mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-05-14 16:38:40 +00:00
* 🌩️ feat: CloudFront CDN File Strategy + signed cookies Squashed from PR #12193: - feat(storage): add CloudFront CDN file strategy - feat(auth): add CloudFront signed cookie support Note: package.json/package-lock.json dependency additions are intentionally omitted from this commit and will be re-added via `npm install` after rebase to avoid lock-file merge conflicts. The two new peer deps that need to be re-installed are: - @aws-sdk/client-cloudfront@^3.1032.0 - @aws-sdk/cloudfront-signer@^3.1012.0 Also fixes 4 missing destructured names in AuthService.spec.js (getUserById, generateToken, generateRefreshToken, createSession) that were referenced in tests but not imported from the mocked '~/models'. * 📦 chore: install CloudFront SDK deps for PR #12193 Adds the two AWS CloudFront packages required by the rebased CloudFront CDN strategy: - @aws-sdk/client-cloudfront - @aws-sdk/cloudfront-signer Following the @aws-sdk/client-s3 pattern: - api/package.json: regular dependency (runtime resolution) - packages/api/package.json: peerDependency Generated by `npm install` against the freshly rebased lock file to avoid the merge conflicts that came from the original PR's lock-file edits being made against an older base of dev. * 🐛 fix: CI failures + review findings on CloudFront PR #12193 CI fixes - Rename packages/data-provider/src/__tests__/cloudfront-config.test.ts → src/cloudfront-config.spec.ts. Jest's default testMatch picks up __tests__/ directories even inside dist/, so the compiled .d.ts shell was being executed as an empty test suite. Moving to .spec.ts (matching the rest of the package) avoids the dist/ pickup. - Add cookieExpiry: 1800 to CloudFront crud.test makeConfig: the schema applies a default so CloudFrontFullConfig requires it. Review findings addressed - #1 (Codex + comprehensive): Normalize CloudFront domain with /\/+$/ regex (and key with /^\/+/ regex) in buildCloudFrontUrl, matching the cookie code so resource policy and file URLs stay aligned even when the configured domain has multiple trailing slashes. Added tests. - #2: Move DEFAULT_BASE_PATH out of s3Config into shared packages/api/src/storage/constants.ts. ImageService no longer imports S3-specific config. - #3: getCloudFrontConfig() returns Readonly<CloudFrontFullConfig> | null to discourage mutation of the cached signing config. - #4: Add cross-field refinement tests for cloudfrontConfigSchema (invalidateOnDelete-without-distributionId, imageSigning="cookies"-without-cookieDomain). - #6: Revert unrelated MCP comment re-indentation in librechat.example.yaml. - #7: Add azure_blob to the strategy list comment. Skipped - #5 (extractKeyFromS3Url with CloudFront URLs): existing deleteFileFromCloudFront tests already cover the path-equivalence assumption; renaming the helper is real refactor work beyond this PR's scope. - #8, #9 (NIT, low confidence): leaving for author judgement. * 🧹 chore: drop dead DEFAULT_BASE_PATH from s3Config test mock After moving DEFAULT_BASE_PATH to ~/storage/constants, crud.ts no longer reads it from s3Config — so the entry in the s3Config jest mock was misleading dead config. The tests still pass because the unmocked real constants module provides the value. --------- Co-authored-by: Danny Avila <danny@librechat.ai>
260 lines
7.8 KiB
JavaScript
260 lines
7.8 KiB
JavaScript
const axios = require('axios');
|
|
const { logger } = require('@librechat/data-schemas');
|
|
const { logAxiosError, validateImage } = require('@librechat/api');
|
|
const {
|
|
FileSources,
|
|
VisionModes,
|
|
ImageDetail,
|
|
ContentTypes,
|
|
EModelEndpoint,
|
|
mergeFileConfig,
|
|
getEndpointFileConfig,
|
|
} = require('librechat-data-provider');
|
|
const { getStrategyFunctions } = require('~/server/services/Files/strategies');
|
|
|
|
/**
|
|
* Converts a readable stream to a base64 encoded string.
|
|
*
|
|
* @param {NodeJS.ReadableStream} stream - The readable stream to convert.
|
|
* @param {boolean} [destroyStream=true] - Whether to destroy the stream after processing.
|
|
* @returns {Promise<string>} - Promise resolving to the base64 encoded content.
|
|
*/
|
|
async function streamToBase64(stream, destroyStream = true) {
|
|
return new Promise((resolve, reject) => {
|
|
const chunks = [];
|
|
|
|
stream.on('data', (chunk) => {
|
|
chunks.push(chunk);
|
|
});
|
|
|
|
stream.on('end', () => {
|
|
try {
|
|
const buffer = Buffer.concat(chunks);
|
|
const base64Data = buffer.toString('base64');
|
|
chunks.length = 0; // Clear the array
|
|
resolve(base64Data);
|
|
} catch (err) {
|
|
reject(err);
|
|
}
|
|
});
|
|
|
|
stream.on('error', (error) => {
|
|
chunks.length = 0;
|
|
reject(error);
|
|
});
|
|
}).finally(() => {
|
|
// Clean up the stream if required
|
|
if (destroyStream && stream.destroy && typeof stream.destroy === 'function') {
|
|
stream.destroy();
|
|
}
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Fetches an image from a URL and returns its base64 representation.
|
|
*
|
|
* @async
|
|
* @param {string} url The URL of the image.
|
|
* @returns {Promise<string>} The base64-encoded string of the image.
|
|
* @throws {Error} If there's an issue fetching the image or encoding it.
|
|
*/
|
|
async function fetchImageToBase64(url) {
|
|
try {
|
|
const response = await axios.get(url, {
|
|
responseType: 'arraybuffer',
|
|
});
|
|
const base64Data = Buffer.from(response.data).toString('base64');
|
|
response.data = null;
|
|
return base64Data;
|
|
} catch (error) {
|
|
const message = 'Error fetching image to convert to base64';
|
|
throw new Error(logAxiosError({ message, error }));
|
|
}
|
|
}
|
|
|
|
const base64Only = new Set([
|
|
EModelEndpoint.google,
|
|
EModelEndpoint.anthropic,
|
|
'Ollama',
|
|
'ollama',
|
|
EModelEndpoint.bedrock,
|
|
]);
|
|
|
|
const blobStorageSources = new Set([
|
|
FileSources.azure_blob,
|
|
FileSources.s3,
|
|
FileSources.firebase,
|
|
FileSources.cloudfront,
|
|
]);
|
|
|
|
/**
|
|
* Encodes and formats the given files.
|
|
* @param {ServerRequest} req - The request object.
|
|
* @param {Array<MongoFile>} files - The array of files to encode and format.
|
|
* @param {object} params - Object containing provider/endpoint information
|
|
* @param {Providers | EModelEndpoint | string} [params.provider] - The provider for the image
|
|
* @param {string} [params.endpoint] - Optional: The endpoint for the image
|
|
* @param {string} [mode] - Optional: The endpoint mode for the image.
|
|
* @returns {Promise<{ files: MongoFile[]; image_urls: MessageContentImageUrl[] }>} - A promise that resolves to the result object containing the encoded images and file details.
|
|
*/
|
|
async function encodeAndFormat(req, files, params, mode) {
|
|
const { provider, endpoint } = params;
|
|
const effectiveEndpoint = endpoint ?? provider;
|
|
const promises = [];
|
|
/** @type {Record<FileSources, Pick<ReturnType<typeof getStrategyFunctions>, 'prepareImagePayload' | 'getDownloadStream'>>} */
|
|
const encodingMethods = {};
|
|
/** @type {{ files: MongoFile[]; image_urls: MessageContentImageUrl[] }} */
|
|
const result = {
|
|
files: [],
|
|
image_urls: [],
|
|
};
|
|
|
|
if (!files || !files.length) {
|
|
return result;
|
|
}
|
|
|
|
for (let file of files) {
|
|
/** @type {FileSources} */
|
|
const source = file.source ?? FileSources.local;
|
|
|
|
if (!file.height) {
|
|
promises.push([file, null]);
|
|
continue;
|
|
}
|
|
|
|
if (!encodingMethods[source]) {
|
|
const { prepareImagePayload, getDownloadStream } = getStrategyFunctions(source);
|
|
if (!prepareImagePayload) {
|
|
throw new Error(`Encoding function not implemented for ${source}`);
|
|
}
|
|
|
|
encodingMethods[source] = { prepareImagePayload, getDownloadStream };
|
|
}
|
|
|
|
const preparePayload = encodingMethods[source].prepareImagePayload;
|
|
/* We need to fetch the image and convert it to base64 if we are using S3/Azure Blob/Firebase storage. */
|
|
if (blobStorageSources.has(source)) {
|
|
try {
|
|
const downloadStream = encodingMethods[source].getDownloadStream;
|
|
let stream = await downloadStream(req, file.filepath);
|
|
let base64Data = await streamToBase64(stream);
|
|
stream = null;
|
|
promises.push([file, base64Data]);
|
|
base64Data = null;
|
|
continue;
|
|
} catch (error) {
|
|
logger.error('Error processing image from blob storage:', error);
|
|
}
|
|
} else if (source !== FileSources.local && base64Only.has(effectiveEndpoint)) {
|
|
const [_file, imageURL] = await preparePayload(req, file);
|
|
promises.push([_file, await fetchImageToBase64(imageURL)]);
|
|
continue;
|
|
}
|
|
promises.push(preparePayload(req, file));
|
|
}
|
|
|
|
const detail = req.body.imageDetail ?? ImageDetail.auto;
|
|
|
|
/** @type {Array<[MongoFile, string]>} */
|
|
const formattedImages = await Promise.all(promises);
|
|
promises.length = 0;
|
|
|
|
/** Extract configured file size limit from fileConfig for this endpoint */
|
|
let configuredFileSizeLimit;
|
|
if (req.config?.fileConfig) {
|
|
const fileConfig = mergeFileConfig(req.config.fileConfig);
|
|
const endpointConfig = getEndpointFileConfig({
|
|
fileConfig,
|
|
endpoint: effectiveEndpoint,
|
|
});
|
|
configuredFileSizeLimit = endpointConfig?.fileSizeLimit;
|
|
}
|
|
|
|
for (const [file, imageContent] of formattedImages) {
|
|
const fileMetadata = {
|
|
type: file.type,
|
|
file_id: file.file_id,
|
|
filepath: file.filepath,
|
|
filename: file.filename,
|
|
embedded: !!file.embedded,
|
|
metadata: file.metadata,
|
|
};
|
|
|
|
if (file.height && file.width) {
|
|
fileMetadata.height = file.height;
|
|
fileMetadata.width = file.width;
|
|
}
|
|
|
|
if (!imageContent) {
|
|
result.files.push(fileMetadata);
|
|
continue;
|
|
}
|
|
|
|
/** Validate image buffer against size limits */
|
|
if (file.height && file.width) {
|
|
const imageBuffer = imageContent.startsWith('http')
|
|
? null
|
|
: Buffer.from(imageContent, 'base64');
|
|
|
|
if (imageBuffer) {
|
|
const validation = await validateImage(
|
|
imageBuffer,
|
|
imageBuffer.length,
|
|
effectiveEndpoint,
|
|
configuredFileSizeLimit,
|
|
);
|
|
|
|
if (!validation.isValid) {
|
|
throw new Error(`Image validation failed for ${file.filename}: ${validation.error}`);
|
|
}
|
|
}
|
|
}
|
|
|
|
const imagePart = {
|
|
type: ContentTypes.IMAGE_URL,
|
|
image_url: {
|
|
url: imageContent.startsWith('http')
|
|
? imageContent
|
|
: `data:${file.type};base64,${imageContent}`,
|
|
detail,
|
|
},
|
|
};
|
|
|
|
if (mode === VisionModes.agents) {
|
|
result.image_urls.push({ ...imagePart });
|
|
result.files.push({ ...fileMetadata });
|
|
continue;
|
|
}
|
|
|
|
if (
|
|
effectiveEndpoint &&
|
|
effectiveEndpoint === EModelEndpoint.google &&
|
|
mode === VisionModes.generative
|
|
) {
|
|
delete imagePart.image_url;
|
|
imagePart.inlineData = {
|
|
mimeType: file.type,
|
|
data: imageContent,
|
|
};
|
|
} else if (effectiveEndpoint && effectiveEndpoint === EModelEndpoint.google) {
|
|
imagePart.image_url = imagePart.image_url.url;
|
|
} else if (effectiveEndpoint && effectiveEndpoint === EModelEndpoint.anthropic) {
|
|
imagePart.type = 'image';
|
|
imagePart.source = {
|
|
type: 'base64',
|
|
media_type: file.type,
|
|
data: imageContent,
|
|
};
|
|
delete imagePart.image_url;
|
|
}
|
|
|
|
result.image_urls.push({ ...imagePart });
|
|
result.files.push({ ...fileMetadata });
|
|
}
|
|
formattedImages.length = 0;
|
|
return { ...result };
|
|
}
|
|
|
|
module.exports = {
|
|
encodeAndFormat,
|
|
};
|