camel-ai 0.2.65__py3-none-any.whl → 0.2.83a6__py3-none-any.whl

camel/toolkits/browser_toolkit.py

@@ -1,4 +1,4 @@
-# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. =========
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -10,7 +10,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. =========
 
 # Enables postponed evaluation of annotations (for string-based type hints)
 from __future__ import annotations
@@ -147,15 +147,12 @@ class BaseBrowser:
         Returns:
             None
         """
-        from playwright.sync_api import (
-            sync_playwright,
-        )
-
         self.history: List[Any] = []
         self.headless = headless
         self.channel = channel
         self._ensure_browser_installed()
-        self.playwright: Playwright = sync_playwright().start()
+        # lazy initialization - playwright is started in init() method
+        self.playwright: Optional[Playwright] = None
         self.page_history: List[
             str
         ] = []  # stores the history of visited pages
@@ -192,7 +189,11 @@ class BaseBrowser:
 
     def init(self) -> None:
         r"""Initialize the browser."""
-        assert self.playwright is not None
+        # lazy start playwright when init() is called, not in __init__
+        if self.playwright is None:
+            from playwright.sync_api import sync_playwright
+
+            self.playwright = sync_playwright().start()
 
         browser_launch_args = [
             "--disable-blink-features=AutomationControlled",  # Basic stealth
@@ -677,18 +678,17 @@ class BaseBrowser:
         targeted text. It is equivalent to pressing Ctrl + F and searching for
         the text.
         """
-        # ruff: noqa: E501
         assert self.page is not None
         script = f"""
-        (function() {{ 
+        (function() {{
             let text = "{search_text}";
             let found = window.find(text);
             if (!found) {{
                 let elements = document.querySelectorAll("*:not(script):not(
-                style)"); 
+                style)");
                 for (let el of elements) {{
                     if (el.innerText && el.innerText.includes(text)) {{
-                        el.scrollIntoView({{behavior: "smooth", block: 
+                        el.scrollIntoView({{behavior: "smooth", block:
                         "center"}});
                         el.style.backgroundColor = "yellow";
                         el.style.border = '2px solid red';
@@ -737,15 +737,14 @@ class BaseBrowser:
         if self.playwright:
             self.playwright.stop()  # Stop playwright instance
 
-    # ruff: noqa: E501
     def show_interactive_elements(self):
         r"""Show simple interactive elements on the current page."""
         assert self.page is not None
         self.page.evaluate(self.page_script)
         self.page.evaluate("""
         () => {
-            document.querySelectorAll('a, button, input, select, textarea, 
-            [tabindex]:not([tabindex="-1"]), 
+            document.querySelectorAll('a, button, input, select, textarea,
+            [tabindex]:not([tabindex="-1"]),
             [contenteditable="true"]').forEach(el => {
                 el.style.border = '2px solid red';
             });
@@ -829,6 +828,9 @@ class BrowserToolkit(BaseToolkit):
 
         Args:
             headless (bool): Whether to run the browser in headless mode.
+                When running inside a CAMEL runtime container, this is
+                automatically set to True since containers typically don't
+                have a display.
             cache_dir (Union[str, None]): The directory to store cache files.
             channel (Literal["chrome", "msedge", "chromium"]): The browser
                 channel to use. Must be one of "chrome", "msedge", or
@@ -852,6 +854,17 @@ class BrowserToolkit(BaseToolkit):
                 is used without saving data. (default: :obj:`None`)
         """
         super().__init__()  # Call to super().__init__() added
+
+        # auto-detect if running inside a CAMEL runtime container
+        # force headless mode since containers typically don't have a display
+        in_runtime = os.environ.get("CAMEL_RUNTIME", "").lower() == "true"
+        if in_runtime and not headless:
+            logger.info(
+                "Detected CAMEL_RUNTIME environment - enabling headless mode "
+                "since containers typically don't have a display"
+            )
+            headless = True
+
         self.browser = BaseBrowser(
             headless=headless,
             cache_dir=cache_dir,
@@ -890,8 +903,8 @@ class BrowserToolkit(BaseToolkit):
 
         if web_agent_model_backend is None:
             web_agent_model_instance = ModelFactory.create(
-                model_platform=ModelPlatformType.OPENAI,
-                model_type=ModelType.GPT_4_1,
+                model_platform=ModelPlatformType.DEFAULT,
+                model_type=ModelType.DEFAULT,
                 model_config_dict={"temperature": 0, "top_p": 1},
             )
         else:
@@ -899,8 +912,8 @@ class BrowserToolkit(BaseToolkit):
 
         if planning_agent_model_backend is None:
             planning_model = ModelFactory.create(
-                model_platform=ModelPlatformType.OPENAI,
-                model_type=ModelType.O3_MINI,
+                model_platform=ModelPlatformType.DEFAULT,
+                model_type=ModelType.DEFAULT,
             )
         else:
             planning_model = planning_agent_model_backend
@@ -1227,8 +1240,8 @@ Here is a plan about how to solve the task step-by-step which you must follow:
         simulation_result: str
         if not task_completed:
             simulation_result = f"""
-                The task is not completed within the round limit. Please 
-                check the last round {self.history_window} information to 
+                The task is not completed within the round limit. Please
+                check the last round {self.history_window} information to
                 see if there is any useful information:
                 <history>{self.history[-self.history_window :]}</history>
             """

camel/toolkits/browser_toolkit_commons.py

@@ -1,4 +1,4 @@
-# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. =========
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -10,7 +10,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. =========
 from __future__ import annotations
 
 import io
@@ -134,7 +134,7 @@ Please find the final answer, or give valuable insights and founds (e.g. if prev
 
 TASK_PLANNING_PROMPT_TEMPLATE = """
 <task>{task_prompt}</task>
-According to the problem above, if we use browser interaction, what is the general process of the interaction after visiting the webpage `{start_url}`? 
+According to the problem above, if we use browser interaction, what is the general process of the interaction after visiting the webpage `{start_url}`?
 
 Please note that it can be viewed as Partially Observable MDP. Do not over-confident about your plan.
 Please first restate the task in detail, and then provide a detailed plan to solve the task.
@@ -156,7 +156,7 @@ Now please carefully examine the current task planning schema, and our history a
 
 Your output should be in json format, including the following fields:
 - `if_need_replan`: bool, A boolean value indicating whether the task needs to be fundamentally replanned.
-- `replanned_schema`: str, The replanned schema for the task, which should not be changed too much compared with the original one. If the task does not need to be replanned, the value should be an empty string. 
+- `replanned_schema`: str, The replanned schema for the task, which should not be changed too much compared with the original one. If the task does not need to be replanned, the value should be an empty string.
 """  # noqa: E501
 
 AVAILABLE_ACTIONS_PROMPT = """

camel/toolkits/code_execution.py

@@ -1,4 +1,4 @@
-# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. =========
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -10,7 +10,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. =========
 from typing import List, Literal, Optional, Union
 
 from camel.interpreters import (
@@ -18,6 +18,7 @@ from camel.interpreters import (
     E2BInterpreter,
     InternalPythonInterpreter,
     JupyterKernelInterpreter,
+    MicrosandboxInterpreter,
     SubprocessInterpreter,
 )
 from camel.logger import get_logger
@@ -43,18 +44,31 @@ class CodeExecutionToolkit(BaseToolkit):
             (default: :obj:`None`)
         require_confirm (bool): Whether to require confirmation before
             executing code. (default: :obj:`False`)
+        timeout (Optional[float]): General timeout for toolkit operations.
+            (default: :obj:`None`)
+        microsandbox_config (Optional[dict]): Configuration for microsandbox
+            interpreter. Available keys: 'server_url', 'api_key',
+            'namespace', 'sandbox_name', 'timeout'.
+            If None, uses default configuration. (default: :obj:`None`)
     """
 
     def __init__(
         self,
         sandbox: Literal[
-            "internal_python", "jupyter", "docker", "subprocess", "e2b"
+            "internal_python",
+            "jupyter",
+            "docker",
+            "subprocess",
+            "e2b",
+            "microsandbox",
         ] = "subprocess",
         verbose: bool = False,
         unsafe_mode: bool = False,
         import_white_list: Optional[List[str]] = None,
         require_confirm: bool = False,
         timeout: Optional[float] = None,
+        # Microsandbox configuration dictionary
+        microsandbox_config: Optional[dict] = None,
     ) -> None:
         super().__init__(timeout=timeout)
         self.verbose = verbose
@@ -68,6 +82,7 @@ class CodeExecutionToolkit(BaseToolkit):
             DockerInterpreter,
             SubprocessInterpreter,
             E2BInterpreter,
+            MicrosandboxInterpreter,
         ]
 
         if sandbox == "internal_python":
@@ -95,6 +110,18 @@ class CodeExecutionToolkit(BaseToolkit):
             )
         elif sandbox == "e2b":
             self.interpreter = E2BInterpreter(require_confirm=require_confirm)
+        elif sandbox == "microsandbox":
+            # Extract parameters with proper types for microsandbox
+            config = microsandbox_config or {}
+
+            self.interpreter = MicrosandboxInterpreter(
+                require_confirm=require_confirm,
+                server_url=config.get("server_url"),
+                api_key=config.get("api_key"),
+                namespace=config.get("namespace", "default"),
+                sandbox_name=config.get("sandbox_name"),
+                timeout=config.get("timeout", 30),
+            )
         else:
             raise RuntimeError(
                 f"The sandbox type `{sandbox}` is not supported."
@@ -122,7 +149,7 @@ class CodeExecutionToolkit(BaseToolkit):
 
     def execute_command(self, command: str) -> Union[str, tuple[str, str]]:
         r"""Execute a command can be used to resolve the dependency of the
-        code.
+        code. Useful if there's dependency issues when you try to execute code.
 
         Args:
             command (str): The command to execute.