github/AutoGPT
1
1
Fork 0
mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-04-30 03:00:41 -04:00
Code Issues Packages Projects Releases Wiki Activity
Files
ec65fd5c8492a877db09f6ff9db11f00a03a386c
AutoGPT/classic/pyproject.toml
Nicholas Tindle e33b1e2105 feat(classic): update classic autogpt a bit to make it more useful for my day to day (#11797) 
## Summary

This PR modernizes AutoGPT Classic to make it more useful for day-to-day
autonomous agent development. Major changes include consolidating the
project structure, adding new prompt strategies, modernizing the
benchmark system, and improving the development experience.

**Note: AutoGPT Classic is an experimental, unsupported project
preserved for educational/historical purposes. Dependencies will not be
actively updated.**

## Changes 🏗️

### Project Structure & Build System
- **Consolidated Poetry projects** - Merged `forge/`,
`original_autogpt/`, and benchmark packages into a single
`pyproject.toml` at `classic/` root
- **Removed old benchmark infrastructure** - Deleted the complex
`agbenchmark` package (3000+ lines) in favor of the new
`direct_benchmark` harness
- **Removed frontend** - Deleted `benchmark/frontend/` React app (no
longer needed)
- **Cleaned up CI workflows** - Simplified GitHub Actions workflows for
the consolidated project structure
- **Added CLAUDE.md** - Documentation for working with the codebase
using Claude Code

### New Direct Benchmark System
- **`direct_benchmark` harness** - New streamlined benchmark runner
with:
  - Rich TUI with multi-panel layout showing parallel test execution
  - Incremental resume and selective reset capabilities
  - CI mode for non-interactive environments
  - Step-level logging with colored prefixes
  - "Would have passed" tracking for timed-out challenges
  - Copy-paste completion blocks for sharing results

### Multiple Prompt Strategies
Added pluggable prompt strategy system supporting:
- **one_shot** - Single-prompt completion
- **plan_execute** - Plan first, then execute steps
- **rewoo** - Reasoning without observation (deferred tool execution)
- **react** - Reason + Act iterative loop
- **lats** - Language Agent Tree Search (MCTS-based exploration)
- **sub_agent** - Multi-agent delegation architecture
- **debate** - Multi-agent debate for consensus

### LLM Provider Improvements
- Added support for modern **Anthropic Claude models**
(claude-3.5-sonnet, claude-3-haiku, etc.)
- Added **Groq** provider support
- Improved tool call error feedback for LLM self-correction
- Fixed deprecated API usage

### Web Components
- **Replaced Selenium with Playwright** for web browsing (better async
support, faster)
- Added **lightweight web fetch component** for simple URL fetching
- **Modernized web search** with tiered provider system (Tavily, Serper,
Google)

### Agent Capabilities
- **Workspace permissions system** - Pattern-based allow/deny lists for
agent commands
- **Rich interactive selector** for command approval with scopes
(once/agent/workspace/deny)
- **TodoComponent** with LLM-powered task decomposition
- **Platform blocks integration** - Connect to AutoGPT Platform API for
additional blocks
- **Sub-agent architecture** - Agents can spawn and coordinate
sub-agents

### Developer Experience
- **Python 3.12+ support** with CI testing on 3.12, 3.13, 3.14
- **Current working directory as default workspace** - Run `autogpt`
from any project directory
- Simplified log format (removed timestamps)
- Improved configuration and setup flow
- External benchmark adapters for GAIA, SWE-bench, and AgentBench

### Bug Fixes
- Fixed N/A command loop when using native tool calling
- Fixed auto-advance plan steps in Plan-Execute strategy
- Fixed approve+feedback to execute command then send feedback
- Fixed parallel tool calls in action history
- Always recreate Docker containers for code execution
- Various pyright type errors resolved
- Linting and formatting issues fixed across codebase

## Test Plan

- [x] CI lint, type, and test checks pass
- [x] Run `poetry install` from `classic/` directory
- [x] Run `poetry run autogpt` and verify CLI starts
- [x] Run `poetry run direct-benchmark run --tests ReadFile` to verify
benchmark works

## Notes

- This is a WIP PR for personal use improvements
- The project is marked as **unsupported** - no active maintenance
planned
- Contains known vulnerabilities in dependencies (intentionally not
updated)

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> **Medium Risk**
> CI/build workflows are substantially reworked (runner matrix removal,
path/layout changes, new benchmark runner), so breakage is most likely
in automation and packaging rather than runtime behavior.
> 
> **Overview**
> **Modernizes the `classic/` project layout and automation around a
single consolidated Poetry project** (root
`classic/pyproject.toml`/`poetry.lock`) and updates docs
(`classic/README.md`, new `classic/CLAUDE.md`) accordingly.
> 
> **Replaces the old `agbenchmark` CI usage with `direct-benchmark` in
GitHub Actions**, including new/updated benchmark smoke and regression
workflows, standardized `working-directory: classic`, and a move to
**Python 3.12** on Ubuntu-only runners (plus updated caching, coverage
flags, and required `ANTHROPIC_API_KEY` wiring).
> 
> Cleans up repo/dev tooling by removing the classic frontend workflow,
deleting the Forge VCR cassette submodule (`.gitmodules`) and associated
CI steps, consolidating `flake8`/`isort`/`pyright` pre-commit hooks to
run from `classic/`, updating ignores for new report/workspace
artifacts, and updating `classic/Dockerfile.autogpt` to build from
Python 3.12 with the consolidated project structure.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
de67834dac. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
2026-04-03 07:16:36 +00:00

196 lines
4.6 KiB
TOML
Raw Blame History

[tool.poetry]
name = "autogpt-classic"
version = "0.5.0"
description = "AutoGPT Classic - autonomous agent framework"
authors = ["Significant Gravitas <support@agpt.co>"]
license = "MIT"
readme = "README.md"
homepage = "https://github.com/Significant-Gravitas/AutoGPT"
keywords = ["autogpt", "ai", "agents", "autonomous", "llm", "gpt", "openai"]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Programming Language :: Python :: 3.14",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
]
packages = [
{ include = "forge", from = "forge" },
{ include = "autogpt", from = "original_autogpt" },
{ include = "direct_benchmark", from = "direct_benchmark" },
]
[tool.poetry.urls]
"Bug Tracker" = "https://github.com/Significant-Gravitas/AutoGPT/issues"
"Documentation" = "https://docs.agpt.co"
[tool.poetry.scripts]
autogpt = "autogpt.app.cli:cli"
serve = "autogpt.app.cli:serve"
direct-benchmark = "direct_benchmark.__main__:main"
[tool.poetry.dependencies]
python = "^3.12"
# Core networking & web
aiohttp = "^3.8.5"
beautifulsoup4 = "^4.12.2"
requests = "*"
trafilatura = "^2.0"
# LLM providers
anthropic = "^0.45.0"
groq = "^0.8.0"
litellm = "^1.17.9"
openai = "^1.50.0"
tiktoken = ">=0.7.0,<1.0.0"
# Web frameworks
fastapi = "^0.109.1"
hypercorn = "^0.14.4"
uvicorn = { extras = ["standard"], version = ">=0.23.2,<1" }
python-multipart = "^0.0.7"
# Data processing
charset-normalizer = "^3.1.0"
demjson3 = "^3.0.0"
jsonschema = "*"
orjson = "^3.8.10"
pydantic = "^2.7.2"
pyyaml = "^6.0"
toml = "^0.10.2"
# Database & storage
boto3 = "^1.33.6"
chromadb = "^1.4.0"
google-cloud-logging = "^3.8.0"
google-cloud-storage = "^2.13.0"
sqlalchemy = "^2.0.19"
# CLI & UI
click = "^8.0"
colorama = "^0.4.6"
prompt-toolkit = "^3.0.0"
rich = "^13.0"
# Document processing
pypdf = "^3.1.0"
python-docx = "*"
pylatexenc = "*"
Pillow = "*"
# NLP
en-core-web-sm = { url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl" }
spacy = "^3.8.0"
# Web automation & search
ddgs = "^9.9"
google-api-python-client = "^2.116"
playwright = "^1.50.0"
# Utilities
distro = "^1.8.0"
docker = "*"
gitpython = "^3.1.32"
gTTS = "^2.3.1"
jinja2 = "^3.1.2"
numpy = ">=2.0.0"
playsound = "~1.2.2"
python-dotenv = "^1.0.0"
sentry-sdk = "^1.40.4"
tenacity = "^8.2.2"
watchdog = "^6.0.0"
# Testing (needed for direct_benchmark challenge evaluation)
pytest = "^8.0"
[tool.poetry.group.dev.dependencies]
# Formatting & linting
black = "^24.10.0"
flake8 = "^7.0.0"
isort = "^5.13.1"
pre-commit = "^3.3.3"
pyright = "^1.1.364"
# Type stubs
boto3-stubs = { extras = ["s3"], version = "^1.33.6" }
google-api-python-client-stubs = "^1.24"
types-beautifulsoup4 = "*"
types-colorama = "*"
types-Pillow = "*"
types-requests = "^2.31.0.2"
# Testing
pytest-asyncio = "^0.23.3"
pytest-cov = "^5.0.0"
pytest-mock = "*"
pytest-recording = "*"
pytest-xdist = "*"
mock = "^5.1.0"
aiohttp-retry = "^2.9.1"
pytest-rerunfailures = "^16.1"
[tool.poetry.group.build]
optional = true
[tool.poetry.group.build.dependencies]
cx-freeze = { git = "https://github.com/ntindle/cx_Freeze.git", rev = "main" }
[tool.poetry.group.benchmarks]
optional = true
[tool.poetry.group.benchmarks.dependencies]
# External benchmark adapters
datasets = "^2.14"
huggingface-hub = "^0.20"
# SWE-bench evaluation (optional - requires Docker)
# swebench = "^2.0" # Install separately if needed
# Modal for cloud evaluation (optional)
# modal = "^0.70" # Install separately if needed
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"
[tool.black]
line-length = 88
target-version = ['py312']
include = '\.pyi?$'
[tool.isort]
profile = "black"
skip_glob = ["data"]
[tool.pyright]
pythonVersion = "3.12"
exclude = [
"data/**",
"**/node_modules",
"**/__pycache__",
"**/.*",
"direct_benchmark/challenges/**", # Legacy code with unavailable imports
"direct_benchmark/direct_benchmark/adapters/**", # Optional deps (datasets, swebench, modal)
]
[tool.pytest.ini_options]
pythonpath = ["."]
testpaths = ["forge/forge", "forge/tests", "original_autogpt/tests"]
asyncio_mode = "auto"
markers = [
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
"integration: marks tests as integration tests",
"requires_agent: marks tests that require a running agent with API keys",
]
Reference in New Issue View Git Blame Copy Permalink