xiaowei 98e541b985 fix: distill LLM 模型切换 gemma-4-31b-it + JSON 解析增强 ... 根因链: 1. gpt-oss-120b 是 reasoning 模型，content=null 答案全在 reasoning 字段， 代码只读 content/reasoning_content（OpenAI 用 reasoning 字段名）→ parse 失败 → 永远降级 keyword 提取 (facts=1 entities=0) 2. skill 记载的 m3/m2.7/mistral-large 均已 EOL 或渠道失效 (2026-07-27 后) 3. gemma-4-31b-it 对 '0.X' 占位符输出 0.0 → prompt 改为明确 0-1 浮点说明 修复: - engine.go: 支持 reasoning 字段 + 剥离 markdown code fence + prompt 评分说明明确化 - zhiyid.service: LLM_MODEL=google/gemma-4-31b-it 验证: LLM entities=2, overall=1.000, facts=3 entities=2, recall 命中 0.765		2026-08-02 23:59:29 +08:00
..
client	…
cmd	fix: add clusters_found/noise_points/quality_score to consolidate API response	2026-06-08 10:35:10 +08:00
internal	fix: distill LLM 模型切换 gemma-4-31b-it + JSON 解析增强	2026-08-02 23:59:29 +08:00
proto	…
static	…
go.mod	…
go.sum	…
integration_test.go	…
zhiyid-new	fix: H1-H6 gaps all resolved	2026-07-02 00:43:46 +08:00