Repository navigation
Document what the Issues classifier reads, fix stale metadata-only exception - #1545
Merged
jpetey75 merged 1 commit intoOct 23, 2026
Conversation
lightdash-bot
added
the
cloudy-needs-review
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
Contributor
Documentation validation✅ All blocking checks passed. Component system0 finding(s) across the corpus. Findings on lines this pull request touched are annotated inline in Files changed. |
jpetey75
deleted the
cloudy/docs-document-what-the-issues-classifier-reads-fix-stal-9abebb20
branch
October 23, 2026 15:23
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two related fixes in the AI agent docs.
The Issues page described agent turns as "scanned in the background" by the review classifier without ever saying what it reads. The Privacy and data handling section now explains that the classifier works from the stored record of a turn (the user's prompt, the agent's answer, the agent's config snapshot, and the tool calls with a truncated preview of their saved results) and runs no queries of its own. It also notes that the classifier respects each agent's data access setting: with data access off, the agent's query tools save only row counts (and column names for SQL) with no row data, so the classifier never sees result rows for those turns, though it still sees prompt text, answers, and the filter values used to build the query. A short pointer in the earlier description of scanning links down to this detail instead of repeating it.
The data access control page described metadata-only mode as withholding data values "except for one-row query results." That exception doesn't match how the query tools behave: with data access off they return row counts (and column names for SQL) but never row values, regardless of result size. The bullet is corrected to match.
A customer pointed this docs problem out in a support thread. Written by Cloudy's docs writer; a teammate reviews it before merge, and edits are welcome.