vodorod/parcer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #734 from getmaxun/browser-ready

Browse Source 
feat: browser checks for run execution
This commit is contained in:
Karishma Shukla
2025-08-18 16:11:19 +05:30
committed by GitHub
parent 422c57533b fe4a12cfe4
commit eaf40349ac
4 changed files with 110 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
server/src/browser-management/classes/BrowserPool.ts
View File

@@ -221,6 +221,12 @@ export class BrowserPool {
return undefined;
}
// Return undefined for failed slots
if (poolInfo.status === "failed") {
logger.log('debug', `Browser ${id} has failed status`);
return undefined;
}
return poolInfo.browser || undefined;
};
@@ -607,8 +613,13 @@ export class BrowserPool {
* @returns true if successful, false if slot wasn't reserved
*/
public upgradeBrowserSlot = (id: string, browser: RemoteBrowser): boolean => {
if (!this.pool[id] || this.pool[id].status !== "reserved") {
logger.log('warn', `Cannot upgrade browser ${id}: slot not reserved`);
if (!this.pool[id]) {
logger.log('warn', `Cannot upgrade browser ${id}: slot does not exist in pool`);
return false;
}
if (this.pool[id].status !== "reserved") {
logger.log('warn', `Cannot upgrade browser ${id}: slot not in reserved state (current: ${this.pool[id].status})`);
return false;
}
@@ -629,4 +640,17 @@ export class BrowserPool {
this.deleteRemoteBrowser(id);
}
};
/**
* Gets the current status of a browser slot.
*
* @param id browser ID to check
* @returns the status or null if browser doesn't exist
*/
public getBrowserStatus = (id: string): "reserved" | "initializing" | "ready" | "failed" | null => {
if (!this.pool[id]) {
return null;
}
return this.pool[id].status || null;
};
}

12
server/src/browser-management/controller.ts
View File

@@ -242,7 +242,7 @@ const initializeBrowserAsync = async (id: string, userId: string) => {
logger.log('warn', `No client connected to browser ${id} within timeout, proceeding with dummy socket`);
resolve(null);
}
}, 10000);
}, 15000);
});
namespace.on('error', (error: any) => {
@@ -272,21 +272,25 @@ const initializeBrowserAsync = async (id: string, userId: string) => {
browserSession = new RemoteBrowser(dummySocket, userId, id);
}
logger.log('debug', `Starting browser initialization for ${id}`);
await browserSession.initialize(userId);
logger.log('debug', `Browser initialization completed for ${id}`);
const upgraded = browserPool.upgradeBrowserSlot(id, browserSession);
if (!upgraded) {
throw new Error('Failed to upgrade reserved browser slot');
}
await new Promise(resolve => setTimeout(resolve, 500));
if (socket) {
socket.emit('ready-for-run');
} else {
setTimeout(async () => {
try {
logger.log('info', `Starting execution for browser ${id} with dummy socket`);
logger.log('info', `Browser ${id} with dummy socket is ready for execution`);
} catch (error: any) {
logger.log('error', `Error executing run for browser ${id}: ${error.message}`);
logger.log('error', `Error with dummy socket browser ${id}: ${error.message}`);
}
}, 100);
}
@@ -299,10 +303,12 @@ const initializeBrowserAsync = async (id: string, userId: string) => {
if (socket) {
socket.emit('error', { message: error.message });
}
throw error;
}
} catch (error: any) {
logger.log('error', `Error setting up browser ${id}: ${error.message}`);
browserPool.failBrowserSlot(id);
throw error;
}
};

44
server/src/pgboss-worker.ts
View File

@@ -215,7 +215,8 @@ async function triggerIntegrationUpdates(runId: string, robotMetaId: string): Pr
* Modified processRunExecution function - only add browser reset
*/
async function processRunExecution(job: Job<ExecuteRunData>) {
const BROWSER_INIT_TIMEOUT = 30000;
const BROWSER_INIT_TIMEOUT = 60000;
const BROWSER_PAGE_TIMEOUT = 45000;
const data = job.data;
logger.log('info', `Processing run execution job for runId: ${data.runId}, browserId: ${data.browserId}`);
@@ -244,15 +245,28 @@ async function processRunExecution(job: Job<ExecuteRunData>) {
let browser = browserPool.getRemoteBrowser(browserId);
const browserWaitStart = Date.now();
let lastLogTime = 0;
while (!browser && (Date.now() - browserWaitStart) < BROWSER_INIT_TIMEOUT) {
logger.log('debug', `Browser ${browserId} not ready yet, waiting...`);
await new Promise(resolve => setTimeout(resolve, 1000));
const currentTime = Date.now();
const browserStatus = browserPool.getBrowserStatus(browserId);
if (browserStatus === null) {
throw new Error(`Browser slot ${browserId} does not exist in pool`);
}
if (currentTime - lastLogTime > 10000) {
logger.log('info', `Browser ${browserId} not ready yet (status: ${browserStatus}), waiting... (${Math.round((currentTime - browserWaitStart) / 1000)}s elapsed)`);
lastLogTime = currentTime;
}
await new Promise(resolve => setTimeout(resolve, 2000));
browser = browserPool.getRemoteBrowser(browserId);
}
if (!browser) {
throw new Error(`Browser ${browserId} not found in pool after timeout`);
const finalStatus = browserPool.getBrowserStatus(browserId);
throw new Error(`Browser ${browserId} not found in pool after ${BROWSER_INIT_TIMEOUT/1000}s timeout (final status: ${finalStatus})`);
}
logger.log('info', `Browser ${browserId} found and ready for execution`);
@@ -273,14 +287,22 @@ async function processRunExecution(job: Job<ExecuteRunData>) {
let currentPage = browser.getCurrentPage();
const pageWaitStart = Date.now();
while (!currentPage && (Date.now() - pageWaitStart) < 30000) {
logger.log('debug', `Page not ready for browser ${browserId}, waiting...`);
let lastPageLogTime = 0;
while (!currentPage && (Date.now() - pageWaitStart) < BROWSER_PAGE_TIMEOUT) {
const currentTime = Date.now();
if (currentTime - lastPageLogTime > 5000) {
logger.log('info', `Page not ready for browser ${browserId}, waiting... (${Math.round((currentTime - pageWaitStart) / 1000)}s elapsed)`);
lastPageLogTime = currentTime;
}
await new Promise(resolve => setTimeout(resolve, 1000));
currentPage = browser.getCurrentPage();
}
if (!currentPage) {
throw new Error(`No current page available for browser ${browserId} after timeout`);
throw new Error(`No current page available for browser ${browserId} after ${BROWSER_PAGE_TIMEOUT/1000}s timeout`);
}
logger.log('info', `Starting workflow execution for run ${data.runId}`);
@@ -776,6 +798,10 @@ async function registerRunExecutionWorker() {
await checkForNewUserQueues();
setInterval(async () => {
await checkForNewUserQueues();
}, 10000);
logger.log('info', 'Run execution worker registered successfully');
} catch (error: unknown) {
const errorMessage = error instanceof Error ? error.message : String(error);
@@ -822,6 +848,10 @@ async function registerAbortRunWorker() {
await checkForNewAbortQueues();
setInterval(async () => {
await checkForNewAbortQueues();
}, 10000);
logger.log('info', 'Abort run worker registration system initialized');
} catch (error: unknown) {
const errorMessage = error instanceof Error ? error.message : String(error);

98
src/helpers/clientSelectorGenerator.ts
View File

@@ -2494,70 +2494,38 @@ class ClientSelectorGenerator {
};
private getAllDescendantsIncludingShadow(
parentElement: HTMLElement
parentElement: HTMLElement,
maxDepth: number = 20
): HTMLElement[] {
const allDescendants: HTMLElement[] = [];
const visited = new Set<HTMLElement>();
const shadowRootsSeen = new Set<ShadowRoot>();
const traverseShadowRoot = (shadowRoot: ShadowRoot, depth: number = 0) => {
if (depth > 10) return;
const traverse = (element: HTMLElement, currentDepth: number) => {
if (currentDepth >= maxDepth || visited.has(element)) {
return;
}
visited.add(element);
try {
const shadowElements = Array.from(
shadowRoot.querySelectorAll("*")
) as HTMLElement[];
if (element !== parentElement) {
allDescendants.push(element);
}
shadowElements.forEach((shadowElement) => {
if (!visited.has(shadowElement)) {
visited.add(shadowElement);
allDescendants.push(shadowElement);
// Traverse light DOM children
const children = Array.from(element.children) as HTMLElement[];
for (const child of children) {
traverse(child, currentDepth + 1);
}
if (
shadowElement.shadowRoot &&
!shadowRootsSeen.has(shadowElement.shadowRoot)
) {
shadowRootsSeen.add(shadowElement.shadowRoot);
traverseShadowRoot(shadowElement.shadowRoot, depth + 1);
}
}
});
Array.from(shadowRoot.children).forEach((child) => {
const htmlChild = child as HTMLElement;
if (
htmlChild.shadowRoot &&
!shadowRootsSeen.has(htmlChild.shadowRoot)
) {
shadowRootsSeen.add(htmlChild.shadowRoot);
traverseShadowRoot(htmlChild.shadowRoot, depth + 1);
}
});
} catch (error) {
console.warn(`Error traversing shadow root:`, error);
// Traverse shadow DOM if it exists
if (element.shadowRoot) {
const shadowChildren = Array.from(element.shadowRoot.children) as HTMLElement[];
for (const shadowChild of shadowChildren) {
traverse(shadowChild, currentDepth + 1);
}
}
};
const regularDescendants = Array.from(
parentElement.querySelectorAll("*")
) as HTMLElement[];
regularDescendants.forEach((descendant) => {
if (!visited.has(descendant)) {
visited.add(descendant);
allDescendants.push(descendant);
}
});
const elementsWithShadow = [parentElement, ...regularDescendants].filter(
(el) => el.shadowRoot
);
elementsWithShadow.forEach((element) => {
if (!shadowRootsSeen.has(element.shadowRoot!)) {
shadowRootsSeen.add(element.shadowRoot!);
traverseShadowRoot(element.shadowRoot!, 0);
}
});
traverse(parentElement, 0);
return allDescendants;
}
@@ -2577,6 +2545,8 @@ class ClientSelectorGenerator {
if (processedElements.has(descendant)) return;
processedElements.add(descendant);
if (!this.isMeaningfulElement(descendant)) return;
const absolutePath = this.buildOptimizedAbsoluteXPath(
descendant,
listSelector,
@@ -2766,16 +2736,20 @@ class ClientSelectorGenerator {
rootElement: HTMLElement,
otherListElements: HTMLElement[] = []
): string | null {
if (!this.elementContains(rootElement, targetElement) || targetElement === rootElement) {
if (
!this.elementContains(rootElement, targetElement) ||
targetElement === rootElement
) {
return null;
}
const pathParts: string[] = [];
let current: HTMLElement | null = targetElement;
let pathDepth = 0;
const MAX_PATH_DEPTH = 20;
// Build path from target up to root
while (current && current !== rootElement) {
// Calculate conflicts for each element in the path
while (current && current !== rootElement && pathDepth < MAX_PATH_DEPTH) {
const classes = this.getCommonClassesAcrossLists(
current,
otherListElements
@@ -2806,11 +2780,15 @@ class ClientSelectorGenerator {
pathParts.unshift(pathPart);
}
// Move to parent (either regular parent or shadow host)
current = current.parentElement ||
current =
current.parentElement ||
((current.getRootNode() as ShadowRoot).host as HTMLElement | null);
if (!current) break;
pathDepth++;
}
if (current !== rootElement) {
return null;
}
return pathParts.length > 0 ? "/" + pathParts.join("/") : null;