- Add Prisma models for conversations, messages, participants, tool runs, and user settings
- Create API endpoints for conversation CRUD and SSE message streaming
- Build landing page with sample prompts at /omega
- Build chat interface with real-time streaming at /omega/[conversationId]
- Integrate @tpmjs/registry-search and @tpmjs/registry-execute packages
- Use OpenAI GPT-4.1 Mini as the default model
- Remove undefined variable reference (run.conversation) in header
- Extract ExpandedRunDetails component to reduce JSX nesting
- Fix vitest configs: rename to .mjs and add ESM-compatible __dirname
- Inline tailwind base config to avoid module resolution issues
- Remove unused imports (Streamdown, viewMode state)
This fixes the Turbopack parsing error that was preventing the build.
- Add SWR package and global SWRProvider
- Create reusable hooks: useTools, useAgents, useCollections,
useStats, useLikeStatus, useBundleSize, useActivity
- Update tool-search page to use useTools hook
- Update agents page to use useAgents hook
- Update BundleSize component to use useBundleSize hook
- Update LikeButton with optimistic updates via useLikeStatus
- Add simple about page with creator info
- Fix user-profile tests to use apiKeyClient instead of session auth
- Fix stats test for new nested response structure (data.overview.*)
- Enable conversation tests with CI OpenAI key setup
- Add setup-openai-key.ts script to configure test user's OPENAI_API_KEY
- Update workflow to run OpenAI key setup before tests
- Add Vitest integration test config with sequential execution
- Create test helpers (auth, cleanup, SSE parser, API client)
- Create test data factories for agents and collections
- Add test context manager for unified test setup
- Create integration tests for:
- Health and stats endpoints
- Tools list and search
- Collections CRUD
- Agents CRUD and conversations
- MCP HTTP transport
- User profile, API keys, and usage
- Public agents and collections
- Sync endpoints (cron-authenticated)
- Add GitHub Actions workflow running on push to main
- Add cleanup-orphans script for test data cleanup
- Add setup-test-credentials script for generating auth tokens
- Update all packages to latest versions via pnpm update --latest
- Downgrade Prisma 7 to 6 (v7 requires schema migration)
- Downgrade Tailwind CSS 4 to 3 (v4 requires PostCSS migration)
- Downgrade Storybook 10 to 8 (addons not available in v10)
- Pin cheerio to 1.0.0-rc.12 via pnpm override (type exports changed)
- Fix AI SDK tool definitions: parameters -> inputSchema
- Fix cheerio types in extract-meta and table-extract tools
- Add explicit type annotations to tool execute functions
- Migrate biome config to v2.3.11 schema
All type-checks, tests, and builds pass.
- Add sonner for toast notifications
- Create CopyButton component for simple copy actions
- Create CopyDropdown component with entity-specific copy options
- Create PackageManagerSelector with localStorage persistence
- Redesign tools page with TableVirtuoso, sort by downloads/likes/recent/name
- Redesign collections page with TableVirtuoso and infinite scroll
- Redesign agents page with TableVirtuoso and infinite scroll
- All tables have fast client-side filtering and copy functionality
- Add Agent, AgentCollection, AgentTool, UserApiKey, Conversation, Message models to Prisma schema
- Create agent types and Zod schemas in @tpmjs/types
- Implement AES-256 API key encryption utilities
- Add CRUD API endpoints for agents, tools, collections, and user API keys
- Create conversation streaming endpoint with SSE events
- Build agent tool builder to merge collections and individual tools
- Add dashboard pages: agents list, new agent form, agent detail/edit, chat interface
- Add API keys settings page for managing provider keys
- Add comprehensive Agents documentation section to /docs
- Update navigation to include Agents link in header and mobile menu
- Add new icons: terminal, puzzle, message, key, info, send
Supported providers: OpenAI, Anthropic, Google, Groq, Mistral
Add Model Context Protocol (MCP) server endpoint for collections,
allowing users to connect Claude Desktop, Cursor, and other MCP
clients to use tools from their collections.
- POST /api/collections/[id]/mcp - JSON-RPC endpoint for MCP
- GET /api/collections/[id]/mcp - Server info for discovery
- Tool name conversion (e.g., @tpmjs/hello → tpmjs-hello--helloWorldTool)
- Handlers for initialize, tools/list, tools/call methods
- Executes tools via existing sandbox executor
Only public collections are accessible (no auth required).
- Add virtualized list using react-virtuoso for smooth scrolling
- Filter by category, verb, quality score, and search
- Expandable cards with parameters, returns, AI guidance
- Add redirect from /tools-ideas to /tool-ideas
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Reduce cron frequency: changes 2min→4hr, keyword 15min→6hr, metrics hourly→daily
- Add Prisma directUrl for connection pooling support
- Add Vercel KV caching to /api/tools endpoint (graceful degradation if not configured)
- Add X-Cache header to indicate cache hit/miss
- Add NEON_COMPUTE_OPTIMIZATION.md with full strategy guide
These changes should reduce Neon CU usage from 100+ to ~20-30 CU-hrs/month.
- Create generate-og-images.ts script for build-time image generation
- Generate 13 static page OG images using gpt-image-1-mini
- Update API route to serve pre-generated images from public/og/
- Add 30-day cache headers and fallback to default image
- Images regenerate if older than 30 days
Run with: pnpm --filter=@tpmjs/web generate-og
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add /api/og/[...path] endpoint for dynamic OG image generation
- Use OpenAI gpt-image-1 for image generation with page-specific prompts
- Cache images in Vercel Blob storage with 30-day TTL
- Extract page content for contextual prompts (static pages, tool details)
- Update all page metadata to use dynamic OG image URLs
- Refactor tool detail page to server component for generateMetadata support
- Fall back to static /public/og-image.png on generation errors
- Add /stats page with animated D3 visualizations
- Create reusable chart components: AnimatedCounter, DonutChart, BarChart, AreaChart
- Expand stats API endpoints: /api/stats, /api/stats/health, /api/stats/executions, /api/stats/sync, /api/stats/tools
- Add Stats link to desktop and mobile navigation
- Add AI SDK v6 integration tests with vitest
Dashboard displays:
- Registry overview metrics with count-up animations
- Health distribution donut charts (import/execution)
- Quality score distribution
- Package tier breakdown
- Execution trends area chart with success/error series
- Token usage statistics
- Top categories bar chart
- Recent sync operations status
- 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
- Replace orbital spinner with 3x3 grid of blocks
- Diagonal wave animation matches dithering aesthetic
- Sharp squares, no rounded corners (brutalist)
- Inline horizontal layout with monospace text
- Consistent styling across all loading states
The new loader evokes "tools being constructed" - fitting
for a tool registry. Uses staggered opacity/scale animation
creating a wave pattern across the grid.
🤖 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>
**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:**
The Interactive Playground was failing with "Missing tiktoken_bg.wasm" error in production. Tiktoken requires WASM files which don't work in Vercel's serverless environment.
**Solution:**
- Remove tiktoken import from tool-executor-agent
- Replace tiktoken-based token counting with character estimation (~4 chars/token)
- Remove tiktoken from package.json dependencies
- Remove experimental webpack WASM config (no longer needed)
**Impact:**
- Token counting is now approximate but consistent
- No more WASM-related runtime errors
- Serverless deployment works properly
- Tool execution now functional in production
🤖 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 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 4 REST API endpoints for the TPMJS tool registry:
**GET /api/tools**
- Search and list tools with filtering, sorting, pagination
- Query params: q (search), category, official, limit, offset
- Returns tools with pagination metadata
- Sorts by quality score and download count
**GET /api/tools/[id]**
- Get tool details by ID (cuid) or package name
- Supports both lookup methods with OR query
- Returns full tool metadata
**POST /api/tools/validate**
- Validate tpmjs field schema
- Determines tier (minimal vs rich)
- Returns validation errors with detailed messages
- Uses @tpmjs/types validateTpmjsField function
**GET /api/stats**
- Aggregate statistics about the registry
- Total tools, official tools, category breakdown
- Recent tools (last 7 days), total downloads
- Efficient parallel queries with Promise.all
All endpoints include proper error handling, TypeScript types,
and follow Next.js 16 App Router conventions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add root biome.json that extends packages/config/biome.json
- Add explicit ignore patterns for dist/, build/, .next/, .turbo/, etc.
- Make a11y lints warnings instead of errors (non-blocking)
- Remove invalid biome-ignore comment from Section.tsx
- Apply formatting to all source files (155 files checked, 129 fixed)
This fixes the CI format check that was failing with 2064+ errors
because Biome was checking generated files in dist/ and .turbo/.
🤖 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": "module" to @tpmjs/eslint-config package.json for ES module support
- Rename eslint.config.js to eslint.config.mjs in apps/web and packages/ui
- Update ESLint configs to ignore build directories (.next, dist, .turbo)
- Extend import/no-internal-modules allowlist for Next.js, testing libs, and React
- Fix unescaped quotes in playground page code elements
- Convert CardDescriptionProps from empty interface to type alias
- Disable jsx-a11y/no-autofocus rule in test files
- Change web app lint script from 'next lint' to 'eslint .'
- Fix TypeScript ref type inference errors in UI package tests by using non-null assertions
- Disable Biome noNonNullAssertion rule for test files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
