new Dockerfile, successfully integrated user interface browser, novnc

.gitignore

@@ -12,6 +12,9 @@ __pycache__/
 .env.development
 .env.test
 docker-compose.override.yml
+
+test_browser.py
+
 export*
 __pycache__/model_tools.cpython-310.pyc
 __pycache__/web_tools.cpython-310.pyc

Dockerfile

@@ -1,21 +1,24 @@
-FROM nikolaik/python-nodejs:python3.11-nodejs20
+FROM python:3.12-slim
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 
 RUN apt-get update && apt-get install -y \
-    curl \
-    git \
-    docker.io \
+    curl git docker.io \
     && rm -rf /var/lib/apt/lists/*
 
-RUN mkdir -p /app/hermes_code /app/hermes_data
+ENV UV_PROJECT_ENVIRONMENT=/app/venv \
+    HERMES_HOME=/app/hermes_data \
+    PYTHONUNBUFFERED=1 \
+    PATH="/app/venv/bin:$PATH"
 
+RUN mkdir -p /app/hermes_code /app/hermes_data
 WORKDIR /app/hermes_code
 
-COPY pyproject.toml requirements.txt* ./
-
-RUN pip install --no-cache-dir browser-use playwright python-telegram-bot
+COPY pyproject.toml uv.lock ./
+RUN uv sync --frozen --no-install-project --extra tg
 
 COPY . .
 
-RUN pip install -e .
+RUN uv sync --frozen --extra tg
 
 CMD ["python", "-m", "gateway.run"]

browser_env/Dockerfile.browser

@@ -0,0 +1,27 @@
+FROM debian:bookworm-slim
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    chromium \
+    xvfb \
+    fluxbox \
+    x11vnc \
+    novnc \
+    websockify \
+    dbus-x11 \
+    socat \
+    procps \
+    curl \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /src
+RUN mkdir -p /src/browser_data
+
+COPY entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+
+EXPOSE 6080 9222
+
+ENTRYPOINT ["/entrypoint.sh"]

browser_env/entrypoint.sh

@@ -0,0 +1,39 @@
+export DISPLAY=:99
+
+mkdir -p /var/run/dbus
+dbus-uuidgen > /var/lib/dbus/machine-id
+dbus-daemon --config-file=/usr/share/dbus-1/system.conf --print-address &
+
+Xvfb :99 -screen 0 1280x720x16 -ac +extension GLX +render -noreset &
+sleep 2
+
+fluxbox &
+x11vnc -display :99 -nopw -listen 0.0.0.0 -xkb -forever -shared &
+websockify --web=/usr/share/novnc/ 6080 localhost:5900 &
+
+socat TCP-LISTEN:9222,fork,reuseaddr TCP:127.0.0.1:9223 &
+
+echo "--- Запуск Chromium в режиме Local-Only (Port 9223) ---"
+
+while true; do
+  rm -f /src/browser_data/SingletonLock
+  
+  chromium \
+    --no-sandbox \
+    --disable-dev-shm-usage \
+    --remote-debugging-port=9223 \
+    --remote-debugging-address=127.0.0.1 \
+    --remote-allow-origins=* \
+    --window-size=1280,720 \
+    --user-data-dir=/src/browser_data \
+    --disable-blink-features=AutomationControlled \
+    --no-first-run \
+    --disable-gpu \
+    --mute-audio \
+    --no-default-browser-check \
+    --disable-software-rasterizer \
+    --disable-features=site-per-process
+
+  echo "Chromium упал или был закрыт агентом, рестарт через 2 секунды..."
+  sleep 2
+done

docker-compose.yml

@@ -1,22 +1,4 @@
 services:
-  browser:
-    image: browserless/chrome:latest
-    container_name: hermes_browser
-    ports:
-      - "3000:3000"
-    environment:
-      - MAX_CONCURRENT_SESSIONS=5
-      - SCREEN_WIDTH=1280
-      - SCREEN_HEIGHT=720
-      - ENABLE_DEBUGGER=true
-    restart: always
-    networks:
-      - hermes-net
-    deploy:
-      resources:
-        limits:
-          memory: 2G
-
   agent:
     build: .
     container_name: hermes-brain
@@ -24,7 +6,7 @@ services:
       - .env
     volumes:
       - .:/app/hermes_code:ro
-      
+
       - ${HERMES_DATA_PATH}/config.yaml:/app/hermes_data/config.yaml:ro
       - ${HERMES_DATA_PATH}/SOUL.md:/app/hermes_data/SOUL.md:ro
       - ./.env:/app/hermes_data/.env:ro
@@ -37,7 +19,7 @@ services:
       - ${HERMES_DATA_PATH}/memories:/app/hermes_data/memories:rw
       - ${HERMES_WORKSPACE_PATH}/hermes:/app/hermes_data/workspace:rw
     environment:
-      - BROWSER_URL=ws://browser:3000
+      - BROWSER_URL=http://browser:9222
     depends_on:
       - browser
     stdin_open: true
@@ -50,6 +32,31 @@ services:
         limits:
           memory: 1.5G
 
+  browser:
+    build:
+      context: ./browser_env
+      dockerfile: Dockerfile.browser
+    container_name: hermes-browser
+    networks:
+      hermes-net:
+        aliases:
+          - browser
+    shm_size: '2gb'
+    volumes:
+      - browser_profiles:/src/browser_data
+    restart: always
+
+  tunnel:
+    image: cloudflare/cloudflared:latest
+    container_name: hermes-tunnel
+    restart: always
+    command: tunnel --url http://browser:6080
+    networks:
+      - hermes-net
+
+volumes:
+  browser_profiles:
+
 networks:
   hermes-net:
     driver: bridge      

model_tools.py

@@ -144,7 +144,7 @@ def _discover_tools():
         "tools.image_generation_tool",
         "tools.skills_tool",
         "tools.skill_manager_tool",
-        "tools.browser_tool",
+        # "tools.browser_tool",
         "tools.cronjob_tools",
         "tools.rl_training_tool",
         "tools.tts_tool",
@@ -158,6 +158,7 @@ def _discover_tools():
         "tools.send_message_tool",
         "tools.honcho_tools",
         "tools.homeassistant_tool",
+        "tools.browser_use_tool"
     ]
     import importlib
     for mod_name in _modules:

pyproject.toml

@@ -34,12 +34,17 @@ dependencies = [
   "faster-whisper>=1.0.0,<2",
   # Skills Hub (GitHub App JWT auth — optional, only needed for bot identity)
   "PyJWT[crypto]>=2.10.1,<3",
+  "browser-use>=0.12.5",
+  "playwright>=1.49.0",
+  "playwright-stealth>=1.0.6",
+  "langchain-openai>=1.1.12",
 ]
 
 [project.optional-dependencies]
 modal = ["swe-rex[modal]>=1.4.0,<2"]
 daytona = ["daytona>=0.148.0,<1"]
 dev = ["pytest>=9.0.2,<10", "pytest-asyncio>=1.3.0,<2", "pytest-xdist>=3.0,<4", "mcp>=1.2.0,<2"]
+tg = ["python-telegram-bot>=22.6,<23", "aiohttp>=3.13.3,<4"]
 messaging = ["python-telegram-bot>=22.6,<23", "discord.py[voice]>=2.7.1,<3", "aiohttp>=3.13.3,<4", "slack-bolt>=1.18.0,<2", "slack-sdk>=3.27.0,<4"]
 cron = ["croniter>=6.0.0,<7"]
 slack = ["slack-bolt>=1.18.0,<2", "slack-sdk>=3.27.0,<4"]

requirements.txt

@@ -19,6 +19,9 @@ PyJWT[crypto]
 # Web tools
 firecrawl-py
 parallel-web>=0.4.2
+browser-use>=0.12.5
+playwright
+playwright-stealth
 
 # Image generation
 fal-client
@@ -33,3 +36,5 @@ croniter
 python-telegram-bot>=20.0
 discord.py>=2.0
 aiohttp>=3.9.0
+langchain-openai>=1.1.12,
+

tools/__init__.py

@@ -64,23 +64,27 @@ from .skill_manager_tool import (
 )
 
 # Browser automation tools (agent-browser + Browserbase)
-from .browser_tool import (
-    browser_navigate,
-    browser_snapshot,
-    browser_click,
-    browser_type,
-    browser_scroll,
-    browser_back,
-    browser_press,
-    browser_close,
-    browser_get_images,
-    browser_vision,
-    cleanup_browser,
-    cleanup_all_browsers,
-    get_active_browser_sessions,
-    check_browser_requirements,
-    BROWSER_TOOL_SCHEMAS
-)
+# from .browser_tool import (
+#     browser_navigate,
+#     browser_snapshot,
+#     browser_click,
+#     browser_type,
+#     browser_scroll,
+#     browser_back,
+#     browser_press,
+#     browser_close,
+#     browser_get_images,
+#     browser_vision,
+#     cleanup_browser,
+#     cleanup_all_browsers,
+#     get_active_browser_sessions,
+#     check_browser_requirements,
+#     BROWSER_TOOL_SCHEMAS
+# )
+
+from .browser_use_tool import run_browser_task
+
+from .browser_tool import cleanup_browser, cleanup_all_browsers
 
 # Cronjob management tools (CLI-only, hermes-cli toolset)
 from .cronjob_tools import (

tools/browser_tool.py

@@ -298,30 +298,32 @@ _cleanup_lock = threading.Lock()
 
 
 def _emergency_cleanup_all_sessions():
-    """
-    Emergency cleanup of all active browser sessions.
-    Called on process exit or interrupt to prevent orphaned sessions.
-    """
-    global _cleanup_done
-    if _cleanup_done:
-        return
-    _cleanup_done = True
+    # """
+    # Emergency cleanup of all active browser sessions.
+    # Called on process exit or interrupt to prevent orphaned sessions.
+    # """
+    # global _cleanup_done
+    # if _cleanup_done:
+    #     return
+    # _cleanup_done = True
     
-    if not _active_sessions:
-        return
+    # if not _active_sessions:
+    #     return
     
-    logger.info("Emergency cleanup: closing %s active session(s)...",
-                len(_active_sessions))
+    # logger.info("Emergency cleanup: closing %s active session(s)...",
+    #             len(_active_sessions))
 
-    try:
-        cleanup_all_browsers()
-    except Exception as e:
-        logger.error("Emergency cleanup error: %s", e)
-    finally:
-        with _cleanup_lock:
-            _active_sessions.clear()
-            _session_last_activity.clear()
-        _recording_sessions.clear()
+    # try:
+    #     cleanup_all_browsers()
+    # except Exception as e:
+    #     logger.error("Emergency cleanup error: %s", e)
+    # finally:
+    #     with _cleanup_lock:
+    #         _active_sessions.clear()
+    #         _session_last_activity.clear()
+    #     _recording_sessions.clear()
+
+    pass
 
 
 # Register cleanup via atexit only.  Previous versions installed SIGINT/SIGTERM
@@ -1657,85 +1659,89 @@ def _cleanup_old_recordings(max_age_hours=72):
 # ============================================================================
 
 def cleanup_browser(task_id: Optional[str] = None) -> None:
-    """
-    Clean up browser session for a task.
+    # """
+    # Clean up browser session for a task.
     
-    Called automatically when a task completes or when inactivity timeout is reached.
-    Closes both the agent-browser session and the Browserbase session.
+    # Called automatically when a task completes or when inactivity timeout is reached.
+    # Closes both the agent-browser session and the Browserbase session.
     
-    Args:
-        task_id: Task identifier to clean up
-    """
-    if task_id is None:
-        task_id = "default"
+    # Args:
+    #     task_id: Task identifier to clean up
+    # """
+    # if task_id is None:
+    #     task_id = "default"
     
-    logger.debug("cleanup_browser called for task_id: %s", task_id)
-    logger.debug("Active sessions: %s", list(_active_sessions.keys()))
+    # logger.debug("cleanup_browser called for task_id: %s", task_id)
+    # logger.debug("Active sessions: %s", list(_active_sessions.keys()))
     
-    # Check if session exists (under lock), but don't remove yet -
-    # _run_browser_command needs it to build the close command.
-    with _cleanup_lock:
-        session_info = _active_sessions.get(task_id)
+    # # Check if session exists (under lock), but don't remove yet -
+    # # _run_browser_command needs it to build the close command.
+    # with _cleanup_lock:
+    #     session_info = _active_sessions.get(task_id)
     
-    if session_info:
-        bb_session_id = session_info.get("bb_session_id", "unknown")
-        logger.debug("Found session for task %s: bb_session_id=%s", task_id, bb_session_id)
+    # if session_info:
+    #     bb_session_id = session_info.get("bb_session_id", "unknown")
+    #     logger.debug("Found session for task %s: bb_session_id=%s", task_id, bb_session_id)
         
-        # Stop auto-recording before closing (saves the file)
-        _maybe_stop_recording(task_id)
+    #     # Stop auto-recording before closing (saves the file)
+    #     _maybe_stop_recording(task_id)
         
-        # Try to close via agent-browser first (needs session in _active_sessions)
-        try:
-            _run_browser_command(task_id, "close", [], timeout=10)
-            logger.debug("agent-browser close command completed for task %s", task_id)
-        except Exception as e:
-            logger.warning("agent-browser close failed for task %s: %s", task_id, e)
+    #     # Try to close via agent-browser first (needs session in _active_sessions)
+    #     try:
+    #         _run_browser_command(task_id, "close", [], timeout=10)
+    #         logger.debug("agent-browser close command completed for task %s", task_id)
+    #     except Exception as e:
+    #         logger.warning("agent-browser close failed for task %s: %s", task_id, e)
         
-        # Now remove from tracking under lock
-        with _cleanup_lock:
-            _active_sessions.pop(task_id, None)
-            _session_last_activity.pop(task_id, None)
+    #     # Now remove from tracking under lock
+    #     with _cleanup_lock:
+    #         _active_sessions.pop(task_id, None)
+    #         _session_last_activity.pop(task_id, None)
         
-        # Cloud mode: close the cloud browser session via provider API
-        if bb_session_id:
-            provider = _get_cloud_provider()
-            if provider is not None:
-                try:
-                    provider.close_session(bb_session_id)
-                except Exception as e:
-                    logger.warning("Could not close cloud browser session: %s", e)
+    #     # Cloud mode: close the cloud browser session via provider API
+    #     if bb_session_id:
+    #         provider = _get_cloud_provider()
+    #         if provider is not None:
+    #             try:
+    #                 provider.close_session(bb_session_id)
+    #             except Exception as e:
+    #                 logger.warning("Could not close cloud browser session: %s", e)
         
-        # Kill the daemon process and clean up socket directory
-        session_name = session_info.get("session_name", "")
-        if session_name:
-            socket_dir = os.path.join(_socket_safe_tmpdir(), f"agent-browser-{session_name}")
-            if os.path.exists(socket_dir):
-                # agent-browser writes {session}.pid in the socket dir
-                pid_file = os.path.join(socket_dir, f"{session_name}.pid")
-                if os.path.isfile(pid_file):
-                    try:
-                        daemon_pid = int(Path(pid_file).read_text().strip())
-                        os.kill(daemon_pid, signal.SIGTERM)
-                        logger.debug("Killed daemon pid %s for %s", daemon_pid, session_name)
-                    except (ProcessLookupError, ValueError, PermissionError, OSError):
-                        logger.debug("Could not kill daemon pid for %s (already dead or inaccessible)", session_name)
-                shutil.rmtree(socket_dir, ignore_errors=True)
+    #     # Kill the daemon process and clean up socket directory
+    #     session_name = session_info.get("session_name", "")
+    #     if session_name:
+    #         socket_dir = os.path.join(_socket_safe_tmpdir(), f"agent-browser-{session_name}")
+    #         if os.path.exists(socket_dir):
+    #             # agent-browser writes {session}.pid in the socket dir
+    #             pid_file = os.path.join(socket_dir, f"{session_name}.pid")
+    #             if os.path.isfile(pid_file):
+    #                 try:
+    #                     daemon_pid = int(Path(pid_file).read_text().strip())
+    #                     os.kill(daemon_pid, signal.SIGTERM)
+    #                     logger.debug("Killed daemon pid %s for %s", daemon_pid, session_name)
+    #                 except (ProcessLookupError, ValueError, PermissionError, OSError):
+    #                     logger.debug("Could not kill daemon pid for %s (already dead or inaccessible)", session_name)
+    #             shutil.rmtree(socket_dir, ignore_errors=True)
         
-        logger.debug("Removed task %s from active sessions", task_id)
-    else:
-        logger.debug("No active session found for task_id: %s", task_id)
+    #     logger.debug("Removed task %s from active sessions", task_id)
+    # else:
+    #     logger.debug("No active session found for task_id: %s", task_id)
+
+    pass
 
 
 def cleanup_all_browsers() -> None:
-    """
-    Clean up all active browser sessions.
+    # """
+    # Clean up all active browser sessions.
     
-    Useful for cleanup on shutdown.
-    """
-    with _cleanup_lock:
-        task_ids = list(_active_sessions.keys())
-    for task_id in task_ids:
-        cleanup_browser(task_id)
+    # Useful for cleanup on shutdown.
+    # """
+    # with _cleanup_lock:
+    #     task_ids = list(_active_sessions.keys())
+    # for task_id in task_ids:
+    #     cleanup_browser(task_id)
+
+    pass
 
 
 def get_active_browser_sessions() -> Dict[str, Dict[str, str]]:
@@ -1822,96 +1828,96 @@ if __name__ == "__main__":
 # ---------------------------------------------------------------------------
 # Registry
 # ---------------------------------------------------------------------------
-from tools.registry import registry
+# from tools.registry import registry
 
-_BROWSER_SCHEMA_MAP = {s["name"]: s for s in BROWSER_TOOL_SCHEMAS}
+# _BROWSER_SCHEMA_MAP = {s["name"]: s for s in BROWSER_TOOL_SCHEMAS}
 
-registry.register(
-    name="browser_navigate",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_navigate"],
-    handler=lambda args, **kw: browser_navigate(url=args.get("url", ""), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="🌐",
-)
-registry.register(
-    name="browser_snapshot",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_snapshot"],
-    handler=lambda args, **kw: browser_snapshot(
-        full=args.get("full", False), task_id=kw.get("task_id"), user_task=kw.get("user_task")),
-    check_fn=check_browser_requirements,
-    emoji="📸",
-)
-registry.register(
-    name="browser_click",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_click"],
-    handler=lambda args, **kw: browser_click(ref=args.get("ref", ""), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="👆",
-)
-registry.register(
-    name="browser_type",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_type"],
-    handler=lambda args, **kw: browser_type(ref=args.get("ref", ""), text=args.get("text", ""), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="⌨️",
-)
-registry.register(
-    name="browser_scroll",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_scroll"],
-    handler=lambda args, **kw: browser_scroll(direction=args.get("direction", "down"), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="📜",
-)
-registry.register(
-    name="browser_back",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_back"],
-    handler=lambda args, **kw: browser_back(task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="◀️",
-)
-registry.register(
-    name="browser_press",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_press"],
-    handler=lambda args, **kw: browser_press(key=args.get("key", ""), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="⌨️",
-)
-registry.register(
-    name="browser_close",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_close"],
-    handler=lambda args, **kw: browser_close(task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="🚪",
-)
-registry.register(
-    name="browser_get_images",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_get_images"],
-    handler=lambda args, **kw: browser_get_images(task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="🖼️",
-)
-registry.register(
-    name="browser_vision",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_vision"],
-    handler=lambda args, **kw: browser_vision(question=args.get("question", ""), annotate=args.get("annotate", False), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="👁️",
-)
-registry.register(
-    name="browser_console",
-    toolset="browser",
-    schema=_BROWSER_SCHEMA_MAP["browser_console"],
-    handler=lambda args, **kw: browser_console(clear=args.get("clear", False), task_id=kw.get("task_id")),
-    check_fn=check_browser_requirements,
-    emoji="🖥️",
-)
+# registry.register(
+#     name="browser_navigate",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_navigate"],
+#     handler=lambda args, **kw: browser_navigate(url=args.get("url", ""), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="🌐",
+# )
+# registry.register(
+#     name="browser_snapshot",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_snapshot"],
+#     handler=lambda args, **kw: browser_snapshot(
+#         full=args.get("full", False), task_id=kw.get("task_id"), user_task=kw.get("user_task")),
+#     check_fn=check_browser_requirements,
+#     emoji="📸",
+# )
+# registry.register(
+#     name="browser_click",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_click"],
+#     handler=lambda args, **kw: browser_click(ref=args.get("ref", ""), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="👆",
+# )
+# registry.register(
+#     name="browser_type",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_type"],
+#     handler=lambda args, **kw: browser_type(ref=args.get("ref", ""), text=args.get("text", ""), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="⌨️",
+# )
+# registry.register(
+#     name="browser_scroll",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_scroll"],
+#     handler=lambda args, **kw: browser_scroll(direction=args.get("direction", "down"), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="📜",
+# )
+# registry.register(
+#     name="browser_back",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_back"],
+#     handler=lambda args, **kw: browser_back(task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="◀️",
+# )
+# registry.register(
+#     name="browser_press",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_press"],
+#     handler=lambda args, **kw: browser_press(key=args.get("key", ""), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="⌨️",
+# )
+# registry.register(
+#     name="browser_close",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_close"],
+#     handler=lambda args, **kw: browser_close(task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="🚪",
+# )
+# registry.register(
+#     name="browser_get_images",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_get_images"],
+#     handler=lambda args, **kw: browser_get_images(task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="🖼️",
+# )
+# registry.register(
+#     name="browser_vision",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_vision"],
+#     handler=lambda args, **kw: browser_vision(question=args.get("question", ""), annotate=args.get("annotate", False), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="👁️",
+# )
+# registry.register(
+#     name="browser_console",
+#     toolset="browser",
+#     schema=_BROWSER_SCHEMA_MAP["browser_console"],
+#     handler=lambda args, **kw: browser_console(clear=args.get("clear", False), task_id=kw.get("task_id")),
+#     check_fn=check_browser_requirements,
+#     emoji="🖥️",
+# )

tools/browser_use_tool.py

@@ -0,0 +1,86 @@
+import json
+import os
+import asyncio
+import socket
+from browser_use import Agent, Browser, ChatOpenAI
+from tools.registry import registry
+
+
+async def run_browser_task(task):
+    browser_host = "browser"
+    browser_port = 9222
+    BROWSER_VIEW_URL = os.getenv("BROWSER_VIEW_URL", "")
+    
+    try:
+        browser_ip = socket.gethostbyname(browser_host)
+        cdp_url = f"http://{browser_ip}:{browser_port}"
+    except Exception:
+        cdp_url = f"http://{browser_host}:{browser_port}"
+
+    browser = Browser(cdp_url=cdp_url)
+
+    llm = ChatOpenAI(
+        model=os.getenv("MODEL_DEFAULT", "qwen3.5-122b"),
+        api_key=os.getenv("OPENAI_API_KEY"),
+        base_url=os.getenv("OPENAI_BASE_URL"),
+        temperature=0.0,
+    )
+
+    agent = Agent(
+        task=task,
+        llm=llm,
+        browser=browser,
+        use_vision=False
+    )
+
+    try:
+        history = await agent.run()
+        final_result = history.final_result()
+
+        response = {
+            "success": True,
+            "result": final_result,
+            "browser_view": BROWSER_VIEW_URL
+        }
+        return json.dumps(response, ensure_ascii=False)
+        
+    except Exception as e:
+        return json.dumps({
+            "success": False, 
+            "error": f"Browser automation failed: {str(e)}"
+        }, ensure_ascii=False)
+        
+    finally:
+        if browser:
+            try:
+                await browser.close()
+            except Exception:
+                pass
+
+
+registry.register(
+    name="internet_browser",
+    toolset="browse_cmd", 
+    schema={
+        "name": "internet_browser",
+        "description": (
+            "ГЛАВНЫЙ ИНСТРУМЕНТ ДЛЯ ВЕБ-СЕРФИНГА. Вызывай этот инструмент НАПРЯМУЮ (через стандартный tool call/function call). "
+            "КАТЕГОРИЧЕСКИ ЗАПРЕЩЕНО использовать `execute_code` или `delegate_task` для работы с браузером. "
+            "Не пиши Python-скрипты! Просто передай в этот инструмент параметр `task`. "
+            "Используй для любых задач в интернете: поиск товаров (Wildberries, Ozon), чтение статей, клики, навигация."
+        ),
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "task": {
+                    "type": "string", 
+                    "description": "Подробная задача на естественном языке. Например: 'Зайди на wildberries.ru, найди черную футболку и верни цену'."
+                }
+            },
+            "required": ["task"]
+        }
+    },
+ 
+    handler=lambda args, **kw: asyncio.run(run_browser_task(args.get("task"))),
+    emoji="🌐",
+)

toolsets.py

@@ -29,6 +29,12 @@ from typing import List, Dict, Any, Set, Optional
 # Shared tool list for CLI and all messaging platform toolsets.
 # Edit this once to update all platforms simultaneously.
 _HERMES_CORE_TOOLS = [
+    # Browser automation
+    # "browser_navigate", "browser_snapshot", "browser_click",
+    # "browser_type", "browser_scroll", "browser_back",
+    # "browser_press", "browser_close", "browser_get_images",
+    # "browser_vision", "browser_console", 
+    "internet_browser",
     # Web
     "web_search", "web_extract",
     # Terminal + process management
@@ -41,11 +47,6 @@ _HERMES_CORE_TOOLS = [
     "mixture_of_agents",
     # Skills
     "skills_list", "skill_view", "skill_manage",
-    # Browser automation
-    "browser_navigate", "browser_snapshot", "browser_click",
-    "browser_type", "browser_scroll", "browser_back",
-    "browser_press", "browser_close", "browser_get_images",
-    "browser_vision", "browser_console",
     # Text-to-speech
     "text_to_speech",
     # Planning & memory
@@ -116,13 +117,20 @@ TOOLSETS = {
     "browser": {
         "description": "Browser automation for web interaction (navigate, click, type, scroll, iframes, hold-click) with web search for finding URLs",
         "tools": [
-            "browser_navigate", "browser_snapshot", "browser_click",
-            "browser_type", "browser_scroll", "browser_back",
-            "browser_press", "browser_close", "browser_get_images",
-            "browser_vision", "browser_console", "web_search"
+            # "browser_navigate", "browser_snapshot", "browser_click",
+            # "browser_type", "browser_scroll", "browser_back",
+            # "browser_press", "browser_close", "browser_get_images",
+            # "browser_vision", "browser_console", "web_search"
+            # "internet_browser"
         ],
         "includes": []
     },
+
+    "browse_cmd": {
+        "description": "Advanced browser automation via browser-use",
+        "tools": ["internet_browser"],
+        "includes": []
+    },
     
     "cronjob": {
         "description": "Cronjob management tool - create, list, update, pause, resume, remove, and trigger scheduled tasks",