fix(provider): expose xhigh instead of max for GLM-5.2 on OpenAI-compatible

[bogerman1]

Issue for this PR

Closes #34278

Type of change

• Bug fix
• New feature
• Refactor / code improvement
• Documentation

What does this PR do?

GLM-5.2's native top reasoning tier is called max, but max is not in the OpenAI reasoning_effort enum (none/minimal/low/medium/high/xhigh). The OpenAI-compatible branch of variants() was exposing max directly, which:

• gets 400'd by spec-compliant upstreams (hyper, Cloudflare AI Gateway, OpenRouter passthrough) that reject reasoning_effort: "max",
• hides the actually-selectable xhigh tier from the TUI switcher.

The sibling OpenRouter branch already does the right thing (exposes xhigh, gateway translates to native max). This PR mirrors that for @ai-sdk/openai-compatible. The Anthropic branch is left alone since @ai-sdk/anthropic accepts max natively.

How did you verify your code works?

$ bun test test/provider/transform.test.ts
275 pass, 0 fail, 523 expect() calls

$ bun run typecheck
(tsgo --noEmit, clean)

$ oxlint packages/opencode/src/provider/transform.ts packages/opencode/test/provider/transform.test.ts
0 errors (143 pre-existing warnings unchanged)

Updated the three existing GLM-5.2 openai-compatible tests to expect xhigh instead of max.

Screenshots / recordings

N/A (no UI change — the variant list is rendered from the map this PR fixes).

Checklist

• I have tested my changes locally
• I have not included unrelated changes in this PR

[github-actions]

Automated PR Cleanup

Thank you for contributing to opencode.

Due to the high volume of PRs from users and AI agents, we periodically close older PRs using automated criteria so maintainers can focus review time on the most active and community-supported contributions.

This PR was closed because it matched the following cleanup criteria:

• The PR was created more than 1 month ago
• The PR had fewer than 2 positive reactions
• Positive reactions are counted as thumbs-up, heart, celebration, or rocket reactions on the PR

PRs created within the last month are not affected by this cleanup.

If you believe this PR was closed incorrectly, or if you are still actively working on it, please leave a comment explaining why it should be reopened. A maintainer can review and reopen it if appropriate.

Thanks again for taking the time to contribute.