perf(hub-ai): reduce CPU load during trading coach chat

Cache chat context, parallelize exchange fetches, skip fund history writes, defer rolling summary to a background thread, and cache markdown rendering on the client. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-14 01:59:43 +08:00
parent 28a23008f3
commit 467d160f4d
5 changed files with 148 additions and 39 deletions
@@ -33,6 +33,7 @@ FUND_HISTORY_DAYS = 180
 CHAT_MAX_ATTACHMENTS = 3
 CHAT_MAX_IMAGE_BYTES = 4 * 1024 * 1024
 CHAT_MAX_TEXT_FILE_BYTES = 200 * 1024
+CHAT_CONTEXT_CACHE_TTL_SEC = _int_env("CHAT_CONTEXT_CACHE_TTL_SEC", 45)


 def trading_day_reset_hour() -> int: