codex-app-server/cloud/playwright_mcp.py

"""Stdio MCP server exposing headless Chromium to codex.

Protocol: JSON-RPC 2.0 over stdio, one JSON object per line.
Logs go to stderr only -- anything on stdout would corrupt the
JSON-RPC stream.

This file is deliberately thin: all browser logic lives in
``playwright_browser.py``. It can run two ways:
- inside the repo: ``python3 -m cloud.playwright_mcp`` (imports
  ``cloud.playwright_browser``);
- copied flat into a tenant codex-home next to
  ``playwright_browser.py`` (imports plain ``playwright_browser``
  from its own directory).
The ``ensure_codex_home_playwright`` helper does the copying;
proxy vars and PLAYWRIGHT_BROWSERS_PATH arrive via the MCP env
block in config.toml, never via tool arguments.

One Browser instance lives for the whole MCP process: navigate
once, then snapshot/click/fill/screenshot against the same page.
"""

import json
import os
import sys

try:
    from cloud.playwright_browser import Browser, BrowserError
except ImportError:  # flat copy in a tenant codex-home
    sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
    from playwright_browser import Browser, BrowserError  # noqa: E402

SERVER_NAME = "playwright"
SERVER_VERSION = "0.1.0"

_TOOLS = [
    {
        "name": "browser_navigate",
        "description": (
            "Open a URL in headless Chromium and return its final "
            "URL and title. Use for pages that need JavaScript to "
            "render, which web_fetch cannot see. Network goes "
            "through the egress proxy, so domains outside the "
            "Tinyproxy whitelist fail with a proxy 403 -- report "
            "that plainly, do not bypass it."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "url": {"type": "string",
                        "description": "http(s) URL, or file:// URL "
                        "for a page already in the worktree"},
            },
            "required": ["url"],
        },
    },
    {
        "name": "browser_snapshot",
        "description": (
            "Return the current page's title, URL and body text "
            "(truncated at 8000 characters with a flag). Call "
            "after navigate, and after click/fill, to see what "
            "actually rendered."
        ),
        "inputSchema": {"type": "object", "properties": {}},
    },
    {
        "name": "browser_click",
        "description": (
            "Click an element by CSS selector or Playwright "
            "selector (e.g. 'button.submit', 'text=Next'). "
            "Then snapshot to see the result."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "selector": {"type": "string"},
            },
            "required": ["selector"],
        },
    },
    {
        "name": "browser_fill",
        "description": (
            "Fill an input/textarea by CSS selector with text. "
            "Then snapshot or click to submit."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "selector": {"type": "string"},
                "text": {"type": "string"},
            },
            "required": ["selector", "text"],
        },
    },
    {
        "name": "browser_evaluate",
        "description": (
            "Run a JavaScript expression in the page and return "
            "its string value (truncated at 4000 characters). "
            "Same sandbox privilege as the shell tool; prefer "
            "snapshot/click/fill for ordinary reads and actions."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "expression": {"type": "string"},
            },
            "required": ["expression"],
        },
    },
    {
        "name": "browser_click_at",
        "description": (
            "Click at viewport coordinates (CSS pixels, origin "
            "top-left of the 1280x800 viewport). This is the tool "
            "a live viewer drives: the user clicks on a screenshot "
            "and the coordinates arrive here. Then snapshot to see "
            "the result."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "x": {"type": "number"},
                "y": {"type": "number"},
            },
            "required": ["x", "y"],
        },
    },
    {
        "name": "browser_live_shot",
        "description": (
            "Screenshot to the FIXED live-view file "
            "browser-live.png plus a browser-live.json status "
            "sidecar (url, title, timestamp), so a watcher can "
            "poll one stable path. Call after every navigate / "
            "click / fill while a live view is wanted. Returns "
            "path, bytes, url, title and timestamp."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "output_filename": {"type": "string",
                                    "description": "Plain basename "
                                    "to save as. Default: "
                                    "browser-live.png"},
            },
        },
    },
    {
        "name": "browser_snapshot_refs",
        "description": (
            "Accessibility-style snapshot: interactive elements "
            "with stable refs (e.g. e3) plus tag, role and name. "
            "Use browser_click_ref to click one; refs are valid "
            "until the next snapshot_refs call."
        ),
        "inputSchema": {"type": "object", "properties": {}},
    },
    {
        "name": "browser_click_ref",
        "description": (
            "Click an element by its ref from browser_snapshot_refs. "
            "More robust than a CSS selector across re-renders."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {"ref": {"type": "string"}},
            "required": ["ref"],
        },
    },
    {
        "name": "browser_mouse_move",
        "description": "Move the mouse to viewport coordinates (1280x800).",
        "inputSchema": {
            "type": "object",
            "properties": {
                "x": {"type": "number"},
                "y": {"type": "number"},
            },
            "required": ["x", "y"],
        },
    },
    {
        "name": "browser_key_press",
        "description": "Press a key (Playwright key name, e.g. Enter, Tab).",
        "inputSchema": {
            "type": "object",
            "properties": {"key": {"type": "string"}},
            "required": ["key"],
        },
    },
    {
        "name": "browser_type_text",
        "description": "Type text at the current focus.",
        "inputSchema": {
            "type": "object",
            "properties": {"text": {"type": "string"}},
            "required": ["text"],
        },
    },
    {
        "name": "browser_screenshot",
        "description": (
            "Save a PNG screenshot of the current page into the "
            "working directory and return its absolute path and "
            "byte size. Verify the returned path with shell/PIL "
            "before reporting success."
        ),
        "inputSchema": {
            "type": "object",
            "properties": {
                "output_filename": {"type": "string",
                                    "description": "Plain basename "
                                    "to save as, e.g. 'shot.png'. "
                                    "Default: shot-<epoch>.png"},
            },
        },
    },
    {
        "name": "browser_close",
        "description": "Close the browser page. Safe to call twice.",
        "inputSchema": {"type": "object", "properties": {}},
    },
]


def _err(code, message):
    return {"code": code, "message": message}


_BROWSER = None
_REMOTE = None


def _get_browser(browser=None):
    global _BROWSER
    if browser is not None:
        return browser
    if _BROWSER is None:
        _BROWSER = Browser()
    return _BROWSER


def _get_remote(browser=None):
    """Remote control state, lazily created. Keyed by browser
    identity so tests passing different fake browsers don't share
    one holder flag."""
    global _REMOTE
    target = _get_browser(browser)
    if _REMOTE is not None and _REMOTE.browser is target:
        return _REMOTE
    try:
        from playwright_remote import RemoteState
    except ImportError:
        try:
            from cloud.playwright_remote import RemoteState
        except ImportError:
            return None
    _REMOTE = RemoteState(target)
    return _REMOTE


def handle_request(request, browser=None):
    """Handle one JSON-RPC request dict. Returns a response dict or
    None for notifications (no id). Tests pass a fake browser."""
    if not isinstance(request, dict):
        return {"jsonrpc": "2.0", "id": None,
                "error": _err(-32700, "request is not an object")}
    method = request.get("method")
    req_id = request.get("id")
    is_notification = "id" not in request

    if method == "initialize":
        if is_notification:
            return None
        return {"jsonrpc": "2.0", "id": req_id,
                "result": {
                    "protocolVersion": request.get("params", {}).get(
                        "protocolVersion", "2024-11-05"),
                    "capabilities": {"tools": {}},
                    "serverInfo": {"name": SERVER_NAME,
                                   "version": SERVER_VERSION}}}
    if method in ("notifications/initialized", "notifications/cancelled"):
        return None
    if method == "ping":
        if is_notification:
            return None
        return {"jsonrpc": "2.0", "id": req_id, "result": {}}
    if method == "tools/list":
        if is_notification:
            return None
        return {"jsonrpc": "2.0", "id": req_id,
                "result": {"tools": _TOOLS}}
    if method == "tools/call":
        if is_notification:
            return None
        params = request.get("params") or {}
        name = params.get("name")
        args = params.get("arguments") or {}
        target = _get_browser(browser)
        remote = _get_remote(browser)
        if remote is not None and remote.get_holder() == "user":
            return {"jsonrpc": "2.0", "id": req_id,
                    "result": {"content": [{"type": "text",
                                            "text": "error: user holds "
                                            "browser control; wait for "
                                            "release"}],
                               "isError": True}}
        try:
            if name == "browser_navigate":
                result = target.navigate(args.get("url"))
            elif name == "browser_snapshot":
                result = target.snapshot()
            elif name == "browser_click":
                result = target.click(args.get("selector"))
            elif name == "browser_fill":
                result = target.fill(args.get("selector"),
                                     args.get("text"))
            elif name == "browser_click_at":
                result = target.click_at(args.get("x"), args.get("y"))
            elif name == "browser_mouse_move":
                result = target.mouse_move(args.get("x"), args.get("y"))
            elif name == "browser_key_press":
                result = target.key_press(args.get("key"))
            elif name == "browser_type_text":
                result = target.type_text(args.get("text"))
            elif name == "browser_snapshot_refs":
                result = target.snapshot_refs()
            elif name == "browser_click_ref":
                result = target.click_ref(args.get("ref"))
            elif name == "browser_live_shot":
                result = target.live_shot(
                    args.get("output_filename"))
            elif name == "browser_evaluate":
                result = target.evaluate(args.get("expression"))
            elif name == "browser_screenshot":
                result = target.screenshot(
                    args.get("output_filename"))
            elif name == "browser_close":
                result = target.close()
            else:
                return {"jsonrpc": "2.0", "id": req_id,
                        "error": _err(-32602, "unknown tool: %r" % name)}
        except Exception as exc:  # noqa: BLE001 - tool errors are data
            return {"jsonrpc": "2.0", "id": req_id,
                    "result": {"content": [{"type": "text",
                                            "text": "error: %s" % exc}],
                               "isError": True}}
        return {"jsonrpc": "2.0", "id": req_id,
                "result": {"content": [{"type": "text",
                                        "text": json.dumps(
                                            result, ensure_ascii=False)}],
                           "isError": False}}
    if is_notification:
        return None
    return {"jsonrpc": "2.0", "id": req_id,
            "error": _err(-32601, "method not found: %r" % method)}


def _drain_remote(browser):
    """Main-thread only: run queued user inputs and pump screencast
    frames (acks). Called on every loop iteration so remote input
    lands even while no JSON-RPC request is in flight."""
    remote = _get_remote(browser)
    if remote is None:
        return
    try:
        from playwright_remote import execute_input
    except ImportError:
        try:
            from cloud.playwright_remote import execute_input
        except ImportError:
            return
    while True:
        try:
            item = remote.inputs.get_nowait()
        except Exception:  # noqa: BLE001 - queue empty
            break
        if remote.get_holder() != "user":
            continue
        try:
            execute_input(browser, item)
        except Exception as exc:  # noqa: BLE001 - input errors are data
            print("playwright_mcp: remote input error: %s" % exc,
                  file=sys.stderr)
    try:
        frame = browser.pump_screencast()
    except Exception:  # noqa: BLE001 - screencast best-effort
        frame = ""
    if frame:
        remote.set_frame(frame)


def main():
    import select
    browser = _get_browser()
    remote = _get_remote(browser)
    if remote is not None:
        try:
            from playwright_remote import start_remote_server
        except ImportError:
            try:
                from cloud.playwright_remote import start_remote_server
            except ImportError:
                start_remote_server = None
        if start_remote_server is not None:
            socket_path = os.environ.get(
                "PLAYWRIGHT_REMOTE_SOCKET",
                os.path.join(browser.cwd, ".browser-remote.sock"))
            try:
                browser.set_frame_sink(_frame_queue())
                start_remote_server(remote, socket_path)
            except Exception as exc:  # noqa: BLE001 - remote best-effort
                print("playwright_mcp: remote server failed: %s" % exc,
                      file=sys.stderr)
    buffer = ""
    while True:
        _drain_remote(browser)
        try:
            readable, _, _ = select.select([sys.stdin], [], [], 0.05)
        except Exception:  # noqa: BLE001 - stdin gone
            break
        if not readable:
            continue
        chunk = sys.stdin.readline()
        if not chunk:
            break
        line = chunk.strip()
        if not line:
            continue
        try:
            request = json.loads(line)
        except json.JSONDecodeError as exc:
            sys.stdout.write(json.dumps(
                {"jsonrpc": "2.0", "id": None,
                 "error": _err(-32700, "parse error: %s" % exc)}) + "\n")
            sys.stdout.flush()
            continue
        try:
            response = handle_request(request, browser)
        except Exception as exc:  # noqa: BLE001 - server must not die
            print("playwright_mcp: handler error: %s" % exc,
                  file=sys.stderr)
            if "id" in request:
                response = {"jsonrpc": "2.0", "id": request["id"],
                            "error": _err(-32603, "internal error")}
            else:
                response = None
        if response is not None:
            sys.stdout.write(json.dumps(response) + "\n")
            sys.stdout.flush()


def _frame_queue():
    try:
        from playwright_remote import SimpleQueue
    except ImportError:
        try:
            from cloud.playwright_remote import SimpleQueue
        except ImportError:
            import collections
            import threading

            class SimpleQueue:  # noqa: D101 - last-resort fallback
                def __init__(self):
                    self._deque = collections.deque()
                    self._lock = threading.Lock()

                def put(self, item):
                    with self._lock:
                        self._deque.append(item)

                def get_nowait(self):
                    with self._lock:
                        if not self._deque:
                            raise IndexError("queue empty")
                        return self._deque.popleft()
    return SimpleQueue()


if __name__ == "__main__":
    main()