Closed
Conversation
Implements POST /api/interview/turn using statelessGenerate() instead of
a direct callLLM() call, aligning the interview turn endpoint with the
same orchestration path used by /api/chat.
- Coach agent (turn 1): gives feedback on the candidate's latest answer
- Interviewer agent (turn 2): asks the next follow-up question
- Both agents are defined as inline agentConfigs (no registry required)
- Text deltas accumulated server-side; JSON response shape kept
compatible with existing frontend: { feedback, nextQuestion,
coachName, interviewerName }
- Provider config resolution (API key, baseUrl, SSRF guard) mirrors
the chat route exactly
https://claude.ai/code/session_019MGKMBhcRnwEkGCRdN1m77
The coding track was always scoring full marks (e.g. 3/3) regardless of
solution correctness because:
- score was set to reviews.length (= number of problems, always = total)
- percentage was hardcoded to 100%
- all problem topics were unconditionally added as weakAreas
- the review-code route silently returned {} on parse failure
Changes:
- Add score (0-10) and verdict (pass/fail) fields to CodeReviewResult
- Update buildCodeReviewPrompt to request score + verdict from the LLM
- review-code route: clamp/normalise score, return 502 if fields missing
- quiz-runner: derive real score from passed.length, compute real %, only
flag weak areas for problems with verdict=fail or score<5
- QuizResults display uses actual pass count instead of reviews.length
- CodeReviewPanel now shows per-problem score badge and missing points
https://claude.ai/code/session_019MGKMBhcRnwEkGCRdN1m77
Contributor
|
Thanks for the contribution, Siddharth! This PR covers a lot of ground (Interview module, Quiz module, Hindi locale — 86 files), which makes it hard to review as a single unit. We'd prefer smaller, focused PRs so each feature can be discussed and reviewed independently. Suggested next steps:
Happy to review focused follow-ups! |
13 tasks
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
3 participants
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.
Summary
Related Issues
Changes
Type of Change
Verification
Steps to reproduce / test
What you personally verified
Evidence
pnpm check && pnpm lint && npx tsc --noEmit)Checklist