Tool request: download workflow run artifact contents

从提议的入口点 download_workflow_run_artifact(owner, repo, run_id, artifact_name) 开始，并检查列出的用于发现和下载 artifact 的 REST 端点。完成的标准是：一次 MCP 工具调用即可获取所选 workflow artifact 的内容，包括用于运行后分析的 token-usage.jsonl，而不要求调用方串联 REST 调用或自行解压 artifact。

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.