fix(inference): url-prefetch follows meta-refresh + flags parked/empty sites#49
Merged
Merged
Conversation
…y sites The onboarding Pillar-1 URL fetch only followed HTTP redirects, so sites using <meta http-equiv="refresh"> (parked domains + some real sites) returned an empty shell and the model guessed the company from the domain name. Now: follow one meta-refresh hop; mark pages with <120 chars of readable text as FETCH FAILED (parked/empty/JS-rendered); detect common parking fingerprints (IONOS/GoDaddy/ Sedo/"defaultsite"/"coming soon"). Verified live: apple.com -> real content; a parked IONOS domain -> COULD_NOT_READ_SITE through the Realtime onboarding worker. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pillar-1 URL fetch only followed HTTP redirects, so sites using
<meta http-equiv=refresh>(parked domains + some real sites) returned an empty shell and the model guessed the company from the domain name. Now follows one meta-refresh hop and flags parked/empty/JS-only pages as FETCH FAILED so the model says it couldn't read the site instead of inventing one.Verified live through the Realtime onboarding worker: apple.com → 820 chars real content; a parked IONOS domain → COULD_NOT_READ_SITE. Already rebuilt + restarted on the Mac inference-server.
🤖 Generated with Claude Code