Host rehearsal no longer needs Node on the production machine, and a failed cleanup now stops with the rehearsal database name. Docs-only staging heads no longer block rollback. Tests no longer hardcode Windows paths, and a trailing slash on the production site still refuses the test code.
pytest 12 passed; tsc exit 0; lint 0 errors; identity tests 9 passed, 0 cancelled. test:db was not run.
Co-Authored-By: Grok (agent loop)
Cache work that depends only on the candidate minute, drop unread response fields, and reject windows above 241 candidates before any chart is built. Eleven canonical scenario hashes match 77057a819. Sealed and reported-offset replays match the 2026-10-08 records (changed_trial_count 8 and 581) and are stored as scoring_perf_2026_10_13.
Co-Authored-By: Grok (agent loop)
Docs-only conflict in BUG_HISTORY: BUG-1311 (#52) and BUG-1312..1315 (#53)
both appended after BUG-1310; kept both in number order. Product owner
chose option A on #53: Claude merges a stale branch when only docs conflict.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LutgzyJqNhPpZy1nFsJtN3
The inner textarea kept a 12px radius after its side padding was cleared, so the first character was cut into an arc. Only .composer textarea is now border-radius 0. The outer frame is unchanged.
Verified: chat-reading-load-mobile.test.ts was 7 pass / 1 fail before the CSS change, then 8 pass / 0 fail / 0 cancelled. tsc --noEmit exit 0. npm run lint 0 errors.
Co-Authored-By: Grok (agent loop)
New reports draw one north-Indian chart for each ready divisional in the body, so the trailing duplicate section drops. Chinese full-data prose no longer glues English onto Han or leaves listed, background, or native. The birth table starts with the ascendant. The D9 same-sign column says yes or no.
Self-test: tsc exit 0; npm run lint exit 0 (0 errors, 125 existing warnings); three frontend test files 39 pass, 0 fail, 0 cancelled; pytest test_report_chart_blank_columns.py 16 passed; seven related report files 88 passed, exit 0; privacy markers 63 passed.
Co-Authored-By: Grok (agent loop)
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.
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.
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
Since BUG-989 a new chat is saved on its first send, and that create already
carries the session's model. selectSessionModel still PATCHed the session
right away; with no row yet the route answered 404 and the composer showed
「云端同步失败」 although the local choice had taken effect. The selection now
returns before any PATCH for an unsaved empty consultation (same predicate as
the send path). Saved chats sync as before.
Full suite 4988 / fail 24, identical to 11333460; build keeps / Static.
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
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
