Add agbenchmark routes + CI test

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

.flake8

@@ -0,0 +1,15 @@
+[flake8]
+max-line-length = 88
+select = "E303, W293, W291, W292, E305, E231, E302"
+exclude =
+    .tox,
+    __pycache__,
+    *.pyc,
+    .env
+    venv*/*,
+    .venv/*,
+    reports/*,
+    dist/*,
+    agent/*,
+    code,
+    agbenchmark/challenges/*

.github/workflows/ci.yml

@@ -0,0 +1,118 @@
+name: CI
+
+on:
+  workflow_dispatch:
+    branches: [master]
+  schedule:
+    - cron: '0 8 * * *'
+  push:
+    branches: [master, ci-test*]
+  pull_request:
+    branches: [stable, master, release-*]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    env:
+      min-python-version: '3.10'
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.ref }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          submodules: true
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ env.min-python-version }}
+
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Install Poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | python -
+
+      - name: Install dependencies
+        run: |
+          export POETRY_VIRTUALENVS_IN_PROJECT=true
+          poetry install -vvv
+
+      - name: Lint with flake8
+        run: poetry run flake8
+
+      - name: Check black formatting
+        run: poetry run  black . --exclude test.py --check
+        if: success() || failure()
+
+      - name: Check isort formatting
+        run: poetry run  isort . --check
+        if: success() || failure()
+
+      - name: Check mypy formatting
+        run: poetry run mypy --ignore-missing-imports .
+        if: success() || failure()
+
+      - name: Check for unused imports and pass statements
+        run: |
+          cmd="poetry run autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring agbenchmark"
+          $cmd --check || (echo "You have unused imports or pass statements, please run '${cmd} --in-place'" && exit 1)
+        if: success() || failure()
+
+  tests:
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.ref }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          submodules: true
+          token: ${{ env.GH_TOKEN }}
+
+      - name: Setup Chrome and ChromeDriver
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y wget
+          wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
+          sudo dpkg -i google-chrome-stable_current_amd64.deb
+          sudo apt-get install -f
+
+
+      - name: Set up Python ${{ env.min-python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ env.min-python-version }}
+
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Install Poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | python -
+
+      - name: Install dependencies
+        run: |
+          poetry install -vvv
+          poetry build
+
+      - name: Run regression tests
+        run: |
+          sh run
+
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          AGENT_NAME: ${{ matrix.agent-name }}
+          HELICONE_API_KEY: ${{ secrets.HELICONE_API_KEY }}
+          REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
+          HELICONE_CACHE_ENABLED: false
+          HELICONE_PROPERTY_AGENT: ${{ matrix.agent-name }}
+          REPORT_LOCATION: ${{ format('../../reports/{0}', matrix.agent-name) }}

autogpt/__main__.py

@@ -2,13 +2,15 @@
 
 from agent_protocol import Agent
 from dotenv import load_dotenv
-
 import autogpt.agent
 import autogpt.db
+from autogpt.benchmark_integration import add_benchmark_routes
 
 if __name__ == "__main__":
     """Runs the agent server"""
     load_dotenv()
+    router = add_benchmark_routes()
+
     database_name = os.getenv("DATABASE_STRING")
     print(database_name)
     port = os.getenv("PORT")
@@ -19,4 +21,4 @@
     agent = Agent.setup_agent(auto_gpt.task_handler, auto_gpt.step_handler)
     agent.db = database
     agent.workspace = workspace
-    agent.start(port=port)
+    agent.start(port=port, router=router)

autogpt/benchmark_integration.py

@@ -0,0 +1,29 @@
+from pathlib import Path
+
+from agent_protocol.agent import base_router
+from fastapi.responses import FileResponse
+from fastapi import (
+    HTTPException as FastAPIHTTPException,  # Import HTTPException from FastAPI
+)
+from agbenchmark.app import get_artifact
+from agbenchmark.app import get_skill_tree
+from fastapi import APIRouter
+
+def add_benchmark_routes():
+
+    new_router = APIRouter()
+
+    @new_router.get("/skill_tree")
+    async def get_skill_tree_endpoint() -> dict:  # Renamed to avoid a clash with the function import
+        return get_skill_tree()
+
+    @new_router.get("/agent/challenges/{challenge_id}/artifacts/{artifact_id}")
+    async def get_artifact_endpoint(
+        challenge_id: str, artifact_id: str
+    ) -> FileResponse:  # Added return type annotation
+        return get_artifact(challenge_id, artifact_id)
+
+    # Include the new router in the base router
+    base_router.include_router(new_router)
+
+    return base_router

mypy.ini

@@ -0,0 +1,13 @@
+[mypy]
+namespace_packages = True
+follow_imports = skip
+check_untyped_defs = True
+disallow_untyped_defs = True
+exclude = ^(agbenchmark/challenges/|agent/|venv|venv-dev)
+ignore_missing_imports = True
+
+[mypy-agbenchmark.utils.data_types.*]
+ignore_errors = True
+
+[mypy-numpy.*]
+ignore_errors = True