@promptbook/node 0.61.0-11 → 0.61.0-13

package/esm/index.es.js

@@ -124,6 +124,39 @@ function __spreadArray(to, from, pack) {
     return to.concat(ar || Array.prototype.slice.call(from));
 }
 
+/**
+ * @@@
+ *
+ * @returns The same object as the input, but deeply frozen
+ *
+ * Note: This function mutates the object
+ */
+function deepFreeze(objectValue) {
+    var e_1, _a;
+    var propertyNames = Object.getOwnPropertyNames(objectValue);
+    try {
+        for (var propertyNames_1 = __values(propertyNames), propertyNames_1_1 = propertyNames_1.next(); !propertyNames_1_1.done; propertyNames_1_1 = propertyNames_1.next()) {
+            var propertyName = propertyNames_1_1.value;
+            var value = objectValue[propertyName];
+            if (value && typeof value === 'object') {
+                deepFreeze(value);
+            }
+        }
+    }
+    catch (e_1_1) { e_1 = { error: e_1_1 }; }
+    finally {
+        try {
+            if (propertyNames_1_1 && !propertyNames_1_1.done && (_a = propertyNames_1.return)) _a.call(propertyNames_1);
+        }
+        finally { if (e_1) throw e_1.error; }
+    }
+    return Object.freeze(objectValue);
+}
+/**
+ * TODO: [🔼] Export from `@promptbook/utils`
+ * TODO: [🧠] Is there a way how to meaningfully test this utility
+ */
+
 /**
  * The maximum number of iterations for a loops
  */
@@ -139,43 +172,74 @@ var PIPELINE_COLLECTION_BASE_FILENAME = "index";
 /**
  * The names of the parameters that are reserved for special purposes
  */
-var RESERVED_PARAMETER_NAMES = [
+var RESERVED_PARAMETER_NAMES = deepFreeze([
     'context',
     // <- TODO: Add more like 'date', 'modelName',...
     // <- TODO: Add [emoji] + instructions ACRY when adding new reserved parameter
-];
+]);
+/*
+TODO: !!! Just testing false-negative detection of [🟡][🟢][🔵][⚪] leak
+*/
+// [🟡][🟢][🔵][⚪]
 
+/**
+ * @@@
+ */
+function deepClone(objectValue) {
+    return JSON.parse(JSON.stringify(objectValue));
+    /*
+    TODO: [🧠] Is there a better implementation?
+    > const propertyNames = Object.getOwnPropertyNames(objectValue);
+    > for (const propertyName of propertyNames) {
+    >     const value = (objectValue as really_any)[propertyName];
+    >     if (value && typeof value === 'object') {
+    >         deepClone(value);
+    >     }
+    > }
+    > return Object.assign({}, objectValue);
+    */
+}
+/**
+ * TODO: [🔼] Export from `@promptbook/utils`
+ * TODO: [🧠] Is there a way how to meaningfully test this utility
+ */
+
+/**
+ * @@@
+ *
+ * TODO: [🔼] Export with addUsage
+ */
+var ZERO_USAGE = deepFreeze({
+    price: { value: 0 },
+    input: {
+        tokensCount: { value: 0 },
+        charactersCount: { value: 0 },
+        wordsCount: { value: 0 },
+        sentencesCount: { value: 0 },
+        linesCount: { value: 0 },
+        paragraphsCount: { value: 0 },
+        pagesCount: { value: 0 },
+    },
+    output: {
+        tokensCount: { value: 0 },
+        charactersCount: { value: 0 },
+        wordsCount: { value: 0 },
+        sentencesCount: { value: 0 },
+        linesCount: { value: 0 },
+        paragraphsCount: { value: 0 },
+        pagesCount: { value: 0 },
+    },
+});
 /**
  * Function `addUsage` will add multiple usages into one
  *
- * Note: If you provide 0 values, it returns void usage
+ * Note: If you provide 0 values, it returns ZERO_USAGE
  */
 function addUsage() {
     var usageItems = [];
     for (var _i = 0; _i < arguments.length; _i++) {
         usageItems[_i] = arguments[_i];
     }
-    var initialStructure = {
-        price: { value: 0 },
-        input: {
-            tokensCount: { value: 0 },
-            charactersCount: { value: 0 },
-            wordsCount: { value: 0 },
-            sentencesCount: { value: 0 },
-            linesCount: { value: 0 },
-            paragraphsCount: { value: 0 },
-            pagesCount: { value: 0 },
-        },
-        output: {
-            tokensCount: { value: 0 },
-            charactersCount: { value: 0 },
-            wordsCount: { value: 0 },
-            sentencesCount: { value: 0 },
-            linesCount: { value: 0 },
-            paragraphsCount: { value: 0 },
-            pagesCount: { value: 0 },
-        },
-    };
     return usageItems.reduce(function (acc, item) {
         var e_1, _a, e_2, _b;
         var _c;
@@ -233,7 +297,7 @@ function addUsage() {
             finally { if (e_2) throw e_2.error; }
         }
         return acc;
-    }, initialStructure);
+    }, deepClone(ZERO_USAGE));
 }
 
 /**
@@ -310,7 +374,7 @@ function forEachAsync(array, options, callbackfunction) {
     });
 }
 
-var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.61.0-10",parameters:[{name:"content",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledge",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{name:"knowledge",title:"Knowledge",dependentParameterNames:["content"],blockType:"PROMPT_TEMPLATE",personaName:null,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> {content}",resultingParameterName:"knowledge"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-10",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.61.0-10",parameters:[{name:"content",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{name:"knowledge",title:"Knowledge",dependentParameterNames:["content"],blockType:"PROMPT_TEMPLATE",personaName:null,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> {content}",resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-10",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.61.0-10",parameters:[{name:"content",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{name:"knowledge",title:"Knowledge",dependentParameterNames:["content"],blockType:"PROMPT_TEMPLATE",expectations:{words:{min:1,max:8}},personaName:null,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> {content}",resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-10",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.61.0-10",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:[{name:"make-model-requirements",title:"Make modelRequirements",dependentParameterNames:["availableModelNames","personaDescription"],blockType:"PROMPT_TEMPLATE",expectFormat:"JSON",personaName:null,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}",resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-10",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],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:"0.61.0-12",parameters:[{name:"content",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledge",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{name:"knowledge",title:"Knowledge",dependentParameterNames:["content"],blockType:"PROMPT_TEMPLATE",personaName:null,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> {content}",resultingParameterName:"knowledge"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-12",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.61.0-12",parameters:[{name:"content",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{name:"knowledge",title:"Knowledge",dependentParameterNames:["content"],blockType:"PROMPT_TEMPLATE",personaName:null,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> {content}",resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-12",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.61.0-12",parameters:[{name:"content",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{name:"knowledge",title:"Knowledge",dependentParameterNames:["content"],blockType:"PROMPT_TEMPLATE",expectations:{words:{min:1,max:8}},personaName:null,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> {content}",resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-12",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.61.0-12",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:[{name:"make-model-requirements",title:"Make modelRequirements",dependentParameterNames:["availableModelNames","personaDescription"],blockType:"PROMPT_TEMPLATE",expectFormat:"JSON",personaName:null,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}",resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-12",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
 
 /**
  * Prettify the html code
@@ -550,7 +614,7 @@ function promptTemplateParameterJsonToString(promptTemplateParameterJson) {
     return parameterString;
 }
 /**
- * TODO: !!!!! Implement new features and commands into `promptTemplateParameterJsonToString`
+ * TODO: !!!! Implement new features and commands into `promptTemplateParameterJsonToString`
  * TODO: [🧠] Is there a way to auto-detect missing features in pipelineJsonToString
  * TODO: Escape all
  */
@@ -890,6 +954,7 @@ function validatePipeline(pipeline) {
     var loopLimit = LOOP_LIMIT;
     var _loop_2 = function () {
         if (loopLimit-- < 0) {
+            // Note: Really UnexpectedError not LimitReachedError - this should not happen and be caught below
             throw new UnexpectedError('Loop limit reached during detection of circular dependencies in `validatePipeline`');
         }
         var currentlyResovedTemplates = unresovedTemplates.filter(function (template) {
@@ -928,7 +993,9 @@ function validatePipeline(pipeline) {
  *     >  ex port function validatePipeline(promptbook: unknown): asserts promptbook is PipelineJson {
  */
 /**
- * TODO: [🧠] !!!!! Validate new things
+ * TODO: [🧠][🐣] !!!! Validate that all samples match expectations
+ * TODO: [🧠][🐣] !!!! Validate that knowledge is valid (non-void)
+ * TODO: [🧠] !!! Validationg not only logic itself but imports around - files and websites and rerefenced pipelines exists
  * TODO: [🛠] Actions, instruments (and maybe knowledge) => Functions and tools
  */
 
@@ -971,7 +1038,7 @@ var SimplePipelineCollection = /** @class */ (function () {
     /**
      * Constructs a pipeline collection from promptbooks
      *
-     * @param promptbooks !!!
+     * @param promptbooks @@@
      *
      * @private Use instead `createCollectionFromJson`
      * Note: During the construction logic of all promptbooks are validated
@@ -1730,7 +1797,7 @@ function arrayableToArray(input) {
 /**
  * The version of the Promptbook library
  */
-var PROMPTBOOK_VERSION = '0.61.0-10';
+var PROMPTBOOK_VERSION = '0.61.0-12';
 // TODO: !!!! List here all the versions and annotate + put into script
 
 /**
@@ -1843,6 +1910,20 @@ function checkExpectations(expectations, value) {
  * TODO: [💝] Unite object for expecting amount and format
  */
 
+/**
+ * This error type indicates that some limit was reached
+ */
+var LimitReachedError = /** @class */ (function (_super) {
+    __extends(LimitReachedError, _super);
+    function LimitReachedError(message) {
+        var _this = _super.call(this, message) || this;
+        _this.name = 'LimitReachedError';
+        Object.setPrototypeOf(_this, LimitReachedError.prototype);
+        return _this;
+    }
+    return LimitReachedError;
+}(Error));
+
 /**
  * Replaces parameters in template with values from parameters object
  *
@@ -1859,7 +1940,7 @@ function replaceParameters(template, parameters) {
     var loopLimit = LOOP_LIMIT;
     var _loop_1 = function () {
         if (loopLimit-- < 0) {
-            throw new UnexpectedError('Loop limit reached during parameters replacement in `replaceParameters`');
+            throw new LimitReachedError('Loop limit reached during parameters replacement in `replaceParameters`');
         }
         var precol = match.groups.precol;
         var parameterName = match.groups.parameterName;
@@ -2347,6 +2428,7 @@ function createPipelineExecutor(options) {
                             switch (_e.label) {
                                 case 0:
                                     if (loopLimit-- < 0) {
+                                        // Note: Really UnexpectedError not LimitReachedError - this should be catched during validatePipeline
                                         throw new UnexpectedError('Loop limit reached during resolving parameters pipeline execution');
                                     }
                                     currentTemplate = unresovedTemplates.find(function (template) {
@@ -2393,7 +2475,7 @@ function createPipelineExecutor(options) {
                     }
                     usage_1 = addUsage.apply(void 0, __spreadArray([], __read(executionReport.promptExecutions.map(function (_a) {
                         var result = _a.result;
-                        return (result === null || result === void 0 ? void 0 : result.usage) || addUsage();
+                        return (result === null || result === void 0 ? void 0 : result.usage) || ZERO_USAGE;
                     })), false));
                     return [2 /*return*/, {
                             isSuccessful: false,
@@ -2422,7 +2504,7 @@ function createPipelineExecutor(options) {
                     }
                     usage = addUsage.apply(void 0, __spreadArray([], __read(executionReport.promptExecutions.map(function (_a) {
                         var result = _a.result;
-                        return (result === null || result === void 0 ? void 0 : result.usage) || addUsage();
+                        return (result === null || result === void 0 ? void 0 : result.usage) || ZERO_USAGE;
                     })), false));
                     return [2 /*return*/, {
                             isSuccessful: true,
@@ -2454,6 +2536,7 @@ function createPipelineExecutor(options) {
  *
  * @param value any values
  * @returns void
+ * @private within the repository
  */
 function TODO_USE() {
     var value = [];
@@ -2589,6 +2672,7 @@ function prepareKnowledgeFromMarkdown(content /* <- TODO: [🖖] (?maybe not) Al
     });
 }
 /**
+ * TODO: [🔼] !!! Export via `@promptbook/markdown`
  * TODO: [🪂] Do it in parallel 11:11
  * Note: No need to aggregate usage here, it is done by intercepting the llmTools
  */
@@ -2597,7 +2681,6 @@ function prepareKnowledgeFromMarkdown(content /* <- TODO: [🖖] (?maybe not) Al
  * Prepares the knowle
  *
  * @see https://github.com/webgptorg/promptbook/discussions/41
- * @private within the package
  */
 function prepareKnowledgePieces(knowledgeSources, options) {
     return __awaiter(this, void 0, void 0, function () {
@@ -2612,7 +2695,7 @@ function prepareKnowledgePieces(knowledgeSources, options) {
                             var partialPieces, pieces;
                             return __generator(this, function (_a) {
                                 switch (_a.label) {
-                                    case 0: return [4 /*yield*/, prepareKnowledgeFromMarkdown(knowledgeSource.source, // <- TODO: !!!!! Unhardcode markdown, detect which type it is
+                                    case 0: return [4 /*yield*/, prepareKnowledgeFromMarkdown(knowledgeSource.source, // <- TODO: [🐝] !!!!! Unhardcode markdown, detect which type it is
                                         options)];
                                     case 1:
                                         partialPieces = _a.sent();
@@ -2650,6 +2733,7 @@ TODO: [🧊] This is how it can look in future
 > ):
 */
 /**
+ * TODO: [🔼] !!! Export via `@promptbook/core`
  * TODO: [🧊] In future one preparation can take data from previous preparation and save tokens and time
  *       Put `knowledgePieces` into `PrepareKnowledgeOptions`
  * TODO: [🪂] More than max things can run in parallel by acident [1,[2a,2b,_],[3a,3b,_]]
@@ -2662,7 +2746,6 @@ TODO: [🧊] This is how it can look in future
  * Prepares the persona for the pipeline
  *
  * @see https://github.com/webgptorg/promptbook/discussions/22
- * @private within the package
  */
 function preparePersona(personaDescription, options) {
     return __awaiter(this, void 0, void 0, function () {
@@ -2706,9 +2789,6 @@ function preparePersona(personaDescription, options) {
                         console.info("PERSONA ".concat(personaDescription), modelRequirements);
                     }
                     modelName = modelRequirements.modelName, systemMessage = modelRequirements.systemMessage, temperature = modelRequirements.temperature;
-                    // TODO: !!! Check validity of `modelName`
-                    // TODO: !!! Check validity of `systemMessage`
-                    // TODO: !!! Check validity of `temperature`
                     return [2 /*return*/, {
                             modelVariant: 'CHAT',
                             modelName: modelName,
@@ -2719,6 +2799,12 @@ function preparePersona(personaDescription, options) {
         });
     });
 }
+/**
+ * TODO: [🔼] !!! Export via `@promptbook/core`
+ * TODO: [🏢] !! Check validity of `modelName` in pipeline
+ * TODO: [🏢] !! Check validity of `systemMessage` in pipeline
+ * TODO: [🏢] !! Check validity of `temperature` in pipeline
+ */
 
 /**
  * Prepare pipeline from string (markdown) format to JSON format
@@ -2744,7 +2830,7 @@ function preparePipeline(pipeline, options) {
                         id: 1,
                         // TODO: [🍥]> date: $currentDate(),
                         promptbookVersion: PROMPTBOOK_VERSION,
-                        modelUsage: addUsage(),
+                        modelUsage: ZERO_USAGE,
                     };
                     preparations = [
                         // ...preparations
@@ -2779,10 +2865,11 @@ function preparePipeline(pipeline, options) {
     });
 }
 /**
+ * TODO: [🔼] !!! Export via `@promptbook/core`
  * TODO: Write tests for `preparePipeline`
  * TODO: [🏏] Leverage the batch API and build queues @see https://platform.openai.com/docs/guides/batch
  * TODO: [🧊] In future one preparation can take data from previous preparation and save tokens and time
- * TODO: !!!!! Use here countTotalUsage
+ * TODO: [🎐] !!!! Use here countTotalUsage
  * TODO: [🛠] Actions, instruments (and maybe knowledge) => Functions and tools
  */
 
@@ -3114,7 +3201,7 @@ var blockCommandParser = {
         'Knowledge BLOCK',
         // 'Knowledge', // <- Note: [⛱] For execution blocks which are also separate commands shortcut does not work
         //---
-        /* TODO: !!!! Not implemented block types will be in examples in future -> */
+        /* Note: Not implemented block types will be in examples in future -> */
         'Instrument BLOCK',
         // 'Instrument', // <- Note: [⛱]
         'Action BLOCK',
@@ -3132,10 +3219,10 @@ var blockCommandParser = {
         if (blockTypes.length !== 1) {
             throw new ParsingError(spaceTrim(function (block) { return "\n                        Unknown block type in BLOCK command\n\n                        Supported block types are:\n                        ".concat(block(BlockTypes.join(', ')), "\n                    "); }));
         }
-        // TODO: !!!! Not supported yet
+        var blockType = blockTypes[0];
         return {
             type: 'BLOCK',
-            blockType: blockTypes[0],
+            blockType: blockType,
         };
     },
 };
@@ -3380,7 +3467,7 @@ var jokerCommandParser = {
 
 var MODEL_VARIANTS = ['COMPLETION', 'CHAT', 'EMBEDDING' /* <- TODO [🏳] */ /* <- [🤖] */];
 /**
- * TODO: [🈁] `seed` should maybe be somewhere else (not in `ModelRequirements`) (simmilar that `user` identification is not here)
+ * TODO: [🧠][🈁] `seed` should maybe be somewhere else (not in `ModelRequirements`) (simmilar that `user` identification is not here)
  * TODO: [🧠][💱] Add more model options: `stop_token`, `logit_bias`, `logprobs` (`top_logprobs`), `top_k`, `top_p`, `presence_penalty`, `frequency_penalty`, `bestOf`, `logitBias`, `logitBiasType`,...
  *       [💱] Probbably keep using just `temperature` in Promptbook (not `top_k` and `top_p`)
  * TODO: [🛠] Actions, instruments (and maybe knowledge) => Functions and tools
@@ -3840,6 +3927,7 @@ var boilerplateCommandParser = {
 };
 /**
  * TODO: [💐] Implement BOILERPLATE command into `pipelineStringToJsonSync` function
+ * Note: [⚪] This should never be in any released package
  */
 
 /**
@@ -3858,7 +3946,7 @@ var COMMANDS = [
     actionCommandParser,
     instrumentCommandParser,
     personaCommandParser,
-    boilerplateCommandParser, // <- TODO: !!!! Only in development, remove in production
+    boilerplateCommandParser, // <- TODO: !! Only in development, remove in production
 ];
 
 /**
@@ -3944,7 +4032,7 @@ function parseCommand(raw, usagePlace) {
     }));
 }
 /**
- * !!!
+ * @@@
  */
 function getSupportedCommandsMessage() {
     return COMMANDS.flatMap(function (_a) {
@@ -3955,7 +4043,7 @@ function getSupportedCommandsMessage() {
     }).join('\n');
 }
 /**
- * !!!
+ * @@@
  */
 function parseCommandVariant(input) {
     var e_1, _a;
@@ -4686,7 +4774,7 @@ function pipelineStringToJsonSync(pipelineString) {
                         if (command.blockType === 'KNOWLEDGE') {
                             knowledgeCommandParser.applyToPipelineJson(pipelineJson, {
                                 type: 'KNOWLEDGE',
-                                source: content, // <- TODO: !!!! Working KNOWLEDGE which not referring to the source file/wweb, but its content itseld
+                                source: content, // <- TODO: [🐝] !!!! Work with KNOWLEDGE which not referring to the source file/wweb, but its content itself
                             });
                             return "continue-templates";
                         }
@@ -4824,7 +4912,7 @@ function pipelineStringToJsonSync(pipelineString) {
             delete template.modelRequirements;
         }
         // TODO: [🍧] What actually about preparation and pushing the block into `promptTemplates`
-        pipelineJson.promptTemplates.push(template /* <- !!! */);
+        pipelineJson.promptTemplates.push(template);
     };
     try {
         // =============================================================
@@ -4961,6 +5049,9 @@ var isRunningInNode = new Function("\n    try {\n        return this === global;
  * Detects if the code is running in a web worker
  */
 new Function("\n    try {\n        if (typeof WorkerGlobalScope !== 'undefined' && self instanceof WorkerGlobalScope) {\n            return true;\n        } else {\n            return false;\n        }\n    } catch (e) {\n        return false;\n    }\n");
+/**
+ * TODO: [🔼] !!! Export via `@promptbook/utils`
+ */
 
 /**
  * Constructs Promptbook from async sources
@@ -5271,6 +5362,7 @@ function listAllFiles(path, isRecursive) {
 }
 /**
  * TODO: !!!! [🧠] Library precompilation and do not mix markdown and json promptbooks
+ * Note: [🟢] This code should never be published outside of `@promptbook/node`
  */
 
 export { PROMPTBOOK_VERSION, createCollectionFromDirectory };