Commit Graph
6 Commits
Author SHA1 Message Date
jesse-ux 16f9f86843 fix(consult): date the full-data cache and slim the model card
The cache key now includes the request date, and files older than two days are removed. The model card keeps values only. Parashari aspects are copied from the engine. Saving a chart warms the packet without blocking the response.

Biography severe conflicts rose from 1 to 3, so this is not accepted for merge. Not pushed.
2026-10-09 10:00:45 +08:00
Jesse_ChenandClaude Opus 5.5 7806c72f2c feat(consult): cards carry functional profile v2; close round-4 backtest residue (BUG-1158, BUG-1176, BUG-1182)
- Evidence-card and biography-backtest goldens regenerated with the capture
  scripts (PYTHONHASHSEED=0, cache TTL 0; byte-identical twice); only the
  functional-role fields change.
- CAREER_FIELD_ASK_RULE: A10 / AL / Sun / 10th lord in 4/6/8/12 say
  resistance or cost only, never "not on stage / go deep", and houses are not
  translated into fields.
- AFFLICTION_RANGE_RULE: no portrait of an afflicted person from the lord's
  house or a benefic occupant ("managing / arranging / cares about your
  future"), actions do not presuppose reaching them, one ask per answer.
- Examples that paired "4th lord in 10th" with "her attention is on your
  future / close" now state the line is unafflicted (Monroe's chart had that
  exact placement and copied it). Retrograde line also bans "drags on".
- Backtest script: several follow-up domains in one run.
Changed assertions carry 原值 / 新值 / 原因 in the test comments.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
2026-10-02 12:32:02 +08:00
Jesse_ChenandClaude Opus 5.5 6a02e5e91e feat(consult): career answers don't guess the field — strength/resistance/timing + one ask; follow-up reads a stated job (BUG-1176 decision); goldens regenerated; rubric round-4 pass lines; backtest script career follow-up
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
2026-10-02 09:12:06 +08:00
Jesse_ChenandClaude Opus 5.5 071a196d11 fix(research): backtest correction turn passes typed history messages
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
2026-10-02 00:46:48 +08:00
Jesse_ChenandClaude Opus 5.5 955bab691a feat(consult): sections presuppose nothing, examples carry no reading rule or job shape, corrections are acknowledged
- natalAnswerShapeBody: NATAL_SECTION_RULE replaces 「这个人是什么样、你们怎么相处、
  事情会怎么走」; the shared voice quotes the same constant (BUG-1164)
- product-voice / VOICE.md: no 逆行 in examples, parents example leads with the
  affliction and asks to confirm, married-presupposing Good example removed (BUG-1165)
- follow-up shape: a user correction is acknowledged, never defended (BUG-1166)
- career examples carry no job shape (升职 / 专业能力 / 做深现有工作) (BUG-1168)
- biography backtest golden regenerated with the real engine so the card carries
  brief 1's aspects, combustion, yoga domains and saturn_from_moon_house;
  backtest script gains --correction follow-up turns

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
2026-10-02 00:38:01 +08:00
Jesse_ChenandClaude Opus 5.5 691ee440e3 feat(research): consult biography backtest harness and pre-change baseline
Independent Staging Quality Gate / validate (push) Successful in 16m20s
Independent Staging Quality Gate / publish (push) Successful in 3m54s
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