feat(ratelimit): env-tunable per-IP auth limiter budgets

Add RATELIMIT_OTC_REQUEST_MAX / RATELIMIT_VERIFY_MAX / RATELIMIT_CHECK_MAX
(default to the existing secure values; non-positive/unparseable → default).
Lets a test/PPE stack that drives the auth endpoints repeatedly from one IP
lift the budget; production leaves them unset. Mirrors the existing
OTC_REQUEST_COOLDOWN_SECONDS knob.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/app/ratelimit.py

@@ -19,11 +19,27 @@ lockouts). Both layers run together.
 """
 from __future__ import annotations
 
+import os
 import threading
 import time
 from collections import defaultdict, deque
 
 
+def _max_events(env_name: str, default: int) -> int:
+    """Per-limiter budget, overridable via env (e.g. a test/PPE stack that
+    drives the auth endpoints repeatedly from one IP). Production leaves these
+    unset and gets the secure defaults below. A non-positive / unparseable
+    value falls back to the default."""
+    raw = os.environ.get(env_name, "").strip()
+    if not raw:
+        return default
+    try:
+        n = int(raw)
+    except ValueError:
+        return default
+    return n if n > 0 else default
+
+
 class SlidingWindowLimiter:
     """Allow at most `max_events` per `window_seconds` per key.
 
@@ -66,12 +82,15 @@ class SlidingWindowLimiter:
 #   * verify: 10 attempts / 5 min / IP across the auth verify surfaces.
 #   * otc request: 5 sends / 5 min / IP (Turnstile is the primary gate;
 #     this is defense in depth against a solved-challenge replay loop).
-verify_limiter = SlidingWindowLimiter(max_events=10, window_seconds=300)
-otc_request_limiter = SlidingWindowLimiter(max_events=5, window_seconds=300)
+verify_limiter = SlidingWindowLimiter(
+    max_events=_max_events("RATELIMIT_VERIFY_MAX", 10), window_seconds=300)
+otc_request_limiter = SlidingWindowLimiter(
+    max_events=_max_events("RATELIMIT_OTC_REQUEST_MAX", 5), window_seconds=300)
 # /auth/passcode/check is an anonymous has-passcode oracle (audit 0026 L3).
 # It's a legitimate Login-flow affordance, so the budget is generous —
 # enough for a human typing emails, tight enough to stop bulk scraping.
-check_limiter = SlidingWindowLimiter(max_events=30, window_seconds=300)
+check_limiter = SlidingWindowLimiter(
+    max_events=_max_events("RATELIMIT_CHECK_MAX", 30), window_seconds=300)
 
 
 def _reset_all_for_tests() -> None:

backend/tests/test_ratelimit_env.py

@@ -0,0 +1,44 @@
+"""The per-IP limiter budgets are env-overridable (test/PPE stacks drive the
+auth endpoints repeatedly from one IP); production leaves them unset and keeps
+the secure defaults. A non-positive / unparseable value falls back."""
+from __future__ import annotations
+
+import importlib
+
+import pytest
+
+
+def _reload_with(monkeypatch, **env):
+    for k, v in env.items():
+        if v is None:
+            monkeypatch.delenv(k, raising=False)
+        else:
+            monkeypatch.setenv(k, v)
+    import app.ratelimit as ratelimit
+    return importlib.reload(ratelimit)
+
+
+@pytest.fixture(autouse=True)
+def _restore():
+    yield
+    # Leave the module in its default state for other tests.
+    import app.ratelimit as ratelimit
+    importlib.reload(ratelimit)
+
+
+def test_defaults_when_unset(monkeypatch):
+    rl = _reload_with(monkeypatch, RATELIMIT_OTC_REQUEST_MAX=None, RATELIMIT_VERIFY_MAX=None)
+    assert rl.otc_request_limiter.max_events == 5
+    assert rl.verify_limiter.max_events == 10
+
+
+def test_env_override(monkeypatch):
+    rl = _reload_with(monkeypatch, RATELIMIT_OTC_REQUEST_MAX="1000", RATELIMIT_VERIFY_MAX="250")
+    assert rl.otc_request_limiter.max_events == 1000
+    assert rl.verify_limiter.max_events == 250
+
+
+def test_bad_value_falls_back_to_default(monkeypatch):
+    rl = _reload_with(monkeypatch, RATELIMIT_OTC_REQUEST_MAX="nope", RATELIMIT_VERIFY_MAX="0")
+    assert rl.otc_request_limiter.max_events == 5   # unparseable → default
+    assert rl.verify_limiter.max_events == 10       # non-positive → default