dsh-read-url 1.2.0 → 1.3.1

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "dsh-read-url",
-  "version": "1.2.0",
-  "description": "DeepSeek Harness URL reader: fetch any webpage (HTML/JSON/RSS/Atom), auto-detect encoding (UTF-16 BOM/GBK/Big5/Shift-JIS), extract clean main content with auto-pagination, output compact text/Markdown to save tokens. Zero runtime dependencies, no API key, drop-in.",
+  "version": "1.3.1",
+  "description": "DeepSeek Harness URL reader: fetch any webpage (HTML/JSON/RSS/Atom), auto-detect encoding (UTF-16 BOM/GBK/Big5/Shift-JIS), extract clean main content with auto-pagination, output compact text/Markdown to save tokens. Zero runtime dependencies, no API key, drop-in. Follows meta-refresh shells, reads JSON-LD metadata, honors base href.",
   "type": "module",
   "main": "index.js",
   "files": [

package/proxy-fallback.js

@@ -97,11 +97,10 @@ export async function fetchViaCurlProxy(url, cfg, externalSignal, proxyOverride)
     '--max-filesize', String(cfg.maxBytes), // unit is BYTES, not KB
     '-x', proxy,
     '-A', cfg.userAgent,
-    // trailing metadata line: "<http_code> <content_type> <url_effective>"
+    // trailing metadata line: "<code> <content_type> <url_effective>"
     // (url_effective last: content_type may be empty, URLs never contain
-    // unencoded spaces — parse from both ends). Without it a redirected
-    // fetch kept the ORIGINAL url as finalUrl and same-host pagination /
-    // link resolution ran against the wrong host.
+    // unencoded spaces — parse from both ends so the final URL of a redirect
+    // chain survives).
     '-w', '\n%{http_code} %{content_type} %{url_effective}',
     url,
   ]