Tool request: download workflow run artifact contents

## Problem

For cost tracking and post-run analysis of agentic workflows, the missing piece is read access to workflow run artifacts. Specifically, downloading the `agent-artifacts` artifact from a completed `gh aw` run to parse `token-usage.jsonl` for per-run token cost data.

The current workaround requires chaining several REST API calls:

1. `GET /repos/{owner}/{repo}/actions/runs/{run_id}/artifacts` to list artifacts
2. `GET /repos/{owner}/{repo}/actions/artifacts/{artifact_id}/zip` to download
3. Unzip and parse the relevant file

This is a lot of plumbing for what should be a natural thing for an AI agent to do: "look at what the last run produced."

## Proposed tool

`download_workflow_run_artifact(owner, repo, run_id, artifact_name)` that returns the artifact contents (or a structured representation for known formats like JSONL).

## Why this matters

The `token-usage.jsonl` format written by gh-aw's firewall proxy (since v0.25.8) contains per-model token counts for every agentic workflow run. A single MCP tool call to retrieve it would unlock a natural class of "analyze what the last agent run did" workflows. Right now that analysis requires dropping out of MCP and into raw REST.

More broadly, artifacts are a primary output mechanism for GitHub Actions. Being able to read them via MCP would make a wide range of post-run analysis workflows significantly simpler.

Parti dall’entry point proposto download_workflow_run_artifact(owner, repo, run_id, artifact_name) e rivedi gli endpoint REST elencati per l’individuazione e il download degli artifact. Il lavoro è completato quando una singola chiamata a uno strumento MCP può recuperare i contenuti dell’artifact di workflow selezionato, incluso token-usage.jsonl per l’analisi post-esecuzione, senza richiedere ai chiamanti di concatenare chiamate REST o decomprimere autonomamente l’artifact.

Scritto dal modello di indicizzazione a partire dal testo della issue.