@crawlee/core 4.0.0-beta.164 → 4.0.0-beta.166

package/configuration.d.ts

@@ -6,47 +6,47 @@ export interface ConfigField<T extends z.ZodType = z.ZodType> {
 }
 export declare function field<T extends z.ZodType>(schema: T, envVar?: string | string[]): ConfigField<T>;
 /** Zod preprocessor treating `'0'` and `'false'` as falsy. */
-export declare const coerceBoolean: z.ZodPreprocess<z.ZodBoolean>;
-export declare const coerceNumber: z.ZodPreprocess<z.ZodNumber>;
+export declare const coerceBoolean: z.ZodPreprocess<z.ZodBoolean, unknown>;
+export declare const coerceNumber: z.ZodPreprocess<z.ZodNumber, unknown>;
 export declare const crawleeConfigFields: {
     /** @default 'default' */
     defaultDatasetId: ConfigField<z.ZodDefault<z.ZodString>>;
     /** @default true */
-    purgeOnStart: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean>>>;
+    purgeOnStart: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean, unknown>>>;
     /** @default 'default' */
     defaultKeyValueStoreId: ConfigField<z.ZodDefault<z.ZodString>>;
     /** @default 'default' */
     defaultRequestQueueId: ConfigField<z.ZodDefault<z.ZodString>>;
     /** @default 0.95 */
-    maxUsedCpuRatio: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber>>>;
+    maxUsedCpuRatio: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber, unknown>>>;
     /** @default 0.25 */
-    availableMemoryRatio: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber>>>;
-    memoryMbytes: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodNumber>>>;
+    availableMemoryRatio: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber, unknown>>>;
+    memoryMbytes: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodNumber, unknown>>>;
     /** @default 60_000 */
-    persistStateIntervalMillis: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber>>>;
+    persistStateIntervalMillis: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber, unknown>>>;
     /**
      * Internal safety-net timeout for a single request, in milliseconds. When unset the crawler derives it from
      * the request handler timeout (twice it, and never below 5 minutes).
      */
-    internalTimeoutMillis: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodNumber>>>;
+    internalTimeoutMillis: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodNumber, unknown>>>;
     /** @default 1_000 */
-    systemInfoIntervalMillis: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber>>>;
+    systemInfoIntervalMillis: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodNumber, unknown>>>;
     /** @default 'INPUT' */
     inputKey: ConfigField<z.ZodDefault<z.ZodString>>;
     /** @default true */
-    headless: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean>>>;
+    headless: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean, unknown>>>;
     /** @default false */
-    xvfb: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean>>>;
+    xvfb: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean, unknown>>>;
     chromeExecutablePath: ConfigField<z.ZodOptional<z.ZodString>>;
     defaultBrowserPath: ConfigField<z.ZodOptional<z.ZodString>>;
     /** @default false */
-    disableBrowserSandbox: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean>>>;
-    logLevel: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodEnum<typeof LogLevel>>>>;
+    disableBrowserSandbox: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean, unknown>>>;
+    logLevel: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodEnum<typeof LogLevel>, unknown>>>;
     /** @default true */
-    persistStorage: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean>>>;
+    persistStorage: ConfigField<z.ZodDefault<z.ZodPreprocess<z.ZodBoolean, unknown>>>;
     /** @default './storage' */
     storageDir: ConfigField<z.ZodDefault<z.ZodString>>;
-    containerized: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodBoolean>>>;
+    containerized: ConfigField<z.ZodOptional<z.ZodPreprocess<z.ZodBoolean, unknown>>>;
 };
 export type FieldsInput<F extends Record<string, ConfigField>> = {
     [K in keyof F]?: z.output<F[K]['schema']>;

package/log.d.ts

@@ -1,7 +1,7 @@
-import type { CrawleeLogger, CrawleeLoggerOptions } from '@crawlee/types';
+import type { CrawleeLogger, CrawleeLoggerOptions, LogOptions } from '@crawlee/types';
 import type { LoggerOptions } from '@apify/log';
 import log, { Log, Logger, LoggerJson, LoggerText, LogLevel } from '@apify/log';
-export type { CrawleeLogger, CrawleeLoggerOptions };
+export type { CrawleeLogger, CrawleeLoggerOptions, LogOptions };
 /**
  * Abstract base class for custom Crawlee logger implementations.
  *
@@ -55,14 +55,14 @@ export declare abstract class BaseCrawleeLogger implements CrawleeLogger {
     getOptions(): CrawleeLoggerOptions;
     setOptions(options: Partial<CrawleeLoggerOptions>): void;
     child(options: Partial<CrawleeLoggerOptions>): CrawleeLogger;
-    error(message: string, data?: Record<string, unknown>): void;
+    error(message: string, data?: Record<string, unknown>, options?: LogOptions): void;
     exception(exception: Error, message: string, data?: Record<string, unknown>): void;
-    softFail(message: string, data?: Record<string, unknown>): void;
-    warning(message: string, data?: Record<string, unknown>): void;
+    softFail(message: string, data?: Record<string, unknown>, options?: LogOptions): void;
+    warning(message: string, data?: Record<string, unknown>, options?: LogOptions): void;
     warningOnce(message: string): void;
-    info(message: string, data?: Record<string, unknown>): void;
-    debug(message: string, data?: Record<string, unknown>): void;
-    perf(message: string, data?: Record<string, unknown>): void;
+    info(message: string, data?: Record<string, unknown>, options?: LogOptions): void;
+    debug(message: string, data?: Record<string, unknown>, options?: LogOptions): void;
+    perf(message: string, data?: Record<string, unknown>, options?: LogOptions): void;
     deprecated(message: string): void;
 }
 /**

package/log.js

@@ -33,7 +33,7 @@ export class BaseCrawleeLogger {
     // Note: If wrapping logger in a Proxy, unbound methods calling #-fields throw TypeError
     // unless bound to the target (see createLogProxy in adaptive-playwright-crawler.ts).
     #options;
-    #warningsLogged = new Set();
+    #loggedOnce = new Set();
     constructor(options = {}) {
         this.#options = options;
     }
@@ -46,7 +46,27 @@ export class BaseCrawleeLogger {
     child(options) {
         return this.createChild(options);
     }
-    error(message, data) {
+    /**
+     * Whether `once` suppresses this message. Keyed by level as well as text, so that a message logged once as
+     * `info` does not swallow the same text logged as a `warning`.
+     *
+     * Handled here rather than in {@link BaseCrawleeLogger.logWithLevel} so that every logger gets it, instead
+     * of each implementation having to dedupe for itself.
+     */
+    #suppressedAsRepeat(level, message, options) {
+        if (!options?.once) {
+            return false;
+        }
+        const key = `${level}:${message}`;
+        if (this.#loggedOnce.has(key)) {
+            return true;
+        }
+        this.#loggedOnce.add(key);
+        return false;
+    }
+    error(message, data, options) {
+        if (this.#suppressedAsRepeat(LogLevel.ERROR, message, options))
+            return;
         this.logWithLevel(LogLevel.ERROR, message, data);
     }
     exception(exception, message, data) {
@@ -56,25 +76,35 @@ export class BaseCrawleeLogger {
             exception,
         });
     }
-    softFail(message, data) {
+    softFail(message, data, options) {
+        if (this.#suppressedAsRepeat(LogLevel.SOFT_FAIL, message, options))
+            return;
         this.logWithLevel(LogLevel.SOFT_FAIL, message, data);
     }
-    warning(message, data) {
+    warning(message, data, options) {
+        if (this.#suppressedAsRepeat(LogLevel.WARNING, message, options))
+            return;
         this.logWithLevel(LogLevel.WARNING, message, data);
     }
     warningOnce(message) {
-        if (!this.#warningsLogged.has(message)) {
-            this.#warningsLogged.add(message);
-            this.warning(message);
-        }
-    }
-    info(message, data) {
+        // Gates before delegating, so that a suppressed repeat is not even a `warning()` call.
+        if (this.#suppressedAsRepeat(LogLevel.WARNING, message, { once: true }))
+            return;
+        this.warning(message);
+    }
+    info(message, data, options) {
+        if (this.#suppressedAsRepeat(LogLevel.INFO, message, options))
+            return;
         this.logWithLevel(LogLevel.INFO, message, data);
     }
-    debug(message, data) {
+    debug(message, data, options) {
+        if (this.#suppressedAsRepeat(LogLevel.DEBUG, message, options))
+            return;
         this.logWithLevel(LogLevel.DEBUG, message, data);
     }
-    perf(message, data) {
+    perf(message, data, options) {
+        if (this.#suppressedAsRepeat(LogLevel.PERF, message, options))
+            return;
         this.logWithLevel(LogLevel.PERF, `[PERF] ${message}`, data);
     }
     deprecated(message) {

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/core",
-    "version": "4.0.0-beta.164",
+    "version": "4.0.0-beta.166",
     "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.",
     "engines": {
         "node": ">=22.0.0"
@@ -47,15 +47,15 @@
         "access": "public"
     },
     "dependencies": {
-        "@apify/consts": "^2.41.0",
-        "@apify/datastructures": "^2.0.3",
-        "@apify/log": "^2.5.18",
-        "@apify/timeout": "^0.4.4",
-        "@apify/utilities": "^2.15.5",
-        "@crawlee/fs-storage": "4.0.0-beta.164",
-        "@crawlee/http-client": "4.0.0-beta.164",
-        "@crawlee/types": "4.0.0-beta.164",
-        "@crawlee/utils": "4.0.0-beta.164",
+        "@apify/consts": "^3.0.1",
+        "@apify/datastructures": "^3.0.1",
+        "@apify/log": "^3.0.1",
+        "@apify/timeout": "^1.0.1",
+        "@apify/utilities": "^3.0.1",
+        "@crawlee/fs-storage": "4.0.0-beta.166",
+        "@crawlee/http-client": "4.0.0-beta.166",
+        "@crawlee/types": "4.0.0-beta.166",
+        "@crawlee/utils": "4.0.0-beta.166",
         "@sapphire/async-queue": "^1.5.5",
         "@standard-schema/spec": "^1.0.0",
         "@vladfrangu/async_event_emitter": "^2.4.6",
@@ -69,7 +69,7 @@
         "tough-cookie": "^6.0.0",
         "tslib": "^2.8.1",
         "type-fest": "^4.41.0",
-        "zod": "^4.4.3"
+        "zod": "^4.5.4"
     },
     "lerna": {
         "command": {
@@ -78,5 +78,5 @@
             }
         }
     },
-    "gitHead": "a2e4e2a3aa3a364c8a44fd2e49ca57f500d2c01f"
+    "gitHead": "5d34cf3b9da170f22cf5b346014ba44060dad827"
 }

package/validators.d.ts

@@ -1,4 +1,5 @@
-export { ArgumentValidationError, parseArgument } from '@crawlee/utils';
+export { ArgumentValidationError } from '@crawlee/utils';
+export { parseArgument } from '@crawlee/utils/internal';
 export { schemas } from '@crawlee/utils/internal';
 /** @internal */
 export declare const validators: {

package/validators.js

@@ -1,5 +1,6 @@
 import { schemas } from '@crawlee/utils/internal';
-export { ArgumentValidationError, parseArgument } from '@crawlee/utils';
+export { ArgumentValidationError } from '@crawlee/utils';
+export { parseArgument } from '@crawlee/utils/internal';
 export { schemas } from '@crawlee/utils/internal';
 /** @internal */
 export const validators = {