TASK-rectification-in-chat-step1-20261006, direct execution.
- The homepage 生时校正 pill and the text trigger (isRectificationHandoffQuestion)
are gone. The consult agent decides (RECTIFICATION_OFFER_RULE, one
definition) and calls offer-birth-time-rectification; the server decides
whether a card may show (self, product on, no case in progress,
feature_pricing price). The offer is stored with the answer and travels on
run.completed; the card hangs under that answer.
- Opening from the card binds the offer to the case in the consultation's own
messages (no table change); GET/POST /api/rectification/cases/[caseId]/source
find the source and go back: one divider (time changed or not), earlier
answers captioned 按校正前的时间, and a 按新时间重新看 button that sends only
when clicked. Auto-return after the post-adopt check or a terminal case, only
for work done in this view.
- Model history skips the divider and notes answers written with the old time.
Full suite 4987 / fail 24, identical to 6ec8efd5 (4973 / 24), no test name
lost; tsc 0; lint 0 errors; build keeps / Static, first-load gzip +0.20%.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Once the discriminator training gate is open, only choice cards are asked
and the range card goes out when they are exhausted; targeted lines, their
re-ask and guided windows no longer hold the card or invite more events.
Delivery body says how many choice questions were used instead of the event
fit percent; narration names an excluded cluster instead of "range
unchanged"; a delivered turn no longer carries a collect question.
Offline replay (v4, 3 radii x 2 directions): truth in range 20/20 in every
cell; guided-window injections give the same width in truth and opposite
directions, so red line 1 was revised by product to truth-in-range only.
Skill 10.0.31 -> 10.0.32 (10.0.31 kept as deprecated for pinned cases).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
T2 of TASK-rectification-grounding-20260927 (product decision P1).
The rectification 「重试（重新生成）」 was a blind agent.generate rewrite that
persisted unchecked text (invented range / fit rate reproduced). Removed:
the regenerate route, regenerate-turn.ts, the regeneration agent and its
read-only tool set, the client regenerate action/state and the
regenerating/canRegenerate props. ChatMessageActions renders the regenerate
button only when onRegenerate is passed; ordinary consultation is unchanged.
The DB function regenerate_agentic_rectification_turn is kept (AGENTS §7.6,
retire in a later round). DESIGN.md / VOICE.md updated; source-contract
tests follow with 原值/新值/原因 notes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
- D2: each intent-classifier attempt is capped at 10 s (same session model,
thinking untouched); a hang takes the existing retry -> classifier_unavailable
path. Success is timed too (RectificationClassifierDiagnostic).
- D3: a typed message builds the NDJSON stream first; the first line is
turn.progress "received", then the classifier and deterministic replies run
inside the stream. Preflight rejections become turn.rejected (old status,
code, message) and the client handles them like the old HTTP rejection.
Stage lines 收到，正在对照你的档案… / 正在记下这件事… / 正在重新对照盘面… /
正在准备下一个问题… are driven by existing tool events and engine calls, are
transient (live row only) and never persisted. VOICE / DESIGN updated.
- D4: RectificationRunDiagnostic records per-step start/end, provider token
usage incl. reasoning tokens, classifier timing and per-engine-call
durations (AsyncLocalStorage scope per turn); RectificationTurnDiagnostic
for deterministic turns. No user text, birth data or model text.
- D5: /v5/versions memo (30 s, complete identities only, per transport); the
exit gate skips its second persistNextInterviewIfIdle when the run's own
call found the next focus already active (provably identical).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
BUG-1045 (recurrence of BUG-585 via BUG-969): the snapshot merge now drops
the attached stem from the streamed "ack + stem" text with the same
stripQuestionSentences the GET route uses; server text unchanged.
BUG-1046: a failed choice submit (409 / network) or typed send withdraws
the local answered mark, remounts the card, re-reads the Case and shows
"这次没提交上，请再点一次。"; the persisted question hangs on the latest
settled assistant message with other copies of the same focus removed
(standalone block only when nothing can carry it); willContinue and the
send() settle merge unseen assistant turns (same gap as BUG-685).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Unify minute and block cache identity, keep unverifiable historical results read-only across server tools and write entrypoints, and aggregate completed receipt sources chronologically through a compatible function migration.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Rectification answers now advance chat_sessions.updated_at (BUG-704).
A ?c= id missing from the loaded page is fetched before anyone may call
it deleted (BUG-705). The range card no longer has a post-card tie-break
button; live questions leave the card visible with adopt locked
(BUG-706/708). Spoken copy bans 相对支持度 (BUG-709).
Task docs assigned 700-704; qizheng already took 700-703.
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.
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.
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.
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>
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>
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>
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>
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>
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
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>
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>
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 chat used to show "当前没有可回答的问题，正在等待服务端更新" / "当前问题暂时无法显示"
/ "题目加载失败，请刷新" as bare copy above the composer. The gap between a
settled turn and its next question is now a state: `preparing` renders the
same timeline live row the reply uses ("正在准备下一个问题…") and refetches the
Case on a 2s timer up to two retries; `unavailable` renders one line and a
44px reload button. A snapshot that never arrived at hydration is the same
gap. A resumed Case with no turns and no server-started opening shows
"这段校正还没有开始。" with one 开始提问 action. Stopping a run keeps what
streamed and says so instead of "暂时不可用"; the opening turn's live row
names what is happening; a 402 explains itself for 600ms before leaving.
BUG-505, BUG-507
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JUei7K13cYxLHE3Axe4A45
Opening a rectification Case used to switch sessions first and read the
turns afterwards, so the reader saw a plain transcript, then an empty
panel, then a remount when the turns arrived (and again after the first
turn settled, because the panel key carried a ready/loading suffix).
The surface hook now reads turns and snapshot in one Case request under
the home reveal budget and only then makes the session active; the
sidebar defers the switch the same way; a session selected at bootstrap
(deep link, refresh) is hydrated during the prepare phase so the reveal
shows the surface itself; the panel key is the session/Case binding only,
later turns fill an empty transcript as a prop update, and unmounting
aborts any stream or snapshot read. The homepage card and the sidebar row
say 正在打开 statically while the Case opens — no spinner after the reveal.
BUG-505
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JUei7K13cYxLHE3Axe4A45
