docs: clarify ngx.sleep(0) is a workaround, link tracking issue #13256

Per review feedback, the comment now states explicitly that the yield
prevents one request from monopolizing the worker but does not bound
per-stream CPU time, add backpressure, or time out stalled streams.
A real fix is tracked in #13256.

Author: nic-6443

apisix/plugins/ai-providers/base.lua

@@ -362,11 +362,15 @@ function _M.parse_streaming_response(self, ctx, res, target_proto, converter)
             plugin.lua_response_filter(ctx, res.headers, chunk)
         end
 
-        -- Yield to the nginx scheduler so other coroutines on this worker
-        -- (health checks, concurrent requests) can run. body_reader() and
-        -- ngx.flush() do not yield when the upstream socket already has data
-        -- buffered or the downstream client drains immediately, so under
-        -- bursty SSE upstreams this loop can monopolize the worker CPU.
+        -- WORKAROUND, not a real fix: yield to the nginx scheduler so other
+        -- coroutines on this worker (health checks, concurrent requests) can
+        -- run. body_reader() and ngx.flush() do not yield when the upstream
+        -- socket already has data buffered or the downstream client drains
+        -- immediately, so under bursty SSE upstreams this loop can monopolize
+        -- the worker CPU. ngx.sleep(0) only prevents a single request from
+        -- monopolizing the worker; it does not bound per-stream CPU time, add
+        -- backpressure, or time out stalled streams. See #13256 for a proper
+        -- solution.
         ngx.sleep(0)
     end
 end