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>
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>
Engine by_time ledgers now include the full candidate set so posterior columns can look up fit and windows. Delivery turns keep up to three sentences after idle persist; the card subtracts repeated traits and folds the board chart.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move 没有/记不清 under the spoken question, inset the timeline to the assistant column, and keep the three-column card after 更像这个 with the closing line under it (BUG-618–620).
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Consultation was passing the birth mahadasha into event-class splits, so marriage hits stayed empty and timing still said 缔结. Read live MD/AD from dasha_sub_periods, derive activation copy from the split, and isolate fence failures so one bad varga cannot 500 the whole report.
Co-authored-by: Cursor <cursoragent@cursor.com>
Venus/Jupiter/Moon periods no longer collapse into one marriage-opportunity line. Full reading reports the ten BPHS conditional dasha families; Skill 6.9.16.
Co-authored-by: Cursor <cursoragent@cursor.com>
Longform report pages kept the D1/D9/Moon and varga headings but skipHtml
stripped the engine's inline SVG. Emit a jyotish-chart JSON fence beside
each SVG and render a diamond chart on the reader without relaxing HTML
sanitization. BUG-607.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep both changelog entries, BUG_HISTORY 602–606, and both task-board rows at 待验收. Auto-merged chat.tsx retains inferenceMarks and collect-reply buttons.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace the minute-row delivery card with up to three compare columns so users can pick the time that fits, and apply the adult-year floor on inspect fallbacks.
Co-authored-by: Cursor <cursoragent@cursor.com>
Make the range card row-select, drop the composer 先这样 control and adopt status bar, keep delivery copy to three sentences with a folded verification report, and skip a second no-message agent run after a terminal delivery turn.
Co-authored-by: Cursor <cursoragent@cursor.com>
Rescored candidate sets were widening because new minutes stayed
neutral. Derive support/conflict from varga signs and dasha segments,
and announce range changes from facts rather than tool names.
Co-authored-by: Cursor <cursoragent@cursor.com>
Point-choice used one compare packet, so a May existence card and the same-domain year card both stayed eligible. Hard-exclude same domain+year; keep adjacent years downranked.
Co-authored-by: Cursor <cursoragent@cursor.com>
The verification template was still quoting the engine's pre-inference span and eliminated dasha tops, and D9/D10 signs were left for the model to guess from transition clocks.
Co-authored-by: Cursor <cursoragent@cursor.com>
Yearless-to-collect now skips domains already confirmed, declined, or asked; adopt-exhausted turns skip leftover collect persist. Collect focus collisions only retry with :next when collect_retry is set.
Co-authored-by: Cursor <cursoragent@cursor.com>
Carry answered probe defs into the new candidate set, replay them by minute, and announce range changes on evidence turns.
Co-authored-by: Cursor <cursoragent@cursor.com>
Set-focus must not append a second narration, and a server-owned stem must not also appear as a question in the assistant body.
Co-authored-by: Cursor <cursoragent@cursor.com>
After the dated domains are asked or declined, keep the occupation question or the range card instead of hanging on a leftover other-collect prompt.
Co-authored-by: Cursor <cursoragent@cursor.com>
Null-check the candidate result before reading resultId so next build can ship. Adopt reconnects prospective windows on the first verify turn, and dismissing the range card now shows the collect hint.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop/idle reuse the scored evidence path so existing answers stay on the range. Delivery uses one range card (Skill 10.0.15) instead of four minute cards.
Co-authored-by: Cursor <cursoragent@cursor.com>
Engine asked_probe_keys no longer include varga split hashes that 400 the scorer, failed compares become visible and retry, user stop can still deliver a range on a stale snapshot, and holdout no longer reasks domains already in the ledger.
Co-authored-by: Cursor <cursoragent@cursor.com>
Intake stores how sure the user is; rectification now searches that range, offers a one-click widen when event fit is low at the edge, and trisects windows longer than two hours before the minute grid.
Co-authored-by: Cursor <cursoragent@cursor.com>
Choice copy was comparing the search window, so every answer said the range had not changed. Block-scan summed raw scores, so longer afternoon windows won before any evidence difference.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep askable cards after exhaustion, explain each probe, read the adopted credible range in reports and chat, and compare declared periods before the minute grid when the clock is unknown.
Co-authored-by: Cursor <cursoragent@cursor.com>
Implement offset and softmax relative-support scales and a public holdout calibration script, but leave the default proportional because no scheme passed the coverage-and-width gate.
Co-authored-by: Cursor <cursoragent@cursor.com>
The first-round title guard compared the pre-RPC snapshot, so append_consultation_question had already rewritten the title and the model name never landed.
Co-authored-by: Cursor <cursoragent@cursor.com>
The four account panes now share a fixed frame, chart profiles open as list then detail, and membership lives in the homepage dialog instead of a separate page.
Co-authored-by: Cursor <cursoragent@cursor.com>
Session history was silently clipped to the first 4000 characters of the last 12 messages, so follow-ups could not see timing or audit tables. Keep an append-only tail plus a checkpoint summary, retry overflow in the same request, and expose cache hit rate in admin usage.
Co-authored-by: Cursor <cursoragent@cursor.com>
Enter now queues one follow-up instead of dropping it, and a rectification stop leaves the streamed reply with a grey notice instead of an error alert.
Co-authored-by: Cursor <cursoragent@cursor.com>
Separated candidates were treated as adoptable while finance, relocation, health, or occupation collect was still pending, so clickable cards and a verification report appeared before those questions were asked.
Co-authored-by: Cursor <cursoragent@cursor.com>
A choice-card yes/weak_yes already told us the domain happened, so skip the same-domain "which year" collect without writing the ledger.
Co-authored-by: Cursor <cursoragent@cursor.com>
Family coverage still continues dated collection when nothing can split leftover minutes, but an already-built choice card must not be displaced by spoken finance collect.
Co-authored-by: Cursor <cursoragent@cursor.com>
Family "没有" was treated as adopt-ready once the training gate was open. Remaining dated domains still distinguish leftover minutes, so persist those questions instead of writing the adopt narration.
Co-authored-by: Cursor <cursoragent@cursor.com>
The time card stayed under an earlier collect question, and the close said to just use a time for now. Keep the card on the delivery turn and present the analysis as this round's result.
Co-authored-by: Cursor <cursoragent@cursor.com>
Adopted reverse-verify repeated already-asked collect stems, treated 「这题跳过」 as stopping the case, and promised holdout/OOS checks that never ran. Collect spoken stems no longer prefix a year.
Co-authored-by: Cursor <cursoragent@cursor.com>
The early-exit reused the pre-click dossier, so the agent never ran on the common path. Use this-turn decision, log agent vs template outcome, and time out after 8s.
Co-authored-by: Cursor <cursoragent@cursor.com>
When leftover probes cannot split adjacent minutes, skip frameless follow-ups and let a no-tool agent explain the stop. Distinguish-card "no" no longer closes a whole evidence domain.
Co-authored-by: Cursor <cursoragent@cursor.com>
