moai-adk 0.25.4__py3-none-any.whl → 0.32.8__py3-none-any.whl

moai_adk/templates/.claude/commands/moai/9-feedback.md

@@ -0,0 +1,314 @@
+---
+name: moai:9-feedback
+description: "Submit feedback or report issues"
+argument-hint: "[issue|suggestion|question]"
+allowed-tools: Read, Write, Edit, Grep, Glob, WebFetch, WebSearch, Bash, TodoWrite, AskUserQuestion, Task, Skill
+model: haiku
+---
+
+##  Pre-execution Context
+
+!git status --porcelain
+!git branch --show-current
+!git log --oneline -1
+
+##  Essential Files
+
+@.moai/config/config.yaml
+
+---
+
+#  MoAI-ADK Step 9: Feedback Loop
+
+> Architecture: Commands → Agents → Skills. This command orchestrates ONLY through `Task()` tool.
+> Delegation Model: Feedback collection delegated to `manager-quality` agent.
+
+Workflow Integration: This command implements the feedback loop of the MoAI workflow, allowing users to report issues or suggestions directly from the CLI.
+
+---
+
+##  Command Purpose
+
+Collect user feedback, bug reports, or feature suggestions and create GitHub issues automatically.
+
+Run on: `$ARGUMENTS` (Feedback type)
+
+---
+
+##  Execution Philosophy
+
+`/moai:9-feedback` performs feedback collection through agent delegation:
+
+```
+User Command: /moai:9-feedback [type]
+    ↓
+Phase 1: Task(subagent_type="manager-quality")
+    → Analyze feedback type
+    → Collect details via AskUserQuestion
+    → Create GitHub Issue via Skill
+    ↓
+Output: Issue created with link
+```
+
+### Key Principle: Full Delegation Pattern
+
+This command exclusively uses these tools:
+
+- [HARD] Task() for agent delegation
+  WHY: Task orchestration ensures feedback collection responsibility lies with specialized agents
+  IMPACT: Direct tool usage bypasses quality assurance and agent expertise
+
+- [HARD] AskUserQuestion() for user interaction AT COMMAND LEVEL ONLY
+  WHY: Subagents via Task() are stateless and cannot interact with users directly
+  IMPACT: Expecting agents to use AskUserQuestion causes workflow failures
+  CORRECT: Command collects feedback type and details, passes to agent as parameters
+
+- [HARD] Delegate all Bash operations to manager-quality agent
+  WHY: Agent context ensures proper error handling and feedback capture
+  IMPACT: Direct Bash execution loses feedback traceability and error context
+
+---
+
+##  Associated Agents & Skills
+
+| Agent/Skill     | Purpose                                       |
+| --------------- | --------------------------------------------- |
+| manager-quality | Feedback collection and GitHub issue creation |
+
+---
+
+## Agent Invocation Patterns (CLAUDE.md Compliance)
+
+This command uses agent execution patterns defined in CLAUDE.md (lines 96-120).
+
+### Sequential Phase-Based Chaining ✅
+
+Command implements simple sequential execution through 2 phases:
+
+Phase Flow:
+- Phase 1: Feedback Collection (manager-quality analyzes type and collects details)
+- Phase 2: GitHub Issue Creation (manager-quality creates issue with collected information)
+
+Each phase receives outputs from previous phase as context.
+
+WHY: Sequential execution ensures complete feedback capture before submission
+- Phase 2 requires validated feedback details from Phase 1
+- Issue creation requires all user input to be collected
+
+IMPACT: Skipping Phase 1 would create incomplete GitHub issues
+
+### Parallel Execution ❌
+
+Not applicable - simple linear workflow
+
+WHY: Feedback workflow has minimal complexity
+- Only one agent (manager-quality) handles entire process
+- Single feedback submission at a time
+- No independent operations to parallelize
+
+IMPACT: Parallel execution unnecessary for single-agent linear workflow
+
+### Resumable Agent Support ❌
+
+Not applicable - command completes in single execution
+
+WHY: Feedback submission is fast atomic operation
+- Typical execution completes in under 30 seconds
+- GitHub API calls are atomic and fast
+- No long-running processes requiring checkpoints
+
+IMPACT: Resume pattern unnecessary for simple feedback workflows
+
+---
+
+Refer to CLAUDE.md "Agent Chaining Patterns" (lines 96-120) for complete pattern architecture.
+
+---
+
+##  Execution Process
+
+### Step 1: Delegate to Quality Gate Agent
+
+Use the manager-quality subagent to collect and submit user feedback:
+
+Task: Collect user feedback and create a GitHub issue.
+
+Context:
+
+- Feedback Type: $ARGUMENTS (default to 'issue' if empty)
+- Conversation Language: {{CONVERSATION_LANGUAGE}}
+
+Instructions:
+
+1. Determine Feedback Type:
+
+   [HARD] Resolve feedback type from $ARGUMENTS if provided
+   WHY: Pre-specified type accelerates feedback collection
+   IMPACT: Skipping argument check forces unnecessary user interaction
+
+   [HARD] Prompt user to select type when $ARGUMENTS is empty
+   WHY: Interactive selection ensures proper categorization
+   IMPACT: Assuming default type may misclassify feedback
+
+   Supported Feedback Types:
+   - Bug Report: Technical issues or errors
+   - Feature Request: Suggestions for improvements
+   - Question/Other: Clarifications or general feedback
+
+2. Collect Details:
+
+   [HARD] Solicit feedback title from user
+   WHY: Title establishes feedback summary for issue search and triage
+   IMPACT: Missing title reduces issue discoverability
+
+   [HARD] Solicit detailed description from user
+   WHY: Description provides context for developers to understand and respond
+   IMPACT: Vague descriptions create follow-up communication overhead
+
+   [SOFT] Solicit priority level from user (Low/Medium/High)
+   WHY: Priority directs team resource allocation
+   IMPACT: Missing priority defaults to normal urgency
+
+3. Create GitHub Issue:
+
+   [HARD] Execute GitHub CLI (gh issue create) command with collected feedback
+   WHY: GitHub integration ensures feedback enters official issue tracking system
+   IMPACT: Untracked feedback is lost to follow-up and implementation
+
+   [HARD] Apply appropriate labels based on feedback type
+   WHY: Labels enable automated triage and dashboard organization
+   IMPACT: Untagged issues are invisible to responsible team members
+
+   [SOFT] Format issue body using consistent template
+   WHY: Standardized templates improve issue clarity and consistency
+   IMPACT: Inconsistent formatting wastes developer time parsing issues
+
+4. Report Result:
+   [HARD] Provide user with created issue URL
+   WHY: Direct issue link enables immediate user access and tracking
+   IMPACT: Missing link requires users to manually search for their feedback
+
+   [HARD] Confirm successful feedback submission to user
+   WHY: Confirmation provides closure and acknowledgment of user contribution
+   IMPACT: Silent completion leaves user uncertain about feedback status
+
+Language and Accessibility:
+
+- [HARD] Use conversation_language for all user-facing interactions
+  WHY: User language ensures comprehension and accessibility
+  IMPACT: Wrong language creates friction and reduces usability
+
+- [HARD] Provide text-based options in AskUserQuestion (exclude emojis)
+  WHY: Text options ensure consistency across all platforms and locales
+  IMPACT: Emoji options are platform-dependent and may not display correctly
+
+---
+
+##  Summary: Execution Verification Checklist
+
+Before considering command execution complete, verify all requirements:
+
+- [HARD] Agent Invoked: manager-quality agent executed with feedback details
+  Verification: Confirm agent Task() call with feedback context
+  Acceptance Criteria: Agent response confirms feedback reception
+
+- [HARD] Feedback Collected: User provided title, description, and type
+  Verification: Confirm all required fields captured
+  Acceptance Criteria: No empty or null feedback fields
+
+- [HARD] Issue Created: GitHub issue successfully submitted to repository
+  Verification: Confirm gh issue create command executed successfully
+  Acceptance Criteria: GitHub API response contains issue ID and URL
+
+- [HARD] Link Provided: User received direct URL to created issue
+  Verification: Confirm issue URL displayed in user response
+  Acceptance Criteria: User can click URL and access their feedback immediately
+
+---
+
+##  Quick Reference
+
+| Scenario         | Entry Point                   | Expected Outcome                            |
+| ---------------- | ----------------------------- | ------------------------------------------- |
+| Report bug       | `/moai:9-feedback issue`      | GitHub issue created with bug label         |
+| Request feature  | `/moai:9-feedback suggestion` | GitHub issue created with enhancement label |
+| Ask question     | `/moai:9-feedback question`   | GitHub issue created with question label    |
+| General feedback | `/moai:9-feedback`            | Interactive feedback collection             |
+
+Associated Agent:
+
+- `manager-quality` - Feedback manager and GitHub issue creator
+
+Feedback Types:
+
+- Bug Report: Technical issues or errors
+- Feature Request: Suggestions for improvements
+- Question: Clarifications or help needed
+- Other: General feedback
+
+Version: 1.0.0 (Agent-Delegated Pattern)
+Last Updated: 2025-11-25
+Architecture: Commands → Agents → Skills (Complete delegation)
+
+---
+
+## Output Format
+
+Structure agent responses with semantic sections for clarity and consistency:
+
+Response Structure:
+
+The agent response must include these sections:
+
+Feedback Summary:
+Concise recap of feedback type, title, and key points submitted
+
+GitHub Integration:
+Confirmation that feedback was submitted to GitHub with issue URL and ID
+
+User Language:
+Response provided in user's conversation_language configuration
+
+Next Actions:
+Clear options for user to continue workflow or submit additional feedback
+
+WHY: Semantic structure ensures consistent response quality and user experience
+IMPACT: Unstructured responses create ambiguity and require user clarification
+
+---
+
+## Post-Submission User Direction
+
+After successful feedback submission, present user with next action options:
+
+[HARD] Display post-submission summary to user
+WHY: Summary confirms successful completion and provides issue reference
+IMPACT: Missing summary leaves user uncertain about submission status
+
+[SOFT] Offer user next step choices via AskUserQuestion
+WHY: Guided choices help users continue productive workflows
+IMPACT: Abrupt completion requires user to determine next actions
+
+Next Step Options:
+- Continue Development: Return to current development workflow
+- Submit Additional Feedback: Report another issue or suggestion
+- View Issue: Open created GitHub issue in browser
+
+Requirements:
+
+- [HARD] Use conversation_language for all post-submission messaging
+  WHY: Consistent language maintains user context
+  IMPACT: Language switching disorients users
+
+- [HARD] Express all options as text labels without emoji characters
+  WHY: Text-only labels ensure universal platform compatibility
+  IMPACT: Emojis may fail to display across different systems
+
+---
+
+##  EXECUTION DIRECTIVE
+
+You must NOW execute the command following the "Execution Process" described above.
+
+1. Use the manager-quality subagent.
+2. Do NOT just describe what you will do. DO IT.

moai_adk/templates/.claude/hooks/__init__.py

@@ -0,0 +1,8 @@
+"""
+Claude Hooks Package
+
+This package contains hook scripts for Claude Code integration.
+"""
+
+__version__ = "1.0.0"
+__author__ = "MoAI-ADK Team"

moai_adk/templates/.claude/hooks/moai/__init__.py

@@ -0,0 +1,8 @@
+"""
+Alfred Hooks Package
+
+This package contains Alfred-specific hook scripts for MoAI-ADK integration.
+"""
+
+__version__ = "1.0.0"
+__author__ = "MoAI-ADK Team"

moai_adk/templates/.claude/hooks/moai/lib/__init__.py

@@ -0,0 +1,85 @@
+"""
+Hook utilities library - Optimized and consolidated
+
+This module provides centralized access to all hook-related utilities:
+- Configuration management (ConfigManager)
+- Core utilities (timeout, common utilities)
+- Data models (HookPayload, HookResult)
+- Project utilities (language detection, git info, SPEC counting)
+- Checkpoint utilities (risky operation detection, checkpoint creation)
+"""
+
+try:
+    # Import core components
+    # Import checkpoint utilities
+    from lib.checkpoint import (
+        create_checkpoint,
+        detect_risky_operation,
+        list_checkpoints,
+    )
+
+    # Import utilities
+    from lib.common import (
+        format_duration,
+        get_file_pattern_category,
+        get_summary_stats,
+        is_root_whitelisted,
+        suggest_moai_location,
+    )
+    from lib.config_manager import (
+        ConfigManager,
+        get_config,
+        get_config_manager,
+        get_exit_code,
+        get_graceful_degradation,
+        get_timeout_seconds,
+    )
+
+    # Import models
+    from lib.models import HookPayload, HookResult
+
+    # Import project utilities
+    from lib.project import (
+        count_specs,
+        find_project_root,
+        get_git_info,
+    )
+    from lib.timeout import CrossPlatformTimeout, TimeoutError, timeout_context
+
+    __all__ = [
+        # Core - Timeout
+        "CrossPlatformTimeout",
+        "TimeoutError",
+        "timeout_context",
+        # Core - Configuration
+        "ConfigManager",
+        "get_config_manager",
+        "get_config",
+        "get_timeout_seconds",
+        "get_graceful_degradation",
+        "get_exit_code",
+        # Common utilities
+        "format_duration",
+        "get_summary_stats",
+        "is_root_whitelisted",
+        "get_file_pattern_category",
+        "suggest_moai_location",
+        # Models
+        "HookPayload",
+        "HookResult",
+        # Checkpoint
+        "create_checkpoint",
+        "detect_risky_operation",
+        "list_checkpoints",
+        # Project
+        "find_project_root",
+        "get_git_info",
+        "count_specs",
+    ]
+
+except ImportError:
+    # Fallback if not all imports are available
+    __all__ = []
+
+__version__ = "1.0.0"
+__author__ = "MoAI-ADK Team"

moai_adk/templates/.claude/hooks/moai/lib/checkpoint.py

@@ -0,0 +1,244 @@
+#!/usr/bin/env python3
+"""Event-Driven Checkpoint system
+
+Detect risky tasks and create automatic checkpoints
+"""
+
+import json
+import subprocess
+from datetime import datetime
+from pathlib import Path
+from typing import Any
+
+
+def detect_risky_operation(tool_name: str, tool_args: dict[str, Any], cwd: str) -> tuple[bool, str]:
+    """Risk task detection (for Event-Driven Checkpoint)
+
+    Claude Code tool automatically detects dangerous tasks before use.
+    When a risk is detected, a checkpoint is automatically created to enable rollback.
+
+    Args:
+        tool_name: Name of the Claude Code tool (Bash, Edit, Write, MultiEdit)
+        tool_args: Tool argument dictionary
+        cwd: Project root directory path
+
+    Returns:
+        (is_risky, operation_type) tuple
+        - is_risky: Whether the operation is dangerous (bool)
+        - operation_type: operation type (str: delete, merge, script, critical-file, refactor)
+
+    Risky Operations:
+        - Bash tool: rm -rf, git merge, git reset --hard, git rebase, script execution
+        - Edit/Write tool: CLAUDE.md, config.json, .claude/skills/*.md
+        - MultiEdit tool: Edit ≥10 items File simultaneously
+        - Script execution: Python, Node, Java, Go, Rust, Dart, Swift, Kotlin, Shell scripts
+
+    Examples:
+        >>> detect_risky_operation("Bash", {"command": "rm -rf src/"}, ".")
+        (True, 'delete')
+        >>> detect_risky_operation("Edit", {"file_path": "CLAUDE.md"}, ".")
+        (True, 'critical-file')
+        >>> detect_risky_operation("Read", {"file_path": "test.py"}, ".")
+        (False, '')
+
+    Notes:
+        - Minimize false positives: ignore safe operations
+        - Performance: lightweight string matching (< 1ms)
+        - Extensibility: Easily added to the patterns dictionary
+
+    """
+    # Bash tool: Detect dangerous commands
+    if tool_name == "Bash":
+        command = tool_args.get("command", "")
+
+        # Mass Delete
+        if any(pattern in command for pattern in ["rm -rf", "git rm"]):
+            return (True, "delete")
+
+        # Git merge/reset/rebase
+        if any(pattern in command for pattern in ["git merge", "git reset --hard", "git rebase"]):
+            return (True, "merge")
+
+        # Execute external script (potentially destructive)
+        if any(command.startswith(prefix) for prefix in ["python ", "node ", "bash ", "sh "]):
+            return (True, "script")
+
+    # Edit/Write tool: Detect important files
+    if tool_name in ("Edit", "Write"):
+        file_path = tool_args.get("file_path", "")
+
+        critical_files = [
+            "CLAUDE.md",
+            "config.json",
+            ".claude/skills/moai-core-dev-guide/reference.md",
+            ".claude/skills/moai-core-spec-metadata-extended/reference.md",
+            ".moai/config/config.json",
+        ]
+
+        if any(cf in file_path for cf in critical_files):
+            return (True, "critical-file")
+
+    # MultiEdit tool: Detect large edits
+    if tool_name == "MultiEdit":
+        edits = tool_args.get("edits", [])
+        if len(edits) >= 10:
+            return (True, "refactor")
+
+    return (False, "")
+
+
+def create_checkpoint(cwd: str, operation_type: str) -> str:
+    """Create checkpoint (Git local branch)
+
+    Automatically creates checkpoints before dangerous operations.
+    Prevent remote repository contamination by creating a Git local branch.
+
+    Args:
+        cwd: Project root directory path
+        operation_type: operation type (delete, merge, script, etc.)
+
+    Returns:
+        checkpoint_branch: Created branch name
+        Returns "checkpoint-failed" on failure
+
+    Branch Naming:
+        before-{operation}-{YYYYMMDD-HHMMSS}
+        Example: before-delete-20251015-143000
+
+    Examples:
+        >>> create_checkpoint(".", "delete")
+        'before-delete-20251015-143000'
+
+    Notes:
+        - Create only local branch (no remote push)
+        - Fallback in case of Git error (ignore and continue)
+        - Do not check dirty working directory (allow uncommitted changes)
+        - Automatically record checkpoint logs (.moai/checkpoints.log)
+
+    """
+    timestamp = datetime.now().strftime("%Y%m%d-%H%M%S")
+    branch_name = f"before-{operation_type}-{timestamp}"
+
+    try:
+        # Create a new local branch from the current branch (without checking out)
+        subprocess.run(
+            ["git", "branch", branch_name],
+            cwd=cwd,
+            check=True,
+            capture_output=True,
+            text=True,
+            timeout=2,
+        )
+
+        # Checkpoint log records
+        log_checkpoint(cwd, branch_name, operation_type)
+
+        return branch_name
+
+    except (
+        subprocess.CalledProcessError,
+        subprocess.TimeoutExpired,
+        FileNotFoundError,
+    ):
+        # Fallback (ignore) in case of Git error
+        return "checkpoint-failed"
+
+
+def log_checkpoint(cwd: str, branch_name: str, operation_type: str) -> None:
+    """Checkpoint log records (.moai/checkpoints.log)
+
+    Checkpoint creation history is recorded in JSON Lines format.
+    SessionStart reads this log to display a list of checkpoints.
+
+    Args:
+        cwd: Project root directory path
+        branch_name: Created checkpoint branch name
+        operation_type: operation type
+
+    Log Format (JSON Lines):
+        {"timestamp": "2025-10-15T14:30:00", "branch": "before-delete-...", "operation": "delete"}
+
+    Examples:
+        >>> log_checkpoint(".", "before-delete-20251015-143000", "delete")
+        # Add 1 line to .moai/checkpoints.log
+
+    Notes:
+        - If the file does not exist, it is automatically created.
+        - Record in append mode (preserve existing logs)
+        - Ignored in case of failure (not critical)
+
+    """
+    log_file = Path(cwd) / ".moai" / "checkpoints.log"
+
+    try:
+        log_file.parent.mkdir(parents=True, exist_ok=True)
+
+        log_entry = {
+            "timestamp": datetime.now().isoformat(),
+            "branch": branch_name,
+            "operation": operation_type,
+        }
+
+        with log_file.open("a") as f:
+            f.write(json.dumps(log_entry) + "\n")
+
+    except (OSError, PermissionError):
+        # Ignore log failures (not critical)
+        pass
+
+
+def list_checkpoints(cwd: str, max_count: int = 10) -> list[dict[str, str]]:
+    """Checkpoint list (parsing .moai/checkpoints.log)
+
+    Returns a list of recently created checkpoints.
+    Used in the SessionStart, /moai:0-project restore command.
+
+    Args:
+        cwd: Project root directory path
+        max_count: Maximum number to return (default 10 items)
+
+    Returns:
+        Checkpoint list (most recent)
+        [{"timestamp": "...", "branch": "...", "operation": "..."}, ...]
+
+    Examples:
+        >>> list_checkpoints(".")
+        [
+            {"timestamp": "2025-10-15T14:30:00", "branch": "before-delete-...", "operation": "delete"},
+            {"timestamp": "2025-10-15T14:25:00", "branch": "before-merge-...", "operation": "merge"},
+        ]
+
+    Notes:
+        - If there is no log file, an empty list is returned.
+        - Ignore lines where JSON parsing fails
+        - Return only the latest max_count
+
+    """
+    log_file = Path(cwd) / ".moai" / "checkpoints.log"
+
+    if not log_file.exists():
+        return []
+
+    checkpoints = []
+
+    try:
+        with log_file.open("r") as f:
+            for line in f:
+                try:
+                    checkpoints.append(json.loads(line.strip()))
+                except json.JSONDecodeError:
+                    # Ignore lines where parsing failed
+                    pass
+    except (OSError, PermissionError):
+        return []
+
+    # Return only the most recent max_count items (in order of latest)
+    return checkpoints[-max_count:]
+
+
+__all__ = [
+    "detect_risky_operation",
+    "create_checkpoint",
+    "log_checkpoint",
+    "list_checkpoints",
+]