- Fix chronological ordering by saving ASSISTANT message before TOOL messages
- Collect tool results during streaming, save after assistant message
- Add "Debug JSON" tab to view raw messages array
- Shows all message fields including toolCalls, toolResult, tokens
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Capture tool call inputs from onChunk and onStepFinish callbacks
- Store toolCalls array in ASSISTANT messages with proper format
- Update chat page to combine ASSISTANT toolCalls (input) with TOOL messages (output)
- Show complete tool call cards with both input args and output results
- Display token usage in assistant messages for debugging
- Handle pending tool calls from ASSISTANT messages without results
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update conversation API to support cursor-based pagination (before/after params)
- Default behavior now returns most recent messages first
- Add react-virtuoso for efficient virtualized message rendering
- Implement scroll-up loading of older messages
- Show loading indicator when fetching history
- Add GET /api/tools/parameters endpoint
- Accepts packageName and name query params
- Supports 'schema' format (raw JSON Schema) or 'parameters' format (simplified array)
- Returns parameter definitions with types, descriptions, and required flags
- Falls back to author-provided parameters if inputSchema not available
Closes#5🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add github.ts to npm-client with functions to fetch GitHub stars
- Add parseGitHubUrl to handle various GitHub URL formats
- Update metrics sync endpoint to fetch and store GitHub stars
- GitHub stars now factor into tool quality score calculation
- Optional GITHUB_TOKEN env var for higher API rate limits
Closes#8🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Use ModelMessage type instead of any[] for type safety
- Format assistant messages with tool calls using ToolCallPart in content array
- Format tool messages with ToolResultPart using proper output structure
- Add ToolCallCard component for sexy debug display of tool calls in chat
- Remove debug console.log statements
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Log each step: auth, body parsing, schema validation, encryption, db upsert
- Check for API_KEY_ENCRYPTION_SECRET presence before encrypt
- Log timing, error details with stack traces
- Return specific error messages for each failure point
- Map tools search response from data.results.tools to expected format
- Map package.npmPackageName to top-level npmPackageName for UI
- Add search parameter support to collections API
- Add Tools section with search/add/remove functionality
- Add Collections section with search/add/remove functionality
- Add GET endpoints to /api/agents/[id]/tools and /api/agents/[id]/collections
- Use debounced search with dropdown for adding tools/collections
- Include click-outside handling to close dropdowns
- 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
- Move endpoint from /api/collections/[id]/mcp to /api/collections/[id]/mcp/[transport]
- Support both 'http' and 'sse' transports
- HTTP: standard JSON-RPC over HTTP
- SSE: Server-Sent Events for streaming responses
- Add test script for validating MCP endpoints
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 Collection and CollectionTool models to Prisma schema
- Create Zod validation schemas for collections
- Implement full CRUD API routes for collections
- Add tool management endpoints (add/remove tools)
- Create UI components: CollectionCard, CollectionForm, CollectionList,
AddToolSearch, CollectionToolList
- Add /dashboard/collections pages for list and detail views
- Add new icons to @tpmjs/ui: folder, plus, trash, edit, box, search,
loader, arrowLeft, alertCircle, globe
- Add xs size variant to Icon component
- Add Collections link to dashboard page
Features:
- Full CRUD for named collections
- Public/private visibility toggle
- Tool search to add tools to collections
- Ownership-based access control
- Collection limit: 50 per user
- Tool limit: 100 per collection
- 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>
- Split camelCase/PascalCase into words (sitemapReadTool → sitemap read tool)
- Add +100 score boost for exact tool name matches
- Fixes issue where searching exact tool name returned 0 results
- 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.
- Add download trend sparkline chart showing 30-day download history
- Add bundle size component with minified/gzipped sizes via bundlephobia proxy
- Add more install commands: yarn, bun, deno (in addition to npm, pnpm)
- Change discovery keyword from "tpmjs-tool" to "tpmjs" across entire codebase
- Update sync endpoints to use new keyword
- Update all documentation and package.json files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- 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 StatsSnapshot model to store daily registry metrics
- Create /api/sync/stats-snapshot endpoint for daily cron captures
- Add GET endpoint to retrieve historical snapshots (up to 365 days)
- Update stats page with Historical Trends section showing:
- Tools & packages growth over time
- Health status trends
- Daily executions history
- NPM downloads trends
- Add cron job running at midnight UTC daily
- Fix PostgreSQL GROUP BY issue in quality distribution query
- 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
The TpmjsToolDefinitionSchema now accepts both 'name' and 'exportName' fields,
transforming exportName to name for backward compatibility with published packages
that still use the old field name.
Also fix type errors in sync routes for auto-discovered tools.
- Database: Migrate column export_name to name in tools table
- Prisma schema: Update Tool model to use name field
- Sync routes: Update keyword and changes sync to use name
- Railway executor: Update API endpoints to use name parameter
- API routes: Update all tool routes to use name field
- Web app: Update all pages and components
- Playground: Update tool loader and sidebar
- create-basic-tools: Update types and generators
- Scripts: Update sync and test scripts
Database migration was done via direct SQL:
ALTER TABLE tools RENAME COLUMN export_name TO name;
The unique constraint remains on (package_id, name).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Breaking change for TPMJS spec:
- Remove `exportName` field support from TpmjsToolDefinitionSchema
- Make `name` field required (replaces deprecated `exportName`)
- Update create-basic-tools to generate `name` field
- Update sync routes to use `name` from validated schema
- Add `permissions: contents: write` to Vercel registry sync workflow
Packages using the old `exportName` field must update to use `name`.
Major changes to the TPMJS specification:
1. Auto-Discovery: The `tools` array is now optional. If omitted, TPMJS
automatically scans package exports and registers any export with
`description` and `execute` properties (standard AI SDK tool format).
2. Renamed `exportName` to `name` in tool definitions for cleaner spec.
3. Added `/list-exports` endpoint to Railway executor that:
- Lists all exports from a package
- Identifies valid AI SDK tools
- Extracts descriptions for auto-discovered tools
4. Added `toolDiscoverySource` field to track 'auto' vs 'manual' discovery.
5. Updated tool page UI with:
- Auto-discovery warning banner
- Badge showing discovery source
6. Updated all documentation pages (docs, spec, publish) to reflect:
- Optional tools array with auto-discovery
- Use of `name` instead of `exportName`
- Auto-extraction of schema and description
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add inputSchema, schemaSource, schemaExtractedAt fields to Tool model
- Create schema extraction helper that calls executor's /load-and-describe
- Update sync routes to extract schema synchronously after tool upsert
- Reduce changes feed batch size from 100 to 30 for extraction time
- Update /api/tools/update-schema to store full JSON Schema
- Add /api/tools/extract-schema endpoint for manual re-extraction
- Update tool page UI with schema source badge and re-extract button
- Add deprecation comments to parameters, returns, aiAgent in types
Authors no longer need to define inputSchema in package.json - it's now
automatically extracted from the tool at sync time. Falls back to
author-provided parameters if extraction fails.
- Add standardized ApiResponse interface with consistent structure
- Implement proper request validation with detailed error messages
- Add response metadata (version, timestamp, requestId, processingTime)
- Include proper HTTP status codes and error handling
- Add validation for pagination parameters (limit: 1-1000, offset: >=0)
- Add health status enum validation
- Include response headers (X-Request-ID, X-Processing-Time, Cache-Control)
- Improve error logging with structured context
- Add count field to pagination response
- Follow REST API industry standards and best practices
- Increase max limit from 50 to 1000 for bulk tool fetching
- Exclude large fields (npmReadme, npmAuthor, npmMaintainers) from API response
- Reduces payload size while maintaining all necessary tool metadata
- Executor now updates TPM.js database directly when loading tools
- Update /api/tools/update-schema to use packageName+exportName lookup
- Remove schema update logic from HLLM proxy (no longer needed)
- Add /api/tools/update-schema endpoint to TPM.js to update tool parameters
- When a tool is executed, fetch its schema from the executor
- Update TPM.js database with the discovered schema (async, non-blocking)
- This ensures /api/tools returns correct inputSchema for all tools
Launch checklist implementation:
- Add Privacy Policy page (/privacy) with GDPR compliance
- Add Terms of Service page (/terms)
- Add custom 404 and error pages with helpful navigation
- Add FAQ page (/faq) covering common questions
- Add SEO meta tags with OpenGraph/Twitter cards
- Add JSON-LD structured data (Organization, WebSite, SoftwareApplication)
- Add sitemap.ts and robots.ts for search engines
- Add security headers (HSTS, CSP, X-Frame-Options) in vercel.json
- Add security.txt at /.well-known/security.txt
- Add API rate limiting (100 req/min default, 20 req/min strict)
- Add empty states in tool search for better UX
- Update AppHeader with FAQ link
- Update AppFooter with Privacy/Terms links
- Update biome.json to allow dangerouslySetInnerHTML for JSON-LD in page files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove direct DB updates from playground
- Add /api/tools/report-health endpoint with all health logic
- Playground now reports results to web app API
- All env var / validation error detection is in one place
- Health status updates based on execution success and error type
- Fix type errors with proper null checks
When a tool is marked as BROKEN but executes successfully in the
playground, update its health status to HEALTHY. This ensures
stale health check data doesn't persist when tools are working.
Also fixes noImplicitAnyLet lint error by refactoring to const.
The search endpoint was missing importHealth, executionHealth,
healthCheckError, and lastHealthCheck fields in the response. This caused
the playground (which uses search-registry tool) to not receive health
data for displaying broken tool badges.
Added all four health fields to the tool mapping in the search response.
🤖 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>
