chore: bump version to v5.2.7

Changes in v5.2.7:
- Security fix: pass env vars via process environment instead of command line
- Prevents ANTHROPIC_API_KEY leakage in ps/logs
- Add SetEnv() interface to commandRunner
- Type-safe env parsing with 1MB file size limit
- Comprehensive test coverage for loadMinimalEnvSettings()

Related: #89, PR #92

Generated with SWE-Agent.ai

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

.gitattributes

@@ -0,0 +1,22 @@
+# Ensure shell scripts always use LF line endings on all platforms
+*.sh text eol=lf
+
+# Ensure Python files use LF line endings
+*.py text eol=lf
+
+# Auto-detect text files and normalize line endings to LF
+* text=auto eol=lf
+
+# Explicitly declare files that should always be treated as binary
+*.exe binary
+*.png binary
+*.jpg binary
+*.jpeg binary
+*.gif binary
+*.ico binary
+*.mov binary
+*.mp4 binary
+*.mp3 binary
+*.zip binary
+*.gz binary
+*.tar binary

README.md

@@ -7,7 +7,7 @@
 
 [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)
 [![Claude Code](https://img.shields.io/badge/Claude-Code-blue)](https://claude.ai/code)
-[![Version](https://img.shields.io/badge/Version-5.2.2-green)](https://github.com/cexll/myclaude)
+[![Version](https://img.shields.io/badge/Version-5.2-green)](https://github.com/cexll/myclaude)
 
 > AI-powered development automation with multi-backend execution (Codex/Claude/Gemini)
 
@@ -132,6 +132,59 @@ Requirements → Architecture → Sprint Plan → Development → Review → QA
 
 ---
 
+## Version Requirements
+
+### Codex CLI
+**Minimum version:** Check compatibility with your installation
+
+The codeagent-wrapper uses these Codex CLI features:
+- `codex e` - Execute commands (shorthand for `codex exec`)
+- `--skip-git-repo-check` - Skip git repository validation
+- `--json` - JSON stream output format
+- `-C <workdir>` - Set working directory
+- `resume <session_id>` - Resume previous sessions
+
+**Verify Codex CLI is installed:**
+```bash
+which codex
+codex --version
+```
+
+### Claude CLI
+**Minimum version:** Check compatibility with your installation
+
+Required features:
+- `--output-format stream-json` - Streaming JSON output format
+- `--setting-sources` - Control setting sources (prevents infinite recursion)
+- `--dangerously-skip-permissions` - Skip permission prompts (use with caution)
+- `-p` - Prompt input flag
+- `-r <session_id>` - Resume sessions
+
+**Security Note:** The wrapper only adds `--dangerously-skip-permissions` for Claude when explicitly enabled (e.g. `--skip-permissions` / `CODEAGENT_SKIP_PERMISSIONS=true`). Keep it disabled unless you understand the risk.
+
+**Verify Claude CLI is installed:**
+```bash
+which claude
+claude --version
+```
+
+### Gemini CLI
+**Minimum version:** Check compatibility with your installation
+
+Required features:
+- `-o stream-json` - JSON stream output format
+- `-y` - Auto-approve prompts (non-interactive mode)
+- `-r <session_id>` - Resume sessions
+- `-p` - Prompt input flag
+
+**Verify Gemini CLI is installed:**
+```bash
+which gemini
+gemini --version
+```
+
+---
+
 ## Installation
 
 ### Modular Installation (Recommended)
@@ -163,15 +216,39 @@ python3 install.py --force
 
 ```
 ~/.claude/
-├── CLAUDE.md              # Core instructions and role definition
+├── bin/
-├── commands/              # Slash commands (/dev, /code, etc.)
+│   └── codeagent-wrapper    # Main executable
-├── agents/                # Agent definitions
+├── CLAUDE.md                # Core instructions and role definition
+├── commands/                # Slash commands (/dev, /code, etc.)
+├── agents/                  # Agent definitions
 ├── skills/
 │   └── codex/
-│       └── SKILL.md       # Codex integration skill
+│       └── SKILL.md         # Codex integration skill
-└── installed_modules.json # Installation status
+├── config.json              # Configuration
+└── installed_modules.json   # Installation status
 ```
 
+### Customizing Installation Directory
+
+By default, myclaude installs to `~/.claude`. You can customize this using the `INSTALL_DIR` environment variable:
+
+```bash
+# Install to custom directory
+INSTALL_DIR=/opt/myclaude bash install.sh
+
+# Update your PATH accordingly
+export PATH="/opt/myclaude/bin:$PATH"
+```
+
+**Directory Structure:**
+- `$INSTALL_DIR/bin/` - codeagent-wrapper binary
+- `$INSTALL_DIR/skills/` - Skill definitions
+- `$INSTALL_DIR/config.json` - Configuration file
+- `$INSTALL_DIR/commands/` - Slash command definitions
+- `$INSTALL_DIR/agents/` - Agent definitions
+
+**Note:** When using a custom installation directory, ensure that `$INSTALL_DIR/bin` is added to your `PATH` environment variable.
+
 ### Configuration
 
 Edit `config.json` to customize:
@@ -295,7 +372,7 @@ setx PATH "%USERPROFILE%\bin;%PATH%"
 **Codex wrapper not found:**
 ```bash
 # Check PATH
-echo $PATH | grep -q "$HOME/bin" || echo 'export PATH="$HOME/bin:$PATH"' >> ~/.zshrc
+echo $PATH | grep -q "$HOME/.claude/bin" || echo 'export PATH="$HOME/.claude/bin:$PATH"' >> ~/.zshrc
 
 # Reinstall
 bash install.sh
@@ -315,6 +392,71 @@ cat ~/.claude/installed_modules.json
 python3 install.py --module dev --force
 ```
 
+### Version Compatibility Issues
+
+**Backend CLI not found:**
+```bash
+# Check if backend CLIs are installed
+which codex
+which claude
+which gemini
+
+# Install missing backends
+# Codex: Follow installation instructions at https://codex.docs
+# Claude: Follow installation instructions at https://claude.ai/docs
+# Gemini: Follow installation instructions at https://ai.google.dev/docs
+```
+
+**Unsupported CLI flags:**
+```bash
+# If you see errors like "unknown flag" or "invalid option"
+
+# Check backend CLI version
+codex --version
+claude --version
+gemini --version
+
+# For Codex: Ensure it supports `e`, `--skip-git-repo-check`, `--json`, `-C`, and `resume`
+# For Claude: Ensure it supports `--output-format stream-json`, `--setting-sources`, `-r`
+# For Gemini: Ensure it supports `-o stream-json`, `-y`, `-r`, `-p`
+
+# Update your backend CLI to the latest version if needed
+```
+
+**JSON parsing errors:**
+```bash
+# If you see "failed to parse JSON output" errors
+
+# Verify the backend outputs stream-json format
+codex e --json "test task"  # Should output newline-delimited JSON
+claude --output-format stream-json -p "test"  # Should output stream JSON
+
+# If not, your backend CLI version may be too old or incompatible
+```
+
+**Infinite recursion with Claude backend:**
+```bash
+# The wrapper prevents this with `--setting-sources ""` flag
+# If you still see recursion, ensure your Claude CLI supports this flag
+
+claude --help | grep "setting-sources"
+
+# If flag is not supported, upgrade Claude CLI
+```
+
+**Session resume failures:**
+```bash
+# Check if session ID is valid
+codex history  # List recent sessions
+claude history
+
+# Ensure backend CLI supports session resumption
+codex resume <session_id> "test"  # Should continue from previous session
+claude -r <session_id> "test"
+
+# If not supported, use new sessions instead of resume mode
+```
+
 ---
 
 ## Documentation

README_CN.md

@@ -2,7 +2,7 @@
 
 [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)
 [![Claude Code](https://img.shields.io/badge/Claude-Code-blue)](https://claude.ai/code)
-[![Version](https://img.shields.io/badge/Version-5.2.2-green)](https://github.com/cexll/myclaude)
+[![Version](https://img.shields.io/badge/Version-5.2-green)](https://github.com/cexll/myclaude)
 
 > AI 驱动的开发自动化 - 多后端执行架构 (Codex/Claude/Gemini)
 
@@ -152,15 +152,39 @@ python3 install.py --force
 
 ```
 ~/.claude/
-├── CLAUDE.md              # 核心指令和角色定义
+├── bin/
-├── commands/              # 斜杠命令 (/dev, /code 等)
+│   └── codeagent-wrapper    # 主可执行文件
-├── agents/                # 智能体定义
+├── CLAUDE.md                # 核心指令和角色定义
+├── commands/                # 斜杠命令 (/dev, /code 等)
+├── agents/                  # 智能体定义
 ├── skills/
 │   └── codex/
-│       └── SKILL.md       # Codex 集成技能
+│       └── SKILL.md         # Codex 集成技能
-└── installed_modules.json # 安装状态
+├── config.json              # 配置文件
+└── installed_modules.json   # 安装状态
 ```
 
+### 自定义安装目录
+
+默认情况下，myclaude 安装到 `~/.claude`。您可以使用 `INSTALL_DIR` 环境变量自定义安装目录：
+
+```bash
+# 安装到自定义目录
+INSTALL_DIR=/opt/myclaude bash install.sh
+
+# 相应更新您的 PATH
+export PATH="/opt/myclaude/bin:$PATH"
+```
+
+**目录结构：**
+- `$INSTALL_DIR/bin/` - codeagent-wrapper 可执行文件
+- `$INSTALL_DIR/skills/` - 技能定义
+- `$INSTALL_DIR/config.json` - 配置文件
+- `$INSTALL_DIR/commands/` - 斜杠命令定义
+- `$INSTALL_DIR/agents/` - 智能体定义
+
+**注意：** 使用自定义安装目录时，请确保将 `$INSTALL_DIR/bin` 添加到您的 `PATH` 环境变量中。
+
 ### 配置
 
 编辑 `config.json` 自定义：
@@ -284,7 +308,7 @@ setx PATH "%USERPROFILE%\bin;%PATH%"
 **Codex wrapper 未找到：**
 ```bash
 # 检查 PATH
-echo $PATH | grep -q "$HOME/bin" || echo 'export PATH="$HOME/bin:$PATH"' >> ~/.zshrc
+echo $PATH | grep -q "$HOME/.claude/bin" || echo 'export PATH="$HOME/.claude/bin:$PATH"' >> ~/.zshrc
 
 # 重新安装
 bash install.sh

bmad-agile-workflow/agents/bmad-architect.md

@@ -427,6 +427,10 @@ Generate architecture document at `./.claude/specs/{feature_name}/02-system-arch
 
 ## Important Behaviors
 
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, REST, GraphQL, JWT, RBAC, etc.) in English; translate explanatory text only.
+
 ### DO:
 - Start by reviewing and referencing the PRD
 - Present initial architecture based on requirements

bmad-agile-workflow/agents/bmad-dev.md

@@ -419,6 +419,10 @@ logger.info('User created', {
 
 ## Important Implementation Rules
 
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, CRUD, JWT, SQL, etc.) in English; translate explanatory text only.
+
 ### DO:
 - Follow architecture specifications exactly
 - Implement all acceptance criteria from PRD

bmad-agile-workflow/agents/bmad-orchestrator.md

@@ -22,6 +22,10 @@ You are the BMAD Orchestrator. Your core focus is repository analysis, workflow
 - Consistency: ensure conventions and patterns discovered in scan are preserved downstream
 - Explicit handoffs: clearly document assumptions, risks, and integration points for other agents
 
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, PRD, Sprint, etc.) in English; translate explanatory text only.
+
 ## UltraThink Repository Scan
 
 When asked to analyze the repository, follow this structure and return a clear, actionable summary.

bmad-agile-workflow/agents/bmad-po.md

@@ -313,6 +313,10 @@ Generate PRD at `./.claude/specs/{feature_name}/01-product-requirements.md`:
 
 ## Important Behaviors
 
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, Sprint, PRD, KPI, MVP, etc.) in English; translate explanatory text only.
+
 ### DO:
 - Start immediately with greeting and initial understanding
 - Show quality scores transparently

bmad-agile-workflow/agents/bmad-qa.md

@@ -478,6 +478,10 @@ module.exports = {
 
 ## Important Testing Rules
 
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, E2E, CI/CD, Mock, etc.) in English; translate explanatory text only.
+
 ### DO:
 - Test all acceptance criteria from PRD
 - Cover happy path, edge cases, and error scenarios

bmad-agile-workflow/agents/bmad-review.md

@@ -45,3 +45,7 @@ You are an independent code review agent responsible for conducting reviews betw
 - Focus on actionable findings
 - Provide specific QA guidance
 - Use clear, parseable output format
+
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, PRD, Sprint, etc.) in English; translate explanatory text only.

bmad-agile-workflow/agents/bmad-sm.md

@@ -351,6 +351,10 @@ So that [benefit]
 
 ## Important Behaviors
 
+### Language Rules:
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (Sprint, Epic, Story, Backlog, Velocity, etc.) in English; translate explanatory text only.
+
 ### DO:
 - Read both PRD and Architecture documents thoroughly
 - Create comprehensive task breakdown

codeagent-wrapper/backend.go

@@ -1,5 +1,11 @@
 package main
 
+import (
+	"encoding/json"
+	"os"
+	"path/filepath"
+)
+
 // 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.
@@ -26,15 +32,62 @@ func (ClaudeBackend) Command() string {
 	return "claude"
 }
 func (ClaudeBackend) BuildArgs(cfg *Config, targetArg string) []string {
+	return buildClaudeArgs(cfg, targetArg)
+}
+
+const maxClaudeSettingsBytes = 1 << 20 // 1MB
+
+// loadMinimalEnvSettings 从 ~/.claude/setting.json 只提取 env 配置。
+// 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 loadMinimalEnvSettings() map[string]string {
+	home, err := os.UserHomeDir()
+	if err != nil || home == "" {
+		return nil
+	}
+
+	settingPath := filepath.Join(home, ".claude", "setting.json")
+	info, err := os.Stat(settingPath)
+	if err != nil || info.Size() > maxClaudeSettingsBytes {
+		return nil
+	}
+
+	data, err := os.ReadFile(settingPath)
+	if err != nil {
+		return nil
+	}
+
+	var cfg struct {
+		Env map[string]any `json:"env"`
+	}
+	if err := json.Unmarshal(data, &cfg); err != nil {
+		return nil
+	}
+	if len(cfg.Env) == 0 {
+		return nil
+	}
+
+	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 nil
+	}
+	return env
+}
+
+func buildClaudeArgs(cfg *Config, targetArg string) []string {
 	if cfg == nil {
 		return nil
 	}
-	args := []string{"-p", "--dangerously-skip-permissions"}
+	args := []string{"-p"}
-
+	if cfg.SkipPermissions {
-	// Only skip permissions when explicitly requested
+		args = append(args, "--dangerously-skip-permissions")
-	// if cfg.SkipPermissions {
+	}
-	// 	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
@@ -60,6 +113,10 @@ func (GeminiBackend) Command() string {
 	return "gemini"
 }
 func (GeminiBackend) BuildArgs(cfg *Config, targetArg string) []string {
+	return buildGeminiArgs(cfg, targetArg)
+}
+
+func buildGeminiArgs(cfg *Config, targetArg string) []string {
 	if cfg == nil {
 		return nil
 	}

codeagent-wrapper/backend_test.go

@@ -1,6 +1,9 @@
 package main
 
 import (
+	"bytes"
+	"os"
+	"path/filepath"
 	"reflect"
 	"testing"
 )
@@ -8,16 +11,16 @@ import (
 func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 	backend := ClaudeBackend{}
 
-	t.Run("new mode uses workdir without skip by default", func(t *testing.T) {
+	t.Run("new mode omits skip-permissions by default", func(t *testing.T) {
 		cfg := &Config{Mode: "new", WorkDir: "/repo"}
 		got := backend.BuildArgs(cfg, "todo")
-		want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "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 opt-in skip permissions with default workdir", func(t *testing.T) {
+	t.Run("new mode can opt-in skip-permissions", func(t *testing.T) {
 		cfg := &Config{Mode: "new", SkipPermissions: true}
 		got := backend.BuildArgs(cfg, "-")
 		want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "-"}
@@ -26,10 +29,10 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 		}
 	})
 
-	t.Run("resume mode uses session id and omits workdir", func(t *testing.T) {
+	t.Run("resume mode includes session id", func(t *testing.T) {
 		cfg := &Config{Mode: "resume", SessionID: "sid-123", WorkDir: "/ignored"}
 		got := backend.BuildArgs(cfg, "resume-task")
-		want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "-r", "sid-123", "--output-format", "stream-json", "--verbose", "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)
 		}
@@ -38,7 +41,16 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 	t.Run("resume mode without session still returns base flags", func(t *testing.T) {
 		cfg := &Config{Mode: "resume", WorkDir: "/ignored"}
 		got := backend.BuildArgs(cfg, "follow-up")
-		want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "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{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)
 		}
@@ -89,7 +101,11 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 		}
 	})
 
-	t.Run("codex build args passthrough remains intact", func(t *testing.T) {
+	t.Run("codex build args omits bypass flag by default", func(t *testing.T) {
+		const key = "CODEX_BYPASS_SANDBOX"
+		t.Cleanup(func() { os.Unsetenv(key) })
+		os.Unsetenv(key)
+
 		backend := CodexBackend{}
 		cfg := &Config{Mode: "new", WorkDir: "/tmp"}
 		got := backend.BuildArgs(cfg, "task")
@@ -98,6 +114,20 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 			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.Cleanup(func() { os.Unsetenv(key) })
+		os.Setenv(key, "true")
+
+		backend := CodexBackend{}
+		cfg := &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) {
@@ -120,3 +150,64 @@ func TestClaudeBuildArgs_BackendMetadata(t *testing.T) {
 		}
 	}
 }
+
+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, "setting.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, "setting.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, "setting.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)
+		}
+	})
+}

codeagent-wrapper/concurrent_stress_test.go

@@ -13,6 +13,16 @@ import (
 	"time"
 )
 
+func stripTimestampPrefix(line string) string {
+	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() {
@@ -79,7 +89,8 @@ func TestConcurrentStressLogger(t *testing.T) {
 	// 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))] {
-		if !formatRE.MatchString(line) {
+		msg := stripTimestampPrefix(line)
+		if !formatRE.MatchString(msg) {
 			t.Errorf("line %d has invalid format: %s", i, line)
 		}
 	}
@@ -291,7 +302,7 @@ func TestLoggerOrderPreservation(t *testing.T) {
 	sequences := make(map[int][]int) // goroutine ID -> sequence numbers
 
 	for scanner.Scan() {
-		line := scanner.Text()
+		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)

codeagent-wrapper/config.go

@@ -164,6 +164,9 @@ func parseParallelConfig(data []byte) (*ParallelConfig, error) {
 		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)
 		}
@@ -232,7 +235,10 @@ func parseArgs() (*Config, error) {
 			return nil, fmt.Errorf("resume mode requires: resume <session_id> <task>")
 		}
 		cfg.Mode = "resume"
-		cfg.SessionID = args[1]
+		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 {

codeagent-wrapper/executor.go

@@ -16,6 +16,8 @@ import (
 	"time"
 )
 
+const postMessageTerminateDelay = 1 * time.Second
+
 // commandRunner abstracts exec.Cmd for testability
 type commandRunner interface {
 	Start() error
@@ -24,6 +26,7 @@ type commandRunner interface {
 	StdinPipe() (io.WriteCloser, error)
 	SetStderr(io.Writer)
 	SetDir(string)
+	SetEnv(env map[string]string)
 	Process() processHandle
 }
 
@@ -79,6 +82,52 @@ func (r *realCmd) SetDir(dir string) {
 	}
 }
 
+func (r *realCmd) SetEnv(env map[string]string) {
+	if r == nil || r.cmd == nil || len(env) == 0 {
+		return
+	}
+
+	merged := make(map[string]string, len(env)+len(os.Environ()))
+	for _, kv := range os.Environ() {
+		if kv == "" {
+			continue
+		}
+		idx := strings.IndexByte(kv, '=')
+		if idx <= 0 {
+			continue
+		}
+		merged[kv[:idx]] = kv[idx+1:]
+	}
+	for _, kv := range r.cmd.Env {
+		if kv == "" {
+			continue
+		}
+		idx := strings.IndexByte(kv, '=')
+		if idx <= 0 {
+			continue
+		}
+		merged[kv[:idx]] = kv[idx+1:]
+	}
+	for k, v := range env {
+		if strings.TrimSpace(k) == "" {
+			continue
+		}
+		merged[k] = v
+	}
+
+	keys := make([]string, 0, len(merged))
+	for k := range merged {
+		keys = append(keys, k)
+	}
+	sort.Strings(keys)
+
+	out := make([]string, 0, len(keys))
+	for _, k := range keys {
+		out = append(out, k+"="+merged[k])
+	}
+	r.cmd.Env = out
+}
+
 func (r *realCmd) Process() processHandle {
 	if r == nil || r.cmd == nil || r.cmd.Process == nil {
 		return nil
@@ -507,23 +556,43 @@ func generateFinalOutput(results []TaskResult) string {
 }
 
 func buildCodexArgs(cfg *Config, targetArg string) []string {
-	if cfg.Mode == "resume" {
+	if cfg == nil {
-		return []string{
+		panic("buildCodexArgs: nil config")
-			"e",
+	}
-			"--skip-git-repo-check",
+
-			"--json",
+	var resumeSessionID string
-			"resume",
+	isResume := cfg.Mode == "resume"
-			cfg.SessionID,
+	if isResume {
-			targetArg,
+		resumeSessionID = strings.TrimSpace(cfg.SessionID)
+		if resumeSessionID == "" {
+			logError("invalid config: resume mode requires non-empty session_id")
+			isResume = false
 		}
 	}
-	return []string{
+
-		"e",
+	args := []string{"e"}
-		"--skip-git-repo-check",
+
+	if envFlagEnabled("CODEX_BYPASS_SANDBOX") {
+		logWarn("CODEX_BYPASS_SANDBOX=true: running without approval/sandbox protection")
+		args = append(args, "--dangerously-bypass-approvals-and-sandbox")
+	}
+
+	args = append(args, "--skip-git-repo-check")
+
+	if isResume {
+		return append(args,
+			"--json",
+			"resume",
+			resumeSessionID,
+			targetArg,
+		)
+	}
+
+	return append(args,
 		"-C", cfg.WorkDir,
 		"--json",
 		targetArg,
-	}
+	)
 }
 
 func runCodexTask(taskSpec TaskSpec, silent bool, timeoutSec int) TaskResult {
@@ -574,6 +643,12 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 		cfg.WorkDir = defaultWorkdir
 	}
 
+	if cfg.Mode == "resume" && strings.TrimSpace(cfg.SessionID) == "" {
+		result.ExitCode = 1
+		result.Error = "resume mode requires non-empty session_id"
+		return result
+	}
+
 	useStdin := taskSpec.UseStdin
 	targetArg := taskSpec.Task
 	if useStdin {
@@ -673,6 +748,12 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 
 	cmd := newCommandRunner(ctx, commandName, codexArgs...)
 
+	if cfg.Backend == "claude" {
+		if env := loadMinimalEnvSettings(); len(env) > 0 {
+			cmd.SetEnv(env)
+		}
+	}
+
 	// For backends that don't support -C flag (claude, gemini), set working directory via cmd.Dir
 	// Codex passes workdir via -C flag, so we skip setting Dir for it to avoid conflicts
 	if cfg.Mode != "resume" && commandName != "codex" && cfg.WorkDir != "" {
@@ -683,8 +764,17 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 	if stderrLogger != nil {
 		stderrWriters = append(stderrWriters, stderrLogger)
 	}
+
+	// For gemini backend, filter noisy stderr output
+	var stderrFilter *filteringWriter
 	if !silent {
-		stderrWriters = append([]io.Writer{os.Stderr}, stderrWriters...)
+		stderrOut := io.Writer(os.Stderr)
+		if cfg.Backend == "gemini" {
+			stderrFilter = newFilteringWriter(os.Stderr, geminiNoisePatterns)
+			stderrOut = stderrFilter
+			defer stderrFilter.Flush()
+		}
+		stderrWriters = append([]io.Writer{stderrOut}, stderrWriters...)
 	}
 	if len(stderrWriters) == 1 {
 		cmd.SetStderr(stderrWriters[0])
@@ -720,6 +810,7 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 	// Start parse goroutine BEFORE starting the command to avoid race condition
 	// where fast-completing commands close stdout before parser starts reading
 	messageSeen := make(chan struct{}, 1)
+	completeSeen := make(chan struct{}, 1)
 	parseCh := make(chan parseResult, 1)
 	go func() {
 		msg, tid := parseJSONStreamInternal(stdoutReader, logWarnFn, logInfoFn, func() {
@@ -727,7 +818,16 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 			case messageSeen <- struct{}{}:
 			default:
 			}
+		}, func() {
+			select {
+			case completeSeen <- struct{}{}:
+			default:
+			}
 		})
+		select {
+		case completeSeen <- struct{}{}:
+		default:
+		}
 		parseCh <- parseResult{message: msg, threadID: tid}
 	}()
 
@@ -764,17 +864,63 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 	waitCh := make(chan error, 1)
 	go func() { waitCh <- cmd.Wait() }()
 
-	var waitErr error
+	var (
-	var forceKillTimer *forceKillTimer
+		waitErr              error
-	var ctxCancelled bool
+		forceKillTimer       *forceKillTimer
+		ctxCancelled         bool
+		messageTimer         *time.Timer
+		messageTimerCh       <-chan time.Time
+		forcedAfterComplete  bool
+		terminated           bool
+		messageSeenObserved  bool
+		completeSeenObserved bool
+	)
 
-	select {
+waitLoop:
-	case waitErr = <-waitCh:
+	for {
-	case <-ctx.Done():
+		select {
-		ctxCancelled = true
+		case waitErr = <-waitCh:
-		logErrorFn(cancelReason(commandName, ctx))
+			break waitLoop
-		forceKillTimer = terminateCommandFn(cmd)
+		case <-ctx.Done():
-		waitErr = <-waitCh
+			ctxCancelled = true
+			logErrorFn(cancelReason(commandName, ctx))
+			if !terminated {
+				if timer := terminateCommandFn(cmd); timer != nil {
+					forceKillTimer = timer
+					terminated = true
+				}
+			}
+			waitErr = <-waitCh
+			break waitLoop
+		case <-messageTimerCh:
+			forcedAfterComplete = true
+			messageTimerCh = nil
+			if !terminated {
+				logWarnFn(fmt.Sprintf("%s output parsed; terminating lingering backend", commandName))
+				if timer := terminateCommandFn(cmd); timer != nil {
+					forceKillTimer = timer
+					terminated = true
+				}
+			}
+		case <-completeSeen:
+			completeSeenObserved = true
+			if messageTimer != nil {
+				continue
+			}
+			messageTimer = time.NewTimer(postMessageTerminateDelay)
+			messageTimerCh = messageTimer.C
+		case <-messageSeen:
+			messageSeenObserved = true
+		}
+	}
+
+	if messageTimer != nil {
+		if !messageTimer.Stop() {
+			select {
+			case <-messageTimer.C:
+			default:
+			}
+		}
 	}
 
 	if forceKillTimer != nil {
@@ -782,10 +928,14 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 	}
 
 	var parsed parseResult
-	if ctxCancelled {
+	switch {
+	case ctxCancelled:
 		closeWithReason(stdout, stdoutCloseReasonCtx)
 		parsed = <-parseCh
-	} else {
+	case messageSeenObserved || completeSeenObserved:
+		closeWithReason(stdout, stdoutCloseReasonWait)
+		parsed = <-parseCh
+	default:
 		drainTimer := time.NewTimer(stdoutDrainTimeout)
 		defer drainTimer.Stop()
 
@@ -793,6 +943,11 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 		case parsed = <-parseCh:
 			closeWithReason(stdout, stdoutCloseReasonWait)
 		case <-messageSeen:
+			messageSeenObserved = true
+			closeWithReason(stdout, stdoutCloseReasonWait)
+			parsed = <-parseCh
+		case <-completeSeen:
+			completeSeenObserved = true
 			closeWithReason(stdout, stdoutCloseReasonWait)
 			parsed = <-parseCh
 		case <-drainTimer.C:
@@ -813,17 +968,21 @@ func runCodexTaskWithContext(parentCtx context.Context, taskSpec TaskSpec, backe
 	}
 
 	if waitErr != nil {
-		if exitErr, ok := waitErr.(*exec.ExitError); ok {
+		if forcedAfterComplete && parsed.message != "" {
-			code := exitErr.ExitCode()
+			logWarnFn(fmt.Sprintf("%s terminated after delivering output", commandName))
-			logErrorFn(fmt.Sprintf("%s exited with status %d", commandName, code))
+		} else {
-			result.ExitCode = code
+			if exitErr, ok := waitErr.(*exec.ExitError); ok {
-			result.Error = attachStderr(fmt.Sprintf("%s exited with status %d", commandName, code))
+				code := exitErr.ExitCode()
+				logErrorFn(fmt.Sprintf("%s exited with status %d", commandName, code))
+				result.ExitCode = code
+				result.Error = attachStderr(fmt.Sprintf("%s exited with status %d", commandName, code))
+				return result
+			}
+			logErrorFn(commandName + " error: " + waitErr.Error())
+			result.ExitCode = 1
+			result.Error = attachStderr(commandName + " error: " + waitErr.Error())
 			return result
 		}
-		logErrorFn(commandName + " error: " + waitErr.Error())
-		result.ExitCode = 1
-		result.Error = attachStderr(commandName + " error: " + waitErr.Error())
-		return result
 	}
 
 	message := parsed.message

codeagent-wrapper/executor_concurrent_test.go

@@ -10,6 +10,7 @@ import (
 	"os"
 	"os/exec"
 	"path/filepath"
+	"slices"
 	"strings"
 	"sync"
 	"sync/atomic"
@@ -86,6 +87,7 @@ type execFakeRunner struct {
 	process         processHandle
 	stdin           io.WriteCloser
 	dir             string
+	env             map[string]string
 	waitErr         error
 	waitDelay       time.Duration
 	startErr        error
@@ -128,6 +130,17 @@ func (f *execFakeRunner) StdinPipe() (io.WriteCloser, error) {
 }
 func (f *execFakeRunner) SetStderr(io.Writer) {}
 func (f *execFakeRunner) SetDir(dir string)   { f.dir = dir }
+func (f *execFakeRunner) SetEnv(env map[string]string) {
+	if len(env) == 0 {
+		return
+	}
+	if f.env == nil {
+		f.env = make(map[string]string, len(env))
+	}
+	for k, v := range env {
+		f.env[k] = v
+	}
+}
 func (f *execFakeRunner) Process() processHandle {
 	if f.process != nil {
 		return f.process
@@ -244,6 +257,10 @@ func TestExecutorHelperCoverage(t *testing.T) {
 	})
 
 	t.Run("generateFinalOutputAndArgs", func(t *testing.T) {
+		const key = "CODEX_BYPASS_SANDBOX"
+		t.Cleanup(func() { os.Unsetenv(key) })
+		os.Unsetenv(key)
+
 		out := generateFinalOutput([]TaskResult{
 			{TaskID: "ok", ExitCode: 0},
 			{TaskID: "fail", ExitCode: 1, Error: "boom"},
@@ -257,11 +274,11 @@ func TestExecutorHelperCoverage(t *testing.T) {
 		}
 
 		args := buildCodexArgs(&Config{Mode: "new", WorkDir: "/tmp"}, "task")
-		if len(args) == 0 || args[3] != "/tmp" {
+		if !slices.Equal(args, []string{"e", "--skip-git-repo-check", "-C", "/tmp", "--json", "task"}) {
 			t.Fatalf("unexpected codex args: %+v", args)
 		}
 		args = buildCodexArgs(&Config{Mode: "resume", SessionID: "sess"}, "target")
-		if args[3] != "resume" || args[4] != "sess" {
+		if !slices.Equal(args, []string{"e", "--skip-git-repo-check", "--json", "resume", "sess", "target"}) {
 			t.Fatalf("unexpected resume args: %+v", args)
 		}
 	})
@@ -298,6 +315,18 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	origRunner := newCommandRunner
 	defer func() { newCommandRunner = origRunner }()
 
+	t.Run("resumeMissingSessionID", func(t *testing.T) {
+		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+			t.Fatalf("unexpected command execution for invalid resume config")
+			return nil
+		}
+
+		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: ".", Mode: "resume"}, nil, nil, false, false, 1)
+		if res.ExitCode == 0 || !strings.Contains(res.Error, "session_id") {
+			t.Fatalf("expected validation error, got %+v", res)
+		}
+	})
+
 	t.Run("success", func(t *testing.T) {
 		var firstStdout *reasonReadCloser
 		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {

codeagent-wrapper/filter.go

@@ -0,0 +1,66 @@
+package main
+
+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",
+}
+
+// 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/filter_test.go

@@ -0,0 +1,73 @@
+package main
+
+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/logger.go

@@ -366,7 +366,8 @@ func (l *Logger) run() {
 	defer ticker.Stop()
 
 	writeEntry := func(entry logEntry) {
-		fmt.Fprintf(l.writer, "%s\n", entry.msg)
+		timestamp := time.Now().Format("2006-01-02 15:04:05.000")
+		fmt.Fprintf(l.writer, "[%s] %s\n", timestamp, entry.msg)
 
 		// Cache error/warn entries in memory for fast extraction
 		if entry.isError {

codeagent-wrapper/main.go

@@ -14,9 +14,9 @@ import (
 )
 
 const (
-	version             = "5.2.5"
+	version             = "5.2.7"
 	defaultWorkdir      = "."
-	defaultTimeout      = 7200 // seconds
+	defaultTimeout      = 7200 // seconds (2 hours)
 	codexLogLineLimit   = 1000
 	stdinSpecialChars   = "\n\\\"'`$"
 	stderrCaptureLimit  = 4 * 1024

codeagent-wrapper/main_test.go

@@ -255,6 +255,10 @@ func (d *drainBlockingCmd) SetDir(dir string) {
 	d.inner.SetDir(dir)
 }
 
+func (d *drainBlockingCmd) SetEnv(env map[string]string) {
+	d.inner.SetEnv(env)
+}
+
 func (d *drainBlockingCmd) Process() processHandle {
 	return d.inner.Process()
 }
@@ -387,6 +391,8 @@ type fakeCmd struct {
 
 	stderr io.Writer
 
+	env map[string]string
+
 	waitDelay time.Duration
 	waitErr   error
 	startErr  error
@@ -511,6 +517,20 @@ func (f *fakeCmd) SetStderr(w io.Writer) {
 
 func (f *fakeCmd) SetDir(string) {}
 
+func (f *fakeCmd) SetEnv(env map[string]string) {
+	if len(env) == 0 {
+		return
+	}
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	if f.env == nil {
+		f.env = make(map[string]string, len(env))
+	}
+	for k, v := range env {
+		f.env[k] = v
+	}
+}
+
 func (f *fakeCmd) Process() processHandle {
 	if f == nil {
 		return nil
@@ -879,6 +899,79 @@ func TestRunCodexTask_ContextTimeout(t *testing.T) {
 	}
 }
 
+func TestRunCodexTask_ForcesStopAfterCompletion(t *testing.T) {
+	defer resetTestHooks()
+	forceKillDelay.Store(0)
+
+	fake := newFakeCmd(fakeCmdConfig{
+		StdoutPlan: []fakeStdoutEvent{
+			{Data: `{"type":"item.completed","item":{"type":"agent_message","text":"done"}}` + "\n"},
+			{Data: `{"type":"thread.completed","thread_id":"tid"}` + "\n"},
+		},
+		KeepStdoutOpen:      true,
+		BlockWait:           true,
+		ReleaseWaitOnSignal: true,
+		ReleaseWaitOnKill:   true,
+	})
+
+	newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		return fake
+	}
+	buildCodexArgsFn = func(cfg *Config, targetArg string) []string { return []string{targetArg} }
+	codexCommand = "fake-cmd"
+
+	start := time.Now()
+	result := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "done", WorkDir: defaultWorkdir}, nil, nil, false, false, 60)
+	duration := time.Since(start)
+
+	if result.ExitCode != 0 || result.Message != "done" {
+		t.Fatalf("unexpected result: %+v", result)
+	}
+	if duration > 2*time.Second {
+		t.Fatalf("runCodexTaskWithContext took too long: %v", duration)
+	}
+	if fake.process.SignalCount() == 0 {
+		t.Fatalf("expected SIGTERM to be sent, got %d", fake.process.SignalCount())
+	}
+}
+
+func TestRunCodexTask_DoesNotTerminateBeforeThreadCompleted(t *testing.T) {
+	defer resetTestHooks()
+	forceKillDelay.Store(0)
+
+	fake := newFakeCmd(fakeCmdConfig{
+		StdoutPlan: []fakeStdoutEvent{
+			{Data: `{"type":"item.completed","item":{"type":"agent_message","text":"intermediate"}}` + "\n"},
+			{Delay: 1100 * time.Millisecond, Data: `{"type":"item.completed","item":{"type":"agent_message","text":"final"}}` + "\n"},
+			{Data: `{"type":"thread.completed","thread_id":"tid"}` + "\n"},
+		},
+		KeepStdoutOpen:      true,
+		BlockWait:           true,
+		ReleaseWaitOnSignal: true,
+		ReleaseWaitOnKill:   true,
+	})
+
+	newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		return fake
+	}
+	buildCodexArgsFn = func(cfg *Config, targetArg string) []string { return []string{targetArg} }
+	codexCommand = "fake-cmd"
+
+	start := time.Now()
+	result := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "done", WorkDir: defaultWorkdir}, nil, nil, false, false, 60)
+	duration := time.Since(start)
+
+	if result.ExitCode != 0 || result.Message != "final" {
+		t.Fatalf("unexpected result: %+v", result)
+	}
+	if duration > 5*time.Second {
+		t.Fatalf("runCodexTaskWithContext took too long: %v", duration)
+	}
+	if fake.process.SignalCount() == 0 {
+		t.Fatalf("expected SIGTERM to be sent, got %d", fake.process.SignalCount())
+	}
+}
+
 func TestBackendParseArgs_NewMode(t *testing.T) {
 	tests := []struct {
 		name    string
@@ -965,6 +1058,8 @@ func TestBackendParseArgs_ResumeMode(t *testing.T) {
 		},
 		{name: "resume missing session_id", args: []string{"codeagent-wrapper", "resume"}, wantErr: true},
 		{name: "resume missing task", args: []string{"codeagent-wrapper", "resume", "session-123"}, wantErr: true},
+		{name: "resume empty session_id", args: []string{"codeagent-wrapper", "resume", "", "task"}, wantErr: true},
+		{name: "resume whitespace session_id", args: []string{"codeagent-wrapper", "resume", "   ", "task"}, wantErr: true},
 	}
 
 	for _, tt := range tests {
@@ -1181,6 +1276,18 @@ do something`
 	}
 }
 
+func TestParallelParseConfig_EmptySessionID(t *testing.T) {
+	input := `---TASK---
+id: task-1
+session_id:
+---CONTENT---
+do something`
+
+	if _, err := parseParallelConfig([]byte(input)); err == nil {
+		t.Fatalf("expected error for empty session_id, got nil")
+	}
+}
+
 func TestParallelParseConfig_InvalidFormat(t *testing.T) {
 	if _, err := parseParallelConfig([]byte("invalid format")); err == nil {
 		t.Fatalf("expected error for invalid format, got nil")
@@ -1281,9 +1388,19 @@ func TestRunShouldUseStdin(t *testing.T) {
 }
 
 func TestRunBuildCodexArgs_NewMode(t *testing.T) {
+	const key = "CODEX_BYPASS_SANDBOX"
+	t.Cleanup(func() { os.Unsetenv(key) })
+	os.Unsetenv(key)
+
 	cfg := &Config{Mode: "new", WorkDir: "/test/dir"}
 	args := buildCodexArgs(cfg, "my task")
-	expected := []string{"e", "--skip-git-repo-check", "-C", "/test/dir", "--json", "my task"}
+	expected := []string{
+		"e",
+		"--skip-git-repo-check",
+		"-C", "/test/dir",
+		"--json",
+		"my task",
+	}
 	if len(args) != len(expected) {
 		t.Fatalf("len mismatch")
 	}
@@ -1295,9 +1412,20 @@ func TestRunBuildCodexArgs_NewMode(t *testing.T) {
 }
 
 func TestRunBuildCodexArgs_ResumeMode(t *testing.T) {
+	const key = "CODEX_BYPASS_SANDBOX"
+	t.Cleanup(func() { os.Unsetenv(key) })
+	os.Unsetenv(key)
+
 	cfg := &Config{Mode: "resume", SessionID: "session-abc"}
 	args := buildCodexArgs(cfg, "-")
-	expected := []string{"e", "--skip-git-repo-check", "--json", "resume", "session-abc", "-"}
+	expected := []string{
+		"e",
+		"--skip-git-repo-check",
+		"--json",
+		"resume",
+		"session-abc",
+		"-",
+	}
 	if len(args) != len(expected) {
 		t.Fatalf("len mismatch")
 	}
@@ -1308,6 +1436,61 @@ func TestRunBuildCodexArgs_ResumeMode(t *testing.T) {
 	}
 }
 
+func TestRunBuildCodexArgs_ResumeMode_EmptySessionHandledGracefully(t *testing.T) {
+	const key = "CODEX_BYPASS_SANDBOX"
+	t.Cleanup(func() { os.Unsetenv(key) })
+	os.Unsetenv(key)
+
+	cfg := &Config{Mode: "resume", SessionID: "   ", WorkDir: "/test/dir"}
+	args := buildCodexArgs(cfg, "task")
+	expected := []string{"e", "--skip-git-repo-check", "-C", "/test/dir", "--json", "task"}
+	if len(args) != len(expected) {
+		t.Fatalf("len mismatch")
+	}
+	for i := range args {
+		if args[i] != expected[i] {
+			t.Fatalf("args[%d]=%s, want %s", i, args[i], expected[i])
+		}
+	}
+}
+
+func TestRunBuildCodexArgs_BypassSandboxEnvTrue(t *testing.T) {
+	defer resetTestHooks()
+	tempDir := t.TempDir()
+	t.Setenv("TMPDIR", tempDir)
+
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger() error = %v", err)
+	}
+	setLogger(logger)
+	defer closeLogger()
+
+	t.Setenv("CODEX_BYPASS_SANDBOX", "true")
+
+	cfg := &Config{Mode: "new", WorkDir: "/test/dir"}
+	args := buildCodexArgs(cfg, "my task")
+	found := false
+	for _, arg := range args {
+		if arg == "--dangerously-bypass-approvals-and-sandbox" {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Fatalf("expected bypass flag in args, got %v", args)
+	}
+
+	logger.Flush()
+	data, err := os.ReadFile(logger.Path())
+	if err != nil {
+		t.Fatalf("failed to read log file: %v", err)
+	}
+	if !strings.Contains(string(data), "CODEX_BYPASS_SANDBOX=true") {
+		t.Fatalf("expected bypass warning log, got: %s", string(data))
+	}
+}
+
 func TestBackendSelectBackend(t *testing.T) {
 	tests := []struct {
 		name string
@@ -1363,7 +1546,13 @@ func TestBackendBuildArgs_CodexBackend(t *testing.T) {
 	backend := CodexBackend{}
 	cfg := &Config{Mode: "new", WorkDir: "/test/dir"}
 	got := backend.BuildArgs(cfg, "task")
-	want := []string{"e", "--skip-git-repo-check", "-C", "/test/dir", "--json", "task"}
+	want := []string{
+		"e",
+		"--skip-git-repo-check",
+		"-C", "/test/dir",
+		"--json",
+		"task",
+	}
 	if len(got) != len(want) {
 		t.Fatalf("length mismatch")
 	}
@@ -1378,13 +1567,13 @@ func TestBackendBuildArgs_ClaudeBackend(t *testing.T) {
 	backend := ClaudeBackend{}
 	cfg := &Config{Mode: "new", WorkDir: defaultWorkdir}
 	got := backend.BuildArgs(cfg, "todo")
-	want := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "todo"}
+	want := []string{"-p", "--setting-sources", "", "--output-format", "stream-json", "--verbose", "todo"}
 	if len(got) != len(want) {
-		t.Fatalf("length mismatch")
+		t.Fatalf("args length=%d, want %d: %v", len(got), len(want), got)
 	}
 	for i := range want {
 		if got[i] != want[i] {
-			t.Fatalf("index %d got %s want %s", i, got[i], want[i])
+			t.Fatalf("index %d got %q want %q (args=%v)", i, got[i], want[i], got)
 		}
 	}
 
@@ -1399,19 +1588,15 @@ func TestClaudeBackendBuildArgs_OutputValidation(t *testing.T) {
 	target := "ensure-flags"
 
 	args := backend.BuildArgs(cfg, target)
-	expectedPrefix := []string{"-p", "--dangerously-skip-permissions", "--setting-sources", "", "--output-format", "stream-json", "--verbose"}
+	want := []string{"-p", "--setting-sources", "", "--output-format", "stream-json", "--verbose", target}
-
+	if len(args) != len(want) {
-	if len(args) != len(expectedPrefix)+1 {
+		t.Fatalf("args length=%d, want %d: %v", len(args), len(want), args)
-		t.Fatalf("args length=%d, want %d", len(args), len(expectedPrefix)+1)
 	}
-	for i, val := range expectedPrefix {
+	for i := range want {
-		if args[i] != val {
+		if args[i] != want[i] {
-			t.Fatalf("args[%d]=%q, want %q", i, args[i], val)
+			t.Fatalf("index %d got %q want %q (args=%v)", i, args[i], want[i], args)
 		}
 	}
-	if args[len(args)-1] != target {
-		t.Fatalf("last arg=%q, want target %q", args[len(args)-1], target)
-	}
 }
 
 func TestBackendBuildArgs_GeminiBackend(t *testing.T) {
@@ -1582,6 +1767,34 @@ func TestBackendParseJSONStream_ClaudeEvents(t *testing.T) {
 	}
 }
 
+func TestBackendParseJSONStream_ClaudeEvents_ItemDoesNotForceCodex(t *testing.T) {
+	tests := []struct {
+		name  string
+		input string
+	}{
+		{
+			name:  "null item",
+			input: `{"type":"result","result":"OK","session_id":"abc123","item":null}`,
+		},
+		{
+			name:  "empty object item",
+			input: `{"type":"result","subtype":"x","result":"OK","session_id":"abc123","item":{}}`,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			message, threadID := parseJSONStream(strings.NewReader(tt.input))
+			if message != "OK" {
+				t.Fatalf("message=%q, want %q", message, "OK")
+			}
+			if threadID != "abc123" {
+				t.Fatalf("threadID=%q, want %q", threadID, "abc123")
+			}
+		})
+	}
+}
+
 func TestBackendParseJSONStream_GeminiEvents(t *testing.T) {
 	input := `{"type":"init","session_id":"xyz789"}
 {"type":"message","role":"assistant","content":"Hi","delta":true,"session_id":"xyz789"}
@@ -1598,6 +1811,43 @@ func TestBackendParseJSONStream_GeminiEvents(t *testing.T) {
 	}
 }
 
+func TestBackendParseJSONStream_GeminiEvents_DeltaFalseStillDetected(t *testing.T) {
+	input := `{"type":"init","session_id":"xyz789"}
+{"type":"message","content":"Hi","delta":false,"session_id":"xyz789"}
+{"type":"result","status":"success","session_id":"xyz789"}`
+
+	message, threadID := parseJSONStream(strings.NewReader(input))
+
+	if message != "Hi" {
+		t.Fatalf("message=%q, want %q", message, "Hi")
+	}
+	if threadID != "xyz789" {
+		t.Fatalf("threadID=%q, want %q", threadID, "xyz789")
+	}
+}
+
+func TestBackendParseJSONStream_GeminiEvents_OnMessageTriggeredOnStatus(t *testing.T) {
+	input := `{"type":"init","session_id":"xyz789"}
+{"type":"message","role":"assistant","content":"Hi","delta":true,"session_id":"xyz789"}
+{"type":"message","content":" there","delta":true}
+{"type":"result","status":"success","session_id":"xyz789"}`
+
+	var called int
+	message, threadID := parseJSONStreamInternal(strings.NewReader(input), nil, nil, func() {
+		called++
+	}, nil)
+
+	if message != "Hi there" {
+		t.Fatalf("message=%q, want %q", message, "Hi there")
+	}
+	if threadID != "xyz789" {
+		t.Fatalf("threadID=%q, want %q", threadID, "xyz789")
+	}
+	if called != 1 {
+		t.Fatalf("onMessage called=%d, want %d", called, 1)
+	}
+}
+
 func TestBackendParseJSONStreamWithWarn_InvalidLine(t *testing.T) {
 	var warnings []string
 	warnFn := func(msg string) { warnings = append(warnings, msg) }
@@ -1614,7 +1864,7 @@ func TestBackendParseJSONStream_OnMessage(t *testing.T) {
 	var called int
 	message, threadID := parseJSONStreamInternal(strings.NewReader(`{"type":"item.completed","item":{"type":"agent_message","text":"hook"}}`), nil, nil, func() {
 		called++
-	})
+	}, nil)
 	if message != "hook" {
 		t.Fatalf("message = %q, want hook", message)
 	}
@@ -1626,10 +1876,86 @@ func TestBackendParseJSONStream_OnMessage(t *testing.T) {
 	}
 }
 
+func TestBackendParseJSONStream_OnComplete_CodexThreadCompleted(t *testing.T) {
+	input := `{"type":"item.completed","item":{"type":"agent_message","text":"first"}}` + "\n" +
+		`{"type":"item.completed","item":{"type":"agent_message","text":"second"}}` + "\n" +
+		`{"type":"thread.completed","thread_id":"t-1"}`
+
+	var onMessageCalls int
+	var onCompleteCalls int
+	message, threadID := parseJSONStreamInternal(strings.NewReader(input), nil, nil, func() {
+		onMessageCalls++
+	}, func() {
+		onCompleteCalls++
+	})
+	if message != "second" {
+		t.Fatalf("message = %q, want second", message)
+	}
+	if threadID != "t-1" {
+		t.Fatalf("threadID = %q, want t-1", threadID)
+	}
+	if onMessageCalls != 2 {
+		t.Fatalf("onMessage calls = %d, want 2", onMessageCalls)
+	}
+	if onCompleteCalls != 1 {
+		t.Fatalf("onComplete calls = %d, want 1", onCompleteCalls)
+	}
+}
+
+func TestBackendParseJSONStream_OnComplete_ClaudeResult(t *testing.T) {
+	input := `{"type":"message","subtype":"stream","session_id":"s-1"}` + "\n" +
+		`{"type":"result","result":"OK","session_id":"s-1"}`
+
+	var onMessageCalls int
+	var onCompleteCalls int
+	message, threadID := parseJSONStreamInternal(strings.NewReader(input), nil, nil, func() {
+		onMessageCalls++
+	}, func() {
+		onCompleteCalls++
+	})
+	if message != "OK" {
+		t.Fatalf("message = %q, want OK", message)
+	}
+	if threadID != "s-1" {
+		t.Fatalf("threadID = %q, want s-1", threadID)
+	}
+	if onMessageCalls != 1 {
+		t.Fatalf("onMessage calls = %d, want 1", onMessageCalls)
+	}
+	if onCompleteCalls != 1 {
+		t.Fatalf("onComplete calls = %d, want 1", onCompleteCalls)
+	}
+}
+
+func TestBackendParseJSONStream_OnComplete_GeminiTerminalResultStatus(t *testing.T) {
+	input := `{"type":"message","role":"assistant","content":"Hi","delta":true,"session_id":"g-1"}` + "\n" +
+		`{"type":"result","status":"success","session_id":"g-1"}`
+
+	var onMessageCalls int
+	var onCompleteCalls int
+	message, threadID := parseJSONStreamInternal(strings.NewReader(input), nil, nil, func() {
+		onMessageCalls++
+	}, func() {
+		onCompleteCalls++
+	})
+	if message != "Hi" {
+		t.Fatalf("message = %q, want Hi", message)
+	}
+	if threadID != "g-1" {
+		t.Fatalf("threadID = %q, want g-1", threadID)
+	}
+	if onMessageCalls != 1 {
+		t.Fatalf("onMessage calls = %d, want 1", onMessageCalls)
+	}
+	if onCompleteCalls != 1 {
+		t.Fatalf("onComplete calls = %d, want 1", onCompleteCalls)
+	}
+}
+
 func TestBackendParseJSONStream_ScannerError(t *testing.T) {
 	var warnings []string
 	warnFn := func(msg string) { warnings = append(warnings, msg) }
-	message, threadID := parseJSONStreamInternal(errReader{err: errors.New("scan-fail")}, warnFn, nil, nil)
+	message, threadID := parseJSONStreamInternal(errReader{err: errors.New("scan-fail")}, warnFn, nil, nil, nil)
 	if message != "" || threadID != "" {
 		t.Fatalf("expected empty output on scanner error, got message=%q threadID=%q", message, threadID)
 	}
@@ -2691,7 +3017,7 @@ func TestVersionFlag(t *testing.T) {
 			t.Errorf("exit = %d, want 0", code)
 		}
 	})
-	want := "codeagent-wrapper version 5.2.5\n"
+	want := "codeagent-wrapper version 5.2.7\n"
 	if output != want {
 		t.Fatalf("output = %q, want %q", output, want)
 	}
@@ -2705,7 +3031,7 @@ func TestVersionShortFlag(t *testing.T) {
 			t.Errorf("exit = %d, want 0", code)
 		}
 	})
-	want := "codeagent-wrapper version 5.2.5\n"
+	want := "codeagent-wrapper version 5.2.7\n"
 	if output != want {
 		t.Fatalf("output = %q, want %q", output, want)
 	}
@@ -2719,7 +3045,7 @@ func TestVersionLegacyAlias(t *testing.T) {
 			t.Errorf("exit = %d, want 0", code)
 		}
 	})
-	want := "codex-wrapper version 5.2.5\n"
+	want := "codex-wrapper version 5.2.7\n"
 	if output != want {
 		t.Fatalf("output = %q, want %q", output, want)
 	}

codeagent-wrapper/parser.go

@@ -50,7 +50,7 @@ func parseJSONStreamWithWarn(r io.Reader, warnFn func(string)) (message, threadI
 }
 
 func parseJSONStreamWithLog(r io.Reader, warnFn func(string), infoFn func(string)) (message, threadID string) {
-	return parseJSONStreamInternal(r, warnFn, infoFn, nil)
+	return parseJSONStreamInternal(r, warnFn, infoFn, nil, nil)
 }
 
 const (
@@ -67,7 +67,35 @@ type codexHeader struct {
 	} `json:"item,omitempty"`
 }
 
-func parseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(string), onMessage func()) (message, threadID string) {
+// 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"`
+}
+
+// ItemContent represents the parsed item.text field for Codex events
+type ItemContent struct {
+	Type string      `json:"type"`
+	Text interface{} `json:"text"`
+}
+
+func parseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(string), onMessage func(), onComplete func()) (message, threadID string) {
 	reader := bufio.NewReaderSize(r, jsonLineReaderSize)
 
 	if warnFn == nil {
@@ -83,6 +111,12 @@ func parseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(strin
 		}
 	}
 
+	notifyComplete := func() {
+		if onComplete != nil {
+			onComplete()
+		}
+	}
+
 	totalEvents := 0
 
 	var (
@@ -112,71 +146,87 @@ func parseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(strin
 			continue
 		}
 
-		var codex codexHeader
+		// Single unmarshal for all backend types
-		if err := json.Unmarshal(line, &codex); err == nil {
+		var event UnifiedEvent
-			isCodex := codex.ThreadID != "" || (codex.Item != nil && codex.Item.Type != "")
+		if err := json.Unmarshal(line, &event); err != nil {
-			if isCodex {
+			warnFn(fmt.Sprintf("Failed to parse event: %s", truncateBytes(line, 100)))
-				var details []string
+			continue
-				if codex.ThreadID != "" {
+		}
-					details = append(details, fmt.Sprintf("thread_id=%s", codex.ThreadID))
-				}
-				if codex.Item != nil && codex.Item.Type != "" {
-					details = append(details, fmt.Sprintf("item_type=%s", codex.Item.Type))
-				}
-				if len(details) > 0 {
-					infoFn(fmt.Sprintf("Parsed event #%d type=%s (%s)", totalEvents, codex.Type, strings.Join(details, ", ")))
-				} else {
-					infoFn(fmt.Sprintf("Parsed event #%d type=%s", totalEvents, codex.Type))
-				}
 
-				switch codex.Type {
+		// Detect backend type by field presence
-				case "thread.started":
+		isCodex := event.ThreadID != ""
-					threadID = codex.ThreadID
+		if !isCodex && len(event.Item) > 0 {
-					infoFn(fmt.Sprintf("thread.started event thread_id=%s", threadID))
+			var itemHeader struct {
-				case "item.completed":
+				Type string `json:"type"`
-					itemType := ""
+			}
-					if codex.Item != nil {
+			if json.Unmarshal(event.Item, &itemHeader) == nil && itemHeader.Type != "" {
-						itemType = codex.Item.Type
+				isCodex = true
+			}
+		}
+		isClaude := event.Subtype != "" || event.Result != ""
+		if !isClaude && event.Type == "result" && event.SessionID != "" && event.Status == "" {
+			isClaude = true
+		}
+		isGemini := event.Role != "" || event.Delta != nil || event.Status != ""
+
+		// 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 "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" {
+				if itemType == "agent_message" && len(event.Item) > 0 {
-						var event JSONEvent
+					// Lazy parse: only parse item content when needed
-						if err := json.Unmarshal(line, &event); err != nil {
+					var item ItemContent
-							warnFn(fmt.Sprintf("Failed to parse Codex event: %s", truncateBytes(line, 100)))
+					if err := json.Unmarshal(event.Item, &item); err == nil {
-							continue
+						normalized := normalizeText(item.Text)
-						}
-
-						normalized := ""
-						if event.Item != nil {
-							normalized = normalizeText(event.Item.Text)
-						}
 						infoFn(fmt.Sprintf("item.completed event item_type=%s message_len=%d", itemType, len(normalized)))
 						if normalized != "" {
 							codexMessage = normalized
 							notifyMessage()
 						}
 					} else {
-						infoFn(fmt.Sprintf("item.completed event item_type=%s", itemType))
+						warnFn(fmt.Sprintf("Failed to parse item content: %s", err.Error()))
 					}
+				} else {
+					infoFn(fmt.Sprintf("item.completed event item_type=%s", itemType))
 				}
-				continue
 			}
-		}
-
-		var raw map[string]json.RawMessage
-		if err := json.Unmarshal(line, &raw); err != nil {
-			warnFn(fmt.Sprintf("Failed to parse line: %s", truncateBytes(line, 100)))
 			continue
 		}
 
-		switch {
+		// Handle Claude events
-		case hasKey(raw, "subtype") || hasKey(raw, "result"):
+		if isClaude {
-			var event ClaudeEvent
-			if err := json.Unmarshal(line, &event); err != nil {
-				warnFn(fmt.Sprintf("Failed to parse Claude event: %s", truncateBytes(line, 100)))
-				continue
-			}
-
 			if event.SessionID != "" && threadID == "" {
 				threadID = event.SessionID
 			}
@@ -188,27 +238,41 @@ func parseJSONStreamInternal(r io.Reader, warnFn func(string), infoFn func(strin
 				notifyMessage()
 			}
 
-		case hasKey(raw, "role") || hasKey(raw, "delta"):
+			if event.Type == "result" {
-			var event GeminiEvent
+				notifyComplete()
-			if err := json.Unmarshal(line, &event); err != nil {
-				warnFn(fmt.Sprintf("Failed to parse Gemini event: %s", truncateBytes(line, 100)))
-				continue
 			}
+			continue
+		}
 
+		// Handle Gemini events
+		if isGemini {
 			if event.SessionID != "" && threadID == "" {
 				threadID = event.SessionID
 			}
 
 			if event.Content != "" {
 				geminiBuffer.WriteString(event.Content)
-				notifyMessage()
 			}
 
-			infoFn(fmt.Sprintf("Parsed Gemini event #%d type=%s role=%s delta=%t status=%s content_len=%d", totalEvents, event.Type, event.Role, event.Delta, event.Status, len(event.Content)))
+			if event.Status != "" {
+				notifyMessage()
 
-		default:
+				if event.Type == "result" && (event.Status == "success" || event.Status == "error" || event.Status == "complete" || event.Status == "failed") {
-			warnFn(fmt.Sprintf("Unknown event format: %s", truncateBytes(line, 100)))
+					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
+		warnFn(fmt.Sprintf("Unknown event format: %s", truncateBytes(line, 100)))
 	}
 
 	switch {

codeagent-wrapper/parser_token_too_long_test.go

@@ -18,7 +18,7 @@ func TestParseJSONStream_SkipsOverlongLineAndContinues(t *testing.T) {
 	var warns []string
 	warnFn := func(msg string) { warns = append(warns, msg) }
 
-	gotMessage, gotThreadID := parseJSONStreamInternal(strings.NewReader(input), warnFn, nil, nil)
+	gotMessage, gotThreadID := parseJSONStreamInternal(strings.NewReader(input), warnFn, nil, nil, nil)
 	if gotMessage != "ok" {
 		t.Fatalf("message=%q, want %q (warns=%v)", gotMessage, "ok", warns)
 	}

dev-workflow/commands/dev.md

@@ -2,9 +2,25 @@
 description: Extreme lightweight end-to-end development workflow with requirements clarification, parallel codeagent execution, and mandatory 90% test coverage
 ---
 
-
 You are the /dev Workflow Orchestrator, an expert development workflow manager specializing in orchestrating minimal, efficient end-to-end development processes with parallel task execution and rigorous test coverage validation.
 
+---
+
+## CRITICAL CONSTRAINTS (NEVER VIOLATE)
+
+These rules have HIGHEST PRIORITY and override all other instructions:
+
+1. **NEVER use Edit, Write, or MultiEdit tools directly** - ALL code changes MUST go through codeagent-wrapper
+2. **MUST use AskUserQuestion in Step 1** - Do NOT skip requirement clarification
+3. **MUST use TodoWrite after Step 1** - Create task tracking list before any analysis
+4. **MUST use codeagent-wrapper for Step 2 analysis** - Do NOT use Read/Glob/Grep directly for deep analysis
+5. **MUST wait for user confirmation in Step 3** - Do NOT proceed to Step 4 without explicit approval
+6. **MUST invoke codeagent-wrapper --parallel for Step 4 execution** - Use Bash tool, NOT Edit/Write or Task tool
+
+**Violation of any constraint above invalidates the entire workflow. Stop and restart if violated.**
+
+---
+
 **Core Responsibilities**
 - Orchestrate a streamlined 6-step development workflow:
   1. Requirement clarification through targeted questioning
@@ -15,14 +31,35 @@ You are the /dev Workflow Orchestrator, an expert development workflow manager s
   6. Completion summary
 
 **Workflow Execution**
-- **Step 1: Requirement Clarification**
+- **Step 1: Requirement Clarification [MANDATORY - DO NOT SKIP]**
-  - Use AskUserQuestion to clarify requirements directly
+  - MUST use AskUserQuestion tool as the FIRST action - no exceptions
   - Focus questions on functional boundaries, inputs/outputs, constraints, testing, and required unit-test coverage levels
   - Iterate 2-3 rounds until clear; rely on judgment; keep questions concise
+  - After clarification complete: MUST use TodoWrite to create task tracking list with workflow steps
 
-- **Step 2: codeagent Deep Analysis (Plan Mode Style)**
+- **Step 2: codeagent-wrapper Deep Analysis (Plan Mode Style) [USE CODEAGENT-WRAPPER ONLY]**
 
-  Use codeagent Skill to perform deep analysis. codeagent should operate in "plan mode" style and must include UI detection:
+  MUST use Bash tool to invoke `codeagent-wrapper` for deep analysis. Do NOT use Read/Glob/Grep tools directly - delegate all exploration to codeagent-wrapper.
+
+  **How to invoke for analysis**:
+  ```bash
+  codeagent-wrapper --backend codex - <<'EOF'
+  Analyze the codebase for implementing [feature name].
+
+  Requirements:
+  - [requirement 1]
+  - [requirement 2]
+
+  Deliverables:
+  1. Explore codebase structure and existing patterns
+  2. Evaluate implementation options with trade-offs
+  3. Make architectural decisions
+  4. Break down into 2-5 parallelizable tasks with dependencies
+  5. Determine if UI work is needed (check for .css/.tsx/.vue files)
+
+  Output the analysis following the structure below.
+  EOF
+  ```
 
   **When Deep Analysis is Needed** (any condition triggers):
   - Multiple valid approaches exist (e.g., Redis vs in-memory vs file-based caching)
@@ -34,7 +71,7 @@ You are the /dev Workflow Orchestrator, an expert development workflow manager s
   - During analysis, output whether the task needs UI work (yes/no) and the evidence
   - UI criteria: presence of style assets (.css, .scss, styled-components, CSS modules, tailwindcss) OR frontend component files (.tsx, .jsx, .vue)
 
-  **What codeagent Does in Analysis Mode**:
+  **What the AI backend does in Analysis Mode** (when invoked via codeagent-wrapper):
   1. **Explore Codebase**: Use Glob, Grep, Read to understand structure, patterns, architecture
   2. **Identify Existing Patterns**: Find how similar features are implemented, reuse conventions
   3. **Evaluate Options**: When multiple approaches exist, list trade-offs (complexity, performance, security, maintainability)
@@ -81,27 +118,39 @@ You are the /dev Workflow Orchestrator, an expert development workflow manager s
     - Options: "Confirm and execute" / "Need adjustments"
   - If user chooses "Need adjustments", return to Step 1 or Step 2 based on feedback
 
-- **Step 4: Parallel Development Execution**
+- **Step 4: Parallel Development Execution [CODEAGENT-WRAPPER ONLY - NO DIRECT EDITS]**
-  - For each task in `dev-plan.md`, invoke codeagent skill with task brief in HEREDOC format:
+  - MUST use Bash tool to invoke `codeagent-wrapper --parallel` for ALL code changes
+  - NEVER use Edit, Write, MultiEdit, or Task tools to modify code directly
+  - Build ONE `--parallel` config that includes all tasks in `dev-plan.md` and submit it once via Bash tool:
     ```bash
-    # Backend task (use codex backend - default)
+    # One shot submission - wrapper handles topology + concurrency
-    codeagent-wrapper --backend codex - <<'EOF'
+    codeagent-wrapper --parallel <<'EOF'
-    Task: [task-id]
+    ---TASK---
+    id: [task-id-1]
+    backend: codex
+    workdir: .
+    dependencies: [optional, comma-separated ids]
+    ---CONTENT---
+    Task: [task-id-1]
     Reference: @.claude/specs/{feature_name}/dev-plan.md
     Scope: [task file scope]
     Test: [test command]
     Deliverables: code + unit tests + coverage ≥90% + coverage summary
-    EOF
 
-    # UI task (use gemini backend - enforced)
+    ---TASK---
-    codeagent-wrapper --backend gemini - <<'EOF'
+    id: [task-id-2]
-    Task: [task-id]
+    backend: gemini
+    workdir: .
+    dependencies: [optional, comma-separated ids]
+    ---CONTENT---
+    Task: [task-id-2]
     Reference: @.claude/specs/{feature_name}/dev-plan.md
     Scope: [task file scope]
     Test: [test command]
     Deliverables: code + unit tests + coverage ≥90% + coverage summary
     EOF
     ```
+  - **Note**: Use `workdir: .` (current directory) for all tasks unless specific subdirectory is required
   - Execute independent tasks concurrently; serialize conflicting ones; track coverage reports
 
 - **Step 5: Coverage Validation**
@@ -113,9 +162,13 @@ You are the /dev Workflow Orchestrator, an expert development workflow manager s
   - Provide completed task list, coverage per task, key file changes
 
 **Error Handling**
-- codeagent failure: retry once, then log and continue
+- **codeagent-wrapper failure**: Retry once with same input; if still fails, log error and ask user for guidance
-- Insufficient coverage: request more tests (max 2 rounds)
+- **Insufficient coverage (<90%)**: Request more tests from the failed task (max 2 rounds); if still fails, report to user
-- Dependency conflicts: serialize automatically
+- **Dependency conflicts**:
+  - Circular dependencies: codeagent-wrapper will detect and fail with error; revise task breakdown to remove cycles
+  - Missing dependencies: Ensure all task IDs referenced in `dependencies` field exist
+- **Parallel execution timeout**: Individual tasks timeout after 2 hours (configurable via CODEX_TIMEOUT); failed tasks can be retried individually
+- **Backend unavailable**: If codex/claude/gemini CLI not found, fail immediately with clear error message
 
 **Quality Standards**
 - Code coverage ≥90%

go.work

@@ -0,0 +1,5 @@
+go 1.21
+
+use (
+	./codeagent-wrapper
+)

hooks/pre-commit.sh

@@ -5,7 +5,7 @@
 set -e
 
 # Get staged files
-STAGED_FILES=$(git diff --cached --name-only --diff-filter=ACM)
+STAGED_FILES="$(git diff --cached --name-only --diff-filter=ACM)"
 
 if [ -z "$STAGED_FILES" ]; then
   echo "No files to validate"
@@ -15,17 +15,32 @@ fi
 echo "Running pre-commit checks..."
 
 # Check Go files
-GO_FILES=$(echo "$STAGED_FILES" | grep '\.go$' || true)
+GO_FILES="$(printf '%s\n' "$STAGED_FILES" | grep '\.go$' || true)"
 if [ -n "$GO_FILES" ]; then
   echo "Checking Go files..."
 
+  if ! command -v gofmt &> /dev/null; then
+    echo "❌ gofmt not found. Please install Go (gofmt is included with the Go toolchain)."
+    exit 1
+  fi
+
   # Format check
-  gofmt -l $GO_FILES | while read -r file; do
+  GO_FILE_ARGS=()
+  while IFS= read -r file; do
     if [ -n "$file" ]; then
-      echo "❌ $file needs formatting (run: gofmt -w $file)"
+      GO_FILE_ARGS+=("$file")
+    fi
+  done <<< "$GO_FILES"
+
+  if [ "${#GO_FILE_ARGS[@]}" -gt 0 ]; then
+    UNFORMATTED="$(gofmt -l "${GO_FILE_ARGS[@]}")"
+    if [ -n "$UNFORMATTED" ]; then
+      echo "❌ The following files need formatting:"
+      echo "$UNFORMATTED"
+      echo "Run: gofmt -w <file>"
       exit 1
     fi
-  done
+  fi
 
   # Run tests
   if command -v go &> /dev/null; then
@@ -38,19 +53,26 @@ if [ -n "$GO_FILES" ]; then
 fi
 
 # Check JSON files
-JSON_FILES=$(echo "$STAGED_FILES" | grep '\.json$' || true)
+JSON_FILES="$(printf '%s\n' "$STAGED_FILES" | grep '\.json$' || true)"
 if [ -n "$JSON_FILES" ]; then
   echo "Validating JSON files..."
-  for file in $JSON_FILES; do
+  if ! command -v jq &> /dev/null; then
+    echo "❌ jq not found. Please install jq to validate JSON files."
+    exit 1
+  fi
+  while IFS= read -r file; do
+    if [ -z "$file" ]; then
+      continue
+    fi
     if ! jq empty "$file" 2>/dev/null; then
       echo "❌ Invalid JSON: $file"
       exit 1
     fi
-  done
+  done <<< "$JSON_FILES"
 fi
 
 # Check Markdown files
-MD_FILES=$(echo "$STAGED_FILES" | grep '\.md$' || true)
+MD_FILES="$(printf '%s\n' "$STAGED_FILES" | grep '\.md$' || true)"
 if [ -n "$MD_FILES" ]; then
   echo "Checking markdown files..."
   # Add markdown linting if needed

install.py

@@ -17,7 +17,10 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, Iterable, List, Optional
 
-import jsonschema
+try:
+    import jsonschema
+except ImportError:  # pragma: no cover
+    jsonschema = None
 
 DEFAULT_INSTALL_DIR = "~/.claude"
 
@@ -87,6 +90,32 @@ def load_config(path: str) -> Dict[str, Any]:
     config_path = Path(path).expanduser().resolve()
     config = _load_json(config_path)
 
+    if jsonschema is None:
+        print(
+            "WARNING: python package 'jsonschema' is not installed; "
+            "skipping config validation. To enable validation run:\n"
+            "  python3 -m pip install jsonschema\n",
+            file=sys.stderr,
+        )
+
+        if not isinstance(config, dict):
+            raise ValueError(
+                f"Config must be a dict, got {type(config).__name__}. "
+                "Check your config.json syntax."
+            )
+
+        required_keys = ["version", "install_dir", "log_file", "modules"]
+        missing = [key for key in required_keys if key not in config]
+        if missing:
+            missing_str = ", ".join(missing)
+            raise ValueError(
+                f"Config missing required keys: {missing_str}. "
+                "Install jsonschema for better validation: "
+                "python3 -m pip install jsonschema"
+            )
+
+        return config
+
     schema_candidates = [
         config_path.parent / "config.schema.json",
         Path(__file__).resolve().with_name("config.schema.json"),

install.sh

@@ -1,12 +1,15 @@
 #!/bin/bash
 set -e
 
-echo "⚠️  WARNING: install.sh is LEGACY and will be removed in future versions."
+if [ -z "${SKIP_WARNING:-}" ]; then
-echo "Please use the new installation method:"
+  echo "⚠️  WARNING: install.sh is LEGACY and will be removed in future versions."
-echo "  python3 install.py --install-dir ~/.claude"
+  echo "Please use the new installation method:"
-echo ""
+  echo "  python3 install.py --install-dir ~/.claude"
-echo "Continuing with legacy installation in 5 seconds..."
+  echo ""
-sleep 5
+  echo "Set SKIP_WARNING=1 to bypass this message"
+  echo "Continuing with legacy installation in 5 seconds..."
+  sleep 5
+fi
 
 # Detect platform
 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
@@ -31,23 +34,25 @@ if ! curl -fsSL "$URL" -o /tmp/codeagent-wrapper; then
     exit 1
 fi
 
-mkdir -p "$HOME/bin"
+INSTALL_DIR="${INSTALL_DIR:-$HOME/.claude}"
+BIN_DIR="${INSTALL_DIR}/bin"
+mkdir -p "$BIN_DIR"
 
-mv /tmp/codeagent-wrapper "$HOME/bin/codeagent-wrapper"
+mv /tmp/codeagent-wrapper "${BIN_DIR}/codeagent-wrapper"
-chmod +x "$HOME/bin/codeagent-wrapper"
+chmod +x "${BIN_DIR}/codeagent-wrapper"
 
-if "$HOME/bin/codeagent-wrapper" --version >/dev/null 2>&1; then
+if "${BIN_DIR}/codeagent-wrapper" --version >/dev/null 2>&1; then
-    echo "codeagent-wrapper installed successfully to ~/bin/codeagent-wrapper"
+    echo "codeagent-wrapper installed successfully to ${BIN_DIR}/codeagent-wrapper"
 else
     echo "ERROR: installation verification failed" >&2
     exit 1
 fi
 
-if [[ ":$PATH:" != *":$HOME/bin:"* ]]; then
+if [[ ":$PATH:" != *":${BIN_DIR}:"* ]]; then
     echo ""
-    echo "WARNING: ~/bin is not in your PATH"
+    echo "WARNING: ${BIN_DIR} is not in your PATH"
-    echo "Add this line to your ~/.bashrc or ~/.zshrc:"
+    echo "Add this line to your ~/.bashrc or ~/.zshrc (then restart your shell):"
     echo ""
-    echo "    export PATH=\"\$HOME/bin:\$PATH\""
+    echo "    export PATH=\"${BIN_DIR}:\$PATH\""
     echo ""
 fi

requirements-driven-workflow/agents/requirements-code.md

@@ -104,6 +104,10 @@ You adhere to core software engineering principles like KISS (Keep It Simple, St
 
 ## Implementation Constraints
 
+### Language Rules
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, SQL, CRUD, etc.) in English; translate explanatory text only.
+
 ### MUST Requirements
 - **Working Solution**: Code must fully implement the specified functionality
 - **Integration Compatibility**: Must work seamlessly with existing codebase

requirements-driven-workflow/agents/requirements-generate.md

@@ -88,6 +88,10 @@ Each phase should be independently deployable and testable.
 
 ## Key Constraints
 
+### Language Rules
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, SQL, CRUD, etc.) in English; translate explanatory text only.
+
 ### MUST Requirements
 - **Direct Implementability**: Every item must be directly translatable to code
 - **Specific Technical Details**: Include exact file paths, function names, table schemas

requirements-driven-workflow/agents/requirements-review.md

@@ -176,6 +176,10 @@ You adhere to core software engineering principles like KISS (Keep It Simple, St
 
 ## Key Constraints
 
+### Language Rules
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, E2E, CI/CD, etc.) in English; translate explanatory text only.
+
 ### MUST Requirements
 - **Functional Verification**: Verify all specified functionality works
 - **Integration Testing**: Ensure seamless integration with existing code

requirements-driven-workflow/agents/requirements-testing.md

@@ -199,6 +199,10 @@ func TestAPIEndpoint(t *testing.T) {
 
 ## Key Constraints
 
+### Language Rules
+- **Language Matching**: Output language matches user input (Chinese input → Chinese doc, English input → English doc). When language is ambiguous, default to Chinese.
+- **Technical Terms**: Keep technical terms (API, E2E, CI/CD, Mock, etc.) in English; translate explanatory text only.
+
 ### MUST Requirements
 - **Specification Coverage**: Must test all requirements from `./.claude/specs/{feature_name}/requirements-spec.md`
 - **Critical Path Testing**: Must test all critical business functionality

skills/codeagent/SKILL.md

@@ -74,7 +74,7 @@ codeagent-wrapper --backend gemini "simple task"
 - `task` (required): Task description, supports `@file` references
 - `working_dir` (optional): Working directory (default: current)
 - `--backend` (optional): Select AI backend (codex/claude/gemini, default: codex)
-  - **Note**: Claude backend defaults to `--dangerously-skip-permissions` for automation compatibility
+  - **Note**: Claude backend only adds `--dangerously-skip-permissions` when explicitly enabled
 
 ## Return Format
 
@@ -147,9 +147,9 @@ Set `CODEAGENT_MAX_PARALLEL_WORKERS` to limit concurrent tasks (default: unlimit
 ## Environment Variables
 
 - `CODEX_TIMEOUT`: Override timeout in milliseconds (default: 7200000 = 2 hours)
-- `CODEAGENT_SKIP_PERMISSIONS`: Control permission checks
+- `CODEAGENT_SKIP_PERMISSIONS`: Control Claude CLI permission checks
-  - For **Claude** backend: Set to `true`/`1` to **disable** `--dangerously-skip-permissions` (default: enabled)
+  - For **Claude** backend: Set to `true`/`1` to add `--dangerously-skip-permissions` (default: disabled)
-  - For **Codex/Gemini** backends: Set to `true`/`1` to enable permission skipping (default: disabled)
+  - For **Codex/Gemini** backends: Currently has no effect
 - `CODEAGENT_MAX_PARALLEL_WORKERS`: Limit concurrent tasks in parallel mode (default: unlimited, recommended: 8)
 
 ## Invocation Pattern
@@ -182,9 +182,8 @@ Bash tool parameters:
 
 ## Security Best Practices
 
-- **Claude Backend**: Defaults to `--dangerously-skip-permissions` for automation workflows
+- **Claude Backend**: Permission checks enabled by default
-  - To enforce permission checks with Claude: Set `CODEAGENT_SKIP_PERMISSIONS=true`
+  - To skip checks: set `CODEAGENT_SKIP_PERMISSIONS=true` or pass `--skip-permissions`
-- **Codex/Gemini Backends**: Permission checks enabled by default
 - **Concurrency Limits**: Set `CODEAGENT_MAX_PARALLEL_WORKERS` in production to prevent resource exhaustion
 - **Automation Context**: This wrapper is designed for AI-driven automation where permission prompts would block execution