20 public AA cases, raman/mean. Lowering MIN_BOUNDARY_DAYS narrows ±10 from
15 to 11 minutes but drops top-1 0.80→0.75; wider radii get wider ranges.
Varga sensitivity weights (V1/V2) match production; D60 (V3) hurts ±10.
Day-precision events offset ±7 never squeeze the true minute out. Production
45/30 gate and equal varga weights stay unchanged.
Hospital records, family estimates and period-only windows now keep distinct copy on the board and range card. Scoring still uses the reported clock as the search-window centre. Hospital minutes outside the current range are stated with the offset and no preference.
When the seven collect lines are closed, the range card still appears, but the copy asks for one more exact-day event of any kind instead of saying the questions are finished. A new dated event after delivery stales the snapshot so the session does not stay delivered.
Offline v4 holdout probe. Last round's width=window result was the
no-elimination metric; production still-valid ranges after six answers
are 15/33/56 minutes. Adjacent merge never fires under step-2 radii.
W1/W2 match baseline; W3 is uncertain after one coverage squeeze.
No production clustering or scoring defaults changed.
Style questions still precede a converging range card when a renderable
followup exists. Exhausted, closed-ceiling, and holdout-unavailable exits
deliver immediately. Hold at most once per Case. Restore the single-gate
exit assertion and stop treating the tie-break ack as an exit carrier.
Build holdout v4 from the public AA set, correct the two v3 dates, and sweep
R1–R5 plus pairs offline. No production scoring defaults change. No
implementation brief: delivered width stays the full window on every radius.
Close leads hold delivery until unused D9/D10 style questions are asked. Tie-break POST merges the new turn into the transcript. Range copy no longer lists declined lines.
tied_first is only terminal when there is no dated probe and targeted collect is exhausted. An unnarrowed opening window cannot announce adopt. Delivered dead choice cards take the delivered gap instead of the repair copy.
Refresh persist failures no longer count as attempts. tied_first completes with a range before stillNeedNarrowing. Delivery narration and cards share DELIVERY_OUTCOMES. The question gap gets a delivered terminal so the unavailable copy does not appear after a range is given.
Spoken collect without askedTurnId now hangs on the last assistant message, remaining-candidate copy uses credible_range, and engine representativeTime no longer keeps eliminated minutes in model house tables.
Distinguish followups that cannot stamp a probe now go to persistExhaustionCollect instead of repeating the card stem in the assistant body. Choice focuses without asked_turn_id hang on the last assistant turn, and persisted_question with a live choice_card renders the existing card. Representative-time inconsistency is warn-only (BUG-676 investigating).
Keep targeted existence questions as A-D cards. Recover collect-schema
stock by question-id prefix, surface the stem when persist fails, and
send spoken targeted existence to the repair exit instead of a naked prompt.
Offline H1-H4 measurement on 20 public AA holdout cases.
Block unique top-1 did not rise; H4 made it worse; minute layer unchanged.
Leave production scoring untouched. Transits must not drive minute conclusions.
Measure four relaxations offline on 20 public AA cases: transit aspects to natal
house lords, tight node conjunctions, year-precision transits, and house-lord
scoring for the block stage. No production change.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0193vBv6w5MV2cifdTUu9H5P
Skipped or already-reported health must not be asked again as health_pressure, and occupation declined as other must still close the occupation line.
Co-authored-by: Cursor <cursoragent@cursor.com>
Hide the button once both personality cards are answered, persist the second card in the same opt-in round, and freeze Skill 10.0.26.
Co-authored-by: Cursor <cursoragent@cursor.com>
GET dropped the A–D card when the recast had no choice_frame, so a refresh left a disabled card and a collect-wait. Project from the persisted copy, rebuild the keep frame, and send a dead choice to repair-exit.
Co-authored-by: Cursor <cursoragent@cursor.com>
Reproduced: with a collect_method_evidence focus open, the plan rebuilds an
active_focus followup without a choice_frame, so GET projects no choice_card and
the card renders disabled while the page waits for a dated event.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0193vBv6w5MV2cifdTUu9H5P
Accepted the targeted-collect cards round and the refresh R3/R4 round; the
range-card tie-break entry keeps showing after D9/D10 are answered and errors
on click. Product decision: one click asks both cards, then the entry goes away.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0193vBv6w5MV2cifdTUu9H5P
After six dated answers, refresh can use 30-day same-year windows plus pratyantar and D9/D10 Narayana. First-round probe rules stay at 45 days.
Co-authored-by: Cursor <cursoragent@cursor.com>
Dated-pool empty now yields existence cards per remaining layer, leftover-candidate copy, and an optional D9/D10 tie-break on the range card. Skill 10.0.25.
Co-authored-by: Cursor <cursoragent@cursor.com>
Same-id focus returns instead of making the model retry; kind_hint targetKind is ignored. Failed receipts keep a redacted original error and known codes. Host fallback recap no longer duplicates dates.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop domain-wheel collecting and age-band years in prompts. Ask until the training gate, then discriminate until convergence, then deliver a range plus a concrete follow-up. Reserve holdout only with four dated events.
Co-authored-by: Cursor <cursoragent@cursor.com>
Ask finance and health like other domains, put year-cued collect questions first, and let the classifier distinguish decline vs skip. Skill 10.0.22.
Co-authored-by: Cursor <cursoragent@cursor.com>
