Spaces:
Running on Zero
Running on Zero
File size: 48,629 Bytes
0475af5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 | #include "server-tools.h"
#include <sheredom/subprocess.h>
#include <filesystem>
#include <fstream>
#include <regex>
#include <thread>
#include <chrono>
#include <atomic>
#include <cstring>
#include <climits>
#include <algorithm>
#include <unordered_set>
#include <functional>
namespace fs = std::filesystem;
//
// internal helpers
//
json server_tool::to_json() const {
return {
{"display_name", display_name},
{"tool", name},
{"type", "builtin"},
{"permissions", json{
{"write", permission_write}
}},
{"definition", get_definition()},
};
}
static constexpr size_t SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT = 8 * 1024 * 1024; // 8 MB
static constexpr int SERVER_TOOL_GIT_LS_FILES_TIMEOUT = 15; // seconds
class tools_io {
public:
struct exec_result {
std::string output;
int exit_code = -1;
bool timed_out = false;
};
virtual ~tools_io() = default;
virtual bool is_directory(const std::string & path) const = 0;
virtual bool is_regular_file(const std::string & path) const = 0;
virtual bool file_size(const std::string & path, uintmax_t & out_size) const = 0;
virtual bool read_file(const std::string & path, std::string & out) const = 0;
virtual bool write_file(const std::string & path, const std::string & content) const = 0;
// paths relative to `base`, '/'-separated; sets `err` if `base` isn't a directory
virtual std::vector<std::string> list_files(const std::string & base, std::string & err) const = 0;
// on_chunk, if set, is called with each chunk of output as it is read (before truncation cuts in);
// returning false terminates the process early (e.g. the client disconnected)
virtual exec_result run(
const std::vector<std::string> & args,
size_t max_output,
int timeout_secs,
const std::function<bool(const std::string &)> & on_chunk = nullptr) const = 0;
};
class tools_io_basic : public tools_io {
public:
bool is_directory(const std::string & path) const override {
std::error_code ec;
return fs::is_directory(path, ec) && !ec;
}
bool is_regular_file(const std::string & path) const override {
std::error_code ec;
return fs::is_regular_file(path, ec) && !ec;
}
bool file_size(const std::string & path, uintmax_t & out_size) const override {
std::error_code ec;
out_size = fs::file_size(path, ec);
return !ec;
}
bool read_file(const std::string & path, std::string & out) const override {
std::ifstream f(path, std::ios::binary);
if (!f) return false;
std::ostringstream ss;
ss << f.rdbuf();
out = ss.str();
return true;
}
bool write_file(const std::string & path, const std::string & content) const override {
std::error_code ec;
fs::path fpath(path);
if (fpath.has_parent_path()) {
fs::create_directories(fpath.parent_path(), ec);
if (ec) return false;
}
std::ofstream f(path, std::ios::binary);
if (!f) return false;
f << content;
return (bool) f;
}
std::vector<std::string> list_files(const std::string & base, std::string & err) const override {
err.clear();
if (!is_directory(base)) {
err = "path does not exist or is not a directory: " + base;
return {};
}
auto res = run(
{"git", "-C", base, "ls-files", "--cached", "--others", "--exclude-standard"},
SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, SERVER_TOOL_GIT_LS_FILES_TIMEOUT);
if (res.exit_code == 0 && !res.timed_out) {
std::vector<std::string> result;
std::istringstream iss(res.output);
std::string line;
while (std::getline(iss, line)) {
if (!line.empty() && line.back() == '\r') line.pop_back();
if (line.empty()) continue;
std::replace(line.begin(), line.end(), '\\', '/');
if (is_regular_file((fs::path(base) / line).string())) {
result.push_back(line);
}
}
return result;
}
return list_files_fallback(base);
}
exec_result run(
const std::vector<std::string> & args,
size_t max_output,
int timeout_secs,
const std::function<bool(const std::string &)> & on_chunk = nullptr) const override {
exec_result res;
subprocess_s proc;
auto argv = to_cstr_vec(args);
int options = subprocess_option_no_window
| subprocess_option_combined_stdout_stderr
| subprocess_option_inherit_environment
| subprocess_option_search_user_path;
if (subprocess_create(argv.data(), options, &proc) != 0) {
res.output = "failed to spawn process";
return res;
}
std::atomic<bool> done{false};
std::atomic<bool> timed_out{false};
std::thread timeout_thread([&]() {
auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(timeout_secs);
while (!done.load()) {
if (std::chrono::steady_clock::now() >= deadline) {
timed_out.store(true);
subprocess_terminate(&proc);
return;
}
std::this_thread::sleep_for(std::chrono::milliseconds(100));
}
});
FILE * f = subprocess_stdout(&proc);
std::string output;
bool truncated = false;
if (f) {
char buf[4096];
while (fgets(buf, sizeof(buf), f) != nullptr) {
if (!truncated) {
size_t len = strlen(buf);
if (output.size() + len <= max_output) {
output.append(buf, len);
if (on_chunk && !on_chunk(std::string(buf, len))) {
subprocess_terminate(&proc);
break;
}
} else {
size_t remaining = max_output - output.size();
output.append(buf, remaining);
if (on_chunk && remaining > 0) on_chunk(std::string(buf, remaining));
truncated = true;
}
}
}
}
done.store(true);
if (timeout_thread.joinable()) {
timeout_thread.join();
}
subprocess_join(&proc, &res.exit_code);
subprocess_destroy(&proc);
res.output = output;
res.timed_out = timed_out.load();
if (truncated) {
res.output += "\n[output truncated]";
}
return res;
}
private:
static std::vector<char *> to_cstr_vec(const std::vector<std::string> & v) {
std::vector<char *> r;
r.reserve(v.size() + 1);
for (const auto & s : v) {
r.push_back(const_cast<char *>(s.c_str()));
}
r.push_back(nullptr);
return r;
}
static const std::unordered_set<std::string> & junk_dir_names() {
static const std::unordered_set<std::string> names = {
".git", ".svn", ".hg", "node_modules", "__pycache__",
".venv", "venv", "dist", "build", "target", ".cache", ".idea", ".vscode",
};
return names;
}
std::vector<std::string> list_files_fallback(const std::string & base) const {
std::vector<std::string> result;
std::error_code ec;
std::vector<std::pair<fs::path, fs::path>> stack;
stack.emplace_back(fs::path(base), fs::path());
while (!stack.empty()) {
auto [dir, rel_dir] = stack.back();
stack.pop_back();
for (const auto & entry : fs::directory_iterator(dir, fs::directory_options::skip_permission_denied, ec)) {
if (ec) break;
std::string fname = entry.path().filename().string();
std::error_code tec;
if (entry.is_directory(tec)) {
if (junk_dir_names().count(fname) > 0) continue;
stack.emplace_back(entry.path(), rel_dir / fname);
} else if (entry.is_regular_file(tec)) {
std::string rel = (rel_dir / fname).string();
std::replace(rel.begin(), rel.end(), '\\', '/');
result.push_back(rel);
}
}
}
return result;
}
};
static std::unique_ptr<tools_io> make_tools_io(const json & params) {
GGML_UNUSED(params); // TODO in follow-up PR
return std::make_unique<tools_io_basic>();
}
// no '/' in pattern -> match basename at any depth; else match full relative path
static bool path_glob_match(const std::string & pattern, const std::string & rel_path) {
if (pattern.find('/') == std::string::npos) {
return glob_match(pattern, fs::path(rel_path).filename().string());
}
if (pattern == "**" || pattern.rfind("**/", 0) == 0 || pattern.rfind('/', 0) == 0) {
return glob_match(pattern, rel_path);
}
return glob_match("**/" + pattern, rel_path);
}
//
// read_file: read a file with optional line range and line-number prefix
//
static constexpr size_t SERVER_TOOL_READ_FILE_MAX_SIZE = 16 * 1024; // 16 KB
struct server_tool_read_file : server_tool {
server_tool_read_file() {
name = "read_file";
display_name = "Read file";
permission_write = false;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description", "Read the contents of a file. Optionally specify a 1-based line range. "
"If append_loc is true, each line is prefixed with its line number (e.g. \"1\u2192 ...\")."},
{"parameters", {
{"type", "object"},
{"properties", {
{"path", {{"type", "string"}, {"description", "Path to the file"}}},
{"start_line", {{"type", "integer"}, {"description", "First line to read, 1-based (default: 1)"}}},
{"end_line", {{"type", "integer"}, {"description", "Last line to read, 1-based inclusive (default: end of file)"}}},
{"append_loc", {{"type", "boolean"}, {"description", "Prefix each line with its line number"}}},
}},
{"required", json::array({"path"})},
}},
}},
};
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path").get<std::string>();
int start_line = json_value(params, "start_line", 1);
int end_line = json_value(params, "end_line", -1); // -1 = no limit
bool append_loc = json_value(params, "append_loc", false);
auto io = make_tools_io(params);
uintmax_t file_size = 0;
if (!io->file_size(path, file_size)) {
return {{"error", "cannot stat file: " + path}};
}
if (file_size > SERVER_TOOL_READ_FILE_MAX_SIZE && end_line == -1) {
return {{"error", string_format(
"file too large (%zu bytes, max %zu). Use start_line/end_line to read a portion.",
(size_t)file_size, SERVER_TOOL_READ_FILE_MAX_SIZE)}};
}
std::string content;
if (!io->read_file(path, content)) {
return {{"error", "failed to open file: " + path}};
}
std::istringstream f(content);
std::string result;
std::string line;
int lineno = 0;
while (std::getline(f, line)) {
lineno++;
if (lineno < start_line) continue;
if (end_line != -1 && lineno > end_line) break;
std::string out_line;
if (append_loc) {
out_line = std::to_string(lineno) + "\u2192 " + line + "\n";
} else {
out_line = line + "\n";
}
if (result.size() + out_line.size() > SERVER_TOOL_READ_FILE_MAX_SIZE) {
result += "[output truncated]";
break;
}
result += out_line;
}
return {{"plain_text_response", result}};
}
};
//
// file_glob_search: find files matching a glob pattern under a base directory
//
static constexpr size_t SERVER_TOOL_FILE_SEARCH_MAX_RESULTS = 100;
struct server_tool_file_glob_search : server_tool {
server_tool_file_glob_search() {
name = "file_glob_search";
display_name = "File search";
permission_write = false;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description",
"Recursively search for files matching a glob pattern under a directory. "
"Automatically skips files ignored by .gitignore (when the directory is inside a git repo) "
"and common junk directories (.git, node_modules, build, dist, etc.) otherwise. "
"A pattern with no '/' (e.g. \"*.cpp\") matches the file's basename at any depth. "
"A pattern containing '/' matches the full relative path; unless already anchored with "
"\"**/\" or a leading '/', it is automatically prefixed with \"**/\"."},
{"parameters", {
{"type", "object"},
{"properties", {
{"path", {{"type", "string"}, {"description", "Base directory to search in"}}},
{"include", {{"type", "string"}, {"description", "Glob pattern for files to include (e.g. \"*.cpp\" or \"src/**/*.cpp\"). Default: **"}}},
{"exclude", {{"type", "string"}, {"description", "Glob pattern for files to exclude"}}},
}},
{"required", json::array({"path"})},
}},
}},
};
}
json invoke(json params, server_tool::stream *) const override {
std::string base = params.at("path").get<std::string>();
std::string include = json_value(params, "include", std::string("**"));
std::string exclude = json_value(params, "exclude", std::string(""));
auto io = make_tools_io(params);
std::string err;
auto files = io->list_files(base, err);
if (!err.empty()) {
return {{"error", err}};
}
std::vector<std::string> matches;
for (const auto & rel : files) {
if (!path_glob_match(include, rel)) continue;
if (!exclude.empty() && path_glob_match(exclude, rel)) continue;
matches.push_back(rel);
}
size_t total = matches.size();
size_t shown = std::min(total, SERVER_TOOL_FILE_SEARCH_MAX_RESULTS);
std::ostringstream output_text;
for (size_t i = 0; i < shown; i++) {
output_text << matches[i] << "\n";
}
output_text << "\n---\nTotal matches: " << total << "\n";
if (total > shown) {
output_text << string_format(
"[%zu results limit reached (%zu total matches). Refine the glob pattern to narrow the search.]\n",
shown, total);
}
return {{"plain_text_response", output_text.str()}};
}
};
//
// grep_search: search for a regex pattern in files
//
static constexpr size_t SERVER_TOOL_GREP_SEARCH_MAX_RESULTS = 100;
struct server_tool_grep_search : server_tool {
server_tool_grep_search() {
name = "grep_search";
display_name = "Grep search";
permission_write = false;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description",
"Search for a pattern in files under a path. Returns matching lines with file paths "
"(and, unless searching a single file, paths relative to the given directory). "
"Automatically skips files ignored by .gitignore (when the directory is inside a git repo) "
"and common junk directories (.git, node_modules, build, dist, etc.) otherwise. "
"include/exclude: a pattern with no '/' matches the basename at any depth; a pattern "
"containing '/' matches the full relative path (auto-anchored with \"**/\" unless already anchored)."},
{"parameters", {
{"type", "object"},
{"properties", {
{"path", {{"type", "string"}, {"description", "File or directory to search in"}}},
{"pattern", {{"type", "string"}, {"description", "Pattern to search for (regular expression unless literal is true)"}}},
{"include", {{"type", "string"}, {"description", "Glob pattern to filter files (default: **)"}}},
{"exclude", {{"type", "string"}, {"description", "Glob pattern to exclude files"}}},
{"return_line_numbers", {{"type", "boolean"}, {"description", "If true, include line numbers in results"}}},
{"literal", {{"type", "boolean"}, {"description", "Treat pattern as a literal string instead of a regular expression (default: false)"}}},
{"ignore_case", {{"type", "boolean"}, {"description", "Case-insensitive search (default: false)"}}},
{"context_lines", {{"type", "integer"}, {"description", "Number of lines of context to show before and after each match (default: 0)"}}},
}},
{"required", json::array({"path", "pattern"})},
}},
}},
};
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path").get<std::string>();
std::string pat_str = params.at("pattern").get<std::string>();
std::string include = json_value(params, "include", std::string("**"));
std::string exclude = json_value(params, "exclude", std::string(""));
bool show_lineno = json_value(params, "return_line_numbers", false);
bool literal = json_value(params, "literal", false);
bool ignore_case = json_value(params, "ignore_case", false);
int ctx_lines = std::max(0, json_value(params, "context_lines", 0));
std::string pattern_src = pat_str;
if (literal) {
static const std::string specials = "\\^$.|?*+()[]{}";
std::string escaped;
escaped.reserve(pat_str.size() * 2);
for (char c : pat_str) {
if (specials.find(c) != std::string::npos) escaped += '\\';
escaped += c;
}
pattern_src = escaped;
}
std::regex pattern;
try {
auto flags = std::regex::ECMAScript;
if (ignore_case) flags |= std::regex::icase;
pattern = std::regex(pattern_src, flags);
} catch (const std::regex_error & e) {
return {{"error", std::string("invalid regex: ") + e.what()}};
}
auto io = make_tools_io(params);
// collect (absolute_path, display_path) pairs to search
std::vector<std::pair<std::string, std::string>> files;
if (io->is_regular_file(path)) {
files.emplace_back(path, path);
} else if (io->is_directory(path)) {
std::string err;
auto candidates = io->list_files(path, err);
if (!err.empty()) {
return {{"error", err}};
}
for (const auto & rel : candidates) {
if (!path_glob_match(include, rel)) continue;
if (!exclude.empty() && path_glob_match(exclude, rel)) continue;
files.emplace_back((fs::path(path) / rel).string(), rel);
}
} else {
return {{"error", "path does not exist: " + path}};
}
std::ostringstream output_text;
size_t total = 0;
bool limit_reached = false;
bool show_num = show_lineno || ctx_lines > 0;
for (const auto & file_entry : files) {
if (limit_reached) break;
const std::string & fpath = file_entry.first;
const std::string & display_path = file_entry.second;
std::string content;
if (!io->read_file(fpath, content)) continue;
std::vector<std::string> lines;
{
std::istringstream f(content);
std::string line;
while (std::getline(f, line)) lines.push_back(line);
}
for (size_t i = 0; i < lines.size(); i++) {
if (total >= SERVER_TOOL_GREP_SEARCH_MAX_RESULTS) {
limit_reached = true;
break;
}
if (!std::regex_search(lines[i], pattern)) continue;
long ctx_start = ctx_lines > 0 ? std::max<long>(0, (long) i - ctx_lines) : (long) i;
long ctx_end = ctx_lines > 0 ? std::min<long>((long) lines.size() - 1, (long) i + ctx_lines) : (long) i;
for (long j = ctx_start; j <= ctx_end; j++) {
bool is_match = (j == (long) i);
output_text << display_path << (is_match ? ':' : '-');
if (show_num) {
output_text << (j + 1) << (is_match ? ':' : '-');
}
output_text << lines[j] << "\n";
}
if (ctx_lines > 0) {
output_text << "--\n";
}
total++;
}
}
output_text << "\n---\nTotal matches: " << total << "\n";
if (limit_reached) {
output_text << string_format(
"[%zu matches limit reached. Narrow the path/pattern/include to see more.]\n",
SERVER_TOOL_GREP_SEARCH_MAX_RESULTS);
}
return {{"plain_text_response", output_text.str()}};
}
};
//
// exec_shell_command: run an arbitrary shell command
//
static constexpr size_t SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_OUTPUT_SIZE = 16 * 1024; // 16 KB
static constexpr int SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_TIMEOUT = 60; // seconds
struct server_tool_exec_shell_command : server_tool {
server_tool_exec_shell_command() {
name = "exec_shell_command";
display_name = "Execute shell command";
permission_write = true;
support_stream = true;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description", "Execute a shell command and return its output (stdout and stderr combined)."},
{"parameters", {
{"type", "object"},
{"properties", {
{"command", {{"type", "string"}, {"description", "Shell command to execute"}}},
{"timeout", {{"type", "integer"}, {"description", string_format("Timeout in seconds (default 10, max %d)", SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_TIMEOUT)}}},
{"max_output_size", {{"type", "integer"}, {"description", string_format("Maximum output size in bytes (default %zu)", SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_OUTPUT_SIZE)}}},
}},
{"required", json::array({"command"})},
}},
}},
};
}
json invoke(json params, server_tool::stream * st) const override {
std::string command = params.at("command").get<std::string>();
int timeout = json_value(params, "timeout", 10);
size_t max_output = (size_t) json_value(params, "max_output_size", (int) SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_OUTPUT_SIZE);
timeout = std::min(timeout, SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_TIMEOUT);
max_output = std::min(max_output, SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_OUTPUT_SIZE);
#ifdef _WIN32
std::vector<std::string> args = {"cmd", "/c", command};
#else
std::vector<std::string> args = {"sh", "-c", command};
#endif
auto io = make_tools_io(params);
if (st) {
auto res = io->run(args, max_output, timeout, [st](const std::string & chunk) {
st->push(chunk);
return !st->alive || st->alive();
});
if (st->alive && !st->alive()) {
return json();
}
std::string tail = string_format("\n[exit code: %d]", res.exit_code);
if (res.timed_out) {
tail += " [exit due to timed out]";
}
st->push(tail);
return json();
}
auto res = io->run(args, max_output, timeout);
std::string text_output = res.output;
text_output += string_format("\n[exit code: %d]", res.exit_code);
if (res.timed_out) {
text_output += " [exit due to timed out]";
}
return {{"plain_text_response", text_output}};
}
};
//
// write_file: create or overwrite a file
//
struct server_tool_write_file : server_tool {
server_tool_write_file() {
name = "write_file";
display_name = "Write file";
permission_write = true;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description", "Write content to a file, creating it (including parent directories) if it does not exist. May use with edit_file for more complex edits."},
{"parameters", {
{"type", "object"},
{"properties", {
{"path", {{"type", "string"}, {"description", "Path of the file to write"}}},
{"content", {{"type", "string"}, {"description", "Content to write"}}},
}},
{"required", json::array({"path", "content"})},
}},
}},
};
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path").get<std::string>();
std::string content = params.at("content").get<std::string>();
auto io = make_tools_io(params);
if (!io->write_file(path, content)) {
return {{"error", "failed to write file: " + path}};
}
return {{"result", "file written successfully"}, {"path", path}, {"bytes", content.size()}};
}
};
//
// edit_file: exact text replacement, one or more edits per call
//
struct server_tool_edit_file : server_tool {
server_tool_edit_file() {
name = "edit_file";
display_name = "Edit file";
permission_write = true;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description",
"Edit a file using exact text replacement. Each edits[].old_text must be unique in the file "
"and is matched against the original content, not incrementally. Merge nearby changes into "
"one edit instead of overlapping edits. Use write_file to replace the whole file."},
{"parameters", {
{"type", "object"},
{"properties", {
{"path", {{"type", "string"}, {"description", "Path to the file to edit"}}},
{"edits", {
{"type", "array"},
{"description", "One or more exact text replacements to apply"},
{"items", {
{"type", "object"},
{"properties", {
{"old_text", {{"type", "string"}, {"description", "Exact text to find; must be unique in the file and must not overlap with other edits"}}},
{"new_text", {{"type", "string"}, {"description", "Text to replace old_text with"}}},
}},
{"required", json::array({"old_text", "new_text"})},
}},
}},
}},
{"required", json::array({"path", "edits"})},
}},
}},
};
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path").get<std::string>();
const json & edits_json = params.at("edits");
if (!edits_json.is_array() || edits_json.empty()) {
return {{"error", "\"edits\" must be a non-empty array"}};
}
struct edit_req {
std::string old_text;
std::string new_text;
};
std::vector<edit_req> edits;
edits.reserve(edits_json.size());
for (const auto & e : edits_json) {
edit_req er;
er.old_text = e.at("old_text").get<std::string>();
er.new_text = e.at("new_text").get<std::string>();
if (er.old_text.empty()) {
return {{"error", string_format("edits[%zu].old_text must not be empty", edits.size())}};
}
edits.push_back(std::move(er));
}
auto io = make_tools_io(params);
std::string original_content;
if (!io->read_file(path, original_content)) {
return {{"error", "failed to open file: " + path}};
}
// does any old_text need fuzzy matching (no exact match found)?
bool any_fuzzy = false;
for (size_t i = 0; i < edits.size(); i++) {
if (original_content.find(edits[i].old_text) != std::string::npos) continue;
std::string fuzzy_content = normalize_for_fuzzy_match(original_content);
std::string fuzzy_old = normalize_for_fuzzy_match(edits[i].old_text);
if (fuzzy_content.find(fuzzy_old) == std::string::npos) {
return {{"error", string_format(
"could not find edits[%zu].old_text in %s, it must match the file's current content exactly",
i, path.c_str())}};
}
any_fuzzy = true;
}
std::string base_content = any_fuzzy ? normalize_for_fuzzy_match(original_content) : original_content;
// uniqueness check always uses fuzzy-normalized text, so a whitespace-only duplicate still counts
std::vector<matched_edit> matched;
matched.reserve(edits.size());
for (size_t i = 0; i < edits.size(); i++) {
std::string needle = any_fuzzy ? normalize_for_fuzzy_match(edits[i].old_text) : edits[i].old_text;
size_t occurrences = count_occurrences(
normalize_for_fuzzy_match(original_content),
normalize_for_fuzzy_match(edits[i].old_text));
if (occurrences > 1) {
return {{"error", string_format(
"found %zu occurrences of edits[%zu].old_text in %s, it must be unique",
occurrences, i, path.c_str())}};
}
size_t idx = base_content.find(needle);
matched.push_back({i, idx, needle.size(), edits[i].new_text});
}
std::sort(matched.begin(), matched.end(), [](const matched_edit & a, const matched_edit & b) {
return a.match_index < b.match_index;
});
for (size_t i = 1; i < matched.size(); i++) {
if (matched[i - 1].match_index + matched[i - 1].match_length > matched[i].match_index) {
return {{"error", string_format(
"edits[%zu] and edits[%zu] overlap in %s; merge them into one edit or target disjoint regions",
matched[i - 1].edit_index, matched[i].edit_index, path.c_str())}};
}
}
std::string new_content = any_fuzzy
? apply_replacements_preserving_unchanged_lines(original_content, base_content, matched)
: apply_replacements(base_content, matched, 0);
if (new_content == original_content) {
return {{"error", "no changes made: the replacement(s) produced identical content"}};
}
if (!io->write_file(path, new_content)) {
return {{"error", "failed to write file: " + path}};
}
return {{"result", "file edited successfully"}, {"path", path}, {"edits_applied", (int) matched.size()}};
}
private:
// strip trailing whitespace, normalize smart quotes/dashes/spaces to ASCII
static std::string normalize_line_for_fuzzy_match(const std::string & line) {
size_t end = line.size();
while (end > 0 && (line[end - 1] == ' ' || line[end - 1] == '\t' || line[end - 1] == '\r')) {
end--;
}
std::string s = line.substr(0, end);
auto replace_all = [](std::string & str, const std::string & from, const std::string & to) {
if (from.empty()) return;
size_t pos = 0;
while ((pos = str.find(from, pos)) != std::string::npos) {
str.replace(pos, from.size(), to);
pos += to.size();
}
};
// smart single quotes -> '
for (unsigned char b : {0x98, 0x99, 0x9A, 0x9B}) {
replace_all(s, std::string("\xE2\x80") + (char) b, "'");
}
// smart double quotes -> "
for (unsigned char b : {0x9C, 0x9D, 0x9E, 0x9F}) {
replace_all(s, std::string("\xE2\x80") + (char) b, "\"");
}
// various dashes -> -
for (unsigned char b = 0x90; b <= 0x95; b++) {
replace_all(s, std::string("\xE2\x80") + (char) b, "-");
}
replace_all(s, "\xE2\x88\x92", "-"); // minus sign
// special spaces -> ' '
replace_all(s, "\xC2\xA0", " "); // no-break space
for (unsigned char b = 0x82; b <= 0x8A; b++) {
replace_all(s, std::string("\xE2\x80") + (char) b, " ");
}
replace_all(s, "\xE2\x80\xAF", " "); // narrow no-break space
replace_all(s, "\xE2\x81\x9F", " "); // medium mathematical space
replace_all(s, "\xE3\x80\x80", " "); // ideographic space
return s;
}
// applies the per-line transform above to every line; preserves line count/positions
static std::string normalize_for_fuzzy_match(const std::string & content) {
std::string result;
result.reserve(content.size());
size_t start = 0;
while (true) {
size_t nl = content.find('\n', start);
bool is_last = nl == std::string::npos;
std::string line = is_last ? content.substr(start) : content.substr(start, nl - start);
result += normalize_line_for_fuzzy_match(line);
if (is_last) break;
result += '\n';
start = nl + 1;
}
return result;
}
// lines with trailing '\n' kept, so untouched ones can be reconstructed verbatim
static std::vector<std::string> split_lines_with_endings(const std::string & content) {
std::vector<std::string> lines;
size_t start = 0;
while (start < content.size()) {
size_t nl = content.find('\n', start);
if (nl == std::string::npos) {
lines.push_back(content.substr(start));
break;
}
lines.push_back(content.substr(start, nl - start + 1));
start = nl + 1;
}
return lines;
}
struct line_span {
size_t start;
size_t end;
};
static std::vector<line_span> get_line_spans(const std::string & content) {
std::vector<line_span> spans;
size_t offset = 0;
for (const auto & line : split_lines_with_endings(content)) {
spans.push_back({offset, offset + line.size()});
offset += line.size();
}
return spans;
}
// count non-overlapping occurrences of `needle` in `content`
static size_t count_occurrences(const std::string & content, const std::string & needle) {
if (needle.empty()) return 0;
size_t count = 0, pos = 0;
while ((pos = content.find(needle, pos)) != std::string::npos) {
count++;
pos += needle.size();
}
return count;
}
struct matched_edit {
size_t edit_index;
size_t match_index; // offset into the "base content" (see below)
size_t match_length;
std::string new_text;
};
// replacements must be sorted ascending by match_index and non-overlapping
static std::string apply_replacements(
const std::string & content,
const std::vector<matched_edit> & replacements,
size_t offset) {
std::string result = content;
for (auto it = replacements.rbegin(); it != replacements.rend(); ++it) {
size_t local_index = it->match_index - offset;
result = result.substr(0, local_index) + it->new_text + result.substr(local_index + it->match_length);
}
return result;
}
// widen a replacement's byte range to the line(s) of `lines` it touches
static bool get_replacement_line_range(
const std::vector<line_span> & lines,
size_t match_index, size_t match_length,
size_t & out_start_line, size_t & out_end_line /* exclusive */) {
size_t replacement_start = match_index;
size_t replacement_end = match_index + match_length;
size_t start_line = (size_t) -1;
for (size_t i = 0; i < lines.size(); i++) {
if (replacement_start >= lines[i].start && replacement_start < lines[i].end) {
start_line = i;
break;
}
}
if (start_line == (size_t) -1) return false;
size_t end_line = start_line;
while (end_line < lines.size() && lines[end_line].end < replacement_end) {
end_line++;
}
if (end_line >= lines.size()) return false;
out_start_line = start_line;
out_end_line = end_line + 1;
return true;
}
// like apply_replacements, but untouched lines come from `original_content`
static std::string apply_replacements_preserving_unchanged_lines(
const std::string & original_content,
const std::string & base_content,
const std::vector<matched_edit> & replacements /* ascending, non-overlapping */) {
auto original_lines = split_lines_with_endings(original_content);
auto base_lines = get_line_spans(base_content);
struct group {
size_t start_line;
size_t end_line; // exclusive
std::vector<matched_edit> reps;
};
std::vector<group> groups;
for (const auto & rep : replacements) {
size_t start_line = 0, end_line = 0;
get_replacement_line_range(base_lines, rep.match_index, rep.match_length, start_line, end_line);
if (!groups.empty() && start_line < groups.back().end_line) {
groups.back().end_line = std::max(groups.back().end_line, end_line);
groups.back().reps.push_back(rep);
} else {
groups.push_back({start_line, end_line, {rep}});
}
}
size_t original_line_index = 0;
std::string result;
for (auto & g : groups) {
for (size_t i = original_line_index; i < g.start_line; i++) {
result += original_lines[i];
}
size_t group_start_offset = base_lines[g.start_line].start;
size_t group_end_offset = base_lines[g.end_line - 1].end;
std::string slice = base_content.substr(group_start_offset, group_end_offset - group_start_offset);
result += apply_replacements(slice, g.reps, group_start_offset);
original_line_index = g.end_line;
}
for (size_t i = original_line_index; i < original_lines.size(); i++) {
result += original_lines[i];
}
return result;
}
};
//
// get_datetime: returns the current date and time
//
struct server_tool_get_datetime : server_tool {
server_tool_get_datetime() {
name = "get_datetime";
display_name = "Get Date & Time";
permission_write = false;
}
json get_definition() const override {
return {
{"type", "function"},
{"function", {
{"name", name},
{"description", "Returns the current date and time"},
}},
};
}
json invoke(json, server_tool::stream *) const override {
auto now = std::chrono::system_clock::now();
auto time = std::chrono::system_clock::to_time_t(now);
return {{"result", std::ctime(&time)}};
}
};
struct server_tool_stream_result : server_task_result {
std::string chunk;
bool done = false;
std::string error_msg;
json to_json() override {
if (!done) {
return {{"chunk", chunk}};
} else {
json result = {{"done", true}};
if (!error_msg.empty()) {
result["error"] = error_msg;
}
return result;
}
}
};
void server_tool::stream::push(const std::string & chunk) {
if (chunk.empty()) return;
auto r = std::make_unique<server_tool_stream_result>();
r->id = id;
r->chunk = chunk;
qr.send(std::move(r));
}
struct server_tools_res : server_http_res {
std::thread worker;
server_response * qr = nullptr; // set only for streaming responses
int id = -1;
~server_tools_res() override {
if (worker.joinable()) {
worker.join();
}
if (qr) {
qr->remove_waiting_task_id(id);
}
}
};
static server_tool & find_tool(std::vector<std::unique_ptr<server_tool>> & tools, const std::string & name, bool require_stream) {
for (auto & t : tools) {
if (t->name == name) {
if (require_stream && !t->support_stream) {
throw std::invalid_argument(string_format("tool \"%s\" does not support stream = true", name.c_str()));
}
return *t;
}
}
throw std::invalid_argument(string_format("unknown tool \"%s\"", name.c_str()));
}
//
// public API
//
static std::vector<std::unique_ptr<server_tool>> build_tools() {
std::vector<std::unique_ptr<server_tool>> tools;
tools.push_back(std::make_unique<server_tool_read_file>());
tools.push_back(std::make_unique<server_tool_file_glob_search>());
tools.push_back(std::make_unique<server_tool_grep_search>());
tools.push_back(std::make_unique<server_tool_exec_shell_command>());
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>());
return tools;
}
void server_tools::setup(const std::vector<std::string> & enabled_tools) {
if (!enabled_tools.empty()) {
std::unordered_set<std::string> enabled_set(enabled_tools.begin(), enabled_tools.end());
auto all_tools = build_tools();
// collect all known tool names for validation
std::vector<std::string> known_names;
known_names.reserve(all_tools.size());
for (const auto & t : all_tools) {
known_names.push_back(t->name);
}
// validate that every requested tool is known
for (const auto & name : enabled_tools) {
if (name == "all") continue;
if (std::find(known_names.begin(), known_names.end(), name) == known_names.end()) {
throw std::runtime_error(string_format(
"unknown tool \"%s\". available tools: %s",
name.c_str(),
string_join(known_names, ", ").c_str()));
}
}
tools.clear();
for (auto & t : all_tools) {
if (enabled_set.count(t->name) > 0 || enabled_set.count("all") > 0) {
tools.push_back(std::move(t));
}
}
}
handle_get = [this](const server_http_req &) -> server_http_res_ptr {
auto res = std::make_unique<server_http_res>();
try {
json result = json::array();
for (const auto & t : tools) {
result.push_back(t->to_json());
}
res->data = safe_json_to_str(result);
} catch (const std::exception & e) {
SRV_ERR("got exception: %s\n", e.what());
res->status = 500;
res->data = safe_json_to_str(format_error_response(e.what(), ERROR_TYPE_SERVER));
}
return res;
};
handle_post = [this](const server_http_req & req) -> server_http_res_ptr {
auto res = std::make_unique<server_tools_res>();
try {
json body = json::parse(req.body);
std::string tool_name = body.at("tool").get<std::string>();
json params = body.value("params", json::object());
bool stream = body.value("stream", false);
server_tool & tool = find_tool(tools, tool_name, stream);
if (stream) {
int id = res_id.fetch_add(1);
queue_res.add_waiting_task_id(id);
res->qr = &queue_res;
res->id = id;
res->worker = std::thread([this, id, &req, &tool, params]() mutable {
server_tool::stream st{queue_res, id, [&req]() {
return !req.should_stop();
}};
auto done = std::make_unique<server_tool_stream_result>();
try {
tool.invoke(params, &st);
} catch (const std::exception & e) {
done->error_msg = e.what();
} catch (...) {
done->error_msg = "An unknown error occurred";
}
done->id = st.id;
done->done = true;
st.qr.send(std::move(done));
});
res->content_type = "text/event-stream";
res->status = 200;
res->next = [this, id](std::string & output) -> bool {
auto result = queue_res.recv(id);
auto * r = dynamic_cast<server_tool_stream_result *>(result.get());
GGML_ASSERT(r != nullptr);
output = "data: " + safe_json_to_str(r->to_json()) + "\n\n";
if (r->done) {
queue_res.remove_waiting_task_id(id);
return false;
}
return true;
};
} else {
json result = tool.invoke(params, nullptr);
res->status = 200;
res->data = safe_json_to_str(result);
}
} catch (const json::exception & e) {
res->status = 400;
res->data = safe_json_to_str(format_error_response(e.what(), ERROR_TYPE_INVALID_REQUEST));
} catch (const std::invalid_argument & e) {
res->status = 404;
res->data = safe_json_to_str(format_error_response(e.what(), ERROR_TYPE_INVALID_REQUEST));
} catch (const std::exception & e) {
SRV_ERR("got exception: %s\n", e.what());
res->status = 500;
res->data = safe_json_to_str(format_error_response(e.what(), ERROR_TYPE_SERVER));
}
return res;
};
}
|