Strip HTML to text before AI multi-recipe detection#75
Merged
Conversation
Root cause of production failure: sending 80KB of raw HTML (with CSS, JS, nav, ads) to CookingQA for multi-recipe detection was: 1. Burning through the Haiku 50K input token/min rate limit 2. Producing unreliable detection results (AI couldn't find recipes buried in HTML noise) 3. Taking 27+ seconds for detection alone Fix: add stripHTMLToText() that removes script/style/nav/header/footer blocks, HTML comments, and tags, then collapses whitespace. Produces clean text ~10-20x smaller than raw HTML. - Detection: uses stripped text capped at 15KB (was 80KB raw HTML) - Per-card extraction: uses stripped text capped at 30KB (was 100KB raw) - Both paths now stay well under Haiku's token limits Co-Authored-By: Claude Opus 4.6 (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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes production failure where multi-recipe detection was:
Fix:
stripHTMLToText()removes script/style/nav/header/footer blocks, HTML comments, and all tags before sending to AI. Produces clean text ~10-20x smaller.Test plan
go build && go vet && go test ./internal/...pass🤖 Generated with Claude Code