Repository navigation
test(corpus): calibrate notification-t case expectations against live… - #202
Merged
Merged
Conversation
… LLM Tune the Notification-T corpus cases after a real-LLM run so the live suites pass deterministically: - assert only the deterministic topic field on success; drop the exact-match assertions on subscriptionCondition/notificationDataFormat whose punctuation the LLM normalizes non-deterministically (为/为: and trailing 。 vary per run) - re-categorize the incomplete-format cases (service-recovery TC00000003) from 正常 to 异常, expecting negotiation.semantic_rejected, since the semantic validator correctly rejects the missing required items - switch the subscribe-incident fault-priority wording from English to Chinese (critical、high triggers content.value_not_allowed in the text flow while the data flow accepts it) - drop the from-text slot.not_provided case (the LLM fabricates the required 上报通知数据格式 slot value non-deterministically); keep the deterministic from-data variant Signed-off-by: z30048074 <zouwenchong@h-partners.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
… LLM
Tune the Notification-T corpus cases after a real-LLM run so the live suites pass deterministically:
Description
Related Issue(s)
Type of Change
Checklist
git commit -s) per the DCOAdditional Context