- Create SDKFlowDiagram component with animated D3 graphics
- Add flowing particle animations along connection paths
- Add hover interactions with tooltips for each node
- Add entrance animations with staggered timing
- Add subtle glow effects and shadows
- Responsive design that adapts to screen width
- Sleek minimal black and white aesthetic with depth effects
- Create @tpmjs/registrySearch package for searching tool registry
- Create @tpmjs/registryExecute package for executing tools via sandbox
- Support self-hosted registries via TPMJS_API_URL and TPMJS_EXECUTOR_URL env vars
- Add /sdk documentation page with usage examples and architecture
- Add SDK link to navigation menu
- Include design doc for registry SDK architecture
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create @tpmjs/markdown-formatter with 2 tools:
- markdownToPlainText: Convert markdown to plain text
- formatMarkdownTable: Format and align markdown tables
- Includes defensive parameter validation
- Uses AI SDK v6 beta with Zod 4 schemas
- Published v0.2.0 to npm
Testing the full end-to-end workflow:
- Package creation following generator patterns
- Changesets for version management
- npm publishing
- TPMJS registry auto-discovery
- Interactive CLI generator for scaffolding TPMJS tool packages
- Generates packages with minimum 2 tools (ideally 2-3)
- Zod 4 schemas - uses Zod directly (not jsonSchema wrapper)
- One file per tool in src/tools/<toolName>.ts
- TPMJS validated against official schemas from @tpmjs/types
- Complete package generation ready to publish to npm
- Works both standalone and in monorepo packages/ folders
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create ToolHealthBadge component in @tpmjs/ui for broken tool indicator
- Create ToolHealthBanner component in @tpmjs/ui for detailed health warnings
- Integrate both components into playground ToolsSidebar:
- Badge shows in tool cards in left sidebar
- Banner shows in tool detail modal
- Update search-registry to include health fields in API responses
- Add package.json exports for new health components
These components provide consistent UI for displaying broken tool status
across the application (tool search, tool detail pages, playground).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update @ai-sdk/react to v3.0.0-beta.131 for compatibility with AI SDK v6
- Fix tool execute method calls with type assertions in API routes
- Update chat components to use UIMessage types from AI SDK
- Move body option into DefaultChatTransport constructor
- Remove deprecated onResponse option from useChat hook
- Remove unused isCoreTool type guard function
- Fix Button variant from 'primary' to 'default'
Resolves all TypeScript compilation errors and build passes successfully.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements a complete dynamic tool loading system that allows the playground to discover and load tools from the TPMJS registry at runtime.
**Architecture:**
- Search tool package (@tpmjs/search-registry) - Searches registry for tools
- Search API endpoint (/api/tools/search) - Text-based search with scoring
- Pre-flight tool loading - Automatically searches and loads tools on every message
- Railway executor service (Deno) - Loads tools from esm.sh via HTTP imports
- Dynamic tool loader - Calls Railway to load and execute tools remotely
**Key Components:**
1. Railway Executor (apps/railway-executor/)
- Deno-based service that natively supports HTTP imports
- Endpoints: /load-and-describe, /execute-tool, /cache/stats, /cache/clear
- Deploys to Railway with deno run --allow-net --allow-env server.ts
2. Search Tool Package (packages/tools/search-registry/)
- AI SDK v6 tool for searching TPMJS registry
- Uses jsonSchema + inputSchema pattern
- Searches /api/tools/search endpoint
3. Search API (apps/web/src/app/api/tools/search/)
- Text-based search with composite scoring
- Scores: text relevance + quality boost + download boost
- Returns tool metadata with importUrl for dynamic loading
4. Dynamic Tool Loader (apps/playground/src/lib/dynamic-tool-loader.ts)
- Calls Railway service to load tools from esm.sh
- Creates tool wrappers that execute remotely
- Process-level module cache + per-conversation tracking
5. Pre-flight Loading (apps/playground/src/app/api/chat/route.ts)
- Automatically searches for tools on every user message
- Loads top 5 matching tools before agent processes request
- Merges with static tools for seamless experience
**Technical Decisions:**
- Deno over Node.js: Native HTTP import support without flags
- Remote execution: Tools run in Railway sandbox, not Vercel
- Pre-flight loading: Better UX than two-turn search pattern
- Text search: BM25 had dependency issues, simple scoring works well
**Environment Variables:**
- RAILWAY_SERVICE_URL: https://endearing-commitment-production.up.railway.app🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
BREAKING CHANGE: Complete refactoring from single-tool to multi-tool package support
Database Schema:
- Split Tool model into Package (1) and Tool (many) with one-to-many relationship
- Package stores npm metadata and package-level tpmjs fields (category, env, frameworks, tier)
- Tool stores individual tool exports with tool-level metadata (exportName, description, parameters, returns, aiAgent)
- Unique constraint on (packageId, exportName) to prevent duplicate tools
- Cascade deletes when packages are removed
Type System:
- Updated tpmjs field schema to support tools array
- Each tool has exportName, description, parameters, returns, aiAgent
- Package-level fields: category, env, frameworks shared across all tools
- Backward compatible with legacy single-tool format (auto-migrates to exportName: "default")
API Updates:
- Updated all /api/tools routes to query Tool model with Package relations
- Updated /api/tools/[slug] to accept package/export path segments
- Updated tool-executor-agent to use actual exportName instead of hardcoded "default"
- Updated metrics sync to calculate quality scores per Tool
Frontend Updates:
- Updated tool search page to display exportName as primary heading
- Updated tool detail pages to show package name as secondary info
- Removed tag-based filtering (tags moved to package level)
Manual Tool Registry:
- Added manual-tools.ts with 23 curated tools from major providers
- Created sync-manual-tools.ts script to sync manual tools to database
- Added MANUAL_TOOLS.md documentation for manual tool system
- Added GitHub workflow for automated daily sync
- Includes tools from: Vercel, Exa, Firecrawl, AWS Bedrock, Perplexity, Tavily, Superagent, Valyu
Playground Updates:
- Updated tool loader to load multiple tools per package
- Added sanitizeToolName for OpenAI API compatibility
Sync System Updates:
- Updated changes feed sync to handle multi-tool packages
- Updated keyword sync to upsert multiple tools per package
- Added orphaned tool deletion when tools removed from package.json
Migration Strategy:
- Database uses same Neon instance for dev and prod
- Schema updated via prisma db push (no migration files yet)
- All data repopulates from npm via sync system
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create new Next.js app at apps/playground for testing TPMJS tools
- Implement AI SDK v6 patterns with DefaultChatTransport and UIMessage format
- Create template tool package at packages/tools/hello with hello-world and hello-name tools
- Use tool() and jsonSchema() helpers to avoid Zod 4 conversion issues with OpenAI
- Add static tool loading system with switch statement (Next.js/webpack compatible)
- Implement chat interface with tool call visualization showing inputs/outputs
- Support multi-step tool execution with stepCountIs(5)
- Stream responses with toUIMessageStreamResponse() for full tool support
- Add sidebar showing available tools (static list)
- Use parts-based message rendering for text and tool calls
- Integrate firecrawl-aisdk tools (scrape, crawl, search)
- Add theme toggle in header (defaults to light mode)
- Fix responsive layout with max-width for message bubbles
- Use biome-ignore comments for legitimate any types in tool loading
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Problem:**
- Tool playground was only showing partial output
- When 'complete' event arrived, it replaced streamed text with final output
- Output was displayed as plain text instead of formatted markdown
**Changes:**
- Fixed streaming bug in ToolPlayground component
- Removed line that overwrote accumulated text on 'complete' event
- Now preserves all streamed chunks for full output display
- Added react-markdown with GitHub Flavored Markdown support
- Install react-markdown and remark-gfm packages
- Added @tailwindcss/typography plugin for prose styling
- Replaced plain <pre> with <ReactMarkdown> component
- Applied prose classes for proper markdown formatting
- Added type="button" to button elements for accessibility
**Files changed:**
- apps/web/src/components/ToolPlayground.tsx
- Comment out setOutput(data.output) on complete event
- Import ReactMarkdown and remarkGfm
- Replace pre element with ReactMarkdown component
- Add prose styling classes
- Add type="button" to buttons
- apps/web/tailwind.config.ts
- Add @tailwindcss/typography plugin
**Result:**
- Full streamed output now displays correctly
- Markdown is rendered with proper formatting (headings, lists, code blocks, etc.)
- Better UX for AI-generated tool responses
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
OpenAI was rejecting tool definitions with error "schema must be a JSON Schema of 'type: "object"'". This was caused by AI SDK v5 not properly converting Zod schemas to JSON Schema format.
**Changes:**
- Upgrade AI SDK from v5.0.104 to v6.0.0-beta.124
- Upgrade @ai-sdk/openai from v2.0.74 to v3.0.0-beta.22
- Upgrade Zod from v3.25.76 to v4.1.13 across all packages
**AI SDK v6 breaking changes:**
- Tool definition API: `parameters` renamed to `inputSchema`
- Removed `aiTool()` wrapper - use plain object with description, inputSchema, execute
- Streaming API: Use `textStream` async iterator instead of onChunk callback
- Zod schemas now properly converted to JSON Schema for OpenAI
**Zod v4 breaking changes:**
- `z.record()` now requires two arguments: `z.record(keySchema, valueSchema)`
- `z.enum()` params changed: `errorMap` removed, use `message` instead
- Type system improvements require explicit type parameters
- Fixed type errors in @tpmjs/env, @tpmjs/npm-client, @tpmjs/types
**Files changed:**
- apps/web/src/lib/ai-agent/tool-executor-agent.ts
- Updated tool definition to use `inputSchema` instead of `parameters`
- Removed `aiTool()` wrapper
- Fixed streaming to use `textStream` iterator
- packages/env/src/index.ts
- Updated type constraint from `z.ZodRawShape` to `Record<string, z.ZodTypeAny>`
- packages/npm-client/src/package.ts
- Fixed `z.record()` calls to include both key and value schemas
- Added type assertions for record indexing
- packages/types/src/tpmjs.ts
- Changed `errorMap` to `message` in z.enum() calls
**Testing:**
- ✅ Type-check passes
- ✅ Production build succeeds
- ✅ All routes compile correctly
This fixes the tool execution error where OpenAI rejected tool schemas with invalid format.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Problem: OpenAI tool names must match ^[a-zA-Z0-9_-]+ but npm package names like @tpmjs/createblogpost contain @ and /
Solution: Add sanitizeToolName() function and update pnpm-lock.yaml
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
**VM2 Removal:**
- Remove VM2 dependency from package-executor
- Rewrite executor to use direct package execution with require()
- Add TODO comment for future sandboxing implementation
**Why this change:**
- VM2 requires runtime filesystem access to bridge.js which doesn't work with Next.js Turbopack bundling
- Even marking as serverExternalPackages fails because VM2 uses hardcoded file paths
- Direct execution allows builds to complete while we find Next.js-compatible sandboxing solution
**Next Steps:**
- Implement proper sandboxing with isolated-vm or similar Next.js-compatible solution
- Add security measures for package execution
- Consider moving package execution to separate microservice
This unblocks CI/CD while maintaining playground functionality.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Syntax Highlighting:**
- Add react-syntax-highlighter with Solarized Light theme
- Proper language detection from markdown code blocks
- Beautiful syntax highlighting for all code examples
- Improved inline code styling with subtle borders
**Enhanced Readability:**
- Larger base typography with prose-lg
- Better contrast for text colors (zinc-700/zinc-300)
- Improved heading spacing and hierarchy
- Enhanced table styling with hover effects and better spacing
- Table headers with uppercase, bold styling
- Table cells with generous padding (px-6 py-4/py-3)
- Row hover effects for better interaction
- Better blockquote styling with blue accents
- Improved list spacing with leading-relaxed
- Enhanced image borders and shadows
**Table Improvements:**
- Professional header styling with background colors
- Better cell padding and spacing
- Hover effects on rows
- Improved borders and shadows
- Responsive overflow handling
All code blocks now have beautiful Solarized Light syntax highlighting, and the overall typography is more readable and professional.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Database Schema:**
- Add npmReadme, npmKeywords, npmAuthor, npmMaintainers fields to Tool model
**NPM Client:**
- Add fetchLatestPackageWithMetadata() function to fetch README and top-level metadata
- Export new PackageVersionWithReadme type
**Sync Workers:**
- Update keyword and changes sync to fetch and store README content
- Store author, maintainers, and keywords from package.json
**UI Components:**
- Create Markdown component using react-markdown with GitHub Flavored Markdown
- Add rehype-sanitize for security and remark-gfm for tables/strikethrough support
**Tool Detail Page:**
- Convert from createElement to JSX for better maintainability
- Display README in a dedicated card with proper markdown rendering
- Show NPM keywords, author, and maintainers in sidebar
- Add ThemeToggle to header
- Improve layout with better spacing and organization
This brings the tool detail pages much closer to NPM's package pages,
providing users with comprehensive information about each tool including
the full README documentation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add test tool package to verify sync system can discover and process tools:
Package Features:
- Creates structured blog posts with frontmatter and metadata
- Supports both Markdown and MDX output formats
- Automatic slug generation from title
- Word count and reading time calculation
- SEO-friendly metadata generation
TPMJS Integration:
- Rich-tier tpmjs field with all optional metadata
- Tagged with 'tpmjs-tool' keyword for NPM discovery
- Complete parameter and return type documentation
- AI agent guidance for optimal LLM usage
- Pricing, authentication, and framework metadata
Implementation:
- Full TypeScript implementation with exported types
- Proper tsconfig and tsup build configuration
- Comprehensive README with usage examples
- Changeset for publishing workflow
- Added packages/tools/* to pnpm workspace
This package serves as an end-to-end test of the sync workers to verify:
1. NPM keyword search discovers the package
2. Changes feed picks up updates
3. tpmjs field validation works correctly
4. Rich-tier metadata is properly extracted
5. Quality score calculation functions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add complete sync worker system for NPM package discovery and metrics:
**Sync Workers:**
- Changes Feed Sync (/api/sync/changes) - Polls NPM changes every 2 min
- Keyword Search Sync (/api/sync/keyword) - Searches tpmjs-tool keyword every 15 min
- Metrics Sync (/api/sync/metrics) - Updates downloads & quality scores hourly
**Features:**
- Secure CRON_SECRET authentication for all sync endpoints
- Comprehensive error handling with sync logs and checkpoints
- Smart package validation and filtering (skip invalid tpmjs fields)
- Automatic tool upsert with discovery method tracking
- Quality score calculation based on tier, downloads, and GitHub stars
- 5-minute timeout support for long-running sync operations
**Dependencies:**
- Add @tpmjs/npm-client to web app for NPM API integration
- Use barrel exports from npm-client package (no subpath imports)
- Add CRON_SECRET env variable validation
- Add ~/src path alias to tsconfig
**Infrastructure:**
- Configure Vercel Cron jobs in vercel.json for automated syncing
- Add publishedAt field to PackageVersion schema
- Fix Prisma JSON field handling (use undefined instead of null)
- Proper null checks for fetchLatestPackageVersion return values
**Type Safety:**
- Cast TpmjsField union type to access optional rich-tier properties
- Handle searchByKeyword array return type correctly
- Fix fetchDownloadStats to return number directly
All API routes follow Next.js 16 conventions with proper type checking.
Type-check and full build successful.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add @tpmjs/db package with Prisma ORM setup
- Define Tool model with NPM metadata and TPMJS fields
- Define SyncCheckpoint model for tracking sync worker progress
- Define SyncLog model for audit trail of sync operations
- Add Prisma client singleton with dev logging
- Add seed script for initializing sync checkpoints
- Include comprehensive README with setup instructions
Package includes:
- Complete Prisma schema matching NPM_MIRROR.md spec
- Three models: Tool, SyncCheckpoint, SyncLog
- Indexes for performance on key fields
- TypeScript support via @tpmjs/tsconfig
- Scripts for db:migrate, db:push, db:studio, db:seed
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implemented 8 production-ready form components with full accessibility:
Components Added:
- Textarea: Multi-line text input with character counter
- Checkbox: Custom styled with indeterminate state support
- Radio & RadioGroup: Context-based radio button groups
- Switch: Toggle with animated thumb and loading state
- Select: Native select with custom styling and option groups
- Slider: Range input with marks, value display, cross-browser support
- FormField: Wrapper component with label, error, and helper text
Features:
- Full accessibility (ARIA attributes, semantic HTML)
- Controlled/uncontrolled patterns via useControlled hook
- Dark mode support with semantic tokens
- Design tokens and shared variant system
- Comprehensive test coverage (856 tests passing)
- Form-specific design tokens (formTokens)
- Shared form variant base classes (formVariants)
Playground Updates:
- Added comprehensive Forms section showcasing all components
- Interactive examples with state management
- Complete form composition example
- All components fully functional and themed
Test Coverage:
- 10+ describe blocks per component
- All edge cases covered
- Accessibility testing
- Cross-browser compatibility
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Packages/apps that run `eslint .` need eslint installed as a
devDependency. While eslint is in @tpmjs/eslint-config, it needs to
be available in the local node_modules/.bin for the lint script to run.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add type-coverage, knip, and dependency-cruiser for code quality
- Set up Node 22 (LTS) with .nvmrc file
- Configure knip for dead code detection across monorepo
- Configure dependency-cruiser with sensible architecture rules
- Add ts-reset for better TypeScript built-in types
- Fix Tabs component type exports for Storybook
- Recreate eslint react.js config that was missing
- Add quality gates documentation
All quality checks pass with 0 errors (only informational warnings).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
