# Stagehand Python 4.0.3a0.dev1483 adds stagehand_facade tool surface for eval benchmarking

> A dev release of Stagehand Python introduces a facade tool surface that allows evals to benchmark the exact byte-identical interface shipped to Claude Code, Codex, and Pi integrations.

- Canonical: https://extractfeed.io/story/stagehand-python-4-0-3a0-dev1483-adds-stagehand-facade-tool-0c6ec60/
- JSON: https://extractfeed.io/api/v1/stories/stagehand-python-4-0-3a0-dev1483-adds-stagehand-facade-tool-0c6ec60.json
- Beat: Open Source & Tooling · Evidence: Primary source · Type/significance: release/2 · First seen: 2026-09-05T14:58:45.519221+00:00 · Updated: 2026-09-05T14:58:45.519221+00:00 · Edition: 2026-09-06
- Framing: model-written (headline, standfirst, why it matters, tags); source facts deterministic

## Briefing
- browserbase/stagehand releases: A dev release of Stagehand Python introduces a facade tool surface that allows evals to benchmark the exact byte-identical interface shipped to Claude Code, Codex, and Pi integrations.

## Why it matters
This change closes the loop on eval harness consolidation by ensuring benchmarks test the same facade that third-party integrations actually use. For practitioners, it means evaluation results will more accurately reflect real-world performance, reducing the gap between lab metrics and production behavior in agentic extraction workflows.

## Sources
- Primary source · browserbase/stagehand releases · 2026-08-30 — [browserbase/stagehand stagehand-python@4.0.3a0.dev1483: feat\(evals\): add stagehand\_facade tool surface \(\#2750\)](https://github.com/browserbase/stagehand/releases/tag/stagehand-python%404.0.3a0.dev1483)

## Watch next
Will this facade surface become the standard interface for benchmarking other browser automation SDKs?

Topics: browserbase, stagehand, claude-code, codex, pi, stagehand, python, eval, benchmarking, facade, mcp

---
extractfeed is an agent-readable changefeed for web scraping and data extraction. Index: https://extractfeed.io/agents.md