Skip to content

Streaming version of o3-mini #693

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

Merged
mrubens merged 1 commit into from
Jan 31, 2025
Merged

Streaming version of o3-mini #693

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
5 changes: 5 additions & 0 deletions .changeset/gold-pillows-fix.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"roo-cline": patch
---

Streaming version of o3-mini
31 changes: 29 additions & 2 deletions src/api/providers/openai-native.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,7 @@ export class OpenAiNativeHandler implements ApiHandler, SingleCompletionHandler
switch (modelId) {
case "o1":
case "o1-preview":
case "o1-mini":
case "o3-mini": {
case "o1-mini": {
// o1-preview and o1-mini don't support streaming, non-1 temp, or system prompt
// o1 doesnt support streaming or non-1 temp but does support a developer prompt
const response = await this.client.chat.completions.create({
Expand All @@ -49,6 +48,34 @@ export class OpenAiNativeHandler implements ApiHandler, SingleCompletionHandler
}
break
}
case "o3-mini": {
Copy link
Contributor

@ellipsis-dev ellipsis-dev bot Jan 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Consider using helper functions for the repeated logic of handling the stream and yielding results. This will reduce redundancy and improve readability. This is from our Development Standards: https://www.notion.so/Development-Standards-59febcf8ead647fd9c2ec3f60c22f3df?pvs=4#11869ad2d5818094a05ef707e188c0d5

const stream = await this.client.chat.completions.create({
model: this.getModel().id,
messages: [{ role: "developer", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
stream: true,
stream_options: { include_usage: true },
})

for await (const chunk of stream) {
const delta = chunk.choices[0]?.delta
if (delta?.content) {
yield {
type: "text",
text: delta.content,
}
}

// contains a null value except for the last chunk which contains the token usage statistics for the entire request
if (chunk.usage) {
yield {
type: "usage",
inputTokens: chunk.usage.prompt_tokens || 0,
outputTokens: chunk.usage.completion_tokens || 0,
}
}
}
break
}
default: {
const stream = await this.client.chat.completions.create({
model: this.getModel().id,
Expand Down
Loading