machinaos 0.0.78 → 0.0.80

package/server/nodes/browser/_install.py

@@ -0,0 +1,63 @@
+"""``agent-browser`` local install — mirrors ``claude_binary_path``.
+
+Same pattern as ``nodes/agent/claude_code_agent/_oauth.py``: ``npm
+install <pkg> --prefix <package_dir("browser")/npm>`` on first call,
+return the resolved binary path. No coupling to the workspace
+``package.json``.
+"""
+
+from __future__ import annotations
+
+import shutil
+import subprocess
+import sys
+from typing import Optional
+
+from core.logging import get_logger
+from core.paths import package_dir
+
+logger = get_logger(__name__)
+
+_NPM_SPEC = "agent-browser@latest"
+
+
+def agent_browser_binary_path() -> Optional[str]:
+    """Return path to the agent-browser CLI, installing on miss."""
+    npm_root = package_dir("browser") / "npm"
+    bin_name = "agent-browser.cmd" if sys.platform == "win32" else "agent-browser"
+    bin_path = npm_root / "node_modules" / ".bin" / bin_name
+
+    if bin_path.exists():
+        return str(bin_path)
+
+    npm_cmd = shutil.which("npm")
+    if not npm_cmd:
+        logger.warning("[browser] npm not on PATH; cannot install %s", _NPM_SPEC)
+        return None
+
+    logger.info("[browser] installing %s into %s", _NPM_SPEC, npm_root)
+    npm_root.mkdir(parents=True, exist_ok=True)
+    result = subprocess.run(
+        [npm_cmd, "install", _NPM_SPEC, "--prefix", str(npm_root), "--no-audit", "--no-fund"],
+        capture_output=True,
+        text=True,
+    )
+    if result.returncode != 0 or not bin_path.exists():
+        logger.error("[browser] npm install failed: %s", result.stderr.strip())
+        return None
+
+    # Fetch the Chrome-for-Testing runtime (agent-browser's documented
+    # post-install step — downloads ~150MB chromium on first use).
+    runtime = subprocess.run(
+        [str(bin_path), "install"],
+        capture_output=True,
+        text=True,
+    )
+    if runtime.returncode != 0:
+        logger.warning("[browser] chromium runtime install failed: %s", runtime.stderr.strip())
+
+    logger.info("[browser] agent-browser installed at %s", bin_path)
+    return str(bin_path)
+
+
+__all__ = ["agent_browser_binary_path"]

package/server/nodes/browser/_service.py

@@ -1,23 +1,19 @@
 """Thin wrapper around agent-browser CLI.
 
-Stateless client — finds the binary via npx, runs commands via subprocess,
-parses JSON output. The agent-browser daemon manages its own lifecycle
-(auto-starts, persists between commands).
+Stateless client — finds the binary via :mod:`nodes.browser._install`,
+runs commands via subprocess, parses JSON output. The agent-browser
+daemon manages its own lifecycle (auto-starts, persists between
+commands).
 
 Invocation strategy
 -------------------
-agent-browser is a pinned project dependency (see package.json). Rather than
-locating its shim manually per-platform, we invoke it via ``npx --no-install``:
-
-    [shutil.which("npx"), "--no-install", "agent-browser", ...args]
-
-This matches the pattern used by ``claude_code_service.py`` and is how npm
-intends locally-pinned CLIs to be invoked. npx handles all the
-cross-platform concerns (local ``node_modules/.bin/`` resolution, Windows
-.CMD vs POSIX shell shim, shebang interpretation) so we don't have to.
-
-``--no-install`` makes the call fail loudly if agent-browser isn't in the
-lockfile, instead of silently pulling from the registry at runtime.
+agent-browser is a MachinaOs-managed local install (see
+``nodes/browser/_install.py``) — same pattern as Claude Code's
+project-local CLI. The binary lives at
+``<package_dir("browser")>/npm/node_modules/.bin/agent-browser[.cmd]``
+and is installed via ``npm install agent-browser --prefix <...>`` on
+first use. No dependency on the workspace ``package.json`` /
+``node_modules`` / pnpm lockfile.
 
 All subprocess calls use ``shell=False`` with list argv — Python handles
 Windows .CMD files natively via ``CreateProcessW``, avoiding the BatBadBut
@@ -26,11 +22,11 @@ Windows .CMD files natively via ``CreateProcessW``, avoiding the BatBadBut
 
 import asyncio
 import json
-import shutil
 import subprocess
 from typing import Any, Dict, List, Optional
 
 from core.logging import get_logger
+from nodes.browser._install import agent_browser_binary_path
 from services._supervisor.util import kill_tree
 
 logger = get_logger(__name__)
@@ -71,7 +67,8 @@ class BrowserService:
         """
         argv = [
             *self._prefix,
-            "--session", session,
+            "--session",
+            session,
             "--json",
         ]
         if headed:
@@ -156,16 +153,15 @@ _instance: Optional[BrowserService] = None
 
 
 def _find_agent_browser_cmd() -> Optional[List[str]]:
-    """Locate agent-browser via npx (pinned to project lockfile).
+    """Resolve agent-browser via the local-install helper.
 
-    Uses ``npx --no-install`` so the call fails loudly if the package is
-    missing, rather than silently pulling from the registry at runtime.
-    Returns None if npx itself is not on PATH (Node.js not installed).
+    Calls :func:`nodes.browser._install.agent_browser_binary_path`,
+    which installs the npm package into :func:`core.paths.package_dir`
+    on first use (mirroring the claude_code_agent precedent). Returns
+    None when ``npm`` is unavailable (Node toolchain missing).
     """
-    npx = shutil.which("npx")
-    if not npx:
-        return None
-    return [npx, "--no-install", "agent-browser"]
+    binary = agent_browser_binary_path()
+    return [binary] if binary else None
 
 
 def get_browser_service() -> Optional[BrowserService]:

package/server/nodes/browser/{browser.py → browser/__init__.py}

@@ -18,6 +18,7 @@ from pydantic import BaseModel, ConfigDict, Field
 
 from core.logging import get_logger
 from services.plugin import ActionNode, NodeContext, Operation, TaskQueue
+from services.plugin.base import NodeUserError
 
 logger = get_logger(__name__)
 
@@ -44,6 +45,7 @@ def _find_browser_via_registry(exe_name: str) -> Optional[str]:
     """
     try:
         import winreg
+
         for hive in (winreg.HKEY_LOCAL_MACHINE, winreg.HKEY_CURRENT_USER):
             try:
                 key = winreg.OpenKey(
@@ -85,13 +87,13 @@ def _resolve_browser(selection: str, custom_path: str) -> Optional[str]:
 def _req(p: Dict[str, Any], key: str) -> str:
     v = (p.get(key) or "").strip()
     if not v:
-        raise ValueError(f"{key} is required")
+        raise NodeUserError(f"{key} is required")
     return v
 
 
 def _req_sel(s: str) -> str:
     if not s:
-        raise ValueError("selector is required")
+        raise NodeUserError("selector is required")
     return s
 
 
@@ -151,15 +153,24 @@ class BrowserParams(BaseModel):
     """
 
     operation: Literal[
-        "navigate", "click", "type", "fill", "screenshot", "snapshot",
-        "get_text", "get_html", "eval", "wait", "scroll", "select",
-        "console", "errors", "batch",
+        "navigate",
+        "click",
+        "type",
+        "fill",
+        "screenshot",
+        "snapshot",
+        "get_text",
+        "get_html",
+        "eval",
+        "wait",
+        "scroll",
+        "select",
+        "console",
+        "errors",
+        "batch",
     ] = Field(
         default="navigate",
-        description=(
-            "Browser operation. Typical flow: navigate -> snapshot -> "
-            "interact using @eN refs -> snapshot."
-        ),
+        description=("Browser operation. Typical flow: navigate -> snapshot -> " "interact using @eN refs -> snapshot."),
     )
 
     # Operation-scoped fields
@@ -172,9 +183,19 @@ class BrowserParams(BaseModel):
         default="",
         description="CSS selector or @eN ref from snapshot.",
         json_schema_extra={
-            "displayOptions": {"show": {"operation": [
-                "click", "type", "fill", "get_text", "get_html", "wait", "select",
-            ]}},
+            "displayOptions": {
+                "show": {
+                    "operation": [
+                        "click",
+                        "type",
+                        "fill",
+                        "get_text",
+                        "get_html",
+                        "wait",
+                        "select",
+                    ]
+                }
+            },
         },
     )
     text: str = Field(
@@ -200,7 +221,9 @@ class BrowserParams(BaseModel):
         json_schema_extra={"displayOptions": {"show": {"operation": ["scroll"]}}},
     )
     amount: int = Field(
-        default=500, ge=1, le=20000,
+        default=500,
+        ge=1,
+        le=20000,
         description="Pixels to scroll.",
         json_schema_extra={"displayOptions": {"show": {"operation": ["scroll"]}}},
     )
@@ -229,12 +252,17 @@ class BrowserParams(BaseModel):
         json_schema_extra={"displayOptions": {"show": {"operation": ["screenshot"]}}},
     )
     screenshot_quality: int = Field(
-        default=85, ge=1, le=100,
+        default=85,
+        ge=1,
+        le=100,
         description="JPEG quality (1-100).",
         json_schema_extra={
-            "displayOptions": {"show": {
-                "operation": ["screenshot"], "screenshot_format": ["jpeg"],
-            }},
+            "displayOptions": {
+                "show": {
+                    "operation": ["screenshot"],
+                    "screenshot_format": ["jpeg"],
+                }
+            },
         },
     )
 
@@ -278,11 +306,15 @@ class BrowserParams(BaseModel):
         description="Proxy URL (e.g. http://user:pass@host:port).",
     )
     action_delay: int = Field(
-        default=0, ge=0, le=60000,
+        default=0,
+        ge=0,
+        le=60000,
         description="Delay before each action in milliseconds (for stealth).",
     )
     timeout: int = Field(
-        default=30, ge=1, le=600,
+        default=30,
+        ge=1,
+        le=600,
         description="Per-action timeout in seconds.",
     )
 
@@ -304,6 +336,8 @@ class BrowserNode(ActionNode):
     group = ("browser", "tool")
     description = "Interactive browser automation via agent-browser CLI"
     component_kind = "square"
+    tool_name = "browser"
+    tool_description = "Control a web browser interactively. Use snapshot to see the page (returns accessibility tree with @eN refs). Then click/type/fill with those refs. Workflow: navigate -> snapshot -> interact -> snapshot. Operations: navigate, click, type, fill, screenshot, snapshot, get_text, get_html, eval, wait, scroll, select, batch."
     handles = (
         {"name": "input-main", "kind": "input", "position": "left", "label": "Input", "role": "main"},
         {"name": "output-main", "kind": "output", "position": "right", "label": "Output", "role": "main"},
@@ -317,7 +351,7 @@ class BrowserNode(ActionNode):
 
     @Operation("dispatch")
     async def dispatch(self, ctx: NodeContext, params: BrowserParams) -> BrowserOutput:
-        from ._service import get_browser_service
+        from .._service import get_browser_service
 
         svc = get_browser_service()
         if not svc:
@@ -326,10 +360,7 @@ class BrowserNode(ActionNode):
             )
 
         op = params.operation
-        session = (
-            params.session.strip()
-            or f"machina_{ctx.raw.get('execution_id', 'default')}"
-        )
+        session = params.session.strip() or f"machina_{ctx.raw.get('execution_id', 'default')}"
         timeout = params.timeout
         browser_sel = params.browser or "chrome"
         if browser_sel == "bundled":
@@ -354,7 +385,9 @@ class BrowserNode(ActionNode):
         if op == "batch":
             cmds = json.loads(params.commands or "[]")
             data = await svc.run(
-                ["batch", "--json"], session, timeout,
+                ["batch", "--json"],
+                session,
+                timeout,
                 stdin=json.dumps(cmds).encode(),
                 **run_kw,
             )

package/server/nodes/browser/browser/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#ff79c6"
+}

package/server/nodes/chat/{chat_history.py → chat_history/__init__.py}

@@ -38,10 +38,8 @@ class ChatHistoryNode(ActionNode):
     description = "Retrieve chat conversation history"
     component_kind = "square"
     handles = (
-        {"name": "input-main", "kind": "input", "position": "left",
-         "label": "Input", "role": "main"},
-        {"name": "output-main", "kind": "output", "position": "right",
-         "label": "Output", "role": "main"},
+        {"name": "input-main", "kind": "input", "position": "left", "label": "Input", "role": "main"},
+        {"name": "output-main", "kind": "output", "position": "right", "label": "Output", "role": "main"},
     )
     annotations = {"destructive": False, "readonly": True, "open_world": True}
     task_queue = TaskQueue.DEFAULT

package/server/nodes/chat/chat_history/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#8be9fd"
+}

package/server/nodes/chat/{chat_send.py → chat_send/__init__.py}

@@ -42,10 +42,8 @@ class ChatSendNode(ActionNode):
     description = "Send messages to chat conversations"
     component_kind = "square"
     handles = (
-        {"name": "input-main", "kind": "input", "position": "left",
-         "label": "Input", "role": "main"},
-        {"name": "output-main", "kind": "output", "position": "right",
-         "label": "Output", "role": "main"},
+        {"name": "input-main", "kind": "input", "position": "left", "label": "Input", "role": "main"},
+        {"name": "output-main", "kind": "output", "position": "right", "label": "Output", "role": "main"},
     )
     annotations = {"destructive": False, "readonly": False, "open_world": True}
     task_queue = TaskQueue.DEFAULT

package/server/nodes/chat/chat_send/icon.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="#4A90D9"><path d="M20 2H4c-1.1 0-2 .9-2 2v18l4-4h14c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2zm0 14H6l-2 2V4h16v12z"/></svg>

package/server/nodes/chat/chat_send/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#8be9fd"
+}

package/server/nodes/code/_base.py

@@ -11,7 +11,7 @@ from typing import Any, Optional
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from services.plugin import ActionNode, NodeContext, Operation, TaskQueue
+from services.plugin import ActionNode, TaskQueue
 
 
 class CodeExecutorParams(BaseModel):

package/server/nodes/code/{javascript_executor.py → javascript_executor/__init__.py}

@@ -6,7 +6,7 @@ from typing import Any
 
 from services.plugin import NodeContext, NodeUserError, Operation
 
-from ._base import CodeExecutorBase, CodeExecutorParams
+from .._base import CodeExecutorBase, CodeExecutorParams
 
 
 class JavaScriptExecutorNode(CodeExecutorBase):
@@ -14,6 +14,8 @@ class JavaScriptExecutorNode(CodeExecutorBase):
     display_name = "JavaScript Executor"
     subtitle = "Run JS"
     description = "Execute JavaScript code via persistent Node.js server"
+    tool_name = "javascript_code"
+    tool_description = "Execute JavaScript code for calculations, data processing, and JSON manipulation. Set output variable with result."
 
     @Operation("execute")
     async def execute_op(self, ctx: NodeContext, params: CodeExecutorParams) -> Any:
@@ -21,7 +23,7 @@ class JavaScriptExecutorNode(CodeExecutorBase):
         persistent Node.js server via the shared NodeJSClient singleton."""
         from aiohttp import ClientConnectorError
 
-        from ._nodejs import get_nodejs_client
+        from .._nodejs import get_nodejs_client
 
         if not params.code.strip():
             raise NodeUserError("No code provided")
@@ -48,9 +50,7 @@ class JavaScriptExecutorNode(CodeExecutorBase):
             ) from exc
 
         if not result.get("success"):
-            raise NodeUserError(
-                result.get("error") or "JavaScript executor failed"
-            )
+            raise NodeUserError(result.get("error") or "JavaScript executor failed")
         return {
             "output": result.get("output"),
             "console_output": result.get("console_output", ""),

package/server/nodes/code/javascript_executor/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#ffb86c"
+}

package/server/nodes/code/{python_executor.py → python_executor/__init__.py}

@@ -6,15 +6,13 @@ from typing import Any
 
 from services.plugin import NodeContext, NodeUserError, Operation
 
-from ._base import CodeExecutorBase, CodeExecutorParams
+from .._base import CodeExecutorBase, CodeExecutorParams
 
 
 # Names available in the sandbox namespace -- kept here so the
 # error-handler can list them when the LLM tries `import X` and hits
 # the "no __import__" wall.
-_SANDBOX_NAMES = (
-    "math, json, datetime, timedelta, re, random, Counter, defaultdict"
-)
+_SANDBOX_NAMES = "math, json, datetime, timedelta, re, random, Counter, defaultdict"
 
 
 class PythonExecutorNode(CodeExecutorBase):
@@ -22,6 +20,8 @@ class PythonExecutorNode(CodeExecutorBase):
     display_name = "Python Executor"
     subtitle = "Run Python"
     description = "Execute Python code for calculations, data processing, and automation"
+    tool_name = "python_code"
+    tool_description = "Execute Python code for calculations, data processing, and automation. Available: math, json, datetime, Counter, defaultdict. Set output variable with result."
 
     @Operation("execute")
     async def execute_op(self, ctx: NodeContext, params: CodeExecutorParams) -> Any:
@@ -52,13 +52,33 @@ class PythonExecutorNode(CodeExecutorBase):
             print(*args, **kwargs)
 
         safe_builtins = {
-            "abs": abs, "all": all, "any": any, "bool": bool,
-            "dict": dict, "enumerate": enumerate, "filter": filter,
-            "float": float, "int": int, "len": len, "list": list,
-            "map": map, "max": max, "min": min, "print": captured_print,
-            "range": range, "round": round, "set": set, "sorted": sorted,
-            "str": str, "sum": sum, "tuple": tuple, "type": type, "zip": zip,
-            "True": True, "False": False, "None": None,
+            "abs": abs,
+            "all": all,
+            "any": any,
+            "bool": bool,
+            "dict": dict,
+            "enumerate": enumerate,
+            "filter": filter,
+            "float": float,
+            "int": int,
+            "len": len,
+            "list": list,
+            "map": map,
+            "max": max,
+            "min": min,
+            "print": captured_print,
+            "range": range,
+            "round": round,
+            "set": set,
+            "sorted": sorted,
+            "str": str,
+            "sum": sum,
+            "tuple": tuple,
+            "type": type,
+            "zip": zip,
+            "True": True,
+            "False": False,
+            "None": None,
             # Pre-injected modules — match the documented sandbox contract
             # (skill docs, CLAUDE.md). No __import__: callers reference these
             # by name, e.g. ``datetime.datetime.now()`` not ``import datetime``.
@@ -113,9 +133,7 @@ class PythonExecutorNode(CodeExecutorBase):
 
             captured = stdout_capture.getvalue()
             suffix = f"\n\nstdout before error:\n{captured}" if captured else ""
-            raise NodeUserError(
-                f"{err_type}{line_info}: {err_msg}{suffix}"
-            ) from exc
+            raise NodeUserError(f"{err_type}{line_info}: {err_msg}{suffix}") from exc
 
         return {
             "output": namespace.get("output"),

package/server/nodes/code/python_executor/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#ffb86c"
+}

package/server/nodes/code/{typescript_executor.py → typescript_executor/__init__.py}

@@ -6,7 +6,7 @@ from typing import Any
 
 from services.plugin import NodeContext, NodeUserError, Operation
 
-from ._base import CodeExecutorBase, CodeExecutorParams
+from .._base import CodeExecutorBase, CodeExecutorParams
 
 
 class TypeScriptExecutorNode(CodeExecutorBase):
@@ -14,13 +14,15 @@ class TypeScriptExecutorNode(CodeExecutorBase):
     display_name = "TypeScript Executor"
     subtitle = "Run TS"
     description = "Execute TypeScript code via persistent Node.js server with type safety"
+    tool_name = "typescript_code"
+    tool_description = "Execute TypeScript code via persistent Node.js server with type safety. Set output variable with result."
 
     @Operation("execute")
     async def execute_op(self, ctx: NodeContext, params: CodeExecutorParams) -> Any:
         """Inlined from handlers/code.py (Wave 11.D.2)."""
         from aiohttp import ClientConnectorError
 
-        from ._nodejs import get_nodejs_client
+        from .._nodejs import get_nodejs_client
 
         if not params.code.strip():
             raise NodeUserError("No code provided")
@@ -44,9 +46,7 @@ class TypeScriptExecutorNode(CodeExecutorBase):
             ) from exc
 
         if not result.get("success"):
-            raise NodeUserError(
-                result.get("error") or "TypeScript executor failed"
-            )
+            raise NodeUserError(result.get("error") or "TypeScript executor failed")
         return {
             "output": result.get("output"),
             "console_output": result.get("console_output", ""),

package/server/nodes/code/typescript_executor/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#ffb86c"
+}

package/server/nodes/document/{document_parser.py → document_parser/__init__.py}

@@ -16,24 +16,28 @@ logger = get_logger(__name__)
 
 def _parse_file_sync(path: Path, parser: str) -> str:
     """Synchronous file parsing — runs in thread pool."""
-    if parser == 'pypdf':
+    if parser == "pypdf":
         from pypdf import PdfReader
-        return "\n\n".join(p.extract_text() or '' for p in PdfReader(str(path)).pages)
-    if parser == 'marker':
+
+        return "\n\n".join(p.extract_text() or "" for p in PdfReader(str(path)).pages)
+    if parser == "marker":
         from marker.converters.pdf import PdfConverter
         from marker.models import create_model_dict
+
         converter = PdfConverter(artifact_dict=create_model_dict())
         result = converter(str(path))
-        return result.markdown if hasattr(result, 'markdown') else str(result)
-    if parser == 'unstructured':
+        return result.markdown if hasattr(result, "markdown") else str(result)
+    if parser == "unstructured":
         from unstructured.partition.auto import partition
+
         return "\n\n".join(str(el) for el in partition(str(path)))
-    if parser == 'beautifulsoup':
+    if parser == "beautifulsoup":
         from bs4 import BeautifulSoup
-        soup = BeautifulSoup(path.read_text(errors='ignore'), 'html.parser')
+
+        soup = BeautifulSoup(path.read_text(errors="ignore"), "html.parser")
         for s in soup(["script", "style"]):
             s.decompose()
-        return soup.get_text(separator='\n')
+        return soup.get_text(separator="\n")
     raise ValueError(f"Unknown parser: {parser}")
 
 
@@ -88,7 +92,7 @@ class DocumentParserNode(ActionNode):
         parser = params.parser
         explicit_path = params.file_path
         input_dir = params.input_dir
-        file_pattern = params.file_pattern or '*.pdf'
+        file_pattern = params.file_pattern or "*.pdf"
 
         paths: list[Path] = []
         if explicit_path:
@@ -103,13 +107,20 @@ class DocumentParserNode(ActionNode):
         for path in paths:
             try:
                 content = await asyncio.to_thread(_parse_file_sync, path, parser)
-                documents.append({
-                    'source': str(path), 'filename': path.name,
-                    'content': content, 'length': len(content), 'parser': parser,
-                })
+                documents.append(
+                    {
+                        "source": str(path),
+                        "filename": path.name,
+                        "content": content,
+                        "length": len(content),
+                        "parser": parser,
+                    }
+                )
             except Exception as e:
-                failed.append({'file': str(path), 'error': str(e)})
+                failed.append({"file": str(path), "error": str(e)})
 
         return DocumentParserOutput(
-            documents=documents, parsed_count=len(documents), failed=failed,
+            documents=documents,
+            parsed_count=len(documents),
+            failed=failed,
         )

package/server/nodes/document/document_parser/meta.json

@@ -0,0 +1,3 @@
+{
+  "color": "#bd93f9"
+}