Merge pull request #175 from Pythagora-io/feature/121-dot_gpt-pilot-f…

…older

create .gpt-pilot directory, save project info & chat log

pilot/const/common.py

@@ -21,6 +21,7 @@
 
 IGNORE_FOLDERS = [
     '.git',
+    '.gpt-pilot',
     '.idea',
     '.vscode',
     '__pycache__',

pilot/helpers/Project.py

@@ -19,11 +19,12 @@
 from database.models.file_snapshot import FileSnapshot
 from database.models.files import File
 from logger.logger import logger
+from utils.dot_gpt_pilot import DotGptPilot
 
 
 class Project:
     def __init__(self, args, name=None, description=None, user_stories=None, user_tasks=None, architecture=None,
-                 development_plan=None, current_step=None, ipc_client_instance=None):
+                 development_plan=None, current_step=None, ipc_client_instance=None, enable_dot_pilot_gpt=True):
         """
         Initialize a project.
 
@@ -69,6 +70,11 @@ def __init__(self, args, name=None, description=None, user_stories=None, user_ta
             self.architecture = architecture
         # if development_plan is not None:
         #     self.development_plan = development_plan
+        self.dot_pilot_gpt = DotGptPilot(log_chat_completions=enable_dot_pilot_gpt)
+
+    def set_root_path(self, root_path: str):
+        self.root_path = root_path
+        self.dot_pilot_gpt.with_root_path(root_path)
 
     def start(self):
         """
@@ -128,6 +134,7 @@ def start(self):
                         break
         # TODO END
 
+        self.dot_pilot_gpt.write_project(self)
         print(json.dumps({
             "project_stage": "coding"
         }), type='info')

pilot/helpers/agents/Developer.py

@@ -41,12 +41,13 @@ def start_coding(self):
             self.implement_task(i, dev_task)
 
         # DEVELOPMENT END
-
+        self.project.dot_pilot_gpt.chat_log_folder(None)
         logger.info('The app is DONE!!! Yay...you can use it now.')
         print(green_bold("The app is DONE!!! Yay...you can use it now.\n"))
 
     def implement_task(self, i, development_task=None):
         print(green_bold(f'Implementing task #{i + 1}: ') + green(f' {development_task["description"]}\n'))
+        self.project.dot_pilot_gpt.chat_log_folder(i + 1)
 
         convo_dev_task = AgentConvo(self)
         convo_dev_task.send_message('development/task/breakdown.prompt', {

pilot/helpers/agents/ProductOwner.py

@@ -27,7 +27,7 @@ def get_project_description(self):
             step = get_progress_steps(self.project.args['app_id'], PROJECT_DESCRIPTION_STEP)
             if step and not should_execute_step(self.project.args['step'], PROJECT_DESCRIPTION_STEP):
                 step_already_finished(self.project.args, step)
-                self.project.root_path = setup_workspace(self.project.args)
+                self.project.set_root_path(setup_workspace(self.project.args))
                 self.project.project_description = step['summary']
                 self.project.project_description_messages = step['messages']
                 return
@@ -39,7 +39,7 @@ def get_project_description(self):
         if 'name' not in self.project.args:
             self.project.args['name'] = clean_filename(ask_user(self.project, 'What is the project name?'))
 
-        self.project.root_path = setup_workspace(self.project.args)
+        self.project.set_root_path(setup_workspace(self.project.args))
 
         self.project.app = save_app(self.project)
 

pilot/helpers/agents/test_CodeMonkey.py

@@ -30,8 +30,8 @@ def setup_method(self):
             current_step='coding',
         )
 
-        self.project.root_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
-                                                              '../../../workspace/TestDeveloper'))
+        self.project.set_root_path(os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                                              '../../../workspace/TestDeveloper')))
         self.project.technologies = []
         last_step = DevelopmentSteps()
         last_step.id = 1

pilot/helpers/agents/test_Developer.py

@@ -31,8 +31,8 @@ def setup_method(self):
             user_stories=[]
         )
 
-        self.project.root_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
-                                                              '../../../workspace/TestDeveloper'))
+        self.project.set_root_path(os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                                              '../../../workspace/TestDeveloper')))
         self.project.technologies = []
         self.project.current_step = ENVIRONMENT_SETUP_STEP
         self.developer = Developer(self.project)

pilot/helpers/agents/test_TechLead.py

@@ -27,8 +27,8 @@ def setup_method(self):
             user_stories=[]
         )
 
-        self.project.root_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
-                                                              '../../../workspace/TestTechLead'))
+        self.project.set_root_path(os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                                              '../../../workspace/TestTechLead')))
         self.project.technologies = []
         self.project.project_description = '''
 The project entails creating a web-based chat application, tentatively named "chat_app." 

pilot/helpers/test_Project.py

@@ -1,8 +1,12 @@
+import os
+import json
 import pytest
-from unittest.mock import patch
+from unittest.mock import patch, MagicMock
 from helpers.Project import Project
 from database.models.files import File
 
+test_root = os.path.join(os.path.dirname(__file__), '../../workspace/gpt-pilot-test').replace('\\', '/')
+
 
 def create_project():
     project = Project({
@@ -14,17 +18,17 @@ def create_project():
         architecture=[],
         user_stories=[]
     )
-    project.root_path = "/temp/gpt-pilot-test"
+    project.set_root_path(test_root)
     project.app = 'test'
     return project
 
 
 @pytest.mark.parametrize('test_data', [
-    {'name': 'package.json', 'path': 'package.json', 'saved_to': '/temp/gpt-pilot-test/package.json'},
-    {'name': 'package.json', 'path': '', 'saved_to': '/temp/gpt-pilot-test/package.json'},
-    # {'name': 'Dockerfile', 'path': None, 'saved_to': '/temp/gpt-pilot-test/Dockerfile'},
-    {'name': None, 'path': 'public/index.html', 'saved_to': '/temp/gpt-pilot-test/public/index.html'},
-    {'name': '', 'path': 'public/index.html', 'saved_to': '/temp/gpt-pilot-test/public/index.html'},
+    {'name': 'package.json', 'path': 'package.json', 'saved_to': f'{test_root}/package.json'},
+    {'name': 'package.json', 'path': '', 'saved_to': f'{test_root}/package.json'},
+    # {'name': 'Dockerfile', 'path': None, 'saved_to': f'{test_root}/Dockerfile'},
+    {'name': None, 'path': 'public/index.html', 'saved_to': f'{test_root}/public/index.html'},
+    {'name': '', 'path': 'public/index.html', 'saved_to': f'{test_root}/public/index.html'},
 
     # TODO: Treatment of paths outside of the project workspace - https://github.com/Pythagora-io/gpt-pilot/issues/129
     # {'name': '/etc/hosts', 'path': None, 'saved_to': '/etc/hosts'},
@@ -65,12 +69,12 @@ def test_save_file(mock_file_insert, mock_update_file, test_data):
 
 
 @pytest.mark.parametrize('file_path, file_name, expected', [
-    ('file.txt', 'file.txt', '/temp/gpt-pilot-test/file.txt'),
-    ('', 'file.txt', '/temp/gpt-pilot-test/file.txt'),
-    ('path/', 'file.txt', '/temp/gpt-pilot-test/path/file.txt'),
-    ('path/to/', 'file.txt', '/temp/gpt-pilot-test/path/to/file.txt'),
-    ('path/to/file.txt', 'file.txt', '/temp/gpt-pilot-test/path/to/file.txt'),
-    ('./path/to/file.txt', 'file.txt', '/temp/gpt-pilot-test/./path/to/file.txt'),  # ideally result would not have `./`
+    ('file.txt', 'file.txt', f'{test_root}/file.txt'),
+    ('', 'file.txt', f'{test_root}/file.txt'),
+    ('path/', 'file.txt', f'{test_root}/path/file.txt'),
+    ('path/to/', 'file.txt', f'{test_root}/path/to/file.txt'),
+    ('path/to/file.txt', 'file.txt', f'{test_root}/path/to/file.txt'),
+    ('./path/to/file.txt', 'file.txt', f'{test_root}/./path/to/file.txt'),  # ideally result would not have `./`
 ])
 def test_get_full_path(file_path, file_name, expected):
     # Given
@@ -100,7 +104,6 @@ def test_get_full_path_absolute(file_path, file_name, expected):
     # Then
     assert absolute_path == expected
 
-
 # This is known to fail and should be avoided
 # def test_get_full_file_path_error():
 #     # Given
@@ -111,4 +114,59 @@ def test_get_full_path_absolute(file_path, file_name, expected):
 #     full_path = project.get_full_file_path(file_path, file_name)
 #
 #     # Then
-#     assert full_path == '/temp/gpt-pilot-test/path/to/file/'
+#     assert full_path == f'{test_root}/path/to/file/'
+
+
+class TestProjectFileLists:
+    def setup_method(self):
+        # Given a project
+        project = create_project()
+        self.project = project
+        project.set_root_path(os.path.join(os.path.dirname(__file__), '../../workspace/directory_tree'))
+        project.project_description = 'Test Project'
+        project.development_plan = [{
+            'description': 'Test User Story',
+            'programmatic_goal': 'Test Programmatic Goal',
+            'user_review_goal': 'Test User Review Goal',
+        }]
+
+        # with directories including common.IGNORE_FOLDERS
+        src = os.path.join(project.root_path, 'src')
+        os.makedirs(src, exist_ok=True)
+        for dir in ['.git', '.idea', '.vscode', '__pycache__', 'node_modules', 'venv', 'dist', 'build']:
+            os.makedirs(os.path.join(project.root_path, dir), exist_ok=True)
+
+        # ...and files
+        with open(os.path.join(project.root_path, 'package.json'), 'w') as file:
+            json.dump({'name': 'test app'}, file, indent=2)
+        with open(os.path.join(src, 'main.js'), 'w') as file:
+            file.write('console.log("Hello World!");')
+
+        # and a non-empty .gpt-pilot directory
+        project.dot_pilot_gpt.write_project(project)
+
+    def test_get_directory_tree(self):
+        # When
+        tree = self.project.get_directory_tree()
+
+        # Then we should not be including the .gpt-pilot directory or other ignored directories
+        assert tree == '''
+|-- /
+|   |-- package.json
+|   |-- src/
+|   |   |-- main.js
+'''.lstrip()
+
+    @patch('helpers.Project.DevelopmentSteps.get_or_create', return_value=('test', True))
+    @patch('helpers.Project.File.get_or_create', return_value=('test', True))
+    @patch('helpers.Project.FileSnapshot.get_or_create', return_value=(MagicMock(), True))
+    def test_save_files_snapshot(self, mock_snap, mock_file, mock_step):
+        # Given a snapshot of the files in the project
+
+        # When we save the file snapshot
+        self.project.save_files_snapshot('test')
+
+        # Then the files should be saved to the project, but nothing from `.gpt-pilot/`
+        assert mock_file.call_count == 2
+        assert mock_file.call_args_list[0][1]['name'] == 'package.json'
+        assert mock_file.call_args_list[1][1]['name'] == 'main.js'

pilot/test/ux_tests/run_command_until_success.py

@@ -20,8 +20,8 @@ def run_command_until_success():
         user_stories=[]
     )
 
-    project.root_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
-                                                     '../../../workspace/TestDeveloper'))
+    project.set_root_path(os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                                     '../../../workspace/TestDeveloper')))
     project.technologies = []
     project.current_step = ENVIRONMENT_SETUP_STEP
     project.app = save_app(project)

pilot/utils/dot_gpt_pilot.py

@@ -0,0 +1,91 @@
+import json
+import os
+import yaml
+from datetime import datetime
+from dotenv import load_dotenv
+
+load_dotenv()
+
+USE_GPTPILOT_FOLDER = os.getenv('USE_GPTPILOT_FOLDER') == 'true'
+
+
+# TODO: Parse files from the `.gpt-pilot` directory to resume a project - `user_stories` may have changed - include checksums for sections which may need to be reprocessed.
+# TODO: Save a summary at the end of each task/sprint.
+class DotGptPilot:
+    """
+    Manages the `.gpt-pilot` directory.
+    """
+    def __init__(self, log_chat_completions: bool = True):
+        if not USE_GPTPILOT_FOLDER:
+            return
+        self.log_chat_completions = log_chat_completions
+        self.dot_gpt_pilot_path = self.with_root_path('~', create=False)
+        self.chat_log_path = self.chat_log_folder(None)
+
+    def with_root_path(self, root_path: str, create=True):
+        if not USE_GPTPILOT_FOLDER:
+            return
+        dot_gpt_pilot_path = os.path.join(root_path, '.gpt-pilot')
+        self.dot_gpt_pilot_path = dot_gpt_pilot_path
+
+        # Create the `.gpt-pilot` directory if required.
+        if create and self.log_chat_completions:  # (... or ...):
+            self.chat_log_folder(None)
+
+        return dot_gpt_pilot_path
+
+    def chat_log_folder(self, task):
+        if not USE_GPTPILOT_FOLDER:
+            return
+        chat_log_path = os.path.join(self.dot_gpt_pilot_path, 'chat_log')
+        if task is not None:
+            chat_log_path = os.path.join(chat_log_path, 'task_' + str(task))
+
+        os.makedirs(chat_log_path, exist_ok=True)
+        self.chat_log_path = chat_log_path
+        return chat_log_path
+
+    def log_chat_completion(self, endpoint: str, model: str, req_type: str, messages: list[dict], response: str):
+        if not USE_GPTPILOT_FOLDER:
+            return
+        if self.log_chat_completions:
+            time = datetime.now().strftime('%Y-%m-%d_%H_%M_%S')
+            with open(os.path.join(self.chat_log_path, f'{time}-{req_type}.yaml'), 'w') as file:
+                data = {
+                    'endpoint': endpoint,
+                    'model': model,
+                    'messages': messages,
+                    'response': response,
+                }
+
+                yaml.safe_dump(data, file, width=120, indent=2, default_flow_style=False, sort_keys=False)
+
+    def log_chat_completion_json(self, endpoint: str, model: str, req_type: str, functions: dict, json_response: str):
+        if not USE_GPTPILOT_FOLDER:
+            return
+        if self.log_chat_completions:
+            time = datetime.now().strftime('%Y-%m-%d_%H_%M_%S')
+
+            with open(os.path.join(self.chat_log_path, f'{time}-{req_type}.json'), 'w') as file:
+                data = {
+                    'endpoint': endpoint,
+                    'model': model,
+                    'functions': functions,
+                    'response': json.loads(json_response),
+                }
+
+                json.dump(data, file, indent=2)
+
+    def write_project(self, project):
+        if not USE_GPTPILOT_FOLDER:
+            return
+        data = {
+            'name': project.args['name'],
+            'description': project.project_description,
+            'user_stories': project.user_stories,
+            'architecture': project.architecture,
+            'development_plan': project.development_plan,
+        }
+
+        with open(os.path.join(self.dot_gpt_pilot_path, 'project.yaml'), 'w') as file:
+            yaml.safe_dump(data, file, width=120, indent=2, default_flow_style=False, sort_keys=False)

pilot/utils/llm_connection.py

@@ -17,7 +17,6 @@
 from utils.function_calling import add_function_calls_to_request, FunctionCallSet, FunctionType
 from utils.questionary import styled_text
 
-
 def get_tokens_in_messages(messages: List[str]) -> int:
     tokenizer = tiktoken.get_encoding("cl100k_base")  # GPT-4 tokenizer
     tokenized_messages = [tokenizer.encode(message['content']) for message in messages]
@@ -335,6 +334,7 @@ def return_result(result_data, lines_printed):
     )
 
     if response.status_code != 200:
+        project.dot_pilot_gpt.log_chat_completion(endpoint, model, req_type, data['messages'], response.text)
         logger.info(f'problem with request (status {response.status_code}): {response.text}')
         raise Exception(f"API responded with status code: {response.status_code}. Response text: {response.text}")
 
@@ -408,10 +408,13 @@ def return_result(result_data, lines_printed):
     #     function_calls['arguments'] = load_data_to_json(function_calls['arguments'])
     #     return return_result({'function_calls': function_calls}, lines_printed)
     logger.info('<<<<<<<<<< LLM Response <<<<<<<<<<\n%s\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<', gpt_response)
+    project.dot_pilot_gpt.log_chat_completion(endpoint, model, req_type, data['messages'], gpt_response)
 
     if expecting_json:
         gpt_response = clean_json_response(gpt_response)
         assert_json_schema(gpt_response, expecting_json)
+        # Note, we log JSON separately from the YAML log above incase the JSON is invalid and an error is raised
+        project.dot_pilot_gpt.log_chat_completion_json(endpoint, model, req_type, expecting_json, gpt_response)
 
     new_code = postprocessing(gpt_response, req_type)  # TODO add type dynamically
     return return_result({'text': new_code}, lines_printed)

pilot/utils/test_llm_connection.py

@@ -19,7 +19,7 @@
 
 load_dotenv()
 
-project = Project({'app_id': 'test-app'}, current_step='test')
+project = Project({'app_id': 'test-app'}, current_step='test', enable_dot_pilot_gpt=False)
 
 
 def test_clean_json_response_True_False():

requirements.txt

@@ -13,6 +13,7 @@ psycopg2-binary==2.9.6
 python-dotenv==1.0.0
 python-editor==1.0.4
 pytest==7.4.2
+pyyaml==6.0.1
 questionary==1.10.0
 readchar==4.0.5
 regex==2023.6.3