The range is the only quantity that expresses convergence, and it existed
only as a sentence in the transcript. The bar makes it permanent.
It is the chat grid's first row, outside the scroll container, so
scrollHeight is untouched and use-conversation-scroll-anchor needs no
change. Its height is fixed because nothing observes it: a growing bar
would alter clientHeight and let an anchored reader lose the tail.
The axis is the current search window, not the opening one, since
widening overruns the opening window. Marks are binary — in range or
excluded — because relative support between candidate minutes carries no
demonstrated minute-level discrimination (BUG-560, blocked).
Band and marks move by transform alone; globals.css bans width
transitions, and transform keeps the motion off the layout path.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016P5RoqzmUQEbeC2qjAkeGr
The worker already persists a phase ladder and durable per-section rows;
the waiting screen parsed the progress fields and rendered none of them.
Chapter progress now drives the screen: one cell per chapter rather than
a percentage bar, since the job percent jumps 0->30 and 90->100.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016P5RoqzmUQEbeC2qjAkeGr
Bare `/` was treating the latest history session as active, so a returning account could auto-open a failed rectification Case and left-align the starter home.
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>
Engine calls already returned markdown; the worker failed because local postgres upsert required onConflict and the appendix write omitted it.
Co-authored-by: Cursor <cursoragent@cursor.com>
Hovering A/B/C/D rewrote a leading/lagging time line and made the card flicker; the step-state sentence above the composer was instructional filler, not something the user needed to answer.
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>
Staging PostgREST rejects the executiveSummary JSON-path alias, so GET /api/reports 500s. Persist a plain card_summary column from the Markdown excerpt instead.
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>
Pass asked probe keys into the engine without changing result fingerprints, block nearby years already asked, and require a dated same-domain ledger event before rendering varga_style cards.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop falling through to "say another event" after dated and occupation collect are done. Deliver an adopt path or a gate sentence, and add a spoken-collect stop control.
Co-authored-by: Cursor <cursoragent@cursor.com>
New reports skip the writer, persist pl9 Markdown as the body, and settle zero-token usage on the catalog model. Planned longform sections now emit blocked rows instead of vanishing.
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>
Deploy-window connection errors were translated into "服务尚未配置".
Only real configuration errors keep that copy; other 503s use service_unavailable.
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>
The staging quality gate failed because database-local-business still listed the old pg_tables set after 20260905010000.
Co-authored-by: Cursor <cursoragent@cursor.com>
Web export now calls the same full pack as the long skill report and caches an owner-only Markdown download. Appendix failure stays unavailable and does not change the main report status.
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>
BUG-430 loaded Inter via next/font/google, which failed Gitea publish
run 2408 when the Docker build could not reach fonts.googleapis.com.
Co-authored-by: Cursor <cursoragent@cursor.com>
Five-theme assemble cleared the chart and actionNotes caps, then failed
three anonymous guards. Log field path plus kind only, and strip
deterministic phrases from sections the producer already marked blocked.
Co-authored-by: Cursor <cursoragent@cursor.com>
Five-theme personal_full still failed final parse after the charts cap
fix because writer output exceeded actionNotes.max(24). Truncate at
assemble; do not raise the schema cap.
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>
Five-theme personal_full assembled nine charts after health vargas landed, but the document schema still capped at six. Bind the count to the enum, align JSON/Python contracts, and log final-parse paths without values.
Co-authored-by: Cursor <cursoragent@cursor.com>
Heartbeat and GET were parsing progress_phase with a pattern that rejects the colon prefix the writer already persists, which aborted generation after the first chapter.
Co-authored-by: Cursor <cursoragent@cursor.com>
set-focus only attaches the question stem. Retracting live Chinese before
it wiped the opening hello with an empty replace. Other public tools still
retract planning prose.
BUG-533.
Co-authored-by: Cursor <cursoragent@cursor.com>
Accepted profiles were selecting a revoked rectification table and failing the report before the engine ran. Degrade to a null window when that optional read fails.
Co-authored-by: Cursor <cursoragent@cursor.com>
