From 3f22902423a6231df0c356cc0cddb6a5a20ec38b Mon Sep 17 00:00:00 2001
From: AJV20 <24819659+AJV20@users.noreply.github.com>
Date: Thu, 28 May 2026 08:40:51 -0400
Subject: [PATCH] fix: forward gateway image attachments

---
 CHANGELOG.md                             |  4 ++
 api/gateway_chat.py                      | 11 ++++-
 tests/test_webui_gateway_chat_backend.py | 55 ++++++++++++++++++++++++
 3 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index a990d204..293228bd 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,6 +3,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Gateway-backed WebUI chat now forwards current-turn image attachments as OpenAI-style multimodal `image_url` parts when native image input is enabled, matching the legacy WebUI runtime's image handoff.
+
 ## [v0.51.152] — 2026-05-28 — Release DX (stage-batch34 — single-PR optional gateway-backed browser chat)
 
 ### Added
diff --git a/api/gateway_chat.py b/api/gateway_chat.py
index 1c658abb..69e653ac 100644
--- a/api/gateway_chat.py
+++ b/api/gateway_chat.py
@@ -202,10 +202,19 @@ def _run_gateway_chat_streaming(
             # Scope Gateway long-term continuity to this WebUI conversation
             # without exposing the browser's auth cookie or CSRF material.
             headers["X-Hermes-Session-Key"] = f"webui:{session_id}"
+        message_content: Any = str(msg_text or "")
+        if attachments:
+            try:
+                from api.streaming import _build_native_multimodal_message
+
+                message_content = _build_native_multimodal_message("", str(msg_text or ""), attachments, str(workspace), cfg=cfg)
+            except Exception:
+                logger.debug("Failed to build gateway multimodal attachment payload", exc_info=True)
+                message_content = str(msg_text or "")
         body = {
             "model": model or "default",
             "stream": True,
-            "messages": [{"role": "user", "content": str(msg_text or "")}],
+            "messages": [{"role": "user", "content": message_content}],
         }
         if model_provider:
             body["provider"] = model_provider
diff --git a/tests/test_webui_gateway_chat_backend.py b/tests/test_webui_gateway_chat_backend.py
index e2bed326..f9c7f94d 100644
--- a/tests/test_webui_gateway_chat_backend.py
+++ b/tests/test_webui_gateway_chat_backend.py
@@ -1,4 +1,6 @@
 from collections import OrderedDict
+import base64
+import json
 
 import api.gateway_chat as gateway_chat
 import api.models as models
@@ -117,3 +119,56 @@ def test_gateway_chat_worker_translates_sse_and_persists_session(tmp_path, monke
     assert captured["headers"]["X-hermes-session-id"] == s.session_id
     assert captured["headers"]["X-hermes-session-key"] == f"webui:{s.session_id}"
     assert '"stream": true' in captured["body"]
+
+
+def test_gateway_chat_worker_forwards_image_attachments_as_multimodal_parts(tmp_path, monkeypatch):
+    session_dir = tmp_path / "sessions"
+    session_dir.mkdir()
+    monkeypatch.setattr(models, "SESSION_DIR", session_dir)
+    monkeypatch.setattr(models, "SESSION_INDEX_FILE", session_dir / "_index.json")
+    monkeypatch.setattr(models, "SESSIONS", OrderedDict())
+
+    image_bytes = base64.b64decode(
+        "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/x8AAwMCAO+/p9sAAAAASUVORK5CYII="
+    )
+    image_path = tmp_path / "photo.png"
+    image_path.write_bytes(image_bytes)
+    captured = {}
+
+    class FakeResponse:
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc, tb):
+            return False
+
+        def __iter__(self):
+            yield b'data: {"choices":[{"delta":{"content":"saw it"}}]}\n\n'
+            yield b'data: [DONE]\n\n'
+
+    def fake_urlopen(req, timeout=0):
+        captured["body"] = json.loads(req.data.decode("utf-8"))
+        return FakeResponse()
+
+    monkeypatch.setenv("HERMES_WEBUI_GATEWAY_BASE_URL", "http://gateway.local")
+    monkeypatch.setattr(gateway_chat.urllib.request, "urlopen", fake_urlopen)
+
+    s = new_session()
+    stream_id = "stream-gateway-image-test"
+    s.active_stream_id = stream_id
+    s.save()
+    STREAMS[stream_id] = create_stream_channel()
+
+    gateway_chat._run_gateway_chat_streaming(
+        s.session_id,
+        "What is in this image?",
+        "test-model",
+        str(tmp_path),
+        stream_id,
+        [{"path": str(image_path), "mime": "image/png", "is_image": True}],
+    )
+
+    content = captured["body"]["messages"][0]["content"]
+    assert content[0] == {"type": "text", "text": "What is in this image?"}
+    assert content[1]["type"] == "image_url"
+    assert content[1]["image_url"]["url"].startswith("data:image/png;base64,")