- Add 'Passing API Keys to Tools' section to registry-execute README
- Add 'Understanding requiredEnvVars' section to registry-search README
- Include example of pre-configuring keys for agents
- Document tools that don't require keys
- Bump both packages to 0.1.2
- Wrap function with tool() from 'ai' package
- Add jsonSchema() for input validation
- Rename export from createBlogPost to createBlogPostTool
- Update package.json with proper tpmjs.tools format
- Bump version to 0.3.0
Fixes executor error: 'Cannot destructure property title of t'
- 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>
Removes importHealth, executionHealth, healthCheckError, and lastHealthCheck
fields from tool search results. Models were refusing to call tools marked
as BROKEN, even when the issue was just a missing env var.
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
- Add defensive checks for required parameters in generated tool code
- Prevents crashes when tools are called with missing/empty params
- Returns descriptive error messages instead of undefined errors
- Update README with explanation of defensive pattern and best practices
- Bump to v1.0.5
Based on learnings from emoji-magic deployment:
- LLMs sometimes make probe calls with empty params
- Defensive checks prevent crashes and provide better error messages
- Even with Zod validation, runtime checks are valuable for robustness
- Add validation in both textToEmoji and emojiMood to handle missing text parameter
- Return descriptive error instead of crashing with undefined error
- Bump to v0.2.1
- Removed all prompts except package name
- Auto-generate description from package name
- Use sensible defaults: 2 example tools, ai-ml category, MIT license
- Generate exampleTool and anotherTool that users can customize
- Much faster UX - no more 10+ prompts for basic usage
- Updated README with simplified flow example
- Bumped version to 1.0.3
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- tsup banner already adds shebang, no need in source
- bump version to 1.0.2
- fixes CLI execution errors
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- 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>
- Implement proper BM25 scoring algorithm in /api/tools/search
- Term frequency with saturation (k1 = 1.5)
- Length normalization (b = 0.75)
- Inverse document frequency (IDF)
- Accept recent messages via 'messages' query param for better context
- Update search-registry tool to:
- Use /api/tools/search endpoint (not /api/tools)
- Pass last 3 user messages for contextual search
- Include recentMessages in tool input schema
- Update chat API to extract and pass last 3 user messages to search
BM25 formula: Σ IDF(qi) * (tf * (k1 + 1)) / (tf + k1 * (1 - b + b * |D| / avgdl))
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change search-registry to use /api/tools instead of /api/tools/search (not deployed yet)
- Add client-side filtering for search queries since deployed API doesn't support search
- Handle both deployed (/api/tools) and local dev (/api/tools/search) response formats
- Remove lint from pre-commit hooks to speed up commits (keep format + type-check)
- Fixes 404 errors when playground tries to search tools in production
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change default TPMJS_API_URL to https://tpmjs.com in production
- Keep localhost:3000 for local development
- Fixes "ECONNREFUSED 127.0.0.1:3000" error in Vercel
- Allows playground to search tools from production registry
🤖 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>
These fields are redundant as they already exist in package.json:
- links: Use package.json repository/homepage fields
- tags: Use package.json keywords field
- status: Not needed in tool metadata
Changes:
- Remove TpmjsLinksSchema type definition
- Remove links, tags, and status from TpmjsRichSchema
- Update validation logic to not check these fields
- Update all documentation (spec page, publish page, HOW_TO_PUBLISH_A_TOOL.md)
- Update example tool package.json
- Simplify field reference tables
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Rename TpmjsEnvVarSchema to TpmjsEnvSchema
- Rename envVars field to env throughout codebase
- Remove example field from TpmjsMinimalSchema (no longer required)
- Update all documentation (spec page, publish page, HOW_TO_PUBLISH_A_TOOL.md)
- Update example tool package.json
- Simplify minimal tier requirements to only category and description
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Replace the authentication field with a more general envVars array that allows tools to specify required environment variables:
Changes to type definitions:
- Remove TpmjsAuthenticationSchema and TpmjsAuthentication type
- Add TpmjsEnvVarSchema with fields: name, description, required, default
- Replace authentication field with envVars array in TpmjsRichSchema
- Update validateTpmjsField to check envVars instead of authentication
Changes to documentation:
- Update /spec page to document envVars instead of authentication
- Update /publish page examples to use envVars
- Update HOW_TO_PUBLISH_A_TOOL.md with envVars examples
- Update validation errors section
- Remove authentication from @tpmjs/createblogpost example
The envVars field is more flexible and clearer - it lists all environment variables a tool needs (API keys, endpoints, config values) rather than trying to categorize authentication types.
Example:
```json
"envVars": [
{
"name": "OPENAI_API_KEY",
"description": "API key for OpenAI services",
"required": true
}
]
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove pricing field from the entire project as it doesn't make sense for tool metadata:
- Remove TpmjsPricingSchema and TpmjsPricing type from types package
- Remove pricing from TpmjsRichSchema validation
- Remove pricing from validateTpmjsField check
- Remove pricing documentation from /spec page
- Remove pricing examples from /publish page
- Remove pricing from HOW_TO_PUBLISH_A_TOOL.md
- Remove pricing from @tpmjs/createblogpost example package.json
The pricing field was removed from Tier 3 (Rich) metadata as it's not relevant for tool discovery and integration. Tools can document pricing in their README or documentation links instead.
🤖 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>
Release @tpmjs/createblogpost v0.2.0 with initial features:
- Creates structured blog posts with frontmatter and metadata
- Supports both Markdown and MDX output formats
- Automatic slug generation, word count, and reading time calculation
- Rich TPMJS metadata for NPM registry discovery
🤖 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>
