Repository navigation
Creating FRQ Runners for AI Grading - #1909
Merged
Merged
Conversation
- Introduced a new Reflection Runner feature that allows students to submit written answers alongside code submissions. - Updated AGENTS.md and AGENTS_MD_DOCUMENTATION.md to include details about the Reflection Runner. - Modified the Gist export process to include reflection answers in the same submission. - Created a new HTML template for the Reflection Runner, styled to match the existing code runner. - Implemented JavaScript logic to handle the reflection runner's behavior, including saving drafts and submitting answers. - Added tests for the Reflection Runner conversion and functionality to ensure proper integration. - Updated various stylesheets to accommodate the new reflection runner design.
Contributor
|
This is a lot in a day. The thought I have is whether .reflection-runner-container is different from another container. Not sure it would need its own unique Sass rule. The example looks sensible. REFLECTION RUNNER is a good name, and asking something after you code is a good pedagogical practice. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add reflection answer boxes to the Variables Challenge (Hack #1)
Testing + Backend
Will commit backend after resolving other conflicts and run through process with Avantika.
Link to testing issue on checking FRQ runner submission to GIST for AI Grading: AAApages#51 (comment)
Problem
The JavaScript Variables and HTML DOM Challenge (
/game/essentials/variables-challenge) asks three"Reflect:" questions in Hack #1, but there was nowhere on the page to answer them. Students could not
submit reflections, so the AI grader scored Hack #1 (60% of the grade) without them, which lowered scores.
Change
hacks at each "Hack #N (Weight: …)" heading, so boxes placed later would be graded as part of
Hack Gamify Team Teach - ML(Tablesaw, Weka, Smile) #2 (40%) instead of Hack Add site.baseurl fix/ updates #1.
_projects/systems/gamebuilder/notebooks/2026-02-16-variables-challenge.ipynb).How the reflection runner works
numbers. 📤 Submit replaces Run, and there's no output panel.
code, as a
.mdfile marked"reflection"in the Gist manifest, so the AI grader grades it aswritten work.
Testing
heading, and are included in the page's Submit Code bundle.