产品 2026-11-07 同步占星师 Yoga 规则批次:
- lord(a) != lord(b) guard on ten two-lord rules (raja 1_4, 1_10, 4_9, 5_9,
7_9, 2_10, 2_7; dhana 5_11, 2_5; kalatra 7_1); Jobs raja_yoga_1_10 and
Presley dhana_yoga_2_5 no longer form, matching her output.
- 23 rules become structural_observation "(Observation)" rows; old effects
move to traditional_effects; engine rows carry claim_kind, legacy_name,
condition_evidence, strength 'observation', strength_basis.
- formation contracts + assess_yoga_formation, formation_checks /
formation_assessment / strength_factors on every JSON-rule row;
participants_expr support; natal yoga context chart_type D1.
- consultation: compact rows, sieve hits and yoga_conditions carry
claim_kind / formation / formation_checks; observation status is
structural_observation; card yogas_detail copies them plus formation_rule.
- reports: personal report never lists an observation as a formed
combination; annual facts rank observations last and the evidence lists
them under 结构观察, not 格局; PL9 tables print 结构观察 for strength /
category and group observations as mixed.
- governed rules (BUG-1207, 1205, 1187/1206, 1596/1624, 1597/1625, 1571)
untouched; Parvata stays disabled; 69 not_implemented unchanged.
- card golden recaptured.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Ported from handoff/product-parity-20261107 (28823446, 99076dad):
- Ashtottari: cycle index counts from the balance-shifted first MD (no
gap before the 108th birthday); dasha_balance_at_birth / dasha_at_birth /
timeline_basis now emitted (the report already read them).
- Bhava Chalit MC in the natal frame (_bhava_midheaven_in_natal_frame).
- Narayana current lookup: no modulo replay outside the two generated
cycles; status selected / outside_generated_timeline.
- Bhava Bala: no unvalidated absolute level; _meta.score_unit = Virupas.
- Field names lined up with hers: required_strength_pct (+ semantics
marker, via shadbala_display sidecar; shadbala.py stays frozen),
Harsha missing_inputs / score_range, cmd_yoga evaluation_error_count.
Already equivalent: yoga failures (BUG-1571), Drik determinism (BUG-1576),
standalone transit ephemeris path, Chara dignity location (BUG-1566), Harsha
max 20 / unknown day-night. Tests: tests/test_handoff_99076dad_sync.py.
Golden recaptured (Narayana status field only).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Astrologer third-round review 2026-11-07, items 4b-4d.
- Shadbala: the ratio total rupas / minimum is labelled a sufficiency
ratio (not auspiciousness, not ishta_phala) on the card, in the annual
package (sufficiency_ratio_pct, rank_by_total_rupas), the report facts
(ranking_basis, ratio_meaning, ranking_by_ratio) and the annual report
text. Chesta reference packet rows carry values_scope on every row.
- Argala: the layer and card say supported is a structural intervention
only; ties broken by the Narayana strength selector carry
ruling_pending / tie_break_ruling_pending (behaviour unchanged).
- Tajika: each annual pack field lists what partial_verified covers
(formula / order / boundary_dates / full_chart); dates_verified is false
and the consultation layer projects it.
The consultation evidence card golden is recaptured for the new layer
fields (start_at / end_at, not_evaluated, verification scope, labels).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Upstream ba8e36ec adds sections.transit for every route. Here the annual route
promises a "transit" label; a real but ungated section broke the evidence-gate
parity test. The section stays for finance/wealth, where the finance support
review reads it; the health override is unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Astrologer third-round review 2026-11-07, item 3. timeline_boundaries
checks end == next start on full timestamps (start inclusive, end
exclusive) and lists every gap or overlap. The solar-return report and
annual pack expose the real return interval (this return to the next
actual return, computed), the Mudda 365.25-day year and the shown window
separately. The annual package checks the year chain, each year's Mudda,
Patyayini, monthly and Varsha Narayana rows, natal Vimshottari / Narayana,
and Mudda across years (a ~8-minute hole the fixed year leaves before the
next return). Consultation dasha rows gain start_at / end_at with the
birth offset and a per-system continuity check; the card carries
continuity_issue only when a table is not continuous.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Astrologer third-round review 2026-11-07, item 2. With is_daytime unknown
the fourth Harsha component is None (status unknown), the total is
withheld and only the known three-component sum (out of 15) is given.
The annual pack, report facts, interpretation rows and the parity
strength table carry the incomplete state instead of a full score.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Product 2026-11-07: sync the astrologer's working branch (ea2a9d65..d09feab7).
- 0266b6ad: year lord picks by the native five-fold Panchavargiya only; a
PyJHora score (research switch) is attached per candidate as
external_oracle_comparison (observation_only_not_selection_input) and
never selects. panchavargiya_selection_policy on the result; candidate_list
and the reader-report candidate table carry the five components and raw total.
The legacy Sun/Mars/Saturn table relabel is not applicable: calc_sodhita_av
was already removed here (BUG-1209).
- 8c4bff8a + a5b75886: Sodhita no longer votes in finance adjudication; the
bridge keeps raw 2/11 scores with prediction_scoring_allowed false.
- ba8e36ec: finance delivery inventory (raw, no vote), wrapped producer status
counts as blocked in machine-evidence sections, transit section, report gate
evidence_claims bindings, finance support review readiness.
- 5962368d: dispositor chain dispositor_sign is the dispositor's own sign.
- 8813c851: BCP observed at the reading date (bcp_reference, PL9 row).
- d09feab7: nakshatra_advanced.calculate_stellar_jeeva_sareera and the
nadi-stellar-roles CLI; specialized-jyotish SKILL.md, usage packs, ontology
and gap scanner mirrored.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Astrologer third-round review 2026-11-07, item 1. _run_custom_expr no
longer swallows exceptions; YogaEngine.detect records evaluation_failed
rows with the error class, and rules naming a condition type no evaluator
implements (69 BVR rules) are listed as not_implemented instead of being
silently never formed. The consultation sieve moves such packet members
to not_evaluated, and the card lists them. dhana_yoga no longer imports
math; parvata_yoga is disabled pending a definition ruling (BUG-1571).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Three-way parity audit 2026-11-07 (U ea2a9d65 / F frozen / P f70ae94e):
- Vimsopaka: look vargas up by "D{n}_" prefix (D60 key was misspelt, every
D60 fell to Neutral) and score only the sign-owner relation (upstream
ab5b8709, BPHS 7.21-27). All 16 varga scores now equal U on 3 charts.
- Narayana: age = total_seconds / (86400 x 365.25) keeping the birth time
(upstream ab5b8709); Rath rows carry start_date / end_date from the
unrounded ages; consult layer, report facts, API and calendar read them.
- Ascendant degree_raw / lon unrounded (engine and chart API).
- position_mode label: legacy is the apparent frame since BUG-1275; the
profile and module labels now say "apparent" (legacy still accepted).
- Functional profile label v2 -> v3_166q4 (the table actually used).
- full-reading Sade Sati uses the dated transit Saturn (upstream e628118d):
Jobs 2026-11-07 peak, owner / Obama not active, as U.
Consult evidence card golden recaptured.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Product 2026-11-07: stay in sync with the astrologer's latest (5fb8379c..ea2a9d65).
- Method layer: mirror SKILL.md re-imported with import_yinduzhanxing.py from a
clean ea2a9d65 clone (import record, manifest, import plan); root SKILL.md
body equals the mirror again (nine-lord editorial reference line). Router and
sub-skills unchanged upstream except her rectification skill, which is the
protected commercial skill here.
- 7b43eaf2: rectification question templates say they are templates (basis,
timing status, answer impact), no regression_hint +5 bias, low confidence
cap, blocked/external execution status in the audit table, invalid answers
ignored by the selector, calculation_profile echoed; API rejects a partial
lat/lon/tz and event rectification without a place.
- a4b4b267: BPHS 27.19 Drik weighting readings as diagnostic variants in
scripts/shadbala_reference/drik_profiles.py (shadbala.py is frozen, ERR-110;
default quarter and BPHS piecewise geometry unchanged, BUG-1586 / BUG-1623);
oracle audit compares rupa with rupa; VP Jain benchmark prints by default.
- bb26dc2d: /api/jaimini special mode carries the Goel fields, no invented
Aries ascendant.
- d66d13ce: annual report exposes tajika_named_yoga_structures.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
- KP monthly support read the birth-balance lord every month (no current_dasha in the issue #137 timeline); now the running lords, matching upstream
- ported prediction_verdict_matrix.py and references/rectification_evidence_contract_v1.json (the contract was always blocked as file missing)
- English audit statuses run / not_run written as Ran / Not run (run is also a packet key)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
- KP layer: sidereal Placidus cusp star/sub/sub-sub lords against MD/AD/PD
lords (upstream KP_SUB_WEIGHTS). Owner window 04:50-05:10, synthetic
5-event ledger: KP off 05:09, KP on 05:06 (upstream 05:09 / 05:06).
- result.python_engine: functional benefic/malefic, A7/UL/A10, SAV,
Shadbala, date-precision weights and the lead-margin verdict
(adjudicate_candidate_rows, neighbour stability, leave-one-out).
- Scan adds D5/D6/D8/D11/D16/D27/D40/D45 (D40/D45/D60 reference-only);
chart-choice boundary lines unchanged.
- When the top score ties, match_tier is 'tied' (分不出前后) with system
confidence 不确定; the UI shows the tie instead of 高度吻合.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Upstream's receipt _status reads execution_status before status and maps
partial_verified to parameter_sensitive, so the primary lane
'two-person Dasha/Narayana/Chara' was never ready and every dossier ended
delivery_readiness=blocked. The Rath view now carries execution_status
(executed when the seed is decided, blocked otherwise) and keeps the book
level in confidence_status, the same shape as upstream's Rashi Dasha
modules. Upstream's gate code is untouched.
Diana-Obama (raman) and the six eval pairs (lahiri): blocked -> ready_for_narrative.
Also syncs the Rath importer list test (varsha_narayana, consultation_native_layers)
and skips the retired BUG-1644 frozen file.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
产品 2026-11-07 占星师方案 (item 4/5/6/8/10): the report reading and the export follow her skill.
- reading_facts v2 contract: birth parameters (no name/coordinates), 12 houses with KP cusps,
functional roles and natural-vs-functional conflicts, per-domain vargas (wealth D2+D11+D10,
A2/A11/A10; career D10+A10, AK/AmK; marriage D9+UL, A7/DK), special points, Jaimini, yogas as
candidates with conditions, Vimshottari to PD + Narayana with dates (birth date + age) and the
legacy variant, every dasha family's current period/status, transits from four reference points,
Sade Sati, double transit, strengths, KP, annual, technique audit, evidence paths, method
differences, blocked / parameter_sensitive / withheld states
- consult card facts: multi-varga domains, A2/A11/A10/AK/A7 participation, D1 varga resolves,
yoga path fixed, Narayana ages; KP is conditional (参数敏感) instead of 不参与
- report writer: professional prompt (evidence first, A/B/C, dual-track timing, status labels),
ninth section 依据与边界 (stored reading v2; v1 still reads), Latin allowed, longer limits
- export: technique audit chapter (Functional Benefic/Malefic, MEVG / Global Web Evidence,
Real Case Calibration rows), parameter/method differences, dasha system status, evidence
boundaries and the D1–D60 ledger (20 formal + 40 research D-N); upstream
varga_evidence_matrix / generic_varga_research_audit + registries ported so the ledger is no
longer blocked
- ordinary projection no longer deletes technique audit / MEVG / 参数敏感; parameter_sensitive
is relabelled 参数敏感
- quality gate: upstream technique_audit_table check restored, plus required-row check
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Port from yinduzhanxing 5fb8379c (MIT): Naisargika, Kaala, Karaka, Tara,
Lagnamsaka, Yogardha, Mandooka, Paryaaya and Padanadhamsa dashas;
Sarvatobhadra, Kota and Kalanala chakras; Nakshatra Latta; Pachakadi;
Raman Amsayu and Pindayu. Producers and their upstream tests are copied;
scripts/upstream_technique_layers.py feeds them our natal and transit
positions and attaches chart.consultation_native_layers.upstream_techniques.
- dasha_registry: kaala and padanadhamsa keys (35 -> 37); the nine ported
dashas are served by compute_dasha or fail closed with upstream's reason.
- technique_registry.json: 16 partial entries; README badges follow.
- Evidence lookup section `upstream_techniques` in the consultation tool.
- Boundaries: Kalanala carries no PyJHora (AGPL) grid coordinates;
Padanadhamsa/Lagnamsaka run on our Narayana engine (no Rath Table 12,
PVR co-lord variants or second cycle). PyJHora observers and the Amsayu
worked-example scaffold live in scripts/research (root .py budget).
- PyJHora black-box cross-checks: Naisargika (lords/years) and Kaala
(seed segment and fraction within 5e-4) on a public chart.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Owner order 2026-11-07 (astrologer plan item 2): metadata-only catalog and rule citations in git; full texts and passage index stay local (gitignored). POST /api/book_citations and a bounded consultation tool with chart condition check.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Product order 2026-11-07: birth-time rectification follows the astrologer's
skill (yinduzhanxing 5fb8379c) in full. The chart-choice page stays; her
method is added as a stage and both results are shown side by side.
- scripts/chart_choice/astrologer.py, POST /api/chart_choice/astrologer:
minute-by-minute scan of D1/D2/D3/D4/D7/D9/D10/D12/D20/D24/D30/D60
(D60 reference only), ascendant nakshatra/pada, KP sub-lord, A7/UL/A10;
her five stages (intake, appearance/birthmark screens, event verification
with Vimshottari MD/AD/PD + Narayana MD/AD per event and the >=5-event
gate, D9/D10 trait correction, report); her 40/35/15/10 scoring, match-rate
tiers (80/60), report confidence (90/70) and engine confidence; family
(六亲) event categories; D30 only with health-type events; Gochara blocked;
our 77-case backtest caveat on every result.
- active_rectification_questions.py synced to upstream (question_bank,
bindings, workflow_status), local adaptations marked LOCAL, accepts an
in-process minute_scan.
- Frontend: /api/chart-choice/astrologer and an AstrologerStage step,
reachable from the result, the no-line case and the current record.
- Consultation reads the other version for domains kept 「两版都读」
(provenance now records other_saved_at).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
- root SKILL.md is her upstream file (body byte-identical to the 5fb8379c mirror; description quoted so YAML parses and Mastra can load the skill)
- chat binds the whole SKILL.md plus references/product_runtime_contract.md (safety-only) instead of a ~477-character excerpt
- every turn carries her full strict-workflow-router (synced to upstream) and the domain's event-judgment file; product lists follow as an extra layer
- import her 10 sub-skills, family router, interpretation status contract, technique ontology and the 54 files her method names
- tests/test_upstream_skill_parity.py (in the quick gate) fails whenever her skill and ours drift
- 18 frontend guards that locked the excerpt design updated 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_01DbBXoyn7Hj3LCW3BUs5bZ8
- marriage_match keeps Rajju (same group) and Vedha (paired) as flags, which
read the same either way round; Mahendra, Stree Deergha and the in-law
star rules are recorded as not used (gender-directed / in-law risk).
- pair_promise_links lists where one person's 7th lord, UL, DK, A7 or Moon
sits in the other's ascendant, Moon or Venus sign (same sign or 1-7 axis).
- Appendix shows both.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2su8Vzqv3jNvkCSqt
`relationship_promise` reads both full charts: 7th lord and 7th-house
occupants, Venus and DK with sign, house, dignity and functional role; UL
with its lord, occupants and the 2nd from UL; D9 ascendant, D9 7th lord and
Venus in D9 (vargottama). Missing charts stay `not_available`. The appendix
adds one promise line per person under their structure line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2su8Vzqv3jNvkCSqt
The 星历 page gets a month calendar for the chosen person: every day is
吉 / 平 / 凶 with two or three life themes from transits against their own
chart, the selected day opens to its themes and "为什么", and below it
「接下来要留心」, 「这几天」 and 「回看」 (owner, 2026-11-07: A's grid plus
C's lower half).
Engine: scripts/personal_calendar.py joins existing calculators on one
date axis (one call, <0.5 s for 45 days): Panchanga in the subject's own
ayanamsa, Tara / Chandra bala, Moon house from Lagna and Moon,
Ashtakavarga SAV + Moon BAV, transit conjunctions with natal points,
functional benefic / malefic, activity verdicts with native inputs,
ingress / station / combustion / eclipse / Vimshottari AD+PD boundaries,
and a month backdrop (Vimshottari MD/AD/PD, Narayana, Sade Sati / Kantaka,
slow-graha contacts, Jupiter+Saturn double transit). New endpoint
/api/personal_calendar.
BUG-1666: check_activity_muhurta ignored Vishti karana, Vyatipata /
Vaidhriti and an avoided Chandra bala, so a Vishti day could be 大吉.
BUG-1667 (closes BUG-703 / BUG-707): /api/panchanga_range now honours the
requested ayanamsa; the day view asks for the subject's own and drops the
Lahiri note.
Frontend: /api/ephemeris/month (own rate-limit bucket, cached),
/api/ephemeris/checks + migration 20261107010000_ephemeris_day_checks
(answers kept with the birth declaration they were made under). Copy is
life-first with the sky events folded under 为什么; draft wording pending
the astrologer. TASK-ephemeris-page decisions 4/6 and hard lines 3/7/9
superseded per the owner; DESIGN.md §16 updated.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXozbkyFNqbu8pVEtZ7W
- Sync references/mahadasha_editorial_bilingual.json (9 lords x 3 paragraphs,
zh + en, per-paragraph source locators) and mahadasha_editorial_policy.md,
plus the one-line pointers in SKILL.md and vimshottari_dasha_guide.md.
- New chapter after 大运解释 in both editions: the three paragraphs side by
side (general / traditionally supportive / traditionally strained), never
picked by lord or chart, Mahadasha layer only; source labelled as secondary
study notes with the original edition pending verification; English only
in the English edition.
- Coverage contract: the topic moves from NOT_CARRIED to the checked list.
No change to the frozen exporter, dates or any scoring.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyeZrYn6ryNcSe5Y2Y
Product: turn the upstream coverage audit into our own automated check.
- scripts/report_render/upstream_coverage.py maps 140 upstream topics to our
zh/en sections and checks presence, real content, key columns (transit
sign, yoga participants, Shadbala components, Kala Chakra signs) and
degraded markers. NOT_CARRIED records the 4 topics we do not ship and why.
It also runs as a CLI on any exported report.
- tests/test_report_upstream_coverage_contract.py runs it on two fictional
charts in both editions, checks the contract itself, and proves it flags a
bad report. The 2026-11-05 export gives 15 findings; today's gives 0.
- Fixes the contract found: Shattrimshatsama gets the opt-in reference table
like the other conditional dashas; a year without a Tajika yoga keeps its
section with one sentence instead of dropping it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyeZrYn6ryNcSe5Y2Y
Each annual chart now opens with its local return time, annual ascendant,
Muntha and year lord; every body gets its whole-sign house from the annual
ascendant, longitude and degree in sign.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyeZrYn6ryNcSe5Y2Y
- BUG-1661: Avastha states were translated by the general glossary, which had
Young as 青年期 and Youth as 壮年期 (the calculator says 少年期 / 青年期) and
left Old, Dina, Sabha and others in English ("Deep 睡眠"). One table taken
from the calculator's enum comments now names them in the report body, the
appendix and the frontend fact table. The Python export also uses a comma
for simultaneous Deeptadi states in English (BUG-1391 fixed only the
frontend).
- Nakshatra dasha context: natal Moon nakshatra, the current MD and AD lords'
nakshatras and Taras, and the nakshatra of each AD lord in the MD. Both
Ashtottari applicability rules are listed; when they disagree the report
says no ruling has been made.
Frontend: report-fact-tables.test.ts assertions updated with 原值/新值/原因.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyeZrYn6ryNcSe5Y2Y
- Prastara: per-planet table of the eight contributors' bindus by sign; the
columns add up to the BAV.
- Avastha inputs: each planet's state in the five systems with its basis and
method (BPHS rule / simplified rule); Chinese state names come from the
module's own meaning text, no new glossary.
- Goel Jaimini: planet parts (Mooltrikona, Karaka, Kendriya, Kartari,
Adhipati, malefic contacts) and sign parts (permanent, Karaka, Sthana,
aspect, lord strength).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyeZrYn6ryNcSe5Y2Y