From 2ecdbc40766db5596d73b92c21fdf13c4fad4677 Mon Sep 17 00:00:00 2001
From: Seth Troisi <sethtroisi@google.com>
Date: Tue, 10 Nov 2026 10:37:08 -0800
Subject: [PATCH] fix: serialize format=json downloads

---
 docs/03_file_management.md |  4 ++--
 src/colab_cli/contents.py  |  3 +++
 tests/test_contents.py     | 37 +++++++++++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/docs/03_file_management.md b/docs/03_file_management.md
index be44c9e3..0a14d302 100644
--- a/docs/03_file_management.md
+++ b/docs/03_file_management.md
@@ -31,7 +31,7 @@ File management on the Colab VM will be implemented using the Jupyter Contents A
 ### 3. Downloading Files (`colab download`)
 - **API**: `GET /api/contents/<remote_path>?content=1` (as seen in HAR).
 - **Response**: JSON with `content` field.
-- **Handling**: Decodes content based on `format` (text or base64) and saves it locally.
+- **Handling**: Decodes content based on `format` (`base64`, `json`, or plain `text`) and saves it locally.
 
 ### 4. Deleting Files (`colab rm`)
 - **API**: `DELETE /api/contents/<remote_path>`.
@@ -59,4 +59,4 @@ TDD is mandatory for all file management features.
 
 ### 2. Error Cases
 - **Test Case**: Verify 404 responses are correctly caught and presented as a "File not found" error to the user.
-- **Test Case**: Verify correct handling of large file uploads exceeding API limits via kernel streaming.
\ No newline at end of file
+- **Test Case**: Verify correct handling of large file uploads exceeding API limits via kernel streaming.
diff --git a/src/colab_cli/contents.py b/src/colab_cli/contents.py
index 72d6d06c..d794b5cb 100644
--- a/src/colab_cli/contents.py
+++ b/src/colab_cli/contents.py
@@ -13,6 +13,7 @@
 # limitations under the License.
 
 import base64
+import json
 from urllib.parse import quote
 
 import requests
@@ -82,6 +83,8 @@ def download(self, remote_path: str, local_path: str):
 
         if fmt == "base64":
             content_bytes = base64.b64decode(content)
+        elif fmt == "json":
+            content_bytes = json.dumps(content, indent=2).encode("utf-8")
         else:
             # Assume text if it's not base64 explicitly encoded
             content_bytes = str(content).encode("utf-8")
diff --git a/tests/test_contents.py b/tests/test_contents.py
index 4c910c88..26d0f3c1 100644
--- a/tests/test_contents.py
+++ b/tests/test_contents.py
@@ -13,6 +13,7 @@
 # limitations under the License.
 
 import base64
+import json
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -123,6 +124,42 @@ def test_download_file(mock_request, client, tmp_path):
     assert local_file.read_bytes() == content_bytes
 
 
+@patch("colab_cli.contents.requests.request")
+def test_download_notebook_json_format(mock_request, client, tmp_path):
+    """Downloading a format=json payload serializes valid 2-space indented JSON."""
+    notebook_doc = {
+        "cells": [
+            {"cell_type": "markdown", "metadata": {}, "source": ["# Demo"]},
+            {
+                "cell_type": "code",
+                "execution_count": 1,
+                "metadata": {},
+                "outputs": [],
+                "source": ["x = 42\n", "print(x)"],
+            },
+        ],
+        "metadata": {"kernelspec": {"display_name": "Python 3", "name": "python3"}},
+        "nbformat": 4,
+        "nbformat_minor": 5,
+    }
+    mock_resp = MagicMock(spec=Response)
+    mock_resp.status_code = 200
+    mock_resp.json.return_value = {
+        "name": "demo.ipynb",
+        "type": "notebook",
+        "format": "json",
+        "content": notebook_doc,
+    }
+    mock_request.return_value = mock_resp
+
+    local_file = tmp_path / "demo.ipynb"
+    client.download("content/demo.ipynb", str(local_file))
+
+    raw = local_file.read_text(encoding="utf-8")
+    assert json.loads(raw) == notebook_doc
+    assert raw == json.dumps(notebook_doc, indent=2)
+
+
 @patch("colab_cli.contents.requests.request")
 def test_upload_file(mock_request, client, tmp_path):
     mock_resp = MagicMock(spec=Response)