The staging publish job built the web image without frontend/tests, and
next build type-checks every .ts under frontend/, so the harness importing
../tests/helpers/postgres-fixture.ts failed with TS2307. The harness depends
on the test fixture, so it now lives in frontend/tests/research; the Python
driver points there. A new test fails if src/ or scripts/ import tests/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Review-only snapshot for BUG-1115 through BUG-1117; not merge-ready. New opening and append-turn PostgreSQL permission failures remain blocked. Persisted joint replay has zero completed questions; segment ordering remains off by default. The existing offline replay JSON is retained stale and unchanged after a denied overwrite, including its CRLF line endings. Browser/provider validation and final serial gates remain pending. No deployment, role permission changes, or staging/main push.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Bundled media carry Next's per-deploy ?dpl= and were downloaded again after
every release. Bytes unchanged; /fonts/serif-sc/* is immutable. Overturns the
serif-headings contract line "bundled by Next, not served from public/"
per TASK-home-first-load-20260930 decision 2.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Archive research scripts, regression tests, M1 results and safe M0 smoke. Keep the incomplete study and failing quick gate explicit. Exclude full M0 JSON, raw logs and unrelated oracle newline changes.
Co-Authored-By: Claude Code <noreply@anthropic.com>
- /api/professional_report_reference accepts languages [zh,en]; one packet, zh
byte-identical, markdown_en + reader_dasha_applicability_en, or
english_unavailable when a Chinese character would leak.
- pl9_reader_english renders the parity volume with report_language=en and a
fixed term table; yoga_engine carries combination_en / effects_en / strength_en.
- 75 fictional charts: zero Han, same line count, same numbers outside yoga tables.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
yoga_rules.json gains effects_en for every rule and an _en sibling for each
Han-bearing string (combo_template, strength, source, accuracy_note); zh values
untouched. reader_dasha_applicability renders language='en' from the same
packet; the default zh output is byte-identical (pinned by sha256).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
Upstream yinduzhanxing 41d1c740 / 59c9139f, hand-merged; 089858c0 verified not applicable.
- solar_return: dt_local was the UT instant verbatim (no caller ever added the
offset). Localise with ZoneInfo at the return instant (IANA id) or the fixed
offset; expose annual_location; Sahams day/night at the true instant;
optional current_location return charts.
- cmd_solar_return / annual_tajika_pack / engine: pass birth IANA zone and
--solar-return-location-mode / --current-* through; external PyJHora
replay blocked when relocated.
- output_json keeps the upstream stream= signature; PL9 exports written
compact via dumps (measured faster than json.dump streaming), 9.57 -> 4.61 MB.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Once the discriminator training gate is open, only choice cards are asked
and the range card goes out when they are exhausted; targeted lines, their
re-ask and guided windows no longer hold the card or invite more events.
Delivery body says how many choice questions were used instead of the event
fit percent; narration names an excluded cluster instead of "range
unchanged"; a delivered turn no longer carries a collect question.
Offline replay (v4, 3 radii x 2 directions): truth in range 20/20 in every
cell; guided-window injections give the same width in truth and opposite
directions, so red line 1 was revised by product to truth-in-range only.
Skill 10.0.31 -> 10.0.32 (10.0.31 kept as deprecated for pinned cases).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
v4 open holdout, ±10/±30/±60, raw and percent priors: only 4/9/14 of 57
day-precision training events split candidates; widths unchanged, top-1
drops. Narrowed year blocking (R3) mixed. All arms no_benefit; no
implementation brief recommended. Two runs byte-identical.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Wording only: _quality_user_meaning names start/change/interruption as
升学/学业变动/学业中断; _display_date_label drops the stored month for
year-precision events. Split hash and month field unchanged; same-machine
A/B (PYTHONHASHSEED=0) differs only in user_meaning/display_date_label.
Re-frozen per ERR-110 under new quality_wording_2026_09_29 records;
sealed rerun (20) and reported-offset sweep (900) identical to 09-21.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Product decision A (TASK-birth-sky-followup-20260928):
- every generation path writes subject.birthFingerprint (stored-row
fingerprint, same function as the chart page's profileFingerprint);
never into the evidence bundle the model reads
- GET /api/reports/:id compares on the server and returns only
report.coverSubject (subject id or null); legacy reports never get one
- report page shows the night cover above the body, paper cover alone on
the first printed A4 page; silent on any failure, no waiting state
- TS / JSON schema / Python contract accept the optional field
- BLOCKED T5 struck through; DESIGN §17, CHANGELOG, checklist, PROGRESS
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE
T1 scripts/birth_sky.py: real alt/az of the seven visible grahas (swe.calc_ut +
swe.azalt, geometric altitude, azimuth converted from swe's south origin to
north-east) and Yale BSC5 stars V<=4.0 (IAU 1976 precession); phase
day / twilight_morning / twilight_evening / night. Thin POST /api/birth_sky
registration in do_POST (no new handler method, no __new__).
T2 GET /api/birth-sky?subject=: birth truth read server side through
loadSubjectBirth + prepareChartViewProfile; zod contract; no billing, no
writes, no birth data in the response.
T3/T4 lib/birth-sky: sentence table, pure Canvas 2D drawBirthSky (night /
paper palettes from DESIGN tokens, east on the left, serif headline with
1.5 s font wait), PNG export via navigator.share or Blob + a.download.
Chart page prefetches and paints the cover once the chart is ok; the header
button appears only when the PNG is ready. Dialog is a lazy chunk.
T7 DESIGN §17, VOICE, CONTEXT glossary, CHANGELOG, real-device checklist.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0199rbQDTsUbCVw84wc8BTFe
Renamed, sliced subset of Noto Serif SC SemiBold (OFL 1.1, noto-cjk
Serif2.003) covering the 6500 level-1 + level-2 characters of the
通用规范汉字表 plus Latin, punctuation and common symbols.
- scripts/fonts/build_serif_slices.py: fontTools subsetting into 30 woff2
slices + serif-sc.css (@font-face, weight 500 700, font-display swap);
byte-identical output for the same input.
- Frequency order (char_order.txt): repo corpus top 300, then Google
Fonts SC frequency bands (nam-files, Apache-2.0), then corpus count;
unranked characters sliced by contiguous code point.
- tests/test_serif_font_slices.py: coverage, no overlap, files exist,
120 KB cap; added to the quick quality gate.
TASK-serif-headings-20260928 T1.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0199rbQDTsUbCVw84wc8BTFe
Every D9 target name contains the "9" of "D9", so the digit comparison never
paired D1 N宫 with D9_N宫 and, for house 9, paired D1 9宫 with any D9 planet
target. Targets now carry structured metadata (layer/kind/house/planet); the
cross-layer loop pairs only the same house or targets that both point at the
D1 house-N lord. Target names and D1/D9/CL layer results are unchanged
(D1/CL golden regenerated byte-identical); 48 samples: cross entries 31 -> 38.
Evidence-card golden regenerated with the capture script.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
`cmd_double_transit_pac` placed the `D9_{N}宫` target on the D9 lagna sign
and the `D9_{lord}(宫主)` target on that planet's D1 longitude. Both now sit
on D9 signs (D9 house-N sign; the lord's navamsa sign), built in one
testable helper. Target names, D1 and Chandra Lagna layers are unchanged
(pre-fix golden, byte-identical). Evidence-card golden regenerated with the
capture script (one public chart: double-transit conclusions 9 -> 10).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
TASK-consult-evidence-card-v2-20260927 T3. Card version evidence-card-v2.
- Base section (every card): the engine's D9 summary (D9 lagna, each
planet's D9 sign and dignity, Vargottama, D1/D9 reversals); D9 houses and
aspects stay out.
- Career: + AL (engine pada A1), 10H SAV, SAV of the Jupiter / Saturn
transit signs.
- Marriage: + 5H / 5L, day / night, Punarphoo (observation_only), Double
Transit on 7H / 7L (house-7 run) and DK / UL, Vivah Saham, gender unknown.
- Wealth: 8H / 12H named.
- Annual: the annual Tajika chart verbatim (parameter_sensitive), or
年盘未接入 when the pack is blocked / not attached (never natal data);
houses 1 + running / next AD lords' houses + the year's Jupiter / Saturn
transit houses, with their basis; ingress / station dates only.
- Timing: Rahu / Ketu with ingress dates, Jupiter / Saturn SAV and BAV,
Double Transit conclusions (no degrees); vargas follow the turn's other
domain, D9 when alone.
- Chara Dasha leaves every card; KP is never on a card. The lookup enum adds
karakamsha, dispositor_chains, inter_chart_linkage, argala, moon_transit;
a KP lookup travels with its blocked note.
- System prompt and tool descriptions name the D9 summary, the
parameter_sensitive / observation_only tags, 年盘未接入 and the lookups.
- Telemetry card version / agentVersion bumped to v2 (three-column notes in
the touched tests).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
TASK-consult-evidence-card-v2-20260927 T1. New module
scripts/consultation_native_layers.py, thinly registered after the merged
engine fields in _attach_local_consultation_layers (no handler method, no new
forgery site). It writes one new top-level chart key,
chart.consultation_native_layers, kept out of chart.modules so the thematic
report's full_reading_module_count does not move:
- d9_summary: D9 lagna, each planet's D9 sign and dignity
(jyotish_engine._get_dignity_level), Vargottama (_calc_vargottama),
D1<->D9 reversals
- punarphoo (punarphoo.detect_punarphoo, observation_only)
- vivah_saham (jyotish_engine._calc_vivah_saham), day_night (gulika)
- slow_transits: Jupiter / Saturn / Rahu / Ketu now with natal house and the
Jupiter / Saturn SAV / BAV, and the next twelve months' ingress / station
dates (ephemeris_events; nodes by the same daily-noon sampling)
- double_transit: cmd_double_transit_pac for houses 1-12, conclusions only,
plus DK / UL targets by the same PAC rule
- karakamsha, argala, dispositor_chains, inter_chart_linkage, moon_transit
(lookup-only layers)
- annual_tajika on the annual route: build_annual_tajika_pack (annual lagna,
Varshesha, Muntha, Mudda Dasha with dates, Sun / Moon / year-lord Tajika
aspects), parameter_sensitive; blocked when the pack is not reliable,
never natal data
A/B on 3 public AA charts x 4 routes: every existing output is identical,
only the new key is added; about 40 ms per workflow. Golden regenerated with
annual and timing routes (family workflow byte-identical apart from the new
key).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
New frontend/src/lib/consultation-evidence-card.ts ports the research
CARD_SPECS: base section (ascendant, house signs, placements with degrees,
functional benefics/malefics with lordship, Vimshottari MD/AD/PD with dates,
Narayana md/ad/pd) plus a section per domain; values copied verbatim from
the projection or engine context, gaps listed, never filled. The tool now
returns toModelEvidenceView: status, evidence_contract (policy, blockers,
layers, limitation), claim_cards = the card, evidence_card meta (D4 line,
supplementable sections), rectification, methodology, domains; the audit
table, spectra, must_use_layers and presentation stay server-side and the
single-domain consultations copy is gone. 「本轮技法」 rows are unchanged.
Golden tests over three public AA engine captures.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
timingKeys now admits current_dasha.md/ad/pd (sign, lord, years,
start_age, end_age), remaining_years and pratyantar_dasha_timeline. Depth
and item caps unchanged. Golden regression over three public AA engine
captures asserts values, not key presence.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Gate run 2958 failed tests/test_api_server_growth_contract.py: the
evidence-card research script added two JyotishAPIHandler forgery sites.
Reuse capture_report_blocked_repairs_golden._handler(); output unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Measure the model-visible consultation payload on three public charts, draft per-domain cards, and record the Narayana/pratyantar projection gap as BUG-1054. No runtime behavior change.
- R1: flipping 1 answer keeps truth in range 98-100% but cuts head hit by
a third or more; 2 flips squeeze truth out in 7-10% of ±30/±60 replays
(two flips = 8 points = SEPARATION_LEAD).
- R2: weights do apply (research scorer == production at V0); V1/V2 are
identity at ±30/±60 by construction and leave six-question metrics
unchanged at ±10 -> no_benefit (measured). Supplementary V1n does not
pass the gate.
- R3: boundary shift is ~3.8 days/minute (1.3-5.9), not 1.1; the 45-day
gate is ~8-34 minutes. The _representative_pairs hypothesis is refuted
(all-pairs adds no dated probes); the bottleneck is monthly evaluation.
New finding recorded as BUG-1048 (investigating): _boundary_windows
year-straddle exemption and positional zip misalignment bypass the gate.
- Dated errata appended (no deletions) to the 09-14/09-16 briefs and
research docs; README board row -> 待验收. No production code, scoring,
thresholds, gates or Skill changed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
Validate on Linux Node 22 and PostgreSQL 17: 3894 frontend tests and 64 database tests pass, with no removed test names or new failures. Preserve static Home, bounded gzip, assertion-change records and manual acceptance gaps.
Co-Authored-By: Claude Code <noreply@anthropic.com>
New reports request reader_main from upstream origin/main 23b9609e.
KP and transit no longer copy an empty vars() dict, solar returns keep
birth_asc_sign_idx, and ordinary projection deletes internal lines whole.
Unify reader cleanup rules, lock writer table guards, and register the exact fictional timestamp collision. Preserve existing ordinary-report safety contracts and source-data gaps.
Validation: report Node 165/165, final safety 29/29, Python 101/101, Chrome 28/28; both PDFs retain all 130 rows. Full Node 3704 tests with the same 91 baseline failures. Privacy test: 62 passed, 1 failed due to 17 protected-file READ_ERRORs; not a green gate. Build, DB, manual checklist and controlled-login gaps remain documented. User explicitly authorized staging push with these gaps disclosed.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Carry explicit local date intervals instead of inferring the day from clock
order. Cluster width, delivery, adoption, and reports keep the actual civil
date; adopted date is stored separately from the reported birth_date.
Algorithm identity is scoring-9 / spec-v5. Scoring weights, confirmation
thresholds, and Skill version are unchanged. Isolated Linux final-3 gates
passed; four pre-existing Python failures remain. This is not a production
release.
Add date-isolated caches and regression coverage, align scoring identity, and freeze full research reruns while preserving historical artifacts. Record unresolved cache/receipt identity and end-to-end acceptance gaps for branch review only.
Co-Authored-By: Claude Code <noreply@anthropic.com>
