Files
Agent-Squad/squad/wp4_conformance_test.go
T
weichen acbe744142
ci / vet-and-test (pull_request) Successful in 26s
ci / docker-checkout-hostgateway (pull_request) Successful in 1s
Add task-board driver with claim/lease/complete and 12-topology aggregate (Q2 WP4)
Why: Q2 acceptance 1 requires a scripted-backend conformance for every one of
the 12 builtin topologies; task_board was the last unlit driver.

Evidence: wp4_conformance_test.go: diamond-dependency board respects the
dependency gate in claim order; orphan lease (claimed + expired) re-arms on
driver re-entry and re-claims with Attempts=2 via Resume; non-critical task
failure cascades dependents to skipped and finishes degraded; fail-closed
when tasks remain unclosable. TestTopologyConformance_allTwelve runs all 12
names (10 runnable to completion, handoff/mailbox rejected as primitives).
Full suite green with -race.

Impact: task_board lit in the topology registry (all 12 topologies now
covered); RunState gains Board (persisted in runstate.json); RunOptions gains
TaskBoardLeaseSeconds; leader topology now maps to mode before plan
confirmation so Topology=leader runs no longer hit the confirmation gate.

Refs: Q2 plan WP4 (2026-10-07-agent-stack-q2q3-plans.md); task card
.task/feature-agent-stack-q2.md
2026-10-08 01:29:03 +00:00

356 lines
14 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package squad
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"time"
)
// wp4_conformance_test.go — Q2 WP4 验收:task_board 拓扑(claim/lease/complete
// 原语 + 依赖门 + 孤儿租约再武装)与全 12 拓扑 conformance 汇总跑。
// ---- task_board ----
// 菱形依赖 a→(b,c)→d:认领序尊重依赖门,全部 done,标准 finalize 收口。
func TestTopologyConformance_taskBoard(t *testing.T) {
be := &iterBackend{calls: map[string]int{}}
sink := &collectSink{}
engine := newTopologyEngine(t, mockScriptPlanner(
StepSpec{ID: "a", Role: "researcher", Title: "任务a", Targets: []string{"a.md"}},
StepSpec{ID: "b", Role: "writer", Title: "任务b", Needs: []string{"a"}, Targets: []string{"b.md"}},
StepSpec{ID: "c", Role: "reviewer", Title: "任务c", Needs: []string{"a"}, Targets: []string{"c.md"}},
StepSpec{ID: "d", Role: "writer", Title: "任务d", Needs: []string{"b", "c"}, Targets: []string{"output.md"}},
), be, sink)
res, err := engine.Run(context.Background(), Goal{Text: "任务板"}, RunOptions{Topology: TopologyTaskBoard})
if err != nil {
t.Fatal(err)
}
if res.Status != RunCompleted {
t.Fatalf("status = %s err = %v", res.Status, res.Error)
}
// 认领序尊重依赖门:a 先于 b/c,d 最后(板上按步骤序认领,确定性)。
var order []string
for _, ev := range sink.snapshot() {
if strings.Contains(ev.Text, "认领") {
order = append(order, ev.StepID)
}
}
want := []string{"a", "b", "c", "d"}
if strings.Join(order, ",") != strings.Join(want, ",") {
t.Fatalf("认领序 = %v,期望 %v", order, want)
}
st, _ := engine.loadRun(engine.runDir(res.RunID))
for _, task := range st.Board {
if task.Status != "done" {
t.Fatalf("任务 %s = %s,期望 done", task.ID, task.Status)
}
}
if sink.countText("task_board:收口(done 4/4)") != 1 {
t.Fatal("缺收口事件")
}
}
// 孤儿租约再武装:崩溃(ctx 取消)留下 claimed+过期租约 → Resume 重入
// 再武装回 open、重新认领(Attempts=2)并跑完。
func TestTaskBoardOrphanLeaseRearms(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
crashed := false
be := &iterBackend{calls: map[string]int{}, content: func(key string, _ int, _ string) []byte {
if key == "02_writer" && !crashed {
crashed = true
cancel() // 模拟进程死亡:runOneStep 在 ctx 检查处退出,步骤回到 pending
}
return nil
}}
sink := &collectSink{}
engine := newTopologyEngine(t, mockScriptPlanner(
StepSpec{ID: "t1", Role: "researcher", Title: "一", Targets: []string{"a.md"}},
StepSpec{ID: "t2", Role: "writer", Title: "二", Needs: []string{"t1"}, Targets: []string{"output.md"}},
), be, sink)
res0, err := engine.Run(ctx, Goal{Text: "任务板"}, RunOptions{Topology: TopologyTaskBoard})
if err != nil {
t.Fatal(err)
}
if res0.Status != RunCancelled {
t.Fatalf("取消后应为 RunCancelled:%s", res0.Status)
}
// 崩溃现场:t2 claimed、租约未过期;步骤在盘上是 running(setStep 只改
// 内存,取消路径的 pending 未落盘)——进程死亡即此形态。测试把租约回拨
// 成过期(孤儿)并把步骤置回 pending(模拟重启前的一致化),再走 Resume。
st, err := engine.loadRun(engine.runDir(res0.RunID))
if err != nil {
t.Fatal(err)
}
found := false
for i := range st.Board {
if st.Board[i].ID == "t2" {
found = true
if st.Board[i].Status != "claimed" || st.Board[i].Attempts != 1 {
t.Fatalf("崩溃现场 t2 = %+v", st.Board[i])
}
st.Board[i].LeaseExpires = time.Now().Add(-time.Hour) // 租约过期 = 孤儿
}
}
if !found {
t.Fatal("板上无 t2")
}
for i := range st.Plan.Workflow.Steps {
if st.Plan.Workflow.Steps[i].ID == "t2" && st.Plan.Workflow.Steps[i].Status == "running" {
st.Plan.Workflow.Steps[i].Status = "pending"
}
}
if err := st.save(); err != nil {
t.Fatal(err)
}
// 重入:孤儿租约再武装 → 重新认领 → 跑完收口。
res, err := engine.Resume(context.Background(), st.Meta.ID)
if err != nil {
t.Fatal(err)
}
if res.Status != RunCompleted {
t.Fatalf("恢复后应完成:%s %v", res.Status, res.Error)
}
if sink.countText("孤儿租约再武装 t2") != 1 {
t.Fatal("缺孤儿租约再武装事件")
}
st2, _ := engine.loadRun(engine.runDir(res.RunID))
for _, task := range st2.Board {
if task.ID == "t2" && task.Attempts != 2 {
t.Fatalf("再武装后 Attempts = %d,期望 2", task.Attempts)
}
}
}
// 依赖门级联:非关键任务失败 → 下游 open 任务级联 skipped → 降级收口。
func TestTaskBoardDependencyGateCascade(t *testing.T) {
be := &iterBackend{calls: map[string]int{}, content: func(key string, _ int, _ string) []byte {
return nil
}}
failBe := &failOnceBackend{inner: be, failKey: "02_writer"}
crit := false
sink := &collectSink{}
engine := newTopologyEngine(t, mockScriptPlanner(
StepSpec{ID: "t0", Role: "researcher", Title: "零", Targets: []string{"output.md"}},
StepSpec{ID: "t1", Role: "writer", Title: "一", Needs: []string{"t0"}, Targets: []string{"b.md"}, Critical: &crit},
StepSpec{ID: "t2", Role: "reviewer", Title: "二", Needs: []string{"t1"}, Targets: []string{"c.md"}},
), failBe, sink)
res, err := engine.Run(context.Background(), Goal{Text: "任务板"}, RunOptions{Topology: TopologyTaskBoard})
if err != nil {
t.Fatal(err)
}
if res.Status != RunDegraded {
t.Fatalf("非关键失败+级联跳过应降级收口:%s %v", res.Status, res.Error)
}
st, _ := engine.loadRun(engine.runDir(res.RunID))
byID := map[string]BoardTask{}
for _, task := range st.Board {
byID[task.ID] = task
}
if byID["t0"].Status != "done" || byID["t1"].Status != "failed" || byID["t2"].Status != "skipped" {
t.Fatalf("板状态 = %+v", byID)
}
for _, s := range st.Plan.Workflow.Steps {
if s.ID == "t2" && (s.Status != "skipped" || s.Error != boardSkipReason) {
t.Fatalf("t2 = %s %q", s.Status, s.Error)
}
}
}
// failOnceBackend 对指定目录恒定失败(非瞬态),其余委托 inner。
type failOnceBackend struct {
inner Executor
failKey string
}
func (b *failOnceBackend) Name() string { return b.inner.Name() }
func (b *failOnceBackend) Execute(ctx context.Context, req ExecRequest) (*ExecResult, error) {
key := filepath.Base(filepath.Clean(req.WorkDir))
if key == b.failKey {
return &ExecResult{Success: false, ErrorReason: "fatal: 拒绝执行"}, nil
}
return b.inner.Execute(ctx, req)
}
// ---- 12/12 汇总 ----
// TestTopologyConformance_allTwelve 全 12 内置拓扑汇总跑:每个拓扑名一次
// 脚本化最小运行(零模型零网络)。graph/mode/driver 十种断言完成收口;
// handoff/mailbox 两个 primitive 断言 fail-closed 拒绝单跑(其原语能力分别
// 由 TestTopologyConformance_handoff 与 WP2 mailbox 测试钉住)。
func TestTopologyConformance_allTwelve(t *testing.T) {
specs := BuiltinTopologies()
if len(specs) != 12 {
t.Fatalf("内置拓扑 = %d,期望 12", len(specs))
}
for _, spec := range specs {
spec := spec
t.Run(spec.Name, func(t *testing.T) {
switch spec.Name {
case TopologySequential:
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "s1", Role: "researcher", Title: "一", Targets: []string{"output.md"}},
), &iterBackend{calls: map[string]int{}}, RunOptions{}, RunCompleted)
case TopologyParallel:
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "s1", Role: "researcher", Title: "甲", Parallel: true, Targets: []string{"a.md"}},
StepSpec{ID: "s2", Role: "writer", Title: "乙", Parallel: true, Targets: []string{"output.md"}},
), &iterBackend{calls: map[string]int{}}, RunOptions{}, RunCompleted)
case TopologyLoop:
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "s1", Role: "researcher", Title: "循环体", Targets: []string{"output.md", "fields.json"},
Loop: &LoopSpec{MaxIterations: 2, UntilField: "done", UntilEquals: "yes"}},
), &iterBackend{calls: map[string]int{}, content: func(_ string, _ int, target string) []byte {
if target == "fields.json" {
return fieldsJSON(map[string]string{"done": "no"})
}
return nil
}}, RunOptions{}, RunCompleted)
case TopologyRouter:
runAgg(t, spec.Name, mockScriptPlanner(routerSteps()...),
&iterBackend{calls: map[string]int{}, content: func(_ string, _ int, target string) []byte {
if target == "fields.json" {
return fieldsJSON(map[string]string{"route": "fast"})
}
return nil
}}, RunOptions{}, RunCompleted)
case TopologyEvaluatorOptimizer:
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "draft", Role: "writer", Title: "起草", Targets: []string{"output.md"}},
StepSpec{ID: "eval", Role: "reviewer", Title: "评审", Targets: []string{"verdict.md", "fields.json"},
Loop: &LoopSpec{MaxIterations: 4, UntilField: "verdict", UntilEquals: "pass", Body: []string{"draft"}}},
), &iterBackend{calls: map[string]int{}, content: func(_ string, iter int, target string) []byte {
if target == "fields.json" {
if iter >= 3 {
return fieldsJSON(map[string]string{"verdict": "pass"})
}
return fieldsJSON(map[string]string{"verdict": "fail"})
}
return nil
}}, RunOptions{}, RunCompleted)
case TopologyLongRunning:
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "s1", Role: "researcher", Title: "一", Targets: []string{"output.md"}},
), &iterBackend{calls: map[string]int{}},
RunOptions{Deadline: time.Now().Add(5 * time.Second)}, RunCompleted)
case TopologyLeader:
b := &leaderScriptBackend{
decisions: []string{delegateJSON("writer", "撰写简报"), closeJSON},
script: map[string]map[string]string{"01_writer": {"output.md": goodReport}},
}
engine := newLeaderEngine(t, b)
res, err := engine.Run(context.Background(), Goal{Text: "汇总"}, RunOptions{Topology: TopologyLeader})
if err != nil {
t.Fatal(err)
}
if res.Status != RunCompleted {
t.Fatalf("status = %s err = %v", res.Status, res.Error)
}
case TopologyReview:
planner := mockScriptPlanner(
StepSpec{ID: "f1", Role: "researcher", Title: "评审", Targets: []string{"findings.json"}},
)
planner.Agents = []RoleSpec{
{Role: "researcher", Name: "评审", Backend: "agg-review"},
{Role: "verifier", Name: "核实", Backend: "agg-review"},
}
engine := newAggEngine(t, planner, &aggReviewBackend{}, []RoleSpec{
{Role: "researcher", Name: "评审", Backend: "agg-review"},
{Role: "verifier", Name: "核实", Backend: "agg-review"},
})
res, err := engine.Run(context.Background(), Goal{Text: "评审"},
RunOptions{Topology: TopologyReview, ReviewTarget: "材料"})
if err != nil {
t.Fatal(err)
}
if res.Status != RunCompleted {
t.Fatalf("status = %s err = %v", res.Status, res.Error)
}
data, _ := os.ReadFile(filepath.Join(res.WorkDir, "output.md"))
if !strings.Contains(string(data), "已丢弃 0 条未验证") || !strings.Contains(string(data), "样例问题") {
t.Fatalf("报告 = %s", data)
}
case TopologyGroupChat:
engine := newAggEngine(t, mockScriptPlanner(
StepSpec{ID: "p1", Role: "researcher", Title: "甲"},
StepSpec{ID: "p2", Role: "writer", Title: "乙"},
), &gcScriptBackend{}, []RoleSpec{
{Role: "researcher", Name: "甲", Backend: "gc-script"},
{Role: "writer", Name: "乙", Backend: "gc-script"},
})
res, err := engine.Run(context.Background(), Goal{Text: "群聊"},
RunOptions{Topology: TopologyGroupChat, GroupChatMaxTurns: 2})
if err != nil {
t.Fatal(err)
}
if res.Status != RunCompleted {
t.Fatalf("status = %s err = %v", res.Status, res.Error)
}
case TopologyTaskBoard:
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "t1", Role: "researcher", Title: "一", Targets: []string{"a.md"}},
StepSpec{ID: "t2", Role: "writer", Title: "二", Needs: []string{"t1"}, Targets: []string{"output.md"}},
), &iterBackend{calls: map[string]int{}}, RunOptions{}, RunCompleted)
case TopologyHandoff, TopologyMailbox:
// primitive:不可单独作为运行拓扑(fail-closed);原语能力由
// 专项 conformance 钉住(handoff/mailbox 测试)。
runAgg(t, spec.Name, mockScriptPlanner(
StepSpec{ID: "s1", Role: "researcher", Title: "一", Targets: []string{"output.md"}},
), &iterBackend{calls: map[string]int{}}, RunOptions{}, RunFailed)
default:
t.Fatalf("未覆盖的拓扑 %q", spec.Name)
}
})
}
}
// runAgg 汇总跑的最小引擎:graph 类拓扑共用 iter 三角色装配。
func runAgg(t *testing.T, topo string, planner Planner, be Executor, opts RunOptions, want RunStatus) {
t.Helper()
opts.Topology = topo
engine := newTopologyEngine(t, planner, be, nil)
res, err := engine.Run(context.Background(), Goal{Text: "汇总跑 " + topo}, opts)
if err != nil {
t.Fatal(err)
}
if res.Status != want {
t.Fatalf("status = %s err = %q,期望 %s", res.Status, res.Error, want)
}
}
// aggReviewBackend 汇总跑用的最小 review 后端:finder 出一条发现,verify 判 PASS。
type aggReviewBackend struct{}
func (b *aggReviewBackend) Name() string { return "agg-review" }
func (b *aggReviewBackend) Execute(_ context.Context, req ExecRequest) (*ExecResult, error) {
key := filepath.Base(filepath.Clean(req.WorkDir))
if strings.HasPrefix(key, "verify_") {
return writeOne(req.WorkDir, "verdict.md", "核对成立。\nVERDICT: PASS"), nil
}
return writeOne(req.WorkDir, "findings.json",
`[{"location":"第1段","severity":"high","issue":"样例问题","evidence":"样例证据"}]`), nil
}
// newAggEngine 自定义角色表的汇总引擎(backend 实例名 = be.Name())。
func newAggEngine(t *testing.T, planner Planner, be Executor, roles []RoleSpec) *SquadEngine {
t.Helper()
dir := t.TempDir()
reg := NewRoleRegistry()
for _, r := range roles {
if err := reg.Register(r); err != nil {
t.Fatal(err)
}
}
backends := NewBackendResolver()
backends.RegisterInstance(be.Name(), be)
engine, err := NewEngine(Options{DataDir: dir, Registry: reg, Planner: planner, Backends: backends, Sink: NopSink{}})
if err != nil {
t.Fatal(err)
}
return engine
}