feat(direct_benchmark): add step-level logging with colored prefixes

- Add step callback to AgentRunner for real-time step logging
- BenchmarkUI now shows:
  - Active runs with current step info
  - Recent steps panel with colored config prefixes
  - Proper Live display refresh (implements __rich_console__)
- Each config gets a distinct color for easy identification
- Verbose mode prints step logs immediately with config prefix
- Fix Live display not updating (pass UI object, not rendered content)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Nicholas Tindle
2026-01-19 23:02:20 -06:00
parent ab95077e5b
commit 0a616d9267
9 changed files with 198 additions and 142 deletions

View File

@@ -30,40 +30,15 @@ jobs:
permissions:
contents: read
timeout-minutes: 30
strategy:
fail-fast: false
matrix:
python-version: ["3.12", "3.13", "3.14"]
platform-os: [ubuntu, macos, macos-arm64, windows]
runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
runs-on: ubuntu-latest
steps:
# Quite slow on macOS (2~4 minutes to set up Docker)
# - name: Set up Docker (macOS)
# if: runner.os == 'macOS'
# uses: crazy-max/ghaction-setup-docker@v3
- name: Start MinIO service (Linux)
if: runner.os == 'Linux'
- name: Start MinIO service
working-directory: '.'
run: |
docker pull minio/minio:edge-cicd
docker run -d -p 9000:9000 minio/minio:edge-cicd
- name: Start MinIO service (macOS)
if: runner.os == 'macOS'
working-directory: ${{ runner.temp }}
run: |
brew install minio/stable/minio
mkdir data
minio server ./data &
# No MinIO on Windows:
# - Windows doesn't support running Linux Docker containers
# - It doesn't seem possible to start background processes on Windows. They are
# killed after the step returns.
# See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
- name: Checkout repository
uses: actions/checkout@v4
with:
@@ -75,41 +50,23 @@ jobs:
git config --global user.name "Auto-GPT-Bot"
git config --global user.email "github-bot@agpt.co"
- name: Set up Python ${{ matrix.python-version }}
- name: Set up Python 3.12
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
python-version: "3.12"
- id: get_date
name: Get date
run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
- name: Set up Python dependency cache
# On Windows, unpacking cached dependencies takes longer than just installing them
if: runner.os != 'Windows'
uses: actions/cache@v4
with:
path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
path: ~/.cache/pypoetry
key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}
- name: Install Poetry (Unix)
if: runner.os != 'Windows'
run: |
curl -sSL https://install.python-poetry.org | python3 -
if [ "${{ runner.os }}" = "macOS" ]; then
PATH="$HOME/.local/bin:$PATH"
echo "$HOME/.local/bin" >> $GITHUB_PATH
fi
- name: Install Poetry (Windows)
if: runner.os == 'Windows'
shell: pwsh
run: |
(Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
$env:PATH += ";$env:APPDATA\Python\Scripts"
echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
- name: Install Poetry
run: curl -sSL https://install.python-poetry.org | python3 -
- name: Install Python dependencies
run: poetry install
@@ -129,7 +86,7 @@ jobs:
CI: true
PLAIN_OUTPUT: True
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
S3_ENDPOINT_URL: http://127.0.0.1:9000
AWS_ACCESS_KEY_ID: minioadmin
AWS_SECRET_ACCESS_KEY: minioadmin
@@ -143,7 +100,7 @@ jobs:
uses: codecov/codecov-action@v5
with:
token: ${{ secrets.CODECOV_TOKEN }}
flags: autogpt-agent,${{ runner.os }}
flags: autogpt-agent
- name: Upload logs to artifact
if: always()

View File

@@ -26,74 +26,31 @@ jobs:
permissions:
contents: read
timeout-minutes: 30
strategy:
fail-fast: false
matrix:
python-version: ["3.12", "3.13", "3.14"]
platform-os: [ubuntu, macos, macos-arm64, windows]
runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
runs-on: ubuntu-latest
steps:
# Quite slow on macOS (2~4 minutes to set up Docker)
# - name: Set up Docker (macOS)
# if: runner.os == 'macOS'
# uses: crazy-max/ghaction-setup-docker@v3
- name: Start MinIO service (Linux)
if: runner.os == 'Linux'
- name: Start MinIO service
working-directory: '.'
run: |
docker pull minio/minio:edge-cicd
docker run -d -p 9000:9000 minio/minio:edge-cicd
- name: Start MinIO service (macOS)
if: runner.os == 'macOS'
working-directory: ${{ runner.temp }}
run: |
brew install minio/stable/minio
mkdir data
minio server ./data &
# No MinIO on Windows:
# - Windows doesn't support running Linux Docker containers
# - It doesn't seem possible to start background processes on Windows. They are
# killed after the step returns.
# See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
- name: Checkout repository
uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
- name: Set up Python 3.12
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
python-version: "3.12"
- name: Set up Python dependency cache
# On Windows, unpacking cached dependencies takes longer than just installing them
if: runner.os != 'Windows'
uses: actions/cache@v4
with:
path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
path: ~/.cache/pypoetry
key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}
- name: Install Poetry (Unix)
if: runner.os != 'Windows'
run: |
curl -sSL https://install.python-poetry.org | python3 -
if [ "${{ runner.os }}" = "macOS" ]; then
PATH="$HOME/.local/bin:$PATH"
echo "$HOME/.local/bin" >> $GITHUB_PATH
fi
- name: Install Poetry (Windows)
if: runner.os == 'Windows'
shell: pwsh
run: |
(Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
$env:PATH += ";$env:APPDATA\Python\Scripts"
echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
- name: Install Poetry
run: curl -sSL https://install.python-poetry.org | python3 -
- name: Install Python dependencies
run: poetry install
@@ -112,7 +69,7 @@ jobs:
# Secrets are not available to fork PRs (GitHub security feature)
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
S3_ENDPOINT_URL: http://127.0.0.1:9000
AWS_ACCESS_KEY_ID: minioadmin
AWS_SECRET_ACCESS_KEY: minioadmin
@@ -126,11 +83,11 @@ jobs:
uses: codecov/codecov-action@v5
with:
token: ${{ secrets.CODECOV_TOKEN }}
flags: forge,${{ runner.os }}
flags: forge
- name: Upload logs to artifact
if: always()
uses: actions/upload-artifact@v4
with:
name: test-logs-${{ matrix.platform-os }}-${{ matrix.python-version }}
name: test-logs
path: classic/forge/logs/