📎 feat: Upload as Text Support for Plaintext, STT, RAG, and Token Limits (#8868)

* 🪶 feat: Add Support for Uploading Plaintext Files

feat: delineate between OCR and text handling in fileConfig field of config file

- also adds support for passing in mimetypes as just plain file extensions

feat: add showLabel bool to support future synthetic component DynamicDropdownInput

feat: add new combination dropdown-input component in params panel to support file type token limits

refactor: move hovercard to side to align with other hovercards

chore: clean up autogenerated comments

feat: add delineation to file upload path between text and ocr configured filetypes

feat: add token limit checks during file upload

refactor: move textParsing out of ocrEnabled logic

refactor: clean up types for filetype config

refactor: finish decoupling DynamicDropdownInput from fileTokenLimits

fix: move image token cost function into file to fix circular dependency causing unittest to fail and remove unused var for linter

chore: remove out of scope code following review

refactor: make fileTokenLimit conform to existing styles

chore: remove unused localization string

chore: undo changes to DynamicInput and other strays

feat: add fileTokenLimit to all provider config panels

fix: move textParsing back into ocr tool_resource block for now so that it doesn't interfere with other upload types

* 📤 feat: Add RAG API Endpoint Support for Text Parsing (#8849)

* feat: implement RAG API integration for text parsing with fallback to native parsing

* chore: remove TODO now that placeholder and fllback are implemented

* ✈️ refactor: Migrate Text Parsing to TS (#8892)

* refactor: move generateShortLivedToken to packages/api

* refactor: move textParsing logic into packages/api

* refactor: reduce nesting and dry code with createTextFile

* fix: add proper source handling

* fix: mock new parseText and parseTextNative functions in jest file

* ci: add test coverage for textParser

* 💬 feat: Add Audio File Support to Upload as Text (#8893)

* feat: add STT support for Upload as Text

* refactor: move processAudioFile to packages/api

* refactor: move textParsing from utils to files

* fix: remove audio/mp3 from unsupported mimetypes test since it is now supported

* ✂️ feat: Configurable File Token Limits and Truncation (#8911)

* feat: add configurable fileTokenLimit default value

* fix: add stt to fileConfig merge logic

* fix: add fileTokenLimit to mergeFileConfig logic so configurable value is actually respected from yaml

* feat: add token limiting to parsed text files

* fix: add extraction logic and update tests so fileTokenLimit isnt sent to LLM providers

* fix: address comments

* refactor: rename textTokenLimiter.ts to text.ts

* chore: update form-data package to address CVE-2025-7783 and update package-lock

* feat: use default supported mime types for ocr on frontend file validation

* fix: should be using logger.debug not console.debug

* fix: mock existsSync in text.spec.ts

* fix: mock logger rather than every one of its function calls

* fix: reorganize imports and streamline file upload processing logic

* refactor: update createTextFile function to use destructured parameters and improve readability

* chore: update file validation to use EToolResources for improved type safety

* chore: update import path for types in audio processing module

* fix: update file configuration access and replace console.debug with logger.debug for improved logging

---------

Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>

api/server/services/Files/images/encode.js

@@ -1,13 +1,16 @@
 const axios = require('axios');
-const { logAxiosError } = require('@librechat/api');
+const { logger } = require('@librechat/data-schemas');
+const { logAxiosError, processTextWithTokenLimit } = require('@librechat/api');
 const {
   FileSources,
   VisionModes,
   ImageDetail,
   ContentTypes,
   EModelEndpoint,
+  mergeFileConfig,
 } = require('librechat-data-provider');
 const { getStrategyFunctions } = require('~/server/services/Files/strategies');
+const countTokens = require('~/server/utils/countTokens');
 
 /**
  * Converts a readable stream to a base64 encoded string.
@@ -102,11 +105,28 @@ async function encodeAndFormat(req, files, endpoint, mode) {
     return result;
   }
 
+  const fileTokenLimit =
+    req.body?.fileTokenLimit ?? mergeFileConfig(req.config?.fileConfig).fileTokenLimit;
+
   for (let file of files) {
     /** @type {FileSources} */
     const source = file.source ?? FileSources.local;
     if (source === FileSources.text && file.text) {
-      result.text += `${!result.text ? 'Attached document(s):\n```md' : '\n\n---\n\n'}# "${file.filename}"\n${file.text}\n`;
+      let fileText = file.text;
+
+      const { text: limitedText, wasTruncated } = await processTextWithTokenLimit({
+        text: fileText,
+        tokenLimit: fileTokenLimit,
+        tokenCountFn: (text) => countTokens(text),
+      });
+
+      if (wasTruncated) {
+        logger.debug(
+          `[encodeAndFormat] Text content truncated for file: ${file.filename} due to token limits`,
+        );
+      }
+
+      result.text += `${!result.text ? 'Attached document(s):\n```md' : '\n\n---\n\n'}# "${file.filename}"\n${limitedText}\n`;
     }
 
     if (!file.height) {
@@ -135,7 +155,7 @@ async function encodeAndFormat(req, files, endpoint, mode) {
         base64Data = null;
         continue;
       } catch (error) {
-        // Error handling code
+        logger.error('Error processing image from blob storage:', error);
       }
     } else if (source !== FileSources.local && base64Only.has(endpoint)) {
       const [_file, imageURL] = await preparePayload(req, file);