Merge branch 'main' into issue-315

.github/CONTRIBUTING.md

@@ -24,7 +24,7 @@ To enforce this we use [`pre-commit`](https://pre-commit.com/) to run [`black`](
 `pre-commit` is part of our `requirements.txt` file so you should already have it installed. If you don't, you can install the library via pip with:
 
 ```bash
-$ pip install -r requirements.txt
+$ pip install -e .
 
 # And then install the `pre-commit` hooks with:
 
@@ -34,7 +34,7 @@ $ pre-commit install
 pre-commit installed at .git/hooks/pre-commit
 ```
 
-Or you could just run `make dev-install` to install the dependencies and the hooks!
+Or you could just run `make dev-install` to install the dependencies and the hooks.
 
 If you are not familiar with the concept of [git hooks](https://git-scm.com/docs/githooks) and/or [`pre-commit`](https://pre-commit.com/) please read the documentation to understand how they work.
 

.github/FUNDING.yml

@@ -0,0 +1,4 @@
+# These are supported funding model platforms
+
+github: [antonosika]
+patreon: gpt-engineer

.github/workflows/codeql.yml

@@ -0,0 +1,66 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ 'main' ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ 'main' ]
+  schedule:
+    - cron: '26 2 * * 6'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Use only 'java' to analyze code written in Java, Kotlin or both
+        # Use only 'javascript' to analyze code written in JavaScript, TypeScript or both
+        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v2
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+
+    # Autobuild attempts to build any compiled languages (C/C++, C#, Go, Java, or Swift).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v2
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+
+    #   If the Autobuild fails above, remove it and uncomment the following three lines.
+    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+
+    # - run: |
+    #     echo "Run, Build Application using script"
+    #     ./location_of_script_within_repo/buildscript.sh
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v2
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/codespell.yml

@@ -0,0 +1,22 @@
+---
+name: Codespell
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

.gitignore

@@ -49,3 +49,10 @@ scratchpad
 # Ignore GPT Engineer files
 projects
 !projects/example
+
+# Pyenv
+.python-version
+
+# Benchmark files
+benchmark
+!benchmark/*/prompt

.pre-commit-config.yaml

@@ -8,6 +8,7 @@ repos:
     rev: v1.3.0
     hooks:
       - id: mypy
+        additional_dependencies: [types-tabulate==0.9.0.2]
 
   - repo: https://github.com/psf/black
     rev: 23.3.0
@@ -30,3 +31,10 @@ repos:
       - id: detect-private-key
       - id: end-of-file-fixer
       - id: trailing-whitespace
+
+- repo: https://github.com/codespell-project/codespell
+  rev: v2.2.5
+  hooks:
+  - id: codespell
+    additional_dependencies:
+      - tomli

DISCLAIMER.md

@@ -0,0 +1,11 @@
+# Disclaimer
+
+gpt-engineer is an experimental application and is provided "as-is" without any warranty, express or implied. By using this software, you agree to assume all risks associated with its use, including but not limited to data loss, system failure, or any other issues that may arise.
+
+The developers and contributors of this project do not accept any responsibility or liability for any losses, damages, or other consequences that may occur as a result of using this software. You are solely responsible for any decisions and actions taken based on the information provided by gpt-engineer.
+
+Please note that the use of the GPT-4 language model can be expensive due to its token usage. By utilizing this project, you acknowledge that you are responsible for monitoring and managing your own token usage and the associated costs. It is highly recommended to check your OpenAI API usage regularly and set up any necessary limits or alerts to prevent unexpected charges.
+
+As an autonomous experiment, gpt-engineern may generate code or take actions that are not in line with real-world business practices or legal requirements. It is your responsibility to ensure that any actions or decisions made by the gneerated code comply with all applicable laws, regulations, and ethical standards. The developers and contributors of this project shall not be held responsible for any consequences arising from the use of this software.
+
+By using gpt-engineer, you agree to indemnify, defend, and hold harmless the developers, contributors, and any affiliated parties from and against any and all claims, damages, losses, liabilities, costs, and expenses (including reasonable attorneys' fees) arising from your use of this software or your violation of these terms.

Makefile

@@ -5,7 +5,7 @@ COLOR_RESET=\033[0m
 COLOR_CYAN=\033[1;36m
 COLOR_GREEN=\033[1;32m
 
-.PHONY: help install dev-install run
+.PHONY: help install run
 
 .DEFAULT_GOAL := help
 
@@ -17,11 +17,8 @@ help:
 	@echo "Please use 'make <target>' where <target> is one of the following:"
 	@echo "  help           	Return this message with usage instructions."
 	@echo "  install        	Will install the dependencies and create a virtual environment."
-	@echo "  dev-install    	Will install the dev dependencies too."
 	@echo "  run <folder_name>  Runs GPT Engineer on the folder with the given name."
 
-dev-install: install
-
 install: create-venv upgrade-pip install-dependencies install-pre-commit farewell
 
 create-venv:

README.md

@@ -37,10 +37,13 @@ For **development**:
 
 **Setup**
 
-With an api key that has GPT4 access run:
+With an OpenAI API key (preferably with GPT-4 access) run:
 
 - `export OPENAI_API_KEY=[your api key]`
 
+Alternative for Windows
+- `set OPENAI_API_KEY=[your api key]` on cmd
+- `$env:OPENAI_API_KEY="[your api key]"` on powershell
 
 **Run**:
 
@@ -50,7 +53,7 @@ With an api key that has GPT4 access run:
 - `gpt-engineer projects/my-new-project`
   - (Note, `gpt-engineer --help` lets you see all available options. For example `--steps use_feedback` lets you improve/fix code in a project)
 
-By running gpt-engineer you agree to our [ToS](https://github.com/AntonOsika/gpt-engineer/TERMS_OF_USE.md).
+By running gpt-engineer you agree to our [terms](https://github.com/AntonOsika/gpt-engineer/blob/main/TERMS_OF_USE.md).
 
 **Results**
 - Check the generated files in `projects/my-new-project/workspace`
@@ -75,7 +78,7 @@ Contributing document [here](.github/CONTRIBUTING.md).
 We are currently looking for more maintainers and community organisers. Email anton.osika@gmail.com if you are interested in an official role.
 
 If you want to see our broader ambitions, check out the [roadmap](https://github.com/AntonOsika/gpt-engineer/blob/main/ROADMAP.md), and join
-[discord ](https://discord.gg/4t5vXHhu)
+[discord](https://discord.gg/8tcDQ89Ej2)
 to get input on how you can contribute to it.
 
 ## Example

ROADMAP.md

@@ -1,7 +1,5 @@
 # Roadmap
 
-We are building AGI. The first step is creating the code generation tooling of the future.
-
 There are three main milestones we believe will 2x gpt-engineer's reliability and capability:
 - Continuous evaluation of our progress
 - Make code generation become small, verifiable steps
@@ -37,7 +35,7 @@ You can:
 
 - Submit your first PR to address an [issue](https://github.com/AntonOsika/gpt-engineer/issues)
 - Submit PRs to address one of the items in the roadmap
-- Review your first PR/issue and propose next steps (further review, merge, close)
+- Do your first review of someone else's PR/issue and propose next steps (further review, merge, close)
 - Sign up to help [measure the progress of gpt-engineer towards recursively coding itself](https://forms.gle/TMX68mScyxQUsE6Y9)
 
 Volunteer work in any of these gets acknowledged.

TERMS_OF_USE.md

@@ -0,0 +1,12 @@
+# Terms of Use
+
+By using gpt-engineer you are aware of and agree to the below Terms of Use, as well as the attached [disclaimer of warranty](https://github.com/AntonOsika/gpt-engineer/blob/main/DISCLAIMER.md).
+
+Both OpenAI, L.L.C. and the creators of gpt-engineer **store data
+about how gpt-engineer is used** with the sole intent of improving the capability of the product. Care is taken to not store any information that can be tied to a person.
+
+Please beware that natural text input, such as the files `prompt` and `feedback`, will be stored and this can, in theory, be used to (although the gpt-engineer creators will never attempt to do so) connect a person's style of writing or content in the files to a real person.
+
+More information about OpenAI's terms of use [here](https://openai.com/policies/terms-of-use).
+
+You can disable storing usage data by gpt-engineer, **but not OpenAI**, by setting the environment variable COLLECT_LEARNINGS_OPT_OUT=true.

benchmark/RESULTS.md

@@ -74,6 +74,6 @@ failing tests, 'WebDriver' object has no attribute 'find_element_by_id'
 
 pomodoro: doesn't run it only tests
 
-currency_converter: backend doesnt return anything
+currency_converter: backend doesn't return anything
 
 weather_app only runs test, no code existed

gpt_engineer/ai.py

@@ -2,6 +2,8 @@
 
 import logging
 
+from typing import Dict, List
+
 import openai
 
 logger = logging.getLogger(__name__)
@@ -29,7 +31,7 @@ def fuser(self, msg):
     def fassistant(self, msg):
         return {"role": "assistant", "content": msg}
 
-    def next(self, messages: list[dict[str, str]], prompt=None):
+    def next(self, messages: List[Dict[str, str]], prompt=None):
         if prompt:
             messages += [{"role": "user", "content": prompt}]
 
@@ -43,7 +45,7 @@ def next(self, messages: list[dict[str, str]], prompt=None):
 
         chat = []
         for chunk in response:
-            delta = chunk["choices"][0]["delta"]
+            delta = chunk["choices"][0]["delta"]  # type: ignore
             msg = delta.get("content", "")
             print(msg, end="")
             chat.append(msg)

gpt_engineer/collect.py

@@ -23,8 +23,8 @@ def send_learning(learning: Learning):
 
 
 def collect_learnings(model: str, temperature: float, steps: List[Step], dbs: DBs):
-    if os.environ.get("COLLECT_LEARNINGS_OPT_OUT") in ["true", "1"]:
-        print("COLLECT_LEARNINGS_OPT_OUT is set to true, not collecting learning")
+    if os.environ.get("COLLECT_LEARNINGS_OPT_IN") in ["false", "1"]:
+        print("COLLECT_LEARNINGS_OPT_IN is set to false, not collecting learning")
         return
 
     learnings = extract_learning(

gpt_engineer/db.py

@@ -1,3 +1,6 @@
+import datetime
+import shutil
+
 from dataclasses import dataclass
 from pathlib import Path
 
@@ -47,3 +50,16 @@ class DBs:
     preprompts: DB
     input: DB
     workspace: DB
+    archive: DB
+
+
+def archive(dbs: DBs):
+    timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+    shutil.move(
+        str(dbs.memory.path), str(dbs.archive.path / timestamp / dbs.memory.path.name)
+    )
+    shutil.move(
+        str(dbs.workspace.path),
+        str(dbs.archive.path / timestamp / dbs.workspace.path.name),
+    )
+    return []

gpt_engineer/main.py

@@ -1,64 +1,57 @@
 import json
 import logging
-import shutil
 
 from pathlib import Path
 
 import typer
 
-from gpt_engineer import steps
 from gpt_engineer.ai import AI, fallback_model
 from gpt_engineer.collect import collect_learnings
-from gpt_engineer.db import DB, DBs
-from gpt_engineer.steps import STEPS
+from gpt_engineer.db import DB, DBs, archive
+from gpt_engineer.steps import STEPS, Config as StepsConfig
 
 app = typer.Typer()
 
 
 @app.command()
 def main(
     project_path: str = typer.Argument("projects/example", help="path"),
-    delete_existing: bool = typer.Argument(False, help="delete existing files"),
     model: str = typer.Argument("gpt-4", help="model id string"),
     temperature: float = 0.1,
-    steps_config: steps.Config = typer.Option(
-        steps.Config.DEFAULT, "--steps", "-s", help="decide which steps to run"
+    steps_config: StepsConfig = typer.Option(
+        StepsConfig.DEFAULT, "--steps", "-s", help="decide which steps to run"
     ),
     verbose: bool = typer.Option(False, "--verbose", "-v"),
-    run_prefix: str = typer.Option(
-        "",
-        help=(
-            "run prefix, if you want to run multiple variants of the same project and "
-            "later compare them"
-        ),
-    ),
 ):
     logging.basicConfig(level=logging.DEBUG if verbose else logging.INFO)
 
-    input_path = Path(project_path).absolute()
-    memory_path = input_path / f"{run_prefix}memory"
-    workspace_path = input_path / f"{run_prefix}workspace"
-
-    if delete_existing:
-        # Delete files and subdirectories in paths
-        shutil.rmtree(memory_path, ignore_errors=True)
-        shutil.rmtree(workspace_path, ignore_errors=True)
-
     model = fallback_model(model)
-
     ai = AI(
         model=model,
         temperature=temperature,
     )
 
+    input_path = Path(project_path).absolute()
+    memory_path = input_path / "memory"
+    workspace_path = input_path / "workspace"
+    archive_path = input_path / "archive"
+
     dbs = DBs(
         memory=DB(memory_path),
         logs=DB(memory_path / "logs"),
         input=DB(input_path),
         workspace=DB(workspace_path),
         preprompts=DB(Path(__file__).parent / "preprompts"),
+        archive=DB(archive_path),
     )
 
+    if steps_config not in [
+        StepsConfig.EXECUTE_ONLY,
+        StepsConfig.USE_FEEDBACK,
+        StepsConfig.EVALUATE,
+    ]:
+        archive(dbs)
+
     steps = STEPS[steps_config]
     for step in steps:
         messages = step(ai, dbs)