fix(llama-cpp): stage model load diagnostics

The generated gRPC source tree omitted the new header and test. Every llama.cpp-derived backend therefore failed when grpc-server.cpp included the missing header.

Assisted-by: Codex:gpt-5.6 [systematic-debugging]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

backend/cpp/llama-cpp/CMakeLists.txt

@@ -125,4 +125,9 @@ if(LLAMA_GRPC_BUILD_TESTS)
     target_include_directories(thread_params_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
     target_compile_features(thread_params_test PRIVATE cxx_std_17)
     add_test(NAME thread_params_test COMMAND thread_params_test)
+
+    add_executable(model_load_error_test model_load_error_test.cpp model_load_error.h)
+    target_include_directories(model_load_error_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
+    target_compile_features(model_load_error_test PRIVATE cxx_std_17)
+    add_test(NAME model_load_error_test COMMAND model_load_error_test)
 endif()

backend/cpp/llama-cpp/grpc-server.cpp

@@ -53,6 +53,7 @@
 #include "arg.h"
 #include "chat-auto-parser.h"
 #include "llama_compat.h" // fork-skew switches, generated by prepare.sh
+#include "model_load_error.h"
 #include "thread_params.h"
 #include "message_content.h"
 #include "passthrough_options.h"
@@ -1615,7 +1616,8 @@ public:
             {
                 std::lock_guard<std::mutex> lock(error_capture_data.error_mutex);
                 if (!error_capture_data.captured_error.empty()) {
-                    error_msg += ". Error: " + error_capture_data.captured_error;
+                    error_msg += ". Error: " +
+                                 localai::model_load_error_with_hint(error_capture_data.captured_error);
                 } else {
                     error_msg += ". Model file may not exist or be invalid.";
                 }

backend/cpp/llama-cpp/model_load_error.h

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <string>
+
+namespace localai {
+
+inline std::string model_load_error_with_hint(const std::string& error) {
+  const std::string mismatch = "wrong number of tensors; expected ";
+  const std::string got = ", got ";
+  const std::string::size_type mismatch_pos = error.find(mismatch);
+  if (mismatch_pos == std::string::npos ||
+      error.find(got, mismatch_pos + mismatch.size()) == std::string::npos) {
+    return error;
+  }
+
+  return error +
+         " Hint: the model may be incompatible with this llama.cpp backend "
+         "or the GGUF file may be corrupt. Try a newer compatible backend "
+         "and verify or re-download the model file.";
+}
+
+}  // namespace localai

backend/cpp/llama-cpp/model_load_error_test.cpp

@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: MIT
+
+#include "model_load_error.h"
+
+#include <cassert>
+#include <string>
+
+int main() {
+  const std::string issue_error =
+      "llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 2131, got 720; "
+      "llama_model_load_from_file_impl: failed to load model";
+  const std::string issue_result = localai::model_load_error_with_hint(issue_error);
+  assert(issue_result.compare(0, issue_error.size(), issue_error) == 0);
+  assert(issue_result.find("incompatible") != std::string::npos);
+  assert(issue_result.find("corrupt") != std::string::npos);
+
+  const std::string generic_error =
+      "wrong number of tensors; expected 42, got 17";
+  const std::string generic_result = localai::model_load_error_with_hint(generic_error);
+  assert(generic_result.compare(0, generic_error.size(), generic_error) == 0);
+  assert(generic_result.size() > generic_error.size());
+
+  const std::string unrelated_error = "failed to open GGUF file";
+  assert(localai::model_load_error_with_hint(unrelated_error) == unrelated_error);
+}

backend/cpp/llama-cpp/prepare.sh

@@ -21,6 +21,10 @@ done
 
 cp -r CMakeLists.txt llama.cpp/tools/grpc-server/
 cp -r grpc-server.cpp llama.cpp/tools/grpc-server/
+# Model-load diagnostics (included by grpc-server.cpp) and their standalone
+# regression test.
+cp -r model_load_error.h llama.cpp/tools/grpc-server/
+cp -r model_load_error_test.cpp llama.cpp/tools/grpc-server/
 # Shared message-reconstruction helpers (included by grpc-server.cpp) and their
 # unit test (compiled only when -DLLAMA_GRPC_BUILD_TESTS=ON).
 cp -r message_content.h llama.cpp/tools/grpc-server/