Round-7 option A is text-first, so Scorpio and Aquarius lords, the Ketu-only degree reversal, and node exaltation years now live in the Rath display layer. Scoring files stay unchanged.
Co-authored-by: Cursor <cursoragent@cursor.com>
Round-6 ruling Q7: default by the AD start sign's odd/even (Table 13, as in
Table 25); Saturn in the MD sign -> always zodiacal (Table 11); Ketu ->
reversed (Table 14); both -> Ketu first. Each AD rule now carries
direction.book_divergence (p.47 J.S. 1.1.34; J.S. 2.4.31-32), not applied;
reference report shows one line, English twins added. Table 25 Taurus 12/12.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Product decision 2026-10-03 (changes the BUG-1160/1161 budget): every
domain card carries the Sanjay Rath Narayana running MD beside the legacy
one, in its short form (label, start sign, MD sign, start / end age).
Card budget 12,000 -> 12,500, with the method checklist 18,000 -> 18,500;
three budget assertions rewritten with old / new / reason notes.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Display only; scoring and timing conclusions keep the legacy algorithm.
narayana_legacy_label attaches a Rath view (seed, deciding level, direction,
24 MDs, running MD/AD) under modules.narayana_dasha.rath for the consultation
modules, full reading Step 4.13 and the CLI. Reference report: one summary
line under the legacy line plus Rath MD / running-MD AD tables (English terms
added). Evidence card: narayana_rath (label, seed sign, level, running MD) on
timing / annual cards only — other cards sit at 11,979 of 12,000 characters.
Goldens re-captured from the real engine.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Annual layer: Mudda segments now start from the natal Moon nakshatra (10 rows
cropped to the Varsha year), year-lord basis reads 「按 Tajika 五分力量」, and
one chart's year lord changes under the five-fold Panchavargiya.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
The full note pushed steve_jobs/marriage to 12,028 characters (budget
12,000), and cutting it in the card broke the 'nothing rewritten' contract.
The engine now also writes algorithm_label 旧算法（从上升起、一律顺行）, the card
copies it verbatim, and Narayana AD/PD rows drop years (end_age - start_age).
Largest card 11,979 (baseline 11,983). Goldens re-captured; the biography
golden now keeps the Narayana label keys too.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
capture_consult_evidence_card_golden.py and capture_consult_biography_backtest_golden.py
(PYTHONHASHSEED=0, JYOTISH_API_CHART_CACHE_TTL_SECONDS=0). Differences are this
batch's own: yogas d9_dignity_modifier (BUG-1213, all None on these charts),
annual year lord / varshesha_basis / Mudda segments (BUG-1214), Narayana
profile + algorithm_note (BUG-1215; capture keeps the two keys). Card test
gains one assertion: timing.narayana.algorithm is the legacy note.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Round-4 ruling Q4 / product decision A: scoring and the consultation and
report time axes keep the old Narayana (from the Lagna, always zodiacal) until
the Rath trial is decided; every user-visible Narayana now says so.
narayana_legacy_label adds profile=legacy_reference_only and the note (zh/en)
at the consumers (consultation modules, full reading Step 4.13, CLI), not in
the frozen narayana_dasha.py (ERR-110/115). The card's timing.narayana carries
'algorithm'; the projection allowlist passes algorithm_note; the reference
report's Narayana section and the dasha-family table show '算法：…' (English
twin in the phrase table). The unused narayana-dasha --variant-profile flag,
the one place offering a Chara Dasha author's profile for Narayana, is removed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
consult-evidence-card-golden.json and consult-biography-backtest-golden.json
re-captured with their capture scripts (JYOTISH_API_CHART_CACHE_TTL_SECONDS=0,
PYTHONHASHSEED=0). Differences are the batch's own: Sodhita chain and
house_scores sav_sodhita (BUG-1209), shadbala minimum fields (BUG-1208),
varshesha_basis (BUG-1212), traditional_yogas names (BUG-1205/1207: Neecha
Bhanga with conditions, Mahapurusha with 部分减弱, Taylor's trikona Hamsa gone),
chart.yogas Kemadruma rows (BUG-1206), Rahu/Ketu status and D9 dignity and
fixed-lord rule hits in the health sieve (BUG-1211).
Card: shadbala rows are rupas / minimum_check / level (the engine's other
three fields restate them; keeps the 12,000-character card budget).
Changed assertions (three columns in PROGRESS): career 10H SAV keys, annual
chart keys, Obama traditional-yoga names.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Astrologer ruling 甲11. Muntha stays natal Lagna + completed years (test pins it on
the main path; muntha.calc_muntha_from_sun_sign is imported nowhere). Panchavargiya
is not implemented (native producer blocked). Consultation annual layer gains
varshesha_basis '暂用 Muntha 主星；占星师口径为 Panchavargiya，待接入' (card keys and
the workflow allowlist carry it); reader report 'Selection basis' row says the
same in both annual sections (zh/en).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Astrologer ruling 乙8. New scripts/ashtakavarga_shodhana.py: per BAV row Trikona then
Ekadhipatya (the two existing ashtakavarga functions, previously only called by
tests), Sodhita SAV = sum of reduced rows; occupied signs = seven grahas. Removed
calc_sodhita_av (Sun/Mars/Saturn contribution removal labelled 'BPHS标准').
Wired into /api/ashtakavarga (result.sodhita, house_scores[*].sav_sodhita) and the
full reading. Reader: SAV table 'Sodhita SAV | Raw SAV', house table gains
Sodhita column, Sodhita BAV table before raw BAV; reference edition section
rewritten. Card: sav_sodhita before sav_score plus sav_columns label. Personal
report facts: score = Sodhita, rawScore/savRawTotal beside (optional schema
fields). Fact tables: Sodhita column and Sodhita BAV subtable. Transit scoring
unchanged (raw bindus).
Golden: report-density-fictional-engine.json leaf worksheets.strengths_and_scores
.ashtakavarga recaptured from the real engine (scripts/research/refresh_density_
fixture_ashtakavarga.py); bav/sav identical, every other leaf byte-equal.
Changed assertions (three columns in PROGRESS): BUG-1200 house-table tests,
report-fact-tables ashtakavarga columns/subtables, run_all t1/t57.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Astrologer ruling 乙14. One condition source, yogas_doshas.calc_nicha_bhanga_raj_yoga
(conditions A-F, now also structured). New scripts/main_yoga_detectors.py turns it
into yoga_engine-shaped rows (zh + en twins) that YogaEngine.detect appends; the
four neechabhanga_* rules are reference_only (kept, renamed, not evaluated).
Card: traditional_yogas canonical 落陷取消（Neecha Bhanga） with 成立条件; compact
yoga entries keep conditions/reductions. Report: category 落陷取消, mixed group,
not raja; personal-report alias neecha_bhanga -> special.
Changed assertion (test_consultation_yoga_detection_merge): canonical name
'Neecha Bhanga Raja Yoga' -> '落陷取消（Neecha Bhanga）' (ruling 乙14).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
- Report p33 table: no Kranti column (no producer; materials.kranti stays blocked).
- Report p53 table: the "SAV" column was the with-Lagna total (386). Split in the
reader into SAV / Lagna BAV / SAV + Lagna with a totals row; ashtakavarga.py is
untouched (frozen rectification identity, ERR-115).
- /api/chart ascendant carries nakshatra / pada / lord (_nakshatra_fields shared with
the nine bodies); chart cache schema 4 -> 5.
- /api/varga_full bodies carry dignity_level from varga_dignity_level, the function
the Vimsopaka path now shares (A/B identical); the chart page shows the D1 status
wording and no longer derives a three-level dignity itself.
- Report page draws each chart once: the trailing block skips charts the body already
fenced (same rule as the export); the birth-time caveat moves under the body's
chart heading.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
The sync5 re-freeze (1029cbaa) moved the product holdout's current-tree
record to sealed_holdout_rerun_upstream_sync5_2026_10_02.json; the test
still read the sync4 file. Three-column note added.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
capture_consult_biography_backtest_golden.py run twice (PYTHONHASHSEED=0,
chart cache TTL 0), byte-identical. Only change: one figure's retrograde Venus
is no longer combust in the graha drishti layer (retrograde orb 8 deg, U3
combustion table). consult-evidence-card-golden.json regenerated twice as
well and is byte-identical to the committed file.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
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
For house 7 the event lord and the opposite lord are the same planet, so
every double-transit hit arrived twice. With the corrected aspect count the
Taylor marriage turn reached 12,040 characters (budget 12,000, test
consult-condensed-checklist "size"). The card now keeps the "(宫主)" row and
drops its "(对宫主)" twin; values stay engine values (the "nothing rewritten"
contract holds), the budget assertion is unchanged (BUG-1155 precedent:
compress the format, not the budget). Taylor marriage 12,040 -> under 11,922.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Both captured with their scripts (PYTHONHASHSEED=0, chart cache TTL 0), twice,
byte-identical. Changes against a18f8d4e: lunar/solar yoga hits and names
(five-planet rule, retired duplicates), double-transit conclusions and active
houses (aspect count from 1, stable order), and Shadbala Sun min_required /
ishta % / level (BPHS 6.5: all nine backtest figures drop one level).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Same procedure as 406d81b8 (BUG-1088): the contract's current_tree_scorer
now points at sealed_holdout_rerun_functional_v2_2026_10_02.json; release
keys and the closed gate are unchanged. 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
- 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
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
- 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 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
