Use generic types (All-Hands-AI#1680)

agenthub/README.md

@@ -16,14 +16,18 @@ Every agent also has a `self.llm` which it can use to interact with the LLM conf
 See the [LiteLLM docs for `self.llm.completion`](https://docs.litellm.ai/docs/completion).
 
 ## State
+
 The `state` contains:
-* A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
-* A list of actions/observations that have happened since the most recent step
-* A [`plan`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/plan.py), which contains the main goal
-  * The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTaskAction`
+
+- A history of actions taken by the agent, as well as any observations (e.g. file content, command output) from those actions
+- A list of actions/observations that have happened since the most recent step
+- A [`plan`](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/plan.py), which contains the main goal
+  - The agent can add and modify subtasks through the `AddTaskAction` and `ModifyTaskAction`
 
 ## Actions
+
 Here is a list of available Actions, which can be returned by `agent.step()`:
+
 - [`CmdRunAction`](../opendevin/action/bash.py) - Runs a command inside a sandboxed terminal
 - [`CmdKillAction`](../opendevin/action/bash.py) - Kills a background command
 - [`IPythonRunCellAction`](../opendevin/action/bash.py) - Execute a block of Python code interactively (in Jupyter notebook) and receives `CmdOutputObservation`. Requires setting up `jupyter` [plugin](../opendevin/sandbox/plugins) as a requirement.
@@ -43,11 +47,13 @@ Here is a list of available Actions, which can be returned by `agent.step()`:
 You can use `action.to_dict()` and `action_from_dict` to serialize and deserialize actions.
 
 ## Observations
+
 There are also several types of Observations. These are typically available in the step following the corresponding Action.
 But they may also appear as a result of asynchronous events (e.g. a message from the user, logs from a command running
 in the background).
 
 Here is a list of available Observations:
+
 - [`CmdOutputObservation`](../opendevin/observation/run.py)
 - [`BrowserOutputObservation`](../opendevin/observation/browse.py)
 - [`FileReadObservation`](../opendevin/observation/files.py)
@@ -59,19 +65,24 @@ Here is a list of available Observations:
 You can use `observation.to_dict()` and `observation_from_dict` to serialize and deserialize observations.
 
 ## Interface
+
 Every agent must implement the following methods:
 
 ### `step`
+
 ```
 def step(self, state: "State") -> "Action"
 ```
+
 `step` moves the agent forward one step towards its goal. This probably means
 sending a prompt to the LLM, then parsing the response into an `Action`.
 
 ### `search_memory`
+
 ```
-def search_memory(self, query: str) -> List[str]:
+def search_memory(self, query: str) -> list[str]:
 ```
+
 `search_memory` should return a list of events that match the query. This will be used
 for the `recall` action.
 

agenthub/SWE_agent/agent.py

@@ -1,5 +1,3 @@
-from typing import List
-
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
 from opendevin.events.action import (
@@ -32,7 +30,7 @@ def __init__(self, llm: LLM):
         super().__init__(llm)
         self.memory_window = 4
         self.max_retries = 2
-        self.running_memory: List[str] = []
+        self.running_memory: list[str] = []
         self.cur_file: str = ''
         self.cur_line: int = 0
 
@@ -41,7 +39,7 @@ def _remember(self, action: Action, observation: Observation) -> None:
         memory = MEMORY_FORMAT(action.to_memory(), observation.to_memory())
         self.running_memory.append(memory)
 
-    def _think_act(self, messages: List[dict]) -> tuple[Action, str]:
+    def _think_act(self, messages: list[dict]) -> tuple[Action, str]:
         resp = self.llm.completion(
             messages=messages,
             temperature=0.05,
@@ -99,7 +97,7 @@ def step(self, state: State) -> Action:
         self.latest_action = action
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return [item for item in self.running_memory if query in item]
 
     def reset(self) -> None:

agenthub/delegator_agent/agent.py

@@ -1,5 +1,3 @@
-from typing import List
-
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
 from opendevin.events.action import Action, AgentDelegateAction, AgentFinishAction
@@ -81,5 +79,5 @@ def step(self, state: State) -> Action:
         else:
             raise Exception('Invalid delegate state')
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return []

agenthub/dummy_agent/agent.py

@@ -1,5 +1,5 @@
 import time
-from typing import List, TypedDict
+from typing import TypedDict
 
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
@@ -35,7 +35,7 @@
 """
 
 ActionObs = TypedDict(
-    'ActionObs', {'action': Action, 'observations': List[Observation]}
+    'ActionObs', {'action': Action, 'observations': list[Observation]}
 )
 
 BACKGROUND_CMD = 'echo "This is in the background" && sleep .1 && echo "This too"'
@@ -49,7 +49,7 @@ class DummyAgent(Agent):
 
     def __init__(self, llm: LLM):
         super().__init__(llm)
-        self.steps: List[ActionObs] = [
+        self.steps: list[ActionObs] = [
             {
                 'action': AddTaskAction(parent='0', goal='check the current directory'),
                 'observations': [NullObservation('')],
@@ -160,5 +160,5 @@ def step(self, state: State) -> Action:
                     ), f'Expected observation {expected_obs}, got {hist_obs}'
         return self.steps[state.iteration]['action']
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return ['I am a computer.']

agenthub/micro/agent.py

@@ -1,5 +1,4 @@
 import json
-from typing import Dict, List
 
 from jinja2 import BaseLoader, Environment
 
@@ -59,7 +58,7 @@ def to_json(obj, **kwargs):
 
 class MicroAgent(Agent):
     prompt = ''
-    agent_definition: Dict = {}
+    agent_definition: dict = {}
 
     def __init__(self, llm: LLM):
         super().__init__(llm)
@@ -83,5 +82,5 @@ def step(self, state: State) -> Action:
         action = parse_response(action_resp)
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return []

agenthub/micro/instructions.py

@@ -1,7 +1,6 @@
 import os
-from typing import Dict
 
-instructions: Dict = {}
+instructions: dict = {}
 
 base_dir = os.path.dirname(os.path.abspath(__file__)) + '/_instructions'
 for root, dirs, files in os.walk(base_dir):

agenthub/monologue_agent/agent.py

@@ -1,5 +1,3 @@
-from typing import List
-
 import agenthub.monologue_agent.utils.prompts as prompts
 from agenthub.monologue_agent.utils.monologue import Monologue
 from opendevin.controller.agent import Agent
@@ -239,7 +237,7 @@ def step(self, state: State) -> Action:
         self.latest_action = action
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         """
         Uses VectorIndexRetriever to find related memories within the long term memory.
         Uses search to produce top 10 results.
@@ -248,7 +246,7 @@ def search_memory(self, query: str) -> List[str]:
         - query (str): The query that we want to find related memories for
 
         Returns:
-        - List[str]: A list of top 10 text results that matched the query
+        - list[str]: A list of top 10 text results that matched the query
         """
         if self.memory is None:
             return []

agenthub/monologue_agent/utils/memory.py

@@ -171,7 +171,7 @@ def search(self, query: str, k: int = 10):
         - k (int): Number of top results to return
 
         Returns:
-        - List[str]: List of top k results found in current memory
+        - list[str]: list of top k results found in current memory
         """
         retriever = VectorIndexRetriever(
             index=self.index,

agenthub/monologue_agent/utils/monologue.py

@@ -36,7 +36,7 @@ def get_thoughts(self):
         Get the current thoughts of the agent.
 
         Returns:
-        - List: The list of thoughts that the agent has.
+        - list: The list of thoughts that the agent has.
         """
         return self.thoughts
 

agenthub/monologue_agent/utils/prompts.py

@@ -1,6 +1,5 @@
 import re
 from json import JSONDecodeError
-from typing import List
 
 from opendevin.core.config import config
 from opendevin.core.exceptions import LLMOutputError
@@ -98,7 +97,7 @@
 """
 
 
-def get_summarize_monologue_prompt(thoughts: List[dict]):
+def get_summarize_monologue_prompt(thoughts: list[dict]):
     """
     Gets the prompt for summarizing the monologue
 
@@ -112,16 +111,16 @@ def get_summarize_monologue_prompt(thoughts: List[dict]):
 
 def get_request_action_prompt(
     task: str,
-    thoughts: List[dict],
-    background_commands_obs: List[CmdOutputObservation] = [],
+    thoughts: list[dict],
+    background_commands_obs: list[CmdOutputObservation] = [],
 ):
     """
     Gets the action prompt formatted with appropriate values.
 
     Parameters:
     - task (str): The current task the agent is trying to accomplish
-    - thoughts (List[dict]): The agent's current thoughts
-    - background_commands_obs (List[CmdOutputObservation]): List of all observed background commands running
+    - thoughts (list[dict]): The agent's current thoughts
+    - background_commands_obs (list[CmdOutputObservation]): list of all observed background commands running
 
     Returns:
     - str: Formatted prompt string with hint, task, monologue, and background included
@@ -203,15 +202,15 @@ def rank(match):
     return action_from_dict(action_dict)
 
 
-def parse_summary_response(response: str) -> List[dict]:
+def parse_summary_response(response: str) -> list[dict]:
     """
     Parses a summary of the monologue
 
     Parameters:
     - response (str): The response string to be parsed
 
     Returns:
-    - List[dict]: The list of summaries output by the model
+    - list[dict]: The list of summaries output by the model
     """
     parsed = json.loads(response)
     return parsed['new_monologue']

agenthub/planner_agent/agent.py

@@ -1,5 +1,3 @@
-from typing import List
-
 from opendevin.controller.agent import Agent
 from opendevin.controller.state.state import State
 from opendevin.events.action import Action, AgentFinishAction
@@ -46,5 +44,5 @@ def step(self, state: State) -> Action:
         action = parse_response(action_resp)
         return action
 
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         return []

agenthub/planner_agent/prompt.py

@@ -1,5 +1,4 @@
 import json
-from typing import List, Tuple
 
 from opendevin.controller.state.plan import Plan
 from opendevin.core.logger import opendevin_logger as logger
@@ -124,14 +123,14 @@ def get_hint(latest_action_id: str) -> str:
     return hints.get(latest_action_id, '')
 
 
-def get_prompt(plan: Plan, history: List[Tuple[Action, Observation]]) -> str:
+def get_prompt(plan: Plan, history: list[tuple[Action, Observation]]) -> str:
     """
     Gets the prompt for the planner agent.
     Formatted with the most recent action-observation pairs, current task, and hint based on last action
 
     Parameters:
     - plan (Plan): The original plan outlined by the user with LLM defined tasks
-    - history (List[Tuple[Action, Observation]]): List of corresponding action-observation pairs
+    - history (list[tuple[Action, Observation]]): list of corresponding action-observation pairs
 
     Returns:
     - str: The formatted string prompt with historical values

docs/modules/usage/agents.md

@@ -8,12 +8,13 @@ sidebar_position: 3
 
 ### Description
 
-This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.13463), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both *simplicity* and *performance* (see paper for more details).
+This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.13463), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a unified **code** action space for both _simplicity_ and _performance_ (see paper for more details).
 
 The conceptual idea is illustrated below. At each turn, the agent can:
 
 1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
 2. **CodeAct**: Choose to perform the task by executing code
+
 - Execute any valid Linux `bash` command
 - Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
 
@@ -22,15 +23,15 @@ The conceptual idea is illustrated below. At each turn, the agent can:
 ### 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)*
-
+_Example of CodeActAgent with `gpt-4-turbo-2024-04-09` performing a data science task (linear regression)_
 
 ### Actions
 
@@ -50,18 +51,17 @@ https://github.com/OpenDevin/OpenDevin/assets/38853559/f592a192-e86c-4f48-ad31-d
 
 ### Methods
 
-| Method          | Description                                                                                                                                                                                                                                             |
-| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `__init__`      | Initializes an agent with `llm` and a list of messages `List[Mapping[str, str]]`                                                                                                                                                                        |
+| Method          | Description                                                                                                                                     |
+| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
+| `__init__`      | Initializes an agent with `llm` and a list of messages `list[Mapping[str, str]]`                                                                |
 | `step`          | Performs one step using the CodeAct Agent. This includes gathering info on previous steps and prompting the model to make a command to execute. |
-| `search_memory` | Not yet implemented                                                                                                                                                                                                                                     |
+| `search_memory` | Not yet implemented                                                                                                                             |
 
 ### Work-in-progress & Next step
 
 [] Support web-browsing
 [] Complete the workflow for CodeAct agent to submit Github PRs
 
-
 ## Monologue Agent
 
 ### Description

opendevin/controller/agent.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Dict, List, Type
+from typing import TYPE_CHECKING, Type
 
 if TYPE_CHECKING:
     from opendevin.controller.state.state import State
@@ -20,8 +20,8 @@ class Agent(ABC):
     It tracks the execution status and maintains a history of interactions.
     """
 
-    _registry: Dict[str, Type['Agent']] = {}
-    sandbox_plugins: List[PluginRequirement] = []
+    _registry: dict[str, Type['Agent']] = {}
+    sandbox_plugins: list[PluginRequirement] = []
 
     def __init__(
         self,
@@ -49,7 +49,7 @@ def step(self, state: 'State') -> 'Action':
         pass
 
     @abstractmethod
-    def search_memory(self, query: str) -> List[str]:
+    def search_memory(self, query: str) -> list[str]:
         """
         Searches the agent's memory for information relevant to the given query.