[codex] Add Claude Opus 4.8 support

[kousw]

Summary

• add Anthropic claude-opus-4-8 to the static model registry with 1M context, 128k output, and fast mode support
• route Opus 4.8 through adaptive thinking plus output_config.effort instead of legacy thinking budgets
• update focused tests and model reasoning docs/agent notes

Validation

• bun x biome format --write packages/core/src/models/anthropic.ts packages/runtime/src/model-reasoning.ts packages/runtime/tests/model-reasoning.test.ts packages/runtime/tests/model-fast.test.ts dev-docs/specs/model-parameter-ui.md packages/core/src/models/AGENTS.md
• bun test packages/runtime/tests/model-reasoning.test.ts packages/runtime/tests/model-fast.test.ts packages/runtime/tests/model-list-static.test.ts
• bun run --filter @codelia/runtime typecheck
• bun run --filter @codelia/core typecheck

[kousw]

@codex review

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9945538f76

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Preserve xhigh effort for Opus 4.8

When users select model.reasoning=xhigh for this newly added Opus 4.8 profile, resolveAnthropicReasoning keeps applied as xhigh but the adaptive-thinking branch then calls toAnthropicOutputEffort, which converts xhigh to max. Anthropic documents xhigh and max as distinct accepted effort values for Claude Opus 4.8 (https://platform.claude.com/docs/en/build-with-claude/effort), so this makes Codelia's xhigh setting run at the more expensive/deeper max level rather than the requested intermediate level.

Useful? React with 👍 / 👎.