chore: import upstream snapshot with attribution

autoagent/agents/system_agent/programming_agent.py

@@ -0,0 +1,98 @@
+from autoagent.types import Agent
+from autoagent.tools import (
+    gen_code_tree_structure, execute_command, read_file, create_file, write_file, list_files, create_directory, run_python, terminal_page_up, terminal_page_down, terminal_page_to
+)
+from autoagent.util import make_message, make_tool_message
+from autoagent.registry import register_agent, register_plugin_agent
+from constant import LOCAL_ROOT, DOCKER_WORKPLACE_NAME
+from autoagent.environment import DockerEnv, BrowserEnv, LocalEnv
+from typing import Union
+from inspect import signature
+def examples(context_variables):
+    working_dir = context_variables.get("working_dir", None)
+    examples_list = []
+    examples_list.extend(make_message('user', "Create a list of numbers from 1 to 10, and display them in a web page at port 5000."))
+    examples_list.extend(make_message('assistant', "I should first use create_file to write the python code into a file named 'app.py' for starting a web server"))
+    examples_list.extend(make_tool_message(create_file, {'path': f"/{working_dir}/app.py", 
+            'content': """
+from flask import Flask
+app = Flask(__name__)
+
+@app.route('/')
+def index():
+    numbers = list(range(1, 11))
+    return str(numbers)
+
+if __name__ == '__main__':
+    app.run(port=5000)"""}, f"File created at: /{working_dir}/app.py"))
+    examples_list.extend(make_message('assistant', 'I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you using `run_python`'))
+    examples_list.extend(make_tool_message(run_python, {'code_path': f"/{working_dir}/app.py"}, f"""
+Traceback (most recent call last):
+  File "/{working_dir}/app.py", line 2, in <module>
+    from flask import Flask
+ModuleNotFoundError: No module named 'flask'"""))
+    examples_list.extend(make_message('assistant', "It seems that Flask is not installed. Let me install Flask for you using `execute_command` by the command: pip install flask"))
+    examples_list.extend(make_tool_message(execute_command, {'command': 'pip install flask'}, """Defaulting to user installation because normal site-packages is not writeable
+Collecting flask
+  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
+Collecting blinker>=1.6.2
+  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
+Collecting Werkzeug>=3.0.0
+  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
+Collecting click>=8.1.3
+  Using cached click-8.1.7-py3-none-any.whl (97 kB)
+Collecting itsdangerous>=2.1.2
+  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
+Requirement already satisfied: Jinja2>=3.1.2 in /home/openhands/.local/lib/python3.10/site-packages (from flask) (3.1.3)
+Requirement already satisfied: MarkupSafe>=2.0 in /home/openhands/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
+Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
+Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0"""))
+    examples_list.extend(make_message('assistant', "Now that Flask is installed, let me run the Python file again using `run_python`"))
+    examples_list.extend(make_tool_message(run_python, {'code_path': f"/{working_dir}/app.py"}, """* Serving Flask app 'app'
+ * Debug mode: off
+WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
+ * Running on http://127.0.0.1:5000
+Press CTRL+C to quit"""))
+    examples_list.extend(make_message('assistant', """The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. Your task is completed."""))
+    return examples_list
+
+@register_agent(name= "Coding Agent", func_name="get_coding_agent")
+@register_plugin_agent(name= "Coding Agent", func_name="get_coding_agent")
+def get_coding_agent(model: str, **kwargs):
+    def instructions(context_variables):
+      code_env: Union[DockerEnv, LocalEnv] = context_variables.get("code_env", LocalEnv())
+      return f"""You are a helpful programming assistant that can write and execute code. You are working in the folder: `{code_env.docker_workplace}`, and you can only access the files in this folder.
+
+  Your can leverage your capabilities by using the specific functions listed below:
+
+  1. Creating project structures based on the user requirement using function `create_directory`.
+  2. Writing clean, efficient, and well-documented code using function `create_file` and `write_file`.
+  3. You must run python scripts using function `run_python` rather than using the `execute_command` function.
+  4. Exam the project to re-use the existing code snippets as much as possible, you may need to use
+  functions like `list_files`, `read_file` and `write_file`.
+  5. Writing the code into the file when creating new files, do not create empty files.
+  6. Before you write code into the existing files, you should first read the file content using function `read_file` and reserve the original content as much as possible.
+  7. Decide whether the task requires execution and debugging before moving to the next or not.
+  8. Generate the commands to run and test the current task, and the dependencies list for this task.
+  9. You only write Python scripts, don't write Jupiter notebooks which require interactive execution.
+  10. Note that every path you read, write, or search should be the absolute path (starting with '/').
+  11. If you should use programming other than Python, you should use the `write_file` function to write the code into a file, and then use the `execute_command` function to run the code.
+  12. If the terminal output is too long, you should use `terminal_page_up` to move the viewport up, `terminal_page_down` to move the viewport down, `terminal_page_to` to move the viewport to the specific page of terminal where the meaningful content is.
+
+  Note that you can use this agent to make complex computation, write a api request, and anything else that can be done by writing code.
+
+  When you think you have completed the task the `System Triage Agent` asked you to do, you should use `transfer_back_to_triage_agent` to transfer the conversation back to the `System Triage Agent`. And you should not stop to try to solve the user's request by transferring to `System Triage Agent` only until the task is completed.
+
+  [IMPORTANT] You can only complete the task by coding. Talk is cheap, show me the code with tools.
+  """
+    tool_list = [gen_code_tree_structure, execute_command, read_file, create_file, write_file, list_files, create_directory, run_python, terminal_page_up, terminal_page_down, terminal_page_to]
+    
+    return Agent(
+    name="Coding Agent",
+    model=model,
+    instructions=instructions,
+    functions=tool_list,
+    # examples=examples,
+    tool_choice = "required", 
+    parallel_tool_calls = False
+    )