Fix fact checker service failures and refresh Parallel APIs - #64
Draft
georgeatparallel wants to merge 1 commit into
Draft
Fix fact checker service failures and refresh Parallel APIs#64georgeatparallel wants to merge 1 commit into
georgeatparallel wants to merge 1 commit into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When an inference request fails, the fact checker can report that the input contains no facts or return an empty unsure verdict. The text-only stream filters out provider errors. Consume the full stream, show safe service-error messages, and reject incomplete verdicts so failures stay visible.
Update Search and Extract to the stable Parallel APIs, pin the tested SDK version, and document the existing Cloudflare logs and analytics limitations.
Validation: nine regression tests using the real SDKs with mocked HTTP responses, TypeScript, default and production Worker deployment dry runs, and repository secret checks pass. Live local tests verify a true claim, reject a false claim, and complete URL extraction with a sourced verdict.
Production recovery still requires checking the deployed Worker's service credentials and logs, then verifying both input paths after deployment.