plain_persian() strips kasra/fatha/damma/shadda/sukun/hamza-above and the written «هی» ezafe, keeping tanwin. Applied
at output, not in data: PlainPersianJSONRenderer runs one byte-level pass over every JSON response (~5 ms per MB
locally), and to_plain() cleans tutor answers including the stream. Rewriting titles in the DB/seed would have broken
question binding by title path and SeedRecord keys. Tests updated to expect the cleaned text; config/tests_plain_persian.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Postgres here allows 60 connections, but each of the 96 gunicorn threads held its
own persistent one: at 100 concurrent users (local Postgres with the same limit)
21% of requests were 500 "remaining connection slots are reserved". Now each worker
has a psycopg pool (8), so the same load gives 0 errors and 714 req/s (was 460).
- A full pool answers 503 + Retry-After (DRF handler and middleware), not 500.
- The AI tutor and the OTP SMS call return their connection before the network wait.
- statement_timeout 30 s, idle-in-transaction 60 s; bad pool settings and the old
DB_CONN_MAX_AGE stop startup instead of failing every request.
- /api/health dbPool: per-worker pool stats and workers x pool + 6 vs max_connections.
- Indexes on the columns global counters filter by time (weekly leaderboard,
global SMS cap, global AI cap); the leaderboard recomputes once per expiry.
- Worker count moves into gunicorn.conf.py (4 on a shared 8-core box).
- security doc: Redis item closed (server uses our own Redis since 2026-10-08).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
