Feature/ab#32006 ai retry and output validation#2106
Draft
jacobwillsmith wants to merge 4 commits intodevfrom
Draft
Feature/ab#32006 ai retry and output validation#2106jacobwillsmith wants to merge 4 commits intodevfrom
jacobwillsmith wants to merge 4 commits intodevfrom
Conversation
# Conflicts: # applications/Unity.GrantManager/src/Unity.GrantManager.Application/AI/OpenAIService.cs # Conflicts: # applications/Unity.GrantManager/src/Unity.GrantManager.Application/AI/OpenAIService.cs
🧪 Unit Test Results (Parallel Execution)📊 Summary
📄 HTML Reports
|
🧪 Unit Test Results (Parallel Execution)📊 Summary
📄 HTML Reports
|
🧪 Unit Test Results (Parallel Execution)📊 Summary
📄 HTML Reports
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull request overview
This pull request adds generic retry handling with output-shape validation to AI generation paths in
OpenAIService. The goal is to reduce transient malformed/partial model responses from being accepted while keeping existing service behavior unchanged when valid output is produced.It also includes a targeted fix for scoresheet section validation so expected question IDs are extracted from both supported section payload shapes (
[...]and{ questions: [...] }), avoiding false retry exhaustion on valid responses.Changes:
GenerateWithRetryAsynchelper with bounded attempts and validator callbacks