Product decision 2026-10-02 (TASK-upstream-sync5 R1): a time range is offered
only with at least 4 dated, primary-scoreable events covering 3 domains,
counted on all of them (training + reserved holdout). Was 3 training events /
2 domains in three TS copies and the Python acceptance gate while the policy
file already said 4/3.
- One definition: references/rectification_policy.v1.json
(minConfirmationEvents / minConfirmationDomains). TS core/types MIN_DATED_*,
rectification-decision MIN_STANDALONE_*, evidence-model MIN_ACCEPTANCE_*,
the convergence evaluator and the post-inference trainingGateOpen all read
it; Python decision_policy MIN_ACCEPTANCE_* alias MIN_CONFIRMATION_*.
- Python receipt counts all scoreable events / domains for event_quality and
domain_diversity; decision policy identity v3 -> v4 (candidate UUIDs carry
it). Candidate scores unchanged (77 v5 cases A/B identical), so the
algorithm stays rectification-v5-matrix-scoring-10.
- Memoization golden v3 written by write_golden; v2 frozen by sha256 with a
test that its scores equal v3 and only the receipt policy moved.
- Collect gap copy names the exact gap ("再来两件……其中至少一件不是……")
instead of always "再来一件"; VOICE.md updated. Legacy life-events form copy
4/3 as well.
- 30 frontend test files, 4 Python tests: fixtures extended to the same
scenario at 4/3, or assertions changed with 原值/新值/原因 notes.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
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
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.
Gate npm test failed 6 assertions that still looked for 目前范围 in host
narration, or expected a range card before unused style probes. Keep the
card title; allow the closed-pool copy and heldForTieBreak path.
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.
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>
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>
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>
