Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

server: add get_info tool

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-03 17:35:02 +02:00
parent dbadb68eec
commit 371e8b0a8c
5 changed files with 56 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+1 -1
View File
@@ -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);
tools/cli/README.md
-1
View File
@@ -54,7 +54,6 @@
| `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
| `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
| `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
| `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
tools/completion/README.md
-1
View File
@@ -137,7 +137,6 @@ llama-completion.exe -m models\gemma-1.1-7b-it.Q4_K_M.gguf --ignore-eos -n -1
| `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
| `-np, --parallel N` | number of parallel sequences to decode (default: 1)<br/>(env: LLAMA_ARG_N_PARALLEL) |
| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
| `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
| `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
tools/server/README.md
+3 -2
View File
@@ -71,7 +71,6 @@ For the full list of features, please refer to [server's changelog](https://gith
| `-ctk, --cache-type-k TYPE` | KV cache data type for K<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_K) |
| `-ctv, --cache-type-v TYPE` | KV cache data type for V<br/>allowed values: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1<br/>(default: f16)<br/>(env: LLAMA_ARG_CACHE_TYPE_V) |
| `-dt, --defrag-thold N` | KV cache defragmentation threshold (DEPRECATED)<br/>(env: LLAMA_ARG_DEFRAG_THOLD) |
| `--rpc SERVERS` | comma-separated list of RPC servers (host:port)<br/>(env: LLAMA_ARG_RPC) |
| `--mlock` | DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing<br/>(env: LLAMA_ARG_MLOCK) |
| `--mmap, --no-mmap` | DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)<br/>(env: LLAMA_ARG_MMAP) |
| `-dio, --direct-io, -ndio, --no-direct-io` | DEPRECATED in favor of `--load-mode`: use DirectIO if available<br/>(env: LLAMA_ARG_DIO) |
@@ -198,7 +197,9 @@ For the full list of features, please refer to [server's changelog](https://gith
| `--ui-config, --webui-config JSON` | JSON that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG) |
| `--ui-config-file, --webui-config-file PATH` | JSON file that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG_FILE) |
| `--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 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) |
| `--ui, --webui, --no-ui, --no-webui` | whether to enable the Web UI (default: enabled)<br/>(env: LLAMA_ARG_UI) |
| `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |
tools/server/server-tools.cpp
+52
View File
@@ -1090,6 +1090,57 @@ 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
std::string os_info = res.output;
while (!os_info.empty() && (os_info.back() == '\n' || os_info.back() == '\r')) {
os_info.pop_back();
}
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;
@@ -1199,6 +1250,7 @@ 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;
}