Zareian
42783f9ba4
Tutor (prompt tutor-v3-stepwise-plain): plain text instead of LaTeX/markdown, with rag/services/mathtext.py converting whatever still slips through; full step-by-step solutions with a check before the final answer; three tones by grade; the last 6 messages of the conversation go to the model and follow-ups are no longer served from another user's cache; book solutions the checker disputes are kept out of the context; a questionId gives the tutor the practice question and the student's wrong answer. /api/health reports when the AI credit runs out. rag_model_benchmark compares chat models on verified book problems (run on the server; credit ran out mid-run). Map: only lessons that have questions count toward finishing an island, lessonIds[0] / nextLessonId is always the next lesson to play, and a finished island stays finished. The Seyar characters (sigma/delta/pi) are seeded. Audit fixes, each reproduced before fixing: - the plan is stored on the order, so paying a monthly order after starting a yearly checkout no longer grants a year - opening checkout no longer demotes an active subscription; renewals extend from the current expiry; expired subscriptions are not reported active - one discount code per order and only before the gateway; a 100% code completes the purchase; lost Zarinpal confirmations are re-verified - the unused /api/payment/webhook "mark paid" endpoint is removed - XP counts only answers recorded on the server - 6-digit OTP, each code dies after 5 wrong guesses; POST /api/auth/logout - a guest who signs up keeps their account and progress (test phones excluded) - affiliate commission on the first real payment; guests excluded - parents with several children no longer get a 500 - SQLite runs transactions IMMEDIATE, since it ignores select_for_update - admin login is rate-limited; display names drop phone numbers and links; userQuestion is capped at 2000 characters - server-side heart enforcement exists behind HEARTS_ENFORCED (off until the frontend handles 403 no_hearts) Not done on purpose: rotating the server's secret key and moving to Postgres. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
75 lines
3.1 KiB
Python
75 lines
3.1 KiB
Python
"""
|
||
کلاینت‌های OpenAI و Qdrant به‌صورتِ lazy (نه در سطحِ ماژول).
|
||
|
||
مخزنِ Rag_backend این‌ها رو موقعِ import می‌ساخت؛ نتیجه این بود که بدونِ
|
||
کلید/شبکه، خودِ import هم crash می‌کرد. اینجا کلاینت فقط وقتی واقعاً لازم
|
||
بشه ساخته می‌شه و بینِ فراخوانی‌ها cache می‌مونه.
|
||
"""
|
||
from functools import lru_cache
|
||
|
||
from django.conf import settings
|
||
|
||
|
||
class RagNotConfigured(RuntimeError):
|
||
"""کلید/کتابخانه‌ی لازم برای مسیرِ RAG موجود نیست."""
|
||
|
||
|
||
@lru_cache(maxsize=1)
|
||
def get_openai_client():
|
||
if not settings.OPENAI_API_KEY:
|
||
raise RagNotConfigured('OPENAI_API_KEY تنظیم نشده است.')
|
||
try:
|
||
from openai import OpenAI
|
||
except ModuleNotFoundError as exc:
|
||
raise RagNotConfigured('پکیجِ openai نصب نیست (pip install -r requirements.txt).') from exc
|
||
|
||
return OpenAI(
|
||
base_url=settings.OPENAI_BASE_URL,
|
||
api_key=settings.OPENAI_API_KEY,
|
||
timeout=settings.OPENAI_TIMEOUT_SECONDS,
|
||
)
|
||
|
||
|
||
@lru_cache(maxsize=1)
|
||
def get_qdrant_client():
|
||
if not settings.QDRANT_API_KEY:
|
||
raise RagNotConfigured('QDRANT_API_KEY تنظیم نشده است.')
|
||
try:
|
||
from qdrant_client import QdrantClient
|
||
except ModuleNotFoundError as exc:
|
||
raise RagNotConfigured('پکیجِ qdrant-client نصب نیست (pip install -r requirements.txt).') from exc
|
||
|
||
# check_compatibility=False: کلاینتِ نصب‌شده (1.19) با سرورِ تیمِ دیگه
|
||
# (1.17) اختلافِ minor داره و کلاینت warning می‌ده؛ APIهایی که استفاده
|
||
# می‌کنیم (get_collections/upsert/query_points/scroll) پایدارن.
|
||
return QdrantClient(
|
||
url=settings.QDRANT_URL,
|
||
api_key=settings.QDRANT_API_KEY,
|
||
check_compatibility=False,
|
||
timeout=settings.QDRANT_TIMEOUT_SECONDS,
|
||
)
|
||
|
||
|
||
def is_account_limit(exc) -> bool:
|
||
"""
|
||
آیا این خطا یعنی «حسابِ سرویس دیگر جواب نمی‌دهد» یا فقط کندیِ لحظه‌ای؟
|
||
|
||
دو شکلِ واقعی که دیدیم و هر دو باید اجرا را متوقف کنند:
|
||
429 initial_usage_limit_exceeded — سقفِ حسابِ تازه، ساعت‌ها
|
||
403 insufficient user quota — اعتبار تمام شده
|
||
|
||
نکته: متنِ دومی «insufficient user quota» است با فاصله، نه زیرخط. محافظِ
|
||
اولِ ما دنبالِ `insufficient_quota` می‌گشت و نمی‌گرفتش، و اجرا ۷۷۰ فراخوانیِ
|
||
محکوم‌به‌شکست زد به‌جای اینکه سرِ اولی بایستد.
|
||
"""
|
||
text = str(exc).lower()
|
||
if 'usage_limit' in text or 'quota' in text:
|
||
return True
|
||
return '403' in text and 'insufficient' in text
|
||
|
||
|
||
def reset_clients_cache():
|
||
"""برای تست‌ها / بعد از تغییرِ settings در زمانِ اجرا."""
|
||
get_openai_client.cache_clear()
|
||
get_qdrant_client.cache_clear()
|