root/Jyotisha
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity
2,360 Commits 53 Branches 0 Tags
84b293fb471817d112404bef205a64a5eb2f308e
Commit Graph
7 Commits
Author SHA1 Message Date
Jesse_ChenandClaude Fable 5.1 84b293fb47 feat(consult): 对话口气改成反差与扮演象的形状
Independent Staging Quality Gate / validate (push) Failing after 7m5s
Details
Independent Staging Quality Gate / publish (push) Skipped
Details 
产品判定现有人设（懂行、可靠、说人话的占星师朋友）出来的是顾问报告。
人设改成把人当一个人认真对待、行动力很强、嘴有点毒但靠谱的同事：直接、
有立场、带一点锋利，毒只对处境不对人且每句锋利都要有盘上的证据。

开场从「一句结论 + 2–3 条短要点 + 一句下一步」换成固定形状，三种模式共用：
反差（表面 A 底下 B，命名成一个格局）→ 谁在推、谁在修（大运主星在推，
行运只负责把结果修得体面）→ 别去应 X 的象，去扮演 Y 的象 → 最多三条短行动
（破折号短句，各 ≤ 20 字）。仍无标题、总长 ≤ 400 字。术语当场用引号里的
白话套住。申报时段与无出生分钟两条降级路线形状照给，只把「谁在推谁在修」
换成窗口内稳定层或公开日历，不编月份。

新增希望纪律：盘上有转机且 answer_policy 允许精确应期时说到月份；没有就说
这段时间是拿来干什么的、可以扮演哪个象。禁「一切都会好 / 相信自己 / 加油 /
你值得更好的 / 宇宙自有安排」。

零业务逻辑改动，Skill 版本不变。tsc 0 错、lint 0 error（118 warning 不变）、
npm test 3468→3471 条且 36 条失败与基线 ff0427cf 逐条相同、/ 仍 Static、
首屏 gzip 两侧字节相同。

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JUei7K13cYxLHE3Axe4A45
 2026-09-17 16:18:07 +00:00
jesse-ux 8144fca27d fix(chat): fold natal reports and drop homepage topic cards
Independent Staging Quality Gate / validate (push) Failing after 9m47s
Details
Independent Staging Quality Gate / publish (push) Skipped
Details 
Homepage no longer waits on /api/onboarding for six starter questions.
Natal answers show the spoken layer first; the Level 2 skeleton sits in a
collapsed 完整分析 block. Wide tables scroll sideways on a phone. Form
inputs are 16px so iOS does not zoom on focus.
 2026-09-15 12:27:16 +08:00
Jesse_ChenandCursor 17b36f3a9f fix(consult): pin daily entrypoint domains and sentence-filter thinking (BUG-612/613)
Independent Staging Quality Gate / validate (push) Successful in 10m6s
Details
Independent Staging Quality Gate / publish (push) Successful in 2m4s
Details 
Homepage「深入看今日」was rewritten to natal 综合, then each compose slice burned its only step on a tool call, so the answer stayed empty. Pin the route theme, write the three daily sections with tools disabled, and filter thinking by sentence so English word-salad cannot leak.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-09 17:38:08 +08:00
Jesse_ChenandCursor ed9497e76a fix(voice): speak first, then keep Level 2 skeleton and boundary semantics 
Natal answers were opening on parameter tables, and rectification turns were one-sentence legal copy. Centralize user-facing strings, keep representative-minute and question-slot red lines, and stop duplicating the opening collect prompt as a second assistant message.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-02 02:27:50 +08:00
Jesse_ChenandCursor 04463e9af3 feat(web): show consult runs as a Lucide timeline with sliced compose 
Keep provider thinking on a separate channel so process talk is not billed as the spoken reply (BUG-359).

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-23 14:38:50 +08:00
Jesse_ChenandCursor 995b752e70 fix(web): keep consultation thinking above one spoken answer 
Per-domain thinking trees were interleaved with sliced analysis, so a finished reply still looked like unfinished checklists. One collapsed thinking panel and one full body restores the reading order.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-23 01:49:05 +08:00
Jesse_ChenandCursor 0ca7da997f fix(web): stop consultation thinking from pinching the answer 
Disable provider thinking so Flash CoT cannot fill max_tokens, raise the
spoken budget to 16384, emit a server-owned step tree, and continue once
when the body ends on length.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-22 21:19:00 +08:00