| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| admin | ||
| agent | ||
| ai | ||
| auth | ||
| clinical-gap | ||
| facts | ||
| patient | ||
| persona | ||
| plan | ||
| plan-aggregate | ||
| realtime-coach | ||
| sync |
问题(用户在邵竞红37发现):卡片标'(诊断)'但其实是影像AI分析(code_source=image_ai)。 '(诊断)'只是 fact 类型(diagnosis_record,对应'(医生建议)'=recommendation),不区分诊断内部 医生 vs 影像AI。区分靠 content.code_source,后端打分已用(影像置信度0.85/0.9<医生1.0),但没进 triggers。 - scenario uniqueTriggers + lead triggerType:code_source=image_ai 的诊断 → trigger type='image_finding' (医生诊断仍 diagnosis;recommendation 不变);sourceStr 文本同步加 '(影像AI)'(喂 AI 话术更谨慎)。 - canonical-codes triggerTypeLabelZh: image_finding '影像所见'→'影像AI'(强调AI来源/低置信)。 - 前端 reason-line 用 triggerTypeLabelZh 自动渲染 → '(影像AI)' / 混合 '(诊断+影像AI)',零改。 验证(本地清plans重算):image_finding trigger 77 个;姜学英 K03@34(唯一诊断=image_ai)→ type=image_finding。 注:改 scenario 需 TRUNCATE plans + recompute 才生效(增量 upsert 不重写旧 signals);服务器下次部署随之生效。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| admin | Loading commit data... | |
| agent | Loading commit data... | |
| ai | Loading commit data... | |
| auth | Loading commit data... | |
| clinical-gap | Loading commit data... | |
| facts | Loading commit data... | |
| patient | Loading commit data... | |
| persona | Loading commit data... | |
| plan | Loading commit data... | |
| plan-aggregate | Loading commit data... | |
| realtime-coach | Loading commit data... | |
| sync | Loading commit data... |