Move-only (TASK-rectification-code-split-20260926 T3/T4). No behavior,
receipt, billing, Skill or scoring change.
- agent-run.ts: 1400 -> 135 lines; runV9AgentTurn 1046 -> 25 lines, no
nested functions. It keeps the public types, the budget constants and the
phase order: agent-run-prepare.ts (reliability, session, year re-ask, Skill
identity, delivered guard, reserve, turn row / replay),
agent-run-retry.ts (attempt loop), agent-run-attempt.ts (the old nested
streamAttempt), agent-run-finish.ts (billing settle, receipts, interview,
finalize), agent-run-support.ts (outcome types, retry classification, turn
receipt writers), agent-run-messages.ts (buildAgentMessages /
buildOpeningBrief, re-exported).
- One token changed with the move: the attempt passes its own
`previousErrorCode` argument to buildAgentMessages instead of reading the
enclosing `lastAttemptError`; the loop passes that same value (clears the
old unused-parameter warning).
- Tests: whole-source contracts read tests/rectification-agent-run-surface.ts;
behavioral runV9AgentTurn tests unchanged. agent-run growth caps added.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Move-only (TASK-rectification-code-split-20260926 T2/T4). No behavior, API,
copy, DB, Skill, billing or scoring change.
- route.ts: 1077 -> 152 lines; POST 927 -> 114. It builds the Supabase
clients (so the setup-failure mapping stays here) and assembles:
agent-route-request.ts (auth / product / schema / flag / Case-Session
binding), agent-route-typed-message.ts (declared-window reply, typed-answer
preflight, unfocused classification), agent-route-structured-choice.ts,
agent-route-agent-turn.ts (opening / read-only / typed agent stream and its
exit gate), agent-route-billing.ts, agent-route-support.ts (schema, one-shot
NDJSON reply, context types).
- The four mutable preflight lets (expectedWrite, collectIntent,
writeClassified, classifierDiagnostic) that crossed branches are one
turnState object; values and flow unchanged.
- Tests: whole-source contracts read tests/rectification-agent-route-surface.ts;
the typed fast-path slice is rebuilt from the new files; billing,
declared-window and structured-choice slices now call the handlers
(billing in a child process because feature-pricing imports server-only),
each with 原值/新值/原因. Route growth caps added.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
One row per rectification Case, written once when the range card is first
delivered (GET /api/rectification/cases/[caseId], fire-and-forget after the
response is built). Numbers and closed enums only: no user / case / session
id, birth data, names, text or timestamps finer than the ISO week. Dedupe via
a separate case_id ledger that cascades with the Case (and account deletion).
Migration 20260926010000 is additive: two RLS tables with no runtime table
grants, SECURITY DEFINER write (service_role), purge (service_role) and
aggregate-only summary (admin_runtime) functions; 180-day retention.
Admin: 「校正统计」 page + GET /api/admin/rectification-telemetry
(admin.customers.read), aggregates only, no per-row view or export.
TASK-rectification-telemetry-20260926. test:db not run locally (no Docker).
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
Carry explicit local date intervals instead of inferring the day from clock
order. Cluster width, delivery, adoption, and reports keep the actual civil
date; adopted date is stored separately from the reported birth_date.
Algorithm identity is scoring-9 / spec-v5. Scoring weights, confirmation
thresholds, and Skill version are unchanged. Isolated Linux final-3 gates
passed; four pre-existing Python failures remain. This is not a production
release.
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>
Add date-isolated caches and regression coverage, align scoring identity, and freeze full research reruns while preserving historical artifacts. Record unresolved cache/receipt identity and end-to-end acceptance gaps for branch review only.
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.
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.
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.
Hold delivery whenever tie-break questions remain, not only on a one-point lead. Drop the event-anchor discard for varga_style; keep the two-sign split gate.
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.
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>
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>
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>
