Workaround model bug where it returns invalid history items.
- Currently there's a bug in the API (or SDK?) where the SDK endpoint will commonly fail with: ``` Error: Failed to generate JSON content: got status: 400 Bad Request. {"error":{"code":400,"message":"* GenerateContentRequest.contents[5].parts: contents.parts must not be empty.\n","status":"INVALID_ARGUMENT"}} ``` - At times the model will respond with an empty parts list where if we send that back up to the API endpoint it explodes with the above. Using a curated history seems like a total hack around this prolbem, and even in the SDK (i'm following up on this), BUT helps mitigate this issue.
This commit is contained in:
parent
cf91f72c5c
commit
4d5f0dc080
|
@ -60,7 +60,12 @@ export async function checkNextSpeaker(
|
||||||
chat: Chat,
|
chat: Chat,
|
||||||
geminiClient: GeminiClient,
|
geminiClient: GeminiClient,
|
||||||
): Promise<NextSpeakerResponse | null> {
|
): Promise<NextSpeakerResponse | null> {
|
||||||
const history = await chat.getHistory();
|
// We need to capture the curated history because there are many moments when the model will return invalid turns
|
||||||
|
// that when passed back up to the endpoint will break subsequent calls. An example of this is when the model decides
|
||||||
|
// to respond with an empty part collection if you were to send that message back to the server it will respond with
|
||||||
|
// a 400 indicating that model part collections MUST have content.
|
||||||
|
const history = await chat.getHistory(/* curated */ true);
|
||||||
|
|
||||||
// Ensure there's a model response to analyze
|
// Ensure there's a model response to analyze
|
||||||
if (history.length === 0 || history[history.length - 1].role !== 'model') {
|
if (history.length === 0 || history[history.length - 1].role !== 'model') {
|
||||||
// Cannot determine next speaker if the last turn wasn't from the model
|
// Cannot determine next speaker if the last turn wasn't from the model
|
||||||
|
|
Loading…
Reference in New Issue