From 3133cc007937561da5bb12ca08a1a0ac21e56192 Mon Sep 17 00:00:00 2001
From: 1wos <1wosomm1@gmail.com>
Date: Thu, 14 May 2026 00:26:15 +0900
Subject: [PATCH] fix(tools): convert image/svg+xml to text in
 LoadArtifactsTool

Gemini rejects every SVG MIME variant with `400 INVALID_ARGUMENT -
Unsupported MIME type`, but `_is_inline_mime_type_supported` returns
True for `image/svg+xml` via the `image/` prefix match, so SVG
artifacts are forwarded as inline image data and crash the request.

Treat SVG the same way #4028 treats CSV / JSON / XML: text-decode it
and deliver it to the model as a text Part.

- Add `_GEMINI_UNSUPPORTED_INLINE_SUBTYPES = frozenset({'image/svg+xml'})`
  and short-circuit `_is_inline_mime_type_supported` so SVG falls
  through to `_as_safe_part_for_llm` instead of being forwarded inline.
- Add `image/svg+xml` to `_TEXT_LIKE_MIME_TYPES` so the fallback path
  utf-8 decodes the SVG markup instead of returning the binary
  placeholder text.
- Add `test_load_artifacts_converts_svg_to_text` mirroring the
  existing CSV test.

Verified against gemini-2.5-flash via google-genai 1.69.0: image/png,
image/jpeg, image/webp, image/avif, image/gif, audio/mpeg, audio/mp3,
video/mp4, video/webm, application/pdf all still accepted unchanged;
image/svg+xml now lands as a text Part rather than crashing.
---
 src/google/adk/tools/load_artifacts_tool.py   | 15 +++++++
 .../tools/test_load_artifacts_tool.py         | 43 +++++++++++++++++++
 2 files changed, 58 insertions(+)

diff --git a/src/google/adk/tools/load_artifacts_tool.py b/src/google/adk/tools/load_artifacts_tool.py
index ec717bad4c..0620797d75 100644
--- a/src/google/adk/tools/load_artifacts_tool.py
+++ b/src/google/adk/tools/load_artifacts_tool.py
@@ -35,10 +35,23 @@
     'video/',
 )
 _GEMINI_SUPPORTED_INLINE_MIME_TYPES = frozenset({'application/pdf'})
+# MIME subtypes that match a supported prefix above but that Gemini
+# rejects with 400 INVALID_ARGUMENT when sent as inline data. These
+# must fall through to the text-conversion path in
+# `_as_safe_part_for_llm` instead of being forwarded as inline image
+# data. Verified empirically against gemini-2.5-flash via
+# google-genai 1.69.0 on 2026-05-13.
+_GEMINI_UNSUPPORTED_INLINE_SUBTYPES = frozenset({
+    'image/svg+xml',
+})
 _TEXT_LIKE_MIME_TYPES = frozenset({
     'application/csv',
     'application/json',
     'application/xml',
+    # SVG is XML-based and Gemini rejects it as inline image data (see
+    # _GEMINI_UNSUPPORTED_INLINE_SUBTYPES above), so it falls through here
+    # and is delivered to the model as text.
+    'image/svg+xml',
 })
 
 if TYPE_CHECKING:
@@ -60,6 +73,8 @@ def _is_inline_mime_type_supported(mime_type: str | None) -> bool:
   normalized = _normalize_mime_type(mime_type)
   if not normalized:
     return False
+  if normalized in _GEMINI_UNSUPPORTED_INLINE_SUBTYPES:
+    return False
   return normalized.startswith(_GEMINI_SUPPORTED_INLINE_MIME_PREFIXES) or (
       normalized in _GEMINI_SUPPORTED_INLINE_MIME_TYPES
   )
diff --git a/tests/unittests/tools/test_load_artifacts_tool.py b/tests/unittests/tools/test_load_artifacts_tool.py
index 6a420574f0..c4fa71e676 100644
--- a/tests/unittests/tools/test_load_artifacts_tool.py
+++ b/tests/unittests/tools/test_load_artifacts_tool.py
@@ -144,6 +144,49 @@ async def test_load_artifacts_keeps_supported_mime_types():
   assert artifact_part.inline_data.mime_type == 'application/pdf'
 
 
+@mark.asyncio
+async def test_load_artifacts_converts_svg_to_text():
+  """`image/svg+xml` matches the `image/` prefix but is rejected by Gemini
+  with 400 INVALID_ARGUMENT, so it must fall through to the text-conversion
+  path instead of being forwarded as inline image data.
+  """
+  artifact_name = 'logo.svg'
+  svg_bytes = (
+      b'<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 10 10">'
+      b'<circle cx="5" cy="5" r="4"/></svg>'
+  )
+  artifact = types.Part(
+      inline_data=types.Blob(data=svg_bytes, mime_type='image/svg+xml')
+  )
+
+  tool_context = _StubToolContext({artifact_name: artifact})
+  llm_request = LlmRequest(
+      contents=[
+          types.Content(
+              role='user',
+              parts=[
+                  types.Part(
+                      function_response=types.FunctionResponse(
+                          name='load_artifacts',
+                          response={'artifact_names': [artifact_name]},
+                      )
+                  )
+              ],
+          )
+      ]
+  )
+
+  await load_artifacts_tool.process_llm_request(
+      tool_context=tool_context, llm_request=llm_request
+  )
+
+  artifact_part = llm_request.contents[-1].parts[1]
+  # The SVG must NOT be forwarded as inline image data — Gemini would 400.
+  assert artifact_part.inline_data is None
+  # And the original SVG markup is delivered as a text part instead.
+  assert artifact_part.text == svg_bytes.decode('utf-8')
+
+
 def test_maybe_base64_to_bytes_decodes_standard_base64():
   """Standard base64 encoded strings are decoded correctly."""
   original = b'hello world'