Skip to content

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

4.9 KB
Raw Blame
package agent

import (
	"context"
	"encoding/json"
	"sync"
	"testing"
	"time"

	"github.com/Tencent/WeKnora/internal/agent/tools"
	"github.com/Tencent/WeKnora/internal/event"
	"github.com/Tencent/WeKnora/internal/types"
	"github.com/stretchr/testify/require"
)

type orderedTestTool struct {
	tools.BaseTool
	run func(context.Context) *types.ToolResult
}

func (t *orderedTestTool) Execute(ctx context.Context, _ json.RawMessage) (*types.ToolResult, error) {
	return t.run(ctx), nil
}

func TestParallelReadsRespectMutationBarriers(t *testing.T) {
	engine := newTestEngine(t, &mockChat{})
	engine.toolRegistry = tools.NewToolRegistry()
	var mu sync.Mutex
	var order []string
	readStarts := make(chan struct{}, 2)
	allowReads := make(chan struct{})
	register := func(name string, run func(context.Context)) {
		engine.toolRegistry.RegisterTool(&orderedTestTool{
			BaseTool: tools.NewBaseTool(name, "", json.RawMessage(`{"type":"object"}`)),
			run: func(ctx context.Context) *types.ToolResult {
				run(ctx)
				mu.Lock()
				order = append(order, name)
				mu.Unlock()
				return &types.ToolResult{Success: true}
			},
		})
	}
	for _, name := range []string{tools.ToolSearchKnowledge, tools.ToolReadDocument} {
		register(name, func(ctx context.Context) {
			readStarts <- struct{}{}
			select {
			case <-allowReads:
			case <-ctx.Done():
			}
		})
	}
	register(tools.ToolWriteSandboxFile, func(context.Context) {})
	register(tools.ToolShellExec, func(context.Context) {})
	register(tools.ToolReadFile, func(context.Context) {})
	register("mcp_unknown_mutation", func(context.Context) {})
	names := []string{
		tools.ToolSearchKnowledge, tools.ToolReadDocument, tools.ToolWriteSandboxFile,
		tools.ToolShellExec, tools.ToolReadFile, "mcp_unknown_mutation",
	}
	response := &types.ChatResponse{}
	for _, name := range names {
		response.ToolCalls = append(response.ToolCalls, types.LLMToolCall{ID: name, Function: types.FunctionCall{Name: name, Arguments: `{}`}})
	}
	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
	defer cancel()
	step := &types.AgentStep{}
	done := make(chan struct{})
	go func() {
		defer close(done)
		engine.executeToolCallsParallel(ctx, response, step, 0, "session", "message")
	}()
	for i := 0; i < 2; i++ {
		select {
		case <-readStarts:
		case <-ctx.Done():
			t.Fatal("independent reads did not run concurrently")
		}
	}
	close(allowReads)
	select {
	case <-done:
	case <-ctx.Done():
		t.Fatal("execution did not finish")
	}
	require.ElementsMatch(t, names[:2], order[:2])
	require.Equal(t, names[2:], order[2:], "write, execute, read and unknown mutation must retain order")
	for i, call := range step.ToolCalls {
		require.Equal(t, names[i], call.Name, "result events retain original order")
	}
}

func TestParallelToolPanicFailsOnlyThatCall(t *testing.T) {
	engine := newTestEngine(t, &mockChat{})
	engine.toolRegistry = tools.NewToolRegistry()
	engine.toolRegistry.RegisterTool(&orderedTestTool{
		BaseTool: tools.NewBaseTool(tools.ToolSearchKnowledge, "", json.RawMessage(`{"type":"object"}`)),
		run:      func(context.Context) *types.ToolResult { panic("tool bug") },
	})
	engine.toolRegistry.RegisterTool(&orderedTestTool{
		BaseTool: tools.NewBaseTool(tools.ToolReadDocument, "", json.RawMessage(`{"type":"object"}`)),
		run:      func(context.Context) *types.ToolResult { return &types.ToolResult{Success: true, Output: "ok"} },
	})
	response := &types.ChatResponse{ToolCalls: []types.LLMToolCall{
		{ID: "a", Function: types.FunctionCall{Name: tools.ToolSearchKnowledge, Arguments: `{}`}},
		{ID: "b", Function: types.FunctionCall{Name: tools.ToolReadDocument, Arguments: `{}`}},
	}}
	step := &types.AgentStep{}

	engine.executeToolCallsParallel(context.Background(), response, step, 0, "session", "message")

	require.Len(t, step.ToolCalls, 2)
	require.False(t, step.ToolCalls[0].Result.Success)
	require.Contains(t, step.ToolCalls[0].Result.Error, "internal error")
	require.True(t, step.ToolCalls[1].Result.Success)
}

func TestToolOutcomeKeepsLiveDataChangeOutOfModelAndHistory(t *testing.T) {
	engine := newTestEngine(t, &mockChat{})
	marker := map[string]any{"operation": "agent.delete", "area": "agent"}
	call := types.ToolCall{Name: tools.ToolRunOperation, Result: &types.ToolResult{
		Success: true, Output: "done", Data: map[string]any{"data_change": marker},
	}}
	var outcomes []event.AgentToolResultData
	engine.eventBus.On(event.EventAgentToolResult, func(_ context.Context, evt event.Event) error {
		outcomes = append(outcomes, evt.Data.(event.AgentToolResultData))
		return nil
	})
	engine.emitToolOutcome(context.Background(), call, 0, "session")
	require.Len(t, outcomes, 1)
	require.Equal(t, marker, outcomes[0].Data["data_change"])
	messages := engine.appendToolResults(nil, types.AgentStep{ToolCalls: []types.ToolCall{call}})
	require.Equal(t, "done", messages[len(messages)-1].Content)
	stored := tools.SanitizeAgentStepsForStorage([]types.AgentStep{{ToolCalls: []types.ToolCall{call}}})
	require.NotContains(t, stored[0].ToolCalls[0].Result.Data, "data_change")
}