mirror of
https://github.com/trycua/computer.git
synced 2026-01-06 05:20:02 -06:00
Updated example, cua-core dep, and added --prompt
This commit is contained in:
Dillon DuPont
@@ -8,7 +8,7 @@ import signal
|
||||
from computer import Computer, VMProviderType
|
||||
|
||||
# Import the unified agent class and types
|
||||
from agent import ComputerAgent, LLMProvider, LLM, AgentLoop
|
||||
from agent import ComputerAgent
|
||||
|
||||
# Import utility functions
|
||||
from utils import load_dotenv_files, handle_sigint
|
||||
@@ -19,8 +19,8 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def run_agent_example():
|
||||
"""Run example of using the ComputerAgent with OpenAI and Omni provider."""
|
||||
print("\n=== Example: ComputerAgent with OpenAI and Omni provider ===")
|
||||
"""Run example of using the ComputerAgent with different models."""
|
||||
print("\n=== Example: ComputerAgent with different models ===")
|
||||
|
||||
try:
|
||||
# Create a local macOS computer
|
||||
@@ -37,28 +37,37 @@ async def run_agent_example():
|
||||
# provider_type=VMProviderType.CLOUD,
|
||||
# )
|
||||
|
||||
# Create Computer instance with async context manager
|
||||
# Create ComputerAgent with new API
|
||||
agent = ComputerAgent(
|
||||
computer=computer,
|
||||
loop=AgentLoop.OPENAI,
|
||||
# loop=AgentLoop.ANTHROPIC,
|
||||
# loop=AgentLoop.UITARS,
|
||||
# loop=AgentLoop.OMNI,
|
||||
model=LLM(provider=LLMProvider.OPENAI), # No model name for Operator CUA
|
||||
# model=LLM(provider=LLMProvider.OPENAI, name="gpt-4o"),
|
||||
# model=LLM(provider=LLMProvider.ANTHROPIC, name="claude-3-7-sonnet-20250219"),
|
||||
# model=LLM(provider=LLMProvider.OLLAMA, name="gemma3:4b-it-q4_K_M"),
|
||||
# model=LLM(provider=LLMProvider.MLXVLM, name="mlx-community/UI-TARS-1.5-7B-4bit"),
|
||||
# model=LLM(
|
||||
# provider=LLMProvider.OAICOMPAT,
|
||||
# name="gemma-3-12b-it",
|
||||
# provider_base_url="http://localhost:1234/v1", # LM Studio local endpoint
|
||||
# ),
|
||||
save_trajectory=True,
|
||||
# Supported models:
|
||||
|
||||
# == OpenAI CUA (computer-use-preview) ==
|
||||
model="openai/computer-use-preview",
|
||||
|
||||
# == Anthropic CUA (Claude > 3.5) ==
|
||||
# model="anthropic/claude-opus-4-20250514",
|
||||
# model="anthropic/claude-sonnet-4-20250514",
|
||||
# model="anthropic/claude-3-7-sonnet-20250219",
|
||||
# model="anthropic/claude-3-5-sonnet-20240620",
|
||||
|
||||
# == UI-TARS ==
|
||||
# model="huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B",
|
||||
# model="mlx/mlx-community/UI-TARS-1.5-7B-6bit",
|
||||
# model="ollama_chat/0000/ui-tars-1.5-7b",
|
||||
|
||||
# == Omniparser + Any LLM ==
|
||||
# model="omniparser+anthropic/claude-opus-4-20250514",
|
||||
# model="omniparser+ollama_chat/gemma3:12b-it-q4_K_M",
|
||||
|
||||
tools=[computer],
|
||||
only_n_most_recent_images=3,
|
||||
verbosity=logging.DEBUG,
|
||||
trajectory_dir="trajectories",
|
||||
use_prompt_caching=True,
|
||||
max_trajectory_budget=1.0,
|
||||
)
|
||||
|
||||
# Example tasks to demonstrate the agent
|
||||
tasks = [
|
||||
"Look for a repository named trycua/cua on GitHub.",
|
||||
"Check the open issues, open the most recent one and read it.",
|
||||
@@ -68,43 +77,35 @@ async def run_agent_example():
|
||||
"Focus on the Composer text area, then write and submit a task to help resolve the GitHub issue.",
|
||||
]
|
||||
|
||||
# Use message-based conversation history
|
||||
history = []
|
||||
|
||||
for i, task in enumerate(tasks):
|
||||
print(f"\nExecuting task {i}/{len(tasks)}: {task}")
|
||||
async for result in agent.run(task):
|
||||
print("Response ID: ", result.get("id"))
|
||||
|
||||
# Print detailed usage information
|
||||
usage = result.get("usage")
|
||||
if usage:
|
||||
print("\nUsage Details:")
|
||||
print(f" Input Tokens: {usage.get('input_tokens')}")
|
||||
if "input_tokens_details" in usage:
|
||||
print(f" Input Tokens Details: {usage.get('input_tokens_details')}")
|
||||
print(f" Output Tokens: {usage.get('output_tokens')}")
|
||||
if "output_tokens_details" in usage:
|
||||
print(f" Output Tokens Details: {usage.get('output_tokens_details')}")
|
||||
print(f" Total Tokens: {usage.get('total_tokens')}")
|
||||
|
||||
print("Response Text: ", result.get("text"))
|
||||
|
||||
# Print tools information
|
||||
tools = result.get("tools")
|
||||
if tools:
|
||||
print("\nTools:")
|
||||
print(tools)
|
||||
|
||||
# Print reasoning and tool call outputs
|
||||
outputs = result.get("output", [])
|
||||
for output in outputs:
|
||||
output_type = output.get("type")
|
||||
if output_type == "reasoning":
|
||||
print("\nReasoning Output:")
|
||||
print(output)
|
||||
elif output_type == "computer_call":
|
||||
print("\nTool Call Output:")
|
||||
print(output)
|
||||
|
||||
print(f"\n✅ Task {i+1}/{len(tasks)} completed: {task}")
|
||||
print(f"\nExecuting task {i+1}/{len(tasks)}: {task}")
|
||||
|
||||
# Add user message to history
|
||||
history.append({"role": "user", "content": task})
|
||||
|
||||
# Run agent with conversation history
|
||||
async for result in agent.run(history, stream=False):
|
||||
# Add agent outputs to history
|
||||
history += result.get("output", [])
|
||||
|
||||
# Print output for debugging
|
||||
for item in result.get("output", []):
|
||||
if item.get("type") == "message":
|
||||
content = item.get("content", [])
|
||||
for content_part in content:
|
||||
if content_part.get("text"):
|
||||
print(f"Agent: {content_part.get('text')}")
|
||||
elif item.get("type") == "computer_call":
|
||||
action = item.get("action", {})
|
||||
action_type = action.get("type", "")
|
||||
print(f"Computer Action: {action_type}({action})")
|
||||
elif item.get("type") == "computer_call_output":
|
||||
print("Computer Output: [Screenshot/Result]")
|
||||
|
||||
print(f"✅ Task {i+1}/{len(tasks)} completed: {task}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in run_agent_example: {e}")
|
||||
|
||||
Reference in New Issue
Block a user