10 Commits

Include renames

Author	SHA1	Message	Date
Jesse_ChenandCursor	0c0df42679	fix(rectification): require three answers before uncertainty stop ... One "一时说不好" no longer ends the interview. Plateau streaks use the same sample floor. Delivery copy states why the range stopped. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-03 12:08:37 +08:00
Jesse_ChenandCursor	35e5781e66	fix(rectification): gate collect-phase adopt cards and keep post-adopt verify answerable ... Public can_adopt follows session_outcome; reverse_verify reuses the persisted question id; offer cards settle on the owning message with a status-bar handoff. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-09-03 09:29:34 +08:00
Jesse_Chen	3a4396a4b7	fix(rectification): adopt evidence-based stop semantics	2026-08-31 12:50:30 +08:00
Jesse_ChenandCursor	68f0759eef	fix(rectification): persist the next interview after a choice tap ... Closing a discriminator used to leave GET without a card after refresh. Write the next dated question in the same request, skip childhood career and move probes, and do not continue a read-only turn when that question is already persisted. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-28 16:30:09 +08:00
Jesse_Chen	85db4591d3	fix(rectification): resolve typed focus answers deterministically	2026-08-27 20:31:05 +08:00
Jesse_Chen	518119acbd	fix(rectification): continue after structured choices	2026-08-27 09:23:32 +08:00
Jesse_ChenandCursor	b1173f7245	fix(web): count only training events for discrimination and split user-stop from validated range ... Three collected events with a reserved holdout were stalling because the discriminator door counted holdout. Public selection_allowed still had snapshot fallbacks, and health only proved the image SHA. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-26 19:36:04 +08:00
Jesse_ChenandCursor	a0ce55f066	fix(web): drive rectification from candidate contrast and allow range close ... Showing a choice card is no longer treated as completion. Distinguish probes require real candidate groups, holdout stays out of scoring, and ordinary sessions can finish with a credible range instead of an exact-minute gate. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-26 17:19:26 +08:00
Jesse_ChenandCursor	f5e73ef326	fix(web): rank remaining-minute probes by split and match choice kind ... Choice cards used a hardcoded domain menu and always asked existence. Rank scoring layers by remaining-minute entropy, keep finance and health volunteer-only, and ask D9/D10 style or exam quality so taps match outcomes. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-25 20:44:55 +08:00
Jesse_ChenandCursor	3659519bd0	fix(web): apply rectification choice cards without invoking the agent ... Clicking A/B/C/D or stop must persist the answer, close the probe, and update posteriors in one idempotent transaction instead of sending the option text as a chat message. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-24 18:38:05 +08:00