Jesse_Chen f5c02924c9 fix(rectification): show spoken collect questions in the chat UI ...

Spoken collect prompts lived only in GET current_question. The chat never
parsed that field, Agent projections returned null after evidence writes,
and active_focus followups collapsed the questionId. Render the parsed
prompt, keep choiceReady on real cards, and give collect focuses a stable
domain-scoped id.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-30 00:51:14 +08:00

..

adr

docs: configure agent engineering workflows

2026-07-28 14:40:24 +08:00

agents

docs: configure agent engineering workflows

2026-07-28 14:40:24 +08:00

benchmark

feat: import oracle collection and calibration parity

2026-07-17 22:35:19 +08:00

operations

fix: repair production lock through direct mount

2026-08-16 04:16:12 +08:00

research

fix(web): count only training events for discrimination and split user-stop from validated range

2026-08-26 19:36:04 +08:00

roadmap

Add jyotish oracle evidence calibration gate

2026-06-25 18:33:26 +08:00

superpowers

fix(home): send starter cards instead of filling the composer

2026-08-21 22:02:40 +08:00

testing

chore: retire legacy rectification runtime

2026-08-07 12:55:32 +08:00

BUG_HISTORY.md

fix(rectification): show spoken collect questions in the chat UI

2026-08-30 00:51:14 +08:00

user_jhora_capture_guide.md

chore: remove private chart data from project

2026-07-08 17:03:04 +08:00

vibe_coding_setup.md

Harden Jyotish runtime evidence gates

2026-07-05 18:27:33 +08:00