feat: 服务层配置接线——email/push/rate_limit/AI凭据/行为开关/映射表/种子键

Task 9: 服务层对全局 settings 的业务引用清零,每个 DEFAULT_CONFIG 组
都有真实消费方。resolve_*_settings(email/push/ai)以空槽回退 env
(平台默认层);contact 行为开关/种子白名单/国名扩表/限流上限经
manager 的 runtime.config 接线。收口: lead_push session_factory 必填、
config.py 死代码清理、PromptProvider frozen、no_contact 视图直取、
AIService wall 参数定型 CompiledWall。403 测试全绿(389+14)。

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

app/engine/routes/chat_rest.py

@@ -8,7 +8,8 @@ Red lines (see spec):
 - WS path (`app/api/routes/chat.py`) shares `ConversationManager` with these
   routes; both paths stay drift-free.
 - `context` seeding is conditional + whitelist (handled in
-  `ConversationManager.create_conversation`).
+  `ConversationManager.create_conversation`; Task 9 起白名单 =
+  租户 config.engine.context_seed_keys——jiancai product_*/auto vehicle_*).
 - The message route consumes `stream_process_message`; lead email is
   triggered inside `ConversationManager` when contact info is detected
   (contact-driven-lead-email plan).
@@ -20,6 +21,7 @@ from sqlalchemy import select
 from app.engine.models import ConversationSource, ConversationStatus, Message
 from app.engine.routes.runtime import get_runtime
 from app.engine.services.conversation import ConversationManager
+from app.engine.services.rate_limit import DEFAULT_MAX
 from app.engine.services.rate_limit import check as rate_check
 
 router = APIRouter(prefix="/api/chat", tags=["chat-rest"])
@@ -111,15 +113,19 @@ async def chat_message(req: MessageRequest, request: Request):
     `ConversationManager` when contact info is detected
     (contact-driven-lead-email plan) — this route carries no email logic.
 
-    A light in-memory rate limit (per ip + X-Device-Id, 30/h) guards GLM
-    spend; only this route is throttled.
+    A light in-memory rate limit (per tenant + ip + X-Device-Id, rolling 1h)
+    guards GLM spend; only this route is throttled. Task 9: 桶键加租户维度
+    (两租户同出口 IP 不互挤配额),上限读租户 config.engine.rate_limit_per_hour
+    (默认 30,与出厂一致)。
     """
+    runtime = get_runtime(request)
     ip = request.client.host if request.client else ""
     dev = request.headers.get("X-Device-Id", "")
-    if not rate_check(ip, dev):
+    engine_cfg = runtime.config.data.get("engine") or {}
+    limit = engine_cfg.get("rate_limit_per_hour") or DEFAULT_MAX
+    if not rate_check(runtime.config.slug, ip, dev, max_requests=limit):
         raise HTTPException(status_code=429, detail="rate limit exceeded")
 
-    runtime = get_runtime(request)
     async with runtime.session_factory() as db:
         manager = ConversationManager(db, runtime=runtime)
         conv = await manager.get_by_session(req.session_id)