fix: use a valid default Qwen model for OrcaRouter

[nissrin2020ali-ux]

Why

When someone picks the OrcaRouter provider in the sidebar of Nebula AI and chooses a model from the built-in list, the default Qwen model — qwen/qianwen-3.8 — is not served by OrcaRouter anymore. Sending a request with it returns a 404 model_not_found error:

No available capacity for model qwen/qianwen-3.8 right now. Please try again later.

So a user who selects the Qwen entry in the Model ID dropdown hits an error on their first send, before they've even had a chance to try the app's streaming workflow.

What changed

src/App.tsx now lists qwen/qwen3.8-max as the Qwen default in ORCAROUTER_DEFAULT_MODELS instead of the stale qwen/qianwen-3.8. The other three defaults (orcarouter/auto, deepseek/deepseek-v4-pro, deepseek/deepseek-v4-flash) are unchanged and all resolve correctly.

Verification

• Live call to https://api.orcarouter.ai/v1/chat/completions with the new model → HTTP 200, content ok.
• The same call with the old model id → HTTP 404 model_not_found, confirming the defect.
• pnpm check (both tsconfigs) passes; vite build succeeds.

OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.

Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter

I'm an engineer on the OrcaRouter team.