Skip to content

Openrouter user #4482

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
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Openrouter user #4482

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
831236a
feat[openrouter]: add openrouter user tracking
VAIBHAVSING Oct 3, 2025
6d4cc6c
feat : refractor code
VAIBHAVSING Oct 3, 2025
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: 7 additions & 2 deletions server/utils/AiProviders/openRouter/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,7 +238,7 @@ class OpenRouterLLM {
];
}

async getChatCompletion(messages = null, { temperature = 0.7 }) {
async getChatCompletion(messages = null, { temperature = 0.7, user = null }) {
if (!(await this.isValidChatCompletionModel(this.model)))
throw new Error(
`OpenRouter chat: ${this.model} is not valid for chat completion!`
Expand All @@ -253,6 +253,9 @@ class OpenRouterLLM {
// This is an OpenRouter specific option that allows us to get the reasoning text
// before the token text.
include_reasoning: true,
// Add user tracking if user information is available
// This enables OpenRouter's user tracking features for multi-user systems
...(user ? { user } : {}),
})
.catch((e) => {
throw new Error(e.message);
Expand Down Expand Up @@ -294,8 +297,10 @@ class OpenRouterLLM {
// This is an OpenRouter specific option that allows us to get the reasoning text
// before the token text.
include_reasoning: true,
// Add user tracking if user information is available
// This enables OpenRouter's user tracking features for multi-user systems
...(user ? { user } : {}),
}),
messages
// We have to manually count the tokens
// OpenRouter has a ton of providers and they all can return slightly differently
// some return chunk.usage on STOP, some do it after stop, its inconsistent.
Expand Down
3 changes: 3 additions & 0 deletions server/utils/chats/apiChatHandler.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,6 +307,7 @@ async function chatSync({
const { textResponse, metrics: performanceMetrics } =
await LLMConnector.getChatCompletion(messages, {
temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
user,
});

if (!textResponse) {
Expand Down Expand Up @@ -649,6 +650,7 @@ async function streamChat({
const { textResponse, metrics: performanceMetrics } =
await LLMConnector.getChatCompletion(messages, {
temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
user,
});
completeText = textResponse;
metrics = performanceMetrics;
Expand All @@ -664,6 +666,7 @@ async function streamChat({
} else {
const stream = await LLMConnector.streamGetChatCompletion(messages, {
temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
user,
});
completeText = await LLMConnector.handleStream(response, stream, { uuid });
metrics = stream.metrics;
Expand Down
2 changes: 2 additions & 0 deletions server/utils/chats/stream.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,6 +248,7 @@ async function streamChatWithWorkspace(
const { textResponse, metrics: performanceMetrics } =
await LLMConnector.getChatCompletion(messages, {
temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
user,
});

completeText = textResponse;
Expand All @@ -264,6 +265,7 @@ async function streamChatWithWorkspace(
} else {
const stream = await LLMConnector.streamGetChatCompletion(messages, {
temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
user,
});
completeText = await LLMConnector.handleStream(response, stream, {
uuid,
Expand Down