Merge develop

.dockerignore

@@ -1,5 +1,28 @@
+**/__pycache__
+**/.venv
+**/.classpath
+**/.dockerignore
+**/.gitignore
 .github
 .idea
 .ollama
-LICENSE
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/charts
+**/docker-compose*
 **/docs
+**/compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+LICENSE
+README.md

.env

@@ -28,11 +28,16 @@ POSTGRES_HOST_PORT=15432
 POSTGRES_CONTAINER_PORT=5432
 #
 # Directories inside a container
-APP_ROOT=/opt/opendevin/app
+APP_ROOT=/opt/opendevin
 WORKSPACE_DIR=/opt/opendevin/workspace
 CONDA_ROOT=/var/lib/miniconda
+# Directories
+APP_DIR=/opt/opendevin
+UI_DIR=/var/www/od_ui
 # Path to ollama models directory at the host machine
 HOST_MODELS_DIR=/mnt/g/LLMs/ollama/models
+WORKSPACE_DIR=/opt/opendevin/workspace
+PYTHONPATH=/opt/opendevin
 # Name of the container's Conda vitual environment
 VENV_NAME=od_env
 #

.github/workflows/lint.yml

@@ -32,11 +32,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: 3.11
-      - name: Create mypy cache directory
-        run: mkdir -p .mypy_cache
-      - name: Install dependencies
-        run: pip install ruff mypy==1.9.0 types-PyYAML types-toml
-      - name: Run mypy
-        run: python -m mypy --install-types --non-interactive --config-file dev_config/python/mypy.ini opendevin/ agenthub/
-      - name: Run ruff
-        run: ruff check --config dev_config/python/ruff.toml opendevin/ agenthub/
+      - name: Install pre-commit
+        run: pip install pre-commit
+      - name: Run pre-commit hooks
+        run: pre-commit run --files opendevin/**/* agenthub/**/* --show-diff-on-failure --config ./dev_config/python/.pre-commit-config.yaml

.github/workflows/stale.yml

@@ -0,0 +1,29 @@
+name: 'Close stale issues'
+on:
+  schedule:
+    - cron: '30 1 * * *'
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/stale@v9
+        with:
+          # Aggressively close issues that have been explicitly labeled `age-out`
+          any-of-labels: age-out
+          stale-issue-message: 'This issue is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 day.'
+          close-issue-message: 'This issue was closed because it has been stalled for over 7 days with no activity.'
+          stale-pr-message: 'This PR is stale because it has been open for 7 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
+          close-pr-message: 'This PR was closed because it has been stalled for over 7 days with no activity.'
+          days-before-stale: 7
+          days-before-close: 1
+
+      - uses: actions/stale@v9
+        with:
+          # Be more lenient with other issues
+          stale-issue-message: 'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
+          close-issue-message: 'This issue was closed because it has been stalled for over 30 days with no activity.'
+          stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
+          close-pr-message: 'This PR was closed because it has been stalled for over 30 days with no activity.'
+          days-before-stale: 30
+          days-before-close: 7

README.md

@@ -157,6 +157,8 @@ For a full list of the LM providers and models available, please consult the [li
 
 There is also [documentation for running with local models using ollama](./docs/documentation/LOCAL_LLM_GUIDE.md).
 
+We are working on a [guide for running OpenDevin with Azure](./docs/documentation/AZURE_LLM_GUIDE.md).
+
 ### 4. Run the Application
 
 - **Run the Application:** Once the setup is complete, launching OpenDevin is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenDevin without any hassle.
@@ -222,7 +224,7 @@ For details, please check [this document](./CONTRIBUTING.md).
 
 ## 🤖 Join Our Community
 
-Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc. 
+Now we have both Slack workspace for the collaboration on building OpenDevin and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
 
 * [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2etftj1dd-X1fDL2PYIVpsmJZkqEYANw)
 * [Discord server](https://discord.gg/mBuDGRzzES)

agenthub/__init__.py

@@ -2,8 +2,8 @@
 load_dotenv()
 
 # Import agents after environment variables are loaded
-from . import monologue_agent # noqa: E402
-from . import codeact_agent # noqa: E402
-from . import planner_agent # noqa: E402
+from . import monologue_agent  # noqa: E402
+from . import codeact_agent  # noqa: E402
+from . import planner_agent  # noqa: E402
 
 __all__ = ['monologue_agent', 'codeact_agent', 'planner_agent']

agenthub/codeact_agent/README.md

@@ -1,6 +1,6 @@
 # CodeAct-based Agent Framework
 
-This folder implements the [CodeAct idea](https://arxiv.org/abs/2402.13463) that relies on LLM to autonomously perform actions in a Bash shell. It requires more from the LLM itself: LLM needs to be capable enough to do all the stuff autonomously, instead of stuck in an infinite loop. 
+This folder implements the [CodeAct idea](https://arxiv.org/abs/2402.13463) that relies on LLM to autonomously perform actions in a Bash shell. It requires more from the LLM itself: LLM needs to be capable enough to do all the stuff autonomously, instead of stuck in an infinite loop.
 
 **NOTE: This agent is still highly experimental and under active development to reach the capability described in the original paper & [repo](https://github.com/xingyaoww/code-act).**
 
@@ -18,6 +18,6 @@ Example: prompts `gpt-4-0125-preview` to write a flask server, install `flask` l
 
 <img width="957" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/68ad10c1-744a-4e9d-bb29-0f163d665a0a">
 
-Most of the things are working as expected, except at the end, the model did not follow the instruction to stop the interaction by outputting `<execute> exit </execute>` as instructed. 
+Most of the things are working as expected, except at the end, the model did not follow the instruction to stop the interaction by outputting `<execute> exit </execute>` as instructed.
 
 **TODO**: This should be fixable by either (1) including a complete in-context example like [this](https://github.com/xingyaoww/mint-bench/blob/main/mint/tasks/in_context_examples/reasoning/with_tool.txt), OR (2) collect some interaction data like this and fine-tune a model (like [this](https://github.com/xingyaoww/code-act), a more complex route).

agenthub/codeact_agent/__init__.py

@@ -1,4 +1,4 @@
 from opendevin.agent import Agent
 from .codeact_agent import CodeActAgent
 
-Agent.register("CodeActAgent", CodeActAgent)
+Agent.register('CodeActAgent', CodeActAgent)

agenthub/codeact_agent/codeact_agent.py

@@ -24,7 +24,7 @@
 {COMMAND_DOCS}
 """
     if COMMAND_DOCS is not None
-    else ""
+    else ''
 )
 SYSTEM_MESSAGE = f"""You are a helpful assistant. You will be provided access (as root) to a bash shell to complete user-provided tasks.
 You will be able to execute commands in the bash shell, interact with the file system, install packages, and receive the output of your commands.
@@ -46,27 +46,29 @@
 {COMMAND_SEGMENT}
 
 When you are done, execute the following to close the shell and end the conversation:
-<execute>exit</execute> 
+<execute>exit</execute>
 """
 
 INVALID_INPUT_MESSAGE = (
     "I don't understand your input. \n"
-    "If you want to execute command, please use <execute> YOUR_COMMAND_HERE </execute>.\n"
-    "If you already completed the task, please exit the shell by generating: <execute> exit </execute>."
+    'If you want to execute command, please use <execute> YOUR_COMMAND_HERE </execute>.\n'
+    'If you already completed the task, please exit the shell by generating: <execute> exit </execute>.'
 )
 
+
 def parse_response(response) -> str:
     action = response.choices[0].message.content
-    if "<execute>" in action and "</execute>" not in action:
-        action += "</execute>"
+    if '<execute>' in action and '</execute>' not in action:
+        action += '</execute>'
     return action
 
+
 class CodeActAgent(Agent):
     """
-    The Code Act Agent is a minimalist agent. 
+    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.
     """
-    
+
     def __init__(
         self,
         llm: LLM,
@@ -82,7 +84,7 @@ def __init__(
 
     def step(self, state: State) -> Action:
         """
-        Performs one step using the Code Act Agent. 
+        Performs one step using the Code Act Agent.
         This includes gathering info on previous steps and prompting the model to make a command to execute.
 
         Parameters:
@@ -97,42 +99,45 @@ def step(self, state: State) -> Action:
         """
 
         if len(self.messages) == 0:
-            assert state.plan.main_goal, "Expecting instruction to be set"
+            assert state.plan.main_goal, 'Expecting instruction to be set'
             self.messages = [
-                {"role": "system", "content": SYSTEM_MESSAGE},
-                {"role": "user", "content": state.plan.main_goal},
+                {'role': 'system', 'content': SYSTEM_MESSAGE},
+                {'role': 'user', 'content': state.plan.main_goal},
             ]
         updated_info = state.updated_info
         if updated_info:
             for prev_action, obs in updated_info:
                 assert isinstance(
                     prev_action, (CmdRunAction, AgentEchoAction)
-                ), "Expecting CmdRunAction or AgentEchoAction for Action"
+                ), 'Expecting CmdRunAction or AgentEchoAction for Action'
                 if isinstance(
                     obs, AgentMessageObservation
                 ):  # warning message from itself
-                    self.messages.append({"role": "user", "content": obs.content})
+                    self.messages.append(
+                        {'role': 'user', 'content': obs.content})
                 elif isinstance(obs, CmdOutputObservation):
-                    content = "OBSERVATION:\n" + obs.content
-                    content += f"\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]"
-                    self.messages.append({"role": "user", "content": content})
+                    content = 'OBSERVATION:\n' + obs.content
+                    content += f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
+                    self.messages.append({'role': 'user', 'content': content})
                 else:
                     raise NotImplementedError(
-                        f"Unknown observation type: {obs.__class__}"
+                        f'Unknown observation type: {obs.__class__}'
                     )
         response = self.llm.completion(
             messages=self.messages,
-            stop=["</execute>"],
+            stop=['</execute>'],
             temperature=0.0
         )
         action_str: str = parse_response(response)
-        self.messages.append({"role": "assistant", "content": action_str})
+        state.num_of_chars += sum(len(message['content'])
+                                  for message in self.messages) + len(action_str)
+        self.messages.append({'role': 'assistant', 'content': action_str})
 
-        command = re.search(r"<execute>(.*)</execute>", action_str, re.DOTALL)
+        command = re.search(r'<execute>(.*)</execute>', action_str, re.DOTALL)
         if command is not None:
             # a command was found
             command_group = command.group(1)
-            if command_group.strip() == "exit":
+            if command_group.strip() == 'exit':
                 return AgentFinishAction()
             return CmdRunAction(command=command_group)
             # # execute the code
@@ -149,4 +154,4 @@ def step(self, state: State) -> Action:
             )  # warning message to itself
 
     def search_memory(self, query: str) -> List[str]:
-        raise NotImplementedError("Implement this abstract method")
+        raise NotImplementedError('Implement this abstract method')

agenthub/monologue_agent/TODO.md

@@ -6,4 +6,3 @@ There's a lot of low-hanging fruit for this agent:
 * Improve memory condensing--condense earlier memories more aggressively
 * Limit the time that `run` can wait (in case agent runs an interactive command and it's hanging)
 * Figure out how to run background processes, e.g. `node server.js` to start a server
-

agenthub/monologue_agent/__init__.py

@@ -1,4 +1,4 @@
 from opendevin.agent import Agent
 from .agent import MonologueAgent
 
-Agent.register("MonologueAgent", MonologueAgent)
+Agent.register('MonologueAgent', MonologueAgent)