Extract SIR #12

	name: Extract SIR

	on:
	workflow_dispatch:
	inputs:
	max_new_files:
	description: "Max PDFs to process (0 = all unprocessed)"
	required: false
	default: "10"

	jobs:
	extract:
	runs-on: ubuntu-latest

	steps:
	- name: Checkout with LFS
	uses: actions/checkout@v4
	with:
	lfs: true
	token: ${{ secrets.GITHUB_TOKEN }}

	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: "3.11"

	- name: Set up uv
	uses: astral-sh/setup-uv@v5
	with:
	enable-cache: true

	- name: Install dependencies
	run: uv pip install --system -r requirements.txt

	- name: Extract SIR from PDFs
	run: \|
	python3 extract_sir_pdf_gemini.py pdfs \
	--output-dir analysis_output \
	--max-new-files ${{ github.event.inputs.max_new_files }} \
	--allow-file-failures
	env:
	GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}

	- name: Commit and push results
	run: \|
	git config user.name "github-actions[bot]"
	git config user.email "github-actions[bot]@users.noreply.github.com"
	git add analysis_output/
	git diff --cached --quiet \|\| git commit -m "auto: extract SIR batch (max=${{ github.event.inputs.max_new_files }})"
	git pull --rebase
	git push

Provide feedback