[Feature]: Support assigning multiple models to a single Agent (Automatic Fallback / Failover)

[ciihom]

Prerequisites

• I will write this issue in English (see our Language Policy)
• I have searched existing issues and discussions to avoid duplicates
• This feature request is specific to oh-my-opencode (not OpenCode core)
• I have read the documentation or asked an AI coding agent with this project's GitHub URL loaded and couldn't find the answer

Problem Description

Currently, in oh-my-opencode (and the underlying OpenCode framework), the model field in an Agent's configuration only accepts a single string. This creates a bottleneck when the primary model's API experiences downtime, rate limiting (HTTP 429), or network timeouts. When this happens, the Agent simply fails, interrupting the workflow unless manually intervened.

Proposed Solution

我希望能够为单个代理分配一个模型数组，以实现自动故障转移。如果主模型发生故障或受到速率限制，代理应自动使用列表中的下一个模型重试请求。
{ "name": "my-smart-agent", "model": [ "anthropic/claude-opus-4-5", "google/gemini-3-pro", "openai/gpt-4o" ], "fallback_strategy": "on_error" // or "on_rate_limit" }

Alternatives Considered

No response

Doctor Output (Optional)

Additional Context

No response

Feature Type

Configuration Option

Contribution

• I'm willing to submit a PR for this feature
• I can help with testing
• I can help with documentation