fix(router): forward extra /sleep query params (level, mode) to upstream (#969)

Fixes #953.

`route_sleep_wakeup_request` consumed only the router-internal `id`
query parameter and dropped everything else, so `POST /sleep?id=X&level=2`
silently degraded to `level=1` because vLLM never saw `level=2`.
Same defect for `mode` on `/sleep` and `tags` on `/wake_up`.

Build a dict of all query params minus `id` and pass it as the aiohttp
`params=` argument to each upstream request. `id` is router-only (used
above to pick the target engine), so excluding it is correct.

Signed-off-by: HumphreySun98 <humphreysun98@gmail.com>
Co-authored-by: Rui Zhang <51696593+ruizhang0101@users.noreply.github.com>

Author: HumphreySun98

src/vllm_router/services/request_service/request.py

@@ -517,9 +517,11 @@ async def route_general_request(
     else:
         endpoints = list(
             filter(
-                lambda x: requested_model in x.model_names
-                and x.Id == request_endpoint
-                and not x.sleep,
+                lambda x: (
+                    requested_model in x.model_names
+                    and x.Id == request_endpoint
+                    and not x.sleep
+                ),
                 endpoints,
             )
         )
@@ -1064,21 +1066,32 @@ async def route_sleep_wakeup_request(
 
     url = server_url + endpoint
 
+    # Forward any additional query parameters (e.g. /sleep `level` and `mode`,
+    # /wake_up `tags`) to the upstream engine. `id` is router-only and is
+    # consumed above to pick the target engine.
+    upstream_params = {k: v for k, v in request.query_params.items() if k != "id"}
+
     async with aiohttp.ClientSession() as client:
         if endpoint == "/is_sleeping":
-            async with client.get(url, headers=headers) as response:
+            async with client.get(
+                url, headers=headers, params=upstream_params
+            ) as response:
                 response.raise_for_status()
                 return await response.json()
         else:
             request_body = await request.body()
             response_status = None
             if request_body:
                 req_data = json.loads(request_body)
-                async with client.post(url, json=req_data, headers=headers) as response:
+                async with client.post(
+                    url, json=req_data, headers=headers, params=upstream_params
+                ) as response:
                     response.raise_for_status()
                     response_status = response.status
             else:
-                async with client.post(url, headers=headers) as response:
+                async with client.post(
+                    url, headers=headers, params=upstream_params
+                ) as response:
                     response.raise_for_status()
                     response_status = response.status