feat: add MIME plumbing for markdown (.md) format

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

package-lock.json

@@ -16,6 +16,7 @@
         "express-rate-limit": "^8.6.1",
         "file-type": "^22.0.1",
         "mammoth": "^1.12.0",
+        "markdown-it": "^15.0.0",
         "multer": "^2.2.0",
         "pdf-lib": "^1.17.1",
         "pdfjs-dist": "^6.2.108",
@@ -24,6 +25,7 @@
         "react": "^19.2.8",
         "react-dom": "^19.2.8",
         "sharp": "^0.35.3",
+        "turndown": "^7.2.4",
         "uuid": "^14.0.1"
       },
       "devDependencies": {
@@ -674,6 +676,12 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/@mixmark-io/domino": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/@mixmark-io/domino/-/domino-2.2.0.tgz",
+      "integrity": "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw==",
+      "license": "BSD-2-Clause"
+    },
     "node_modules/@napi-rs/canvas": {
       "version": "1.0.3",
       "resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-1.0.3.tgz",
@@ -2557,6 +2565,18 @@
         "node": ">= 0.8"
       }
     },
+    "node_modules/entities": {
+      "version": "8.0.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-8.0.0.tgz",
+      "integrity": "sha512-zwfzJecQ/Uej6tusMqwAqU/6KL2XaB2VZ2Jg54Je6ahNBGNH6Ek6g3jjNCF0fG9EWQKGZNddNjU5F1ZQn/sBnA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
     "node_modules/es-define-property": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
@@ -3663,6 +3683,25 @@
         "url": "https://github.com/sponsors/antonk52"
       }
     },
+    "node_modules/linkify-it": {
+      "version": "6.1.0",
+      "resolved": "https://registry.npmjs.org/linkify-it/-/linkify-it-6.1.0.tgz",
+      "integrity": "sha512-wJ/TwpSDTLepCrQoYWYIExIKg5Zchex2Nn5yk2mFnB+6PtdkHtyLx742md9csRjjOnGkKIS/RrbY7l8D6gT9Vw==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/puzrin"
+        },
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/markdown-it"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "uc.micro": "^3.0.0"
+      }
+    },
     "node_modules/lodash": {
       "version": "4.18.1",
       "resolved": "https://registry.npmjs.org/lodash/-/lodash-4.18.1.tgz",
@@ -3714,6 +3753,49 @@
         "node": ">=12.0.0"
       }
     },
+    "node_modules/markdown-it": {
+      "version": "15.0.0",
+      "resolved": "https://registry.npmjs.org/markdown-it/-/markdown-it-15.0.0.tgz",
+      "integrity": "sha512-Lf8ajvVNdRpzSNB4VegxNy7gjs8gU35l4b4+ET49LrQC5PKYwLZ72u60LeJ9gv3qiaesuYjJWCyVeQmv/QWKQw==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/puzrin"
+        },
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/markdown-it"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "argparse": "^3.0.0",
+        "entities": "^8.0.0",
+        "linkify-it": "^6.0.0",
+        "mdurl": "^2.1.0",
+        "punycode.js": "^2.3.1",
+        "uc.micro": "^3.0.0"
+      },
+      "bin": {
+        "markdown-it": "bin/markdown-it.mjs"
+      }
+    },
+    "node_modules/markdown-it/node_modules/argparse": {
+      "version": "3.0.0",
+      "resolved": "https://registry.npmjs.org/argparse/-/argparse-3.0.0.tgz",
+      "integrity": "sha512-BOp5NMrHqKxmq/OLr+clzzrRxgOKSLkcjmkWuChp7Irqwn4s74WjOBPIgWfA/HMcBnVkZ5XEuf9uUqzlpfCQ6A==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/puzrin"
+        },
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/nodeca"
+        }
+      ],
+      "license": "Python-2.0"
+    },
     "node_modules/math-intrinsics": {
       "version": "1.1.0",
       "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
@@ -3723,6 +3805,12 @@
         "node": ">= 0.4"
       }
     },
+    "node_modules/mdurl": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/mdurl/-/mdurl-2.1.0.tgz",
+      "integrity": "sha512-1+HBaOx0zi/dQWht8rNv9MYf9qqpqL/kxI0hXImU6Y547zM6Sni8BQibt7ifgMcYtQg41ao3Ivd6cnSM86inpg==",
+      "license": "MIT"
+    },
     "node_modules/media-typer": {
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/media-typer/-/media-typer-1.1.1.tgz",
@@ -4488,6 +4576,15 @@
         "node": ">= 0.10"
       }
     },
+    "node_modules/punycode.js": {
+      "version": "2.3.1",
+      "resolved": "https://registry.npmjs.org/punycode.js/-/punycode.js-2.3.1.tgz",
+      "integrity": "sha512-uxFIHU0YlHYhDQtV4R9J6a52SLx28BCjT+4ieh7IGbgwVJWO+km431c4yRlREUAsAmt/uMjQUyQHNEPf0M39CA==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/puppeteer": {
       "version": "25.4.0",
       "resolved": "https://registry.npmjs.org/puppeteer/-/puppeteer-25.4.0.tgz",
@@ -5226,6 +5323,19 @@
       "integrity": "sha512-Xni35NKzjgMrwevysHTCArtLDpPvye8zV/0E4EyYn43P7/7qvQwPh9BGkHewbMulVntbigmcT7rdX3BNo9wRJg==",
       "license": "0BSD"
     },
+    "node_modules/turndown": {
+      "version": "7.2.4",
+      "resolved": "https://registry.npmjs.org/turndown/-/turndown-7.2.4.tgz",
+      "integrity": "sha512-I8yFsfRzmzK0WV1pNNOA4A7y4RDfFxPRxb3t+e3ui14qSGOxGtiSP6GjeX+Y6CHb7HYaFj7ECUD7VE5kQMZWGQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@mixmark-io/domino": "^2.2.0"
+      },
+      "engines": {
+        "node": ">=18",
+        "npm": ">=9"
+      }
+    },
     "node_modules/tv4": {
       "version": "1.3.0",
       "resolved": "https://registry.npmjs.org/tv4/-/tv4-1.3.0.tgz",
@@ -5296,6 +5406,12 @@
       "integrity": "sha512-/aCDEGatGvZ2BIk+HmLf4ifCJFwvKFNb9/JeZPMulfgFracn9QFcAf5GO8B/mweUjSoblS5In0cWhqpfs/5PQA==",
       "license": "MIT"
     },
+    "node_modules/uc.micro": {
+      "version": "3.0.0",
+      "resolved": "https://registry.npmjs.org/uc.micro/-/uc.micro-3.0.0.tgz",
+      "integrity": "sha512-U3PppEkleoTnIfi8BozMx3yju3qc/L6SwqWo2Sw+54PX+PX0q9I+r1Um5HCmqD7n9VDX5/v3vQH/AjA6deDdtw==",
+      "license": "MIT"
+    },
     "node_modules/uint8array-extras": {
       "version": "1.5.0",
       "resolved": "https://registry.npmjs.org/uint8array-extras/-/uint8array-extras-1.5.0.tgz",

package.json

@@ -19,6 +19,7 @@
     "express-rate-limit": "^8.6.1",
     "file-type": "^22.0.1",
     "mammoth": "^1.12.0",
+    "markdown-it": "^15.0.0",
     "multer": "^2.2.0",
     "pdf-lib": "^1.17.1",
     "pdfjs-dist": "^6.2.108",
@@ -27,6 +28,7 @@
     "react": "^19.2.8",
     "react-dom": "^19.2.8",
     "sharp": "^0.35.3",
+    "turndown": "^7.2.4",
     "uuid": "^14.0.1"
   },
   "devDependencies": {

src/mime.js

@@ -13,6 +13,7 @@ const OUTPUT_MIME_TYPES = {
   html: 'text/html',
   txt: 'text/plain',
   docx: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+  md: 'text/markdown',
 };
 
 export async function detectInputMime(filePath) {
@@ -31,6 +32,7 @@ export function outputMimeType(targetFormat) {
 const UNDETECTABLE_TEXT_FORMATS = {
   txt: 'text/plain',
   html: 'text/html',
+  md: 'text/markdown',
 };
 
 function normalizeFormat(format) {

test/mime.test.js

@@ -20,6 +20,7 @@ describe('outputMimeType', () => {
     expect(outputMimeType('docx')).toBe(
       'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
     );
+    expect(outputMimeType('md')).toBe('text/markdown');
   });
 
   it('throws for an unknown target format', () => {
@@ -61,6 +62,17 @@ describe('resolveInputFormat', () => {
     await fs.unlink(fixturePath);
   });
 
+  it('trusts the declared format for undetectable md files', async () => {
+    const fixturePath = path.join(import.meta.dirname, 'fixtures', 'sample.md');
+    await fs.writeFile(fixturePath, '# plain markdown, no magic bytes');
+
+    const result = await resolveInputFormat(fixturePath, 'md');
+
+    expect(result).toEqual({ mime: 'text/markdown', valid: true });
+
+    await fs.unlink(fixturePath);
+  });
+
   it('rejects an undetectable file declared as a binary format', async () => {
     const fixturePath = path.join(import.meta.dirname, 'fixtures', 'sample-fake.png');
     await fs.writeFile(fixturePath, 'this is not really a PNG');