fix(llama-cpp): let parallel:1 in the model options win over LLAMACPP_PARALLEL (#12426)

The environment fallback was applied whenever n_parallel was still 1
after option parsing. An explicit `parallel: 1` in the model YAML is
indistinguishable from the default that way, so it was replaced by
LLAMACPP_PARALLEL. The docs say options in the YAML take precedence
over environment variables; a single model could not be forced to one
slot while the global variable was set.

Track whether the options set the slot count and resolve it in a small
helper (parallel_params.h): option first, then LLAMACPP_PARALLEL, then
1. The helper gets a standalone unit test picked up by
`make test-backend-cpp`.

Assisted-by: Claude:claude-opus-5-5

Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>

backend/cpp/llama-cpp/parallel_params.h

@@ -0,0 +1,25 @@
+#pragma once
+
+#include <optional>
+#include <string>
+
+namespace llama_grpc {
+
+// resolve_n_parallel picks the slot count. A value from the model options
+// always wins, including an explicit 1: the YAML takes precedence over the
+// environment, as documented. LLAMACPP_PARALLEL is only the fallback when
+// the options do not set it; a value that does not parse is ignored.
+inline int resolve_n_parallel(const std::optional<int>& from_options, const char* env, int fallback = 1) {
+    if (from_options) {
+        return *from_options;
+    }
+    if (env != nullptr) {
+        try {
+            return std::stoi(env);
+        } catch (const std::exception&) {
+        }
+    }
+    return fallback;
+}
+
+} // namespace llama_grpc