Repository navigation
Improve agent recovery from the first eval run - #113
Merged
Merged
Conversation
- Suggest a field whose name ends with the guessed one at a camelCase boundary (name -> customerName), the most common rejected query. - Add a hint with the server's limit to HotChocolate page-size errors (HC0051), which the SDL cannot express. - Sample: replace the 'fastest animal' question, which the schema cannot answer, and state the orders page limit in its description.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to the first eval run against Azure AI Foundry (gpt-5.4-mini): 8/8 passed, 2.9 tool calls and ~4,400 tokens per question, but three things wasted calls.
name→customerNamecaused 3 of 4 rejected queries; the error listed the fields but had no "did you mean".NameSuggestions.Closestnow falls back to a field ending with the guessed word at a camelCase boundary.first: 100thenfirst: 20against a max of 2 (6 tool calls, 41 s). Server errors with HotChocolate'sHC0051now carry ahintwith the limit from the error's extensions (maxAllowedItems,coordinate).Design doc's Query quality table updated. Tests: 296 passed, 0 warnings.
Stacked on #112; base retargets to
mainonce that merges.