Career significator and house-lord rows now carry one presentation sentence. Values stay the same. A second three-repeat biography run still has one field conflict, so this is not accepted.
Not pushed.
The career checklist now says the direction section only covers strength, resistance, timing, and three events. Warm builds one packet per cache key and skips when its own cap is full.
A three-repeat biography run still has one career answer that names a direction from a planet nature, so this is not accepted. Not pushed.
The career checklist now says significators are only for strength and affliction. Chart-save warm no longer takes a heavy-compute slot.
Biography severe conflicts fell from 3 to 1. One career answer still names a direction from a planet nature, so this is not accepted for merge. Not pushed.
The cache key now includes the request date, and files older than two days are removed. The model card keeps values only. Parashari aspects are copied from the engine. Saving a chart warms the packet without blocking the response.
Biography severe conflicts rose from 1 to 3, so this is not accepted for merge. Not pushed.
Dialogue cards now take numbers from the same packet as the full-data report. Each of the twelve domains gets one table the card builder assembles. Lookups allow three calls a turn. further_reading is a per-domain technique index. BUG-1293, BUG-1294, BUG-1295.
The frozen comparison put an engine-default (Raman) native chart next to a
LAHIRI PyJHora chart, so half of every recorded difference was ayanamsa.
Both the freezer and the test now pass ayanamsa_name=lahiri; the fixture and
the progress diff table are regenerated. Report code is unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Add the interpretation pages from fields the engine already computed, project the annual tables the reader prints, and clear English Han on the four measured charts. Patyayini is not implemented. The generate button copy is unchanged.
This commit stays on the feature branch and is not pushed to staging.
Generate the full-data edition (pl9_personal_long_report.v4) and remove the reader edition. English still contains Han, so the API withholds it (BUG-1272, investigating). This commit is not pushed to staging.
The nutation branch left the quick gate red: eight expectations still encoded
the mean-ayanamsa frame (dasha boundaries two days late, a solar-return frame
gap that was the bug itself, a 0.01 Kala drift from frozen sidereal fixtures)
and three goldens were never regenerated. Python full suite is back to the
baseline list; quick gate passes.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
The 77-case eval exited 0. Prior top-1 fell 1.3 points on all three radii, and the online-interval plus-or-minus 30 cell fell 5.2 points. Scoring stays untuned and the branch stays unpushed.
The quick gate finished with four pytest failures. Two memoization failures were the placeholder commit seen by that process; the current tree passes those tests. The double-transit golden still matches the pre-nutation degrees and is not regenerated. The v5 prior cells already dropped 1.3 points, so this branch stays unpushed.
Production images do not install PyJHora, so those eight points were blocked.
Swiss Ephemeris now computes them in-process. Rectification keeps the old
Hora and Ghati formulas.
BUG-1273.
fb8277bf left the quick gate red: the native scan golden still carried the
pre-PVR D5/D11 signs, and the user-invocation contract still expected the
antardasha start laid from the day-truncated mahadasha date. Both values now
come from the real engine; Python full suite is back to the 62-failure
baseline, quick gate passes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
TASK-rectification-in-chat-step1-20261006, direct execution.
- The homepage 生时校正 pill and the text trigger (isRectificationHandoffQuestion)
are gone. The consult agent decides (RECTIFICATION_OFFER_RULE, one
definition) and calls offer-birth-time-rectification; the server decides
whether a card may show (self, product on, no case in progress,
feature_pricing price). The offer is stored with the answer and travels on
run.completed; the card hangs under that answer.
- Opening from the card binds the offer to the case in the consultation's own
messages (no table change); GET/POST /api/rectification/cases/[caseId]/source
find the source and go back: one divider (time changed or not), earlier
answers captioned 按校正前的时间, and a 按新时间重新看 button that sends only
when clicked. Auto-return after the post-adopt check or a terminal case, only
for work done in this view.
- Model history skips the divider and notes answers written with the old time.
Full suite 4987 / fail 24, identical to 6ec8efd5 (4973 / 24), no test name
lost; tsc 0; lint 0 errors; build keeps / Static, first-load gzip +0.20%.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
About 30 fixed rectification lines lose the receipt tone: no 「已记录。」
openings (收到 when the range holds, 好 when it moves), 麻烦 instead of 请,
时间 instead of 候选 in what the user reads, and no 「新建对话」 after
adoption. Numbers, clocks, ranges and the honesty boundaries are unchanged.
CHOICE_ACK_RE also recognises the new acknowledgements, so a model sentence
that repeats one is still dropped; the delivery guard matches the delivery
sentence by containment and does not depend on the opening.
Full suite 4973 / fail 24, identical to 61d6f248; build keeps / Static.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Both rectification prompts now share RECTIFICATION_VOICE_HEAD, the same warm
voice as the consultation answer (no mind-reading here: these turns collect
facts). Opening and read-only turns used to send the whole bound Skill (11,812
characters for 10.0.33); they now send the sections they act on, plus the
product-identity section when the bound Skill has it. 9.0.0 still goes out
whole (BUG-621). Rule bodies, scoring, cards and adoption are unchanged.
Opening input 7,433 -> 3,892 tokens in a DeepSeek replay. Full suite 4970 /
fail 24, identical to c76fdda7; build keeps / Static.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
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
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.
