@eko-ai/eko 1.0.6 → 1.0.8

package/dist/services/workflow/generator.d.ts

@@ -1,11 +1,13 @@
-import { LLMProvider } from '../../types/llm.types';
+import { LLMProvider, Message } from '../../types/llm.types';
 import { Workflow } from '../../types/workflow.types';
 import { ToolRegistry } from '../../core/tool-registry';
 export declare class WorkflowGenerator {
     private llmProvider;
     private toolRegistry;
+    message_history: Message[];
     constructor(llmProvider: LLMProvider, toolRegistry: ToolRegistry);
     generateWorkflow(prompt: string): Promise<Workflow>;
+    modifyWorkflow(prompt: string): Promise<Workflow>;
+    private doGenerateWorkflow;
     private createWorkflowFromData;
-    modifyWorkflow(workflow: Workflow, prompt: string): Promise<Workflow>;
 }

package/dist/services/workflow/templates.d.ts

@@ -3,5 +3,6 @@ import { ToolRegistry } from '../../core/tool-registry';
 export declare function createWorkflowPrompts(tools: ToolDefinition[]): {
     formatSystemPrompt: () => string;
     formatUserPrompt: (requirement: string) => string;
+    modifyUserPrompt: (prompt: string) => string;
 };
 export declare function createWorkflowGenerationTool(registry: ToolRegistry): ToolDefinition;

package/dist/types/index.d.ts

@@ -3,4 +3,3 @@ export * from './workflow.types';
 export * from './eko.types';
 export * from './llm.types';
 export * from './tools.types';
-export * from './framework.types';

package/dist/web/tools/browser.d.ts

@@ -4,7 +4,8 @@ export declare function clear_input(xpath?: string, highlightIndex?: number): bo
 export declare function left_click(xpath?: string, highlightIndex?: number): boolean;
 export declare function right_click(xpath?: string, highlightIndex?: number): boolean;
 export declare function double_click(xpath?: string, highlightIndex?: number): boolean;
-export declare function screenshot(): Promise<ScreenshotResult>;
+export declare function screenshot(compress?: boolean): Promise<ScreenshotResult>;
+export declare function compress_image(dataUrl: string, scale?: number, quality?: number): Promise<string>;
 export declare function scroll_to(xpath?: string, highlightIndex?: number): boolean;
 export declare function get_dropdown_options(xpath?: string, highlightIndex?: number): {
     options: Array<{

package/dist/web.cjs.js

@@ -8419,7 +8419,7 @@ function right_click(xpath, highlightIndex) {
 function double_click(xpath, highlightIndex) {
     return simulateMouseEvent(['mousedown', 'mouseup', 'click', 'mousedown', 'mouseup', 'click', 'dblclick'], 0, xpath, highlightIndex);
 }
-async function screenshot() {
+async function screenshot(compress) {
     const [width, height] = size();
     const scrollX = window.scrollX || window.pageXOffset;
     const scrollY = window.scrollY || window.pageYOffset;
@@ -8437,7 +8437,10 @@ async function screenshot() {
         // backgroundColor: 'white',
         // scale: window.devicePixelRatio || 1,
     });
-    const dataUrl = canvas.toDataURL('image/png');
+    let dataUrl = canvas.toDataURL('image/png');
+    if (compress) {
+        dataUrl = await compress_image(dataUrl, 0.7, 0.8);
+    }
     let data = dataUrl.substring(dataUrl.indexOf('base64,') + 7);
     return {
         image: {
@@ -8447,6 +8450,25 @@ async function screenshot() {
         },
     };
 }
+function compress_image(dataUrl, scale = 0.8, quality = 0.8) {
+    return new Promise((resolve) => {
+        const img = new Image();
+        img.onload = function () {
+            const canvas = document.createElement('canvas');
+            const ctx = canvas.getContext('2d');
+            let width = img.width * scale;
+            let height = img.height * scale;
+            canvas.width = width;
+            canvas.height = height;
+            ctx.drawImage(img, 0, 0, width, height);
+            resolve(canvas.toDataURL('image/jpeg', quality));
+        };
+        img.onerror = function () {
+            resolve(dataUrl);
+        };
+        img.src = dataUrl;
+    });
+}
 function scroll_to(xpath, highlightIndex) {
     let element = null;
     if (highlightIndex != null) {
@@ -8633,6 +8655,7 @@ function simulateMouseEvent(eventTypes, button, xpath, highlightIndex) {
 var browser = /*#__PURE__*/Object.freeze({
     __proto__: null,
     clear_input: clear_input,
+    compress_image: compress_image,
     double_click: double_click,
     extractHtmlContent: extractHtmlContent,
     get_dropdown_options: get_dropdown_options,
@@ -8653,7 +8676,6 @@ class BrowserUse {
         this.name = 'browser_use';
         this.description = `Use structured commands to interact with the browser, manipulating page elements through screenshots and webpage element extraction.
 * This is a browser GUI interface where you need to analyze webpages by taking screenshots and extracting page element structures, and specify action sequences to complete designated tasks.
-* Some operations may need time to process, so you might need to wait and continuously take screenshots and extract element structures to check the operation results.
 * Before any operation, you must first call the \`screenshot_extract_element\` command, which will return the browser page screenshot and structured element information, both specially processed.
 * ELEMENT INTERACTION:
    - Only use indexes that exist in the provided element list
@@ -8663,17 +8685,7 @@ class BrowserUse {
    - If no suitable elements exist, use other functions to complete the task
    - If stuck, try alternative approaches
    - Handle popups/cookies by accepting or closing them
-   - Use scroll to find elements you are looking for
-* Form filling:
-   - If you fill a input field and your action sequence is interrupted, most often a list with suggestions poped up under the field and you need to first select the right element from the suggestion list.
-* ACTION SEQUENCING:
-   - Actions are executed in the order they appear in the list 
-   - Each action should logically follow from the previous one
-   - If the page changes after an action, the sequence is interrupted and you get the new state.
-   - If content only disappears the sequence continues.
-   - Only provide the action sequence until you think the page will change.
-   - Try to be efficient, e.g. fill forms at once, or chain actions where nothing changes on the page like saving, extracting, checkboxes...
-   - only use multiple actions if it makes sense.`;
+   - Use scroll to find elements you are looking for`;
         this.input_schema = {
             type: 'object',
             properties: {
@@ -8804,7 +8816,7 @@ class BrowserUse {
                     await sleep(100);
                     let element_result = get_clickable_elements(true, null);
                     context.selector_map = element_result.selector_map;
-                    let screenshot$1 = await screenshot();
+                    let screenshot$1 = await screenshot(true);
                     remove_highlight();
                     result = { image: screenshot$1.image, text: element_result.element_str };
                     break;
@@ -9074,7 +9086,7 @@ ${pseudoHtml}
     return false;
 }
 async function executeWithBrowserUse$1(context, task_prompt) {
-    let screenshot_result = await screenshot();
+    let screenshot_result = await screenshot(false);
     let messages = [
         {
             role: 'user',
@@ -9289,7 +9301,7 @@ ${pseudoHtml}
     return null;
 }
 async function executeWithBrowserUse(context, task_prompt) {
-    let screenshot_result = await screenshot();
+    let screenshot_result = await screenshot(false);
     let messages = [
         {
             role: 'user',

package/dist/web.esm.js

@@ -8417,7 +8417,7 @@ function right_click(xpath, highlightIndex) {
 function double_click(xpath, highlightIndex) {
     return simulateMouseEvent(['mousedown', 'mouseup', 'click', 'mousedown', 'mouseup', 'click', 'dblclick'], 0, xpath, highlightIndex);
 }
-async function screenshot() {
+async function screenshot(compress) {
     const [width, height] = size();
     const scrollX = window.scrollX || window.pageXOffset;
     const scrollY = window.scrollY || window.pageYOffset;
@@ -8435,7 +8435,10 @@ async function screenshot() {
         // backgroundColor: 'white',
         // scale: window.devicePixelRatio || 1,
     });
-    const dataUrl = canvas.toDataURL('image/png');
+    let dataUrl = canvas.toDataURL('image/png');
+    if (compress) {
+        dataUrl = await compress_image(dataUrl, 0.7, 0.8);
+    }
     let data = dataUrl.substring(dataUrl.indexOf('base64,') + 7);
     return {
         image: {
@@ -8445,6 +8448,25 @@ async function screenshot() {
         },
     };
 }
+function compress_image(dataUrl, scale = 0.8, quality = 0.8) {
+    return new Promise((resolve) => {
+        const img = new Image();
+        img.onload = function () {
+            const canvas = document.createElement('canvas');
+            const ctx = canvas.getContext('2d');
+            let width = img.width * scale;
+            let height = img.height * scale;
+            canvas.width = width;
+            canvas.height = height;
+            ctx.drawImage(img, 0, 0, width, height);
+            resolve(canvas.toDataURL('image/jpeg', quality));
+        };
+        img.onerror = function () {
+            resolve(dataUrl);
+        };
+        img.src = dataUrl;
+    });
+}
 function scroll_to(xpath, highlightIndex) {
     let element = null;
     if (highlightIndex != null) {
@@ -8631,6 +8653,7 @@ function simulateMouseEvent(eventTypes, button, xpath, highlightIndex) {
 var browser = /*#__PURE__*/Object.freeze({
     __proto__: null,
     clear_input: clear_input,
+    compress_image: compress_image,
     double_click: double_click,
     extractHtmlContent: extractHtmlContent,
     get_dropdown_options: get_dropdown_options,
@@ -8651,7 +8674,6 @@ class BrowserUse {
         this.name = 'browser_use';
         this.description = `Use structured commands to interact with the browser, manipulating page elements through screenshots and webpage element extraction.
 * This is a browser GUI interface where you need to analyze webpages by taking screenshots and extracting page element structures, and specify action sequences to complete designated tasks.
-* Some operations may need time to process, so you might need to wait and continuously take screenshots and extract element structures to check the operation results.
 * Before any operation, you must first call the \`screenshot_extract_element\` command, which will return the browser page screenshot and structured element information, both specially processed.
 * ELEMENT INTERACTION:
    - Only use indexes that exist in the provided element list
@@ -8661,17 +8683,7 @@ class BrowserUse {
    - If no suitable elements exist, use other functions to complete the task
    - If stuck, try alternative approaches
    - Handle popups/cookies by accepting or closing them
-   - Use scroll to find elements you are looking for
-* Form filling:
-   - If you fill a input field and your action sequence is interrupted, most often a list with suggestions poped up under the field and you need to first select the right element from the suggestion list.
-* ACTION SEQUENCING:
-   - Actions are executed in the order they appear in the list 
-   - Each action should logically follow from the previous one
-   - If the page changes after an action, the sequence is interrupted and you get the new state.
-   - If content only disappears the sequence continues.
-   - Only provide the action sequence until you think the page will change.
-   - Try to be efficient, e.g. fill forms at once, or chain actions where nothing changes on the page like saving, extracting, checkboxes...
-   - only use multiple actions if it makes sense.`;
+   - Use scroll to find elements you are looking for`;
         this.input_schema = {
             type: 'object',
             properties: {
@@ -8802,7 +8814,7 @@ class BrowserUse {
                     await sleep(100);
                     let element_result = get_clickable_elements(true, null);
                     context.selector_map = element_result.selector_map;
-                    let screenshot$1 = await screenshot();
+                    let screenshot$1 = await screenshot(true);
                     remove_highlight();
                     result = { image: screenshot$1.image, text: element_result.element_str };
                     break;
@@ -9072,7 +9084,7 @@ ${pseudoHtml}
     return false;
 }
 async function executeWithBrowserUse$1(context, task_prompt) {
-    let screenshot_result = await screenshot();
+    let screenshot_result = await screenshot(false);
     let messages = [
         {
             role: 'user',
@@ -9287,7 +9299,7 @@ ${pseudoHtml}
     return null;
 }
 async function executeWithBrowserUse(context, task_prompt) {
-    let screenshot_result = await screenshot();
+    let screenshot_result = await screenshot(false);
     let messages = [
         {
             role: 'user',

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eko-ai/eko",
-  "version": "1.0.6",
+  "version": "1.0.8",
   "description": "Empowering language to transform human words into action.",
   "main": "dist/index.cjs.js",
   "module": "dist/index.esm.js",
@@ -51,12 +51,6 @@
     "dev": "tsc --watch",
     "clean": "rimraf dist",
     "test": "jest",
-    "test:watch": "jest --watch",
-    "test:coverage": "jest --coverage",
-    "lint": "eslint src/**/*.ts",
-    "lint:fix": "eslint src/**/*.ts --fix",
-    "format": "prettier --write \"src/**/*.ts\"",
-    "prepublishOnly": "npm run build",
     "docs": "typedoc"
   },
   "author": "FellouAI",
@@ -75,15 +69,19 @@
   },
   "dependencies": {
     "@anthropic-ai/sdk": "^0.33.0",
+    "chromium-bidi": "^0.12.0",
     "dotenv": "^16.0.0",
     "html2canvas": "^1.4.1",
     "openai": "^4.77.0",
+    "playwright": "^1.49.1",
     "uuid": "^11.0.3",
     "zod": "^3.22.4"
   },
   "devDependencies": {
     "@rollup/plugin-commonjs": "^28.0.2",
+    "@rollup/plugin-json": "^6.1.0",
     "@rollup/plugin-node-resolve": "^16.0.0",
+    "@rollup/plugin-replace": "^6.0.2",
     "@rollup/plugin-typescript": "^12.1.2",
     "@types/chrome": "0.0.158",
     "@types/jest": "^29.5.12",