Repository navigation
fix(skills): handle REQS007 by its reason, since fallback_autoparse no longer retries - #1
Merged
Merged
Conversation
…o longer retries The extract skills said fallback_autoparse defaults to true and retries with autoparse. The Zenrows MCP server removed that fallback: the parameter is deprecated and has no effect, and REQS007 now carries a reason (domain_not_prepared, page_not_recognised, domain_not_enabled) with prepare_domain and prepared_domain_status for the first. The skills now follow that, mark mode='autoparse' deprecated and list include_html.
AnderRV
approved these changes
Oct 27, 2026
The release PR sets plugin.json and marketplace.json to 0.1.1, and the notes go on the GitHub release.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
The
extract-structured-dataandusing-zenrowsskills sayfallback_autoparse"defaults totrue, which retries once with autoparse". The Zenrows MCP server removed that fallback (zenrows-mcp 2.14). On the live server (2.16.1) the parameter reads "Deprecated, has no effect", andREQS007comes back with areasonand, for an unprepared domain, the next step (prepare_domain).What changed
extract-structured-data: theREQS007bullet handles eachreason:domain_not_prepared(prepare_domain, pollprepared_domain_status, retry),page_not_recognised(another page ormode='css', don't prepare again) anddomain_not_enabled(mode='css'or support).fallback_autoparseandmode='autoparse'are marked deprecated. The parameter table points toprepare_domain.using-zenrows: theextractparameter list dropsfallback_autoparseand addsinclude_html, with one line onprepare_domain/prepared_domain_status. TheREQS007error line reads thereason.fix(skills)commit.Skill text only. The same change goes to the other Zenrows plugin repos, including openai-zenrows, which these skills match.
Sources
Every step matches the live
extract,prepare_domainandprepared_domain_statusschemas on mcp.zenrows.com (2.16.1), the server'sREQS007error text, and docs.zenrows.com/extract/setup ("Domain coverage").Verification
extracton an unprepared domain in Copilot with this plugin.