7 Commits

Author	SHA1	Message	Date
sit002	6ab2aec57e	Update content	2025-12-02 15:55:32 +08:00
sit002	5e8d901a18	security: remove .autograde from student repo ... - Grading scripts are now fetched from tests repo at runtime - Students cannot modify grading scripts to cheat - Workflow fetches scripts from private tests repo	2025-12-02 15:17:54 +08:00
sit002	3dc343684d	fix: enforce integer scores matching rubric scoring_guide ... - Prompt now explicitly requires integer scores (0/1/2/3/4) - Code rounds any decimal scores to nearest integer - Prevents LLM from giving 2.5, 3.5 etc.	2025-12-02 14:36:33 +08:00
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
sit002	38b6d5498d	fix: calculate total from criteria scores instead of trusting LLM ... LLM sometimes returns inconsistent total values. Now we always compute total = sum(criteria.score) for accuracy.	2025-12-02 14:19:16 +08:00
sit002	9de97bddf1	fix: allow --question to be a string instead of file path	2025-12-01 23:46:38 +08:00
sit002	d0a4992cd6	Initial commit	2025-12-01 22:12:02 +08:00