## State Check
+
+> Paste the raw state-check command output; each command starts with `$ `.
+
 ## Review Summary
 
 - **Reviewer**: {reviewer-name}
@@ -55,6 +59,17 @@ Use this template when writing `review.md` or `review-r{N}.md`.
 
 > If this round has no env-blocked findings, keep the section heading and write "None".
 
+
+## Evidence
+
+> Pair each "I verified X" claim with the corresponding raw tool output; the gate only checks that this section exists and at least one `$ ` line is present.
+
+- Claim: {verified claim}
+```text
+$ {command}
+{raw output}
+```
+
 ## Highlights
 
 - {what went well}

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

@@ -13,6 +13,10 @@
   - `{implementation-artifact}`
   - `{refinement-artifact}`（如存在）
 
+## 状态核对
+
+> 粘贴状态核对命令原文；每条命令以 `$ ` 开头。
+
 ## 审查摘要
 
 - **审查者**：{reviewer-name}
@@ -55,6 +59,17 @@
 
 > 如本轮无 env-blocked 项，保留段落标题并写「（无）」。
 
+
+## 证据原文
+
+> 每条“我验证了 X”断言都要配对对应 tool output 原文；gate 仅校验本段存在和至少一行 `$ `。
+
+- 断言：{verified claim}
+```text
+$ {command}
+{raw output}
+```
+
 ## 亮点
 
 - {what went well}

package/dist/package.json

@@ -1,5 +0,0 @@
-{
-  "name": "@fitlab-ai/agent-infra",
-  "version": "0.6.2-alpha.1",
-  "type": "module"
-}