ci: add release/* branch source validation workflow (#11)

release/* 仅接受 hotfix/* 或带 cherry-pick/backport 标签的 PR。
详见 iac_modules/docs/tldr-github-branch-model.md

Co-authored-by: Haitao Pan <haitao.pan@xworkmate.ai>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

.github/workflows/validate-release-pr.yml

@@ -0,0 +1,44 @@
+name: Validate Release PR
+
+# release/* 分支的发布策略门禁：仅接受 hotfix/* 或带 cherry-pick/backport 标签的 PR。
+# 详见 iac_modules/docs/tldr-github-branch-model.md
+on:
+  pull_request_target:
+    types: [opened, synchronize, reopened, labeled, unlabeled]
+
+permissions:
+  contents: read
+  pull-requests: read
+
+jobs:
+  validate-release-source:
+    runs-on: ubuntu-latest
+    if: startsWith(github.base_ref, 'release/')
+    steps:
+      - name: Check PR source branch
+        run: |
+          SRC="${{ github.head_ref }}"
+          TGT="${{ github.base_ref }}"
+          LABELS="${{ join(github.event.pull_request.labels.*.name, ',') }}"
+
+          echo "🔍 Validating PR into release branch"
+          echo "  source: $SRC"
+          echo "  target: $TGT"
+          echo "  labels: $LABELS"
+
+          if [[ "$SRC" =~ ^hotfix/ ]]; then
+            echo "✅ Allowed: hotfix/* branch"
+            exit 0
+          fi
+
+          if [[ "$LABELS" =~ (^|,)(cherry-pick|backport)(,|$) ]]; then
+            echo "✅ Allowed: cherry-pick/backport labeled PR"
+            exit 0
+          fi
+
+          echo "❌ Rejected."
+          echo "release/* 仅接受："
+          echo "  - 来自 hotfix/* 的 PR"
+          echo "  - 带 cherry-pick 或 backport 标签的 PR（已验证 feature 的 backport/cherry-pick）"
+          echo "禁止从 main / develop / feature/* 直接合并到 release/*。"
+          exit 1

internal/acp/http_handler.go

@@ -37,6 +37,7 @@ func (s *Server) Handler() http.Handler {
 				"commit":    info.Commit,
 				"version":   info.Version,
 				"buildDate": info.BuildDate,
+				"metrics":   bridgeStabilityMetricsSnapshot(), // T12
 			}
 			body, _ := json.Marshal(resp)
 			w.Header().Set("Content-Type", "application/json")

internal/acp/metrics.go

@@ -0,0 +1,29 @@
+package acp
+
+import "sync/atomic"
+
+// 关键稳定性指标（T12，docs/cases/06 §5）。
+//
+// 进程内累计计数，经 /api/ping 暴露，用于把「网关抖动 / run 超时」从靠用户截图
+// 变为可监控。三个计数对应三类已知的不稳定来源：
+//   - gatewaySocketClosed       : gatewayRPCError 命中 OPENCLAW_GATEWAY_SOCKET_CLOSED（连接断）
+//   - taskGetUnconfirmedFallback: tasks.get 走持久 run 仓兜底（gateway 无法确认 run，T7）
+//   - runDeadlineInterrupt      : run 超过 DeadlineAt 且 gateway 无法确认，回 interrupted（T9）
+var bridgeStabilityMetrics struct {
+	gatewaySocketClosed        atomic.Int64
+	taskGetUnconfirmedFallback atomic.Int64
+	runDeadlineInterrupt       atomic.Int64
+}
+
+func metricGatewaySocketClosedInc()        { bridgeStabilityMetrics.gatewaySocketClosed.Add(1) }
+func metricTaskGetUnconfirmedFallbackInc() { bridgeStabilityMetrics.taskGetUnconfirmedFallback.Add(1) }
+func metricRunDeadlineInterruptInc()       { bridgeStabilityMetrics.runDeadlineInterrupt.Add(1) }
+
+// bridgeStabilityMetricsSnapshot 返回当前计数快照，供 /api/ping 输出。
+func bridgeStabilityMetricsSnapshot() map[string]any {
+	return map[string]any{
+		"gatewaySocketClosed":        bridgeStabilityMetrics.gatewaySocketClosed.Load(),
+		"taskGetUnconfirmedFallback": bridgeStabilityMetrics.taskGetUnconfirmedFallback.Load(),
+		"runDeadlineInterrupt":       bridgeStabilityMetrics.runDeadlineInterrupt.Load(),
+	}
+}

internal/acp/openclaw_run_registry.go

@@ -1,6 +1,7 @@
 package acp
 
 import (
+	"log"
 	"strings"
 	"time"
 
@@ -125,11 +126,15 @@ func (s *Server) openClawTaskGetGatewayUnconfirmedFallback(params map[string]any
 		return s.markOpenClawRunDeadlineInterruptedLocked(sess, code, message)
 	}
 	// 仍在预算内：合成 running 句柄让客户端继续轮询，不因一次瞬时抖动硬失败。
+	metricTaskGetUnconfirmedFallbackInc() // T12
 	running := openClawRunningTaskResult(sess.openClaw)
 	running["transportDegraded"] = true
 	if strings.TrimSpace(code) != "" {
 		running["transportDegradedCode"] = strings.TrimSpace(code)
 	}
+	// T11：带 runId 的日志，便于与 App / 插件 / 网关四层按 runId 串联。
+	log.Printf("level=warn component=openclaw_run_registry event=tasks_get_unconfirmed_fallback runId=%q openclawSessionKey=%q code=%q",
+		sess.openClaw.RunID, sess.openClaw.SessionKey, strings.TrimSpace(code))
 	sess.lastResult = cloneMap(running)
 	return running
 }
@@ -143,6 +148,13 @@ func (s *Server) markOpenClawRunDeadlineInterruptedLocked(sess *session, code st
 	sess.task.ProgressStage = "interrupted"
 	sess.task.ProgressMessage = "OpenClaw run exceeded its budget and could not be confirmed"
 	sess.task.UpdatedAt = now
+	metricRunDeadlineInterruptInc() // T12
+	// T11：带 runId 的终态日志。
+	if sess.openClaw != nil {
+		log.Printf("level=warn component=openclaw_run_registry event=run_deadline_interrupt runId=%q openclawSessionKey=%q deadlineAt=%q code=%q",
+			sess.openClaw.RunID, sess.openClaw.SessionKey,
+			sess.openClaw.DeadlineAt.UTC().Format(time.RFC3339Nano), strings.TrimSpace(code))
+	}
 
 	result := map[string]any{
 		"ok":                 true,

internal/acp/orchestrator.go

@@ -1687,11 +1687,16 @@ func applyOpenClawConstraintDeliveryStatus(result map[string]any) {
 
 func gatewayRPCError(errorPayload map[string]any, fallback string) *shared.RPCError {
 	if isOpenClawRetryableGatewayError(errorPayload) {
+		metricGatewaySocketClosedInc() // T12
+		// T10：连接断属「可重试 / run 可能仍在后台、可续轮询」语义，而非 run 确实失败。
+		// 带 retryable/poll 提示，客户端据此降级为「后台续跑·重连中」(T5) 续轮询 tasks.get，而非硬失败。
 		return &shared.RPCError{
 			Code:    -32002,
 			Message: "OPENCLAW_GATEWAY_SOCKET_CLOSED: OpenClaw gateway connection closed during task execution",
 			Data: map[string]any{
 				"code":          "OPENCLAW_GATEWAY_SOCKET_CLOSED",
+				"retryable":     true,
+				"poll":          true,
 				"originalCode":  strings.TrimSpace(shared.StringArg(errorPayload, "code", "")),
 				"originalError": strings.TrimSpace(shared.StringArg(errorPayload, "message", "")),
 			},

internal/acp/orchestrator_normalize_result_test.go

@@ -132,6 +132,49 @@ func TestNormalizeOpenClawTaskGetUnknownArtifactEvidenceKeepsActiveRecordRunning
 	}
 }
 
+func TestExpectedArtifactDirectoriesDoNotBlockTerminalTaskState(t *testing.T) {
+	params := map[string]any{"expectedArtifactDirs": []any{"reports/", "artifacts/"}}
+	payload := map[string]any{
+		"success":           true,
+		"status":            string(TaskStateCompleted),
+		"artifactScope":     "tasks/session/run",
+		"artifactDirectory": "/remote/openclaw/workspace/tasks/session/run",
+		"expectedArtifactDirs": []any{
+			"reports/",
+			"artifacts/",
+		},
+	}
+
+	if openClawTaskGetRequiresArtifactExport(params, payload) {
+		t.Fatal("expectedArtifactDirs must remain non-blocking scan hints")
+	}
+	got := normalizeOpenClawTaskGetResult(params, payload, "openclaw", nil)
+	if status := shared.StringArg(got, "status", ""); status != string(TaskStateCompleted) {
+		t.Fatalf("expected terminal status to remain completed, got %#v", got)
+	}
+	if parseBool(got["pending"]) {
+		t.Fatalf("expected terminal payload not to become pending, got %#v", got)
+	}
+}
+
+func TestRequiredArtifactExtensionsStillBlockUntilVerified(t *testing.T) {
+	params := map[string]any{"requiredArtifactExtensions": []any{"md"}}
+	payload := map[string]any{
+		"success":           true,
+		"status":            string(TaskStateCompleted),
+		"artifactScope":     "tasks/session/run",
+		"artifactDirectory": "/remote/openclaw/workspace/tasks/session/run",
+	}
+
+	if !openClawTaskGetRequiresArtifactExport(params, payload) {
+		t.Fatal("requiredArtifactExtensions must remain a blocking delivery contract")
+	}
+	got := normalizeOpenClawTaskGetResult(params, payload, "openclaw", nil)
+	if status := shared.StringArg(got, "status", ""); status != string(TaskStateRunning) {
+		t.Fatalf("expected missing required artifact to remain syncing, got %#v", got)
+	}
+}
+
 func TestNormalizeOpenClawTaskGetUnknownArtifactEvidenceFailsAfterDeadlineWithoutRequiredArtifacts(t *testing.T) {
 	payload := map[string]any{
 		"success":            false,

internal/acp/rpc_handler.go

@@ -471,9 +471,11 @@ func openClawTaskGetRequiresArtifactExport(params map[string]any, payload map[st
 	if parseBool(params["requiresExportBeforeFinalResponse"]) || parseBool(payload["requiresExportBeforeFinalResponse"]) {
 		return true
 	}
-	return len(shared.ListArg(params, "expectedArtifactDirs")) > 0 ||
-		len(shared.ListArg(payload, "expectedArtifactDirs")) > 0 ||
-		len(shared.ListArg(params, "requiredArtifactExtensions")) > 0 ||
+	// expectedArtifactDirs are discovery hints for the plugin's workspace-root
+	// scan. They do not prove that the caller requires a file before the run can
+	// reach a terminal state. Treating them as a blocking contract turns a
+	// failed/no-output agent run into an endless "syncing-artifacts" loop.
+	return len(shared.ListArg(params, "requiredArtifactExtensions")) > 0 ||
 		len(shared.ListArg(payload, "requiredArtifactExtensions")) > 0
 }