base classes

This commit is contained in:
Adam Wilson
2025-08-18 20:24:36 -06:00
parent a636b7fbf7
commit 42e4962063
16 changed files with 167 additions and 131 deletions
@@ -0,0 +1,72 @@
name: 'Reusable Test Runner | RAG + CoT | Generic'
on:
workflow_call:
inputs:
batch_offset:
description: 'Starting prompt index offset'
required: true
type: number
range_name:
description: 'Human readable range name (e.g., "1-20")'
required: true
type: string
test_file_path:
description: 'Path to the test file to run'
required: true
type: string
model_display_name:
description: 'Human readable model name for workflow title'
required: true
type: string
batch_size:
description: 'Number of prompts per batch'
required: false
type: number
default: 2
jobs:
test:
runs-on: ubuntu-latest
strategy:
# Always 10 batches per workflow
matrix:
batch: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
fail-fast: false
steps:
- name: 'checkout'
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
- name: 'set up Python'
uses: actions/setup-python@v3
with:
python-version: '3.12'
- name: 'set up Python dependencies'
shell: bash
run: pip install -r ${{ github.workspace }}/requirements.txt
- name: 'run text generation tests - ${{ inputs.model_display_name }} - range ${{ inputs.range_name }} batch ${{ matrix.batch }}'
shell: bash
env:
PROMPT_BATCH: ${{ matrix.batch }}
BATCH_SIZE: ${{ inputs.batch_size }}
BATCH_OFFSET: ${{ inputs.batch_offset }}
run: pytest ${{ inputs.test_file_path }} -s --disable-warnings
- name: Check for changes
id: verify-changed-files
run: |
if [ -n "$(git status --porcelain)" ]; then
echo "changed=true" >> $GITHUB_OUTPUT
else
echo "changed=false" >> $GITHUB_OUTPUT
fi
- name: Commit and push changes
if: steps.verify-changed-files.outputs.changed == 'true'
run: |
git config --local user.email "42450907+lightbroker@users.noreply.github.com"
git config --local user.name "Adam Wilson"
git add .
git commit -m "Auto-generated files from ${{ inputs.model_display_name }} range ${{ inputs.range_name }} batch ${{ matrix.batch }} [skip ci]"
git push