The method block bound into every chat turn quoted most of SKILL.md (benchmark
scores, CLI flags, oracle queues, file paths) plus the shared method, whose
output contract asks for JSON verdicts, A/B/C/D confidence, audit tables, raw
data and web verification - the opposite of the chat shape. Chat now quotes
only the truth-boundary sections and adds CHAT_METHOD_BOUNDARIES for the
limits from the dropped sections it still has to keep. SKILL.md and the shared
method file are unchanged for reports and skill_read.
Natal system prompt 55,242 -> 26,591 characters. DeepSeek A/B on public
golden charts (flash 10 questions): input 24,560 -> 14,025 tokens, 37.8 ->
30.3 s, no regression in automatic checks or reading; a high-rigor request
still says plainly that no external check was done. Full suite 4970 / fail
24, identical to b8385adb; build keeps / Static.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
The English shape summary sat in the system prompt four times (contract,
index, natal heading rule, skill skeleton) and the contract restated the
Chinese ANSWER SHAPE point by point. Keep the summary in the contract only and
drop the restatements; the Chinese ANSWER SHAPE stays the one full statement.
General answer-policy bullets no longer sit under the reference_transparency
header.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Product 2026-10-07: the answer voice becomes a knowing, gentle older sister,
matching the homepage greeting, and may read feelings: after the answer, one
sentence, with 可能 / 多半, never a guess stated as fact or a question
rewritten into a need; another person's feelings need chart evidence and only
on an unafflicted line (afflicted lines keep the range rule, BUG-1182).
Overturns the feelings part of BUG-1070.
Also removes rules that contradicted the answer shape: 'restate the same
constraint', the rectification 'say progress' line, 'answer concisely', and
'every time say what to do' (now only when things are hard).
Full suite 4969 / fail 24, identical to 52d14e8f; tsc 0; lint 0 errors;
build keeps / Static, first-load gzip unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
The slot wait was a fixed 5 minutes from the moment a file started queueing.
With 46 fixture files sharing 2 slots the queue outlasted that, so whichever
file came last failed the gate at random (runs 1742 and 1746). The deadline
now restarts whenever a slot changes hands; only 10 minutes with no slot
changing hands (a hung holder) fails. The 2-slot cap from BUG-281 stays.
Full suite 4967 / fail 24, identical to 171a3f25; tsc 0; lint 0 errors.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
BUG-1252: answer prose drops text-wrap: pretty. WebKit (every iPhone browser)
applies it to the whole paragraph, so lines came out evenly short with a blank
strip on the right and every streamed character re-broke the lines above.
BUG-1253: the condensed checklists and shared reading open with an
analysis-only note; PLAIN_SPEECH_RULE (one definition) tells the writer not to
quote layer names, signal counts, rules or house-counting, caps evidence in
brackets at two, and gives everyday words for card fields with no Chinese name
(no coined names like 合力星). Marriage layers become everyday wording; career,
wealth and health say not to announce layers.
Full suite 4966 / fail 24, identical to baseline d2c22ca2 (4962 / 24); build
keeps / Static; first-load gzip unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
The answered choice persists the acknowledgement, a blank line, and the
rewritten delivery. The exit fill-in required equality and wrote the
deterministic delivery again. Check containment instead, and pin it on the
real answer path. The suspected widen staleness regression did not hold;
keep a guard test.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Accept and GET now decide with the same birth snapshot as the answer, so an under-age probe cannot flip can_adopt. The exit skips a second write when this reply already delivered. The card stays without an adopt button when adoption is not allowed, and a refusal shows the Chinese sentence.
Acceptance fix for 28113fa0 (TASK-consult-conversational-answer-fix-20261006):
- F1: chat-answer-detail no longer pins 'Every H2 must start its own line'
(first turns carry no H2), assertion change noted in three columns.
- F2: Good examples separate paragraphs with a blank line and the shape says
so; .message p is pre-wrap, so a single newline only wraps.
- Product request: remove the assistant avatar on every surface (consult,
rectification, onboarding); --assistant-content-inset back to 0px.
Full suite 4941 / fail 24, identical to baseline 86cafe68 minus a timing flake;
build keeps / Static; first-load gzip -0.1%.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Ordinary consult first turns drop Markdown headings and the required
action list. People are named in the paragraph, and pinned examples no
longer contain copyable advice. BUG-1244, BUG-1245.
N1, N2, N3, and N5 do not pass. Switching ayanamsa moves level-5 lords and
equal-division D150 past the 20% wording line. Two full runs are byte-identical.
No production scoring change. closed_by_design.
Running the study as a file does not put scripts/ on sys.path, so the
production chart imports failed before any scoring. The library inserts
that directory itself. No rule or threshold changed.
Five-level Vimshottari and equal-division D150 helpers, plus a runner that
refuses to score until the preregistration file exists. First three lords
match the production chain on the v5 events. No production files changed.
Consult turns reuse a same-day official snapshot inside the rectification gate, or record deferred_in_consultation instead of starting another 4-second snapshot. Classification, step 0, step 1, and the time to the first answer character go into the existing usage metadata and a new admin usage column.
BUG-1231, BUG-1232
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>
The fictional chart's 2026 return moves 08:48:04 -> 08:41:55 (PyJHora within
0.09 min); the annual Lagna crosses from Taurus 1.3 to Aries 29.6 and the
current-year lord becomes Jupiter. Not in the quick gate, so the BUG-1220
acceptance missed it. Full Python suite: 62 failures before and after,
identical lists.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Round-6 ruling Q6b: Table 25 Gemini/Sagittarius and Virgo/Pisces are the
book software's seventh-level Rule 8 special case; keep the general result
(Sagittarius, Pisces at level 5), every Rath output carries the note
(known_book_differences), test pins the two pairs.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
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
Panchadhikari blocked -> status blocked + reason, year_lord None, sentence
「年主暂无法确定（原因）」 on card and report; Tri-Pataka blocked with it;
Mudda unchanged. Aligned with upstream 03bea6ed. Nine public charts: both
producers byte-identical before/after.
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: the annual Harsha / Panchavargiya strength
layer's Panchavargiya column is the same `_calc_native_panchavargiya_bala`
score the year-lord selection compares (BUG-1217): five components, score
out of 20, labelled 「Tajika 五分力量」 / "Tajika five-fold strength". The
unreachable dignity-proxy block is removed; Harsha Bala unchanged; the
combined figure stays blocked (not ruled).
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
The natal Sun target came from compute_chart_data while the solver iterates
on _get_sun_lon_jd (swe sidereal flags); the frames differ by up to ~17",
moving the return by up to ~7 minutes. The annual chart was also cast at the
truncated minute. Ports upstream yinduzhanxing 7cc6425d / 46ed9399 (these two
hunks only). PyJHora reference: 3 cases within 0.03 min. 243 public-figure
annual charts: annual Lagna changes 13, year lord 11, Mudda first lord 0.
v5 77 cases identical to 3c27c38e; consult goldens re-captured byte-identical.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
