[Feature]: Show the actual model used behind OpenCode aliases

[KarmCraft]

Before submitting

• I searched existing issues and did not find a duplicate.
• I am describing a concrete problem or use case, not just a vague idea.

Area

apps/server

Problem or use case

OpenCode can expose an alias such as auto while a router chooses a different backend model for each turn. T3 only retains the alias, so I cannot see which model actually answered.

Related to #2481, but the selected model and the routed model are not the same. #5699 also touches provenance, for externally appended messages rather than provider responses.

Proposed solution

Let provider adapters attach optional, safe per-message metadata for the actual model, then show it in a small assistant-message footer, for example: OpenCode · auto → GPT-5.6 Luna · high.

If the provider does not expose this metadata, keep the current UI unchanged.

Why this matters

With dynamic routing, model attribution is needed to understand quality, latency, and cost without asking the assistant after every turn.

Smallest useful scope

Support optional actual-model metadata for OpenCode assistant messages and render it on web.

Contribution

• I would be open to helping implement this.

[KarmCraft]

I refreshed T3 PR #6551 against current main; it is conflict-free and its focused checks pass. Its upstream dependency, OpenCode PR anomalyco/opencode#42433, is also current with dev. We are now waiting for the OpenCode maintainers' status and merge before this can move forward on the T3 side.

[pantharshit007]

Whoever picks this, also resolve this issue.
If you are connected to multiple provider for example: Github copilot, XAI and OpenRouter, and I am using Grok model, I have no idea to know which provider is powering this session: is it my XAI subscription or my Copilot one or is it my api pricing based openrouter one.