860d94732a
When a custom OpenAI-compatible provider uses a prefix that matches a built-in alias (e.g. 'ark' -> 'volcengine-ark'), resolveProviderAlias() converts it to the built-in provider ID, causing the provider-node matching logic to be skipped. The request is then routed to the wrong provider, resulting in a 404 model_not_found error. Fix: always check provider-node prefix matching using the original user input (parsed.providerAlias) before falling back to the resolved alias, regardless of whether resolveProviderAlias() transformed it. Co-authored-by: H1d3rOne <H1d3rOne@users.noreply.github.com> Made-with: Cursor |
||
|---|---|---|
| .. | ||
| app | ||
| i18n | ||
| lib | ||
| mitm | ||
| models | ||
| shared | ||
| sse | ||
| store | ||
| dashboardGuard.js | ||
| proxy.js | ||
| server-init.js | ||