@absolutejs/rag 0.22.0 → 0.22.2

package/CHANGELOG.md

@@ -6,6 +6,18 @@ This file is generated by `absolute-changelog` from the entries in
 `changelog/`. Edit an entry, not this file — and add new ones under
 `changelog/unreleased/`.
 
+## 0.22.2 — 2026-09-24
+
+### Fixed
+
+- **Replace backtracking HTML app-shell detection with DOM inspection and allow isolated reader clients to fail without in-process parsing** (`readRAGWebpage`, `createWebsiteReaderClient`, `createWebpageReaderClient`)
+
+## 0.22.1 — 2026-09-24
+
+### Fixed
+
+- **Retry owned-index initialization after a transient database outage instead of retaining a rejected initialization promise** (`createWebIndex`)
+
 ## 0.22.0 — 2026-09-24
 
 ### Added

package/WEB_INDEX.md

@@ -104,3 +104,5 @@ Schedule retention of obsolete generations in the host database/storage lifecycl
 `WEB_INDEX_TEST_DATABASE_URL=... bun test tests/webIndex.test.ts tests/webIndexFlows.test.ts` uses an explicit disposable PostgreSQL database with pgvector. Tests clear the owned-index tables in that database. They cover restart, native retrieval filters, worker fencing, tenant isolation, bounded admission, robots failure, conditional requests, deletion, model-generation isolation, authorization and evidence attribution.
 
 `benchmarks/web-index/live.ts --live --output=NEW_PATH` declares four public pages and compares native lexical retrieval with Brave using identical extraction/review settings. It caps the run at eight research searches and sixteen model calls, preserves raw journals and reports cold/first and warm latency samples separately. It requires its own disposable database. Those pages were selected in advance; results are not web-wide or held-out discovery claims. No Exa parity is implied.
+
+The final controlled 100-page lifecycle run measured 11.31 ms warm query p50 / 13.36 ms p95, 88.50 ms update-to-query visibility and 37.94 ms takedown-to-confirmation. It uses PostgreSQL 15, simulated public-page responses and deterministic vectors, not external embedding APIs. Run `benchmarks/web-index/lifecycle.ts` with a disposable database and `--output=NEW_PATH` to reproduce; do not generalize those numbers to public network/model latency.

package/changelog.json

@@ -2,6 +2,34 @@
 	"contract": 1,
 	"name": "@absolutejs/rag",
 	"releases": [
+		{
+			"changes": [
+				{
+					"kind": "fixed",
+					"summary": "Replace backtracking HTML app-shell detection with DOM inspection and allow isolated reader clients to fail without in-process parsing",
+					"symbols": [
+						"readRAGWebpage",
+						"createWebsiteReaderClient",
+						"createWebpageReaderClient"
+					]
+				}
+			],
+			"date": "2026-09-24",
+			"version": "0.22.2"
+		},
+		{
+			"changes": [
+				{
+					"kind": "fixed",
+					"summary": "Retry owned-index initialization after a transient database outage instead of retaining a rejected initialization promise",
+					"symbols": [
+						"createWebIndex"
+					]
+				}
+			],
+			"date": "2026-09-24",
+			"version": "0.22.1"
+		},
 		{
 			"changes": [
 				{

package/dist/research/index.js

@@ -111227,6 +111227,15 @@ var hasIncompleteAppContent = (html) => {
   const text = compact(main.textContent);
   return text.length < 100 || /^(?:loading|please wait)(?:[.\s]|$)/iu.test(text);
 };
+var hasEmptyAppRoot = (html) => {
+  const { document: document2 } = parseHTML(html);
+  return Array.from(document2.querySelectorAll("div,main,section")).some((element) => {
+    const attributes = Array.from(element.attributes);
+    const id = attributes.find((attribute2) => attribute2.name.toLowerCase() === "id")?.value.toLowerCase();
+    const classes = attributes.find((attribute2) => attribute2.name.toLowerCase() === "class")?.value.toLowerCase().split(/\s+/u) ?? [];
+    return (id !== undefined && ["root", "app", "__next"].includes(id) || classes.includes("todoapp")) && element.children.length === 0 && !element.textContent?.trim();
+  });
+};
 
 // src/web/text.ts
 var websiteHtmlText = (html) => {
@@ -117855,8 +117864,8 @@ var parseWebsiteServiceResult = (value) => {
   return row;
 };
 var createWebsiteReaderClient = (options) => async (input) => {
-  const timeoutMs = options.timeoutMs ?? 85000, reserveMs = options.fallbackReserveMs ?? 15000;
-  if (!(reserveMs > 0 && timeoutMs > reserveMs))
+  const timeoutMs = options.timeoutMs ?? 85000, reserveMs = options.fallback ? options.fallbackReserveMs ?? 15000 : 0;
+  if (!(reserveMs >= 0 && timeoutMs > reserveMs))
     throw new Error("Reader deadline must reserve fallback time");
   const signal = AbortSignal.any([
     ...input.signal ? [input.signal] : [],
@@ -117897,6 +117906,15 @@ var createWebsiteReaderClient = (options) => async (input) => {
     return result;
   } catch (error) {
     signal.throwIfAborted();
+    if (!options.fallback)
+      return {
+        status: "error",
+        text: "",
+        error: {
+          code: "reader_unavailable",
+          message: "Website reader unavailable. Retry shortly; no website evidence was retrieved."
+        }
+      };
     const result = parseWebsiteServiceResult(await options.fallback({ ...request, signal }));
     signal.throwIfAborted();
     return {
@@ -117956,7 +117974,7 @@ var titleOf = (html) => {
   const title = /<title\b[^>]*>([\s\S]*?)<\/title>/iu.exec(html)?.[1];
   return title ? prepareRAGDocument({ text: title, format: "html" }).normalizedText : null;
 };
-var isShell = (html, text) => text.length < 300 || hasIncompleteAppContent(html) || /(?:enable|requires?|turn on)\s+javascript|javascript\s+(?:is\s+)?(?:disabled|required)/iu.test(text) || /<(?:div|main|section)[^>]*(?:id=["'](?:root|app|__next)["']|class=["']todoapp["'])[^>]*>\s*<\//iu.test(html);
+var isShell = (html, text) => text.length < 300 || hasIncompleteAppContent(html) || /(?:enable|requires?|turn on)\s+javascript|javascript\s+(?:is\s+)?(?:disabled|required)/iu.test(text) || hasEmptyAppRoot(html);
 var isChallenge = (text) => /verify (?:that )?you are human|checking your browser|just a moment|enable javascript and cookies to continue|access denied/iu.test(text.slice(0, 1000));
 var readRAGWebpage = async (options) => {
   const attempts = [];
@@ -125413,5 +125431,5 @@ export {
   selectResearchMonitorEvents
 };
 
-//# debugId=9DCC894B3A3B129664756E2164756E21
+//# debugId=9B57E533D9808F8964756E2164756E21
 //# sourceMappingURL=index.js.map