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_test.cpp

@@ -0,0 +1,29 @@
+#include "parallel_params.h"
+
+#include <cstdio>
+
+int main() {
+    // parallel:1 in the model options must not be replaced by the environment.
+    if (llama_grpc::resolve_n_parallel(1, "4") != 1) {
+        std::fprintf(stderr, "explicit parallel:1 was overwritten by LLAMACPP_PARALLEL\n");
+        return 1;
+    }
+    if (llama_grpc::resolve_n_parallel(8, "4") != 8) {
+        std::fprintf(stderr, "explicit parallel was overwritten by LLAMACPP_PARALLEL\n");
+        return 1;
+    }
+    // Without an option the environment applies, otherwise the default.
+    if (llama_grpc::resolve_n_parallel(std::nullopt, "4") != 4) {
+        std::fprintf(stderr, "LLAMACPP_PARALLEL was not used as fallback\n");
+        return 1;
+    }
+    if (llama_grpc::resolve_n_parallel(std::nullopt, nullptr) != 1) {
+        std::fprintf(stderr, "default slot count is not 1\n");
+        return 1;
+    }
+    if (llama_grpc::resolve_n_parallel(std::nullopt, "many") != 1) {
+        std::fprintf(stderr, "unparsable LLAMACPP_PARALLEL was not ignored\n");
+        return 1;
+    }
+    return 0;
+}