pagetrace 0.7.0 → 0.8.0

package/CHANGELOG.md

@@ -6,6 +6,18 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 While the version is below 1.0.0, breaking changes ship in a minor release.
 
+## [0.8.0] - 2026-09-06
+
+### Fixed
+
+- `siteUrl` now overrides the crawled origin for an origin crawl, not just a
+  `--dir` crawl. Checking a local build or a preview deployment means crawling
+  `http://localhost:3000` while every page's canonical points at production, so
+  `canonical.offsite` fired on every page and made the check useless in exactly
+  the setup it is most wanted. Where you crawl and what the site calls itself are
+  separate things; `siteUrl` is now the authority on the latter. Without it the
+  crawled origin is still used, so nothing changes for a plain production crawl.
+
 ## [0.7.0] - 2026-09-06
 
 ### Changed
@@ -237,6 +249,7 @@ Initial release. `snapshot`, `check` and `audit` commands; filesystem and HTTP
 crawling; diff classified by transition; absolute, cross-page and hreflang audit
 rules; pretty, JSON, markdown, GitHub and HTML reporters.
 
+[0.8.0]: https://github.com/shyamexe/pagetrace/compare/v0.7.0...v0.8.0
 [0.7.0]: https://github.com/shyamexe/pagetrace/compare/v0.6.0...v0.7.0
 [0.6.0]: https://github.com/shyamexe/pagetrace/compare/v0.5.0...v0.6.0
 [0.5.0]: https://github.com/shyamexe/pagetrace/compare/v0.4.0...v0.5.0

package/README.md

@@ -156,7 +156,7 @@ Alongside the diff, `check` runs absolute rules: missing title, canonical, `h1`,
 }
 ```
 
-`siteUrl` is only needed for a `--dir` crawl, and only to detect canonicals pointing at another host — a staging hostname leaking into production canonicals. A `--url` crawl infers it.
+`siteUrl` is what the site calls itself, which is not always where you are crawling it. It is what `canonical.offsite` compares against, so set it when checking a `--dir` build, and when crawling a local build or a preview deployment whose pages carry production canonicals. A plain crawl of production infers it.
 
 Every finding has a stable `code`. Set any code to `error`, `warn`, `info`, or `off`.
 

package/dist/cli.cjs

@@ -1451,7 +1451,11 @@ async function snapshotFromOrigin(origin, options = {}) {
   const base = new URL(origin);
   const agents = options.aiAgents ?? DEFAULT_AI_AGENTS;
   const timeout = options.timeout;
-  const site = { origin: base.origin, robotsTxt: null, llmsTxt: null };
+  const site = {
+    origin: options.siteUrl ? new URL(options.siteUrl).origin : base.origin,
+    robotsTxt: null,
+    llmsTxt: null
+  };
   const limit = options.limit ?? 200;
   const robots = await fetchText(new URL("/robots.txt", base).href, timeout);
   if (robots !== null) site.robotsTxt = extractRobotsTxt(robots, agents);
@@ -1641,7 +1645,7 @@ cli.command("audit", "Audit a site as it stands, with explanations and fixes").o
   }
 });
 cli.help();
-cli.version("0.7.0");
+cli.version("0.8.0");
 async function main() {
   try {
     cli.parse(process.argv, { run: false });

package/dist/cli.js

@@ -1428,7 +1428,11 @@ async function snapshotFromOrigin(origin, options = {}) {
   const base = new URL(origin);
   const agents = options.aiAgents ?? DEFAULT_AI_AGENTS;
   const timeout = options.timeout;
-  const site = { origin: base.origin, robotsTxt: null, llmsTxt: null };
+  const site = {
+    origin: options.siteUrl ? new URL(options.siteUrl).origin : base.origin,
+    robotsTxt: null,
+    llmsTxt: null
+  };
   const limit = options.limit ?? 200;
   const robots = await fetchText(new URL("/robots.txt", base).href, timeout);
   if (robots !== null) site.robotsTxt = extractRobotsTxt(robots, agents);
@@ -1618,7 +1622,7 @@ cli.command("audit", "Audit a site as it stands, with explanations and fixes").o
   }
 });
 cli.help();
-cli.version("0.7.0");
+cli.version("0.8.0");
 async function main() {
   try {
     cli.parse(process.argv, { run: false });

package/dist/index.cjs

@@ -1490,7 +1490,11 @@ async function snapshotFromOrigin(origin, options = {}) {
   const base = new URL(origin);
   const agents = options.aiAgents ?? DEFAULT_AI_AGENTS;
   const timeout = options.timeout;
-  const site = { origin: base.origin, robotsTxt: null, llmsTxt: null };
+  const site = {
+    origin: options.siteUrl ? new URL(options.siteUrl).origin : base.origin,
+    robotsTxt: null,
+    llmsTxt: null
+  };
   const limit = options.limit ?? 200;
   const robots = await fetchText(new URL("/robots.txt", base).href, timeout);
   if (robots !== null) site.robotsTxt = extractRobotsTxt(robots, agents);

package/dist/index.d.cts

@@ -94,8 +94,10 @@ interface Config {
     /** Minimum word count before a page is flagged as thin. */
     minWordCount?: number;
     /**
-     * The site's own origin, e.g. "https://example.com". Lets a --dir crawl detect
-     * canonicals pointing at another host; an origin crawl infers it.
+     * The site's own origin, e.g. "https://example.com". Used to detect canonicals
+     * pointing at another host. A --dir crawl has no other source for it, and an
+     * origin crawl of a local build or preview deployment needs it to override the
+     * URL being crawled, since those serve production canonicals.
      */
     siteUrl?: string;
 }

package/dist/index.d.ts

@@ -94,8 +94,10 @@ interface Config {
     /** Minimum word count before a page is flagged as thin. */
     minWordCount?: number;
     /**
-     * The site's own origin, e.g. "https://example.com". Lets a --dir crawl detect
-     * canonicals pointing at another host; an origin crawl infers it.
+     * The site's own origin, e.g. "https://example.com". Used to detect canonicals
+     * pointing at another host. A --dir crawl has no other source for it, and an
+     * origin crawl of a local build or preview deployment needs it to override the
+     * URL being crawled, since those serve production canonicals.
      */
     siteUrl?: string;
 }

package/dist/index.js

@@ -1419,7 +1419,11 @@ async function snapshotFromOrigin(origin, options = {}) {
   const base = new URL(origin);
   const agents = options.aiAgents ?? DEFAULT_AI_AGENTS;
   const timeout = options.timeout;
-  const site = { origin: base.origin, robotsTxt: null, llmsTxt: null };
+  const site = {
+    origin: options.siteUrl ? new URL(options.siteUrl).origin : base.origin,
+    robotsTxt: null,
+    llmsTxt: null
+  };
   const limit = options.limit ?? 200;
   const robots = await fetchText(new URL("/robots.txt", base).href, timeout);
   if (robots !== null) site.robotsTxt = extractRobotsTxt(robots, agents);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pagetrace",
-  "version": "0.7.0",
+  "version": "0.8.0",
   "description": "Baseline your site's SEO and AEO surface, diff every build against it, and fail CI on regressions.",
   "main": "./dist/index.cjs",
   "scripts": {