Ahmed Ibrahim 90ef94d3b3 Surface context window error to the client (#4675) ...

In the past, we were treating `input exceeded context window` as a
streaming error and retrying on it. Retrying on it has no point because
it won't change the behavior. In this PR, we surface the error to the
client without retry and also send a token count event to indicate that
the context window is full.

<img width="650" height="125" alt="image"
src="https://github.com/user-attachments/assets/c26b1213-4c27-4bfc-90f4-51a270a3efd5"
/>

2025-10-05 01:40:06 +00:00

..

compact.rs

Surface context window error to the client (#4675)

2025-10-05 01:40:06 +00:00