fix: use ANTHROPIC_AUTH_TOKEN for Claude CLI env injection

- Change env var from ANTHROPIC_API_KEY to ANTHROPIC_AUTH_TOKEN
- Add Backend field propagation in taskSpec (cli.go)
- Add stderr logging for injected env vars with API key masking
- Add comprehensive tests for env injection flow

Generated with SWE-Agent.ai

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

.claude-plugin/marketplace.json

@@ -1,209 +1,54 @@
 {
-  "name": "claude-code-dev-workflows",
+  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
+  "name": "myclaude",
+  "version": "5.6.1",
+  "description": "Professional multi-agent development workflows with OmO orchestration, Requirements-Driven and BMAD methodologies",
   "owner": {
-    "name": "Claude Code Dev Workflows",
-    "email": "contact@example.com",
-    "url": "https://github.com/cexll/myclaude"
-  },
-  "metadata": {
-    "description": "Professional multi-agent development workflows with Requirements-Driven and BMAD methodologies, featuring 16+ specialized agents and 12+ commands",
-    "version": "1.0.0"
+    "name": "cexll",
+    "email": "evanxian9@gmail.com"
   },
   "plugins": [
     {
-      "name": "requirements-driven-development",
-      "source": "./requirements-driven-workflow/",
-      "description": "Streamlined requirements-driven development workflow with 90% quality gates for practical feature implementation",
-      "version": "1.0.0",
-      "author": {
-        "name": "Claude Code Dev Workflows",
-        "url": "https://github.com/cexll/myclaude"
-      },
-      "homepage": "https://github.com/cexll/myclaude",
-      "repository": "https://github.com/cexll/myclaude",
-      "license": "MIT",
-      "keywords": [
-        "requirements",
-        "workflow",
-        "automation",
-        "quality-gates",
-        "feature-development",
-        "agile",
-        "specifications"
-      ],
-      "category": "workflows",
-      "strict": false,
-      "commands": [
-        "./commands/requirements-pilot.md"
-      ],
-      "agents": [
-        "./agents/requirements-generate.md",
-        "./agents/requirements-code.md",
-        "./agents/requirements-testing.md",
-        "./agents/requirements-review.md"
-      ]
+      "name": "omo",
+      "description": "Multi-agent orchestration for code analysis, bug investigation, fix planning, and implementation with intelligent routing to specialized agents",
+      "version": "5.6.1",
+      "source": "./skills/omo",
+      "category": "development"
     },
     {
-      "name": "bmad-agile-workflow",
-      "source": "./bmad-agile-workflow/",
+      "name": "dev",
+      "description": "Lightweight development workflow with requirements clarification, parallel codex execution, and mandatory 90% test coverage",
+      "version": "5.6.1",
+      "source": "./dev-workflow",
+      "category": "development"
+    },
+    {
+      "name": "requirements",
+      "description": "Requirements-driven development workflow with quality gates for practical feature implementation",
+      "version": "5.6.1",
+      "source": "./requirements-driven-workflow",
+      "category": "development"
+    },
+    {
+      "name": "bmad",
       "description": "Full BMAD agile workflow with role-based agents (PO, Architect, SM, Dev, QA) and interactive approval gates",
-      "version": "1.0.0",
-      "author": {
-        "name": "Claude Code Dev Workflows",
-        "url": "https://github.com/cexll/myclaude"
-      },
-      "homepage": "https://github.com/cexll/myclaude",
-      "repository": "https://github.com/cexll/myclaude",
-      "license": "MIT",
-      "keywords": [
-        "bmad",
-        "agile",
-        "scrum",
-        "product-owner",
-        "architect",
-        "developer",
-        "qa",
-        "workflow-orchestration"
-      ],
-      "category": "workflows",
-      "strict": false,
-      "commands": [
-        "./commands/bmad-pilot.md"
-      ],
-      "agents": [
-        "./agents/bmad-po.md",
-        "./agents/bmad-architect.md",
-        "./agents/bmad-sm.md",
-        "./agents/bmad-dev.md",
-        "./agents/bmad-qa.md",
-        "./agents/bmad-orchestrator.md",
-        "./agents/bmad-review.md"
-      ]
+      "version": "5.6.1",
+      "source": "./bmad-agile-workflow",
+      "category": "development"
     },
     {
-      "name": "development-essentials",
-      "source": "./development-essentials/",
+      "name": "dev-kit",
       "description": "Essential development commands for coding, debugging, testing, optimization, and documentation",
-      "version": "1.0.0",
-      "author": {
-        "name": "Claude Code Dev Workflows",
-        "url": "https://github.com/cexll/myclaude"
-      },
-      "homepage": "https://github.com/cexll/myclaude",
-      "repository": "https://github.com/cexll/myclaude",
-      "license": "MIT",
-      "keywords": [
-        "code",
-        "debug",
-        "test",
-        "optimize",
-        "review",
-        "bugfix",
-        "refactor",
-        "documentation"
-      ],
-      "category": "essentials",
-      "strict": false,
-      "commands": [
-        "./commands/code.md",
-        "./commands/debug.md",
-        "./commands/test.md",
-        "./commands/optimize.md",
-        "./commands/review.md",
-        "./commands/bugfix.md",
-        "./commands/refactor.md",
-        "./commands/docs.md",
-        "./commands/ask.md",
-        "./commands/think.md"
-      ],
-      "agents": [
-        "./agents/code.md",
-        "./agents/bugfix.md",
-        "./agents/bugfix-verify.md",
-        "./agents/optimize.md",
-        "./agents/debug.md"
-      ]
+      "version": "5.6.1",
+      "source": "./development-essentials",
+      "category": "productivity"
     },
     {
-      "name": "codex-cli",
-      "source": "./skills/codex/",
-      "description": "Execute Codex CLI for code analysis, refactoring, and automated code changes with file references (@syntax) and structured output",
-      "version": "1.0.0",
-      "author": {
-        "name": "Claude Code Dev Workflows",
-        "url": "https://github.com/cexll/myclaude"
-      },
-      "homepage": "https://github.com/cexll/myclaude",
-      "repository": "https://github.com/cexll/myclaude",
-      "license": "MIT",
-      "keywords": [
-        "codex",
-        "code-analysis",
-        "refactoring",
-        "automation",
-        "gpt-5",
-        "ai-coding"
-      ],
-      "category": "essentials",
-      "strict": false,
-      "skills": [
-        "./SKILL.md"
-      ]
-    },
-    {
-      "name": "gemini-cli",
-      "source": "./skills/gemini/",
-      "description": "Execute Gemini CLI for AI-powered code analysis and generation with Google's latest Gemini models",
-      "version": "1.0.0",
-      "author": {
-        "name": "Claude Code Dev Workflows",
-        "url": "https://github.com/cexll/myclaude"
-      },
-      "homepage": "https://github.com/cexll/myclaude",
-      "repository": "https://github.com/cexll/myclaude",
-      "license": "MIT",
-      "keywords": [
-        "gemini",
-        "google-ai",
-        "code-analysis",
-        "code-generation",
-        "ai-reasoning"
-      ],
-      "category": "essentials",
-      "strict": false,
-      "skills": [
-        "./SKILL.md"
-      ]
-    },
-    {
-      "name": "dev-workflow",
-      "source": "./dev-workflow/",
-      "description": "Minimal lightweight development workflow with requirements clarification, parallel codex execution, and mandatory 90% test coverage",
-      "version": "1.0.0",
-      "author": {
-        "name": "Claude Code Dev Workflows",
-        "url": "https://github.com/cexll/myclaude"
-      },
-      "homepage": "https://github.com/cexll/myclaude",
-      "repository": "https://github.com/cexll/myclaude",
-      "license": "MIT",
-      "keywords": [
-        "dev",
-        "workflow",
-        "codex",
-        "testing",
-        "coverage",
-        "concurrent",
-        "lightweight"
-      ],
-      "category": "workflows",
-      "strict": false,
-      "commands": [
-        "./commands/dev.md"
-      ],
-      "agents": [
-        "./agents/dev-plan-generator.md"
-      ]
+      "name": "sparv",
+      "description": "Minimal SPARV workflow (Specify→Plan→Act→Review→Vault) with 10-point spec gate, unified journal, 2-action saves, 3-failure protocol, and EHRB risk detection",
+      "version": "1.1.0",
+      "source": "./skills/sparv",
+      "category": "development"
     }
   ]
 }

.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

.github/workflows/release.yml

@@ -74,7 +74,7 @@ jobs:
           if [ "${{ matrix.goos }}" = "windows" ]; then
             OUTPUT_NAME="${OUTPUT_NAME}.exe"
           fi
-          go build -ldflags="-s -w -X main.version=${VERSION}" -o ${OUTPUT_NAME} .
+          go build -ldflags="-s -w -X main.version=${VERSION}" -o ${OUTPUT_NAME} ./cmd/codeagent
           chmod +x ${OUTPUT_NAME}
           echo "artifact_path=codeagent-wrapper/${OUTPUT_NAME}" >> $GITHUB_OUTPUT
 
@@ -104,38 +104,10 @@ jobs:
           cp install.sh install.bat release/
           ls -la release/
 
-      - name: Extract release notes from CHANGELOG
-        id: extract_notes
-        run: |
-          VERSION=${GITHUB_REF#refs/tags/v}
-
-          # Extract version section from CHANGELOG.md
-          awk -v ver="$VERSION" '
-            /^## [0-9]+\.[0-9]+\.[0-9]+ - / {
-              if (found) exit
-              if ($2 == ver) {
-                found = 1
-                next
-              }
-            }
-            found && /^## / { exit }
-            found { print }
-          ' CHANGELOG.md > release_notes.md
-
-          # Fallback to auto-generated if extraction failed
-          if [ ! -s release_notes.md ]; then
-            echo "⚠️ No release notes found in CHANGELOG.md for version $VERSION" > release_notes.md
-            echo "" >> release_notes.md
-            echo "## What's Changed" >> release_notes.md
-            echo "See commits in this release for details." >> release_notes.md
-          fi
-
-          cat release_notes.md
-
       - name: Create Release
         uses: softprops/action-gh-release@v2
         with:
           files: release/*
-          body_path: release_notes.md
+          generate_release_notes: true
           draft: false
           prerelease: false

.gitignore

@@ -1,6 +1,10 @@
 .claude/
 .claude-trace
+.DS_Store
+**/.DS_Store
 .venv
 .pytest_cache
 __pycache__
 .coverage
+coverage.out
+references

CHANGELOG.md

@@ -1,129 +1,772 @@
 # Changelog
 
-## 5.2.0 - 2025-12-13
+All notable changes to this project will be documented in this file.
 
-### 🚀 Core Features
+## [5.6.4] - 2026-01-15
 
-#### Skills System Enhancements
-- **New Skills**: Added `codeagent`, `product-requirements`, `prototype-prompt-generator` to `skill-rules.json`
-- **Auto-Activation**: Skills automatically trigger based on keyword/pattern matching via hooks
-- **Backward Compatibility**: Retained `skills/codex/SKILL.md` for existing workflows
+### 🚀 Features
 
-#### Multi-Backend Support (codeagent-wrapper)
-- **Renamed**: `codex-wrapper` → `codeagent-wrapper` with pluggable backend architecture
-- **Three Backends**: Codex (default), Claude, Gemini via `--backend` flag
-- **Smart Parser**: Auto-detects backend JSON stream formats
-- **Session Resume**: All backends support `-r <session_id>` cross-session resume
-- **Parallel Execution**: DAG task scheduling with global and per-task backend configuration
-- **Concurrency Control**: `CODEAGENT_MAX_PARALLEL_WORKERS` env var limits concurrent tasks (max 100)
-- **Test Coverage**: 93.4% (backend.go 100%, config.go 97.8%, executor.go 96.4%)
+- add reasoning effort config for codex backend
+- default to skip-permissions and bypass-sandbox
+- add multi-agent support with yolo mode
+- add omo module for multi-agent orchestration
+- add intelligent backend selection based on task complexity (#61)
+- v5.4.0 structured execution report (#94)
+- add millisecond-precision timestamps to all log entries (#91)
+- skill-install install script and security scan
+- add uninstall scripts with selective module removal
 
-#### Dev Workflow
-- **`/dev`**: 6-step minimal dev workflow with mandatory 90% test coverage
+### 🐛 Bug Fixes
 
-#### Hooks System
-- **UserPromptSubmit**: Auto-activate skills based on context
-- **PostToolUse**: Auto-validation/formatting after tool execution
-- **Stop**: Cleanup and reporting on session end
-- **Examples**: Skill auto-activation, pre-commit checks
+- filter codex stderr noise logs
+- use config override for codex reasoning effort
+- propagate SkipPermissions to parallel tasks (#113)
+- add timeout for Windows process termination
+- reject dash as workdir parameter (#118)
+- add sleep in fake script to prevent CI race condition
+- fix gemini env load
+- fix omo
+- fix codeagent skill TaskOutput
+- 修复 Gemini init 事件 session_id 未提取的问题 (#111)
+- Windows 后端退出：taskkill 结束进程树 + turn.completed 支持 (#108)
+- support model parameter for all backends, auto-inject from settings (#105)
+- replace setx with reg add to avoid 1024-char PATH truncation (#101)
+- 移除未知事件格式的日志噪声 (#96)
+- prevent duplicate PATH entries on reinstall (#95)
+- Minor issues #12 and #13 - ASCII mode and performance optimization
+- correct settings.json filename and bump version to v5.2.8
+- allow claude backend to read env from setting.json while preventing recursion (#92)
+- comprehensive security and quality improvements for PR #85 & #87 (#90)
+- Improve backend termination after message and extend timeout (#86)
+- Parser重复解析优化 + 严重bug修复 + PR #86兼容性 (#88)
+- filter noisy stderr output from gemini backend (#83)
+- 修復 wsl install.sh 格式問題 (#78)
+- 修复多 backend 并行日志 PID 混乱并移除包装格式 (#74) (#76)
 
-#### Skills System
-- **Auto-Activation**: `skill-rules.json` regex trigger rules
-- **codeagent skill**: Multi-backend wrapper integration
-- **Modular Design**: Easy to extend with custom skills
+### 🚜 Refactor
 
-#### Installation System Enhancements
-- **`merge_json` operation**: Auto-merge `settings.json` configuration
-- **Modular Installation**: `python3 install.py --module dev`
-- **Verbose Logging**: `--verbose/-v` enables terminal real-time output
-- **Streaming Output**: `op_run_command` streams bash script execution
-- **Configuration Cleanup**: Removed deprecated `gh` module from `config.json`
+- remove sisyphus agent and unused code
+- streamline agent documentation and remove sisyphus
 
 ### 📚 Documentation
 
-- `docs/architecture.md` (21KB): Architecture overview with ASCII diagrams
-- `docs/CODEAGENT-WRAPPER.md` (9KB): Complete usage guide
-- `docs/HOOKS.md` (4KB): Customization guide
-- `README.md`: Added documentation index, corrected default backend description
+- add OmO workflow to README and fix plugin marketplace structure
+- update FAQ for default bypass/skip-permissions behavior
+- 添加 FAQ 常见问题章节
+- update troubleshooting with idempotent PATH commands (#95)
 
-### 🔧 Important Fixes
+### 💼 Other
 
-#### codeagent-wrapper
-- Fixed Claude/Gemini backend `-C` (workdir) and `-r` (resume) parameter support (codeagent-wrapper/backend.go:80-120)
-- Corrected Claude backend permission flag logic `if cfg.SkipPermissions` (codeagent-wrapper/backend.go:95)
-- Fixed parallel mode startup banner duplication (codeagent-wrapper/main.go:184-194 removed)
-- Extract and display recent errors on abnormal exit `Logger.ExtractRecentErrors()` (codeagent-wrapper/logger.go:156)
-- Added task block index to parallel config error messages (codeagent-wrapper/config.go:245)
-- Refactored signal handling logic to avoid duplicate nil checks (codeagent-wrapper/main.go:290-305)
-- Removed binary artifacts from tracking (codeagent-wrapper, *.test, coverage.out)
+- add test-cases skill
+- add browser skill
+- BMADh和Requirements-Driven支持根据语义生成对应的文档 (#82)
+- update all readme
 
-#### Installation Scripts
-- Fixed issue #55: `op_run_command` uses Popen + selectors for real-time streaming output
-- Fixed issue #56: Display recent errors instead of entire log
-- Changed module list header from "Enabled" to "Default" to avoid ambiguity
+## [5.2.4] - 2025-12-16
 
-#### CI/CD
-- Removed `.claude/` config file validation step (.github/workflows/ci.yml:45)
-- Updated version test case from 5.1.0 → 5.2.0 (codeagent-wrapper/main_test.go:23)
 
-#### Commands & Documentation
-- Reverted `skills/codex/SKILL.md` to `codex-wrapper` for backward compatibility
+### ⚙️ Miscellaneous Tasks
 
-#### dev-workflow
-- Replaced Codex skill → codeagent skill throughout
-- Added UI auto-detection: backend tasks use codex, UI tasks use gemini
-- Corrected agent name: `develop-doc-generator` → `dev-plan-generator`
 
-### ⚙️ Configuration & Environment Variables
+- integrate git-cliff for automated changelog generation
 
-#### New Environment Variables
-- `CODEAGENT_SKIP_PERMISSIONS`: Control permission check behavior
-  - Claude backend defaults to `--dangerously-skip-permissions` enabled, set to `true` to disable
-  - Codex/Gemini backends default to permission checks enabled, set to `true` to skip
-- `CODEAGENT_MAX_PARALLEL_WORKERS`: Parallel task concurrency limit (default: unlimited, recommended: 8, max: 100)
+- bump version to 5.2.4
 
-#### Configuration Files
-- `config.schema.json`: Added `op_merge_json` schema validation
+### 🐛 Bug Fixes
 
-### ⚠️ Breaking Changes
 
-**codex-wrapper → codeagent-wrapper rename**
+- 防止 Claude backend 无限递归调用
 
-**Migration**:
-```bash
-python3 install.py --module dev --force
-```
+- isolate log files per task in parallel mode
 
-**Backward Compatibility**: `codex-wrapper/main.go` provides compatibility entry point
+### 💼 Other
 
-### 📦 Installation
 
-```bash
-# Install dev module
-python3 install.py --module dev
+- Merge pull request #70 from cexll/fix/prevent-codeagent-infinite-recursion
 
-# List all modules
-python3 install.py --list-modules
+- Merge pull request #69 from cexll/myclaude-master-20251215-073053-338465000
 
-# Verbose logging mode
-python3 install.py --module dev --verbose
-```
+- update CHANGELOG.md
 
-### 🧪 Test Results
+- Merge pull request #65 from cexll/fix/issue-64-buffer-overflow
 
-✅ **All tests passing**
-- Overall coverage: 93.4%
-- Security scan: 0 issues (gosec)
-- Linting: Pass
+## [5.2.3] - 2025-12-15
 
-### 📄 Related PRs & Issues
 
-- PR #53: Enterprise Workflow with Multi-Backend Support
-- Issue #55: Installation script execution not visible
-- Issue #56: Unfriendly error logging on abnormal exit
+### 🐛 Bug Fixes
 
-### 👥 Contributors
 
-- Claude Sonnet 4.5
-- Claude Opus 4.5
-- SWE-Agent-Bot
+- 修复 bufio.Scanner token too long 错误 ([#64](https://github.com/cexll/myclaude/issues/64))
+
+### 💼 Other
+
+
+- change version
+
+### 🧪 Testing
+
+
+- 同步测试中的版本号至 5.2.3
+
+## [5.2.2] - 2025-12-13
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- Bump version and clean up documentation
+
+### 🐛 Bug Fixes
+
+
+- fix codeagent backend claude no auto
+
+- fix install.py dev fail
+
+### 🧪 Testing
+
+
+- Fix tests for ClaudeBackend default --dangerously-skip-permissions
+
+## [5.2.1] - 2025-12-13
+
+
+### 🐛 Bug Fixes
+
+
+- fix codeagent claude and gemini root dir
+
+### 💼 Other
+
+
+- update readme
+
+## [5.2.0] - 2025-12-13
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- Update CHANGELOG and remove deprecated test files
+
+### 🐛 Bug Fixes
+
+
+- fix race condition in stdout parsing
+
+- add worker limit cap and remove legacy alias
+
+- use -r flag for gemini backend resume
+
+- clarify module list shows default state not enabled
+
+- use -r flag for claude backend resume
+
+- remove binary artifacts and improve error messages
+
+- 异常退出时显示最近错误信息
+
+- op_run_command 实时流式输出
+
+- 修复权限标志逻辑和版本号测试
+
+- 重构信号处理逻辑避免重复 nil 检查
+
+- 移除 .claude 配置文件验证步骤
+
+- 修复并行执行启动横幅重复打印问题
+
+- 修复master合并后的编译和测试问题
+
+### 💼 Other
+
+
+- Merge rc/5.2 into master: v5.2.0 release improvements
+
+- Merge pull request #53 from cexll/rc/5.2
+
+- remove docs
+
+- remove docs
+
+- add prototype prompt skill
+
+- add prd skill
+
+- update memory claude
+
+- remove command gh flow
+
+- update license
+
+- Merge branch 'master' into rc/5.2
+
+- Merge pull request #52 from cexll/fix/parallel-log-path-on-startup
+
+### 📚 Documentation
+
+
+- remove GitHub workflow related content
+
+### 🚀 Features
+
+
+- Complete skills system integration and config cleanup
+
+- Improve release notes and installation scripts
+
+- 添加终端日志输出和 verbose 模式
+
+- 完整多后端支持与安全优化
+
+- 替换 Codex 为 codeagent 并添加 UI 自动检测
+
+### 🚜 Refactor
+
+
+- 调整文件命名和技能定义
+
+### 🧪 Testing
+
+
+- 添加 ExtractRecentErrors 单元测试
+
+## [5.1.4] - 2025-12-09
+
+
+### 🐛 Bug Fixes
+
+
+- 任务启动时立即返回日志文件路径以支持实时调试
+
+## [5.1.3] - 2025-12-08
+
+
+### 🐛 Bug Fixes
+
+
+- resolve CI timing race in TestFakeCmdInfra
+
+## [5.1.2] - 2025-12-08
+
+
+### 🐛 Bug Fixes
+
+
+- 修复channel同步竞态条件和死锁问题
+
+### 💼 Other
+
+
+- Merge pull request #51 from cexll/fix/channel-sync-race-conditions
+
+- change codex-wrapper version
+
+## [5.1.1] - 2025-12-08
+
+
+### 🐛 Bug Fixes
+
+
+- 增强日志清理的安全性和可靠性
+
+- resolve data race on forceKillDelay with atomic operations
+
+### 💼 Other
+
+
+- Merge pull request #49 from cexll/freespace8/master
+
+- resolve signal handling conflict preserving testability and Windows support
+
+### 🧪 Testing
+
+
+- 补充测试覆盖提升至 89.3%
+
+## [5.1.0] - 2025-12-07
+
+
+### 💼 Other
+
+
+- Merge pull request #45 from Michaelxwb/master
+
+- 修改windows安装说明
+
+- 修改打包脚本
+
+- 支持windows系统的安装
+
+- Merge pull request #1 from Michaelxwb/feature-win
+
+- 支持window
+
+### 🚀 Features
+
+
+- 添加启动时清理日志的功能和--cleanup标志支持
+
+- implement enterprise workflow with multi-backend support
+
+## [5.0.0] - 2025-12-05
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- clarify unit-test coverage levels in requirement questions
+
+### 🐛 Bug Fixes
+
+
+- defer startup log until args parsed
+
+### 💼 Other
+
+
+- Merge branch 'master' of github.com:cexll/myclaude
+
+- Merge pull request #43 from gurdasnijor/smithery/add-badge
+
+- Add Smithery badge
+
+- Merge pull request #42 from freespace8/master
+
+### 📚 Documentation
+
+
+- rewrite documentation for v5.0 modular architecture
+
+### 🚀 Features
+
+
+- feat install.py
+
+- implement modular installation system
+
+### 🚜 Refactor
+
+
+- remove deprecated plugin modules
+
+## [4.8.2] - 2025-12-02
+
+
+### 🐛 Bug Fixes
+
+
+- skip signal test in CI environment
+
+- make forceKillDelay testable to prevent signal test timeout
+
+- correct Go version in go.mod from 1.25.3 to 1.21
+
+- fix codex wrapper async log
+
+- capture and include stderr in error messages
+
+### 💼 Other
+
+
+- Merge pull request #41 from cexll/fix-async-log
+
+- remove test case 90
+
+- optimize codex-wrapper
+
+- Merge branch 'master' into fix-async-log
+
+## [4.8.1] - 2025-12-01
+
+
+### 🎨 Styling
+
+
+- replace emoji with text labels
+
+### 🐛 Bug Fixes
+
+
+- improve --parallel parameter validation and docs
+
+### 💼 Other
+
+
+- remove codex-wrapper bin
+
+## [4.8.0] - 2025-11-30
+
+
+### 💼 Other
+
+
+- update codex skill dependencies
+
+## [4.7.3] - 2025-11-29
+
+
+### 🐛 Bug Fixes
+
+
+- 保留日志文件以便程序退出后调试并完善日志输出功能
+
+### 💼 Other
+
+
+- Merge pull request #34 from cexll/cce-worktree-master-20251129-111802-997076000
+
+- update CLAUDE.md and codex skill
+
+### 📚 Documentation
+
+
+- improve codex skill parameter best practices
+
+### 🚀 Features
+
+
+- add session resume support and improve output format
+
+- add parallel execution support to codex-wrapper
+
+- add async logging to temp file with lifecycle management
+
+## [4.7.2] - 2025-11-28
+
+
+### 🐛 Bug Fixes
+
+
+- improve buffer size and streamline message extraction
+
+### 💼 Other
+
+
+- Merge pull request #32 from freespace8/master
+
+### 🧪 Testing
+
+
+- 增加对超大单行文本和非字符串文本的处理测试
+
+## [4.7.1] - 2025-11-27
+
+
+### 💼 Other
+
+
+- optimize dev pipline
+
+- Merge feat/codex-wrapper: fix repository URLs
+
+## [4.7] - 2025-11-27
+
+
+### 🐛 Bug Fixes
+
+
+- update repository URLs to cexll/myclaude
+
+## [4.7-alpha1] - 2025-11-27
+
+
+### 🐛 Bug Fixes
+
+
+- fix marketplace schema validation error in dev-workflow plugin
+
+### 💼 Other
+
+
+- Merge pull request #29 from cexll/feat/codex-wrapper
+
+- Add codex-wrapper Go implementation
+
+- update readme
+
+- update readme
+
+## [4.6] - 2025-11-25
+
+
+### 💼 Other
+
+
+- update dev workflow
+
+- update dev workflow
+
+## [4.5] - 2025-11-25
+
+
+### 🐛 Bug Fixes
+
+
+- fix codex skill eof
+
+### 💼 Other
+
+
+- update dev workflow plugin
+
+- update readme
+
+## [4.4] - 2025-11-22
+
+
+### 🐛 Bug Fixes
+
+
+- fix codex skill timeout and add more log
+
+- fix codex skill
+
+### 💼 Other
+
+
+- update gemini skills
+
+- update dev workflow
+
+- update codex skills model config
+
+- Merge branch 'master' of github.com:cexll/myclaude
+
+- Merge pull request #24 from cexll/swe-agent/23-1763544297
+
+### 🚀 Features
+
+
+- 支持通过环境变量配置 skills 模型
+
+## [4.3] - 2025-11-19
+
+
+### 🐛 Bug Fixes
+
+
+- fix codex skills running
+
+### 💼 Other
+
+
+- update skills plugin
+
+- update gemini
+
+- update doc
+
+- Add Gemini CLI integration skill
+
+### 🚀 Features
+
+
+- feat simple dev workflow
+
+## [4.2.2] - 2025-11-15
+
+
+### 💼 Other
+
+
+- update codex skills
+
+## [4.2.1] - 2025-11-14
+
+
+### 💼 Other
+
+
+- Merge pull request #21 from Tshoiasc/master
+
+- Merge branch 'master' into master
+
+- Change default model to gpt-5.1-codex
+
+- Enhance codex.py to auto-detect long inputs and switch to stdin mode, improving handling of shell argument issues. Updated build_codex_args to support stdin and added relevant logging for task length warnings.
+
+## [4.2] - 2025-11-13
+
+
+### 🐛 Bug Fixes
+
+
+- fix codex.py wsl run err
+
+### 💼 Other
+
+
+- optimize codex skills
+
+- Merge branch 'master' of github.com:cexll/myclaude
+
+- Rename SKILLS.md to SKILL.md
+
+- optimize codex skills
+
+### 🚀 Features
+
+
+- feat codex skills
+
+## [4.1] - 2025-11-04
+
+
+### 💼 Other
+
+
+- update enhance-prompt.md response
+
+- update readme
+
+### 📚 Documentation
+
+
+- 新增 /enhance-prompt 命令并更新所有 README 文档
+
+## [4.0] - 2025-10-22
+
+
+### 🐛 Bug Fixes
+
+
+- fix skills format
+
+### 💼 Other
+
+
+- Merge branch 'master' of github.com:cexll/myclaude
+
+- Merge pull request #18 from cexll/swe-agent/17-1760969135
+
+- update requirements clarity
+
+- update .gitignore
+
+- Fix #17: Update root marketplace.json to use skills array
+
+- Fix #17: Convert requirements-clarity to correct plugin directory format
+
+- Fix #17: Convert requirements-clarity to correct plugin directory format
+
+- Convert requirements-clarity to plugin format with English prompts
+
+- Translate requirements-clarity skill to English for plugin compatibility
+
+- Add requirements-clarity Claude Skill
+
+- Add requirements clarification command
+
+- update
+
+## [3.5] - 2025-10-20
+
+
+### 💼 Other
+
+
+- Merge pull request #15 from cexll/swe-agent/13-1760944712
+
+- Fix #13: Clean up redundant README files
+
+- Optimize README structure - Solution A (modular)
+
+- Merge pull request #14 from cexll/swe-agent/12-1760944588
+
+- Fix #12: Update Makefile install paths for new directory structure
+
+## [3.4] - 2025-10-20
+
+
+### 💼 Other
+
+
+- Merge pull request #11 from cexll/swe-agent/10-1760752533
+
+- Fix marketplace metadata references
+
+- Fix plugin configuration: rename to marketplace.json and update repository URLs
+
+- Fix #10: Restructure plugin directories to ensure proper command isolation
+
+## [3.3] - 2025-10-15
+
+
+### 💼 Other
+
+
+- Update README-zh.md
+
+- Update README.md
+
+- Update marketplace.json
+
+- Update Chinese README with v3.2 plugin system documentation
+
+- Update README with v3.2 plugin system documentation
+
+## [3.2] - 2025-10-10
+
+
+### 💼 Other
+
+
+- Add Claude Code plugin system support
+
+- update readme
+
+- Add Makefile for quick deployment and update READMEs
+
+## [3.1] - 2025-09-17
+
+
+### ◀️ Revert
+
+
+- revert
+
+### 🐛 Bug Fixes
+
+
+- fixed bmad-orchestrator not fund
+
+- fix bmad
+
+### 💼 Other
+
+
+- update bmad review with codex support
+
+- 优化 BMAD 工作流和代理配置
+
+- update gpt5
+
+- support bmad output-style
+
+- update bmad user guide
+
+- update bmad readme
+
+- optimize requirements pilot
+
+- add use gpt5 codex
+
+- add bmad pilot
+
+- sync READMEs with actual commands/agents; remove nonexistent commands; enhance requirements-pilot with testing decision gate and options.
+
+- Update Chinese README and requirements-pilot command to align with latest workflow
+
+- update readme
+
+- update agent
+
+- update bugfix sub agents
+
+- Update ask support KISS YAGNI SOLID
+
+- Add comprehensive documentation and multi-agent workflow system
+
+- update commands
+<!-- generated by git-cliff -->

Makefile

@@ -1,7 +1,7 @@
 # Claude Code Multi-Agent Workflow System Makefile
 # Quick deployment for BMAD and Requirements workflows
 
-.PHONY: help install deploy-bmad deploy-requirements deploy-essentials deploy-advanced deploy-all deploy-commands deploy-agents clean test
+.PHONY: help install deploy-bmad deploy-requirements deploy-essentials deploy-advanced deploy-all deploy-commands deploy-agents clean test changelog
 
 # Default target
 help:
@@ -22,6 +22,7 @@ help:
 	@echo "  deploy-all           - Deploy everything (commands + agents)"
 	@echo "  test-bmad            - Test BMAD workflow with sample"
 	@echo "  test-requirements    - Test Requirements workflow with sample"
+	@echo "  changelog            - Update CHANGELOG.md using git-cliff"
 	@echo "  clean                - Clean generated artifacts"
 	@echo "  help                 - Show this help message"
 
@@ -145,3 +146,17 @@ all: deploy-all
 version:
 	@echo "Claude Code Multi-Agent Workflow System v3.1"
 	@echo "BMAD + Requirements-Driven Development"
+
+# Update CHANGELOG.md using git-cliff
+changelog:
+	@echo "📝 Updating CHANGELOG.md with git-cliff..."
+	@if ! command -v git-cliff > /dev/null 2>&1; then \
+		echo "❌ git-cliff not found. Installing via Homebrew..."; \
+		brew install git-cliff; \
+	fi
+	@git-cliff -o CHANGELOG.md
+	@echo "✅ CHANGELOG.md updated successfully!"
+	@echo ""
+	@echo "Preview the changes:"
+	@echo "  git diff CHANGELOG.md"
+

README.md

@@ -1,29 +1,15 @@
+[中文](README_CN.md) [English](README.md)
+
 # Claude Code Multi-Agent Workflow System
 
 [![Run in Smithery](https://smithery.ai/badge/skills/cexll)](https://smithery.ai/skills?ns=cexll&utm_source=github&utm_medium=badge)
-
-
 [![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-green)](https://github.com/cexll/myclaude)
+[![Version](https://img.shields.io/badge/Version-6.x-green)](https://github.com/cexll/myclaude)
 
-> AI-powered development automation with multi-backend execution (Codex/Claude/Gemini)
+> AI-powered development automation with multi-backend execution (Codex/Claude/Gemini/OpenCode)
 
-## Core Concept: Multi-Backend Architecture
-
-This system leverages a **dual-agent architecture** with pluggable AI backends:
-
-| Role | Agent | Responsibility |
-|------|-------|----------------|
-| **Orchestrator** | Claude Code | Planning, context gathering, verification, user interaction |
-| **Executor** | codeagent-wrapper | Code editing, test execution (Codex/Claude/Gemini backends) |
-
-**Why this separation?**
-- Claude Code excels at understanding context and orchestrating complex workflows
-- Specialized backends (Codex for code, Claude for reasoning, Gemini for prototyping) excel at focused execution
-- Backend selection via `--backend codex|claude|gemini` matches the model to the task
-
-## Quick Start(Please execute in Powershell on Windows)
+## Quick Start
 
 ```bash
 git clone https://github.com/cexll/myclaude.git
@@ -31,111 +17,23 @@ cd myclaude
 python3 install.py --install-dir ~/.claude
 ```
 
-## Workflows Overview
+## Modules Overview
 
-### 1. Dev Workflow (Recommended)
-
-**The primary workflow for most development tasks.**
-
-```bash
-/dev "implement user authentication with JWT"
-```
-
-**6-Step Process:**
-1. **Requirements Clarification** - Interactive Q&A to clarify scope
-2. **Codex Deep Analysis** - Codebase exploration and architecture decisions
-3. **Dev Plan Generation** - Structured task breakdown with test requirements
-4. **Parallel Execution** - Codex executes tasks concurrently
-5. **Coverage Validation** - Enforce ≥90% test coverage
-6. **Completion Summary** - Report with file changes and coverage stats
-
-**Key Features:**
-- Claude Code orchestrates, Codex executes all code changes
-- Automatic task parallelization for speed
-- Mandatory 90% test coverage gate
-- Rollback on failure
-
-**Best For:** Feature development, refactoring, bug fixes with tests
-
----
-
-### 2. BMAD Agile Workflow
-
-**Full enterprise agile methodology with 6 specialized agents.**
-
-```bash
-/bmad-pilot "build e-commerce checkout system"
-```
-
-**Agents:**
-| Agent | Role |
-|-------|------|
-| Product Owner | Requirements & user stories |
-| Architect | System design & tech decisions |
-| Tech Lead | Sprint planning & task breakdown |
-| Developer | Implementation |
-| Code Reviewer | Quality assurance |
-| QA Engineer | Testing & validation |
-
-**Process:**
-```
-Requirements → Architecture → Sprint Plan → Development → Review → QA
-     ↓              ↓             ↓            ↓          ↓       ↓
-   PRD.md      DESIGN.md     SPRINT.md     Code      REVIEW.md  TEST.md
-```
-
-**Best For:** Large features, team coordination, enterprise projects
-
----
-
-### 3. Requirements-Driven Workflow
-
-**Lightweight requirements-to-code pipeline.**
-
-```bash
-/requirements-pilot "implement API rate limiting"
-```
-
-**Process:**
-1. Requirements generation with quality scoring
-2. Implementation planning
-3. Code generation
-4. Review and testing
-
-**Best For:** Quick prototypes, well-defined features
-
----
-
-### 4. Development Essentials
-
-**Direct commands for daily coding tasks.**
-
-| Command | Purpose |
-|---------|---------|
-| `/code` | Implement a feature |
-| `/debug` | Debug an issue |
-| `/test` | Write tests |
-| `/review` | Code review |
-| `/optimize` | Performance optimization |
-| `/refactor` | Code refactoring |
-| `/docs` | Documentation |
-
-**Best For:** Quick tasks, no workflow overhead needed
-
-## Enterprise Workflow Features
-
-- **Multi-backend execution:** `codeagent-wrapper --backend codex|claude|gemini` (default `codex`) so you can match the model to the task without changing workflows.
-- **GitHub workflow commands:** `/gh-create-issue "short need"` creates structured issues; `/gh-issue-implement 123` pulls issue #123, drives development, and prepares the PR.
-- **Skills + hooks activation:** .claude/hooks run automation (tests, reviews), while `.claude/skills/skill-rules.json` auto-suggests the right skills. Keep hooks enabled in `.claude/settings.json` to activate the enterprise workflow helpers.
-
----
+| Module | Description | Documentation |
+|--------|-------------|---------------|
+| [do](skills/do/README.md) | **Recommended** - 7-phase feature development with codeagent orchestration | `/do` command |
+| [dev](dev-workflow/README.md) | Lightweight dev workflow with Codex integration | `/dev` command |
+| [omo](skills/omo/README.md) | Multi-agent orchestration with intelligent routing | `/omo` command |
+| [bmad](bmad-agile-workflow/README.md) | BMAD agile workflow with 6 specialized agents | `/bmad-pilot` command |
+| [requirements](requirements-driven-workflow/README.md) | Lightweight requirements-to-code pipeline | `/requirements-pilot` command |
+| [essentials](development-essentials/README.md) | Core development commands and utilities | `/code`, `/debug`, etc. |
+| [sparv](skills/sparv/README.md) | SPARV workflow (Specify→Plan→Act→Review→Vault) | `/sparv` command |
+| course | Course development (combines dev + product-requirements + test-cases) | Composite module |
 
 ## Installation
 
-### Modular Installation (Recommended)
-
 ```bash
-# Install all enabled modules (dev + essentials by default)
+# Install all enabled modules
 python3 install.py --install-dir ~/.claude
 
 # Install specific module
@@ -144,147 +42,72 @@ python3 install.py --module dev
 # List available modules
 python3 install.py --list-modules
 
-# Force overwrite existing files
+# Force overwrite
 python3 install.py --force
 ```
 
-### Available Modules
+### Module Configuration
 
-| Module | Default | Description |
-|--------|---------|-------------|
-| `dev` | ✓ Enabled | Dev workflow + Codex integration |
-| `essentials` | ✓ Enabled | Core development commands |
-| `bmad` | Disabled | Full BMAD agile workflow |
-| `requirements` | Disabled | Requirements-driven workflow |
-
-### What Gets Installed
-
-```
-~/.claude/
-├── CLAUDE.md              # Core instructions and role definition
-├── commands/              # Slash commands (/dev, /code, etc.)
-├── agents/                # Agent definitions
-├── skills/
-│   └── codex/
-│       └── SKILL.md       # Codex integration skill
-└── installed_modules.json # Installation status
-```
-
-### Configuration
-
-Edit `config.json` to customize:
+Edit `config.json` to enable/disable modules:
 
 ```json
 {
-  "version": "1.0",
-  "install_dir": "~/.claude",
   "modules": {
-    "dev": {
-      "enabled": true,
-      "operations": [
-        {"type": "merge_dir", "source": "dev-workflow"},
-        {"type": "copy_file", "source": "memorys/CLAUDE.md", "target": "CLAUDE.md"},
-        {"type": "copy_file", "source": "skills/codex/SKILL.md", "target": "skills/codex/SKILL.md"},
-        {"type": "run_command", "command": "bash install.sh"}
-      ]
-    }
+    "dev": { "enabled": true },
+    "bmad": { "enabled": false },
+    "requirements": { "enabled": false },
+    "essentials": { "enabled": false },
+    "omo": { "enabled": false },
+    "sparv": { "enabled": false },
+    "do": { "enabled": false },
+    "course": { "enabled": false }
   }
 }
 ```
 
-**Operation Types:**
-| Type | Description |
-|------|-------------|
-| `merge_dir` | Merge subdirs (commands/, agents/) into install dir |
-| `copy_dir` | Copy entire directory |
-| `copy_file` | Copy single file to target path |
-| `run_command` | Execute shell command |
-
----
-
-## Codex Integration
-
-The `codex` skill enables Claude Code to delegate code execution to Codex CLI.
-
-### Usage in Workflows
-
-```bash
-# Codex is invoked via the skill
-codeagent-wrapper - <<'EOF'
-implement @src/auth.ts with JWT validation
-EOF
-```
-
-### Parallel Execution
-
-```bash
-codeagent-wrapper --parallel <<'EOF'
----TASK---
-id: backend_api
-workdir: /project/backend
----CONTENT---
-implement REST endpoints for /api/users
-
----TASK---
-id: frontend_ui
-workdir: /project/frontend
-dependencies: backend_api
----CONTENT---
-create React components consuming the API
-EOF
-```
-
-### Install Codex Wrapper
-
-```bash
-# Automatic (via dev module)
-python3 install.py --module dev
-
-# Manual
-bash install.sh
-```
-
-#### Windows
-
-Windows installs place `codeagent-wrapper.exe` in `%USERPROFILE%\bin`.
-
-```powershell
-# PowerShell (recommended)
-powershell -ExecutionPolicy Bypass -File install.ps1
-
-# Batch (cmd)
-install.bat
-```
-
-**Add to PATH** (if installer doesn't detect it):
-
-```powershell
-# PowerShell - persistent for current user
-[Environment]::SetEnvironmentVariable('PATH', "$HOME\bin;" + [Environment]::GetEnvironmentVariable('PATH','User'), 'User')
-
-# PowerShell - current session only
-$Env:PATH = "$HOME\bin;$Env:PATH"
-```
-
-```batch
-REM cmd.exe - persistent for current user
-setx PATH "%USERPROFILE%\bin;%PATH%"
-```
-
----
-
 ## Workflow Selection Guide
 
-| Scenario | Recommended Workflow |
-|----------|---------------------|
-| New feature with tests | `/dev` |
-| Quick bug fix | `/debug` or `/code` |
-| Large multi-sprint feature | `/bmad-pilot` |
-| Prototype or POC | `/requirements-pilot` |
-| Code review | `/review` |
-| Performance issue | `/optimize` |
+| Scenario | Recommended |
+|----------|-------------|
+| Feature development (default) | `/do` |
+| Lightweight feature | `/dev` |
+| Bug investigation + fix | `/omo` |
+| Large enterprise project | `/bmad-pilot` |
+| Quick prototype | `/requirements-pilot` |
+| Simple task | `/code`, `/debug` |
 
----
+## Core Architecture
+
+| Role | Agent | Responsibility |
+|------|-------|----------------|
+| **Orchestrator** | Claude Code | Planning, context gathering, verification |
+| **Executor** | codeagent-wrapper | Code editing, test execution (Codex/Claude/Gemini/OpenCode) |
+
+## Backend CLI Requirements
+
+| Backend | Required Features |
+|---------|-------------------|
+| Codex | `codex e`, `--json`, `-C`, `resume` |
+| Claude | `--output-format stream-json`, `-r` |
+| Gemini | `-o stream-json`, `-y`, `-r` |
+
+## Directory Structure After Installation
+
+```
+~/.claude/
+├── bin/codeagent-wrapper
+├── CLAUDE.md
+├── commands/
+├── agents/
+├── skills/
+└── config.json
+```
+
+## Documentation
+
+- [Codeagent-Wrapper Guide](docs/CODEAGENT-WRAPPER.md)
+- [Hooks Documentation](docs/HOOKS.md)
+- [codeagent-wrapper](codeagent-wrapper/README.md)
 
 ## Troubleshooting
 
@@ -292,52 +115,38 @@ 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
-
-# Reinstall
 bash install.sh
 ```
 
-**Permission denied:**
-```bash
-python3 install.py --install-dir ~/.claude --force
-```
-
 **Module not loading:**
 ```bash
-# Check installation status
 cat ~/.claude/installed_modules.json
-
-# Reinstall specific module
-python3 install.py --module dev --force
+python3 install.py --module <name> --force
 ```
 
----
+**Backend CLI errors:**
+```bash
+which codex && codex --version
+which claude && claude --version
+which gemini && gemini --version
+```
 
-## Documentation
+## FAQ
 
-### Core Guides
-- **[Architecture Overview](docs/architecture.md)** - System architecture and component design
-- **[Codeagent-Wrapper Guide](docs/CODEAGENT-WRAPPER.md)** - Multi-backend execution wrapper
-- **[GitHub Workflow Guide](docs/GITHUB-WORKFLOW.md)** - Issue-to-PR automation
-- **[Hooks Documentation](docs/HOOKS.md)** - Custom hooks and automation
+| Issue | Solution |
+|-------|----------|
+| "Unknown event format" | Logging display issue, can be ignored |
+| Gemini can't read .gitignore files | Remove from .gitignore or use different backend |
+| `/dev` slow | Check logs, try faster model, use single repo |
+| Codex permission denied | Set `approval_policy = "never"` in ~/.codex/config.yaml |
 
-### Additional Resources
-- **[Enterprise Workflow Ideas](docs/enterprise-workflow-ideas.md)** - Advanced patterns and best practices
-- **[Installation Log](install.log)** - Installation history and troubleshooting
-
----
+See [GitHub Issues](https://github.com/cexll/myclaude/issues) for more.
 
 ## License
 
-AGPL-3.0 License - see [LICENSE](LICENSE)
+AGPL-3.0 - see [LICENSE](LICENSE)
 
 ## Support
 
-- **Issues**: [GitHub Issues](https://github.com/cexll/myclaude/issues)
-- **Documentation**: [docs/](docs/)
-
----
-
-**Claude Code + Codex = Better Development** - Orchestration meets execution.
+- [GitHub Issues](https://github.com/cexll/myclaude/issues)
+- [Documentation](docs/)

README_CN.md

@@ -2,25 +2,11 @@
 
 [![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-green)](https://github.com/cexll/myclaude)
+[![Version](https://img.shields.io/badge/Version-6.x-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)
+> AI 驱动的开发自动化 - 多后端执行架构 (Codex/Claude/Gemini/OpenCode)
 
-## 核心概念：多后端架构
-
-本系统采用**双智能体架构**与可插拔 AI 后端：
-
-| 角色 | 智能体 | 职责 |
-|------|-------|------|
-| **编排者** | Claude Code | 规划、上下文收集、验证、用户交互 |
-| **执行者** | codeagent-wrapper | 代码编辑、测试执行（Codex/Claude/Gemini 后端）|
-
-**为什么分离？**
-- Claude Code 擅长理解上下文和编排复杂工作流
-- 专业后端（Codex 擅长代码、Claude 擅长推理、Gemini 擅长原型）专注执行
-- 通过 `--backend codex|claude|gemini` 匹配模型与任务
-
-## 快速开始（windows上请在Powershell中执行）
+## 快速开始
 
 ```bash
 git clone https://github.com/cexll/myclaude.git
@@ -28,37 +14,125 @@ cd myclaude
 python3 install.py --install-dir ~/.claude
 ```
 
-## 工作流概览
+## 模块概览
 
-### 1. Dev 工作流（推荐）
+| 模块 | 描述 | 文档 |
+|------|------|------|
+| [do](skills/do/README.md) | **推荐** - 7 阶段功能开发 + codeagent 编排 | `/do` 命令 |
+| [dev](dev-workflow/README.md) | 轻量级开发工作流 + Codex 集成 | `/dev` 命令 |
+| [omo](skills/omo/README.md) | 多智能体编排 + 智能路由 | `/omo` 命令 |
+| [bmad](bmad-agile-workflow/README.md) | BMAD 敏捷工作流 + 6 个专业智能体 | `/bmad-pilot` 命令 |
+| [requirements](requirements-driven-workflow/README.md) | 轻量级需求到代码流水线 | `/requirements-pilot` 命令 |
+| [essentials](development-essentials/README.md) | 核心开发命令和工具 | `/code`, `/debug` 等 |
+| [sparv](skills/sparv/README.md) | SPARV 工作流 (Specify→Plan→Act→Review→Vault) | `/sparv` 命令 |
+| course | 课程开发（组合 dev + product-requirements + test-cases） | 组合模块 |
 
-**大多数开发任务的首选工作流。**
+## 核心架构
+
+| 角色 | 智能体 | 职责 |
+|------|-------|------|
+| **编排者** | Claude Code | 规划、上下文收集、验证 |
+| **执行者** | codeagent-wrapper | 代码编辑、测试执行（Codex/Claude/Gemini/OpenCode 后端）|
+
+## 工作流详解
+
+### do 工作流（推荐）
+
+7 阶段功能开发，通过 codeagent-wrapper 编排多个智能体。**大多数功能开发任务的首选工作流。**
+
+```bash
+/do "添加用户登录功能"
+```
+
+**7 阶段：**
+| 阶段 | 名称 | 目标 |
+|------|------|------|
+| 1 | Discovery | 理解需求 |
+| 2 | Exploration | 映射代码库模式 |
+| 3 | Clarification | 解决歧义（**强制**）|
+| 4 | Architecture | 设计实现方案 |
+| 5 | Implementation | 构建功能（**需审批**）|
+| 6 | Review | 捕获缺陷 |
+| 7 | Summary | 记录结果 |
+
+**智能体：**
+- `code-explorer` - 代码追踪、架构映射
+- `code-architect` - 设计方案、文件规划
+- `code-reviewer` - 代码审查、简化建议
+- `develop` - 实现代码、运行测试
+
+---
+
+### Dev 工作流
+
+轻量级开发工作流，适合简单功能开发。
 
 ```bash
 /dev "实现 JWT 用户认证"
 ```
 
 **6 步流程：**
-1. **需求澄清** - 交互式问答明确范围
-2. **Codex 深度分析** - 代码库探索和架构决策
-3. **开发计划生成** - 结构化任务分解和测试要求
-4. **并行执行** - Codex 并发执行任务
-5. **覆盖率验证** - 强制 ≥90% 测试覆盖率
-6. **完成总结** - 文件变更和覆盖率报告
-
-**核心特性：**
-- Claude Code 编排，Codex 执行所有代码变更
-- 自动任务并行化提升速度
-- 强制 90% 测试覆盖率门禁
-- 失败自动回滚
-
-**适用场景：** 功能开发、重构、带测试的 bug 修复
+1. 需求澄清 - 交互式问答
+2. Codex 深度分析 - 代码库探索
+3. 开发计划生成 - 结构化任务分解
+4. 并行执行 - Codex 并发执行
+5. 覆盖率验证 - 强制 ≥90%
+6. 完成总结 - 报告生成
 
 ---
 
-### 2. BMAD 敏捷工作流
+### OmO 多智能体编排器
 
-**包含 6 个专业智能体的完整企业敏捷方法论。**
+基于风险信号智能路由任务到专业智能体。
+
+```bash
+/omo "分析并修复这个认证 bug"
+```
+
+**智能体层级：**
+| 智能体 | 角色 | 后端 |
+|-------|------|------|
+| `oracle` | 技术顾问 | Claude |
+| `librarian` | 外部研究 | Claude |
+| `explore` | 代码库搜索 | OpenCode |
+| `develop` | 代码实现 | Codex |
+| `frontend-ui-ux-engineer` | UI/UX 专家 | Gemini |
+| `document-writer` | 文档撰写 | Gemini |
+
+**常用配方：**
+- 解释代码：`explore`
+- 位置已知的小修复：直接 `develop`
+- Bug 修复（位置未知）：`explore → develop`
+- 跨模块重构：`explore → oracle → develop`
+
+---
+
+### SPARV 工作流
+
+极简 5 阶段工作流：Specify → Plan → Act → Review → Vault。
+
+```bash
+/sparv "实现订单导出功能"
+```
+
+**核心规则：**
+- **10 分规格门**：得分 0-10，必须 >=9 才能进入 Plan
+- **2 动作保存**：每 2 次工具调用写入 journal.md
+- **3 失败协议**：连续 3 次失败后停止并上报
+- **EHRB**：高风险操作需明确确认
+
+**评分维度（各 0-2 分）：**
+1. Value - 为什么做，可验证的收益
+2. Scope - MVP + 不在范围内的内容
+3. Acceptance - 可测试的验收标准
+4. Boundaries - 错误/性能/兼容/安全边界
+5. Risk - EHRB/依赖/未知 + 处理方式
+
+---
+
+### BMAD 敏捷工作流
+
+完整企业敏捷方法论 + 6 个专业智能体。
 
 ```bash
 /bmad-pilot "构建电商结账系统"
@@ -69,43 +143,36 @@ python3 install.py --install-dir ~/.claude
 |-------|------|
 | Product Owner | 需求与用户故事 |
 | Architect | 系统设计与技术决策 |
-| Tech Lead | Sprint 规划与任务分解 |
+| Scrum Master | Sprint 规划与任务分解 |
 | Developer | 实现 |
 | Code Reviewer | 质量保证 |
 | QA Engineer | 测试与验证 |
 
-**流程：**
-```
-需求 → 架构 → Sprint计划 → 开发 → 审查 → QA
- ↓      ↓       ↓         ↓      ↓      ↓
-PRD.md DESIGN.md SPRINT.md Code REVIEW.md TEST.md
-```
-
-**适用场景：** 大型功能、团队协作、企业项目
+**审批门：**
+- PRD 完成后（90+ 分）需用户审批
+- 架构完成后（90+ 分）需用户审批
 
 ---
 
-### 3. 需求驱动工作流
+### 需求驱动工作流
 
-**轻量级需求到代码流水线。**
+轻量级需求到代码流水线。
 
 ```bash
 /requirements-pilot "实现 API 限流"
 ```
 
-**流程：**
-1. 带质量评分的需求生成
-2. 实现规划
-3. 代码生成
-4. 审查和测试
-
-**适用场景：** 快速原型、明确定义的功能
+**100 分质量评分：**
+- 功能清晰度：30 分
+- 技术具体性：25 分
+- 实现完整性：25 分
+- 业务上下文：20 分
 
 ---
 
-### 4. 开发基础命令
+### 开发基础命令
 
-**日常编码任务的直接命令。**
+日常编码任务的直接命令。
 
 | 命令 | 用途 |
 |------|------|
@@ -117,16 +184,12 @@ PRD.md DESIGN.md SPRINT.md Code REVIEW.md TEST.md
 | `/refactor` | 代码重构 |
 | `/docs` | 编写文档 |
 
-**适用场景：** 快速任务，无需工作流开销
-
 ---
 
 ## 安装
 
-### 模块化安装（推荐）
-
 ```bash
-# 安装所有启用的模块（默认：dev + essentials）
+# 安装所有启用的模块
 python3 install.py --install-dir ~/.claude
 
 # 安装特定模块
@@ -135,186 +198,77 @@ python3 install.py --module dev
 # 列出可用模块
 python3 install.py --list-modules
 
-# 强制覆盖现有文件
+# 强制覆盖
 python3 install.py --force
 ```
 
-### 可用模块
+### 模块配置
 
-| 模块 | 默认 | 描述 |
-|------|------|------|
-| `dev` | ✓ 启用 | Dev 工作流 + Codex 集成 |
-| `essentials` | ✓ 启用 | 核心开发命令 |
-| `bmad` | 禁用 | 完整 BMAD 敏捷工作流 |
-| `requirements` | 禁用 | 需求驱动工作流 |
-
-### 安装内容
-
-```
-~/.claude/
-├── 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
-└── installed_modules.json # 安装状态
-```
-
-### 配置
-
-编辑 `config.json` 自定义：
+编辑 `config.json` 启用/禁用模块：
 
 ```json
 {
-  "version": "1.0",
-  "install_dir": "~/.claude",
   "modules": {
-    "dev": {
-      "enabled": true,
-      "operations": [
-        {"type": "merge_dir", "source": "dev-workflow"},
-        {"type": "copy_file", "source": "memorys/CLAUDE.md", "target": "CLAUDE.md"},
-        {"type": "copy_file", "source": "skills/codex/SKILL.md", "target": "skills/codex/SKILL.md"},
-        {"type": "run_command", "command": "bash install.sh"}
-      ]
-    }
+    "dev": { "enabled": true },
+    "bmad": { "enabled": false },
+    "requirements": { "enabled": false },
+    "essentials": { "enabled": false },
+    "omo": { "enabled": false },
+    "sparv": { "enabled": false },
+    "do": { "enabled": false },
+    "course": { "enabled": false }
   }
 }
 ```
 
-**操作类型：**
-| 类型 | 描述 |
-|------|------|
-| `merge_dir` | 合并子目录 (commands/, agents/) 到安装目录 |
-| `copy_dir` | 复制整个目录 |
-| `copy_file` | 复制单个文件到目标路径 |
-| `run_command` | 执行 shell 命令 |
-
----
-
-## Codex 集成
-
-`codex` 技能使 Claude Code 能够将代码执行委托给 Codex CLI。
-
-### 工作流中的使用
-
-```bash
-# 通过技能调用 Codex
-codeagent-wrapper - <<'EOF'
-在 @src/auth.ts 中实现 JWT 验证
-EOF
-```
-
-### 并行执行
-
-```bash
-codeagent-wrapper --parallel <<'EOF'
----TASK---
-id: backend_api
-workdir: /project/backend
----CONTENT---
-实现 /api/users 的 REST 端点
-
----TASK---
-id: frontend_ui
-workdir: /project/frontend
-dependencies: backend_api
----CONTENT---
-创建消费 API 的 React 组件
-EOF
-```
-
-### 安装 Codex Wrapper
-
-```bash
-# 自动（通过 dev 模块）
-python3 install.py --module dev
-
-# 手动
-bash install.sh
-```
-
-#### Windows 系统
-
-Windows 系统会将 `codeagent-wrapper.exe` 安装到 `%USERPROFILE%\bin`。
-
-```powershell
-# PowerShell（推荐）
-powershell -ExecutionPolicy Bypass -File install.ps1
-
-# 批处理（cmd）
-install.bat
-```
-
-**添加到 PATH**（如果安装程序未自动检测）：
-
-```powershell
-# PowerShell - 永久添加（当前用户）
-[Environment]::SetEnvironmentVariable('PATH', "$HOME\bin;" + [Environment]::GetEnvironmentVariable('PATH','User'), 'User')
-
-# PowerShell - 仅当前会话
-$Env:PATH = "$HOME\bin;$Env:PATH"
-```
-
-```batch
-REM cmd.exe - 永久添加（当前用户）
-setx PATH "%USERPROFILE%\bin;%PATH%"
-```
-
----
-
 ## 工作流选择指南
 
-| 场景 | 推荐工作流 |
-|------|----------|
-| 带测试的新功能 | `/dev` |
-| 快速 bug 修复 | `/debug` 或 `/code` |
-| 大型多 Sprint 功能 | `/bmad-pilot` |
-| 原型或 POC | `/requirements-pilot` |
-| 代码审查 | `/review` |
-| 性能问题 | `/optimize` |
+| 场景 | 推荐 |
+|------|------|
+| 功能开发（默认） | `/do` |
+| 轻量级功能 | `/dev` |
+| Bug 调查 + 修复 | `/omo` |
+| 大型企业项目 | `/bmad-pilot` |
+| 快速原型 | `/requirements-pilot` |
+| 简单任务 | `/code`, `/debug` |
 
----
+## 后端 CLI 要求
+
+| 后端 | 必需功能 |
+|------|----------|
+| Codex | `codex e`, `--json`, `-C`, `resume` |
+| Claude | `--output-format stream-json`, `-r` |
+| Gemini | `-o stream-json`, `-y`, `-r` |
 
 ## 故障排查
 
-### 常见问题
-
 **Codex wrapper 未找到：**
 ```bash
-# 检查 PATH
-echo $PATH | grep -q "$HOME/bin" || echo 'export PATH="$HOME/bin:$PATH"' >> ~/.zshrc
-
-# 重新安装
 bash install.sh
 ```
 
-**权限被拒绝：**
-```bash
-python3 install.py --install-dir ~/.claude --force
-```
-
 **模块未加载：**
 ```bash
-# 检查安装状态
 cat ~/.claude/installed_modules.json
-
-# 重新安装特定模块
-python3 install.py --module dev --force
+python3 install.py --module <name> --force
 ```
 
----
+## FAQ
+
+| 问题 | 解决方案 |
+|------|----------|
+| "Unknown event format" | 日志显示问题，可忽略 |
+| Gemini 无法读取 .gitignore 文件 | 从 .gitignore 移除或使用其他后端 |
+| `/dev` 执行慢 | 检查日志，尝试更快模型，使用单一仓库 |
+| Codex 权限拒绝 | 在 ~/.codex/config.yaml 设置 `approval_policy = "never"` |
+
+更多问题请访问 [GitHub Issues](https://github.com/cexll/myclaude/issues)。
 
 ## 许可证
 
-AGPL-3.0 License - 查看 [LICENSE](LICENSE)
+AGPL-3.0 - 查看 [LICENSE](LICENSE)
 
 ## 支持
 
-- **问题反馈**: [GitHub Issues](https://github.com/cexll/myclaude/issues)
-- **文档**: [docs/](docs/)
-
----
-
-**Claude Code + Codex = 更好的开发** - 编排遇见执行。
+- [GitHub Issues](https://github.com/cexll/myclaude/issues)
+- [文档](docs/)

bmad-agile-workflow/.claude-plugin/marketplace.json

@@ -1,37 +0,0 @@
-{
-  "name": "bmad-agile-workflow",
-  "source": "./",
-  "description": "Full BMAD agile workflow with role-based agents (PO, Architect, SM, Dev, QA) and interactive approval gates",
-  "version": "1.0.0",
-  "author": {
-    "name": "Claude Code Dev Workflows",
-    "url": "https://github.com/cexll/myclaude"
-  },
-  "homepage": "https://github.com/cexll/myclaude",
-  "repository": "https://github.com/cexll/myclaude",
-  "license": "MIT",
-  "keywords": [
-    "bmad",
-    "agile",
-    "scrum",
-    "product-owner",
-    "architect",
-    "developer",
-    "qa",
-    "workflow-orchestration"
-  ],
-  "category": "workflows",
-  "strict": false,
-  "commands": [
-    "./commands/bmad-pilot.md"
-  ],
-  "agents": [
-    "./agents/bmad-po.md",
-    "./agents/bmad-architect.md",
-    "./agents/bmad-sm.md",
-    "./agents/bmad-dev.md",
-    "./agents/bmad-qa.md",
-    "./agents/bmad-orchestrator.md",
-    "./agents/bmad-review.md"
-  ]
-}

bmad-agile-workflow/.claude-plugin/plugin.json

@@ -0,0 +1,9 @@
+{
+  "name": "bmad",
+  "description": "Full BMAD agile workflow with role-based agents (PO, Architect, SM, Dev, QA) and interactive approval gates",
+  "version": "5.6.1",
+  "author": {
+    "name": "cexll",
+    "email": "cexll@cexll.com"
+  }
+}

bmad-agile-workflow/README.md

@@ -0,0 +1,109 @@
+# bmad - BMAD Agile Workflow
+
+Full enterprise agile methodology with 6 specialized agents, UltraThink analysis, and repository-aware development.
+
+## Installation
+
+```bash
+python install.py --module bmad
+```
+
+## Usage
+
+```bash
+/bmad-pilot <PROJECT_DESCRIPTION> [OPTIONS]
+```
+
+### Options
+
+| Option | Description |
+|--------|-------------|
+| `--skip-tests` | Skip QA testing phase |
+| `--direct-dev` | Skip SM planning, go directly to development |
+| `--skip-scan` | Skip initial repository scanning |
+
+## Workflow Phases
+
+| Phase | Agent | Deliverable | Description |
+|-------|-------|-------------|-------------|
+| 0 | Orchestrator | `00-repo-scan.md` | Repository scanning with UltraThink analysis |
+| 1 | Product Owner (PO) | `01-product-requirements.md` | PRD with 90+ quality score required |
+| 2 | Architect | `02-system-architecture.md` | Technical design with 90+ score required |
+| 3 | Scrum Master (SM) | `03-sprint-plan.md` | Sprint backlog with stories and estimates |
+| 4 | Developer | Implementation code | Multi-sprint implementation |
+| 4.5 | Reviewer | `04-dev-reviewed.md` | Code review (Pass/Pass with Risk/Fail) |
+| 5 | QA Engineer | Test suite | Comprehensive testing and validation |
+
+## Agents
+
+| Agent | Role |
+|-------|------|
+| `bmad-orchestrator` | Repository scanning, workflow coordination |
+| `bmad-po` | Requirements gathering, PRD creation |
+| `bmad-architect` | System design, technology decisions |
+| `bmad-sm` | Sprint planning, task breakdown |
+| `bmad-dev` | Code implementation |
+| `bmad-review` | Code review, quality assessment |
+| `bmad-qa` | Testing, validation |
+
+## Approval Gates
+
+Two mandatory stop points require explicit user approval:
+
+1. **After PRD** (Phase 1 → 2): User must approve requirements before architecture
+2. **After Architecture** (Phase 2 → 3): User must approve design before implementation
+
+## Output Structure
+
+```
+.claude/specs/{feature_name}/
+├── 00-repo-scan.md
+├── 01-product-requirements.md
+├── 02-system-architecture.md
+├── 03-sprint-plan.md
+└── 04-dev-reviewed.md
+```
+
+## UltraThink Methodology
+
+Applied throughout the workflow for deep analysis:
+
+1. **Hypothesis Generation** - Form hypotheses about the problem
+2. **Evidence Collection** - Gather evidence from codebase
+3. **Pattern Recognition** - Identify recurring patterns
+4. **Synthesis** - Create comprehensive understanding
+5. **Validation** - Cross-check findings
+
+## Interactive Confirmation Flow
+
+PO and Architect phases use iterative refinement:
+
+1. Agent produces initial draft + quality score
+2. Orchestrator presents to user with clarification questions
+3. User provides responses
+4. Agent refines until quality >= 90
+5. User confirms to save deliverable
+
+## When to Use
+
+- Large multi-sprint features
+- Enterprise projects requiring documentation
+- Team coordination scenarios
+- Projects needing formal approval gates
+
+## Directory Structure
+
+```
+bmad-agile-workflow/
+├── README.md
+├── commands/
+│   └── bmad-pilot.md
+└── agents/
+    ├── bmad-orchestrator.md
+    ├── bmad-po.md
+    ├── bmad-architect.md
+    ├── bmad-sm.md
+    ├── bmad-dev.md
+    ├── bmad-review.md
+    └── bmad-qa.md
+```

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

cliff.toml

@@ -0,0 +1,72 @@
+# git-cliff configuration file
+# https://git-cliff.org/docs/configuration
+
+[changelog]
+# changelog header
+header = """
+# Changelog
+
+All notable changes to this project will be documented in this file.
+"""
+# template for the changelog body
+body = """
+{% if version %}
+## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }}
+{% else %}
+## Unreleased
+{% endif %}
+{% for group, commits in commits | group_by(attribute="group") %}
+### {{ group }}
+
+{% for commit in commits %}
+- {{ commit.message | split(pat="\n") | first }}
+{% endfor -%}
+{% endfor -%}
+"""
+# remove the leading and trailing whitespace from the template
+trim = true
+# changelog footer
+footer = """
+<!-- generated by git-cliff -->
+"""
+
+[git]
+# parse the commits based on https://www.conventionalcommits.org
+conventional_commits = true
+# filter out the commits that are not conventional
+filter_unconventional = false
+# process each line of a commit as an individual commit
+split_commits = false
+# regex for preprocessing the commit messages
+commit_preprocessors = [
+  { pattern = '\((\w+\s)?#([0-9]+)\)', replace = "([#${2}](https://github.com/cexll/myclaude/issues/${2}))" },
+]
+# regex for parsing and grouping commits
+commit_parsers = [
+  { message = "^feat", group = "🚀 Features" },
+  { message = "^fix", group = "🐛 Bug Fixes" },
+  { message = "^doc", group = "📚 Documentation" },
+  { message = "^perf", group = "⚡ Performance" },
+  { message = "^refactor", group = "🚜 Refactor" },
+  { message = "^style", group = "🎨 Styling" },
+  { message = "^test", group = "🧪 Testing" },
+  { message = "^chore\\(release\\):", skip = true },
+  { message = "^chore", group = "⚙️ Miscellaneous Tasks" },
+  { body = ".*security", group = "🛡️ Security" },
+  { message = "^revert", group = "◀️ Revert" },
+  { message = ".*", group = "💼 Other" },
+]
+# protect breaking changes from being skipped due to matching a skipping commit_parser
+protect_breaking_commits = false
+# filter out the commits that are not matched by commit parsers
+filter_commits = false
+# glob pattern for matching git tags
+tag_pattern = "v[0-9]*"
+# regex for skipping tags
+skip_tags = "v0.1.0-beta.1"
+# regex for ignoring tags
+ignore_tags = ""
+# sort the tags topologically
+topo_order = false
+# sort the commits inside sections by oldest/newest order
+sort_commits = "newest"

codeagent-wrapper/.github/workflows/ci.yml

@@ -0,0 +1,39 @@
+name: CI
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        go-version: ["1.21", "1.22"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version: ${{ matrix.go-version }}
+          cache: true
+      - name: Test
+        run: make test
+      - name: Build
+        run: make build
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version: "1.22"
+          cache: true
+      - name: Lint
+        run: make lint
+

codeagent-wrapper/.gitignore

@@ -1,4 +1,7 @@
 # Build artifacts
+bin/
+codeagent
+codeagent.exe
 codeagent-wrapper
 codeagent-wrapper.exe
 *.test
@@ -9,3 +12,12 @@ coverage*.out
 cover.out
 cover_*.out
 coverage.html
+
+# Logs
+*.log
+
+# Temp files
+*.tmp
+*.swp
+*~
+.DS_Store

codeagent-wrapper/Makefile

@@ -0,0 +1,37 @@
+GO ?= go
+
+TOOLS_BIN := $(CURDIR)/bin
+TOOLCHAIN ?= go1.22.0
+GOLANGCI_LINT_VERSION := v1.56.2
+STATICCHECK_VERSION := v0.4.7
+
+GOLANGCI_LINT := $(TOOLS_BIN)/golangci-lint
+STATICCHECK := $(TOOLS_BIN)/staticcheck
+
+.PHONY: build test lint clean install
+
+build:
+	$(GO) build -o codeagent ./cmd/codeagent
+	$(GO) build -o codeagent-wrapper ./cmd/codeagent-wrapper
+
+test:
+	$(GO) test ./...
+
+$(GOLANGCI_LINT):
+	@mkdir -p $(TOOLS_BIN)
+	GOTOOLCHAIN=$(TOOLCHAIN) GOBIN=$(TOOLS_BIN) $(GO) install github.com/golangci/golangci-lint/cmd/golangci-lint@$(GOLANGCI_LINT_VERSION)
+
+$(STATICCHECK):
+	@mkdir -p $(TOOLS_BIN)
+	GOTOOLCHAIN=$(TOOLCHAIN) GOBIN=$(TOOLS_BIN) $(GO) install honnef.co/go/tools/cmd/staticcheck@$(STATICCHECK_VERSION)
+
+lint: $(GOLANGCI_LINT) $(STATICCHECK)
+	GOTOOLCHAIN=$(TOOLCHAIN) $(GOLANGCI_LINT) run ./...
+	GOTOOLCHAIN=$(TOOLCHAIN) $(STATICCHECK) ./...
+
+clean:
+	@python3 -c 'import glob, os; paths=["codeagent","codeagent.exe","codeagent-wrapper","codeagent-wrapper.exe","coverage.out","cover.out","coverage.html"]; paths += glob.glob("coverage*.out") + glob.glob("cover_*.out") + glob.glob("*.test"); [os.remove(p) for p in paths if os.path.exists(p)]'
+
+install:
+	$(GO) install ./cmd/codeagent
+	$(GO) install ./cmd/codeagent-wrapper

codeagent-wrapper/README.md

@@ -0,0 +1,152 @@
+# codeagent-wrapper
+
+`codeagent-wrapper` 是一个用 Go 编写的“多后端 AI 代码代理”命令行包装器：用统一的 CLI 入口封装不同的 AI 工具后端（Codex / Claude / Gemini / Opencode），并提供一致的参数、配置与会话恢复体验。
+
+入口：`cmd/codeagent/main.go`（生成二进制名：`codeagent`）和 `cmd/codeagent-wrapper/main.go`（生成二进制名：`codeagent-wrapper`）。两者行为一致。
+
+## 功能特性
+
+- 多后端支持：`codex` / `claude` / `gemini` / `opencode`
+- 统一命令行：`codeagent [flags] <task>` / `codeagent resume <session_id> <task> [workdir]`
+- 自动 stdin：遇到换行/特殊字符/超长任务自动走 stdin，避免 shell quoting 地狱；也可显式使用 `-`
+- 配置合并：支持配置文件与 `CODEAGENT_*` 环境变量（viper）
+- Agent 预设：从 `~/.codeagent/models.json` 读取 backend/model/prompt 等预设
+- 并行执行：`--parallel` 从 stdin 读取多任务配置，支持依赖拓扑并发执行
+- 日志清理：`codeagent cleanup` 清理旧日志（日志写入系统临时目录）
+
+## 安装
+
+要求：Go 1.21+。
+
+在仓库根目录执行：
+
+```bash
+go install ./cmd/codeagent
+go install ./cmd/codeagent-wrapper
+```
+
+安装后确认：
+
+```bash
+codeagent version
+codeagent-wrapper version
+```
+
+## 使用示例
+
+最简单用法（默认后端：`codex`）：
+
+```bash
+codeagent "分析 internal/app/cli.go 的入口逻辑，给出改进建议"
+```
+
+指定后端：
+
+```bash
+codeagent --backend claude "解释 internal/executor/parallel_config.go 的并行配置格式"
+```
+
+指定工作目录（第 2 个位置参数）：
+
+```bash
+codeagent "在当前 repo 下搜索潜在数据竞争" .
+```
+
+显式从 stdin 读取 task（使用 `-`）：
+
+```bash
+cat task.txt | codeagent -
+```
+
+恢复会话：
+
+```bash
+codeagent resume <session_id> "继续上次任务"
+```
+
+并行模式（从 stdin 读取任务配置；禁止位置参数）：
+
+```bash
+codeagent --parallel <<'EOF'
+---TASK---
+id: t1
+workdir: .
+backend: codex
+---CONTENT---
+列出本项目的主要模块以及它们的职责。
+---TASK---
+id: t2
+dependencies: t1
+backend: claude
+---CONTENT---
+基于 t1 的结论，提出重构风险点与建议。
+EOF
+```
+
+## 配置说明
+
+### 配置文件
+
+默认查找路径（当 `--config` 为空时）：
+
+- `$HOME/.codeagent/config.(yaml|yml|json|toml|...)`
+
+示例（YAML）：
+
+```yaml
+backend: codex
+model: gpt-4.1
+skip-permissions: false
+```
+
+也可以通过 `--config /path/to/config.yaml` 显式指定。
+
+### 环境变量（`CODEAGENT_*`）
+
+通过 viper 读取并自动映射 `-` 为 `_`，常用项：
+
+- `CODEAGENT_BACKEND`（`codex|claude|gemini|opencode`）
+- `CODEAGENT_MODEL`
+- `CODEAGENT_AGENT`
+- `CODEAGENT_PROMPT_FILE`
+- `CODEAGENT_REASONING_EFFORT`
+- `CODEAGENT_SKIP_PERMISSIONS`
+- `CODEAGENT_FULL_OUTPUT`（并行模式 legacy 输出）
+- `CODEAGENT_MAX_PARALLEL_WORKERS`（0 表示不限制，上限 100）
+
+### Agent 预设（`~/.codeagent/models.json`）
+
+可在 `~/.codeagent/models.json` 定义 agent → backend/model/prompt 等映射，用 `--agent <name>` 选择：
+
+```json
+{
+  "default_backend": "opencode",
+  "default_model": "opencode/grok-code",
+  "agents": {
+    "develop": {
+      "backend": "codex",
+      "model": "gpt-4.1",
+      "prompt_file": "~/.codeagent/prompts/develop.md",
+      "description": "Code development"
+    }
+  }
+}
+```
+
+## 支持的后端
+
+该项目本身不内置模型能力，依赖你本机安装并可在 `PATH` 中找到对应 CLI：
+
+- `codex`：执行 `codex e ...`（默认会添加 `--dangerously-bypass-approvals-and-sandbox`；如需关闭请设置 `CODEX_BYPASS_SANDBOX=false`）
+- `claude`：执行 `claude -p ... --output-format stream-json`（默认会跳过权限提示；如需开启请设置 `CODEAGENT_SKIP_PERMISSIONS=false`）
+- `gemini`：执行 `gemini ... -o stream-json`（可从 `~/.gemini/.env` 加载环境变量）
+- `opencode`：执行 `opencode run --format json`
+
+## 开发
+
+```bash
+make build
+make test
+make lint
+make clean
+```

codeagent-wrapper/backend.go

@@ -1,86 +0,0 @@
-package main
-
-// 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, targetArg string) []string
-	Command() string
-}
-
-type CodexBackend struct{}
-
-func (CodexBackend) Name() string { return "codex" }
-func (CodexBackend) Command() string {
-	return "codex"
-}
-func (CodexBackend) BuildArgs(cfg *Config, targetArg string) []string {
-	return buildCodexArgs(cfg, targetArg)
-}
-
-type ClaudeBackend struct{}
-
-func (ClaudeBackend) Name() string { return "claude" }
-func (ClaudeBackend) Command() string {
-	return "claude"
-}
-func (ClaudeBackend) BuildArgs(cfg *Config, targetArg string) []string {
-	if cfg == nil {
-		return nil
-	}
-	args := []string{"-p"}
-
-	// Only skip permissions when explicitly requested
-	if cfg.SkipPermissions {
-		args = append(args, "--dangerously-skip-permissions")
-	}
-
-	workdir := cfg.WorkDir
-	if workdir == "" {
-		workdir = defaultWorkdir
-	}
-
-	if cfg.Mode == "resume" {
-		if cfg.SessionID != "" {
-			// Claude CLI uses -r <session_id> for resume.
-			args = append(args, "-r", cfg.SessionID)
-		}
-	} else {
-		args = append(args, "-C", workdir)
-	}
-
-	args = append(args, "--output-format", "stream-json", "--verbose", targetArg)
-
-	return args
-}
-
-type GeminiBackend struct{}
-
-func (GeminiBackend) Name() string { return "gemini" }
-func (GeminiBackend) Command() string {
-	return "gemini"
-}
-func (GeminiBackend) BuildArgs(cfg *Config, targetArg string) []string {
-	if cfg == nil {
-		return nil
-	}
-	args := []string{"-o", "stream-json", "-y"}
-
-	workdir := cfg.WorkDir
-	if workdir == "" {
-		workdir = defaultWorkdir
-	}
-
-	if cfg.Mode == "resume" {
-		if cfg.SessionID != "" {
-			args = append(args, "-r", cfg.SessionID)
-		}
-	} else {
-		args = append(args, "-C", workdir)
-	}
-
-	args = append(args, "-p", targetArg)
-
-	return args
-}

codeagent-wrapper/backend_test.go

@@ -1,122 +0,0 @@
-package main
-
-import (
-	"reflect"
-	"testing"
-)
-
-func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
-	backend := ClaudeBackend{}
-
-	t.Run("new mode uses workdir without skip by default", func(t *testing.T) {
-		cfg := &Config{Mode: "new", WorkDir: "/repo"}
-		got := backend.BuildArgs(cfg, "todo")
-		want := []string{"-p", "-C", "/repo", "--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) {
-		cfg := &Config{Mode: "new", SkipPermissions: true}
-		got := backend.BuildArgs(cfg, "-")
-		want := []string{"-p", "--dangerously-skip-permissions", "-C", defaultWorkdir, "--output-format", "stream-json", "--verbose", "-"}
-		if !reflect.DeepEqual(got, want) {
-			t.Fatalf("got %v, want %v", got, want)
-		}
-	})
-
-	t.Run("resume mode uses session id and omits workdir", func(t *testing.T) {
-		cfg := &Config{Mode: "resume", SessionID: "sid-123", WorkDir: "/ignored"}
-		got := backend.BuildArgs(cfg, "resume-task")
-		want := []string{"-p", "-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) {
-		cfg := &Config{Mode: "resume", WorkDir: "/ignored"}
-		got := backend.BuildArgs(cfg, "follow-up")
-		want := []string{"-p", "--output-format", "stream-json", "--verbose", "follow-up"}
-		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 TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
-	t.Run("gemini new mode defaults workdir", func(t *testing.T) {
-		backend := GeminiBackend{}
-		cfg := &Config{Mode: "new", WorkDir: "/workspace"}
-		got := backend.BuildArgs(cfg, "task")
-		want := []string{"-o", "stream-json", "-y", "-C", "/workspace", "-p", "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{Mode: "resume", SessionID: "sid-999"}
-		got := backend.BuildArgs(cfg, "resume")
-		want := []string{"-o", "stream-json", "-y", "-r", "sid-999", "-p", "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{Mode: "resume"}
-		got := backend.BuildArgs(cfg, "resume")
-		want := []string{"-o", "stream-json", "-y", "-p", "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("codex build args passthrough remains intact", func(t *testing.T) {
-		backend := CodexBackend{}
-		cfg := &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)
-		}
-	})
-}
-
-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)
-		}
-	}
-}

codeagent-wrapper/bench_test.go

@@ -1,39 +0,0 @@
-package main
-
-import (
-	"testing"
-)
-
-// 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/cmd/codeagent/main.go

@@ -0,0 +1,7 @@
+package main
+
+import app "codeagent-wrapper/internal/app"
+
+func main() {
+	app.Run()
+}

codeagent-wrapper/config.go

@@ -1,272 +0,0 @@
-package main
-
-import (
-	"bytes"
-	"context"
-	"fmt"
-	"os"
-	"strconv"
-	"strings"
-)
-
-// Config holds CLI configuration
-type Config struct {
-	Mode               string // "new" or "resume"
-	Task               string
-	SessionID          string
-	WorkDir            string
-	ExplicitStdin      bool
-	Timeout            int
-	Backend            string
-	SkipPermissions    bool
-	MaxParallelWorkers int
-}
-
-// 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"`
-	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"`
-}
-
-var backendRegistry = map[string]Backend{
-	"codex":  CodexBackend{},
-	"claude": ClaudeBackend{},
-	"gemini": GeminiBackend{},
-}
-
-func selectBackend(name string) (Backend, error) {
-	key := strings.ToLower(strings.TrimSpace(name))
-	if key == "" {
-		key = defaultBackendName
-	}
-	if backend, ok := backendRegistry[key]; ok {
-		return backend, nil
-	}
-	return nil, fmt.Errorf("unsupported backend %q", name)
-}
-
-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
-	}
-}
-
-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}
-		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":
-				task.WorkDir = value
-			case "session_id":
-				task.SessionID = value
-				task.Mode = "resume"
-			case "backend":
-				task.Backend = value
-			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 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 _, 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
-}
-
-func parseArgs() (*Config, error) {
-	args := os.Args[1:]
-	if len(args) == 0 {
-		return nil, fmt.Errorf("task required")
-	}
-
-	backendName := defaultBackendName
-	skipPermissions := envFlagEnabled("CODEAGENT_SKIP_PERMISSIONS")
-	filtered := make([]string, 0, len(args))
-	for i := 0; i < len(args); i++ {
-		arg := args[i]
-		switch {
-		case arg == "--backend":
-			if i+1 >= len(args) {
-				return nil, fmt.Errorf("--backend flag requires a value")
-			}
-			backendName = args[i+1]
-			i++
-			continue
-		case strings.HasPrefix(arg, "--backend="):
-			value := strings.TrimPrefix(arg, "--backend=")
-			if value == "" {
-				return nil, fmt.Errorf("--backend flag requires a value")
-			}
-			backendName = value
-			continue
-		case arg == "--skip-permissions", arg == "--dangerously-skip-permissions":
-			skipPermissions = true
-			continue
-		case strings.HasPrefix(arg, "--skip-permissions="):
-			skipPermissions = parseBoolFlag(strings.TrimPrefix(arg, "--skip-permissions="), skipPermissions)
-			continue
-		case strings.HasPrefix(arg, "--dangerously-skip-permissions="):
-			skipPermissions = parseBoolFlag(strings.TrimPrefix(arg, "--dangerously-skip-permissions="), skipPermissions)
-			continue
-		}
-		filtered = append(filtered, arg)
-	}
-
-	if len(filtered) == 0 {
-		return nil, fmt.Errorf("task required")
-	}
-	args = filtered
-
-	cfg := &Config{WorkDir: defaultWorkdir, Backend: backendName, SkipPermissions: skipPermissions}
-	cfg.MaxParallelWorkers = 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 = args[1]
-		cfg.Task = args[2]
-		cfg.ExplicitStdin = (args[2] == "-")
-		if len(args) > 3 {
-			cfg.WorkDir = args[3]
-		}
-	} else {
-		cfg.Mode = "new"
-		cfg.Task = args[0]
-		cfg.ExplicitStdin = (args[0] == "-")
-		if len(args) > 1 {
-			cfg.WorkDir = args[1]
-		}
-	}
-
-	return cfg, nil
-}
-
-const maxParallelWorkersLimit = 100
-
-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 {
-		logWarn(fmt.Sprintf("Invalid CODEAGENT_MAX_PARALLEL_WORKERS=%q, falling back to unlimited", raw))
-		return 0
-	}
-
-	if value > maxParallelWorkersLimit {
-		logWarn(fmt.Sprintf("CODEAGENT_MAX_PARALLEL_WORKERS=%d exceeds limit, capping at %d", value, maxParallelWorkersLimit))
-		return maxParallelWorkersLimit
-	}
-
-	return value
-}

codeagent-wrapper/executor.go

@@ -1,871 +0,0 @@
-package main
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"io"
-	"os"
-	"os/exec"
-	"os/signal"
-	"sort"
-	"strings"
-	"sync"
-	"sync/atomic"
-	"syscall"
-	"time"
-)
-
-// commandRunner abstracts exec.Cmd for testability
-type commandRunner interface {
-	Start() error
-	Wait() error
-	StdoutPipe() (io.ReadCloser, error)
-	StdinPipe() (io.WriteCloser, error)
-	SetStderr(io.Writer)
-	Process() processHandle
-}
-
-// processHandle abstracts os.Process for testability
-type processHandle interface {
-	Pid() int
-	Kill() error
-	Signal(os.Signal) error
-}
-
-// realCmd implements commandRunner using exec.Cmd
-type realCmd struct {
-	cmd *exec.Cmd
-}
-
-func (r *realCmd) Start() error {
-	if r.cmd == nil {
-		return errors.New("command is nil")
-	}
-	return r.cmd.Start()
-}
-
-func (r *realCmd) Wait() error {
-	if r.cmd == nil {
-		return errors.New("command is nil")
-	}
-	return r.cmd.Wait()
-}
-
-func (r *realCmd) StdoutPipe() (io.ReadCloser, error) {
-	if r.cmd == nil {
-		return nil, errors.New("command is nil")
-	}
-	return r.cmd.StdoutPipe()
-}
-
-func (r *realCmd) StdinPipe() (io.WriteCloser, error) {
-	if r.cmd == nil {
-		return nil, errors.New("command is nil")
-	}
-	return r.cmd.StdinPipe()
-}
-
-func (r *realCmd) SetStderr(w io.Writer) {
-	if r.cmd != nil {
-		r.cmd.Stderr = w
-	}
-}
-
-func (r *realCmd) Process() processHandle {
-	if r == nil || r.cmd == nil || r.cmd.Process == nil {
-		return nil
-	}
-	return &realProcess{proc: r.cmd.Process}
-}
-
-// realProcess implements processHandle using os.Process
-type realProcess struct {
-	proc *os.Process
-}
-
-func (p *realProcess) Pid() int {
-	if p == nil || p.proc == nil {
-		return 0
-	}
-	return p.proc.Pid
-}
-
-func (p *realProcess) Kill() error {
-	if p == nil || p.proc == nil {
-		return nil
-	}
-	return p.proc.Kill()
-}
-
-func (p *realProcess) Signal(sig os.Signal) error {
-	if p == nil || p.proc == nil {
-		return nil
-	}
-	return p.proc.Signal(sig)
-}
-
-// newCommandRunner creates a new commandRunner (test hook injection point)
-var newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-	return &realCmd{cmd: commandContext(ctx, name, args...)}
-}
-
-type parseResult struct {
-	message  string
-	threadID string
-}
-
-var runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
-	if task.WorkDir == "" {
-		task.WorkDir = defaultWorkdir
-	}
-	if task.Mode == "" {
-		task.Mode = "new"
-	}
-	if task.UseStdin || shouldUseStdin(task.Task, false) {
-		task.UseStdin = true
-	}
-
-	backendName := task.Backend
-	if backendName == "" {
-		backendName = defaultBackendName
-	}
-
-	backend, err := selectBackendFn(backendName)
-	if err != nil {
-		return TaskResult{TaskID: task.ID, ExitCode: 1, Error: err.Error()}
-	}
-	task.Backend = backend.Name()
-
-	parentCtx := task.Context
-	if parentCtx == nil {
-		parentCtx = context.Background()
-	}
-	return runCodexTaskWithContext(parentCtx, task, backend, nil, false, true, timeout)
-}
-
-func topologicalSort(tasks []TaskSpec) ([][]TaskSpec, error) {
-	idToTask := make(map[string]TaskSpec, len(tasks))
-	indegree := make(map[string]int, len(tasks))
-	adj := make(map[string][]string, len(tasks))
-
-	for _, task := range tasks {
-		idToTask[task.ID] = task
-		indegree[task.ID] = 0
-	}
-
-	for _, task := range tasks {
-		for _, dep := range task.Dependencies {
-			if _, ok := idToTask[dep]; !ok {
-				return nil, fmt.Errorf("dependency %q not found for task %q", dep, task.ID)
-			}
-			indegree[task.ID]++
-			adj[dep] = append(adj[dep], task.ID)
-		}
-	}
-
-	queue := make([]string, 0, len(tasks))
-	for _, task := range tasks {
-		if indegree[task.ID] == 0 {
-			queue = append(queue, task.ID)
-		}
-	}
-
-	layers := make([][]TaskSpec, 0)
-	processed := 0
-
-	for len(queue) > 0 {
-		current := queue
-		queue = nil
-		layer := make([]TaskSpec, len(current))
-		for i, id := range current {
-			layer[i] = idToTask[id]
-			processed++
-		}
-		layers = append(layers, layer)
-
-		next := make([]string, 0)
-		for _, id := range current {
-			for _, neighbor := range adj[id] {
-				indegree[neighbor]--
-				if indegree[neighbor] == 0 {
-					next = append(next, neighbor)
-				}
-			}
-		}
-		queue = append(queue, next...)
-	}
-
-	if processed != len(tasks) {
-		cycleIDs := make([]string, 0)
-		for id, deg := range indegree {
-			if deg > 0 {
-				cycleIDs = append(cycleIDs, id)
-			}
-		}
-		sort.Strings(cycleIDs)
-		return nil, fmt.Errorf("cycle detected involving tasks: %s", strings.Join(cycleIDs, ","))
-	}
-
-	return layers, nil
-}
-
-func executeConcurrent(layers [][]TaskSpec, timeout int) []TaskResult {
-	maxWorkers := resolveMaxParallelWorkers()
-	return executeConcurrentWithContext(context.Background(), layers, timeout, maxWorkers)
-}
-
-func executeConcurrentWithContext(parentCtx context.Context, layers [][]TaskSpec, timeout int, maxWorkers int) []TaskResult {
-	totalTasks := 0
-	for _, layer := range layers {
-		totalTasks += len(layer)
-	}
-
-	results := make([]TaskResult, 0, totalTasks)
-	failed := make(map[string]TaskResult, totalTasks)
-	resultsCh := make(chan TaskResult, totalTasks)
-
-	var startPrintMu sync.Mutex
-	bannerPrinted := false
-
-	printTaskStart := func(taskID string) {
-		logger := activeLogger()
-		if logger == nil {
-			return
-		}
-		path := logger.Path()
-		if path == "" {
-			return
-		}
-		startPrintMu.Lock()
-		if !bannerPrinted {
-			fmt.Fprintln(os.Stderr, "=== Starting Parallel Execution ===")
-			bannerPrinted = true
-		}
-		fmt.Fprintf(os.Stderr, "Task %s: Log: %s\n", taskID, path)
-		startPrintMu.Unlock()
-	}
-
-	ctx := parentCtx
-	if ctx == nil {
-		ctx = context.Background()
-	}
-	ctx, cancel := context.WithCancel(ctx)
-	defer cancel()
-
-	workerLimit := maxWorkers
-	if workerLimit < 0 {
-		workerLimit = 0
-	}
-
-	var sem chan struct{}
-	if workerLimit > 0 {
-		sem = make(chan struct{}, workerLimit)
-	}
-
-	logConcurrencyPlanning(workerLimit, totalTasks)
-
-	acquireSlot := func() bool {
-		if sem == nil {
-			return true
-		}
-		select {
-		case sem <- struct{}{}:
-			return true
-		case <-ctx.Done():
-			return false
-		}
-	}
-
-	releaseSlot := func() {
-		if sem == nil {
-			return
-		}
-		select {
-		case <-sem:
-		default:
-		}
-	}
-
-	var activeWorkers int64
-
-	for _, layer := range layers {
-		var wg sync.WaitGroup
-		executed := 0
-
-		for _, task := range layer {
-			if skip, reason := shouldSkipTask(task, failed); skip {
-				res := TaskResult{TaskID: task.ID, ExitCode: 1, Error: reason}
-				results = append(results, res)
-				failed[task.ID] = res
-				continue
-			}
-
-			if ctx.Err() != nil {
-				res := cancelledTaskResult(task.ID, ctx)
-				results = append(results, res)
-				failed[task.ID] = res
-				continue
-			}
-
-			executed++
-			wg.Add(1)
-			go func(ts TaskSpec) {
-				defer wg.Done()
-				defer func() {
-					if r := recover(); r != nil {
-						resultsCh <- TaskResult{TaskID: ts.ID, ExitCode: 1, Error: fmt.Sprintf("panic: %v", r)}
-					}
-				}()
-
-				if !acquireSlot() {
-					resultsCh <- cancelledTaskResult(ts.ID, ctx)
-					return
-				}
-				defer releaseSlot()
-
-				current := atomic.AddInt64(&activeWorkers, 1)
-				logConcurrencyState("start", ts.ID, int(current), workerLimit)
-				defer func() {
-					after := atomic.AddInt64(&activeWorkers, -1)
-					logConcurrencyState("done", ts.ID, int(after), workerLimit)
-				}()
-
-				ts.Context = ctx
-				printTaskStart(ts.ID)
-				resultsCh <- runCodexTaskFn(ts, timeout)
-			}(task)
-		}
-
-		wg.Wait()
-
-		for i := 0; i < executed; i++ {
-			res := <-resultsCh
-			results = append(results, res)
-			if res.ExitCode != 0 || res.Error != "" {
-				failed[res.TaskID] = res
-			}
-		}
-	}
-
-	return results
-}
-
-func cancelledTaskResult(taskID string, ctx context.Context) TaskResult {
-	exitCode := 130
-	msg := "execution cancelled"
-	if ctx != nil && errors.Is(ctx.Err(), context.DeadlineExceeded) {
-		exitCode = 124
-		msg = "execution timeout"
-	}
-	return TaskResult{TaskID: taskID, ExitCode: exitCode, Error: msg}
-}
-
-func shouldSkipTask(task TaskSpec, failed map[string]TaskResult) (bool, string) {
-	if len(task.Dependencies) == 0 {
-		return false, ""
-	}
-
-	var blocked []string
-	for _, dep := range task.Dependencies {
-		if _, ok := failed[dep]; ok {
-			blocked = append(blocked, dep)
-		}
-	}
-
-	if len(blocked) == 0 {
-		return false, ""
-	}
-
-	return true, fmt.Sprintf("skipped due to failed dependencies: %s", strings.Join(blocked, ","))
-}
-
-func generateFinalOutput(results []TaskResult) string {
-	var sb strings.Builder
-
-	success := 0
-	failed := 0
-	for _, res := range results {
-		if res.ExitCode == 0 && res.Error == "" {
-			success++
-		} else {
-			failed++
-		}
-	}
-
-	sb.WriteString(fmt.Sprintf("=== Parallel Execution Summary ===\n"))
-	sb.WriteString(fmt.Sprintf("Total: %d | Success: %d | Failed: %d\n\n", len(results), success, failed))
-
-	for _, res := range results {
-		sb.WriteString(fmt.Sprintf("--- Task: %s ---\n", res.TaskID))
-		if res.Error != "" {
-			sb.WriteString(fmt.Sprintf("Status: FAILED (exit code %d)\nError: %s\n", res.ExitCode, res.Error))
-		} else if res.ExitCode != 0 {
-			sb.WriteString(fmt.Sprintf("Status: FAILED (exit code %d)\n", res.ExitCode))
-		} else {
-			sb.WriteString("Status: SUCCESS\n")
-		}
-		if res.SessionID != "" {
-			sb.WriteString(fmt.Sprintf("Session: %s\n", res.SessionID))
-		}
-		if res.LogPath != "" {
-			sb.WriteString(fmt.Sprintf("Log: %s\n", res.LogPath))
-		}
-		if res.Message != "" {
-			sb.WriteString(fmt.Sprintf("\n%s\n", res.Message))
-		}
-		sb.WriteString("\n")
-	}
-
-	return sb.String()
-}
-
-func buildCodexArgs(cfg *Config, targetArg string) []string {
-	if cfg.Mode == "resume" {
-		return []string{
-			"e",
-			"--skip-git-repo-check",
-			"--json",
-			"resume",
-			cfg.SessionID,
-			targetArg,
-		}
-	}
-	return []string{
-		"e",
-		"--skip-git-repo-check",
-		"-C", cfg.WorkDir,
-		"--json",
-		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 {
-	result := TaskResult{TaskID: taskSpec.ID}
-	setLogPath := func() {
-		if result.LogPath != "" {
-			return
-		}
-		if logger := activeLogger(); logger != nil {
-			result.LogPath = logger.Path()
-		}
-	}
-
-	cfg := &Config{
-		Mode:      taskSpec.Mode,
-		Task:      taskSpec.Task,
-		SessionID: taskSpec.SessionID,
-		WorkDir:   taskSpec.WorkDir,
-		Backend:   defaultBackendName,
-	}
-
-	commandName := codexCommand
-	argsBuilder := buildCodexArgsFn
-	if backend != nil {
-		commandName = backend.Command()
-		argsBuilder = backend.BuildArgs
-		cfg.Backend = backend.Name()
-	} else if taskSpec.Backend != "" {
-		cfg.Backend = taskSpec.Backend
-	} else if commandName != "" {
-		cfg.Backend = commandName
-	}
-
-	if cfg.Mode == "" {
-		cfg.Mode = "new"
-	}
-	if cfg.WorkDir == "" {
-		cfg.WorkDir = defaultWorkdir
-	}
-
-	useStdin := taskSpec.UseStdin
-	targetArg := taskSpec.Task
-	if useStdin {
-		targetArg = "-"
-	}
-
-	var codexArgs []string
-	if useCustomArgs {
-		codexArgs = customArgs
-	} else {
-		codexArgs = argsBuilder(cfg, targetArg)
-	}
-
-	prefixMsg := func(msg string) string {
-		if taskSpec.ID == "" {
-			return msg
-		}
-		return fmt.Sprintf("[Task: %s] %s", taskSpec.ID, msg)
-	}
-
-	var logInfoFn func(string)
-	var logWarnFn func(string)
-	var logErrorFn func(string)
-
-	if silent {
-		// Silent mode: only persist to file when available; avoid stderr noise.
-		logInfoFn = func(msg string) {
-			if logger := activeLogger(); logger != nil {
-				logger.Info(prefixMsg(msg))
-			}
-		}
-		logWarnFn = func(msg string) {
-			if logger := activeLogger(); logger != nil {
-				logger.Warn(prefixMsg(msg))
-			}
-		}
-		logErrorFn = func(msg string) {
-			if logger := activeLogger(); logger != nil {
-				logger.Error(prefixMsg(msg))
-			}
-		}
-	} else {
-		logInfoFn = func(msg string) { logInfo(prefixMsg(msg)) }
-		logWarnFn = func(msg string) { logWarn(prefixMsg(msg)) }
-		logErrorFn = func(msg string) { logError(prefixMsg(msg)) }
-	}
-
-	stderrBuf := &tailBuffer{limit: stderrCaptureLimit}
-
-	var stdoutLogger *logWriter
-	var stderrLogger *logWriter
-
-	var tempLogger *Logger
-	if silent && activeLogger() == nil {
-		if l, err := NewLogger(); err == nil {
-			setLogger(l)
-			tempLogger = l
-		}
-	}
-	defer func() {
-		if tempLogger != nil {
-			_ = closeLogger()
-		}
-	}()
-	defer setLogPath()
-	if logger := activeLogger(); logger != nil {
-		result.LogPath = logger.Path()
-	}
-
-	if !silent {
-		stdoutLogger = newLogWriter("CODEX_STDOUT: ", codexLogLineLimit)
-		stderrLogger = newLogWriter("CODEX_STDERR: ", codexLogLineLimit)
-	}
-
-	ctx := parentCtx
-	if ctx == nil {
-		ctx = context.Background()
-	}
-
-	ctx, cancel := context.WithTimeout(ctx, time.Duration(timeoutSec)*time.Second)
-	defer cancel()
-	ctx, stop := signal.NotifyContext(ctx, syscall.SIGINT, syscall.SIGTERM)
-	defer stop()
-
-	attachStderr := func(msg string) string {
-		return fmt.Sprintf("%s; stderr: %s", msg, stderrBuf.String())
-	}
-
-	cmd := newCommandRunner(ctx, commandName, codexArgs...)
-
-	stderrWriters := []io.Writer{stderrBuf}
-	if stderrLogger != nil {
-		stderrWriters = append(stderrWriters, stderrLogger)
-	}
-	if !silent {
-		stderrWriters = append([]io.Writer{os.Stderr}, stderrWriters...)
-	}
-	if len(stderrWriters) == 1 {
-		cmd.SetStderr(stderrWriters[0])
-	} else {
-		cmd.SetStderr(io.MultiWriter(stderrWriters...))
-	}
-
-	var stdinPipe io.WriteCloser
-	var err error
-	if useStdin {
-		stdinPipe, err = cmd.StdinPipe()
-		if err != nil {
-			logErrorFn("Failed to create stdin pipe: " + err.Error())
-			result.ExitCode = 1
-			result.Error = attachStderr("failed to create stdin pipe: " + err.Error())
-			return result
-		}
-	}
-
-	stdout, err := cmd.StdoutPipe()
-	if err != nil {
-		logErrorFn("Failed to create stdout pipe: " + err.Error())
-		result.ExitCode = 1
-		result.Error = attachStderr("failed to create stdout pipe: " + err.Error())
-		return result
-	}
-
-	stdoutReader := io.Reader(stdout)
-	if stdoutLogger != nil {
-		stdoutReader = io.TeeReader(stdout, stdoutLogger)
-	}
-
-	// 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)
-	parseCh := make(chan parseResult, 1)
-	go func() {
-		msg, tid := parseJSONStreamInternal(stdoutReader, logWarnFn, logInfoFn, func() {
-			select {
-			case messageSeen <- struct{}{}:
-			default:
-			}
-		})
-		parseCh <- parseResult{message: msg, threadID: tid}
-	}()
-
-	logInfoFn(fmt.Sprintf("Starting %s with args: %s %s...", commandName, commandName, strings.Join(codexArgs[:min(5, len(codexArgs))], " ")))
-
-	if err := cmd.Start(); err != nil {
-		if strings.Contains(err.Error(), "executable file not found") {
-			msg := fmt.Sprintf("%s command not found in PATH", commandName)
-			logErrorFn(msg)
-			result.ExitCode = 127
-			result.Error = attachStderr(msg)
-			return result
-		}
-		logErrorFn("Failed to start " + commandName + ": " + err.Error())
-		result.ExitCode = 1
-		result.Error = attachStderr("failed to start " + commandName + ": " + err.Error())
-		return result
-	}
-
-	logInfoFn(fmt.Sprintf("Starting %s with PID: %d", commandName, cmd.Process().Pid()))
-	if logger := activeLogger(); logger != nil {
-		logInfoFn(fmt.Sprintf("Log capturing to: %s", logger.Path()))
-	}
-
-	if useStdin && stdinPipe != nil {
-		logInfoFn(fmt.Sprintf("Writing %d chars to stdin...", len(taskSpec.Task)))
-		go func(data string) {
-			defer stdinPipe.Close()
-			_, _ = io.WriteString(stdinPipe, data)
-		}(taskSpec.Task)
-		logInfoFn("Stdin closed")
-	}
-
-	waitCh := make(chan error, 1)
-	go func() { waitCh <- cmd.Wait() }()
-
-	var waitErr error
-	var forceKillTimer *forceKillTimer
-	var ctxCancelled bool
-
-	select {
-	case waitErr = <-waitCh:
-	case <-ctx.Done():
-		ctxCancelled = true
-		logErrorFn(cancelReason(commandName, ctx))
-		forceKillTimer = terminateCommandFn(cmd)
-		waitErr = <-waitCh
-	}
-
-	if forceKillTimer != nil {
-		forceKillTimer.Stop()
-	}
-
-	var parsed parseResult
-	if ctxCancelled {
-		closeWithReason(stdout, stdoutCloseReasonCtx)
-		parsed = <-parseCh
-	} else {
-		drainTimer := time.NewTimer(stdoutDrainTimeout)
-		defer drainTimer.Stop()
-
-		select {
-		case parsed = <-parseCh:
-			closeWithReason(stdout, stdoutCloseReasonWait)
-		case <-messageSeen:
-			closeWithReason(stdout, stdoutCloseReasonWait)
-			parsed = <-parseCh
-		case <-drainTimer.C:
-			closeWithReason(stdout, stdoutCloseReasonDrain)
-			parsed = <-parseCh
-		}
-	}
-
-	if ctxErr := ctx.Err(); ctxErr != nil {
-		if errors.Is(ctxErr, context.DeadlineExceeded) {
-			result.ExitCode = 124
-			result.Error = attachStderr(fmt.Sprintf("%s execution timeout", commandName))
-			return result
-		}
-		result.ExitCode = 130
-		result.Error = attachStderr("execution cancelled")
-		return result
-	}
-
-	if waitErr != nil {
-		if exitErr, ok := waitErr.(*exec.ExitError); ok {
-			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
-	}
-
-	message := parsed.message
-	threadID := parsed.threadID
-	if message == "" {
-		logErrorFn(fmt.Sprintf("%s completed without agent_message output", commandName))
-		result.ExitCode = 1
-		result.Error = attachStderr(fmt.Sprintf("%s completed without agent_message output", commandName))
-		return result
-	}
-
-	if stdoutLogger != nil {
-		stdoutLogger.Flush()
-	}
-	if stderrLogger != nil {
-		stderrLogger.Flush()
-	}
-
-	result.ExitCode = 0
-	result.Message = message
-	result.SessionID = threadID
-	if logger := activeLogger(); logger != nil {
-		result.LogPath = logger.Path()
-	}
-
-	return result
-}
-
-func forwardSignals(ctx context.Context, cmd commandRunner, logErrorFn func(string)) {
-	notify := signalNotifyFn
-	stop := signalStopFn
-	if notify == nil {
-		notify = signal.Notify
-	}
-	if stop == nil {
-		stop = signal.Stop
-	}
-
-	sigCh := make(chan os.Signal, 1)
-	notify(sigCh, syscall.SIGINT, syscall.SIGTERM)
-
-	go func() {
-		defer stop(sigCh)
-		select {
-		case sig := <-sigCh:
-			logErrorFn(fmt.Sprintf("Received signal: %v", sig))
-			if proc := cmd.Process(); proc != nil {
-				_ = proc.Signal(syscall.SIGTERM)
-				time.AfterFunc(time.Duration(forceKillDelay.Load())*time.Second, func() {
-					if p := cmd.Process(); p != nil {
-						_ = p.Kill()
-					}
-				})
-			}
-		case <-ctx.Done():
-		}
-	}()
-}
-
-func cancelReason(commandName string, ctx context.Context) string {
-	if ctx == nil {
-		return "Context cancelled"
-	}
-
-	if commandName == "" {
-		commandName = codexCommand
-	}
-
-	if errors.Is(ctx.Err(), context.DeadlineExceeded) {
-		return fmt.Sprintf("%s execution timeout", commandName)
-	}
-
-	return fmt.Sprintf("Execution cancelled, terminating %s process", commandName)
-}
-
-type stdoutReasonCloser interface {
-	CloseWithReason(string) error
-}
-
-func closeWithReason(rc io.ReadCloser, reason string) {
-	if rc == nil {
-		return
-	}
-	if c, ok := rc.(stdoutReasonCloser); ok {
-		_ = c.CloseWithReason(reason)
-		return
-	}
-	_ = rc.Close()
-}
-
-type forceKillTimer struct {
-	timer   *time.Timer
-	done    chan struct{}
-	stopped atomic.Bool
-	drained atomic.Bool
-}
-
-func (t *forceKillTimer) Stop() {
-	if t == nil || t.timer == nil {
-		return
-	}
-	if !t.timer.Stop() {
-		<-t.done
-		t.drained.Store(true)
-	}
-	t.stopped.Store(true)
-}
-
-func terminateCommand(cmd commandRunner) *forceKillTimer {
-	if cmd == nil {
-		return nil
-	}
-	proc := cmd.Process()
-	if proc == nil {
-		return nil
-	}
-
-	_ = proc.Signal(syscall.SIGTERM)
-
-	done := make(chan struct{}, 1)
-	timer := time.AfterFunc(time.Duration(forceKillDelay.Load())*time.Second, func() {
-		if p := cmd.Process(); p != nil {
-			_ = p.Kill()
-		}
-		close(done)
-	})
-
-	return &forceKillTimer{timer: timer, done: done}
-}
-
-func terminateProcess(cmd commandRunner) *time.Timer {
-	if cmd == nil {
-		return nil
-	}
-	proc := cmd.Process()
-	if proc == nil {
-		return nil
-	}
-
-	_ = proc.Signal(syscall.SIGTERM)
-
-	return time.AfterFunc(time.Duration(forceKillDelay.Load())*time.Second, func() {
-		if p := cmd.Process(); p != nil {
-			_ = p.Kill()
-		}
-	})
-}

codeagent-wrapper/executor_concurrent_test.go

@@ -1,576 +0,0 @@
-package main
-
-import (
-	"bytes"
-	"context"
-	"errors"
-	"io"
-	"os"
-	"os/exec"
-	"strings"
-	"sync"
-	"sync/atomic"
-	"syscall"
-	"testing"
-	"time"
-)
-
-type execFakeProcess struct {
-	pid     int
-	signals []os.Signal
-	killed  atomic.Int32
-	mu      sync.Mutex
-}
-
-func (p *execFakeProcess) Pid() int { return p.pid }
-func (p *execFakeProcess) Kill() error {
-	p.killed.Add(1)
-	return nil
-}
-func (p *execFakeProcess) Signal(sig os.Signal) error {
-	p.mu.Lock()
-	p.signals = append(p.signals, sig)
-	p.mu.Unlock()
-	return nil
-}
-
-type writeCloserStub struct {
-	bytes.Buffer
-	closed atomic.Bool
-}
-
-func (w *writeCloserStub) Close() error {
-	w.closed.Store(true)
-	return nil
-}
-
-type reasonReadCloser struct {
-	r       io.Reader
-	closed  []string
-	mu      sync.Mutex
-	closedC chan struct{}
-}
-
-func newReasonReadCloser(data string) *reasonReadCloser {
-	return &reasonReadCloser{r: strings.NewReader(data), closedC: make(chan struct{}, 1)}
-}
-
-func (rc *reasonReadCloser) Read(p []byte) (int, error) { return rc.r.Read(p) }
-func (rc *reasonReadCloser) Close() error               { rc.record("close"); return nil }
-func (rc *reasonReadCloser) CloseWithReason(reason string) error {
-	rc.record(reason)
-	return nil
-}
-
-func (rc *reasonReadCloser) record(reason string) {
-	rc.mu.Lock()
-	rc.closed = append(rc.closed, reason)
-	rc.mu.Unlock()
-	select {
-	case rc.closedC <- struct{}{}:
-	default:
-	}
-}
-
-type execFakeRunner struct {
-	stdout          io.ReadCloser
-	process         processHandle
-	stdin           io.WriteCloser
-	waitErr         error
-	waitDelay       time.Duration
-	startErr        error
-	stdoutErr       error
-	stdinErr        error
-	allowNilProcess bool
-	started         atomic.Bool
-}
-
-func (f *execFakeRunner) Start() error {
-	if f.startErr != nil {
-		return f.startErr
-	}
-	f.started.Store(true)
-	return nil
-}
-func (f *execFakeRunner) Wait() error {
-	if f.waitDelay > 0 {
-		time.Sleep(f.waitDelay)
-	}
-	return f.waitErr
-}
-func (f *execFakeRunner) StdoutPipe() (io.ReadCloser, error) {
-	if f.stdoutErr != nil {
-		return nil, f.stdoutErr
-	}
-	if f.stdout == nil {
-		f.stdout = io.NopCloser(strings.NewReader(""))
-	}
-	return f.stdout, nil
-}
-func (f *execFakeRunner) StdinPipe() (io.WriteCloser, error) {
-	if f.stdinErr != nil {
-		return nil, f.stdinErr
-	}
-	if f.stdin != nil {
-		return f.stdin, nil
-	}
-	return &writeCloserStub{}, nil
-}
-func (f *execFakeRunner) SetStderr(io.Writer) {}
-func (f *execFakeRunner) Process() processHandle {
-	if f.process != nil {
-		return f.process
-	}
-	if f.allowNilProcess {
-		return nil
-	}
-	return &execFakeProcess{pid: 1}
-}
-
-func TestExecutorHelperCoverage(t *testing.T) {
-	t.Run("realCmdAndProcess", func(t *testing.T) {
-		rc := &realCmd{}
-		if err := rc.Start(); err == nil {
-			t.Fatalf("expected error for nil command")
-		}
-		if err := rc.Wait(); err == nil {
-			t.Fatalf("expected error for nil command")
-		}
-		if _, err := rc.StdoutPipe(); err == nil {
-			t.Fatalf("expected error for nil command")
-		}
-		if _, err := rc.StdinPipe(); err == nil {
-			t.Fatalf("expected error for nil command")
-		}
-		rc.SetStderr(io.Discard)
-		if rc.Process() != nil {
-			t.Fatalf("expected nil process")
-		}
-		rcWithCmd := &realCmd{cmd: &exec.Cmd{}}
-		rcWithCmd.SetStderr(io.Discard)
-		echoCmd := exec.Command("echo", "ok")
-		rcProc := &realCmd{cmd: echoCmd}
-		stdoutPipe, err := rcProc.StdoutPipe()
-		if err != nil {
-			t.Fatalf("StdoutPipe error: %v", err)
-		}
-		stdinPipe, err := rcProc.StdinPipe()
-		if err != nil {
-			t.Fatalf("StdinPipe error: %v", err)
-		}
-		rcProc.SetStderr(io.Discard)
-		if err := rcProc.Start(); err != nil {
-			t.Fatalf("Start failed: %v", err)
-		}
-		_, _ = stdinPipe.Write([]byte{})
-		_ = stdinPipe.Close()
-		procHandle := rcProc.Process()
-		if procHandle == nil {
-			t.Fatalf("expected process handle")
-		}
-		_ = procHandle.Signal(syscall.SIGTERM)
-		_ = procHandle.Kill()
-		_ = rcProc.Wait()
-		_, _ = io.ReadAll(stdoutPipe)
-
-		rp := &realProcess{}
-		if rp.Pid() != 0 {
-			t.Fatalf("nil process should have pid 0")
-		}
-		if rp.Kill() != nil {
-			t.Fatalf("nil process Kill should be nil")
-		}
-		if rp.Signal(syscall.SIGTERM) != nil {
-			t.Fatalf("nil process Signal should be nil")
-		}
-		rpLive := &realProcess{proc: &os.Process{Pid: 99}}
-		if rpLive.Pid() != 99 {
-			t.Fatalf("expected pid 99, got %d", rpLive.Pid())
-		}
-		_ = rpLive.Kill()
-		_ = rpLive.Signal(syscall.SIGTERM)
-	})
-
-	t.Run("topologicalSortAndSkip", func(t *testing.T) {
-		layers, err := topologicalSort([]TaskSpec{{ID: "root"}, {ID: "child", Dependencies: []string{"root"}}})
-		if err != nil || len(layers) != 2 {
-			t.Fatalf("unexpected topological sort result: layers=%d err=%v", len(layers), err)
-		}
-		if _, err := topologicalSort([]TaskSpec{{ID: "cycle", Dependencies: []string{"cycle"}}}); err == nil {
-			t.Fatalf("expected cycle detection error")
-		}
-
-		failed := map[string]TaskResult{"root": {ExitCode: 1}}
-		if skip, _ := shouldSkipTask(TaskSpec{ID: "child", Dependencies: []string{"root"}}, failed); !skip {
-			t.Fatalf("should skip when dependency failed")
-		}
-		if skip, _ := shouldSkipTask(TaskSpec{ID: "leaf"}, failed); skip {
-			t.Fatalf("should not skip task without dependencies")
-		}
-		if skip, _ := shouldSkipTask(TaskSpec{ID: "child-ok", Dependencies: []string{"root"}}, map[string]TaskResult{}); skip {
-			t.Fatalf("should not skip when dependencies succeeded")
-		}
-	})
-
-	t.Run("cancelledTaskResult", func(t *testing.T) {
-		ctx, cancel := context.WithCancel(context.Background())
-		cancel()
-		res := cancelledTaskResult("t1", ctx)
-		if res.ExitCode != 130 {
-			t.Fatalf("expected cancel exit code, got %d", res.ExitCode)
-		}
-
-		timeoutCtx, timeoutCancel := context.WithTimeout(context.Background(), 0)
-		defer timeoutCancel()
-		res = cancelledTaskResult("t2", timeoutCtx)
-		if res.ExitCode != 124 {
-			t.Fatalf("expected timeout exit code, got %d", res.ExitCode)
-		}
-	})
-
-	t.Run("generateFinalOutputAndArgs", func(t *testing.T) {
-		out := generateFinalOutput([]TaskResult{
-			{TaskID: "ok", ExitCode: 0},
-			{TaskID: "fail", ExitCode: 1, Error: "boom"},
-		})
-		if !strings.Contains(out, "ok") || !strings.Contains(out, "fail") {
-			t.Fatalf("unexpected summary output: %s", out)
-		}
-		out = generateFinalOutput([]TaskResult{{TaskID: "rich", ExitCode: 0, SessionID: "sess", LogPath: "/tmp/log", Message: "hello"}})
-		if !strings.Contains(out, "Session: sess") || !strings.Contains(out, "Log: /tmp/log") || !strings.Contains(out, "hello") {
-			t.Fatalf("rich output missing fields: %s", out)
-		}
-
-		args := buildCodexArgs(&Config{Mode: "new", WorkDir: "/tmp"}, "task")
-		if len(args) == 0 || args[3] != "/tmp" {
-			t.Fatalf("unexpected codex args: %+v", args)
-		}
-		args = buildCodexArgs(&Config{Mode: "resume", SessionID: "sess"}, "target")
-		if args[3] != "resume" || args[4] != "sess" {
-			t.Fatalf("unexpected resume args: %+v", args)
-		}
-	})
-
-	t.Run("executeConcurrentWrapper", func(t *testing.T) {
-		orig := runCodexTaskFn
-		defer func() { runCodexTaskFn = orig }()
-		runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
-			return TaskResult{TaskID: task.ID, ExitCode: 0, Message: "done"}
-		}
-		os.Setenv("CODEAGENT_MAX_PARALLEL_WORKERS", "1")
-		defer os.Unsetenv("CODEAGENT_MAX_PARALLEL_WORKERS")
-
-		results := executeConcurrent([][]TaskSpec{{{ID: "wrap"}}}, 1)
-		if len(results) != 1 || results[0].TaskID != "wrap" {
-			t.Fatalf("unexpected wrapper results: %+v", results)
-		}
-
-		unbounded := executeConcurrentWithContext(context.Background(), [][]TaskSpec{{{ID: "unbounded"}}}, 1, 0)
-		if len(unbounded) != 1 || unbounded[0].ExitCode != 0 {
-			t.Fatalf("unexpected unbounded result: %+v", unbounded)
-		}
-
-		ctx, cancel := context.WithCancel(context.Background())
-		cancel()
-		cancelled := executeConcurrentWithContext(ctx, [][]TaskSpec{{{ID: "cancel"}}}, 1, 1)
-		if cancelled[0].ExitCode == 0 {
-			t.Fatalf("expected cancelled result, got %+v", cancelled[0])
-		}
-	})
-}
-
-func TestExecutorRunCodexTaskWithContext(t *testing.T) {
-	origRunner := newCommandRunner
-	defer func() { newCommandRunner = origRunner }()
-
-	t.Run("success", func(t *testing.T) {
-		var firstStdout *reasonReadCloser
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			rc := newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"hello"}}`)
-			if firstStdout == nil {
-				firstStdout = rc
-			}
-			return &execFakeRunner{stdout: rc, process: &execFakeProcess{pid: 1234}}
-		}
-
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{ID: "task-1", Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.Error != "" || res.Message != "hello" || res.ExitCode != 0 {
-			t.Fatalf("unexpected result: %+v", res)
-		}
-
-		select {
-		case <-firstStdout.closedC:
-		case <-time.After(1 * time.Second):
-			t.Fatalf("stdout not closed with reason")
-		}
-
-		orig := runCodexTaskFn
-		runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
-			return TaskResult{TaskID: task.ID, ExitCode: 0, Message: "ok"}
-		}
-		t.Cleanup(func() { runCodexTaskFn = orig })
-
-		if res := runCodexTask(TaskSpec{Task: "task-text", WorkDir: "."}, true, 1); res.ExitCode != 0 {
-			t.Fatalf("runCodexTask failed: %+v", res)
-		}
-
-		msg, threadID, code := runCodexProcess(context.Background(), []string{"arg"}, "content", false, 1)
-		if code != 0 || msg == "" {
-			t.Fatalf("runCodexProcess unexpected result: msg=%q code=%d threadID=%s", msg, code, threadID)
-		}
-	})
-
-	t.Run("startErrors", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{startErr: errors.New("executable file not found"), process: &execFakeProcess{pid: 1}}
-		}
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.ExitCode != 127 {
-			t.Fatalf("expected missing executable exit code, got %d", res.ExitCode)
-		}
-
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{startErr: errors.New("start failed"), process: &execFakeProcess{pid: 2}}
-		}
-		res = runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected non-zero exit on start failure")
-		}
-	})
-
-	t.Run("timeoutAndPipes", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{
-				stdout:    newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"slow"}}`),
-				process:   &execFakeProcess{pid: 5},
-				waitDelay: 20 * time.Millisecond,
-			}
-		}
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: ".", UseStdin: true}, nil, nil, false, false, 0)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected timeout result, got %+v", res)
-		}
-	})
-
-	t.Run("pipeErrors", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{stdoutErr: errors.New("stdout fail"), process: &execFakeProcess{pid: 6}}
-		}
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected failure on stdout pipe error")
-		}
-
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{stdinErr: errors.New("stdin fail"), process: &execFakeProcess{pid: 7}}
-		}
-		res = runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: ".", UseStdin: true}, nil, nil, false, false, 1)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected failure on stdin pipe error")
-		}
-	})
-
-	t.Run("waitExitError", func(t *testing.T) {
-		err := exec.Command("false").Run()
-		exitErr, _ := err.(*exec.ExitError)
-		if exitErr == nil {
-			t.Fatalf("expected exec.ExitError")
-		}
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{
-				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"ignored"}}`),
-				process: &execFakeProcess{pid: 8},
-				waitErr: exitErr,
-			}
-		}
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected non-zero exit on wait error")
-		}
-	})
-
-	t.Run("contextCancelled", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{
-				stdout:    newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"cancel"}}`),
-				process:   &execFakeProcess{pid: 9},
-				waitDelay: 10 * time.Millisecond,
-			}
-		}
-		ctx, cancel := context.WithCancel(context.Background())
-		cancel()
-		res := runCodexTaskWithContext(ctx, TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected cancellation result")
-		}
-	})
-
-	t.Run("silentLogger", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{
-				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"quiet"}}`),
-				process: &execFakeProcess{pid: 10},
-			}
-		}
-		_ = closeLogger()
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, true, 1)
-		if res.ExitCode != 0 || res.LogPath == "" {
-			t.Fatalf("expected success with temp logger, got %+v", res)
-		}
-		_ = closeLogger()
-	})
-
-	t.Run("missingMessage", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
-			return &execFakeRunner{
-				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"task","text":"noop"}}`),
-				process: &execFakeProcess{pid: 11},
-			}
-		}
-		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
-		if res.ExitCode == 0 {
-			t.Fatalf("expected failure when no agent_message returned")
-		}
-	})
-}
-
-func TestExecutorSignalAndTermination(t *testing.T) {
-	forceKillDelay.Store(0)
-	defer forceKillDelay.Store(5)
-
-	proc := &execFakeProcess{pid: 42}
-	cmd := &execFakeRunner{process: proc}
-
-	origNotify := signalNotifyFn
-	origStop := signalStopFn
-	defer func() {
-		signalNotifyFn = origNotify
-		signalStopFn = origStop
-	}()
-
-	signalNotifyFn = func(c chan<- os.Signal, sigs ...os.Signal) {
-		go func() { c <- syscall.SIGINT }()
-	}
-	signalStopFn = func(c chan<- os.Signal) {}
-
-	forwardSignals(context.Background(), cmd, func(string) {})
-	time.Sleep(20 * time.Millisecond)
-
-	proc.mu.Lock()
-	signalled := len(proc.signals)
-	proc.mu.Unlock()
-	if signalled == 0 {
-		t.Fatalf("process did not receive signal")
-	}
-	if proc.killed.Load() == 0 {
-		t.Fatalf("process was not killed after signal")
-	}
-
-	timer := terminateProcess(cmd)
-	if timer == nil {
-		t.Fatalf("terminateProcess returned nil timer")
-	}
-	timer.Stop()
-
-	ft := terminateCommand(cmd)
-	if ft == nil {
-		t.Fatalf("terminateCommand returned nil")
-	}
-	ft.Stop()
-
-	cmdKill := &execFakeRunner{process: &execFakeProcess{pid: 50}}
-	ftKill := terminateCommand(cmdKill)
-	time.Sleep(10 * time.Millisecond)
-	if p, ok := cmdKill.process.(*execFakeProcess); ok && p.killed.Load() == 0 {
-		t.Fatalf("terminateCommand did not kill process")
-	}
-	ftKill.Stop()
-
-	cmdKill2 := &execFakeRunner{process: &execFakeProcess{pid: 51}}
-	timer2 := terminateProcess(cmdKill2)
-	time.Sleep(10 * time.Millisecond)
-	if p, ok := cmdKill2.process.(*execFakeProcess); ok && p.killed.Load() == 0 {
-		t.Fatalf("terminateProcess did not kill process")
-	}
-	timer2.Stop()
-
-	if terminateCommand(nil) != nil {
-		t.Fatalf("terminateCommand should return nil for nil cmd")
-	}
-	if terminateCommand(&execFakeRunner{allowNilProcess: true}) != nil {
-		t.Fatalf("terminateCommand should return nil when process is nil")
-	}
-	if terminateProcess(nil) != nil {
-		t.Fatalf("terminateProcess should return nil for nil cmd")
-	}
-	if terminateProcess(&execFakeRunner{allowNilProcess: true}) != nil {
-		t.Fatalf("terminateProcess should return nil when process is nil")
-	}
-
-	signalNotifyFn = func(c chan<- os.Signal, sigs ...os.Signal) {}
-	ctxDone, cancelDone := context.WithCancel(context.Background())
-	cancelDone()
-	forwardSignals(ctxDone, &execFakeRunner{process: &execFakeProcess{pid: 70}}, func(string) {})
-}
-
-func TestExecutorCancelReasonAndCloseWithReason(t *testing.T) {
-	if reason := cancelReason("", nil); !strings.Contains(reason, "Context") {
-		t.Fatalf("unexpected cancelReason for nil ctx: %s", reason)
-	}
-	ctx, cancel := context.WithTimeout(context.Background(), 0)
-	defer cancel()
-	if !strings.Contains(cancelReason("cmd", ctx), "timeout") {
-		t.Fatalf("expected timeout reason")
-	}
-	cancelCtx, cancelFn := context.WithCancel(context.Background())
-	cancelFn()
-	if !strings.Contains(cancelReason("cmd", cancelCtx), "Execution cancelled") {
-		t.Fatalf("expected cancellation reason")
-	}
-	if !strings.Contains(cancelReason("", cancelCtx), "codex") {
-		t.Fatalf("expected default command name in cancel reason")
-	}
-
-	rc := &reasonReadCloser{r: strings.NewReader("data"), closedC: make(chan struct{}, 1)}
-	closeWithReason(rc, "why")
-	select {
-	case <-rc.closedC:
-	default:
-		t.Fatalf("CloseWithReason was not called")
-	}
-
-	plain := io.NopCloser(strings.NewReader("x"))
-	closeWithReason(plain, "noop")
-	closeWithReason(nil, "noop")
-}
-
-func TestExecutorForceKillTimerStop(t *testing.T) {
-	done := make(chan struct{}, 1)
-	ft := &forceKillTimer{timer: time.AfterFunc(50*time.Millisecond, func() { done <- struct{}{} }), done: done}
-	ft.Stop()
-
-	done2 := make(chan struct{}, 1)
-	ft2 := &forceKillTimer{timer: time.AfterFunc(0, func() { done2 <- struct{}{} }), done: done2}
-	time.Sleep(10 * time.Millisecond)
-	ft2.Stop()
-
-	var nilTimer *forceKillTimer
-	nilTimer.Stop()
-	(&forceKillTimer{}).Stop()
-}
-
-func TestExecutorForwardSignalsDefaults(t *testing.T) {
-	origNotify := signalNotifyFn
-	origStop := signalStopFn
-	signalNotifyFn = nil
-	signalStopFn = nil
-	defer func() {
-		signalNotifyFn = origNotify
-		signalStopFn = origStop
-	}()
-
-	ctx, cancel := context.WithCancel(context.Background())
-	cancel()
-	forwardSignals(ctx, &execFakeRunner{process: &execFakeProcess{pid: 80}}, func(string) {})
-	time.Sleep(10 * time.Millisecond)
-}

codeagent-wrapper/go.mod

@@ -1,3 +1,43 @@
 module codeagent-wrapper
 
 go 1.21
+
+require (
+	github.com/goccy/go-json v0.10.5
+	github.com/rs/zerolog v1.34.0
+	github.com/shirou/gopsutil/v3 v3.24.5
+	github.com/spf13/cobra v1.8.1
+	github.com/spf13/pflag v1.0.5
+	github.com/spf13/viper v1.19.0
+)
+
+require (
+	github.com/fsnotify/fsnotify v1.7.0 // indirect
+	github.com/go-ole/go-ole v1.2.6 // indirect
+	github.com/hashicorp/hcl v1.0.0 // indirect
+	github.com/inconshreveable/mousetrap v1.1.0 // indirect
+	github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0 // indirect
+	github.com/magiconair/properties v1.8.7 // indirect
+	github.com/mattn/go-colorable v0.1.13 // indirect
+	github.com/mattn/go-isatty v0.0.19 // indirect
+	github.com/mitchellh/mapstructure v1.5.0 // indirect
+	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
+	github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c // indirect
+	github.com/sagikazarmark/locafero v0.4.0 // indirect
+	github.com/sagikazarmark/slog-shim v0.1.0 // indirect
+	github.com/shoenig/go-m1cpu v0.1.6 // indirect
+	github.com/sourcegraph/conc v0.3.0 // indirect
+	github.com/spf13/afero v1.11.0 // indirect
+	github.com/spf13/cast v1.6.0 // indirect
+	github.com/subosito/gotenv v1.6.0 // indirect
+	github.com/tklauser/go-sysconf v0.3.12 // indirect
+	github.com/tklauser/numcpus v0.6.1 // indirect
+	github.com/yusufpapurcu/wmi v1.2.4 // indirect
+	go.uber.org/atomic v1.9.0 // indirect
+	go.uber.org/multierr v1.9.0 // indirect
+	golang.org/x/exp v0.0.0-20230905200255-921286631fa9 // indirect
+	golang.org/x/sys v0.20.0 // indirect
+	golang.org/x/text v0.14.0 // indirect
+	gopkg.in/ini.v1 v1.67.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

codeagent-wrapper/go.sum

@@ -0,0 +1,117 @@
+github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
+github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8=
+github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
+github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
+github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
+github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY=
+github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
+github.com/goccy/go-json v0.10.5 h1:Fq85nIqj+gXn/S5ahsiTlK3TmC85qgirsdTP/+DeaC4=
+github.com/goccy/go-json v0.10.5/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
+github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
+github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
+github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
+github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
+github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0 h1:6E+4a0GO5zZEnZ81pIr0yLvtUWk2if982qA3F3QD6H4=
+github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0/go.mod h1:zJYVVT2jmtg6P3p1VtQj7WsuWi/y4VnjVBn7F8KPB3I=
+github.com/magiconair/properties v1.8.7 h1:IeQXZAiQcpL9mgcAe1Nu6cX9LLw6ExEHKjN0VQdvPDY=
+github.com/magiconair/properties v1.8.7/go.mod h1:Dhd985XPs7jluiymwWYZ0G4Z61jb3vdS329zhj2hYo0=
+github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
+github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
+github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
+github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
+github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
+github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
+github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
+github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM=
+github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
+github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c h1:ncq/mPwQF4JjgDlrVEn3C11VoGHZN7m8qihwgMEtzYw=
+github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE=
+github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
+github.com/rs/xid v1.6.0/go.mod h1:7XoLgs4eV+QndskICGsho+ADou8ySMSjJKDIan90Nz0=
+github.com/rs/zerolog v1.34.0 h1:k43nTLIwcTVQAncfCw4KZ2VY6ukYoZaBPNOE8txlOeY=
+github.com/rs/zerolog v1.34.0/go.mod h1:bJsvje4Z08ROH4Nhs5iH600c3IkWhwp44iRc54W6wYQ=
+github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/sagikazarmark/locafero v0.4.0 h1:HApY1R9zGo4DBgr7dqsTH/JJxLTTsOt7u6keLGt6kNQ=
+github.com/sagikazarmark/locafero v0.4.0/go.mod h1:Pe1W6UlPYUk/+wc/6KFhbORCfqzgYEpgQ3O5fPuL3H4=
+github.com/sagikazarmark/slog-shim v0.1.0 h1:diDBnUNK9N/354PgrxMywXnAwEr1QZcOr6gto+ugjYE=
+github.com/sagikazarmark/slog-shim v0.1.0/go.mod h1:SrcSrq8aKtyuqEI1uvTDTK1arOWRIczQRv+GVI1AkeQ=
+github.com/shirou/gopsutil/v3 v3.24.5 h1:i0t8kL+kQTvpAYToeuiVk3TgDeKOFioZO3Ztz/iZ9pI=
+github.com/shirou/gopsutil/v3 v3.24.5/go.mod h1:bsoOS1aStSs9ErQ1WWfxllSeS1K5D+U30r2NfcubMVk=
+github.com/shoenig/go-m1cpu v0.1.6 h1:nxdKQNcEB6vzgA2E2bvzKIYRuNj7XNJ4S/aRSwKzFtM=
+github.com/shoenig/go-m1cpu v0.1.6/go.mod h1:1JJMcUBvfNwpq05QDQVAnx3gUHr9IYF7GNg9SUEw2VQ=
+github.com/shoenig/test v0.6.4 h1:kVTaSd7WLz5WZ2IaoM0RSzRsUD+m8wRR+5qvntpn4LU=
+github.com/shoenig/test v0.6.4/go.mod h1:byHiCGXqrVaflBLAMq/srcZIHynQPQgeyvkvXnjqq0k=
+github.com/sourcegraph/conc v0.3.0 h1:OQTbbt6P72L20UqAkXXuLOj79LfEanQ+YQFNpLA9ySo=
+github.com/sourcegraph/conc v0.3.0/go.mod h1:Sdozi7LEKbFPqYX2/J+iBAM6HpqSLTASQIKqDmF7Mt0=
+github.com/spf13/afero v1.11.0 h1:WJQKhtpdm3v2IzqG8VMqrr6Rf3UYpEF239Jy9wNepM8=
+github.com/spf13/afero v1.11.0/go.mod h1:GH9Y3pIexgf1MTIWtNGyogA5MwRIDXGUr+hbWNoBjkY=
+github.com/spf13/cast v1.6.0 h1:GEiTHELF+vaR5dhz3VqZfFSzZjYbgeKDpBxQVS4GYJ0=
+github.com/spf13/cast v1.6.0/go.mod h1:ancEpBxwJDODSW/UG4rDrAqiKolqNNh2DX3mk86cAdo=
+github.com/spf13/cobra v1.8.1 h1:e5/vxKd/rZsfSJMUX1agtjeTDf+qv1/JdBF8gg5k9ZM=
+github.com/spf13/cobra v1.8.1/go.mod h1:wHxEcudfqmLYa8iTfL+OuZPbBZkmvliBWKIezN3kD9Y=
+github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
+github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/spf13/viper v1.19.0 h1:RWq5SEjt8o25SROyN3z2OrDB9l7RPd3lwTWU8EcEdcI=
+github.com/spf13/viper v1.19.0/go.mod h1:GQUN9bilAbhU/jgc1bKs99f/suXKeUMct8Adx5+Ntkg=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
+github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
+github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/subosito/gotenv v1.6.0 h1:9NlTDc1FTs4qu0DDq7AEtTPNw6SVm7uBMsUCUjABIf8=
+github.com/subosito/gotenv v1.6.0/go.mod h1:Dk4QP5c2W3ibzajGcXpNraDfq2IrhjMIvMSWPKKo0FU=
+github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
+github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
+github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
+github.com/tklauser/numcpus v0.6.1/go.mod h1:1XfjsgE2zo8GVw7POkMbHENHzVg3GzmoZ9fESEdAacY=
+github.com/yusufpapurcu/wmi v1.2.4 h1:zFUKzehAFReQwLys1b/iSMl+JQGSCSjtVqQn9bBrPo0=
+github.com/yusufpapurcu/wmi v1.2.4/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
+go.uber.org/atomic v1.9.0 h1:ECmE8Bn/WFTYwEW/bpKD3M8VtR/zQVbavAoalC1PYyE=
+go.uber.org/atomic v1.9.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
+go.uber.org/multierr v1.9.0 h1:7fIwc/ZtS0q++VgcfqFDxSBZVv/Xo49/SYnDFupUwlI=
+go.uber.org/multierr v1.9.0/go.mod h1:X2jQV1h+kxSjClGpnseKVIxpmcjrj7MNnI0bnlfKTVQ=
+golang.org/x/exp v0.0.0-20230905200255-921286631fa9 h1:GoHiUyI/Tp2nVkLI2mCxVkOjsbSXD66ic0XW0js0R9g=
+golang.org/x/exp v0.0.0-20230905200255-921286631fa9/go.mod h1:S2oDrQGGwySpoQPVqRShND87VCbxmc6bL1Yd2oYrm6k=
+golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
+golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=
+gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/ini.v1 v1.67.0 h1:Dgnx+6+nfE+IfzjUEISNeydPJh9AXNNsWbGP9KzCsOA=
+gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

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               = "6.1.2"
+	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 +1,664 @@
+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,
+		Backend:         cfg.Backend,
+		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
+	}
+
+	// Validate that we got a meaningful output message
+	if strings.TrimSpace(result.Message) == "" {
+		logError(fmt.Sprintf("no output message: backend=%s returned empty result.Message with exit_code=0", cfg.Backend))
+		return 1
+	}
+
+	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

@@ -1,4 +1,4 @@
-package main
+package wrapper
 
 import (
 	"bufio"
@@ -11,8 +11,29 @@ import (
 	"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() {
@@ -76,10 +97,11 @@ func TestConcurrentStressLogger(t *testing.T) {
 	t.Logf("Successfully wrote %d/%d logs (%.1f%%)",
 		actualCount, totalExpected, float64(actualCount)/float64(totalExpected)*100)
 
-	// 验证日志格式
-	formatRE := regexp.MustCompile(`^\[\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d{3}\] \[PID:\d+\] INFO: goroutine-`)
+	// 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)
 		}
 	}
@@ -291,18 +313,15 @@ 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
-		parts := strings.SplitN(line, " INFO: ", 2)
-		if len(parts) != 2 {
-			t.Errorf("invalid log format: %s", line)
+		// 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
 		}
-		if _, err := fmt.Sscanf(parts[1], "G%d-SEQ%d", &gid, &seq); err == nil {
-			sequences[gid] = append(sequences[gid], seq)
-		} else {
-			t.Errorf("failed to parse sequence from line: %s", line)
-		}
+		sequences[gid] = append(sequences[gid], seq)
 	}
 
 	// 验证每个 goroutine 内部顺序

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

@@ -1,7 +1,8 @@
-package main
+package wrapper
 
 import (
 	"bytes"
+	"codeagent-wrapper/internal/logger"
 	"fmt"
 	"io"
 	"os"
@@ -36,7 +37,9 @@ func captureStdout(t *testing.T, fn func()) string {
 	os.Stdout = old
 
 	var buf bytes.Buffer
-	io.Copy(&buf, r)
+	if _, err := io.Copy(&buf, r); err != nil {
+		t.Fatalf("io.Copy() error = %v", err)
+	}
 	return buf.String()
 }
 
@@ -46,33 +49,127 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 
 	lines := strings.Split(out, "\n")
 	var currentTask *TaskResult
+	inTaskResults := false
 
 	for _, line := range lines {
 		line = strings.TrimSpace(line)
-		if strings.HasPrefix(line, "Total:") {
+
+		// 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:") {
-					fmt.Sscanf(p, "Total: %d", &payload.Summary.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:") {
-					fmt.Sscanf(p, "Success: %d", &payload.Summary.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:") {
-					fmt.Sscanf(p, "Failed: %d", &payload.Summary.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 {
+		} 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") {
-					fmt.Sscanf(line, "Status: FAILED (exit code %d)", &currentTask.ExitCode)
+					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
 				}
@@ -82,15 +179,11 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 				currentTask.SessionID = strings.TrimPrefix(line, "Session: ")
 			} else if strings.HasPrefix(line, "Log:") {
 				currentTask.LogPath = strings.TrimSpace(strings.TrimPrefix(line, "Log:"))
-			} else if line != "" && !strings.HasPrefix(line, "===") && !strings.HasPrefix(line, "---") {
-				if currentTask.Message != "" {
-					currentTask.Message += "\n"
-				}
-				currentTask.Message += line
 			}
 		}
 	}
 
+	// Handle last task
 	if currentTask != nil {
 		payload.Results = append(payload.Results, *currentTask)
 	}
@@ -98,32 +191,6 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 	return payload
 }
 
-func extractTaskBlock(t *testing.T, output, taskID string) string {
-	t.Helper()
-	header := fmt.Sprintf("--- Task: %s ---", taskID)
-	lines := strings.Split(output, "\n")
-	var block []string
-	collecting := false
-	for _, raw := range lines {
-		trimmed := strings.TrimSpace(raw)
-		if !collecting {
-			if trimmed == header {
-				collecting = true
-				block = append(block, trimmed)
-			}
-			continue
-		}
-		if strings.HasPrefix(trimmed, "--- Task: ") && trimmed != header {
-			break
-		}
-		block = append(block, trimmed)
-	}
-	if len(block) == 0 {
-		t.Fatalf("task block %s not found in output:\n%s", taskID, output)
-	}
-	return strings.Join(block, "\n")
-}
-
 func findResultByID(t *testing.T, payload integrationOutput, id string) TaskResult {
 	t.Helper()
 	for _, res := range payload.Results {
@@ -135,6 +202,37 @@ func findResultByID(t *testing.T, payload integrationOutput, id string) TaskResu
 	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
@@ -320,7 +418,7 @@ id: beta
 ---CONTENT---
 task-beta`
 	stdinReader = bytes.NewReader([]byte(input))
-	os.Args = []string{"codex-wrapper", "--parallel"}
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
 
 	var exitCode int
 	output := captureStdout(t, func() {
@@ -343,9 +441,10 @@ task-beta`
 	}
 
 	for _, id := range []string{"alpha", "beta"} {
-		want := fmt.Sprintf("Log: %s", logPathFor(id))
-		if !strings.Contains(output, want) {
-			t.Fatalf("parallel output missing %q for %s:\n%s", want, id, output)
+		// 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)
 		}
 	}
 }
@@ -372,9 +471,9 @@ id: d
 ---CONTENT---
 ok-d`
 	stdinReader = bytes.NewReader([]byte(input))
-	os.Args = []string{"codex-wrapper", "--parallel"}
+	os.Args = []string{"codeagent-wrapper", "--parallel"}
 
-	expectedLog := filepath.Join(tempDir, fmt.Sprintf("codex-wrapper-%d.log", os.Getpid()))
+	expectedLog := filepath.Join(tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", os.Getpid()))
 
 	origRun := runCodexTaskFn
 	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
@@ -426,10 +525,11 @@ ok-d`
 		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", expectedLog): {},
-		fmt.Sprintf("Task b: Log: %s", expectedLog): {},
-		fmt.Sprintf("Task d: Log: %s", expectedLog): {},
+		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) {
@@ -447,7 +547,7 @@ func TestRunNonParallelOutputsIncludeLogPathsIntegration(t *testing.T) {
 	defer resetTestHooks()
 
 	tempDir := setTempDirEnv(t, t.TempDir())
-	os.Args = []string{"codex-wrapper", "integration-log-check"}
+	os.Args = []string{"codeagent-wrapper", "integration-log-check"}
 	stdinReader = strings.NewReader("")
 	isTerminalFn = func() bool { return true }
 	codexCommand = "echo"
@@ -465,7 +565,7 @@ func TestRunNonParallelOutputsIncludeLogPathsIntegration(t *testing.T) {
 	if exitCode != 0 {
 		t.Fatalf("run() exit=%d, want 0", exitCode)
 	}
-	expectedLog := filepath.Join(tempDir, fmt.Sprintf("codex-wrapper-%d.log", os.Getpid()))
+	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)
@@ -549,16 +649,16 @@ ok-e`
 	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"} {
-		block := extractTaskBlock(t, output, id)
-		want := fmt.Sprintf("Log: %s", logPathFor(id))
-		if !strings.Contains(block, want) {
-			t.Fatalf("task %s block missing %q:\n%s", id, want, block)
+		logPath := logPathFor(id)
+		if !strings.Contains(output, logPath) {
+			t.Fatalf("task %s log path %q not found in output:\n%s", id, logPath, output)
 		}
 	}
-	blockB := extractTaskBlock(t, output, "B")
-	if strings.Contains(blockB, "Log:") {
-		t.Fatalf("skipped task B should not emit a log line:\n%s", blockB)
+	// 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)
 	}
 }
 
@@ -568,7 +668,6 @@ func TestRunParallelTimeoutPropagation(t *testing.T) {
 	t.Cleanup(func() {
 		runCodexTaskFn = origRun
 		resetTestHooks()
-		os.Unsetenv("CODEX_TIMEOUT")
 	})
 
 	var receivedTimeout int
@@ -577,7 +676,7 @@ func TestRunParallelTimeoutPropagation(t *testing.T) {
 		return TaskResult{TaskID: task.ID, ExitCode: 124, Error: "timeout"}
 	}
 
-	os.Setenv("CODEX_TIMEOUT", "1")
+	t.Setenv("CODEX_TIMEOUT", "1")
 	input := `---TASK---
 id: T
 ---CONTENT---
@@ -647,11 +746,11 @@ func TestRunStartupCleanupRemovesOrphansEndToEnd(t *testing.T) {
 
 	tempDir := setTempDirEnv(t, t.TempDir())
 
-	orphanA := createTempLog(t, tempDir, "codex-wrapper-5001.log")
-	orphanB := createTempLog(t, tempDir, "codex-wrapper-5002-extra.log")
-	orphanC := createTempLog(t, tempDir, "codex-wrapper-5003-suffix.log")
+	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("codex-wrapper-%d.log", runningPID))
+	runningLog := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", runningPID))
 	unrelated := createTempLog(t, tempDir, "wrapper.log")
 
 	stubProcessRunning(t, func(pid int) bool {
@@ -667,7 +766,7 @@ func TestRunStartupCleanupRemovesOrphansEndToEnd(t *testing.T) {
 	codexCommand = createFakeCodexScript(t, "tid-startup", "ok")
 	stdinReader = strings.NewReader("")
 	isTerminalFn = func() bool { return true }
-	os.Args = []string{"codex-wrapper", "task"}
+	os.Args = []string{"codeagent-wrapper", "task"}
 
 	if exit := run(); exit != 0 {
 		t.Fatalf("run() exit=%d, want 0", exit)
@@ -693,7 +792,7 @@ func TestRunStartupCleanupConcurrentWrappers(t *testing.T) {
 
 	const totalLogs = 40
 	for i := 0; i < totalLogs; i++ {
-		createTempLog(t, tempDir, fmt.Sprintf("codex-wrapper-%d.log", 9000+i))
+		createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", 9000+i))
 	}
 
 	stubProcessRunning(t, func(pid int) bool {
@@ -717,7 +816,7 @@ func TestRunStartupCleanupConcurrentWrappers(t *testing.T) {
 	close(start)
 	wg.Wait()
 
-	matches, err := filepath.Glob(filepath.Join(tempDir, "codex-wrapper-*.log"))
+	matches, err := filepath.Glob(filepath.Join(tempDir, "codeagent-wrapper-*.log"))
 	if err != nil {
 		t.Fatalf("glob error: %v", err)
 	}
@@ -731,9 +830,9 @@ func TestRunCleanupFlagEndToEnd_Success(t *testing.T) {
 
 	tempDir := setTempDirEnv(t, t.TempDir())
 
-	staleA := createTempLog(t, tempDir, "codex-wrapper-2100.log")
-	staleB := createTempLog(t, tempDir, "codex-wrapper-2200-extra.log")
-	keeper := createTempLog(t, tempDir, "codex-wrapper-2300.log")
+	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()
@@ -745,7 +844,7 @@ func TestRunCleanupFlagEndToEnd_Success(t *testing.T) {
 		return time.Time{}
 	})
 
-	os.Args = []string{"codex-wrapper", "--cleanup"}
+	os.Args = []string{"codeagent-wrapper", "--cleanup"}
 
 	var exitCode int
 	output := captureStdout(t, func() {
@@ -769,10 +868,10 @@ func TestRunCleanupFlagEndToEnd_Success(t *testing.T) {
 	if !strings.Contains(output, "Files kept: 1") {
 		t.Fatalf("missing 'Files kept: 1' in output: %q", output)
 	}
-	if !strings.Contains(output, "codex-wrapper-2100.log") || !strings.Contains(output, "codex-wrapper-2200-extra.log") {
+	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, "codex-wrapper-2300.log") {
+	if !strings.Contains(output, "codeagent-wrapper-2300.log") {
 		t.Fatalf("missing kept file names in output: %q", output)
 	}
 
@@ -785,7 +884,7 @@ func TestRunCleanupFlagEndToEnd_Success(t *testing.T) {
 		t.Fatalf("expected kept log to remain, err=%v", err)
 	}
 
-	currentLog := filepath.Join(tempDir, fmt.Sprintf("codex-wrapper-%d.log", os.Getpid()))
+	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) {
@@ -804,7 +903,7 @@ func TestRunCleanupFlagEndToEnd_FailureDoesNotAffectStartup(t *testing.T) {
 		return CleanupStats{Scanned: 1}, fmt.Errorf("permission denied")
 	}
 
-	os.Args = []string{"codex-wrapper", "--cleanup"}
+	os.Args = []string{"codeagent-wrapper", "--cleanup"}
 
 	var exitCode int
 	errOutput := captureStderr(t, func() {
@@ -821,7 +920,7 @@ func TestRunCleanupFlagEndToEnd_FailureDoesNotAffectStartup(t *testing.T) {
 		t.Fatalf("cleanup called %d times, want 1", calls)
 	}
 
-	currentLog := filepath.Join(tempDir, fmt.Sprintf("codex-wrapper-%d.log", os.Getpid()))
+	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) {
@@ -834,7 +933,7 @@ func TestRunCleanupFlagEndToEnd_FailureDoesNotAffectStartup(t *testing.T) {
 	codexCommand = createFakeCodexScript(t, "tid-cleanup-e2e", "ok")
 	stdinReader = strings.NewReader("")
 	isTerminalFn = func() bool { return true }
-	os.Args = []string{"codex-wrapper", "post-cleanup task"}
+	os.Args = []string{"codeagent-wrapper", "post-cleanup task"}
 
 	var normalExit int
 	normalOutput := captureStdout(t, func() {

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_AUTH_TOKEN"] = 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/env_inject_test.go

@@ -0,0 +1,193 @@
+package executor
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	backend "codeagent-wrapper/internal/backend"
+	config "codeagent-wrapper/internal/config"
+)
+
+// TestEnvInjectionWithAgent tests the full flow of env injection with agent config
+func TestEnvInjectionWithAgent(t *testing.T) {
+	// Setup temp config
+	tmpDir := t.TempDir()
+	configDir := filepath.Join(tmpDir, ".codeagent")
+	if err := os.MkdirAll(configDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+
+	// Write test config with agent that has base_url and api_key
+	configContent := `{
+		"default_backend": "codex",
+		"agents": {
+			"test-agent": {
+				"backend": "claude",
+				"model": "test-model",
+				"base_url": "https://test.api.com",
+				"api_key": "test-api-key-12345678"
+			}
+		}
+	}`
+	configPath := filepath.Join(configDir, "models.json")
+	if err := os.WriteFile(configPath, []byte(configContent), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	// Override HOME to use temp dir
+	oldHome := os.Getenv("HOME")
+	os.Setenv("HOME", tmpDir)
+	defer os.Setenv("HOME", oldHome)
+
+	// Reset config cache
+	config.ResetModelsConfigCacheForTest()
+	defer config.ResetModelsConfigCacheForTest()
+
+	// Test ResolveAgentConfig
+	agentBackend, model, _, _, baseURL, apiKey, _ := config.ResolveAgentConfig("test-agent")
+	t.Logf("ResolveAgentConfig: backend=%q, model=%q, baseURL=%q, apiKey=%q",
+		agentBackend, model, baseURL, apiKey)
+
+	if agentBackend != "claude" {
+		t.Errorf("expected backend 'claude', got %q", agentBackend)
+	}
+	if baseURL != "https://test.api.com" {
+		t.Errorf("expected baseURL 'https://test.api.com', got %q", baseURL)
+	}
+	if apiKey != "test-api-key-12345678" {
+		t.Errorf("expected apiKey 'test-api-key-12345678', got %q", apiKey)
+	}
+
+	// Test Backend.Env
+	b := backend.ClaudeBackend{}
+	env := b.Env(baseURL, apiKey)
+	t.Logf("Backend.Env: %v", env)
+
+	if env == nil {
+		t.Fatal("expected non-nil env from Backend.Env")
+	}
+	if env["ANTHROPIC_BASE_URL"] != baseURL {
+		t.Errorf("expected ANTHROPIC_BASE_URL=%q, got %q", baseURL, env["ANTHROPIC_BASE_URL"])
+	}
+	if env["ANTHROPIC_AUTH_TOKEN"] != apiKey {
+		t.Errorf("expected ANTHROPIC_AUTH_TOKEN=%q, got %q", apiKey, env["ANTHROPIC_AUTH_TOKEN"])
+	}
+}
+
+// TestEnvInjectionLogic tests the exact logic used in executor
+func TestEnvInjectionLogic(t *testing.T) {
+	// Setup temp config
+	tmpDir := t.TempDir()
+	configDir := filepath.Join(tmpDir, ".codeagent")
+	if err := os.MkdirAll(configDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+
+	configContent := `{
+		"default_backend": "codex",
+		"agents": {
+			"explore": {
+				"backend": "claude",
+				"model": "MiniMax-M2.1",
+				"base_url": "https://api.minimaxi.com/anthropic",
+				"api_key": "eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.test"
+			}
+		}
+	}`
+	configPath := filepath.Join(configDir, "models.json")
+	if err := os.WriteFile(configPath, []byte(configContent), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	oldHome := os.Getenv("HOME")
+	os.Setenv("HOME", tmpDir)
+	defer os.Setenv("HOME", oldHome)
+
+	config.ResetModelsConfigCacheForTest()
+	defer config.ResetModelsConfigCacheForTest()
+
+	// Simulate the executor logic
+	cfgBackend := "claude" // This should come from taskSpec.Backend
+	agentName := "explore"
+
+	// Step 1: Get backend config (usually empty for claude without global config)
+	baseURL, apiKey := config.ResolveBackendConfig(cfgBackend)
+	t.Logf("Step 1 - ResolveBackendConfig(%q): baseURL=%q, apiKey=%q", cfgBackend, baseURL, apiKey)
+
+	// Step 2: If agent specified, get agent config
+	if agentName != "" {
+		agentBackend, _, _, _, agentBaseURL, agentAPIKey, _ := config.ResolveAgentConfig(agentName)
+		t.Logf("Step 2 - ResolveAgentConfig(%q): backend=%q, baseURL=%q, apiKey=%q",
+			agentName, agentBackend, agentBaseURL, agentAPIKey)
+
+		// Step 3: Check if agent backend matches cfg backend
+		if strings.EqualFold(strings.TrimSpace(agentBackend), strings.TrimSpace(cfgBackend)) {
+			baseURL, apiKey = agentBaseURL, agentAPIKey
+			t.Logf("Step 3 - Backend match! Using agent config: baseURL=%q, apiKey=%q", baseURL, apiKey)
+		} else {
+			t.Logf("Step 3 - Backend mismatch: agent=%q, cfg=%q", agentBackend, cfgBackend)
+		}
+	}
+
+	// Step 4: Get env vars from backend
+	b := backend.ClaudeBackend{}
+	injected := b.Env(baseURL, apiKey)
+	t.Logf("Step 4 - Backend.Env: %v", injected)
+
+	// Verify
+	if len(injected) == 0 {
+		t.Fatal("Expected env vars to be injected, got none")
+	}
+
+	expectedURL := "https://api.minimaxi.com/anthropic"
+	if injected["ANTHROPIC_BASE_URL"] != expectedURL {
+		t.Errorf("ANTHROPIC_BASE_URL: expected %q, got %q", expectedURL, injected["ANTHROPIC_BASE_URL"])
+	}
+
+	if _, ok := injected["ANTHROPIC_AUTH_TOKEN"]; !ok {
+		t.Error("ANTHROPIC_AUTH_TOKEN not set")
+	}
+
+	// Step 5: Test masking
+	for k, v := range injected {
+		masked := maskSensitiveValue(k, v)
+		t.Logf("Step 5 - Env log: %s=%s", k, masked)
+	}
+}
+
+// TestTaskSpecBackendPropagation tests that taskSpec.Backend is properly used
+func TestTaskSpecBackendPropagation(t *testing.T) {
+	// Simulate what happens in RunCodexTaskWithContext
+	taskSpec := TaskSpec{
+		ID:      "test",
+		Task:    "hello",
+		Backend: "claude",
+		Agent:   "explore",
+	}
+
+	// This is the logic from executor.go lines 889-916
+	cfg := &config.Config{
+		Mode:    "new",
+		Task:    taskSpec.Task,
+		Backend: "codex", // default
+	}
+
+	var backend Backend = nil // nil in single mode
+	commandName := "codex"    // default
+
+	if backend != nil {
+		cfg.Backend = backend.Name()
+	} else if taskSpec.Backend != "" {
+		cfg.Backend = taskSpec.Backend
+	} else if commandName != "" {
+		cfg.Backend = commandName
+	}
+
+	t.Logf("taskSpec.Backend=%q, cfg.Backend=%q", taskSpec.Backend, cfg.Backend)
+
+	if cfg.Backend != "claude" {
+		t.Errorf("expected cfg.Backend='claude', got %q", cfg.Backend)
+	}
+}

codeagent-wrapper/internal/executor/env_logging_test.go

@@ -0,0 +1,333 @@
+package executor
+
+import (
+	"strings"
+	"testing"
+
+	backend "codeagent-wrapper/internal/backend"
+)
+
+func TestMaskSensitiveValue(t *testing.T) {
+	tests := []struct {
+		name     string
+		key      string
+		value    string
+		expected string
+	}{
+		{
+			name:     "API_KEY with long value",
+			key:      "ANTHROPIC_AUTH_TOKEN",
+			value:    "sk-ant-api03-xxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+			expected: "sk-a****xxxx",
+		},
+		{
+			name:     "api_key lowercase",
+			key:      "api_key",
+			value:    "abcdefghijklmnop",
+			expected: "abcd****mnop",
+		},
+		{
+			name:     "AUTH_TOKEN",
+			key:      "AUTH_TOKEN",
+			value:    "eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9",
+			expected: "eyJh****VCJ9",
+		},
+		{
+			name:     "SECRET",
+			key:      "MY_SECRET",
+			value:    "super-secret-value-12345",
+			expected: "supe****2345",
+		},
+		{
+			name:     "short key value (8 chars)",
+			key:      "API_KEY",
+			value:    "12345678",
+			expected: "****",
+		},
+		{
+			name:     "very short key value",
+			key:      "API_KEY",
+			value:    "abc",
+			expected: "****",
+		},
+		{
+			name:     "empty key value",
+			key:      "API_KEY",
+			value:    "",
+			expected: "",
+		},
+		{
+			name:     "non-sensitive BASE_URL",
+			key:      "ANTHROPIC_BASE_URL",
+			value:    "https://api.anthropic.com",
+			expected: "https://api.anthropic.com",
+		},
+		{
+			name:     "non-sensitive MODEL",
+			key:      "MODEL",
+			value:    "claude-3-opus",
+			expected: "claude-3-opus",
+		},
+		{
+			name:     "case insensitive - Key",
+			key:      "My_Key",
+			value:    "1234567890abcdef",
+			expected: "1234****cdef",
+		},
+		{
+			name:     "case insensitive - TOKEN",
+			key:      "ACCESS_TOKEN",
+			value:    "access123456789",
+			expected: "acce****6789",
+		},
+		{
+			name:     "partial match - apikey",
+			key:      "MYAPIKEY",
+			value:    "1234567890",
+			expected: "1234****7890",
+		},
+		{
+			name:     "partial match - secretvalue",
+			key:      "SECRETVALUE",
+			value:    "abcdefghij",
+			expected: "abcd****ghij",
+		},
+		{
+			name:     "9 char value (just above threshold)",
+			key:      "API_KEY",
+			value:    "123456789",
+			expected: "1234****6789",
+		},
+		{
+			name:     "exactly 8 char value (at threshold)",
+			key:      "API_KEY",
+			value:    "12345678",
+			expected: "****",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := maskSensitiveValue(tt.key, tt.value)
+			if result != tt.expected {
+				t.Errorf("maskSensitiveValue(%q, %q) = %q, want %q", tt.key, tt.value, result, tt.expected)
+			}
+		})
+	}
+}
+
+func TestMaskSensitiveValue_NoLeakage(t *testing.T) {
+	// Ensure sensitive values are never fully exposed
+	sensitiveKeys := []string{"API_KEY", "api_key", "AUTH_TOKEN", "SECRET", "access_token", "MYAPIKEY"}
+	longValue := "this-is-a-very-long-secret-value-that-should-be-masked"
+
+	for _, key := range sensitiveKeys {
+		t.Run(key, func(t *testing.T) {
+			masked := maskSensitiveValue(key, longValue)
+			// Should not contain the full value
+			if masked == longValue {
+				t.Errorf("key %q: value was not masked", key)
+			}
+			// Should contain mask marker
+			if !strings.Contains(masked, "****") {
+				t.Errorf("key %q: masked value %q does not contain ****", key, masked)
+			}
+			// First 4 chars should be visible
+			if !strings.HasPrefix(masked, longValue[:4]) {
+				t.Errorf("key %q: masked value should start with first 4 chars", key)
+			}
+			// Last 4 chars should be visible
+			if !strings.HasSuffix(masked, longValue[len(longValue)-4:]) {
+				t.Errorf("key %q: masked value should end with last 4 chars", key)
+			}
+		})
+	}
+}
+
+func TestMaskSensitiveValue_NonSensitivePassthrough(t *testing.T) {
+	// Non-sensitive keys should pass through unchanged
+	nonSensitiveKeys := []string{
+		"ANTHROPIC_BASE_URL",
+		"BASE_URL",
+		"MODEL",
+		"BACKEND",
+		"WORKDIR",
+		"HOME",
+		"PATH",
+	}
+	value := "any-value-here-12345"
+
+	for _, key := range nonSensitiveKeys {
+		t.Run(key, func(t *testing.T) {
+			result := maskSensitiveValue(key, value)
+			if result != value {
+				t.Errorf("key %q: expected passthrough but got %q", key, result)
+			}
+		})
+	}
+}
+
+// TestClaudeBackendEnv tests that ClaudeBackend.Env returns correct env vars
+func TestClaudeBackendEnv(t *testing.T) {
+	tests := []struct {
+		name       string
+		baseURL    string
+		apiKey     string
+		expectKeys []string
+		expectNil  bool
+	}{
+		{
+			name:       "both base_url and api_key",
+			baseURL:    "https://api.custom.com",
+			apiKey:     "sk-test-key-12345",
+			expectKeys: []string{"ANTHROPIC_BASE_URL", "ANTHROPIC_AUTH_TOKEN"},
+		},
+		{
+			name:       "only base_url",
+			baseURL:    "https://api.custom.com",
+			apiKey:     "",
+			expectKeys: []string{"ANTHROPIC_BASE_URL"},
+		},
+		{
+			name:       "only api_key",
+			baseURL:    "",
+			apiKey:     "sk-test-key-12345",
+			expectKeys: []string{"ANTHROPIC_AUTH_TOKEN"},
+		},
+		{
+			name:      "both empty",
+			baseURL:   "",
+			apiKey:    "",
+			expectNil: true,
+		},
+		{
+			name:      "whitespace only",
+			baseURL:   "   ",
+			apiKey:    "  ",
+			expectNil: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			b := backend.ClaudeBackend{}
+			env := b.Env(tt.baseURL, tt.apiKey)
+
+			if tt.expectNil {
+				if env != nil {
+					t.Errorf("expected nil env, got %v", env)
+				}
+				return
+			}
+
+			if env == nil {
+				t.Fatal("expected non-nil env")
+			}
+
+			for _, key := range tt.expectKeys {
+				if _, ok := env[key]; !ok {
+					t.Errorf("expected key %q in env", key)
+				}
+			}
+
+			// Verify values are correct
+			if tt.baseURL != "" && strings.TrimSpace(tt.baseURL) != "" {
+				if env["ANTHROPIC_BASE_URL"] != strings.TrimSpace(tt.baseURL) {
+					t.Errorf("ANTHROPIC_BASE_URL = %q, want %q", env["ANTHROPIC_BASE_URL"], strings.TrimSpace(tt.baseURL))
+				}
+			}
+			if tt.apiKey != "" && strings.TrimSpace(tt.apiKey) != "" {
+				if env["ANTHROPIC_AUTH_TOKEN"] != strings.TrimSpace(tt.apiKey) {
+					t.Errorf("ANTHROPIC_AUTH_TOKEN = %q, want %q", env["ANTHROPIC_AUTH_TOKEN"], strings.TrimSpace(tt.apiKey))
+				}
+			}
+		})
+	}
+}
+
+// TestEnvLoggingIntegration tests that env vars are properly masked in logs
+func TestEnvLoggingIntegration(t *testing.T) {
+	b := backend.ClaudeBackend{}
+	baseURL := "https://api.minimaxi.com/anthropic"
+	apiKey := "eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.longjwttoken"
+
+	env := b.Env(baseURL, apiKey)
+	if env == nil {
+		t.Fatal("expected non-nil env")
+	}
+
+	// Verify that when we log these values, sensitive ones are masked
+	for k, v := range env {
+		masked := maskSensitiveValue(k, v)
+
+		if k == "ANTHROPIC_BASE_URL" {
+			// URL should not be masked
+			if masked != v {
+				t.Errorf("BASE_URL should not be masked: got %q, want %q", masked, v)
+			}
+		}
+
+		if k == "ANTHROPIC_AUTH_TOKEN" {
+			// API key should be masked
+			if masked == v {
+				t.Errorf("API_KEY should be masked, but got original value")
+			}
+			if !strings.Contains(masked, "****") {
+				t.Errorf("masked API_KEY should contain ****: got %q", masked)
+			}
+			// Should still show first 4 and last 4 chars
+			if !strings.HasPrefix(masked, v[:4]) {
+				t.Errorf("masked value should start with first 4 chars of original")
+			}
+			if !strings.HasSuffix(masked, v[len(v)-4:]) {
+				t.Errorf("masked value should end with last 4 chars of original")
+			}
+		}
+	}
+}
+
+// TestGeminiBackendEnv tests GeminiBackend.Env for comparison
+func TestGeminiBackendEnv(t *testing.T) {
+	b := backend.GeminiBackend{}
+	env := b.Env("https://custom.api", "gemini-api-key-12345")
+
+	if env == nil {
+		t.Fatal("expected non-nil env")
+	}
+
+	// Check that GEMINI env vars are set
+	if _, ok := env["GOOGLE_GEMINI_BASE_URL"]; !ok {
+		t.Error("expected GOOGLE_GEMINI_BASE_URL in env")
+	}
+	if _, ok := env["GEMINI_API_KEY"]; !ok {
+		t.Error("expected GEMINI_API_KEY in env")
+	}
+
+	// Verify masking works for Gemini keys too
+	for k, v := range env {
+		masked := maskSensitiveValue(k, v)
+		if strings.Contains(strings.ToLower(k), "key") {
+			if masked == v && len(v) > 0 {
+				t.Errorf("key %q should be masked", k)
+			}
+		}
+	}
+}
+
+// TestCodexBackendEnv tests CodexBackend.Env
+func TestCodexBackendEnv(t *testing.T) {
+	b := backend.CodexBackend{}
+	env := b.Env("https://custom.api", "codex-api-key-12345")
+
+	if env == nil {
+		t.Fatal("expected non-nil env for codex")
+	}
+
+	// Check for OPENAI env vars
+	if _, ok := env["OPENAI_BASE_URL"]; !ok {
+		t.Error("expected OPENAI_BASE_URL in env")
+	}
+	if _, ok := env["OPENAI_API_KEY"]; !ok {
+		t.Error("expected OPENAI_API_KEY in env")
+	}
+}

codeagent-wrapper/internal/executor/env_stderr_test.go

@@ -0,0 +1,133 @@
+package executor
+
+import (
+	"context"
+	"errors"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+type fakeCmd struct {
+	env map[string]string
+}
+
+func (f *fakeCmd) Start() error { return nil }
+func (f *fakeCmd) Wait() error  { return nil }
+func (f *fakeCmd) StdoutPipe() (io.ReadCloser, error) {
+	return io.NopCloser(strings.NewReader("")), nil
+}
+func (f *fakeCmd) StderrPipe() (io.ReadCloser, error) {
+	return nil, errors.New("fake stderr pipe error")
+}
+func (f *fakeCmd) StdinPipe() (io.WriteCloser, error) {
+	return nil, errors.New("fake stdin pipe error")
+}
+func (f *fakeCmd) SetStderr(io.Writer) {}
+func (f *fakeCmd) SetDir(string)       {}
+func (f *fakeCmd) 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 *fakeCmd) Process() processHandle { return nil }
+
+func TestEnvInjection_LogsToStderrAndMasksKey(t *testing.T) {
+	// Arrange ~/.codeagent/models.json via HOME override.
+	tmpDir := t.TempDir()
+	configDir := filepath.Join(tmpDir, ".codeagent")
+	if err := os.MkdirAll(configDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	const baseURL = "https://api.minimaxi.com/anthropic"
+	const apiKey = "eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.test"
+	models := `{
+  "agents": {
+    "explore": {
+      "backend": "claude",
+      "model": "MiniMax-M2.1",
+      "base_url": "` + baseURL + `",
+      "api_key": "` + apiKey + `"
+    }
+  }
+}`
+	if err := os.WriteFile(filepath.Join(configDir, "models.json"), []byte(models), 0o644); err != nil {
+		t.Fatal(err)
+	}
+
+	oldHome := os.Getenv("HOME")
+	if err := os.Setenv("HOME", tmpDir); err != nil {
+		t.Fatal(err)
+	}
+	defer func() { _ = os.Setenv("HOME", oldHome) }()
+
+	config.ResetModelsConfigCacheForTest()
+	defer config.ResetModelsConfigCacheForTest()
+
+	// Capture stderr (RunCodexTaskWithContext prints env injection lines there).
+	r, w, err := os.Pipe()
+	if err != nil {
+		t.Fatal(err)
+	}
+	oldStderr := os.Stderr
+	os.Stderr = w
+	defer func() { os.Stderr = oldStderr }()
+
+	readDone := make(chan string, 1)
+	go func() {
+		defer r.Close()
+		b, _ := io.ReadAll(r)
+		readDone <- string(b)
+	}()
+
+	var cmd *fakeCmd
+	restoreRunner := SetNewCommandRunner(func(ctx context.Context, name string, args ...string) CommandRunner {
+		cmd = &fakeCmd{}
+		return cmd
+	})
+	defer restoreRunner()
+
+	// Act: force an early return right after env injection by making StderrPipe fail.
+	_ = RunCodexTaskWithContext(
+		context.Background(),
+		TaskSpec{Task: "hi", WorkDir: ".", Backend: "claude", Agent: "explore"},
+		nil,
+		"claude",
+		nil,
+		nil,
+		false,
+		false,
+		1,
+	)
+
+	_ = w.Close()
+	got := <-readDone
+
+	// Assert: env was injected into the command and logging is present with masking.
+	if cmd == nil || cmd.env == nil {
+		t.Fatalf("expected cmd env to be set, got cmd=%v env=%v", cmd, nil)
+	}
+	if cmd.env["ANTHROPIC_BASE_URL"] != baseURL {
+		t.Fatalf("ANTHROPIC_BASE_URL=%q, want %q", cmd.env["ANTHROPIC_BASE_URL"], baseURL)
+	}
+	if cmd.env["ANTHROPIC_AUTH_TOKEN"] != apiKey {
+		t.Fatalf("ANTHROPIC_AUTH_TOKEN=%q, want %q", cmd.env["ANTHROPIC_AUTH_TOKEN"], apiKey)
+	}
+
+	if !strings.Contains(got, "Env: ANTHROPIC_BASE_URL="+baseURL) {
+		t.Fatalf("stderr missing base URL env log; stderr=%q", got)
+	}
+	if !strings.Contains(got, "Env: ANTHROPIC_AUTH_TOKEN=eyJh****test") {
+		t.Fatalf("stderr missing masked API key log; stderr=%q", got)
+	}
+}

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

@@ -1,10 +1,11 @@
-package main
+package logger
 
 import (
 	"bufio"
 	"context"
 	"errors"
 	"fmt"
+	"hash/crc32"
 	"os"
 	"path/filepath"
 	"strconv"
@@ -12,28 +13,35 @@ import (
 	"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
-	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
+	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 {
-	level string
-	msg   string
+	msg     string
+	level   zerolog.Level
+	isError bool // true for ERROR or WARN levels
 }
 
 // CleanupStats captures the outcome of a cleanupOldLogs run.
@@ -55,6 +63,10 @@ var (
 	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) {
@@ -64,14 +76,23 @@ func NewLogger() (*Logger, error) {
 // 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) {
-	filename := fmt.Sprintf("%s-%d", primaryLogPrefix(), os.Getpid())
+	pid := os.Getpid()
+	filename := fmt.Sprintf("%s-%d", PrimaryLogPrefix(), pid)
+	var safeSuffix string
 	if suffix != "" {
-		filename += "-" + 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
@@ -86,12 +107,81 @@ func NewLoggerWithSuffix(suffix string) (*Logger, error) {
 		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 {
@@ -100,22 +190,30 @@ func (l *Logger) Path() string {
 	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.log("INFO", msg) }
+func (l *Logger) Info(msg string) { l.logWithLevel(zerolog.InfoLevel, msg) }
 
 // Warn logs at WARN level.
-func (l *Logger) Warn(msg string) { l.log("WARN", msg) }
+func (l *Logger) Warn(msg string) { l.logWithLevel(zerolog.WarnLevel, msg) }
 
 // Debug logs at DEBUG level.
-func (l *Logger) Debug(msg string) { l.log("DEBUG", msg) }
+func (l *Logger) Debug(msg string) { l.logWithLevel(zerolog.DebugLevel, msg) }
 
 // Error logs at ERROR level.
-func (l *Logger) Error(msg string) { l.log("ERROR", msg) }
+func (l *Logger) Error(msg string) { l.logWithLevel(zerolog.ErrorLevel, msg) }
 
-// Close stops the worker and syncs the log file.
+// 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.
-// Returns after a 5-second timeout if worker doesn't stop gracefully.
+// 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
@@ -126,42 +224,51 @@ func (l *Logger) Close() error {
 	l.closeOnce.Do(func() {
 		l.closed.Store(true)
 		close(l.done)
-		close(l.ch)
 
-		// Wait for worker with timeout
+		timeout := loggerCloseTimeout()
 		workerDone := make(chan struct{})
 		go func() {
 			l.workerWG.Wait()
 			close(workerDone)
 		}()
 
-		select {
-		case <-workerDone:
-			// Worker stopped gracefully
-		case <-time.After(5 * time.Second):
-			// Worker timeout - proceed with cleanup anyway
-			closeErr = fmt.Errorf("logger worker timeout during close")
+		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 err := l.writer.Flush(); err != nil && closeErr == nil {
-			closeErr = err
+		if l.workerErr != nil && closeErr == nil {
+			closeErr = l.workerErr
 		}
-
-		if err := l.file.Sync(); err != nil && closeErr == nil {
-			closeErr = err
-		}
-
-		if err := l.file.Close(); err != nil && closeErr == nil {
-			closeErr = err
-		}
-
-		// Log file is kept for debugging - NOT removed
-		// Users can manually clean up /tmp/<wrapper>-*.log files
 	})
 
 	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 {
@@ -170,34 +277,29 @@ func (l *Logger) RemoveLogFile() error {
 	return os.Remove(l.path)
 }
 
-// ExtractRecentErrors reads the log file and returns the most recent ERROR and WARN entries.
+// 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 || l.path == "" {
+	if l == nil || maxEntries <= 0 {
 		return nil
 	}
 
-	f, err := os.Open(l.path)
-	if err != nil {
+	l.errorMu.Lock()
+	defer l.errorMu.Unlock()
+
+	if len(l.errorEntries) == 0 {
 		return nil
 	}
-	defer f.Close()
 
-	var entries []string
-	scanner := bufio.NewScanner(f)
-	for scanner.Scan() {
-		line := scanner.Text()
-		if strings.Contains(line, "] ERROR:") || strings.Contains(line, "] WARN:") {
-			entries = append(entries, line)
-		}
+	// Return last N entries
+	start := 0
+	if len(l.errorEntries) > maxEntries {
+		start = len(l.errorEntries) - maxEntries
 	}
 
-	// Keep only the last maxEntries
-	if len(entries) > maxEntries {
-		entries = entries[len(entries)-maxEntries:]
-	}
-
-	return entries
+	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.
@@ -246,7 +348,7 @@ func (l *Logger) Flush() {
 	}
 }
 
-func (l *Logger) log(level, msg string) {
+func (l *Logger) logWithLevel(entryLevel zerolog.Level, msg string) {
 	if l == nil {
 		return
 	}
@@ -254,7 +356,8 @@ func (l *Logger) log(level, msg string) {
 		return
 	}
 
-	entry := logEntry{level: level, msg: msg}
+	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()
@@ -275,18 +378,42 @@ func (l *Logger) run() {
 	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 {
-				// Channel closed, final flush
-				_ = l.writer.Flush()
+				finalize()
 				return
 			}
-			timestamp := time.Now().Format("2006-01-02 15:04:05.000")
-			pid := os.Getpid()
-			fmt.Fprintf(l.writer, "[%s] [PID:%d] %s: %s\n", timestamp, pid, entry.level, entry.msg)
-			l.pendingWG.Done()
+			writeEntry(entry)
 
 		case <-ticker.C:
 			_ = l.writer.Flush()
@@ -296,6 +423,21 @@ func (l *Logger) run() {
 			_ = 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
+				}
+			}
 		}
 	}
 }
@@ -309,10 +451,7 @@ func cleanupOldLogs() (CleanupStats, error) {
 	var stats CleanupStats
 	tempDir := os.TempDir()
 
-	prefixes := logPrefixes()
-	if len(prefixes) == 0 {
-		prefixes = []string{defaultWrapperName}
-	}
+	prefixes := LogPrefixes()
 
 	seen := make(map[string]struct{})
 	var matches []string
@@ -343,7 +482,8 @@ func cleanupOldLogs() (CleanupStats, error) {
 			stats.Kept++
 			stats.KeptFiles = append(stats.KeptFiles, filename)
 			if reason != "" {
-				logWarn(fmt.Sprintf("cleanupOldLogs: skipping %s: %s", filename, reason))
+				// Use Debug level to avoid polluting Recent Errors with cleanup noise
+				logDebug(fmt.Sprintf("cleanupOldLogs: skipping %s: %s", filename, reason))
 			}
 			continue
 		}
@@ -461,10 +601,7 @@ func isPIDReused(logPath string, pid int) bool {
 	if procStartTime.IsZero() {
 		// Can't determine process start time
 		// Check if file is very old (>7 days), likely from a dead process
-		if time.Since(fileModTime) > 7*24*time.Hour {
-			return true // File is old enough to be from a different process
-		}
-		return false // Be conservative for recent files
+		return time.Since(fileModTime) > 7*24*time.Hour
 	}
 
 	// If the log file was modified before the process started, PID was reused
@@ -474,10 +611,7 @@ func isPIDReused(logPath string, pid int) bool {
 
 func parsePIDFromLog(path string) (int, bool) {
 	name := filepath.Base(path)
-	prefixes := logPrefixes()
-	if len(prefixes) == 0 {
-		prefixes = []string{defaultWrapperName}
-	}
+	prefixes := LogPrefixes()
 
 	for _, prefix := range prefixes {
 		prefixWithDash := fmt.Sprintf("%s-", prefix)
@@ -531,3 +665,19 @@ func renderWorkerLimit(limit int) string {
 	}
 	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

@@ -1,4 +1,4 @@
-package main
+package logger
 
 import (
 	"bufio"
@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"math"
 	"os"
-	"os/exec"
 	"path/filepath"
 	"strconv"
 	"strings"
@@ -26,7 +25,7 @@ func compareCleanupStats(got, want CleanupStats) bool {
 	return true
 }
 
-func TestRunLoggerCreatesFileWithPID(t *testing.T) {
+func TestLoggerCreatesFileWithPID(t *testing.T) {
 	tempDir := t.TempDir()
 	t.Setenv("TMPDIR", tempDir)
 
@@ -46,7 +45,7 @@ func TestRunLoggerCreatesFileWithPID(t *testing.T) {
 	}
 }
 
-func TestRunLoggerWritesLevels(t *testing.T) {
+func TestLoggerWritesLevels(t *testing.T) {
 	tempDir := t.TempDir()
 	t.Setenv("TMPDIR", tempDir)
 
@@ -69,7 +68,7 @@ func TestRunLoggerWritesLevels(t *testing.T) {
 	}
 
 	content := string(data)
-	checks := []string{"INFO: info message", "WARN: warn message", "DEBUG: debug message", "ERROR: error message"}
+	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)
@@ -77,7 +76,7 @@ func TestRunLoggerWritesLevels(t *testing.T) {
 	}
 }
 
-func TestRunLoggerCloseRemovesFileAndStopsWorker(t *testing.T) {
+func TestLoggerCloseStopsWorkerAndKeepsFile(t *testing.T) {
 	tempDir := t.TempDir()
 	t.Setenv("TMPDIR", tempDir)
 
@@ -102,21 +101,9 @@ func TestRunLoggerCloseRemovesFileAndStopsWorker(t *testing.T) {
 
 	// Clean up manually for test
 	defer os.Remove(logPath)
-
-	done := make(chan struct{})
-	go func() {
-		logger.workerWG.Wait()
-		close(done)
-	}()
-
-	select {
-	case <-done:
-	case <-time.After(200 * time.Millisecond):
-		t.Fatalf("worker goroutine did not exit after Close")
-	}
 }
 
-func TestRunLoggerConcurrentWritesSafe(t *testing.T) {
+func TestLoggerConcurrentWritesSafe(t *testing.T) {
 	tempDir := t.TempDir()
 	t.Setenv("TMPDIR", tempDir)
 
@@ -165,50 +152,13 @@ func TestRunLoggerConcurrentWritesSafe(t *testing.T) {
 	}
 }
 
-func TestRunLoggerTerminateProcessActive(t *testing.T) {
-	cmd := exec.Command("sleep", "5")
-	if err := cmd.Start(); err != nil {
-		t.Skipf("cannot start sleep command: %v", err)
-	}
-
-	timer := terminateProcess(&realCmd{cmd: cmd})
-	if timer == nil {
-		t.Fatalf("terminateProcess returned nil timer for active process")
-	}
-	defer timer.Stop()
-
-	done := make(chan error, 1)
-	go func() {
-		done <- cmd.Wait()
-	}()
-
-	select {
-	case <-time.After(500 * time.Millisecond):
-		t.Fatalf("process not terminated promptly")
-	case <-done:
-	}
-
-	// Force the timer callback to run immediately to cover the kill branch.
-	timer.Reset(0)
-	time.Sleep(10 * time.Millisecond)
-}
-
-func TestRunTerminateProcessNil(t *testing.T) {
-	if timer := terminateProcess(nil); timer != nil {
-		t.Fatalf("terminateProcess(nil) should return nil timer")
-	}
-	if timer := terminateProcess(&realCmd{cmd: &exec.Cmd{}}); timer != nil {
-		t.Fatalf("terminateProcess with nil process should return nil timer")
-	}
-}
-
-func TestRunCleanupOldLogsRemovesOrphans(t *testing.T) {
+func TestLoggerCleanupOldLogsRemovesOrphans(t *testing.T) {
 	tempDir := setTempDirEnv(t, t.TempDir())
 
-	orphan1 := createTempLog(t, tempDir, "codex-wrapper-111.log")
-	orphan2 := createTempLog(t, tempDir, "codex-wrapper-222-suffix.log")
-	running1 := createTempLog(t, tempDir, "codex-wrapper-333.log")
-	running2 := createTempLog(t, tempDir, "codex-wrapper-444-extra-info.log")
+	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}
@@ -252,19 +202,19 @@ func TestRunCleanupOldLogsRemovesOrphans(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsHandlesInvalidNamesAndErrors(t *testing.T) {
+func TestLoggerCleanupOldLogsHandlesInvalidNamesAndErrors(t *testing.T) {
 	tempDir := setTempDirEnv(t, t.TempDir())
 
 	invalid := []string{
-		"codex-wrapper-.log",
-		"codex-wrapper.log",
-		"codex-wrapper-foo-bar.txt",
+		"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, "codex-wrapper-555-extra.log")
+	target := createTempLog(t, tempDir, "codeagent-wrapper-555-extra.log")
 
 	var checked []int
 	stubProcessRunning(t, func(pid int) bool {
@@ -310,7 +260,7 @@ func TestRunCleanupOldLogsHandlesInvalidNamesAndErrors(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsHandlesGlobFailures(t *testing.T) {
+func TestLoggerCleanupOldLogsHandlesGlobFailures(t *testing.T) {
 	stubProcessRunning(t, func(pid int) bool {
 		t.Fatalf("process check should not run when glob fails")
 		return false
@@ -336,7 +286,7 @@ func TestRunCleanupOldLogsHandlesGlobFailures(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsEmptyDirectoryStats(t *testing.T) {
+func TestLoggerCleanupOldLogsEmptyDirectoryStats(t *testing.T) {
 	setTempDirEnv(t, t.TempDir())
 
 	stubProcessRunning(t, func(int) bool {
@@ -356,12 +306,12 @@ func TestRunCleanupOldLogsEmptyDirectoryStats(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsHandlesTempDirPermissionErrors(t *testing.T) {
+func TestLoggerCleanupOldLogsHandlesTempDirPermissionErrors(t *testing.T) {
 	tempDir := setTempDirEnv(t, t.TempDir())
 
 	paths := []string{
-		createTempLog(t, tempDir, "codex-wrapper-6100.log"),
-		createTempLog(t, tempDir, "codex-wrapper-6101.log"),
+		createTempLog(t, tempDir, "codeagent-wrapper-6100.log"),
+		createTempLog(t, tempDir, "codeagent-wrapper-6101.log"),
 	}
 
 	stubProcessRunning(t, func(int) bool { return false })
@@ -396,11 +346,11 @@ func TestRunCleanupOldLogsHandlesTempDirPermissionErrors(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsHandlesPermissionDeniedFile(t *testing.T) {
+func TestLoggerCleanupOldLogsHandlesPermissionDeniedFile(t *testing.T) {
 	tempDir := setTempDirEnv(t, t.TempDir())
 
-	protected := createTempLog(t, tempDir, "codex-wrapper-6200.log")
-	deletable := createTempLog(t, tempDir, "codex-wrapper-6201.log")
+	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{} })
@@ -433,13 +383,13 @@ func TestRunCleanupOldLogsHandlesPermissionDeniedFile(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsPerformanceBound(t *testing.T) {
+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("codex-wrapper-%d.log", 10000+i)
+		name := fmt.Sprintf("codeagent-wrapper-%d.log", 10000+i)
 		fakePaths[i] = createTempLog(t, tempDir, name)
 	}
 
@@ -476,21 +426,11 @@ func TestRunCleanupOldLogsPerformanceBound(t *testing.T) {
 	}
 }
 
-func TestRunCleanupOldLogsCoverageSuite(t *testing.T) {
-	TestBackendParseJSONStream_CoverageSuite(t)
-}
-
-// Reuse the existing coverage suite so the focused TestLogger run still exercises
-// the rest of the codebase and keeps coverage high.
-func TestRunLoggerCoverageSuite(t *testing.T) {
-	TestBackendParseJSONStream_CoverageSuite(t)
-}
-
-func TestRunCleanupOldLogsKeepsCurrentProcessLog(t *testing.T) {
+func TestLoggerCleanupOldLogsKeepsCurrentProcessLog(t *testing.T) {
 	tempDir := setTempDirEnv(t, t.TempDir())
 
 	currentPID := os.Getpid()
-	currentLog := createTempLog(t, tempDir, fmt.Sprintf("codex-wrapper-%d.log", currentPID))
+	currentLog := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", currentPID))
 
 	stubProcessRunning(t, func(pid int) bool {
 		if pid != currentPID {
@@ -518,7 +458,7 @@ func TestRunCleanupOldLogsKeepsCurrentProcessLog(t *testing.T) {
 	}
 }
 
-func TestIsPIDReusedScenarios(t *testing.T) {
+func TestLoggerIsPIDReusedScenarios(t *testing.T) {
 	now := time.Now()
 	tests := []struct {
 		name      string
@@ -552,7 +492,7 @@ func TestIsPIDReusedScenarios(t *testing.T) {
 	}
 }
 
-func TestIsUnsafeFileSecurityChecks(t *testing.T) {
+func TestLoggerIsUnsafeFileSecurityChecks(t *testing.T) {
 	tempDir := t.TempDir()
 	absTempDir, err := filepath.Abs(tempDir)
 	if err != nil {
@@ -566,7 +506,7 @@ func TestIsUnsafeFileSecurityChecks(t *testing.T) {
 		stubEvalSymlinks(t, func(path string) (string, error) {
 			return filepath.Join(absTempDir, filepath.Base(path)), nil
 		})
-		unsafe, reason := isUnsafeFile(filepath.Join(absTempDir, "codex-wrapper-1.log"), tempDir)
+		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)
 		}
@@ -592,26 +532,32 @@ func TestIsUnsafeFileSecurityChecks(t *testing.T) {
 		})
 		otherDir := t.TempDir()
 		stubEvalSymlinks(t, func(string) (string, error) {
-			return filepath.Join(otherDir, "codex-wrapper-9.log"), nil
+			return filepath.Join(otherDir, "codeagent-wrapper-9.log"), nil
 		})
-		unsafe, reason := isUnsafeFile(filepath.Join(otherDir, "codex-wrapper-9.log"), tempDir)
+		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 TestRunLoggerPathAndRemove(t *testing.T) {
+func TestLoggerPathAndRemove(t *testing.T) {
 	tempDir := t.TempDir()
-	path := filepath.Join(tempDir, "sample.log")
-	if err := os.WriteFile(path, []byte("test"), 0o644); err != nil {
-		t.Fatalf("failed to create temp file: %v", err)
+	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)
 	}
 
-	logger := &Logger{path: path}
-	if got := logger.Path(); got != path {
-		t.Fatalf("Path() = %q, want %q", got, path)
-	}
 	if err := logger.RemoveLogFile(); err != nil {
 		t.Fatalf("RemoveLogFile() error = %v", err)
 	}
@@ -628,45 +574,20 @@ func TestRunLoggerPathAndRemove(t *testing.T) {
 	}
 }
 
-func TestRunLoggerInternalLog(t *testing.T) {
-	logger := &Logger{
-		ch:        make(chan logEntry, 1),
-		done:      make(chan struct{}),
-		pendingWG: sync.WaitGroup{},
-	}
-
-	done := make(chan logEntry, 1)
-	go func() {
-		entry := <-logger.ch
-		logger.pendingWG.Done()
-		done <- entry
-	}()
-
-	logger.log("INFO", "hello")
-	entry := <-done
-	if entry.level != "INFO" || entry.msg != "hello" {
-		t.Fatalf("unexpected entry %+v", entry)
-	}
-
-	logger.closed.Store(true)
-	logger.log("INFO", "ignored")
-	close(logger.done)
-}
-
-func TestRunParsePIDFromLog(t *testing.T) {
+func TestLoggerParsePIDFromLog(t *testing.T) {
 	hugePID := strconv.FormatInt(math.MaxInt64, 10) + "0"
 	tests := []struct {
 		name string
 		pid  int
 		ok   bool
 	}{
-		{"codex-wrapper-123.log", 123, true},
-		{"codex-wrapper-999-extra.log", 999, true},
-		{"codex-wrapper-.log", 0, false},
+		{"codeagent-wrapper-123.log", 123, true},
+		{"codeagent-wrapper-999-extra.log", 999, true},
+		{"codeagent-wrapper-.log", 0, false},
 		{"invalid-name.log", 0, false},
-		{"codex-wrapper--5.log", 0, false},
-		{"codex-wrapper-0.log", 0, false},
-		{fmt.Sprintf("codex-wrapper-%s.log", hugePID), 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 {
@@ -705,56 +626,32 @@ func setTempDirEnv(t *testing.T, dir string) string {
 
 func stubProcessRunning(t *testing.T, fn func(int) bool) {
 	t.Helper()
-	original := processRunningCheck
-	processRunningCheck = fn
-	t.Cleanup(func() {
-		processRunningCheck = original
-	})
+	t.Cleanup(SetProcessRunningCheck(fn))
 }
 
 func stubProcessStartTime(t *testing.T, fn func(int) time.Time) {
 	t.Helper()
-	original := processStartTimeFn
-	processStartTimeFn = fn
-	t.Cleanup(func() {
-		processStartTimeFn = original
-	})
+	t.Cleanup(SetProcessStartTimeFn(fn))
 }
 
 func stubRemoveLogFile(t *testing.T, fn func(string) error) {
 	t.Helper()
-	original := removeLogFileFn
-	removeLogFileFn = fn
-	t.Cleanup(func() {
-		removeLogFileFn = original
-	})
+	t.Cleanup(SetRemoveLogFileFn(fn))
 }
 
 func stubGlobLogFiles(t *testing.T, fn func(string) ([]string, error)) {
 	t.Helper()
-	original := globLogFiles
-	globLogFiles = fn
-	t.Cleanup(func() {
-		globLogFiles = original
-	})
+	t.Cleanup(SetGlobLogFilesFn(fn))
 }
 
 func stubFileStat(t *testing.T, fn func(string) (os.FileInfo, error)) {
 	t.Helper()
-	original := fileStatFn
-	fileStatFn = fn
-	t.Cleanup(func() {
-		fileStatFn = original
-	})
+	t.Cleanup(SetFileStatFn(fn))
 }
 
 func stubEvalSymlinks(t *testing.T, fn func(string) (string, error)) {
 	t.Helper()
-	original := evalSymlinksFn
-	evalSymlinksFn = fn
-	t.Cleanup(func() {
-		evalSymlinksFn = original
-	})
+	t.Cleanup(SetEvalSymlinksFn(fn))
 }
 
 type fakeFileInfo struct {
@@ -769,69 +666,93 @@ func (f fakeFileInfo) ModTime() time.Time { return f.modTime }
 func (f fakeFileInfo) IsDir() bool        { return false }
 func (f fakeFileInfo) Sys() interface{}   { return nil }
 
-func TestExtractRecentErrors(t *testing.T) {
+func TestLoggerExtractRecentErrors(t *testing.T) {
 	tests := []struct {
 		name       string
-		content    string
+		logs       []struct{ level, msg string }
 		maxEntries int
 		want       []string
 	}{
 		{
 			name:       "empty log",
-			content:    "",
+			logs:       nil,
 			maxEntries: 10,
 			want:       nil,
 		},
 		{
 			name: "no errors",
-			content: `[2025-01-01 12:00:00.000] [PID:123] INFO: started
-[2025-01-01 12:00:01.000] [PID:123] DEBUG: processing`,
+			logs: []struct{ level, msg string }{
+				{"INFO", "started"},
+				{"DEBUG", "processing"},
+			},
 			maxEntries: 10,
 			want:       nil,
 		},
 		{
 			name: "single error",
-			content: `[2025-01-01 12:00:00.000] [PID:123] INFO: started
-[2025-01-01 12:00:01.000] [PID:123] ERROR: something failed`,
+			logs: []struct{ level, msg string }{
+				{"INFO", "started"},
+				{"ERROR", "something failed"},
+			},
 			maxEntries: 10,
-			want:       []string{"[2025-01-01 12:00:01.000] [PID:123] ERROR: something failed"},
+			want:       []string{"something failed"},
 		},
 		{
 			name: "error and warn",
-			content: `[2025-01-01 12:00:00.000] [PID:123] INFO: started
-[2025-01-01 12:00:01.000] [PID:123] WARN: warning message
-[2025-01-01 12:00:02.000] [PID:123] ERROR: error message`,
+			logs: []struct{ level, msg string }{
+				{"INFO", "started"},
+				{"WARN", "warning message"},
+				{"ERROR", "error message"},
+			},
 			maxEntries: 10,
 			want: []string{
-				"[2025-01-01 12:00:01.000] [PID:123] WARN: warning message",
-				"[2025-01-01 12:00:02.000] [PID:123] ERROR: error message",
+				"warning message",
+				"error message",
 			},
 		},
 		{
 			name: "truncate to max",
-			content: `[2025-01-01 12:00:00.000] [PID:123] ERROR: error 1
-[2025-01-01 12:00:01.000] [PID:123] ERROR: error 2
-[2025-01-01 12:00:02.000] [PID:123] ERROR: error 3
-[2025-01-01 12:00:03.000] [PID:123] ERROR: error 4
-[2025-01-01 12:00:04.000] [PID:123] ERROR: error 5`,
+			logs: []struct{ level, msg string }{
+				{"ERROR", "error 1"},
+				{"ERROR", "error 2"},
+				{"ERROR", "error 3"},
+				{"ERROR", "error 4"},
+				{"ERROR", "error 5"},
+			},
 			maxEntries: 3,
 			want: []string{
-				"[2025-01-01 12:00:02.000] [PID:123] ERROR: error 3",
-				"[2025-01-01 12:00:03.000] [PID:123] ERROR: error 4",
-				"[2025-01-01 12:00:04.000] [PID:123] ERROR: error 5",
+				"error 3",
+				"error 4",
+				"error 5",
 			},
 		},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			tempDir := t.TempDir()
-			logPath := filepath.Join(tempDir, "test.log")
-			if err := os.WriteFile(logPath, []byte(tt.content), 0o644); err != nil {
-				t.Fatalf("failed to write test log: %v", err)
+			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 := &Logger{path: logPath}
+			logger.Flush()
+
 			got := logger.ExtractRecentErrors(tt.maxEntries)
 
 			if len(got) != len(tt.want) {
@@ -846,23 +767,137 @@ func TestExtractRecentErrors(t *testing.T) {
 	}
 }
 
-func TestExtractRecentErrorsNilLogger(t *testing.T) {
+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 TestExtractRecentErrorsEmptyPath(t *testing.T) {
-	logger := &Logger{path: ""}
+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 TestExtractRecentErrorsFileNotExist(t *testing.T) {
-	logger := &Logger{path: "/nonexistent/path/to/log.log"}
+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)
+	}
+}