Repository navigation
Conversation
The delta-cart-main-classic check passed a cart holding the right route, cabin and total on the wrong day. It now needs Trip Summary's journey date to be the date the task asked for. Delta shows the date without its year, so a relative fixture date can resolve to that form with "format": "month_day".
Contributor
Author
|
Closing: not wanted. The benchmark changes are in kernel/benchmarks#13. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
delta-cart-main-classicis graded from the Trip Summary page the agent leaves: route, cabin, passenger count and amount due. It did not check the date, so a cart holding a Main Classic ATL to MCO fare on the wrong day passed.Journey dateline to carry the date the task asked for.Thu, Dec 10), so a relative fixture date can resolve to that form:{"days_from_start": 28, "format": "month_day"}givesDec 10. The ISO form the prompt uses is unchanged.The rule accepts the date on the label's line or the next one, with or without a weekday or year around it.
Not changed
Flight numbers are still not compared with the page.
extractreads one value per pattern andsame_as_answercompares sets, so a connecting itinerary would fail a correct answer; that needs a multi-value extract first. Whether the fare is the cheapest is still left toagreement.Testing
node --test "bench/**/*.test.mjs": 131 passed. The new test grades the real intent against Trip Summary's visible text for one flight, and fails it when the task asked for another day (Dec 11, andDec 1againstDec 10).node scripts/validate-registry.mjs/purchase/flights/trip-summarypage was seen. The older/completepurchase/page the check also accepts was not, and no paired bench run was made.