mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-19 01:04:55 +02:00
Merge branch 'master' into xsn/server_docker_isolate
This commit is contained in:
+2
-2
@@ -2582,7 +2582,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
params.mtmd_batch_max_tokens = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MTMD_BATCH_MAX_TOKENS"));
|
||||
if (llama_supports_rpc()) {
|
||||
if (params.is_gen_docs || llama_supports_rpc()) {
|
||||
add_opt(common_arg(
|
||||
{"--rpc"}, "SERVERS",
|
||||
"comma-separated list of RPC servers (host:port)",
|
||||
@@ -3331,7 +3331,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
{"--tools"}, "TOOL1,TOOL2,...",
|
||||
"experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)\n"
|
||||
"specify \"all\" to enable all tools\n"
|
||||
"available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime\n"
|
||||
"available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime, get_info\n"
|
||||
"note: for security reasons, this will limit --cors-origins to localhost by default",
|
||||
[](common_params & params, const std::string & value) {
|
||||
params.server_tools = parse_csv_row(value);
|
||||
|
||||
@@ -740,6 +740,8 @@ struct common_params {
|
||||
llama_progress_callback load_progress_callback = NULL;
|
||||
void * load_progress_callback_user_data = NULL;
|
||||
bool no_alloc = false; // Don't allocate model buffers
|
||||
|
||||
bool is_gen_docs = false; // whether we are running inside llama-gen-docs
|
||||
};
|
||||
|
||||
// call once at the start of a program if it uses libcommon
|
||||
|
||||
@@ -70,6 +70,8 @@ static void write_table(std::ostringstream & ss, std::vector<common_arg *> & opt
|
||||
|
||||
static void write_help(std::ostringstream & ss, const md_file & md) {
|
||||
common_params params;
|
||||
params.is_gen_docs = true;
|
||||
|
||||
auto ctx_arg = common_params_parser_init(params, md.ex);
|
||||
|
||||
std::vector<common_arg *> common_options;
|
||||
|
||||
@@ -199,6 +199,7 @@ For the full list of features, please refer to [server's changelog](https://gith
|
||||
| `--ui-mcp-proxy, --webui-mcp-proxy, --no-ui-mcp-proxy, --no-webui-mcp-proxy` | experimental: whether to enable MCP CORS proxy - do not enable in untrusted environments (default: disabled)<br/>(env: LLAMA_ARG_UI_MCP_PROXY) |
|
||||
| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_TOOLS) |
|
||||
| `--tools-runtime OPTION` | experimental: run tools in a separate runtime environment (default: none, use host environment)<br/>available options:<br/> 'docker:<image>': spin up a new Docker container and reuse it for all invocations, clean up on server exit<br/> 'docker-container:<id>': use an existing Docker container by ID, won't stop on server exit<br/><br/>(env: LLAMA_ARG_TOOLS_RUNTIME) |
|
||||
| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime, get_info<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_TOOLS) |
|
||||
| `--mcp-servers-config PATH` | experimental: path to JSON file with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_MCP_SERVERS_CONFIG) |
|
||||
| `--mcp-servers-json JSON` | experimental: inline JSON with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_MCP_SERVERS_JSON) |
|
||||
| `-ag, --agent, -no-ag, --no-agent` | whether to enable CORS proxy and all built-in tools - do not enable in untrusted environments (default: disabled)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_AGENT) |
|
||||
|
||||
@@ -1281,6 +1281,56 @@ struct server_tool_get_datetime : server_tool {
|
||||
}
|
||||
};
|
||||
|
||||
//
|
||||
// get_info: returns runtime info (OS name/version and cwd)
|
||||
//
|
||||
|
||||
struct server_tool_get_info : server_tool {
|
||||
server_tool_get_info() {
|
||||
name = "get_info";
|
||||
display_name = "Get Runtime Info";
|
||||
permission_write = false;
|
||||
}
|
||||
|
||||
json get_definition() const override {
|
||||
return {
|
||||
{"type", "function"},
|
||||
{"function", {
|
||||
{"name", name},
|
||||
{"description", "Returns runtime info: the OS name/version and the current working directory"},
|
||||
{"parameters", {
|
||||
{"type", "object"},
|
||||
{"properties", json::object()},
|
||||
}},
|
||||
}},
|
||||
};
|
||||
}
|
||||
|
||||
json invoke(json params, server_tool::stream *) const override {
|
||||
auto io = make_tools_io(params);
|
||||
|
||||
#ifdef _WIN32
|
||||
auto res = io->run({"cmd", "/c", "ver"}, 4096, 5);
|
||||
#else
|
||||
auto res = io->run({"uname", "-a"}, 4096, 5);
|
||||
#endif
|
||||
// "ver" prints a blank line before the version, so the output is stripped on both ends;
|
||||
// a failed spawn or a timeout leaves a diagnostic in res.output, which is not an OS name
|
||||
std::string os_info = res.exit_code == 0 && !res.timed_out ? string_strip(res.output) : "unknown";
|
||||
|
||||
std::string cwd = json_value(params, "cwd", std::string());
|
||||
if (cwd.empty()) {
|
||||
std::error_code ec;
|
||||
cwd = fs::current_path(ec).string();
|
||||
}
|
||||
|
||||
return {
|
||||
{"os", os_info},
|
||||
{"cwd", cwd},
|
||||
};
|
||||
}
|
||||
};
|
||||
|
||||
struct server_tool_stream_result : server_task_result {
|
||||
std::string chunk;
|
||||
bool done = false;
|
||||
@@ -1488,6 +1538,7 @@ static std::vector<std::unique_ptr<server_tool>> build_tools() {
|
||||
tools.push_back(std::make_unique<server_tool_write_file>());
|
||||
tools.push_back(std::make_unique<server_tool_edit_file>());
|
||||
tools.push_back(std::make_unique<server_tool_get_datetime>());
|
||||
tools.push_back(std::make_unique<server_tool_get_info>());
|
||||
return tools;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user