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>
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
`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
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>
20 public AA cases, raman/mean. Lowering MIN_BOUNDARY_DAYS narrows ±10 from
15 to 11 minutes but drops top-1 0.80→0.75; wider radii get wider ranges.
Varga sensitivity weights (V1/V2) match production; D60 (V3) hurts ±10.
Day-precision events offset ±7 never squeeze the true minute out. Production
45/30 gate and equal varga weights stay unchanged.
Offline v4 holdout probe. Last round's width=window result was the
no-elimination metric; production still-valid ranges after six answers
are 15/33/56 minutes. Adjacent merge never fires under step-2 radii.
W1/W2 match baseline; W3 is uncertain after one coverage squeeze.
No production clustering or scoring defaults changed.
Build holdout v4 from the public AA set, correct the two v3 dates, and sweep
R1–R5 plus pairs offline. No production scoring defaults change. No
implementation brief: delivered width stays the full window on every radius.
Offline H1-H4 measurement on 20 public AA holdout cases.
Block unique top-1 did not rise; H4 made it worse; minute layer unchanged.
Leave production scoring untouched. Transits must not drive minute conclusions.
