\n ⚠ Warning: This is a pre-release version of the library. It is not yet ready for production use. Please look at latest stable release.\n\n\n## 📦 Package `@promptbook/types`\n\n- Promptbooks are [divided into several](#-packages) packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).\n- This package `@promptbook/types` is one part of the promptbook ecosystem.\n\nTo install this package, run:\n\n```bash\n# Install entire promptbook ecosystem\nnpm i ptbk\n\nnpm i -D @promptbook/types\n```\n\nComprehensive TypeScript type definitions for all Promptbook entities, enabling type-safe development and excellent IDE support throughout the Promptbook ecosystem.\n\n## 🎯 Purpose and Motivation\n\nThis package centralizes all TypeScript type definitions used throughout the Promptbook ecosystem. It enables developers to write type-safe code when working with promptbooks, pipelines, LLM providers, and other Promptbook components, providing excellent IntelliSense and compile-time error checking.\n\n## 🔧 High-Level Functionality\n\nThe package provides type definitions for:\n\n- **Pipeline Structures**: Complete type definitions for promptbook JSON structures\n- **Execution Types**: Types for pipeline execution, results, and error handling\n- **LLM Provider Types**: Configuration and option types for all supported providers\n- **Command Types**: Type definitions for all promptbook commands\n- **Utility Types**: Helper types for common patterns and data structures\n- **Component Types**: React component prop types for UI components\n\n## ✨ Key Features\n\n- 📝 **Complete Type Coverage** - Types for all Promptbook entities and APIs\n- 🔒 **Type Safety** - Compile-time validation and error prevention\n- 💡 **Excellent IntelliSense** - Rich IDE support with autocomplete and documentation\n- 🏗️ **Structural Types** - Detailed types for promptbook JSON structures\n- 🔧 **Provider-Agnostic** - Generic types that work across all LLM providers\n- 📊 **Execution Types** - Comprehensive types for pipeline execution and results\n- 🎨 **Component Types** - React component prop types for UI development\n- 🔄 **Version Compatibility** - Types that evolve with the Promptbook ecosystem\n\n## Usage Example\n\n```typescript\nimport type { PipelineJson } from '@promptbook/types';\nimport { compilePipeline } from '@promptbook/core';\n\nconst promptbook: PipelineJson = compilePipeline(\n spaceTrim(`\n\n # ✨ Example prompt\n\n - OUTPUT PARAMETER {greeting}\n\n\n ## 💬 Prompt\n\n \\`\\`\\`text\n Hello\n \\`\\`\\`\n\n -> {greeting}\n\n `),\n);\n```\n\n## 📦 Exported Type Categories\n\n### Agent and Book Types\n\n- `AgentBasicInformation` - Basic agent information structure (type)\n- `AgentModelRequirements` - Model requirements for agents (type)\n- `string_book` - Book content string type (type)\n- `BookCommitment` - Book commitment structure (type)\n- `CommitmentDefinition` - Commitment definition interface (type)\n- `ParsedCommitment` - Parsed commitment structure (type)\n\n### Component Types\n\n- `AvatarChipProps` - Avatar chip component props (type)\n- `AvatarChipFromSourceProps` - Avatar chip from source props (type)\n- `AvatarProfileProps` - Avatar profile component props (type)\n- `AvatarProfileFromSourceProps` - Avatar profile from source props (type)\n- `BookEditorProps` - Book editor component props (type)\n- `ChatProps` - Chat component props (type)\n- `LlmChatProps` - LLM chat component props (type)\n- `ChatMessage` - Chat message structure (type)\n- `ChatParticipant` - Chat participant information (type)\n\n### Collection and Pipeline Types\n\n- `PipelineCollection` - Pipeline collection interface (type)\n- `PipelineJson` - Complete pipeline JSON structure (type)\n- `PipelineString` - Pipeline string format (type)\n- `PipelineInterface` - Pipeline interface definition (type)\n- `TaskJson` - Task JSON structure (type)\n- `PromptTaskJson` - Prompt task structure (type)\n- `ScriptTaskJson` - Script task structure (type)\n- `SimpleTaskJson` - Simple task structure (type)\n- `DialogTaskJson` - Dialog task structure (type)\n- `CommonTaskJson` - Common task properties (type)\n\n### Command Types\n\n- `Command` - Base command interface (type)\n- `CommandParser` - Command parser interface (type)\n- `PipelineBothCommandParser` - Pipeline both command parser (type)\n- `PipelineHeadCommandParser` - Pipeline head command parser (type)\n- `PipelineTaskCommandParser` - Pipeline task command parser (type)\n- `CommandParserInput` - Command parser input (type)\n- `CommandType` - Command type enumeration (type)\n- `CommandUsagePlace` - Command usage context (type)\n- `BookVersionCommand` - Book version command (type)\n- `ExpectCommand` - Expect command structure (type)\n- `ForeachCommand` - Foreach command structure (type)\n- `ForeachJson` - Foreach JSON structure (type)\n- `FormatCommand` - Format command structure (type)\n- `FormfactorCommand` - Formfactor command structure (type)\n- `JokerCommand` - Joker command structure (type)\n- `KnowledgeCommand` - Knowledge command structure (type)\n- `ModelCommand` - Model command structure (type)\n- `ParameterCommand` - Parameter command structure (type)\n- `PersonaCommand` - Persona command structure (type)\n- `PostprocessCommand` - Postprocess command structure (type)\n- `SectionCommand` - Section command structure (type)\n- `UrlCommand` - URL command structure (type)\n- `ActionCommand` - Action command structure (type)\n- `InstrumentCommand` - Instrument command structure (type)\n\n### Execution Types\n\n- `ExecutionTools` - Execution tools interface (type)\n- `LlmExecutionTools` - LLM execution tools interface (type)\n- `LlmExecutionToolsConstructor` - LLM execution tools constructor (type)\n- `PipelineExecutor` - Pipeline executor interface (type)\n- `PipelineExecutorResult` - Execution result structure (type)\n- `ExecutionTask` - Execution task structure (type)\n- `PreparationTask` - Preparation task structure (type)\n- `task_status` - Task status type (type)\n- `AbstractTask` - Abstract task interface (type)\n- `Task` - Task interface (type)\n- `ExecutionReportJson` - Execution report structure (type)\n- `ExecutionPromptReportJson` - Execution prompt report structure (type)\n- `ExecutionReportString` - Execution report string (type)\n- `ExecutionReportStringOptions` - Report formatting options (type)\n- `PromptResult` - Prompt execution result (type)\n- `CompletionPromptResult` - Completion prompt result (type)\n- `ChatPromptResult` - Chat prompt result (type)\n- `EmbeddingPromptResult` - Embedding prompt result (type)\n- `Usage` - Usage tracking structure (type)\n- `UsageCounts` - Usage counts structure (type)\n- `UncertainNumber` - Uncertain number type (type)\n- `AvailableModel` - Available model information (type)\n- `AbstractTaskResult` - Abstract task result (type)\n- `EmbeddingVector` - Embedding vector type (type)\n\n### LLM Provider Configuration Types\n\n- `AnthropicClaudeExecutionToolsOptions` - Anthropic Claude configuration (type)\n- `AnthropicClaudeExecutionToolsNonProxiedOptions` - Anthropic Claude non-proxied options (type)\n- `AnthropicClaudeExecutionToolsProxiedOptions` - Anthropic Claude proxied options (type)\n- `OpenAiExecutionToolsOptions` - OpenAI configuration (type)\n- `OpenAiAssistantExecutionToolsOptions` - OpenAI Assistant configuration (type)\n- `OpenAiCompatibleExecutionToolsOptions` - OpenAI Compatible configuration (type)\n- `OpenAiCompatibleExecutionToolsNonProxiedOptions` - OpenAI Compatible non-proxied options (type)\n- `OpenAiCompatibleExecutionToolsProxiedOptions` - OpenAI Compatible proxied options (type)\n- `AzureOpenAiExecutionToolsOptions` - Azure OpenAI configuration (type)\n- `GoogleExecutionToolsOptions` - Google configuration (type)\n- `DeepseekExecutionToolsOptions` - Deepseek configuration (type)\n- `OllamaExecutionToolsOptions` - Ollama configuration (type)\n- `VercelExecutionToolsOptions` - Vercel configuration (type)\n- `VercelProvider` - Vercel provider type (type)\n\n### Parameter and Data Types\n\n- `ParameterJson` - Parameter definition structure (type)\n- `InputParameterJson` - Input parameter structure (type)\n- `IntermediateParameterJson` - Intermediate parameter structure (type)\n- `OutputParameterJson` - Output parameter structure (type)\n- `CommonParameterJson` - Common parameter properties (type)\n- `Parameters` - Parameter collection type (type)\n- `InputParameters` - Input parameters type (type)\n- `Expectations` - Expectation validation structure (type)\n- `ExpectationUnit` - Expectation unit type (type)\n- `ExpectationAmount` - Expectation amount type (type)\n- `PersonaJson` - Persona definition structure (type)\n- `PersonaPreparedJson` - Prepared persona structure (type)\n- `KnowledgeSourceJson` - Knowledge source structure (type)\n- `KnowledgeSourcePreparedJson` - Prepared knowledge source structure (type)\n- `KnowledgePiecePreparedJson` - Prepared knowledge piece structure (type)\n\n### Utility and Helper Types\n\n- `string_prompt` - Prompt string type (type)\n- `string_template` - Template string type (type)\n- `string_text_prompt` - Text prompt string type (type)\n- `string_chat_prompt` - Chat prompt string type (type)\n- `string_system_message` - System message string type (type)\n- `string_completion_prompt` - Completion prompt string type (type)\n- `string_parameter_name` - Parameter name type (type)\n- `string_parameter_value` - Parameter value type (type)\n- `string_reserved_parameter_name` - Reserved parameter name type (type)\n- `ReservedParameters` - Reserved parameters type (type)\n- `string_model_name` - Model name type (type)\n- `string_url` - URL string type (type)\n- `string_filename` - Filename string type (type)\n- `string_absolute_filename` - Absolute filename type (type)\n- `string_relative_filename` - Relative filename type (type)\n- `string_dirname` - Directory name type (type)\n- `string_absolute_dirname` - Absolute directory name type (type)\n- `string_relative_dirname` - Relative directory name type (type)\n- `number_tokens` - Token count type (type)\n- `number_usd` - USD amount type (type)\n- `ModelVariant` - Model variant enumeration (type)\n- `ScriptLanguage` - Script language enumeration (type)\n- `TaskType` - Task type enumeration (type)\n- `SectionType` - Section type enumeration (type)\n- `ModelRequirements` - Model requirements type (type)\n- `CompletionModelRequirements` - Completion model requirements (type)\n- `ChatModelRequirements` - Chat model requirements (type)\n- `EmbeddingModelRequirements` - Embedding model requirements (type)\n\n### Remote Server Types\n\n- `RemoteServerOptions` - Remote server configuration (type)\n- `AnonymousRemoteServerOptions` - Anonymous remote server options (type)\n- `ApplicationRemoteServerOptions` - Application remote server options (type)\n- `ApplicationRemoteServerClientOptions` - Application remote server client options (type)\n- `RemoteClientOptions` - Remote client configuration (type)\n- `Identification` - User identification structure (type)\n- `ApplicationModeIdentification` - Application mode identification (type)\n- `AnonymousModeIdentification` - Anonymous mode identification (type)\n- `LoginRequest` - Login request structure (type)\n- `LoginResponse` - Login response structure (type)\n- `RemoteServer` - Remote server interface (type)\n\n### Storage and Scraper Types\n\n- `PromptbookStorage` - Storage interface (type)\n- `FileCacheStorageOptions` - File cache storage options (type)\n- `IndexedDbStorageOptions` - IndexedDB storage options (type)\n- `Scraper` - Scraper interface (type)\n- `ScraperConstructor` - Scraper constructor type (type)\n- `ScraperSourceHandler` - Scraper source handler (type)\n- `ScraperIntermediateSource` - Scraper intermediate source (type)\n- `ScraperAndConverterMetadata` - Scraper and converter metadata (type)\n- `Converter` - Content converter interface (type)\n\n### Additional Types\n\n- `Prompt` - Prompt interface (type)\n- `CompletionPrompt` - Completion prompt interface (type)\n- `ChatPrompt` - Chat prompt interface (type)\n- `EmbeddingPrompt` - Embedding prompt interface (type)\n- `NonEmptyArray` - Non-empty array type (type)\n- `NonEmptyReadonlyArray` - Non-empty readonly array type (type)\n- `IntermediateFilesStrategy` - Intermediate files strategy (type)\n- `string_promptbook_version` - Promptbook version string type (type)\n\n> 💡 This package provides TypeScript types for promptbook applications. For runtime functionality, see [@promptbook/core](#-packages) or install all packages with `npm i ptbk`\n\n\n---\n\nRest of the documentation is common for **entire promptbook ecosystem**:\n\n\n\n\n## 📖 The Book Whitepaper\n\nPromptbook lets you create **persistent AI agents** that work on real goals for your company. The [**Agents Server**](https://gallery.ptbk.io/) is the heart of the project - a place where your AI agents live, remember context, collaborate in teams, and get things done.\n\nNowadays, the biggest challenge for most business applications isn't the raw capabilities of AI models. Large language models such as Claude Mythos, GPT-5.6 or Kimi K2.7 are incredibly capable.\n\nThe main challenge lies in **managing the context**, providing rules and knowledge, and narrowing the personality.\n\nIn Promptbook, you define your agents **using simple Books** - a human-readable language that is explicit, easy to understand and write, reliable, and highly portable. You then deploy them to the **Agents Server**, where they run persistently and work toward their goals.\n\n
| \n\n**Lawyer** \n \nGOAL You are a company lawyer. \nYour job is to provide legal advice and support to the company and its employees. \nRespond to incoming legal inquiries via email and keep the company website updated with the latest legal policies. \n \n**RULE** You are knowledgeable, professional, and detail-oriented. \n**KNOWLEDGE** https://company.com/company-policies.pdf \n**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx \n \n \nTEAM You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law. \n\n |
| \n\n**Paul Smith & Associés** \n \n**PERSONA** You are a company lawyer. \nYour job is to provide legal advice and support to the company and its employees. \n\n |
| \n\n**Company Lawyer** \n \nGOAL \nYour job is to provide legal advice and support to the company and its employees. \nGOAL Respond to incoming legal inquiries via email within 24 hours. \nGOAL Keep the company website updated with the latest legal policies and compliance information. \n\n |
| \n\n**Paul Smith & Associés** \n \n**PERSONA** You are a company lawyer. \nYour job is to provide legal advice and support to the company and its employees. \nGOAL Respond to incoming legal inquiries via email within 24 hours. \nGOAL Keep the company website updated with the latest legal policies and compliance information. \n**KNOWLEDGE** https://company.com/company-policies.pdf \n**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx \n\n |
| \n\n**Paul Smith & Associés** \n \n**PERSONA** You are a company lawyer. \nYour job is to provide legal advice and support to the company and its employees. \nGOAL Respond to incoming legal inquiries via email within 24 hours. \nGOAL Keep the company website updated with the latest legal policies and compliance information. \n**RULE** Always ensure compliance with local laws and regulations. \n**RULE** Never provide legal advice outside your area of expertise. \n**RULE** Never provide legal advice about criminal law. \n**KNOWLEDGE** https://company.com/company-policies.pdf \n**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx \n\n |
| \n\n**Paul Smith & Associés** \n \n**PERSONA** You are a company lawyer. \nYour job is to provide legal advice and support to the company and its employees. \nGOAL Respond to incoming legal inquiries via email within 24 hours. \nGOAL Keep the company website updated with the latest legal policies and compliance information. \n**RULE** Always ensure compliance with local laws and regulations. \n**RULE** Never provide legal advice outside your area of expertise. \n**RULE** Never provide legal advice about criminal law. \n**KNOWLEDGE** https://company.com/company-policies.pdf \n**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx \n\n |
| \n\n**Paul Smith & Associés** \n \n**PERSONA** You are a company lawyer. \nYour job is to provide legal advice and support to the company and its employees. \nGOAL Respond to incoming legal inquiries via email within 24 hours. \nGOAL Keep the company website updated with the latest legal policies and compliance information. \n**RULE** Always ensure compliance with local laws and regulations. \n**RULE** Never provide legal advice outside your area of expertise. \n**RULE** Never provide legal advice about criminal law. \n**KNOWLEDGE** https://company.com/company-policies.pdf \n**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx \nTEAM You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law. \n\n |
| Project | \nAbout | \n
|---|---|
| ⭐ Agents Server | \n\n The primary way to use Promptbook. A production-ready platform where your AI agents live - create, manage, deploy, and interact with persistent agents that work on goals. Available as a hosted service or self-hosted via Docker.\n | \n
| Book language | \n\n Human-friendly, high-level language that abstracts away low-level details of AI. It allows to focus on personality, behavior, knowledge, and rules of AI agents rather than on models, parameters, and prompt engineering.\n \n There is also a plugin for VSCode to support .book file extension\n | \n
| Promptbook Engine | \n\n The open-source core that powers the Agents Server. Can also be used as a standalone TypeScript/JavaScript library to embed agent capabilities into your own applications.\n Released as multiple NPM packages.\n | \n
| Platform | \nDescription | \n
|---|---|
| 💬 Discord | \nJoin our active developer community for discussions and support | \n
| 🗣️ GitHub Discussions | \nTechnical discussions, feature requests, and community Q&A | \n
| Professional updates and industry insights | \n|
| General announcements and community engagement | \n|
| 🔗 ptbk.io | \nOfficial landing page with project information | \n
| 📸 Instagram @promptbook.studio | \nVisual updates, UI showcases, and design inspiration | \n
| Data & Knowledge Management | \nPipeline Control | \n
|---|---|
\n
| \n \n
| \n
| Language & Output Control | \nAdvanced Generation | \n
\n
| \n \n
| \n