common, server : use the same User-Agent by default (#18957)

This commit also ensures that if a custom User-Agent is used, it will be
the only one sent.

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

common/common.h

@@ -57,6 +57,8 @@ extern const char * LLAMA_COMMIT;
 extern const char * LLAMA_COMPILER;
 extern const char * LLAMA_BUILD_TARGET;
 
+const static std::string build_info("b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT);
+
 struct common_control_vector_load_info;
 
 //

common/download.cpp

@@ -323,14 +323,17 @@ static int common_download_file_single_online(const std::string & url,
 
     auto [cli, parts] = common_http_client(url);
 
-    httplib::Headers default_headers = {{"User-Agent", "llama-cpp"}};
+    httplib::Headers headers;
-    if (!bearer_token.empty()) {
-        default_headers.insert({"Authorization", "Bearer " + bearer_token});
-    }
     for (const auto & h : custom_headers) {
-        default_headers.emplace(h.first, h.second);
+        headers.emplace(h.first, h.second);
     }
-    cli.set_default_headers(default_headers);
+    if (headers.find("User-Agent") == headers.end()) {
+        headers.emplace("User-Agent", "llama-cpp/" + build_info);
+    }
+    if (!bearer_token.empty()) {
+        headers.emplace("Authorization", "Bearer " + bearer_token);
+    }
+    cli.set_default_headers(headers);
 
     const bool file_exists = std::filesystem::exists(path);
 
@@ -437,10 +440,12 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string
                                                              const common_remote_params & params) {
     auto [cli, parts] = common_http_client(url);
 
-    httplib::Headers headers = {{"User-Agent", "llama-cpp"}};
+    httplib::Headers headers;
-
+    for (const auto & h : params.headers) {
-    for (const auto & header : params.headers) {
+        headers.emplace(h.first, h.second);
-        headers.emplace(header.first, header.second);
+    }
+    if (headers.find("User-Agent") == headers.end()) {
+        headers.emplace("User-Agent", "llama-cpp/" + build_info);
     }
 
     if (params.timeout > 0) {

tools/server/server-common.cpp

@@ -779,7 +779,6 @@ static void handle_media(
         // download remote image
         // TODO @ngxson : maybe make these params configurable
         common_remote_params params;
-        params.headers.push_back({"User-Agent", "llama.cpp/" + build_info});
         params.max_size = 1024 * 1024 * 10; // 10MB
         params.timeout  = 10; // seconds
         SRV_INF("downloading image from '%s'\n", url.c_str());

tools/server/server-common.h

@@ -13,8 +13,6 @@
 #include <vector>
 #include <cinttypes>
 
-const static std::string build_info("b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT);
-
 using json = nlohmann::ordered_json;
 
 #define SLT_INF(slot, fmt, ...) LOG_INF("slot %12.*s: id %2d | task %d | " fmt, 12, __func__, (slot).id, ((slot).task ? (slot).task->id : -1), __VA_ARGS__)