thefux 3e906605a0 fix: strict rate-limit detection, probe non-escalation, distinct error codes ...

Fixes three issues that caused per-mint rate-limit state to never recover:

1. _is_mint_rate_limited: remove substring matching on 'rate limit' /
   'too many requests' in exception messages.  Only HTTP 429
   (httpx.HTTPStatusError) is now classified as a rate limit, preventing
   false positives (e.g. a 503 with 'database rate exceeded' in its body).

2. _run_probe: use apply_cooldown() instead of apply_rate_limit_cooldown()
   when a probe fails due to a rate limit.  The probe is a recovery check,
   not a new request, so it should not escalate the exponential backoff
   counter (_consecutive_rate_limits).  This prevents the cooldown from
   ratcheting 60s → 120s → 240s → ... → 7h on repeated probe failures.

3. classify_redemption_error: split the combined _is_mint_rate_limited ||
   is_mint_connection_error check into two separate classifications:
   - mint_rate_limited / cashu_mint_rate_limited (503, retryable)
   - mint_unreachable / cashu_mint_unreachable (503, retryable)
   Callers (routstrd) can now distinguish temporary rate limits from
   permanent connection failures when deciding fallback strategy.

Tests: 20 new tests covering strict 429 detection, classification
priority, probe non-escalation, and cooldown reset behaviour.

2026-07-18 14:34:42 +00:00

..

integration

make trusted mint available for lightning topup

2026-07-14 21:59:43 +02:00

unit

fix: strict rate-limit detection, probe non-escalation, distinct error codes

2026-07-18 14:34:42 +00:00

run_integration.py

dump wip stash

2025-08-06 20:31:55 -03:00