Add direct MiniMax provider models

[octo-patch]

Reason: add target provider/model to existing provider registry

Add direct MiniMax model entries for the global and China OpenAI-compatible endpoints and a separate region-selectable Anthropic-compatible OpenCode provider. The registry exposes MiniMax-M3 and MiniMax-M2.7 with their supported modalities, reasoning capability, context limits, output limits, and pricing metadata. Deployment documentation also covers the Anthropic-compatible Claude runtime and the complete tiered pricing schedule. Existing defaults remain unchanged.

Validation:

• AGENTFIELD_SERVER=http://localhost:9999 python -m pytest -q tests/test_minimax_provider_config.py
• ruff check tests/test_minimax_provider_config.py
• python -m compileall -q swe_af
• jq empty opencode.json
• git diff --check
• OpenCode model-listing checks for all three direct providers.
• Local request-capture checks for the global and China Chat Completions paths and the Anthropic Messages path.

[CLAassistant]

All committers have signed the CLA.

[octo-patch]

I added a separate minimax-anthropic OpenCode provider so the built-in minimax catalog remains unchanged, added the target model limits and complete tiered pricing documentation, and expanded the focused tests. I ran the focused pytest suite, Ruff, compileall, JSON and diff checks, model-listing checks, and local request captures for both Chat Completions regions and the Anthropic Messages path.

[octo-patch]

Thanks for the review. I merged the latest main branch, preserved the MiniMax provider configuration while adopting the updated optional GitHub token manifest behavior, and pushed a new commit. I ran the focused MiniMax pytest suite (6 passed), Ruff, YAML and JSON parsing, and git diff checks.