moai-adk 0.34.0__py3-none-any.whl → 1.1.0__py3-none-any.whl

moai_adk/templates/.claude/commands/moai/fix.md

@@ -0,0 +1,264 @@
+---
+description: "Agentic auto-fix - Parallel scan with autonomous correction"
+argument-hint: "[--dry] [--sequential] [--level N] [file_path]"
+type: utility
+allowed-tools: Task, AskUserQuestion, TodoWrite, Bash, Read, Write, Edit, Glob, Grep
+model: inherit
+---
+
+## Pre-execution Context
+
+!git status --porcelain
+!git diff --name-only HEAD
+
+## Essential Files
+
+@.moai/config/sections/ralph.yaml
+
+---
+
+# /moai:fix - Agentic Auto-Fix
+
+## Core Principle: Fully Autonomous Fixing
+
+AI autonomously finds and fixes issues.
+
+```
+START: Issue Detection
+  ↓
+AI: Parallel Scan → Classify → Fix → Verify
+  ↓
+AI: Add Completion Marker
+```
+
+## Command Purpose
+
+Autonomously fix LSP errors and linting issues:
+
+1. **Parallel Scan** (LSP + AST-grep + Linters simultaneously)
+2. **Auto Classification** (Level 1-4)
+3. **Auto Fix** (Level 1-2)
+4. **Verification**
+5. **Report**
+
+Target: $ARGUMENTS
+
+## Quick Start
+
+```bash
+# Default fix (parallel scan)
+/moai:fix
+
+# Sequential scan (for debugging)
+/moai:fix --sequential
+
+# Preview only
+/moai:fix --dry
+
+# Specific file
+/moai:fix src/auth.py
+
+# Limit fix level
+/moai:fix --level 2
+```
+
+## Command Options
+
+| Option | Alias | Description | Default |
+|--------|-------|-------------|---------|
+| `--dry` | --dry-run | Preview only | Apply |
+| `--sequential` | --seq | Sequential scan (for debugging) | Parallel |
+| `--level N` | - | Maximum fix level | 3 |
+| `--errors` | --errors-only | Fix errors only | All |
+| `--security` | --include-security | Include security issues | Exclude |
+| `--no-fmt` | --no-format | Skip formatting | Include |
+
+## Parallel Scan
+
+```bash
+# Sequential (30s)
+LSP → AST → Linter
+
+# Parallel (8s)
+LSP   ├─┐
+      ├─→ Merge (3.75x faster)
+AST   ├─┤
+     ├─┘
+Linter
+```
+
+### Parallel Scan Implementation
+
+By default, execute all diagnostic tools simultaneously for optimal performance:
+
+Step 1 - Launch Background Tasks:
+
+1. LSP Diagnostics: Use Bash tool with run_in_background set to true for LSP diagnostic command based on detected language
+2. AST-grep Scan: Use Bash tool with run_in_background set to true for ast-grep with security rules from sgconfig.yml
+3. Linter Scan: Use Bash tool with run_in_background set to true for appropriate linter (ruff, eslint, etc.)
+
+Step 2 - Collect Results:
+
+1. Use TaskOutput tool to collect results from all three background tasks
+2. Wait for all tasks to complete (timeout: 120 seconds per task)
+3. Handle partial failures gracefully - continue with available results
+
+Step 3 - Aggregate and Deduplicate:
+
+1. Parse output from each tool into structured issue list
+2. Remove duplicate issues appearing in multiple scanners
+3. Sort by severity: Critical, High, Medium, Low
+4. Group by file path for efficient fixing
+
+Step 4 - Proceed to Classification:
+
+1. Classify aggregated issues into Levels 1-4
+2. Call TodoWrite with all issues as pending items
+3. Begin fix execution
+
+Language-Specific Commands:
+
+Python: ruff check --output-format json for linter, mypy --output json for types
+TypeScript: eslint --format json for linter, tsc --noEmit for types
+Go: golangci-lint run --out-format json for linter
+Rust: cargo clippy --message-format json for linter
+
+## Auto-Fix Levels
+
+| Level | Description | Approval | Examples |
+|-------|-------------|----------|----------|
+| 1 | Immediate | Not required | import, whitespace |
+| 2 | Safe | Log only | rename var, add type |
+| 3 | Review | Required | logic, API |
+| 4 | Manual | Not allowed | security, architecture |
+
+## TODO-Obsessive Rule
+
+[HARD] TodoWrite Tool Mandatory Usage:
+
+1. Immediate Creation: When issues are discovered, call TodoWrite tool to add items with pending status
+2. Immediate Progress: Before starting work, call TodoWrite tool to change item to in_progress
+3. Immediate Completion: After completing work, call TodoWrite tool to change item to completed
+4. Prohibited: Output TODO lists as text (MUST use TodoWrite tool)
+
+WHY: Using TodoWrite tool allows users to track progress in real-time.
+
+## Output Format
+
+### Preview
+
+```markdown
+## Fix: Dry Run
+
+### Scan (0.8s, parallel)
+- LSP: 12 issues
+- AST-grep: 0 security
+- Linter: 5 issues
+
+### Level 1 (12 items)
+- src/auth.py: import, formatting
+- src/api/routes.py: import order
+- tests/test_auth.py: whitespace
+
+### Level 2 (3 items)
+- src/auth.py:45 - 'usr' → 'user'
+- src/api/routes.py:78 - add type
+- src/models.py:23 - dataclass?
+
+### Level 4 (2 items)
+- src/auth.py:67 - logic error
+- src/api/routes.py:112 - SQL injection
+
+No changes (--dry).
+```
+
+### Complete
+
+```markdown
+## Fix: Complete
+
+### Applied
+- Level 1: 12 issues
+- Level 2: 3 issues
+- Level 3: 0 issues
+
+### Evidence
+**src/auth.py:5** - Removed unused `os`, `sys`
+**src/auth.py:23** - Fixed whitespace
+**src/api/routes.py:12** - Sorted imports
+
+### Remaining (Level 4)
+1. src/auth.py:67 - logic error
+2. src/api/routes.py:112 - SQL injection
+
+### Next
+/moai:loop  # Continue with loop
+```
+
+## Quick Reference
+
+```bash
+# Fix (default parallel)
+/moai:fix
+
+# Sequential scan
+/moai:fix --sequential
+
+# Preview only
+/moai:fix --dry
+
+# Errors only
+/moai:fix --errors
+
+# Specific file
+/moai:fix src/auth.py
+```
+
+---
+
+## EXECUTION DIRECTIVE
+
+1. Parse $ARGUMENTS (extract --sequential, --dry, --level, --errors, --security flags)
+
+2. Detect project language from indicator files (pyproject.toml, package.json, go.mod, Cargo.toml)
+
+3. Execute diagnostic scan:
+
+   IF --sequential flag is specified:
+
+   3a. Run LSP diagnostics, then AST-grep, then Linter sequentially
+
+   ELSE (default parallel mode):
+
+   3b. Launch all three diagnostic tools in parallel using Bash with run_in_background:
+       - Task 1: LSP diagnostics for detected language
+       - Task 2: AST-grep scan with sgconfig.yml rules
+       - Task 3: Linter for detected language
+
+   3c. Collect results using TaskOutput for each background task
+
+   3d. Aggregate results, remove duplicates, sort by severity
+
+4. Classify aggregated issues into Level 1-4
+
+5. [HARD] Call TodoWrite tool to add all discovered issues with pending status
+
+6. IF --dry flag: Display preview and exit
+
+7. [HARD] Before each fix, call TodoWrite to change item to in_progress
+
+8. Execute Level 1-2 fixes automatically
+
+9. [HARD] After each fix completion, call TodoWrite to change item to completed
+
+10. Request approval for Level 3 fixes via AskUserQuestion
+
+11. Verify fixes by re-running affected diagnostics
+
+12. Report with evidence (file:line changes made)
+
+---
+
+Version: 2.1.0
+Last Updated: 2026-01-11
+Core: Agentic AI Auto-Fix

moai_adk/templates/.claude/commands/moai/loop.md

@@ -0,0 +1,363 @@
+---
+description: "Agentic autonomous loop - Auto-fix until completion marker"
+argument-hint: "[--max N] [--auto] [--seq] | --resume snapshot"
+type: utility
+allowed-tools: Task, AskUserQuestion, TodoWrite, Bash, Read, Write, Edit, Glob, Grep
+model: inherit
+---
+
+## Pre-execution Context
+
+!git status --porcelain
+!git diff --name-only HEAD
+
+## Essential Files
+
+@.moai/config/sections/ralph.yaml
+
+---
+
+# /moai:loop - Agentic Autonomous Loop
+
+## Core Principle: Fully Autonomous Iterative Fixing
+
+AI autonomously finds issues, fixes them, and repeats until completion.
+
+```
+START: Issue Detection
+  ↓
+AI: Fix → Verify → Repeat
+  ↓
+AI: Add Completion Marker
+  ↓
+<moai>DONE</moai>
+```
+
+## Command Purpose
+
+Autonomously fix LSP errors, test failures, and coverage issues:
+
+1. **Parallel Diagnostics** (LSP + AST-grep + Tests simultaneously)
+2. **Auto TODO Generation**
+3. **Autonomous Fixing** (Level 1-3)
+4. **Iterative Verification**
+5. **Completion Marker Detection**
+
+Arguments: $ARGUMENTS
+
+## Quick Start
+
+```bash
+# Default autonomous loop (parallel diagnostics)
+/moai:loop
+
+# Maximum 50 iterations
+/moai:loop --max 50
+
+# Sequential diagnostics + auto fix
+/moai:loop --sequential --auto
+
+# Restore from snapshot
+/moai:loop --resume latest
+```
+
+## Command Options
+
+| Option | Alias | Description | Default |
+|--------|-------|-------------|---------|
+| `--max N` | --max-iterations | Maximum iteration count | 100 |
+| `--auto` | --auto-fix | Enable auto-fix | Level 1 |
+| `--sequential` | --seq | Sequential diagnostics (for debugging) | Parallel |
+| `--errors` | --errors-only | Fix errors only | All |
+| `--coverage` | --include-coverage | Include coverage | 85% |
+| `--resume ID` | --resume-from | Restore from snapshot | - |
+
+## Completion Promise
+
+AI adds a marker when all work is complete:
+
+```markdown
+## Loop Complete
+
+Resolved 5 errors, 3 warnings in 7 iterations. <moai>DONE</moai>
+```
+
+**Marker Types**:
+- `<moai>DONE</moai>` - Task complete
+- `<moai>COMPLETE</moai>` - Full completion
+- `<moai:done />` - XML format
+
+Without marker, loop continues.
+
+## Autonomous Loop Flow
+
+```
+START: /moai:loop
+
+PARALLEL Diagnostics (default)
+  ├── LSP: Errors/Warnings
+  ├── AST-grep: Security
+  ├── Tests: Test results
+  └── Coverage: Coverage metrics
+  ↓
+Integrated Results
+  ↓
+Completion Marker Detected?
+  ├── YES → COMPLETE
+  ↓
+Conditions Met?
+  ├── YES → "Add marker or continue?"
+  ↓
+TODO Generation (immediate)
+  ↓
+Fix Execution (autonomous)
+  ├── Level 1: Immediate fix (import, formatting)
+  ├── Level 2: Safe fix (rename, type)
+  └── Level 3: Approval required (logic, api)
+  ↓
+Verification
+  ↓
+Max reached? → STOP
+  ↓
+Repeat
+```
+
+## Parallel Diagnostics
+
+```bash
+# Sequential (--sequential)
+LSP → AST-grep → Tests → Coverage
+Total 30s
+
+# Parallel (default)
+LSP ├─┐
+     ├─→ Merge → 8s (3.75x faster)
+AST ├─┤
+    ├─┘
+Tests ┤
+       └─→ 3-4x speed improvement
+Coverage
+```
+
+### Parallel Diagnostics Implementation
+
+By default, execute all four diagnostic tools simultaneously each iteration for optimal performance:
+
+Step 1 - Launch Background Tasks:
+
+1. LSP Diagnostics: Use Bash tool with run_in_background set to true for language-specific LSP diagnostic command
+2. AST-grep Scan: Use Bash tool with run_in_background set to true for ast-grep with security and quality rules
+3. Test Runner: Use Bash tool with run_in_background set to true for language-specific test framework (pytest, jest, go test)
+4. Coverage Check: Use Bash tool with run_in_background set to true for coverage measurement (coverage.py, c8, go test -cover)
+
+Step 2 - Collect Results:
+
+1. Use TaskOutput tool to collect results from all four background tasks
+2. Wait for all tasks to complete (timeout: 120 seconds per task)
+3. Handle partial failures gracefully - continue with available results
+
+Step 3 - Aggregate Diagnostics:
+
+1. Parse output from each tool into structured diagnostic report
+2. Calculate metrics: error count, warning count, test pass rate, coverage percentage
+3. Detect completion conditions: zero errors AND tests passing AND coverage meets threshold
+
+Step 4 - Completion Check:
+
+1. Check for completion marker in previous iteration response
+2. If marker found: Exit loop with success
+3. If all conditions met and no new issues: Prompt for completion marker or continue
+
+Language-Specific Commands:
+
+Python: pytest --tb=short for tests, coverage run -m pytest for coverage
+TypeScript: npm test or jest for tests, npm run coverage for coverage
+Go: go test ./... for tests, go test -cover ./... for coverage
+Rust: cargo test for tests, cargo tarpaulin for coverage
+
+## TODO-Obsessive Rule
+
+[HARD] TodoWrite Tool Mandatory Usage:
+
+Call TodoWrite tool on every iteration to manage tasks:
+
+1. Immediate Creation: When issues are discovered, call TodoWrite to add items with pending status
+2. Immediate Progress: Before starting work, call TodoWrite to change item to in_progress
+3. Immediate Completion: After completing work, call TodoWrite to change item to completed
+4. Prohibited: Output TODO lists as text (MUST use TodoWrite tool)
+
+WHY: Using TodoWrite tool allows users to track progress in real-time.
+
+## Auto-Fix Levels
+
+| Level | Description | Approval | Examples |
+|-------|-------------|----------|----------|
+| 1 | Immediate fix | Not required | import sort, whitespace |
+| 2 | Safe fix | Log only | rename var, add type |
+| 3 | Approval needed | Required | logic change, API modify |
+| 4 | Manual required | Not allowed | security, architecture |
+
+## Output Format
+
+### Running
+
+```markdown
+## Loop: 3/100 (parallel)
+
+### Diagnostics (0.8s)
+- LSP: 2 errors, 5 warnings
+- AST-grep: 0 security issues
+- Tests: 23/25 passing
+- Coverage: 82%
+
+### TODO
+1. [x] src/auth.py:45 - undefined 'jwt_token'
+2. [in_progress] src/auth.py:67 - missing return
+3. [ ] tests/test_auth.py:12 - unused 'result'
+
+Fixing...
+```
+
+### Complete (Marker Detected)
+
+```markdown
+## Loop: COMPLETE
+
+### Summary
+- Iterations: 7
+- Errors fixed: 5
+- Warnings fixed: 3
+- Tests: 25/25 passing
+- Coverage: 87%
+
+### Files Modified
+- src/auth.py (7 fixes)
+- tests/test_auth.py (3 fixes)
+- src/api/routes.py (2 fixes)
+
+<moai>DONE</moai>
+```
+
+### Max Iterations Reached
+
+```markdown
+## Loop: MAX REACHED (100/100)
+
+### Remaining
+- Errors: 1
+- Warnings: 2
+
+### Options
+1. /moai:loop --max 200  # Continue
+2. /moai:fix             # Single run
+3. Manual fix
+```
+
+## State & Snapshot
+
+```bash
+# State storage
+.moai/cache/.moai_loop_state.json
+
+# Snapshots
+.moai/cache/ralph-snapshots/
+├── iteration-001.json
+├── iteration-002.json
+└── latest.json
+
+# Restore
+/moai:loop --resume iteration-002
+/moai:loop --resume latest
+```
+
+## Cancellation
+
+```bash
+# Cancel (save snapshot)
+/moai:cancel-loop --snapshot
+
+# Force cancel
+/moai:cancel-loop --force
+```
+
+## Quick Reference
+
+```bash
+# Autonomous loop (default parallel)
+/moai:loop
+
+# Sequential + auto
+/moai:loop --sequential --auto
+
+# Max iterations
+/moai:loop --max 50
+
+# Errors only
+/moai:loop --errors
+
+# Restore
+/moai:loop --resume latest
+```
+
+---
+
+## EXECUTION DIRECTIVE
+
+1. Parse $ARGUMENTS (extract --max, --auto, --sequential, --errors, --coverage, --resume flags)
+
+2. IF --resume flag: Load state from specified snapshot and continue from saved iteration
+
+3. Detect project language from indicator files (pyproject.toml, package.json, go.mod, Cargo.toml)
+
+4. Initialize iteration counter to 0
+
+5. LOOP START (while iteration less than max):
+
+   5a. Check for completion marker in previous response:
+       - If DONE, COMPLETE, or done marker found: Exit loop with success
+
+   5b. Execute diagnostic scan:
+
+       IF --sequential flag is specified:
+
+       - Run LSP, then AST-grep, then Tests, then Coverage sequentially
+
+       ELSE (default parallel mode):
+
+       - Launch all four diagnostic tools in parallel using Bash with run_in_background:
+         - Task 1: LSP diagnostics for detected language
+         - Task 2: AST-grep scan with sgconfig.yml rules
+         - Task 3: Test runner for detected language
+         - Task 4: Coverage measurement for detected language
+
+       - Collect results using TaskOutput for each background task
+
+       - Aggregate results into unified diagnostic report
+
+   5c. Check completion conditions:
+       - Zero errors AND all tests passing AND coverage meets threshold
+       - If all conditions met: Prompt user to add completion marker or continue
+
+   5d. [HARD] Call TodoWrite tool to add newly discovered issues with pending status
+
+   5e. [HARD] Before each fix, call TodoWrite to change item to in_progress
+
+   5f. Execute fixes based on --auto level (Level 1-3)
+
+   5g. [HARD] After each fix completion, call TodoWrite to change item to completed
+
+   5h. Save iteration snapshot to .moai/cache/ralph-snapshots/
+
+   5i. Increment iteration counter
+
+6. LOOP END
+
+7. IF max iterations reached without completion: Display remaining issues and options
+
+8. Report final summary with evidence
+
+---
+
+Version: 2.1.0
+Last Updated: 2026-01-11
+Core: Agentic AI Autonomous Loop