fix(test): set USERPROFILE on Windows for skills tests

os.UserHomeDir() uses USERPROFILE on Windows, not HOME. Add
setTestHome helper that sets both env vars for cross-platform
compatibility in CI.

Generated with SWE-Agent.ai

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

.claude-plugin/marketplace.json

@@ -15,33 +15,33 @@
       "source": "./skills/omo",
       "category": "development"
     },
-    {
-      "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",
+      "source": "./agents/requirements",
       "category": "development"
     },
     {
       "name": "bmad",
       "description": "Full BMAD agile workflow with role-based agents (PO, Architect, SM, Dev, QA) and interactive approval gates",
       "version": "5.6.1",
-      "source": "./bmad-agile-workflow",
+      "source": "./agents/bmad",
       "category": "development"
     },
     {
       "name": "dev-kit",
       "description": "Essential development commands for coding, debugging, testing, optimization, and documentation",
       "version": "5.6.1",
-      "source": "./development-essentials",
+      "source": "./agents/development-essentials",
       "category": "productivity"
+    },
+    {
+      "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"
     }
   ]
 }

.github/workflows/ci.yml

@@ -8,7 +8,10 @@ on:
 
 jobs:
   test:
-    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+    runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4
 
@@ -21,11 +24,13 @@ jobs:
         run: |
           cd codeagent-wrapper
           go test -v -cover -coverprofile=coverage.out ./...
+        shell: bash
 
       - name: Check coverage
         run: |
           cd codeagent-wrapper
           go tool cover -func=coverage.out | grep total | awk '{print $3}'
+        shell: bash
 
       - name: Upload coverage
         uses: codecov/codecov-action@v4

.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 ${OUTPUT_NAME} .
+          go build -ldflags="-s -w -X codeagent-wrapper/internal/app.version=${VERSION}" -o ${OUTPUT_NAME} ./cmd/codeagent-wrapper
           chmod +x ${OUTPUT_NAME}
           echo "artifact_path=codeagent-wrapper/${OUTPUT_NAME}" >> $GITHUB_OUTPUT
 
@@ -91,6 +91,33 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Generate Release Notes
+        id: release_notes
+        run: |
+          # Get previous tag
+          PREVIOUS_TAG=$(git tag --sort=-version:refname | grep -v "^${{ github.ref_name }}$" | head -n 1)
+
+          if [ -z "$PREVIOUS_TAG" ]; then
+            echo "No previous tag found, using all commits"
+            COMMITS=$(git log --pretty=format:"- %s (%h)" --no-merges)
+          else
+            echo "Generating notes from $PREVIOUS_TAG to ${{ github.ref_name }}"
+            COMMITS=$(git log ${PREVIOUS_TAG}..${{ github.ref_name }} --pretty=format:"- %s (%h)" --no-merges)
+          fi
+
+          # Create release notes
+          cat > release_notes.md <<EOF
+          ## What's Changed
+
+          ${COMMITS}
+
+          **Full Changelog**: https://github.com/${{ github.repository }}/compare/${PREVIOUS_TAG}...${{ github.ref_name }}
+          EOF
+
+          cat release_notes.md
 
       - name: Download all artifacts
         uses: actions/download-artifact@v4
@@ -108,6 +135,6 @@ jobs:
         uses: softprops/action-gh-release@v2
         with:
           files: release/*
-          generate_release_notes: true
+          body_path: release_notes.md
           draft: false
           prerelease: false

.gitignore

@@ -7,3 +7,6 @@
 __pycache__
 .coverage
 coverage.out
+references
+output/
+.worktrees/

CHANGELOG.md

@@ -2,6 +2,451 @@
 
 All notable changes to this project will be documented in this file.
 
+## [6.0.0] - 2026-01-26
+
+### 🚀 Features
+
+- support `npx github:cexll/myclaude` for installation and execution
+- default module changed from `dev` to `do`
+
+### 🚜 Refactor
+
+- restructure: create `agents/` and move `bmad-agile-workflow` → `agents/bmad`, `requirements-driven-workflow` → `agents/requirements`, `development-essentials` → `agents/development-essentials`
+- remove legacy directories: `docs/`, `hooks/`, `dev-workflow/`
+- update references across `config.json`, `README.md`, `README_CN.md`, `marketplace.json`, etc.
+
+### 📚 Documentation
+
+- add `skills/README.md` and `PLUGIN_README.md`
+
+### 💼 Other
+
+- add `package.json` and `bin/cli.js` for npx packaging
+
+## [6.1.5] - 2026-01-25
+
+
+### 🐛 Bug Fixes
+
+
+- correct gitignore to not exclude cmd/codeagent-wrapper
+
+## [6.1.4] - 2026-01-25
+
+
+### 🐛 Bug Fixes
+
+
+- support concurrent tasks with unique state files
+
+## [6.1.3] - 2026-01-25
+
+
+### 🐛 Bug Fixes
+
+
+- correct build path in release workflow
+
+- increase stdoutDrainTimeout from 100ms to 500ms
+
+## [6.1.2] - 2026-01-24
+
+
+### 🐛 Bug Fixes
+
+
+- use ANTHROPIC_AUTH_TOKEN for Claude CLI env injection
+
+### 💼 Other
+
+
+- update codeagent version
+
+### 📚 Documentation
+
+
+- restructure root READMEs with do as recommended workflow
+
+- update do/omo/sparv module READMEs with detailed workflows
+
+- add README for bmad and requirements modules
+
+### 🧪 Testing
+
+
+- use prefix match for version flag tests
+
+## [6.1.1] - 2026-01-23
+
+
+### 🚜 Refactor
+
+
+- rename feature-dev to do workflow
+
+## [6.1.0] - 2026-01-23
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- ignore references directory
+
+- add go.work.sum for workspace dependencies
+
+### 🐛 Bug Fixes
+
+
+- read GEMINI_MODEL from ~/.gemini/.env ([#131](https://github.com/cexll/myclaude/issues/131))
+
+- validate non-empty output message before printing
+
+### 🚀 Features
+
+
+- add feature-dev skill with 7-phase workflow
+
+- support \${CLAUDE_PLUGIN_ROOT} variable in hooks config
+
+## [6.0.0-alpha1] - 2026-01-20
+
+
+### 🐛 Bug Fixes
+
+
+- add missing cmd/codeagent/main.go entry point
+
+- update release workflow build path for new directory structure
+
+- write PATH config to both profile and rc files ([#128](https://github.com/cexll/myclaude/issues/128))
+
+### 🚀 Features
+
+
+- add course module with dev, product-requirements and test-cases skills
+
+- add hooks management to install.py
+
+### 🚜 Refactor
+
+
+- restructure codebase to internal/ directory with modular architecture
+
+## [5.6.7] - 2026-01-17
+
+
+### 💼 Other
+
+
+- remove .sparv
+
+### 📚 Documentation
+
+
+- update 'Agent Hierarchy' model for frontend-ui-ux-engineer and document-writer in README ([#127](https://github.com/cexll/myclaude/issues/127))
+
+- update mappings for frontend-ui-ux-engineer and document-writer in README ([#126](https://github.com/cexll/myclaude/issues/126))
+
+### 🚀 Features
+
+
+- add sparv module and interactive plugin manager
+
+- add sparv enhanced rules v1.1
+
+- add sparv skill to claude-plugin v1.1.0
+
+- feat sparv skill
+
+## [5.6.6] - 2026-01-16
+
+
+### 🐛 Bug Fixes
+
+
+- remove extraneous dash arg for opencode stdin mode ([#124](https://github.com/cexll/myclaude/issues/124))
+
+### 💼 Other
+
+
+- update readme
+
+## [5.6.5] - 2026-01-16
+
+
+### 🐛 Bug Fixes
+
+
+- correct default models for oracle and librarian agents ([#120](https://github.com/cexll/myclaude/issues/120))
+
+### 🚀 Features
+
+
+- feat dev skill
+
+## [5.6.4] - 2026-01-15
+
+
+### 🐛 Bug Fixes
+
+
+- filter codex 0.84.0 stderr noise logs ([#122](https://github.com/cexll/myclaude/issues/122))
+
+- filter codex stderr noise logs
+
+## [5.6.3] - 2026-01-14
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- bump codeagent-wrapper version to 5.6.3
+
+### 🐛 Bug Fixes
+
+
+- update version tests to match 5.6.3
+
+- use config override for codex reasoning effort
+
+## [5.6.2] - 2026-01-14
+
+
+### 🐛 Bug Fixes
+
+
+- propagate SkipPermissions to parallel tasks ([#113](https://github.com/cexll/myclaude/issues/113))
+
+- add timeout for Windows process termination
+
+- reject dash as workdir parameter ([#118](https://github.com/cexll/myclaude/issues/118))
+
+### 📚 Documentation
+
+
+- add OmO workflow to README and fix plugin marketplace structure
+
+### 🚜 Refactor
+
+
+- remove sisyphus agent and unused code
+
+## [5.6.1] - 2026-01-13
+
+
+### 🐛 Bug Fixes
+
+
+- add sleep in fake script to prevent CI race condition
+
+- fix gemini env load
+
+- fix omo
+
+### 🚀 Features
+
+
+- add reasoning effort config for codex backend
+
+## [5.6.0] - 2026-01-13
+
+
+### 📚 Documentation
+
+
+- update FAQ for default bypass/skip-permissions behavior
+
+### 🚀 Features
+
+
+- default to skip-permissions and bypass-sandbox
+
+- add omo module for multi-agent orchestration
+
+### 🚜 Refactor
+
+
+- streamline agent documentation and remove sisyphus
+
+## [5.5.0] - 2026-01-12
+
+
+### 🐛 Bug Fixes
+
+
+- 修复 Gemini init 事件 session_id 未提取的问题 ([#111](https://github.com/cexll/myclaude/issues/111))
+
+- fix codeagent skill TaskOutput
+
+### 💼 Other
+
+
+- Merge branch 'master' of github.com:cexll/myclaude
+
+- add test-cases skill
+
+- add browser skill
+
+### 🚀 Features
+
+
+- add multi-agent support with yolo mode
+
+## [5.4.4] - 2026-01-08
+
+
+### 💼 Other
+
+
+- 修复 Windows 后端退出：taskkill 结束进程树 + turn.completed 支持 ([#108](https://github.com/cexll/myclaude/issues/108))
+
+## [5.4.3] - 2026-01-06
+
+
+### 🐛 Bug Fixes
+
+
+- support model parameter for all backends, auto-inject from settings ([#105](https://github.com/cexll/myclaude/issues/105))
+
+### 📚 Documentation
+
+
+- add FAQ Q5 for permission/sandbox env vars
+
+### 🚀 Features
+
+
+- feat skill-install install script and security scan
+
+- add uninstall scripts with selective module removal
+
+## [5.4.2] - 2025-12-31
+
+
+### 🐛 Bug Fixes
+
+
+- replace setx with reg add to avoid 1024-char PATH truncation ([#101](https://github.com/cexll/myclaude/issues/101))
+
+## [5.4.1] - 2025-12-26
+
+
+### 🐛 Bug Fixes
+
+
+- 移除未知事件格式的日志噪声 ([#96](https://github.com/cexll/myclaude/issues/96))
+
+- prevent duplicate PATH entries on reinstall ([#95](https://github.com/cexll/myclaude/issues/95))
+
+### 📚 Documentation
+
+
+- 添加 FAQ 常见问题章节
+
+- update troubleshooting with idempotent PATH commands ([#95](https://github.com/cexll/myclaude/issues/95))
+
+### 🚀 Features
+
+
+- Add intelligent backend selection based on task complexity ([#61](https://github.com/cexll/myclaude/issues/61))
+
+## [5.4.0] - 2025-12-24
+
+
+### 🐛 Bug Fixes
+
+
+- Minor issues #12 and #13 - ASCII mode and performance optimization
+
+- code review fixes for PR #94 - all critical and major issues resolved
+
+### 🚀 Features
+
+
+- v5.4.0 structured execution report ([#94](https://github.com/cexll/myclaude/issues/94))
+
+## [5.2.8] - 2025-12-22
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- simplify release workflow to use GitHub auto-generated notes
+
+### 🐛 Bug Fixes
+
+
+- correct settings.json filename and bump version to v5.2.8
+
+## [5.2.7] - 2025-12-21
+
+
+### ⚙️ Miscellaneous Tasks
+
+
+- bump version to v5.2.7
+
+### 🐛 Bug Fixes
+
+
+- allow claude backend to read env from setting.json while preventing recursion ([#92](https://github.com/cexll/myclaude/issues/92))
+
+- comprehensive security and quality improvements for PR #85 & #87 ([#90](https://github.com/cexll/myclaude/issues/90))
+
+- Parser重复解析优化 + 严重bug修复 + PR #86兼容性 ([#88](https://github.com/cexll/myclaude/issues/88))
+
+### 💼 Other
+
+
+- Improve backend termination after message and extend timeout ([#86](https://github.com/cexll/myclaude/issues/86))
+
+### 🚀 Features
+
+
+- add millisecond-precision timestamps to all log entries ([#91](https://github.com/cexll/myclaude/issues/91))
+
+## [5.2.6] - 2025-12-19
+
+
+### 🐛 Bug Fixes
+
+
+- filter noisy stderr output from gemini backend ([#83](https://github.com/cexll/myclaude/issues/83))
+
+- 修復 wsl install.sh 格式問題 ([#78](https://github.com/cexll/myclaude/issues/78))
+
+### 💼 Other
+
+
+- update all readme
+
+- BMADh和Requirements-Driven支持根据语义生成对应的文档 ([#82](https://github.com/cexll/myclaude/issues/82))
+
+## [5.2.5] - 2025-12-17
+
+
+### 🐛 Bug Fixes
+
+
+- 修复多 backend 并行日志 PID 混乱并移除包装格式 ([#74](https://github.com/cexll/myclaude/issues/74)) ([#76](https://github.com/cexll/myclaude/issues/76))
+
+- replace "Codex" to "codeagent" in dev-plan-generator subagent
+
+- 修復 win python install.py
+
+### 💼 Other
+
+
+- Merge pull request #71 from aliceric27/master
+
+- Merge branch 'cexll:master' into master
+
+- Merge pull request #72 from changxvv/master
+
+- update changelog
+
+- update codeagent skill backend select
+
 ## [5.2.4] - 2025-12-16
 
 

Makefile

@@ -7,12 +7,12 @@
 help:
 	@echo "Claude Code Multi-Agent Workflow - Quick Deployment"
 	@echo ""
-	@echo "Recommended installation: python3 install.py --install-dir ~/.claude"
+	@echo "Recommended installation: npx github:cexll/myclaude"
 	@echo ""
 	@echo "Usage: make [target]"
 	@echo ""
 	@echo "Targets:"
-	@echo "  install              - LEGACY: install all configurations (prefer install.py)"
+	@echo "  install              - LEGACY: install all configurations (prefer npx github:cexll/myclaude)"
 	@echo "  deploy-bmad          - Deploy BMAD workflow (bmad-pilot)"
 	@echo "  deploy-requirements  - Deploy Requirements workflow (requirements-pilot)"
 	@echo "  deploy-essentials    - Deploy Development Essentials workflow"
@@ -31,16 +31,16 @@ CLAUDE_CONFIG_DIR = ~/.claude
 SPECS_DIR = .claude/specs
 
 # Workflow directories
-BMAD_DIR = bmad-agile-workflow
+BMAD_DIR = agents/bmad
-REQUIREMENTS_DIR = requirements-driven-workflow
+REQUIREMENTS_DIR = agents/requirements
-ESSENTIALS_DIR = development-essentials
+ESSENTIALS_DIR = agents/development-essentials
 ADVANCED_DIR = advanced-ai-agents
 OUTPUT_STYLES_DIR = output-styles
 
 # Install all configurations
 install: deploy-all
 	@echo "⚠️  LEGACY PATH: make install will be removed in future versions."
-	@echo "    Prefer: python3 install.py --install-dir ~/.claude"
+	@echo "    Prefer: npx github:cexll/myclaude"
 	@echo "✅ Installation complete!"
 
 # Deploy BMAD workflow
@@ -159,4 +159,3 @@ changelog:
 	@echo ""
 	@echo "Preview the changes:"
 	@echo "  git diff CHANGELOG.md"
-

PLUGIN_README.md

@@ -0,0 +1,18 @@
+# Plugin System
+
+Claude Code plugins for this repo are defined in `.claude-plugin/marketplace.json`.
+
+## Install
+
+```bash
+/plugin marketplace add cexll/myclaude
+/plugin list
+```
+
+## Available Plugins
+
+- `bmad` - BMAD workflow (`./agents/bmad`)
+- `requirements` - requirements-driven workflow (`./agents/requirements`)
+- `dev-kit` - development essentials (`./agents/development-essentials`)
+- `omo` - orchestration skill (`./skills/omo`)
+- `sparv` - SPARV workflow (`./skills/sparv`)

README.md

@@ -3,404 +3,107 @@
 # 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
+## Quick Start
-
-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)
 
 ```bash
-git clone https://github.com/cexll/myclaude.git
+npx github:cexll/myclaude
-cd myclaude
-python3 install.py --install-dir ~/.claude
 ```
 
-## Workflows Overview
+## Modules Overview
 
-### 0. OmO Multi-Agent Orchestrator (Recommended for Complex Tasks)
+| Module | Description | Documentation |
-
+|--------|-------------|---------------|
-**Intelligent multi-agent orchestration that routes tasks to specialized agents based on risk signals.**
+| [do](skills/do/README.md) | **Recommended** - 7-phase feature development with codeagent orchestration | `/do` command |
-
+| [omo](skills/omo/README.md) | Multi-agent orchestration with intelligent routing | `/omo` command |
-```bash
+| [bmad](agents/bmad/README.md) | BMAD agile workflow with 6 specialized agents | `/bmad-pilot` command |
-/omo "analyze and fix this authentication bug"
+| [requirements](agents/requirements/README.md) | Lightweight requirements-to-code pipeline | `/requirements-pilot` command |
-```
+| [essentials](agents/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 |
-**Agent Hierarchy:**
+| course | Course development (combines dev + product-requirements + test-cases) | Composite module |
-| Agent | Role | Backend | Model |
-|-------|------|---------|-------|
-| `oracle` | Technical advisor | Claude | claude-opus-4-5 |
-| `librarian` | External research | Claude | claude-sonnet-4-5 |
-| `explore` | Codebase search | OpenCode | grok-code |
-| `develop` | Code implementation | Codex | gpt-5.2 |
-| `frontend-ui-ux-engineer` | UI/UX specialist | Gemini | gemini-3-pro |
-| `document-writer` | Documentation | Gemini | gemini-3-flash |
-
-**Routing Signals (Not Fixed Pipeline):**
-- Code location unclear → `explore`
-- External library/API → `librarian`
-- Risky/multi-file change → `oracle`
-- Implementation needed → `develop` / `frontend-ui-ux-engineer`
-
-**Common Recipes:**
-- Explain code: `explore`
-- Small fix with known location: `develop` directly
-- Bug fix, location unknown: `explore → develop`
-- Cross-cutting refactor: `explore → oracle → develop`
-- External API integration: `explore + librarian → oracle → develop`
-
-**Best For:** Complex bug investigation, multi-file refactoring, architecture decisions
-
----
-
-### 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.
-
----
-
-## Version Requirements
-
-### Codex CLI
-**Minimum version:** Check compatibility with your installation
-
-The codeagent-wrapper uses these Codex CLI features:
-- `codex e` - Execute commands (shorthand for `codex exec`)
-- `--skip-git-repo-check` - Skip git repository validation
-- `--json` - JSON stream output format
-- `-C <workdir>` - Set working directory
-- `resume <session_id>` - Resume previous sessions
-
-**Verify Codex CLI is installed:**
-```bash
-which codex
-codex --version
-```
-
-### Claude CLI
-**Minimum version:** Check compatibility with your installation
-
-Required features:
-- `--output-format stream-json` - Streaming JSON output format
-- `--setting-sources` - Control setting sources (prevents infinite recursion)
-- `--dangerously-skip-permissions` - Skip permission prompts (use with caution)
-- `-p` - Prompt input flag
-- `-r <session_id>` - Resume sessions
-
-**Security Note:** The wrapper adds `--dangerously-skip-permissions` for Claude by default. Set `CODEAGENT_SKIP_PERMISSIONS=false` to disable if you need permission prompts.
-
-**Verify Claude CLI is installed:**
-```bash
-which claude
-claude --version
-```
-
-### Gemini CLI
-**Minimum version:** Check compatibility with your installation
-
-Required features:
-- `-o stream-json` - JSON stream output format
-- `-y` - Auto-approve prompts (non-interactive mode)
-- `-r <session_id>` - Resume sessions
-- `-p` - Prompt input flag
-
-**Verify Gemini CLI is installed:**
-```bash
-which gemini
-gemini --version
-```
-
----
 
 ## Installation
 
-### Modular Installation (Recommended)
-
 ```bash
-# Install all enabled modules (dev + essentials by default)
+# Interactive installer (recommended)
-python3 install.py --install-dir ~/.claude
+npx github:cexll/myclaude
 
-# Install specific module
+# List installable items (modules / skills / wrapper)
-python3 install.py --module dev
+npx github:cexll/myclaude --list
 
-# List available modules
+# Detect installed modules and update from GitHub
-python3 install.py --list-modules
+npx github:cexll/myclaude --update
 
-# Force overwrite existing files
+# Custom install directory / overwrite
-python3 install.py --force
+npx github:cexll/myclaude --install-dir ~/.claude --force
 ```
 
-### Available Modules
+`--update` detects already installed modules in the target install dir (defaults to `~/.claude`, via `installed_modules.json` when present) and updates them from GitHub (latest release) by overwriting the module files.
 
-| Module | Default | Description |
+### Module Configuration
-|--------|---------|-------------|
-| `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
+Edit `config.json` to enable/disable modules:
-
-```
-~/.claude/
-├── bin/
-│   └── codeagent-wrapper    # Main executable
-├── CLAUDE.md                # Core instructions and role definition
-├── commands/                # Slash commands (/dev, /code, etc.)
-├── agents/                  # Agent definitions
-├── skills/
-│   └── codex/
-│       └── SKILL.md         # Codex integration skill
-├── config.json              # Configuration
-└── installed_modules.json   # Installation status
-```
-
-### Customizing Installation Directory
-
-By default, myclaude installs to `~/.claude`. You can customize this using the `INSTALL_DIR` environment variable:
-
-```bash
-# Install to custom directory
-INSTALL_DIR=/opt/myclaude bash install.sh
-
-# Update your PATH accordingly
-export PATH="/opt/myclaude/bin:$PATH"
-```
-
-**Directory Structure:**
-- `$INSTALL_DIR/bin/` - codeagent-wrapper binary
-- `$INSTALL_DIR/skills/` - Skill definitions
-- `$INSTALL_DIR/config.json` - Configuration file
-- `$INSTALL_DIR/commands/` - Slash command definitions
-- `$INSTALL_DIR/agents/` - Agent definitions
-
-**Note:** When using a custom installation directory, ensure that `$INSTALL_DIR/bin` is added to your `PATH` environment variable.
-
-### Configuration
-
-Edit `config.json` to customize:
 
 ```json
 {
-  "version": "1.0",
-  "install_dir": "~/.claude",
   "modules": {
-    "dev": {
+    "bmad": { "enabled": false },
-      "enabled": true,
+    "requirements": { "enabled": false },
-      "operations": [
+    "essentials": { "enabled": false },
-        {"type": "merge_dir", "source": "dev-workflow"},
+    "omo": { "enabled": false },
-        {"type": "copy_file", "source": "memorys/CLAUDE.md", "target": "CLAUDE.md"},
+    "sparv": { "enabled": false },
-        {"type": "copy_file", "source": "skills/codex/SKILL.md", "target": "skills/codex/SKILL.md"},
+    "do": { "enabled": true },
-        {"type": "run_command", "command": "bash install.sh"}
+    "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 (use PowerShell method above instead)
-REM WARNING: This expands %PATH% which includes system PATH, causing duplication
-REM Note: Using reg add instead of setx to avoid 1024-character truncation limit
-reg add "HKCU\Environment" /v Path /t REG_EXPAND_SZ /d "%USERPROFILE%\bin;%PATH%" /f
-```
-
----
-
 ## Workflow Selection Guide
 
-| Scenario | Recommended Workflow |
+| Scenario | Recommended |
-|----------|---------------------|
+|----------|-------------|
-| New feature with tests | `/dev` |
+| Feature development (default) | `/do` |
-| Quick bug fix | `/debug` or `/code` |
+| Bug investigation + fix | `/omo` |
-| Large multi-sprint feature | `/bmad-pilot` |
+| Large enterprise project | `/bmad-pilot` |
-| Prototype or POC | `/requirements-pilot` |
+| Quick prototype | `/requirements-pilot` |
-| Code review | `/review` |
+| Simple task | `/code`, `/debug` |
-| Performance issue | `/optimize` |
 
----
+## 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](codeagent-wrapper/README.md)
+- [Plugin System](PLUGIN_README.md)
 
 ## Troubleshooting
 
@@ -408,214 +111,41 @@ reg add "HKCU\Environment" /v Path /t REG_EXPAND_SZ /d "%USERPROFILE%\bin;%PATH%
 
 **Codex wrapper not found:**
 ```bash
-# Installer auto-adds PATH, check if configured
+# Select: codeagent-wrapper
-if [[ ":$PATH:" != *":$HOME/.claude/bin:"* ]]; then
+npx github:cexll/myclaude
-    echo "PATH not configured. Reinstalling..."
-    bash install.sh
-fi
-
-# Or manually add (idempotent command)
-[[ ":$PATH:" != *":$HOME/.claude/bin:"* ]] && echo 'export PATH="$HOME/.claude/bin:$PATH"' >> ~/.zshrc
-```
-
-**Permission denied:**
-```bash
-python3 install.py --install-dir ~/.claude --force
 ```
 
 **Module not loading:**
 ```bash
-# Check installation status
 cat ~/.claude/installed_modules.json
-
+npx github:cexll/myclaude --force
-# Reinstall specific module
-python3 install.py --module dev --force
 ```
 
-### Version Compatibility Issues
+**Backend CLI errors:**
-
-**Backend CLI not found:**
 ```bash
-# Check if backend CLIs are installed
+which codex && codex --version
-which codex
+which claude && claude --version
-which claude
+which gemini && gemini --version
-which gemini
-
-# Install missing backends
-# Codex: Follow installation instructions at https://codex.docs
-# Claude: Follow installation instructions at https://claude.ai/docs
-# Gemini: Follow installation instructions at https://ai.google.dev/docs
 ```
 
-**Unsupported CLI flags:**
+## FAQ
-```bash
-# If you see errors like "unknown flag" or "invalid option"
 
-# Check backend CLI version
+| Issue | Solution |
-codex --version
+|-------|----------|
-claude --version
+| "Unknown event format" | Logging display issue, can be ignored |
-gemini --version
+| Gemini can't read .gitignore files | Remove from .gitignore or use different backend |
+| Codex permission denied | Set `approval_policy = "never"` in ~/.codex/config.yaml |
 
-# For Codex: Ensure it supports `e`, `--skip-git-repo-check`, `--json`, `-C`, and `resume`
+See [GitHub Issues](https://github.com/cexll/myclaude/issues) for more.
-# For Claude: Ensure it supports `--output-format stream-json`, `--setting-sources`, `-r`
-# For Gemini: Ensure it supports `-o stream-json`, `-y`, `-r`, `-p`
-
-# Update your backend CLI to the latest version if needed
-```
-
-**JSON parsing errors:**
-```bash
-# If you see "failed to parse JSON output" errors
-
-# Verify the backend outputs stream-json format
-codex e --json "test task"  # Should output newline-delimited JSON
-claude --output-format stream-json -p "test"  # Should output stream JSON
-
-# If not, your backend CLI version may be too old or incompatible
-```
-
-**Infinite recursion with Claude backend:**
-```bash
-# The wrapper prevents this with `--setting-sources ""` flag
-# If you still see recursion, ensure your Claude CLI supports this flag
-
-claude --help | grep "setting-sources"
-
-# If flag is not supported, upgrade Claude CLI
-```
-
-**Session resume failures:**
-```bash
-# Check if session ID is valid
-codex history  # List recent sessions
-claude history
-
-# Ensure backend CLI supports session resumption
-codex resume <session_id> "test"  # Should continue from previous session
-claude -r <session_id> "test"
-
-# If not supported, use new sessions instead of resume mode
-```
-
----
-
-## FAQ (Frequently Asked Questions)
-
-### Q1: `codeagent-wrapper` execution fails with "Unknown event format"
-
-**Problem:**
-```
-Unknown event format: {"type":"turn.started"}
-Unknown event format: {"type":"assistant", ...}
-```
-
-**Solution:**
-This is a logging event format display issue and does not affect actual functionality. It will be fixed in the next version. You can ignore these log outputs.
-
-**Related Issue:** [#96](https://github.com/cexll/myclaude/issues/96)
-
----
-
-### Q2: Gemini cannot read files ignored by `.gitignore`
-
-**Problem:**
-When using `codeagent-wrapper --backend gemini`, files in directories like `.claude/` that are ignored by `.gitignore` cannot be read.
-
-**Solution:**
-- **Option 1:** Remove `.claude/` from your `.gitignore` file
-- **Option 2:** Ensure files that need to be read are not in `.gitignore` list
-
-**Related Issue:** [#75](https://github.com/cexll/myclaude/issues/75)
-
----
-
-### Q3: `/dev` command parallel execution is very slow
-
-**Problem:**
-Using `/dev` command for simple features takes too long (over 30 minutes) with no visibility into task progress.
-
-**Solution:**
-1. **Check logs:** Review `C:\Users\User\AppData\Local\Temp\codeagent-wrapper-*.log` to identify bottlenecks
-2. **Adjust backend:**
-   - Try faster models like `gpt-5.1-codex-max`
-   - Running in WSL may be significantly faster
-3. **Workspace:** Use a single repository instead of monorepo with multiple sub-projects
-
-**Related Issue:** [#77](https://github.com/cexll/myclaude/issues/77)
-
----
-
-### Q4: Codex permission denied with new Go version
-
-**Problem:**
-After upgrading to the new Go-based Codex implementation, execution fails with permission denied errors.
-
-**Solution:**
-Add the following configuration to `~/.codex/config.yaml` (Windows: `c:\user\.codex\config.toml`):
-```yaml
-model = "gpt-5.1-codex-max"
-model_reasoning_effort = "high"
-model_reasoning_summary = "detailed"
-approval_policy = "never"
-sandbox_mode = "workspace-write"
-disable_response_storage = true
-network_access = true
-```
-
-**Key settings:**
-- `approval_policy = "never"` - Remove approval restrictions
-- `sandbox_mode = "workspace-write"` - Allow workspace write access
-- `network_access = true` - Enable network access
-
-**Related Issue:** [#31](https://github.com/cexll/myclaude/issues/31)
-
----
-
-### Q5: How to disable default bypass/skip-permissions mode
-
-**Background:**
-By default, codeagent-wrapper enables bypass mode for both Codex and Claude backends:
-- `CODEX_BYPASS_SANDBOX=true` - Bypasses Codex sandbox restrictions
-- `CODEAGENT_SKIP_PERMISSIONS=true` - Skips Claude permission prompts
-
-**To disable (if you need sandbox/permission protection):**
-```bash
-export CODEX_BYPASS_SANDBOX=false
-export CODEAGENT_SKIP_PERMISSIONS=false
-```
-
-Or add to your shell profile (`~/.zshrc` or `~/.bashrc`):
-```bash
-echo 'export CODEX_BYPASS_SANDBOX=false' >> ~/.zshrc
-echo 'export CODEAGENT_SKIP_PERMISSIONS=false' >> ~/.zshrc
-```
-
-**Note:** Disabling bypass mode will require manual approval for certain operations.
-
----
-
-**Still having issues?** Visit [GitHub Issues](https://github.com/cexll/myclaude/issues) to search or report new issues.
-
----
-
-## Documentation
-- **[Codeagent-Wrapper Guide](docs/CODEAGENT-WRAPPER.md)** - Multi-backend execution wrapper
-- **[Hooks Documentation](docs/HOOKS.md)** - Custom hooks and automation
-
-### Additional Resources
-- **[Installation Log](install.log)** - Installation history and troubleshooting
-
----
 
 ## License
 
-AGPL-3.0 License - see [LICENSE](LICENSE)
+AGPL-3.0 - see [LICENSE](LICENSE)
+
+### Commercial Licensing
+
+For commercial use without AGPL obligations, contact: evanxian9@gmail.com
 
 ## Support
 
-- **Issues**: [GitHub Issues](https://github.com/cexll/myclaude/issues)
+- [GitHub Issues](https://github.com/cexll/myclaude/issues)
-- **Documentation**: [docs/](docs/)
-
----
-
-**Claude Code + Codex = Better Development** - Orchestration meets execution.

README_CN.md

@@ -2,98 +2,116 @@
 
 [![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
+## 快速开始
 
-本系统采用**双智能体架构**与可插拔 AI 后端：
+```bash
+npx github:cexll/myclaude
+```
+
+## 模块概览
+
+| 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 |
+| [omo](skills/omo/README.md) | 多智能体编排 + 智能路由 | `/omo` 命令 |
+| [bmad](agents/bmad/README.md) | BMAD 敏捷工作流 + 6 个专业智能体 | `/bmad-pilot` 命令 |
+| [requirements](agents/requirements/README.md) | 轻量级需求到代码流水线 | `/requirements-pilot` 命令 |
+| [essentials](agents/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 |
+
+## 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、用户交互 |
+| **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 后端）|
+| **执行者** | codeagent-wrapper | 代码编辑、测试执行（Codex/Claude/Gemini/OpenCode 后端）|
 
-**为什么分离？**
+## 工作流详解
-- 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）
+### 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
-git clone https://github.com/cexll/myclaude.git
+/do "添加用户登录功能"
-cd myclaude
-python3 install.py --install-dir ~/.claude
 ```
 
-## 工作流概览
+**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 |
 
-### 0. OmO 多智能体编排器（复杂任务推荐）
+**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
 
-**基于风险信号智能路由任务到专业智能体的多智能体编排系统。**
+---
+
+### OmO 多智能体编排器
+
+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 | 模型 |
+| 智能体 | 角色 | 后端 |
-|-------|------|------|------|
+|-------|------|------|
-| `oracle` | 技术顾问 | Claude | claude-opus-4-5 |
+| `oracle` | 技术顾问 | Claude |
-| `librarian` | 外部研究 | Claude | claude-sonnet-4-5 |
+| `librarian` | 外部研究 | Claude |
-| `explore` | 代码库搜索 | OpenCode | grok-code |
+| `explore` | 代码库搜索 | OpenCode |
-| `develop` | 代码实现 | Codex | gpt-5.2 |
+| `develop` | 代码实现 | Codex |
-| `frontend-ui-ux-engineer` | UI/UX 专家 | Gemini | gemini-3-pro |
+| `frontend-ui-ux-engineer` | UI/UX 专家 | Gemini |
-| `document-writer` | 文档撰写 | Gemini | gemini-3-flash |
+| `document-writer` | 文档撰写 | Gemini |
-
-**路由信号（非固定流水线）：**
-- 代码位置不明确 → `explore`
-- 外部库/API → `librarian`
-- 高风险/多文件变更 → `oracle`
-- 需要实现 → `develop` / `frontend-ui-ux-engineer`
 
 **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`
+- Bug 修复（位置未知）：`explore → develop`
 - 跨模块重构：`explore → oracle → develop`
-- 外部 API 集成：`explore + librarian → oracle → develop`
-
-**适用场景：** 复杂 bug 调查、多文件重构、架构决策
 
 ---
 
-### 1. Dev 工作流（推荐）
+### SPARV 工作流
 
-**大多数开发任务的首选工作流。**
+极简 5 阶段工作流：Specify → Plan → Act → Review → Vault。
 
 ```bash
-/dev "实现 JWT 用户认证"
+/sparv "实现订单导出功能"
 ```
 
-**6 步流程：**
+**核心规则：**
-1. **需求澄清** - 交互式问答明确范围
+- **10 分规格门**：得分 0-10，必须 >=9 才能进入 Plan
-2. **Codex 深度分析** - 代码库探索和架构决策
+- **2 动作保存**：每 2 次工具调用写入 journal.md
-3. **开发计划生成** - 结构化任务分解和测试要求
+- **3 失败协议**：连续 3 次失败后停止并上报
-4. **并行执行** - Codex 并发执行任务
+- **EHRB**：高风险操作需明确确认
-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：**
+**评分维度（各 0-2 分）：**
-- Claude Code 编排，Codex 执行所有代码变更
+1. Value - 为什么做，可验证的收益
-- 自动任务并行化提升速度
+2. Scope - MVP + 不在范围内的内容
-- 强制 90% 测试覆盖率门禁
+3. Acceptance - 可测试的验收标准
-- 失败自动回滚
+4. Boundaries - 错误/性能/兼容/安全边界
-
+5. Risk - EHRB/依赖/未知 + 处理方式
-**适用场景：** 功能开发、重构、带测试的 bug 修复
 
 ---
 
-### 2. BMAD 敏捷工作流
+### BMAD 敏捷工作流
 
-**包含 6 个专业智能体的完整企业敏捷方法论。**
+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"
@@ -104,43 +122,36 @@ 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：**
+**审批门：**
-```
+- PRD 完成后（90+ 分）需用户审批
-需求 → 架构 → Sprint计划 → 开发 → 审查 → QA
+- 架构完成后（90+ 分）需用户审批
- ↓      ↓       ↓         ↓      ↓      ↓
-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
 
 ---
 
-### 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：**
+**100 分质量评分：**
-1. 带质量评分的需求生成
+- 功能清晰度：30 分
-2. 实现规划
+- 技术具体性：25 分
-3. 代码生成
+- 实现完整性：25 分
-4. 审查和测试
+- 业务上下文：20 分
-
-**适用场景：** 快速原型、明确定义的功能
 
 ---
 
-### 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 |
 |------|------|
@@ -152,332 +163,94 @@ 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）
+# 交互式安装器（推荐）
-python3 install.py --install-dir ~/.claude
+npx github:cexll/myclaude
 
-# 安装特定模块
+# 列出可安装项（module:* / skill:* / codeagent-wrapper）
-python3 install.py --module dev
+npx github:cexll/myclaude --list
 
-# 列出可用模块
+# 检测已安装 modules 并从 GitHub 更新
-python3 install.py --list-modules
+npx github:cexll/myclaude --update
 
-# 强制覆盖现有文件
+# 指定安装目录 / 强制覆盖
-python3 install.py --force
+npx github:cexll/myclaude --install-dir ~/.claude --force
 ```
 
-### 可用模块
+`--update` 会在目标安装目录（默认 `~/.claude`，优先读取 `installed_modules.json`）检测已安装 modules，并从 GitHub 拉取最新发布版本覆盖更新。
 
-| 模块 | 默认 | 描述 |
+### 模块配置
-|------|------|------|
-| `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
+编辑 `config.json` 启用/禁用模块：
-
-```
-~/.claude/
-├── bin/
-│   └── codeagent-wrapper    # 主可执行文件
-├── 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
-├── config.json              # 配置文件
-└── installed_modules.json   # 安装状态
-```
-
-### 自定义安装目录
-
-默认情况下，myclaude 安装到 `~/.claude`。您可以使用 `INSTALL_DIR` 环境变量自定义安装目录：
-
-```bash
-# 安装到自定义目录
-INSTALL_DIR=/opt/myclaude bash install.sh
-
-# 相应更新您的 PATH
-export PATH="/opt/myclaude/bin:$PATH"
-```
-
-**目录结构：**
-- `$INSTALL_DIR/bin/` - codeagent-wrapper 可执行文件
-- `$INSTALL_DIR/skills/` - 技能定义
-- `$INSTALL_DIR/config.json` - 配置文件
-- `$INSTALL_DIR/commands/` - 斜杠命令定义
-- `$INSTALL_DIR/agents/` - 智能体定义
-
-**注意：** 使用自定义安装目录时，请确保将 `$INSTALL_DIR/bin` 添加到您的 `PATH` 环境变量中。
-
-### 配置
-
-编辑 `config.json` 自定义：
 
 ```json
 {
-  "version": "1.0",
-  "install_dir": "~/.claude",
   "modules": {
-    "dev": {
+    "bmad": { "enabled": false },
-      "enabled": true,
+    "requirements": { "enabled": false },
-      "operations": [
+    "essentials": { "enabled": false },
-        {"type": "merge_dir", "source": "dev-workflow"},
+    "omo": { "enabled": false },
-        {"type": "copy_file", "source": "memorys/CLAUDE.md", "target": "CLAUDE.md"},
+    "sparv": { "enabled": false },
-        {"type": "copy_file", "source": "skills/codex/SKILL.md", "target": "skills/codex/SKILL.md"},
+    "do": { "enabled": true },
-        {"type": "run_command", "command": "bash install.sh"}
+    "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）（建议使用上面的 PowerShell 方法）
-REM 警告：此命令会展开 %PATH% 包含系统 PATH，导致重复
-REM 注意：使用 reg add 而非 setx 以避免 1024 字符截断限制
-reg add "HKCU\Environment" /v Path /t REG_EXPAND_SZ /d "%USERPROFILE%\bin;%PATH%" /f
-```
-
----
-
 ## 工作流选择指南
 
-| 场景 | 推荐工作流 |
+| 场景 | 推荐 |
-|------|----------|
+|------|------|
-| 带测试的新功能 | `/dev` |
+| 功能开发（默认） | `/do` |
-| 快速 bug 修复 | `/debug` 或 `/code` |
+| Bug 调查 + 修复 | `/omo` |
-| 大型多 Sprint 功能 | `/bmad-pilot` |
+| 大型企业项目 | `/bmad-pilot` |
-| 原型或 POC | `/requirements-pilot` |
+| 快速原型 | `/requirements-pilot` |
-| 代码审查 | `/review` |
+| 简单任务 | `/code`, `/debug` |
-| 性能问题 | `/optimize` |
 
----
+## 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
-# 安装程序会自动添加 PATH，检查是否已添加
+# 选择：codeagent-wrapper
-if [[ ":$PATH:" != *":$HOME/.claude/bin:"* ]]; then
+npx github:cexll/myclaude
-    echo "PATH not configured. Reinstalling..."
-    bash install.sh
-fi
-
-# 或手动添加（幂等性命令）
-[[ ":$PATH:" != *":$HOME/.claude/bin:"* ]] && echo 'export PATH="$HOME/.claude/bin:$PATH"' >> ~/.zshrc
-```
-
-**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
-
+npx github:cexll/myclaude --force
-# 重新安装特定模块
-python3 install.py --module dev --force
 ```
 
----
+## FAQ
 
-## 常见问题 (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 |
+| Codex 权限拒绝 | 在 ~/.codex/config.yaml 设置 `approval_policy = "never"` |
 
-### Q1: `codeagent-wrapper` 执行时报错 "Unknown event format"
+更多问题请访问 [GitHub Issues](https://github.com/cexll/myclaude/issues)。
-
-**问题描述：**
-执行 `codeagent-wrapper` 时出现错误：
-```
-Unknown event format: {"type":"turn.started"}
-Unknown event format: {"type":"assistant", ...}
-```
-
-**解决方案：**
-这是日志事件流的显示问题，不影响实际功能执行。预计在下个版本中修复。如需排查其他问题，可忽略此日志输出。
-
-**相关 Issue：** [#96](https://github.com/cexll/myclaude/issues/96)
-
----
-
-### Q2: Gemini 无法读取 `.gitignore` 忽略的文件
-
-**问题描述：**
-使用 `codeagent-wrapper --backend gemini` 时，无法读取 `.claude/` 等被 `.gitignore` 忽略的目录中的文件。
-
-**解决方案：**
-- **方案一：** 在项目根目录的 `.gitignore` 中取消对 `.claude/` 的忽略
-- **方案二：** 确保需要读取的文件不在 `.gitignore` 忽略列表中
-
-**相关 Issue：** [#75](https://github.com/cexll/myclaude/issues/75)
-
----
-
-### Q3: `/dev` 命令并行执行特别慢
-
-**问题描述：**
-使用 `/dev` 命令开发简单功能耗时过长（超过30分钟），无法了解任务执行状态。
-
-**解决方案：**
-1. **检查日志：** 查看 `C:\Users\User\AppData\Local\Temp\codeagent-wrapper-*.log` 分析瓶颈
-2. **调整后端：**
-   - 尝试使用 `gpt-5.1-codex-max` 等更快的模型
-   - 在 WSL 环境下运行速度可能更快
-3. **工作区选择：** 使用独立的代码仓库而非包含多个子项目的 monorepo
-
-**相关 Issue：** [#77](https://github.com/cexll/myclaude/issues/77)
-
----
-
-### Q4: 新版 Go 实现的 Codex 权限不足
-
-**问题描述：**
-升级到新版 Go 实现的 Codex 后，出现权限不足的错误。
-
-**解决方案：**
-在 `~/.codex/config.yaml` 中添加以下配置（Windows: `c:\user\.codex\config.toml`）：
-```yaml
-model = "gpt-5.1-codex-max"
-model_reasoning_effort = "high"
-model_reasoning_summary = "detailed"
-approval_policy = "never"
-sandbox_mode = "workspace-write"
-disable_response_storage = true
-network_access = true
-```
-
-**关键配置说明：**
-- `approval_policy = "never"` - 移除审批限制
-- `sandbox_mode = "workspace-write"` - 允许工作区写入权限
-- `network_access = true` - 启用网络访问
-
-**相关 Issue：** [#31](https://github.com/cexll/myclaude/issues/31)
-
----
-
-### Q5: 执行时遇到权限拒绝或沙箱限制
-
-**问题描述：**
-运行 codeagent-wrapper 时出现权限错误或沙箱限制。
-
-**解决方案：**
-设置以下环境变量：
-```bash
-export CODEX_BYPASS_SANDBOX=true
-export CODEAGENT_SKIP_PERMISSIONS=true
-```
-
-或添加到 shell 配置文件（`~/.zshrc` 或 `~/.bashrc`）：
-```bash
-echo 'export CODEX_BYPASS_SANDBOX=true' >> ~/.zshrc
-echo 'export CODEAGENT_SKIP_PERMISSIONS=true' >> ~/.zshrc
-```
-
-**注意：** 这些设置会绕过安全限制，请仅在可信环境中使用。
-
----
-
-**仍有疑问？** 请访问 [GitHub Issues](https://github.com/cexll/myclaude/issues) 搜索或提交新问题。
-
----
 
 ## 许可证
 
-AGPL-3.0 License - 查看 [LICENSE](LICENSE)
+AGPL-3.0 - 查看 [LICENSE](LICENSE)
+
+### 商业授权
+
+如需商业授权（无需遵守 AGPL 义务），请联系：evanxian9@gmail.com
 
 ## 支持
 
-- **问题反馈**: [GitHub Issues](https://github.com/cexll/myclaude/issues)
+- [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。

agents/bmad/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
+
+```
+agents/bmad/
+├── 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
+```

agents/development-essentials/DEVELOPMENT-COMMANDS.md

@@ -304,7 +304,7 @@ Deep reasoning and analysis for complex problems.
 ## 🔌 Agent Configuration
 
 All commands use specialized agents configured in:
-- `development-essentials/agents/`
+- `agents/development-essentials/agents/`
 - Agent prompt templates
 - Tool access permissions
 - Output formatting

agents/development-essentials/README.md

@@ -244,8 +244,8 @@ Development Essentials 模块包含以下专用代理：
 ## 🔗 相关文档
 
 - [主文档](../README.md) - 项目总览
-- [BMAD工作流](../docs/BMAD-WORKFLOW.md) - 完整敏捷流程
+- [BMAD工作流](../agents/bmad/BMAD-WORKFLOW.md) - 完整敏捷流程
-- [Requirements工作流](../docs/REQUIREMENTS-WORKFLOW.md) - 轻量级开发流程
+- [Requirements工作流](../agents/requirements/REQUIREMENTS-WORKFLOW.md) - 轻量级开发流程
 - [插件系统](../PLUGIN_README.md) - 插件安装和管理
 
 ---

agents/requirements/README.md

@@ -0,0 +1,90 @@
+# requirements - Requirements-Driven Workflow
+
+Lightweight requirements-to-code pipeline with interactive quality gates.
+
+## Installation
+
+```bash
+python install.py --module requirements
+```
+
+## Usage
+
+```bash
+/requirements-pilot <FEATURE_DESCRIPTION> [OPTIONS]
+```
+
+### Options
+
+| Option | Description |
+|--------|-------------|
+| `--skip-tests` | Skip testing phase entirely |
+| `--skip-scan` | Skip initial repository scanning |
+
+## Workflow Phases
+
+| Phase | Description | Output |
+|-------|-------------|--------|
+| 0 | Repository scanning | `00-repository-context.md` |
+| 1 | Requirements confirmation | `requirements-confirm.md` (90+ score required) |
+| 2 | Implementation | Code + `requirements-spec.md` |
+
+## Quality Scoring (100-point system)
+
+| Category | Points | Focus |
+|----------|--------|-------|
+| Functional Clarity | 30 | Input/output specs, success criteria |
+| Technical Specificity | 25 | Integration points, constraints |
+| Implementation Completeness | 25 | Edge cases, error handling |
+| Business Context | 20 | User value, priority |
+
+## Sub-Agents
+
+| Agent | Role |
+|-------|------|
+| `requirements-generate` | Create technical specifications |
+| `requirements-code` | Implement functionality |
+| `requirements-review` | Code quality evaluation |
+| `requirements-testing` | Test case creation |
+
+## Approval Gate
+
+One mandatory stop point after Phase 1:
+- Requirements must achieve 90+ quality score
+- User must explicitly approve before implementation begins
+
+## Testing Decision
+
+After code review passes (≥90%):
+- `--skip-tests`: Complete without testing
+- No option: Interactive prompt with smart recommendations based on task complexity
+
+## Output Structure
+
+```
+.claude/specs/{feature_name}/
+├── 00-repository-context.md
+├── requirements-confirm.md
+└── requirements-spec.md
+```
+
+## When to Use
+
+- Quick prototypes
+- Well-defined features
+- Smaller scope tasks
+- When full BMAD workflow is overkill
+
+## Directory Structure
+
+```
+agents/requirements/
+├── README.md
+├── commands/
+│   └── requirements-pilot.md
+└── agents/
+    ├── requirements-generate.md
+    ├── requirements-code.md
+    ├── requirements-review.md
+    └── requirements-testing.md
+```

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

@@ -0,0 +1,47 @@
+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
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+      - uses: actions/setup-go@v5
+        with:
+          go-version: ${{ matrix.go-version }}
+          cache: true
+      - name: Test
+        run: make test
+      - name: Build
+        run: make build
+      - name: Verify version
+        run: ./codeagent-wrapper --version
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+      - uses: actions/setup-go@v5
+        with:
+          go-version: "1.22"
+          cache: true
+      - name: Lint
+        run: make lint
+

codeagent-wrapper/.gitignore

@@ -1,6 +1,9 @@
 # Build artifacts
-codeagent-wrapper
+bin/
-codeagent-wrapper.exe
+codeagent
+codeagent.exe
+/codeagent-wrapper
+/codeagent-wrapper.exe
 *.test
 
 # Coverage reports
@@ -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
+VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo dev)
+LDFLAGS := -ldflags "-X codeagent-wrapper/internal/app.version=$(VERSION)"
+
+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 $(LDFLAGS) -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 $(LDFLAGS) ./cmd/codeagent-wrapper

codeagent-wrapper/README.md

@@ -0,0 +1,157 @@
+# 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）：
+
+- `$HOME/.codeagent/config.(yaml|yml|json|toml|...)`
+
+示例（YAML）：
+
+```yaml
+backend: codex
+model: gpt-4.1
+skip-permissions: false
+```
+
+也可以通过 `--config /path/to/config.yaml` 显式指定。
+
+### 环境变量（`CODEAGENT_*`）
+
+通过 viper 读取并自动映射 `-` 为 `_`，常用项：
+
+- `CODEAGENT_BACKEND`（`codex|claude|gemini|opencode`）
+- `CODEAGENT_MODEL`
+- `CODEAGENT_AGENT`
+- `CODEAGENT_PROMPT_FILE`
+- `CODEAGENT_REASONING_EFFORT`
+- `CODEAGENT_SKIP_PERMISSIONS`
+- `CODEAGENT_FULL_OUTPUT`（并行模式 legacy 输出）
+- `CODEAGENT_MAX_PARALLEL_WORKERS`（0 表示不限制，上限 100）
+
+### Agent 预设（`~/.codeagent/models.json`）
+
+可在 `~/.codeagent/models.json` 定义 agent → backend/model/prompt 等映射，用 `--agent <name>` 选择：
+
+```json
+{
+  "default_backend": "opencode",
+  "default_model": "opencode/grok-code",
+  "agents": {
+    "develop": {
+      "backend": "codex",
+      "model": "gpt-4.1",
+      "prompt_file": "~/.codeagent/prompts/develop.md",
+      "description": "Code development"
+    }
+  }
+}
+```
+
+## 支持的后端
+
+该项目本身不内置模型能力，依赖你本机安装并可在 `PATH` 中找到对应 CLI：
+
+- `codex`：执行 `codex e ...`（默认会添加 `--dangerously-bypass-approvals-and-sandbox`；如需关闭请设置 `CODEX_BYPASS_SANDBOX=false`）
+- `claude`：执行 `claude -p ... --output-format stream-json`（默认会跳过权限提示；如需开启请设置 `CODEAGENT_SKIP_PERMISSIONS=false`）
+- `gemini`：执行 `gemini ... -o stream-json`（可从 `~/.gemini/.env` 加载环境变量）
+- `opencode`：执行 `opencode run --format json`
+
+## 开发
+
+```bash
+make build
+make test
+make lint
+make clean
+```
+
+## 故障排查
+
+- macOS 下如果看到临时目录相关的 `permission denied`（例如临时可执行文件无法在 `/var/folders/.../T` 执行），可设置一个可执行的临时目录：`CODEAGENT_TMPDIR=$HOME/.codeagent/tmp`。
+- `claude` 后端的 `base_url/api_key`（来自 `~/.codeagent/models.json`）会注入到子进程环境变量：`ANTHROPIC_BASE_URL` / `ANTHROPIC_API_KEY`。若 `base_url` 指向本地代理（如 `localhost:23001`），请确认代理进程在运行。

codeagent-wrapper/USER_GUIDE.md

@@ -14,14 +14,10 @@ Multi-backend AI code execution wrapper supporting Codex, Claude, and Gemini.
 ## Installation
 
 ```bash
-# Clone repository
+# Recommended: run the installer and select "codeagent-wrapper"
-git clone https://github.com/cexll/myclaude.git
+npx github:cexll/myclaude
-cd myclaude
 
-# Install via install.py (includes binary compilation)
+# Manual build (optional; requires repo checkout)
-python3 install.py --module dev
-
-# Or manual installation
 cd codeagent-wrapper
 go build -o ~/.claude/bin/codeagent-wrapper
 ```

codeagent-wrapper/agent_config.go

@@ -1,79 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"path/filepath"
-)
-
-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"`
-}
-
-type ModelsConfig struct {
-	DefaultBackend string                      `json:"default_backend"`
-	DefaultModel   string                      `json:"default_model"`
-	Agents         map[string]AgentModelConfig `json:"agents"`
-}
-
-var defaultModelsConfig = ModelsConfig{
-	DefaultBackend: "opencode",
-	DefaultModel:   "opencode/grok-code",
-	Agents: map[string]AgentModelConfig{
-			"oracle":                  {Backend: "claude", Model: "claude-sonnet-4-20250514", PromptFile: "~/.claude/skills/omo/references/oracle.md", Description: "Technical advisor"},
-			"librarian":               {Backend: "claude", Model: "claude-sonnet-4-5-20250514", 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"},
-		},
-	}
-
-func loadModelsConfig() *ModelsConfig {
-	home, err := os.UserHomeDir()
-	if err != nil {
-		logWarn(fmt.Sprintf("Failed to resolve home directory for models config: %v; using defaults", err))
-		return &defaultModelsConfig
-	}
-
-	configPath := filepath.Join(home, ".codeagent", "models.json")
-	data, err := os.ReadFile(configPath)
-	if err != nil {
-		if !os.IsNotExist(err) {
-			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 {
-		logWarn(fmt.Sprintf("Failed to parse models config %s: %v; using defaults", configPath, err))
-		return &defaultModelsConfig
-	}
-
-	// 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
-		}
-	}
-
-	return &cfg
-}
-
-func resolveAgentConfig(agentName string) (backend, model, promptFile, reasoning string, yolo bool) {
-	cfg := loadModelsConfig()
-	if agent, ok := cfg.Agents[agentName]; ok {
-		return agent.Backend, agent.Model, agent.PromptFile, agent.Reasoning, agent.Yolo
-	}
-	return cfg.DefaultBackend, cfg.DefaultModel, "", "", false
-}

codeagent-wrapper/agent_config_test.go

@@ -1,208 +0,0 @@
-package main
-
-import (
-	"os"
-	"path/filepath"
-	"reflect"
-	"testing"
-)
-
-func TestResolveAgentConfig_Defaults(t *testing.T) {
-	home := t.TempDir()
-	t.Setenv("HOME", home)
-	t.Setenv("USERPROFILE", home)
-
-	// Test that default agents resolve correctly without config file
-	tests := []struct {
-		agent          string
-		wantBackend    string
-		wantModel      string
-		wantPromptFile string
-	}{
-			{"oracle", "claude", "claude-sonnet-4-20250514", "~/.claude/skills/omo/references/oracle.md"},
-			{"librarian", "claude", "claude-sonnet-4-5-20250514", "~/.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)
-
-	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)
-
-	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",
-		"agents": {
-			"custom-agent": {
-				"backend": "codex",
-				"model": "gpt-4o",
-				"description": "Custom agent"
-			}
-		}
-	}`
-	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)
-
-	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")
-	}
-}
-
-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)
-
-	cfg := loadModelsConfig()
-	// Should fall back to defaults
-	if cfg.DefaultBackend != "opencode" {
-		t.Errorf("invalid JSON should fallback, got DefaultBackend = %q", cfg.DefaultBackend)
-	}
-}
-
-func TestOpencodeBackend_BuildArgs(t *testing.T) {
-	backend := OpencodeBackend{}
-
-	t.Run("basic", func(t *testing.T) {
-		cfg := &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{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{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{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)
-		}
-	})
-}
-
-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")
-	}
-}
-
-func TestBackendRegistry_IncludesOpencode(t *testing.T) {
-	if _, ok := backendRegistry["opencode"]; !ok {
-		t.Error("backendRegistry should include opencode")
-	}
-}

codeagent-wrapper/backend.go

@@ -1,237 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"os"
-	"path/filepath"
-	"strings"
-)
-
-// 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 {
-	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{}
-	}
-
-	settingPath := filepath.Join(home, ".claude", "settings.json")
-	info, err := os.Stat(settingPath)
-	if err != nil || info.Size() > maxClaudeSettingsBytes {
-		return minimalClaudeSettings{}
-	}
-
-	data, err := os.ReadFile(settingPath)
-	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
-}
-
-// loadMinimalEnvSettings is kept for backwards tests; prefer loadMinimalClaudeSettings.
-func loadMinimalEnvSettings() map[string]string {
-	settings := loadMinimalClaudeSettings()
-	if len(settings.Env) == 0 {
-		return nil
-	}
-	return settings.Env
-}
-
-// 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
-	}
-
-	envPath := filepath.Join(home, ".gemini", ".env")
-	data, err := os.ReadFile(envPath)
-	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 buildClaudeArgs(cfg *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 || 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)
-		}
-	}
-	// Note: claude CLI doesn't support -C flag; workdir set via cmd.Dir
-
-	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 {
-	return buildGeminiArgs(cfg, targetArg)
-}
-
-type OpencodeBackend struct{}
-
-func (OpencodeBackend) Name() string    { return "opencode" }
-func (OpencodeBackend) Command() string { return "opencode" }
-func (OpencodeBackend) BuildArgs(cfg *Config, targetArg string) []string {
-	args := []string{"run"}
-	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", targetArg)
-	return args
-}
-
-func buildGeminiArgs(cfg *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)
-		}
-	}
-	// Note: gemini CLI doesn't support -C flag; workdir set via cmd.Dir
-
-	// 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/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-wrapper/main.go

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

codeagent-wrapper/config.go

@@ -1,473 +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
-	Model              string
-	ReasoningEffort    string
-	ExplicitStdin      bool
-	Timeout            int
-	Backend            string
-	Agent              string
-	PromptFile         string
-	PromptFileExplicit bool
-	SkipPermissions    bool
-	Yolo               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"`
-	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
-}
-
-var backendRegistry = map[string]Backend{
-	"codex":    CodexBackend{},
-	"claude":   ClaudeBackend{},
-	"gemini":   GeminiBackend{},
-	"opencode": OpencodeBackend{},
-}
-
-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
-	}
-}
-
-// 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
-}
-
-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 = 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 := validateAgentName(task.Agent); err != nil {
-				return nil, fmt.Errorf("task block #%d invalid agent name: %w", taskIndex, err)
-			}
-			backend, model, promptFile, reasoning, _ := 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
-}
-
-func parseArgs() (*Config, error) {
-	args := os.Args[1:]
-	if len(args) == 0 {
-		return nil, fmt.Errorf("task required")
-	}
-
-	backendName := defaultBackendName
-	model := ""
-	reasoningEffort := ""
-	agentName := ""
-	promptFile := ""
-	promptFileExplicit := false
-	yolo := false
-	skipPermissions := envFlagEnabled("CODEAGENT_SKIP_PERMISSIONS")
-	filtered := make([]string, 0, len(args))
-	for i := 0; i < len(args); i++ {
-		arg := args[i]
-		switch {
-		case arg == "--agent":
-			if i+1 >= len(args) {
-				return nil, fmt.Errorf("--agent flag requires a value")
-			}
-			value := strings.TrimSpace(args[i+1])
-			if value == "" {
-				return nil, fmt.Errorf("--agent flag requires a value")
-			}
-			if err := validateAgentName(value); err != nil {
-				return nil, fmt.Errorf("--agent flag invalid value: %w", err)
-			}
-			resolvedBackend, resolvedModel, resolvedPromptFile, resolvedReasoning, resolvedYolo := resolveAgentConfig(value)
-			backendName = resolvedBackend
-			model = resolvedModel
-			if !promptFileExplicit {
-				promptFile = resolvedPromptFile
-			}
-			if reasoningEffort == "" {
-				reasoningEffort = resolvedReasoning
-			}
-			yolo = resolvedYolo
-			agentName = value
-			i++
-			continue
-		case strings.HasPrefix(arg, "--agent="):
-			value := strings.TrimSpace(strings.TrimPrefix(arg, "--agent="))
-			if value == "" {
-				return nil, fmt.Errorf("--agent flag requires a value")
-			}
-			if err := validateAgentName(value); err != nil {
-				return nil, fmt.Errorf("--agent flag invalid value: %w", err)
-			}
-			resolvedBackend, resolvedModel, resolvedPromptFile, resolvedReasoning, resolvedYolo := resolveAgentConfig(value)
-			backendName = resolvedBackend
-			model = resolvedModel
-			if !promptFileExplicit {
-				promptFile = resolvedPromptFile
-			}
-			if reasoningEffort == "" {
-				reasoningEffort = resolvedReasoning
-			}
-			yolo = resolvedYolo
-			agentName = value
-			continue
-		case arg == "--prompt-file":
-			if i+1 >= len(args) {
-				return nil, fmt.Errorf("--prompt-file flag requires a value")
-			}
-			value := strings.TrimSpace(args[i+1])
-			if value == "" {
-				return nil, fmt.Errorf("--prompt-file flag requires a value")
-			}
-			promptFile = value
-			promptFileExplicit = true
-			i++
-			continue
-		case strings.HasPrefix(arg, "--prompt-file="):
-			value := strings.TrimSpace(strings.TrimPrefix(arg, "--prompt-file="))
-			if value == "" {
-				return nil, fmt.Errorf("--prompt-file flag requires a value")
-			}
-			promptFile = value
-			promptFileExplicit = true
-			continue
-		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 arg == "--model":
-			if i+1 >= len(args) {
-				return nil, fmt.Errorf("--model flag requires a value")
-			}
-			model = args[i+1]
-			i++
-			continue
-		case strings.HasPrefix(arg, "--model="):
-			value := strings.TrimPrefix(arg, "--model=")
-			if value == "" {
-				return nil, fmt.Errorf("--model flag requires a value")
-			}
-			model = value
-			continue
-		case arg == "--reasoning-effort":
-			if i+1 >= len(args) {
-				return nil, fmt.Errorf("--reasoning-effort flag requires a value")
-			}
-			value := strings.TrimSpace(args[i+1])
-			if value == "" {
-				return nil, fmt.Errorf("--reasoning-effort flag requires a value")
-			}
-			reasoningEffort = value
-			i++
-			continue
-		case strings.HasPrefix(arg, "--reasoning-effort="):
-			value := strings.TrimSpace(strings.TrimPrefix(arg, "--reasoning-effort="))
-			if value == "" {
-				return nil, fmt.Errorf("--reasoning-effort flag requires a value")
-			}
-			reasoningEffort = value
-			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, Agent: agentName, PromptFile: promptFile, PromptFileExplicit: promptFileExplicit, SkipPermissions: skipPermissions, Yolo: yolo, Model: strings.TrimSpace(model), ReasoningEffort: strings.TrimSpace(reasoningEffort)}
-	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 = 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 {
-			// Validate workdir: "-" is not a valid directory
-			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 {
-			// Validate workdir: "-" is not a valid directory
-			if args[1] == "-" {
-				return nil, fmt.Errorf("invalid workdir: '-' is not a valid directory path")
-			}
-			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/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

@@ -1,4 +1,4 @@
-package main
+package wrapper
 
 import (
 	"context"
@@ -6,6 +6,9 @@ import (
 	"path/filepath"
 	"testing"
 	"time"
+
+	config "codeagent-wrapper/internal/config"
+	executor "codeagent-wrapper/internal/executor"
 )
 
 func TestValidateAgentName(t *testing.T) {
@@ -28,7 +31,7 @@ func TestValidateAgentName(t *testing.T) {
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			err := validateAgentName(tt.input)
+			err := config.ValidateAgentName(tt.input)
 			if (err != nil) != tt.wantErr {
 				t.Fatalf("validateAgentName(%q) err=%v, wantErr=%v", tt.input, err, tt.wantErr)
 			}
@@ -59,6 +62,8 @@ 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 {
@@ -117,10 +122,8 @@ func TestDefaultRunCodexTaskFn_AppliesAgentPromptFile(t *testing.T) {
 		WaitDelay: 2 * time.Millisecond,
 	})
 
-	newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+	_ = executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner { return fake })
-		return fake
+	_ = executor.SetSelectBackendFn(func(name string) (Backend, error) {
-	}
-	selectBackendFn = func(name string) (Backend, error) {
 		return testBackend{
 			name:    name,
 			command: "fake-cmd",
@@ -128,7 +131,7 @@ func TestDefaultRunCodexTaskFn_AppliesAgentPromptFile(t *testing.T) {
 				return []string{targetArg}
 			},
 		}, nil
-	}
+	})
 
 	res := defaultRunCodexTaskFn(TaskSpec{
 		ID:         "t",

codeagent-wrapper/internal/app/app.go

@@ -0,0 +1,279 @@
+package wrapper
+
+import (
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+)
+
+var version = "dev"
+
+const (
+	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     = 500 * 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 +1,116 @@
+package wrapper
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"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)
+
+	configDir := filepath.Join(home, ".codeagent")
+	if err := os.MkdirAll(configDir, 0o755); err != nil {
+		b.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(configDir, "models.json"), []byte(`{
+  "agents": {
+    "develop": { "backend": "codex", "model": "gpt-test" }
+  }
+}`), 0o644); err != nil {
+		b.Fatal(err)
+	}
+
+	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 +1,707 @@
+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
+	Skills          string
+	SkipPermissions bool
+	Worktree        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.StringVar(&opts.Skills, "skills", "", "Comma-separated skill names for spec injection")
+
+	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")
+	fs.BoolVar(&opts.Worktree, "worktree", false, "Execute in a new git worktree (auto-generates task ID)")
+}
+
+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) {
+	ensureExecutableTempDir()
+	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
+	var resolvedAllowedTools, resolvedDisallowedTools []string
+	if agentName != "" {
+		var resolvedYolo bool
+		var err error
+		resolvedBackend, resolvedModel, resolvedPromptFile, resolvedReasoning, _, _, resolvedYolo, resolvedAllowedTools, resolvedDisallowedTools, err = config.ResolveAgentConfig(agentName)
+		if err != nil {
+			return nil, fmt.Errorf("failed to resolve agent %q: %w", agentName, err)
+		}
+		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")
+	}
+
+	var skills []string
+	if cmd.Flags().Changed("skills") {
+		for _, s := range strings.Split(opts.Skills, ",") {
+			s = strings.TrimSpace(s)
+			if s != "" {
+				skills = append(skills, s)
+			}
+		}
+	}
+
+	cfg := &Config{
+		WorkDir:            defaultWorkdir,
+		Backend:            backendName,
+		Agent:              agentName,
+		PromptFile:         promptFile,
+		PromptFileExplicit: promptFileExplicit,
+		SkipPermissions:    skipPermissions,
+		Yolo:               yolo,
+		Model:              model,
+		ReasoningEffort:    reasoningEffort,
+		MaxParallelWorkers: config.ResolveMaxParallelWorkers(),
+		AllowedTools:       resolvedAllowedTools,
+		DisallowedTools:    resolvedDisallowedTools,
+		Skills:             skills,
+		Worktree:           opts.Worktree,
+	}
+
+	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") || cmd.Flags().Changed("skills") {
+		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)
+	}
+
+	// Resolve skills: explicit > auto-detect from workdir
+	skills := cfg.Skills
+	if len(skills) == 0 {
+		skills = detectProjectSkills(cfg.WorkDir)
+	}
+	if len(skills) > 0 {
+		if content := resolveSkillContent(skills, 0); content != "" {
+			taskText = taskText + "\n\n# Domain Best Practices\n\n" + content
+		}
+	}
+
+	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 cfg.Mode == "new" && strings.TrimSpace(taskText) == "integration-log-check" {
+		logInfo("Integration log check: skipping backend execution")
+		return 0
+	}
+
+	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,
+		Worktree:        cfg.Worktree,
+		AllowedTools:    cfg.AllowedTools,
+		DisallowedTools: cfg.DisallowedTools,
+		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"
@@ -11,9 +11,20 @@ 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
 	}

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 +1,62 @@
+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)
+}
+
+func detectProjectSkills(workDir string) []string {
+	return executor.DetectProjectSkills(workDir)
+}
+
+func resolveSkillContent(skills []string, maxBudget int) string {
+	return executor.ResolveSkillContent(skills, maxBudget)
+}

codeagent-wrapper/internal/app/executor_concurrent_test.go

@@ -1,4 +1,4 @@
-package main
+package wrapper
 
 import (
 	"bufio"
@@ -15,9 +15,10 @@ import (
 	"strings"
 	"sync"
 	"sync/atomic"
-	"syscall"
 	"testing"
 	"time"
+
+	executor "codeagent-wrapper/internal/executor"
 )
 
 var executorTestTaskCounter atomic.Int64
@@ -91,7 +92,7 @@ func (rc *reasonReadCloser) record(reason string) {
 type execFakeRunner struct {
 	stdout          io.ReadCloser
 	stderr          io.ReadCloser
-	process         processHandle
+	process         executor.ProcessHandle
 	stdin           io.WriteCloser
 	dir             string
 	env             map[string]string
@@ -158,7 +159,7 @@ func (f *execFakeRunner) SetEnv(env map[string]string) {
 		f.env[k] = v
 	}
 }
-func (f *execFakeRunner) Process() processHandle {
+func (f *execFakeRunner) Process() executor.ProcessHandle {
 	if f.process != nil {
 		return f.process
 	}
@@ -168,225 +169,15 @@ func (f *execFakeRunner) Process() processHandle {
 	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.StderrPipe(); 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)
-		rcWithCmd.SetDir("/tmp")
-		if rcWithCmd.cmd.Dir != "/tmp" {
-			t.Fatalf("expected SetDir to set cmd.Dir, got %q", rcWithCmd.cmd.Dir)
-		}
-		echoCmd := exec.Command("echo", "ok")
-		rcProc := &realCmd{cmd: echoCmd}
-		stdoutPipe, err := rcProc.StdoutPipe()
-		if err != nil {
-			t.Fatalf("StdoutPipe error: %v", err)
-		}
-		stderrPipe, err := rcProc.StderrPipe()
-		if err != nil {
-			t.Fatalf("StderrPipe error: %v", err)
-		}
-		stdinPipe, err := rcProc.StdinPipe()
-		if err != nil {
-			t.Fatalf("StdinPipe error: %v", err)
-		}
-		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)
-		_, _ = io.ReadAll(stderrPipe)
-
-		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) {
-		const key = "CODEX_BYPASS_SANDBOX"
-		t.Setenv(key, "false")
-
-		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)
-		}
-		// Test summary mode (default) - should have new format with ### headers
-		out = generateFinalOutput([]TaskResult{{TaskID: "rich", ExitCode: 0, SessionID: "sess", LogPath: "/tmp/log", Message: "hello"}})
-		if !strings.Contains(out, "### rich") {
-			t.Fatalf("summary output missing task header: %s", out)
-		}
-		// Test full output mode - should have Session and Message
-		out = generateFinalOutputWithMode([]TaskResult{{TaskID: "rich", ExitCode: 0, SessionID: "sess", LogPath: "/tmp/log", Message: "hello"}}, false)
-		if !strings.Contains(out, "Session: sess") || !strings.Contains(out, "Log: /tmp/log") || !strings.Contains(out, "hello") {
-			t.Fatalf("full output missing fields: %s", out)
-		}
-
-		args := buildCodexArgs(&Config{Mode: "new", WorkDir: "/tmp"}, "task")
-		if !slices.Equal(args, []string{"e", "--skip-git-repo-check", "-C", "/tmp", "--json", "task"}) {
-			t.Fatalf("unexpected codex args: %+v", args)
-		}
-		args = buildCodexArgs(&Config{Mode: "resume", SessionID: "sess"}, "target")
-		if !slices.Equal(args, []string{"e", "--skip-git-repo-check", "--json", "resume", "sess", "target"}) {
-			t.Fatalf("unexpected resume args: %+v", args)
-		}
-	})
-
-	t.Run("generateFinalOutputASCIIMode", func(t *testing.T) {
-		t.Setenv("CODEAGENT_ASCII_MODE", "true")
-
-		results := []TaskResult{
-			{TaskID: "ok", ExitCode: 0, Coverage: "92%", CoverageNum: 92, CoverageTarget: 90, KeyOutput: "done"},
-			{TaskID: "warn", ExitCode: 0, Coverage: "80%", CoverageNum: 80, CoverageTarget: 90, KeyOutput: "did"},
-			{TaskID: "bad", ExitCode: 2, Error: "boom"},
-		}
-		out := generateFinalOutput(results)
-
-		for _, sym := range []string{"PASS", "WARN", "FAIL"} {
-			if !strings.Contains(out, sym) {
-				t.Fatalf("ASCII mode should include %q, got: %s", sym, out)
-			}
-		}
-		for _, sym := range []string{"✓", "⚠️", "✗"} {
-			if strings.Contains(out, sym) {
-				t.Fatalf("ASCII mode should not include %q, got: %s", sym, out)
-			}
-		}
-	})
-
-	t.Run("generateFinalOutputUnicodeMode", func(t *testing.T) {
-		t.Setenv("CODEAGENT_ASCII_MODE", "false")
-
-		results := []TaskResult{
-			{TaskID: "ok", ExitCode: 0, Coverage: "92%", CoverageNum: 92, CoverageTarget: 90, KeyOutput: "done"},
-			{TaskID: "warn", ExitCode: 0, Coverage: "80%", CoverageNum: 80, CoverageTarget: 90, KeyOutput: "did"},
-			{TaskID: "bad", ExitCode: 2, Error: "boom"},
-		}
-		out := generateFinalOutput(results)
-
-		for _, sym := range []string{"✓", "⚠️", "✗"} {
-			if !strings.Contains(out, sym) {
-				t.Fatalf("Unicode mode should include %q, got: %s", sym, out)
-			}
-		}
-	})
-
-	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"}
-		}
-		t.Setenv("CODEAGENT_MAX_PARALLEL_WORKERS", "1")
-
-		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 resetTestHooks()
-	defer func() { newCommandRunner = origRunner }()
 
 	t.Run("resumeMissingSessionID", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			t.Fatalf("unexpected command execution for invalid resume config")
 			return nil
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 
 		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: ".", Mode: "resume"}, nil, nil, false, false, 1)
 		if res.ExitCode == 0 || !strings.Contains(res.Error, "session_id") {
@@ -396,13 +187,14 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 
 	t.Run("success", func(t *testing.T) {
 		var firstStdout *reasonReadCloser
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.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}}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 
 		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 {
@@ -432,17 +224,18 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("startErrors", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{startErr: errors.New("executable file not found"), process: &execFakeProcess{pid: 1}}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		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 {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.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")
@@ -450,13 +243,14 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("timeoutAndPipes", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:    newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"slow"}}`),
 				process:   &execFakeProcess{pid: 5},
 				waitDelay: 20 * time.Millisecond,
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		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)
@@ -464,17 +258,18 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("pipeErrors", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{stdoutErr: errors.New("stdout fail"), process: &execFakeProcess{pid: 6}}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		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 {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.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")
@@ -487,13 +282,14 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 		if exitErr == nil {
 			t.Fatalf("expected exec.ExitError")
 		}
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"ignored"}}`),
 				process: &execFakeProcess{pid: 8},
 				waitErr: exitErr,
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		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")
@@ -501,13 +297,14 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("contextCancelled", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:    newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"cancel"}}`),
 				process:   &execFakeProcess{pid: 9},
 				waitDelay: 10 * time.Millisecond,
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		ctx, cancel := context.WithCancel(context.Background())
 		cancel()
 		res := runCodexTaskWithContext(ctx, TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, false, 1)
@@ -517,12 +314,13 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("silentLogger", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"quiet"}}`),
 				process: &execFakeProcess{pid: 10},
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		_ = closeLogger()
 		res := runCodexTaskWithContext(context.Background(), TaskSpec{Task: "payload", WorkDir: "."}, nil, nil, false, true, 1)
 		if res.ExitCode != 0 || res.LogPath == "" {
@@ -532,12 +330,13 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("injectedLogger", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"injected"}}`),
 				process: &execFakeProcess{pid: 12},
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		_ = closeLogger()
 
 		injected, err := NewLoggerWithSuffix("executor-injected")
@@ -549,7 +348,7 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 			_ = os.Remove(injected.Path())
 		}()
 
-		ctx := withTaskLogger(context.Background(), injected)
+		ctx := executor.WithTaskLogger(context.Background(), injected)
 		res := runCodexTaskWithContext(ctx, TaskSpec{ID: "task-injected", Task: "payload", WorkDir: "."}, nil, nil, false, true, 1)
 		if res.ExitCode != 0 || res.LogPath != injected.Path() {
 			t.Fatalf("expected injected logger path, got %+v", res)
@@ -569,12 +368,13 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("contextLoggerWithoutParent", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"ctx"}}`),
 				process: &execFakeProcess{pid: 14},
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		_ = closeLogger()
 
 		taskLogger, err := NewLoggerWithSuffix("executor-taskctx")
@@ -586,8 +386,8 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 			_ = os.Remove(taskLogger.Path())
 		})
 
-		ctx := withTaskLogger(context.Background(), taskLogger)
+		ctx := executor.WithTaskLogger(context.Background(), taskLogger)
-		res := runCodexTaskWithContext(nil, TaskSpec{ID: "task-context", Task: "payload", WorkDir: ".", Context: ctx}, nil, nil, false, true, 1)
+		res := runCodexTaskWithContext(context.TODO(), TaskSpec{ID: "task-context", Task: "payload", WorkDir: ".", Context: ctx}, nil, nil, false, true, 1)
 		if res.ExitCode != 0 || res.LogPath != taskLogger.Path() {
 			t.Fatalf("expected task logger to be reused from spec context, got %+v", res)
 		}
@@ -607,16 +407,17 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 
 	t.Run("backendSetsDirAndNilContext", func(t *testing.T) {
 		var rc *execFakeRunner
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			rc = &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"backend"}}`),
 				process: &execFakeProcess{pid: 13},
 			}
 			return rc
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 
 		_ = closeLogger()
-		res := runCodexTaskWithContext(nil, TaskSpec{ID: "task-backend", Task: "payload", WorkDir: "/tmp"}, ClaudeBackend{}, nil, false, false, 1)
+		res := runCodexTaskWithContext(context.TODO(), TaskSpec{ID: "task-backend", Task: "payload", WorkDir: "/tmp"}, ClaudeBackend{}, nil, false, false, 1)
 		if res.ExitCode != 0 || res.Message != "backend" {
 			t.Fatalf("unexpected result: %+v", res)
 		}
@@ -628,13 +429,14 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	t.Run("claudeSkipPermissionsPropagatesFromTaskSpec", func(t *testing.T) {
 		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
 		var gotArgs []string
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			gotArgs = append([]string(nil), args...)
 			return &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"agent_message","text":"ok"}}`),
 				process: &execFakeProcess{pid: 15},
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 
 		_ = closeLogger()
 		res := runCodexTaskWithContext(context.Background(), TaskSpec{ID: "task-skip", Task: "payload", WorkDir: ".", SkipPermissions: true}, ClaudeBackend{}, nil, false, false, 1)
@@ -647,12 +449,13 @@ func TestExecutorRunCodexTaskWithContext(t *testing.T) {
 	})
 
 	t.Run("missingMessage", func(t *testing.T) {
-		newCommandRunner = func(ctx context.Context, name string, args ...string) commandRunner {
+		executor.SetNewCommandRunner(func(ctx context.Context, name string, args ...string) executor.CommandRunner {
 			return &execFakeRunner{
 				stdout:  newReasonReadCloser(`{"type":"item.completed","item":{"type":"task","text":"noop"}}`),
 				process: &execFakeProcess{pid: 11},
 			}
-		}
+		})
+		t.Cleanup(func() { executor.SetNewCommandRunner(nil) })
 		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")
@@ -678,7 +481,7 @@ func TestExecutorParallelLogIsolation(t *testing.T) {
 
 	origRun := runCodexTaskFn
 	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
-		logger := taskLoggerFromContext(task.Context)
+		logger := executor.TaskLoggerFromContext(task.Context)
 		if logger == nil {
 			return TaskResult{TaskID: task.ID, ExitCode: 1, Error: "missing task logger"}
 		}
@@ -702,7 +505,7 @@ func TestExecutorParallelLogIsolation(t *testing.T) {
 	os.Stderr = stderrW
 	defer func() { os.Stderr = oldStderr }()
 
-	results := executeConcurrentWithContext(nil, [][]TaskSpec{{{ID: taskA}, {ID: taskB}}}, 1, -1)
+	results := executeConcurrentWithContext(context.TODO(), [][]TaskSpec{{{ID: taskA}, {ID: taskB}}}, 1, -1)
 
 	_ = stderrW.Close()
 	os.Stderr = oldStderr
@@ -764,11 +567,10 @@ func TestExecutorParallelLogIsolation(t *testing.T) {
 }
 
 func TestConcurrentExecutorParallelLogIsolationAndClosure(t *testing.T) {
-	tempDir := t.TempDir()
+	setTempDirEnv(t, t.TempDir())
-	t.Setenv("TMPDIR", tempDir)
 
 	oldArgs := os.Args
-	os.Args = []string{defaultWrapperName}
+	os.Args = []string{wrapperName}
 	t.Cleanup(func() { os.Args = oldArgs })
 
 	mainLogger, err := NewLoggerWithSuffix("concurrent-main")
@@ -814,7 +616,7 @@ func TestConcurrentExecutorParallelLogIsolationAndClosure(t *testing.T) {
 	runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
 		readyCh <- struct{}{}
 
-		logger := taskLoggerFromContext(task.Context)
+		logger := executor.TaskLoggerFromContext(task.Context)
 		loggerCh <- taskLoggerInfo{taskID: task.ID, logger: logger}
 		if logger == nil {
 			return TaskResult{TaskID: task.ID, ExitCode: 1, Error: "missing task logger"}
@@ -901,15 +703,9 @@ func TestConcurrentExecutorParallelLogIsolationAndClosure(t *testing.T) {
 	}
 
 	for taskID, logger := range loggers {
-		if !logger.closed.Load() {
+		if !logger.IsClosed() {
 			t.Fatalf("expected task logger to be closed for %q", taskID)
 		}
-		if logger.file == nil {
-			t.Fatalf("expected task logger file to be non-nil for %q", taskID)
-		}
-		if _, err := logger.file.Write([]byte("x")); err == nil {
-			t.Fatalf("expected task logger file to be closed for %q", taskID)
-		}
 	}
 
 	mainLogger.Flush()
@@ -979,10 +775,10 @@ func parseTaskIDFromLogLine(line string) (string, bool) {
 }
 
 func TestExecutorTaskLoggerContext(t *testing.T) {
-	if taskLoggerFromContext(nil) != nil {
+	if executor.TaskLoggerFromContext(context.TODO()) != nil {
-		t.Fatalf("expected nil logger from nil context")
+		t.Fatalf("expected nil logger from TODO context")
 	}
-	if taskLoggerFromContext(context.Background()) != nil {
+	if executor.TaskLoggerFromContext(context.Background()) != nil {
 		t.Fatalf("expected nil logger when context has no logger")
 	}
 
@@ -995,12 +791,12 @@ func TestExecutorTaskLoggerContext(t *testing.T) {
 		_ = os.Remove(logger.Path())
 	}()
 
-	ctx := withTaskLogger(context.Background(), logger)
+	ctx := executor.WithTaskLogger(context.Background(), logger)
-	if got := taskLoggerFromContext(ctx); got != logger {
+	if got := executor.TaskLoggerFromContext(ctx); got != logger {
 		t.Fatalf("expected logger roundtrip, got %v", got)
 	}
 
-	if taskLoggerFromContext(withTaskLogger(context.Background(), nil)) != nil {
+	if executor.TaskLoggerFromContext(executor.WithTaskLogger(context.Background(), nil)) != nil {
 		t.Fatalf("expected nil logger when injected logger is nil")
 	}
 }
@@ -1132,8 +928,7 @@ func TestExecutorExecuteConcurrentWithContextBranches(t *testing.T) {
 	t.Run("TestConcurrentTaskLoggerFailure", func(t *testing.T) {
 		// Create a writable temp dir for the main logger, then flip TMPDIR to a read-only
 		// location so task-specific loggers fail to open.
-		writable := t.TempDir()
+		writable := setTempDirEnv(t, t.TempDir())
-		t.Setenv("TMPDIR", writable)
 
 		mainLogger, err := NewLoggerWithSuffix("shared-main")
 		if err != nil {
@@ -1146,18 +941,18 @@ func TestExecutorExecuteConcurrentWithContextBranches(t *testing.T) {
 			_ = os.Remove(mainLogger.Path())
 		})
 
-		noWrite := filepath.Join(writable, "ro")
+		notDir := filepath.Join(writable, "not-a-dir")
-		if err := os.Mkdir(noWrite, 0o500); err != nil {
+		if err := os.WriteFile(notDir, []byte("x"), 0o644); err != nil {
-			t.Fatalf("failed to create read-only temp dir: %v", err)
+			t.Fatalf("failed to create temp file: %v", err)
 		}
-		t.Setenv("TMPDIR", noWrite)
+		setTempDirEnv(t, notDir)
 
 		taskA := nextExecutorTestTaskID("shared-a")
 		taskB := nextExecutorTestTaskID("shared-b")
 
 		orig := runCodexTaskFn
 		runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
-			logger := taskLoggerFromContext(task.Context)
+			logger := executor.TaskLoggerFromContext(task.Context)
 			if logger != mainLogger {
 				return TaskResult{TaskID: task.ID, ExitCode: 1, Error: "unexpected logger"}
 			}
@@ -1191,9 +986,6 @@ func TestExecutorExecuteConcurrentWithContextBranches(t *testing.T) {
 			if res.LogPath != mainLogger.Path() {
 				t.Fatalf("shared log path mismatch: got %q want %q", res.LogPath, mainLogger.Path())
 			}
-			if !res.sharedLog {
-				t.Fatalf("expected sharedLog flag for %+v", res)
-			}
 			if !strings.Contains(stderrOut, "Log (shared)") {
 				t.Fatalf("stderr missing shared marker: %s", stderrOut)
 			}
@@ -1217,12 +1009,11 @@ func TestExecutorExecuteConcurrentWithContextBranches(t *testing.T) {
 	})
 
 	t.Run("TestSanitizeTaskID", func(t *testing.T) {
-		tempDir := t.TempDir()
+		setTempDirEnv(t, t.TempDir())
-		t.Setenv("TMPDIR", tempDir)
 
 		orig := runCodexTaskFn
 		runCodexTaskFn = func(task TaskSpec, timeout int) TaskResult {
-			logger := taskLoggerFromContext(task.Context)
+			logger := executor.TaskLoggerFromContext(task.Context)
 			if logger == nil {
 				return TaskResult{TaskID: task.ID, ExitCode: 1, Error: "missing logger"}
 			}
@@ -1260,7 +1051,14 @@ func TestExecutorExecuteConcurrentWithContextBranches(t *testing.T) {
 			if err != nil {
 				t.Fatalf("failed to read log %q: %v", res.LogPath, err)
 			}
-			if !strings.Contains(string(data), "TASK="+res.TaskID) {
+			found := false
+			for _, line := range strings.Split(string(data), "\n") {
+				if strings.Contains(stripTimestampPrefix(line), "TASK="+res.TaskID) {
+					found = true
+					break
+				}
+			}
+			if !found {
 				t.Fatalf("log for %q missing task marker, content: %s", res.TaskID, string(data))
 			}
 			_ = os.Remove(res.LogPath)
@@ -1268,147 +1066,6 @@ func TestExecutorExecuteConcurrentWithContextBranches(t *testing.T) {
 	})
 }
 
-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 runtime.GOOS != "windows" && 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)
-}
-
 func TestExecutorSharedLogFalseWhenCustomLogPath(t *testing.T) {
 	devNull, err := os.OpenFile(os.DevNull, os.O_WRONLY, 0)
 	if err != nil {
@@ -1421,8 +1078,7 @@ func TestExecutorSharedLogFalseWhenCustomLogPath(t *testing.T) {
 		_ = devNull.Close()
 	})
 
-	tempDir := t.TempDir()
+	tempDir := setTempDirEnv(t, t.TempDir())
-	t.Setenv("TMPDIR", tempDir)
 
 	// Setup: 创建主 logger
 	mainLogger, err := NewLoggerWithSuffix("shared-main")
@@ -1438,11 +1094,11 @@ func TestExecutorSharedLogFalseWhenCustomLogPath(t *testing.T) {
 	// 模拟场景：task logger 创建失败（通过设置只读的 TMPDIR），
 	// 回退到主 logger（handle.shared=true），
 	// 但 runCodexTaskFn 返回自定义的 LogPath（不等于主 logger 的路径）
-	roDir := filepath.Join(tempDir, "ro")
+	notDir := filepath.Join(tempDir, "not-a-dir")
-	if err := os.Mkdir(roDir, 0o500); err != nil {
+	if err := os.WriteFile(notDir, []byte("x"), 0o644); err != nil {
-		t.Fatalf("failed to create read-only dir: %v", err)
+		t.Fatalf("failed to create temp file: %v", err)
 	}
-	t.Setenv("TMPDIR", roDir)
+	setTempDirEnv(t, notDir)
 
 	orig := runCodexTaskFn
 	customLogPath := "/custom/path/to.log"
@@ -1464,10 +1120,9 @@ func TestExecutorSharedLogFalseWhenCustomLogPath(t *testing.T) {
 	}
 
 	res := results[0]
-	// 关键断言：即使 handle.shared=true（因为 task logger 创建失败），
+	out := generateFinalOutputWithMode(results, false)
-	// 但因为 LogPath 不等于主 logger 的路径，sharedLog 应为 false
+	if strings.Contains(out, "(shared)") {
-	if res.sharedLog {
+		t.Fatalf("did not expect shared marker when LogPath differs from shared logger, got: %s", out)
-		t.Fatalf("expected sharedLog=false when LogPath differs from shared logger, got true")
 	}
 
 	// 验证 LogPath 确实是自定义的

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()
 }
 
@@ -57,11 +60,17 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 			for _, p := range parts {
 				p = strings.TrimSpace(p)
 				if strings.HasSuffix(p, "tasks") {
-					fmt.Sscanf(p, "%d tasks", &payload.Summary.Total)
+					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") {
-					fmt.Sscanf(p, "%d passed", &payload.Summary.Success)
+					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") {
-					fmt.Sscanf(p, "%d failed", &payload.Summary.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:") {
@@ -70,11 +79,17 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 			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" {
@@ -94,34 +109,39 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 			currentTask = &TaskResult{}
 
 			taskLine := strings.TrimPrefix(line, "### ")
-			success, warning, failed := getStatusSymbols()
+			parseMarker := func(marker string, exitCode int) bool {
-			// Parse different formats
+				needle := " " + marker
-			if strings.Contains(taskLine, " "+success) {
+				if !strings.Contains(taskLine, needle) {
-				parts := strings.Split(taskLine, " "+success)
+					return false
+				}
+				parts := strings.Split(taskLine, needle)
 				currentTask.TaskID = strings.TrimSpace(parts[0])
-				currentTask.ExitCode = 0
+				currentTask.ExitCode = exitCode
-				// Extract coverage if present
+				if exitCode == 0 && len(parts) > 1 {
-				if len(parts) > 1 {
 					coveragePart := strings.TrimSpace(parts[1])
 					if strings.HasSuffix(coveragePart, "%") {
 						currentTask.Coverage = coveragePart
 					}
 				}
-			} else if strings.Contains(taskLine, " "+warning) {
+				return true
-				parts := strings.Split(taskLine, " "+warning)
+			}
-				currentTask.TaskID = strings.TrimSpace(parts[0])
+
-				currentTask.ExitCode = 0
+			switch {
-			} else if strings.Contains(taskLine, " "+failed) {
+			case parseMarker("✓", 0), parseMarker("PASS", 0):
-				parts := strings.Split(taskLine, " "+failed)
+				// ok
-				currentTask.TaskID = strings.TrimSpace(parts[0])
+			case parseMarker("⚠️", 0), parseMarker("WARN", 0):
-				currentTask.ExitCode = 1
+				// warning
-			} else {
+			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:") {
-				fmt.Sscanf(line, "Exit code: %d", &currentTask.ExitCode)
+				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:") {
@@ -147,7 +167,9 @@ func parseIntegrationOutput(t *testing.T, out string) integrationOutput {
 				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
 				}
@@ -180,6 +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
@@ -365,7 +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() {
@@ -418,9 +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 {
@@ -474,9 +527,9 @@ ok-d`
 
 	// After parallel log isolation fix, each task has its own log file
 	expectedLines := map[string]struct{}{
-		fmt.Sprintf("Task a: Log: %s", filepath.Join(tempDir, fmt.Sprintf("codex-wrapper-%d-a.log", os.Getpid()))): {},
+		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("codex-wrapper-%d-b.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("codex-wrapper-%d-d.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) {
@@ -494,13 +547,11 @@ 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"
+	codexCommand = createFakeCodexScript(t, "integration-session", "done")
-	buildCodexArgsFn = func(cfg *Config, targetArg string) []string {
+	buildCodexArgsFn = func(cfg *Config, targetArg string) []string { return []string{} }
-		return []string{`{"type":"thread.started","thread_id":"integration-session"}` + "\n" + `{"type":"item.completed","item":{"type":"agent_message","text":"done"}}`}
-	}
 
 	var exitCode int
 	stderr := captureStderr(t, func() {
@@ -512,7 +563,7 @@ 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)
@@ -672,20 +723,18 @@ func TestRunConcurrentSpeedupBenchmark(t *testing.T) {
 	layers := [][]TaskSpec{tasks}
 
 	serialStart := time.Now()
-	for _, task := range tasks {
+	_ = executeConcurrentWithContext(nil, layers, 5, 1)
-		_ = runCodexTaskFn(task, 5)
-	}
 	serialElapsed := time.Since(serialStart)
 
 	concurrentStart := time.Now()
-	_ = executeConcurrent(layers, 5)
+	_ = executeConcurrentWithContext(nil, layers, 5, 0)
 	concurrentElapsed := time.Since(concurrentStart)
 
-	if concurrentElapsed >= serialElapsed/5 {
-		t.Fatalf("expected concurrent time <20%% of serial, serial=%v concurrent=%v", serialElapsed, concurrentElapsed)
-	}
 	ratio := float64(concurrentElapsed) / float64(serialElapsed)
 	t.Logf("speedup ratio (concurrent/serial)=%.3f", ratio)
+	if concurrentElapsed >= serialElapsed/2 {
+		t.Fatalf("expected concurrent time <50%% of serial, serial=%v concurrent=%v", serialElapsed, concurrentElapsed)
+	}
 }
 
 func TestRunStartupCleanupRemovesOrphansEndToEnd(t *testing.T) {
@@ -693,11 +742,11 @@ func TestRunStartupCleanupRemovesOrphansEndToEnd(t *testing.T) {
 
 	tempDir := setTempDirEnv(t, t.TempDir())
 
-	orphanA := createTempLog(t, tempDir, "codex-wrapper-5001.log")
+	orphanA := createTempLog(t, tempDir, "codeagent-wrapper-5001.log")
-	orphanB := createTempLog(t, tempDir, "codex-wrapper-5002-extra.log")
+	orphanB := createTempLog(t, tempDir, "codeagent-wrapper-5002-extra.log")
-	orphanC := createTempLog(t, tempDir, "codex-wrapper-5003-suffix.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 {
@@ -713,7 +762,7 @@ 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)
@@ -739,7 +788,7 @@ 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 {
@@ -763,7 +812,7 @@ 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)
 	}
@@ -777,21 +826,26 @@ func TestRunCleanupFlagEndToEnd_Success(t *testing.T) {
 
 	tempDir := setTempDirEnv(t, t.TempDir())
 
-	staleA := createTempLog(t, tempDir, "codex-wrapper-2100.log")
+	basePID := os.Getpid()
-	staleB := createTempLog(t, tempDir, "codex-wrapper-2200-extra.log")
+	stalePID1 := basePID + 10000
-	keeper := createTempLog(t, tempDir, "codex-wrapper-2300.log")
+	stalePID2 := basePID + 11000
+	keeperPID := basePID + 12000
+
+	staleA := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", stalePID1))
+	staleB := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d-extra.log", stalePID2))
+	keeper := createTempLog(t, tempDir, fmt.Sprintf("codeagent-wrapper-%d.log", keeperPID))
 
 	stubProcessRunning(t, func(pid int) bool {
-		return pid == 2300 || pid == os.Getpid()
+		return pid == keeperPID || pid == basePID
 	})
 	stubProcessStartTime(t, func(pid int) time.Time {
-		if pid == 2300 || pid == os.Getpid() {
+		if pid == keeperPID || pid == basePID {
 			return time.Now().Add(-1 * time.Hour)
 		}
 		return time.Time{}
 	})
 
-	os.Args = []string{"codex-wrapper", "--cleanup"}
+	os.Args = []string{"codeagent-wrapper", "--cleanup"}
 
 	var exitCode int
 	output := captureStdout(t, func() {
@@ -815,10 +869,10 @@ 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, fmt.Sprintf("codeagent-wrapper-%d.log", stalePID1)) || !strings.Contains(output, fmt.Sprintf("codeagent-wrapper-%d-extra.log", stalePID2)) {
 		t.Fatalf("missing deleted file names in output: %q", output)
 	}
-	if !strings.Contains(output, "codex-wrapper-2300.log") {
+	if !strings.Contains(output, fmt.Sprintf("codeagent-wrapper-%d.log", keeperPID)) {
 		t.Fatalf("missing kept file names in output: %q", output)
 	}
 
@@ -831,7 +885,7 @@ 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) {
@@ -850,7 +904,7 @@ 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() {
@@ -867,7 +921,7 @@ 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) {
@@ -880,7 +934,7 @@ 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/os_paths_test.go

@@ -0,0 +1,46 @@
+package wrapper
+
+import (
+	"os"
+	"testing"
+)
+
+func TestParseArgs_Workdir_OSPaths(t *testing.T) {
+	oldArgv := os.Args
+	t.Cleanup(func() { os.Args = oldArgv })
+
+	workdirs := []struct {
+		name string
+		path string
+	}{
+		{name: "windows drive forward slashes", path: "D:/repo/path"},
+		{name: "windows drive backslashes", path: `C:\repo\path`},
+		{name: "windows UNC", path: `\\server\share\repo`},
+		{name: "unix absolute", path: "/home/user/repo"},
+		{name: "relative", path: "./relative/repo"},
+	}
+
+	for _, wd := range workdirs {
+		t.Run("new mode: "+wd.name, func(t *testing.T) {
+			os.Args = []string{"codeagent-wrapper", "task", wd.path}
+			cfg, err := parseArgs()
+			if err != nil {
+				t.Fatalf("parseArgs() error: %v", err)
+			}
+			if cfg.Mode != "new" || cfg.Task != "task" || cfg.WorkDir != wd.path {
+				t.Fatalf("cfg mismatch: got mode=%q task=%q workdir=%q, want mode=%q task=%q workdir=%q", cfg.Mode, cfg.Task, cfg.WorkDir, "new", "task", wd.path)
+			}
+		})
+
+		t.Run("resume mode: "+wd.name, func(t *testing.T) {
+			os.Args = []string{"codeagent-wrapper", "resume", "sid-1", "task", wd.path}
+			cfg, err := parseArgs()
+			if err != nil {
+				t.Fatalf("parseArgs() error: %v", err)
+			}
+			if cfg.Mode != "resume" || cfg.SessionID != "sid-1" || cfg.Task != "task" || cfg.WorkDir != wd.path {
+				t.Fatalf("cfg mismatch: got mode=%q sid=%q task=%q workdir=%q, want mode=%q sid=%q task=%q workdir=%q", cfg.Mode, cfg.SessionID, cfg.Task, cfg.WorkDir, "resume", "sid-1", "task", wd.path)
+			}
+		})
+	}
+}

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/stdin_mode_test.go

@@ -0,0 +1,119 @@
+package wrapper
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestRunSingleMode_UseStdin_TargetArgAndTaskText(t *testing.T) {
+	defer resetTestHooks()
+
+	setTempDirEnv(t, t.TempDir())
+	logger, err := NewLogger()
+	if err != nil {
+		t.Fatalf("NewLogger(): %v", err)
+	}
+	setLogger(logger)
+	t.Cleanup(func() { _ = closeLogger() })
+
+	type testCase struct {
+		name       string
+		cfgTask    string
+		explicit   bool
+		stdinData  string
+		isTerminal bool
+
+		wantUseStdin bool
+		wantTarget   string
+		wantTaskText string
+	}
+
+	longTask := strings.Repeat("a", 801)
+
+	tests := []testCase{
+		{
+			name:         "piped input forces stdin mode",
+			cfgTask:      "cli-task",
+			stdinData:    "piped task text",
+			isTerminal:   false,
+			wantUseStdin: true,
+			wantTarget:   "-",
+			wantTaskText: "piped task text",
+		},
+		{
+			name:         "explicit dash forces stdin mode",
+			cfgTask:      "-",
+			explicit:     true,
+			stdinData:    "explicit task text",
+			isTerminal:   true,
+			wantUseStdin: true,
+			wantTarget:   "-",
+			wantTaskText: "explicit task text",
+		},
+		{
+			name:         "special char backslash forces stdin mode",
+			cfgTask:      `C:\repo\file.go`,
+			isTerminal:   true,
+			wantUseStdin: true,
+			wantTarget:   "-",
+			wantTaskText: `C:\repo\file.go`,
+		},
+		{
+			name:         "length>800 forces stdin mode",
+			cfgTask:      longTask,
+			isTerminal:   true,
+			wantUseStdin: true,
+			wantTarget:   "-",
+			wantTaskText: longTask,
+		},
+		{
+			name:         "simple task uses argv target",
+			cfgTask:      "analyze code",
+			isTerminal:   true,
+			wantUseStdin: false,
+			wantTarget:   "analyze code",
+			wantTaskText: "analyze code",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			var gotTarget string
+			buildCodexArgsFn = func(cfg *Config, targetArg string) []string {
+				gotTarget = targetArg
+				return []string{targetArg}
+			}
+
+			var gotTask TaskSpec
+			runTaskFn = func(task TaskSpec, silent bool, timeout int) TaskResult {
+				gotTask = task
+				return TaskResult{ExitCode: 0, Message: "ok"}
+			}
+
+			stdinReader = strings.NewReader(tt.stdinData)
+			isTerminalFn = func() bool { return tt.isTerminal }
+
+			cfg := &Config{
+				Mode:          "new",
+				Task:          tt.cfgTask,
+				WorkDir:       defaultWorkdir,
+				Backend:       defaultBackendName,
+				ExplicitStdin: tt.explicit,
+			}
+
+			if code := runSingleMode(cfg, "codeagent-wrapper"); code != 0 {
+				t.Fatalf("runSingleMode() = %d, want 0", code)
+			}
+
+			if gotTarget != tt.wantTarget {
+				t.Fatalf("targetArg = %q, want %q", gotTarget, tt.wantTarget)
+			}
+			if gotTask.UseStdin != tt.wantUseStdin {
+				t.Fatalf("taskSpec.UseStdin = %v, want %v", gotTask.UseStdin, tt.wantUseStdin)
+			}
+			if gotTask.Task != tt.wantTaskText {
+				t.Fatalf("taskSpec.Task = %q, want %q", gotTask.Task, tt.wantTaskText)
+			}
+		})
+	}
+}

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/tmpdir.go

@@ -0,0 +1,134 @@
+package wrapper
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"runtime"
+	"strings"
+)
+
+const tmpDirEnvOverrideKey = "CODEAGENT_TMPDIR"
+
+var tmpDirExecutableCheckFn = canExecuteInDir
+
+func ensureExecutableTempDir() {
+	// Windows doesn't execute scripts via shebang, and os.TempDir semantics differ.
+	if runtime.GOOS == "windows" {
+		return
+	}
+
+	if override := strings.TrimSpace(os.Getenv(tmpDirEnvOverrideKey)); override != "" {
+		if resolved, err := resolvePathWithTilde(override); err == nil {
+			if err := os.MkdirAll(resolved, 0o700); err == nil {
+				if ok, _ := tmpDirExecutableCheckFn(resolved); ok {
+					setTempEnv(resolved)
+					return
+				}
+			}
+		}
+		// Invalid override should not block execution; fall back to default behavior.
+	}
+
+	current := currentTempDirFromEnv()
+	if current == "" {
+		current = "/tmp"
+	}
+
+	ok, _ := tmpDirExecutableCheckFn(current)
+	if ok {
+		return
+	}
+
+	fallback := defaultFallbackTempDir()
+	if fallback == "" {
+		return
+	}
+	if err := os.MkdirAll(fallback, 0o700); err != nil {
+		return
+	}
+	if ok, _ := tmpDirExecutableCheckFn(fallback); !ok {
+		return
+	}
+
+	setTempEnv(fallback)
+	fmt.Fprintf(os.Stderr, "INFO: temp dir is not executable; set TMPDIR=%s\n", fallback)
+}
+
+func setTempEnv(dir string) {
+	_ = os.Setenv("TMPDIR", dir)
+	_ = os.Setenv("TMP", dir)
+	_ = os.Setenv("TEMP", dir)
+}
+
+func defaultFallbackTempDir() string {
+	home, err := os.UserHomeDir()
+	if err != nil || strings.TrimSpace(home) == "" {
+		return ""
+	}
+	return filepath.Clean(filepath.Join(home, ".codeagent", "tmp"))
+}
+
+func currentTempDirFromEnv() string {
+	for _, k := range []string{"TMPDIR", "TMP", "TEMP"} {
+		if v := strings.TrimSpace(os.Getenv(k)); v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func resolvePathWithTilde(p string) (string, error) {
+	p = strings.TrimSpace(p)
+	if p == "" {
+		return "", errors.New("empty path")
+	}
+
+	if p == "~" || strings.HasPrefix(p, "~/") || strings.HasPrefix(p, "~\\") {
+		home, err := os.UserHomeDir()
+		if err != nil || strings.TrimSpace(home) == "" {
+			if err == nil {
+				err = errors.New("empty home directory")
+			}
+			return "", fmt.Errorf("resolve ~: %w", err)
+		}
+		if p == "~" {
+			return home, nil
+		}
+		return filepath.Clean(home + p[1:]), nil
+	}
+
+	return filepath.Clean(p), nil
+}
+
+func canExecuteInDir(dir string) (bool, error) {
+	dir = strings.TrimSpace(dir)
+	if dir == "" {
+		return false, errors.New("empty dir")
+	}
+
+	f, err := os.CreateTemp(dir, "codeagent-tmp-exec-*")
+	if err != nil {
+		return false, err
+	}
+	path := f.Name()
+	defer func() { _ = os.Remove(path) }()
+
+	if _, err := f.WriteString("#!/bin/sh\nexit 0\n"); err != nil {
+		_ = f.Close()
+		return false, err
+	}
+	if err := f.Close(); err != nil {
+		return false, err
+	}
+	if err := os.Chmod(path, 0o700); err != nil {
+		return false, err
+	}
+
+	if err := exec.Command(path).Run(); err != nil {
+		return false, err
+	}
+	return true, nil
+}

codeagent-wrapper/internal/app/tmpdir_test.go

@@ -0,0 +1,103 @@
+package wrapper
+
+import (
+	"os"
+	"path/filepath"
+	"runtime"
+	"testing"
+)
+
+func TestEnsureExecutableTempDir_Override(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("ensureExecutableTempDir is no-op on Windows")
+	}
+	restore := captureTempEnv()
+	t.Cleanup(restore)
+
+	t.Setenv("HOME", t.TempDir())
+	t.Setenv("USERPROFILE", os.Getenv("HOME"))
+
+	orig := tmpDirExecutableCheckFn
+	tmpDirExecutableCheckFn = func(string) (bool, error) { return true, nil }
+	t.Cleanup(func() { tmpDirExecutableCheckFn = orig })
+
+	override := filepath.Join(t.TempDir(), "mytmp")
+	t.Setenv(tmpDirEnvOverrideKey, override)
+
+	ensureExecutableTempDir()
+
+	if got := os.Getenv("TMPDIR"); got != override {
+		t.Fatalf("TMPDIR=%q, want %q", got, override)
+	}
+	if got := os.Getenv("TMP"); got != override {
+		t.Fatalf("TMP=%q, want %q", got, override)
+	}
+	if got := os.Getenv("TEMP"); got != override {
+		t.Fatalf("TEMP=%q, want %q", got, override)
+	}
+	if st, err := os.Stat(override); err != nil || !st.IsDir() {
+		t.Fatalf("override dir not created: stat=%v err=%v", st, err)
+	}
+}
+
+func TestEnsureExecutableTempDir_FallbackWhenCurrentNotExecutable(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("ensureExecutableTempDir is no-op on Windows")
+	}
+	restore := captureTempEnv()
+	t.Cleanup(restore)
+
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+
+	cur := filepath.Join(t.TempDir(), "cur-tmp")
+	if err := os.MkdirAll(cur, 0o700); err != nil {
+		t.Fatal(err)
+	}
+	t.Setenv("TMPDIR", cur)
+
+	fallback := filepath.Join(home, ".codeagent", "tmp")
+
+	orig := tmpDirExecutableCheckFn
+	tmpDirExecutableCheckFn = func(dir string) (bool, error) {
+		if filepath.Clean(dir) == filepath.Clean(cur) {
+			return false, nil
+		}
+		if filepath.Clean(dir) == filepath.Clean(fallback) {
+			return true, nil
+		}
+		return true, nil
+	}
+	t.Cleanup(func() { tmpDirExecutableCheckFn = orig })
+
+	ensureExecutableTempDir()
+
+	if got := os.Getenv("TMPDIR"); filepath.Clean(got) != filepath.Clean(fallback) {
+		t.Fatalf("TMPDIR=%q, want %q", got, fallback)
+	}
+	if st, err := os.Stat(fallback); err != nil || !st.IsDir() {
+		t.Fatalf("fallback dir not created: stat=%v err=%v", st, err)
+	}
+}
+
+func captureTempEnv() func() {
+	type entry struct {
+		set bool
+		val string
+	}
+	snapshot := make(map[string]entry, 3)
+	for _, k := range []string{"TMPDIR", "TMP", "TEMP"} {
+		v, ok := os.LookupEnv(k)
+		snapshot[k] = entry{set: ok, val: v}
+	}
+	return func() {
+		for k, e := range snapshot {
+			if !e.set {
+				_ = os.Unsetenv(k)
+				continue
+			}
+			_ = os.Setenv(k, e.val)
+		}
+	}
+}

codeagent-wrapper/internal/app/utils.go

@@ -1,4 +1,4 @@
-package main
+package wrapper
 
 import (
 	"bytes"
@@ -7,6 +7,8 @@ import (
 	"os"
 	"strconv"
 	"strings"
+
+	utils "codeagent-wrapper/internal/utils"
 )
 
 func resolveTimeout() int {
@@ -52,7 +54,7 @@ func shouldUseStdin(taskText string, piped bool) bool {
 	if len(taskText) > 800 {
 		return true
 	}
-	return strings.IndexAny(taskText, stdinSpecialChars) >= 0
+	return strings.ContainsAny(taskText, stdinSpecialChars)
 }
 
 func defaultIsTerminal() bool {
@@ -196,69 +198,21 @@ func (b *tailBuffer) String() string {
 }
 
 func truncate(s string, maxLen int) string {
-	if len(s) <= maxLen {
+	return utils.Truncate(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 utils.SafeTruncate(s, maxLen)
-		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
+	return utils.SanitizeOutput(s)
-	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()
 }
 
 func min(a, b int) int {
-	if a < b {
+	return utils.Min(a, b)
-		return a
-	}
-	return b
 }
 
 func hello() string {
@@ -381,7 +335,7 @@ func extractFilesChangedFromLines(lines []string) []string {
 		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.Trim(file, "`\"'()[],:")
 				file = strings.TrimPrefix(file, "@")
 				if file != "" && !seen[file] {
 					files = append(files, file)
@@ -398,7 +352,7 @@ func extractFilesChangedFromLines(lines []string) []string {
 		// 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.Trim(part, "`\"'()[],:")
 			part = strings.TrimPrefix(part, "@")
 			for _, ext := range exts {
 				if strings.HasSuffix(part, ext) && !seen[part] {
@@ -567,116 +521,3 @@ func extractKeyOutputFromLines(lines []string, maxLen int) string {
 	clean := strings.TrimSpace(strings.Join(lines, "\n"))
 	return safeTruncate(clean, maxLen)
 }
-
-// extractCoverageGap extracts what's missing from coverage reports
-// Looks for uncovered lines, branches, or functions
-func extractCoverageGap(message string) string {
-	if message == "" {
-		return ""
-	}
-
-	lower := strings.ToLower(message)
-	lines := strings.Split(message, "\n")
-
-	// Look for uncovered/missing patterns
-	for _, line := range lines {
-		lineLower := strings.ToLower(line)
-		line = strings.TrimSpace(line)
-
-		// Common patterns for uncovered code
-		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
-		}
-
-		// Look for specific file:line patterns in coverage reports
-		if strings.Contains(lineLower, "branch") && strings.Contains(lineLower, "not taken") {
-			if len(line) > 100 {
-				return line[:97] + "..."
-			}
-			return line
-		}
-	}
-
-	// Look for function names that aren't covered
-	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
-// Returns the most relevant error information up to maxLen characters
-func extractErrorDetail(message string, maxLen int) string {
-	if message == "" || maxLen <= 0 {
-		return ""
-	}
-
-	lines := strings.Split(message, "\n")
-	var errorLines []string
-
-	// Look for error-related lines
-	for _, line := range lines {
-		line = strings.TrimSpace(line)
-		if line == "" {
-			continue
-		}
-
-		lower := strings.ToLower(line)
-
-		// Skip noise lines
-		if strings.HasPrefix(line, "at ") && strings.Contains(line, "(") {
-			// Stack trace line - only keep first one
-			if len(errorLines) > 0 && strings.HasPrefix(strings.ToLower(errorLines[len(errorLines)-1]), "at ") {
-				continue
-			}
-		}
-
-		// Prioritize error/fail lines
-		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 {
-		// No specific error lines found, take last few lines
-		start := len(lines) - 5
-		if start < 0 {
-			start = 0
-		}
-		for _, line := range lines[start:] {
-			line = strings.TrimSpace(line)
-			if line != "" {
-				errorLines = append(errorLines, line)
-			}
-		}
-	}
-
-	// Join and truncate
-	result := strings.Join(errorLines, " | ")
-	return safeTruncate(result, maxLen)
-}

codeagent-wrapper/internal/app/utils_test.go

@@ -1,4 +1,4 @@
-package main
+package wrapper
 
 import (
 	"fmt"

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

@@ -1,4 +1,4 @@
-package main
+package backend
 
 import (
 	"bytes"
@@ -6,6 +6,8 @@ import (
 	"path/filepath"
 	"reflect"
 	"testing"
+
+	config "codeagent-wrapper/internal/config"
 )
 
 func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
@@ -13,7 +15,7 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 
 	t.Run("new mode omits skip-permissions when env disabled", func(t *testing.T) {
 		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
-		cfg := &Config{Mode: "new", WorkDir: "/repo"}
+		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) {
@@ -22,7 +24,7 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 	})
 
 	t.Run("new mode includes skip-permissions by default", func(t *testing.T) {
-		cfg := &Config{Mode: "new", SkipPermissions: false}
+		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) {
@@ -32,7 +34,7 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 
 	t.Run("resume mode includes session id", func(t *testing.T) {
 		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
-		cfg := &Config{Mode: "resume", SessionID: "sid-123", WorkDir: "/ignored"}
+		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) {
@@ -42,7 +44,7 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 
 	t.Run("resume mode without session still returns base flags", func(t *testing.T) {
 		t.Setenv("CODEAGENT_SKIP_PERMISSIONS", "false")
-		cfg := &Config{Mode: "resume", WorkDir: "/ignored"}
+		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) {
@@ -51,7 +53,7 @@ func TestClaudeBuildArgs_ModesAndPermissions(t *testing.T) {
 	})
 
 	t.Run("resume mode can opt-in skip permissions", func(t *testing.T) {
-		cfg := &Config{Mode: "resume", SessionID: "sid-123", SkipPermissions: true}
+		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) {
@@ -70,7 +72,7 @@ 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{Mode: "new", Model: "opus"}
+		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) {
@@ -80,7 +82,7 @@ func TestBackendBuildArgs_Model(t *testing.T) {
 
 	t.Run("gemini includes -m when set", func(t *testing.T) {
 		backend := GeminiBackend{}
-		cfg := &Config{Mode: "new", Model: "gemini-3-pro-preview"}
+		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) {
@@ -93,7 +95,7 @@ func TestBackendBuildArgs_Model(t *testing.T) {
 		t.Setenv(key, "false")
 
 		backend := CodexBackend{}
-		cfg := &Config{Mode: "new", WorkDir: "/tmp", Model: "o3"}
+		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) {
@@ -105,7 +107,7 @@ func TestBackendBuildArgs_Model(t *testing.T) {
 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"}
+		cfg := &config.Config{Mode: "new", WorkDir: "/workspace"}
 		got := backend.BuildArgs(cfg, "task")
 		want := []string{"-o", "stream-json", "-y", "task"}
 		if !reflect.DeepEqual(got, want) {
@@ -115,7 +117,7 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 
 	t.Run("gemini resume mode uses session id", func(t *testing.T) {
 		backend := GeminiBackend{}
-		cfg := &Config{Mode: "resume", SessionID: "sid-999"}
+		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) {
@@ -125,7 +127,7 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 
 	t.Run("gemini resume mode without session omits identifier", func(t *testing.T) {
 		backend := GeminiBackend{}
-		cfg := &Config{Mode: "resume"}
+		cfg := &config.Config{Mode: "resume"}
 		got := backend.BuildArgs(cfg, "resume")
 		want := []string{"-o", "stream-json", "-y", "resume"}
 		if !reflect.DeepEqual(got, want) {
@@ -142,7 +144,7 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 
 	t.Run("gemini stdin mode uses -p flag", func(t *testing.T) {
 		backend := GeminiBackend{}
-		cfg := &Config{Mode: "new"}
+		cfg := &config.Config{Mode: "new"}
 		got := backend.BuildArgs(cfg, "-")
 		want := []string{"-o", "stream-json", "-y", "-p", "-"}
 		if !reflect.DeepEqual(got, want) {
@@ -155,7 +157,7 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 		t.Setenv(key, "false")
 
 		backend := CodexBackend{}
-		cfg := &Config{Mode: "new", WorkDir: "/tmp"}
+		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) {
@@ -168,7 +170,7 @@ func TestClaudeBuildArgs_GeminiAndCodexModes(t *testing.T) {
 		t.Setenv(key, "true")
 
 		backend := CodexBackend{}
-		cfg := &Config{Mode: "new", WorkDir: "/tmp"}
+		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) {
@@ -204,7 +206,7 @@ func TestLoadMinimalEnvSettings(t *testing.T) {
 	t.Setenv("USERPROFILE", home)
 
 	t.Run("missing file returns empty", func(t *testing.T) {
-		if got := loadMinimalEnvSettings(); len(got) != 0 {
+		if got := LoadMinimalEnvSettings(); len(got) != 0 {
 			t.Fatalf("got %v, want empty", got)
 		}
 	})
@@ -220,7 +222,7 @@ func TestLoadMinimalEnvSettings(t *testing.T) {
 			t.Fatalf("WriteFile: %v", err)
 		}
 
-		got := loadMinimalEnvSettings()
+		got := LoadMinimalEnvSettings()
 		if got["ANTHROPIC_API_KEY"] != "secret" || got["FOO"] != "bar" {
 			t.Fatalf("got %v, want keys present", got)
 		}
@@ -234,7 +236,7 @@ func TestLoadMinimalEnvSettings(t *testing.T) {
 			t.Fatalf("WriteFile: %v", err)
 		}
 
-		got := loadMinimalEnvSettings()
+		got := LoadMinimalEnvSettings()
 		if got["GOOD"] != "ok" {
 			t.Fatalf("got %v, want GOOD=ok", got)
 		}
@@ -249,12 +251,72 @@ func TestLoadMinimalEnvSettings(t *testing.T) {
 	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)
+		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 {
+		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 +1,149 @@
+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 != "" {
+		// Claude Code CLI uses ANTHROPIC_API_KEY for API-key based auth.
+		env["ANTHROPIC_API_KEY"] = apiKey
+	}
+	return env
+}
+func (ClaudeBackend) BuildArgs(cfg *config.Config, targetArg string) []string {
+	return buildClaudeArgs(cfg, targetArg)
+}
+
+const MaxClaudeSettingsBytes = 1 << 20 // 1MB
+
+type MinimalClaudeSettings struct {
+	Env   map[string]string
+	Model string
+}
+
+// LoadMinimalClaudeSettings 从 ~/.claude/settings.json 只提取安全的最小子集：
+// - env: 只接受字符串类型的值
+// - model: 只接受字符串类型的值
+// 文件缺失/解析失败/超限都返回空。
+func LoadMinimalClaudeSettings() MinimalClaudeSettings {
+	home, err := os.UserHomeDir()
+	if err != nil || home == "" {
+		return MinimalClaudeSettings{}
+	}
+
+	claudeDir := filepath.Clean(filepath.Join(home, ".claude"))
+	settingPath := filepath.Clean(filepath.Join(claudeDir, "settings.json"))
+	rel, err := filepath.Rel(claudeDir, settingPath)
+	if err != nil || rel == ".." || strings.HasPrefix(rel, ".."+string(os.PathSeparator)) {
+		return MinimalClaudeSettings{}
+	}
+
+	info, err := os.Stat(settingPath)
+	if err != nil || info.Size() > MaxClaudeSettingsBytes {
+		return MinimalClaudeSettings{}
+	}
+
+	data, err := os.ReadFile(settingPath) // #nosec G304 -- path is fixed under user home and validated to stay within claudeDir
+	if err != nil {
+		return MinimalClaudeSettings{}
+	}
+
+	var cfg struct {
+		Env   map[string]any `json:"env"`
+		Model any            `json:"model"`
+	}
+	if err := json.Unmarshal(data, &cfg); err != nil {
+		return MinimalClaudeSettings{}
+	}
+
+	out := MinimalClaudeSettings{}
+
+	if model, ok := cfg.Model.(string); ok {
+		out.Model = strings.TrimSpace(model)
+	}
+
+	if len(cfg.Env) == 0 {
+		return out
+	}
+
+	env := make(map[string]string, len(cfg.Env))
+	for k, v := range cfg.Env {
+		s, ok := v.(string)
+		if !ok {
+			continue
+		}
+		env[k] = s
+	}
+	if len(env) == 0 {
+		return out
+	}
+	out.Env = env
+	return out
+}
+
+func LoadMinimalEnvSettings() map[string]string {
+	settings := LoadMinimalClaudeSettings()
+	if len(settings.Env) == 0 {
+		return nil
+	}
+	return settings.Env
+}
+
+func buildClaudeArgs(cfg *config.Config, targetArg string) []string {
+	if cfg == nil {
+		return nil
+	}
+	args := []string{"-p"}
+	// Default to skip permissions unless CODEAGENT_SKIP_PERMISSIONS=false
+	if cfg.SkipPermissions || cfg.Yolo || config.EnvFlagDefaultTrue("CODEAGENT_SKIP_PERMISSIONS") {
+		args = append(args, "--dangerously-skip-permissions")
+	}
+
+	// Prevent infinite recursion: disable all setting sources (user, project, local)
+	// This ensures a clean execution environment without CLAUDE.md or skills that would trigger codeagent
+	args = append(args, "--setting-sources", "")
+
+	if model := strings.TrimSpace(cfg.Model); model != "" {
+		args = append(args, "--model", model)
+	}
+
+	if cfg.Mode == "resume" {
+		if cfg.SessionID != "" {
+			// Claude CLI uses -r <session_id> for resume.
+			args = append(args, "-r", cfg.SessionID)
+		}
+	}
+
+	if len(cfg.AllowedTools) > 0 {
+		args = append(args, "--allowedTools")
+		args = append(args, cfg.AllowedTools...)
+	}
+	if len(cfg.DisallowedTools) > 0 {
+		args = append(args, "--disallowedTools")
+		args = append(args, cfg.DisallowedTools...)
+	}
+
+	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/codex_paths_test.go

@@ -0,0 +1,54 @@
+package backend
+
+import (
+	"reflect"
+	"testing"
+
+	config "codeagent-wrapper/internal/config"
+)
+
+func TestBuildCodexArgs_Workdir_OSPaths(t *testing.T) {
+	t.Setenv("CODEX_BYPASS_SANDBOX", "false")
+
+	tests := []struct {
+		name    string
+		workdir string
+	}{
+		{name: "windows drive forward slashes", workdir: "D:/repo/path"},
+		{name: "windows drive backslashes", workdir: `C:\repo\path`},
+		{name: "windows UNC", workdir: `\\server\share\repo`},
+		{name: "unix absolute", workdir: "/home/user/repo"},
+		{name: "relative", workdir: "./relative/repo"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			cfg := &config.Config{Mode: "new", WorkDir: tt.workdir}
+			got := BuildCodexArgs(cfg, "task")
+			want := []string{"e", "--skip-git-repo-check", "-C", tt.workdir, "--json", "task"}
+			if !reflect.DeepEqual(got, want) {
+				t.Fatalf("BuildCodexArgs() = %v, want %v", got, want)
+			}
+		})
+	}
+
+	t.Run("new mode stdin target uses dash", func(t *testing.T) {
+		cfg := &config.Config{Mode: "new", WorkDir: `C:\repo\path`}
+		got := BuildCodexArgs(cfg, "-")
+		want := []string{"e", "--skip-git-repo-check", "-C", `C:\repo\path`, "--json", "-"}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("BuildCodexArgs() = %v, want %v", got, want)
+		}
+	})
+}
+
+func TestBuildCodexArgs_ResumeMode_OmitsWorkdir(t *testing.T) {
+	t.Setenv("CODEX_BYPASS_SANDBOX", "false")
+
+	cfg := &config.Config{Mode: "resume", SessionID: "sid-123", WorkDir: `C:\repo\path`}
+	got := BuildCodexArgs(cfg, "-")
+	want := []string{"e", "--skip-git-repo-check", "--json", "resume", "sid-123", "-"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("BuildCodexArgs() = %v, want %v", got, want)
+	}
+}

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 +1,261 @@
+package config
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+
+	"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"`
+	AllowedTools    []string `json:"allowed_tools,omitempty"`
+	DisallowedTools []string `json:"disallowed_tools,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{}
+
+const modelsConfigTildePath = "~/.codeagent/models.json"
+
+const modelsConfigExample = `{
+  "default_backend": "codex",
+  "default_model": "gpt-4.1",
+  "backends": {
+    "codex": { "api_key": "..." },
+    "claude": { "api_key": "..." }
+  },
+  "agents": {
+    "develop": {
+      "backend": "codex",
+      "model": "gpt-4.1",
+      "prompt_file": "~/.codeagent/prompts/develop.md",
+      "reasoning": "high",
+      "yolo": true
+    }
+  }
+}`
+
+var (
+	modelsConfigOnce   sync.Once
+	modelsConfigCached *ModelsConfig
+	modelsConfigErr    error
+)
+
+func modelsConfig() (*ModelsConfig, error) {
+	modelsConfigOnce.Do(func() {
+		modelsConfigCached, modelsConfigErr = loadModelsConfig()
+	})
+	return modelsConfigCached, modelsConfigErr
+}
+
+func modelsConfigPath() (string, error) {
+	home, err := os.UserHomeDir()
+	if err != nil || strings.TrimSpace(home) == "" {
+		return "", fmt.Errorf("failed to resolve user home directory: %w", err)
+	}
+
+	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 "", fmt.Errorf("refusing to read models config outside %s: %s", configDir, configPath)
+	}
+	return configPath, nil
+}
+
+func modelsConfigHint(configPath string) string {
+	configPath = strings.TrimSpace(configPath)
+	if configPath == "" {
+		return fmt.Sprintf("Create %s with e.g.:\n%s", modelsConfigTildePath, modelsConfigExample)
+	}
+	return fmt.Sprintf("Create %s (resolved to %s) with e.g.:\n%s", modelsConfigTildePath, configPath, modelsConfigExample)
+}
+
+func loadModelsConfig() (*ModelsConfig, error) {
+	configPath, err := modelsConfigPath()
+	if err != nil {
+		return nil, fmt.Errorf("%w\n\n%s", err, modelsConfigHint(""))
+	}
+
+	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) {
+			return nil, fmt.Errorf("models config not found: %s\n\n%s", configPath, modelsConfigHint(configPath))
+		}
+		return nil, fmt.Errorf("failed to read models config %s: %w\n\n%s", configPath, err, modelsConfigHint(configPath))
+	}
+
+	var cfg ModelsConfig
+	if err := json.Unmarshal(data, &cfg); err != nil {
+		return nil, fmt.Errorf("failed to parse models config %s: %w\n\n%s", configPath, err, modelsConfigHint(configPath))
+	}
+
+	cfg.DefaultBackend = strings.TrimSpace(cfg.DefaultBackend)
+	cfg.DefaultModel = strings.TrimSpace(cfg.DefaultModel)
+
+	// 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, nil
+}
+
+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, err := modelsConfig()
+	if err != nil || cfg == nil {
+		return "", ""
+	}
+	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, allowedTools, disallowedTools []string, err error) {
+	if err := ValidateAgentName(agentName); err != nil {
+		return "", "", "", "", "", "", false, nil, nil, err
+	}
+
+	cfg, err := modelsConfig()
+	if err != nil {
+		return "", "", "", "", "", "", false, nil, nil, err
+	}
+	if cfg == nil {
+		return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("models config is nil\n\n%s", modelsConfigHint(""))
+	}
+
+	if agent, ok := cfg.Agents[agentName]; ok {
+		backend = strings.TrimSpace(agent.Backend)
+		if backend == "" {
+			backend = strings.TrimSpace(cfg.DefaultBackend)
+			if backend == "" {
+				configPath, pathErr := modelsConfigPath()
+				if pathErr != nil {
+					return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("agent %q has empty backend and default_backend is not set\n\n%s", agentName, modelsConfigHint(""))
+				}
+				return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("agent %q has empty backend and default_backend is not set\n\n%s", agentName, modelsConfigHint(configPath))
+			}
+		}
+		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)
+		}
+
+		model = strings.TrimSpace(agent.Model)
+		if model == "" {
+			configPath, pathErr := modelsConfigPath()
+			if pathErr != nil {
+				return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("agent %q has empty model; set agents.%s.model in %s\n\n%s", agentName, agentName, modelsConfigTildePath, modelsConfigHint(""))
+			}
+			return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("agent %q has empty model; set agents.%s.model in %s\n\n%s", agentName, agentName, modelsConfigTildePath, modelsConfigHint(configPath))
+		}
+		return backend, model, agent.PromptFile, agent.Reasoning, baseURL, apiKey, agent.Yolo, agent.AllowedTools, agent.DisallowedTools, nil
+	}
+
+	if dynamic, ok := LoadDynamicAgent(agentName); ok {
+		backend = strings.TrimSpace(cfg.DefaultBackend)
+		model = strings.TrimSpace(cfg.DefaultModel)
+		configPath, pathErr := modelsConfigPath()
+		if backend == "" || model == "" {
+			if pathErr != nil {
+				return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("dynamic agent %q requires default_backend and default_model to be set in %s\n\n%s", agentName, modelsConfigTildePath, modelsConfigHint(""))
+			}
+			return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("dynamic agent %q requires default_backend and default_model to be set in %s\n\n%s", agentName, modelsConfigTildePath, modelsConfigHint(configPath))
+		}
+		backendCfg := resolveBackendConfig(cfg, backend)
+		baseURL = strings.TrimSpace(backendCfg.BaseURL)
+		apiKey = strings.TrimSpace(backendCfg.APIKey)
+		return backend, model, dynamic.PromptFile, "", baseURL, apiKey, false, nil, nil, nil
+	}
+
+	configPath, pathErr := modelsConfigPath()
+	if pathErr != nil {
+		return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("agent %q not found in %s\n\n%s", agentName, modelsConfigTildePath, modelsConfigHint(""))
+	}
+	return "", "", "", "", "", "", false, nil, nil, fmt.Errorf("agent %q not found in %s\n\n%s", agentName, modelsConfigTildePath, modelsConfigHint(configPath))
+}
+
+func ResolveAgentConfig(agentName string) (backend, model, promptFile, reasoning, baseURL, apiKey string, yolo bool, allowedTools, disallowedTools []string, err error) {
+	return resolveAgentConfig(agentName)
+}
+
+func ResetModelsConfigCacheForTest() {
+	modelsConfigCached = nil
+	modelsConfigErr = nil
+	modelsConfigOnce = sync.Once{}
+}

codeagent-wrapper/internal/config/agent_config_test.go

@@ -0,0 +1,262 @@
+package config
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestResolveAgentConfig_NoConfig_ReturnsHelpfulError(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	_, _, _, _, _, _, _, _, _, err := ResolveAgentConfig("develop")
+	if err == nil {
+		t.Fatalf("expected error, got nil")
+	}
+	msg := err.Error()
+	if !strings.Contains(msg, modelsConfigTildePath) {
+		t.Fatalf("error should mention %s, got: %s", modelsConfigTildePath, msg)
+	}
+	if !strings.Contains(msg, filepath.Join(home, ".codeagent", "models.json")) {
+		t.Fatalf("error should mention resolved config path, got: %s", msg)
+	}
+	if !strings.Contains(msg, "\"agents\"") {
+		t.Fatalf("error should include example config, got: %s", msg)
+	}
+}
+
+func TestLoadModelsConfig_NoFile(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	ResetModelsConfigCacheForTest()
+
+	_, err := loadModelsConfig()
+	if err == nil {
+		t.Fatalf("expected error, got nil")
+	}
+}
+
+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, err := loadModelsConfig()
+	if err != nil {
+		t.Fatalf("loadModelsConfig: %v", err)
+	}
+
+	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")
+		}
+	}
+
+	if _, ok := cfg.Agents["oracle"]; ok {
+		t.Error("oracle should not be present without explicit config")
+	}
+
+	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, _, _, _, err := ResolveAgentConfig("custom-agent")
+	if err != nil {
+		t.Fatalf("ResolveAgentConfig(custom-agent): %v", err)
+	}
+	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)
+	}
+
+	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"
+}`), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	backend, model, promptFile, _, _, _, _, _, _, err := ResolveAgentConfig("sarsh")
+	if err != nil {
+		t.Fatalf("ResolveAgentConfig(sarsh): %v", err)
+	}
+	if backend != "codex" {
+		t.Errorf("backend = %q, want %q", backend, "codex")
+	}
+	if model != "gpt-test" {
+		t.Errorf("model = %q, want %q", model, "gpt-test")
+	}
+	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()
+
+	_, err := loadModelsConfig()
+	if err == nil {
+		t.Fatalf("expected error, got nil")
+	}
+}
+
+func TestResolveAgentConfig_UnknownAgent_ReturnsError(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	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": {
+    "develop": { "backend": "codex", "model": "gpt-test" }
+  }
+}`), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	_, _, _, _, _, _, _, _, _, err := ResolveAgentConfig("unknown-agent")
+	if err == nil {
+		t.Fatalf("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "unknown-agent") {
+		t.Fatalf("error should mention agent name, got: %s", err.Error())
+	}
+}
+
+func TestResolveAgentConfig_EmptyModel_ReturnsError(t *testing.T) {
+	home := t.TempDir()
+	t.Setenv("HOME", home)
+	t.Setenv("USERPROFILE", home)
+	t.Cleanup(ResetModelsConfigCacheForTest)
+	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(`{
+  "agents": {
+    "bad-agent": { "backend": "codex", "model": " " }
+  }
+}`), 0o644); err != nil {
+		t.Fatalf("WriteFile: %v", err)
+	}
+
+	_, _, _, _, _, _, _, _, _, err := ResolveAgentConfig("bad-agent")
+	if err == nil {
+		t.Fatalf("expected error, got nil")
+	}
+	if !strings.Contains(strings.ToLower(err.Error()), "empty model") {
+		t.Fatalf("error should mention empty model, got: %s", err.Error())
+	}
+}

codeagent-wrapper/internal/config/config.go

@@ -0,0 +1,106 @@
+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
+	AllowedTools       []string
+	DisallowedTools    []string
+	Skills             []string
+	Worktree           bool // Execute in a new git worktree
+}
+
+// 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 +1,196 @@
+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)
+	}
+
+	t.Setenv("HOME", tmpDir)
+	t.Setenv("USERPROFILE", tmpDir)
+
+	// Reset config cache
+	config.ResetModelsConfigCacheForTest()
+	defer config.ResetModelsConfigCacheForTest()
+
+	// Test ResolveAgentConfig
+	agentBackend, model, _, _, baseURL, apiKey, _, _, _, err := config.ResolveAgentConfig("test-agent")
+	if err != nil {
+		t.Fatalf("ResolveAgentConfig: %v", err)
+	}
+	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_API_KEY"] != apiKey {
+		t.Errorf("expected ANTHROPIC_API_KEY=%q, got %q", apiKey, env["ANTHROPIC_API_KEY"])
+	}
+}
+
+// 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)
+	}
+
+	t.Setenv("HOME", tmpDir)
+	t.Setenv("USERPROFILE", tmpDir)
+
+	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, _, _, _, err := config.ResolveAgentConfig(agentName)
+		if err != nil {
+			t.Fatalf("ResolveAgentConfig(%q): %v", agentName, err)
+		}
+		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_API_KEY"]; !ok {
+		t.Error("ANTHROPIC_API_KEY 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_API_KEY",
+			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_API_KEY"},
+		},
+		{
+			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_API_KEY"},
+		},
+		{
+			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_API_KEY"] != strings.TrimSpace(tt.apiKey) {
+					t.Errorf("ANTHROPIC_API_KEY = %q, want %q", env["ANTHROPIC_API_KEY"], 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_API_KEY" {
+			// 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")
+	}
+}