Challenge evaluation frontend - #74281
Open
Nokondi wants to merge 3 commits into
Open
Conversation
ChallengeResponse gains an evaluation_status enum and ready_for_evaluation?, ChallengeResponseAsset gains uploaded? and download_bytes, and ChallengeEvaluationPromptHelper builds the OpenAI messages and structured-output schema from a challenge's rubric. Nothing invokes these yet; the evaluation job and endpoint follow in a separate PR. ChallengeResponse#summarize now omits the evaluation fields (evaluation_result, evaluation_status, student_feedback, evaluated_at) unless include_evaluation is set: students will not see their AI evaluation until a teacher has reviewed it. Nothing writes these fields yet, so no observable behavior changes. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
POST /challenge_responses/:id/evaluate (owner-only) enqueues EvaluateChallengeResponseJob, which runs the student's text and transcript through the PII and profanity filters, sends the response content (including whiteboard images) to OpenAI with a structured-output schema built from the challenge's rubric, and records the outcome in evaluation_result/evaluation_status. Content filter hits are terminal statuses and never reach the LLM. The result is stored for later teacher review (teacher view is future work), so the endpoint is fire-and-forget: clients get a 202 and never poll. GET /challenge_responses/:id now includes the evaluation fields for teachers only. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
After the asset upload succeeds, both challenge modalities fire a fire-and-forget POST to /challenge_responses/:id/evaluate; the student never sees the result, so nothing waits on or polls for it. A shared DSCO Dialog in ChallengeBox confirms submission for both modalities, replacing VideoChallenge's inline text (which previously showed even when the upload had failed; the submitted callback now fires only on success). The ChallengeResponse type drops the evaluation fields the server now withholds from students, and the asset field is fixed to download_url, matching what the server actually sends. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Jul 31, 2026
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.
Part 3 of 3
Adds frontend connections for challenge activity rubric evaluation
Links
Part 1
Part 2
Testing story
Added and updated unit tests
Deployment notes
This will be deployed after parts 1 and 2 have been merged.
Privacy and security