refactor: restructure codebase to internal/ directory with modular architecture

- Move all source files to internal/{app,backend,config,executor,logger,parser,utils}
- Integrate third-party libraries: zerolog, goccy/go-json, gopsutil, cobra/viper
- Add comprehensive unit tests for utils package (94.3% coverage)
- Add performance benchmarks for string operations
- Fix error display: cleanup warnings no longer pollute Recent Errors
- Add GitHub Actions CI workflow
- Add Makefile for build automation
- Add README documentation

Generated with SWE-Agent.ai

Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>

codeagent-wrapper/internal/app/agent_validation_test.go

@@ -0,0 +1,150 @@
+package wrapper
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	config "codeagent-wrapper/internal/config"
+	executor "codeagent-wrapper/internal/executor"
+)
+
+func TestValidateAgentName(t *testing.T) {
+	tests := []struct {
+		name    string
+		input   string
+		wantErr bool
+	}{
+		{name: "simple", input: "develop", wantErr: false},
+		{name: "upper", input: "ABC", wantErr: false},
+		{name: "digits", input: "a1", wantErr: false},
+		{name: "dash underscore", input: "a-b_c", wantErr: false},
+		{name: "empty", input: "", wantErr: true},
+		{name: "space", input: "a b", wantErr: true},
+		{name: "slash", input: "a/b", wantErr: true},
+		{name: "dotdot", input: "../evil", wantErr: true},
+		{name: "unicode", input: "中文", wantErr: true},
+		{name: "symbol", input: "a$b", wantErr: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := config.ValidateAgentName(tt.input)
+			if (err != nil) != tt.wantErr {
+				t.Fatalf("validateAgentName(%q) err=%v, wantErr=%v", tt.input, err, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestParseArgs_InvalidAgentNameRejected(t *testing.T) {
+	defer resetTestHooks()
+	os.Args = []string{"codeagent-wrapper", "--agent", "../evil", "task"}
+	if _, err := parseArgs(); err == nil {
+		t.Fatalf("expected parseArgs to reject invalid agent name")
+	}
+}
+
+func TestParseParallelConfig_InvalidAgentNameRejected(t *testing.T) {
+	input := `---TASK---
+id: task-1
+agent: ../evil
+---CONTENT---
+do something`
+	if _, err := parseParallelConfig([]byte(input)); err == nil {
+		t.Fatalf("expected parseParallelConfig to reject invalid agent name")
+	}
+}
+
+func TestParseParallelConfig_ResolvesAgentPromptFile(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(config.ResetModelsConfigCacheForTest)
+	config.ResetModelsConfigCacheForTest()
+
+	configDir := filepath.Join(home, ".codeagent")
+	if err := os.MkdirAll(configDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+	if err := os.WriteFile(filepath.Join(configDir, "models.json"), []byte(`{
+  "default_backend": "codex",
+  "default_model": "gpt-test",
+  "agents": {
+    "custom-agent": {
+      "backend": "codex",
+      "model": "gpt-test",
+      "prompt_file": "~/.claude/prompt.md"
+    }
+  }
+}`), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	input := `---TASK---
+id: task-1
+agent: custom-agent
+---CONTENT---
+do something`
+	cfg, err := parseParallelConfig([]byte(input))
+	if err != nil {
+		t.Fatalf("parseParallelConfig() unexpected error: %v", err)
+	}
+	if len(cfg.Tasks) != 1 {
+		t.Fatalf("expected 1 task, got %d", len(cfg.Tasks))
+	}
+	if got := cfg.Tasks[0].PromptFile; got != "~/.claude/prompt.md" {
+		t.Fatalf("PromptFile = %q, want %q", got, "~/.claude/prompt.md")
+	}
+}
+
+func TestDefaultRunCodexTaskFn_AppliesAgentPromptFile(t *testing.T) {
+	defer resetTestHooks()
+
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	claudeDir := filepath.Join(home, ".claude")
+	if err := os.MkdirAll(claudeDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+	if err := os.WriteFile(filepath.Join(claudeDir, "prompt.md"), []byte("P\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	fake := newFakeCmd(fakeCmdConfig{
+		StdoutPlan: []fakeStdoutEvent{
+			{Data: `{"type":"item.completed","item":{"type":"agent_message","text":"ok"}}` + "\n"},
+		},
+		WaitDelay: 2 * time.Millisecond,
+	})
+
+	_ = executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner { return fake })
+	_ = executor.SetSelectBackendFn(func(name string) (Backend, error) {
+		return testBackend{
+			name:    name,
+			command: "fake-cmd",
+			argsFn: func(cfg *Config, targetArg string) []string {
+				return []string{targetArg}
+			},
+		}, nil
+	})
+
+	res := defaultRunCodexTaskFn(TaskSpec{
+		ID:         "t",
+		Task:       "do",
+		Backend:    "codex",
+		PromptFile: "~/.claude/prompt.md",
+	}, 5)
+	if res.ExitCode != 0 {
+		t.Fatalf("unexpected result: %+v", res)
+	}
+
+	want := "<agent-prompt>\nP\n</agent-prompt>\n\ndo"
+	if got := fake.StdinContents(); got != want {
+		t.Fatalf("stdin mismatch:\n got=%q\nwant=%q", got, want)
+	}
+}

codeagent-wrapper/internal/app/app.go

@@ -0,0 +1,278 @@
+package wrapper
+
+import (
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+)
+
+const (
+	version               = "6.0.0-alpha1"
+	defaultWorkdir        = "."
+	defaultTimeout        = 7200 // seconds (2 hours)
+	defaultCoverageTarget = 90.0
+	codexLogLineLimit     = 1000
+	stdinSpecialChars     = "\n\\\"'`$"
+	stderrCaptureLimit    = 4 * 1024
+	defaultBackendName    = "codex"
+	defaultCodexCommand   = "codex"
+
+	// stdout close reasons
+	stdoutCloseReasonWait  = "wait-done"
+	stdoutCloseReasonDrain = "drain-timeout"
+	stdoutCloseReasonCtx   = "context-cancel"
+	stdoutDrainTimeout     = 100 * time.Millisecond
+)
+
+// Test hooks for dependency injection
+var (
+	stdinReader         io.Reader = os.Stdin
+	isTerminalFn                  = defaultIsTerminal
+	codexCommand                  = defaultCodexCommand
+	cleanupHook         func()
+	startupCleanupAsync = true
+
+	buildCodexArgsFn   = buildCodexArgs
+	selectBackendFn    = selectBackend
+	cleanupLogsFn      = cleanupOldLogs
+	defaultBuildArgsFn = buildCodexArgs
+	runTaskFn          = runCodexTask
+	exitFn             = os.Exit
+)
+
+func runStartupCleanup() {
+	if cleanupLogsFn == nil {
+		return
+	}
+	defer func() {
+		if r := recover(); r != nil {
+			logWarn(fmt.Sprintf("cleanupOldLogs panic: %v", r))
+		}
+	}()
+	if _, err := cleanupLogsFn(); err != nil {
+		logWarn(fmt.Sprintf("cleanupOldLogs error: %v", err))
+	}
+}
+
+func scheduleStartupCleanup() {
+	if !startupCleanupAsync {
+		runStartupCleanup()
+		return
+	}
+	if cleanupLogsFn == nil {
+		return
+	}
+	fn := cleanupLogsFn
+	go func() {
+		defer func() {
+			if r := recover(); r != nil {
+				logWarn(fmt.Sprintf("cleanupOldLogs panic: %v", r))
+			}
+		}()
+		if _, err := fn(); err != nil {
+			logWarn(fmt.Sprintf("cleanupOldLogs error: %v", err))
+		}
+	}()
+}
+
+func runCleanupMode() int {
+	if cleanupLogsFn == nil {
+		fmt.Fprintln(os.Stderr, "Cleanup failed: log cleanup function not configured")
+		return 1
+	}
+
+	stats, err := cleanupLogsFn()
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "Cleanup failed: %v\n", err)
+		return 1
+	}
+
+	fmt.Println("Cleanup completed")
+	fmt.Printf("Files scanned: %d\n", stats.Scanned)
+	fmt.Printf("Files deleted: %d\n", stats.Deleted)
+	if len(stats.DeletedFiles) > 0 {
+		for _, f := range stats.DeletedFiles {
+			fmt.Printf("  - %s\n", f)
+		}
+	}
+	fmt.Printf("Files kept: %d\n", stats.Kept)
+	if len(stats.KeptFiles) > 0 {
+		for _, f := range stats.KeptFiles {
+			fmt.Printf("  - %s\n", f)
+		}
+	}
+	if stats.Errors > 0 {
+		fmt.Printf("Deletion errors: %d\n", stats.Errors)
+	}
+	return 0
+}
+
+func readAgentPromptFile(path string, allowOutsideClaudeDir bool) (string, error) {
+	raw := strings.TrimSpace(path)
+	if raw == "" {
+		return "", nil
+	}
+
+	expanded := raw
+	if raw == "~" || strings.HasPrefix(raw, "~/") || strings.HasPrefix(raw, "~\\") {
+		home, err := os.UserHomeDir()
+		if err != nil {
+			return "", err
+		}
+		if raw == "~" {
+			expanded = home
+		} else {
+			expanded = home + raw[1:]
+		}
+	}
+
+	absPath, err := filepath.Abs(expanded)
+	if err != nil {
+		return "", err
+	}
+	absPath = filepath.Clean(absPath)
+
+	home, err := os.UserHomeDir()
+	if err != nil {
+		if !allowOutsideClaudeDir {
+			return "", err
+		}
+		logWarn(fmt.Sprintf("Failed to resolve home directory for prompt file validation: %v; proceeding without restriction", err))
+	} else {
+		allowedDirs := []string{
+			filepath.Clean(filepath.Join(home, ".claude")),
+			filepath.Clean(filepath.Join(home, ".codeagent", "agents")),
+		}
+		for i := range allowedDirs {
+			allowedAbs, err := filepath.Abs(allowedDirs[i])
+			if err == nil {
+				allowedDirs[i] = filepath.Clean(allowedAbs)
+			}
+		}
+
+		isWithinDir := func(path, dir string) bool {
+			rel, err := filepath.Rel(dir, path)
+			if err != nil {
+				return false
+			}
+			rel = filepath.Clean(rel)
+			if rel == "." {
+				return true
+			}
+			if rel == ".." {
+				return false
+			}
+			prefix := ".." + string(os.PathSeparator)
+			return !strings.HasPrefix(rel, prefix)
+		}
+
+		if !allowOutsideClaudeDir {
+			withinAllowed := false
+			for _, dir := range allowedDirs {
+				if isWithinDir(absPath, dir) {
+					withinAllowed = true
+					break
+				}
+			}
+			if !withinAllowed {
+				logWarn(fmt.Sprintf("Refusing to read prompt file outside allowed dirs (%s): %s", strings.Join(allowedDirs, ", "), absPath))
+				return "", fmt.Errorf("prompt file must be under ~/.claude or ~/.codeagent/agents")
+			}
+
+			resolvedPath, errPath := filepath.EvalSymlinks(absPath)
+			if errPath == nil {
+				resolvedPath = filepath.Clean(resolvedPath)
+				resolvedAllowed := make([]string, 0, len(allowedDirs))
+				for _, dir := range allowedDirs {
+					resolvedBase, errBase := filepath.EvalSymlinks(dir)
+					if errBase != nil {
+						continue
+					}
+					resolvedAllowed = append(resolvedAllowed, filepath.Clean(resolvedBase))
+				}
+				if len(resolvedAllowed) > 0 {
+					withinResolved := false
+					for _, dir := range resolvedAllowed {
+						if isWithinDir(resolvedPath, dir) {
+							withinResolved = true
+							break
+						}
+					}
+					if !withinResolved {
+						logWarn(fmt.Sprintf("Refusing to read prompt file outside allowed dirs (%s) (resolved): %s", strings.Join(resolvedAllowed, ", "), resolvedPath))
+						return "", fmt.Errorf("prompt file must be under ~/.claude or ~/.codeagent/agents")
+					}
+				}
+			}
+		} else {
+			withinAllowed := false
+			for _, dir := range allowedDirs {
+				if isWithinDir(absPath, dir) {
+					withinAllowed = true
+					break
+				}
+			}
+			if !withinAllowed {
+				logWarn(fmt.Sprintf("Reading prompt file outside allowed dirs (%s): %s", strings.Join(allowedDirs, ", "), absPath))
+			}
+		}
+	}
+
+	data, err := os.ReadFile(absPath)
+	if err != nil {
+		return "", err
+	}
+	return strings.TrimRight(string(data), "\r\n"), nil
+}
+
+func wrapTaskWithAgentPrompt(prompt string, task string) string {
+	return "<agent-prompt>\n" + prompt + "\n</agent-prompt>\n\n" + task
+}
+
+func runCleanupHook() {
+	if logger := activeLogger(); logger != nil {
+		logger.Flush()
+	}
+	if cleanupHook != nil {
+		cleanupHook()
+	}
+}
+
+func printHelp() {
+	name := currentWrapperName()
+	help := fmt.Sprintf(`%[1]s - Go wrapper for AI CLI backends
+
+Usage:
+    %[1]s "task" [workdir]
+    %[1]s --backend claude "task" [workdir]
+    %[1]s --prompt-file /path/to/prompt.md "task" [workdir]
+    %[1]s - [workdir]              Read task from stdin
+    %[1]s resume <session_id> "task" [workdir]
+    %[1]s resume <session_id> - [workdir]
+    %[1]s --parallel               Run tasks in parallel (config from stdin)
+    %[1]s --parallel --full-output Run tasks in parallel with full output (legacy)
+    %[1]s --version
+    %[1]s --help
+
+Parallel mode examples:
+    %[1]s --parallel < tasks.txt
+    echo '...' | %[1]s --parallel
+    %[1]s --parallel --full-output < tasks.txt
+    %[1]s --parallel <<'EOF'
+
+Environment Variables:
+    CODEX_TIMEOUT         Timeout in milliseconds (default: 7200000)
+    CODEAGENT_ASCII_MODE  Use ASCII symbols instead of Unicode (PASS/WARN/FAIL)
+
+Exit Codes:
+    0    Success
+    1    General error (missing args, no output)
+    124  Timeout
+    127  backend command not found
+    130  Interrupted (Ctrl+C)
+    *    Passthrough from backend process`, name)
+	fmt.Println(help)
+}

codeagent-wrapper/internal/app/backend.go

@@ -0,0 +1,9 @@
+package wrapper
+
+import backend "codeagent-wrapper/internal/backend"
+
+type Backend = backend.Backend
+type CodexBackend = backend.CodexBackend
+type ClaudeBackend = backend.ClaudeBackend
+type GeminiBackend = backend.GeminiBackend
+type OpencodeBackend = backend.OpencodeBackend

codeagent-wrapper/internal/app/backend_init.go

@@ -0,0 +1,7 @@
+package wrapper
+
+import backend "codeagent-wrapper/internal/backend"
+
+func init() {
+	backend.SetLogFuncs(logWarn, logError)
+}

codeagent-wrapper/internal/app/backend_registry.go

@@ -0,0 +1,5 @@
+package wrapper
+
+import backend "codeagent-wrapper/internal/backend"
+
+func selectBackend(name string) (Backend, error) { return backend.Select(name) }

codeagent-wrapper/internal/app/bench_test.go

@@ -0,0 +1,103 @@
+package wrapper
+
+import (
+	"bytes"
+	"os"
+	"testing"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+var (
+	benchCmdSink      any
+	benchConfigSink   *Config
+	benchMessageSink  string
+	benchThreadIDSink string
+)
+
+// BenchmarkStartup_NewRootCommand measures CLI startup overhead (command+flags construction).
+func BenchmarkStartup_NewRootCommand(b *testing.B) {
+	b.ReportAllocs()
+	for i := 0; i < b.N; i++ {
+		benchCmdSink = newRootCommand()
+	}
+}
+
+// BenchmarkConfigParse_ParseArgs measures config parsing from argv/env (steady-state).
+func BenchmarkConfigParse_ParseArgs(b *testing.B) {
+	home := b.TempDir()
+	b.Setenv("HOME", home)
+	b.Setenv("USERPROFILE", home)
+
+	config.ResetModelsConfigCacheForTest()
+	b.Cleanup(config.ResetModelsConfigCacheForTest)
+
+	origArgs := os.Args
+	os.Args = []string{"codeagent-wrapper", "--agent", "develop", "task"}
+	b.Cleanup(func() { os.Args = origArgs })
+
+	if _, err := parseArgs(); err != nil {
+		b.Fatalf("warmup parseArgs() error: %v", err)
+	}
+
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		cfg, err := parseArgs()
+		if err != nil {
+			b.Fatalf("parseArgs() error: %v", err)
+		}
+		benchConfigSink = cfg
+	}
+}
+
+// BenchmarkJSONParse_ParseJSONStreamInternal measures line-delimited JSON stream parsing.
+func BenchmarkJSONParse_ParseJSONStreamInternal(b *testing.B) {
+	stream := []byte(
+		`{"type":"thread.started","thread_id":"t"}` + "\n" +
+			`{"type":"item.completed","item":{"type":"agent_message","text":"hello"}}` + "\n" +
+			`{"type":"thread.completed","thread_id":"t"}` + "\n",
+	)
+	b.SetBytes(int64(len(stream)))
+
+	b.ReportAllocs()
+	for i := 0; i < b.N; i++ {
+		message, threadID := parseJSONStreamInternal(bytes.NewReader(stream), nil, nil, nil, nil)
+		benchMessageSink = message
+		benchThreadIDSink = threadID
+	}
+}
+
+// BenchmarkLoggerWrite 测试日志写入性能
+func BenchmarkLoggerWrite(b *testing.B) {
+	logger, err := NewLogger()
+	if err != nil {
+		b.Fatal(err)
+	}
+	defer logger.Close()
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		logger.Info("benchmark log message")
+	}
+	b.StopTimer()
+	logger.Flush()
+}
+
+// BenchmarkLoggerConcurrentWrite 测试并发日志写入性能
+func BenchmarkLoggerConcurrentWrite(b *testing.B) {
+	logger, err := NewLogger()
+	if err != nil {
+		b.Fatal(err)
+	}
+	defer logger.Close()
+
+	b.ResetTimer()
+	b.RunParallel(func(pb *testing.PB) {
+		for pb.Next() {
+			logger.Info("concurrent benchmark log message")
+		}
+	})
+	b.StopTimer()
+	logger.Flush()
+}

codeagent-wrapper/internal/app/cli.go

@@ -0,0 +1,657 @@
+package wrapper
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"reflect"
+	"strings"
+
+	config "codeagent-wrapper/internal/config"
+
+	"github.com/spf13/cobra"
+	"github.com/spf13/pflag"
+	"github.com/spf13/viper"
+)
+
+type exitError struct {
+	code int
+}
+
+func (e exitError) Error() string {
+	return fmt.Sprintf("exit %d", e.code)
+}
+
+type cliOptions struct {
+	Backend         string
+	Model           string
+	ReasoningEffort string
+	Agent           string
+	PromptFile      string
+	SkipPermissions bool
+
+	Parallel   bool
+	FullOutput bool
+
+	Cleanup    bool
+	Version    bool
+	ConfigFile string
+}
+
+func Main() {
+	Run()
+}
+
+// Run is the program entrypoint for cmd/codeagent/main.go.
+func Run() {
+	exitFn(run())
+}
+
+func run() int {
+	cmd := newRootCommand()
+	cmd.SetArgs(os.Args[1:])
+	if err := cmd.Execute(); err != nil {
+		var ee exitError
+		if errors.As(err, &ee) {
+			return ee.code
+		}
+		return 1
+	}
+	return 0
+}
+
+func newRootCommand() *cobra.Command {
+	name := currentWrapperName()
+	opts := &cliOptions{}
+
+	cmd := &cobra.Command{
+		Use:           fmt.Sprintf("%s [flags] <task>|resume <session_id> <task> [workdir]", name),
+		Short:         "Go wrapper for AI CLI backends",
+		SilenceErrors: true,
+		SilenceUsage:  true,
+		Args:          cobra.ArbitraryArgs,
+		RunE: func(cmd *cobra.Command, args []string) error {
+			if opts.Version {
+				fmt.Printf("%s version %s\n", name, version)
+				return nil
+			}
+			if opts.Cleanup {
+				code := runCleanupMode()
+				if code == 0 {
+					return nil
+				}
+				return exitError{code: code}
+			}
+
+			exitCode := runWithLoggerAndCleanup(func() int {
+				v, err := config.NewViper(opts.ConfigFile)
+				if err != nil {
+					logError(err.Error())
+					return 1
+				}
+
+				if opts.Parallel {
+					return runParallelMode(cmd, args, opts, v, name)
+				}
+
+				logInfo("Script started")
+
+				cfg, err := buildSingleConfig(cmd, args, os.Args[1:], opts, v)
+				if err != nil {
+					logError(err.Error())
+					return 1
+				}
+				logInfo(fmt.Sprintf("Parsed args: mode=%s, task_len=%d, backend=%s", cfg.Mode, len(cfg.Task), cfg.Backend))
+				return runSingleMode(cfg, name)
+			})
+
+			if exitCode == 0 {
+				return nil
+			}
+			return exitError{code: exitCode}
+		},
+	}
+	cmd.CompletionOptions.DisableDefaultCmd = true
+
+	addRootFlags(cmd.Flags(), opts)
+	cmd.AddCommand(newVersionCommand(name), newCleanupCommand())
+
+	return cmd
+}
+
+func addRootFlags(fs *pflag.FlagSet, opts *cliOptions) {
+	fs.StringVar(&opts.ConfigFile, "config", "", "Config file path (default: $HOME/.codeagent/config.*)")
+	fs.BoolVarP(&opts.Version, "version", "v", false, "Print version and exit")
+	fs.BoolVar(&opts.Cleanup, "cleanup", false, "Clean up old logs and exit")
+
+	fs.BoolVar(&opts.Parallel, "parallel", false, "Run tasks in parallel (config from stdin)")
+	fs.BoolVar(&opts.FullOutput, "full-output", false, "Parallel mode: include full task output (legacy)")
+
+	fs.StringVar(&opts.Backend, "backend", defaultBackendName, "Backend to use (codex, claude, gemini, opencode)")
+	fs.StringVar(&opts.Model, "model", "", "Model override")
+	fs.StringVar(&opts.ReasoningEffort, "reasoning-effort", "", "Reasoning effort (backend-specific)")
+	fs.StringVar(&opts.Agent, "agent", "", "Agent preset name (from ~/.codeagent/models.json)")
+	fs.StringVar(&opts.PromptFile, "prompt-file", "", "Prompt file path")
+
+	fs.BoolVar(&opts.SkipPermissions, "skip-permissions", false, "Skip permissions prompts (also via CODEAGENT_SKIP_PERMISSIONS)")
+	fs.BoolVar(&opts.SkipPermissions, "dangerously-skip-permissions", false, "Alias for --skip-permissions")
+}
+
+func newVersionCommand(name string) *cobra.Command {
+	return &cobra.Command{
+		Use:           "version",
+		Short:         "Print version and exit",
+		SilenceErrors: true,
+		SilenceUsage:  true,
+		RunE: func(cmd *cobra.Command, args []string) error {
+			fmt.Printf("%s version %s\n", name, version)
+			return nil
+		},
+	}
+}
+
+func newCleanupCommand() *cobra.Command {
+	return &cobra.Command{
+		Use:           "cleanup",
+		Short:         "Clean up old logs and exit",
+		SilenceErrors: true,
+		SilenceUsage:  true,
+		RunE: func(cmd *cobra.Command, args []string) error {
+			code := runCleanupMode()
+			if code == 0 {
+				return nil
+			}
+			return exitError{code: code}
+		},
+	}
+}
+
+func runWithLoggerAndCleanup(fn func() int) (exitCode int) {
+	logger, err := NewLogger()
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "ERROR: failed to initialize logger: %v\n", err)
+		return 1
+	}
+	setLogger(logger)
+
+	defer func() {
+		logger := activeLogger()
+		if logger != nil {
+			logger.Flush()
+		}
+		if err := closeLogger(); err != nil {
+			fmt.Fprintf(os.Stderr, "ERROR: failed to close logger: %v\n", err)
+		}
+		if logger == nil {
+			return
+		}
+
+		if exitCode != 0 {
+			if entries := logger.ExtractRecentErrors(10); len(entries) > 0 {
+				fmt.Fprintln(os.Stderr, "\n=== Recent Errors ===")
+				for _, entry := range entries {
+					fmt.Fprintln(os.Stderr, entry)
+				}
+				fmt.Fprintf(os.Stderr, "Log file: %s (deleted)\n", logger.Path())
+			}
+		}
+		_ = logger.RemoveLogFile()
+	}()
+	defer runCleanupHook()
+
+	// Clean up stale logs from previous runs.
+	scheduleStartupCleanup()
+
+	return fn()
+}
+
+func parseArgs() (*Config, error) {
+	opts := &cliOptions{}
+	cmd := &cobra.Command{SilenceErrors: true, SilenceUsage: true, Args: cobra.ArbitraryArgs}
+	addRootFlags(cmd.Flags(), opts)
+
+	rawArgv := os.Args[1:]
+	if err := cmd.ParseFlags(rawArgv); err != nil {
+		return nil, err
+	}
+	args := cmd.Flags().Args()
+
+	v, err := config.NewViper(opts.ConfigFile)
+	if err != nil {
+		return nil, err
+	}
+
+	return buildSingleConfig(cmd, args, rawArgv, opts, v)
+}
+
+func buildSingleConfig(cmd *cobra.Command, args []string, rawArgv []string, opts *cliOptions, v *viper.Viper) (*Config, error) {
+	backendName := defaultBackendName
+	model := ""
+	reasoningEffort := ""
+	agentName := ""
+	promptFile := ""
+	promptFileExplicit := false
+	yolo := false
+
+	if cmd.Flags().Changed("agent") {
+		agentName = strings.TrimSpace(opts.Agent)
+		if agentName == "" {
+			return nil, fmt.Errorf("--agent flag requires a value")
+		}
+		if err := config.ValidateAgentName(agentName); err != nil {
+			return nil, fmt.Errorf("--agent flag invalid value: %w", err)
+		}
+	} else {
+		agentName = strings.TrimSpace(v.GetString("agent"))
+		if agentName != "" {
+			if err := config.ValidateAgentName(agentName); err != nil {
+				return nil, fmt.Errorf("--agent flag invalid value: %w", err)
+			}
+		}
+	}
+
+	var resolvedBackend, resolvedModel, resolvedPromptFile, resolvedReasoning string
+	if agentName != "" {
+		var resolvedYolo bool
+		resolvedBackend, resolvedModel, resolvedPromptFile, resolvedReasoning, _, _, resolvedYolo = config.ResolveAgentConfig(agentName)
+		yolo = resolvedYolo
+	}
+
+	if cmd.Flags().Changed("prompt-file") {
+		promptFile = strings.TrimSpace(opts.PromptFile)
+		if promptFile == "" {
+			return nil, fmt.Errorf("--prompt-file flag requires a value")
+		}
+		promptFileExplicit = true
+	} else if val := strings.TrimSpace(v.GetString("prompt-file")); val != "" {
+		promptFile = val
+		promptFileExplicit = true
+	} else {
+		promptFile = resolvedPromptFile
+	}
+
+	agentFlagChanged := cmd.Flags().Changed("agent")
+	backendFlagChanged := cmd.Flags().Changed("backend")
+	if backendFlagChanged {
+		backendName = strings.TrimSpace(opts.Backend)
+		if backendName == "" {
+			return nil, fmt.Errorf("--backend flag requires a value")
+		}
+	}
+
+	switch {
+	case agentFlagChanged && backendFlagChanged && lastFlagIndex(rawArgv, "agent") > lastFlagIndex(rawArgv, "backend"):
+		backendName = resolvedBackend
+	case !backendFlagChanged && agentName != "":
+		backendName = resolvedBackend
+	case !backendFlagChanged:
+		if val := strings.TrimSpace(v.GetString("backend")); val != "" {
+			backendName = val
+		}
+	}
+
+	modelFlagChanged := cmd.Flags().Changed("model")
+	if modelFlagChanged {
+		model = strings.TrimSpace(opts.Model)
+		if model == "" {
+			return nil, fmt.Errorf("--model flag requires a value")
+		}
+	}
+
+	switch {
+	case agentFlagChanged && modelFlagChanged && lastFlagIndex(rawArgv, "agent") > lastFlagIndex(rawArgv, "model"):
+		model = strings.TrimSpace(resolvedModel)
+	case !modelFlagChanged && agentName != "":
+		model = strings.TrimSpace(resolvedModel)
+	case !modelFlagChanged:
+		model = strings.TrimSpace(v.GetString("model"))
+	}
+
+	if cmd.Flags().Changed("reasoning-effort") {
+		reasoningEffort = strings.TrimSpace(opts.ReasoningEffort)
+		if reasoningEffort == "" {
+			return nil, fmt.Errorf("--reasoning-effort flag requires a value")
+		}
+	} else if val := strings.TrimSpace(v.GetString("reasoning-effort")); val != "" {
+		reasoningEffort = val
+	} else if agentName != "" {
+		reasoningEffort = strings.TrimSpace(resolvedReasoning)
+	}
+
+	skipChanged := cmd.Flags().Changed("skip-permissions") || cmd.Flags().Changed("dangerously-skip-permissions")
+	skipPermissions := false
+	if skipChanged {
+		skipPermissions = opts.SkipPermissions
+	} else {
+		skipPermissions = v.GetBool("skip-permissions")
+	}
+
+	if len(args) == 0 {
+		return nil, fmt.Errorf("task required")
+	}
+
+	cfg := &Config{
+		WorkDir:            defaultWorkdir,
+		Backend:            backendName,
+		Agent:              agentName,
+		PromptFile:         promptFile,
+		PromptFileExplicit: promptFileExplicit,
+		SkipPermissions:    skipPermissions,
+		Yolo:               yolo,
+		Model:              model,
+		ReasoningEffort:    reasoningEffort,
+		MaxParallelWorkers: config.ResolveMaxParallelWorkers(),
+	}
+
+	if args[0] == "resume" {
+		if len(args) < 3 {
+			return nil, fmt.Errorf("resume mode requires: resume <session_id> <task>")
+		}
+		cfg.Mode = "resume"
+		cfg.SessionID = strings.TrimSpace(args[1])
+		if cfg.SessionID == "" {
+			return nil, fmt.Errorf("resume mode requires non-empty session_id")
+		}
+		cfg.Task = args[2]
+		cfg.ExplicitStdin = (args[2] == "-")
+		if len(args) > 3 {
+			if args[3] == "-" {
+				return nil, fmt.Errorf("invalid workdir: '-' is not a valid directory path")
+			}
+			cfg.WorkDir = args[3]
+		}
+	} else {
+		cfg.Mode = "new"
+		cfg.Task = args[0]
+		cfg.ExplicitStdin = (args[0] == "-")
+		if len(args) > 1 {
+			if args[1] == "-" {
+				return nil, fmt.Errorf("invalid workdir: '-' is not a valid directory path")
+			}
+			cfg.WorkDir = args[1]
+		}
+	}
+
+	return cfg, nil
+}
+
+func lastFlagIndex(argv []string, name string) int {
+	if len(argv) == 0 {
+		return -1
+	}
+	name = strings.TrimSpace(name)
+	if name == "" {
+		return -1
+	}
+
+	needle := "--" + name
+	prefix := needle + "="
+	last := -1
+	for i, arg := range argv {
+		if arg == needle || strings.HasPrefix(arg, prefix) {
+			last = i
+		}
+	}
+	return last
+}
+
+func runParallelMode(cmd *cobra.Command, args []string, opts *cliOptions, v *viper.Viper, name string) int {
+	if len(args) > 0 {
+		fmt.Fprintln(os.Stderr, "ERROR: --parallel reads its task configuration from stdin; no positional arguments are allowed.")
+		fmt.Fprintln(os.Stderr, "Usage examples:")
+		fmt.Fprintf(os.Stderr, "  %s --parallel < tasks.txt\n", name)
+		fmt.Fprintf(os.Stderr, "  echo '...' | %s --parallel\n", name)
+		fmt.Fprintf(os.Stderr, "  %s --parallel <<'EOF'\n", name)
+		fmt.Fprintf(os.Stderr, "  %s --parallel --full-output <<'EOF'  # include full task output\n", name)
+		return 1
+	}
+
+	if cmd.Flags().Changed("agent") || cmd.Flags().Changed("prompt-file") || cmd.Flags().Changed("reasoning-effort") {
+		fmt.Fprintln(os.Stderr, "ERROR: --parallel reads its task configuration from stdin; only --backend, --model, --full-output and --skip-permissions are allowed.")
+		return 1
+	}
+
+	backendName := defaultBackendName
+	if cmd.Flags().Changed("backend") {
+		backendName = strings.TrimSpace(opts.Backend)
+		if backendName == "" {
+			fmt.Fprintln(os.Stderr, "ERROR: --backend flag requires a value")
+			return 1
+		}
+	} else if val := strings.TrimSpace(v.GetString("backend")); val != "" {
+		backendName = val
+	}
+
+	model := ""
+	if cmd.Flags().Changed("model") {
+		model = strings.TrimSpace(opts.Model)
+		if model == "" {
+			fmt.Fprintln(os.Stderr, "ERROR: --model flag requires a value")
+			return 1
+		}
+	} else {
+		model = strings.TrimSpace(v.GetString("model"))
+	}
+
+	fullOutput := opts.FullOutput
+	if !cmd.Flags().Changed("full-output") && v.IsSet("full-output") {
+		fullOutput = v.GetBool("full-output")
+	}
+
+	skipChanged := cmd.Flags().Changed("skip-permissions") || cmd.Flags().Changed("dangerously-skip-permissions")
+	skipPermissions := false
+	if skipChanged {
+		skipPermissions = opts.SkipPermissions
+	} else {
+		skipPermissions = v.GetBool("skip-permissions")
+	}
+
+	backend, err := selectBackendFn(backendName)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "ERROR: %v\n", err)
+		return 1
+	}
+	backendName = backend.Name()
+
+	data, err := io.ReadAll(stdinReader)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "ERROR: failed to read stdin: %v\n", err)
+		return 1
+	}
+
+	cfg, err := parseParallelConfig(data)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "ERROR: %v\n", err)
+		return 1
+	}
+
+	cfg.GlobalBackend = backendName
+	model = strings.TrimSpace(model)
+	for i := range cfg.Tasks {
+		if strings.TrimSpace(cfg.Tasks[i].Backend) == "" {
+			cfg.Tasks[i].Backend = backendName
+		}
+		if strings.TrimSpace(cfg.Tasks[i].Model) == "" && model != "" {
+			cfg.Tasks[i].Model = model
+		}
+		cfg.Tasks[i].SkipPermissions = cfg.Tasks[i].SkipPermissions || skipPermissions
+	}
+
+	timeoutSec := resolveTimeout()
+	layers, err := topologicalSort(cfg.Tasks)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "ERROR: %v\n", err)
+		return 1
+	}
+
+	results := executeConcurrent(layers, timeoutSec)
+
+	for i := range results {
+		results[i].CoverageTarget = defaultCoverageTarget
+		if results[i].Message == "" {
+			continue
+		}
+
+		lines := strings.Split(results[i].Message, "\n")
+		results[i].Coverage = extractCoverageFromLines(lines)
+		results[i].CoverageNum = extractCoverageNum(results[i].Coverage)
+		results[i].FilesChanged = extractFilesChangedFromLines(lines)
+		results[i].TestsPassed, results[i].TestsFailed = extractTestResultsFromLines(lines)
+		results[i].KeyOutput = extractKeyOutputFromLines(lines, 150)
+	}
+
+	fmt.Println(generateFinalOutputWithMode(results, !fullOutput))
+
+	exitCode := 0
+	for _, res := range results {
+		if res.ExitCode != 0 {
+			exitCode = res.ExitCode
+		}
+	}
+	return exitCode
+}
+
+func runSingleMode(cfg *Config, name string) int {
+	backend, err := selectBackendFn(cfg.Backend)
+	if err != nil {
+		logError(err.Error())
+		return 1
+	}
+	cfg.Backend = backend.Name()
+
+	cmdInjected := codexCommand != defaultCodexCommand
+	argsInjected := buildCodexArgsFn != nil && reflect.ValueOf(buildCodexArgsFn).Pointer() != reflect.ValueOf(defaultBuildArgsFn).Pointer()
+
+	if backend.Name() != defaultBackendName || !cmdInjected {
+		codexCommand = backend.Command()
+	}
+	if backend.Name() != defaultBackendName || !argsInjected {
+		buildCodexArgsFn = backend.BuildArgs
+	}
+	logInfo(fmt.Sprintf("Selected backend: %s", backend.Name()))
+
+	timeoutSec := resolveTimeout()
+	logInfo(fmt.Sprintf("Timeout: %ds", timeoutSec))
+	cfg.Timeout = timeoutSec
+
+	var taskText string
+	var piped bool
+
+	if cfg.ExplicitStdin {
+		logInfo("Explicit stdin mode: reading task from stdin")
+		data, err := io.ReadAll(stdinReader)
+		if err != nil {
+			logError("Failed to read stdin: " + err.Error())
+			return 1
+		}
+		taskText = string(data)
+		if taskText == "" {
+			logError("Explicit stdin mode requires task input from stdin")
+			return 1
+		}
+		piped = !isTerminal()
+	} else {
+		pipedTask, err := readPipedTask()
+		if err != nil {
+			logError("Failed to read piped stdin: " + err.Error())
+			return 1
+		}
+		piped = pipedTask != ""
+		if piped {
+			taskText = pipedTask
+		} else {
+			taskText = cfg.Task
+		}
+	}
+
+	if strings.TrimSpace(cfg.PromptFile) != "" {
+		prompt, err := readAgentPromptFile(cfg.PromptFile, cfg.PromptFileExplicit)
+		if err != nil {
+			logError("Failed to read prompt file: " + err.Error())
+			return 1
+		}
+		taskText = wrapTaskWithAgentPrompt(prompt, taskText)
+	}
+
+	useStdin := cfg.ExplicitStdin || shouldUseStdin(taskText, piped)
+
+	targetArg := taskText
+	if useStdin {
+		targetArg = "-"
+	}
+	codexArgs := buildCodexArgsFn(cfg, targetArg)
+
+	logger := activeLogger()
+	if logger == nil {
+		fmt.Fprintln(os.Stderr, "ERROR: logger is not initialized")
+		return 1
+	}
+
+	fmt.Fprintf(os.Stderr, "[%s]\n", name)
+	fmt.Fprintf(os.Stderr, "  Backend: %s\n", cfg.Backend)
+	fmt.Fprintf(os.Stderr, "  Command: %s %s\n", codexCommand, strings.Join(codexArgs, " "))
+	fmt.Fprintf(os.Stderr, "  PID: %d\n", os.Getpid())
+	fmt.Fprintf(os.Stderr, "  Log: %s\n", logger.Path())
+
+	if useStdin {
+		var reasons []string
+		if piped {
+			reasons = append(reasons, "piped input")
+		}
+		if cfg.ExplicitStdin {
+			reasons = append(reasons, "explicit \"-\"")
+		}
+		if strings.Contains(taskText, "\n") {
+			reasons = append(reasons, "newline")
+		}
+		if strings.Contains(taskText, "\\") {
+			reasons = append(reasons, "backslash")
+		}
+		if strings.Contains(taskText, "\"") {
+			reasons = append(reasons, "double-quote")
+		}
+		if strings.Contains(taskText, "'") {
+			reasons = append(reasons, "single-quote")
+		}
+		if strings.Contains(taskText, "`") {
+			reasons = append(reasons, "backtick")
+		}
+		if strings.Contains(taskText, "$") {
+			reasons = append(reasons, "dollar")
+		}
+		if len(taskText) > 800 {
+			reasons = append(reasons, "length>800")
+		}
+		if len(reasons) > 0 {
+			logWarn(fmt.Sprintf("Using stdin mode for task due to: %s", strings.Join(reasons, ", ")))
+		}
+	}
+
+	logInfo(fmt.Sprintf("%s running...", cfg.Backend))
+
+	taskSpec := TaskSpec{
+		Task:            taskText,
+		WorkDir:         cfg.WorkDir,
+		Mode:            cfg.Mode,
+		SessionID:       cfg.SessionID,
+		Model:           cfg.Model,
+		ReasoningEffort: cfg.ReasoningEffort,
+		Agent:           cfg.Agent,
+		SkipPermissions: cfg.SkipPermissions,
+		UseStdin:        useStdin,
+	}
+
+	result := runTaskFn(taskSpec, false, cfg.Timeout)
+
+	if result.ExitCode != 0 {
+		return result.ExitCode
+	}
+
+	fmt.Println(result.Message)
+	if result.SessionID != "" {
+		fmt.Printf("\n---\nSESSION_ID: %s\n", result.SessionID)
+	}
+
+	return 0
+}

codeagent-wrapper/internal/app/concurrent_stress_test.go

@@ -0,0 +1,445 @@
+package wrapper
+
+import (
+	"bufio"
+	"context"
+	"fmt"
+	"os"
+	"regexp"
+	"strings"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/goccy/go-json"
+)
+
+func stripTimestampPrefix(line string) string {
+	line = strings.TrimSpace(line)
+	if strings.HasPrefix(line, "{") {
+		var evt struct {
+			Message string `json:"message"`
+		}
+		if err := json.Unmarshal([]byte(line), &evt); err == nil && evt.Message != "" {
+			return evt.Message
+		}
+	}
+	if !strings.HasPrefix(line, "[") {
+		return line
+	}
+	if idx := strings.Index(line, "] "); idx >= 0 {
+		return line[idx+2:]
+	}
+	return line
+}
+
+// TestConcurrentStressLogger 高并发压力测试
+func TestConcurrentStressLogger(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping stress test in short mode")
+	}
+
+	logger, err := NewLoggerWithSuffix("stress")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer logger.Close()
+
+	t.Logf("Log file: %s", logger.Path())
+
+	const (
+		numGoroutines  = 100  // 并发协程数
+		logsPerRoutine = 1000 // 每个协程写入日志数
+		totalExpected  = numGoroutines * logsPerRoutine
+	)
+
+	var wg sync.WaitGroup
+	start := time.Now()
+
+	// 启动并发写入
+	for i := 0; i < numGoroutines; i++ {
+		wg.Add(1)
+		go func(id int) {
+			defer wg.Done()
+			for j := 0; j < logsPerRoutine; j++ {
+				logger.Info(fmt.Sprintf("goroutine-%d-msg-%d", id, j))
+			}
+		}(i)
+	}
+
+	wg.Wait()
+	logger.Flush()
+	elapsed := time.Since(start)
+
+	// 读取日志文件验证
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to read log file: %v", err)
+	}
+
+	lines := strings.Split(strings.TrimSpace(string(data)), "\n")
+	actualCount := len(lines)
+
+	t.Logf("Concurrent stress test results:")
+	t.Logf("  Goroutines: %d", numGoroutines)
+	t.Logf("  Logs per goroutine: %d", logsPerRoutine)
+	t.Logf("  Total expected: %d", totalExpected)
+	t.Logf("  Total actual: %d", actualCount)
+	t.Logf("  Duration: %v", elapsed)
+	t.Logf("  Throughput: %.2f logs/sec", float64(totalExpected)/elapsed.Seconds())
+
+	// 验证日志数量
+	if actualCount < totalExpected/10 {
+		t.Errorf("too many logs lost: got %d, want at least %d (10%% of %d)",
+			actualCount, totalExpected/10, totalExpected)
+	}
+	t.Logf("Successfully wrote %d/%d logs (%.1f%%)",
+		actualCount, totalExpected, float64(actualCount)/float64(totalExpected)*100)
+
+	// 验证日志格式（纯文本，无前缀）
+	formatRE := regexp.MustCompile(`^goroutine-\d+-msg-\d+$`)
+	for i, line := range lines[:min(10, len(lines))] {
+		msg := stripTimestampPrefix(line)
+		if !formatRE.MatchString(msg) {
+			t.Errorf("line %d has invalid format: %s", i, line)
+		}
+	}
+}
+
+// TestConcurrentBurstLogger 突发流量测试
+func TestConcurrentBurstLogger(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping burst test in short mode")
+	}
+
+	logger, err := NewLoggerWithSuffix("burst")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer logger.Close()
+
+	t.Logf("Log file: %s", logger.Path())
+
+	const (
+		numBursts          = 10
+		goroutinesPerBurst = 50
+		logsPerGoroutine   = 100
+	)
+
+	totalLogs := 0
+	start := time.Now()
+
+	// 模拟突发流量
+	for burst := 0; burst < numBursts; burst++ {
+		var wg sync.WaitGroup
+		for i := 0; i < goroutinesPerBurst; i++ {
+			wg.Add(1)
+			totalLogs += logsPerGoroutine
+			go func(b, g int) {
+				defer wg.Done()
+				for j := 0; j < logsPerGoroutine; j++ {
+					logger.Info(fmt.Sprintf("burst-%d-goroutine-%d-msg-%d", b, g, j))
+				}
+			}(burst, i)
+		}
+		wg.Wait()
+		time.Sleep(10 * time.Millisecond) // 突发间隔
+	}
+
+	logger.Flush()
+	elapsed := time.Since(start)
+
+	// 验证
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to read log file: %v", err)
+	}
+
+	lines := strings.Split(strings.TrimSpace(string(data)), "\n")
+	actualCount := len(lines)
+
+	t.Logf("Burst test results:")
+	t.Logf("  Total bursts: %d", numBursts)
+	t.Logf("  Goroutines per burst: %d", goroutinesPerBurst)
+	t.Logf("  Expected logs: %d", totalLogs)
+	t.Logf("  Actual logs: %d", actualCount)
+	t.Logf("  Duration: %v", elapsed)
+	t.Logf("  Throughput: %.2f logs/sec", float64(totalLogs)/elapsed.Seconds())
+
+	if actualCount < totalLogs/10 {
+		t.Errorf("too many logs lost: got %d, want at least %d (10%% of %d)", actualCount, totalLogs/10, totalLogs)
+	}
+	t.Logf("Successfully wrote %d/%d logs (%.1f%%)",
+		actualCount, totalLogs, float64(actualCount)/float64(totalLogs)*100)
+}
+
+// TestLoggerChannelCapacity 测试 channel 容量极限
+func TestLoggerChannelCapacity(t *testing.T) {
+	logger, err := NewLoggerWithSuffix("capacity")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer logger.Close()
+
+	const rapidLogs = 2000 // 超过 channel 容量 (1000)
+
+	start := time.Now()
+	for i := 0; i < rapidLogs; i++ {
+		logger.Info(fmt.Sprintf("rapid-log-%d", i))
+	}
+	sendDuration := time.Since(start)
+
+	logger.Flush()
+	flushDuration := time.Since(start) - sendDuration
+
+	t.Logf("Channel capacity test:")
+	t.Logf("  Logs sent: %d", rapidLogs)
+	t.Logf("  Send duration: %v", sendDuration)
+	t.Logf("  Flush duration: %v", flushDuration)
+
+	// 验证仍有合理比例的日志写入（非阻塞模式允许部分丢失）
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatal(err)
+	}
+	lines := strings.Split(strings.TrimSpace(string(data)), "\n")
+	actualCount := len(lines)
+
+	if actualCount < rapidLogs/10 {
+		t.Errorf("too many logs lost: got %d, want at least %d (10%% of %d)", actualCount, rapidLogs/10, rapidLogs)
+	}
+	t.Logf("Logs persisted: %d/%d (%.1f%%)", actualCount, rapidLogs, float64(actualCount)/float64(rapidLogs)*100)
+}
+
+// TestLoggerMemoryUsage 内存使用测试
+func TestLoggerMemoryUsage(t *testing.T) {
+	logger, err := NewLoggerWithSuffix("memory")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer logger.Close()
+
+	const numLogs = 20000
+	longMessage := strings.Repeat("x", 500) // 500 字节长消息
+
+	start := time.Now()
+	for i := 0; i < numLogs; i++ {
+		logger.Info(fmt.Sprintf("log-%d-%s", i, longMessage))
+	}
+	logger.Flush()
+	elapsed := time.Since(start)
+
+	// 检查文件大小
+	info, err := os.Stat(logger.Path())
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	expectedTotalSize := int64(numLogs * 500) // 理论最小总字节数
+	expectedMinSize := expectedTotalSize / 10 // 接受最多 90% 丢失
+	actualSize := info.Size()
+
+	t.Logf("Memory/disk usage test:")
+	t.Logf("  Logs written: %d", numLogs)
+	t.Logf("  Message size: 500 bytes")
+	t.Logf("  File size: %.2f MB", float64(actualSize)/1024/1024)
+	t.Logf("  Duration: %v", elapsed)
+	t.Logf("  Write speed: %.2f MB/s", float64(actualSize)/1024/1024/elapsed.Seconds())
+	t.Logf("  Persistence ratio: %.1f%%", float64(actualSize)/float64(expectedTotalSize)*100)
+
+	if actualSize < expectedMinSize {
+		t.Errorf("file size too small: got %d bytes, expected at least %d", actualSize, expectedMinSize)
+	}
+}
+
+// TestLoggerFlushTimeout 测试 Flush 超时机制
+func TestLoggerFlushTimeout(t *testing.T) {
+	logger, err := NewLoggerWithSuffix("flush")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer logger.Close()
+
+	// 写入一些日志
+	for i := 0; i < 100; i++ {
+		logger.Info(fmt.Sprintf("test-log-%d", i))
+	}
+
+	// 测试 Flush 应该在合理时间内完成
+	start := time.Now()
+	logger.Flush()
+	duration := time.Since(start)
+
+	t.Logf("Flush duration: %v", duration)
+
+	if duration > 6*time.Second {
+		t.Errorf("Flush took too long: %v (expected < 6s)", duration)
+	}
+}
+
+// TestLoggerOrderPreservation 测试日志顺序保持
+func TestLoggerOrderPreservation(t *testing.T) {
+	logger, err := NewLoggerWithSuffix("order")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer logger.Close()
+
+	const numGoroutines = 10
+	const logsPerRoutine = 100
+
+	var wg sync.WaitGroup
+	for i := 0; i < numGoroutines; i++ {
+		wg.Add(1)
+		go func(id int) {
+			defer wg.Done()
+			for j := 0; j < logsPerRoutine; j++ {
+				logger.Info(fmt.Sprintf("G%d-SEQ%04d", id, j))
+			}
+		}(i)
+	}
+
+	wg.Wait()
+	logger.Flush()
+
+	// 读取并验证每个 goroutine 的日志顺序
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	scanner := bufio.NewScanner(strings.NewReader(string(data)))
+	sequences := make(map[int][]int) // goroutine ID -> sequence numbers
+
+	for scanner.Scan() {
+		line := stripTimestampPrefix(scanner.Text())
+		var gid, seq int
+		// Parse format: G0-SEQ0001 (without INFO: prefix)
+		_, err := fmt.Sscanf(line, "G%d-SEQ%04d", &gid, &seq)
+		if err != nil {
+			t.Errorf("invalid log format: %s (error: %v)", line, err)
+			continue
+		}
+		sequences[gid] = append(sequences[gid], seq)
+	}
+
+	// 验证每个 goroutine 内部顺序
+	for gid, seqs := range sequences {
+		for i := 0; i < len(seqs)-1; i++ {
+			if seqs[i] >= seqs[i+1] {
+				t.Errorf("Goroutine %d: out of order at index %d: %d >= %d",
+					gid, i, seqs[i], seqs[i+1])
+			}
+		}
+		if len(seqs) != logsPerRoutine {
+			t.Errorf("Goroutine %d: missing logs, got %d, want %d",
+				gid, len(seqs), logsPerRoutine)
+		}
+	}
+
+	t.Logf("Order preservation test: all %d goroutines maintained sequence order", len(sequences))
+}
+
+func TestConcurrentWorkerPoolLimit(t *testing.T) {
+	orig := runCodexTaskFn
+	defer func() { runCodexTaskFn = orig }()
+
+	logger, err := NewLoggerWithSuffix("pool-limit")
+	if err != nil {
+		t.Fatal(err)
+	}
+	setLogger(logger)
+	t.Cleanup(func() {
+		_ = closeLogger()
+		_ = logger.RemoveLogFile()
+	})
+
+	var active int64
+	var maxSeen int64
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		if task.Context == nil {
+			t.Fatalf("context not propagated for task %s", task.ID)
+		}
+		cur := atomic.AddInt64(&active, 1)
+		for {
+			prev := atomic.LoadInt64(&maxSeen)
+			if cur <= prev || atomic.CompareAndSwapInt64(&maxSeen, prev, cur) {
+				break
+			}
+		}
+		select {
+		case <-task.Context.Done():
+			atomic.AddInt64(&active, -1)
+			return TaskResult{TaskID: task.ID, ExitCode: 130, Error: "context cancelled"}
+		case <-time.After(30 * time.Millisecond):
+		}
+		atomic.AddInt64(&active, -1)
+		return TaskResult{TaskID: task.ID}
+	}
+
+	layers := [][]TaskSpec{{{ID: "t1"}, {ID: "t2"}, {ID: "t3"}, {ID: "t4"}, {ID: "t5"}}}
+	results := executeConcurrentWithContext(context.Background(), layers, 5, 2)
+
+	if len(results) != 5 {
+		t.Fatalf("unexpected result count: got %d", len(results))
+	}
+	if maxSeen > 2 {
+		t.Fatalf("worker pool exceeded limit: saw %d active workers", maxSeen)
+	}
+
+	logger.Flush()
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to read log file: %v", err)
+	}
+	content := string(data)
+	if !strings.Contains(content, "worker_limit=2") {
+		t.Fatalf("concurrency planning log missing, content: %s", content)
+	}
+	if !strings.Contains(content, "parallel: start") {
+		t.Fatalf("concurrency start logs missing, content: %s", content)
+	}
+}
+
+func TestConcurrentCancellationPropagation(t *testing.T) {
+	orig := runCodexTaskFn
+	defer func() { runCodexTaskFn = orig }()
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		if task.Context == nil {
+			t.Fatalf("context not propagated for task %s", task.ID)
+		}
+		select {
+		case <-task.Context.Done():
+			return TaskResult{TaskID: task.ID, ExitCode: 130, Error: "context cancelled"}
+		case <-time.After(200 * time.Millisecond):
+			return TaskResult{TaskID: task.ID}
+		}
+	}
+
+	layers := [][]TaskSpec{{{ID: "a"}, {ID: "b"}, {ID: "c"}}}
+	go func() {
+		time.Sleep(50 * time.Millisecond)
+		cancel()
+	}()
+
+	results := executeConcurrentWithContext(ctx, layers, 1, 2)
+	if len(results) != 3 {
+		t.Fatalf("unexpected result count: got %d", len(results))
+	}
+
+	cancelled := 0
+	for _, res := range results {
+		if res.ExitCode != 0 {
+			cancelled++
+		}
+	}
+
+	if cancelled == 0 {
+		t.Fatalf("expected cancellation to propagate, got results: %+v", results)
+	}
+}

codeagent-wrapper/internal/app/config_alias.go

@@ -0,0 +1,7 @@
+package wrapper
+
+import config "codeagent-wrapper/internal/config"
+
+// Keep the existing Config name throughout the codebase, but source the
+// implementation from internal/config.
+type Config = config.Config

codeagent-wrapper/internal/app/executor_alias.go

@@ -0,0 +1,54 @@
+package wrapper
+
+import (
+	"context"
+
+	backend "codeagent-wrapper/internal/backend"
+	config "codeagent-wrapper/internal/config"
+	executor "codeagent-wrapper/internal/executor"
+)
+
+// defaultRunCodexTaskFn is the default implementation of runCodexTaskFn (exposed for test reset).
+func defaultRunCodexTaskFn(task TaskSpec, timeout int) TaskResult {
+	return executor.DefaultRunCodexTaskFn(task, timeout)
+}
+
+var runCodexTaskFn = defaultRunCodexTaskFn
+
+func topologicalSort(tasks []TaskSpec) ([][]TaskSpec, error) {
+	return executor.TopologicalSort(tasks)
+}
+
+func executeConcurrent(layers [][]TaskSpec, timeout int) []TaskResult {
+	maxWorkers := config.ResolveMaxParallelWorkers()
+	return executeConcurrentWithContext(context.Background(), layers, timeout, maxWorkers)
+}
+
+func executeConcurrentWithContext(parentCtx context.Context, layers [][]TaskSpec, timeout int, maxWorkers int) []TaskResult {
+	return executor.ExecuteConcurrentWithContext(parentCtx, layers, timeout, maxWorkers, runCodexTaskFn)
+}
+
+func generateFinalOutput(results []TaskResult) string {
+	return executor.GenerateFinalOutput(results)
+}
+
+func generateFinalOutputWithMode(results []TaskResult, summaryOnly bool) string {
+	return executor.GenerateFinalOutputWithMode(results, summaryOnly)
+}
+
+func buildCodexArgs(cfg *Config, targetArg string) []string {
+	return backend.BuildCodexArgs(cfg, targetArg)
+}
+
+func runCodexTask(taskSpec TaskSpec, silent bool, timeoutSec int) TaskResult {
+	return runCodexTaskWithContext(context.Background(), taskSpec, nil, nil, false, silent, timeoutSec)
+}
+
+func runCodexProcess(parentCtx context.Context, codexArgs []string, taskText string, useStdin bool, timeoutSec int) (message, threadID string, exitCode int) {
+	res := runCodexTaskWithContext(parentCtx, TaskSpec{Task: taskText, WorkDir: defaultWorkdir, Mode: "new", UseStdin: useStdin}, nil, codexArgs, true, false, timeoutSec)
+	return res.Message, res.SessionID, res.ExitCode
+}
+
+func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backend Backend, customArgs []string, useCustomArgs bool, silent bool, timeoutSec int) TaskResult {
+	return executor.RunCodexTaskWithContext(parentCtx, taskSpec, backend, codexCommand, buildCodexArgsFn, customArgs, useCustomArgs, silent, timeoutSec)
+}

codeagent-wrapper/internal/app/logger.go

@@ -0,0 +1,26 @@
+package wrapper
+
+import ilogger "codeagent-wrapper/internal/logger"
+
+type Logger = ilogger.Logger
+type CleanupStats = ilogger.CleanupStats
+
+func NewLogger() (*Logger, error) { return ilogger.NewLogger() }
+
+func NewLoggerWithSuffix(suffix string) (*Logger, error) { return ilogger.NewLoggerWithSuffix(suffix) }
+
+func setLogger(l *Logger) { ilogger.SetLogger(l) }
+
+func closeLogger() error { return ilogger.CloseLogger() }
+
+func activeLogger() *Logger { return ilogger.ActiveLogger() }
+
+func logInfo(msg string) { ilogger.LogInfo(msg) }
+
+func logWarn(msg string) { ilogger.LogWarn(msg) }
+
+func logError(msg string) { ilogger.LogError(msg) }
+
+func cleanupOldLogs() (CleanupStats, error) { return ilogger.CleanupOldLogs() }
+
+func sanitizeLogSuffix(raw string) string { return ilogger.SanitizeLogSuffix(raw) }

codeagent-wrapper/internal/app/main_integration_test.go

@@ -0,0 +1,949 @@
+package wrapper
+
+import (
+	"bytes"
+	"codeagent-wrapper/internal/logger"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+)
+
+type integrationSummary struct {
+	Total   int `json:"total"`
+	Success int `json:"success"`
+	Failed  int `json:"failed"`
+}
+
+type integrationOutput struct {
+	Results []TaskResult       `json:"results"`
+	Summary integrationSummary `json:"summary"`
+}
+
+func captureStdout(t *testing.T, fn func()) string {
+	t.Helper()
+	old := os.Stdout
+	r, w, _ := os.Pipe()
+	os.Stdout = w
+
+	fn()
+
+	w.Close()
+	os.Stdout = old
+
+	var buf bytes.Buffer
+	if _, err := io.Copy(&buf, r); err != nil {
+		t.Fatalf("io.Copy() error = %v", err)
+	}
+	return buf.String()
+}
+
+func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
+	t.Helper()
+	var payload integrationOutput
+
+	lines := strings.Split(out, "\n")
+	var currentTask *TaskResult
+	inTaskResults := false
+
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+
+		// Parse new format header: "X tasks | Y passed | Z failed"
+		if strings.Contains(line, "tasks |") && strings.Contains(line, "passed |") {
+			parts := strings.Split(line, "|")
+			for _, p := range parts {
+				p = strings.TrimSpace(p)
+				if strings.HasSuffix(p, "tasks") {
+					if _, err := fmt.Sscanf(p, "%d tasks", &payload.Summary.Total); err != nil {
+						t.Fatalf("failed to parse total tasks from %q: %v", p, err)
+					}
+				} else if strings.HasSuffix(p, "passed") {
+					if _, err := fmt.Sscanf(p, "%d passed", &payload.Summary.Success); err != nil {
+						t.Fatalf("failed to parse passed tasks from %q: %v", p, err)
+					}
+				} else if strings.HasSuffix(p, "failed") {
+					if _, err := fmt.Sscanf(p, "%d failed", &payload.Summary.Failed); err != nil {
+						t.Fatalf("failed to parse failed tasks from %q: %v", p, err)
+					}
+				}
+			}
+		} else if strings.HasPrefix(line, "Total:") {
+			// Legacy format: "Total: X | Success: Y | Failed: Z"
+			parts := strings.Split(line, "|")
+			for _, p := range parts {
+				p = strings.TrimSpace(p)
+				if strings.HasPrefix(p, "Total:") {
+					if _, err := fmt.Sscanf(p, "Total: %d", &payload.Summary.Total); err != nil {
+						t.Fatalf("failed to parse total tasks from %q: %v", p, err)
+					}
+				} else if strings.HasPrefix(p, "Success:") {
+					if _, err := fmt.Sscanf(p, "Success: %d", &payload.Summary.Success); err != nil {
+						t.Fatalf("failed to parse passed tasks from %q: %v", p, err)
+					}
+				} else if strings.HasPrefix(p, "Failed:") {
+					if _, err := fmt.Sscanf(p, "Failed: %d", &payload.Summary.Failed); err != nil {
+						t.Fatalf("failed to parse failed tasks from %q: %v", p, err)
+					}
+				}
+			}
+		} else if line == "## Task Results" {
+			inTaskResults = true
+		} else if line == "## Summary" {
+			// End of task results section
+			if currentTask != nil {
+				payload.Results = append(payload.Results, *currentTask)
+				currentTask = nil
+			}
+			inTaskResults = false
+		} else if inTaskResults && strings.HasPrefix(line, "### ") {
+			// New task: ### task-id ✓ 92% or ### task-id PASS 92% (ASCII mode)
+			if currentTask != nil {
+				payload.Results = append(payload.Results, *currentTask)
+			}
+			currentTask = &TaskResult{}
+
+			taskLine := strings.TrimPrefix(line, "### ")
+			parseMarker := func(marker string, exitCode int) bool {
+				needle := " " + marker
+				if !strings.Contains(taskLine, needle) {
+					return false
+				}
+				parts := strings.Split(taskLine, needle)
+				currentTask.TaskID = strings.TrimSpace(parts[0])
+				currentTask.ExitCode = exitCode
+				if exitCode == 0 && len(parts) > 1 {
+					coveragePart := strings.TrimSpace(parts[1])
+					if strings.HasSuffix(coveragePart, "%") {
+						currentTask.Coverage = coveragePart
+					}
+				}
+				return true
+			}
+
+			switch {
+			case parseMarker("✓", 0), parseMarker("PASS", 0):
+				// ok
+			case parseMarker("⚠️", 0), parseMarker("WARN", 0):
+				// warning
+			case parseMarker("✗", 1), parseMarker("FAIL", 1):
+				// fail
+			default:
+				currentTask.TaskID = taskLine
+			}
+		} else if currentTask != nil && inTaskResults {
+			// Parse task details
+			if strings.HasPrefix(line, "Exit code:") {
+				if _, err := fmt.Sscanf(line, "Exit code: %d", &currentTask.ExitCode); err != nil {
+					t.Fatalf("failed to parse exit code from %q: %v", line, err)
+				}
+			} else if strings.HasPrefix(line, "Error:") {
+				currentTask.Error = strings.TrimPrefix(line, "Error: ")
+			} else if strings.HasPrefix(line, "Log:") {
+				currentTask.LogPath = strings.TrimSpace(strings.TrimPrefix(line, "Log:"))
+			} else if strings.HasPrefix(line, "Did:") {
+				currentTask.KeyOutput = strings.TrimSpace(strings.TrimPrefix(line, "Did:"))
+			} else if strings.HasPrefix(line, "Detail:") {
+				// Error detail for failed tasks
+				if currentTask.Message == "" {
+					currentTask.Message = strings.TrimSpace(strings.TrimPrefix(line, "Detail:"))
+				}
+			}
+		} else if strings.HasPrefix(line, "--- Task:") {
+			// Legacy full output format
+			if currentTask != nil {
+				payload.Results = append(payload.Results, *currentTask)
+			}
+			currentTask = &TaskResult{}
+			currentTask.TaskID = strings.TrimSuffix(strings.TrimPrefix(line, "--- Task: "), " ---")
+		} else if currentTask != nil && !inTaskResults {
+			// Legacy format parsing
+			if strings.HasPrefix(line, "Status: SUCCESS") {
+				currentTask.ExitCode = 0
+			} else if strings.HasPrefix(line, "Status: FAILED") {
+				if strings.Contains(line, "exit code") {
+					if _, err := fmt.Sscanf(line, "Status: FAILED (exit code %d)", &currentTask.ExitCode); err != nil {
+						t.Fatalf("failed to parse exit code from %q: %v", line, err)
+					}
+				} else {
+					currentTask.ExitCode = 1
+				}
+			} else if strings.HasPrefix(line, "Error:") {
+				currentTask.Error = strings.TrimPrefix(line, "Error: ")
+			} else if strings.HasPrefix(line, "Session:") {
+				currentTask.SessionID = strings.TrimPrefix(line, "Session: ")
+			} else if strings.HasPrefix(line, "Log:") {
+				currentTask.LogPath = strings.TrimSpace(strings.TrimPrefix(line, "Log:"))
+			}
+		}
+	}
+
+	// Handle last task
+	if currentTask != nil {
+		payload.Results = append(payload.Results, *currentTask)
+	}
+
+	return payload
+}
+
+func findResultByID(t *testing.T, payload integrationOutput, id string) TaskResult {
+	t.Helper()
+	for _, res := range payload.Results {
+		if res.TaskID == id {
+			return res
+		}
+	}
+	t.Fatalf("result for task %s not found", id)
+	return TaskResult{}
+}
+
+func setTempDirEnv(t *testing.T, dir string) string {
+	t.Helper()
+	resolved := dir
+	if eval, err := filepath.EvalSymlinks(dir); err == nil {
+		resolved = eval
+	}
+	t.Setenv("TMPDIR", resolved)
+	t.Setenv("TEMP", resolved)
+	t.Setenv("TMP", resolved)
+	return resolved
+}
+
+func createTempLog(t *testing.T, dir, name string) string {
+	t.Helper()
+	path := filepath.Join(dir, name)
+	if err := os.WriteFile(path, []byte("test"), 0o644); err != nil {
+		t.Fatalf("failed to create temp log %s: %v", path, err)
+	}
+	return path
+}
+
+func stubProcessRunning(t *testing.T, fn func(int) bool) {
+	t.Helper()
+	t.Cleanup(logger.SetProcessRunningCheck(fn))
+}
+
+func stubProcessStartTime(t *testing.T, fn func(int) time.Time) {
+	t.Helper()
+	t.Cleanup(logger.SetProcessStartTimeFn(fn))
+}
+
+func TestRunParallelEndToEnd_OrderAndConcurrency(t *testing.T) {
+	defer resetTestHooks()
+	origRun := runCodexTaskFn
+	t.Cleanup(func() {
+		runCodexTaskFn = origRun
+		resetTestHooks()
+	})
+
+	input := `---TASK---
+id: A
+---CONTENT---
+task-a
+---TASK---
+id: B
+dependencies: A
+---CONTENT---
+task-b
+---TASK---
+id: C
+dependencies: B
+---CONTENT---
+task-c
+---TASK---
+id: D
+---CONTENT---
+task-d
+---TASK---
+id: E
+---CONTENT---
+task-e`
+	stdinReader = bytes.NewReader([]byte(input))
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
+
+	var mu sync.Mutex
+	starts := make(map[string]time.Time)
+	ends := make(map[string]time.Time)
+	var running int64
+	var maxParallel int64
+
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		start := time.Now()
+		mu.Lock()
+		starts[task.ID] = start
+		mu.Unlock()
+
+		cur := atomic.AddInt64(&running, 1)
+		for {
+			prev := atomic.LoadInt64(&maxParallel)
+			if cur <= prev {
+				break
+			}
+			if atomic.CompareAndSwapInt64(&maxParallel, prev, cur) {
+				break
+			}
+		}
+
+		time.Sleep(40 * time.Millisecond)
+
+		mu.Lock()
+		ends[task.ID] = time.Now()
+		mu.Unlock()
+
+		atomic.AddInt64(&running, -1)
+		return TaskResult{TaskID: task.ID, ExitCode: 0, Message: task.Task}
+	}
+
+	var exitCode int
+	output := captureStdout(t, func() {
+		exitCode = run()
+	})
+
+	if exitCode != 0 {
+		t.Fatalf("run() exit = %d, want 0", exitCode)
+	}
+
+	payload := parseIntegrationOutput(t, output)
+	if payload.Summary.Failed != 0 || payload.Summary.Total != 5 || payload.Summary.Success != 5 {
+		t.Fatalf("unexpected summary: %+v", payload.Summary)
+	}
+
+	aEnd := ends["A"]
+	bStart := starts["B"]
+	cStart := starts["C"]
+	bEnd := ends["B"]
+	if aEnd.IsZero() || bStart.IsZero() || bEnd.IsZero() || cStart.IsZero() {
+		t.Fatalf("missing timestamps, starts=%v ends=%v", starts, ends)
+	}
+	if !aEnd.Before(bStart) && !aEnd.Equal(bStart) {
+		t.Fatalf("B should start after A ends: A_end=%v B_start=%v", aEnd, bStart)
+	}
+	if !bEnd.Before(cStart) && !bEnd.Equal(cStart) {
+		t.Fatalf("C should start after B ends: B_end=%v C_start=%v", bEnd, cStart)
+	}
+
+	dStart := starts["D"]
+	eStart := starts["E"]
+	if dStart.IsZero() || eStart.IsZero() {
+		t.Fatalf("missing D/E start times: %v", starts)
+	}
+	delta := dStart.Sub(eStart)
+	if delta < 0 {
+		delta = -delta
+	}
+	if delta > 25*time.Millisecond {
+		t.Fatalf("D and E should run in parallel, delta=%v", delta)
+	}
+	if maxParallel < 2 {
+		t.Fatalf("expected at least 2 concurrent tasks, got %d", maxParallel)
+	}
+}
+
+func TestRunParallelCycleDetectionStopsExecution(t *testing.T) {
+	defer resetTestHooks()
+	origRun := runCodexTaskFn
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		t.Fatalf("task %s should not execute on cycle", task.ID)
+		return TaskResult{}
+	}
+	t.Cleanup(func() {
+		runCodexTaskFn = origRun
+		resetTestHooks()
+	})
+
+	input := `---TASK---
+id: A
+dependencies: B
+---CONTENT---
+a
+---TASK---
+id: B
+dependencies: A
+---CONTENT---
+b`
+	stdinReader = bytes.NewReader([]byte(input))
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
+
+	exitCode := 0
+	output := captureStdout(t, func() {
+		exitCode = run()
+	})
+
+	if exitCode == 0 {
+		t.Fatalf("cycle should cause non-zero exit, got %d", exitCode)
+	}
+	if strings.TrimSpace(output) != "" {
+		t.Fatalf("expected no JSON output on cycle, got %q", output)
+	}
+}
+
+func TestRunParallelOutputsIncludeLogPaths(t *testing.T) {
+	defer resetTestHooks()
+	origRun := runCodexTaskFn
+	t.Cleanup(func() {
+		runCodexTaskFn = origRun
+		resetTestHooks()
+	})
+
+	tempDir := t.TempDir()
+	logPathFor := func(id string) string {
+		return filepath.Join(tempDir, fmt.Sprintf("%s.log", id))
+	}
+
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		res := TaskResult{
+			TaskID:    task.ID,
+			Message:   fmt.Sprintf("result-%s", task.ID),
+			SessionID: fmt.Sprintf("session-%s", task.ID),
+			LogPath:   logPathFor(task.ID),
+		}
+		if task.ID == "beta" {
+			res.ExitCode = 9
+			res.Error = "boom"
+		}
+		return res
+	}
+
+	input := `---TASK---
+id: alpha
+---CONTENT---
+task-alpha
+---TASK---
+id: beta
+---CONTENT---
+task-beta`
+	stdinReader = bytes.NewReader([]byte(input))
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
+
+	var exitCode int
+	output := captureStdout(t, func() {
+		exitCode = run()
+	})
+
+	if exitCode != 9 {
+		t.Fatalf("parallel run exit=%d, want 9", exitCode)
+	}
+
+	payload := parseIntegrationOutput(t, output)
+	alpha := findResultByID(t, payload, "alpha")
+	beta := findResultByID(t, payload, "beta")
+
+	if alpha.LogPath != logPathFor("alpha") {
+		t.Fatalf("alpha log path = %q, want %q", alpha.LogPath, logPathFor("alpha"))
+	}
+	if beta.LogPath != logPathFor("beta") {
+		t.Fatalf("beta log path = %q, want %q", beta.LogPath, logPathFor("beta"))
+	}
+
+	for _, id := range []string{"alpha", "beta"} {
+		// Summary mode shows log paths in table format, not "Log: xxx"
+		logPath := logPathFor(id)
+		if !strings.Contains(output, logPath) {
+			t.Fatalf("parallel output missing log path %q for %s:\n%s", logPath, id, output)
+		}
+	}
+}
+
+func TestRunParallelStartupLogsPrinted(t *testing.T) {
+	defer resetTestHooks()
+
+	tempDir := setTempDirEnv(t, t.TempDir())
+	input := `---TASK---
+id: a
+---CONTENT---
+fail
+---TASK---
+id: b
+---CONTENT---
+ok-b
+---TASK---
+id: c
+dependencies: a
+---CONTENT---
+should-skip
+---TASK---
+id: d
+---CONTENT---
+ok-d`
+	stdinReader = bytes.NewReader([]byte(input))
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
+
+	expectedLog := filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", os.Getpid()))
+
+	origRun := runCodexTaskFn
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		path := expectedLog
+		if logger := activeLogger(); logger != nil && logger.Path() != "" {
+			path = logger.Path()
+		}
+		if task.ID == "a" {
+			return TaskResult{TaskID: task.ID, ExitCode: 3, Error: "boom", LogPath: path}
+		}
+		return TaskResult{TaskID: task.ID, ExitCode: 0, Message: task.Task, LogPath: path}
+	}
+	t.Cleanup(func() { runCodexTaskFn = origRun })
+
+	var exitCode int
+	var stdoutOut string
+	stderrOut := captureStderr(t, func() {
+		stdoutOut = captureStdout(t, func() {
+			exitCode = run()
+		})
+	})
+
+	if exitCode == 0 {
+		t.Fatalf("expected non-zero exit due to task failure, got %d", exitCode)
+	}
+	if stdoutOut == "" {
+		t.Fatalf("expected parallel summary on stdout")
+	}
+
+	lines := strings.Split(strings.TrimSpace(stderrOut), "\n")
+	var bannerSeen bool
+	var taskLines []string
+	for _, raw := range lines {
+		line := strings.TrimSpace(raw)
+		if line == "" {
+			continue
+		}
+		if line == "=== Starting Parallel Execution ===" {
+			if bannerSeen {
+				t.Fatalf("banner printed multiple times:\n%s", stderrOut)
+			}
+			bannerSeen = true
+			continue
+		}
+		taskLines = append(taskLines, line)
+	}
+
+	if !bannerSeen {
+		t.Fatalf("expected startup banner in stderr, got:\n%s", stderrOut)
+	}
+
+	// After parallel log isolation fix, each task has its own log file
+	expectedLines := map[string]struct{}{
+		fmt.Sprintf("Task a: Log: %s", filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d-a.log", os.Getpid()))): {},
+		fmt.Sprintf("Task b: Log: %s", filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d-b.log", os.Getpid()))): {},
+		fmt.Sprintf("Task d: Log: %s", filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d-d.log", os.Getpid()))): {},
+	}
+
+	if len(taskLines) != len(expectedLines) {
+		t.Fatalf("startup log lines mismatch, got %d lines:\n%s", len(taskLines), stderrOut)
+	}
+
+	for _, line := range taskLines {
+		if _, ok := expectedLines[line]; !ok {
+			t.Fatalf("unexpected startup line %q\nstderr:\n%s", line, stderrOut)
+		}
+	}
+}
+
+func TestRunNonParallelOutputsIncludeLogPathsIntegration(t *testing.T) {
+	defer resetTestHooks()
+
+	tempDir := setTempDirEnv(t, t.TempDir())
+	os.Args = []string{"codeagent-wrapper", "integration-log-check"}
+	stdinReader = strings.NewReader("")
+	isTerminalFn = func() bool { return true }
+	codexCommand = "echo"
+	buildCodexArgsFn = func(cfg *Config, targetArg string) []string {
+		return []string{`{"type":"thread.started","thread_id":"integration-session"}` + "\n" + `{"type":"item.completed","item":{"type":"agent_message","text":"done"}}`}
+	}
+
+	var exitCode int
+	stderr := captureStderr(t, func() {
+		_ = captureStdout(t, func() {
+			exitCode = run()
+		})
+	})
+
+	if exitCode != 0 {
+		t.Fatalf("run() exit=%d, want 0", exitCode)
+	}
+	expectedLog := filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", os.Getpid()))
+	wantLine := fmt.Sprintf("Log: %s", expectedLog)
+	if !strings.Contains(stderr, wantLine) {
+		t.Fatalf("stderr missing %q, got: %q", wantLine, stderr)
+	}
+}
+
+func TestRunParallelPartialFailureBlocksDependents(t *testing.T) {
+	defer resetTestHooks()
+	origRun := runCodexTaskFn
+	t.Cleanup(func() {
+		runCodexTaskFn = origRun
+		resetTestHooks()
+	})
+
+	tempDir := t.TempDir()
+	logPathFor := func(id string) string {
+		return filepath.Join(tempDir, fmt.Sprintf("%s.log", id))
+	}
+
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		path := logPathFor(task.ID)
+		if task.ID == "A" {
+			return TaskResult{TaskID: "A", ExitCode: 2, Error: "boom", LogPath: path}
+		}
+		return TaskResult{TaskID: task.ID, ExitCode: 0, Message: task.Task, LogPath: path}
+	}
+
+	input := `---TASK---
+id: A
+---CONTENT---
+fail
+---TASK---
+id: B
+dependencies: A
+---CONTENT---
+blocked
+---TASK---
+id: D
+---CONTENT---
+ok-d
+---TASK---
+id: E
+---CONTENT---
+ok-e`
+	stdinReader = bytes.NewReader([]byte(input))
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
+
+	var exitCode int
+	output := captureStdout(t, func() {
+		exitCode = run()
+	})
+
+	payload := parseIntegrationOutput(t, output)
+	if exitCode == 0 {
+		t.Fatalf("expected non-zero exit when a task fails, got %d", exitCode)
+	}
+
+	resA := findResultByID(t, payload, "A")
+	resB := findResultByID(t, payload, "B")
+	resD := findResultByID(t, payload, "D")
+	resE := findResultByID(t, payload, "E")
+
+	if resA.ExitCode == 0 {
+		t.Fatalf("task A should fail, got %+v", resA)
+	}
+	if resB.ExitCode == 0 || !strings.Contains(resB.Error, "dependencies") {
+		t.Fatalf("task B should be skipped due to dependency failure, got %+v", resB)
+	}
+	if resD.ExitCode != 0 || resE.ExitCode != 0 {
+		t.Fatalf("independent tasks should run successfully, D=%+v E=%+v", resD, resE)
+	}
+	if payload.Summary.Failed != 2 || payload.Summary.Total != 4 {
+		t.Fatalf("unexpected summary after partial failure: %+v", payload.Summary)
+	}
+	if resA.LogPath != logPathFor("A") {
+		t.Fatalf("task A log path = %q, want %q", resA.LogPath, logPathFor("A"))
+	}
+	if resB.LogPath != "" {
+		t.Fatalf("task B should not report a log path when skipped, got %q", resB.LogPath)
+	}
+	if resD.LogPath != logPathFor("D") || resE.LogPath != logPathFor("E") {
+		t.Fatalf("expected log paths for D/E, got D=%q E=%q", resD.LogPath, resE.LogPath)
+	}
+	// Summary mode shows log paths in table, verify they appear in output
+	for _, id := range []string{"A", "D", "E"} {
+		logPath := logPathFor(id)
+		if !strings.Contains(output, logPath) {
+			t.Fatalf("task %s log path %q not found in output:\n%s", id, logPath, output)
+		}
+	}
+	// Task B was skipped, should have "-" or empty log path in table
+	if resB.LogPath != "" {
+		t.Fatalf("skipped task B should have empty log path, got %q", resB.LogPath)
+	}
+}
+
+func TestRunParallelTimeoutPropagation(t *testing.T) {
+	defer resetTestHooks()
+	origRun := runCodexTaskFn
+	t.Cleanup(func() {
+		runCodexTaskFn = origRun
+		resetTestHooks()
+	})
+
+	var receivedTimeout int
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		receivedTimeout = timeout
+		return TaskResult{TaskID: task.ID, ExitCode: 124, Error: "timeout"}
+	}
+
+	t.Setenv("CODEX_TIMEOUT", "1")
+	input := `---TASK---
+id: T
+---CONTENT---
+slow`
+	stdinReader = bytes.NewReader([]byte(input))
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
+
+	exitCode := 0
+	output := captureStdout(t, func() {
+		exitCode = run()
+	})
+
+	payload := parseIntegrationOutput(t, output)
+	if receivedTimeout != 1 {
+		t.Fatalf("expected timeout 1s to propagate, got %d", receivedTimeout)
+	}
+	if exitCode != 124 {
+		t.Fatalf("expected timeout exit code 124, got %d", exitCode)
+	}
+	if payload.Summary.Failed != 1 || payload.Summary.Total != 1 {
+		t.Fatalf("unexpected summary for timeout case: %+v", payload.Summary)
+	}
+	res := findResultByID(t, payload, "T")
+	if res.Error == "" || res.ExitCode != 124 {
+		t.Fatalf("timeout result not propagated, got %+v", res)
+	}
+}
+
+func TestRunConcurrentSpeedupBenchmark(t *testing.T) {
+	defer resetTestHooks()
+	origRun := runCodexTaskFn
+	t.Cleanup(func() {
+		runCodexTaskFn = origRun
+		resetTestHooks()
+	})
+
+	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
+		time.Sleep(50 * time.Millisecond)
+		return TaskResult{TaskID: task.ID}
+	}
+
+	tasks := make([]TaskSpec, 10)
+	for i := range tasks {
+		tasks[i] = TaskSpec{ID: fmt.Sprintf("task-%d", i)}
+	}
+	layers := [][]TaskSpec{tasks}
+
+	serialStart := time.Now()
+	for _, task := range tasks {
+		_ = runCodexTaskFn(task, 5)
+	}
+	serialElapsed := time.Since(serialStart)
+
+	concurrentStart := time.Now()
+	_ = executeConcurrent(layers, 5)
+	concurrentElapsed := time.Since(concurrentStart)
+
+	if concurrentElapsed >= serialElapsed/5 {
+		t.Fatalf("expected concurrent time <20%% of serial, serial=%v concurrent=%v", serialElapsed, concurrentElapsed)
+	}
+	ratio := float64(concurrentElapsed) / float64(serialElapsed)
+	t.Logf("speedup ratio (concurrent/serial)=%.3f", ratio)
+}
+
+func TestRunStartupCleanupRemovesOrphansEndToEnd(t *testing.T) {
+	defer resetTestHooks()
+
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	orphanA := createTempLog(t, tempDir, "codeagent-wrapper-5001.log")
+	orphanB := createTempLog(t, tempDir, "codeagent-wrapper-5002-extra.log")
+	orphanC := createTempLog(t, tempDir, "codeagent-wrapper-5003-suffix.log")
+	runningPID := 81234
+	runningLog := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", runningPID))
+	unrelated := createTempLog(t, tempDir, "wrapper.log")
+
+	stubProcessRunning(t, func(pid int) bool {
+		return pid == runningPID || pid == os.Getpid()
+	})
+	stubProcessStartTime(t, func(pid int) time.Time {
+		if pid == runningPID || pid == os.Getpid() {
+			return time.Now().Add(-1 * time.Hour)
+		}
+		return time.Time{}
+	})
+
+	codexCommand = createFakeCodexScript(t, "tid-startup", "ok")
+	stdinReader = strings.NewReader("")
+	isTerminalFn = func() bool { return true }
+	os.Args = []string{"codeagent-wrapper", "task"}
+
+	if exit := run(); exit != 0 {
+		t.Fatalf("run() exit=%d, want 0", exit)
+	}
+
+	for _, orphan := range []string{orphanA, orphanB, orphanC} {
+		if _, err := os.Stat(orphan); !os.IsNotExist(err) {
+			t.Fatalf("expected orphan %s to be removed, err=%v", orphan, err)
+		}
+	}
+	if _, err := os.Stat(runningLog); err != nil {
+		t.Fatalf("expected running log to remain, err=%v", err)
+	}
+	if _, err := os.Stat(unrelated); err != nil {
+		t.Fatalf("expected unrelated file to remain, err=%v", err)
+	}
+}
+
+func TestRunStartupCleanupConcurrentWrappers(t *testing.T) {
+	defer resetTestHooks()
+
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	const totalLogs = 40
+	for i := 0; i < totalLogs; i++ {
+		createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", 9000+i))
+	}
+
+	stubProcessRunning(t, func(pid int) bool {
+		return false
+	})
+	stubProcessStartTime(t, func(int) time.Time { return time.Time{} })
+
+	var wg sync.WaitGroup
+	const instances = 5
+	start := make(chan struct{})
+
+	for i := 0; i < instances; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			<-start
+			runStartupCleanup()
+		}()
+	}
+
+	close(start)
+	wg.Wait()
+
+	matches, err := filepath.Glob(filepath.Join(tempDir, "codeagent-wrapper-*.log"))
+	if err != nil {
+		t.Fatalf("glob error: %v", err)
+	}
+	if len(matches) != 0 {
+		t.Fatalf("expected all orphan logs to be removed, remaining=%v", matches)
+	}
+}
+
+func TestRunCleanupFlagEndToEnd_Success(t *testing.T) {
+	defer resetTestHooks()
+
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	staleA := createTempLog(t, tempDir, "codeagent-wrapper-2100.log")
+	staleB := createTempLog(t, tempDir, "codeagent-wrapper-2200-extra.log")
+	keeper := createTempLog(t, tempDir, "codeagent-wrapper-2300.log")
+
+	stubProcessRunning(t, func(pid int) bool {
+		return pid == 2300 || pid == os.Getpid()
+	})
+	stubProcessStartTime(t, func(pid int) time.Time {
+		if pid == 2300 || pid == os.Getpid() {
+			return time.Now().Add(-1 * time.Hour)
+		}
+		return time.Time{}
+	})
+
+	os.Args = []string{"codeagent-wrapper", "--cleanup"}
+
+	var exitCode int
+	output := captureStdout(t, func() {
+		exitCode = run()
+	})
+
+	if exitCode != 0 {
+		t.Fatalf("cleanup exit = %d, want 0", exitCode)
+	}
+
+	// Check that output contains expected counts and file names
+	if !strings.Contains(output, "Cleanup completed") {
+		t.Fatalf("missing 'Cleanup completed' in output: %q", output)
+	}
+	if !strings.Contains(output, "Files scanned: 3") {
+		t.Fatalf("missing 'Files scanned: 3' in output: %q", output)
+	}
+	if !strings.Contains(output, "Files deleted: 2") {
+		t.Fatalf("missing 'Files deleted: 2' in output: %q", output)
+	}
+	if !strings.Contains(output, "Files kept: 1") {
+		t.Fatalf("missing 'Files kept: 1' in output: %q", output)
+	}
+	if !strings.Contains(output, "codeagent-wrapper-2100.log") || !strings.Contains(output, "codeagent-wrapper-2200-extra.log") {
+		t.Fatalf("missing deleted file names in output: %q", output)
+	}
+	if !strings.Contains(output, "codeagent-wrapper-2300.log") {
+		t.Fatalf("missing kept file names in output: %q", output)
+	}
+
+	for _, path := range []string{staleA, staleB} {
+		if _, err := os.Stat(path); !os.IsNotExist(err) {
+			t.Fatalf("expected %s to be removed, err=%v", path, err)
+		}
+	}
+	if _, err := os.Stat(keeper); err != nil {
+		t.Fatalf("expected kept log to remain, err=%v", err)
+	}
+
+	currentLog := filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", os.Getpid()))
+	if _, err := os.Stat(currentLog); err == nil {
+		t.Fatalf("cleanup mode should not create new log file %s", currentLog)
+	} else if !os.IsNotExist(err) {
+		t.Fatalf("stat(%s) unexpected error: %v", currentLog, err)
+	}
+}
+
+func TestRunCleanupFlagEndToEnd_FailureDoesNotAffectStartup(t *testing.T) {
+	defer resetTestHooks()
+
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	calls := 0
+	cleanupLogsFn = func() (CleanupStats, error) {
+		calls++
+		return CleanupStats{Scanned: 1}, fmt.Errorf("permission denied")
+	}
+
+	os.Args = []string{"codeagent-wrapper", "--cleanup"}
+
+	var exitCode int
+	errOutput := captureStderr(t, func() {
+		exitCode = run()
+	})
+
+	if exitCode != 1 {
+		t.Fatalf("cleanup failure exit = %d, want 1", exitCode)
+	}
+	if !strings.Contains(errOutput, "Cleanup failed") || !strings.Contains(errOutput, "permission denied") {
+		t.Fatalf("cleanup stderr = %q, want failure message", errOutput)
+	}
+	if calls != 1 {
+		t.Fatalf("cleanup called %d times, want 1", calls)
+	}
+
+	currentLog := filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", os.Getpid()))
+	if _, err := os.Stat(currentLog); err == nil {
+		t.Fatalf("cleanup failure should not create new log file %s", currentLog)
+	} else if !os.IsNotExist(err) {
+		t.Fatalf("stat(%s) unexpected error: %v", currentLog, err)
+	}
+
+	cleanupLogsFn = func() (CleanupStats, error) {
+		return CleanupStats{}, nil
+	}
+	codexCommand = createFakeCodexScript(t, "tid-cleanup-e2e", "ok")
+	stdinReader = strings.NewReader("")
+	isTerminalFn = func() bool { return true }
+	os.Args = []string{"codeagent-wrapper", "post-cleanup task"}
+
+	var normalExit int
+	normalOutput := captureStdout(t, func() {
+		normalExit = run()
+	})
+
+	if normalExit != 0 {
+		t.Fatalf("normal run exit = %d, want 0", normalExit)
+	}
+	if !strings.Contains(normalOutput, "ok") {
+		t.Fatalf("normal run output = %q, want codex output", normalOutput)
+	}
+}

codeagent-wrapper/internal/app/parallel_config.go

@@ -0,0 +1,9 @@
+package wrapper
+
+import (
+	executor "codeagent-wrapper/internal/executor"
+)
+
+func parseParallelConfig(data []byte) (*ParallelConfig, error) {
+	return executor.ParseParallelConfig(data)
+}

codeagent-wrapper/internal/app/parser.go

@@ -0,0 +1,34 @@
+package wrapper
+
+import (
+	"bufio"
+	"io"
+
+	parser "codeagent-wrapper/internal/parser"
+
+	"github.com/goccy/go-json"
+)
+
+func parseJSONStream(r io.Reader) (message, threadID string) {
+	return parseJSONStreamWithLog(r, logWarn, logInfo)
+}
+
+func parseJSONStreamWithWarn(r io.Reader, warnFn func(string)) (message, threadID string) {
+	return parseJSONStreamWithLog(r, warnFn, logInfo)
+}
+
+func parseJSONStreamWithLog(r io.Reader, warnFn func(string), infoFn func(string)) (message, threadID string) {
+	return parseJSONStreamInternal(r, warnFn, infoFn, nil, nil)
+}
+
+func parseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(string), onMessage func(), onComplete func()) (message, threadID string) {
+	return parser.ParseJSONStreamInternal(r, warnFn, infoFn, onMessage, onComplete)
+}
+
+func hasKey(m map[string]json.RawMessage, key string) bool { return parser.HasKey(m, key) }
+
+func discardInvalidJSON(decoder *json.Decoder, reader *bufio.Reader) (*bufio.Reader, error) {
+	return parser.DiscardInvalidJSON(decoder, reader)
+}
+
+func normalizeText(text interface{}) string { return parser.NormalizeText(text) }

codeagent-wrapper/internal/app/task_types.go

@@ -0,0 +1,8 @@
+package wrapper
+
+import executor "codeagent-wrapper/internal/executor"
+
+// Type aliases to keep existing names in the wrapper package.
+type ParallelConfig = executor.ParallelConfig
+type TaskSpec = executor.TaskSpec
+type TaskResult = executor.TaskResult

codeagent-wrapper/internal/app/terminal_test.go

@@ -0,0 +1,30 @@
+package wrapper
+
+import (
+	"os"
+	"testing"
+)
+
+func TestDefaultIsTerminalCoverage(t *testing.T) {
+	oldStdin := os.Stdin
+	t.Cleanup(func() { os.Stdin = oldStdin })
+
+	f, err := os.CreateTemp(t.TempDir(), "stdin-*")
+	if err != nil {
+		t.Fatalf("os.CreateTemp() error = %v", err)
+	}
+	defer os.Remove(f.Name())
+
+	os.Stdin = f
+	if got := defaultIsTerminal(); got {
+		t.Fatalf("defaultIsTerminal() = %v, want false for regular file", got)
+	}
+
+	if err := f.Close(); err != nil {
+		t.Fatalf("Close() error = %v", err)
+	}
+	os.Stdin = f
+	if got := defaultIsTerminal(); !got {
+		t.Fatalf("defaultIsTerminal() = %v, want true when Stat fails", got)
+	}
+}

codeagent-wrapper/internal/app/utils.go

@@ -0,0 +1,523 @@
+package wrapper
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"os"
+	"strconv"
+	"strings"
+
+	utils "codeagent-wrapper/internal/utils"
+)
+
+func resolveTimeout() int {
+	raw := os.Getenv("CODEX_TIMEOUT")
+	if raw == "" {
+		return defaultTimeout
+	}
+
+	parsed, err := strconv.Atoi(raw)
+	if err != nil || parsed <= 0 {
+		logWarn(fmt.Sprintf("Invalid CODEX_TIMEOUT '%s', falling back to %ds", raw, defaultTimeout))
+		return defaultTimeout
+	}
+
+	if parsed > 10000 {
+		return parsed / 1000
+	}
+	return parsed
+}
+
+func readPipedTask() (string, error) {
+	if isTerminal() {
+		logInfo("Stdin is tty, skipping pipe read")
+		return "", nil
+	}
+	logInfo("Reading from stdin pipe...")
+	data, err := io.ReadAll(stdinReader)
+	if err != nil {
+		return "", fmt.Errorf("read stdin: %w", err)
+	}
+	if len(data) == 0 {
+		logInfo("Stdin pipe returned empty data")
+		return "", nil
+	}
+	logInfo(fmt.Sprintf("Read %d bytes from stdin pipe", len(data)))
+	return string(data), nil
+}
+
+func shouldUseStdin(taskText string, piped bool) bool {
+	if piped {
+		return true
+	}
+	if len(taskText) > 800 {
+		return true
+	}
+	return strings.ContainsAny(taskText, stdinSpecialChars)
+}
+
+func defaultIsTerminal() bool {
+	fi, err := os.Stdin.Stat()
+	if err != nil {
+		return true
+	}
+	return (fi.Mode() & os.ModeCharDevice) != 0
+}
+
+func isTerminal() bool {
+	return isTerminalFn()
+}
+
+func getEnv(key, defaultValue string) string {
+	if val := os.Getenv(key); val != "" {
+		return val
+	}
+	return defaultValue
+}
+
+type logWriter struct {
+	prefix  string
+	maxLen  int
+	buf     bytes.Buffer
+	dropped bool
+}
+
+func newLogWriter(prefix string, maxLen int) *logWriter {
+	if maxLen <= 0 {
+		maxLen = codexLogLineLimit
+	}
+	return &logWriter{prefix: prefix, maxLen: maxLen}
+}
+
+func (lw *logWriter) Write(p []byte) (int, error) {
+	if lw == nil {
+		return len(p), nil
+	}
+	total := len(p)
+	for len(p) > 0 {
+		if idx := bytes.IndexByte(p, '\n'); idx >= 0 {
+			lw.writeLimited(p[:idx])
+			lw.logLine(true)
+			p = p[idx+1:]
+			continue
+		}
+		lw.writeLimited(p)
+		break
+	}
+	return total, nil
+}
+
+func (lw *logWriter) Flush() {
+	if lw == nil || lw.buf.Len() == 0 {
+		return
+	}
+	lw.logLine(false)
+}
+
+func (lw *logWriter) logLine(force bool) {
+	if lw == nil {
+		return
+	}
+	line := lw.buf.String()
+	dropped := lw.dropped
+	lw.dropped = false
+	lw.buf.Reset()
+	if line == "" && !force {
+		return
+	}
+	if lw.maxLen > 0 {
+		if dropped {
+			if lw.maxLen > 3 {
+				line = line[:min(len(line), lw.maxLen-3)] + "..."
+			} else {
+				line = line[:min(len(line), lw.maxLen)]
+			}
+		} else if len(line) > lw.maxLen {
+			cutoff := lw.maxLen
+			if cutoff > 3 {
+				line = line[:cutoff-3] + "..."
+			} else {
+				line = line[:cutoff]
+			}
+		}
+	}
+	logInfo(lw.prefix + line)
+}
+
+func (lw *logWriter) writeLimited(p []byte) {
+	if lw == nil || len(p) == 0 {
+		return
+	}
+	if lw.maxLen <= 0 {
+		lw.buf.Write(p)
+		return
+	}
+
+	remaining := lw.maxLen - lw.buf.Len()
+	if remaining <= 0 {
+		lw.dropped = true
+		return
+	}
+	if len(p) <= remaining {
+		lw.buf.Write(p)
+		return
+	}
+	lw.buf.Write(p[:remaining])
+	lw.dropped = true
+}
+
+type tailBuffer struct {
+	limit int
+	data  []byte
+}
+
+func (b *tailBuffer) Write(p []byte) (int, error) {
+	if b.limit <= 0 {
+		return len(p), nil
+	}
+
+	if len(p) >= b.limit {
+		b.data = append(b.data[:0], p[len(p)-b.limit:]...)
+		return len(p), nil
+	}
+
+	total := len(b.data) + len(p)
+	if total <= b.limit {
+		b.data = append(b.data, p...)
+		return len(p), nil
+	}
+
+	overflow := total - b.limit
+	b.data = append(b.data[overflow:], p...)
+	return len(p), nil
+}
+
+func (b *tailBuffer) String() string {
+	return string(b.data)
+}
+
+func truncate(s string, maxLen int) string {
+	return utils.Truncate(s, maxLen)
+}
+
+// safeTruncate safely truncates string to maxLen, avoiding panic and UTF-8 corruption.
+func safeTruncate(s string, maxLen int) string {
+	return utils.SafeTruncate(s, maxLen)
+}
+
+// sanitizeOutput removes ANSI escape sequences and control characters.
+func sanitizeOutput(s string) string {
+	return utils.SanitizeOutput(s)
+}
+
+func min(a, b int) int {
+	return utils.Min(a, b)
+}
+
+func hello() string {
+	return "hello world"
+}
+
+func greet(name string) string {
+	return "hello " + name
+}
+
+func farewell(name string) string {
+	return "goodbye " + name
+}
+
+// extractCoverageFromLines extracts coverage from pre-split lines.
+func extractCoverageFromLines(lines []string) string {
+	if len(lines) == 0 {
+		return ""
+	}
+
+	end := len(lines)
+	for end > 0 && strings.TrimSpace(lines[end-1]) == "" {
+		end--
+	}
+
+	if end == 1 {
+		trimmed := strings.TrimSpace(lines[0])
+		if strings.HasSuffix(trimmed, "%") {
+			if num, err := strconv.ParseFloat(strings.TrimSuffix(trimmed, "%"), 64); err == nil && num >= 0 && num <= 100 {
+				return trimmed
+			}
+		}
+	}
+
+	coverageKeywords := []string{"file", "stmt", "branch", "line", "coverage", "total"}
+
+	for _, line := range lines[:end] {
+		lower := strings.ToLower(line)
+
+		hasKeyword := false
+		tokens := strings.FieldsFunc(lower, func(r rune) bool { return r < 'a' || r > 'z' })
+		for _, token := range tokens {
+			for _, kw := range coverageKeywords {
+				if strings.HasPrefix(token, kw) {
+					hasKeyword = true
+					break
+				}
+			}
+			if hasKeyword {
+				break
+			}
+		}
+		if !hasKeyword {
+			continue
+		}
+		if !strings.Contains(line, "%") {
+			continue
+		}
+
+		// Extract percentage pattern: number followed by %
+		for i := 0; i < len(line); i++ {
+			if line[i] == '%' && i > 0 {
+				// Walk back to find the number
+				j := i - 1
+				for j >= 0 && (line[j] == '.' || (line[j] >= '0' && line[j] <= '9')) {
+					j--
+				}
+				if j < i-1 {
+					numStr := line[j+1 : i]
+					// Validate it's a reasonable percentage
+					if num, err := strconv.ParseFloat(numStr, 64); err == nil && num >= 0 && num <= 100 {
+						return numStr + "%"
+					}
+				}
+			}
+		}
+	}
+
+	return ""
+}
+
+// extractCoverage extracts coverage percentage from task output
+// Supports common formats: "Coverage: 92%", "92% coverage", "coverage 92%", "TOTAL 92%"
+func extractCoverage(message string) string {
+	if message == "" {
+		return ""
+	}
+
+	return extractCoverageFromLines(strings.Split(message, "\n"))
+}
+
+// extractCoverageNum extracts coverage as a numeric value for comparison
+func extractCoverageNum(coverage string) float64 {
+	if coverage == "" {
+		return 0
+	}
+	// Remove % sign and parse
+	numStr := strings.TrimSuffix(coverage, "%")
+	if num, err := strconv.ParseFloat(numStr, 64); err == nil {
+		return num
+	}
+	return 0
+}
+
+// extractFilesChangedFromLines extracts files from pre-split lines.
+func extractFilesChangedFromLines(lines []string) []string {
+	if len(lines) == 0 {
+		return nil
+	}
+
+	var files []string
+	seen := make(map[string]bool)
+	exts := []string{".ts", ".tsx", ".js", ".jsx", ".go", ".py", ".rs", ".java", ".vue", ".css", ".scss", ".md", ".json", ".yaml", ".yml", ".toml"}
+
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+
+		// Pattern 1: "Modified: path/to/file.ts" or "Created: path/to/file.ts"
+		matchedPrefix := false
+		for _, prefix := range []string{"Modified:", "Created:", "Updated:", "Edited:", "Wrote:", "Changed:"} {
+			if strings.HasPrefix(line, prefix) {
+				file := strings.TrimSpace(strings.TrimPrefix(line, prefix))
+				file = strings.Trim(file, "`\"'()[],:")
+				file = strings.TrimPrefix(file, "@")
+				if file != "" && !seen[file] {
+					files = append(files, file)
+					seen[file] = true
+				}
+				matchedPrefix = true
+				break
+			}
+		}
+		if matchedPrefix {
+			continue
+		}
+
+		// Pattern 2: Tokens that look like file paths (allow root files, strip @ prefix).
+		parts := strings.Fields(line)
+		for _, part := range parts {
+			part = strings.Trim(part, "`\"'()[],:")
+			part = strings.TrimPrefix(part, "@")
+			for _, ext := range exts {
+				if strings.HasSuffix(part, ext) && !seen[part] {
+					files = append(files, part)
+					seen[part] = true
+					break
+				}
+			}
+		}
+	}
+
+	// Limit to first 10 files to avoid bloat
+	if len(files) > 10 {
+		files = files[:10]
+	}
+
+	return files
+}
+
+// extractFilesChanged extracts list of changed files from task output
+// Looks for common patterns like "Modified: file.ts", "Created: file.ts", file paths in output
+func extractFilesChanged(message string) []string {
+	if message == "" {
+		return nil
+	}
+
+	return extractFilesChangedFromLines(strings.Split(message, "\n"))
+}
+
+// extractTestResultsFromLines extracts test results from pre-split lines.
+func extractTestResultsFromLines(lines []string) (passed, failed int) {
+	if len(lines) == 0 {
+		return 0, 0
+	}
+
+	// Common patterns:
+	// pytest: "12 passed, 2 failed"
+	// jest: "Tests: 2 failed, 12 passed"
+	// go: "ok ... 12 tests"
+
+	for _, line := range lines {
+		line = strings.ToLower(line)
+
+		// Look for test result lines
+		if !strings.Contains(line, "pass") && !strings.Contains(line, "fail") && !strings.Contains(line, "test") {
+			continue
+		}
+
+		// Extract numbers near "passed" or "pass"
+		if idx := strings.Index(line, "pass"); idx != -1 {
+			// Look for number before "pass"
+			num := extractNumberBefore(line, idx)
+			if num > 0 {
+				passed = num
+			}
+		}
+
+		// Extract numbers near "failed" or "fail"
+		if idx := strings.Index(line, "fail"); idx != -1 {
+			num := extractNumberBefore(line, idx)
+			if num > 0 {
+				failed = num
+			}
+		}
+
+		// go test style: "ok ... 12 tests"
+		if passed == 0 {
+			if idx := strings.Index(line, "test"); idx != -1 {
+				num := extractNumberBefore(line, idx)
+				if num > 0 {
+					passed = num
+				}
+			}
+		}
+
+		// If we found both, stop
+		if passed > 0 && failed > 0 {
+			break
+		}
+	}
+
+	return passed, failed
+}
+
+// extractTestResults extracts test pass/fail counts from task output
+func extractTestResults(message string) (passed, failed int) {
+	if message == "" {
+		return 0, 0
+	}
+
+	return extractTestResultsFromLines(strings.Split(message, "\n"))
+}
+
+// extractNumberBefore extracts a number that appears before the given index
+func extractNumberBefore(s string, idx int) int {
+	if idx <= 0 {
+		return 0
+	}
+
+	// Walk backwards to find digits
+	end := idx - 1
+	for end >= 0 && (s[end] == ' ' || s[end] == ':' || s[end] == ',') {
+		end--
+	}
+	if end < 0 {
+		return 0
+	}
+
+	start := end
+	for start >= 0 && s[start] >= '0' && s[start] <= '9' {
+		start--
+	}
+	start++
+
+	if start > end {
+		return 0
+	}
+
+	numStr := s[start : end+1]
+	if num, err := strconv.Atoi(numStr); err == nil {
+		return num
+	}
+	return 0
+}
+
+// extractKeyOutputFromLines extracts key output from pre-split lines.
+func extractKeyOutputFromLines(lines []string, maxLen int) string {
+	if len(lines) == 0 || maxLen <= 0 {
+		return ""
+	}
+
+	// Priority 1: Look for explicit summary lines
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+		lower := strings.ToLower(line)
+		if strings.HasPrefix(lower, "summary:") || strings.HasPrefix(lower, "completed:") ||
+			strings.HasPrefix(lower, "implemented:") || strings.HasPrefix(lower, "added:") ||
+			strings.HasPrefix(lower, "created:") || strings.HasPrefix(lower, "fixed:") {
+			content := line
+			for _, prefix := range []string{"Summary:", "Completed:", "Implemented:", "Added:", "Created:", "Fixed:",
+				"summary:", "completed:", "implemented:", "added:", "created:", "fixed:"} {
+				content = strings.TrimPrefix(content, prefix)
+			}
+			content = strings.TrimSpace(content)
+			if len(content) > 0 {
+				return safeTruncate(content, maxLen)
+			}
+		}
+	}
+
+	// Priority 2: First meaningful line (skip noise)
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+		if line == "" || strings.HasPrefix(line, "```") || strings.HasPrefix(line, "---") ||
+			strings.HasPrefix(line, "#") || strings.HasPrefix(line, "//") {
+			continue
+		}
+		// Skip very short lines (likely headers or markers)
+		if len(line) < 20 {
+			continue
+		}
+		return safeTruncate(line, maxLen)
+	}
+
+	// Fallback: truncate entire message
+	clean := strings.TrimSpace(strings.Join(lines, "\n"))
+	return safeTruncate(clean, maxLen)
+}

codeagent-wrapper/internal/app/utils_test.go

@@ -0,0 +1,143 @@
+package wrapper
+
+import (
+	"fmt"
+	"reflect"
+	"strings"
+	"testing"
+)
+
+func TestExtractCoverage(t *testing.T) {
+	tests := []struct {
+		name string
+		in   string
+		want string
+	}{
+		{"bare int", "92%", "92%"},
+		{"bare float", "92.5%", "92.5%"},
+		{"coverage prefix", "coverage: 92%", "92%"},
+		{"total prefix", "TOTAL 92%", "92%"},
+		{"all files", "All files 92%", "92%"},
+		{"empty", "", ""},
+		{"no number", "coverage: N/A", ""},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := extractCoverage(tt.in); got != tt.want {
+				t.Fatalf("extractCoverage(%q) = %q, want %q", tt.in, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestExtractTestResults(t *testing.T) {
+	tests := []struct {
+		name       string
+		in         string
+		wantPassed int
+		wantFailed int
+	}{
+		{"pytest one line", "12 passed, 2 failed", 12, 2},
+		{"pytest split lines", "12 passed\n2 failed", 12, 2},
+		{"jest format", "Tests: 2 failed, 12 passed, 14 total", 12, 2},
+		{"go test style count", "ok\texample.com/foo\t0.12s\t12 tests", 12, 0},
+		{"zero counts", "0 passed, 0 failed", 0, 0},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			passed, failed := extractTestResults(tt.in)
+			if passed != tt.wantPassed || failed != tt.wantFailed {
+				t.Fatalf("extractTestResults(%q) = (%d, %d), want (%d, %d)", tt.in, passed, failed, tt.wantPassed, tt.wantFailed)
+			}
+		})
+	}
+}
+
+func TestExtractFilesChanged(t *testing.T) {
+	tests := []struct {
+		name string
+		in   string
+		want []string
+	}{
+		{"root file", "Modified: main.go\n", []string{"main.go"}},
+		{"path file", "Created: codeagent-wrapper/utils.go\n", []string{"codeagent-wrapper/utils.go"}},
+		{"at prefix", "Updated: @codeagent-wrapper/main.go\n", []string{"codeagent-wrapper/main.go"}},
+		{"token scan", "Files: @main.go, @codeagent-wrapper/utils.go\n", []string{"main.go", "codeagent-wrapper/utils.go"}},
+		{"space path", "Modified: dir/with space/file.go\n", []string{"dir/with space/file.go"}},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := extractFilesChanged(tt.in); !reflect.DeepEqual(got, tt.want) {
+				t.Fatalf("extractFilesChanged(%q) = %#v, want %#v", tt.in, got, tt.want)
+			}
+		})
+	}
+
+	t.Run("limits to first 10", func(t *testing.T) {
+		var b strings.Builder
+		for i := 0; i < 12; i++ {
+			fmt.Fprintf(&b, "Modified: file%d.go\n", i)
+		}
+		got := extractFilesChanged(b.String())
+		if len(got) != 10 {
+			t.Fatalf("len(files)=%d, want 10: %#v", len(got), got)
+		}
+		for i := 0; i < 10; i++ {
+			want := fmt.Sprintf("file%d.go", i)
+			if got[i] != want {
+				t.Fatalf("files[%d]=%q, want %q", i, got[i], want)
+			}
+		}
+	})
+}
+
+func TestSafeTruncate(t *testing.T) {
+	tests := []struct {
+		name   string
+		in     string
+		maxLen int
+		want   string
+	}{
+		{"empty", "", 4, ""},
+		{"zero maxLen", "hello", 0, ""},
+		{"one rune", "你好", 1, "你"},
+		{"two runes no truncate", "你好", 2, "你好"},
+		{"three runes no truncate", "你好", 3, "你好"},
+		{"two runes truncates long", "你好世界", 2, "你"},
+		{"three runes truncates long", "你好世界", 3, "你"},
+		{"four with ellipsis", "你好世界啊", 4, "你..."},
+		{"emoji", "🙂🙂🙂🙂🙂", 4, "🙂..."},
+		{"no truncate", "你好世界", 4, "你好世界"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := safeTruncate(tt.in, tt.maxLen); got != tt.want {
+				t.Fatalf("safeTruncate(%q, %d) = %q, want %q", tt.in, tt.maxLen, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestSanitizeOutput(t *testing.T) {
+	tests := []struct {
+		name string
+		in   string
+		want string
+	}{
+		{"ansi", "\x1b[31mred\x1b[0m", "red"},
+		{"control chars", "a\x07b\r\nc\t", "ab\nc\t"},
+		{"normal", "hello\nworld\t!", "hello\nworld\t!"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := sanitizeOutput(tt.in); got != tt.want {
+				t.Fatalf("sanitizeOutput(%q) = %q, want %q", tt.in, got, tt.want)
+			}
+		})
+	}
+}

codeagent-wrapper/internal/app/wrapper_name.go

@@ -0,0 +1,9 @@
+package wrapper
+
+import ilogger "codeagent-wrapper/internal/logger"
+
+const wrapperName = ilogger.WrapperName
+
+func currentWrapperName() string { return ilogger.CurrentWrapperName() }
+
+func primaryLogPrefix() string { return ilogger.PrimaryLogPrefix() }

codeagent-wrapper/internal/backend/backend.go

@@ -0,0 +1,33 @@
+package backend
+
+import config "codeagent-wrapper/internal/config"
+
+// Backend defines the contract for invoking different AI CLI backends.
+// Each backend is responsible for supplying the executable command and
+// building the argument list based on the wrapper config.
+type Backend interface {
+	Name() string
+	BuildArgs(cfg *config.Config, targetArg string) []string
+	Command() string
+	Env(baseURL, apiKey string) map[string]string
+}
+
+var (
+	logWarnFn  = func(string) {}
+	logErrorFn = func(string) {}
+)
+
+// SetLogFuncs configures optional logging hooks used by some backends.
+// Callers can safely pass nil to disable the hook.
+func SetLogFuncs(warnFn, errorFn func(string)) {
+	if warnFn != nil {
+		logWarnFn = warnFn
+	} else {
+		logWarnFn = func(string) {}
+	}
+	if errorFn != nil {
+		logErrorFn = errorFn
+	} else {
+		logErrorFn = func(string) {}
+	}
+}

codeagent-wrapper/internal/backend/backend_test.go

@@ -0,0 +1,322 @@
+package backend
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"reflect"
+	"testing"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
+	backend := ClaudeBackend{}
+
+	t.Run("new mode omits skip-permissions when env disabled", func(t *testing.T) {
+		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
+		cfg := &config.Config{Mode: "new", WorkDir: "/repo"}
+		got := backend.BuildArgs(cfg, "todo")
+		want := []string{"-p", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "todo"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("new mode includes skip-permissions by default", func(t *testing.T) {
+		cfg := &config.Config{Mode: "new", SkipPermissions: false}
+		got := backend.BuildArgs(cfg, "-")
+		want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "-"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("resume mode includes session id", func(t *testing.T) {
+		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
+		cfg := &config.Config{Mode: "resume", SessionID: "sid-123", WorkDir: "/ignored"}
+		got := backend.BuildArgs(cfg, "resume-task")
+		want := []string{"-p", "--setting-sources", "", "-r", "sid-123", "--output-format", "stream-json", "--verbose", "resume-task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("resume mode without session still returns base flags", func(t *testing.T) {
+		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
+		cfg := &config.Config{Mode: "resume", WorkDir: "/ignored"}
+		got := backend.BuildArgs(cfg, "follow-up")
+		want := []string{"-p", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "follow-up"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("resume mode can opt-in skip permissions", func(t *testing.T) {
+		cfg := &config.Config{Mode: "resume", SessionID: "sid-123", SkipPermissions: true}
+		got := backend.BuildArgs(cfg, "resume-task")
+		want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "-r", "sid-123", "--output-format", "stream-json", "--verbose", "resume-task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("nil config returns nil", func(t *testing.T) {
+		if backend.BuildArgs(nil, "ignored") != nil {
+			t.Fatalf("nil config should return nil args")
+		}
+	})
+}
+
+func TestBackendBuildArgs_Model(t *testing.T) {
+	t.Run("claude includes --model when set", func(t *testing.T) {
+		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
+		backend := ClaudeBackend{}
+		cfg := &config.Config{Mode: "new", Model: "opus"}
+		got := backend.BuildArgs(cfg, "todo")
+		want := []string{"-p", "--setting-sources", "", "--model", "opus", "--output-format", "stream-json", "--verbose", "todo"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("gemini includes -m when set", func(t *testing.T) {
+		backend := GeminiBackend{}
+		cfg := &config.Config{Mode: "new", Model: "gemini-3-pro-preview"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"-o", "stream-json", "-y", "-m", "gemini-3-pro-preview", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("codex includes --model when set", func(t *testing.T) {
+		const key = "CODEX_BYPASS_SANDBOX"
+		t.Setenv(key, "false")
+
+		backend := CodexBackend{}
+		cfg := &config.Config{Mode: "new", WorkDir: "/tmp", Model: "o3"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"e", "--model", "o3", "--skip-git-repo-check", "-C", "/tmp", "--json", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+}
+
+func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
+	t.Run("gemini new mode defaults workdir", func(t *testing.T) {
+		backend := GeminiBackend{}
+		cfg := &config.Config{Mode: "new", WorkDir: "/workspace"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"-o", "stream-json", "-y", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("gemini resume mode uses session id", func(t *testing.T) {
+		backend := GeminiBackend{}
+		cfg := &config.Config{Mode: "resume", SessionID: "sid-999"}
+		got := backend.BuildArgs(cfg, "resume")
+		want := []string{"-o", "stream-json", "-y", "-r", "sid-999", "resume"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("gemini resume mode without session omits identifier", func(t *testing.T) {
+		backend := GeminiBackend{}
+		cfg := &config.Config{Mode: "resume"}
+		got := backend.BuildArgs(cfg, "resume")
+		want := []string{"-o", "stream-json", "-y", "resume"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("gemini nil config returns nil", func(t *testing.T) {
+		backend := GeminiBackend{}
+		if backend.BuildArgs(nil, "ignored") != nil {
+			t.Fatalf("nil config should return nil args")
+		}
+	})
+
+	t.Run("gemini stdin mode uses -p flag", func(t *testing.T) {
+		backend := GeminiBackend{}
+		cfg := &config.Config{Mode: "new"}
+		got := backend.BuildArgs(cfg, "-")
+		want := []string{"-o", "stream-json", "-y", "-p", "-"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("codex build args omits bypass flag by default", func(t *testing.T) {
+		const key = "CODEX_BYPASS_SANDBOX"
+		t.Setenv(key, "false")
+
+		backend := CodexBackend{}
+		cfg := &config.Config{Mode: "new", WorkDir: "/tmp"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"e", "--skip-git-repo-check", "-C", "/tmp", "--json", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("codex build args includes bypass flag when enabled", func(t *testing.T) {
+		const key = "CODEX_BYPASS_SANDBOX"
+		t.Setenv(key, "true")
+
+		backend := CodexBackend{}
+		cfg := &config.Config{Mode: "new", WorkDir: "/tmp"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"e", "--dangerously-bypass-approvals-and-sandbox", "--skip-git-repo-check", "-C", "/tmp", "--json", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("got %v, want %v", got, want)
+		}
+	})
+}
+
+func TestClaudeBuildArgs_BackendMetadata(t *testing.T) {
+	tests := []struct {
+		backend Backend
+		name    string
+		command string
+	}{
+		{backend: CodexBackend{}, name: "codex", command: "codex"},
+		{backend: ClaudeBackend{}, name: "claude", command: "claude"},
+		{backend: GeminiBackend{}, name: "gemini", command: "gemini"},
+	}
+
+	for _, tt := range tests {
+		if got := tt.backend.Name(); got != tt.name {
+			t.Fatalf("Name() = %s, want %s", got, tt.name)
+		}
+		if got := tt.backend.Command(); got != tt.command {
+			t.Fatalf("Command() = %s, want %s", got, tt.command)
+		}
+	}
+}
+
+func TestLoadMinimalEnvSettings(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	t.Run("missing file returns empty", func(t *testing.T) {
+		if got := LoadMinimalEnvSettings(); len(got) != 0 {
+			t.Fatalf("got %v, want empty", got)
+		}
+	})
+
+	t.Run("valid env returns string map", func(t *testing.T) {
+		dir := filepath.Join(home, ".claude")
+		if err := os.MkdirAll(dir, 0o755); err != nil {
+			t.Fatalf("MkdirAll: %v", err)
+		}
+		path := filepath.Join(dir, "settings.json")
+		data := []byte(`{"env":{"ANTHROPIC_API_KEY":"secret","FOO":"bar"}}`)
+		if err := os.WriteFile(path, data, 0o600); err != nil {
+			t.Fatalf("WriteFile: %v", err)
+		}
+
+		got := LoadMinimalEnvSettings()
+		if got["ANTHROPIC_API_KEY"] != "secret" || got["FOO"] != "bar" {
+			t.Fatalf("got %v, want keys present", got)
+		}
+	})
+
+	t.Run("non-string values are ignored", func(t *testing.T) {
+		dir := filepath.Join(home, ".claude")
+		path := filepath.Join(dir, "settings.json")
+		data := []byte(`{"env":{"GOOD":"ok","BAD":123,"ALSO_BAD":true}}`)
+		if err := os.WriteFile(path, data, 0o600); err != nil {
+			t.Fatalf("WriteFile: %v", err)
+		}
+
+		got := LoadMinimalEnvSettings()
+		if got["GOOD"] != "ok" {
+			t.Fatalf("got %v, want GOOD=ok", got)
+		}
+		if _, ok := got["BAD"]; ok {
+			t.Fatalf("got %v, want BAD omitted", got)
+		}
+		if _, ok := got["ALSO_BAD"]; ok {
+			t.Fatalf("got %v, want ALSO_BAD omitted", got)
+		}
+	})
+
+	t.Run("oversized file returns empty", func(t *testing.T) {
+		dir := filepath.Join(home, ".claude")
+		path := filepath.Join(dir, "settings.json")
+		data := bytes.Repeat([]byte("a"), MaxClaudeSettingsBytes+1)
+		if err := os.WriteFile(path, data, 0o600); err != nil {
+			t.Fatalf("WriteFile: %v", err)
+		}
+		if got := LoadMinimalEnvSettings(); len(got) != 0 {
+			t.Fatalf("got %v, want empty", got)
+		}
+	})
+}
+
+func TestOpencodeBackend_BuildArgs(t *testing.T) {
+	backend := OpencodeBackend{}
+
+	t.Run("basic", func(t *testing.T) {
+		cfg := &config.Config{Mode: "new"}
+		got := backend.BuildArgs(cfg, "hello")
+		want := []string{"run", "--format", "json", "hello"}
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("with model", func(t *testing.T) {
+		cfg := &config.Config{Mode: "new", Model: "opencode/grok-code"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"run", "-m", "opencode/grok-code", "--format", "json", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("resume mode", func(t *testing.T) {
+		cfg := &config.Config{Mode: "resume", SessionID: "ses_123", Model: "opencode/grok-code"}
+		got := backend.BuildArgs(cfg, "follow-up")
+		want := []string{"run", "-m", "opencode/grok-code", "-s", "ses_123", "--format", "json", "follow-up"}
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("resume without session", func(t *testing.T) {
+		cfg := &config.Config{Mode: "resume"}
+		got := backend.BuildArgs(cfg, "task")
+		want := []string{"run", "--format", "json", "task"}
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("got %v, want %v", got, want)
+		}
+	})
+
+	t.Run("stdin mode omits dash", func(t *testing.T) {
+		cfg := &config.Config{Mode: "new"}
+		got := backend.BuildArgs(cfg, "-")
+		want := []string{"run", "--format", "json"}
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("got %v, want %v", got, want)
+		}
+	})
+}
+
+func TestOpencodeBackend_Interface(t *testing.T) {
+	backend := OpencodeBackend{}
+
+	if backend.Name() != "opencode" {
+		t.Errorf("Name() = %q, want %q", backend.Name(), "opencode")
+	}
+	if backend.Command() != "opencode" {
+		t.Errorf("Command() = %q, want %q", backend.Command(), "opencode")
+	}
+}

codeagent-wrapper/internal/backend/claude.go

@@ -0,0 +1,139 @@
+package backend
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+
+	config "codeagent-wrapper/internal/config"
+
+	"github.com/goccy/go-json"
+)
+
+type ClaudeBackend struct{}
+
+func (ClaudeBackend) Name() string    { return "claude" }
+func (ClaudeBackend) Command() string { return "claude" }
+func (ClaudeBackend) Env(baseURL, apiKey string) map[string]string {
+	baseURL = strings.TrimSpace(baseURL)
+	apiKey = strings.TrimSpace(apiKey)
+	if baseURL == "" && apiKey == "" {
+		return nil
+	}
+	env := make(map[string]string, 2)
+	if baseURL != "" {
+		env["ANTHROPIC_BASE_URL"] = baseURL
+	}
+	if apiKey != "" {
+		env["ANTHROPIC_API_KEY"] = apiKey
+	}
+	return env
+}
+func (ClaudeBackend) BuildArgs(cfg *config.Config, targetArg string) []string {
+	return buildClaudeArgs(cfg, targetArg)
+}
+
+const MaxClaudeSettingsBytes = 1 << 20 // 1MB
+
+type MinimalClaudeSettings struct {
+	Env   map[string]string
+	Model string
+}
+
+// LoadMinimalClaudeSettings 从 ~/.claude/settings.json 只提取安全的最小子集：
+// - env: 只接受字符串类型的值
+// - model: 只接受字符串类型的值
+// 文件缺失/解析失败/超限都返回空。
+func LoadMinimalClaudeSettings() MinimalClaudeSettings {
+	home, err := os.UserHomeDir()
+	if err != nil || home == "" {
+		return MinimalClaudeSettings{}
+	}
+
+	claudeDir := filepath.Clean(filepath.Join(home, ".claude"))
+	settingPath := filepath.Clean(filepath.Join(claudeDir, "settings.json"))
+	rel, err := filepath.Rel(claudeDir, settingPath)
+	if err != nil || rel == ".." || strings.HasPrefix(rel, ".."+string(os.PathSeparator)) {
+		return MinimalClaudeSettings{}
+	}
+
+	info, err := os.Stat(settingPath)
+	if err != nil || info.Size() > MaxClaudeSettingsBytes {
+		return MinimalClaudeSettings{}
+	}
+
+	data, err := os.ReadFile(settingPath) // #nosec G304 -- path is fixed under user home and validated to stay within claudeDir
+	if err != nil {
+		return MinimalClaudeSettings{}
+	}
+
+	var cfg struct {
+		Env   map[string]any `json:"env"`
+		Model any            `json:"model"`
+	}
+	if err := json.Unmarshal(data, &cfg); err != nil {
+		return MinimalClaudeSettings{}
+	}
+
+	out := MinimalClaudeSettings{}
+
+	if model, ok := cfg.Model.(string); ok {
+		out.Model = strings.TrimSpace(model)
+	}
+
+	if len(cfg.Env) == 0 {
+		return out
+	}
+
+	env := make(map[string]string, len(cfg.Env))
+	for k, v := range cfg.Env {
+		s, ok := v.(string)
+		if !ok {
+			continue
+		}
+		env[k] = s
+	}
+	if len(env) == 0 {
+		return out
+	}
+	out.Env = env
+	return out
+}
+
+func LoadMinimalEnvSettings() map[string]string {
+	settings := LoadMinimalClaudeSettings()
+	if len(settings.Env) == 0 {
+		return nil
+	}
+	return settings.Env
+}
+
+func buildClaudeArgs(cfg *config.Config, targetArg string) []string {
+	if cfg == nil {
+		return nil
+	}
+	args := []string{"-p"}
+	// Default to skip permissions unless CODEAGENT_SKIP_PERMISSIONS=false
+	if cfg.SkipPermissions || cfg.Yolo || config.EnvFlagDefaultTrue("CODEAGENT_SKIP_PERMISSIONS") {
+		args = append(args, "--dangerously-skip-permissions")
+	}
+
+	// Prevent infinite recursion: disable all setting sources (user, project, local)
+	// This ensures a clean execution environment without CLAUDE.md or skills that would trigger codeagent
+	args = append(args, "--setting-sources", "")
+
+	if model := strings.TrimSpace(cfg.Model); model != "" {
+		args = append(args, "--model", model)
+	}
+
+	if cfg.Mode == "resume" {
+		if cfg.SessionID != "" {
+			// Claude CLI uses -r <session_id> for resume.
+			args = append(args, "-r", cfg.SessionID)
+		}
+	}
+
+	args = append(args, "--output-format", "stream-json", "--verbose", targetArg)
+
+	return args
+}

codeagent-wrapper/internal/backend/codex.go

@@ -0,0 +1,79 @@
+package backend
+
+import (
+	"strings"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+type CodexBackend struct{}
+
+func (CodexBackend) Name() string    { return "codex" }
+func (CodexBackend) Command() string { return "codex" }
+func (CodexBackend) Env(baseURL, apiKey string) map[string]string {
+	baseURL = strings.TrimSpace(baseURL)
+	apiKey = strings.TrimSpace(apiKey)
+	if baseURL == "" && apiKey == "" {
+		return nil
+	}
+	env := make(map[string]string, 2)
+	if baseURL != "" {
+		env["OPENAI_BASE_URL"] = baseURL
+	}
+	if apiKey != "" {
+		env["OPENAI_API_KEY"] = apiKey
+	}
+	return env
+}
+func (CodexBackend) BuildArgs(cfg *config.Config, targetArg string) []string {
+	return BuildCodexArgs(cfg, targetArg)
+}
+
+func BuildCodexArgs(cfg *config.Config, targetArg string) []string {
+	if cfg == nil {
+		panic("buildCodexArgs: nil config")
+	}
+
+	var resumeSessionID string
+	isResume := cfg.Mode == "resume"
+	if isResume {
+		resumeSessionID = strings.TrimSpace(cfg.SessionID)
+		if resumeSessionID == "" {
+			logErrorFn("invalid config: resume mode requires non-empty session_id")
+			isResume = false
+		}
+	}
+
+	args := []string{"e"}
+
+	// Default to bypass sandbox unless CODEX_BYPASS_SANDBOX=false
+	if cfg.Yolo || config.EnvFlagDefaultTrue("CODEX_BYPASS_SANDBOX") {
+		logWarnFn("YOLO mode or CODEX_BYPASS_SANDBOX enabled: running without approval/sandbox protection")
+		args = append(args, "--dangerously-bypass-approvals-and-sandbox")
+	}
+
+	if model := strings.TrimSpace(cfg.Model); model != "" {
+		args = append(args, "--model", model)
+	}
+
+	if reasoningEffort := strings.TrimSpace(cfg.ReasoningEffort); reasoningEffort != "" {
+		args = append(args, "-c", "model_reasoning_effort="+reasoningEffort)
+	}
+
+	args = append(args, "--skip-git-repo-check")
+
+	if isResume {
+		return append(args,
+			"--json",
+			"resume",
+			resumeSessionID,
+			targetArg,
+		)
+	}
+
+	return append(args,
+		"-C", cfg.WorkDir,
+		"--json",
+		targetArg,
+	)
+}

codeagent-wrapper/internal/backend/gemini.go

@@ -0,0 +1,110 @@
+package backend
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+type GeminiBackend struct{}
+
+func (GeminiBackend) Name() string    { return "gemini" }
+func (GeminiBackend) Command() string { return "gemini" }
+func (GeminiBackend) Env(baseURL, apiKey string) map[string]string {
+	baseURL = strings.TrimSpace(baseURL)
+	apiKey = strings.TrimSpace(apiKey)
+	if baseURL == "" && apiKey == "" {
+		return nil
+	}
+	env := make(map[string]string, 2)
+	if baseURL != "" {
+		env["GOOGLE_GEMINI_BASE_URL"] = baseURL
+	}
+	if apiKey != "" {
+		env["GEMINI_API_KEY"] = apiKey
+	}
+	return env
+}
+func (GeminiBackend) BuildArgs(cfg *config.Config, targetArg string) []string {
+	return buildGeminiArgs(cfg, targetArg)
+}
+
+// LoadGeminiEnv loads environment variables from ~/.gemini/.env
+// Supports GEMINI_API_KEY, GEMINI_MODEL, GOOGLE_GEMINI_BASE_URL
+// Also sets GEMINI_API_KEY_AUTH_MECHANISM=bearer for third-party API compatibility
+func LoadGeminiEnv() map[string]string {
+	home, err := os.UserHomeDir()
+	if err != nil || home == "" {
+		return nil
+	}
+
+	envDir := filepath.Clean(filepath.Join(home, ".gemini"))
+	envPath := filepath.Clean(filepath.Join(envDir, ".env"))
+	rel, err := filepath.Rel(envDir, envPath)
+	if err != nil || rel == ".." || strings.HasPrefix(rel, ".."+string(os.PathSeparator)) {
+		return nil
+	}
+
+	data, err := os.ReadFile(envPath) // #nosec G304 -- path is fixed under user home and validated to stay within envDir
+	if err != nil {
+		return nil
+	}
+
+	env := make(map[string]string)
+	for _, line := range strings.Split(string(data), "\n") {
+		line = strings.TrimSpace(line)
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+		idx := strings.IndexByte(line, '=')
+		if idx <= 0 {
+			continue
+		}
+		key := strings.TrimSpace(line[:idx])
+		value := strings.TrimSpace(line[idx+1:])
+		if key != "" && value != "" {
+			env[key] = value
+		}
+	}
+
+	// Set bearer auth mechanism for third-party API compatibility
+	if _, ok := env["GEMINI_API_KEY"]; ok {
+		if _, hasAuth := env["GEMINI_API_KEY_AUTH_MECHANISM"]; !hasAuth {
+			env["GEMINI_API_KEY_AUTH_MECHANISM"] = "bearer"
+		}
+	}
+
+	if len(env) == 0 {
+		return nil
+	}
+	return env
+}
+
+func buildGeminiArgs(cfg *config.Config, targetArg string) []string {
+	if cfg == nil {
+		return nil
+	}
+	args := []string{"-o", "stream-json", "-y"}
+
+	if model := strings.TrimSpace(cfg.Model); model != "" {
+		args = append(args, "-m", model)
+	}
+
+	if cfg.Mode == "resume" {
+		if cfg.SessionID != "" {
+			args = append(args, "-r", cfg.SessionID)
+		}
+	}
+
+	// Use positional argument instead of deprecated -p flag.
+	// For stdin mode ("-"), use -p to read from stdin.
+	if targetArg == "-" {
+		args = append(args, "-p", targetArg)
+	} else {
+		args = append(args, targetArg)
+	}
+
+	return args
+}

codeagent-wrapper/internal/backend/opencode.go

@@ -0,0 +1,29 @@
+package backend
+
+import (
+	"strings"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+type OpencodeBackend struct{}
+
+func (OpencodeBackend) Name() string                                 { return "opencode" }
+func (OpencodeBackend) Command() string                              { return "opencode" }
+func (OpencodeBackend) Env(baseURL, apiKey string) map[string]string { return nil }
+func (OpencodeBackend) BuildArgs(cfg *config.Config, targetArg string) []string {
+	args := []string{"run"}
+	if cfg != nil {
+		if model := strings.TrimSpace(cfg.Model); model != "" {
+			args = append(args, "-m", model)
+		}
+		if cfg.Mode == "resume" && cfg.SessionID != "" {
+			args = append(args, "-s", cfg.SessionID)
+		}
+	}
+	args = append(args, "--format", "json")
+	if targetArg != "-" {
+		args = append(args, targetArg)
+	}
+	return args
+}

codeagent-wrapper/internal/backend/registry.go

@@ -0,0 +1,29 @@
+package backend
+
+import (
+	"fmt"
+	"strings"
+)
+
+var registry = map[string]Backend{
+	"codex":    CodexBackend{},
+	"claude":   ClaudeBackend{},
+	"gemini":   GeminiBackend{},
+	"opencode": OpencodeBackend{},
+}
+
+// Registry exposes the available backends. Intended for internal inspection/tests.
+func Registry() map[string]Backend {
+	return registry
+}
+
+func Select(name string) (Backend, error) {
+	key := strings.ToLower(strings.TrimSpace(name))
+	if key == "" {
+		key = "codex"
+	}
+	if backend, ok := registry[key]; ok {
+		return backend, nil
+	}
+	return nil, fmt.Errorf("unsupported backend %q", name)
+}

codeagent-wrapper/internal/config/agent.go

@@ -0,0 +1,220 @@
+package config
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+
+	ilogger "codeagent-wrapper/internal/logger"
+
+	"github.com/goccy/go-json"
+)
+
+type BackendConfig struct {
+	BaseURL string `json:"base_url,omitempty"`
+	APIKey  string `json:"api_key,omitempty"`
+}
+
+type AgentModelConfig struct {
+	Backend     string `json:"backend"`
+	Model       string `json:"model"`
+	PromptFile  string `json:"prompt_file,omitempty"`
+	Description string `json:"description,omitempty"`
+	Yolo        bool   `json:"yolo,omitempty"`
+	Reasoning   string `json:"reasoning,omitempty"`
+	BaseURL     string `json:"base_url,omitempty"`
+	APIKey      string `json:"api_key,omitempty"`
+}
+
+type ModelsConfig struct {
+	DefaultBackend string                      `json:"default_backend"`
+	DefaultModel   string                      `json:"default_model"`
+	Agents         map[string]AgentModelConfig `json:"agents"`
+	Backends       map[string]BackendConfig    `json:"backends,omitempty"`
+}
+
+var defaultModelsConfig = ModelsConfig{
+	DefaultBackend: "opencode",
+	DefaultModel:   "opencode/grok-code",
+	Agents: map[string]AgentModelConfig{
+		"oracle":                  {Backend: "claude", Model: "claude-opus-4-5-20251101", PromptFile: "~/.claude/skills/omo/references/oracle.md", Description: "Technical advisor"},
+		"librarian":               {Backend: "claude", Model: "claude-sonnet-4-5-20250929", PromptFile: "~/.claude/skills/omo/references/librarian.md", Description: "Researcher"},
+		"explore":                 {Backend: "opencode", Model: "opencode/grok-code", PromptFile: "~/.claude/skills/omo/references/explore.md", Description: "Code search"},
+		"develop":                 {Backend: "codex", Model: "", PromptFile: "~/.claude/skills/omo/references/develop.md", Description: "Code development"},
+		"frontend-ui-ux-engineer": {Backend: "gemini", Model: "", PromptFile: "~/.claude/skills/omo/references/frontend-ui-ux-engineer.md", Description: "Frontend engineer"},
+		"document-writer":         {Backend: "gemini", Model: "", PromptFile: "~/.claude/skills/omo/references/document-writer.md", Description: "Documentation"},
+	},
+}
+
+var (
+	modelsConfigOnce   sync.Once
+	modelsConfigCached *ModelsConfig
+)
+
+func modelsConfig() *ModelsConfig {
+	modelsConfigOnce.Do(func() {
+		modelsConfigCached = loadModelsConfig()
+	})
+	if modelsConfigCached == nil {
+		return &defaultModelsConfig
+	}
+	return modelsConfigCached
+}
+
+func loadModelsConfig() *ModelsConfig {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		ilogger.LogWarn(fmt.Sprintf("Failed to resolve home directory for models config: %v; using defaults", err))
+		return &defaultModelsConfig
+	}
+
+	configDir := filepath.Clean(filepath.Join(home, ".codeagent"))
+	configPath := filepath.Clean(filepath.Join(configDir, "models.json"))
+	rel, err := filepath.Rel(configDir, configPath)
+	if err != nil || rel == ".." || strings.HasPrefix(rel, ".."+string(os.PathSeparator)) {
+		return &defaultModelsConfig
+	}
+
+	data, err := os.ReadFile(configPath) // #nosec G304 -- path is fixed under user home and validated to stay within configDir
+	if err != nil {
+		if !os.IsNotExist(err) {
+			ilogger.LogWarn(fmt.Sprintf("Failed to read models config %s: %v; using defaults", configPath, err))
+		}
+		return &defaultModelsConfig
+	}
+
+	var cfg ModelsConfig
+	if err := json.Unmarshal(data, &cfg); err != nil {
+		ilogger.LogWarn(fmt.Sprintf("Failed to parse models config %s: %v; using defaults", configPath, err))
+		return &defaultModelsConfig
+	}
+
+	cfg.DefaultBackend = strings.TrimSpace(cfg.DefaultBackend)
+	if cfg.DefaultBackend == "" {
+		cfg.DefaultBackend = defaultModelsConfig.DefaultBackend
+	}
+	cfg.DefaultModel = strings.TrimSpace(cfg.DefaultModel)
+	if cfg.DefaultModel == "" {
+		cfg.DefaultModel = defaultModelsConfig.DefaultModel
+	}
+
+	// Merge with defaults
+	for name, agent := range defaultModelsConfig.Agents {
+		if _, exists := cfg.Agents[name]; !exists {
+			if cfg.Agents == nil {
+				cfg.Agents = make(map[string]AgentModelConfig)
+			}
+			cfg.Agents[name] = agent
+		}
+	}
+
+	// Normalize backend keys so lookups can be case-insensitive.
+	if len(cfg.Backends) > 0 {
+		normalized := make(map[string]BackendConfig, len(cfg.Backends))
+		for k, v := range cfg.Backends {
+			key := strings.ToLower(strings.TrimSpace(k))
+			if key == "" {
+				continue
+			}
+			normalized[key] = v
+		}
+		if len(normalized) > 0 {
+			cfg.Backends = normalized
+		} else {
+			cfg.Backends = nil
+		}
+	}
+
+	return &cfg
+}
+
+func LoadDynamicAgent(name string) (AgentModelConfig, bool) {
+	if err := ValidateAgentName(name); err != nil {
+		return AgentModelConfig{}, false
+	}
+
+	home, err := os.UserHomeDir()
+	if err != nil || strings.TrimSpace(home) == "" {
+		return AgentModelConfig{}, false
+	}
+
+	absPath := filepath.Join(home, ".codeagent", "agents", name+".md")
+	info, err := os.Stat(absPath)
+	if err != nil || info.IsDir() {
+		return AgentModelConfig{}, false
+	}
+
+	return AgentModelConfig{PromptFile: "~/.codeagent/agents/" + name + ".md"}, true
+}
+
+func ResolveBackendConfig(backendName string) (baseURL, apiKey string) {
+	cfg := modelsConfig()
+	resolved := resolveBackendConfig(cfg, backendName)
+	return strings.TrimSpace(resolved.BaseURL), strings.TrimSpace(resolved.APIKey)
+}
+
+func resolveBackendConfig(cfg *ModelsConfig, backendName string) BackendConfig {
+	if cfg == nil || len(cfg.Backends) == 0 {
+		return BackendConfig{}
+	}
+	key := strings.ToLower(strings.TrimSpace(backendName))
+	if key == "" {
+		key = strings.ToLower(strings.TrimSpace(cfg.DefaultBackend))
+	}
+	if key == "" {
+		return BackendConfig{}
+	}
+	if backend, ok := cfg.Backends[key]; ok {
+		return backend
+	}
+	return BackendConfig{}
+}
+
+func resolveAgentConfig(agentName string) (backend, model, promptFile, reasoning, baseURL, apiKey string, yolo bool) {
+	cfg := modelsConfig()
+	if agent, ok := cfg.Agents[agentName]; ok {
+		backend = strings.TrimSpace(agent.Backend)
+		if backend == "" {
+			backend = cfg.DefaultBackend
+		}
+		backendCfg := resolveBackendConfig(cfg, backend)
+
+		baseURL = strings.TrimSpace(agent.BaseURL)
+		if baseURL == "" {
+			baseURL = strings.TrimSpace(backendCfg.BaseURL)
+		}
+		apiKey = strings.TrimSpace(agent.APIKey)
+		if apiKey == "" {
+			apiKey = strings.TrimSpace(backendCfg.APIKey)
+		}
+
+		return backend, strings.TrimSpace(agent.Model), agent.PromptFile, agent.Reasoning, baseURL, apiKey, agent.Yolo
+	}
+
+	if dynamic, ok := LoadDynamicAgent(agentName); ok {
+		backend = cfg.DefaultBackend
+		model = cfg.DefaultModel
+		backendCfg := resolveBackendConfig(cfg, backend)
+		baseURL = strings.TrimSpace(backendCfg.BaseURL)
+		apiKey = strings.TrimSpace(backendCfg.APIKey)
+		return backend, model, dynamic.PromptFile, "", baseURL, apiKey, false
+	}
+
+	backend = cfg.DefaultBackend
+	model = cfg.DefaultModel
+	backendCfg := resolveBackendConfig(cfg, backend)
+	baseURL = strings.TrimSpace(backendCfg.BaseURL)
+	apiKey = strings.TrimSpace(backendCfg.APIKey)
+	return backend, model, "", "", baseURL, apiKey, false
+}
+
+func ResolveAgentConfig(agentName string) (backend, model, promptFile, reasoning, baseURL, apiKey string, yolo bool) {
+	return resolveAgentConfig(agentName)
+}
+
+func ResetModelsConfigCacheForTest() {
+	modelsConfigCached = nil
+	modelsConfigOnce = sync.Once{}
+}

codeagent-wrapper/internal/config/agent_config_test.go

@@ -0,0 +1,221 @@
+package config
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestResolveAgentConfig_Defaults(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	// Test that default agents resolve correctly without config file
+	tests := []struct {
+		agent          string
+		wantBackend    string
+		wantModel      string
+		wantPromptFile string
+	}{
+		{"oracle", "claude", "claude-opus-4-5-20251101", "~/.claude/skills/omo/references/oracle.md"},
+		{"librarian", "claude", "claude-sonnet-4-5-20250929", "~/.claude/skills/omo/references/librarian.md"},
+		{"explore", "opencode", "opencode/grok-code", "~/.claude/skills/omo/references/explore.md"},
+		{"frontend-ui-ux-engineer", "gemini", "", "~/.claude/skills/omo/references/frontend-ui-ux-engineer.md"},
+		{"document-writer", "gemini", "", "~/.claude/skills/omo/references/document-writer.md"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.agent, func(t *testing.T) {
+			backend, model, promptFile, _, _, _, _ := resolveAgentConfig(tt.agent)
+			if backend != tt.wantBackend {
+				t.Errorf("backend = %q, want %q", backend, tt.wantBackend)
+			}
+			if model != tt.wantModel {
+				t.Errorf("model = %q, want %q", model, tt.wantModel)
+			}
+			if promptFile != tt.wantPromptFile {
+				t.Errorf("promptFile = %q, want %q", promptFile, tt.wantPromptFile)
+			}
+		})
+	}
+}
+
+func TestResolveAgentConfig_UnknownAgent(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	backend, model, promptFile, _, _, _, _ := resolveAgentConfig("unknown-agent")
+	if backend != "opencode" {
+		t.Errorf("unknown agent backend = %q, want %q", backend, "opencode")
+	}
+	if model != "opencode/grok-code" {
+		t.Errorf("unknown agent model = %q, want %q", model, "opencode/grok-code")
+	}
+	if promptFile != "" {
+		t.Errorf("unknown agent promptFile = %q, want empty", promptFile)
+	}
+}
+
+func TestLoadModelsConfig_NoFile(t *testing.T) {
+	home := "/nonexistent/path/that/does/not/exist"
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	cfg := loadModelsConfig()
+	if cfg.DefaultBackend != "opencode" {
+		t.Errorf("DefaultBackend = %q, want %q", cfg.DefaultBackend, "opencode")
+	}
+	if len(cfg.Agents) != 6 {
+		t.Errorf("len(Agents) = %d, want 6", len(cfg.Agents))
+	}
+}
+
+func TestLoadModelsConfig_WithFile(t *testing.T) {
+	// Create temp dir and config file
+	tmpDir := t.TempDir()
+	configDir := filepath.Join(tmpDir, ".codeagent")
+	if err := os.MkdirAll(configDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+
+	configContent := `{
+		"default_backend": "claude",
+		"default_model": "claude-opus-4",
+		"backends": {
+			"Claude": {
+				"base_url": "https://backend.example",
+				"api_key": "backend-key"
+			},
+			"codex": {
+				"base_url": "https://openai.example",
+				"api_key": "openai-key"
+			}
+		},
+		"agents": {
+			"custom-agent": {
+				"backend": "codex",
+				"model": "gpt-4o",
+				"description": "Custom agent",
+				"base_url": "https://agent.example",
+				"api_key": "agent-key"
+			}
+		}
+	}`
+	configPath := filepath.Join(configDir, "models.json")
+	if err := os.WriteFile(configPath, []byte(configContent), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	t.Setenv("HOME", tmpDir)
+	t.Setenv("USERPROFILE", tmpDir)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	cfg := loadModelsConfig()
+
+	if cfg.DefaultBackend != "claude" {
+		t.Errorf("DefaultBackend = %q, want %q", cfg.DefaultBackend, "claude")
+	}
+	if cfg.DefaultModel != "claude-opus-4" {
+		t.Errorf("DefaultModel = %q, want %q", cfg.DefaultModel, "claude-opus-4")
+	}
+
+	// Check custom agent
+	if agent, ok := cfg.Agents["custom-agent"]; !ok {
+		t.Error("custom-agent not found")
+	} else {
+		if agent.Backend != "codex" {
+			t.Errorf("custom-agent.Backend = %q, want %q", agent.Backend, "codex")
+		}
+		if agent.Model != "gpt-4o" {
+			t.Errorf("custom-agent.Model = %q, want %q", agent.Model, "gpt-4o")
+		}
+	}
+
+	// Check that defaults are merged
+	if _, ok := cfg.Agents["oracle"]; !ok {
+		t.Error("default agent oracle should be merged")
+	}
+
+	baseURL, apiKey := ResolveBackendConfig("claude")
+	if baseURL != "https://backend.example" {
+		t.Errorf("ResolveBackendConfig(baseURL) = %q, want %q", baseURL, "https://backend.example")
+	}
+	if apiKey != "backend-key" {
+		t.Errorf("ResolveBackendConfig(apiKey) = %q, want %q", apiKey, "backend-key")
+	}
+
+	backend, model, _, _, agentBaseURL, agentAPIKey, _ := ResolveAgentConfig("custom-agent")
+	if backend != "codex" {
+		t.Errorf("ResolveAgentConfig(backend) = %q, want %q", backend, "codex")
+	}
+	if model != "gpt-4o" {
+		t.Errorf("ResolveAgentConfig(model) = %q, want %q", model, "gpt-4o")
+	}
+	if agentBaseURL != "https://agent.example" {
+		t.Errorf("ResolveAgentConfig(baseURL) = %q, want %q", agentBaseURL, "https://agent.example")
+	}
+	if agentAPIKey != "agent-key" {
+		t.Errorf("ResolveAgentConfig(apiKey) = %q, want %q", agentAPIKey, "agent-key")
+	}
+}
+
+func TestResolveAgentConfig_DynamicAgent(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	agentDir := filepath.Join(home, ".codeagent", "agents")
+	if err := os.MkdirAll(agentDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+	if err := os.WriteFile(filepath.Join(agentDir, "sarsh.md"), []byte("prompt\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	backend, model, promptFile, _, _, _, _ := resolveAgentConfig("sarsh")
+	if backend != "opencode" {
+		t.Errorf("backend = %q, want %q", backend, "opencode")
+	}
+	if model != "opencode/grok-code" {
+		t.Errorf("model = %q, want %q", model, "opencode/grok-code")
+	}
+	if promptFile != "~/.codeagent/agents/sarsh.md" {
+		t.Errorf("promptFile = %q, want %q", promptFile, "~/.codeagent/agents/sarsh.md")
+	}
+}
+
+func TestLoadModelsConfig_InvalidJSON(t *testing.T) {
+	tmpDir := t.TempDir()
+	configDir := filepath.Join(tmpDir, ".codeagent")
+	if err := os.MkdirAll(configDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+
+	// Write invalid JSON
+	configPath := filepath.Join(configDir, "models.json")
+	if err := os.WriteFile(configPath, []byte("invalid json {"), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	t.Setenv("HOME", tmpDir)
+	t.Setenv("USERPROFILE", tmpDir)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	cfg := loadModelsConfig()
+	// Should fall back to defaults
+	if cfg.DefaultBackend != "opencode" {
+		t.Errorf("invalid JSON should fallback, got DefaultBackend = %q", cfg.DefaultBackend)
+	}
+}

codeagent-wrapper/internal/config/config.go

@@ -0,0 +1,102 @@
+package config
+
+import (
+	"fmt"
+	"os"
+	"strconv"
+	"strings"
+)
+
+// Config holds CLI configuration.
+type Config struct {
+	Mode               string // "new" or "resume"
+	Task               string
+	SessionID          string
+	WorkDir            string
+	Model              string
+	ReasoningEffort    string
+	ExplicitStdin      bool
+	Timeout            int
+	Backend            string
+	Agent              string
+	PromptFile         string
+	PromptFileExplicit bool
+	SkipPermissions    bool
+	Yolo               bool
+	MaxParallelWorkers int
+}
+
+// EnvFlagEnabled returns true when the environment variable exists and is not
+// explicitly set to a falsey value ("0/false/no/off").
+func EnvFlagEnabled(key string) bool {
+	val, ok := os.LookupEnv(key)
+	if !ok {
+		return false
+	}
+	val = strings.TrimSpace(strings.ToLower(val))
+	switch val {
+	case "", "0", "false", "no", "off":
+		return false
+	default:
+		return true
+	}
+}
+
+func ParseBoolFlag(val string, defaultValue bool) bool {
+	val = strings.TrimSpace(strings.ToLower(val))
+	switch val {
+	case "1", "true", "yes", "on":
+		return true
+	case "0", "false", "no", "off":
+		return false
+	default:
+		return defaultValue
+	}
+}
+
+// EnvFlagDefaultTrue returns true unless the env var is explicitly set to
+// false/0/no/off.
+func EnvFlagDefaultTrue(key string) bool {
+	val, ok := os.LookupEnv(key)
+	if !ok {
+		return true
+	}
+	return ParseBoolFlag(val, true)
+}
+
+func ValidateAgentName(name string) error {
+	if strings.TrimSpace(name) == "" {
+		return fmt.Errorf("agent name is empty")
+	}
+	for _, r := range name {
+		switch {
+		case r >= 'a' && r <= 'z':
+		case r >= 'A' && r <= 'Z':
+		case r >= '0' && r <= '9':
+		case r == '-', r == '_':
+		default:
+			return fmt.Errorf("agent name %q contains invalid character %q", name, r)
+		}
+	}
+	return nil
+}
+
+const maxParallelWorkersLimit = 100
+
+// ResolveMaxParallelWorkers reads CODEAGENT_MAX_PARALLEL_WORKERS. It returns 0
+// for "unlimited".
+func ResolveMaxParallelWorkers() int {
+	raw := strings.TrimSpace(os.Getenv("CODEAGENT_MAX_PARALLEL_WORKERS"))
+	if raw == "" {
+		return 0
+	}
+
+	value, err := strconv.Atoi(raw)
+	if err != nil || value < 0 {
+		return 0
+	}
+	if value > maxParallelWorkersLimit {
+		return maxParallelWorkersLimit
+	}
+	return value
+}

codeagent-wrapper/internal/config/viper.go

@@ -0,0 +1,47 @@
+package config
+
+import (
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"github.com/spf13/viper"
+)
+
+// NewViper returns a viper instance configured for CODEAGENT_* environment
+// variables and an optional config file.
+//
+// Search order when configFile is empty:
+//   - $HOME/.codeagent/config.(yaml|yml|json|toml|...)
+func NewViper(configFile string) (*viper.Viper, error) {
+	v := viper.New()
+	v.SetEnvPrefix("CODEAGENT")
+	v.SetEnvKeyReplacer(strings.NewReplacer("-", "_"))
+	v.AutomaticEnv()
+
+	if strings.TrimSpace(configFile) != "" {
+		v.SetConfigFile(configFile)
+		if err := v.ReadInConfig(); err != nil {
+			return nil, err
+		}
+		return v, nil
+	}
+
+	home, err := os.UserHomeDir()
+	if err != nil || strings.TrimSpace(home) == "" {
+		return v, nil
+	}
+
+	v.SetConfigName("config")
+	v.AddConfigPath(filepath.Join(home, ".codeagent"))
+	if err := v.ReadInConfig(); err != nil {
+		var notFound viper.ConfigFileNotFoundError
+		if errors.As(err, &notFound) {
+			return v, nil
+		}
+		return nil, err
+	}
+
+	return v, nil
+}

codeagent-wrapper/internal/executor/filter.go

@@ -0,0 +1,72 @@
+package executor
+
+import (
+	"bytes"
+	"io"
+	"strings"
+)
+
+// geminiNoisePatterns contains stderr patterns to filter for gemini backend
+var geminiNoisePatterns = []string{
+	"[STARTUP]",
+	"Session cleanup disabled",
+	"Warning:",
+	"(node:",
+	"(Use `node --trace-warnings",
+	"Loaded cached credentials",
+	"Loading extension:",
+	"YOLO mode is enabled",
+}
+
+// codexNoisePatterns contains stderr patterns to filter for codex backend
+var codexNoisePatterns = []string{
+	"ERROR codex_core::codex: needs_follow_up:",
+	"ERROR codex_core::skills::loader:",
+}
+
+// filteringWriter wraps an io.Writer and filters out lines matching patterns
+type filteringWriter struct {
+	w        io.Writer
+	patterns []string
+	buf      bytes.Buffer
+}
+
+func newFilteringWriter(w io.Writer, patterns []string) *filteringWriter {
+	return &filteringWriter{w: w, patterns: patterns}
+}
+
+func (f *filteringWriter) Write(p []byte) (n int, err error) {
+	f.buf.Write(p)
+	for {
+		line, err := f.buf.ReadString('\n')
+		if err != nil {
+			// incomplete line, put it back
+			f.buf.WriteString(line)
+			break
+		}
+		if !f.shouldFilter(line) {
+			_, _ = f.w.Write([]byte(line))
+		}
+	}
+	return len(p), nil
+}
+
+func (f *filteringWriter) shouldFilter(line string) bool {
+	for _, pattern := range f.patterns {
+		if strings.Contains(line, pattern) {
+			return true
+		}
+	}
+	return false
+}
+
+// Flush writes any remaining buffered content
+func (f *filteringWriter) Flush() {
+	if f.buf.Len() > 0 {
+		remaining := f.buf.String()
+		if !f.shouldFilter(remaining) {
+			_, _ = f.w.Write([]byte(remaining))
+		}
+		f.buf.Reset()
+	}
+}

codeagent-wrapper/internal/executor/filter_test.go

@@ -0,0 +1,73 @@
+package executor
+
+import (
+	"bytes"
+	"testing"
+)
+
+func TestFilteringWriter(t *testing.T) {
+	tests := []struct {
+		name     string
+		patterns []string
+		input    string
+		want     string
+	}{
+		{
+			name:     "filter STARTUP lines",
+			patterns: geminiNoisePatterns,
+			input:    "[STARTUP] Recording metric\nHello World\n[STARTUP] Another line\n",
+			want:     "Hello World\n",
+		},
+		{
+			name:     "filter Warning lines",
+			patterns: geminiNoisePatterns,
+			input:    "Warning: something bad\nActual output\n",
+			want:     "Actual output\n",
+		},
+		{
+			name:     "filter multiple patterns",
+			patterns: geminiNoisePatterns,
+			input:    "YOLO mode is enabled\nSession cleanup disabled\nReal content\nLoading extension: foo\n",
+			want:     "Real content\n",
+		},
+		{
+			name:     "no filtering needed",
+			patterns: geminiNoisePatterns,
+			input:    "Line 1\nLine 2\nLine 3\n",
+			want:     "Line 1\nLine 2\nLine 3\n",
+		},
+		{
+			name:     "empty input",
+			patterns: geminiNoisePatterns,
+			input:    "",
+			want:     "",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			var buf bytes.Buffer
+			fw := newFilteringWriter(&buf, tt.patterns)
+			_, _ = fw.Write([]byte(tt.input))
+			fw.Flush()
+
+			if got := buf.String(); got != tt.want {
+				t.Errorf("got %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestFilteringWriterPartialLines(t *testing.T) {
+	var buf bytes.Buffer
+	fw := newFilteringWriter(&buf, geminiNoisePatterns)
+
+	// Write partial line
+	_, _ = fw.Write([]byte("Hello "))
+	_, _ = fw.Write([]byte("World\n"))
+	fw.Flush()
+
+	if got := buf.String(); got != "Hello World\n" {
+		t.Errorf("got %q, want %q", got, "Hello World\n")
+	}
+}

codeagent-wrapper/internal/executor/log_helpers.go

@@ -0,0 +1,124 @@
+package executor
+
+import "bytes"
+
+type logWriter struct {
+	prefix  string
+	maxLen  int
+	buf     bytes.Buffer
+	dropped bool
+}
+
+func newLogWriter(prefix string, maxLen int) *logWriter {
+	if maxLen <= 0 {
+		maxLen = codexLogLineLimit
+	}
+	return &logWriter{prefix: prefix, maxLen: maxLen}
+}
+
+func (lw *logWriter) Write(p []byte) (int, error) {
+	if lw == nil {
+		return len(p), nil
+	}
+	total := len(p)
+	for len(p) > 0 {
+		if idx := bytes.IndexByte(p, '\n'); idx >= 0 {
+			lw.writeLimited(p[:idx])
+			lw.logLine(true)
+			p = p[idx+1:]
+			continue
+		}
+		lw.writeLimited(p)
+		break
+	}
+	return total, nil
+}
+
+func (lw *logWriter) Flush() {
+	if lw == nil || lw.buf.Len() == 0 {
+		return
+	}
+	lw.logLine(false)
+}
+
+func (lw *logWriter) logLine(force bool) {
+	if lw == nil {
+		return
+	}
+	line := lw.buf.String()
+	dropped := lw.dropped
+	lw.dropped = false
+	lw.buf.Reset()
+	if line == "" && !force {
+		return
+	}
+	if lw.maxLen > 0 {
+		if dropped {
+			if lw.maxLen > 3 {
+				line = line[:min(len(line), lw.maxLen-3)] + "..."
+			} else {
+				line = line[:min(len(line), lw.maxLen)]
+			}
+		} else if len(line) > lw.maxLen {
+			cutoff := lw.maxLen
+			if cutoff > 3 {
+				line = line[:cutoff-3] + "..."
+			} else {
+				line = line[:cutoff]
+			}
+		}
+	}
+	logInfo(lw.prefix + line)
+}
+
+func (lw *logWriter) writeLimited(p []byte) {
+	if lw == nil || len(p) == 0 {
+		return
+	}
+	if lw.maxLen <= 0 {
+		lw.buf.Write(p)
+		return
+	}
+
+	remaining := lw.maxLen - lw.buf.Len()
+	if remaining <= 0 {
+		lw.dropped = true
+		return
+	}
+	if len(p) <= remaining {
+		lw.buf.Write(p)
+		return
+	}
+	lw.buf.Write(p[:remaining])
+	lw.dropped = true
+}
+
+type tailBuffer struct {
+	limit int
+	data  []byte
+}
+
+func (b *tailBuffer) Write(p []byte) (int, error) {
+	if b.limit <= 0 {
+		return len(p), nil
+	}
+
+	if len(p) >= b.limit {
+		b.data = append(b.data[:0], p[len(p)-b.limit:]...)
+		return len(p), nil
+	}
+
+	total := len(b.data) + len(p)
+	if total <= b.limit {
+		b.data = append(b.data, p...)
+		return len(p), nil
+	}
+
+	overflow := total - b.limit
+	b.data = append(b.data[overflow:], p...)
+	return len(p), nil
+}
+
+func (b *tailBuffer) String() string {
+	return string(b.data)
+}

codeagent-wrapper/internal/executor/log_writer_limit_test.go

@@ -0,0 +1,36 @@
+package executor
+
+import (
+	"os"
+	"strings"
+	"testing"
+)
+
+func TestLogWriterWriteLimitsBuffer(t *testing.T) {
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger error: %v", err)
+	}
+	setLogger(logger)
+	t.Cleanup(func() { _ = closeLogger() })
+
+	lw := newLogWriter("P:", 10)
+	_, _ = lw.Write([]byte(strings.Repeat("a", 100)))
+
+	if lw.buf.Len() != 10 {
+		t.Fatalf("logWriter buffer len=%d, want %d", lw.buf.Len(), 10)
+	}
+	if !lw.dropped {
+		t.Fatalf("expected logWriter to drop overlong line bytes")
+	}
+
+	lw.Flush()
+	logger.Flush()
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("ReadFile error: %v", err)
+	}
+	if !strings.Contains(string(data), "P:aaaaaaa...") {
+		t.Fatalf("log output missing truncated entry, got %q", string(data))
+	}
+}

codeagent-wrapper/internal/executor/parallel_config.go

@@ -0,0 +1,135 @@
+package executor
+
+import (
+	"bytes"
+	"fmt"
+	"strings"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+func ParseParallelConfig(data []byte) (*ParallelConfig, error) {
+	trimmed := bytes.TrimSpace(data)
+	if len(trimmed) == 0 {
+		return nil, fmt.Errorf("parallel config is empty")
+	}
+
+	tasks := strings.Split(string(trimmed), "---TASK---")
+	var cfg ParallelConfig
+	seen := make(map[string]struct{})
+
+	taskIndex := 0
+	for _, taskBlock := range tasks {
+		taskBlock = strings.TrimSpace(taskBlock)
+		if taskBlock == "" {
+			continue
+		}
+		taskIndex++
+
+		parts := strings.SplitN(taskBlock, "---CONTENT---", 2)
+		if len(parts) != 2 {
+			return nil, fmt.Errorf("task block #%d missing ---CONTENT--- separator", taskIndex)
+		}
+
+		meta := strings.TrimSpace(parts[0])
+		content := strings.TrimSpace(parts[1])
+
+		task := TaskSpec{WorkDir: defaultWorkdir}
+		agentSpecified := false
+		for _, line := range strings.Split(meta, "\n") {
+			line = strings.TrimSpace(line)
+			if line == "" {
+				continue
+			}
+			kv := strings.SplitN(line, ":", 2)
+			if len(kv) != 2 {
+				continue
+			}
+			key := strings.TrimSpace(kv[0])
+			value := strings.TrimSpace(kv[1])
+
+			switch key {
+			case "id":
+				task.ID = value
+			case "workdir":
+				// Validate workdir: "-" is not a valid directory
+				if value == "-" {
+					return nil, fmt.Errorf("task block #%d has invalid workdir: '-' is not a valid directory path", taskIndex)
+				}
+				task.WorkDir = value
+			case "session_id":
+				task.SessionID = value
+				task.Mode = "resume"
+			case "backend":
+				task.Backend = value
+			case "model":
+				task.Model = value
+			case "reasoning_effort":
+				task.ReasoningEffort = value
+			case "agent":
+				agentSpecified = true
+				task.Agent = value
+			case "skip_permissions", "skip-permissions":
+				if value == "" {
+					task.SkipPermissions = true
+					continue
+				}
+				task.SkipPermissions = config.ParseBoolFlag(value, false)
+			case "dependencies":
+				for _, dep := range strings.Split(value, ",") {
+					dep = strings.TrimSpace(dep)
+					if dep != "" {
+						task.Dependencies = append(task.Dependencies, dep)
+					}
+				}
+			}
+		}
+
+		if task.Mode == "" {
+			task.Mode = "new"
+		}
+
+		if agentSpecified {
+			if strings.TrimSpace(task.Agent) == "" {
+				return nil, fmt.Errorf("task block #%d has empty agent field", taskIndex)
+			}
+			if err := config.ValidateAgentName(task.Agent); err != nil {
+				return nil, fmt.Errorf("task block #%d invalid agent name: %w", taskIndex, err)
+			}
+			backend, model, promptFile, reasoning, _, _, _ := config.ResolveAgentConfig(task.Agent)
+			if task.Backend == "" {
+				task.Backend = backend
+			}
+			if task.Model == "" {
+				task.Model = model
+			}
+			if task.ReasoningEffort == "" {
+				task.ReasoningEffort = reasoning
+			}
+			task.PromptFile = promptFile
+		}
+
+		if task.ID == "" {
+			return nil, fmt.Errorf("task block #%d missing id field", taskIndex)
+		}
+		if content == "" {
+			return nil, fmt.Errorf("task block #%d (%q) missing content", taskIndex, task.ID)
+		}
+		if task.Mode == "resume" && strings.TrimSpace(task.SessionID) == "" {
+			return nil, fmt.Errorf("task block #%d (%q) has empty session_id", taskIndex, task.ID)
+		}
+		if _, exists := seen[task.ID]; exists {
+			return nil, fmt.Errorf("task block #%d has duplicate id: %s", taskIndex, task.ID)
+		}
+
+		task.Task = content
+		cfg.Tasks = append(cfg.Tasks, task)
+		seen[task.ID] = struct{}{}
+	}
+
+	if len(cfg.Tasks) == 0 {
+		return nil, fmt.Errorf("no tasks found")
+	}
+
+	return &cfg, nil
+}

codeagent-wrapper/internal/executor/prompt.go

@@ -0,0 +1,130 @@
+package executor
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+func ReadAgentPromptFile(path string, allowOutsideClaudeDir bool) (string, error) {
+	raw := strings.TrimSpace(path)
+	if raw == "" {
+		return "", nil
+	}
+
+	expanded := raw
+	if raw == "~" || strings.HasPrefix(raw, "~/") || strings.HasPrefix(raw, "~\\") {
+		home, err := os.UserHomeDir()
+		if err != nil {
+			return "", err
+		}
+		if raw == "~" {
+			expanded = home
+		} else {
+			expanded = home + raw[1:]
+		}
+	}
+
+	absPath, err := filepath.Abs(expanded)
+	if err != nil {
+		return "", err
+	}
+	absPath = filepath.Clean(absPath)
+
+	home, err := os.UserHomeDir()
+	if err != nil {
+		if !allowOutsideClaudeDir {
+			return "", err
+		}
+		logWarn(fmt.Sprintf("Failed to resolve home directory for prompt file validation: %v; proceeding without restriction", err))
+	} else {
+		allowedDirs := []string{
+			filepath.Clean(filepath.Join(home, ".claude")),
+			filepath.Clean(filepath.Join(home, ".codeagent", "agents")),
+		}
+		for i := range allowedDirs {
+			allowedAbs, err := filepath.Abs(allowedDirs[i])
+			if err == nil {
+				allowedDirs[i] = filepath.Clean(allowedAbs)
+			}
+		}
+
+		isWithinDir := func(path, dir string) bool {
+			rel, err := filepath.Rel(dir, path)
+			if err != nil {
+				return false
+			}
+			rel = filepath.Clean(rel)
+			if rel == "." {
+				return true
+			}
+			if rel == ".." {
+				return false
+			}
+			prefix := ".." + string(os.PathSeparator)
+			return !strings.HasPrefix(rel, prefix)
+		}
+
+		if !allowOutsideClaudeDir {
+			withinAllowed := false
+			for _, dir := range allowedDirs {
+				if isWithinDir(absPath, dir) {
+					withinAllowed = true
+					break
+				}
+			}
+			if !withinAllowed {
+				logWarn(fmt.Sprintf("Refusing to read prompt file outside allowed dirs (%s): %s", strings.Join(allowedDirs, ", "), absPath))
+				return "", fmt.Errorf("prompt file must be under ~/.claude or ~/.codeagent/agents")
+			}
+
+			resolvedPath, errPath := filepath.EvalSymlinks(absPath)
+			if errPath == nil {
+				resolvedPath = filepath.Clean(resolvedPath)
+				resolvedAllowed := make([]string, 0, len(allowedDirs))
+				for _, dir := range allowedDirs {
+					resolvedBase, errBase := filepath.EvalSymlinks(dir)
+					if errBase != nil {
+						continue
+					}
+					resolvedAllowed = append(resolvedAllowed, filepath.Clean(resolvedBase))
+				}
+				if len(resolvedAllowed) > 0 {
+					withinResolved := false
+					for _, dir := range resolvedAllowed {
+						if isWithinDir(resolvedPath, dir) {
+							withinResolved = true
+							break
+						}
+					}
+					if !withinResolved {
+						logWarn(fmt.Sprintf("Refusing to read prompt file outside allowed dirs (%s) (resolved): %s", strings.Join(resolvedAllowed, ", "), resolvedPath))
+						return "", fmt.Errorf("prompt file must be under ~/.claude or ~/.codeagent/agents")
+					}
+				}
+			}
+		} else {
+			withinAllowed := false
+			for _, dir := range allowedDirs {
+				if isWithinDir(absPath, dir) {
+					withinAllowed = true
+					break
+				}
+			}
+			if !withinAllowed {
+				logWarn(fmt.Sprintf("Reading prompt file outside allowed dirs (%s): %s", strings.Join(allowedDirs, ", "), absPath))
+			}
+		}
+	}
+
+	data, err := os.ReadFile(absPath)
+	if err != nil {
+		return "", err
+	}
+	return strings.TrimRight(string(data), "\r\n"), nil
+}
+
+func WrapTaskWithAgentPrompt(prompt string, task string) string {
+	return "<agent-prompt>\n" + prompt + "\n</agent-prompt>\n\n" + task
+}

codeagent-wrapper/internal/executor/prompt_file_test.go

@@ -0,0 +1,186 @@
+package executor
+
+import (
+	"os"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"testing"
+)
+
+func TestWrapTaskWithAgentPrompt(t *testing.T) {
+	got := WrapTaskWithAgentPrompt("P", "do")
+	want := "<agent-prompt>\nP\n</agent-prompt>\n\ndo"
+	if got != want {
+		t.Fatalf("wrapTaskWithAgentPrompt mismatch:\n got=%q\nwant=%q", got, want)
+	}
+}
+
+func TestReadAgentPromptFile_EmptyPath(t *testing.T) {
+	for _, allowOutside := range []bool{false, true} {
+		got, err := ReadAgentPromptFile("   ", allowOutside)
+		if err != nil {
+			t.Fatalf("unexpected error (allowOutside=%v): %v", allowOutside, err)
+		}
+		if got != "" {
+			t.Fatalf("expected empty result (allowOutside=%v), got %q", allowOutside, got)
+		}
+	}
+}
+
+func TestReadAgentPromptFile_ExplicitAbsolutePath(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "prompt.md")
+	if err := os.WriteFile(path, []byte("LINE1\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	got, err := ReadAgentPromptFile(path, true)
+	if err != nil {
+		t.Fatalf("readAgentPromptFile error: %v", err)
+	}
+	if got != "LINE1" {
+		t.Fatalf("got %q, want %q", got, "LINE1")
+	}
+}
+
+func TestReadAgentPromptFile_ExplicitTildeExpansion(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	path := filepath.Join(home, "prompt.md")
+	if err := os.WriteFile(path, []byte("P\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	got, err := ReadAgentPromptFile("~/prompt.md", true)
+	if err != nil {
+		t.Fatalf("readAgentPromptFile error: %v", err)
+	}
+	if got != "P" {
+		t.Fatalf("got %q, want %q", got, "P")
+	}
+}
+
+func TestReadAgentPromptFile_RestrictedAllowsClaudeDir(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	claudeDir := filepath.Join(home, ".claude")
+	if err := os.MkdirAll(claudeDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+	path := filepath.Join(claudeDir, "prompt.md")
+	if err := os.WriteFile(path, []byte("OK\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	got, err := ReadAgentPromptFile("~/.claude/prompt.md", false)
+	if err != nil {
+		t.Fatalf("readAgentPromptFile error: %v", err)
+	}
+	if got != "OK" {
+		t.Fatalf("got %q, want %q", got, "OK")
+	}
+}
+
+func TestReadAgentPromptFile_RestrictedAllowsCodeagentAgentsDir(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	agentDir := filepath.Join(home, ".codeagent", "agents")
+	if err := os.MkdirAll(agentDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+	path := filepath.Join(agentDir, "sarsh.md")
+	if err := os.WriteFile(path, []byte("OK\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	got, err := ReadAgentPromptFile("~/.codeagent/agents/sarsh.md", false)
+	if err != nil {
+		t.Fatalf("readAgentPromptFile error: %v", err)
+	}
+	if got != "OK" {
+		t.Fatalf("got %q, want %q", got, "OK")
+	}
+}
+
+func TestReadAgentPromptFile_RestrictedRejectsOutsideClaudeDir(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	path := filepath.Join(home, "prompt.md")
+	if err := os.WriteFile(path, []byte("NO\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	if _, err := ReadAgentPromptFile("~/prompt.md", false); err == nil {
+		t.Fatalf("expected error for prompt file outside ~/.claude, got nil")
+	}
+}
+
+func TestReadAgentPromptFile_RestrictedRejectsTraversal(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	path := filepath.Join(home, "secret.md")
+	if err := os.WriteFile(path, []byte("SECRET\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	if _, err := ReadAgentPromptFile("~/.claude/../secret.md", false); err == nil {
+		t.Fatalf("expected traversal to be rejected, got nil")
+	}
+}
+
+func TestReadAgentPromptFile_NotFound(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	claudeDir := filepath.Join(home, ".claude")
+	if err := os.MkdirAll(claudeDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+
+	_, err := ReadAgentPromptFile("~/.claude/missing.md", false)
+	if err == nil || !os.IsNotExist(err) {
+		t.Fatalf("expected not-exist error, got %v", err)
+	}
+}
+
+func TestReadAgentPromptFile_PermissionDenied(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("chmod-based permission test is not reliable on Windows")
+	}
+
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	claudeDir := filepath.Join(home, ".claude")
+	if err := os.MkdirAll(claudeDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll: %v", err)
+	}
+	path := filepath.Join(claudeDir, "private.md")
+	if err := os.WriteFile(path, []byte("PRIVATE\n"), 0o600); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+	if err := os.Chmod(path, 0o000); err != nil {
+		t.Fatalf("Chmod: %v", err)
+	}
+
+	_, err := ReadAgentPromptFile("~/.claude/private.md", false)
+	if err == nil {
+		t.Fatalf("expected permission error, got nil")
+	}
+	if !os.IsPermission(err) && !strings.Contains(strings.ToLower(err.Error()), "permission") {
+		t.Fatalf("expected permission denied, got: %v", err)
+	}
+}

codeagent-wrapper/internal/executor/report_helpers.go

@@ -0,0 +1,104 @@
+package executor
+
+import "strings"
+
+// extractCoverageGap extracts what's missing from coverage reports.
+func extractCoverageGap(message string) string {
+	if message == "" {
+		return ""
+	}
+
+	lower := strings.ToLower(message)
+	lines := strings.Split(message, "\n")
+
+	for _, line := range lines {
+		lineLower := strings.ToLower(line)
+		line = strings.TrimSpace(line)
+
+		if strings.Contains(lineLower, "uncovered") ||
+			strings.Contains(lineLower, "not covered") ||
+			strings.Contains(lineLower, "missing coverage") ||
+			strings.Contains(lineLower, "lines not covered") {
+			if len(line) > 100 {
+				return line[:97] + "..."
+			}
+			return line
+		}
+
+		if strings.Contains(lineLower, "branch") && strings.Contains(lineLower, "not taken") {
+			if len(line) > 100 {
+				return line[:97] + "..."
+			}
+			return line
+		}
+	}
+
+	if strings.Contains(lower, "function") && strings.Contains(lower, "0%") {
+		for _, line := range lines {
+			if strings.Contains(strings.ToLower(line), "0%") && strings.Contains(line, "function") {
+				line = strings.TrimSpace(line)
+				if len(line) > 100 {
+					return line[:97] + "..."
+				}
+				return line
+			}
+		}
+	}
+
+	return ""
+}
+
+// extractErrorDetail extracts meaningful error context from task output.
+func extractErrorDetail(message string, maxLen int) string {
+	if message == "" || maxLen <= 0 {
+		return ""
+	}
+
+	lines := strings.Split(message, "\n")
+	var errorLines []string
+
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+		if line == "" {
+			continue
+		}
+
+		lower := strings.ToLower(line)
+
+		if strings.HasPrefix(line, "at ") && strings.Contains(line, "(") {
+			if len(errorLines) > 0 && strings.HasPrefix(strings.ToLower(errorLines[len(errorLines)-1]), "at ") {
+				continue
+			}
+		}
+
+		if strings.Contains(lower, "error") ||
+			strings.Contains(lower, "fail") ||
+			strings.Contains(lower, "exception") ||
+			strings.Contains(lower, "assert") ||
+			strings.Contains(lower, "expected") ||
+			strings.Contains(lower, "timeout") ||
+			strings.Contains(lower, "not found") ||
+			strings.Contains(lower, "cannot") ||
+			strings.Contains(lower, "undefined") ||
+			strings.HasPrefix(line, "FAIL") ||
+			strings.HasPrefix(line, "●") {
+			errorLines = append(errorLines, line)
+		}
+	}
+
+	if len(errorLines) == 0 {
+		start := len(lines) - 5
+		if start < 0 {
+			start = 0
+		}
+		for _, line := range lines[start:] {
+			line = strings.TrimSpace(line)
+			if line != "" {
+				errorLines = append(errorLines, line)
+			}
+		}
+	}
+
+	result := strings.Join(errorLines, " | ")
+	return safeTruncate(result, maxLen)
+}

codeagent-wrapper/internal/executor/signal_unix.go

@@ -0,0 +1,16 @@
+//go:build unix || darwin || linux
+// +build unix darwin linux
+
+package executor
+
+import (
+	"syscall"
+)
+
+// sendTermSignal sends SIGTERM for graceful shutdown on Unix.
+func sendTermSignal(proc processHandle) error {
+	if proc == nil {
+		return nil
+	}
+	return proc.Signal(syscall.SIGTERM)
+}

codeagent-wrapper/internal/executor/signal_windows.go

@@ -0,0 +1,87 @@
+//go:build windows
+// +build windows
+
+package executor
+
+import (
+	"io"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"strings"
+)
+
+// sendTermSignal on Windows directly kills the process.
+// SIGTERM is not supported on Windows.
+func sendTermSignal(proc processHandle) error {
+	if proc == nil {
+		return nil
+	}
+	pid := proc.Pid()
+	if pid > 0 {
+		// Kill the whole process tree to avoid leaving inheriting child processes around.
+		// This also helps prevent exec.Cmd.Wait() from blocking on stderr/stdout pipes held open by children.
+		taskkill := "taskkill"
+		if root := os.Getenv("SystemRoot"); root != "" {
+			taskkill = filepath.Join(root, "System32", "taskkill.exe")
+		}
+		cmd := exec.Command(taskkill, "/PID", strconv.Itoa(pid), "/T", "/F")
+		cmd.Stdout = io.Discard
+		cmd.Stderr = io.Discard
+		if err := cmd.Run(); err == nil {
+			return nil
+		}
+		if err := killProcessTree(pid); err == nil {
+			return nil
+		}
+	}
+	return proc.Kill()
+}
+
+func killProcessTree(pid int) error {
+	if pid <= 0 {
+		return nil
+	}
+
+	wmic := "wmic"
+	if root := os.Getenv("SystemRoot"); root != "" {
+		wmic = filepath.Join(root, "System32", "wbem", "WMIC.exe")
+	}
+
+	queryChildren := "(ParentProcessId=" + strconv.Itoa(pid) + ")"
+	listCmd := exec.Command(wmic, "process", "where", queryChildren, "get", "ProcessId", "/VALUE")
+	listCmd.Stderr = io.Discard
+	out, err := listCmd.Output()
+	if err == nil {
+		for _, childPID := range parseWMICPIDs(out) {
+			_ = killProcessTree(childPID)
+		}
+	}
+
+	querySelf := "(ProcessId=" + strconv.Itoa(pid) + ")"
+	termCmd := exec.Command(wmic, "process", "where", querySelf, "call", "terminate")
+	termCmd.Stdout = io.Discard
+	termCmd.Stderr = io.Discard
+	if termErr := termCmd.Run(); termErr != nil && err == nil {
+		err = termErr
+	}
+	return err
+}
+
+func parseWMICPIDs(out []byte) []int {
+	const prefix = "ProcessId="
+	var pids []int
+	for _, line := range strings.Split(string(out), "\n") {
+		line = strings.TrimSpace(line)
+		if !strings.HasPrefix(line, prefix) {
+			continue
+		}
+		n, err := strconv.Atoi(strings.TrimSpace(strings.TrimPrefix(line, prefix)))
+		if err != nil || n <= 0 {
+			continue
+		}
+		pids = append(pids, n)
+	}
+	return pids
+}

codeagent-wrapper/internal/executor/stdin.go

@@ -0,0 +1,15 @@
+package executor
+
+import "strings"
+
+const stdinSpecialChars = "\n\\\"'`$"
+
+func ShouldUseStdin(taskText string, piped bool) bool {
+	if piped {
+		return true
+	}
+	if len(taskText) > 800 {
+		return true
+	}
+	return strings.ContainsAny(taskText, stdinSpecialChars)
+}

codeagent-wrapper/internal/executor/task_types.go

@@ -0,0 +1,46 @@
+package executor
+
+import "context"
+
+// ParallelConfig defines the JSON schema for parallel execution.
+type ParallelConfig struct {
+	Tasks         []TaskSpec `json:"tasks"`
+	GlobalBackend string     `json:"backend,omitempty"`
+}
+
+// TaskSpec describes an individual task entry in the parallel config.
+type TaskSpec struct {
+	ID              string          `json:"id"`
+	Task            string          `json:"task"`
+	WorkDir         string          `json:"workdir,omitempty"`
+	Dependencies    []string        `json:"dependencies,omitempty"`
+	SessionID       string          `json:"session_id,omitempty"`
+	Backend         string          `json:"backend,omitempty"`
+	Model           string          `json:"model,omitempty"`
+	ReasoningEffort string          `json:"reasoning_effort,omitempty"`
+	Agent           string          `json:"agent,omitempty"`
+	PromptFile      string          `json:"prompt_file,omitempty"`
+	SkipPermissions bool            `json:"skip_permissions,omitempty"`
+	Mode            string          `json:"-"`
+	UseStdin        bool            `json:"-"`
+	Context         context.Context `json:"-"`
+}
+
+// TaskResult captures the execution outcome of a task.
+type TaskResult struct {
+	TaskID    string `json:"task_id"`
+	ExitCode  int    `json:"exit_code"`
+	Message   string `json:"message"`
+	SessionID string `json:"session_id"`
+	Error     string `json:"error"`
+	LogPath   string `json:"log_path"`
+	// Structured report fields
+	Coverage       string   `json:"coverage,omitempty"`        // extracted coverage percentage (e.g., "92%")
+	CoverageNum    float64  `json:"coverage_num,omitempty"`    // numeric coverage for comparison
+	CoverageTarget float64  `json:"coverage_target,omitempty"` // target coverage (default 90)
+	FilesChanged   []string `json:"files_changed,omitempty"`   // list of changed files
+	KeyOutput      string   `json:"key_output,omitempty"`      // brief summary of what was done
+	TestsPassed    int      `json:"tests_passed,omitempty"`    // number of tests passed
+	TestsFailed    int      `json:"tests_failed,omitempty"`    // number of tests failed
+	sharedLog      bool
+}

codeagent-wrapper/internal/executor/testhooks.go

@@ -0,0 +1,57 @@
+package executor
+
+import (
+	"context"
+	"os/exec"
+
+	backend "codeagent-wrapper/internal/backend"
+)
+
+type CommandRunner = commandRunner
+type ProcessHandle = processHandle
+
+func SetForceKillDelay(seconds int32) (restore func()) {
+	prev := forceKillDelay.Load()
+	forceKillDelay.Store(seconds)
+	return func() { forceKillDelay.Store(prev) }
+}
+
+func SetSelectBackendFn(fn func(string) (Backend, error)) (restore func()) {
+	prev := selectBackendFn
+	if fn != nil {
+		selectBackendFn = fn
+	} else {
+		selectBackendFn = backend.Select
+	}
+	return func() { selectBackendFn = prev }
+}
+
+func SetCommandContextFn(fn func(context.Context, string, ...string) *exec.Cmd) (restore func()) {
+	prev := commandContext
+	if fn != nil {
+		commandContext = fn
+	} else {
+		commandContext = exec.CommandContext
+	}
+	return func() { commandContext = prev }
+}
+
+func SetNewCommandRunner(fn func(context.Context, string, ...string) CommandRunner) (restore func()) {
+	prev := newCommandRunner
+	if fn != nil {
+		newCommandRunner = fn
+	} else {
+		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+			return &realCmd{cmd: commandContext(ctx, name, args...)}
+		}
+	}
+	return func() { newCommandRunner = prev }
+}
+
+func WithTaskLogger(ctx context.Context, logger *Logger) context.Context {
+	return withTaskLogger(ctx, logger)
+}
+
+func TaskLoggerFromContext(ctx context.Context) *Logger {
+	return taskLoggerFromContext(ctx)
+}

codeagent-wrapper/internal/logger/active.go

@@ -0,0 +1,59 @@
+package logger
+
+import "sync/atomic"
+
+var loggerPtr atomic.Pointer[Logger]
+
+func setLogger(l *Logger) {
+	loggerPtr.Store(l)
+}
+
+func closeLogger() error {
+	logger := loggerPtr.Swap(nil)
+	if logger == nil {
+		return nil
+	}
+	return logger.Close()
+}
+
+func activeLogger() *Logger {
+	return loggerPtr.Load()
+}
+
+func logDebug(msg string) {
+	if logger := activeLogger(); logger != nil {
+		logger.Debug(msg)
+	}
+}
+
+func logInfo(msg string) {
+	if logger := activeLogger(); logger != nil {
+		logger.Info(msg)
+	}
+}
+
+func logWarn(msg string) {
+	if logger := activeLogger(); logger != nil {
+		logger.Warn(msg)
+	}
+}
+
+func logError(msg string) {
+	if logger := activeLogger(); logger != nil {
+		logger.Error(msg)
+	}
+}
+
+func SetLogger(l *Logger) { setLogger(l) }
+
+func CloseLogger() error { return closeLogger() }
+
+func ActiveLogger() *Logger { return activeLogger() }
+
+func LogInfo(msg string) { logInfo(msg) }
+
+func LogDebug(msg string) { logDebug(msg) }
+
+func LogWarn(msg string) { logWarn(msg) }
+
+func LogError(msg string) { logError(msg) }

codeagent-wrapper/internal/logger/logger.go

@@ -0,0 +1,683 @@
+package logger
+
+import (
+	"bufio"
+	"context"
+	"errors"
+	"fmt"
+	"hash/crc32"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	"github.com/rs/zerolog"
+)
+
+// Logger writes log messages asynchronously to a temp file.
+// It is intentionally minimal: a buffered channel + single worker goroutine
+// to avoid contention while keeping ordering guarantees.
+type Logger struct {
+	path         string
+	file         *os.File
+	writer       *bufio.Writer
+	zlogger      zerolog.Logger
+	ch           chan logEntry
+	flushReq     chan chan struct{}
+	done         chan struct{}
+	closed       atomic.Bool
+	closeOnce    sync.Once
+	workerWG     sync.WaitGroup
+	pendingWG    sync.WaitGroup
+	flushMu      sync.Mutex
+	workerErr    error
+	errorEntries []string // Cache of recent ERROR/WARN entries
+	errorMu      sync.Mutex
+}
+
+type logEntry struct {
+	msg     string
+	level   zerolog.Level
+	isError bool // true for ERROR or WARN levels
+}
+
+// CleanupStats captures the outcome of a cleanupOldLogs run.
+type CleanupStats struct {
+	Scanned      int
+	Deleted      int
+	Kept         int
+	Errors       int
+	DeletedFiles []string
+	KeptFiles    []string
+}
+
+var (
+	processRunningCheck = isProcessRunning
+	processStartTimeFn  = getProcessStartTime
+	removeLogFileFn     = os.Remove
+	globLogFiles        = filepath.Glob
+	fileStatFn          = os.Lstat // Use Lstat to detect symlinks
+	evalSymlinksFn      = filepath.EvalSymlinks
+)
+
+const maxLogSuffixLen = 64
+
+var logSuffixCounter atomic.Uint64
+
+// NewLogger creates the async logger and starts the worker goroutine.
+// The log file is created under os.TempDir() using the required naming scheme.
+func NewLogger() (*Logger, error) {
+	return NewLoggerWithSuffix("")
+}
+
+// NewLoggerWithSuffix creates a logger with an optional suffix in the filename.
+// Useful for tests that need isolated log files within the same process.
+func NewLoggerWithSuffix(suffix string) (*Logger, error) {
+	pid := os.Getpid()
+	filename := fmt.Sprintf("%s-%d", PrimaryLogPrefix(), pid)
+	var safeSuffix string
+	if suffix != "" {
+		safeSuffix = sanitizeLogSuffix(suffix)
+	}
+	if safeSuffix != "" {
+		filename += "-" + safeSuffix
+	}
+	filename += ".log"
+
+	path := filepath.Clean(filepath.Join(os.TempDir(), filename))
+
+	if err := os.MkdirAll(filepath.Dir(path), 0o700); err != nil {
+		return nil, err
+	}
+
+	f, err := os.OpenFile(path, os.O_CREATE|os.O_WRONLY|os.O_APPEND, 0o600)
+	if err != nil {
+		return nil, err
+	}
+
+	l := &Logger{
+		path:     path,
+		file:     f,
+		writer:   bufio.NewWriterSize(f, 4096),
+		ch:       make(chan logEntry, 1000),
+		flushReq: make(chan chan struct{}, 1),
+		done:     make(chan struct{}),
+	}
+
+	l.zlogger = zerolog.New(l.writer).With().Timestamp().Logger()
+
+	l.workerWG.Add(1)
+	go l.run()
+
+	return l, nil
+}
+
+func sanitizeLogSuffix(raw string) string {
+	trimmed := strings.TrimSpace(raw)
+	if trimmed == "" {
+		return fallbackLogSuffix()
+	}
+
+	var b strings.Builder
+	changed := false
+	for _, r := range trimmed {
+		if isSafeLogRune(r) {
+			b.WriteRune(r)
+		} else {
+			changed = true
+			b.WriteByte('-')
+		}
+		if b.Len() >= maxLogSuffixLen {
+			changed = true
+			break
+		}
+	}
+
+	sanitized := strings.Trim(b.String(), "-.")
+	if sanitized != b.String() {
+		changed = true // Mark if trim removed any characters
+	}
+	if sanitized == "" {
+		return fallbackLogSuffix()
+	}
+
+	if changed || len(sanitized) > maxLogSuffixLen {
+		hash := crc32.ChecksumIEEE([]byte(trimmed))
+		hashStr := fmt.Sprintf("%x", hash)
+
+		maxPrefix := maxLogSuffixLen - len(hashStr) - 1
+		if maxPrefix < 1 {
+			maxPrefix = 1
+		}
+		if len(sanitized) > maxPrefix {
+			sanitized = sanitized[:maxPrefix]
+		}
+
+		sanitized = fmt.Sprintf("%s-%s", sanitized, hashStr)
+	}
+
+	return sanitized
+}
+
+func fallbackLogSuffix() string {
+	next := logSuffixCounter.Add(1)
+	return fmt.Sprintf("task-%d", next)
+}
+
+func isSafeLogRune(r rune) bool {
+	switch {
+	case r >= 'a' && r <= 'z':
+		return true
+	case r >= 'A' && r <= 'Z':
+		return true
+	case r >= '0' && r <= '9':
+		return true
+	case r == '-', r == '_', r == '.':
+		return true
+	default:
+		return false
+	}
+}
+
+// Path returns the underlying log file path (useful for tests/inspection).
+func (l *Logger) Path() string {
+	if l == nil {
+		return ""
+	}
+	return l.path
+}
+
+func (l *Logger) IsClosed() bool {
+	if l == nil {
+		return true
+	}
+	return l.closed.Load()
+}
+
+// Info logs at INFO level.
+func (l *Logger) Info(msg string) { l.logWithLevel(zerolog.InfoLevel, msg) }
+
+// Warn logs at WARN level.
+func (l *Logger) Warn(msg string) { l.logWithLevel(zerolog.WarnLevel, msg) }
+
+// Debug logs at DEBUG level.
+func (l *Logger) Debug(msg string) { l.logWithLevel(zerolog.DebugLevel, msg) }
+
+// Error logs at ERROR level.
+func (l *Logger) Error(msg string) { l.logWithLevel(zerolog.ErrorLevel, msg) }
+
+// Close signals the worker to flush and close the log file.
+// The log file is NOT removed, allowing inspection after program exit.
+// It is safe to call multiple times.
+// Waits up to CODEAGENT_LOGGER_CLOSE_TIMEOUT_MS (default: 5000) for shutdown; set to 0 to wait indefinitely.
+// Returns an error if shutdown doesn't complete within the timeout.
+func (l *Logger) Close() error {
+	if l == nil {
+		return nil
+	}
+
+	var closeErr error
+
+	l.closeOnce.Do(func() {
+		l.closed.Store(true)
+		close(l.done)
+
+		timeout := loggerCloseTimeout()
+		workerDone := make(chan struct{})
+		go func() {
+			l.workerWG.Wait()
+			close(workerDone)
+		}()
+
+		if timeout > 0 {
+			select {
+			case <-workerDone:
+				// Worker stopped gracefully
+			case <-time.After(timeout):
+				closeErr = fmt.Errorf("logger worker timeout during close")
+				return
+			}
+		} else {
+			<-workerDone
+		}
+
+		if l.workerErr != nil && closeErr == nil {
+			closeErr = l.workerErr
+		}
+	})
+
+	return closeErr
+}
+
+func loggerCloseTimeout() time.Duration {
+	const defaultTimeout = 5 * time.Second
+
+	raw := strings.TrimSpace(os.Getenv("CODEAGENT_LOGGER_CLOSE_TIMEOUT_MS"))
+	if raw == "" {
+		return defaultTimeout
+	}
+	ms, err := strconv.Atoi(raw)
+	if err != nil {
+		return defaultTimeout
+	}
+	if ms <= 0 {
+		return 0
+	}
+	return time.Duration(ms) * time.Millisecond
+}
+
+// RemoveLogFile removes the log file. Should only be called after Close().
+func (l *Logger) RemoveLogFile() error {
+	if l == nil {
+		return nil
+	}
+	return os.Remove(l.path)
+}
+
+// ExtractRecentErrors returns the most recent ERROR and WARN entries from memory cache.
+// Returns up to maxEntries entries in chronological order.
+func (l *Logger) ExtractRecentErrors(maxEntries int) []string {
+	if l == nil || maxEntries <= 0 {
+		return nil
+	}
+
+	l.errorMu.Lock()
+	defer l.errorMu.Unlock()
+
+	if len(l.errorEntries) == 0 {
+		return nil
+	}
+
+	// Return last N entries
+	start := 0
+	if len(l.errorEntries) > maxEntries {
+		start = len(l.errorEntries) - maxEntries
+	}
+
+	result := make([]string, len(l.errorEntries)-start)
+	copy(result, l.errorEntries[start:])
+	return result
+}
+
+// Flush waits for all pending log entries to be written. Primarily for tests.
+// Returns after a 5-second timeout to prevent indefinite blocking.
+func (l *Logger) Flush() {
+	if l == nil {
+		return
+	}
+
+	l.flushMu.Lock()
+	defer l.flushMu.Unlock()
+
+	// Wait for pending entries with timeout
+	done := make(chan struct{})
+	go func() {
+		l.pendingWG.Wait()
+		close(done)
+	}()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	select {
+	case <-done:
+		// All pending entries processed
+	case <-ctx.Done():
+		// Timeout - return without full flush
+		return
+	}
+
+	// Trigger writer flush
+	flushDone := make(chan struct{})
+	select {
+	case l.flushReq <- flushDone:
+		// Wait for flush to complete
+		select {
+		case <-flushDone:
+			// Flush completed
+		case <-time.After(1 * time.Second):
+			// Flush timeout
+		}
+	case <-l.done:
+		// Logger is closing
+	case <-time.After(1 * time.Second):
+		// Timeout sending flush request
+	}
+}
+
+func (l *Logger) logWithLevel(entryLevel zerolog.Level, msg string) {
+	if l == nil {
+		return
+	}
+	if l.closed.Load() {
+		return
+	}
+
+	isError := entryLevel == zerolog.WarnLevel || entryLevel == zerolog.ErrorLevel
+	entry := logEntry{msg: msg, level: entryLevel, isError: isError}
+	l.flushMu.Lock()
+	l.pendingWG.Add(1)
+	l.flushMu.Unlock()
+
+	select {
+	case l.ch <- entry:
+		// Successfully sent to channel
+	case <-l.done:
+		// Logger is closing, drop this entry
+		l.pendingWG.Done()
+		return
+	}
+}
+
+func (l *Logger) run() {
+	defer l.workerWG.Done()
+
+	ticker := time.NewTicker(500 * time.Millisecond)
+	defer ticker.Stop()
+
+	writeEntry := func(entry logEntry) {
+		l.zlogger.WithLevel(entry.level).Msg(entry.msg)
+
+		// Cache error/warn entries in memory for fast extraction
+		if entry.isError {
+			l.errorMu.Lock()
+			l.errorEntries = append(l.errorEntries, entry.msg)
+			if len(l.errorEntries) > 100 { // Keep last 100
+				l.errorEntries = l.errorEntries[1:]
+			}
+			l.errorMu.Unlock()
+		}
+
+		l.pendingWG.Done()
+	}
+
+	finalize := func() {
+		if err := l.writer.Flush(); err != nil && l.workerErr == nil {
+			l.workerErr = err
+		}
+		if err := l.file.Sync(); err != nil && l.workerErr == nil {
+			l.workerErr = err
+		}
+		if err := l.file.Close(); err != nil && l.workerErr == nil {
+			l.workerErr = err
+		}
+	}
+
+	for {
+		select {
+		case entry, ok := <-l.ch:
+			if !ok {
+				finalize()
+				return
+			}
+			writeEntry(entry)
+
+		case <-ticker.C:
+			_ = l.writer.Flush()
+
+		case flushDone := <-l.flushReq:
+			// Explicit flush request - flush writer and sync to disk
+			_ = l.writer.Flush()
+			_ = l.file.Sync()
+			close(flushDone)
+
+		case <-l.done:
+			for {
+				select {
+				case entry, ok := <-l.ch:
+					if !ok {
+						finalize()
+						return
+					}
+					writeEntry(entry)
+				default:
+					finalize()
+					return
+				}
+			}
+		}
+	}
+}
+
+// cleanupOldLogs scans os.TempDir() for wrapper log files and removes those
+// whose owning process is no longer running (i.e., orphaned logs).
+// It includes safety checks for:
+// - PID reuse: Compares file modification time with process start time
+// - Symlink attacks: Ensures files are within TempDir and not symlinks
+func cleanupOldLogs() (CleanupStats, error) {
+	var stats CleanupStats
+	tempDir := os.TempDir()
+
+	prefixes := LogPrefixes()
+
+	seen := make(map[string]struct{})
+	var matches []string
+	for _, prefix := range prefixes {
+		pattern := filepath.Join(tempDir, fmt.Sprintf("%s-*.log", prefix))
+		found, err := globLogFiles(pattern)
+		if err != nil {
+			logWarn(fmt.Sprintf("cleanupOldLogs: failed to list logs: %v", err))
+			return stats, fmt.Errorf("cleanupOldLogs: %w", err)
+		}
+		for _, path := range found {
+			if _, ok := seen[path]; ok {
+				continue
+			}
+			seen[path] = struct{}{}
+			matches = append(matches, path)
+		}
+	}
+
+	var removeErr error
+
+	for _, path := range matches {
+		stats.Scanned++
+		filename := filepath.Base(path)
+
+		// Security check: Verify file is not a symlink and is within tempDir
+		if shouldSkipFile, reason := isUnsafeFile(path, tempDir); shouldSkipFile {
+			stats.Kept++
+			stats.KeptFiles = append(stats.KeptFiles, filename)
+			if reason != "" {
+				// Use Debug level to avoid polluting Recent Errors with cleanup noise
+				logDebug(fmt.Sprintf("cleanupOldLogs: skipping %s: %s", filename, reason))
+			}
+			continue
+		}
+
+		pid, ok := parsePIDFromLog(path)
+		if !ok {
+			stats.Kept++
+			stats.KeptFiles = append(stats.KeptFiles, filename)
+			continue
+		}
+
+		// Check if process is running
+		if !processRunningCheck(pid) {
+			// Process not running, safe to delete
+			if err := removeLogFileFn(path); err != nil {
+				if errors.Is(err, os.ErrNotExist) {
+					// File already deleted by another process, don't count as success
+					stats.Kept++
+					stats.KeptFiles = append(stats.KeptFiles, filename+" (already deleted)")
+					continue
+				}
+				stats.Errors++
+				logWarn(fmt.Sprintf("cleanupOldLogs: failed to remove %s: %v", filename, err))
+				removeErr = errors.Join(removeErr, fmt.Errorf("failed to remove %s: %w", filename, err))
+				continue
+			}
+			stats.Deleted++
+			stats.DeletedFiles = append(stats.DeletedFiles, filename)
+			continue
+		}
+
+		// Process is running, check for PID reuse
+		if isPIDReused(path, pid) {
+			// PID was reused, the log file is orphaned
+			if err := removeLogFileFn(path); err != nil {
+				if errors.Is(err, os.ErrNotExist) {
+					stats.Kept++
+					stats.KeptFiles = append(stats.KeptFiles, filename+" (already deleted)")
+					continue
+				}
+				stats.Errors++
+				logWarn(fmt.Sprintf("cleanupOldLogs: failed to remove %s (PID reused): %v", filename, err))
+				removeErr = errors.Join(removeErr, fmt.Errorf("failed to remove %s: %w", filename, err))
+				continue
+			}
+			stats.Deleted++
+			stats.DeletedFiles = append(stats.DeletedFiles, filename)
+			continue
+		}
+
+		// Process is running and owns this log file
+		stats.Kept++
+		stats.KeptFiles = append(stats.KeptFiles, filename)
+	}
+
+	if removeErr != nil {
+		return stats, fmt.Errorf("cleanupOldLogs: %w", removeErr)
+	}
+
+	return stats, nil
+}
+
+// isUnsafeFile checks if a file is unsafe to delete (symlink or outside tempDir).
+// Returns (true, reason) if the file should be skipped.
+func isUnsafeFile(path string, tempDir string) (bool, string) {
+	// Check if file is a symlink
+	info, err := fileStatFn(path)
+	if err != nil {
+		if errors.Is(err, os.ErrNotExist) {
+			return true, "" // File disappeared, skip silently
+		}
+		return true, fmt.Sprintf("stat failed: %v", err)
+	}
+
+	// Check if it's a symlink
+	if info.Mode()&os.ModeSymlink != 0 {
+		return true, "refusing to delete symlink"
+	}
+
+	// Resolve any path traversal and verify it's within tempDir
+	resolvedPath, err := evalSymlinksFn(path)
+	if err != nil {
+		return true, fmt.Sprintf("path resolution failed: %v", err)
+	}
+
+	// Get absolute path of tempDir
+	absTempDir, err := filepath.Abs(tempDir)
+	if err != nil {
+		return true, fmt.Sprintf("tempDir resolution failed: %v", err)
+	}
+
+	// Ensure resolved path is within tempDir
+	relPath, err := filepath.Rel(absTempDir, resolvedPath)
+	if err != nil || strings.HasPrefix(relPath, "..") {
+		return true, "file is outside tempDir"
+	}
+
+	return false, ""
+}
+
+// isPIDReused checks if a PID has been reused by comparing file modification time
+// with process start time. Returns true if the log file was created by a different
+// process that previously had the same PID.
+func isPIDReused(logPath string, pid int) bool {
+	// Get file modification time (when log was last written)
+	info, err := fileStatFn(logPath)
+	if err != nil {
+		// If we can't stat the file, be conservative and keep it
+		return false
+	}
+	fileModTime := info.ModTime()
+
+	// Get process start time
+	procStartTime := processStartTimeFn(pid)
+	if procStartTime.IsZero() {
+		// Can't determine process start time
+		// Check if file is very old (>7 days), likely from a dead process
+		return time.Since(fileModTime) > 7*24*time.Hour
+	}
+
+	// If the log file was modified before the process started, PID was reused
+	// Add a small buffer (1 second) to account for clock skew and file system timing
+	return fileModTime.Add(1 * time.Second).Before(procStartTime)
+}
+
+func parsePIDFromLog(path string) (int, bool) {
+	name := filepath.Base(path)
+	prefixes := LogPrefixes()
+
+	for _, prefix := range prefixes {
+		prefixWithDash := fmt.Sprintf("%s-", prefix)
+		if !strings.HasPrefix(name, prefixWithDash) || !strings.HasSuffix(name, ".log") {
+			continue
+		}
+
+		core := strings.TrimSuffix(strings.TrimPrefix(name, prefixWithDash), ".log")
+		if core == "" {
+			continue
+		}
+
+		pidPart := core
+		if idx := strings.IndexRune(core, '-'); idx != -1 {
+			pidPart = core[:idx]
+		}
+
+		if pidPart == "" {
+			continue
+		}
+
+		pid, err := strconv.Atoi(pidPart)
+		if err != nil || pid <= 0 {
+			continue
+		}
+		return pid, true
+	}
+
+	return 0, false
+}
+
+func logConcurrencyPlanning(limit, total int) {
+	logger := activeLogger()
+	if logger == nil {
+		return
+	}
+	logger.Info(fmt.Sprintf("parallel: worker_limit=%s total_tasks=%d", renderWorkerLimit(limit), total))
+}
+
+func logConcurrencyState(event, taskID string, active, limit int) {
+	logger := activeLogger()
+	if logger == nil {
+		return
+	}
+	logger.Debug(fmt.Sprintf("parallel: %s task=%s active=%d limit=%s", event, taskID, active, renderWorkerLimit(limit)))
+}
+
+func renderWorkerLimit(limit int) string {
+	if limit <= 0 {
+		return "unbounded"
+	}
+	return strconv.Itoa(limit)
+}
+
+func CleanupOldLogs() (CleanupStats, error) { return cleanupOldLogs() }
+
+func IsUnsafeFile(path string, tempDir string) (bool, string) { return isUnsafeFile(path, tempDir) }
+
+func IsPIDReused(logPath string, pid int) bool { return isPIDReused(logPath, pid) }
+
+func ParsePIDFromLog(path string) (int, bool) { return parsePIDFromLog(path) }
+
+func LogConcurrencyPlanning(limit, total int) { logConcurrencyPlanning(limit, total) }
+
+func LogConcurrencyState(event, taskID string, active, limit int) {
+	logConcurrencyState(event, taskID, active, limit)
+}
+
+func SanitizeLogSuffix(raw string) string { return sanitizeLogSuffix(raw) }

codeagent-wrapper/internal/logger/logger_additional_coverage_test.go

@@ -0,0 +1,158 @@
+package logger
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestLoggerNilReceiverNoop(t *testing.T) {
+	var logger *Logger
+	logger.Info("info")
+	logger.Warn("warn")
+	logger.Debug("debug")
+	logger.Error("error")
+	logger.Flush()
+	if err := logger.Close(); err != nil {
+		t.Fatalf("Close() on nil logger should return nil, got %v", err)
+	}
+}
+
+func TestLoggerConcurrencyLogHelpers(t *testing.T) {
+	setTempDirEnv(t, t.TempDir())
+
+	logger, err := NewLoggerWithSuffix("concurrency")
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix error: %v", err)
+	}
+	setLogger(logger)
+	defer func() { _ = closeLogger() }()
+
+	logConcurrencyPlanning(0, 2)
+	logConcurrencyPlanning(3, 2)
+	logConcurrencyState("start", "task-1", 1, 0)
+	logConcurrencyState("done", "task-1", 0, 3)
+	logger.Flush()
+
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to read log file: %v", err)
+	}
+	output := string(data)
+
+	checks := []string{
+		"parallel: worker_limit=unbounded total_tasks=2",
+		"parallel: worker_limit=3 total_tasks=2",
+		"parallel: start task=task-1 active=1 limit=unbounded",
+		"parallel: done task=task-1 active=0 limit=3",
+	}
+	for _, c := range checks {
+		if !strings.Contains(output, c) {
+			t.Fatalf("log output missing %q, got: %s", c, output)
+		}
+	}
+}
+
+func TestLoggerConcurrencyLogHelpersNoopWithoutActiveLogger(t *testing.T) {
+	_ = closeLogger()
+	logConcurrencyPlanning(1, 1)
+	logConcurrencyState("start", "task-1", 0, 1)
+}
+
+func TestLoggerCleanupOldLogsSkipsUnsafeAndHandlesAlreadyDeleted(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	unsafePath := createTempLog(t, tempDir, fmt.Sprintf("%s-%d.log", PrimaryLogPrefix(), 222))
+	orphanPath := createTempLog(t, tempDir, fmt.Sprintf("%s-%d.log", PrimaryLogPrefix(), 111))
+
+	stubFileStat(t, func(path string) (os.FileInfo, error) {
+		if path == unsafePath {
+			return fakeFileInfo{mode: os.ModeSymlink}, nil
+		}
+		return os.Lstat(path)
+	})
+
+	stubProcessRunning(t, func(pid int) bool {
+		if pid == 111 {
+			_ = os.Remove(orphanPath)
+		}
+		return false
+	})
+
+	stats, err := cleanupOldLogs()
+	if err != nil {
+		t.Fatalf("cleanupOldLogs() unexpected error: %v", err)
+	}
+
+	if stats.Scanned != 2 {
+		t.Fatalf("scanned = %d, want %d", stats.Scanned, 2)
+	}
+	if stats.Deleted != 0 {
+		t.Fatalf("deleted = %d, want %d", stats.Deleted, 0)
+	}
+	if stats.Kept != 2 {
+		t.Fatalf("kept = %d, want %d", stats.Kept, 2)
+	}
+	if stats.Errors != 0 {
+		t.Fatalf("errors = %d, want %d", stats.Errors, 0)
+	}
+
+	hasSkip := false
+	hasAlreadyDeleted := false
+	for _, name := range stats.KeptFiles {
+		if strings.Contains(name, "already deleted") {
+			hasAlreadyDeleted = true
+		}
+		if strings.Contains(name, filepath.Base(unsafePath)) {
+			hasSkip = true
+		}
+	}
+	if !hasSkip {
+		t.Fatalf("expected kept files to include unsafe log %q, got %+v", filepath.Base(unsafePath), stats.KeptFiles)
+	}
+	if !hasAlreadyDeleted {
+		t.Fatalf("expected kept files to include already deleted marker, got %+v", stats.KeptFiles)
+	}
+}
+
+func TestLoggerIsUnsafeFileErrorPaths(t *testing.T) {
+	tempDir := t.TempDir()
+
+	t.Run("stat ErrNotExist", func(t *testing.T) {
+		stubFileStat(t, func(string) (os.FileInfo, error) {
+			return nil, os.ErrNotExist
+		})
+
+		unsafe, reason := isUnsafeFile("missing.log", tempDir)
+		if !unsafe || reason != "" {
+			t.Fatalf("expected missing file to be skipped silently, got unsafe=%v reason=%q", unsafe, reason)
+		}
+	})
+
+	t.Run("stat error", func(t *testing.T) {
+		stubFileStat(t, func(string) (os.FileInfo, error) {
+			return nil, fmt.Errorf("boom")
+		})
+
+		unsafe, reason := isUnsafeFile("broken.log", tempDir)
+		if !unsafe || !strings.Contains(reason, "stat failed") {
+			t.Fatalf("expected stat failure to be unsafe, got unsafe=%v reason=%q", unsafe, reason)
+		}
+	})
+
+	t.Run("EvalSymlinks error", func(t *testing.T) {
+		stubFileStat(t, func(string) (os.FileInfo, error) {
+			return fakeFileInfo{}, nil
+		})
+		stubEvalSymlinks(t, func(string) (string, error) {
+			return "", fmt.Errorf("resolve failed")
+		})
+
+		unsafe, reason := isUnsafeFile("cannot-resolve.log", tempDir)
+		if !unsafe || !strings.Contains(reason, "path resolution failed") {
+			t.Fatalf("expected resolution failure to be unsafe, got unsafe=%v reason=%q", unsafe, reason)
+		}
+	})
+}

codeagent-wrapper/internal/logger/logger_suffix_test.go

@@ -0,0 +1,115 @@
+package logger
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestLoggerWithSuffixNamingAndIsolation(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	taskA := "task-1"
+	taskB := "task-2"
+
+	loggerA, err := NewLoggerWithSuffix(taskA)
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix(%q) error = %v", taskA, err)
+	}
+	defer loggerA.Close()
+
+	loggerB, err := NewLoggerWithSuffix(taskB)
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix(%q) error = %v", taskB, err)
+	}
+	defer loggerB.Close()
+
+	wantA := filepath.Join(tempDir, fmt.Sprintf("%s-%d-%s.log", PrimaryLogPrefix(), os.Getpid(), taskA))
+	if loggerA.Path() != wantA {
+		t.Fatalf("loggerA path = %q, want %q", loggerA.Path(), wantA)
+	}
+
+	wantB := filepath.Join(tempDir, fmt.Sprintf("%s-%d-%s.log", PrimaryLogPrefix(), os.Getpid(), taskB))
+	if loggerB.Path() != wantB {
+		t.Fatalf("loggerB path = %q, want %q", loggerB.Path(), wantB)
+	}
+
+	if loggerA.Path() == loggerB.Path() {
+		t.Fatalf("expected different log files, got %q", loggerA.Path())
+	}
+
+	loggerA.Info("from taskA")
+	loggerB.Info("from taskB")
+	loggerA.Flush()
+	loggerB.Flush()
+
+	dataA, err := os.ReadFile(loggerA.Path())
+	if err != nil {
+		t.Fatalf("failed to read loggerA file: %v", err)
+	}
+	dataB, err := os.ReadFile(loggerB.Path())
+	if err != nil {
+		t.Fatalf("failed to read loggerB file: %v", err)
+	}
+
+	if !strings.Contains(string(dataA), "from taskA") {
+		t.Fatalf("loggerA missing its message, got: %q", string(dataA))
+	}
+	if strings.Contains(string(dataA), "from taskB") {
+		t.Fatalf("loggerA contains loggerB message, got: %q", string(dataA))
+	}
+	if !strings.Contains(string(dataB), "from taskB") {
+		t.Fatalf("loggerB missing its message, got: %q", string(dataB))
+	}
+	if strings.Contains(string(dataB), "from taskA") {
+		t.Fatalf("loggerB contains loggerA message, got: %q", string(dataB))
+	}
+}
+
+func TestLoggerWithSuffixReturnsErrorWhenTempDirNotWritable(t *testing.T) {
+	base := t.TempDir()
+	noWrite := filepath.Join(base, "ro")
+	if err := os.Mkdir(noWrite, 0o500); err != nil {
+		t.Fatalf("failed to create read-only temp dir: %v", err)
+	}
+	t.Cleanup(func() { _ = os.Chmod(noWrite, 0o700) })
+	setTempDirEnv(t, noWrite)
+
+	logger, err := NewLoggerWithSuffix("task-err")
+	if err == nil {
+		_ = logger.Close()
+		t.Fatalf("expected error when temp dir is not writable")
+	}
+}
+
+func TestLoggerWithSuffixSanitizesUnsafeSuffix(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	raw := "../bad id/with?chars"
+	safe := sanitizeLogSuffix(raw)
+	if safe == "" {
+		t.Fatalf("sanitizeLogSuffix returned empty string")
+	}
+	if strings.ContainsAny(safe, "/\\") {
+		t.Fatalf("sanitized suffix should not contain path separators, got %q", safe)
+	}
+
+	logger, err := NewLoggerWithSuffix(raw)
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix(%q) error = %v", raw, err)
+	}
+	t.Cleanup(func() {
+		_ = logger.Close()
+		_ = os.Remove(logger.Path())
+	})
+
+	wantBase := fmt.Sprintf("%s-%d-%s.log", PrimaryLogPrefix(), os.Getpid(), safe)
+	if gotBase := filepath.Base(logger.Path()); gotBase != wantBase {
+		t.Fatalf("log filename = %q, want %q", gotBase, wantBase)
+	}
+	if dir := filepath.Dir(logger.Path()); dir != tempDir {
+		t.Fatalf("logger path dir = %q, want %q", dir, tempDir)
+	}
+}

codeagent-wrapper/internal/logger/logger_test.go

@@ -0,0 +1,903 @@
+package logger
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"math"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+)
+
+func compareCleanupStats(got, want CleanupStats) bool {
+	if got.Scanned != want.Scanned || got.Deleted != want.Deleted || got.Kept != want.Kept || got.Errors != want.Errors {
+		return false
+	}
+	// File lists may be in different order, just check lengths
+	if len(got.DeletedFiles) != want.Deleted || len(got.KeptFiles) != want.Kept {
+		return false
+	}
+	return true
+}
+
+func TestLoggerCreatesFileWithPID(t *testing.T) {
+	tempDir := t.TempDir()
+	t.Setenv("TMPDIR", tempDir)
+
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger() error = %v", err)
+	}
+	defer logger.Close()
+
+	expectedPath := filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", os.Getpid()))
+	if logger.Path() != expectedPath {
+		t.Fatalf("logger path = %s, want %s", logger.Path(), expectedPath)
+	}
+
+	if _, err := os.Stat(expectedPath); err != nil {
+		t.Fatalf("log file not created: %v", err)
+	}
+}
+
+func TestLoggerWritesLevels(t *testing.T) {
+	tempDir := t.TempDir()
+	t.Setenv("TMPDIR", tempDir)
+
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger() error = %v", err)
+	}
+	defer logger.Close()
+
+	logger.Info("info message")
+	logger.Warn("warn message")
+	logger.Debug("debug message")
+	logger.Error("error message")
+
+	logger.Flush()
+
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to read log file: %v", err)
+	}
+
+	content := string(data)
+	checks := []string{"info message", "warn message", "debug message", "error message"}
+	for _, c := range checks {
+		if !strings.Contains(content, c) {
+			t.Fatalf("log file missing entry %q, content: %s", c, content)
+		}
+	}
+}
+
+func TestLoggerCloseStopsWorkerAndKeepsFile(t *testing.T) {
+	tempDir := t.TempDir()
+	t.Setenv("TMPDIR", tempDir)
+
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger() error = %v", err)
+	}
+
+	logger.Info("before close")
+	logger.Flush()
+
+	logPath := logger.Path()
+
+	if err := logger.Close(); err != nil {
+		t.Fatalf("Close() returned error: %v", err)
+	}
+
+	// After recent changes, log file is kept for debugging - NOT removed
+	if _, err := os.Stat(logPath); os.IsNotExist(err) {
+		t.Fatalf("log file should exist after Close for debugging, but got IsNotExist")
+	}
+
+	// Clean up manually for test
+	defer os.Remove(logPath)
+}
+
+func TestLoggerConcurrentWritesSafe(t *testing.T) {
+	tempDir := t.TempDir()
+	t.Setenv("TMPDIR", tempDir)
+
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger() error = %v", err)
+	}
+	defer logger.Close()
+
+	const goroutines = 10
+	const perGoroutine = 50
+
+	var wg sync.WaitGroup
+	wg.Add(goroutines)
+
+	for i := 0; i < goroutines; i++ {
+		go func(id int) {
+			defer wg.Done()
+			for j := 0; j < perGoroutine; j++ {
+				logger.Debug(fmt.Sprintf("g%d-%d", id, j))
+			}
+		}(i)
+	}
+
+	wg.Wait()
+	logger.Flush()
+
+	f, err := os.Open(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to open log file: %v", err)
+	}
+	defer f.Close()
+
+	scanner := bufio.NewScanner(f)
+	count := 0
+	for scanner.Scan() {
+		count++
+	}
+	if err := scanner.Err(); err != nil {
+		t.Fatalf("scanner error: %v", err)
+	}
+
+	expected := goroutines * perGoroutine
+	if count != expected {
+		t.Fatalf("unexpected log line count: got %d, want %d", count, expected)
+	}
+}
+
+func TestLoggerCleanupOldLogsRemovesOrphans(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	orphan1 := createTempLog(t, tempDir, "codeagent-wrapper-111.log")
+	orphan2 := createTempLog(t, tempDir, "codeagent-wrapper-222-suffix.log")
+	running1 := createTempLog(t, tempDir, "codeagent-wrapper-333.log")
+	running2 := createTempLog(t, tempDir, "codeagent-wrapper-444-extra-info.log")
+	untouched := createTempLog(t, tempDir, "unrelated.log")
+
+	runningPIDs := map[int]bool{333: true, 444: true}
+	stubProcessRunning(t, func(pid int) bool {
+		return runningPIDs[pid]
+	})
+
+	// Stub process start time to be in the past so files won't be considered as PID reused
+	stubProcessStartTime(t, func(pid int) time.Time {
+		if runningPIDs[pid] {
+			// Return a time before file creation
+			return time.Now().Add(-1 * time.Hour)
+		}
+		return time.Time{}
+	})
+
+	stats, err := cleanupOldLogs()
+	if err != nil {
+		t.Fatalf("cleanupOldLogs() unexpected error: %v", err)
+	}
+
+	want := CleanupStats{Scanned: 4, Deleted: 2, Kept: 2}
+	if !compareCleanupStats(stats, want) {
+		t.Fatalf("cleanup stats mismatch: got %+v, want %+v", stats, want)
+	}
+
+	if _, err := os.Stat(orphan1); !os.IsNotExist(err) {
+		t.Fatalf("expected orphan %s to be removed, err=%v", orphan1, err)
+	}
+	if _, err := os.Stat(orphan2); !os.IsNotExist(err) {
+		t.Fatalf("expected orphan %s to be removed, err=%v", orphan2, err)
+	}
+	if _, err := os.Stat(running1); err != nil {
+		t.Fatalf("expected running log %s to remain, err=%v", running1, err)
+	}
+	if _, err := os.Stat(running2); err != nil {
+		t.Fatalf("expected running log %s to remain, err=%v", running2, err)
+	}
+	if _, err := os.Stat(untouched); err != nil {
+		t.Fatalf("expected unrelated file %s to remain, err=%v", untouched, err)
+	}
+}
+
+func TestLoggerCleanupOldLogsHandlesInvalidNamesAndErrors(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	invalid := []string{
+		"codeagent-wrapper-.log",
+		"codeagent-wrapper.log",
+		"codeagent-wrapper-foo-bar.txt",
+		"not-a-codex.log",
+	}
+	for _, name := range invalid {
+		createTempLog(t, tempDir, name)
+	}
+	target := createTempLog(t, tempDir, "codeagent-wrapper-555-extra.log")
+
+	var checked []int
+	stubProcessRunning(t, func(pid int) bool {
+		checked = append(checked, pid)
+		return false
+	})
+
+	stubProcessStartTime(t, func(pid int) time.Time {
+		return time.Time{} // Return zero time for processes not running
+	})
+
+	removeErr := errors.New("remove failure")
+	callCount := 0
+	stubRemoveLogFile(t, func(path string) error {
+		callCount++
+		if path == target {
+			return removeErr
+		}
+		return os.Remove(path)
+	})
+
+	stats, err := cleanupOldLogs()
+	if err == nil {
+		t.Fatalf("cleanupOldLogs() expected error")
+	}
+	if !errors.Is(err, removeErr) {
+		t.Fatalf("cleanupOldLogs error = %v, want %v", err, removeErr)
+	}
+
+	want := CleanupStats{Scanned: 2, Kept: 1, Errors: 1}
+	if !compareCleanupStats(stats, want) {
+		t.Fatalf("cleanup stats mismatch: got %+v, want %+v", stats, want)
+	}
+
+	if len(checked) != 1 || checked[0] != 555 {
+		t.Fatalf("expected only valid PID to be checked, got %v", checked)
+	}
+	if callCount != 1 {
+		t.Fatalf("expected remove to be called once, got %d", callCount)
+	}
+	if _, err := os.Stat(target); err != nil {
+		t.Fatalf("expected errored file %s to remain for manual cleanup, err=%v", target, err)
+	}
+}
+
+func TestLoggerCleanupOldLogsHandlesGlobFailures(t *testing.T) {
+	stubProcessRunning(t, func(pid int) bool {
+		t.Fatalf("process check should not run when glob fails")
+		return false
+	})
+	stubProcessStartTime(t, func(int) time.Time {
+		return time.Time{}
+	})
+
+	globErr := errors.New("glob failure")
+	stubGlobLogFiles(t, func(pattern string) ([]string, error) {
+		return nil, globErr
+	})
+
+	stats, err := cleanupOldLogs()
+	if err == nil {
+		t.Fatalf("cleanupOldLogs() expected error")
+	}
+	if !errors.Is(err, globErr) {
+		t.Fatalf("cleanupOldLogs error = %v, want %v", err, globErr)
+	}
+	if stats.Scanned != 0 || stats.Deleted != 0 || stats.Kept != 0 || stats.Errors != 0 || len(stats.DeletedFiles) != 0 || len(stats.KeptFiles) != 0 {
+		t.Fatalf("cleanup stats mismatch: got %+v, want zero", stats)
+	}
+}
+
+func TestLoggerCleanupOldLogsEmptyDirectoryStats(t *testing.T) {
+	setTempDirEnv(t, t.TempDir())
+
+	stubProcessRunning(t, func(int) bool {
+		t.Fatalf("process check should not run for empty directory")
+		return false
+	})
+	stubProcessStartTime(t, func(int) time.Time {
+		return time.Time{}
+	})
+
+	stats, err := cleanupOldLogs()
+	if err != nil {
+		t.Fatalf("cleanupOldLogs() unexpected error: %v", err)
+	}
+	if stats.Scanned != 0 || stats.Deleted != 0 || stats.Kept != 0 || stats.Errors != 0 || len(stats.DeletedFiles) != 0 || len(stats.KeptFiles) != 0 {
+		t.Fatalf("cleanup stats mismatch: got %+v, want zero", stats)
+	}
+}
+
+func TestLoggerCleanupOldLogsHandlesTempDirPermissionErrors(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	paths := []string{
+		createTempLog(t, tempDir, "codeagent-wrapper-6100.log"),
+		createTempLog(t, tempDir, "codeagent-wrapper-6101.log"),
+	}
+
+	stubProcessRunning(t, func(int) bool { return false })
+	stubProcessStartTime(t, func(int) time.Time { return time.Time{} })
+
+	var attempts int
+	stubRemoveLogFile(t, func(path string) error {
+		attempts++
+		return &os.PathError{Op: "remove", Path: path, Err: os.ErrPermission}
+	})
+
+	stats, err := cleanupOldLogs()
+	if err == nil {
+		t.Fatalf("cleanupOldLogs() expected error")
+	}
+	if !errors.Is(err, os.ErrPermission) {
+		t.Fatalf("cleanupOldLogs error = %v, want permission", err)
+	}
+
+	want := CleanupStats{Scanned: len(paths), Errors: len(paths)}
+	if !compareCleanupStats(stats, want) {
+		t.Fatalf("cleanup stats mismatch: got %+v, want %+v", stats, want)
+	}
+
+	if attempts != len(paths) {
+		t.Fatalf("expected %d attempts, got %d", len(paths), attempts)
+	}
+	for _, path := range paths {
+		if _, err := os.Stat(path); err != nil {
+			t.Fatalf("expected protected file %s to remain, err=%v", path, err)
+		}
+	}
+}
+
+func TestLoggerCleanupOldLogsHandlesPermissionDeniedFile(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	protected := createTempLog(t, tempDir, "codeagent-wrapper-6200.log")
+	deletable := createTempLog(t, tempDir, "codeagent-wrapper-6201.log")
+
+	stubProcessRunning(t, func(int) bool { return false })
+	stubProcessStartTime(t, func(int) time.Time { return time.Time{} })
+
+	stubRemoveLogFile(t, func(path string) error {
+		if path == protected {
+			return &os.PathError{Op: "remove", Path: path, Err: os.ErrPermission}
+		}
+		return os.Remove(path)
+	})
+
+	stats, err := cleanupOldLogs()
+	if err == nil {
+		t.Fatalf("cleanupOldLogs() expected error")
+	}
+	if !errors.Is(err, os.ErrPermission) {
+		t.Fatalf("cleanupOldLogs error = %v, want permission", err)
+	}
+
+	want := CleanupStats{Scanned: 2, Deleted: 1, Errors: 1}
+	if !compareCleanupStats(stats, want) {
+		t.Fatalf("cleanup stats mismatch: got %+v, want %+v", stats, want)
+	}
+
+	if _, err := os.Stat(protected); err != nil {
+		t.Fatalf("expected protected file to remain, err=%v", err)
+	}
+	if _, err := os.Stat(deletable); !os.IsNotExist(err) {
+		t.Fatalf("expected deletable file to be removed, err=%v", err)
+	}
+}
+
+func TestLoggerCleanupOldLogsPerformanceBound(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	const fileCount = 400
+	fakePaths := make([]string, fileCount)
+	for i := 0; i < fileCount; i++ {
+		name := fmt.Sprintf("codeagent-wrapper-%d.log", 10000+i)
+		fakePaths[i] = createTempLog(t, tempDir, name)
+	}
+
+	stubGlobLogFiles(t, func(pattern string) ([]string, error) {
+		return fakePaths, nil
+	})
+	stubProcessRunning(t, func(int) bool { return false })
+	stubProcessStartTime(t, func(int) time.Time { return time.Time{} })
+
+	var removed int
+	stubRemoveLogFile(t, func(path string) error {
+		removed++
+		return nil
+	})
+
+	start := time.Now()
+	stats, err := cleanupOldLogs()
+	elapsed := time.Since(start)
+
+	if err != nil {
+		t.Fatalf("cleanupOldLogs() unexpected error: %v", err)
+	}
+
+	if removed != fileCount {
+		t.Fatalf("expected %d removals, got %d", fileCount, removed)
+	}
+	if elapsed > 100*time.Millisecond {
+		t.Fatalf("cleanup took too long: %v for %d files", elapsed, fileCount)
+	}
+
+	want := CleanupStats{Scanned: fileCount, Deleted: fileCount}
+	if !compareCleanupStats(stats, want) {
+		t.Fatalf("cleanup stats mismatch: got %+v, want %+v", stats, want)
+	}
+}
+
+func TestLoggerCleanupOldLogsKeepsCurrentProcessLog(t *testing.T) {
+	tempDir := setTempDirEnv(t, t.TempDir())
+
+	currentPID := os.Getpid()
+	currentLog := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", currentPID))
+
+	stubProcessRunning(t, func(pid int) bool {
+		if pid != currentPID {
+			t.Fatalf("unexpected pid check: %d", pid)
+		}
+		return true
+	})
+	stubProcessStartTime(t, func(pid int) time.Time {
+		if pid == currentPID {
+			return time.Now().Add(-1 * time.Hour)
+		}
+		return time.Time{}
+	})
+
+	stats, err := cleanupOldLogs()
+	if err != nil {
+		t.Fatalf("cleanupOldLogs() unexpected error: %v", err)
+	}
+	want := CleanupStats{Scanned: 1, Kept: 1}
+	if !compareCleanupStats(stats, want) {
+		t.Fatalf("cleanup stats mismatch: got %+v, want %+v", stats, want)
+	}
+	if _, err := os.Stat(currentLog); err != nil {
+		t.Fatalf("expected current process log to remain, err=%v", err)
+	}
+}
+
+func TestLoggerIsPIDReusedScenarios(t *testing.T) {
+	now := time.Now()
+	tests := []struct {
+		name      string
+		statErr   error
+		modTime   time.Time
+		startTime time.Time
+		want      bool
+	}{
+		{"stat error", errors.New("stat failed"), time.Time{}, time.Time{}, false},
+		{"old file unknown start", nil, now.Add(-8 * 24 * time.Hour), time.Time{}, true},
+		{"recent file unknown start", nil, now.Add(-2 * time.Hour), time.Time{}, false},
+		{"pid reused", nil, now.Add(-2 * time.Hour), now.Add(-30 * time.Minute), true},
+		{"pid active", nil, now.Add(-30 * time.Minute), now.Add(-2 * time.Hour), false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			stubFileStat(t, func(string) (os.FileInfo, error) {
+				if tt.statErr != nil {
+					return nil, tt.statErr
+				}
+				return fakeFileInfo{modTime: tt.modTime}, nil
+			})
+			stubProcessStartTime(t, func(int) time.Time {
+				return tt.startTime
+			})
+			if got := isPIDReused("log", 1234); got != tt.want {
+				t.Fatalf("isPIDReused() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestLoggerIsUnsafeFileSecurityChecks(t *testing.T) {
+	tempDir := t.TempDir()
+	absTempDir, err := filepath.Abs(tempDir)
+	if err != nil {
+		t.Fatalf("filepath.Abs() error = %v", err)
+	}
+
+	t.Run("symlink", func(t *testing.T) {
+		stubFileStat(t, func(string) (os.FileInfo, error) {
+			return fakeFileInfo{mode: os.ModeSymlink}, nil
+		})
+		stubEvalSymlinks(t, func(path string) (string, error) {
+			return filepath.Join(absTempDir, filepath.Base(path)), nil
+		})
+		unsafe, reason := isUnsafeFile(filepath.Join(absTempDir, "codeagent-wrapper-1.log"), tempDir)
+		if !unsafe || reason != "refusing to delete symlink" {
+			t.Fatalf("expected symlink to be rejected, got unsafe=%v reason=%q", unsafe, reason)
+		}
+	})
+
+	t.Run("path traversal", func(t *testing.T) {
+		stubFileStat(t, func(string) (os.FileInfo, error) {
+			return fakeFileInfo{}, nil
+		})
+		outside := filepath.Join(filepath.Dir(absTempDir), "etc", "passwd")
+		stubEvalSymlinks(t, func(string) (string, error) {
+			return outside, nil
+		})
+		unsafe, reason := isUnsafeFile(filepath.Join("..", "..", "etc", "passwd"), tempDir)
+		if !unsafe || reason != "file is outside tempDir" {
+			t.Fatalf("expected traversal path to be rejected, got unsafe=%v reason=%q", unsafe, reason)
+		}
+	})
+
+	t.Run("outside temp dir", func(t *testing.T) {
+		stubFileStat(t, func(string) (os.FileInfo, error) {
+			return fakeFileInfo{}, nil
+		})
+		otherDir := t.TempDir()
+		stubEvalSymlinks(t, func(string) (string, error) {
+			return filepath.Join(otherDir, "codeagent-wrapper-9.log"), nil
+		})
+		unsafe, reason := isUnsafeFile(filepath.Join(otherDir, "codeagent-wrapper-9.log"), tempDir)
+		if !unsafe || reason != "file is outside tempDir" {
+			t.Fatalf("expected outside file to be rejected, got unsafe=%v reason=%q", unsafe, reason)
+		}
+	})
+}
+
+func TestLoggerPathAndRemove(t *testing.T) {
+	tempDir := t.TempDir()
+	t.Setenv("TMPDIR", tempDir)
+
+	logger, err := NewLoggerWithSuffix("sample")
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix() error = %v", err)
+	}
+	path := logger.Path()
+	if path == "" {
+		_ = logger.Close()
+		t.Fatalf("logger.Path() returned empty path")
+	}
+	if err := logger.Close(); err != nil {
+		t.Fatalf("Close() error = %v", err)
+	}
+
+	if err := logger.RemoveLogFile(); err != nil {
+		t.Fatalf("RemoveLogFile() error = %v", err)
+	}
+	if _, err := os.Stat(path); !os.IsNotExist(err) {
+		t.Fatalf("expected log file to be removed, err=%v", err)
+	}
+
+	var nilLogger *Logger
+	if nilLogger.Path() != "" {
+		t.Fatalf("nil logger Path() should be empty")
+	}
+	if err := nilLogger.RemoveLogFile(); err != nil {
+		t.Fatalf("nil logger RemoveLogFile() should return nil, got %v", err)
+	}
+}
+
+func TestLoggerParsePIDFromLog(t *testing.T) {
+	hugePID := strconv.FormatInt(math.MaxInt64, 10) + "0"
+	tests := []struct {
+		name string
+		pid  int
+		ok   bool
+	}{
+		{"codeagent-wrapper-123.log", 123, true},
+		{"codeagent-wrapper-999-extra.log", 999, true},
+		{"codeagent-wrapper-.log", 0, false},
+		{"invalid-name.log", 0, false},
+		{"codeagent-wrapper--5.log", 0, false},
+		{"codeagent-wrapper-0.log", 0, false},
+		{fmt.Sprintf("codeagent-wrapper-%s.log", hugePID), 0, false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, ok := parsePIDFromLog(filepath.Join("/tmp", tt.name))
+			if ok != tt.ok {
+				t.Fatalf("parsePIDFromLog ok = %v, want %v", ok, tt.ok)
+			}
+			if ok && got != tt.pid {
+				t.Fatalf("pid = %d, want %d", got, tt.pid)
+			}
+		})
+	}
+}
+
+func createTempLog(t *testing.T, dir, name string) string {
+	t.Helper()
+	path := filepath.Join(dir, name)
+	if err := os.WriteFile(path, []byte("test"), 0o644); err != nil {
+		t.Fatalf("failed to create temp log %s: %v", path, err)
+	}
+	return path
+}
+
+func setTempDirEnv(t *testing.T, dir string) string {
+	t.Helper()
+	resolved := dir
+	if eval, err := filepath.EvalSymlinks(dir); err == nil {
+		resolved = eval
+	}
+	t.Setenv("TMPDIR", resolved)
+	t.Setenv("TEMP", resolved)
+	t.Setenv("TMP", resolved)
+	return resolved
+}
+
+func stubProcessRunning(t *testing.T, fn func(int) bool) {
+	t.Helper()
+	t.Cleanup(SetProcessRunningCheck(fn))
+}
+
+func stubProcessStartTime(t *testing.T, fn func(int) time.Time) {
+	t.Helper()
+	t.Cleanup(SetProcessStartTimeFn(fn))
+}
+
+func stubRemoveLogFile(t *testing.T, fn func(string) error) {
+	t.Helper()
+	t.Cleanup(SetRemoveLogFileFn(fn))
+}
+
+func stubGlobLogFiles(t *testing.T, fn func(string) ([]string, error)) {
+	t.Helper()
+	t.Cleanup(SetGlobLogFilesFn(fn))
+}
+
+func stubFileStat(t *testing.T, fn func(string) (os.FileInfo, error)) {
+	t.Helper()
+	t.Cleanup(SetFileStatFn(fn))
+}
+
+func stubEvalSymlinks(t *testing.T, fn func(string) (string, error)) {
+	t.Helper()
+	t.Cleanup(SetEvalSymlinksFn(fn))
+}
+
+type fakeFileInfo struct {
+	modTime time.Time
+	mode    os.FileMode
+}
+
+func (f fakeFileInfo) Name() string       { return "fake" }
+func (f fakeFileInfo) Size() int64        { return 0 }
+func (f fakeFileInfo) Mode() os.FileMode  { return f.mode }
+func (f fakeFileInfo) ModTime() time.Time { return f.modTime }
+func (f fakeFileInfo) IsDir() bool        { return false }
+func (f fakeFileInfo) Sys() interface{}   { return nil }
+
+func TestLoggerExtractRecentErrors(t *testing.T) {
+	tests := []struct {
+		name       string
+		logs       []struct{ level, msg string }
+		maxEntries int
+		want       []string
+	}{
+		{
+			name:       "empty log",
+			logs:       nil,
+			maxEntries: 10,
+			want:       nil,
+		},
+		{
+			name: "no errors",
+			logs: []struct{ level, msg string }{
+				{"INFO", "started"},
+				{"DEBUG", "processing"},
+			},
+			maxEntries: 10,
+			want:       nil,
+		},
+		{
+			name: "single error",
+			logs: []struct{ level, msg string }{
+				{"INFO", "started"},
+				{"ERROR", "something failed"},
+			},
+			maxEntries: 10,
+			want:       []string{"something failed"},
+		},
+		{
+			name: "error and warn",
+			logs: []struct{ level, msg string }{
+				{"INFO", "started"},
+				{"WARN", "warning message"},
+				{"ERROR", "error message"},
+			},
+			maxEntries: 10,
+			want: []string{
+				"warning message",
+				"error message",
+			},
+		},
+		{
+			name: "truncate to max",
+			logs: []struct{ level, msg string }{
+				{"ERROR", "error 1"},
+				{"ERROR", "error 2"},
+				{"ERROR", "error 3"},
+				{"ERROR", "error 4"},
+				{"ERROR", "error 5"},
+			},
+			maxEntries: 3,
+			want: []string{
+				"error 3",
+				"error 4",
+				"error 5",
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			logger, err := NewLoggerWithSuffix("extract-test")
+			if err != nil {
+				t.Fatalf("NewLoggerWithSuffix() error = %v", err)
+			}
+			defer logger.Close()
+			defer func() { _ = logger.RemoveLogFile() }()
+
+			// Write logs using logger methods
+			for _, entry := range tt.logs {
+				switch entry.level {
+				case "INFO":
+					logger.Info(entry.msg)
+				case "WARN":
+					logger.Warn(entry.msg)
+				case "ERROR":
+					logger.Error(entry.msg)
+				case "DEBUG":
+					logger.Debug(entry.msg)
+				}
+			}
+
+			logger.Flush()
+
+			got := logger.ExtractRecentErrors(tt.maxEntries)
+
+			if len(got) != len(tt.want) {
+				t.Fatalf("ExtractRecentErrors() got %d entries, want %d", len(got), len(tt.want))
+			}
+			for i, entry := range got {
+				if entry != tt.want[i] {
+					t.Errorf("entry[%d] = %q, want %q", i, entry, tt.want[i])
+				}
+			}
+		})
+	}
+}
+
+func TestLoggerExtractRecentErrorsNilLogger(t *testing.T) {
+	var logger *Logger
+	if got := logger.ExtractRecentErrors(10); got != nil {
+		t.Fatalf("nil logger ExtractRecentErrors() should return nil, got %v", got)
+	}
+}
+
+func TestLoggerExtractRecentErrorsEmptyPath(t *testing.T) {
+	logger := &Logger{}
+	if got := logger.ExtractRecentErrors(10); got != nil {
+		t.Fatalf("empty path ExtractRecentErrors() should return nil, got %v", got)
+	}
+}
+
+func TestLoggerExtractRecentErrorsFileNotExist(t *testing.T) {
+	logger := &Logger{}
+	if got := logger.ExtractRecentErrors(10); got != nil {
+		t.Fatalf("nonexistent file ExtractRecentErrors() should return nil, got %v", got)
+	}
+}
+
+func TestSanitizeLogSuffixNoDuplicates(t *testing.T) {
+	testCases := []string{
+		"task",
+		"task.",
+		".task",
+		"-task",
+		"task-",
+		"--task--",
+		"..task..",
+	}
+
+	seen := make(map[string]string)
+	for _, input := range testCases {
+		result := sanitizeLogSuffix(input)
+		if result == "" {
+			t.Fatalf("sanitizeLogSuffix(%q) returned empty string", input)
+		}
+
+		if prev, exists := seen[result]; exists {
+			t.Fatalf("collision detected: %q and %q both produce %q", input, prev, result)
+		}
+		seen[result] = input
+
+		// Verify result is safe for file names
+		if strings.ContainsAny(result, "/\\:*?\"<>|") {
+			t.Fatalf("sanitizeLogSuffix(%q) = %q contains unsafe characters", input, result)
+		}
+	}
+}
+
+func TestExtractRecentErrorsBoundaryCheck(t *testing.T) {
+	logger, err := NewLoggerWithSuffix("boundary-test")
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix() error = %v", err)
+	}
+	defer logger.Close()
+	defer func() { _ = logger.RemoveLogFile() }()
+
+	// Write some errors
+	logger.Error("error 1")
+	logger.Warn("warn 1")
+	logger.Error("error 2")
+	logger.Flush()
+
+	// Test zero
+	result := logger.ExtractRecentErrors(0)
+	if result != nil {
+		t.Fatalf("ExtractRecentErrors(0) should return nil, got %v", result)
+	}
+
+	// Test negative
+	result = logger.ExtractRecentErrors(-5)
+	if result != nil {
+		t.Fatalf("ExtractRecentErrors(-5) should return nil, got %v", result)
+	}
+
+	// Test positive still works
+	result = logger.ExtractRecentErrors(10)
+	if len(result) != 3 {
+		t.Fatalf("ExtractRecentErrors(10) expected 3 entries, got %d", len(result))
+	}
+}
+
+func TestErrorEntriesMaxLimit(t *testing.T) {
+	logger, err := NewLoggerWithSuffix("max-limit-test")
+	if err != nil {
+		t.Fatalf("NewLoggerWithSuffix() error = %v", err)
+	}
+	defer logger.Close()
+	defer func() { _ = logger.RemoveLogFile() }()
+
+	// Write 150 error/warn entries
+	for i := 1; i <= 150; i++ {
+		if i%2 == 0 {
+			logger.Error(fmt.Sprintf("error-%03d", i))
+		} else {
+			logger.Warn(fmt.Sprintf("warn-%03d", i))
+		}
+	}
+	logger.Flush()
+
+	// Extract all cached errors
+	result := logger.ExtractRecentErrors(200) // Request more than cache size
+
+	// Should only have last 100 entries (entries 51-150 in sequence)
+	if len(result) != 100 {
+		t.Fatalf("expected 100 cached entries, got %d", len(result))
+	}
+
+	// Verify entries are the last 100 (entries 51-150)
+	if !strings.Contains(result[0], "051") {
+		t.Fatalf("first cached entry should be entry 51, got: %s", result[0])
+	}
+	if !strings.Contains(result[99], "150") {
+		t.Fatalf("last cached entry should be entry 150, got: %s", result[99])
+	}
+
+	// Verify order is preserved - simplified logic
+	for i := 0; i < len(result)-1; i++ {
+		expectedNum := 51 + i
+		nextNum := 51 + i + 1
+
+		expectedEntry := fmt.Sprintf("%03d", expectedNum)
+		nextEntry := fmt.Sprintf("%03d", nextNum)
+
+		if !strings.Contains(result[i], expectedEntry) {
+			t.Fatalf("entry at index %d should contain %s, got: %s", i, expectedEntry, result[i])
+		}
+		if !strings.Contains(result[i+1], nextEntry) {
+			t.Fatalf("entry at index %d should contain %s, got: %s", i+1, nextEntry, result[i+1])
+		}
+	}
+}

codeagent-wrapper/internal/logger/process_check.go

@@ -0,0 +1,63 @@
+package logger
+
+import (
+	"errors"
+	"math"
+	"time"
+
+	"github.com/shirou/gopsutil/v3/process"
+)
+
+func pidToInt32(pid int) (int32, bool) {
+	if pid <= 0 || pid > math.MaxInt32 {
+		return 0, false
+	}
+	return int32(pid), true
+}
+
+// isProcessRunning reports whether a process with the given pid appears to be running.
+// It is intentionally conservative on errors to avoid deleting logs for live processes.
+func isProcessRunning(pid int) bool {
+	pid32, ok := pidToInt32(pid)
+	if !ok {
+		return false
+	}
+
+	exists, err := process.PidExists(pid32)
+	if err == nil {
+		return exists
+	}
+
+	// If we can positively identify that the process doesn't exist, report false.
+	if errors.Is(err, process.ErrorProcessNotRunning) {
+		return false
+	}
+
+	// Permission/inspection failures: assume it's running to be safe.
+	return true
+}
+
+// getProcessStartTime returns the start time of a process.
+// Returns zero time if the start time cannot be determined.
+func getProcessStartTime(pid int) time.Time {
+	pid32, ok := pidToInt32(pid)
+	if !ok {
+		return time.Time{}
+	}
+
+	proc, err := process.NewProcess(pid32)
+	if err != nil {
+		return time.Time{}
+	}
+
+	ms, err := proc.CreateTime()
+	if err != nil || ms <= 0 {
+		return time.Time{}
+	}
+
+	return time.UnixMilli(ms)
+}
+
+func IsProcessRunning(pid int) bool { return isProcessRunning(pid) }
+
+func GetProcessStartTime(pid int) time.Time { return getProcessStartTime(pid) }

codeagent-wrapper/internal/logger/process_check_test.go

@@ -0,0 +1,112 @@
+package logger
+
+import (
+	"math"
+	"os"
+	"os/exec"
+	"runtime"
+	"strconv"
+	"testing"
+	"time"
+)
+
+func TestIsProcessRunning(t *testing.T) {
+	t.Run("boundary values", func(t *testing.T) {
+		if isProcessRunning(0) {
+			t.Fatalf("pid 0 should never be treated as running")
+		}
+		if isProcessRunning(-1) {
+			t.Fatalf("negative pid should never be treated as running")
+		}
+	})
+
+	t.Run("pid out of int32 range", func(t *testing.T) {
+		if strconv.IntSize <= 32 {
+			t.Skip("int cannot represent values above int32 range")
+		}
+
+		pid := int(int64(math.MaxInt32) + 1)
+		if isProcessRunning(pid) {
+			t.Fatalf("expected pid %d (out of int32 range) to be treated as not running", pid)
+		}
+	})
+
+	t.Run("current process", func(t *testing.T) {
+		if !isProcessRunning(os.Getpid()) {
+			t.Fatalf("expected current process (pid=%d) to be running", os.Getpid())
+		}
+	})
+
+	t.Run("fake pid", func(t *testing.T) {
+		const nonexistentPID = 1 << 30
+		if isProcessRunning(nonexistentPID) {
+			t.Fatalf("expected pid %d to be reported as not running", nonexistentPID)
+		}
+	})
+
+	t.Run("terminated process", func(t *testing.T) {
+		pid := exitedProcessPID(t)
+		if isProcessRunning(pid) {
+			t.Fatalf("expected exited child process (pid=%d) to be reported as not running", pid)
+		}
+	})
+}
+
+func exitedProcessPID(t *testing.T) int {
+	t.Helper()
+
+	var cmd *exec.Cmd
+	if runtime.GOOS == "windows" {
+		cmd = exec.Command("cmd", "/c", "exit 0")
+	} else {
+		cmd = exec.Command("sh", "-c", "exit 0")
+	}
+
+	if err := cmd.Start(); err != nil {
+		t.Fatalf("failed to start helper process: %v", err)
+	}
+	pid := cmd.Process.Pid
+
+	if err := cmd.Wait(); err != nil {
+		t.Fatalf("helper process did not exit cleanly: %v", err)
+	}
+
+	time.Sleep(50 * time.Millisecond)
+	return pid
+}
+
+func TestGetProcessStartTimeReadsProcStat(t *testing.T) {
+	start := getProcessStartTime(os.Getpid())
+	if start.IsZero() {
+		t.Fatalf("expected non-zero start time for current process")
+	}
+	if start.After(time.Now().Add(5 * time.Second)) {
+		t.Fatalf("start time is unexpectedly in the future: %v", start)
+	}
+}
+
+func TestGetProcessStartTimeInvalidData(t *testing.T) {
+	if !getProcessStartTime(0).IsZero() {
+		t.Fatalf("expected zero time for pid 0")
+	}
+	if !getProcessStartTime(-1).IsZero() {
+		t.Fatalf("expected zero time for negative pid")
+	}
+	if !getProcessStartTime(1 << 30).IsZero() {
+		t.Fatalf("expected zero time for non-existent pid")
+	}
+	if strconv.IntSize > 32 {
+		pid := int(int64(math.MaxInt32) + 1)
+		if !getProcessStartTime(pid).IsZero() {
+			t.Fatalf("expected zero time for pid %d (out of int32 range)", pid)
+		}
+	}
+}
+
+func TestGetBootTimeParsesBtime(t *testing.T) {
+	t.Skip("legacy boot-time probing removed; start time now uses gopsutil")
+}
+
+func TestGetBootTimeInvalidData(t *testing.T) {
+	t.Skip("legacy boot-time probing removed; start time now uses gopsutil")
+}

codeagent-wrapper/internal/logger/testhooks.go

@@ -0,0 +1,67 @@
+package logger
+
+import (
+	"os"
+	"path/filepath"
+	"time"
+)
+
+func SetProcessRunningCheck(fn func(int) bool) (restore func()) {
+	prev := processRunningCheck
+	if fn != nil {
+		processRunningCheck = fn
+	} else {
+		processRunningCheck = isProcessRunning
+	}
+	return func() { processRunningCheck = prev }
+}
+
+func SetProcessStartTimeFn(fn func(int) time.Time) (restore func()) {
+	prev := processStartTimeFn
+	if fn != nil {
+		processStartTimeFn = fn
+	} else {
+		processStartTimeFn = getProcessStartTime
+	}
+	return func() { processStartTimeFn = prev }
+}
+
+func SetRemoveLogFileFn(fn func(string) error) (restore func()) {
+	prev := removeLogFileFn
+	if fn != nil {
+		removeLogFileFn = fn
+	} else {
+		removeLogFileFn = os.Remove
+	}
+	return func() { removeLogFileFn = prev }
+}
+
+func SetGlobLogFilesFn(fn func(string) ([]string, error)) (restore func()) {
+	prev := globLogFiles
+	if fn != nil {
+		globLogFiles = fn
+	} else {
+		globLogFiles = filepath.Glob
+	}
+	return func() { globLogFiles = prev }
+}
+
+func SetFileStatFn(fn func(string) (os.FileInfo, error)) (restore func()) {
+	prev := fileStatFn
+	if fn != nil {
+		fileStatFn = fn
+	} else {
+		fileStatFn = os.Lstat
+	}
+	return func() { fileStatFn = prev }
+}
+
+func SetEvalSymlinksFn(fn func(string) (string, error)) (restore func()) {
+	prev := evalSymlinksFn
+	if fn != nil {
+		evalSymlinksFn = fn
+	} else {
+		evalSymlinksFn = filepath.EvalSymlinks
+	}
+	return func() { evalSymlinksFn = prev }
+}

codeagent-wrapper/internal/logger/wrapper_name.go

@@ -0,0 +1,13 @@
+package logger
+
+// WrapperName is the fixed name for this tool.
+const WrapperName = "codeagent-wrapper"
+
+// CurrentWrapperName returns the wrapper name (always "codeagent-wrapper").
+func CurrentWrapperName() string { return WrapperName }
+
+// LogPrefixes returns the log file name prefixes to look for.
+func LogPrefixes() []string { return []string{WrapperName} }
+
+// PrimaryLogPrefix returns the preferred filename prefix for log files.
+func PrimaryLogPrefix() string { return WrapperName }

codeagent-wrapper/internal/parser/event.go

@@ -0,0 +1,74 @@
+package parser
+
+import "github.com/goccy/go-json"
+
+// JSONEvent represents a Codex JSON output event.
+type JSONEvent struct {
+	Type     string     `json:"type"`
+	ThreadID string     `json:"thread_id,omitempty"`
+	Item     *EventItem `json:"item,omitempty"`
+}
+
+// EventItem represents the item field in a JSON event.
+type EventItem struct {
+	Type string      `json:"type"`
+	Text interface{} `json:"text"`
+}
+
+// ClaudeEvent for Claude stream-json format.
+type ClaudeEvent struct {
+	Type      string `json:"type"`
+	Subtype   string `json:"subtype,omitempty"`
+	SessionID string `json:"session_id,omitempty"`
+	Result    string `json:"result,omitempty"`
+}
+
+// GeminiEvent for Gemini stream-json format.
+type GeminiEvent struct {
+	Type      string `json:"type"`
+	SessionID string `json:"session_id,omitempty"`
+	Role      string `json:"role,omitempty"`
+	Content   string `json:"content,omitempty"`
+	Delta     bool   `json:"delta,omitempty"`
+	Status    string `json:"status,omitempty"`
+}
+
+// UnifiedEvent combines all backend event formats into a single structure
+// to avoid multiple JSON unmarshal operations per event.
+type UnifiedEvent struct {
+	// Common fields
+	Type string `json:"type"`
+
+	// Codex-specific fields
+	ThreadID string          `json:"thread_id,omitempty"`
+	Item     json.RawMessage `json:"item,omitempty"` // Lazy parse
+
+	// Claude-specific fields
+	Subtype   string `json:"subtype,omitempty"`
+	SessionID string `json:"session_id,omitempty"`
+	Result    string `json:"result,omitempty"`
+
+	// Gemini-specific fields
+	Role    string `json:"role,omitempty"`
+	Content string `json:"content,omitempty"`
+	Delta   *bool  `json:"delta,omitempty"`
+	Status  string `json:"status,omitempty"`
+
+	// Opencode-specific fields (camelCase sessionID)
+	OpencodeSessionID string          `json:"sessionID,omitempty"`
+	Part              json.RawMessage `json:"part,omitempty"`
+}
+
+// OpencodePart represents the part field in opencode events.
+type OpencodePart struct {
+	Type      string `json:"type"`
+	Text      string `json:"text,omitempty"`
+	Reason    string `json:"reason,omitempty"`
+	SessionID string `json:"sessionID,omitempty"`
+}
+
+// ItemContent represents the parsed item.text field for Codex events.
+type ItemContent struct {
+	Type string      `json:"type"`
+	Text interface{} `json:"text"`
+}

codeagent-wrapper/internal/parser/parser.go

@@ -0,0 +1,436 @@
+package parser
+
+import (
+	"bufio"
+	"bytes"
+	"errors"
+	"fmt"
+	"io"
+	"strings"
+	"sync"
+
+	"github.com/goccy/go-json"
+)
+
+const (
+	jsonLineReaderSize   = 64 * 1024
+	jsonLineMaxBytes     = 10 * 1024 * 1024
+	jsonLinePreviewBytes = 256
+)
+
+type lineScratch struct {
+	buf     []byte
+	preview []byte
+}
+
+const maxPooledLineScratchCap = 1 << 20 // 1 MiB
+
+var lineScratchPool = sync.Pool{
+	New: func() any {
+		return &lineScratch{
+			buf:     make([]byte, 0, jsonLineReaderSize),
+			preview: make([]byte, 0, jsonLinePreviewBytes),
+		}
+	},
+}
+
+func ParseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(string), onMessage func(), onComplete func()) (message, threadID string) {
+	reader := bufio.NewReaderSize(r, jsonLineReaderSize)
+	scratch := lineScratchPool.Get().(*lineScratch)
+	if scratch.buf == nil {
+		scratch.buf = make([]byte, 0, jsonLineReaderSize)
+	} else {
+		scratch.buf = scratch.buf[:0]
+	}
+	if scratch.preview == nil {
+		scratch.preview = make([]byte, 0, jsonLinePreviewBytes)
+	} else {
+		scratch.preview = scratch.preview[:0]
+	}
+	defer func() {
+		if cap(scratch.buf) > maxPooledLineScratchCap {
+			scratch.buf = nil
+		} else if scratch.buf != nil {
+			scratch.buf = scratch.buf[:0]
+		}
+		if cap(scratch.preview) > jsonLinePreviewBytes*4 {
+			scratch.preview = nil
+		} else if scratch.preview != nil {
+			scratch.preview = scratch.preview[:0]
+		}
+		lineScratchPool.Put(scratch)
+	}()
+
+	if warnFn == nil {
+		warnFn = func(string) {}
+	}
+	if infoFn == nil {
+		infoFn = func(string) {}
+	}
+
+	notifyMessage := func() {
+		if onMessage != nil {
+			onMessage()
+		}
+	}
+
+	notifyComplete := func() {
+		if onComplete != nil {
+			onComplete()
+		}
+	}
+
+	totalEvents := 0
+
+	var (
+		codexMessage    string
+		claudeMessage   string
+		geminiBuffer    strings.Builder
+		opencodeMessage strings.Builder
+	)
+
+	for {
+		line, tooLong, err := readLineWithLimit(reader, jsonLineMaxBytes, jsonLinePreviewBytes, scratch)
+		if err != nil {
+			if errors.Is(err, io.EOF) {
+				break
+			}
+			warnFn("Read stdout error: " + err.Error())
+			break
+		}
+
+		line = bytes.TrimSpace(line)
+		if len(line) == 0 {
+			continue
+		}
+		totalEvents++
+
+		if tooLong {
+			warnFn(fmt.Sprintf("Skipped overlong JSON line (> %d bytes): %s", jsonLineMaxBytes, TruncateBytes(line, 100)))
+			continue
+		}
+
+		// Single unmarshal for all backend types
+		var event UnifiedEvent
+		if err := json.Unmarshal(line, &event); err != nil {
+			warnFn(fmt.Sprintf("Failed to parse event: %s", TruncateBytes(line, 100)))
+			continue
+		}
+
+		// Detect backend type by field presence
+		isCodex := event.ThreadID != ""
+		if !isCodex && len(event.Item) > 0 {
+			var itemHeader struct {
+				Type string `json:"type"`
+			}
+			if json.Unmarshal(event.Item, &itemHeader) == nil && itemHeader.Type != "" {
+				isCodex = true
+			}
+		}
+		// Codex-specific event types without thread_id or item
+		if !isCodex && (event.Type == "turn.started" || event.Type == "turn.completed") {
+			isCodex = true
+		}
+		isClaude := event.Subtype != "" || event.Result != ""
+		if !isClaude && event.Type == "result" && event.SessionID != "" && event.Status == "" {
+			isClaude = true
+		}
+		isGemini := (event.Type == "init" && event.SessionID != "") || event.Role != "" || event.Delta != nil || event.Status != ""
+		isOpencode := event.OpencodeSessionID != "" && len(event.Part) > 0
+
+		// Handle Opencode events first (most specific detection)
+		if isOpencode {
+			if threadID == "" {
+				threadID = event.OpencodeSessionID
+			}
+
+			var part OpencodePart
+			if err := json.Unmarshal(event.Part, &part); err != nil {
+				warnFn(fmt.Sprintf("Failed to parse opencode part: %s", err.Error()))
+				continue
+			}
+
+			// Extract sessionID from part if available
+			if part.SessionID != "" && threadID == "" {
+				threadID = part.SessionID
+			}
+
+			infoFn(fmt.Sprintf("Parsed Opencode event #%d type=%s part_type=%s", totalEvents, event.Type, part.Type))
+
+			if event.Type == "text" && part.Text != "" {
+				opencodeMessage.WriteString(part.Text)
+				notifyMessage()
+			}
+
+			if part.Type == "step-finish" && part.Reason == "stop" {
+				notifyComplete()
+			}
+			continue
+		}
+
+		// Handle Codex events
+		if isCodex {
+			var details []string
+			if event.ThreadID != "" {
+				details = append(details, fmt.Sprintf("thread_id=%s", event.ThreadID))
+			}
+
+			if len(details) > 0 {
+				infoFn(fmt.Sprintf("Parsed event #%d type=%s (%s)", totalEvents, event.Type, strings.Join(details, ", ")))
+			} else {
+				infoFn(fmt.Sprintf("Parsed event #%d type=%s", totalEvents, event.Type))
+			}
+
+			switch event.Type {
+			case "thread.started":
+				threadID = event.ThreadID
+				infoFn(fmt.Sprintf("thread.started event thread_id=%s", threadID))
+
+			case "thread.completed":
+				if event.ThreadID != "" && threadID == "" {
+					threadID = event.ThreadID
+				}
+				infoFn(fmt.Sprintf("thread.completed event thread_id=%s", event.ThreadID))
+				notifyComplete()
+
+			case "turn.completed":
+				infoFn("turn.completed event")
+				notifyComplete()
+
+			case "item.completed":
+				var itemType string
+				if len(event.Item) > 0 {
+					var itemHeader struct {
+						Type string `json:"type"`
+					}
+					if err := json.Unmarshal(event.Item, &itemHeader); err == nil {
+						itemType = itemHeader.Type
+					}
+				}
+
+				if itemType == "agent_message" && len(event.Item) > 0 {
+					// Lazy parse: only parse item content when needed
+					var item ItemContent
+					if err := json.Unmarshal(event.Item, &item); err == nil {
+						normalized := NormalizeText(item.Text)
+						infoFn(fmt.Sprintf("item.completed event item_type=%s message_len=%d", itemType, len(normalized)))
+						if normalized != "" {
+							codexMessage = normalized
+							notifyMessage()
+						}
+					} else {
+						warnFn(fmt.Sprintf("Failed to parse item content: %s", err.Error()))
+					}
+				} else {
+					infoFn(fmt.Sprintf("item.completed event item_type=%s", itemType))
+				}
+			}
+			continue
+		}
+
+		// Handle Claude events
+		if isClaude {
+			if event.SessionID != "" && threadID == "" {
+				threadID = event.SessionID
+			}
+
+			infoFn(fmt.Sprintf("Parsed Claude event #%d type=%s subtype=%s result_len=%d", totalEvents, event.Type, event.Subtype, len(event.Result)))
+
+			if event.Result != "" {
+				claudeMessage = event.Result
+				notifyMessage()
+			}
+
+			if event.Type == "result" {
+				notifyComplete()
+			}
+			continue
+		}
+
+		// Handle Gemini events
+		if isGemini {
+			if event.SessionID != "" && threadID == "" {
+				threadID = event.SessionID
+			}
+
+			if event.Content != "" {
+				geminiBuffer.WriteString(event.Content)
+			}
+
+			if event.Status != "" {
+				notifyMessage()
+
+				if event.Type == "result" && (event.Status == "success" || event.Status == "error" || event.Status == "complete" || event.Status == "failed") {
+					notifyComplete()
+				}
+			}
+
+			delta := false
+			if event.Delta != nil {
+				delta = *event.Delta
+			}
+
+			infoFn(fmt.Sprintf("Parsed Gemini event #%d type=%s role=%s delta=%t status=%s content_len=%d", totalEvents, event.Type, event.Role, delta, event.Status, len(event.Content)))
+			continue
+		}
+
+		// Unknown event format from other backends (turn.started/assistant/user); ignore.
+		continue
+	}
+
+	switch {
+	case opencodeMessage.Len() > 0:
+		message = opencodeMessage.String()
+	case geminiBuffer.Len() > 0:
+		message = geminiBuffer.String()
+	case claudeMessage != "":
+		message = claudeMessage
+	default:
+		message = codexMessage
+	}
+
+	infoFn(fmt.Sprintf("parseJSONStream completed: events=%d, message_len=%d, thread_id_found=%t", totalEvents, len(message), threadID != ""))
+	return message, threadID
+}
+
+func HasKey(m map[string]json.RawMessage, key string) bool {
+	_, ok := m[key]
+	return ok
+}
+
+func DiscardInvalidJSON(decoder *json.Decoder, reader *bufio.Reader) (*bufio.Reader, error) {
+	var buffered bytes.Buffer
+
+	if decoder != nil {
+		if buf := decoder.Buffered(); buf != nil {
+			_, _ = buffered.ReadFrom(buf)
+		}
+	}
+
+	line, err := reader.ReadBytes('\n')
+	buffered.Write(line)
+
+	data := buffered.Bytes()
+	newline := bytes.IndexByte(data, '\n')
+	if newline == -1 {
+		return reader, err
+	}
+
+	remaining := data[newline+1:]
+	if len(remaining) == 0 {
+		return reader, err
+	}
+
+	return bufio.NewReader(io.MultiReader(bytes.NewReader(remaining), reader)), err
+}
+
+func readLineWithLimit(r *bufio.Reader, maxBytes int, previewBytes int, scratch *lineScratch) (line []byte, tooLong bool, err error) {
+	if r == nil {
+		return nil, false, errors.New("reader is nil")
+	}
+	if maxBytes <= 0 {
+		return nil, false, errors.New("maxBytes must be > 0")
+	}
+	if previewBytes < 0 {
+		previewBytes = 0
+	}
+
+	part, isPrefix, err := r.ReadLine()
+	if err != nil {
+		return nil, false, err
+	}
+
+	if !isPrefix {
+		if len(part) > maxBytes {
+			return part[:min(len(part), previewBytes)], true, nil
+		}
+		return part, false, nil
+	}
+
+	if scratch == nil {
+		scratch = &lineScratch{}
+	}
+	if scratch.preview == nil {
+		scratch.preview = make([]byte, 0, min(previewBytes, len(part)))
+	}
+	if scratch.buf == nil {
+		scratch.buf = make([]byte, 0, min(maxBytes, len(part)*2))
+	}
+
+	preview := scratch.preview[:0]
+	if previewBytes > 0 {
+		preview = append(preview, part[:min(previewBytes, len(part))]...)
+	}
+
+	buf := scratch.buf[:0]
+	total := 0
+	if len(part) > maxBytes {
+		tooLong = true
+	} else {
+		buf = append(buf, part...)
+		total = len(part)
+	}
+
+	for isPrefix {
+		part, isPrefix, err = r.ReadLine()
+		if err != nil {
+			return nil, tooLong, err
+		}
+
+		if previewBytes > 0 && len(preview) < previewBytes {
+			preview = append(preview, part[:min(previewBytes-len(preview), len(part))]...)
+		}
+
+		if !tooLong {
+			if total+len(part) > maxBytes {
+				tooLong = true
+				continue
+			}
+			buf = append(buf, part...)
+			total += len(part)
+		}
+	}
+
+	if tooLong {
+		scratch.preview = preview
+		scratch.buf = buf
+		return preview, true, nil
+	}
+	scratch.preview = preview
+	scratch.buf = buf
+	return buf, false, nil
+}
+
+func TruncateBytes(b []byte, maxLen int) string {
+	if len(b) <= maxLen {
+		return string(b)
+	}
+	if maxLen < 0 {
+		return ""
+	}
+	return string(b[:maxLen]) + "..."
+}
+
+func NormalizeText(text interface{}) string {
+	switch v := text.(type) {
+	case string:
+		return v
+	case []interface{}:
+		var sb strings.Builder
+		for _, item := range v {
+			if s, ok := item.(string); ok {
+				sb.WriteString(s)
+			}
+		}
+		return sb.String()
+	default:
+		return ""
+	}
+}
+
+func min(a, b int) int {
+	if a < b {
+		return a
+	}
+	return b
+}

codeagent-wrapper/internal/parser/parser_opencode_test.go

@@ -0,0 +1,50 @@
+package parser
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestParseJSONStream_Opencode(t *testing.T) {
+	input := `{"type":"step_start","timestamp":1768187730683,"sessionID":"ses_44fced3c7ffe83sZpzY1rlQka3","part":{"id":"prt_bb0339afa001NTqoJ2NS8x91zP","sessionID":"ses_44fced3c7ffe83sZpzY1rlQka3","messageID":"msg_bb033866f0011oZxTqvfy0TKtS","type":"step-start","snapshot":"904f0fd58c125b79e60f0993e38f9d9f6200bf47"}}
+{"type":"text","timestamp":1768187744432,"sessionID":"ses_44fced3c7ffe83sZpzY1rlQka3","part":{"id":"prt_bb0339cb5001QDd0Lh0PzFZpa3","sessionID":"ses_44fced3c7ffe83sZpzY1rlQka3","messageID":"msg_bb033866f0011oZxTqvfy0TKtS","type":"text","text":"Hello from opencode"}}
+{"type":"step_finish","timestamp":1768187744471,"sessionID":"ses_44fced3c7ffe83sZpzY1rlQka3","part":{"id":"prt_bb033d0af0019VRZzpO2OVW1na","sessionID":"ses_44fced3c7ffe83sZpzY1rlQka3","messageID":"msg_bb033866f0011oZxTqvfy0TKtS","type":"step-finish","reason":"stop","snapshot":"904f0fd58c125b79e60f0993e38f9d9f6200bf47","cost":0}}`
+
+	message, threadID := ParseJSONStreamInternal(strings.NewReader(input), nil, nil, nil, nil)
+
+	if threadID != "ses_44fced3c7ffe83sZpzY1rlQka3" {
+		t.Errorf("threadID = %q, want %q", threadID, "ses_44fced3c7ffe83sZpzY1rlQka3")
+	}
+	if message != "Hello from opencode" {
+		t.Errorf("message = %q, want %q", message, "Hello from opencode")
+	}
+}
+
+func TestParseJSONStream_Opencode_MultipleTextEvents(t *testing.T) {
+	input := `{"type":"text","sessionID":"ses_123","part":{"type":"text","text":"Part 1"}}
+{"type":"text","sessionID":"ses_123","part":{"type":"text","text":" Part 2"}}
+{"type":"step_finish","sessionID":"ses_123","part":{"type":"step-finish","reason":"stop"}}`
+
+	message, threadID := ParseJSONStreamInternal(strings.NewReader(input), nil, nil, nil, nil)
+
+	if threadID != "ses_123" {
+		t.Errorf("threadID = %q, want %q", threadID, "ses_123")
+	}
+	if message != "Part 1 Part 2" {
+		t.Errorf("message = %q, want %q", message, "Part 1 Part 2")
+	}
+}
+
+func TestParseJSONStream_Opencode_NoStopReason(t *testing.T) {
+	input := `{"type":"text","sessionID":"ses_456","part":{"type":"text","text":"Content"}}
+{"type":"step_finish","sessionID":"ses_456","part":{"type":"step-finish","reason":"tool-calls"}}`
+
+	message, threadID := ParseJSONStreamInternal(strings.NewReader(input), nil, nil, nil, nil)
+
+	if threadID != "ses_456" {
+		t.Errorf("threadID = %q, want %q", threadID, "ses_456")
+	}
+	if message != "Content" {
+		t.Errorf("message = %q, want %q", message, "Content")
+	}
+}

codeagent-wrapper/internal/parser/parser_token_too_long_test.go

@@ -0,0 +1,31 @@
+package parser
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestParseJSONStream_SkipsOverlongLineAndContinues(t *testing.T) {
+	// Exceed the 10MB bufio.Scanner limit in parseJSONStreamInternal.
+	tooLong := strings.Repeat("a", 11*1024*1024)
+
+	input := strings.Join([]string{
+		`{"type":"item.completed","item":{"type":"other_type","text":"` + tooLong + `"}}`,
+		`{"type":"thread.started","thread_id":"t-1"}`,
+		`{"type":"item.completed","item":{"type":"agent_message","text":"ok"}}`,
+	}, "\n")
+
+	var warns []string
+	warnFn := func(msg string) { warns = append(warns, msg) }
+
+	gotMessage, gotThreadID := ParseJSONStreamInternal(strings.NewReader(input), warnFn, nil, nil, nil)
+	if gotMessage != "ok" {
+		t.Fatalf("message=%q, want %q (warns=%v)", gotMessage, "ok", warns)
+	}
+	if gotThreadID != "t-1" {
+		t.Fatalf("threadID=%q, want %q (warns=%v)", gotThreadID, "t-1", warns)
+	}
+	if len(warns) == 0 || !strings.Contains(warns[0], "Skipped overlong JSON line") {
+		t.Fatalf("expected warning about overlong JSON line, got %v", warns)
+	}
+}

codeagent-wrapper/internal/parser/parser_unknown_event_test.go

@@ -0,0 +1,32 @@
+package parser
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestBackendParseJSONStream_UnknownEventsAreSilent(t *testing.T) {
+	input := strings.Join([]string{
+		`{"type":"turn.started"}`,
+		`{"type":"assistant","text":"hi"}`,
+		`{"type":"user","text":"yo"}`,
+		`{"type":"item.completed","item":{"type":"agent_message","text":"ok"}}`,
+	}, "\n")
+
+	var infos []string
+	infoFn := func(msg string) { infos = append(infos, msg) }
+
+	message, threadID := ParseJSONStreamInternal(strings.NewReader(input), nil, infoFn, nil, nil)
+	if message != "ok" {
+		t.Fatalf("message=%q, want %q (infos=%v)", message, "ok", infos)
+	}
+	if threadID != "" {
+		t.Fatalf("threadID=%q, want empty (infos=%v)", threadID, infos)
+	}
+
+	for _, msg := range infos {
+		if strings.Contains(msg, "Agent event:") {
+			t.Fatalf("unexpected log for unknown event: %q", msg)
+		}
+	}
+}

codeagent-wrapper/internal/parser/truncate_bytes_test.go

@@ -0,0 +1,15 @@
+package parser
+
+import "testing"
+
+func TestTruncateBytes(t *testing.T) {
+	if got := TruncateBytes([]byte("abc"), 3); got != "abc" {
+		t.Fatalf("TruncateBytes() = %q, want %q", got, "abc")
+	}
+	if got := TruncateBytes([]byte("abcd"), 3); got != "abc..." {
+		t.Fatalf("TruncateBytes() = %q, want %q", got, "abc...")
+	}
+	if got := TruncateBytes([]byte("abcd"), -1); got != "" {
+		t.Fatalf("TruncateBytes() = %q, want empty string", got)
+	}
+}

codeagent-wrapper/internal/utils/math.go

@@ -0,0 +1,8 @@
+package utils
+
+func Min(a, b int) int {
+	if a < b {
+		return a
+	}
+	return b
+}

codeagent-wrapper/internal/utils/math_test.go

@@ -0,0 +1,36 @@
+package utils
+
+import "testing"
+
+func TestMin(t *testing.T) {
+	tests := []struct {
+		name string
+		a, b int
+		want int
+	}{
+		{"a less than b", 1, 2, 1},
+		{"b less than a", 5, 3, 3},
+		{"equal values", 7, 7, 7},
+		{"negative a", -5, 3, -5},
+		{"negative b", 5, -3, -3},
+		{"both negative", -5, -3, -5},
+		{"zero and positive", 0, 5, 0},
+		{"zero and negative", 0, -5, -5},
+		{"large values", 1000000, 999999, 999999},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Min(tt.a, tt.b)
+			if got != tt.want {
+				t.Errorf("Min(%d, %d) = %d, want %d", tt.a, tt.b, got, tt.want)
+			}
+		})
+	}
+}
+
+func BenchmarkMin(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		Min(i, i+1)
+	}
+}

codeagent-wrapper/internal/utils/strings.go

@@ -0,0 +1,62 @@
+package utils
+
+import "strings"
+
+func Truncate(s string, maxLen int) string {
+	if len(s) <= maxLen {
+		return s
+	}
+	if maxLen < 0 {
+		return ""
+	}
+	return s[:maxLen] + "..."
+}
+
+// SafeTruncate safely truncates string to maxLen, avoiding panic and UTF-8 corruption.
+func SafeTruncate(s string, maxLen int) string {
+	if maxLen <= 0 || s == "" {
+		return ""
+	}
+
+	runes := []rune(s)
+	if len(runes) <= maxLen {
+		return s
+	}
+
+	if maxLen < 4 {
+		return string(runes[:1])
+	}
+
+	cutoff := maxLen - 3
+	if cutoff <= 0 {
+		return string(runes[:1])
+	}
+	if len(runes) <= cutoff {
+		return s
+	}
+	return string(runes[:cutoff]) + "..."
+}
+
+// SanitizeOutput removes ANSI escape sequences and control characters.
+func SanitizeOutput(s string) string {
+	var result strings.Builder
+	inEscape := false
+	for i := 0; i < len(s); i++ {
+		if s[i] == '\x1b' && i+1 < len(s) && s[i+1] == '[' {
+			inEscape = true
+			i++ // skip '['
+			continue
+		}
+		if inEscape {
+			if (s[i] >= 'A' && s[i] <= 'Z') || (s[i] >= 'a' && s[i] <= 'z') {
+				inEscape = false
+			}
+			continue
+		}
+		// Keep printable chars and common whitespace.
+		if s[i] >= 32 || s[i] == '\n' || s[i] == '\t' {
+			result.WriteByte(s[i])
+		}
+	}
+	return result.String()
+}

codeagent-wrapper/internal/utils/strings_test.go

@@ -0,0 +1,122 @@
+package utils
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestTruncate(t *testing.T) {
+	tests := []struct {
+		name   string
+		s      string
+		maxLen int
+		want   string
+	}{
+		{"empty string", "", 10, ""},
+		{"short string", "hello", 10, "hello"},
+		{"exact length", "hello", 5, "hello"},
+		{"needs truncation", "hello world", 5, "hello..."},
+		{"zero maxLen", "hello", 0, "..."},
+		{"negative maxLen", "hello", -1, ""},
+		{"maxLen 1", "hello", 1, "h..."},
+		{"unicode bytes truncate", "你好世界", 10, "你好世\xe7..."},  // Truncate works on bytes, not runes
+		{"mixed truncate", "hello世界abc", 7, "hello\xe4\xb8..."}, // byte-based truncation
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Truncate(tt.s, tt.maxLen)
+			if got != tt.want {
+				t.Errorf("Truncate(%q, %d) = %q, want %q", tt.s, tt.maxLen, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestSafeTruncate(t *testing.T) {
+	tests := []struct {
+		name   string
+		s      string
+		maxLen int
+		want   string
+	}{
+		{"empty string", "", 10, ""},
+		{"zero maxLen", "hello", 0, ""},
+		{"negative maxLen", "hello", -1, ""},
+		{"short string", "hello", 10, "hello"},
+		{"exact length", "hello", 5, "hello"},
+		{"needs truncation", "hello world", 8, "hello..."},
+		{"maxLen 1", "hello", 1, "h"},
+		{"maxLen 2", "hello", 2, "h"},
+		{"maxLen 3", "hello", 3, "h"},
+		{"maxLen 4", "hello", 4, "h..."},
+		{"unicode preserved", "你好世界", 10, "你好世界"},
+		{"unicode exact", "你好世界", 4, "你好世界"},
+		{"unicode truncate", "你好世界test", 6, "你好世..."},
+		{"mixed unicode", "ab你好cd", 5, "ab..."},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := SafeTruncate(tt.s, tt.maxLen)
+			if got != tt.want {
+				t.Errorf("SafeTruncate(%q, %d) = %q, want %q", tt.s, tt.maxLen, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestSanitizeOutput(t *testing.T) {
+	tests := []struct {
+		name string
+		s    string
+		want string
+	}{
+		{"empty string", "", ""},
+		{"plain text", "hello world", "hello world"},
+		{"with newline", "hello\nworld", "hello\nworld"},
+		{"with tab", "hello\tworld", "hello\tworld"},
+		{"ANSI color red", "\x1b[31mred\x1b[0m", "red"},
+		{"ANSI bold", "\x1b[1mbold\x1b[0m", "bold"},
+		{"ANSI complex", "\x1b[1;31;40mtext\x1b[0m", "text"},
+		{"control chars", "hello\x00\x01\x02world", "helloworld"},
+		{"mixed ANSI and control", "\x1b[32m\x00ok\x1b[0m", "ok"},
+		{"multiple ANSI sequences", "\x1b[31mred\x1b[0m \x1b[32mgreen\x1b[0m", "red green"},
+		{"incomplete escape", "\x1b[", ""},
+		{"escape without bracket", "\x1bA", "A"},
+		{"cursor movement", "\x1b[2Aup\x1b[2Bdown", "updown"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := SanitizeOutput(tt.s)
+			if got != tt.want {
+				t.Errorf("SanitizeOutput(%q) = %q, want %q", tt.s, got, tt.want)
+			}
+		})
+	}
+}
+
+func BenchmarkTruncate(b *testing.B) {
+	s := strings.Repeat("hello world ", 100)
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		Truncate(s, 50)
+	}
+}
+
+func BenchmarkSafeTruncate(b *testing.B) {
+	s := strings.Repeat("你好世界", 100)
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		SafeTruncate(s, 50)
+	}
+}
+
+func BenchmarkSanitizeOutput(b *testing.B) {
+	s := strings.Repeat("\x1b[31mred\x1b[0m text ", 50)
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		SanitizeOutput(s)
+	}
+}