Commit Graph
6 Commits
Author SHA1 Message Date
ClaudeandClaude Opus 5.5 3e7388c37f feat(narayana): default to Sanjay Rath, keep the legacy algorithm as a labelled comparison (BUG-1601, #166 Q9)
Product decision 2026-11-04 on astrologer ruling #166 Q9. One builder,
narayana_legacy_label.product_narayana, makes the product Narayana object:
the Rath view on top (label "Sanjay Rath 版(默认;…)", seed sign, 24 MDs,
running MD / AD with remaining_years, the running MD's ADs) and the whole
labelled legacy result under `legacy`. When Rath cannot decide a start sign
the object says blocked in plain words; legacy never stands in.

- Consultation card: timing.narayana is Rath; the legacy running MD rides
  as a short timing.narayana_legacy; timing.narayana_rath is gone.
- Full reading / report: Rath block first, "- 对照:旧算法…" after; the
  parity chapter lists Rath (default), source-aware and legacy (comparison);
  dasha master pack Narayana periods are the Rath MDs.
- /api/dasha narayana: periods are Rath, legacy under `legacy`.
- Annual: Rath is the product timeline (used_by_product_timeline true),
  narayana_skeleton_profile "rath", legacy is the reference and never counts.
- CLI narayana-dasha prints Rath first, legacy as comparison.
- Consult full-data cache schema v2 -> v3 so old legacy-default packets miss.

Rectification scoring is untouched and still calls calc_narayana_mahadasha
(frozen identity). Evidence-card, biography and card-facts captures were
regenerated with their scripts; annual-report-facts.json was regenerated from
its endpoint function. Tests pinning legacy-as-default are rewritten with
原值/新值/原因.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-05 04:32:07 +08:00
Jesse_ChenandClaude Opus 5.5 18c6e13028 Consult card keeps parsed packets in memory, prewarms each turn, writes 0600 (issue #129, BUG-1476)
Independent Staging Quality Gate / publish (push) Canceled after 0s
Independent Staging Quality Gate / validate (push) Canceled after 11s
- consult_packet_view keeps the last 3 parsed packets with their shared domain
  base (~30 MB each). A hit reads no file and copies nothing: attach for one
  domain 0.106 s -> 0.002 s. Memory holds the file's JSON round trip, i.e.
  exactly what a hit returned before; consult_card_facts sha256 equal old/new.
- Cache files are created 0600, same bytes as before.
- The consult route fires a warm for the turn's chart before reserving credit,
  so the day's first question does not build the packet on the answer path.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 11:57:53 +08:00
jesse-uxandGrok (agent loop) 69c739fbee 个人长报告同盘同日重试改为秒回
完整数据版在版本号明确时复用当天的结果。渲染快捷算法留下但默认关闭,本机只快了大约两成。

Co-Authored-By: Grok (agent loop)
2026-10-14 06:37:40 +08:00
jesse-ux 85c3030e96 fix(consult): limit career direction and single-flight chart warm
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.
2026-10-09 15:53:51 +08:00
jesse-ux 16f9f86843 fix(consult): date the full-data cache and slim the model card
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.
2026-10-09 10:00:45 +08:00
jesse-ux 3874a328a5 feat(consult): copy the full-data packet into a per-domain judgment table
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.
2026-10-09 10:00:45 +08:00