94289d057e
A model the installed pi-ai catalog does not describe was reported as text-only with no way to say otherwise, so a vision model added through the custom-provider form was refused at every image admission point. The justification in the source described the DeepSeek chat-completions serializer, which does reject image blocks; the pi-ai request converter and every wire protocol it speaks carry images. Modalities now resolve entry `input` -> installed catalog entry -> route `defaultInput`, the chain the two capacity fallbacks already use, so the route value is a fallback and never narrows a catalog model. Its default stays `[text]`: nothing can interrogate a gateway for its modalities, and over-claiming admits an image the provider rejects mid-turn, after prompt admission has already committed the message. |
||
|---|---|---|
| .. | ||
| index.i18n.yaml | ||
| index.md | ||
| index.zh.md | ||
| providers-custom-form.png | ||
| providers-custom-form.zh.png | ||
| providers-models-page.png | ||
| providers-models-page.zh.png | ||
| providers.i18n.yaml | ||
| providers.md | ||
| providers.zh.md | ||
| python-sdk.i18n.yaml | ||
| python-sdk.md | ||
| python-sdk.zh.md | ||
