精简动作审查输入并支持审批来源定位 (#125)
* fix: 精简审查背景并区分人工消息与调度输入 * fix: 模型审查仅提交当前调用与选定背景 * feat: 审批来源定位原会话并移除 Worker 审查背景
This commit is contained in:
1 parent
0d6fa880b8
commit
04d25eb133
30 files changed
+1143
-465
No files matched your search
@@ -4,20 +4,19 @@ import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/Autumn-27/artex/db"
|
||||
"github.com/Autumn-27/artex/guard"
|
||||
"github.com/Autumn-27/artex/intercept"
|
||||
"github.com/Autumn-27/norma/agentcore"
|
||||
"github.com/Autumn-27/norma/llm"
|
||||
"github.com/Autumn-27/norma/permission"
|
||||
"github.com/Autumn-27/norma/tool"
|
||||
)
|
||||
|
||||
// Real PostgreSQL + SDK hooks: the second call must see both the first result
|
||||
// and a newly registered task constraint. No model or shell command is executed.
|
||||
func TestTaskReviewContextAcrossToolCalls(t *testing.T) {
|
||||
// Real PostgreSQL + SDK hooks: Worker reviews receive the current call only.
|
||||
// Intent summaries, inherited background and prior execution are excluded.
|
||||
func TestWorkerReviewContextAcrossToolCalls(t *testing.T) {
|
||||
dsn, _, err := db.DSN()
|
||||
if err != nil {
|
||||
t.Skip("no test database configured")
|
||||
@@ -53,13 +52,9 @@ func TestTaskReviewContextAcrossToolCalls(t *testing.T) {
|
||||
}
|
||||
var inputs []intercept.ReviewInput
|
||||
ic.SetReviewer(func(_ context.Context, _ int64, _ string, in intercept.ReviewInput) (intercept.Decision, error) {
|
||||
if in.Task == nil {
|
||||
t.Error("reviewer did not receive task context")
|
||||
return intercept.Decision{Action: "deny"}, nil
|
||||
}
|
||||
inputs = append(inputs, in)
|
||||
action := "allow"
|
||||
if len(in.Task.Constraints) > 0 {
|
||||
if string(in.Arguments) == `{"step":2}` {
|
||||
action = "deny"
|
||||
}
|
||||
return intercept.Decision{Action: action, Message: "probe policy"}, nil
|
||||
@@ -90,10 +85,16 @@ func TestTaskReviewContextAcrossToolCalls(t *testing.T) {
|
||||
})
|
||||
workDir := t.TempDir()
|
||||
ctx := intercept.WithTaskContext(t.Context(), taskID, "test-agent", nil)
|
||||
ctx = withTaskReviewContext(ctx, expID, ts, workDir, &db.Node{Payload: json.RawMessage(`{"summary":"创建并清理"}`)})
|
||||
_, _, err = captureRun(ctx, agentcore.Options{Provider: provider, Tools: []tool.CoreTool{probe},
|
||||
Hooks: guard.NewWithInterceptor(ic).Hooks(), PermissionMode: permission.ModeBypass, WorkingDir: workDir, MaxTurns: 3},
|
||||
"请完成当前验证步骤", nil)
|
||||
ctx = intercept.WithReviewContext(ctx, "/parent", intercept.ReviewBackground{Source: intercept.BackgroundUserMessage, Text: "PARENT_BACKGROUND_SENTINEL"})
|
||||
intentPayload := map[string]any{"summary": "创建并清理", "extra": "FULL_INTENT_SENTINEL"}
|
||||
intentID, err := ts.AddNode("intent", intentPayload, 0, "running", "planner", nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
rawIntent, _ := json.Marshal(intentPayload)
|
||||
worker := NewWorker(provider, "test-model", workDir, nil, 0, 3, probe)
|
||||
_, _, err = worker.Execute(ctx, "test-agent", expID, nil, ts, &db.Node{ID: intentID, Payload: rawIntent}, guard.NewWithInterceptor(ic).Hooks(), nil, nil, nil)
|
||||
runDir := ensureRunDir(workDir, expID, intentID)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -101,15 +102,25 @@ func TestTaskReviewContextAcrossToolCalls(t *testing.T) {
|
||||
t.Fatalf("reviews=%d executions=%d", len(inputs), executions)
|
||||
}
|
||||
first, second := inputs[0], inputs[1]
|
||||
if first.Task == nil || first.Task.TaskID != expID || first.Task.Description != "只操作隔离测试目录" || len(first.Task.Constraints) != 0 || len(first.History) != 0 {
|
||||
t.Fatalf("wrong initial task snapshot: %+v", first)
|
||||
for _, in := range inputs {
|
||||
if in.Version != 4 || in.Background != nil || in.WorkingDir != runDir {
|
||||
t.Fatalf("unexpected Worker background: %+v", in)
|
||||
}
|
||||
raw, _ := json.Marshal(in)
|
||||
for _, forbidden := range []string{"创建并清理", "PARENT_BACKGROUND_SENTINEL", `"background"`, "只操作隔离测试目录", "验证创建和清理", "禁止后续清理", "FULL_INTENT_SENTINEL", "全局探索态势", `"task_id"`, `"task"`, `"turn_input"`, `"worker_intent"`, `"history"`, `"history_truncated"`, `"correlation"`, "Created a new fixture"} {
|
||||
if strings.Contains(string(raw), forbidden) {
|
||||
t.Fatalf("unexpected review data: %s", forbidden)
|
||||
}
|
||||
}
|
||||
}
|
||||
if second.Task.Goal != "验证创建和清理" || len(second.Task.Constraints) != 1 || second.Task.Constraints[0].Text != "禁止后续清理" || second.WorkingDir != workDir || second.Intent == "" || second.TurnInput != "请完成当前验证步骤" {
|
||||
t.Fatalf("lost fresh task context: %+v", second)
|
||||
constraints, err := ts.ListConstraints()
|
||||
if err != nil || len(constraints) != 1 {
|
||||
t.Fatal("Agent task constraints were unexpectedly changed")
|
||||
}
|
||||
if second.Correlation != "exact" || len(second.History) != 1 || second.History[0].ToolUseID != "call-1" || second.History[0].Status != "succeeded" || string(second.Arguments) != `{"step":2}` {
|
||||
t.Fatalf("lost paired execution evidence: %+v", second)
|
||||
if string(first.Arguments) != `{"step":1}` || string(second.Arguments) != `{"step":2}` {
|
||||
t.Fatal("review lost current parameters")
|
||||
}
|
||||
|
||||
rows, err := d.ListTaskIntercepts(taskID)
|
||||
if err != nil || len(rows) != 2 {
|
||||
t.Fatalf("rows=%d err=%v", len(rows), err)
|
||||
@@ -120,31 +131,29 @@ func TestTaskReviewContextAcrossToolCalls(t *testing.T) {
|
||||
t.Fatalf("verdict lost model input: %+v err=%v", detail, err)
|
||||
}
|
||||
var saved intercept.ReviewInput
|
||||
if json.Unmarshal(detail.Audit.ModelInput, &saved) != nil || saved.Task == nil || saved.TurnInput != first.TurnInput {
|
||||
t.Fatal("stored review input cannot reconstruct the actual task context")
|
||||
if json.Unmarshal(detail.Audit.ModelInput, &saved) != nil || saved.Background != nil || saved.Version != 4 {
|
||||
t.Fatal("stored Worker review input retained a background")
|
||||
}
|
||||
if row.Status == "allowed" && (detail.Audit.ExecutionStatus != "succeeded" || len(saved.Task.Constraints) != 0) {
|
||||
t.Fatal("automatic allow lost execution result or its original constraint snapshot")
|
||||
if row.Status == "allowed" && (detail.Audit.ExecutionStatus != "succeeded" || saved.Version != 4) {
|
||||
t.Fatal("automatic allow lost execution result or its original background snapshot")
|
||||
}
|
||||
if detail.Audit.Correlation != "exact" {
|
||||
t.Fatal("audit lost call correlation")
|
||||
}
|
||||
if row.Status == "denied" {
|
||||
found := false
|
||||
for _, entry := range detail.Audit.Context {
|
||||
if entry.Kind == "tool_result" && entry.ToolUseID == "call-1" && strings.Contains(entry.Text, "Created a new fixture") {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatal("prior execution missing from separate audit")
|
||||
}
|
||||
}
|
||||
if row.Status == "denied" && detail.Audit.ExecutionStatus != "not_executed" {
|
||||
t.Fatal("denial recorded an execution")
|
||||
}
|
||||
}
|
||||
|
||||
t.Run("unavailable_constraints_do_not_fail_open", func(t *testing.T) {
|
||||
if err := ic.SetJudgeConfig(intercept.JudgeConfig{Enabled: true, FailAction: "allow"}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
ic.SetReviewer(func(context.Context, int64, string, intercept.ReviewInput) (intercept.Decision, error) {
|
||||
t.Error("reviewer called without required task constraints")
|
||||
return intercept.Decision{Action: "allow"}, nil
|
||||
})
|
||||
ctx := intercept.WithReviewContext(t.Context(), workDir, "", func(context.Context) (*intercept.ReviewTask, error) {
|
||||
return nil, fmt.Errorf("task database unavailable")
|
||||
})
|
||||
decision, judged := ic.Judge(ctx, probeName, json.RawMessage(`{}`))
|
||||
if !judged || decision.Action != "ask" || !decision.ModelFallback || len(decision.ModelInput) != 0 {
|
||||
t.Fatalf("missing policy was silently allowed: %+v", decision)
|
||||
}
|
||||
})
|
||||
}
|
||||
Reference in new issue
Block a user