Full TAP failed because invite_more is not a target_kind enum value, and
exhaustion re-decide after skipped targeted persist must reuse decideAfterInferenceChange.
Co-authored-by: Cursor <cursoragent@cursor.com>
Empty engine refresh now records an already_answered attempt so GET can leave wait-to-narrow; collect kinds map onto the table CHECK; remaining candidates drive probe refresh.
Co-authored-by: Cursor <cursoragent@cursor.com>
Empty refreshes were writing inference rows, and GET-selected probe keys could miss inference_state, so persist rejected the next card.
Co-authored-by: Cursor <cursoragent@cursor.com>
Dated-choice exhaustion is not convergence. Refresh probes from remaining
active candidates, then ask a targeted collect, then deliver. Skill 10.0.24.
Co-authored-by: Cursor <cursoragent@cursor.com>
Staging gate 2558 failed because leftover tests still expected D9/D10 or leftover collect after the pool emptied. Discriminate sessions still deliver; dated precision cards still ask.
Co-authored-by: Cursor <cursoragent@cursor.com>
When dated choice probes are exhausted after the training gate, stop treating yearless D9/D10 cards as the next discriminator and persist a range carrier in the same answer transaction.
Co-authored-by: Cursor <cursoragent@cursor.com>
Occupation collect was wiping year-month into an unscored note, and idle gap copy never joined the evidence turn.
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>
A superseded collect row still occupied the unique question id, so the last
"没有" skipped the unasked domain and spoke delivery copy while can_adopt stayed false.
Co-authored-by: Cursor <cursoragent@cursor.com>
The staging gate failed because that case claimed 记下了 without a write tool, which the unwritten-evidence guard now rejects.
Co-authored-by: Cursor <cursoragent@cursor.com>
Representative minutes still undercounted width on dossier refresh and parsed snapshots even after the engine used cluster coverage.
Co-authored-by: Cursor <cursoragent@cursor.com>
Host only says 记下了 after a real write; Mastra schema rejections fail closed. Ledger year keys no longer drop quality probes, dual-dasha agreement is per cluster, width uses cluster span, and public house tables follow the inference minute.
Co-authored-by: Cursor <cursoragent@cursor.com>
Evidence turns that already recorded a batch no longer fail the whole run when the model emits no text; unchanged ranges now name which clock spans lead or lag, and the timeline no longer says 收窄.
Co-authored-by: Cursor <cursoragent@cursor.com>
Dated life events with clock times were swallowed as birth-window replies, and compare columns still stopped at the first nine candidates after the hour-window cap.
Co-authored-by: Cursor <cursoragent@cursor.com>
Ask dated dasha probes first; D9/D10 and nakshatra wait until that pool is empty, score at half weight, and never eliminate. Skill 10.0.21.
Co-authored-by: Cursor <cursoragent@cursor.com>
Thinking models were spending the first natal step on skill_read or a Level 2 draft, so home chips such as 家庭 never satisfied the calculation contract.
Co-authored-by: Cursor <cursoragent@cursor.com>
Users consistently rejected skip chips on spoken collect. Typing those phrases still declines or skips the domain.
Co-authored-by: Cursor <cursoragent@cursor.com>
Hour windows no longer drop later signature clusters. Credible range uses cluster coverage, and a mid-session spoken birth window gets a fixed reply without calling the model.
Co-authored-by: Cursor <cursoragent@cursor.com>
Session open was sending the live registry version into v2, so every Skill
bump rejected older cases with an unmapped 500 and no error on the clicked row.
Co-authored-by: Cursor <cursoragent@cursor.com>
Writing selectionOfferLockRef during render tripped react-hooks/refs after the two contract tests went green. The lock now updates like seededTurns, and nextSelectionCardLock reuses the same object when the key is unchanged.
Co-authored-by: Cursor <cursoragent@cursor.com>
