Files
Jyotisha/docs/research
Jesse_ChenandClaude Fable 5 ce1939b074 docs(tasks): 星盘页与 VedAstro 外网调用脱钩 + 运行期真相两单
星盘页首屏那一发 /api/chart 没传 skip_vedastro_main_entry_overview,
本机实测冷算 0.40–0.66 秒里约 0.36 秒是 VedAstro 空转(连 endpoint 都
没配的情况下);带标志的同一调用是 5 毫秒。生产 env 开着 network 与
fanout,等于首屏同步等 24 个外部请求加 3 次领域扫描,而前端 mapper 与
contract 根本不读这份证据。BUG-718,复发自 BUG-161。

运行期单记录两条新发现:官方 vedastro==1.23.25 其实是 REST 客户端,
且 import 时请求 pypi 并 pip install --upgrade 自升级(实测 pin 装完
一 import 即变 1.23.26);无 key 时免费层排队是同步 sleep 加进程级
全局锁,24 个请求约 4.8 分钟堵住前台线程。台账补 ERR-107 / ERR-108,
生产 env 核对清单交产品负责人执行。

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0155nFCgCHtoA7jhSDGmZmMu
2026-09-15 15:47:32 +00:00
..

Research Workspace

This directory stores research notes, audits, benchmark packets, and active adjudicator iteration records for the Jyotish project.

Layout

  • active/
    • reserved for current working research fronts that directly support the next implementation cycle
  • archive/
    • historical round notes, sidecar work orders, and local draft research that should not clutter normal implementation work
  • top-level docs/research/*.md
    • current canonical research notes that are still referenced by active engineering work

What Stays Top-Level

Keep a research file at the top level only if at least one of the following is true:

  • it is referenced by an active implementation spec
  • it is referenced by tests, workflow docs, or benchmark dashboards
  • it captures a currently active adjudicator audit or closure board

What Moves To Archive

Move a research file into archive/ when:

  • it is a completed round log or sidecar work order
  • it is a local exploration draft with no active code dependency
  • it is superseded by a newer audit, dashboard, or implementation note

Current Working Rule

When adding new research notes:

  1. put active, decision-driving notes at the top level
  2. move noisy round-by-round drafts into archive/
  3. avoid storing transient terminal captures or scratch outputs here