Agent-System/internal/squad/noncritical_degrade_test.go

package squad_test

import (
	"context"
	"os"
	"path/filepath"
	"strings"
	"testing"
	"time"

	"chat-agent-system/internal/agent"
	"chat-agent-system/internal/squad"
)

// failFirstBackend 第一步失败、其余成功。
type failFirstBackend struct {
	calls int
}

func (b *failFirstBackend) Name() string { return "fail-first" }

func (b *failFirstBackend) Execute(ctx context.Context, req agent.Request) (*agent.Result, error) {
	b.calls++
	if b.calls == 1 {
		return &agent.Result{Success: false, ErrorReason: "boom"}, nil
	}
	body := []byte("# core deliverable\n")
	_ = os.WriteFile(filepath.Join(req.WorkDir, "output.md"), body, 0o644)
	return &agent.Result{Success: true, Patches: map[string][]byte{"output.md": body}}, nil
}

func prepareDegradeWS(t *testing.T) (string, *squad.WorkflowDriver) {
	t.Helper()
	tmpDir := t.TempDir()
	engine := squad.NewWorkspaceEngine(nil)
	ws, err := engine.PrepareWorkspace(squad.WorkspacePrepareRequest{
		WorkDir:     tmpDir,
		TaskKey:     "degrade_test",
		StageTitle:  "降级验收",
		ProjectName: "degrade-audit",
		Backend:     "fail-first",
		WorkflowSteps: []squad.StepSpec{
			{ID: "step_01_optional", Role: "writer", Title: "可选分析", SubWorkspace: "tasks/01_optional", Mode: "execute"},
			{ID: "step_02_core", Role: "writer", Title: "核心成文", SubWorkspace: "tasks/02_core", Mode: "execute"},
		},
	})
	if err != nil {
		t.Fatalf("PrepareWorkspace: %v", err)
	}
	return ws.WorkDir, squad.NewWorkflowDriver(engine)
}

// A5：非关键步骤失败 → degraded 记录、后续步骤继续、整体 degraded + DegradedSteps。
func TestNonCriticalStepDegradesAndContinues(t *testing.T) {
	wsDir, driver := prepareDegradeWS(t)
	wf, err := driver.LoadWorkflow(wsDir)
	if err != nil {
		t.Fatal(err)
	}
	nonCritical := false
	for i := range wf.Steps {
		if wf.Steps[i].ID == "step_01_optional" {
			wf.Steps[i].Critical = &nonCritical
		}
	}
	_ = driver.SaveWorkflow(wsDir, wf)

	backend := &failFirstBackend{}
	res, err := driver.Execute(context.Background(), wsDir, backend, squad.ExecuteOptions{Timeout: 30 * time.Second})
	if err != nil {
		t.Fatalf("degraded run must not hard-fail: %v", err)
	}
	if !res.Success {
		t.Fatalf("degraded run Success must be true, reason=%s", res.ErrorReason)
	}
	if len(res.DegradedSteps) != 1 || res.DegradedSteps[0] != "step_01_optional" {
		t.Fatalf("DegradedSteps = %v", res.DegradedSteps)
	}
	after, _ := driver.LoadWorkflow(wsDir)
	if after.Status != "degraded" {
		t.Fatalf("wf.Status = %s, want degraded", after.Status)
	}
	found := false
	for _, s := range after.Steps {
		if s.ID == "step_01_optional" {
			found = true
			if s.Status != "degraded" || !strings.Contains(s.Error, "boom") {
				t.Fatalf("step_01 = %s err=%s", s.Status, s.Error)
			}
		}
		if s.ID == "step_02_core" && s.Status != "completed" {
			t.Fatalf("step_02 must complete, got %s", s.Status)
		}
	}
	if !found {
		t.Fatal("step_01_optional missing")
	}
	if backend.calls != 2 {
		t.Fatalf("second step must run, calls=%d", backend.calls)
	}
}

// A5：关键步骤（默认 nil）失败行为不变——立即终止、不跑后续。
func TestCriticalStepFailureStillAborts(t *testing.T) {
	wsDir, driver := prepareDegradeWS(t)
	backend := &failFirstBackend{}
	res, err := driver.Execute(context.Background(), wsDir, backend, squad.ExecuteOptions{Timeout: 30 * time.Second})
	if err == nil || (res != nil && res.Success) {
		t.Fatalf("critical failure must abort: err=%v res=%+v", err, res)
	}
	after, _ := driver.LoadWorkflow(wsDir)
	if after.Status != "failed" {
		t.Fatalf("wf.Status = %s, want failed", after.Status)
	}
	if backend.calls != 1 {
		t.Fatalf("second step must not run after critical failure, calls=%d", backend.calls)
	}
}