ModelOutputTruncatedError(
self,
truncation: OutputTruncation,
model: str | None = None,
*,
| Name | Type | Description |
|---|---|---|
truncation* | OutputTruncation | Why the provider stopped the reply. |
model | str | None | Default: NoneModel identifier, when known. |
no_usage | bool | Default: FalseThe provider reported zero tokens for the request, so the stated reason is likely not the real cause. |
has_reasoning | bool | Default: False |
invalid_tool_call | bool | Default: False |
| Name | Type |
|---|---|
| truncation | OutputTruncation |
| model | str | None |
| no_usage | bool |
| has_reasoning | bool |
| invalid_tool_call | bool |
The model stopped before it gave any reply.
Subclasses ValueError so that the LangGraph server keeps the message when
it serializes the error for the client. Other exception types are redacted
to "An internal error occurred".
The reply contained reasoning content.
The reply contains an unparseable tool call.