- 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
Before 57782aea `_has_malefic_aspect` skipped `pn == planet_sign` (planet
name vs sign name), so Mars / Saturn counted themselves as a malefic
conjunction and Ruchaka / Shasha were never valid. Fictional placements;
red on 57782aea^ (Ruchaka is_valid False), green now.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Functional roles feed the *_functional_*_auxiliary rules, so 57782aea changes
candidate scores for identical input (memoization fixture 12:00: 8.6274 ->
8.4977). Per the "scoring semantics change => bump ALGORITHM_VERSION"
precedent (scoring-7 -> 8 -> 9), the identity moves to scoring-10; policy v3,
input contract v5 and Skill versions are unchanged, history is not relabeled.
Five frontend sites and one SQL guard tested `=== "...scoring-9"` for the
dated candidate-window contract; they now use isDatedScoringAlgorithmVersion /
a generation regex (>= 9). Migration 20261002010000 only recreates
validate_dated_rectification_candidate (one-line guard change).
Memoization golden v2 written by the test's own write_golden; v1 (scoring-8)
frozen by sha256. Real-engine scoring-10 cross-midnight golden added. Research
records re-frozen per ERR-110 (label functional_v2_2026_10_02) and
scripts/functional_benefics.py added to the frozen production identity
(ERR-114: 57782aea changed scores without tripping it).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Ported verbatim from the upstream skill repo (yinduzhanxing e9beae6b) with
product authorization 2026-10-02: scripts/functional_benefics.py,
scripts/pancha_mahapurusha.py, references/functional-role-profile.md; only
the two functional-role methods of scripts/yoga_engine.py (our file diverged).
v5 77-case rectification eval: 5 cells up (to +7.8pp), one cell -1.3pp (one
case); product accepted. Rectification memoization golden still to be
regenerated (scores change with the grouping).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
- AFFLICTION_RANGE_RULE (one definition, consultation-thinking-plan.ts):
pressure / distance signs + evidence + a range of realities, no verdict on
facts the user knows better, no opposite reassurance, one ask per answer;
quoted by the shared reading (line 3) and NATAL_SECTION_RULE
- parents line 2, marriage line, health line 1 follow it; career gets a
'lifetime career shape first' line and neutral three layers (no 面试/职位)
- follow-up correction rule: map only lines that fit; say 盘本身分不出这一点
- voice / VOICE.md parents example rewritten to the range form
- contract tests updated with 原值/新值/原因
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Annual / timing single-domain turns take the career / marriage / wealth budget:
contract + card <= 12,000, total with the checklist <= 18,000.
CONSULT_READING_BUDGET_BLOCKED removed; size assertions and the pinned
blocker test changed (原值/新值/原因 in the tests and brief 2's progress record);
BUG-1160/1161 resolved, BLOCKED.md entry struck through.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
- 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
- T1 (BUG-1160): 「通用读法 · 先看受冲」 opens every turn's methodology once.
- T2 (BUG-1161): Chinese lists for parents, children, education, migration,
family, annual, general, health; health replaces the English route in the
web consultation only.
- T3 (BUG-1162): career / marriage / wealth each gain an affliction line.
- T4 (BUG-1163): health label 健康, prompt asks about the constitution first.
- Single-domain annual / timing turns keep the pre-brief method
(CONSULT_READING_BUDGET_BLOCKED): they would exceed the 12,000-character
assertions, which this brief may not change.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
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
TASK-consult-card-affliction-data-20261001 T5/T6: BUG-1154~1159 (1158 functional
classification source, investigating; 1159 yoga list is the packet candidate
set, investigating), progress record with size table, T4 diagnosis and T5
findings, BLOCKED entry, task index status.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
TASK-consult-card-affliction-data-20261001 T1-T4 (BUG-1154~1157, BUG-1159 mitigation).
- Engine layer graha_drishti (aspects.calc_house_aspects; combustion via the
full reading's own rule, extracted as jyotish_engine.is_combust, orbs
unchanged); yoga_domains (fixed Raman packet table by rule_id, with the
sieve's hit); slow_transits.saturn_from_moon_house.
- Card: planets get aspected_by / conjunct_with / combust (true only);
domain house rows get aspected_by; parents roles get lord_rows and
significator_rows with functional class, D12 house lord and its sign;
health houses [1,6,8,12], education [4,5,9]; annual copies
saturn_from_moon_house; yogas filtered by domain tag with hits.
- Budget (D6): antardashas as [lord, start, end], D9 vargottama only when
true; all 12,000-char assertions unchanged.
- Golden regenerated by the real engine; jyotish_api_server.py untouched.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
On the staging test-OTP channel, 验证码登录 with a fresh mailbox no longer
stops at 设置登录密码; it records consent and enters the app. 注册账号 still
sets a password, second factor still comes first, and production (no
IDENTITY_TEST_OTP) is unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Late night no longer remarks on being awake (产品 2026-10-01); every daypart,
weekday and returning line reworded in the same caring voice. Daily line:
each house sentence names where the Moon is in plain words, then one concrete
sentence; no stacked hedges. Sign-fallback moods rewritten the same way.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
The answer outline (think.plan / thinking.section) was drawn as four think
rows and ticked done as soon as the chart calculation started. The reducer
now keeps the outline only as calculate-row detail; live and history views
share it. Product chose option B on 2026-10-01.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
The 77-case persisted replay after the BUG-1143 fix keeps every truth segment
at both 21 and 61 minutes with segment order on, so the default envelope moves
from 21 to 61 minutes. Bug numbers follow staging (BUG-1142 was taken).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
BUG-1142: distinguish focuses wrote the planner domain verbatim, and
health_pressure is not in the focus table's target_domain check. The write
failed inside a swallowed retry and the session went straight to delivery
although tap cards remained. Every focus write now goes through
focusTargetDomain (persistableFocusDomain, BUG-672), and focus-to-probe
matching uses sameCollectDomain.
BUG-1143: segmentOrderEnabledFor turns segment-gain probe order on by default
when the scanned window is at most 21 minutes, where the 77-case persisted
replay gained head hits with no lost truth segment. RECTIFICATION_SEGMENT_ORDER
=off disables it; =on keeps the 61-minute research envelope.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
The 70s answer clock was sized for a non-reasoning writer; thinking tokens
come out of the same clock and deepseek-v4-pro took 77s on a parents answer.
Product 2026-10-01 chose five minutes. The general / no-birth-minute loop has
no tools, so it now starts on the answer clock instead of the 110s tool clock.
Tool phase and domain budget unchanged; maxDuration 240 -> 480.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
