If a request falls back to another model, you now see the model that actually answered.
What's wrong with this entry?
When a request falls back to a different model mid-stream, the model shown to the client now matches the one that actually answered.
- A streamed content block of type "fallback" sets the accumulated message's model to the fallback target.
- The gateway's event re-encoder rewrites the model on the opening
message_startevent when an override model is in play.
content_block.type === "fallback"
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.234
Search field in the model picker
Both mention model
-
v2.1.236
Cancellable waits when
/modeltalks to a cloud sessionBoth mention model
-
v2.1.238
Model and effort switch warning now checks whether the cache is actually warm
Both mention model