Merge pull request #1536 from alexhoshina/fix/allow-picoclaw-media-tempdir

Fix: allow picoclaw media tempdir

pkg/agent/instance.go

@@ -10,6 +10,7 @@ import (
 	"strings"
 
 	"github.com/sipeed/picoclaw/pkg/config"
+	"github.com/sipeed/picoclaw/pkg/media"
 	"github.com/sipeed/picoclaw/pkg/memory"
 	"github.com/sipeed/picoclaw/pkg/providers"
 	"github.com/sipeed/picoclaw/pkg/routing"
@@ -66,7 +67,7 @@ func NewAgentInstance(
 	readRestrict := restrict && !defaults.AllowReadOutsideWorkspace
 
 	// Compile path whitelist patterns from config.
-	allowReadPaths := compilePatterns(cfg.Tools.AllowReadPaths)
+	allowReadPaths := buildAllowReadPatterns(cfg)
 	allowWritePaths := compilePatterns(cfg.Tools.AllowWritePaths)
 
 	toolsRegistry := tools.NewToolRegistry()
@@ -82,7 +83,7 @@ func NewAgentInstance(
 		toolsRegistry.Register(tools.NewListDirTool(workspace, readRestrict, allowReadPaths))
 	}
 	if cfg.Tools.IsToolEnabled("exec") {
-		execTool, err := tools.NewExecToolWithConfig(workspace, restrict, cfg)
+		execTool, err := tools.NewExecToolWithConfig(workspace, restrict, cfg, allowReadPaths)
 		if err != nil {
 			log.Fatalf("Critical error: unable to initialize exec tool: %v", err)
 		}
@@ -282,6 +283,28 @@ func compilePatterns(patterns []string) []*regexp.Regexp {
 	return compiled
 }
 
+func buildAllowReadPatterns(cfg *config.Config) []*regexp.Regexp {
+	var configured []string
+	if cfg != nil {
+		configured = cfg.Tools.AllowReadPaths
+	}
+
+	compiled := compilePatterns(configured)
+	mediaDirPattern := regexp.MustCompile(mediaTempDirPattern())
+	for _, pattern := range compiled {
+		if pattern.String() == mediaDirPattern.String() {
+			return compiled
+		}
+	}
+
+	return append(compiled, mediaDirPattern)
+}
+
+func mediaTempDirPattern() string {
+	sep := regexp.QuoteMeta(string(os.PathSeparator))
+	return "^" + regexp.QuoteMeta(filepath.Clean(media.TempDir())) + "(?:" + sep + "|$)"
+}
+
 // Close releases resources held by the agent's session store.
 func (a *AgentInstance) Close() error {
 	if a.Sessions != nil {

pkg/agent/instance_test.go

@@ -1,10 +1,14 @@
 package agent
 
 import (
+	"context"
 	"os"
+	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/sipeed/picoclaw/pkg/config"
+	"github.com/sipeed/picoclaw/pkg/media"
 )
 
 func TestNewAgentInstance_UsesDefaultsTemperatureAndMaxTokens(t *testing.T) {
@@ -160,3 +164,85 @@ func TestNewAgentInstance_ResolveCandidatesFromModelListAlias(t *testing.T) {
 		})
 	}
 }
+
+func TestNewAgentInstance_AllowsMediaTempDirForReadListAndExec(t *testing.T) {
+	workspace := t.TempDir()
+	mediaDir := media.TempDir()
+	if err := os.MkdirAll(mediaDir, 0o700); err != nil {
+		t.Fatalf("MkdirAll(mediaDir) error = %v", err)
+	}
+
+	mediaFile, err := os.CreateTemp(mediaDir, "instance-tool-*.txt")
+	if err != nil {
+		t.Fatalf("CreateTemp(mediaDir) error = %v", err)
+	}
+	mediaPath := mediaFile.Name()
+	if _, err := mediaFile.WriteString("attachment content"); err != nil {
+		mediaFile.Close()
+		t.Fatalf("WriteString(mediaFile) error = %v", err)
+	}
+	if err := mediaFile.Close(); err != nil {
+		t.Fatalf("Close(mediaFile) error = %v", err)
+	}
+	t.Cleanup(func() { _ = os.Remove(mediaPath) })
+
+	cfg := &config.Config{
+		Agents: config.AgentsConfig{
+			Defaults: config.AgentDefaults{
+				Workspace:           workspace,
+				Model:               "test-model",
+				RestrictToWorkspace: true,
+			},
+		},
+		Tools: config.ToolsConfig{
+			ReadFile: config.ReadFileToolConfig{Enabled: true},
+			ListDir:  config.ToolConfig{Enabled: true},
+			Exec: config.ExecConfig{
+				ToolConfig:         config.ToolConfig{Enabled: true},
+				EnableDenyPatterns: true,
+				AllowRemote:        true,
+			},
+		},
+	}
+
+	agent := NewAgentInstance(nil, &cfg.Agents.Defaults, cfg, &mockProvider{})
+
+	readTool, ok := agent.Tools.Get("read_file")
+	if !ok {
+		t.Fatal("read_file tool not registered")
+	}
+	readResult := readTool.Execute(context.Background(), map[string]any{"path": mediaPath})
+	if readResult.IsError {
+		t.Fatalf("read_file should allow media temp dir, got: %s", readResult.ForLLM)
+	}
+	if !strings.Contains(readResult.ForLLM, "attachment content") {
+		t.Fatalf("read_file output missing media content: %s", readResult.ForLLM)
+	}
+
+	listTool, ok := agent.Tools.Get("list_dir")
+	if !ok {
+		t.Fatal("list_dir tool not registered")
+	}
+	listResult := listTool.Execute(context.Background(), map[string]any{"path": mediaDir})
+	if listResult.IsError {
+		t.Fatalf("list_dir should allow media temp dir, got: %s", listResult.ForLLM)
+	}
+	if !strings.Contains(listResult.ForLLM, filepath.Base(mediaPath)) {
+		t.Fatalf("list_dir output missing media file: %s", listResult.ForLLM)
+	}
+
+	execTool, ok := agent.Tools.Get("exec")
+	if !ok {
+		t.Fatal("exec tool not registered")
+	}
+	execResult := execTool.Execute(context.Background(), map[string]any{
+		"command":     "cat " + filepath.Base(mediaPath),
+		"working_dir": mediaDir,
+	})
+	if execResult.IsError {
+		t.Fatalf("exec should allow media temp dir, got: %s", execResult.ForLLM)
+	}
+	if !strings.Contains(execResult.ForLLM, "attachment content") {
+		t.Fatalf("exec output missing media content: %s", execResult.ForLLM)
+	}
+}

pkg/agent/loop.go

@@ -117,6 +117,8 @@ func registerSharedTools(
 	registry *AgentRegistry,
 	provider providers.LLMProvider,
 ) {
+	allowReadPaths := buildAllowReadPatterns(cfg)
+
 	for _, agentID := range registry.ListAgentIDs() {
 		agent, ok := registry.GetAgent(agentID)
 		if !ok {
@@ -195,6 +197,7 @@ func registerSharedTools(
 				cfg.Agents.Defaults.RestrictToWorkspace,
 				cfg.Agents.Defaults.GetMaxMediaSize(),
 				nil,
+				allowReadPaths,
 			)
 			agent.Tools.Register(sendFileTool)
 		}