@crawlee/basic 4.0.0-beta.179 → 4.0.0-beta.180

package/internals/basic-crawler.js

@@ -374,8 +374,7 @@ export class BasicCrawler {
                 })
                 : suppliedManager;
             if (requestList !== undefined) {
-                // The list is read first, while new requests still have somewhere writable to go; the tandem also
-                // forwards `persistState()` to the loader.
+                // The list is read first, while new requests still have somewhere writable to go.
                 this.requestManager = new RequestManagerTandem(requestList, writableManager ?? (() => this.openOwnedRequestQueue()));
             }
             else if (writableManager !== undefined) {
@@ -1497,26 +1496,9 @@ export class BasicCrawler {
                 }
             });
         }
-        const requestManagerPersistPromise = (async () => {
-            // The request manager persists its read-only loader's state, if it has one that supports
-            // persistence (e.g. a tandem wrapping a `RequestList`). For a plain `RequestQueue`, this is a no-op.
-            if (this.requestManager?.persistState) {
-                if ((await this.requestManager.checkReadiness()).status === 'finished')
-                    return;
-                await this.requestManager.persistState().catch((err) => {
-                    if (err.message.includes('Cannot persist state.')) {
-                        this.log.error("The crawler attempted to persist its request list's state and failed due to missing or " +
-                            'invalid configuration. Make sure to use either RequestList.open() or the "stateKeyPrefix" option of RequestList ' +
-                            'constructor to ensure your crawling state is persisted through host migrations and restarts.');
-                    }
-                    else {
-                        this.log.exception(err, 'An unexpected error occurred when the crawler ' +
-                            "attempted to persist its request list's state.");
-                    }
-                });
-            }
-        })();
-        await Promise.all([requestManagerPersistPromise, this.statistics.persistState?.()]);
+        // Captures the statistics changed while draining above. No PERSIST_STATE event is tied to the drain:
+        // the periodic one is unrelated, and the one the platform emits on migration arrives before any of this.
+        await this.statistics.persistState?.();
     }
     /**
      * Fetches the next request to process from the underlying request provider.

package/internals/throttling_request_manager.d.ts

@@ -212,6 +212,5 @@ export declare class ThrottlingRequestManager<T extends IRequestManager = IReque
      */
     fetchNextRequest<R extends Dictionary = Dictionary>(): Promise<Request<R> | null>;
     [Symbol.asyncIterator](): AsyncGenerator<Request<Dictionary>, void, unknown>;
-    persistState(): Promise<void>;
     drop(): Promise<void>;
 }

package/internals/throttling_request_manager.js

@@ -818,9 +818,6 @@ export class ThrottlingRequestManager {
             yield req;
         }
     }
-    async persistState() {
-        await this.#forEachManager((manager) => manager.persistState?.());
-    }
     async drop() {
         await this.#forEachManager((manager) => manager.drop?.());
         this.#subManagers.clear();

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/basic",
-    "version": "4.0.0-beta.179",
+    "version": "4.0.0-beta.180",
     "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"
@@ -42,10 +42,10 @@
         "@apify/datastructures": "^3.0.1",
         "@apify/timeout": "^1.0.1",
         "@apify/utilities": "^3.0.1",
-        "@crawlee/core": "4.0.0-beta.179",
-        "@crawlee/http-client": "4.0.0-beta.179",
-        "@crawlee/types": "4.0.0-beta.179",
-        "@crawlee/utils": "4.0.0-beta.179",
+        "@crawlee/core": "4.0.0-beta.180",
+        "@crawlee/http-client": "4.0.0-beta.180",
+        "@crawlee/types": "4.0.0-beta.180",
+        "@crawlee/utils": "4.0.0-beta.180",
         "@sapphire/async-queue": "^1.5.5",
         "@standard-schema/spec": "^1.0.0",
         "csv-stringify": "^6.5.2",
@@ -57,7 +57,7 @@
         "zod": "^4.5.4"
     },
     "optionalDependencies": {
-        "@crawlee/impit-client": "4.0.0-beta.179"
+        "@crawlee/impit-client": "4.0.0-beta.180"
     },
     "lerna": {
         "command": {
@@ -66,5 +66,5 @@
             }
         }
     },
-    "gitHead": "8b7816439436b46bad1007a48df9e8bef0564bd0"
+    "gitHead": "4adb7b0a96ee16824ee53d18f437961d9287f977"
 }