The card's model view gains evidence_index: the snapshot id and coverage, one id
template per fact path, status codes with a legend and the per-id exceptions.
Positions, houses, roles, afflictions, Arudha and derived houses, points, SAV,
KP, Argala, transits, double transit, Saturn cycles, the annual chart, every
dasha level, judgment and participation rows now resolve; rows that name their
own id keep it. Branch rows carry their #br: id from the facts packet. A
coverage check lists any card leaf that is neither a fact nor marked not
citable; it is empty on all public golden cards.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Per the astrologer's 2026-11-18 review of the evidence-pack draft (§二 1-5, §五.3, §五.5):
logical_key / snapshot-scoped evidence_id / content_hash; birth-branch ids bound to the parent
range and intervals; snapshot over opaque subject, birth input revision, calculation profile,
rule versions, retractions, observation instant and coverage (calculation time recorded only);
execution / formation / interpretation / source status; base-level edges with type, scope,
conditions, method version, basis and review status (engineering dependencies only);
dependency_closure with visited set, cycle report and budget; interpretation_key; a parseable
synthetic fixture and the review's test list.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Evidence-pack step 1 (owner 2026-11-18). One ASCII form, ev:<family>:<body>, for D1 and varga
placements, AL/UL derived houses, special points, Shadbala, dasha periods, transits, double
transit and yoga rule instances; an evidence base with links taken only from what the data
states; a snapshot id binding the birth input revision, calculation date and rule versions.
The internal-word check drops ids from the basis section and logs them in the body.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
(a) formed / disabled / observation (the yoga rule states on the card since
BUG-1967) and key: true|false fragments are now internal words; the table uses
only existing product wording (computed and conditions_not_met yoga texts,
未执行, 已停用, 燃烧 / 未燃烧, 逆行 / 顺行), a one-word key set to true keeps
the term, anything else is dropped. Offline rerun over 63 saved answers: 5 new
basis hits, all the two real leaks, no new false positives.
(b) The relations line states AL's 2nd / 11th (and UL's 2nd for marriage
continuity) against the natal house of the same number: same sign or not, and
where the natal lord sits. No voice rule added.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
The chat now carries the birth window the personal report reads
(consultationBirthTimeWindow). The facts packet samples the chart every
60 s across it, bisects each change to 1 s and recomputes every dependent
field per branch (scripts/consult_facts/birth_range_branches.py). Without
a declared window, or with only the default 30-minute trial, the rows stay
not_evaluated; a sample that does not reproduce the card is not branched.
A self-chosen side only orders branches. The key block lists the branches
and the relations line states what they share first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
The marriage card reads the question by fixed Chinese and English patterns
(consultation-marriage-intent.ts, no model call). For marriage_continuity
UL's 2nd joins the key block and its relations line (role main); for any
other marriage or love question it stays in the participation rows as an
auxiliary layer with an analysis-only note, per the astrologer's
2026-11-17 batch-2 item 6.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
The astrologer's 2026-11-17 batch-2 reply (section 3, items 2, 3, 4, 6) asked that
the chat card stop treating the first 30 yoga rows as the whole list. The owner
approved editing scripts/consultation_native_layers.py for this item.
- Native layer: no row cap; each row has rule_id (engine id, or a deterministic
derived:<category>:<name>), method_version and rule_state (formed / candidate /
not_formed / not_executed / disabled; observation for structural rows); the
layer adds rules_version and not_formed / not_executed / disabled / superseded
lists. Same-named rules with different ids are no longer merged; an id-less
chart.yogas row adopts the engine's id. Main detectors list their reference
rules (parent/evidence, not one id). Parvata is disabled_source_mismatch;
retired legacy spellings (Voshi, Sunapha, ...) point to their precise rules.
- Card: selectEvidenceCardYogaDetail keeps the rows the card's domains read and
records selected_by; later-house lord rows are listed short; omitted is a
structured count; the full layer is the new yoga_conditions lookup section.
- Personal report keeps its previous rows exactly (report-side dedupe + cap);
its yoga field list now matches the card.
- Size budgets raised with recorded old/new values and reasons.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Her second-batch items 4-6: main evidence of their own view, parallel to the natal
houses. Derived product-side from the packet's AL / UL sign (D1, inclusive count;
AL in Pisces -> Aries): target sign and natal house, occupants, lord and its natal
place, aspects, rule source. A missing start stays 派生未计算. They join the wealth /
marriage key block and its relations line; the report reading material treats them
as executed. The yoga card (30-row cap, rule ids) is generated in a frozen file and
is not changed here.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Shadbala reads 达到 / 未达到最低线 (her item 9; owner agreed) and the card carries
min_required for the 判断依据 line; required_strength_ratio beside ishta_bala_pct;
remedies no longer trigger from Shadbala (unaccepted_threshold). Education uses D24,
not D5 (item 7). Vighati keeps its position only (item 1); the 64th Navamsa from the
Moon and Pranapada take part as auxiliary layers with her fields (items 2, 3). The
annual natal two-Hora D2 gives Hora membership instead of the lagna lord's house,
and its birth-time stability check compares that membership (item 8).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Three things only; no constant or method choice changes (astrologer 2026-11-17:
totals are not tuned).
- _ayana_bala: the fold used strict inequalities, so a tropical longitude of
exactly 180 or 270 was not folded and the 0-90 declination table was
extrapolated (Sun -191.13 / -5126.06 Virupa). The two endpoints now join the
preceding branch. Sweep (every 0.01 deg, seven planets): only those two
angles differ from before.
- _d30_sign: `degree <= upper` put exact boundary degrees in the previous
segment, the opposite of scripts/varga.py and of every other varga here.
Now `<`. Sweep (every 0.001 deg, twelve signs): equal to varga.py everywhere;
only the eight boundary degrees differ from before.
- The 150/125/100/75/50 % band of total / minimum has no source (her Q2). The
display layer no longer returns it; the report table drops the column; the
chat context, card, lookup and the page-built evidence row carry met / not
met the minimum line and the raw ratio. The engine still computes the field
(the rectification feature hash covers the row).
BUG_HISTORY: BUG-1961 with a dated correction note on the wording of
BUG-1581 / 1582 / 1584 / 1586.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Astrologer 2026-11-17 Q8: a two-Hora D2 has no accepted twelve-house reading.
BUG-1954 changed the key block; the wealth judgment table (BUG-1907) and the
personal report reading material still carried the whole-sign D2 house.
- domain facts: domain_varga_hora / domain_varga_horas for D2, no D2 house
- judgment table: Hora on the row, no house signal for D2, D2 house dropped
from facts saved earlier
- report reading material: D2 rows carry hora, no house; Gulika / Maandi /
Indu Lagna read as supporting layers (three tests failed after BUG-1954)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
- D2 in the key block gives the two-Hora method, each body's longitude against
15 degrees and its Hora; no twelve-house rows. Other vargas name their
construction and source.
- Gulika, Maandi (health) and Indu Lagna (wealth) take part as auxiliary
layers instead of blocked rows; the boundary is an analysis-only note.
- The dasa-convergence lookup adds computation status, sub-period end points
and shared basis; unexecuted systems are not listed.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
After the fact guard, lines of the basis section that carry field names or
status identifiers get one model rewrite; what is left is replaced from a
table of existing wording or dropped. The body is only reported and the
answer is never failed for this check. Source fixes: the 5 / 15-minute
accuracy value reaches the model in words, the Argala lookup keeps the
Chinese verdict only, and four prompt lines no longer name a card key.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
The personal calendar's Kantaka flag is Saturn in the 4th / 7th / 10th sign
from the Moon only; the Moon's 8th is reported as Ashtama Shani on its own.
The PL9 report export lists 8th-house rows in a separate Ashtama Shani table
with sign and dates kept. Her calculators are untouched.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Kantaka = from the Moon, houses 4 / 7 / 10. The Moon's 8th is listed apart as
Ashtama Shani with its transit record kept. The current status is read from
the same timeline rows at the card's reference date; the engine's merged
Moon-and-Lagna flag is no longer shown. Her calculators are untouched.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
- key_facts carries a rule-built line of positions and relations per domain
- the block's label no longer pulls varga placements into the answer body
- Argala rows keep the Chinese verdict only; the voice drops a quoted field name
- a dropped premise clause takes the rest of its sentence in fact repair
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
A short key_facts block per domain is placed ahead of the full card in the
model view: the route table's own items (domain vargas read off their own
lagna, padas, karakas, route points) copied from the card. Blocked points
stay where they are. The answer voice is unchanged.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Vimsopaka, Pushkara, Dasha Sandhi and Dasa Convergence are copied from the
full-data packet into consult_card_facts.chart_supplements and exposed as four
evidence-lookup sections. The Gulika / Mandi / Indu Lagna contradiction on the
card is recorded as blocked, pending the astrologer.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
After the owner's staging test: the voice now asks for the character of a
relationship from the planets involved and the classical texts, keeps
period names and method status in the basis section, and stops calling a
candidate cancellation resolved.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
Owner decision 2026-11-16: the extracted passages live in
references/book_corpus/texts/ instead of a host-provisioned file. The
loader and extractor default to that path; the full transcriptions stay
local-only.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
Owner decision 2026-11-16: deliver B. V. Raman's "How to Judge a Horoscope"
passages. Whether the verbatim text may live in git is not decided, so the text
stays in a local data file and its location is a deployment choice.
- scripts/research/extract_raman_htjh_house_texts.py reads the two book
transcriptions from a given directory and writes one data file (default
references/book_corpus/local/, gitignored): per house, the passage for its
lord in each of the twelve houses and for each of the nine planets occupying
it, with volume, heading, page, source line range and the text as transcribed.
What cannot be located is left out and listed in the coverage table.
- scripts/book_citations/raman_house_texts.py loads that file from
JYOTISH_RAMAN_HOUSE_TEXTS_PATH (same default) and builds the native layer
`classical_texts`: rows only for this chart's own placements, each capped at
600 characters at a sentence end. Without the file the layer reports
not_available_yet with the reason and nothing else changes.
- The card lists, per domain section, the rows of that domain's houses whose
placement equals what the card already shows; a passage shared by two domains
is written once. Each row carries its source and a fixed reference-only status.
- P-10 gains one sentence on how to use the passages; the facts catalog lists
them with the book catalog as source; product_runtime_contract.md section R
records the decision and the manual provisioning step (also deploy/README.md).
No book text is committed; tests use invented passages.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
Both models copied the rule's own words for a strained relationship into
answers. The rule now asks for the model's own description, and the sample
counts recorded earlier are corrected.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
The rule engine detected Raja Yoga (Parivartana) but the compact yoga row kept
only the name and the two planets, and no domain section referred to it. The
row now carries the engine's own placements (`exchange`), is never cut by the
30-row cap, and each domain section lists the exchanges one of its house lords
takes part in (`lord_exchanges`). Status stays the detector's (`computed`).
Parents (A4, A9), family (A4), children (A5) and health (A6, A8) carry the
house Arudhas named by references/bhrigu-pada-all-event-freeze-execution-guide.md
section 4, on the card and in the domain facts catalog, with the table's own
domain words. Education and migration are left as they were.
Classical book passages are not shipped: see product_runtime_contract.md section Q.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
The plain voice no longer coins a label for the user's pattern, drops the
body tags, keeps one cause sentence per part and bans sentences about the
reading itself. The parent and marriage pressure lines ask for one direct
judgment instead of saying the chart cannot tell.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
The receipt carries a small chart record copied from the evidence card
(natal positions with D9 signs, running Vimshottari and Narayana periods,
slow transits with the next sign change); the page renders it as a folded
set of tables. A first answer that reads the chart but stops without its
判断依据 section gets one continuation that writes only that section.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
The owner decided on 2026-11-16 to merge 深度解读 and 简明解读. The composer
pill is gone; every answer is the plain voice, each main judgment tagged
明显 or 只是可能, and ends with a 判断依据 section the page folds above
the page-built 解读依据 list. The professional voice stays for research
runs only. Recorded in product_runtime_contract.md §P.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
Double Transit on each domain's own houses, on the reference date and in the
later stretches of the key-date window; divisional ascendant boundary margin
for every card varga; whole-sign houses in the domain vargas, Bhava Bala and
Jaimini sign aspects in the domain facts.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
The consult card's career section showed the birth mahadasha as the current
one, and a house lord that is Mars/Saturn/Rahu/Ketu was listed as conjunct
with itself. BUG-1902 (two Kantaka definitions on one card) is recorded as
investigating, pending the astrologer's ruling.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
- Words in a question no longer switch to 简明解读; 「不要把某颗星简单说成…」
had forced a plain answer under the 深度解读 pill.
- On phone width a composer with pills is the two-layer card: text on
top, 常用问题 + mode pill + send below.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq