@promptbook/deepseek 0.103.0-1 → 0.103.0-100

package/README.md

@@ -9,8 +9,8 @@ Turn your company's scattered knowledge into AI ready Books
 
 
 
-[![NPM Version of ![Promptbook logo - cube with letters P and B](./design/logo-h1.png) Promptbook](https://badge.fury.io/js/promptbook.svg)](https://www.npmjs.com/package/promptbook)
-[![Quality of package ![Promptbook logo - cube with letters P and B](./design/logo-h1.png) Promptbook](https://packagequality.com/shield/promptbook.svg)](https://packagequality.com/#?package=promptbook)
+[![NPM Version of ![Promptbook logo](./design/logo-h1.png) Promptbook](https://badge.fury.io/js/promptbook.svg)](https://www.npmjs.com/package/promptbook)
+[![Quality of package ![Promptbook logo](./design/logo-h1.png) Promptbook](https://packagequality.com/shield/promptbook.svg)](https://packagequality.com/#?package=promptbook)
 [![Known Vulnerabilities](https://snyk.io/test/github/webgptorg/promptbook/badge.svg)](https://snyk.io/test/github/webgptorg/promptbook)
 [![🧪 Test Books](https://github.com/webgptorg/promptbook/actions/workflows/test-books.yml/badge.svg)](https://github.com/webgptorg/promptbook/actions/workflows/test-books.yml)
 [![🧪 Test build](https://github.com/webgptorg/promptbook/actions/workflows/test-build.yml/badge.svg)](https://github.com/webgptorg/promptbook/actions/workflows/test-build.yml)
@@ -23,11 +23,7 @@ Turn your company's scattered knowledge into AI ready Books
 
 ## 🌟 New Features
 
--   🚀 **GPT-5 Support** - Now includes OpenAI's most advanced language model with unprecedented reasoning capabilities and 200K context window
--   💡 VS Code support for `.book` files with syntax highlighting and IntelliSense
--   🐳 Official Docker image (`hejny/promptbook`) for seamless containerized usage
--   🔥 Native support for OpenAI `o3-mini`, GPT-4 and other leading LLMs
--   🔍 DeepSeek integration for advanced knowledge search
+-   **Gemini 3 Support**
 
 
 
@@ -59,19 +55,162 @@ Rest of the documentation is common for **entire promptbook ecosystem**:
 
 
 
-## 🤍 The Book Abstract
+## 📖 The Book Whitepaper
 
-**It's time for a paradigm shift! The future of software is written in plain English, French, or Latin.**
+For most business applications nowadays, the biggest challenge isn't about the raw capabilities of AI models. Large language models like GPT-5 or Claude-4.1 are extremely capable.
 
-During the computer revolution, we have seen [multiple generations of computer languages](https://github.com/webgptorg/promptbook/discussions/180), from the physical rewiring of the vacuum tubes through low-level machine code to the high-level languages like Python or JavaScript. And now, we're on the edge of the **next revolution**!
+The main challenge is to narrow it down, constrain it, set the proper **context, rules, knowledge, and personality**. There are a lot of tools which can do exactly this. On one side, there are no-code platforms which can launch your agent in seconds. On the other side, there are heavy frameworks like Langchain or Semantic Kernel, which can give you deep control.
 
-It's a revolution of writing software in **plain human language** that is understandable and executable by both humans and machines – and it's going to change everything!
+Promptbook takes the best from both worlds. You are defining your AI behavior by simple **books**, which are very explicit. They are automatically enforced, but they are very easy to understand, very easy to write, and very reliable and portable.
 
-The incredible growth in power of microprocessors and the Moore's Law have been the driving force behind the ever-more powerful languages, and it's been an amazing journey! Similarly, the large language models (like GPT or Claude) are the next big thing in language technology, and they're set to transform the way we interact with computers.
+<table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
 
-This shift will happen whether we're ready or not. Our mission is to make it excellent, not just good.
+**<ins>Paul Smith & Associés</ins>**<br/>
+<br/>
+**PERSONA** You are a company lawyer.<br/>
+Your job is to provide legal advice and support to the company and its employees.<br/>
+You are knowledgeable, professional, and detail-oriented.<br/>
 
-**Join us in this journey!**
+</td></tr></table>
+
+<div style="page-break-after: always;"></div>
+
+### Aspects of great AI agent
+
+We have created a language called **Book**, which allows you to write AI agents in their native language and create your own AI persona. Book provides a guide to define all the traits and commitments.
+
+You can look at it as prompting (or writing a system message), but decorated by **commitments**.
+
+#### `Persona` commitment
+
+Personas define the character of your AI persona, its role, and how it should interact with users. It sets the tone and style of communication.
+
+<table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
+
+**<ins>Paul Smith & Associés</ins>**<br/>
+<br/>
+**PERSONA** You are a company lawyer.<br/>
+Your job is to provide legal advice and support to the company and its employees.<br/>
+You are knowledgeable, professional, and detail-oriented.<br/>
+
+</td></tr></table>
+
+#### `Knowledge` commitment
+
+Knowledge Commitment allows you to provide specific information, facts, or context that the AI should be aware of when responding.
+
+This can include domain-specific knowledge, company policies, or any other relevant information.
+
+Promptbook Engine will automatically enforce this knowledge during interactions. When the knowledge is short enough, it will be included in the prompt. When it is too long, it will be stored in vector databases and RAG retrieved when needed. But you don't need to care about it.
+
+<table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
+
+**<ins>Paul Smith & Associés</ins>**<br/>
+<br/>
+**PERSONA** You are a company lawyer.<br/>
+Your job is to provide legal advice and support to the company and its employees.<br/>
+You are knowledgeable, professional, and detail-oriented.<br/>
+<br/>
+**KNOWLEDGE** https://company.com/company-policies.pdf<br/>
+**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
+
+</td></tr></table>
+
+#### `Rule` commitment
+
+Rules will enforce specific behaviors or constraints on the AI's responses. This can include ethical guidelines, communication styles, or any other rules you want the AI to follow.
+
+Depending on rule strictness, Promptbook will either propagate it to the prompt or use other techniques, like adversary agent, to enforce it.
+
+<table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
+
+**<ins>Paul Smith & Associés</ins>**<br/>
+<br/>
+**PERSONA** You are a company lawyer.<br/>
+Your job is to provide legal advice and support to the company and its employees.<br/>
+You are knowledgeable, professional, and detail-oriented.<br/>
+<br/>
+**RULE** Always ensure compliance with laws and regulations.<br/>
+**RULE** Never provide legal advice outside your area of expertise.<br/>
+**RULE** Never provide legal advice about criminal law.<br/>
+**KNOWLEDGE** https://company.com/company-policies.pdf<br/>
+**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
+
+</td></tr></table>
+
+#### `Action` commitment
+
+Action Commitment allows you to define specific actions that the AI can take during interactions. This can include things like posting on a social media platform, sending emails, creating calendar events, or interacting with your internal systems.
+
+<table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
+
+**<ins>Paul Smith & Associés</ins>**<br/>
+<br/>
+**PERSONA** You are a company lawyer.<br/>
+Your job is to provide legal advice and support to the company and its employees.<br/>
+You are knowledgeable, professional, and detail-oriented.<br/>
+<br/>
+**RULE** Always ensure compliance with laws and regulations.<br/>
+**RULE** Never provide legal advice outside your area of expertise.<br/>
+**RULE** Never provide legal advice about criminal law.<br/>
+**KNOWLEDGE** https://company.com/company-policies.pdf<br/>
+**KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
+**ACTION** When a user asks about an issue that could be treated as a crime, notify legal@company.com.<br/>
+
+</td></tr></table>
+
+[Read more about the language](./BLUEPRINT.md)
+
+<div style="page-break-after: always;"></div>
+
+### Where to use your AI agent in book
+
+Books can be useful in various applications and scenarios. Here are some examples:
+
+#### Chat apps:
+
+Create your own chat shopping assistant and place it in your eShop.
+You will be able to answer customer questions, help them find products, and provide personalized recommendations. Everything is tightly controlled by the book you have written.
+
+#### Reply Agent:
+
+Create your own AI agent, which will look at your emails and reply to them. It can even create drafts for you to review before sending.
+
+#### Coding Agent:
+
+Do you love Vibecoding, but the AI code is not always aligned with your coding style and architecture, rules, security, etc.? Create your own coding agent to help enforce your specific coding standards and practices.
+
+This can be integrated to almost any Vibecoding platform, like GitHub Copilot, Amazon CodeWhisperer, Cursor, Cline, Kilocode, Roocode,...
+
+They will work the same as you are used to, but with your specific rules written in book.
+
+#### Internal Expertise
+
+Do you have an app written in TypeScript, Python, C#, Java, or any other language, and you are integrating the AI.
+
+You can avoid struggle with choosing the best model, its settings like temperature, max tokens, etc., by writing a book agent and using it as your AI expertise.
+
+Doesn't matter if you do automations, data analysis, customer support, sentiment analysis, classification, or any other task. Your AI agent will be tailored to your specific needs and requirements.
+
+Even works in no-code platforms!
+
+<div style="page-break-after: always;"></div>
+
+### How to create your AI agent in book
+
+Now you want to use it. There are several ways how to write your first book:
+
+#### From scratch with help from Paul
+
+We have written ai asistant in book who can help you with writing your first book.
+
+#### Your AI twin
+
+Copy your own behavior, personality, and knowledge into book and create your AI twin. It can help you with your work, personal life, or any other task.
+
+#### AI persona workpool
+
+Or you can pick from our library of pre-written books for various roles and tasks. You can find books for customer support, coding, marketing, sales, HR, legal, and many other roles.
 
 
 
@@ -186,81 +325,6 @@ Join our growing community of developers and users:
 
 
 
-## 📘 Book Language Blueprint
-
-_A concise, Markdown-based DSL for crafting AI workflows and automations._
-
-### Introduction
-
-Book is a Markdown-based language that simplifies the creation of AI applications, workflows, and automations. With human-readable commands, you can define inputs, outputs, personas, knowledge sources, and actions—without needing model-specific details.
-
-### Example
-
-```book
-# 🌟 My First Book
-
--   BOOK VERSION 1.0.0
--   URL https://promptbook.studio/hello.book
--   INPUT PARAMETER {topic}
--   OUTPUT PARAMETER {article}
-
-# Write an Article
-
--   PERSONA Jane, marketing specialist with prior experience in tech and AI writing
--   KNOWLEDGE https://wikipedia.org/
--   KNOWLEDGE ./journalist-ethics.pdf
--   EXPECT MIN 1 Sentence
--   EXPECT MAX 5 Pages
-
-> Write an article about {topic}
-
-→ {article}
-```
-
-Each part of the book defines one of three circles:
-
-### **1. What:** Workflows, Tasks and Parameters
-
-What work needs to be done. Each book defines a [workflow _(scenario or pipeline)_](https://github.com/webgptorg/promptbook/discussions/88), which is one or more tasks. Each workflow has a fixed input and output. For example, you have a book that generates an article from a topic. Once it generates an article about AI, once about marketing, once about cooking. The workflow (= your AI program) is the same, only the input and output change.
-
-**Related commands:**
-
--   [PARAMETER](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PARAMETER.md)
-
-### **2. Who:** Personas
-
-Who does the work. Each task is performed by a persona. A persona is a description of your virtual employee. It is a higher abstraction than the model, tokens, temperature, top-k, top-p and other model parameters.
-
-You can describe what you want in human language like `Jane, creative writer with a sense of sharp humour` instead of `gpt-4-2024-13-31, temperature 1.2, top-k 40, STOP token ".\n",...`.
-
-Personas can have access to different knowledge, tools and actions. They can also consult their work with other personas or user, if allowed.
-
-**Related commands:**
-
--   [PERSONA](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PERSONA.md)
-
-### **3. How:** Knowledge, Instruments and Actions
-
-The resources used by the personas are used to do the work.
-
-**Related commands:**
-
--   [KNOWLEDGE](https://github.com/webgptorg/promptbook/blob/main/documents/commands/KNOWLEDGE.md) of documents, websites, and other resources
--   [INSTRUMENT](https://github.com/webgptorg/promptbook/blob/main/documents/commands/INSTRUMENT.md) for real-time data like time, location, weather, stock prices, searching the internet, calculations, etc.
--   [ACTION](https://github.com/webgptorg/promptbook/blob/main/documents/commands/ACTION.md) for actions like sending emails, creating files, ending a workflow, etc.
-
-### General Principles
-
-Book language is based on markdown. It is subset of markdown. It is designed to be easy to read and write. It is designed to be understandable by both humans and machines and without specific knowledge of the language.
-
-The file has a `.book` extension and uses UTF-8 encoding without BOM.
-
-Books have two variants: flat — just a prompt without structure, and full — with tasks, commands, and prompts.
-
-As it is source code, it can leverage all the features of version control systems like git and does not suffer from the problems of binary formats, proprietary formats, or no-code solutions.
-
-But unlike programming languages, it is designed to be understandable by non-programmers and non-technical people.
-
 
 
 ## 📚 Documentation

package/esm/index.es.js

@@ -1,5 +1,5 @@
 import colors from 'colors';
-import spaceTrim, { spaceTrim as spaceTrim$1 } from 'spacetrim';
+import spaceTrim$2, { spaceTrim as spaceTrim$1 } from 'spacetrim';
 import { randomBytes } from 'crypto';
 
 // ⚠️ WARNING: This code has been generated so that any manual changes will be overwritten
@@ -9,14 +9,14 @@ import { randomBytes } from 'crypto';
  * @generated
  * @see https://github.com/webgptorg/book
  */
-const BOOK_LANGUAGE_VERSION = '1.0.0';
+const BOOK_LANGUAGE_VERSION = '2.0.0';
 /**
  * The version of the Promptbook engine
  *
  * @generated
  * @see https://github.com/webgptorg/promptbook
  */
-const PROMPTBOOK_ENGINE_VERSION = '0.103.0-1';
+const PROMPTBOOK_ENGINE_VERSION = '0.103.0-100';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -43,6 +43,7 @@ const $isRunningInJest = new Function(`
 /**
  * Generates random token
  *
+ * Note: `$` is used to indicate that this function is not a pure function - it is not deterministic
  * Note: This function is cryptographically secure (it uses crypto.randomBytes internally)
  *
  * @private internal helper function
@@ -52,6 +53,7 @@ function $randomToken(randomness) {
     return randomBytes(randomness).toString('hex');
 }
 /**
+ * TODO: [🤶] Maybe export through `@promptbook/utils` or `@promptbook/random` package
  * TODO: Maybe use nanoid instead https://github.com/ai/nanoid
  */
 
@@ -118,10 +120,13 @@ const LINES_PER_STANDARD_PAGE = 44;
  * @public exported from `@promptbook/utils`
  */
 function countLines(text) {
+    if (text === '') {
+        return 0;
+    }
     text = text.replace('\r\n', '\n');
     text = text.replace('\r', '\n');
     const lines = text.split('\n');
-    return lines.reduce((count, line) => count + Math.ceil(line.length / CHARACTERS_PER_STANDARD_LINE), 0);
+    return lines.reduce((count, line) => count + Math.max(Math.ceil(line.length / CHARACTERS_PER_STANDARD_LINE), 1), 0);
 }
 /**
  * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
@@ -602,6 +607,17 @@ function $getCurrentDate() {
     return new Date().toISOString();
 }
 
+/**
+ * Trims string from all 4 sides
+ *
+ * Note: This is a re-exported function from the `spacetrim` package which is
+ *       Developed by same author @hejny as this package
+ *
+ * @public exported from `@promptbook/utils`
+ * @see https://github.com/hejny/spacetrim#usage
+ */
+const spaceTrim = spaceTrim$1;
+
 /**
  * @private util of `@promptbook/color`
  * @de
@@ -650,6 +666,7 @@ function take(initialValue) {
  * @public exported from `@promptbook/color`
  */
 const CSS_COLORS = {
+    promptbook: '#79EAFD',
     transparent: 'rgba(0,0,0,0)',
     aliceblue: '#f0f8ff',
     antiquewhite: '#faebd7',
@@ -831,9 +848,6 @@ function checkChannelValue(channelName, value) {
         throw new Error(`${channelName} channel is greater than 255, it is ${value}`);
     }
 }
-/**
- * TODO: [🧠][🚓] Is/which combination it better to use asserts/check, validate or is utility function?
- */
 
 /**
  * Color object represents an RGB color with alpha channel
@@ -868,6 +882,28 @@ class Color {
             throw new Error(`Can not create color from given object`);
         }
     }
+    /**
+     * Creates a new Color instance from miscellaneous formats
+     * It just does not throw error when it fails, it returns PROMPTBOOK_COLOR instead
+     *
+     * @param color
+     * @returns Color object
+     */
+    static fromSafe(color) {
+        try {
+            return Color.from(color);
+        }
+        catch (error) {
+            // <- Note: Can not use `assertsError(error)` here because it causes circular dependency
+            console.warn(spaceTrim((block) => `
+                        Color.fromSafe error:
+                        ${block(error.message)}
+
+                        Returning default PROMPTBOOK_COLOR.
+                    `));
+            return Color.fromString('promptbook');
+        }
+    }
     /**
      * Creates a new Color instance from miscellaneous string formats
      *
@@ -935,6 +971,9 @@ class Color {
         if (hex.length === 3) {
             return Color.fromHex3(hex);
         }
+        if (hex.length === 4) {
+            return Color.fromHex4(hex);
+        }
         if (hex.length === 6) {
             return Color.fromHex6(hex);
         }
@@ -955,6 +994,19 @@ class Color {
         const b = parseInt(hex.substr(2, 1), 16) * 16;
         return take(new Color(r, g, b));
     }
+    /**
+     * Creates a new Color instance from color in hex format with 4 digits (with alpha channel)
+     *
+     * @param color in hex for example `09df`
+     * @returns Color object
+     */
+    static fromHex4(hex) {
+        const r = parseInt(hex.substr(0, 1), 16) * 16;
+        const g = parseInt(hex.substr(1, 1), 16) * 16;
+        const b = parseInt(hex.substr(2, 1), 16) * 16;
+        const a = parseInt(hex.substr(3, 1), 16) * 16;
+        return take(new Color(r, g, b, a));
+    }
     /**
      * Creates a new Color instance from color in hex format with 6 color digits (without alpha channel)
      *
@@ -1145,7 +1197,8 @@ class Color {
      * @returns true if the value is a valid hex color string (e.g., `#009edd`, `#fff`, etc.)
      */
     static isHexColorString(value) {
-        return typeof value === 'string' && /^#(?:[0-9a-fA-F]{3}){1,2}$/.test(value);
+        return (typeof value === 'string' &&
+            /^#(?:[0-9a-fA-F]{3}|[0-9a-fA-F]{4}|[0-9a-fA-F]{6}|[0-9a-fA-F]{8})$/.test(value));
     }
     /**
      * Creates new Color object
@@ -1260,6 +1313,23 @@ class Color {
  * TODO: Maybe connect with textures
  */
 
+/**
+ * Makes color transformer which returns a grayscale version of the color
+ *
+ * @param amount from 0 to 1
+ *
+ * @public exported from `@promptbook/color`
+ */
+function grayscale(amount) {
+    return ({ red, green, blue, alpha }) => {
+        const average = (red + green + blue) / 3;
+        red = Math.round(average * amount + red * (1 - amount));
+        green = Math.round(average * amount + green * (1 - amount));
+        blue = Math.round(average * amount + blue * (1 - amount));
+        return Color.fromValues(red, green, blue, alpha);
+    };
+}
+
 /**
  * Converts HSL values to RGB values
  *
@@ -1375,102 +1445,6 @@ function lighten(amount) {
  * TODO: Maybe implement by mix+hsl
  */
 
-/**
- * Calculates distance between two colors
- *
- * @param color1 first color
- * @param color2 second color
- *
- * Note: This function is inefficient. Use colorDistanceSquared instead if possible.
- *
- * @public exported from `@promptbook/color`
- */
-/**
- * Calculates distance between two colors without square root
- *
- * @param color1 first color
- * @param color2 second color
- *
- * @public exported from `@promptbook/color`
- */
-function colorDistanceSquared(color1, color2) {
-    const rmean = (color1.red + color2.red) / 2;
-    const r = color1.red - color2.red;
-    const g = color1.green - color2.green;
-    const b = color1.blue - color2.blue;
-    const weightR = 2 + rmean / 256;
-    const weightG = 4.0;
-    const weightB = 2 + (255 - rmean) / 256;
-    const distance = weightR * r * r + weightG * g * g + weightB * b * b;
-    return distance;
-}
-
-/**
- * Makes color transformer which finds the nearest color from the given list
- *
- * @param colors array of colors to choose from
- *
- * @public exported from `@promptbook/color`
- */
-function nearest(...colors) {
-    return (color) => {
-        const distances = colors.map((c) => colorDistanceSquared(c, color));
-        const minDistance = Math.min(...distances);
-        const minIndex = distances.indexOf(minDistance);
-        const nearestColor = colors[minIndex];
-        return nearestColor;
-    };
-}
-
-/**
- * Color transformer which returns the negative color
- *
- * @public exported from `@promptbook/color`
- */
-function negative(color) {
-    const r = 255 - color.red;
-    const g = 255 - color.green;
-    const b = 255 - color.blue;
-    return Color.fromValues(r, g, b, color.alpha);
-}
-
-/**
- * Makes color transformer which finds the furthest color from the given list
- *
- * @param colors array of colors to choose from
- *
- * @public exported from `@promptbook/color`
- */
-function furthest(...colors) {
-    return (color) => {
-        const furthestColor = negative(nearest(...colors.map(negative))(color));
-        return furthestColor;
-    };
-}
-/**
- * Makes color transformer which finds the best text color (black or white) for the given background color
- *
- * @public exported from `@promptbook/color`
- */
-furthest(Color.get('white'), Color.from('black'));
-
-/**
- * Makes color transformer which returns a grayscale version of the color
- *
- * @param amount from 0 to 1
- *
- * @public exported from `@promptbook/color`
- */
-function grayscale(amount) {
-    return ({ red, green, blue, alpha }) => {
-        const average = (red + green + blue) / 3;
-        red = Math.round(average * amount + red * (1 - amount));
-        green = Math.round(average * amount + green * (1 - amount));
-        blue = Math.round(average * amount + blue * (1 - amount));
-        return Color.fromValues(red, green, blue, alpha);
-    };
-}
-
 /**
  * Makes color transformer which saturate the given color
  *
@@ -1519,16 +1493,32 @@ const ADMIN_GITHUB_NAME = 'hejny';
  *
  * @public exported from `@promptbook/core`
  */
-const PROMPTBOOK_COLOR = Color.fromHex('#79EAFD');
-// <- TODO: [🧠] Using `Color` here increases the package size approx 3kb, maybe remove it
+const PROMPTBOOK_COLOR = Color.fromString('promptbook');
+// <- TODO: [🧠][🈵] Using `Color` here increases the package size approx 3kb, maybe remove it
+/**
+ * Colors for syntax highlighting in the `<BookEditor/>`
+ *
+ * TODO: [🗽] Unite branding and make single place for it
+ *
+ * @public exported from `@promptbook/core`
+ */
+({
+    TITLE: Color.fromHex('#244EA8'),
+    LINE: Color.fromHex('#eeeeee'),
+    SEPARATOR: Color.fromHex('#cccccc'),
+    COMMITMENT: Color.fromHex('#DA0F78'),
+    PARAMETER: Color.fromHex('#8e44ad'),
+});
+// <- TODO: [🧠][🈵] Using `Color` here increases the package size approx 3kb, maybe remove it
 /**
- * Dark color of the Promptbook
+ * Chat color of the Promptbook (in chat)
  *
  * TODO: [🗽] Unite branding and make single place for it
  *
  * @public exported from `@promptbook/core`
  */
 PROMPTBOOK_COLOR.then(lighten(0.1)).then(saturate(0.9)).then(grayscale(0.9));
+// <- TODO: [🧠][🈵] Using `Color` and `lighten`, `saturate`,... here increases the package size approx 3kb, maybe remove it
 /**
  * Color of the user (in chat)
  *
@@ -1612,7 +1602,7 @@ function orderJson(options) {
 function getErrorReportUrl(error) {
     const report = {
         title: `🐜 Error report from ${NAME}`,
-        body: spaceTrim((block) => `
+        body: spaceTrim$2((block) => `
 
 
             \`${error.name || 'Error'}\` has occurred in the [${NAME}], please look into it @${ADMIN_GITHUB_NAME}.
@@ -1770,7 +1760,7 @@ function checkSerializableAsJson(options) {
     }
     else if (typeof value === 'object') {
         if (value instanceof Date) {
-            throw new UnexpectedError(spaceTrim((block) => `
+            throw new UnexpectedError(spaceTrim$2((block) => `
                         \`${name}\` is Date
 
                         Use \`string_date_iso8601\` instead
@@ -1789,7 +1779,7 @@ function checkSerializableAsJson(options) {
             throw new UnexpectedError(`${name} is RegExp`);
         }
         else if (value instanceof Error) {
-            throw new UnexpectedError(spaceTrim((block) => `
+            throw new UnexpectedError(spaceTrim$2((block) => `
                         \`${name}\` is unserialized Error
 
                         Use function \`serializeError\`
@@ -1812,7 +1802,7 @@ function checkSerializableAsJson(options) {
             }
             catch (error) {
                 assertsError(error);
-                throw new UnexpectedError(spaceTrim((block) => `
+                throw new UnexpectedError(spaceTrim$2((block) => `
                             \`${name}\` is not serializable
 
                             ${block(error.stack || error.message)}
@@ -1844,7 +1834,7 @@ function checkSerializableAsJson(options) {
         }
     }
     else {
-        throw new UnexpectedError(spaceTrim((block) => `
+        throw new UnexpectedError(spaceTrim$2((block) => `
                     \`${name}\` is unknown type
 
                     Additional message for \`${name}\`:
@@ -1874,7 +1864,7 @@ function deepClone(objectValue) {
     TODO: [🧠] Is there a better implementation?
     > const propertyNames = Object.getOwnPropertyNames(objectValue);
     > for (const propertyName of propertyNames) {
-    >     const value = (objectValue as really_any)[propertyName];
+    >     const value = (objectValue as chococake)[propertyName];
     >     if (value && typeof value === 'object') {
     >         deepClone(value);
     >     }
@@ -2208,7 +2198,7 @@ function createExecutionToolsFromVercelProvider(options) {
             const modelName = modelRequirements.modelName ||
                 ((_a = availableModels.find(({ modelVariant }) => modelVariant === 'CHAT')) === null || _a === void 0 ? void 0 : _a.modelName);
             if (!modelName) {
-                throw new PipelineExecutionError(spaceTrim(`
+                throw new PipelineExecutionError(spaceTrim$2(`
                         Can not determine which model to use.
 
                         You need to provide at least one of:
@@ -2226,7 +2216,7 @@ function createExecutionToolsFromVercelProvider(options) {
             let promptMessages;
             if ('thread' in prompt && Array.isArray(prompt.thread)) {
                 promptMessages = prompt.thread.map((msg) => ({
-                    role: msg.role === 'assistant' ? 'assistant' : (msg.role === 'system' ? 'system' : 'user'),
+                    role: msg.role === 'assistant' ? 'assistant' : msg.role === 'system' ? 'system' : 'user',
                     content: [
                         {
                             type: 'text',