@crawlee/basic 4.0.0-beta.127 → 4.0.0-beta.129

package/internals/basic-crawler.js

@@ -833,8 +833,8 @@ export class BasicCrawler {
             await this.#autoscaledPool.run();
         }
         finally {
-            await this.teardown();
             await this.statistics.stopCapturing();
+            await this.teardown();
             process.off('SIGINT', sigintHandler);
             eventManager.off(EventType.MIGRATING, boundPauseOnMigration);
             eventManager.off(EventType.ABORTING, boundPauseOnMigration);
@@ -1150,7 +1150,9 @@ export class BasicCrawler {
             // Only log the limit message when an explicit `limit` was passed (not the internal
             // `maxRequestsPerCrawl`-derived one), and only once per call.
             if (options.limit !== undefined && allSkipped.some((s) => s.reason === 'limit')) {
-                this.log.info(`Skipping requests in this call due to the enqueueLinks limit of ${options.limit}.`);
+                this.log.info(requestLimit === options.limit
+                    ? `Skipping requests in this call due to the enqueueLinks limit of ${options.limit}.`
+                    : `Skipping requests in this call due to the remaining maxRequestsPerCrawl budget of ${requestLimit}, which is lower than the enqueueLinks limit of ${options.limit}.`);
             }
             await Promise.all(allSkipped.map(async ({ url, reason }) => {
                 await this.handleSkippedRequest({ url, reason });
@@ -1706,11 +1708,16 @@ export class BasicCrawler {
      * To stop the crawler gracefully (waiting for all running requests to finish), use {@link BasicCrawler.stop|`crawler.stop()`} instead.
      */
     async teardown() {
-        serviceLocator.getEventManager().emit(EventType.PERSIST_STATE, { isMigrating: false });
+        // When this crawler initialized the event manager, its close() call emits
+        // the final persistence event after the crawler-specific state has been
+        // saved. External event managers still need an explicit event here.
+        if (!this.#closeEvents) {
+            serviceLocator.getEventManager().emit(EventType.PERSIST_STATE, { isMigrating: false });
+        }
+        await this.#sessionPoolDep.ifOwned(async (pool) => pool.teardown({ persistState: this.#closeEvents ?? false }));
         if (this.#closeEvents) {
             await serviceLocator.getEventManager().close();
         }
-        await this.#sessionPoolDep.ifOwned((pool) => pool.teardown());
         await this.#autoscaledPool?.abort();
         await this.#concurrencySystemDep?.ifOwned((system) => system.stop());
     }

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/basic",
-    "version": "4.0.0-beta.127",
+    "version": "4.0.0-beta.129",
     "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": "^2.0.0",
         "@apify/timeout": "^0.4.4",
         "@apify/utilities": "^2.15.5",
-        "@crawlee/core": "4.0.0-beta.127",
-        "@crawlee/http-client": "4.0.0-beta.127",
-        "@crawlee/types": "4.0.0-beta.127",
-        "@crawlee/utils": "4.0.0-beta.127",
+        "@crawlee/core": "4.0.0-beta.129",
+        "@crawlee/http-client": "4.0.0-beta.129",
+        "@crawlee/types": "4.0.0-beta.129",
+        "@crawlee/utils": "4.0.0-beta.129",
         "csv-stringify": "^6.5.2",
         "tldts": "^7.0.6",
         "tslib": "^2.8.1",
@@ -53,7 +53,7 @@
         "zod": "^4.4.3"
     },
     "optionalDependencies": {
-        "@crawlee/impit-client": "^4.0.0-beta.127"
+        "@crawlee/impit-client": "^4.0.0-beta.129"
     },
     "lerna": {
         "command": {
@@ -62,5 +62,5 @@
             }
         }
     },
-    "gitHead": "4aa4a4d8d105bb530649ac5cd9197a3169106bd9"
+    "gitHead": "b8a2e854bb8620679ca8e9f774fce4932c4e3b51"
 }