feat: enhance model caching and output modalities handling

- Updated `refresh_models_cache` to include output modalities in the models cache.
- Added `get_model_output_modalities` function to retrieve output modalities for a specific model.
- Modified tests to cover new functionality for output modalities.
- Updated OpenRouter video generation functions to support audio generation and improved error handling.
- Enhanced dashboard to display generated images and videos.
- Refactored frontend templates to accommodate new data structures for generated content.
- Adjusted tests to validate changes in model handling and dashboard rendering.

Co-authored-by: Copilot <copilot@github.com>

backend/tests/test_ai.py

@@ -53,7 +53,7 @@ async def _user_token(client):
 async def test_list_models(client):
     token = await _user_token(client)
     with patch(
-        "backend.app.routers.ai.openrouter.list_models",
+        "app.routers.ai.openrouter.list_models",
         new_callable=AsyncMock,
         return_value=FAKE_MODELS,
     ):
@@ -74,7 +74,7 @@ async def test_list_models_unauthenticated(client):
 async def test_list_models_upstream_error(client):
     token = await _user_token(client)
     with patch(
-        "backend.app.routers.ai.openrouter.list_models",
+        "app.routers.ai.openrouter.list_models",
         new_callable=AsyncMock,
         side_effect=Exception("Connection refused"),
     ):
@@ -91,7 +91,7 @@ async def test_list_models_upstream_error(client):
 async def test_chat_success(client):
     token = await _user_token(client)
     with patch(
-        "backend.app.routers.ai.openrouter.chat_completion",
+        "app.routers.ai.openrouter.chat_completion",
         new_callable=AsyncMock,
         return_value=FAKE_CHAT_RESPONSE,
     ):
@@ -115,7 +115,7 @@ async def test_chat_success(client):
 async def test_chat_passes_parameters(client):
     token = await _user_token(client)
     mock = AsyncMock(return_value=FAKE_CHAT_RESPONSE)
-    with patch("backend.app.routers.ai.openrouter.chat_completion", new_callable=AsyncMock, return_value=FAKE_CHAT_RESPONSE) as mock:
+    with patch("app.routers.ai.openrouter.chat_completion", new_callable=AsyncMock, return_value=FAKE_CHAT_RESPONSE) as mock:
         await client.post(
             "/ai/chat",
             json={
@@ -145,7 +145,7 @@ async def test_chat_unauthenticated(client):
 async def test_chat_upstream_error(client):
     token = await _user_token(client)
     with patch(
-        "backend.app.routers.ai.openrouter.chat_completion",
+        "app.routers.ai.openrouter.chat_completion",
         new_callable=AsyncMock,
         side_effect=Exception("timeout"),
     ):
@@ -160,7 +160,7 @@ async def test_chat_upstream_error(client):
 async def test_chat_malformed_upstream_response(client):
     token = await _user_token(client)
     with patch(
-        "backend.app.routers.ai.openrouter.chat_completion",
+        "app.routers.ai.openrouter.chat_completion",
         new_callable=AsyncMock,
         return_value={"id": "x", "choices": []},  # empty choices
     ):