sit002 c25bcfddd0 fix: improve LLM prompt to use actual rubric score ranges ... Previous prompt had hardcoded 0-3 score examples which misled LLM. Now prompt instructs LLM to read max_score from rubric for each criterion.		2025-12-02 14:21:42 +08:00
..
workflow_templates	Initial commit	2025-12-01 22:12:02 +08:00
aggregate_final_grade.py	feat: preserve LLM grading details (criteria, confidence, reasons)	2025-12-02 12:05:48 +08:00
aggregate_llm_grades.py	Initial commit	2025-12-01 22:12:02 +08:00
create_minimal_metadata.py	feat: preserve LLM grading details (criteria, confidence, reasons)	2025-12-02 12:05:48 +08:00
generate_pdf_report.py	feat: add commit SHA marker at top-right corner of each page	2025-12-02 14:08:08 +08:00
grade_grouped.py	Initial commit	2025-12-01 22:12:02 +08:00
grade.py	Initial commit	2025-12-01 22:12:02 +08:00
llm_grade.py	fix: improve LLM prompt to use actual rubric score ranges	2025-12-02 14:21:42 +08:00
objective_grade.py	Initial commit	2025-12-01 22:12:02 +08:00
post_comment.py	Initial commit	2025-12-01 22:12:02 +08:00
run_tests.py	Initial commit	2025-12-01 22:12:02 +08:00
test_objective_grade.sh	Initial commit	2025-12-01 22:12:02 +08:00
upload_metadata.py	fix: handle list response when checking file existence	2025-12-02 10:01:40 +08:00