github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2025-12-26 05:48:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: convert agent prompts into structured Jinja2 templates (#3360)

Browse Source 
* commit jinja draft

* remove extra file

* update system prompt

* remove github message

* update prompts

* add prompt manager and its tests

* use prompt manager for codeact and bump version

* fix integration tests

* fix lint

* simplify test case

* update system

* fix integration tests

* update credit path for aider

* Update CREDITS.md

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

---------

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
This commit is contained in:
Xingyao Wang 2024-08-19 00:38:46 +08:00 committed by GitHub
parent a2ea17909d
commit 537fb7d985
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
12 changed files with 499 additions and 90 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CREDITS.md
View File

@ -14,7 +14,7 @@ OpenDevin includes and adapts the following open source projects. We are gratefu
#### [Aider](https://github.com/paul-gauthier/aider)
- License: Apache License 2.0
- Description: AI pair programming tool. OpenDevin has adapted and integrated its linter module for code-related tasks in ./opendevin/runtime/plugins/agent_skills/agentskills.py.
- Description: AI pair programming tool. OpenDevin has adapted and integrated its linter module for code-related tasks in [`agentskills utilities`](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/agent_skills/utils/aider)
#### [BrowserGym](https://github.com/ServiceNow/BrowserGym)
- License: Apache License 2.0

61
agenthub/codeact_agent/codeact_agent.py
View File

@ -1,11 +1,6 @@
import os
from agenthub.codeact_agent.action_parser import CodeActResponseParser
from agenthub.codeact_agent.prompt import (
COMMAND_DOCS,
EXAMPLES,
GITHUB_MESSAGE,
SYSTEM_PREFIX,
SYSTEM_SUFFIX,
)
from opendevin.controller.agent import Agent
from opendevin.controller.state.state import State
from opendevin.core.config import AgentConfig
@ -32,24 +27,11 @@ from opendevin.runtime.plugins import (
JupyterRequirement,
PluginRequirement,
)
ENABLE_GITHUB = True
# FIXME: We can tweak these two settings to create MicroAgents specialized toward different area
def get_system_message() -> str:
if ENABLE_GITHUB:
return f'{SYSTEM_PREFIX}\n{GITHUB_MESSAGE}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
else:
return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
def get_in_context_example() -> str:
return EXAMPLES
from opendevin.utils.prompt import PromptManager
class CodeActAgent(Agent):
VERSION = '1.8'
VERSION = '1.9'
"""
The Code Act Agent is a minimalist agent.
The agent works by passing the model a list of action-observation pairs and prompting the model to take the next step.
@ -67,23 +49,6 @@ class CodeActAgent(Agent):
![image](https://github.com/OpenDevin/OpenDevin/assets/38853559/92b622e3-72ad-4a61-8f41-8c040b6d5fb3)
### Plugin System
To make the CodeAct agent more powerful with only access to `bash` action space, CodeAct agent leverages OpenDevin's plugin system:
- [Jupyter plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/jupyter): for IPython execution via bash command
- [SWE-agent tool plugin](https://github.com/OpenDevin/OpenDevin/tree/main/opendevin/runtime/plugins/swe_agent_commands): Powerful bash command line tools for software development tasks introduced by [swe-agent](https://github.com/princeton-nlp/swe-agent).
### Demo
https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
*Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)*
### Work-in-progress & Next step
[] Support web-browsing
[] Complete the workflow for CodeAct agent to submit Github PRs
"""
sandbox_plugins: list[PluginRequirement] = [
@ -94,9 +59,6 @@ class CodeActAgent(Agent):
JupyterRequirement(),
]
system_message: str = get_system_message()
in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
action_parser = CodeActResponseParser()
def __init__(
@ -111,6 +73,11 @@ class CodeActAgent(Agent):
"""
super().__init__(llm, config)
self.reset()
self.prompt_manager = PromptManager(
prompt_dir=os.path.join(os.path.dirname(__file__)),
agent_skills_docs=AgentSkillsRequirement.documentation,
micro_agent_name=None, # TODO: implement micro-agent
)
def action_to_str(self, action: Action) -> str:
if isinstance(action, CmdRunAction):
@ -218,8 +185,14 @@ class CodeActAgent(Agent):
def _get_messages(self, state: State) -> list[Message]:
messages: list[Message] = [
Message(role='system', content=[TextContent(text=self.system_message)]),
Message(role='user', content=[TextContent(text=self.in_context_example)]),
Message(
role='system',
content=[TextContent(text=self.prompt_manager.system_message)],
),
Message(
role='user',
content=[TextContent(text=self.prompt_manager.initial_user_message)],
),
]
for event in state.history.get_events():

41
agenthub/codeact_agent/system_prompt.j2 Normal file
View File

@ -0,0 +1,41 @@
{% set MINIMAL_SYSTEM_PREFIX %}
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
The assistant can use an interactive Python (Jupyter Notebook) environment, executing code with <execute_ipython>.
<execute_ipython>
print("Hello World!")
</execute_ipython>
The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
Important, however: do not run interactive commands. You do not have access to stdin.
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
{% endset %}
{% set BROWSING_PREFIX %}
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
{% endset %}
{% set PIP_INSTALL_PREFIX %}
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
{% endset %}
{% set SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX %}
{% set COMMAND_DOCS %}
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
{{ agent_skills_docs }}
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
{% endset %}
{% set SYSTEM_SUFFIX %}
Responses should be concise.
The assistant should attempt fewer things at a time instead of putting too many commands OR too much code in one "execute" block.
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
{% endset %}
{# Combine all parts without newlines between them #}
{{ SYSTEM_PREFIX -}}
{{- COMMAND_DOCS -}}
{{- SYSTEM_SUFFIX }}

231
agenthub/codeact_agent/user_prompt.j2 Normal file
View File

@ -0,0 +1,231 @@
{% set DEFAULT_EXAMPLE %}
--- START OF EXAMPLE ---
USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
ASSISTANT:
Sure! Let me create a Python file `app.py`:
<execute_ipython>
create_file('app.py')
</execute_ipython>
USER:
OBSERVATION:
[File: /workspace/app.py (1 lines total)]
(this is the beginning of the file)
1|
(this is the end of the file)
[File app.py created.]
ASSISTANT:
Now I will write the Python code for starting a web server and save it to the file `app.py`:
<execute_ipython>
EDITED_CODE="""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)"""
insert_content_at_line(
'app.py',
1,
EDITED_CODE,
)
</execute_ipython>
USER:
OBSERVATION:
(this is the beginning of the file)
1|from flask import Flask
2|app = Flask(__name__)
3|
4|@app.route('/')
5|def index():
6| numbers = list(range(1, 11))
7| return str(numbers)
8|
9|if __name__ == '__main__':
10| app.run(port=5000)
(this is the end of the file)
[File updated (edited at line 1). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
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:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
OBSERVATION:
[1] 121[1]+ Exit 1 python3 app.py > server.log 2>&1
ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
<execute_bash>
cat server.log
</execute_bash>
USER:
OBSERVATION:
Traceback (most recent call last):
File "/workspace/app.py", line 2, in <module>
from flask import Flask
ModuleNotFoundError: No module named 'flask'
ASSISTANT:
It seems that Flask is not installed. Let me install Flask for you:
<execute_bash>
pip install flask
</execute_bash>
USER:
OBSERVATION:
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/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.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
ASSISTANT:
Now that Flask is installed, let me run the Python file again:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
OBSERVATION:
[1] 124
ASSISTANT:
Let me check the server log again:
<execute_bash>
cat server.log
</execute_bash>
USER:
OBSERVATION:
* 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
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. If you have any further questions, feel free to ask!
USER: Now browse the newly started server's homepage and show me the content.
ASSISTANT:
Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
<execute_browse>
Get the content on "http://127.0.0.1:5000"
</execute_browse>
USER:
OBSERVATION:
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
ASSISTANT:
The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
USER: Now kill the server, make it display the numbers in a table format.
ASSISTANT:
Sure! Let me stop the server first:
<execute_bash>
kill 124
</execute_bash>
USER:
OBSERVATION:
[1]+ Terminated python3 app.py > server.log 2>&1
ASSISTANT:
The server has been stopped. Let me open the Python file and modify it.
<execute_ipython>
open_file('app.py')
</execute_ipython>
USER:
[File: /workspace/app.py (10 lines total)]
(this is the beginning of the file)
1|from flask import Flask
2|app = Flask(__name__)
3|
4|@app.route('/')
5|def index():
6| numbers = list(range(1, 11))
7| return str(numbers)
8|
9|if __name__ == '__main__':
10| app.run(port=5000)
(this is the end of the file)
ASSISTANT:
I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
<execute_ipython>
edit_file_by_replace(
'app.py',
to_replace=" return str(numbers)",
new_content=" return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'",
)
</execute_ipython>
USER:
Observation:
[File: /workspace/app.py (10 lines total after edit)]
(this is the beginning of the file)
1|from flask import Flask
2|app = Flask(__name__)
3|
4|@app.route('/')
5|def index():
6| numbers = list(range(1, 11))
7| return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
8|
9|if __name__ == '__main__':
10| app.run(port=5000)
(this is the end of the file)
[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
ASSISTANT:
Running the updated file:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 126
ASSISTANT:
The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
<finish></finish>
--- END OF EXAMPLE ---
{% endset %}
Here is an example of how you can interact with the environment for task solving:
{{ DEFAULT_EXAMPLE }}
{% if micro_agent %}
--- BEGIN OF GUIDELINE ---
The following information may assist you in completing your task:
{{ micro_agent }}
--- END OF GUIDELINE ---
{% endif %}
NOW, LET'S START!

70
opendevin/utils/prompt.py Normal file
View File

@ -0,0 +1,70 @@
import os
from jinja2 import Template
class PromptManager:
"""
Manages prompt templates and micro-agents for AI interactions.
This class handles loading and rendering of system and user prompt templates,
as well as loading micro-agent specifications. It provides methods to access
rendered system and initial user messages for AI interactions.
Attributes:
prompt_dir (str): Directory containing prompt templates.
agent_skills_docs (str): Documentation of agent skills.
micro_agent (str | None): Content of the micro-agent definition file, if specified.
"""
def __init__(
self,
prompt_dir: str,
agent_skills_docs: str,
micro_agent_name: str | None = None,
):
self.prompt_dir: str = prompt_dir
self.agent_skills_docs: str = agent_skills_docs
self.system_template: Template = self._load_template('system_prompt')
self.user_template: Template = self._load_template('user_prompt')
self.micro_agent: str | None = (
self._load_micro_agent(micro_agent_name) if micro_agent_name else None
)
def _load_template(self, template_name: str) -> Template:
template_path = os.path.join(self.prompt_dir, f'{template_name}.j2')
if not os.path.exists(template_path):
raise FileNotFoundError(f'Prompt file {template_path} not found')
with open(template_path, 'r') as file:
return Template(file.read())
def _load_micro_agent(self, micro_agent_name: str) -> str:
micro_agent_path = os.path.join(self.prompt_dir, f'micro/{micro_agent_name}.md')
if not os.path.exists(micro_agent_path):
raise FileNotFoundError(
f'Micro agent file {micro_agent_path} for {micro_agent_name} is not found'
)
with open(micro_agent_path, 'r') as file:
return file.read()
@property
def system_message(self) -> str:
rendered = self.system_template.render(
agent_skills_docs=self.agent_skills_docs,
).strip()
return rendered
@property
def initial_user_message(self) -> str:
"""This is the initial user message provided to the agent
before *actual* user instructions are provided.
It is used to provide a demonstration of how the agent
should behave in order to solve the user's task. And it may
optionally contain some additional context about the user's task.
These additional context will convert the current generic agent
into a more specialized agent that is tailored to the user's task.
"""
rendered = self.user_template.render(micro_agent=self.micro_agent)
return rendered.strip()

12
tests/integration/mock/eventstream_runtime/CodeActAgent/test_ipython/prompt_001.log
View File

@ -14,15 +14,12 @@ Important, however: do not run interactive commands. You do not have access to s
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
To interact with GitHub, use the $GITHUB_TOKEN environment variable.
For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
If $GITHUB_TOKEN is not set, ask the user to set it.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
open_file(path: str, line_number: int | None = 1, context_lines: int | None = 100) -> None:
@ -160,6 +157,7 @@ parse_pptx(file_path: str) -> None:
Args:
file_path: str: The path to the file to open.
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
Responses should be concise.
@ -167,8 +165,7 @@ The assistant should attempt fewer things at a time instead of putting too many
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
When handling files, try to use full paths and pwd to avoid errors.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
----------
@ -394,6 +391,7 @@ The server is running on port 5000 with PID 126. You can access the list of numb
--- END OF EXAMPLE ---
NOW, LET'S START!
----------

12
tests/integration/mock/eventstream_runtime/CodeActAgent/test_ipython/prompt_002.log
View File

@ -14,15 +14,12 @@ Important, however: do not run interactive commands. You do not have access to s
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
To interact with GitHub, use the $GITHUB_TOKEN environment variable.
For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
If $GITHUB_TOKEN is not set, ask the user to set it.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
open_file(path: str, line_number: int | None = 1, context_lines: int | None = 100) -> None:
@ -160,6 +157,7 @@ parse_pptx(file_path: str) -> None:
Args:
file_path: str: The path to the file to open.
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
Responses should be concise.
@ -167,8 +165,7 @@ The assistant should attempt fewer things at a time instead of putting too many
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
When handling files, try to use full paths and pwd to avoid errors.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
----------
@ -394,6 +391,7 @@ The server is running on port 5000 with PID 126. You can access the list of numb
--- END OF EXAMPLE ---
NOW, LET'S START!
----------

12
tests/integration/mock/eventstream_runtime/CodeActAgent/test_ipython_module/prompt_001.log
View File

@ -14,15 +14,12 @@ Important, however: do not run interactive commands. You do not have access to s
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
To interact with GitHub, use the $GITHUB_TOKEN environment variable.
For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
If $GITHUB_TOKEN is not set, ask the user to set it.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
open_file(path: str, line_number: int | None = 1, context_lines: int | None = 100) -> None:
@ -160,6 +157,7 @@ parse_pptx(file_path: str) -> None:
Args:
file_path: str: The path to the file to open.
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
Responses should be concise.
@ -167,8 +165,7 @@ The assistant should attempt fewer things at a time instead of putting too many
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
When handling files, try to use full paths and pwd to avoid errors.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
----------
@ -394,6 +391,7 @@ The server is running on port 5000 with PID 126. You can access the list of numb
--- END OF EXAMPLE ---
NOW, LET'S START!
----------

14
tests/integration/mock/eventstream_runtime/CodeActAgent/test_ipython_module/prompt_002.log
View File

@ -14,15 +14,12 @@ Important, however: do not run interactive commands. You do not have access to s
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
To interact with GitHub, use the $GITHUB_TOKEN environment variable.
For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
If $GITHUB_TOKEN is not set, ask the user to set it.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
open_file(path: str, line_number: int | None = 1, context_lines: int | None = 100) -> None:
@ -160,6 +157,7 @@ parse_pptx(file_path: str) -> None:
Args:
file_path: str: The path to the file to open.
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
Responses should be concise.
@ -167,8 +165,7 @@ The assistant should attempt fewer things at a time instead of putting too many
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
When handling files, try to use full paths and pwd to avoid errors.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
----------
@ -394,6 +391,7 @@ The server is running on port 5000 with PID 126. You can access the list of numb
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
@ -417,7 +415,7 @@ Collecting pymsgbox==1.0.9
[?25h Preparing metadata (pyproject.toml) ... [?25l- done
[?25hBuilding wheels for collected packages: pymsgbox
Building wheel for pymsgbox (pyproject.toml) ... [?25l- done
[?25h Created wheel for pymsgbox: filename=PyMsgBox-1.0.9-py3-none-any.whl size=7406 sha256=ef14d567d93427570776c0692e72503e364d52371ced8369846b1c6f72ea9a2b
[?25h Created wheel for pymsgbox: filename=PyMsgBox-1.0.9-py3-none-any.whl size=7406 sha256=391299f2b6b17f4a9ea59401bcd79dad45a98a5fd3dd3ce22cfe879cf074e2b4
Stored in directory: /home/opendevin/.cache/pip/wheels/85/92/63/e126ee5f33d8f2ed04f96e43ef5df7270a2f331848752e8662
Successfully built pymsgbox
Installing collected packages: pymsgbox

14
tests/integration/mock/eventstream_runtime/CodeActAgent/test_ipython_module/prompt_003.log
View File

@ -14,15 +14,12 @@ Important, however: do not run interactive commands. You do not have access to s
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
To interact with GitHub, use the $GITHUB_TOKEN environment variable.
For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
If $GITHUB_TOKEN is not set, ask the user to set it.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
open_file(path: str, line_number: int | None = 1, context_lines: int | None = 100) -> None:
@ -160,6 +157,7 @@ parse_pptx(file_path: str) -> None:
Args:
file_path: str: The path to the file to open.
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
Responses should be concise.
@ -167,8 +165,7 @@ The assistant should attempt fewer things at a time instead of putting too many
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
When handling files, try to use full paths and pwd to avoid errors.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
----------
@ -394,6 +391,7 @@ The server is running on port 5000 with PID 126. You can access the list of numb
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
@ -417,7 +415,7 @@ Collecting pymsgbox==1.0.9
[?25h Preparing metadata (pyproject.toml) ... [?25l- done
[?25hBuilding wheels for collected packages: pymsgbox
Building wheel for pymsgbox (pyproject.toml) ... [?25l- done
[?25h Created wheel for pymsgbox: filename=PyMsgBox-1.0.9-py3-none-any.whl size=7406 sha256=ef14d567d93427570776c0692e72503e364d52371ced8369846b1c6f72ea9a2b
[?25h Created wheel for pymsgbox: filename=PyMsgBox-1.0.9-py3-none-any.whl size=7406 sha256=391299f2b6b17f4a9ea59401bcd79dad45a98a5fd3dd3ce22cfe879cf074e2b4
Stored in directory: /home/opendevin/.cache/pip/wheels/85/92/63/e126ee5f33d8f2ed04f96e43ef5df7270a2f331848752e8662
Successfully built pymsgbox
Installing collected packages: pymsgbox

14
tests/integration/mock/eventstream_runtime/CodeActAgent/test_ipython_module/prompt_004.log
View File

@ -14,15 +14,12 @@ Important, however: do not run interactive commands. You do not have access to s
Also, you need to handle commands that may run indefinitely and not return a result. For such cases, you should redirect the output to a file and run the command in the background to avoid blocking the execution.
For example, to run a Python script that might run indefinitely without returning immediately, you can use the following format: <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
Also, if a command execution result saying like: Command: "npm start" timed out. Sending SIGINT to the process, you should also retry with running the command in the background.
The assistant can browse the Internet with <execute_browse> and </execute_browse>.
For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
To interact with GitHub, use the $GITHUB_TOKEN environment variable.
For example, to push a branch `my_branch` to the GitHub repo `owner/repo`:
<execute_bash> git push https://$GITHUB_TOKEN@github.com/owner/repo.git my_branch </execute_bash>
If $GITHUB_TOKEN is not set, ask the user to set it.
The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
open_file(path: str, line_number: int | None = 1, context_lines: int | None = 100) -> None:
@ -160,6 +157,7 @@ parse_pptx(file_path: str) -> None:
Args:
file_path: str: The path to the file to open.
Please note that THE `edit_file_by_replace`, `append_file` and `insert_content_at_line` FUNCTIONS REQUIRE PROPER INDENTATION. If the assistant would like to add the line ' print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
Responses should be concise.
@ -167,8 +165,7 @@ The assistant should attempt fewer things at a time instead of putting too many
Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
If the assistant is finished with the task you MUST include <finish></finish> in your response.
IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
When handling files, try to use full paths and pwd to avoid errors.
The assistant should utilize full file paths and the 'pwd' command to prevent path-related errors. The assistant should refrain from excessive apologies in its responses.
----------
@ -394,6 +391,7 @@ The server is running on port 5000 with PID 126. You can access the list of numb
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
@ -417,7 +415,7 @@ Collecting pymsgbox==1.0.9
[?25h Preparing metadata (pyproject.toml) ... [?25l- done
[?25hBuilding wheels for collected packages: pymsgbox
Building wheel for pymsgbox (pyproject.toml) ... [?25l- done
[?25h Created wheel for pymsgbox: filename=PyMsgBox-1.0.9-py3-none-any.whl size=7406 sha256=ef14d567d93427570776c0692e72503e364d52371ced8369846b1c6f72ea9a2b
[?25h Created wheel for pymsgbox: filename=PyMsgBox-1.0.9-py3-none-any.whl size=7406 sha256=391299f2b6b17f4a9ea59401bcd79dad45a98a5fd3dd3ce22cfe879cf074e2b4
Stored in directory: /home/opendevin/.cache/pip/wheels/85/92/63/e126ee5f33d8f2ed04f96e43ef5df7270a2f331848752e8662
Successfully built pymsgbox
Installing collected packages: pymsgbox

106
tests/unit/test_prompt_manager.py Normal file
View File

@ -0,0 +1,106 @@
import os
import shutil
import pytest
from opendevin.utils.prompt import PromptManager
@pytest.fixture
def prompt_dir(tmp_path):
# Copy contents from "agenthub/codeact_agent" to the temp directory
shutil.copytree('agenthub/codeact_agent', tmp_path, dirs_exist_ok=True)
# Return the temporary directory path
return tmp_path
SAMPLE_AGENT_SKILLS_DOCS = """Sample agent skills documentation"""
@pytest.fixture
def agent_skills_docs():
return SAMPLE_AGENT_SKILLS_DOCS
def test_prompt_manager_without_micro_agent(prompt_dir, agent_skills_docs):
manager = PromptManager(prompt_dir, agent_skills_docs)
assert manager.prompt_dir == prompt_dir
assert manager.agent_skills_docs == agent_skills_docs
assert manager.micro_agent is None
assert isinstance(manager.system_message, str)
assert (
"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."
in manager.system_message
)
assert SAMPLE_AGENT_SKILLS_DOCS in manager.system_message
assert isinstance(manager.initial_user_message, str)
assert '--- BEGIN OF GUIDELINE ---' not in manager.initial_user_message
assert '--- END OF GUIDELINE ---' not in manager.initial_user_message
assert "NOW, LET'S START!" in manager.initial_user_message
assert 'micro_agent' not in manager.initial_user_message
def test_prompt_manager_with_micro_agent(prompt_dir, agent_skills_docs):
micro_agent_name = 'test_micro_agent'
micro_agent_content = (
'## Micro Agent\n'
'This is a test micro agent.\n'
'It is used to test the prompt manager.\n'
)
# Create a temporary micro agent file
os.makedirs(os.path.join(prompt_dir, 'micro'), exist_ok=True)
with open(os.path.join(prompt_dir, 'micro', f'{micro_agent_name}.md'), 'w') as f:
f.write(micro_agent_content)
manager = PromptManager(prompt_dir, agent_skills_docs, micro_agent_name)
assert manager.prompt_dir == prompt_dir
assert manager.agent_skills_docs == agent_skills_docs
assert manager.micro_agent == micro_agent_content
assert isinstance(manager.system_message, str)
assert (
"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."
in manager.system_message
)
assert SAMPLE_AGENT_SKILLS_DOCS in manager.system_message
assert isinstance(manager.initial_user_message, str)
assert (
'--- BEGIN OF GUIDELINE ---\n'
+ 'The following information may assist you in completing your task:\n\n'
+ micro_agent_content
+ '\n'
+ '--- END OF GUIDELINE ---\n'
+ "\n\nNOW, LET'S START!"
) in manager.initial_user_message
assert micro_agent_content in manager.initial_user_message
# Clean up the temporary file
os.remove(os.path.join(prompt_dir, 'micro', f'{micro_agent_name}.md'))
def test_prompt_manager_file_not_found(prompt_dir, agent_skills_docs):
with pytest.raises(FileNotFoundError):
PromptManager(prompt_dir, agent_skills_docs, 'non_existent_micro_agent')
def test_prompt_manager_template_rendering(prompt_dir, agent_skills_docs):
# Create temporary template files
with open(os.path.join(prompt_dir, 'system_prompt.j2'), 'w') as f:
f.write('System prompt: {{ agent_skills_docs }}')
with open(os.path.join(prompt_dir, 'user_prompt.j2'), 'w') as f:
f.write('User prompt: {{ micro_agent }}')
manager = PromptManager(prompt_dir, agent_skills_docs)
assert manager.system_message == f'System prompt: {agent_skills_docs}'
assert manager.initial_user_message == 'User prompt: None'
# Clean up temporary files
os.remove(os.path.join(prompt_dir, 'system_prompt.j2'))
os.remove(os.path.join(prompt_dir, 'user_prompt.j2'))