feat: upload and extract zip/tar archives into workspace (#525)

- Add extract_archive() with zip-slip and tar-slip protection
- New /api/upload/extract endpoint for archive uploads
- Auto-detect archive files (.zip, .tar.gz, .tgz, .bz2, .xz)
- Archives extracted into named subfolder (avoids overwrites)
- Workspace file tree auto-refreshes after extraction
- Archive extensions added to file picker accept list
- i18n: archive_extracted key in all 7 locales

Security: path traversal blocked via resolve() prefix check,
matching existing safe_resolve_ws() sandbox pattern.

api/routes.py

@@ -413,7 +413,7 @@ from api.workspace import (
     _is_blocked_system_path,
     _workspace_blocked_roots,
 )
-from api.upload import handle_upload, handle_transcribe
+from api.upload import handle_upload, handle_upload_extract, handle_transcribe
 from api.streaming import _sse, _run_agent_streaming, cancel_stream
 from api.providers import get_providers, set_provider_key, remove_provider_key
 from api.onboarding import (
@@ -1196,6 +1196,8 @@ def handle_post(handler, parsed) -> bool:
 
     if parsed.path == "/api/upload":
         return handle_upload(handler)
+    if parsed.path == "/api/upload/extract":
+        return handle_upload_extract(handler)
 
     if parsed.path == "/api/transcribe":
         return handle_transcribe(handler)

api/upload.py

@@ -88,6 +88,98 @@ def handle_upload(handler):
         return j(handler, {'error': 'Upload failed'}, status=500)
 
 
+def extract_archive(file_bytes: bytes, filename: str, workspace: Path):
+    """Extract a zip or tar archive into the workspace.
+
+    Returns a dict with ``extracted`` (int), ``files`` (list[str]).
+    Raises ValueError on zip-slip or unsupported format.
+    """
+    import zipfile, tarfile, io, os
+
+    name = Path(filename).name
+    stem = Path(filename).stem  # strip .zip / .tar.gz etc.
+
+    if name.lower().endswith(('.zip',)):
+        _mode = 'zip'
+    elif name.lower().endswith(('.tar', '.tar.gz', '.tgz', '.tar.bz2', '.tbz2', '.tar.xz', '.txz')):
+        _mode = 'tar'
+    else:
+        raise ValueError(f'Unsupported archive format: {filename}')
+
+    # Determine destination directory — use archive stem as folder name
+    dest_dir = safe_resolve_ws(workspace, stem)
+    # Avoid overwriting existing files by appending a suffix
+    if dest_dir.exists():
+        import string, random
+        while dest_dir.exists():
+            suffix = ''.join(random.choices(string.digits, k=3))
+            dest_dir = dest_dir.with_name(stem + '_' + suffix)
+    dest_dir.mkdir(parents=True, exist_ok=True)
+
+    extracted_files = []
+
+    if _mode == 'zip':
+        with zipfile.ZipFile(io.BytesIO(file_bytes)) as zf:
+            for member in zf.infolist():
+                # Skip directories
+                if member.is_dir():
+                    continue
+                # Zip-slip protection
+                member_path = (dest_dir / member.filename).resolve()
+                if not str(member_path).startswith(str(dest_dir.resolve())):
+                    raise ValueError(f'Zip-slip blocked: {member.filename}')
+                member_path.parent.mkdir(parents=True, exist_ok=True)
+                with zf.open(member) as src, open(member_path, 'wb') as dst:
+                    dst.write(src.read())
+                extracted_files.append(str(member_path.relative_to(workspace.resolve())))
+
+    elif _mode == 'tar':
+        with tarfile.open(fileobj=io.BytesIO(file_bytes)) as tf:
+            for member in tf.getmembers():
+                if not member.isfile():
+                    continue
+                # Tar-slip protection
+                member_path = (dest_dir / member.name).resolve()
+                if not str(member_path).startswith(str(dest_dir.resolve())):
+                    raise ValueError(f'Tar-slip blocked: {member.name}')
+                member_path.parent.mkdir(parents=True, exist_ok=True)
+                with tf.extractfile(member) as src, open(member_path, 'wb') as dst:
+                    if src:
+                        dst.write(src.read())
+                extracted_files.append(str(member_path.relative_to(workspace.resolve())))
+
+    return {'extracted': len(extracted_files), 'files': extracted_files, 'dest': str(dest_dir)}
+
+
+def handle_upload_extract(handler):
+    """Handle archive upload and extraction."""
+    import traceback as _tb
+    try:
+        content_type = handler.headers.get('Content-Type', '')
+        content_length = int(handler.headers.get('Content-Length', 0) or 0)
+        if content_length > MAX_UPLOAD_BYTES:
+            return j(handler, {'error': f'File too large (max {MAX_UPLOAD_BYTES//1024//1024}MB)'}, status=413)
+        fields, files = parse_multipart(handler.rfile, content_type, content_length)
+        session_id = fields.get('session_id', '')
+        if 'file' not in files:
+            return j(handler, {'error': 'No file field in request'}, status=400)
+        filename, file_bytes = files['file']
+        if not filename:
+            return j(handler, {'error': 'No filename in upload'}, status=400)
+        try:
+            s = get_session(session_id)
+        except KeyError:
+            return j(handler, {'error': 'Session not found'}, status=404)
+        workspace = Path(s.workspace)
+        result = extract_archive(file_bytes, filename, workspace)
+        return j(handler, {'ok': True, **result})
+    except ValueError as e:
+        return j(handler, {'error': str(e)}, status=400)
+    except Exception:
+        print('[webui] upload extract error: ' + _tb.format_exc(), flush=True)
+        return j(handler, {'error': 'Archive extraction failed'}, status=500)
+
+
 def handle_transcribe(handler):
     import traceback as _tb
     temp_path = None

static/i18n.js

@@ -239,6 +239,7 @@ const LOCALES = {
     empty_dir: '(empty)',
     upload_failed: 'Upload failed: ',
     all_uploads_failed: (n) => `All ${n} upload(s) failed`,
+    archive_extracted: (n, c) => `Extracted ${n} file(s) from ${c} archive(s)`,
     session_pin: 'Pin conversation',
     session_unpin: 'Unpin conversation',
     session_pin_desc: 'Keep this conversation at the top',
@@ -865,6 +866,7 @@ const LOCALES = {
     empty_dir: '(пусто)',
     upload_failed: 'Не удалось загрузить: ',
     all_uploads_failed: (n) => `Не удалось загрузить все ${n} файлов`,
+    archive_extracted: (n, c) => `Извлечено ${n} файл(ов) из ${c} архив(ов)`,
     settings_title: 'Настройки',
     settings_save_btn: 'Сохранить настройки',
     settings_label_model: 'Модель по умолчанию',
@@ -1487,6 +1489,7 @@ const LOCALES = {
     empty_dir: '(vacío)',
     upload_failed: 'Error al subir: ',
     all_uploads_failed: (n) => `Fallaron las ${n} subida(s)`,
+    archive_extracted: (n, c) => `${n} archivo(s) extraído(s) de ${c} archivo(s) comprimido(s)`,
     // settings panel
     settings_title: 'Configuración',
     settings_save_btn: 'Guardar configuración',
@@ -2006,6 +2009,7 @@ const LOCALES = {
     model_not_found_label: 'Modell nicht gefunden',
     // commands.js
     cmd_help: 'Verfügbare Befehle auflisten',
+    archive_extracted: (n, c) => `${n} Datei(en) aus ${c} Archiv(en) entpackt`,
     cmd_clear: 'Konversationsverlauf löschen',
     cmd_compress: 'Kontext manuell komprimieren (Nutzung: /compress [Thema])',
     cmd_compact_alias: 'Alte Alias für /compress',
@@ -2641,6 +2645,7 @@ const LOCALES = {
     // onboarding
     onboarding_badge: '首次运行',
     onboarding_title: '欢迎使用 Hermes Web UI',
+    archive_extracted: (n, c) => `从 ${c} 个压缩包中解压了 ${n} 个文件`,
     onboarding_lead: '快速引导将验证 Hermes、保存真实的提供商配置、选择工作区和模型，并可选设置密码保护应用。',
     onboarding_back: '返回',
     onboarding_continue: '继续',
@@ -3179,6 +3184,7 @@ const LOCALES = {
     settings_saved: '\u8a2d\u5b9a\u5df2\u5132\u5b58',
     settings_save_failed: '\u5132\u5b58\u5931\u6557\uff1a',
     settings_load_failed: '\u8a2d\u5b9a\u52a0\u8f09\u5931\u6557\uff1a',
+    archive_extracted: (n, c) => `\u5f9e ${c} \u500b\u58d3\u7e2e\u5305\u4e2d\u89e3\u58d3\u7e2e\u4e86 ${n} \u500b\u6a94\u6848`,
     settings_saved_pw: '\u8a2d\u5b9a\u5df2\u5132\u5b58\uff0c\u5bc6\u78bc\u4fdd\u8b77\u5df2\u555f\u7528\uff0c\u7576\u524d\u700f\u89bd\u5668\u6703\u4fdd\u6301\u767b\u5165',
     settings_saved_pw_updated: '\u8a2d\u5b9a\u5df2\u5132\u5b58\uff0c\u5bc6\u78bc\u5df2\u66f4\u65b0',
     // login page
@@ -3869,6 +3875,7 @@ const LOCALES = {
     workspace_auto_create_folder: '폴더가 없으면 생성',
     folder_add_as_space_btn: '스페이스로 추가',
     folder_add_as_space_msg: '이 폴더를 워크스페이스 목록의 새 스페이스로 추가할까요?',
+    archive_extracted: (n, c) => `${c}개 압축 파일에서 ${n}개 파일 압축 해제됨`,
     folder_add_as_space_title: '스페이스로 추가할까요?',
     remove_title: 'Remove',
     empty_dir: '(비어 있음)',

static/index.html

@@ -323,7 +323,7 @@
         <textarea id="msg" rows="1" placeholder="Message Hermes…"></textarea>
         <div class="composer-footer">
           <div class="composer-left">
-            <input type="file" id="fileInput" multiple accept="image/*,text/*,application/pdf,application/json,application/vnd.ms-excel,application/vnd.openxmlformats-officedocument.spreadsheetml.sheet,application/msword,application/vnd.openxmlformats-officedocument.wordprocessingml.document,.md,.py,.js,.ts,.yaml,.yml,.toml,.csv,.sh,.txt,.log,.env,.xls,.xlsx,.doc,.docx" style="display:none">
+            <input type="file" id="fileInput" multiple accept="image/*,text/*,application/pdf,application/json,application/vnd.ms-excel,application/vnd.openxmlformats-officedocument.spreadsheetml.sheet,application/msword,application/vnd.openxmlformats-officedocument.wordprocessingml.document,.md,.py,.js,.ts,.yaml,.yml,.toml,.csv,.sh,.txt,.log,.env,.xls,.xlsx,.doc,.docx,.zip,.tar,.gz,.tgz,.bz2,.xz" style="display:none">
             <button class="icon-btn" id="btnAttach" title="Attach files">
               <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M21.44 11.05l-9.19 9.19a6 6 0 0 1-8.49-8.49l9.19-9.19a4 4 0 0 1 5.66 5.66l-9.2 9.19a2 2 0 0 1-2.83-2.83l8.49-8.48"/></svg>
             </button>

static/ui.js

@@ -88,6 +88,7 @@ document.addEventListener('click', e => {
 });
 
 const _IMAGE_EXTS=/\.(png|jpg|jpeg|gif|webp|bmp|ico|avif)$/i;
+const _ARCHIVE_EXTS=/\.(zip|tar|tar\.gz|tgz|tar\.bz2|tbz2|tar\.xz|txz)$/i;
 
 // Dynamic model labels -- populated by populateModelDropdown(), fallback to static map
 let _dynamicModelLabels={};
@@ -3665,17 +3666,27 @@ async function uploadPendingFiles(){
     const f=S.pendingFiles[i];const fd=new FormData();
     fd.append('session_id',S.session.session_id);fd.append('file',f,f.name);
     try{
-      const res=await fetch(new URL('api/upload',location.href).href,{method:'POST',credentials:'include',body:fd});
+      const isArchive=_ARCHIVE_EXTS.test(f.name);
+      const url=new URL(isArchive?'api/upload/extract':'api/upload',location.href).href;
+      const res=await fetch(url,{method:'POST',credentials:'include',body:fd});
       if(_redirectIfUnauth(res)) return;
       if(!res.ok){const err=await res.text();throw new Error(err);}
       const data=await res.json();
       if(data.error)throw new Error(data.error);
-      names.push({name: data.filename, path: data.path});
+      if(isArchive){
+        names.push({name: data.dest, path: data.dest, extracted: data.extracted});
+        if(typeof loadDir==='function')loadDir(S.currentDir||'.');
+      }else{
+        names.push({name: data.filename, path: data.path});
+      }
     }catch(e){failures++;setStatus(`\u274c ${t('upload_failed')}${f.name} \u2014 ${e.message}`);}
     bar.style.width=`${Math.round((i+1)/total*100)}%`;
   }
   barWrap.classList.remove('active');bar.style.width='0%';
   S.pendingFiles=[];renderTray();
   if(failures===total&&total>0)throw new Error(t('all_uploads_failed',total));
+  // Show extraction summary
+  const extracted=names.filter(n=>n.extracted);
+  if(extracted.length)showToast(t('archive_extracted',extracted.reduce((s,n)=>s+n.extracted,0),extracted.length));
   return names;
 }