@sylphx/flow 1.4.6 → 1.4.8

package/assets/slash-commands/polish.md

@@ -0,0 +1,88 @@
+---
+name: polish
+description: Polish project presentation - docs, README, packaging, metadata
+agent: writer
+---
+
+# Polish Project
+
+Make project professional, welcoming, and well-documented.
+
+## Scope
+
+**README:**
+- Clear project description (what, why, how)
+- Installation instructions (tested)
+- Quick start example (copy-paste ready)
+- Key features (3-5 bullet points)
+- API overview
+- Links to full docs
+- Badges (build status, coverage, version, license)
+- Contributing guidelines link
+- License
+
+**Documentation:**
+- API reference (all public functions)
+- Usage examples (common scenarios)
+- Tutorials (step-by-step guides)
+- Architecture overview
+- Troubleshooting guide
+- FAQ
+- Migration guides (if applicable)
+
+**Code Comments:**
+- JSDoc for public APIs
+- Complex logic explained (WHY not WHAT)
+- Non-obvious decisions documented
+- Examples in comments where helpful
+
+**Packaging (package.json):**
+- Accurate description
+- Relevant keywords (10-15)
+- Repository URL
+- Homepage URL
+- Bug tracker URL
+- Author info
+- License
+- Engines specified
+- Files field (only ship necessary)
+
+**GitHub Metadata:**
+- Topics/tags (10-20 relevant tags)
+- Description (concise, searchable)
+- Website URL
+- Social preview image (if applicable)
+
+**Changelog:**
+- Update CHANGELOG.md
+- Clear version history
+- Breaking changes highlighted
+- Migration instructions
+
+**Contributing:**
+- CONTRIBUTING.md
+- Code of conduct
+- Development setup
+- Testing guidelines
+- PR process
+
+## Execution
+
+1. **Audit** what exists vs what's missing
+2. **Update** outdated content
+3. **Create** missing documentation
+4. **Test** all code examples
+5. **Verify** all links work
+6. **Ensure** consistency across docs
+
+## Quality Checks
+
+- [ ] README explains project in <5 min read
+- [ ] New user can get started in <10 min
+- [ ] All examples tested and work
+- [ ] No broken links
+- [ ] Search-friendly keywords
+- [ ] Professional presentation
+- [ ] Beginner-friendly
+
+Report: What was added/updated, coverage improved.

package/assets/slash-commands/quality.md

@@ -0,0 +1,182 @@
+---
+name: quality
+description: Improve test coverage, fix tests, optimize performance, reduce bundle size
+agent: coder
+---
+
+# Quality Assurance
+
+Maximize quality metrics: tests, coverage, performance, bundle size.
+
+## Scope
+
+**Testing:**
+- Fix failing tests
+- Add missing tests (.test.ts for all modules)
+- Improve coverage (critical paths 100%, business logic 80%+)
+- Test edge cases
+- Test error paths
+- Integration tests
+- E2E tests (if applicable)
+
+**Benchmarking:**
+- Add benchmarks (.bench.ts for critical functions)
+- Measure performance
+- Identify regressions
+- Optimize slow operations
+
+**Performance:**
+- Profile hot paths
+- Optimize algorithms (reduce complexity)
+- Fix memory leaks
+- Reduce allocations
+- Cache expensive operations
+- Lazy load where possible
+
+**Bundle Size:**
+- Analyze bundle composition
+- Remove unused dependencies
+- Tree-shake effectively
+- Code split strategically
+- Compress assets
+- Use dynamic imports
+
+**Code Quality:**
+- Fix lint errors/warnings
+- Improve type safety (no `any`)
+- Reduce complexity
+- Improve maintainability
+- Follow code standards
+
+**Security:**
+- Fix vulnerabilities
+- Update dependencies
+- Validate inputs
+- Sanitize outputs
+- Secure defaults
+
+## Execution
+
+### 1. Test Coverage
+
+```bash
+# Run tests with coverage
+npm run test:coverage
+
+# Identify gaps
+# Add tests for uncovered code
+# Focus on critical paths first
+```
+
+**Priority:**
+- Critical business logic (100%)
+- Error handling (100%)
+- Edge cases (90%)
+- Happy paths (100%)
+- Integration points (80%)
+
+### 2. Benchmarking
+
+```bash
+# Run benchmarks
+npm run bench
+
+# Compare against baseline
+# Identify regressions
+# Optimize bottlenecks
+```
+
+**Add benchmarks for:**
+- Algorithm complexity (O(n) vs O(n²))
+- Database queries
+- API calls
+- Data processing
+- Rendering (if UI)
+
+### 3. Performance Profiling
+
+```bash
+# Profile application
+node --inspect ...
+# Or use Clinic.js, 0x, etc.
+
+# Identify bottlenecks
+# Optimize hot paths
+# Measure improvements
+```
+
+**Check:**
+- CPU usage
+- Memory usage
+- I/O operations
+- Network calls
+- Rendering time
+
+### 4. Bundle Analysis
+
+```bash
+# Analyze bundle
+npm run build -- --analyze
+
+# Check size
+ls -lh dist/
+
+# Identify large dependencies
+# Remove unnecessary code
+```
+
+**Optimize:**
+- Remove unused dependencies
+- Use smaller alternatives
+- Dynamic imports for large modules
+- Tree-shake effectively
+- Minify properly
+
+### 5. Quality Metrics
+
+**Track:**
+- Test coverage: `npm run test:coverage`
+- Bundle size: `ls -lh dist/`
+- Performance: `npm run bench`
+- Security: `npm audit`
+- Type coverage: TypeScript strict mode
+- Lint score: `npm run lint`
+
+## Targets
+
+**Tests:**
+- Coverage: ≥80% (business logic ≥90%)
+- All critical paths: 100%
+- Build time: <30s
+- Test time: <10s
+
+**Performance:**
+- Page load: <3s
+- API response: <200ms
+- Time to interactive: <5s
+- Bundle size: <100KB (gzipped)
+
+**Quality:**
+- Zero lint errors
+- Zero `any` types (unless justified)
+- Zero security vulnerabilities (high/critical)
+- Complexity score: <10 per function
+
+## Commit Strategy
+
+Atomic commits per improvement:
+- `test(auth): add tests for token validation`
+- `perf(db): optimize user query with batch loading`
+- `build: reduce bundle size by 40% with code splitting`
+
+## Exit Criteria
+
+- [ ] All tests pass
+- [ ] Coverage meets targets
+- [ ] Benchmarks added for critical functions
+- [ ] Performance optimized
+- [ ] Bundle size reduced
+- [ ] No security vulnerabilities
+- [ ] Quality metrics improved
+
+Report: Coverage %, bundle size reduction, performance gains, benchmarks added.

package/assets/slash-commands/release.md

@@ -0,0 +1,104 @@
+---
+name: release
+description: Publish new version and monitor release process
+agent: coder
+---
+
+# Release & Publish
+
+Prepare, publish, and monitor package release.
+
+## Pre-Release Checks
+
+**Quality Gates:**
+- [ ] All tests pass
+- [ ] No lint errors
+- [ ] Build successful
+- [ ] No security vulnerabilities
+- [ ] Dependencies up to date
+- [ ] CHANGELOG updated
+- [ ] README accurate
+- [ ] Breaking changes documented
+
+**Version Decision:**
+- Breaking changes → `major`
+- New features → `minor` (default)
+- Bug fixes → `patch`
+
+## Release Process
+
+### For TypeScript/JavaScript Projects
+
+1. **Create Changeset:**
+   ```bash
+   bunx changeset
+   ```
+   - Select package
+   - Choose version bump type
+   - Write clear summary
+
+2. **Version Bump:**
+   ```bash
+   bunx changeset version
+   ```
+   - Updates package.json
+   - Updates CHANGELOG.md
+   - Consumes changeset
+
+3. **Commit & Push:**
+   ```bash
+   git add -A
+   git commit -m "chore(release): <package>@<version>"
+   git push
+   ```
+
+4. **Monitor CI:**
+   ```bash
+   gh run list --workflow=release --limit 5
+   gh run watch <run-id>
+   ```
+
+5. **Verify Publication:**
+   ```bash
+   npm view <package>@<version>
+   ```
+
+### For Other Projects
+
+1. Update version in manifest (package.json, setup.py, etc.)
+2. Update CHANGELOG
+3. Create git tag
+4. Push tag to trigger release
+5. Monitor CI/CD
+
+## Post-Release
+
+- [ ] Verify package published
+- [ ] Test installation: `npm install <package>@latest`
+- [ ] Create GitHub release with notes
+- [ ] Announce (if public package)
+- [ ] Close related issues/PRs
+
+## Troubleshooting
+
+**CI fails on install:**
+- Update lockfile locally: `bun install`
+- Commit and push
+
+**Tests fail in CI:**
+- Run tests locally: `npm test`
+- Fix issues, commit, push
+
+**Build fails:**
+- Check build locally: `npm run build`
+- Fix errors, commit, push
+
+## Exit Criteria
+
+- [ ] Package published successfully
+- [ ] CI workflow completed
+- [ ] GitHub release created
+- [ ] Version verified on registry
+- [ ] Installation tested
+
+Report: Version number, publish time, registry URL.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sylphx/flow",
-  "version": "1.4.6",
+  "version": "1.4.8",
   "description": "AI-powered development workflow automation with autonomous loop mode and smart configuration",
   "type": "module",
   "bin": {
@@ -15,7 +15,7 @@
     "test": "vitest run",
     "test:watch": "vitest",
     "type-check": "tsc --noEmit",
-    "prepublishOnly": "rm -rf assets && cp -r ../../assets assets"
+    "prepublishOnly": "echo 'Using assets from packages/flow/assets'"
   },
   "dependencies": {
     "commander": "^14.0.2",

package/src/commands/init-core.ts

@@ -168,11 +168,6 @@ export async function installComponents(
   if (target.setupAgents && options.agents !== false) {
     const agentSpinner = quiet ? null : ora({ text: 'Installing agents', color: 'cyan' }).start();
     try {
-      // DEBUG: Log force flag
-      if (!quiet && options.clear) {
-        console.log(`[DEBUG] Installing agents with force=${options.clear}`);
-      }
-
       const agentResult = await target.setupAgents(process.cwd(), { ...options, quiet: true, force: options.clear });
       result.installed.agents = agentResult.count;
 
@@ -252,11 +247,6 @@ export async function installComponents(
       color: 'cyan',
     }).start();
     try {
-      // DEBUG: Log force flag
-      if (!quiet && options.clear) {
-        console.log(`[DEBUG] Installing slash commands with force=${options.clear}`);
-      }
-
       const commandsResult = await target.setupSlashCommands(process.cwd(), { ...options, quiet: true, force: options.clear });
       result.installed.slashCommands = commandsResult.count;
 

package/src/core/installers/file-installer.ts

@@ -124,36 +124,9 @@ export async function installToDirectory(
     let content = fs.readFileSync(sourcePath, 'utf8');
     content = await transform(content, file);
 
-    // DEBUG: Log installation details (always show in force mode)
-    if (options.force) {
-      console.log(
-        `[DEBUG] Installing ${file} - force=${options.force}, exists=${!!localInfo}, path=${targetPath}`
-      );
-    }
-
     // Force mode: always overwrite without checking
     if (options.force) {
-      const contentPreview = content.substring(0, 100).replace(/\n/g, ' ');
-      console.log(`[DEBUG] Writing content (first 100 chars): ${contentPreview}...`);
-
       fs.writeFileSync(targetPath, content, 'utf8');
-
-      // DEBUG: Verify write and read back
-      const written = fs.existsSync(targetPath);
-      if (!written) {
-        console.warn(`[DEBUG] ⚠ Failed to write: ${targetPath}`);
-      } else {
-        const readBack = fs.readFileSync(targetPath, 'utf8');
-        const readBackPreview = readBack.substring(0, 100).replace(/\n/g, ' ');
-        console.log(`[DEBUG] Read back (first 100 chars): ${readBackPreview}...`);
-
-        if (readBack !== content) {
-          console.warn(`[DEBUG] ⚠ Content mismatch! Written ${content.length} bytes, read ${readBack.length} bytes`);
-        } else {
-          console.log(`[DEBUG] ✓ Verified write: ${targetPath}`);
-        }
-      }
-
       results.push({
         file,
         status: localInfo ? 'updated' : 'added',

package/src/utils/sync-utils.ts

@@ -388,25 +388,12 @@ export async function executeSyncDelete(
   // Delete Flow templates
   for (const file of flowFiles) {
     try {
-      const existsBefore = fs.existsSync(file);
-      if (!existsBefore) {
-        console.log(chalk.dim(`  ⊘ Already deleted: ${path.basename(file)}`));
-        continue;
-      }
-
       await fs.promises.unlink(file);
-
-      // Verify deletion
-      const existsAfter = fs.existsSync(file);
-      if (existsAfter) {
-        console.warn(chalk.yellow(`  ⚠ File still exists after deletion: ${path.basename(file)}`));
-      } else {
-        console.log(chalk.dim(`  ✓ Deleted: ${path.basename(file)}`));
-        templatesDeleted++;
-      }
+      console.log(chalk.dim(`  ✓ Deleted: ${path.basename(file)}`));
+      templatesDeleted++;
     } catch (error) {
       if ((error as NodeJS.ErrnoException).code !== 'ENOENT') {
-        console.warn(chalk.yellow(`  ⚠ Failed to delete: ${path.basename(file)} - ${error}`));
+        console.warn(chalk.yellow(`  ⚠ Failed to delete: ${path.basename(file)}`));
       }
     }
   }

package/assets/slash-commands/commit.md

@@ -1,23 +0,0 @@
----
-description: Create a git commit with meaningful message
----
-
-# Create Git Commit
-
-## Context
-
-- Current git status: !`git status`
-- Current git diff (staged and unstaged changes): !`git diff HEAD`
-- Current branch: !`git branch --show-current`
-- Recent commits: !`git log --oneline -10`
-
-## Your Task
-
-Based on the above changes, create a single git commit with a meaningful commit message that:
-
-1. Follows conventional commits format: `type(scope): description`
-2. Accurately describes what changed and why
-3. Includes any breaking changes or important notes
-4. Uses present tense ("add" not "added")
-
-After creating the commit, show the commit message for review.

package/assets/slash-commands/context.md

@@ -1,112 +0,0 @@
----
-description: Display current context window usage and token breakdown
----
-
-# Context Window Usage
-
-Display detailed information about the current context window usage, including token counts for different components.
-
-## Your Task
-
-Analyze and display the context window usage with the following sections:
-
-### 1. Model Information
-Show the current model being used and its token limits.
-
-### 2. Visual Token Usage Bar
-Create a visual bar chart (10 blocks wide) showing token usage breakdown using these Unicode characters:
-- ⛁ (filled) - Used tokens
-- ⛀ (half-filled) - Partially used blocks
-- ⛶ (empty) - Reserved/System tokens
-- ⛝ (light) - Free space/buffer
-
-### 3. Token Breakdown
-
-Calculate and display tokens for each category:
-
-#### System Prompt
-- Count tokens in the system prompt
-- Show: `⛁ System prompt: X.Xk tokens (X.X%)`
-
-#### System Tools
-- Count tokens for all built-in tool definitions (filesystem, shell, search, interaction tools)
-- Show: `⛁ System tools: X.Xk tokens (X.X%)`
-
-#### MCP Tools
-- Count tokens for all MCP tool definitions
-- List each MCP tool with its token count
-- Show: `⛁ MCP tools: X.Xk tokens (X.X%)`
-
-#### Custom Agents
-- Count tokens for custom agent definitions (if any)
-- List each agent with token count
-- Show: `⛁ Custom agents: X tokens (X.X%)`
-
-#### Messages
-- Count tokens in all messages in the current session
-- Show: `⛁ Messages: X tokens (X.X%)`
-
-#### Free Space
-- Calculate remaining available tokens
-- Show: `⛶ Free space: XXXk (XX.X%)`
-
-#### Autocompact Buffer
-- Calculate reserved buffer space (typically 22.5% of total)
-- Show: `⛝ Autocompact buffer: XX.Xk tokens (XX.X%)`
-
-### 4. Detailed Listings
-
-Show expandable sections with details:
-
-```
-MCP tools · /mcp
-└ mcp__tool_name (server-name): XXX tokens
-└ ...
-
-Custom agents · /agents
-└ agent-name (Project): XX tokens
-└ ...
-
-SlashCommand Tool · X commands
-└ Total: XXX tokens
-```
-
-## Display Format
-
-Use this exact format for the output:
-
-```
-Context Usage
-⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛀ ⛁ ⛁   model-name · XXk/XXXk tokens (XX%)
-⛀ ⛀ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶
-⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ System prompt: X.Xk tokens (X.X%)
-⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ System tools: XX.Xk tokens (X.X%)
-⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ MCP tools: X.Xk tokens (X.X%)
-⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ Custom agents: XX tokens (X.X%)
-⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ Messages: XXX tokens (X.X%)
-⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛝ ⛝ ⛝   ⛶ Free space: XXXk (XX.X%)
-⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝   ⛝ Autocompact buffer: XX.Xk tokens (XX.X%)
-⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝
-
-MCP tools · /mcp
-└ tool_name (server-name): XXX tokens
-└ ...
-
-Custom agents · /agents
-└ agent-name (Project): XX tokens
-└ ...
-
-SlashCommand Tool · X commands
-└ Total: XXX tokens
-```
-
-## Implementation Notes
-
-1. Use the `countTokens()` utility from `src/utils/token-counter.ts` with the current session model name
-2. Get current session from app store to access model name and messages
-3. Get system prompt from `src/core/ai-sdk.ts` (SYSTEM_PROMPT constant)
-4. Get tool definitions from `src/tools/registry.ts` (getAISDKTools())
-5. Calculate percentages based on the model's max token limit (e.g., 200k for Claude Sonnet 4.5)
-6. Round token counts appropriately (show decimals for k, no decimals for raw numbers)
-7. Ensure the bar chart accurately represents the proportions
-8. Use proper indentation and alignment for readability

package/assets/slash-commands/explain.md

@@ -1,35 +0,0 @@
----
-description: Explain code in detail
----
-
-# Explain Code
-
-## Context
-
-$ARGUMENTS
-
-## Your Task
-
-Provide a comprehensive explanation of the code above (or at the specified location) that includes:
-
-1. **Overview**
-   - What does this code do?
-   - What problem does it solve?
-
-2. **How It Works**
-   - Step-by-step breakdown of the logic
-   - Key algorithms or patterns used
-   - Important design decisions
-
-3. **Components**
-   - Main functions/classes/modules
-   - Their roles and responsibilities
-   - How they interact
-
-4. **Important Details**
-   - Edge cases handled
-   - Performance considerations
-   - Security implications
-   - Dependencies and requirements
-
-Use clear language and provide examples where helpful.

package/assets/slash-commands/review.md

@@ -1,39 +0,0 @@
----
-description: Review code for quality, security, and best practices
----
-
-# Code Review
-
-## Context
-
-$ARGUMENTS
-
-## Your Task
-
-Review the code above (or at the specified location) and provide feedback on:
-
-1. **Code Quality**
-   - Readability and maintainability
-   - Code organization and structure
-   - Naming conventions
-   - Comments and documentation
-
-2. **Security**
-   - Potential vulnerabilities
-   - Input validation
-   - Authentication/authorization issues
-   - Data exposure risks
-
-3. **Performance**
-   - Algorithmic efficiency
-   - Resource usage
-   - Potential bottlenecks
-   - Scalability concerns
-
-4. **Best Practices**
-   - Language-specific idioms
-   - Design patterns
-   - Error handling
-   - Testing coverage
-
-Provide specific, actionable suggestions for improvement.