Merge PR #93: [moz] impl(§17): CI/部署失败 steps 分支指引 + 基础设施 Issue 转交流程

src/api/toolchain_routes.py

@@ -778,9 +778,8 @@ def _send_deploy_failure_task(repo: str, pr_number: int, pr_title: str, reason:
             action_type="deploy_failure",
             steps=[
                 "检查 deploy 日志",
-                "排查失败原因",
-                "修复并重新部署",
-                "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）",
+                "根据 deploy 日志判断失败原因类型：\n  a. 代码/配置问题（rsync 路径错、依赖缺失、启动失败）→ 修复 → 重新部署\n  b. 基础设施问题（Gitea 不可用、网络不通、磁盘满、SSH 故障）→ 在该仓库创建 Issue 指派 jiangwei-infra（见下方「需要创建 Issue 时」），label 必须包含 type/infrastructure",
+                "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）— 报告中说明判断的原因类型和执行的操作",
             ],
             context_data={
                 "repo": repo,
@@ -997,6 +996,34 @@ async def _handle_issues(payload: Dict[str, Any]) -> None:
             "brief": brief,
         })
 
+        # 检查是否是基础设施 Issue（按 label 分流）
+        is_infrastructure = any("infrastructure" in lbl.lower() for lbl in labels_list)
+
+        if is_infrastructure:
+            infra_steps = [
+                "根据 Issue body 中的错误来源和日志片段排查问题",
+                "修复基础设施问题（如修复 CI runner 环境、恢复网络、重启服务等）",
+                "修复后在 Issue 上 comment 说明修复方式和结果",
+                "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）",
+            ]
+            title = f"基础设施 Issue: {issue_title} ({repo}#{issue_number})"
+            _send_toolchain_task(
+                to_agent=assignee,
+                title=title,
+                description=text,
+                event_type="infrastructure_failure",
+                action_type="infrastructure_failure",
+                steps=infra_steps,
+                context_data={
+                    "issue_number": issue_number,
+                    "repo": repo,
+                    "issue_title": issue_title,
+                    "labels": labels,
+                    "issue_body": issue_body or "(无描述)",
+                    "brief": brief,
+                },
+            )
+        else:
             title = f"Issue 指派: {issue_title} ({repo}#{issue_number})"
             _send_toolchain_task(
                 to_agent=assignee,
@@ -1043,9 +1070,8 @@ async def _handle_issues(payload: Dict[str, Any]) -> None:
                     action_type="deploy_failure",
                     steps=[
                         "检查 deploy 日志",
-                        "排查失败原因",
-                        "修复并重新部署",
-                        "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）",
+                        "根据 deploy 日志判断失败原因类型：\n  a. 代码/配置问题（rsync 路径错、依赖缺失、启动失败）→ 修复 → 重新部署\n  b. 基础设施问题（Gitea 不可用、网络不通、磁盘满、SSH 故障）→ 在该仓库创建 Issue 指派 jiangwei-infra（见下方「需要创建 Issue 时」），label 必须包含 type/infrastructure",
+                        "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）— 报告中说明判断的原因类型和执行的操作",
                     ],
                     context_data={
                         "repo": repo,
@@ -1126,9 +1152,8 @@ async def _handle_issue_comment(payload: Dict[str, Any]) -> None:
             action_type="ci_failure",
             steps=[
                 "查看完整 CI 日志（PR 页面或 Gitea Actions 页面）",
-                "修复失败的测试",
-                "push → CI 自动重跑",
-                "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）",
+                "根据 CI 日志判断失败原因类型：\n  a. 代码问题（lint/test 失败）→ 修复失败的测试 → push 到原分支 → CI 自动重跑\n  b. 基础设施问题（runner 环境/Python/venv/Gitea/网络故障）→ 在该仓库创建 Issue 指派 jiangwei-infra（见下方「需要创建 Issue 时」），label 必须包含 type/infrastructure",
+                "提交 action report（POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments，comment_type=action_report）— 报告中说明判断的原因类型和执行的操作",
             ],
             context_data={
                 "pr_number": issue_number,

src/daemon/toolchain_handler.py

@@ -166,6 +166,19 @@ class ToolchainApiSection:
             "",
             "⚠️ 不要使用 Mail API(飞鸽传书)。所有协作通过 Gitea 留痕。",
             "",
+            "### 需要创建 Issue 时",
+            "",
+            "如果步骤中要求创建 Issue 指派他人（如 jiangwei-infra）：",
+            "```bash",
+            f'curl -s -X POST "{_GITEA_BASE}/repos/{{repo}}/issues" \\',
+            '  -H "Authorization: token <your-token>" \\',
+            '  -H "Content-Type: application/json" \\',
+            '  -d \'{"title": "[moz] infra: 简述问题", "body": "## 问题描述\\n\\n<简要描述问题现象>\\n\\n## 错误来源\\n\\n- 仓库: <repo>\\n- PR/Commit: <链接>\\n- CI/Deploy run: <Gitea Actions 页面链接>\\n\\n## 日志关键片段\\n\\n```<错误日志摘要>```\\n\\n## 判断依据\\n\\n<为什么判断为基础设施问题>", "assignees": ["jiangwei-infra"], "labels": [<label_id>]}\'',
+            "```",
+            "",
+            "⚠️ Issue body 必须包含错误来源链接（PR/Commit + CI run），让排查者能直接看到全貌。",
+            "⚠️ label 数字 ID 先 GET /repos/{repo}/labels 查询 type/infrastructure 对应的 ID。",
+            "",
         ]
         return "\n".join(lines)
 
@@ -218,6 +231,7 @@ class ToolchainConstraintsSection:
             '| “我已经知道了” | ❌ 知道不等于执行。执行步骤 + 提交 action report 才算完成 |',
             '| “步骤太多了，选几个做就行” | ❌ 错！必须逐条执行，不可跳过 |',
             '| “这个步骤不适用于当前情况” | ❌ 如果确实不适用，在 action report 中说明原因，但其他步骤必须执行 |',
+            '| “CI/部署失败不是我代码的问题，我什么也不用做” | ❌ 错！即使是基础设施问题，你也必须创建 Issue 指派 jiangwei-infra（body 含错误来源链接 + 日志 + 判断依据），并在 action report 中说明。不能只报告“不是我的问题”就完事 |',
             "",
         ]
         return "\n".join(lines)

tests/unit/test_toolchain_handler_v2.py

@@ -523,3 +523,73 @@ class TestFullPromptBuild:
         # Must have constraints with Red Flags
         assert "Red Flags" in prompt
         assert "强制要求" in prompt
+
+
+# ---------------------------------------------------------------------------
+# §17 v2: CI/deploy failure branching + issue label routing + Issue API guidance
+# ---------------------------------------------------------------------------
+
+class TestCiFailureBranching:
+    """ci_failure steps should include a/b branching guidance."""
+
+    def test_ci_failure_steps_contain_branching(self):
+        source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
+        source = source_file.read_text()
+        assert '基础设施问题' in source
+        assert 'type/infrastructure' in source
+        assert 'jiangwei-infra' in source
+
+
+class TestDeployFailureBranching:
+    """deploy_failure steps should include a/b branching guidance."""
+
+    def test_deploy_failure_steps_contain_branching(self):
+        source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
+        source = source_file.read_text()
+        count = source.count('基础设施问题（Gitea 不可用')
+        assert count >= 2, f'Expected >=2 deploy_failure branching, found {count}'
+
+
+class TestIssueAssignedLabelRouting:
+    """issue_assigned handler should route by type/infrastructure label."""
+
+    def test_label_check_in_source(self):
+        source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
+        source = source_file.read_text()
+        assert 'is_infrastructure' in source
+        assert 'infrastructure_failure' in source
+        assert '基础设施 Issue' in source
+
+    def test_normal_issue_keeps_coding_steps(self):
+        source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
+        source = source_file.read_text()
+        assert '创建分支 fix/' in source
+        assert 'issue_assigned' in source
+
+
+class TestToolchainApiIssueGuidance:
+    """ToolchainApiSection should include Issue creation guidance."""
+
+    def test_has_issue_creation_section(self):
+        source_file = PROJECT_ROOT / "src" / "daemon" / "toolchain_handler.py"
+        source = source_file.read_text()
+        assert "需要创建 Issue 时" in source
+        assert "/issues" in source
+        assert "jiangwei-infra" in source
+        assert "type/infrastructure" in source
+
+    def test_issue_body_template_mentions_required_fields(self):
+        source_file = PROJECT_ROOT / "src" / "daemon" / "toolchain_handler.py"
+        source = source_file.read_text()
+        assert "错误来源" in source
+        assert "判断依据" in source
+
+
+class TestRedFlagsInfrastructure:
+    """Red Flags should include the 'not my code' entry."""
+
+    def test_has_infrastructure_red_flag(self):
+        source_file = PROJECT_ROOT / "src" / "daemon" / "toolchain_handler.py"
+        source = source_file.read_text()
+        assert "不是我代码的问题" in source
+        assert "基础设施问题" in source