yex

devplacepy/services/openai_gateway/service.py

@@ -11,7 +11,7 @@ from fastapi.responses import JSONResponse
 
 from devplacepy.database import get_int_setting
 from devplacepy.services.base import BaseService, ConfigField
-from devplacepy.services.openai_gateway import config
+from devplacepy.services.openai_gateway import config, quota
 from devplacepy.services.openai_gateway.analytics import summary_metrics
 from devplacepy.services.openai_gateway.gateway import GatewayRuntime
 from devplacepy.services.openai_gateway.routing import model_store
@@ -262,6 +262,58 @@ class GatewayService(BaseService):
             "with this key. Clear it and restart to rotate.",
             group="Access",
         ),
+        ConfigField(
+            quota.FIELD_DEFAULT_USER,
+            "Default per-user daily cap ($)",
+            type="float",
+            default=1.0,
+            minimum=0,
+            help="Rolling 24h cap applied to a signed-in member with no matching quota rule. "
+            "0 = unlimited. Overridable per user/app-reference on /admin/gateway.",
+            group="Quota",
+        ),
+        ConfigField(
+            quota.FIELD_DEFAULT_ADMIN,
+            "Default per-admin daily cap ($)",
+            type="float",
+            default=0.0,
+            minimum=0,
+            help="Rolling 24h cap applied to an administrator with no matching quota rule. "
+            "0 = unlimited (the default - admins are exempt unless a rule says otherwise).",
+            group="Quota",
+        ),
+        ConfigField(
+            quota.FIELD_DEFAULT_GUEST,
+            "Default per-guest daily cap ($)",
+            type="float",
+            default=0.05,
+            minimum=0,
+            help="Rolling 24h cap applied to an unauthenticated caller with no matching quota "
+            "rule (only reachable when authentication is not required). 0 = unlimited.",
+            group="Quota",
+        ),
+        ConfigField(
+            quota.FIELD_DEFAULT_INTERNAL,
+            "Default per-internal-key daily cap ($)",
+            type="float",
+            default=0.0,
+            minimum=0,
+            help="Rolling 24h cap applied to calls authenticated with the auto-generated internal "
+            "key (DevPlace's own services: news, bots, Devii guests, correction/modifier). "
+            "0 = unlimited (the default - do not cap this without a matching quota rule, or "
+            "internal platform traffic will start failing).",
+            group="Quota",
+        ),
+        ConfigField(
+            quota.FIELD_DEFAULT_KEY,
+            "Default per-access-key daily cap ($)",
+            type="float",
+            default=0.0,
+            minimum=0,
+            help="Rolling 24h cap applied to calls authenticated with the static access key. "
+            "0 = unlimited by default (it is an admin-provisioned trusted secret).",
+            group="Quota",
+        ),
         ConfigField(
             "gateway_price_cache_hit_per_m",
             "Chat price cache-hit / 1M ($)",
@@ -463,6 +515,37 @@ class GatewayService(BaseService):
             return (kind, user.get("uid") or "unknown")
         return ("anonymous", "anonymous")
 
+    def _audit_quota_exceeded(
+        self,
+        owner_kind: str,
+        owner_id: str,
+        app_reference: str,
+        spent: float,
+        limit: float,
+        rule,
+    ) -> None:
+        from devplacepy.services.audit import record as audit
+        from devplacepy.services.openai_gateway.usage import audit_actor_for
+
+        actor_kind, actor_uid, actor_role = audit_actor_for(owner_kind, owner_id)
+        audit.record_system(
+            "ai.quota.exceeded",
+            actor_kind=actor_kind,
+            actor_uid=actor_uid,
+            actor_role=actor_role,
+            origin="api",
+            result="denied",
+            summary=f"AI gateway call by {owner_kind}/{owner_id} blocked - 24h quota reached",
+            metadata={
+                "owner_kind": owner_kind,
+                "owner_id": owner_id,
+                "app_reference": app_reference,
+                "spent_usd": round(spent, 6),
+                "limit_usd": limit,
+                "rule_uid": rule.uid if rule else None,
+            },
+        )
+
     def _models_response(self) -> JSONResponse:
         created = int(time.time())
         seen: set = set()
@@ -501,6 +584,17 @@ class GatewayService(BaseService):
         )
         if subpath == "models" and request.method == "GET":
             return self._models_response()
+        limit, scope, rule = quota.resolve(owner[0], owner[1], app_reference, cfg)
+        if limit > 0:
+            spent = quota.spent_24h(*scope)
+            if spent >= limit:
+                self.log(
+                    f"Rejected {owner[0]}:{owner[1]} app={app_reference}: "
+                    f"quota exceeded (${spent:.4f}/${limit:.4f}"
+                    f"{' rule ' + rule.uid if rule else ' default'})"
+                )
+                self._audit_quota_exceeded(owner[0], owner[1], app_reference, spent, limit, rule)
+                raise HTTPException(status_code=429, detail="AI gateway daily quota exceeded")
         if subpath == "chat/completions" and request.method == "POST":
             try:
                 body = await request.json()