2 commits

Author	SHA1	Message	Date
wangzhuc	df72e51ea1	feat: rewrite humanness_score.py with continuous scoring and param mapping ... - 11 checks across 2 tiers (6 statistical + 5 pattern), up from 6 - Continuous 0-1 scores instead of pass/fail booleans - Each check maps to a writing-config parameter via param field - New checks: negative emotion ratio, adverb density, vocabulary richness, sentence length range, self-correction patterns - New --tier3 flag for agent to pass LLM structural analysis score - param_scores in JSON output: flat param→score map for optimization - Standalone mode redistributes weights (T1=62.5%, T2=37.5%) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-03-30 19:54:11 +08:00
wangzhuc	8e16c70ead	新增优化循环框架：humanness_score.py + optimize_loop.py ... 借鉴 Karpathy autoresearch 的 change→score→keep/rollback 模式： - humanness_score.py: 固定打分器，两层评分（客观checklist + 主观读者感） 6项客观检查：禁用词/真实引用/破句/句长方差/段长方差/词汇温度 1项主观LLM判官（stub，需配置API） 复合分 0-100（越低越像人） - optimize_loop.py: 迭代框架，通过修改 writing-config.yaml 参数 自动生成文章→打分→保留或回滚→记录到 results.tsv Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-03-28 23:18:55 +08:00