@promptbook/cli 0.66.0-0 → 0.66.0-1

package/esm/typings/src/_packages/anthropic-claude.index.d.ts

@@ -5,6 +5,7 @@ import type { AnthropicClaudeExecutionToolsOptions } from '../llm-providers/anth
 import type { AnthropicClaudeExecutionToolsDirectOptions } from '../llm-providers/anthropic-claude/AnthropicClaudeExecutionToolsOptions';
 import type { AnthropicClaudeExecutionToolsProxiedOptions } from '../llm-providers/anthropic-claude/AnthropicClaudeExecutionToolsOptions';
 import { createAnthropicClaudeExecutionTools } from '../llm-providers/anthropic-claude/createAnthropicClaudeExecutionTools';
+import { _ } from '../llm-providers/anthropic-claude/register1';
 export { PROMPTBOOK_VERSION };
 export { ANTHROPIC_CLAUDE_MODELS };
 export { AnthropicClaudeExecutionTools };
@@ -12,3 +13,4 @@ export type { AnthropicClaudeExecutionToolsOptions };
 export type { AnthropicClaudeExecutionToolsDirectOptions };
 export type { AnthropicClaudeExecutionToolsProxiedOptions };
 export { createAnthropicClaudeExecutionTools };
+export { _ };

package/esm/typings/src/_packages/core.index.d.ts

@@ -15,6 +15,9 @@ import { MAX_KNOWLEDGE_SOURCES_SCRAPING_TOTAL } from '../config';
 import { EXECUTIONS_CACHE_DIRNAME } from '../config';
 import { PIPELINE_COLLECTION_BASE_FILENAME } from '../config';
 import { RESERVED_PARAMETER_NAMES } from '../config';
+import { DEFAULT_REMOTE_URL } from '../config';
+import { DEFAULT_REMOTE_URL_PATH } from '../config';
+import { BOILERPLATE_LLM_TOOLS_CONFIGURATION_ } from '../config';
 import { pipelineJsonToString } from '../conversion/pipelineJsonToString';
 import type { PipelineStringToJsonOptions } from '../conversion/pipelineStringToJson';
 import { pipelineStringToJson } from '../conversion/pipelineStringToJson';
@@ -45,7 +48,6 @@ import { CallbackInterfaceTools } from '../knowledge/dialogs/callback/CallbackIn
 import type { CallbackInterfaceToolsOptions } from '../knowledge/dialogs/callback/CallbackInterfaceToolsOptions';
 import { prepareKnowledgePieces } from '../knowledge/prepare-knowledge/_common/prepareKnowledgePieces';
 import { prepareKnowledgeFromMarkdown } from '../knowledge/prepare-knowledge/markdown/prepareKnowledgeFromMarkdown';
-import { LLM_CONFIGURATION_BOILERPLATES } from '../llm-providers/_common/config';
 import { createLlmToolsFromConfiguration } from '../llm-providers/_common/createLlmToolsFromConfiguration';
 import { cacheLlmTools } from '../llm-providers/_common/utils/cache/cacheLlmTools';
 import { countTotalUsage } from '../llm-providers/_common/utils/count-total-usage/countTotalUsage';
@@ -80,6 +82,9 @@ export { MAX_KNOWLEDGE_SOURCES_SCRAPING_TOTAL };
 export { EXECUTIONS_CACHE_DIRNAME };
 export { PIPELINE_COLLECTION_BASE_FILENAME };
 export { RESERVED_PARAMETER_NAMES };
+export { DEFAULT_REMOTE_URL };
+export { DEFAULT_REMOTE_URL_PATH };
+export { BOILERPLATE_LLM_TOOLS_CONFIGURATION_ };
 export { pipelineJsonToString };
 export type { PipelineStringToJsonOptions };
 export { pipelineStringToJson };
@@ -110,7 +115,6 @@ export { CallbackInterfaceTools };
 export type { CallbackInterfaceToolsOptions };
 export { prepareKnowledgePieces };
 export { prepareKnowledgeFromMarkdown };
-export { LLM_CONFIGURATION_BOILERPLATES };
 export { createLlmToolsFromConfiguration };
 export { cacheLlmTools };
 export { countTotalUsage };

package/esm/typings/src/config.d.ts

@@ -1,3 +1,4 @@
+import type { LlmToolsConfiguration } from './llm-providers/_common/LlmToolsConfiguration';
 /**
  * Warning message for the generated sections and files files
  *
@@ -107,9 +108,30 @@ export declare const RESERVED_PARAMETER_RESTRICTED: string;
 export declare const MOMENT_ARG_THRESHOLDS: {
     readonly ss: 3;
 };
+/**
+ * @@@
+ *
+ * @public exported from `@promptbook/core`
+ */
+export declare const DEFAULT_REMOTE_URL = "https://api.pavolhejny.com/";
+/**
+ * @@@
+ *
+ * @public exported from `@promptbook/core`
+ */
+export declare const DEFAULT_REMOTE_URL_PATH = "/promptbook/socket.io";
+/**
+ * @@@
+ *
+ * @public exported from `@promptbook/core`
+ */
+export declare const BOILERPLATE_LLM_TOOLS_CONFIGURATION_: LlmToolsConfiguration;
 /**
  * @@@
  *
  * @private within the repository
  */
 export declare const DEBUG_ALLOW_PAYED_TESTING: boolean;
+/**
+ * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
+ */

package/esm/typings/src/execution/LlmExecutionTools.d.ts

@@ -28,6 +28,16 @@ export type LlmExecutionTools = {
      * @example "Use all models from OpenAI"
      */
     readonly description: string_markdown;
+    /**
+     * Check comfiguration
+     *
+     * @returns nothing if configuration is correct
+     * @throws {Error} if configuration is incorrect
+     */
+    /**
+     * List all available models that can be used
+     */
+    listModels(): Promisable<Array<AvailableModel>>;
     /**
      * Calls a chat model
      */
@@ -40,10 +50,6 @@ export type LlmExecutionTools = {
      * Calls an embedding model
      */
     callEmbeddingModel?(prompt: Prompt): Promise<EmbeddingPromptResult>;
-    /**
-     * List all available models that can be used
-     */
-    listModels(): Promisable<Array<AvailableModel>>;
 };
 /**
  * Represents a model that can be used for prompt execution
@@ -63,8 +69,8 @@ export type AvailableModel = {
     readonly modelVariant: ModelVariant;
 };
 /**
+ * TODO: Implement destroyable pattern to free resources
  * TODO: [🏳] Add `callTranslationModel`
- * TODO: Maybe reorder `listModels` and put it befor `callChatModel`, `callCompletionModel`, `callEmbeddingModel`
  * TODO: [🧠] Emulation of one type of model with another one - emuate chat with completion; emulate translation with chat
  * TODO: [🍓][♐] Some heuristic to pick the best model in listed models
  * TODO: [🧠] Should or should not there be a word "GPT" in both callCompletionModel and callChatModel

package/esm/typings/src/llm-providers/_common/config.d.ts

@@ -1,15 +1,10 @@
 import type { LlmExecutionTools } from '../../execution/LlmExecutionTools';
 import type { TODO_any } from '../../utils/organization/TODO_any';
-import type { LlmToolsConfiguration } from './LlmToolsConfiguration';
-/**
- * @public exported from `@promptbook/core`
- */
-export declare const LLM_CONFIGURATION_BOILERPLATES: LlmToolsConfiguration;
 /**
  * @private internal type for `createLlmToolsFromConfiguration`
  */
 export declare const EXECUTION_TOOLS_CLASSES: Record<`create${string}`, (options: TODO_any) => LlmExecutionTools>;
 /**
- * TODO: [🧠] Better file name than `config.ts` + maybe move to two separate files
+ * TODO: !!!!!!! Make global register for this
  * TODO: [🧠][🎌] Adding this should be responsibility of each provider package NOT this one central place
  */

package/esm/typings/src/llm-providers/anthropic-claude/computeAnthropicClaudeUsage.d.ts

@@ -0,0 +1,18 @@
+import type Anthropic from '@anthropic-ai/sdk';
+import type { PartialDeep } from 'type-fest';
+import type { PromptResultUsage } from '../../execution/PromptResultUsage';
+import type { Prompt } from '../../types/Prompt';
+/**
+ * Computes the usage of the Anthropic Claude API based on the response from Anthropic Claude
+ *
+ * @param promptContent The content of the prompt
+ * @param resultContent The content of the result (for embedding prompts or failed prompts pass empty string)
+ * @param rawResponse The raw response from Anthropic Claude API
+ * @throws {PipelineExecutionError} If the usage is not defined in the response from Anthropic Claude
+ * @private internal utility of `AnthropicClaudeExecutionTools`
+ */
+export declare function computeAnthropicClaudeUsage(promptContent: Prompt['content'], // <- Note: Intentionally using [] to access type properties to bring jsdoc from Prompt/PromptResult to consumer
+resultContent: string, rawResponse: PartialDeep<Pick<Anthropic.Messages.Message, 'model' | 'usage'>>): PromptResultUsage;
+/**
+ * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+ */

package/esm/typings/src/llm-providers/anthropic-claude/computeAnthropicClaudeUsage.test.d.ts

@@ -0,0 +1,4 @@
+export {};
+/**
+ * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+ */

package/esm/typings/src/llm-providers/anthropic-claude/register1.d.ts

@@ -0,0 +1,4 @@
+/**
+ * @public exported from `@promptbook/anthropic-claude`
+ */
+export declare const _: undefined;

package/esm/typings/src/llm-providers/openai/computeOpenaiUsage.d.ts

@@ -1,4 +1,5 @@
 import type OpenAI from 'openai';
+import type { PartialDeep } from 'type-fest';
 import type { PromptResultUsage } from '../../execution/PromptResultUsage';
 import type { Prompt } from '../../types/Prompt';
 /**
@@ -11,4 +12,7 @@ import type { Prompt } from '../../types/Prompt';
  * @private internal utility of `OpenAiExecutionTools`
  */
 export declare function computeOpenaiUsage(promptContent: Prompt['content'], // <- Note: Intentionally using [] to access type properties to bring jsdoc from Prompt/PromptResult to consumer
-resultContent: string, rawResponse: Pick<OpenAI.Chat.Completions.ChatCompletion | OpenAI.Completions.Completion | OpenAI.Embeddings.CreateEmbeddingResponse, 'model' | 'usage'>): PromptResultUsage;
+resultContent: string, rawResponse: PartialDeep<Pick<OpenAI.Chat.Completions.ChatCompletion | OpenAI.Completions.Completion | OpenAI.Embeddings.CreateEmbeddingResponse, 'model' | 'usage'>>): PromptResultUsage;
+/**
+ * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+ */

package/esm/typings/src/llm-providers/openai/computeOpenaiUsage.test.d.ts

@@ -1 +1,4 @@
 export {};
+/**
+ * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+ */

package/esm/typings/src/llm-providers/remote/interfaces/RemoteLlmExecutionToolsOptions.d.ts

@@ -25,7 +25,7 @@ export type RemoteLlmExecutionToolsOptions = CommonExecutionToolsOptions & {
     /**
      * If set, only these models will be listed as available
      *
-     * TODO: [🧠] !!!! Figure out better solution
+     * TODO: [🧠] !!!!!! Figure out better solution
      */
     readonly models?: Array<AvailableModel>;
     /**
@@ -51,3 +51,6 @@ export type RemoteLlmExecutionToolsOptions = CommonExecutionToolsOptions & {
      */
     readonly clientId: client_id;
 });
+/**
+ * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
+ */ 

package/esm/typings/src/utils/environment/getGlobalScope.d.ts

@@ -7,3 +7,6 @@ import type { really_any } from '../organization/really_any';
  * @public exported from `@promptbook/utils`
  */
 export declare function $getGlobalScope(): really_any;
+/***
+ * TODO: !!!!! Make private and promptbook registry from this
+ */ 

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@promptbook/cli",
-    "version": "0.66.0-0",
+    "version": "0.66.0-1",
     "description": "Supercharge your use of large language models",
     "private": false,
     "sideEffects": false,

package/umd/index.umd.js

@@ -39,7 +39,7 @@
     /**
      * The version of the Promptbook library
      */
-    var PROMPTBOOK_VERSION = '0.65.0';
+    var PROMPTBOOK_VERSION = '0.66.0-0';
     // TODO: !!!! List here all the versions and annotate + put into script
 
     /*! *****************************************************************************
@@ -322,6 +322,9 @@
      * @private within the repository
      */
     var RESERVED_PARAMETER_RESTRICTED = 'RESTRICTED-' + REPLACING_NONCE;
+    /**
+     * TODO: [🧠][🧜‍♂️] Maybe join remoteUrl and path into single value
+     */
 
     /**
      * Initializes `about` command for Promptbook CLI utilities
@@ -851,7 +854,7 @@
         });
     }
 
-    var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n-   Make pieces of information concise, clear, and easy to understand\n-   One piece of information should be approximately 1 paragraph\n-   Divide the paragraphs by markdown horizontal lines ---\n-   Omit irrelevant information\n-   Group redundant information\n-   Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",dependentParameterNames:["knowledgeContent"],resultingParameterName:"knowledgePieces"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n-   Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear\n-   Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.65.0",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",modelRequirements:{modelVariant:"CHAT",modelName:"gpt-4-turbo"},content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n### Option `modelName`\n\nPick from the following models:\n\n-   {availableModelNames}\n\n### Option `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Option `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n-   `0.1`: Low temperature, extremely conservative and deterministic\n-   `0.5`: Medium temperature, balanced between conservative and creative\n-   `1.0`: High temperature, creative and bit random\n-   `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n-   `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",expectFormat:"JSON",dependentParameterNames:["availableModelNames","personaDescription"],resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
+    var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n-   Make pieces of information concise, clear, and easy to understand\n-   One piece of information should be approximately 1 paragraph\n-   Divide the paragraphs by markdown horizontal lines ---\n-   Omit irrelevant information\n-   Group redundant information\n-   Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",dependentParameterNames:["knowledgeContent"],resultingParameterName:"knowledgePieces"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n-   Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n-   Write just title, nothing else\n-   Title should be concise and clear\n-   Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.66.0-0",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",modelRequirements:{modelVariant:"CHAT",modelName:"gpt-4-turbo"},content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n### Option `modelName`\n\nPick from the following models:\n\n-   {availableModelNames}\n\n### Option `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Option `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n-   `0.1`: Low temperature, extremely conservative and deterministic\n-   `0.5`: Medium temperature, balanced between conservative and creative\n-   `1.0`: High temperature, creative and bit random\n-   `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n-   `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",expectFormat:"JSON",dependentParameterNames:["availableModelNames","personaDescription"],resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
 
     /**
      * This error indicates that the promptbook in a markdown format cannot be parsed into a valid promptbook object
@@ -6825,6 +6828,15 @@
      * TODO: [🎰] Some mechanism to auto-update available models
      */
 
+    /**
+     * Get current date in ISO 8601 format
+     *
+     * @private internal utility
+     */
+    function getCurrentIsoDate() {
+        return new Date().toISOString();
+    }
+
     /**
      * Helper of usage compute
      *
@@ -6859,13 +6871,42 @@
     }
 
     /**
-     * Get current date in ISO 8601 format
+     * Computes the usage of the Anthropic Claude API based on the response from Anthropic Claude
      *
-     * @private internal utility
+     * @param promptContent The content of the prompt
+     * @param resultContent The content of the result (for embedding prompts or failed prompts pass empty string)
+     * @param rawResponse The raw response from Anthropic Claude API
+     * @throws {PipelineExecutionError} If the usage is not defined in the response from Anthropic Claude
+     * @private internal utility of `AnthropicClaudeExecutionTools`
      */
-    function getCurrentIsoDate() {
-        return new Date().toISOString();
+    function computeAnthropicClaudeUsage(promptContent, // <- Note: Intentionally using [] to access type properties to bring jsdoc from Prompt/PromptResult to consumer
+    resultContent, rawResponse) {
+        var _a, _b;
+        if (rawResponse.usage === undefined) {
+            throw new PipelineExecutionError('The usage is not defined in the response from Anthropic Claude');
+        }
+        if (((_a = rawResponse.usage) === null || _a === void 0 ? void 0 : _a.input_tokens) === undefined) {
+            throw new PipelineExecutionError('In Anthropic Claude response `usage.prompt_tokens` not defined');
+        }
+        var inputTokens = rawResponse.usage.input_tokens;
+        var outputTokens = ((_b = rawResponse.usage) === null || _b === void 0 ? void 0 : _b.output_tokens) || 0;
+        var modelInfo = ANTHROPIC_CLAUDE_MODELS.find(function (model) { return model.modelName === rawResponse.model; });
+        var price;
+        if (modelInfo === undefined || modelInfo.pricing === undefined) {
+            price = uncertainNumber();
+        }
+        else {
+            price = uncertainNumber(inputTokens * modelInfo.pricing.prompt + outputTokens * modelInfo.pricing.output);
+        }
+        return {
+            price: price,
+            input: __assign({ tokensCount: uncertainNumber(rawResponse.usage.input_tokens) }, computeUsageCounts(promptContent)),
+            output: __assign({ tokensCount: uncertainNumber(outputTokens) }, computeUsageCounts(resultContent)),
+        };
     }
+    /**
+     * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+     */
 
     /**
      * Execution Tools for calling Anthropic Claude API.
@@ -6886,9 +6927,8 @@
             var anthropicOptions = __assign({}, options);
             delete anthropicOptions.isVerbose;
             delete anthropicOptions.isProxied;
-            this.client = new Anthropic__default["default"](
-            //            <- TODO: [🧱] Implement in a functional (not new Class) way
-            anthropicOptions);
+            this.client = new Anthropic__default["default"](anthropicOptions);
+            // <- TODO: !!!!!! Lazy-load client
         }
         Object.defineProperty(AnthropicClaudeExecutionTools.prototype, "title", {
             get: function () {
@@ -6959,15 +6999,10 @@
                             if (contentBlock.type !== 'text') {
                                 throw new PipelineExecutionError("Returned content is not \"text\" type but \"".concat(contentBlock.type, "\""));
                             }
-                            console.log('!!!!!! rawResponse.usage', rawResponse.usage);
                             resultContent = contentBlock.text;
                             // eslint-disable-next-line prefer-const
                             complete = getCurrentIsoDate();
-                            usage = {
-                                price: { value: 0, isUncertain: true } /* <- TODO: [🐞] !!!!!! Compute usage */,
-                                input: __assign({ tokensCount: uncertainNumber(rawResponse.usage.input_tokens) }, computeUsageCounts(prompt.content)),
-                                output: __assign({ tokensCount: uncertainNumber(rawResponse.usage.output_tokens) }, computeUsageCounts(prompt.content)),
-                            };
+                            usage = computeAnthropicClaudeUsage(content, '', rawResponse);
                             return [2 /*return*/, {
                                     content: resultContent,
                                     modelName: rawResponse.model,
@@ -7492,9 +7527,8 @@
             this.options = options;
             this.client = new openai.OpenAIClient(
             //            <- TODO: [🧱] Implement in a functional (not new Class) way
-            "https://".concat(options.resourceName, ".openai.azure.com/"), new openai.AzureKeyCredential(
-            //            <- TODO: [🧱] Implement in a functional (not new Class) way
-            options.apiKey));
+            "https://".concat(options.resourceName, ".openai.azure.com/"), new openai.AzureKeyCredential(options.apiKey));
+            // <- TODO: !!!!!! Lazy-load client
         }
         Object.defineProperty(AzureOpenAiExecutionTools.prototype, "title", {
             get: function () {
@@ -7764,6 +7798,9 @@
             output: __assign({ tokensCount: uncertainNumber(outputTokens) }, computeUsageCounts(resultContent)),
         };
     }
+    /**
+     * TODO: [🤝] DRY Maybe some common abstraction between `computeOpenaiUsage` and `computeAnthropicClaudeUsage`
+     */
 
     /**
      * Execution Tools for calling OpenAI API.
@@ -7784,6 +7821,7 @@
             delete openAiOptions.isVerbose;
             delete openAiOptions.user;
             this.client = new OpenAI__default["default"](__assign({}, openAiOptions));
+            // <- TODO: !!!!!! Lazy-load client
         }
         Object.defineProperty(OpenAiExecutionTools.prototype, "title", {
             get: function () {
@@ -8085,7 +8123,7 @@
         // <- Note: [🦑] Add here new LLM provider
     };
     /**
-     * TODO: [🧠] Better file name than `config.ts` + maybe move to two separate files
+     * TODO: !!!!!!! Make global register for this
      * TODO: [🧠][🎌] Adding this should be responsibility of each provider package NOT this one central place
      */