536 Commits
Author SHA1 Message Date
ClaudeandClaude Opus 5.5 a78f9e281f fix(chat,report): a chosen 生时纠正 scenario gets no chat opening or per-claim other-scenario line; reports drop 「提到的时间段是有条件的推测」 (BUG-2147)
Independent Staging Quality Gate / publish (push) Blocked by required conditions
Independent Staging Quality Gate / validate-python (push) In progress
Independent Staging Quality Gate / validate-frontend (push) In progress
Owner 2026-11-22 「1 2 都去掉」, astrologer confirmation pending (contract G-19).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-22 06:42:37 +08:00
ClaudeandClaude Opus 5.5 4687945a96 fix(report): a birth time chosen in 生时纠正 opens with no statement (BUG-2146)
Independent Staging Quality Gate / validate-python (push) Successful in 10m18s
Independent Staging Quality Gate / validate-frontend (push) Successful in 13m58s
Independent Staging Quality Gate / publish (push) Successful in 3m14s
Owner 2026-11-22 「去掉」: a self-chosen scenario is treated like a rectified
time. Personal, annual and synastry pages and exports no longer write the
self-chosen statement ending 「其他可能的出生时间尚未作比较。」, and the
personal opening drops 「提到的时间段是有条件的推测」 for such reports.
Stored reports follow at display. Contract notice G-17 records the
suspension of the astrologer's 11-17 / 11-19 self-choice rules pending her
confirmation.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-22 03:29:47 +08:00
ClaudeandClaude Opus 5.5 2cbd520542 fix(report): 依据与边界 keeps the evidence moved out of the body (BUG-2145)
Round 28: the section failed its repair on fact_with_inference and fell back
to a computed text that only said 「所需依据已算出」, so the planets, signs,
houses and periods BUG-2143 moved there were lost.

- writer rule (contract G-17): this section is fact paragraphs, no inference
  words; the repair note names the words; the last pass drops inferring
  clauses of a fact paragraph like reader wording (salvage reason
  fact_with_inference)
- computed 依据与边界 lists the chart evidence per theme (sign, house, lord,
  dignity, D10/D2/D9, A10/AmK/UL/DK, health lords, Badhaka, current and next
  period to the month), only audit rows with content, birth-scenario limits
  only for an uncertain time (BUG-2141), packed into the stored 4 paragraphs
- chat 判断依据: drop 「只是条件性窗口」「只作当年结构」 tails and 「本轮只解释到…」,
  「本轮未交付」 → 「这次没有展开」; numbers kept (655 answers, 46 lines → 0)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-22 03:28:57 +08:00
ClaudeandClaude Opus 5.5 1e09ea5a0f fix(report): reading body says what a planet means in life, not which houses it rules; two or three turning points at month precision (BUG-2143)
Independent Staging Quality Gate / validate-python (push) Successful in 10m13s
Independent Staging Quality Gate / validate-frontend (push) Successful in 13m41s
Independent Staging Quality Gate / publish (push) Successful in 3m33s
Owner 2026-11-22: 「木星管第五宫和第八宫,落在第八宫自己的星座」 every one or two sentences and runs of
exact days made the reading unreadable. The report rules now keep house numbers and exact days in
「依据与边界」 (evidence moved, not deleted; the skill's evidence-first is the working order), 「现在这几年」
covers the current and the next period linked by cause, and the in-report questions take the same
plain terms. New reader-wording checks house_mechanics and date_density go to the one repair; the
last pass drops house clauses and shortens dates to the month.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-22 01:28:13 +08:00
ClaudeandClaude Opus 5.5 ed09962d2b fix(report): trust an entered minute unless marked uncertain; no per-section birth-time line; one opening note for uncertain times (BUG-2141)
Independent Staging Quality Gate / validate-python (push) Successful in 10m0s
Independent Staging Quality Gate / validate-frontend (push) Successful in 13m34s
Independent Staging Quality Gate / publish (push) Successful in 3m28s
Owner 2026-11-22 「同意」: users saw 「本节关于……尚未作比较。」 at the end of almost every
section, because every time not confirmed in 生时纠正 was trial-read at ±30 minutes.

- birth-time-trust.ts: uncertain = source approximate / period_only / unknown, record kind
  approximate / derived, 「说不准」, or a declared range > 0 (same declaration the rectification
  page reads). Everything else is read as entered: personal report confirmed_minute, annual
  report ±1 confirmed_minute (was known:false → ±30).
- No section line in the writer, computed fallback or annual sections; stored lines are taken
  out on the page, export and question material (依据与边界 keeps its own limit sentence); the
  opening clause and appendix mark about birth time are gone.
- Uncertain and not settled in 生时纠正: one opening sentence with a /rectification link
  (page and export, personal and annual); 「按你提供的出生时间,」 on dated conclusions and the
  question-material lead only in that case.
- Contract R-04 / §AM rewritten, notice G-15; annual writing rule and both chat rules updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-22 01:05:19 +08:00
ClaudeandClaude Opus 5.5 e8e358213d fix(chat): answers and their judgment basis name no books, authors, tables or pages (BUG-2133)
Independent Staging Quality Gate / validate-python (push) Successful in 10m1s
Independent Staging Quality Gate / validate-frontend (push) Successful in 13m17s
Independent Staging Quality Gate / publish (push) Successful in 3m10s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-21 20:02:05 +08:00
ClaudeandClaude Opus 5.5 0658bfd02d fix(yoga): quarantine the house-based Aasraya rules and the unsourced 70% threshold; progeny effects no longer promise a time or an outcome (BUG-2128)
Astrologer's Yoga manual 2026-11-21, P0. asraya_partial and asraya_yoga are
disabled with an accuracy note (ids kept); Aasraya proper stays as
Rajju/Musala/Nala. Two Kaalanirdesat progeny rules get conditional Chinese and
English effects. Topics file rebuilt; enabled count 408 -> 406.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
2026-11-21 19:36:15 +08:00
ClaudeandClaude Opus 5.5 450150c975 fix(report): the model-written report names no books, authors, tables or pages (BUG-2130)
The reading facts gave the writer 「PVR 表 30」 as the functional-profile label and
Narayana readings with page and table citations; the annual material and its
program-written notes named author versions and table numbers. Facts now carry
plain labels (ids kept), every report writer and in-report answer gets one
no-citation clause, the reading and the answers are checked, and stored text
loses its citations where it is shown.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-21 19:16:37 +08:00
ClaudeandClaude Opus 5.5 6135ae2f36 feat(report): the current period lords' connection paths reach the reading as an index (BUG-2126)
Independent Staging Quality Gate / validate-frontend (push) Successful in 6m25s
Independent Staging Quality Gate / validate-python (push) Successful in 7m42s
Independent Staging Quality Gate / publish (push) Successful in 3m13s
The reading facts gain timing.period_connections from jyotisha-20's indirect_activation (BUG-2121): per
house only the matched paths, their lords and levels, and one fact line; built even when the data
chapters were not rendered. The writer rule and the question instruction call it an index, not an
activation verdict; the eight body sections hold back 激活 / 引动 / 被点亮 / 被触发.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-21 16:23:50 +08:00
ClaudeandClaude Opus 5.5 977023b86c fix(report): a section failing only on reader wording keeps its other sentences; the birth-time condition is put in by the program (BUG-2117)
Independent Staging Quality Gate / validate-frontend (push) Successful in 6m24s
Independent Staging Quality Gate / validate-python (push) Successful in 7m38s
Independent Staging Quality Gate / publish (push) Successful in 3m21s
Round twenty-four: 「事业」 and 「感情」 fell back to three bare computed lines. A section
was sent back with its first reason only; the repair fixed that one and the dated
sentence without its birth-time condition survived. The condition is now inserted by
the program, the repair note names every reader-wording rule, and after the repair a
section failing only on reader wording drops the offending sentences and keeps the
rest when at least 60% and two sentences stay. Also: richer computed 事业/感情, the
basis rule names the Narayana, witness and same-fact fields, report scenario note and
annual Bhrigu note in the 11-21 wording, and a claim about every planet's strength is
unsupported when the material lists one below the line.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-21 11:26:25 +08:00
ClaudeandClaude Opus 5.5 a205a5b5fe fix(report): the birth-time line names the affected themes; dated conclusions carry the condition; no over-strong dignity wording (BUG-2112)
Independent Staging Quality Gate / validate-frontend (push) Successful in 6m20s
Independent Staging Quality Gate / validate-python (push) Successful in 7m33s
Independent Staging Quality Gate / publish (push) Successful in 3m36s
Per the astrologer's 2026-11-21 review (items 1 and 2): one line per
section in her wording, naming only the affected claim types; a dated
conclusion in an affected paragraph says it is by the chosen birth time;
question material keeps the line; stored readings show the new line;
dignity is never mapped to 施展不开 / 最能发挥 / 问题已经消失.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-21 08:17:21 +08:00
ClaudeandClaude Opus 5.5 41c1fc3ccd fix: normal readings never calibrate on the user's past events (BUG-2111)
The astrologer (2026-11-21) ruled that ordinary readings and forecasts never
use the user's experiences or feedback; only the rectification flow may.
Her reference files still told the model to back-calculate the user's known
events first, stop predicting below 3/5 matches, and grade A by such
verification. Until she edits them upstream, a product layer cuts those
passages out of every text sent to a model: the personal reading's quoted
references, the chat's methodology excerpts, and every chat prompt before
it reaches the provider (covering skill_read). The files are not edited;
a test names any rule that stops matching once she changes them.

Grade A no longer asks for a historical back-test. The status
user_history_verification_required is no longer a gap: no verification
questions, no penalty in ranking, never shown as 「需要过往经历核对」, not
offered to the report or synastry writers. 「未见阻断项」 is caught in the
reading and in report-question answers. Contract §AU announces the layer.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-21 08:16:42 +08:00
ClaudeandClaude Opus 5.5 7ca1e9cc4d fix(report): the reading drops 「只作参考」 hedges, draws no life verdict from strength, and says the other-scenario line once per section (BUG-2101)
Independent Staging Quality Gate / validate-frontend (push) Successful in 6m14s
Independent Staging Quality Gate / validate-python (push) Successful in 7m34s
Independent Staging Quality Gate / publish (push) Successful in 3m28s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-20 21:32:26 +08:00
ClaudeandClaude Opus 5.5 0d638bc788 fix(report): the reading's sections for readers name no techniques; names stay in 依据与边界 (BUG-2098)
The personal report reading wrote UL, 入庙, 小运, 婚姻煞 and the like in the
sections written for ordinary readers. Owner 2026-11-20: the body uses plain
words, technique names stay in 「依据与边界」 and the data chapters.

- Rules (product contract, report-reading block, notice G-9): the eight
  sections take the chat's PLAIN_TERMS and time-naming rule; dignity is judged
  from dignity_zh but told by its meaning; 「现在这几年」 gives dates and the
  ruling planet, no dasha names, no Narayana; names only in 「依据与边界」.
- Check: technique_name, after every fact check, through the existing one
  section repair; a writer's own plain gloss next to a name is kept instead.
  A section held back for a name still counts toward the draft length, so the
  draft stays usable and reaches the repair.
- Computed fallback text uses plain labels and drops the Narayana paragraph.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-20 20:42:52 +08:00
ClaudeandClaude Fable 5.2 2245b163f4 fix(yoga): Rohini gana is Manushya; the engine keeps distinct instances and records executed conditions; 19 rules name their participants (BUG-2075)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2Vp62Ur3C7yRWQdSq
2026-11-20 15:45:51 +08:00
ClaudeandClaude Opus 5.5 c9ab5ec53c fix: plain wording for unchanged trial ranges and 「情景」 in the paragraph-end birth-time line (BUG-2055)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
2026-11-20 11:51:49 +08:00
ClaudeandClaude Fable 5.2 fba5955ea0 fix: annual timing row folds into the basis, timeline and labels read plainly; date spacing and synastry summary wording (BUG-2043)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m38s
Independent Staging Quality Gate / validate-python (push) Successful in 7m9s
Independent Staging Quality Gate / publish (push) Successful in 4m27s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 22:16:19 +08:00
ClaudeandClaude Fable 5.2 bffb516ea4 docs: the annual reader-layer contract section is AS (AR is the report leftovers section)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m34s
Independent Staging Quality Gate / validate-python (push) Successful in 7m9s
Independent Staging Quality Gate / publish (push) Successful in 3m23s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 19:59:38 +08:00
ClaudeandClaude Fable 5.2 7e92d7d621 fix(annual): the annual report reads the chosen birth range, keeps sections when a divisional ascendant changes, and speaks everyday words (BUG-2037)
- a range chosen in rectification is the range the annual report reads (same source as the personal report and chat)
- a divisional ascendant changing inside the checked range no longer caps the conclusion type at D; the first rated item of that section carries the plain birth-time line
- D2 Hora candidates no longer make the wealth ceiling unreadable
- writing rules: technique, numbers and status go to the folded basis; body text in everyday words, no disclaimers; a reader wording pass after the checks
- the basis folds under the text on the page and follows it in the export
- a planet on its own natal position is a return
- basis length caps 600/800 -> 1000; a rewrite logs section id and check codes

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 19:59:27 +08:00
ClaudeandClaude Fable 5.2 af2e4988e8 fix: report and synastry reader text loses its last backstage wording (BUG-2038)
A pronoun whose planet was in a removed sentence takes that planet; only a planet
back in its natal sign is given to the reading; the 现在这几年 section leads with
the stage of life and dates only the main dasha; the health reminder is one fixed
program sentence; the synastry appendix no longer doubles 所以 and shows the
technical summary with names, no machine tags, minutes as 分 and 秒.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 19:49:28 +08:00
ClaudeandClaude Fable 5.2 def4c986bb fix: plain advice, plain distances and dates, no grade letters in the annual report, named people in synastry analysis (BUG-2034)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m31s
Independent Staging Quality Gate / validate-python (push) Successful in 7m0s
Independent Staging Quality Gate / publish (push) Successful in 3m34s
Reader-layer leftovers from the round-eight staging retest (astrologer's
2026-11-19 layering rule; owner's no-hedging rule).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 18:29:42 +08:00
ClaudeandClaude Fable 5.2 7fdaa1775a fix: the Moon's always-true branch alone no longer cancels a debilitation (BUG-2027)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m36s
Independent Staging Quality Gate / validate-python (push) Successful in 7m1s
Independent Staging Quality Gate / publish (push) Successful in 3m27s
Astrologer 2026-11-19, answer to question 17. Two flags per condition: witness_is_reference
(the Moon in the 1st from the Moon, true for every chart) and witness_is_debilitated_planet
(Mercury as its own witness, a real position condition that still counts). A planet that hits
only the always-true branch keeps the label 落陷, gets no row or cancel relation and is never
the basis of a Raja Yoga candidate; the literal hit stays in backstage evidence (literal_only).
This is the product policy neecha_bhanga_policy_v1; the raw rule version stays light_on_life_p295.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 17:07:34 +08:00
ClaudeandClaude Fable 5.2 70c5198146 fix(report): readers see everyday words, not grade letters, vargas or seconds (BUG-2028)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 16:59:16 +08:00
ClaudeandClaude Fable 5.2 b92741fe54 fix: synastry readers get one plain sentence when no event has a timing basis; scan periods and system gaps stay backstage (BUG-2029)
Astrologer 2026-11-19, layering rule and Q19. The page and export drop the
exploratory block; the appendix and stored rows use her sentences and keep
the four no-period states apart; the follow-up no longer volunteers scan
periods or reads system gaps out as missing data.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 16:59:16 +08:00
ClaudeandClaude Fable 5.2 d3bbd5cb86 docs: the contract refers to the yoga candidate status text instead of quoting it (BUG-2024)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m45s
Independent Staging Quality Gate / validate-python (push) Successful in 7m10s
Independent Staging Quality Gate / publish (push) Successful in 3m27s
The single-table test allows that text only in yoga-status-words.ts.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 16:14:28 +08:00
ClaudeandClaude Fable 5.2 7c84a8860f fix(report): facts carry plain fact sentences, a cancelled debilitation reads as conditions met, and rendered yoga text no longer names the reference library (BUG-2024)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 16:03:37 +08:00
ClaudeandClaude Fable 5.2 8dd72709db fix(report): the reading says a slow planet is back in its natal sign and names Saturn's house from the Moon; one node name in the export; status words in reader wording; wealth may cite AL's 2nd and 11th (BUG-2021)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m48s
Independent Staging Quality Gate / validate-python (push) Successful in 7m9s
Independent Staging Quality Gate / publish (push) Successful in 3m29s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 14:51:25 +08:00
ClaudeandClaude Fable 5.2 97a46ac748 fix: synastry follow-up gets both Moon nakshatras, house-label and scan-period notes; event states and the appendix read in reader words (BUG-2022)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m45s
Independent Staging Quality Gate / validate-python (push) Successful in 7m10s
Independent Staging Quality Gate / publish (push) Successful in 3m39s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 14:28:18 +08:00
ClaudeandClaude Fable 5.2 b01f3ce870 fix(report): an unsupported reference drops its sentence, not the section; Ashtakavarga is auxiliary outside career and wealth (BUG-2019)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m38s
Independent Staging Quality Gate / validate-python (push) Successful in 7m54s
Independent Staging Quality Gate / publish (push) Successful in 3m21s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 13:12:06 +08:00
ClaudeandClaude Fable 5.2 96d7d8dfc3 fix(report): grades move from under every paragraph to one opening statement and a folded appendix; ordinary limits are said once (BUG-2015)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 13:11:48 +08:00
ClaudeandClaude Fable 5.2 2b3113abc5 fix: Neecha Bhanga has one named default rule read by both the planet label and the main detector (BUG-2012)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 13:11:48 +08:00
ClaudeandClaude Fable 5.2 0e70378c81 fix(report): a varga ascendant near a sign change no longer blanks a section; paragraphs that use it say the other scenario is not evaluated (BUG-2013)
Independent Staging Quality Gate / validate-python (push) Successful in 9m33s
Independent Staging Quality Gate / validate-frontend (push) Successful in 12m21s
Independent Staging Quality Gate / publish (push) Successful in 3m22s
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 12:40:27 +08:00
ClaudeandClaude Fable 5.2 db098419aa fix: synastry scan-only periods move to a collapsed exploratory block; one verification line; 罗睺 / 计都 throughout (BUG-2014)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-19 12:40:27 +08:00
CodexandClaude 6f2e0a9ed7 feat: add natal sign comparisons to consultation transit facts (BUG-1995)
Independent Staging Quality Gate / validate-python (push) Successful in 10m4s
Independent Staging Quality Gate / validate-frontend (push) Successful in 12m38s
Independent Staging Quality Gate / publish (push) Successful in 3m13s
2026-11-18 23:42:42 +08:00
ClaudeandClaude Opus 5.5 c8da0a5efa fix: Neecha Bhanga judged per planet keeps one row, id and cancels edge per planet (BUG-1988)
The main detector forms a cancellation for each debilitated planet with the same name and
rule_id. The detected-list merge, the route sieve and the yoga layer each treated the second
planet as a repeat, so Einstein's Moon kept its status label but lost its row, id and edge.
Per-object rules now dedupe by (rule_id, planet): instance key and evidence id name the planet.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-18 19:01:19 +08:00
ClaudeandClaude Opus 5.5 33210e240a feat: wealth pack states each named-rule cancellation as one analysis sentence; staging turns the pack on by code (BUG-1987)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m52s
Independent Staging Quality Gate / validate-python (push) Successful in 7m14s
Independent Staging Quality Gate / publish (push) Successful in 3m10s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-18 18:19:56 +08:00
ClaudeandClaude Opus 5.5 e9e5fb207f feat: wealth evidence pack behind a staging switch, with named-rule cancellations and full dependency closure (BUG-1985)
Independent Staging Quality Gate / validate-frontend (push) Successful in 6m17s
Independent Staging Quality Gate / validate-python (push) Successful in 8m14s
Independent Staging Quality Gate / publish (push) Successful in 3m40s
Evidence-pack step 2, one-topic vertical slice (owner 2026-11-18; the astrologer's 11-18
review §二.4–二.6, §三 questions 1 and 3, §六 step 2).

- The evidence base gains the one relation the data states with a named rule: the Neecha
  Bhanga main detector cancels the debilitation effect of its planet (the placement stays),
  and depends on the witnesses it cites. No weakens edge: there is no named rule for one.
- lib/evidence-pack.ts builds the wealth pack from the card's own indexed facts: direct
  evidence; limits (cancellations with their witnesses, engine-stated yoga reductions,
  coexisting pressure); time (only when the question asks about time, range from the
  question); gaps and disagreements. The dependency closure follows every level with a
  visited set, cycle record and budget; a stopped walk is a visible gap.
- CONSULT_EVIDENCE_PACK_DOMAINS (default off; wealth on staging only) swaps the wealth key
  block for the pack; off, the model view is byte-identical. The time scope comes from the
  split question, never from user feedback (test E).
- The backtest harness reads a whole facts packet; timing.horizon is registered as non-fact.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-18 17:30:50 +08:00
ClaudeandClaude Opus 5.5 a4d6a5cf83 feat: every citable fact on the chat card resolves to an evidence id through a compact evidence index (BUG-1982)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m51s
Independent Staging Quality Gate / validate-python (push) Successful in 7m23s
Independent Staging Quality Gate / publish (push) Successful in 4m27s
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
2026-11-18 16:23:02 +08:00
ClaudeandClaude Opus 5.5 dd4eab82df fix: evidence ids name objects not values; snapshot v2 with subject, profile and times; four status fields; evidenced edges; dependency closure (BUG-1978)
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
2026-11-18 16:22:52 +08:00
ClaudeandClaude Opus 5.5 a26f990557 feat: readings see only the split-out question and answers written from it; feedback-only turns restate the last reading (BUG-1980)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m45s
Independent Staging Quality Gate / validate-python (push) Successful in 7m13s
Independent Staging Quality Gate / publish (push) Successful in 3m21s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
2026-11-18 15:10:43 +08:00
ClaudeandClaude Opus 5.5 8c1564dfff feat: stable evidence ids and a snapshot id across the chat card and report facts (BUG-1976)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m41s
Independent Staging Quality Gate / validate-python (push) Successful in 7m13s
Independent Staging Quality Gate / publish (push) Successful in 3m15s
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
2026-11-18 14:37:42 +08:00
ClaudeandClaude Opus 5.5 ab400951c2 fix: what users say happened stays background in chat; only 生时纠正 uses it (BUG-1977)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m47s
Independent Staging Quality Gate / validate-python (push) Successful in 7m23s
Independent Staging Quality Gate / publish (push) Successful in 3m31s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
2026-11-18 12:59:09 +08:00
ClaudeandClaude Opus 5.5 43ed8e484b fix: yoga card selection follows the astrologer's 11-18 ruling: per-domain recall houses, rule-level topic map, reasons kept, dependencies attached, four fields, reconcilable counts, paged and per-rule lookup (BUG-1975)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m42s
Independent Staging Quality Gate / validate-python (push) Successful in 7m32s
Independent Staging Quality Gate / publish (push) Successful in 3m8s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-18 12:32:51 +08:00
ClaudeandClaude Opus 5.5 f3c8c6a10c fix: basis English words go to the rewrite, numeric keys keep their label, the rewrite call gets its own thinking budget (BUG-1972)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m37s
Independent Staging Quality Gate / validate-python (push) Successful in 7m20s
Independent Staging Quality Gate / publish (push) Successful in 3m13s
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-18 11:32:06 +08:00
ClaudeandClaude Opus 5.5 c553bd6e7d fix: internal-word check catches rule states and key: true fragments; wealth line relates AL houses to natal houses (BUG-1970)
Independent Staging Quality Gate / validate-frontend (push) Failing after 4m18s
Independent Staging Quality Gate / validate-python (push) Successful in 8m0s
Independent Staging Quality Gate / publish (push) Skipped
(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
2026-11-18 09:56:55 +08:00
ClaudeandClaude Opus 5.5 45ec5974de feat: AL / UL derived houses and Pranapada branch across the birth window (BUG-1969)
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
2026-11-18 09:52:40 +08:00
ClaudeandClaude Opus 5.5 9625325b9a fix: UL's 2nd is main evidence only for questions about a marriage lasting (BUG-1968)
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
2026-11-18 09:25:48 +08:00
ClaudeandClaude Opus 5.5 b86030ab71 feat: yoga card rows carry rule ids and states, chosen by domain instead of the first 30 (BUG-1967)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m30s
Independent Staging Quality Gate / validate-python (push) Successful in 10m21s
Independent Staging Quality Gate / publish (push) Successful in 3m53s
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
2026-11-18 00:49:13 +08:00
ClaudeandClaude Opus 5.5 ef23f4642f feat: AL's 2nd / 11th and UL's 2nd are derived on the chat card (BUG-1965)
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m34s
Independent Staging Quality Gate / validate-python (push) Successful in 10m20s
Independent Staging Quality Gate / publish (push) Successful in 3m31s
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
2026-11-17 23:40:26 +08:00
ClaudeandClaude Opus 5.5 9d7a17a1a5 fix: chat card, annual D2 and remedies follow the astrologer's second-batch rulings (BUG-1964)
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
2026-11-17 23:40:26 +08:00