chore: 从汽车AI客服项目拷贝骨架并清理(blog页/redis)

Co-Authored-By: Claude Code <noreply@anthropic.com>

app/services/rate_limit.py

@@ -0,0 +1,39 @@
+"""Minimal in-memory rate limiter (per (ip, device_id), rolling 1h window).
+
+Mirrors hesu's rate_limit.py shape. Only the chat message route uses this;
+session/history endpoints are cheap and not throttled. State is process-local
+and resets on restart, which is acceptable for a single-worker ai-kefu deploy.
+
+Caveats:
+- Single-process, in-memory. Under `uvicorn --workers >1` each worker keeps
+  its own `_buckets`, so the effective cap is `max_requests * workers`.
+- Keyed on (ip, device_id); a client rotating the `X-Device-Id` header per
+  request bypasses it. This is a light safeguard against accidental GLM-cost
+  burn, NOT abuse-proof.
+"""
+import time
+from collections import defaultdict
+
+_buckets: dict[tuple[str, str], list[float]] = defaultdict(list)
+WINDOW = 3600
+DEFAULT_MAX = 30
+
+
+def check(
+    ip: str | None,
+    device_id: str | None,
+    *,
+    max_requests: int = DEFAULT_MAX,
+) -> bool:
+    """Return True if the request is under the cap (and record it), else False."""
+    key = (ip or "", device_id or "")
+    now = time.time()
+    _buckets[key] = [t for t in _buckets[key] if t > now - WINDOW]
+    if len(_buckets[key]) >= max_requests:
+        return False
+    _buckets[key].append(now)
+    return True
+
+
+def _reset_for_test() -> None:
+    _buckets.clear()