cli : move to HTTP-based implementation (#24948)

* cli: move to HTTP-based implementation

* wip

* working

* remote server ok

* cli support router mode

Co-authored-by: Piotr Wilkin <ilintar@gmail.com>

* case: router with only one model

* Apply suggestions from code review

Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>

* remove outdated comment

* use destructor instead

* add ftype

* cli-view --> cli-ui

* pimpl

* no more json in header

* nits fixes

* also show model aliases

---------

Co-authored-by: Piotr Wilkin <ilintar@gmail.com>
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
This commit is contained in:
Xuan-Son Nguyen
2026-07-08 14:52:43 +02:00
committed by GitHub
co-authored by Piotr Wilkin Piotr Wilkin
parent 07e012afdc
commit c264f65ff9
14 changed files with 1336 additions and 724 deletions
+9 -3
View File
@@ -719,9 +719,8 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
// model is required (except for server)
// TODO @ngxson : maybe show a list of available models in CLI in this case
if (params.model.path.empty()
&& !params.usage
&& !params.completion) {
bool can_skip_model = params.usage || params.completion || !params.server_base.empty();
if (!can_skip_model && params.model.path.empty()) {
throw std::invalid_argument("error: --model is required\n");
}
}
@@ -1241,6 +1240,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.completion = true;
}
));
add_opt(common_arg(
{"--server-base"}, "URL",
string_format("connect to this server instead of starting a new one, example: 'http://localhost:8080' (default: none)"),
[](common_params & params, const std::string & value) {
params.server_base = value;
}
).set_examples({LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--verbose-prompt"},
string_format("print a verbose prompt before generation (default: %s)", params.verbose_prompt ? "true" : "false"),
+3
View File
@@ -644,6 +644,9 @@ struct common_params {
std::map<std::string, std::string> default_template_kwargs;
// CLI params
std::string server_base; // if set, connect to this server instead of starting a new one
// UI configs
bool ui = true;
bool ui_mcp_proxy = false;
+70
View File
@@ -2,6 +2,16 @@
#include <cpp-httplib/httplib.h>
#ifdef _WIN32
#include <winsock2.h>
#include <windows.h>
#else
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <unistd.h>
#endif
struct common_http_url {
std::string scheme;
std::string user;
@@ -119,3 +129,63 @@ static std::pair<httplib::Client, common_http_url> common_http_client(const std:
static std::string common_http_show_masked_url(const common_http_url & parts) {
return parts.scheme + "://" + (parts.user.empty() ? "" : "****:****@") + common_http_format_host(parts.host) + parts.path;
}
static int common_http_get_free_port() {
#ifdef _WIN32
WSADATA wsaData;
if (WSAStartup(MAKEWORD(2, 2), &wsaData) != 0) {
return -1;
}
typedef SOCKET native_socket_t;
#define INVALID_SOCKET_VAL INVALID_SOCKET
#define CLOSE_SOCKET(s) closesocket(s)
#else
typedef int native_socket_t;
#define INVALID_SOCKET_VAL -1
#define CLOSE_SOCKET(s) close(s)
#endif
native_socket_t sock = socket(AF_INET, SOCK_STREAM, 0);
if (sock == INVALID_SOCKET_VAL) {
#ifdef _WIN32
WSACleanup();
#endif
return -1;
}
struct sockaddr_in serv_addr;
std::memset(&serv_addr, 0, sizeof(serv_addr));
serv_addr.sin_family = AF_INET;
serv_addr.sin_addr.s_addr = htonl(INADDR_ANY);
serv_addr.sin_port = htons(0);
if (bind(sock, (struct sockaddr*)&serv_addr, sizeof(serv_addr)) != 0) {
CLOSE_SOCKET(sock);
#ifdef _WIN32
WSACleanup();
#endif
return -1;
}
#ifdef _WIN32
int namelen = sizeof(serv_addr);
#else
socklen_t namelen = sizeof(serv_addr);
#endif
if (getsockname(sock, (struct sockaddr*)&serv_addr, &namelen) != 0) {
CLOSE_SOCKET(sock);
#ifdef _WIN32
WSACleanup();
#endif
return -1;
}
int port = ntohs(serv_addr.sin_port);
CLOSE_SOCKET(sock);
#ifdef _WIN32
WSACleanup();
#endif
return port;
}