Merge remote-tracking branch 'upstream/master' into xsn/server_docker_isolate

tools/server/server-tools.cpp

@@ -11,18 +11,60 @@
 #include <atomic>
 #include <cstring>
 #include <cstdint>
+#include <cstdlib>
 #include <algorithm>
 #include <unordered_set>
+#include <tuple>
 #include <functional>
 #include <memory>
 #include <mutex>
 
+#if defined(_WIN32)
+#   ifndef NOMINMAX
+#       define NOMINMAX
+#   endif
+#   include <windows.h>
+#endif
+
 namespace fs = std::filesystem;
 
 //
 // internal helpers
 //
 
+// a child process writes in the OEM code page, so accented output would reach
+// the JSON layer as invalid bytes. run() spawns without a console, so the
+// console code page never applies
+static std::string console_output_to_utf8(const std::string & text) {
+#if defined(_WIN32)
+    // a chunk can end mid sequence, so the incomplete tail is dropped first
+    if (text.empty() || is_valid_utf8(text.substr(0, validate_utf8(text)))) {
+        // never decode twice a child that already emits UTF-8
+        return text;
+    }
+
+    const UINT cp = GetOEMCP();
+
+    // fail rather than emit replacement characters when the code page is wrong
+    const int wide_len = MultiByteToWideChar(cp, MB_ERR_INVALID_CHARS, text.data(), (int) text.size(), nullptr, 0);
+    if (wide_len <= 0) {
+        return text;
+    }
+    std::wstring wide(wide_len, L'\0');
+    MultiByteToWideChar(cp, MB_ERR_INVALID_CHARS, text.data(), (int) text.size(), wide.data(), wide_len);
+
+    const int utf8_len = WideCharToMultiByte(CP_UTF8, 0, wide.data(), wide_len, nullptr, 0, nullptr, nullptr);
+    if (utf8_len <= 0) {
+        return text;
+    }
+    std::string utf8(utf8_len, '\0');
+    WideCharToMultiByte(CP_UTF8, 0, wide.data(), wide_len, utf8.data(), utf8_len, nullptr, nullptr);
+    return utf8;
+#else
+    return text;
+#endif
+}
+
 json server_tool::to_json() const {
     return {
         {"display_name", display_name},
@@ -36,7 +78,56 @@ json server_tool::to_json() const {
 }
 
 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
+// budget for one listing call, shared by the git and walker paths
+static constexpr int SERVER_TOOL_LIST_ENTRIES_TIMEOUT = 15; // seconds
+
+// entry kinds a directory listing may return
+enum class list_kind {
+    files, // regular files only
+    dirs,  // directories only
+    all,   // both
+};
+
+// a narrow path uses the active code page on Windows, so every crossing between
+// a std::string (always UTF-8 here) and fs::path is converted explicitly
+static fs::path path_from_utf8(const std::string & s) {
+    return fs::u8path(s);
+}
+
+// '/' separators on every platform: Windows accepts them, the web UI needs them
+static std::string path_to_utf8(const fs::path & p) {
+    const auto s = p.generic_u8string();
+    return std::string(s.begin(), s.end());
+}
+
+// home directory, read once at first use (getenv is not thread safe against setenv)
+static const std::string & home_dir() {
+    static const std::string home = [] {
+#ifdef _WIN32
+        // the narrow getenv would return the profile path in the active code page
+        const wchar_t * w = _wgetenv(L"HOME");
+        if (w == nullptr) w = _wgetenv(L"USERPROFILE");
+        return w ? path_to_utf8(fs::path(w)) : std::string();
+#else
+        const char * h = getenv("HOME");
+        return h ? std::string(h) : std::string();
+#endif
+    }();
+    return home;
+}
+
+static std::string expand_home(const std::string & path) {
+    if (path.empty() || path[0] != '~') return path;
+    if (path.size() > 1 && path[1] != '/' && path[1] != '\\') return path;
+    const std::string & home = home_dir();
+    if (home.empty()) return path;
+    return home + path.substr(1);
+}
+
+// depth of a '/'-separated relative path: "a/b/c" is 3
+static int entry_depth(const std::string & rel) {
+    return 1 + (int) std::count(rel.begin(), rel.end(), '/');
+}
 
 class tools_io {
 public:
@@ -53,8 +144,20 @@ public:
     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;
+    // resolve `path` against the IO's working directory; absolute paths are returned unchanged
+    virtual std::string resolve(const std::string & path) const = 0;
+    struct list_entry {
+        std::string rel; // '/'-separated, relative to `base`
+        bool is_dir = false;
+    };
+    struct list_result {
+        std::vector<list_entry> entries;
+        std::string err;        // set when `base` is not a directory
+        bool truncated = false; // set when the walk could not see everything
+    };
+    // entries relative to `base`, which must already be resolved (absolute)
+    // max_depth == 0 means unlimited, 1 means direct children of `base` only
+    virtual list_result list_entries(const std::string & base, int max_depth, list_kind kind) 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(
@@ -114,14 +217,14 @@ static tools_io::exec_result run_subprocess(
                 size_t len = strlen(buf);
                 if (output.size() + len <= max_output) {
                     output.append(buf, len);
-                    if (on_chunk && !on_chunk(std::string(buf, len))) {
+                    if (on_chunk && !on_chunk(console_output_to_utf8(std::string(buf, len)))) {
                         proc.terminate();
                         break;
                     }
                 } else {
                     size_t remaining = max_output - output.size();
                     output.append(buf, remaining);
-                    if (on_chunk && remaining > 0) on_chunk(std::string(buf, remaining));
+                    if (on_chunk && remaining > 0) on_chunk(console_output_to_utf8(std::string(buf, remaining)));
                     truncated = true;
                 }
             }
@@ -135,7 +238,7 @@ static tools_io::exec_result run_subprocess(
 
     res.exit_code = proc.join();
 
-    res.output    = output;
+    res.output    = console_output_to_utf8(output);
     res.timed_out = timed_out.load();
     if (truncated) {
         res.output += "\n[output truncated]";
@@ -148,24 +251,50 @@ public:
     // cwd, if non-empty, is used to resolve relative paths and as the working directory for run()
     explicit tools_io_basic(std::string cwd = "") : cwd(std::move(cwd)) {}
 
+    // expands a leading `~`, then resolves `path` against `cwd` (or the server
+    // working directory when `cwd` is unset); the result is always absolute
+    std::string resolve(const std::string & path) const override {
+        const std::string p = expand_home(path);
+
+        fs::path full = path_from_utf8(p);
+        if (!full.is_absolute()) {
+            if (cwd.empty()) {
+                std::error_code ec;
+                const fs::path cur = fs::current_path(ec);
+                if (ec) return p;
+                full = cur / full;
+            } else {
+                full = path_from_utf8(cwd) / full;
+            }
+        }
+
+        // drop "." and ".." so they never reach git or the client
+        full = full.lexically_normal();
+        // a trailing ".." normalizes to a path that ends with a separator
+        if (!full.has_filename() && full != full.root_path()) {
+            full = full.parent_path();
+        }
+        return path_to_utf8(full);
+    }
+
     bool is_directory(const std::string & path) const override {
         std::error_code ec;
-        return fs::is_directory(resolve(path), ec) && !ec;
+        return fs::is_directory(path_from_utf8(resolve(path)), ec) && !ec;
     }
 
     bool is_regular_file(const std::string & path) const override {
         std::error_code ec;
-        return fs::is_regular_file(resolve(path), ec) && !ec;
+        return fs::is_regular_file(path_from_utf8(resolve(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(resolve(path), ec);
+        out_size = fs::file_size(path_from_utf8(resolve(path)), ec);
         return !ec;
     }
 
     bool read_file(const std::string & path, std::string & out) const override {
-        std::ifstream f(resolve(path), std::ios::binary);
+        std::ifstream f(path_from_utf8(resolve(path)), std::ios::binary);
         if (!f) return false;
         std::ostringstream ss;
         ss << f.rdbuf();
@@ -175,7 +304,7 @@ public:
 
     bool write_file(const std::string & path, const std::string & content) const override {
         std::error_code ec;
-        fs::path fpath(resolve(path));
+        fs::path fpath = path_from_utf8(resolve(path));
         if (fpath.has_parent_path()) {
             fs::create_directories(fpath.parent_path(), ec);
             if (ec) return false;
@@ -186,34 +315,41 @@ public:
         return (bool) f;
     }
 
-    std::vector<std::string> list_files(const std::string & base, std::string & err) const override {
-        err.clear();
-        std::string abs_base = resolve(base);
-        if (!is_directory(base)) {
-            err = "path does not exist or is not a directory: " + base;
-            return {};
+    list_result list_entries(const std::string & base, int max_depth, list_kind kind) const override {
+        list_result out;
+
+        std::error_code ec;
+        if (!fs::is_directory(base, ec) || ec) {
+            out.err = "path does not exist or is not a directory";
+            return out;
         }
 
-        auto res = run(
-            {"git", "-C", abs_base, "ls-files", "--cached", "--others", "--exclude-standard"},
-            SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, SERVER_TOOL_GIT_LS_FILES_TIMEOUT);
+        const auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(SERVER_TOOL_LIST_ENTRIES_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);
+        // git ls-files cannot list directories; use the walker when they are requested
+        if (kind == list_kind::files) {
+            auto res = run(
+                {"git", "-C", base, "ls-files", "--cached", "--others", "--exclude-standard"},
+                SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, SERVER_TOOL_LIST_ENTRIES_TIMEOUT);
+
+            if (res.exit_code == 0 && !res.timed_out) {
+                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 (max_depth > 0 && entry_depth(line) > max_depth) continue;
+                    if (is_regular_file(path_to_utf8(path_from_utf8(base) / path_from_utf8(line)))) {
+                        out.entries.push_back({line, false});
+                    }
                 }
+                return out;
             }
-            return result;
         }
 
-        return list_files_fallback(abs_base);
+        out.entries = list_entries_fallback(base, max_depth, kind, deadline, out.truncated);
+        return out;
     }
 
     exec_result run(
@@ -227,12 +363,40 @@ public:
 private:
     std::string cwd;
 
-    // resolves `path` against `cwd` if `path` is relative and `cwd` is set; otherwise returns `path` unchanged
-    std::string resolve(const std::string & path) const {
-        if (cwd.empty() || fs::path(path).is_absolute()) {
-            return path;
+    // a link can point back to an ancestor and loop forever, so it is never walked
+    static bool is_link(const fs::directory_entry & entry) {
+        std::error_code ec;
+        if (entry.is_symlink(ec) || ec) {
+            return true;
         }
-        return (fs::path(cwd) / path).string();
+#if defined(_WIN32)
+        // a junction looks like a plain directory to std::filesystem, so read the reparse tag
+        WIN32_FIND_DATAW data;
+        const HANDLE h = FindFirstFileW(entry.path().c_str(), &data);
+        if (h == INVALID_HANDLE_VALUE) {
+            return false;
+        }
+        FindClose(h);
+        if ((data.dwFileAttributes & FILE_ATTRIBUTE_REPARSE_POINT) == 0) {
+            return false;
+        }
+        // other reparse points (cloud placeholder, dedup stub) are real directories
+        return data.dwReserved0 == IO_REPARSE_TAG_SYMLINK || data.dwReserved0 == IO_REPARSE_TAG_MOUNT_POINT;
+#else
+        return false;
+#endif
+    }
+
+    // NTFS is case insensitive, so Build and build are the same directory
+    static std::string get_effective_name(const std::string & fname) {
+#if defined(_WIN32)
+        std::string lowered = fname;
+        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
+                       [](unsigned char c) { return (char) std::tolower(c); });
+        return lowered;
+#else
+        return fname;
+#endif
     }
 
     static const std::unordered_set<std::string> & junk_dir_names() {
@@ -243,28 +407,57 @@ private:
         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<list_entry> list_entries_fallback(const std::string & base, int max_depth, list_kind kind,
+                                                  std::chrono::steady_clock::time_point deadline, bool & truncated) const {
+        std::vector<list_entry> result;
 
-        std::vector<std::pair<fs::path, fs::path>> stack;
-        stack.emplace_back(fs::path(base), fs::path());
+        std::vector<std::tuple<fs::path, fs::path, int>> stack;
+        stack.emplace_back(path_from_utf8(base), fs::path(), 0);
 
         while (!stack.empty()) {
-            auto [dir, rel_dir] = stack.back();
+            if (std::chrono::steady_clock::now() >= deadline) {
+                truncated = true;
+                return result;
+            }
+
+            auto [dir, rel_dir, depth] = std::move(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 ec;
+            // step the iterator by hand: the throwing increment escapes on a directory that goes away
+            fs::directory_iterator it(dir, fs::directory_options::skip_permission_denied, ec);
+            // permission errors are skipped above, so this is a subtree the caller never sees
+            if (ec) {
+                truncated = true;
+                continue;
+            }
+            for (const fs::directory_iterator end; it != end; it.increment(ec)) {
+                if (ec) {
+                    truncated = true;
+                    break;
+                }
+                if (std::chrono::steady_clock::now() >= deadline) {
+                    truncated = true;
+                    return result;
+                }
+                const fs::directory_entry & entry = *it;
+                const fs::path fname = entry.path().filename();
                 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);
+                const bool is_dir = entry.is_directory(tec);
+                if (tec) continue;
+                if (is_dir) {
+                    if (kind == list_kind::dirs || kind == list_kind::all) {
+                        result.push_back({path_to_utf8(rel_dir / fname), true});
+                    }
+                    // junk directories stay selectable but are never walked: they can be enormous
+                    if (junk_dir_names().count(get_effective_name(path_to_utf8(fname))) > 0) continue;
+                    if (!is_link(entry) && (max_depth == 0 || depth + 1 < max_depth)) {
+                        stack.emplace_back(entry.path(), rel_dir / fname, depth + 1);
+                    }
                 } else if (entry.is_regular_file(tec)) {
-                    std::string rel = (rel_dir / fname).string();
-                    std::replace(rel.begin(), rel.end(), '\\', '/');
-                    result.push_back(rel);
+                    if (kind == list_kind::files || kind == list_kind::all) {
+                        result.push_back({path_to_utf8(rel_dir / fname), false});
+                    }
                 }
             }
         }
@@ -347,35 +540,42 @@ public:
         return ok;
     }
 
-    std::vector<std::string> list_files(const std::string & base, std::string & err) const override {
-        err.clear();
-        std::string abs_base = resolve(base);
+    list_result list_entries(const std::string & base, int max_depth, list_kind kind) const override {
+        list_result out;
+
+        const std::string abs_base = resolve(base);
         if (!is_directory(base)) {
-            err = "path does not exist or is not a directory: " + base;
-            return {};
+            out.err = "path does not exist or is not a directory";
+            return out;
         }
 
-        auto res = exec(
-            {"sh", "-c", "cd \"$1\" && git ls-files --cached --others --exclude-standard", "_", abs_base},
-            SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, true);
+        // git ls-files cannot list directories; use the walker when they are requested
+        if (kind == list_kind::files) {
+            auto res = exec(
+                {"sh", "-c", "cd \"$1\" && git ls-files --cached --others --exclude-standard", "_", abs_base},
+                SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, true);
 
-        if (res.exit_code == 0 && !res.timed_out) {
-            return split_lines(res.output, /*strip_dot_slash=*/false);
+            if (res.exit_code == 0 && !res.timed_out) {
+                for (const auto & rel : split_lines(res.output, /*strip_dot_slash=*/false)) {
+                    if (max_depth > 0 && entry_depth(rel) > max_depth) continue;
+                    out.entries.push_back({rel, false});
+                }
+                return out;
+            }
         }
 
-        static const char * prune_names[] = {
-            ".git", ".svn", ".hg", "node_modules", "__pycache__",
-            ".venv", "venv", "dist", "build", "target", ".cache", ".idea", ".vscode",
-        };
-        std::string prune_expr;
-        for (const char * n : prune_names) {
-            if (!prune_expr.empty()) prune_expr += " -o ";
-            prune_expr += std::string("-name ") + n;
+        if (kind == list_kind::dirs || kind == list_kind::all) {
+            for (auto & rel : find_entries(abs_base, max_depth, /*dirs=*/true, out.truncated)) {
+                out.entries.push_back({std::move(rel), true});
+            }
+        }
+        if (kind == list_kind::files || kind == list_kind::all) {
+            for (auto & rel : find_entries(abs_base, max_depth, /*dirs=*/false, out.truncated)) {
+                out.entries.push_back({std::move(rel), false});
+            }
         }
-        std::string find_cmd = "cd \"$1\" && find . \\( " + prune_expr + " \\) -prune -o -type f -print";
-        auto find_res = exec({"sh", "-c", find_cmd, "_", abs_base}, SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, true);
 
-        return split_lines(find_res.output, /*strip_dot_slash=*/true);
+        return out;
     }
 
     // wraps the command with an in-container `timeout`, since killing the local `docker exec` client
@@ -440,6 +640,32 @@ private:
         }
         return result;
     }
+
+    // one `find` pass in the container. junk directories stay selectable but are never descended into,
+    // and -mindepth/-maxdepth keep a busybox image working as well as a GNU one
+    std::vector<std::string> find_entries(const std::string & abs_base, int max_depth, bool dirs, bool & truncated) const {
+        static const char * junk_names[] = {
+            ".git", ".svn", ".hg", "node_modules", "__pycache__",
+            ".venv", "venv", "dist", "build", "target", ".cache", ".idea", ".vscode",
+        };
+
+        std::string prune_expr;
+        for (const char * n : junk_names) {
+            if (!prune_expr.empty()) prune_expr += " -o ";
+            prune_expr += std::string("-name ") + n;
+        }
+
+        std::string cmd = "cd \"$1\" && find . -mindepth 1";
+        if (max_depth > 0) {
+            cmd += " -maxdepth " + std::to_string(max_depth);
+        }
+        cmd += " \\( " + prune_expr + " \\) -prune";
+        cmd += dirs ? " -print -o -type d -print" : " -o -type f -print";
+
+        auto res = exec({"sh", "-c", cmd, "_", abs_base}, SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, true);
+        truncated = truncated || res.timed_out;
+        return split_lines(res.output, /*strip_dot_slash=*/true);
+    }
 };
 
 static std::unique_ptr<tools_io> make_tools_io(const json & params) {
@@ -453,7 +679,7 @@ static std::unique_ptr<tools_io> make_tools_io(const json & params) {
 // 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());
+        return glob_match(pattern, path_to_utf8(path_from_utf8(rel_path).filename()));
     }
     if (pattern == "**" || pattern.rfind("**/", 0) == 0 || pattern.rfind('/', 0) == 0) {
         return glob_match(pattern, rel_path);
@@ -550,7 +776,10 @@ struct server_tool_read_file : server_tool {
 // file_glob_search: find files matching a glob pattern under a base directory
 //
 
-static constexpr size_t SERVER_TOOL_FILE_SEARCH_MAX_RESULTS = 100;
+static constexpr int SERVER_TOOL_FILE_SEARCH_MAX_RESULTS = 100;
+static constexpr const char * SERVER_TOOL_FILE_SEARCH_TYPE_FILE = "file";
+static constexpr const char * SERVER_TOOL_FILE_SEARCH_TYPE_DIR  = "dir";
+static constexpr const char * SERVER_TOOL_FILE_SEARCH_TYPE_ALL  = "all";
 
 struct server_tool_file_glob_search : server_tool {
     server_tool_file_glob_search() {
@@ -570,13 +799,18 @@ struct server_tool_file_glob_search : server_tool {
                     "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 \"**/\"."},
+                    "\"**/\" or a leading '/', it is automatically prefixed with \"**/\". "
+                    "Use type=\"dir\" or \"all\" to also list directories; directory entries are suffixed with '/' in the output. "
+                    "Note: directory listings do not apply .gitignore filtering."},
                 {"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"}}},
+                        {"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"}}},
+                        {"type",      {{"type", "string"},  {"description", "Entry type to return: \"file\" (default), \"dir\" or \"all\""}}},
+                        {"max_depth", {{"type", "integer"}, {"description", "Maximum depth to descend into subdirectories (default: 0 = unlimited; 1 = direct children only)"}}},
+                        {"limit",     {{"type", "integer"}, {"description", string_format("Maximum number of results to return, capped at %d (default %d)", SERVER_TOOL_FILE_SEARCH_MAX_RESULTS, SERVER_TOOL_FILE_SEARCH_MAX_RESULTS)}}},
                     }},
                     {"required", json::array({"path"})},
                 }},
@@ -585,30 +819,55 @@ struct server_tool_file_glob_search : server_tool {
     }
 
     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}};
+
+        const std::string path = params.at("path").get<std::string>();
+
+        std::string base      = io->resolve(path);
+        std::string include   = json_value(params, "include", std::string("**"));
+        std::string exclude   = json_value(params, "exclude", std::string(""));
+        std::string type      = json_value(params, "type",    std::string("file"));
+        int         max_depth = std::max(0, json_value(params, "max_depth", 0));
+        const int   limit_req = json_value(params, "limit", SERVER_TOOL_FILE_SEARCH_MAX_RESULTS);
+        if (limit_req < 1) {
+            return {{"error", "invalid limit: " + std::to_string(limit_req) + " (expected 1 or more)"}};
+        }
+        const int   limit     = std::min(limit_req, SERVER_TOOL_FILE_SEARCH_MAX_RESULTS);
+
+        list_kind kind;
+        if (type == SERVER_TOOL_FILE_SEARCH_TYPE_FILE) {
+            kind = list_kind::files;
+        } else if (type == SERVER_TOOL_FILE_SEARCH_TYPE_DIR) {
+            kind = list_kind::dirs;
+        } else if (type == SERVER_TOOL_FILE_SEARCH_TYPE_ALL) {
+            kind = list_kind::all;
+        } else {
+            return {{"error", "invalid type: " + type + " (expected \"file\", \"dir\" or \"all\")"}};
         }
 
-        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);
+        const auto listing = io->list_entries(base, max_depth, kind);
+        if (!listing.err.empty()) {
+            return {{"error", listing.err + ": " + path}};
+        }
+
+        std::vector<tools_io::list_entry> matches;
+        for (const auto & entry : listing.entries) {
+            if (!path_glob_match(include, entry.rel)) continue;
+            if (!exclude.empty() && path_glob_match(exclude, entry.rel)) continue;
+            matches.push_back(entry);
         }
 
         size_t total = matches.size();
-        size_t shown = std::min(total, SERVER_TOOL_FILE_SEARCH_MAX_RESULTS);
+        size_t shown = std::min(total, (size_t) limit);
 
         std::ostringstream output_text;
+        json entries_json = json::array();
         for (size_t i = 0; i < shown; i++) {
-            output_text << matches[i] << "\n";
+            output_text << matches[i].rel << (matches[i].is_dir ? "/" : "") << "\n";
+            entries_json.push_back({
+                {"path", matches[i].rel},
+                {"type", matches[i].is_dir ? "dir" : "file"},
+            });
         }
 
         output_text << "\n---\nTotal matches: " << total << "\n";
@@ -617,8 +876,16 @@ struct server_tool_file_glob_search : server_tool {
                 "[%zu results limit reached (%zu total matches). Refine the glob pattern to narrow the search.]\n",
                 shown, total);
         }
+        if (listing.truncated) {
+            output_text << "[results truncated: time budget or unreadable directory]\n";
+        }
 
-        return {{"plain_text_response", output_text.str()}};
+        // `base` is always absolute (resolve falls back to the server cwd), so
+        // API clients (e.g. the web UI picker) can join the relative entries
+        // into absolute paths. `plain_text_response` is what the model sees;
+        // `entries` is the same data as structured JSON for the UI picker,
+        // which reads `entries`/`base` instead of re-parsing the text.
+        return {{"plain_text_response", output_text.str()}, {"entries", entries_json}, {"base", base}};
     }
 };
 
@@ -701,18 +968,18 @@ struct server_tool_grep_search : server_tool {
         // 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}};
+        const std::string abs_path = io->resolve(path);
+        if (io->is_regular_file(abs_path)) {
+            files.emplace_back(abs_path, path);
+        } else if (io->is_directory(abs_path)) {
+            const auto listing = io->list_entries(abs_path, 0, list_kind::files);
+            if (!listing.err.empty()) {
+                return {{"error", listing.err + ": " + path}};
             }
-            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);
+            for (const auto & entry : listing.entries) {
+                if (!path_glob_match(include, entry.rel)) continue;
+                if (!exclude.empty() && path_glob_match(exclude, entry.rel)) continue;
+                files.emplace_back(path_to_utf8(path_from_utf8(abs_path) / path_from_utf8(entry.rel)), entry.rel);
             }
         } else {
             return {{"error", "path does not exist: " + path}};
@@ -1285,6 +1552,9 @@ struct server_tool_get_datetime : server_tool {
 // get_info: returns runtime info (OS name/version and cwd)
 //
 
+static constexpr size_t SERVER_TOOL_GET_INFO_MAX_OUTPUT = 4096;
+static constexpr int    SERVER_TOOL_GET_INFO_TIMEOUT    = 5; // seconds
+
 struct server_tool_get_info : server_tool {
     server_tool_get_info() {
         name = "get_info";
@@ -1318,13 +1588,13 @@ struct server_tool_get_info : server_tool {
         std::vector<std::string> args = {"uname", "-a"};
 #endif
 
-        auto res = io->run(args, 4096, 5);
+        auto res = io->run(args, SERVER_TOOL_GET_INFO_MAX_OUTPUT, SERVER_TOOL_GET_INFO_TIMEOUT);
         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();
+            cwd = path_to_utf8(fs::current_path(ec));
         }
 
         return {