common: support remote preset (#18520)

* arg: support remote preset

* proof reading

* allow one HF repo to point to multiple HF repos

* docs: mention about multiple GGUF use case

* correct clean_file_name

* download: also return HTTP status code

* fix case with cache file used

* fix --offline option

common/download.cpp

@@ -157,6 +157,10 @@ static std::string read_etag(const std::string & path) {
     return none;
 }
 
+static bool is_http_status_ok(int status) {
+    return status >= 200 && status < 400;
+}
+
 #ifdef LLAMA_USE_CURL
 
 //
@@ -306,12 +310,14 @@ static bool common_download_head(CURL *              curl,
 }
 
 // download one single file from remote URL to local path
-static bool common_download_file_single_online(const std::string & url,
+// returns status code or -1 on error
+static int common_download_file_single_online(const std::string & url,
                                                const std::string & path,
                                                const std::string & bearer_token,
                                                const common_header_list & custom_headers) {
     static const int max_attempts        = 3;
     static const int retry_delay_seconds = 2;
+
     for (int i = 0; i < max_attempts; ++i) {
         std::string etag;
 
@@ -371,7 +377,7 @@ static bool common_download_file_single_online(const std::string & url,
                 LOG_WRN("%s: deleting previous downloaded file: %s\n", __func__, path.c_str());
                 if (remove(path.c_str()) != 0) {
                     LOG_ERR("%s: unable to delete file: %s\n", __func__, path.c_str());
-                    return false;
+                    return -1;
                 }
             }
 
@@ -380,14 +386,14 @@ static bool common_download_file_single_online(const std::string & url,
                 if (std::filesystem::exists(path_temporary)) {
                     if (remove(path_temporary.c_str()) != 0) {
                         LOG_ERR("%s: unable to delete file: %s\n", __func__, path_temporary.c_str());
-                        return false;
+                        return -1;
                     }
                 }
 
                 if (std::filesystem::exists(path)) {
                     if (remove(path.c_str()) != 0) {
                         LOG_ERR("%s: unable to delete file: %s\n", __func__, path.c_str());
-                        return false;
+                        return -1;
                     }
                 }
             }
@@ -414,23 +420,27 @@ static bool common_download_file_single_online(const std::string & url,
 
             long http_code = 0;
             curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &http_code);
-            if (http_code < 200 || http_code >= 400) {
+
+            int status = static_cast<int>(http_code);
+            if (!is_http_status_ok(http_code)) {
                 LOG_ERR("%s: invalid http status code received: %ld\n", __func__, http_code);
-                return false;
+                return status; // TODO: maybe only return on certain codes
             }
 
             if (rename(path_temporary.c_str(), path.c_str()) != 0) {
                 LOG_ERR("%s: unable to rename file: %s to %s\n", __func__, path_temporary.c_str(), path.c_str());
-                return false;
+                return -1;
             }
+
+            return static_cast<int>(http_code);
         } else {
             LOG_INF("%s: using cached file: %s\n", __func__, path.c_str());
-        }
 
-        break;
+            return 304; // Not Modified - fake cached response
+        }
     }
 
-    return true;
+    return -1; // max attempts reached
 }
 
 std::pair<long, std::vector<char>> common_remote_get_content(const std::string & url, const common_remote_params & params) {
@@ -625,7 +635,8 @@ static bool common_pull_file(httplib::Client & cli,
 }
 
 // download one single file from remote URL to local path
-static bool common_download_file_single_online(const std::string & url,
+// returns status code or -1 on error
+static int common_download_file_single_online(const std::string & url,
                                                const std::string & path,
                                                const std::string & bearer_token,
                                                const common_header_list & custom_headers) {
@@ -659,8 +670,10 @@ static bool common_download_file_single_online(const std::string & url,
             LOG_WRN("%s: HEAD invalid http status code received: %d\n", __func__, head ? head->status : -1);
             if (file_exists) {
                 LOG_INF("%s: Using cached file (HEAD failed): %s\n", __func__, path.c_str());
-                return true;
+                return 304; // 304 Not Modified - fake cached response
             }
+            return head->status; // cannot use cached file, return raw status code
+            // TODO: maybe retry only on certain codes
         }
 
         std::string etag;
@@ -692,12 +705,12 @@ static bool common_download_file_single_online(const std::string & url,
         if (file_exists) {
             if (!should_download_from_scratch) {
                 LOG_INF("%s: using cached file: %s\n", __func__, path.c_str());
-                return true;
+                return 304; // 304 Not Modified - fake cached response
             }
             LOG_WRN("%s: deleting previous downloaded file: %s\n", __func__, path.c_str());
             if (remove(path.c_str()) != 0) {
                 LOG_ERR("%s: unable to delete file: %s\n", __func__, path.c_str());
-                return false;
+                return -1;
             }
         }
 
@@ -709,7 +722,7 @@ static bool common_download_file_single_online(const std::string & url,
                 existing_size = std::filesystem::file_size(path_temporary);
             } else if (remove(path_temporary.c_str()) != 0) {
                 LOG_ERR("%s: unable to delete file: %s\n", __func__, path_temporary.c_str());
-                return false;
+                return -1;
             }
         }
 
@@ -730,15 +743,16 @@ static bool common_download_file_single_online(const std::string & url,
 
         if (std::rename(path_temporary.c_str(), path.c_str()) != 0) {
             LOG_ERR("%s: unable to rename file: %s to %s\n", __func__, path_temporary.c_str(), path.c_str());
-            return false;
+            return -1;
         }
         if (!etag.empty()) {
             write_etag(path, etag);
         }
-        break;
+
+        return head->status; // TODO: use actual GET status?
     }
 
-    return true;
+    return -1; // max attempts reached
 }
 
 std::pair<long, std::vector<char>> common_remote_get_content(const std::string          & url,
@@ -777,22 +791,22 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string
 
 #if defined(LLAMA_USE_CURL) || defined(LLAMA_USE_HTTPLIB)
 
-static bool common_download_file_single(const std::string & url,
-                                        const std::string & path,
-                                        const std::string & bearer_token,
-                                        bool                offline,
-                                        const common_header_list & headers) {
+int common_download_file_single(const std::string & url,
+                                const std::string & path,
+                                const std::string & bearer_token,
+                                bool offline,
+                                const common_header_list & headers) {
     if (!offline) {
         return common_download_file_single_online(url, path, bearer_token, headers);
     }
 
     if (!std::filesystem::exists(path)) {
         LOG_ERR("%s: required file is not available in cache (offline mode): %s\n", __func__, path.c_str());
-        return false;
+        return -1;
     }
 
     LOG_INF("%s: using cached file (offline mode): %s\n", __func__, path.c_str());
-    return true;
+    return 304; // Not Modified - fake cached response
 }
 
 // download multiple files from remote URLs to local paths
@@ -810,7 +824,8 @@ static bool common_download_file_multiple(const std::vector<std::pair<std::strin
             std::async(
                 std::launch::async,
                 [&bearer_token, offline, &headers](const std::pair<std::string, std::string> & it) -> bool {
-                    return common_download_file_single(it.first, it.second, bearer_token, offline, headers);
+                    const int http_status = common_download_file_single(it.first, it.second, bearer_token, offline, headers);
+                    return is_http_status_ok(http_status);
                 },
                 item
             )
@@ -837,7 +852,8 @@ bool common_download_model(const common_params_model & model,
         return false;
     }
 
-    if (!common_download_file_single(model.url, model.path, bearer_token, offline, headers)) {
+    const int http_status = common_download_file_single(model.url, model.path, bearer_token, offline, headers);
+    if (!is_http_status_ok(http_status)) {
         return false;
     }
 
@@ -975,7 +991,7 @@ common_hf_file_res common_get_hf_file(const std::string & hf_repo_with_tag,
     } else if (res_code == 401) {
         throw std::runtime_error("error: model is private or does not exist; if you are accessing a gated model, please provide a valid HF token");
     } else {
-        throw std::runtime_error(string_format("error from HF API, response code: %ld, data: %s", res_code, res_str.c_str()));
+        throw std::runtime_error(string_format("error from HF API (%s), response code: %ld, data: %s", url.c_str(), res_code, res_str.c_str()));
     }
 
     // check response
@@ -1094,7 +1110,8 @@ std::string common_docker_resolve_model(const std::string & docker) {
         std::string local_path = fs_get_cache_file(model_filename);
 
         const std::string blob_url = url_prefix + "/blobs/" + gguf_digest;
-        if (!common_download_file_single(blob_url, local_path, token, false, {})) {
+        const int http_status = common_download_file_single(blob_url, local_path, token, false, {});
+        if (!is_http_status_ok(http_status)) {
             throw std::runtime_error("Failed to download Docker Model");
         }
 
@@ -1120,6 +1137,14 @@ std::string common_docker_resolve_model(const std::string &) {
     throw std::runtime_error("download functionality is not enabled in this build");
 }
 
+int common_download_file_single(const std::string &,
+                                const std::string &,
+                                const std::string &,
+                                bool,
+                                const common_header_list &) {
+    throw std::runtime_error("download functionality is not enabled in this build");
+}
+
 #endif // LLAMA_USE_CURL || LLAMA_USE_HTTPLIB
 
 std::vector<common_cached_model_info> common_list_cached_models() {