🎞️ feat: OpenRouter Audio/Video File Upload Support (#11070)
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run

* Added video upload support for OpenRouter

- Added VIDEO_URL content type to support video_url message format
- Implemented OpenRouter video encoding using base64 data URLs
- Extended encodeAndFormatVideos() to handle OpenRouter provider
- Updated UI to accept video uploads for OpenRouter (mp4, webm, mpeg, mov)
- Fixed case-sensitivity in provider detection for agents
- Made isDocumentSupportedProvider() and isOpenAILikeProvider() case-insensitive

Videos are now converted to data:video/mp4;base64,... format compatible
with OpenRouter's API requirements per their documentation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* refactor: change multimodal and google_multimodal to more transparent variable names of image_document and image_document_video_audio

(also google_multimodal doesn't apply as much since we are adding support for video and audio uploads for open router)

* fix: revert .toLowerCase change to isOpenAILikeProvider and isDocumentSupportedProvider which broke upload to provider detection for openAI endpoints

* wip: add audio support to openrouter

* fix: filetypes now properly parsed and sent rather than destructured mimetypes for openrouter

* refactor: Omit to Exclude for ESLint

* feat: update DragDropModal for new openrouter support

* fix: special case openrouter for lower case provider

(currently getting issues with the provider coming in as 'OpenRouter' and our enum being 'openrouter') This will probably require a larger refactor later to handle case insensitivity for all providers, but that will have to be thoroughly tested in its own isolated PR

---------

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
This commit is contained in:
papasaidfine 2025-12-25 13:23:29 -05:00 committed by GitHub
parent 5caa008432
commit 4fe223eedd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 113 additions and 29 deletions

View file

@ -79,6 +79,21 @@ export async function encodeAndFormatAudios(
mimeType: file.type,
data: content,
});
} else if (provider === Providers.OPENROUTER) {
// Extract format from filename extension (e.g., 'audio.mp3' -> 'mp3')
// OpenRouter expects format values like: wav, mp3, aiff, aac, ogg, flac, m4a, pcm16, pcm24
// Note: MIME types don't always match (e.g., 'audio/mpeg' is mp3, not mpeg), so that is why we are using the file extension instead
const format = file.filename.split('.').pop()?.toLowerCase();
if (!format) {
throw new Error(`Could not extract audio format from filename: ${file.filename}`);
}
result.audios.push({
type: 'input_audio',
input_audio: {
data: content,
format,
},
});
}
result.files.push(metadata);

View file

@ -79,6 +79,13 @@ export async function encodeAndFormatVideos(
mimeType: file.type,
data: content,
});
} else if (provider === Providers.OPENROUTER) {
result.videos.push({
type: 'video_url',
video_url: {
url: `data:${file.type};base64,${content}`,
},
});
}
result.files.push(metadata);

View file

@ -29,12 +29,25 @@ export interface AudioProcessingResult {
bytes: number;
}
/** Google video block format */
export interface GoogleVideoBlock {
type: 'media';
mimeType: string;
data: string;
}
/** OpenRouter video block format */
export interface OpenRouterVideoBlock {
type: 'video_url';
video_url: {
url: string;
};
}
export type VideoBlock = GoogleVideoBlock | OpenRouterVideoBlock;
export interface VideoResult {
videos: Array<{
type: string;
mimeType: string;
data: string;
}>;
videos: VideoBlock[];
files: Array<{
file_id?: string;
temp_file_id?: string;
@ -100,12 +113,26 @@ export interface DocumentResult {
}>;
}
export interface AudioResult {
audios: Array<{
type: string;
mimeType: string;
/** Google audio block format */
export interface GoogleAudioBlock {
type: 'media';
mimeType: string;
data: string;
}
/** OpenRouter audio block format */
export interface OpenRouterAudioBlock {
type: 'input_audio';
input_audio: {
data: string;
}>;
format: string;
};
}
export type AudioBlock = GoogleAudioBlock | OpenRouterAudioBlock;
export interface AudioResult {
audios: AudioBlock[];
files: Array<{
file_id?: string;
temp_file_id?: string;