fix: retry overloaded OpenAI stream errors

[marcusquinn]

Summary

• Classify OpenAI service_unavailable_error / server_is_overloaded stream chunks as retryable API errors.
• Add regression coverage for the overloaded Responses SSE error shape so sessions use the existing retry path instead of surfacing a terminal error.

Fixes #25731

Verification

• git diff --check -- packages/opencode/src/provider/error.ts packages/opencode/test/session/retry.test.ts
• bun test test/session/retry.test.ts from packages/opencode was attempted but blocked in this worktree by missing preload dependency: @opentui/solid/preload.

---

aidevops.sh v3.14.42 plugin for OpenCode v1.14.33 with gpt-5.5 spent 1h 2m and 681,876 tokens on this with the user in an interactive session.

[github-actions]

This PR doesn't fully meet our contributing guidelines and PR template.

What needs to be fixed:

• PR description is missing required template sections. Please use the PR template.

Please edit this PR description to address the above within 2 hours, or it will be automatically closed.

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

I found a related PR that should be checked:

fix(session): retry Codex server_is_overloaded stream errors (PR #25728)

This PR addresses a very similar issue - handling server_is_overloaded stream errors as retryable, but for Codex. Since PR #25732 is doing the same thing for OpenAI, these two PRs should be reviewed together to ensure consistent error handling patterns across providers.

[github-actions]

This pull request has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new pull request that follows our guidelines.