Jesse_ChenandClaude Opus 5.5 691ee440e3 feat(research): consult biography backtest harness and pre-change baseline ...

TASK-consult-no-presupposition-and-backtest-20261001 T4 infrastructure only
(T1-T3 untouched). New files only, so it merges cleanly with the parallel
evidence-card brief.

- capture_consult_biography_backtest_golden.py: same handler/body/trim as the
  evidence-card golden; nine public AA charts x parents/marriage/health/career.
- consult-biography-backtest-golden.json: real engine output, byte-reproducible.
- consult_biography_backtest_rubric.json: facts with sources, must_not,
  expected_signals per figure x domain.
- consult-biography-backtest.mts: runs the product's real agent, tools, card,
  methodology, user-turn shape and streamAgentResponse; deterministic checks only.
- Baseline on 9b937c4a: 39/72 severe biography conflicts; all five audit cases
  reproduce in both runs.

BUG-1170 is registered when brief 3 lands.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE

2026-10-02 00:10:06 +08:00

..

jev_intent_samples

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

angle_timing_lib.py

research(rectification): angle-timing A1 — real vs shuffled and age-preserving jittered dates, 0/9 tests significant (BUG-1141)

2026-10-01 10:55:46 +08:00

angle_timing_positive_control.py

research(rectification): positive control for the angle-timing pipeline; Claude acceptance (BUG-1141)

2026-10-01 10:55:47 +08:00

angle_timing_research.py

research(rectification): angle-timing A1 — real vs shuffled and age-preserving jittered dates, 0/9 tests significant (BUG-1141)

2026-10-01 10:55:46 +08:00

answer_flip_tolerance.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

capture_consult_biography_backtest_golden.py

feat(research): consult biography backtest harness and pre-change baseline

2026-10-02 00:10:06 +08:00

capture_consult_evidence_card_golden.py

fix(engine): D9 double-transit targets check the D9 signs they name (BUG-1060)

2026-09-27 17:30:05 +08:00

cluster_width_lib.py

docs(research): measure why delivered range width equals the search window

2026-09-14 22:11:47 +08:00

cluster_width_probe.py

docs(research): measure why delivered range width equals the search window

2026-09-14 22:11:47 +08:00

consult_evidence_card_lib.py

research: consultation evidence-card inventory and draft

2026-09-27 01:27:57 +08:00

consult_evidence_card_run.py

feat(engine): expose native technique layers in the consultation output

2026-09-27 16:27:24 +08:00

consult_evidence_card_time.py

research: consultation evidence-card inventory and draft

2026-09-27 01:27:57 +08:00

dasha_shift_per_minute.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

fewer_probes_card_replay.py

feat(rectification): 少问几道就出卡，交付卡以范围为主（D1–D4）

2026-09-26 14:27:12 +08:00

futile_collect_stop_replay.py

fix(rectification): stop spoken collect once the training gate opens (BUG-1084..1087)

2026-09-29 10:06:57 +08:00

generate_varga_api_golden.py

feat(rectification): submit varga-resolution implementation for review

2026-10-01 08:04:04 +08:00

generate_varga_segment_goldens.py

feat(rectification): submit varga-resolution implementation for review

2026-10-01 08:04:04 +08:00

guided_collect_holdout_replay.py

fix(rectification): 有题就接着问，题问完才出卡；引导窗口不再硬贴领域

2026-09-16 12:16:55 +00:00

holdout_v4_build.py

docs(research): measure minute-resolution scoring; no variant clears all radii

2026-09-14 20:43:27 +08:00

holdout_v5_baseline.py

research(rectification): baseline runner never rewrites the published 09-14 report

2026-09-29 19:52:43 +08:00

holdout_v5_build.py

research(rectification): holdout v5 — drop current-year events (harness cutoff 2026-09-14), index pages

2026-09-29 19:52:43 +08:00

house_lord_gochara_supply.py

docs(research): measure house-lord gochara rules with no benefit

2026-09-14 01:07:11 +08:00

jev_intent_corpus_build.py

research(jev-intent): 修复轮重造语料并全量对照

2026-09-19 11:30:31 +08:00

jev_intent_current.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_probe_v2.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_probe.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_questions.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_source_b_v2.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

measure_consult_evidence_card.ts

feat(consult): evidence card v2 per the astrologer's review

2026-09-27 16:44:19 +08:00

midnight_date_anchor_regression.py

fix(rectification): anchor candidate windows to civil dates across midnight

2026-09-21 02:55:00 +08:00

minute_resolution_lib.py

docs(research): measure minute-resolution scoring; no variant clears all radii

2026-09-14 20:43:27 +08:00

minute_resolution_sweep.py

docs(research): measure minute-resolution scoring; no variant clears all radii

2026-09-14 20:43:27 +08:00

offline_research_20260926_lib.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

precision_gate_lib.py

docs(research): measure precision-adaptive probe gates; no variant clears the bar

2026-09-15 09:04:03 +08:00

precision_gate_sweep.py

docs(research): measure precision-adaptive probe gates; no variant clears the bar

2026-09-15 09:04:03 +08:00

probe_supply_after_six.py

docs(research): measure dated probe supply after six answers

2026-09-13 12:59:46 +08:00

project_consult_model_context.ts

research: consultation evidence-card inventory and draft

2026-09-27 01:27:57 +08:00

quality_wording_ab.py

fix(rectification): name education quality events by kind, no month for year precision (BUG-1088)

2026-09-29 10:06:13 +08:00

reported_offset_sweep.py

fix(rectification): name education quality events by kind, no month for year precision (BUG-1088)

2026-09-29 10:06:13 +08:00

representative_pairs_probe.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

scoring_research_lib.py

research(rectification): scoring-method scaffold — LR weights, absence, precision follow-up pipelines on v4, verdicts pending v5 (BUG-1091)

2026-09-29 19:06:45 +08:00

scoring_research.py

research(rectification): v5 verdict for scoring-method research — LR weights, absence and precision follow-up all fail hard line 1 (BUG-1091 closed_by_design)

2026-09-30 00:30:34 +08:00

sealed_holdout_rerun.py

fix(rectification): name education quality events by kind, no month for year precision (BUG-1088)

2026-09-29 10:06:13 +08:00

typed_event_as_probe.py

research(rectification): typed events scored as answered probes — no benefit (BUG-1089)

2026-09-29 10:06:13 +08:00

varga_resolution_lib.py

research(rectification): varga-resolution M0 — per-minute ascendant segments and six-probe interval chart types on v5 (BUG-1105)

2026-09-30 09:34:08 +08:00

varga_resolution_method_replay.py

feat(rectification): submit varga-resolution implementation for review

2026-10-01 08:04:04 +08:00

varga_resolution_persisted_replay.py

fix(build): move the persisted-replay research harness out of frontend/scripts; guard runtime sources against tests/ imports (BUG-1140)

2026-10-01 09:37:00 +08:00

varga_resolution_probe.py

feat(rectification): submit varga-resolution implementation for review

2026-10-01 08:04:04 +08:00

varga_resolution_production_bridge.py

feat(rectification): submit varga-resolution implementation for review

2026-10-01 08:04:04 +08:00

varga_sensitivity_rerun.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00