Feature hasn't been suggested before.
Describe the enhancement you want to request
Sometimes I have a tool call by a subagent overflow context and get this message, e.g.
This model's maximum context length is 131072 tokens. However, you requested 137717 tokens (105717 in the messages, 32000 in the completion). Please reduce the length of the messages or completion.
In such a case the subagent stops execution, it would be great to allow the model to see that the tool call failed, and continue the subagent execution.
Feature hasn't been suggested before.
Describe the enhancement you want to request
Sometimes I have a tool call by a subagent overflow context and get this message, e.g.
This model's maximum context length is 131072 tokens. However, you requested 137717 tokens (105717 in the messages, 32000 in the completion). Please reduce the length of the messages or completion.In such a case the subagent stops execution, it would be great to allow the model to see that the tool call failed, and continue the subagent execution.