scrape text regression test (#3387)

Co-authored-by: James Collins <collijk@uw.edu>

autogpt/main.py

@@ -12,7 +12,7 @@ from autogpt.configurator import create_config
 from autogpt.logs import logger
 from autogpt.memory import get_memory
 from autogpt.plugins import scan_plugins
-from autogpt.prompts.prompt import construct_main_ai_config
+from autogpt.prompts.prompt import DEFAULT_TRIGGERING_PROMPT, construct_main_ai_config
 from autogpt.utils import get_current_git_branch, get_latest_bulletin
 from autogpt.workspace import Workspace
 from scripts.install_plugin_deps import install_plugin_dependencies
@@ -124,11 +124,7 @@ def run_auto_gpt(
     # Initialize variables
     full_message_history = []
     next_action_count = 0
-    # Make a constant:
-    triggering_prompt = (
-        "Determine which next command to use, and respond using the"
-        " format specified above:"
-    )
+
     # Initialize memory and make sure it is empty.
     # this is particularly important for indexing and referencing pinecone memory
     memory = get_memory(cfg, init=True)
@@ -148,7 +144,7 @@ def run_auto_gpt(
         command_registry=command_registry,
         config=ai_config,
         system_prompt=system_prompt,
-        triggering_prompt=triggering_prompt,
+        triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
         workspace_directory=workspace_directory,
     )
     agent.start_interaction_loop()

autogpt/prompts/prompt.py

@@ -10,6 +10,10 @@ from autogpt.utils import clean_input
 
 CFG = Config()
 
+DEFAULT_TRIGGERING_PROMPT = (
+    "Determine which next command to use, and respond using the format specified above:"
+)
+
 
 def build_default_prompt_generator() -> PromptGenerator:
     """
@@ -71,9 +75,6 @@ def build_default_prompt_generator() -> PromptGenerator:
         "Every command has a cost, so be smart and efficient. Aim to complete tasks in"
         " the least number of steps."
     )
-    prompt_generator.add_performance_evaluation(
-        "If you cannot think of a valid command to perform start or message an agent to determine the next command."
-    )
     prompt_generator.add_performance_evaluation("Write all code to a file.")
     return prompt_generator
 

tests/integration/agent_factory.py

@@ -0,0 +1,87 @@
+import os
+
+from autogpt.agent import Agent
+from autogpt.app import CFG
+from autogpt.commands.command import CommandRegistry
+from autogpt.config import AIConfig
+from autogpt.memory import get_memory
+from autogpt.prompts.prompt import DEFAULT_TRIGGERING_PROMPT
+
+
+def create_browser_agent(workspace):
+    command_registry = CommandRegistry()
+    command_registry.import_commands("autogpt.commands.file_operations")
+    command_registry.import_commands("autogpt.commands.web_selenium")
+    command_registry.import_commands("autogpt.app")
+
+    ai_config = AIConfig(
+        ai_name="browse_website-GPT",
+        ai_role="an AI designed to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer the question 'What is the price of the book?' and write the price to a file named \"browse_website.txt\", and use the task_complete command to complete the task.",
+        ai_goals=[
+            "Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer the question 'What is the price of the book?'",
+            'Write the price of the book to a file named "browse_website.txt".',
+            "Use the task_complete command to complete the task.",
+            "Do not use any other commands.",
+        ],
+    )
+    ai_config.command_registry = command_registry
+    CFG.set_continuous_mode(True)
+    CFG.set_memory_backend("no_memory")
+    CFG.set_temperature(0)
+
+    memory = get_memory(CFG, init=True)
+    system_prompt = ai_config.construct_full_prompt()
+
+    agent = Agent(
+        ai_name="",
+        memory=memory,
+        full_message_history=[],
+        command_registry=command_registry,
+        config=ai_config,
+        next_action_count=0,
+        system_prompt=system_prompt,
+        triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
+        workspace_directory=workspace.root,
+    )
+
+    return agent
+
+
+def create_writer_agent(workspace):
+    command_registry = CommandRegistry()
+    command_registry.import_commands("autogpt.commands.file_operations")
+    command_registry.import_commands("autogpt.app")
+
+    ai_config = AIConfig(
+        ai_name="write_to_file-GPT",
+        ai_role="an AI designed to use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\" and then use the task_complete command to complete the task.",
+        ai_goals=[
+            "Use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\".",
+            "Use the task_complete command to complete the task.",
+            "Do not use any other commands.",
+        ],
+    )
+    ai_config.command_registry = command_registry
+    CFG.set_continuous_mode(True)
+    CFG.set_memory_backend("no_memory")
+    CFG.set_temperature(0)
+    memory = get_memory(CFG, init=True)
+    triggering_prompt = (
+        "Determine which next command to use, and respond using the"
+        " format specified above:"
+    )
+    system_prompt = ai_config.construct_full_prompt()
+
+    agent = Agent(
+        ai_name="",
+        memory=memory,
+        full_message_history=[],
+        command_registry=command_registry,
+        config=ai_config,
+        next_action_count=0,
+        system_prompt=system_prompt,
+        triggering_prompt=triggering_prompt,
+        workspace_directory=workspace.root,
+    )
+
+    return agent

tests/integration/agent_utils.py

@@ -0,0 +1,10 @@
+import concurrent
+
+
+def run_interaction_loop(agent, timeout):
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        future = executor.submit(agent.start_interaction_loop)
+        try:
+            result = future.result(timeout=timeout)
+        except concurrent.futures.TimeoutError:
+            assert False, f"The process took longer than {timeout} seconds to complete."

tests/integration/goal_oriented/test_browse_website.py

@@ -0,0 +1,27 @@
+import os
+
+import pytest
+
+from autogpt.commands.file_operations import read_file
+from autogpt.config import Config
+from tests.integration.agent_factory import create_browser_agent
+from tests.integration.agent_utils import run_interaction_loop
+from tests.utils import get_workspace_file_path, requires_api_key
+
+CFG = Config()
+
+
+@requires_api_key("OPENAI_API_KEY")
+@pytest.mark.vcr
+def test_browse_website(workspace) -> None:
+    CFG.workspace_path = workspace.root
+    CFG.file_logger_path = os.path.join(workspace.root, "file_logger.txt")
+
+    file_name = get_workspace_file_path(workspace, "browse_website.txt")
+    agent = create_browser_agent(workspace)
+    try:
+        run_interaction_loop(agent, 40)
+    # catch system exit exceptions
+    except SystemExit:  # the agent returns an exception when it shuts down
+        content = read_file(file_name)
+        assert "£25.89" in content, f"Expected £25.89, got {content}"

tests/integration/goal_oriented/test_write_file.py

@@ -1,14 +1,11 @@
-import concurrent
 import os
-import unittest
 
 import pytest
 
-from autogpt.agent import Agent
-from autogpt.commands.command import CommandRegistry
-from autogpt.commands.file_operations import delete_file, read_file
-from autogpt.config import AIConfig, Config
-from autogpt.memory import get_memory
+from autogpt.commands.file_operations import read_file
+from autogpt.config import Config
+from tests.integration.agent_factory import create_writer_agent
+from tests.integration.agent_utils import run_interaction_loop
 from tests.utils import requires_api_key
 
 CFG = Config()
@@ -23,59 +20,8 @@ def test_write_file(workspace) -> None:
     file_name = str(workspace.get_path("hello_world.txt"))
     agent = create_writer_agent(workspace)
     try:
-        with concurrent.futures.ThreadPoolExecutor() as executor:
-            future = executor.submit(agent.start_interaction_loop)
-            try:
-                result = future.result(timeout=45)
-            except concurrent.futures.TimeoutError:
-                assert False, "The process took longer than 45 seconds to complete."
+        run_interaction_loop(agent, 40)
     # catch system exit exceptions
     except SystemExit:  # the agent returns an exception when it shuts down
         content = read_file(file_name)
         assert content == "Hello World", f"Expected 'Hello World', got {content}"
-
-
-def create_writer_agent(workspace):
-    command_registry = CommandRegistry()
-    command_registry.import_commands("autogpt.commands.file_operations")
-    command_registry.import_commands("autogpt.app")
-
-    ai_config = AIConfig(
-        ai_name="write_to_file-GPT",
-        ai_role="an AI designed to use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\" and then use the task_complete command to complete the task.",
-        ai_goals=[
-            "Use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\".",
-            "Use the task_complete command to complete the task.",
-            "Do not use any other commands.",
-        ],
-    )
-    ai_config.command_registry = command_registry
-    CFG.set_continuous_mode(True)
-    CFG.set_memory_backend("no_memory")
-    CFG.set_temperature(0)
-    memory = get_memory(CFG, init=True)
-    triggering_prompt = (
-        "Determine which next command to use, and respond using the"
-        " format specified above:"
-    )
-    system_prompt = ai_config.construct_full_prompt()
-
-    agent = Agent(
-        ai_name="",
-        memory=memory,
-        full_message_history=[],
-        command_registry=command_registry,
-        config=ai_config,
-        next_action_count=0,
-        system_prompt=system_prompt,
-        triggering_prompt=triggering_prompt,
-        workspace_directory=workspace.root,
-    )
-
-    os.environ["TIKTOKEN_CACHE_DIR"] = ""
-
-    return agent
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/utils.py

@@ -40,3 +40,7 @@ def skip_in_ci(test_function):
         os.environ.get("CI") == "true",
         reason="This test doesn't work on GitHub Actions.",
     )(test_function)
+
+
+def get_workspace_file_path(workspace, file_name):
+    return str(workspace.get_path(file_name))