Skip to content

fix: ensure prompt_tokens is always present in Anthropic streaming responses #1509

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vrushankportkey wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: ensure prompt_tokens is always present in Anthropic streaming responses #1509

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion src/providers/anthropic/chatComplete.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -731,8 +731,14 @@ export const getAnthropicStreamChunkTransform = (provider: string) => {

// final chunk
if (parsedChunk.type === 'message_delta' && parsedChunk.usage) {
// Use input_tokens from message_delta if not available from message_start
const promptTokens =
streamState?.usage?.prompt_tokens ??
parsedChunk.usage?.input_tokens ??
0;

const totalTokens =
(streamState?.usage?.prompt_tokens ?? 0) +
promptTokens +
(streamState?.usage?.cache_creation_input_tokens ?? 0) +
(streamState?.usage?.cache_read_input_tokens ?? 0) +
(parsedChunk.usage.output_tokens ?? 0);
Expand All @@ -755,6 +761,7 @@ export const getAnthropicStreamChunkTransform = (provider: string) => {
],
usage: {
...streamState.usage,
prompt_tokens: promptTokens,
completion_tokens: parsedChunk.usage?.output_tokens,
total_tokens: totalTokens,
prompt_tokens_details: {
Expand Down
7 changes: 6 additions & 1 deletion src/providers/google-vertex-ai/chatComplete.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1014,8 +1014,12 @@ export const VertexAnthropicChatCompleteStreamChunkTransform: (
}

if (parsedChunk.type === 'message_delta' && parsedChunk.usage) {
// Use input_tokens from message_delta if not available from message_start
const promptTokens =
streamState?.usage?.prompt_tokens ?? parsedChunk.usage?.input_tokens ?? 0;

const totalTokens =
(streamState?.usage?.prompt_tokens ?? 0) +
promptTokens +
(streamState?.usage?.cache_creation_input_tokens ?? 0) +
(streamState?.usage?.cache_read_input_tokens ?? 0) +
(parsedChunk.usage.output_tokens ?? 0);
Expand All @@ -1039,6 +1043,7 @@ export const VertexAnthropicChatCompleteStreamChunkTransform: (
],
usage: {
...streamState.usage,
prompt_tokens: promptTokens,
completion_tokens: parsedChunk.usage?.output_tokens,
total_tokens: totalTokens,
prompt_tokens_details: {
Expand Down