Merge branch 'main' of github.com:AntonOsika/gpt-engineer

* 'main' of github.com:AntonOsika/gpt-engineer:
  Mark test as failed because it requires OpenAI API access currently
  `black`
  Create test_ai.py
  fix to_files
  execute_workspace -> gen_entrypoint; execute_entrypoint
  Ignore my-new-project/
  Added CODE_OF_CONDUCT.md to the .github directory (#147)
  make pre commit pass in the whole codebase (#149)
  Create ci.yaml
  Fix linting
  Add support for directory paths in filenames and improve code splitting - Enforce an explicit markdown code block format - Add a token to split the output to clearly detect when the code blocks start - Save all non-code output to a `README.md` file - Update RegEx to extract and strip text more reliably and clean up the output - Update the identify prompts appropriately
  Enhance philosophy to include supporting documents - Create instructions for running/compiling the project - Create any package manager files
  Generate instructions for all platforms - Update prompt to create instructions for all 3 major OS platforms - Fix small typo
  Add support for directory creation and binary files - Use the `Path` module instead of `os` - Add ability to create any amount of missing directories for a given file - Add ability to save both text and binary files to save images (or other file types) later
  Add cleanup & move `projects` to their own directory - Add optional argument to clean and delete the working directories of the project before running the prompt - Add `.gitignore` entry to ignore all possible projects - Update readme

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,131 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity or expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting using an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+anton.osika@gmail.com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of reporters of incidents.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

.github/workflows/ci.yaml

@@ -0,0 +1,33 @@
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+
+      - name: Install package
+        run: pip install -e .
+
+      - name: Install test runner
+        run: pip install pytest pytest-cov
+
+      - name: Run unit tests
+        run: pytest --cov=gpt_engineer

.gitignore

@@ -38,3 +38,7 @@ archive
 # any log file
 *log.txt
 todo
+
+# Ignore GPT Engineer files
+projects
+my-new-project/

README.md

@@ -22,12 +22,13 @@ GPT Engineer is made to be easy to adapt, extend, and make your agent learn how
 - `export OPENAI_API_KEY=[your api key]` with a key that has GPT4 access
 
 **Run**:
-- Create a new empty folder with a `main_prompt` file (or copy the example folder `cp -r example/ my-new-project`)
+- Create a new empty folder with a `main_prompt` file in the `projects` folder (or copy the example folder `cp -r projects/example/ projects/my-new-project`)
 - Fill in the `main_prompt` in your new folder
 - Run `python -m gpt_engineer.main my-new-project`
+  - Optionally pass in `true` to delete the working files before running
 
 **Results**:
-- Check the generated files in my-new-project/workspace
+- Check the generated files in projects/my-new-project/workspace
 
 ### Limitations
 Implementing additional chain of thought prompting, e.g. [Reflexion](https://github.com/noahshinn024/reflexion), should be able to make it more reliable and not miss requested functionality in the main prompt.

gpt_engineer/ai.py

@@ -8,10 +8,12 @@ class AI:
         try:
             openai.Model.retrieve("gpt-4")
         except openai.error.InvalidRequestError:
-            print("Model gpt-4 not available for provided api key reverting "
+            print(
-                  "to gpt-3.5.turbo. Sign up for the gpt-4 wait list here: "
+                "Model gpt-4 not available for provided api key reverting "
-                  "https://openai.com/waitlist/gpt-4-api")
+                "to gpt-3.5.turbo. Sign up for the gpt-4 wait list here: "
-            self.kwargs['model'] = "gpt-3.5-turbo"
+                "https://openai.com/waitlist/gpt-4-api"
+            )
+            self.kwargs["model"] = "gpt-3.5-turbo"
 
     def start(self, system, user):
         messages = [
@@ -26,10 +28,10 @@ class AI:
 
     def fuser(self, msg):
         return {"role": "user", "content": msg}
+
     def fassistant(self, msg):
         return {"role": "assistant", "content": msg}
 
-
     def next(self, messages: list[dict[str, str]], prompt=None):
         if prompt:
             messages = messages + [{"role": "user", "content": prompt}]

gpt_engineer/chat_to_files.py

@@ -1,27 +1,42 @@
 import re
-from typing import List, Tuple
-from gpt_engineer.db import DB
 
 
-def parse_chat(chat) -> List[Tuple[str, str]]:
+def parse_chat(chat):  # -> List[Tuple[str, str]]:
-    # Get all ``` blocks
+    # Split the chat into sections by the "*CODEBLOCKSBELOW*" token
-    regex = r"```(.*?)```"
+    split_chat = chat.split("*CODEBLOCKSBELOW*")
 
-    matches = re.finditer(regex, chat, re.DOTALL)
+    # Check if the "*CODEBLOCKSBELOW*" token was found
+    is_token_found = len(split_chat) > 1
+
+    # If the "*CODEBLOCKSBELOW*" token is found, use the first part as README
+    # and second part as code blocks. Otherwise, treat README as optional and
+    # proceed with empty README and the entire chat as code blocks
+    readme = split_chat[0].strip() if is_token_found else "No readme"
+    code_blocks = split_chat[1] if is_token_found else chat
+
+    # Get all ``` blocks and preceding filenames
+    regex = r"(\S+?)\n```\S+\n(.+?)```"
+    matches = re.finditer(regex, code_blocks, re.DOTALL)
 
     files = []
     for match in matches:
-        path = match.group(1).split("\n")[0]
+        # Strip the filename of any non-allowed characters and convert / to \
+        path = re.sub(r'[<>"|?*]', "", match.group(1))
+
         # Get the code
-        code = match.group(1).split("\n")[1:]
+        code = match.group(2)
-        code = "\n".join(code)
+
         # Add the file to the list
         files.append((path, code))
 
+    # Add README to the list
+    files.append(("README.txt", readme))
+
+    # Return the files
     return files
 
 
-def to_files(chat: str, workspace: DB):
+def to_files(chat, workspace):
     workspace["all_output.txt"] = chat
 
     files = parse_chat(chat)

gpt_engineer/db.py

@@ -1,33 +1,51 @@
 from dataclasses import dataclass
-import os
 from pathlib import Path
 
 
+# This class represents a simple database that stores its data as files in a directory.
+# It supports both text and binary files, and can handle directory structures.
 class DB:
-    """A simple key-value store, where keys are filenames and values are file contents."""
-
     def __init__(self, path):
+        # Convert the path string to a Path object and get its absolute path.
         self.path = Path(path).absolute()
-        os.makedirs(self.path, exist_ok=True)
+
+        # Create the directory if it doesn't exist.
+        self.path.mkdir(parents=True, exist_ok=True)
 
     def __getitem__(self, key):
-        with open(self.path / key, encoding='utf-8') as f:
+        # Combine the database directory with the provided file path.
-            return f.read()
+        full_path = self.path / key
+
+        # Check if the file exists before trying to open it.
+        if full_path.is_file():
+            # Open the file in text mode and return its content.
+            with full_path.open("r") as f:
+                return f.read()
+        else:
+            # If the file doesn't exist, raise an error.
+            raise FileNotFoundError(f"No such file: '{full_path}'")
 
     def __setitem__(self, key, val):
-        Path(self.path / key).absolute().parent.mkdir(parents=True, exist_ok=True)
+        # Combine the database directory with the provided file path.
+        full_path = self.path / key
 
-        with open(self.path / key, 'w', encoding='utf-8') as f:
+        # Create the directory tree if it doesn't exist.
-            f.write(val)
+        full_path.parent.mkdir(parents=True, exist_ok=True)
 
-    def __contains__(self, key):
+        # Write the data to the file. If val is a string, it's written as text.
-        return (self.path / key).exists()
+        # If val is bytes, it's written as binary data.
+        if isinstance(val, str):
+            full_path.write_text(val)
+        elif isinstance(val, bytes):
+            full_path.write_bytes(val)
+        else:
+            # If val is neither a string nor bytes, raise an error.
+            raise TypeError("val must be either a str or bytes")
 
 
+# dataclass for all dbs:
 @dataclass
 class DBs:
-    """A dataclass for all dbs"""
-
     memory: DB
     logs: DB
     identity: DB

gpt_engineer/main.py

@@ -1,32 +1,41 @@
-import os
 import json
+import os
 import pathlib
+import shutil
+
 import typer
 
-from gpt_engineer.chat_to_files import to_files
 from gpt_engineer.ai import AI
-from gpt_engineer.steps import STEPS
 from gpt_engineer.db import DB, DBs
-
+from gpt_engineer.steps import STEPS
 
 app = typer.Typer()
 
 
 @app.command()
 def chat(
-    project_path: str = typer.Argument(str(pathlib.Path(os.path.curdir) / "example"), help="path"),
+    project_path: str = typer.Argument("example", help="path"),
+    delete_existing: str = typer.Argument(None, help="delete existing files"),
     run_prefix: str = typer.Option(
         "",
-        help="run prefix, if you want to run multiple variants of the same project and later compare them",
+        help=(
+            "run prefix, if you want to run multiple variants of the same project and "
+            "later compare them",
+        ),
     ),
     model: str = "gpt-4",
     temperature: float = 0.1,
     steps_config: str = "default",
 ):
     app_dir = pathlib.Path(os.path.curdir)
-    input_path = project_path
+    input_path = pathlib.Path(app_dir / "projects" / project_path)
-    memory_path = pathlib.Path(project_path) / (run_prefix + "memory")
+    memory_path = input_path / (run_prefix + "memory")
-    workspace_path = pathlib.Path(project_path) / (run_prefix + "workspace")
+    workspace_path = input_path / (run_prefix + "workspace")
+
+    if delete_existing == "true":
+        # Delete files and subdirectories in paths
+        shutil.rmtree(memory_path, ignore_errors=True)
+        shutil.rmtree(workspace_path, ignore_errors=True)
 
     ai = AI(
         model=model,
@@ -45,5 +54,6 @@ def chat(
         messages = step(ai, dbs)
         dbs.logs[step.__name__] = json.dumps(messages)
 
+
 if __name__ == "__main__":
     app()

gpt_engineer/steps.py

@@ -2,9 +2,8 @@ import json
 import subprocess
 
 from gpt_engineer.ai import AI
-from gpt_engineer.chat_to_files import to_files
+from gpt_engineer.chat_to_files import parse_chat, to_files
 from gpt_engineer.db import DBs
-from gpt_engineer.chat_to_files import parse_chat
 
 
 def setup_sys_prompt(dbs):
@@ -54,7 +53,8 @@ def clarify(ai: AI, dbs: DBs):
 
 def gen_spec(ai: AI, dbs: DBs):
     """
-    Generate a spec from the main prompt + clarifications and save the results to the workspace
+    Generate a spec from the main prompt + clarifications and save the results to
+    the workspace
     """
     messages = [
         ai.fsystem(setup_sys_prompt(dbs)),
@@ -67,6 +67,7 @@ def gen_spec(ai: AI, dbs: DBs):
 
     return messages
 
+
 def respec(ai: AI, dbs: DBs):
     messages = dbs.logs[gen_spec.__name__]
     messages += [ai.fsystem(dbs.identity["respec"])]
@@ -75,10 +76,13 @@ def respec(ai: AI, dbs: DBs):
     messages = ai.next(
         messages,
         (
-            'Based on the conversation so far, please reiterate the specification for the program. '
+            "Based on the conversation so far, please reiterate the specification for "
-            'If there are things that can be improved, please incorporate the improvements. '
+            "the program. "
-            "If you are satisfied with the specification, just write out the specification word by word again."
+            "If there are things that can be improved, please incorporate the "
-        )
+            "improvements. "
+            "If you are satisfied with the specification, just write out the "
+            "specification word by word again."
+        ),
     )
 
     dbs.memory["specification"] = messages[-1]["content"]
@@ -116,6 +120,7 @@ def gen_clarified_code(ai: AI, dbs: DBs):
     to_files(messages[-1]["content"], dbs.workspace)
     return messages
 
+
 def gen_code(ai: AI, dbs: DBs):
     # get the messages from previous step
 
@@ -130,12 +135,6 @@ def gen_code(ai: AI, dbs: DBs):
     return messages
 
 
-def execute_workspace(ai: AI, dbs: DBs):
-    messages = gen_entrypoint(ai, dbs)
-    execute_entrypoint(ai, dbs)
-    return messages
-
-
 def execute_entrypoint(ai, dbs):
     command = dbs.workspace["run.sh"]
 
@@ -157,8 +156,10 @@ def execute_entrypoint(ai, dbs):
 def gen_entrypoint(ai, dbs):
     messages = ai.start(
         system=(
-            f"You will get information about a codebase that is currently on disk in the current folder.\n"
+            "You will get information about a codebase that is currently on disk in "
-            "From this you will answer with one code block that includes all the necessary macos terminal commands to "
+            f"the folder {dbs.workspace.path}.\n"
+            "From this you will answer with code blocks that includes all the necessary "
+            "Windows, MacOS, and Linux terminal commands to "
             "a) install dependencies "
             "b) run all necessary parts of the codebase (in parallell if necessary).\n"
             "Do not install globally. Do not use sudo.\n"
@@ -170,11 +171,16 @@ def gen_entrypoint(ai, dbs):
 
     blocks = parse_chat(messages[-1]["content"])
     for lang, _ in blocks:
-        assert lang in ["", "bash", "sh"], "Generated entrypoint command that was not bash"
+        assert lang in [
+            "",
+            "bash",
+            "sh",
+        ], "Generated entrypoint command that was not bash"
 
     dbs.workspace["run.sh"] = "\n".join(block for lang, block in blocks)
     return messages
 
+
 def use_feedback(ai: AI, dbs: DBs):
     messages = [
         ai.fsystem(setup_sys_prompt(dbs)),
@@ -182,18 +188,25 @@ def use_feedback(ai: AI, dbs: DBs):
         ai.fassistant(dbs.workspace["all_output.txt"]),
         ai.fsystem(dbs.identity["use_feedback"]),
     ]
-    messages = ai.next(messages, dbs.memory['feedback'])
+    messages = ai.next(messages, dbs.memory["feedback"])
     to_files(messages[-1]["content"], dbs.workspace)
     return messages
 
 
 # Different configs of what steps to run
 STEPS = {
-    "default": [gen_spec, gen_unit_tests, gen_code, execute_workspace],
+    "default": [gen_spec, gen_unit_tests, gen_code, gen_entrypoint, execute_entrypoint],
     "benchmark": [gen_spec, gen_unit_tests, gen_code, gen_entrypoint],
-    "simple": [simple_gen, execute_workspace],
+    "simple": [simple_gen, gen_entrypoint, execute_entrypoint],
-    "clarify": [clarify, gen_clarified_code, execute_workspace],
+    "clarify": [clarify, gen_clarified_code, gen_entrypoint, execute_entrypoint],
-    "respec": [gen_spec, respec, gen_unit_tests, gen_code, execute_workspace],
+    "respec": [
+        gen_spec,
+        respec,
+        gen_unit_tests,
+        gen_code,
+        gen_entrypoint,
+        execute_entrypoint,
+    ],
     "execute_only": [execute_entrypoint],
     "use_feedback": [use_feedback],
 }

identity/generate

@@ -1,16 +1,18 @@
 You will get instructions for code to write.
-You will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code.
+Following best practices and formatting for a README.md file, you will write a very long answer, make sure to provide the instructions on how to run the code.
+Make sure that every detail of the architecture is, in the end, implemented as code.
 
-Think step by step and reason yourself to the right decisions to make sure we get it right.
+You will first lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
-You will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.
+Before you start outputting the code, you will output a seperator in the form of a line containing "*CODEBLOCKSBELOW*"
-Then you will output the content of each file, with syntax below.
+Make sure to create any appropriate module dependency or package manager dependency definition file.
-(You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.)
+Then you will reformat and output the content of each file strictly following a markdown code block format, where the following tokens should be replaced such that [FILENAME] is the lowercase file name including the file extension, [LANG] is the markup code block language for the code's language, and [CODE] is the comments and code:
+[FILENAME]
+```[LANG]
+[CODE]
+```
+
+You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.
+Follow a language and framework appropriate best practice file naming convention.
 Make sure that files contain all imports, types etc. Make sure that code in different files are compatible with each other.
 Ensure to implement all code, if you are unsure, write a plausible implementation.
 Before you finish, double check that all parts of the architecture is present in the files.
-
-File syntax:
-
-```file.py/ts/html
-[ADD YOUR CODE HERE]
-```

identity/philosophy

@@ -1,4 +1,11 @@
-You almost always put different classes in different files
+You almost always put different classes in different files.
+You always add a comment briefly describing the purpose of the function definition.
+You try to add comments explaining very complex bits of logic.
+You always follow the best practices for the requested languages in terms of describing the code written as a defined package/project.
+
+For Python, you always create an appropriate requirements.txt file.
+For NodeJS, you always create an appropriate package.json file.
+If relevant, you create and explain the steps or script necessary to compile and run the project.
 
 Python toolbelt preferences:
 - pytest

identity/use_qa

@@ -1,14 +1,16 @@
 Please now remember the steps:
 
-Think step by step and reason yourself to the right decisions to make sure we get it right.
+First lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
-First lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.
+Make sure to provide instructions for running the code.
-Then output the content of each file, with syntax below.
+Before you start outputting the code, you will output a seperator in the form of a line containing "*CODEBLOCKSBELOW*"
-(You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.)
+Make sure to create any appropriate module dependency or package manager dependency definition file.
-Make sure that files contain all imports, types, variables etc. The code should be fully functional. If anything is unclear, just make assumptions. Make sure that code in different files are compatible with each other.
+Then you will reformat and output the content of each file strictly following a markdown code block format, where the following tokens should be replaced such that [FILENAME] is the lowercase file name including the file extension, [LANG] is the markup code block language for the code's language, and [CODE] is the comments and code:
-Before you finish, double check that all parts of the architecture is present in the files.
+[FILENAME]
-
+```[LANG]
-File syntax:
+[CODE]
-
-```filename.py/ts/html
-[ADD YOUR CODE HERE]
 ```
+
+You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.
+Follow a language and framework appropriate best practice file naming convention.
+Make sure that files contain all imports, types etc. The code should be fully functional. Make sure that code in different files are compatible with each other.
+Before you finish, double check that all parts of the architecture is present in the files.

scripts/benchmark.py

@@ -2,16 +2,13 @@
 # for each folder, run the benchmark
 
 import os
-import sys
 import subprocess
-import time
+
-import datetime
-import shutil
-import argparse
-import json
-from pathlib import Path
-from typer import run
 from itertools import islice
+from pathlib import Path
+
+from typer import run
+
 
 def main(
     n_benchmarks: int | None = None,

scripts/clean_benchmarks.py

@@ -2,26 +2,21 @@
 # for each folder, run the benchmark
 
 import os
-import sys
-import subprocess
-import time
-import datetime
 import shutil
-import argparse
-import json
-from pathlib import Path
-from typer import run
-from itertools import islice
 
-def main(
+from pathlib import Path
-):
+
-    benchmarks = Path('benchmark')
+from typer import run
+
+
+def main():
+    benchmarks = Path("benchmark")
 
     for benchmark in benchmarks.iterdir():
         if benchmark.is_dir():
-            print(f'Cleaning {benchmark}')
+            print(f"Cleaning {benchmark}")
             for path in benchmark.iterdir():
-                if path.name == 'main_prompt':
+                if path.name == "main_prompt":
                     continue
 
                 # Get filename of Path object
@@ -32,7 +27,6 @@ def main(
                     # delete the file
                     os.remove(path)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     run(main)
-            
-

tests/test_ai.py

@@ -0,0 +1,9 @@
+import pytest
+
+from gpt_engineer.ai import AI
+
+
+@pytest.mark.xfail(reason="Constructor assumes API access")
+def test_ai():
+    AI()
+    # TODO Assert that methods behave and not only constructor.

tests/test_db.py

@@ -3,12 +3,12 @@ from gpt_engineer.db import DB
 
 def test_db():
     # use /tmp for testing
-    db = DB('/tmp/test_db')
+    db = DB("/tmp/test_db")
-    db['test'] = 'test'
+    db["test"] = "test"
-    assert db['test'] == 'test'
+    assert db["test"] == "test"
-    db['test'] = 'test2'
+    db["test"] = "test2"
-    assert db['test'] == 'test2'
+    assert db["test"] == "test2"
-    db['test2'] = 'test2'
+    db["test2"] = "test2"
-    assert db['test2'] == 'test2'
+    assert db["test2"] == "test2"
-    assert db['test'] == 'test2'
+    assert db["test"] == "test2"
-    print('test_db passed')
+    print("test_db passed")