Sequential Steps

from timbal import Agent, Workflow
from timbal.state import get_run_context


def fetch_content(url: str) -> str:
    """Fetch raw content from a URL.

    This sample returns a fixed page so the workflow runs offline. Replace the
    body with urllib or httpx when you want the live document.
    """
    _ = url
    return "<title>Example Domain</title><p>An illustrative example.</p>"


def extract_metadata(html: str) -> dict:
    """Extract title and text from HTML content."""
    import re
    title_match = re.search(r"<title>(.*?)</title>", html)
    text = re.sub(r"<[^>]+>", " ", html)
    text = re.sub(r"\s+", " ", text).strip()
    return {
        "title": title_match.group(1) if title_match else "Untitled",
        "text": text[:5000],
    }


summarizer = Agent(
    name="summarizer",
    model="openai/gpt-5-mini",
    system_prompt="Summarize the given text in 3 bullet points. Be concise."
)


def format_report(title: str, summary: str) -> str:
    """Format the final report."""
    return f"# {title}\n\n{summary}"


pipeline = (
    Workflow(name="document_pipeline")
    .step(fetch_content, url="https://example.com")
    .step(extract_metadata,
        html=lambda: get_run_context().step_span("fetch_content").output)
    .step(summarizer,
        prompt=lambda: get_run_context().step_span("extract_metadata").output["text"])
    .step(format_report,
        title=lambda: get_run_context().step_span("extract_metadata").output["title"],
        summary=lambda: get_run_context().step_span("summarizer").output.collect_text())
)