ci(evals): run eval workflow on OpenRouter

[sentry-junior]

Summary

Moves the eval CI job and eval harness off a direct OpenAI key onto OpenRouter, so GitHub Actions no longer needs OPENAI_API_KEY for evals.

Changes

• .github/workflows/eval.yml now injects OPENROUTER_API_KEY and EMBEDDED_AGENT_PROVIDER=openrouter
• eval scorers/task runners default to getOpenRouterModel() instead of hardcoding openai("gpt-4o")
• MSW unhandled-request filters also allow openrouter.ai traffic during evals
• docs/comments updated to mention OPENROUTER_API_KEY

Follow-up

• Ensure the Actions environment has an OPENROUTER_API_KEY secret before relying on eval CI results
• Hosted Cloudflare chat OpenAI usage is covered separately by feat(mcp): route hosted AI through OpenRouter with gpt-5.6-luna@medium #1213

Test plan

• pnpm --filter @sentry/mcp-server-evals exec tsc -b --force
• After secret is set, confirm Eval workflow can call OpenRouter successfully

Requested by Daniel Griesser.

--

View Junior Session Sentry

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 30f9fe2. Configure here.}