Owner 2026-11-21: after BUG-2115 the full-data report still printed source
lines and book references (Goel 出处 line, the PVR 2014 article in the
conditional-dasha note, PVR / Light on Life / BPHS verse in the calculation
notes, Tithi lord table source, rashi-dasha 出处 lines, Narayana p.43 label and
p.50 / Table 13 direction notes, functional profile source row, Ashtakavarga
book calibration). Method names stay; the book, page, chapter and ruling round
go. Engine labels for the consultation card are unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
A host-side systemd timer (04:45 Asia/Shanghai) makes sure a restore-verified
daily backup exists (running the existing recovery script in daily mode when the
Gitea workflow did not), then uploads it with an OSS V1 signature computed in
the script, Content-MD5 and an ETag check. Secrets never reach argv or output.
Failures write a marker and alert through the existing Feishu monitor.
Not installed on the production host.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
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
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
A security-definer function, gated by support.quality.read and granted to
admin_runtime only, returns per report the reading's section statuses and
the transform log without any reading text; the admin page 报告写作记录
lists sections, reasons, repair, salvage and fallback per report.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Annual clock captions no longer end with "this report's native calculation";
the general dasha reference drops its per-lord study-notes citation; the birth
data section translates user_reported / family_exact and the other stored codes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
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
The annual method data shows only its numbers and clock facts; the research
chapter says "reference algorithm"; KP and Sade Sati describe the ephemeris
without naming Swiss Ephemeris. Reader leak checks now cover the whole report.
BUG-2055/2058/2063/2064/2074/2079/2090/2102 marked resolved after the owner's
staging walkthrough.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXp2U3BH1SxwAGyhhbe1
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
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
Rules sharing an English name printed each other's Chinese name in the reading
facts; each row now takes its engine row's name_cn by rule id. Neecha Bhanga rows
carry the fallen planet and the cancellation witnesses as two roles in the data
chapters' words. Narayana's direction readings are read from the report packet
when BUG-2105 stores them, and skipped otherwise.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
After BUG-2100 merged the supplementary timing chapters, one chapter holds up to
~505k characters and a question read only its first 20k. A chapter over 12k
characters is now read as its lead, a list of its ### parts by id
(chapter_<n>_<k>), then parts from the top; a part can be read by its id, and a
passage selected in a long chapter is read from the part that holds it. Cut
material ends with a mark the model is told about. The TOC timing pattern gains
年运 and Timing so 「年运附表」 and "Additional timing calculations" match their
other-language twins.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
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
At 1100 px with the sidebar open and the question panel closed the left
contents kept their 240 px column and the text was 461 wide. BUG-2093
folded them only while the side panel was open, and never on reports
that take no questions. The report view now measures its own layout box
(which keeps its width whether the column shows or not) and folds the
contents into their 「目录」 button whenever 240 + 48 + 520 do not fit,
on every report; the phone pill still takes over at 860 and below. The
reader keeps its place across the change; the place helpers move to
lib/personal-report-toc-layout.ts and are shared with the panel wiring.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
The writer was told to put 「只作参考」 into each section's basis and saw
the grade cap in its material, so stored annual reports showed
「这一块等级上限为 C」 and dozens of 「只作参考」 to readers. A shared
display pass (annualBasisText) now removes those notes on the page, in
the export and in what the question feature reads, keeping every date,
house, sign, number and technique name; stored reports are untouched.
New reports are written and stored without them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
The self-hosted data client accepts only plain column names in a select; the
JSON-path alias added for the personal report's subject name threw and the
route answered 500 for every personal, annual and synastry report. The name is
now read from the report document only when a personal report's conversation
is first created. A test scans every literal select in the app.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
A personal report generated from now on keeps the calculation facts its reading was written
from (one server-owned section row, bound to the reading's facts hash) and takes questions
beside the report, as the annual and pair reports do. Older reports show no entries.
- material: each reading section with the facts it is about, written as plain lines the answer
check can read; data chapters and the eight tables on demand; 20,000-character budget
- the annual turn is shared (runReportQuestionTurn); the consult route hands a bound
conversation to the personal or the annual handler by the report's own row
- page: entries beside the nine sections and each data chapter, selectable prose, the page
entry in the title bar, quotes that turn to their chapter; the reader keeps its place when
the panel opens or closes
- layout: contents on the left; with the panel open they fold into 「目录」 at the text's top
left when the window cannot hold contents, 520 of text and the panel
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Staging retest round twenty-one: an annual answer copied 大运 / 小运 / 细运
and the writer's 「两套计时…说法一致」 note from the saved basis lines, and
another drew 「这副担子加得是实的」 from 「八分力三、总分三十」. Both now go to
the existing reword round; the instruction line says not to draw weight
from a number; whole note sentences with no date, number or house are left
out of what the model reads.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
Pair follow-ups: 他 / 她 / 乙方 for one of the two goes to the one reword round with
both names, and a stored name with a space is written back as stored. Annual
questions: a birth-time limit or a minimum-line verdict the material read does not
make goes to the reword round, and an unsupported birth-time sentence never reaches
the reader; one instruction line says so. Asking about a selected passage makes its
section the current one on both report pages.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8