Files
Agent-System-Backend/internal/runmgr/exec_tool_artifact_test.go
weichen fec2d16cc6 Close Task 10 renderer delivery gaps
Why:
- Independent review found trusted-boundary, semantic parity, replay-budget,
  comparison, persistence, cancellation, provenance, and routing gaps.
- Storage migration must include the new durable delivery table.

Evidence:
- go test -count=1 ./...
- go test -race ./internal/docgen ./internal/tools ./internal/runmgr
- go test ./... (deps/agent-document-renderer)
- go vet ./...
- go build ./...
- CGO_ENABLED=0 go build -trimpath ./cmd/agent-system
- Python house-style unittest suite and git diff --check

Impact:
- Word delivery now uses host-owned freezes, Markdown-first resumable persistence,
  closed registration boundaries, semantic shared rendering, and real comparison.
- Controlled/project documents still fail closed to RDM and non-Word flows remain
  unchanged.

Refs:
- Unified Document Renderer implementation plan Task 10
- /tmp/task10-backend-review-last.md
- Renderer d5cd8c126045a27d5a5cc5da23f64d3c737e116a
2026-10-15 21:44:03 +00:00

253 lines
9.2 KiB
Go

// ExecuteTool 工件回填契约(交付物卡片根因修复的验收):注册表工具经
// rc.WriteArtifact 写入的工件必须出现在 ToolCallResult.Artifact 上——
// llm.go 据此生成对话内 artifact_ref 卡片部件。此前只有超长截断路径会设置它。
package runmgr
import (
"context"
"crypto/sha256"
"encoding/hex"
"encoding/json"
"os"
"path/filepath"
"reflect"
"strings"
"testing"
"time"
"agent-document-renderer/render"
"agent-system-backend/internal/bus"
"agent-system-backend/internal/docgen"
"agent-system-backend/internal/settings"
"agent-system-backend/internal/store"
"agent-system-backend/internal/tools"
core "agent-system-core"
)
func newExecEnv(t *testing.T) (*runCtx, *store.Store) {
t.Helper()
st, err := store.OpenSQLite(filepath.Join(t.TempDir(), "exec.db"))
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { st.Close() })
b := bus.New()
reg := tools.NewRegistry()
if err := reg.RegisterBuiltin(); err != nil {
t.Fatal(err)
}
proj, err := st.CreateProject("alice", "p1")
if err != nil {
t.Fatal(err)
}
conv, err := st.CreateConversation("alice", proj.ID, "c1", "")
if err != nil {
t.Fatal(err)
}
svc := settings.NewService(st)
m := &Manager{st: st, bus: b, registry: reg, settings: svc, events: newEventBuffer(st, b)}
eff := svc.Effective("alice", "")
c := &runCtx{
mgr: m, run: core.Run{ProjectID: proj.ID, ConversationID: conv.ID, Owner: "alice"},
prof: core.AgentProfile{}, eff: eff, ctx: context.Background(),
}
return c, st
}
func TestExecuteToolBackfillsArtifact(t *testing.T) {
c, _ := newExecEnv(t)
res := c.ExecuteTool(core.ToolCallRequest{
CallID: "call1", Name: "write_artifact",
Arguments: json.RawMessage(`{"name":"summary.md","kind":"document","content":"# 摘要正文"}`),
})
if res.Status != "ok" {
t.Fatalf("write_artifact: %s", res.Output)
}
if res.Artifact == nil {
t.Fatal("ToolCallResult.Artifact 未回填——对话内交付物卡片不会出现(回归)")
}
if res.Artifact.Name != "summary.md" {
t.Errorf("回填工件名不符: %+v", res.Artifact)
}
}
// Arbitrary Python may create local DOCX bytes, but cannot publish them as a
// trusted Word delivery without the host renderer operation.
func TestRunPythonDOCXCannotRegisterAsTrustedDelivery(t *testing.T) {
c, st := newExecEnv(t)
root := t.TempDir()
c.mgr.SetWorkspaceRoot(root)
if err := tools.RegisterExecTools(c.mgr.registry); err != nil {
t.Fatal(err)
}
if err := tools.RegisterInterpreterTools(c.mgr.registry); err != nil {
t.Fatal(err)
}
// 夹具必须是结构合法的最小 docx:登记口会做 OPC 结构自检,
// 伪 zip(PK 魔数+垃圾字节)现在会被拒绝而非登记。
py := c.ExecuteTool(core.ToolCallRequest{
CallID: "py1", Name: "run_python",
Arguments: json.RawMessage(`{"script":"import zipfile\nwith zipfile.ZipFile('note.docx','w') as z:\n z.writestr('[Content_Types].xml','<?xml version=\"1.0\"?><Types/>')\n z.writestr('word/document.xml','<?xml version=\"1.0\"?><doc/>')\n"}`),
})
if py.Status != "ok" || !strings.Contains(py.Output, "exit=0") {
t.Fatalf("run_python: %s %s", py.Status, py.Output)
}
res := c.ExecuteTool(core.ToolCallRequest{
CallID: "reg1", Name: "register_artifact",
Arguments: json.RawMessage(`{"path":"note.docx"}`),
})
if res.Status != "error" || res.Artifact != nil || !strings.Contains(res.Output, "render_document") {
t.Fatalf("direct DOCX registration was not rejected: %+v", res)
}
b, err := os.ReadFile(filepath.Join(root, "alice", c.run.ConversationID, "note.docx"))
if err != nil {
t.Fatal(err)
}
if string(b[:4]) != "PK\x03\x04" {
t.Fatalf("stored bytes: %q", b)
}
artifacts, err := st.ListArtifacts("alice", c.run.ProjectID)
if err != nil || len(artifacts) != 0 {
t.Fatalf("rejected DOCX became visible: %+v err=%v", artifacts, err)
}
}
// 空手工具(如 time_now)不得凭空挂 Artifact。
func TestExecuteToolNoArtifactByDefault(t *testing.T) {
c, _ := newExecEnv(t)
res := c.ExecuteTool(core.ToolCallRequest{CallID: "c1", Name: "time_now", Arguments: json.RawMessage(`{}`)})
if res.Status != "ok" || res.Artifact != nil {
t.Errorf("无产物工具不应携带 Artifact: %+v", res)
}
}
func TestGeneratedDocxIsSearchable(t *testing.T) {
c, st := newExecEnv(t)
const marker = "zebraindexword"
delivery, err := docgen.Generate(context.Background(), docgen.Request{
DocumentID: "searchable", Title: "纪要", DocumentType: "general", Language: "zh-CN",
Markdown: []byte("结论:" + marker), Mode: render.ModePreview,
FrozenAt: time.Date(2026, 10, 15, 12, 0, 0, 0, time.UTC), RequestedBy: "alice",
})
if err != nil {
t.Fatal(err)
}
mime := "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
if _, err := c.WriteArtifact("note.docx", "document", mime, delivery.DOCX.Bytes); err != nil {
t.Fatal(err)
}
hits, err := st.SearchKnowledge("alice", core.RetrievalQuery{Text: marker, ProjectID: c.run.ProjectID, TopK: 5})
if err != nil {
t.Fatal(err)
}
if len(hits) == 0 {
t.Fatal("generated docx text was not indexed")
}
if _, err := c.WriteArtifact("bad.docx", "document", mime, []byte("notazipmarker")); err != nil {
t.Fatal(err)
}
hits, err = st.SearchKnowledge("alice", core.RetrievalQuery{Text: "notazipmarker", ProjectID: c.run.ProjectID, TopK: 5})
if err != nil {
t.Fatal(err)
}
if len(hits) != 0 {
t.Fatalf("unparseable docx bytes should not be indexed, got %d hits", len(hits))
}
}
func TestRenderedDeliverySurvivesRestartWithStableIdentity(t *testing.T) {
databasePath := filepath.Join(t.TempDir(), "renderer-restart.db")
st, err := store.OpenSQLite(databasePath)
if err != nil {
t.Fatal(err)
}
if err := st.EnsureUser("alice", "Alice"); err != nil {
t.Fatal(err)
}
registry := tools.NewRegistry()
if err := registry.RegisterBuiltin(); err != nil {
t.Fatal(err)
}
project, err := st.CreateProject("alice", "p1")
if err != nil {
t.Fatal(err)
}
conversation, err := st.CreateConversation("alice", project.ID, "c1", "")
if err != nil {
t.Fatal(err)
}
eventBus := bus.New()
events := newEventBuffer(st, eventBus)
eventsStopped := false
t.Cleanup(func() {
if !eventsStopped {
events.stop()
}
})
manager := &Manager{st: st, bus: eventBus, registry: registry, settings: settings.NewService(st), events: events}
run := &runCtx{
mgr: manager, run: core.Run{ID: "run-before-restart", ProjectID: project.ID, ConversationID: conversation.ID, Owner: "alice"},
prof: core.AgentProfile{}, eff: manager.settings.Effective("alice", ""), ctx: context.Background(),
}
args := json.RawMessage(`{"operationId":"restart-operation","name":"重启纪要","documentId":"restart-minutes","documentType":"general","language":"zh-CN","markdown":"# 重启纪要\n\n缓存身份保持。\n","mode":"preview","controlled":false,"projectDocument":false}`)
result := run.ExecuteTool(core.ToolCallRequest{CallID: "render-restart", Name: "render_document", Arguments: args})
if result.Status != "ok" {
t.Fatalf("render_document: %s", result.Output)
}
var firstReceipt docgen.OperationReceipt
if err := json.Unmarshal([]byte(result.Output), &firstReceipt); err != nil || firstReceipt.FrozenAt.IsZero() {
t.Fatalf("first receipt=%#v err=%v", firstReceipt, err)
}
artifacts, err := st.ListArtifacts("alice", project.ID)
if err != nil || len(artifacts) != 4 {
t.Fatalf("stored artifacts=%d err=%v", len(artifacts), err)
}
want := map[string]string{}
for _, item := range artifacts {
raw, err := st.ArtifactContentByID(item.ID)
if err != nil {
t.Fatal(err)
}
sum := sha256.Sum256(raw)
want[item.ID] = hex.EncodeToString(sum[:])
}
events.stop()
eventsStopped = true
if err := st.Close(); err != nil {
t.Fatal(err)
}
reopened, err := store.OpenSQLite(databasePath)
if err != nil {
t.Fatal(err)
}
defer reopened.Close()
reopenedBus := bus.New()
reopenedEvents := newEventBuffer(reopened, reopenedBus)
defer reopenedEvents.stop()
reopenedManager := &Manager{st: reopened, bus: reopenedBus, registry: registry, settings: settings.NewService(reopened), events: reopenedEvents}
reopenedRun := &runCtx{
mgr: reopenedManager, run: core.Run{ID: "run-after-restart", ProjectID: project.ID, ConversationID: conversation.ID, Owner: "alice"},
prof: core.AgentProfile{}, eff: reopenedManager.settings.Effective("alice", ""), ctx: context.Background(),
}
retryResult := reopenedRun.ExecuteTool(core.ToolCallRequest{CallID: "render-restart-retry", Name: "render_document", Arguments: args})
if retryResult.Status != "ok" {
t.Fatalf("restart retry: %s", retryResult.Output)
}
var retryReceipt docgen.OperationReceipt
if err := json.Unmarshal([]byte(retryResult.Output), &retryReceipt); err != nil || !retryReceipt.CacheHit ||
!retryReceipt.FrozenAt.Equal(firstReceipt.FrozenAt) || !reflect.DeepEqual(retryReceipt.Artifacts, firstReceipt.Artifacts) {
t.Fatalf("restart receipt changed: first=%#v retry=%#v err=%v", firstReceipt, retryReceipt, err)
}
for artifactID, wantHash := range want {
raw, err := reopened.ArtifactContentByID(artifactID)
if err != nil {
t.Fatalf("artifact %s after restart: %v", artifactID, err)
}
sum := sha256.Sum256(raw)
if got := hex.EncodeToString(sum[:]); got != wantHash {
t.Errorf("artifact %s hash after restart = %s, want %s", artifactID, got, wantHash)
}
}
}