👤 feat: User Placeholder Variables for Custom Endpoint Headers (#7993)

* 🔧 refactor: move `processMCPEnv` from `librechat-data-provider` and move to `@librechat/api`

* 🔧 refactor: Update resolveHeaders import paths

* 🔧 refactor: Enhance resolveHeaders to support user and custom variables

- Updated resolveHeaders function to accept user and custom user variables for placeholder replacement.
- Modified header resolution in multiple client and controller files to utilize the enhanced resolveHeaders functionality.
- Added comprehensive tests for resolveHeaders to ensure correct processing of user and custom variables.

* 🔧 fix: Update user ID placeholder processing in env.ts

* 🔧 fix: Remove arguments passing this.user rather than req.user

- Updated multiple client and controller files to call resolveHeaders without the user parameter

* 🔧 refactor: Enhance processUserPlaceholders to be more readable / less nested

* 🔧 refactor: Update processUserPlaceholders to pass all tests in mpc.spec.ts and env.spec.ts

* chore: remove legacy ChatGPTClient

* chore: remove LLM initialization code

* chore: initial deprecation removal of `gptPlugins`

* chore: remove cohere-ai dependency from package.json and package-lock.json

* chore: update brace-expansion to version 2.0.2 and add license information

* chore: remove PluginsClient test file

* chore: remove legacy

* ci: remove deprecated sendMessage/getCompletion/chatCompletion tests

---------

Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
This commit is contained in:
Danny Avila 2025-06-23 12:39:27 -04:00 committed by GitHub
parent 01e9b196bc
commit a058963a9f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
30 changed files with 542 additions and 2844 deletions

View file

@ -531,44 +531,6 @@ describe('OpenAIClient', () => {
});
});
describe('sendMessage/getCompletion/chatCompletion', () => {
afterEach(() => {
delete process.env.AZURE_OPENAI_DEFAULT_MODEL;
delete process.env.AZURE_USE_MODEL_AS_DEPLOYMENT_NAME;
});
it('should call getCompletion and fetchEventSource when using a text/instruct model', async () => {
const model = 'text-davinci-003';
const onProgress = jest.fn().mockImplementation(() => ({}));
const testClient = new OpenAIClient('test-api-key', {
...defaultOptions,
modelOptions: { model },
});
const getCompletion = jest.spyOn(testClient, 'getCompletion');
await testClient.sendMessage('Hi mom!', { onProgress });
expect(getCompletion).toHaveBeenCalled();
expect(getCompletion.mock.calls.length).toBe(1);
expect(getCompletion.mock.calls[0][0]).toBe('||>User:\nHi mom!\n||>Assistant:\n');
expect(fetchEventSource).toHaveBeenCalled();
expect(fetchEventSource.mock.calls.length).toBe(1);
// Check if the first argument (url) is correct
const firstCallArgs = fetchEventSource.mock.calls[0];
const expectedURL = 'https://api.openai.com/v1/completions';
expect(firstCallArgs[0]).toBe(expectedURL);
const requestBody = JSON.parse(firstCallArgs[1].body);
expect(requestBody).toHaveProperty('model');
expect(requestBody.model).toBe(model);
});
});
describe('checkVisionRequest functionality', () => {
let client;
const attachments = [{ type: 'image/png' }];