feat(chat): add optional photo upload support

Add vision/multimodal support to chat, allowing users to send images
alongside or instead of text prompts. Images are transmitted and persisted
as base64 data URLs.

Backend:
- Add Images []string to Message struct for persistence
- Add Images []string to GenerateTextRequest with relaxed validation
- Build multimodal user messages using OpenAI SDK content parts
- Pass images through from handlers to client
- Deep-copy Images slice in message cloning

Frontend:
- Add images?: string[] to Message and GenerateTextRequest types
- Add image selection state and file input handler
- Add camera icon button, hidden file input, and image preview strip
- Render images in user message bubbles
- Pass images through to GenerateTextRequest

Tests:
- Add TestSendMessageWithImage for vision model testing
This commit is contained in:
2026-05-01 18:27:09 -04:00
parent c51c0ab070
commit e60b1ea8d5
9 changed files with 150 additions and 13 deletions

View File

@@ -92,3 +92,35 @@ func TestSummarizeChat(t *testing.T) {
t.Logf("Output: %s", output)
}
}
func TestSendMessageWithImage(t *testing.T) {
t.Skip("requires live LLM API - run manually with: go test -run TestSendMessageWithImage ./internal/client/")
// Initialize Client
baseURL, err := url.Parse("https://llm-api.va.reichard.io/v1")
if err != nil {
t.Fatalf("Failed to parse base URL: %v", err)
}
client := NewClient(baseURL)
// Create Context
ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
defer cancel()
// Generate Text Stream
_, err = client.SendMessage(ctx, []*store.Message{{
Role: "user",
Content: "What is in this image?",
Images: []string{
"https://llm-api.va.reichard.io/v1/images/test.png",
},
}}, "vllm-qwen3-8b-vision", func(mc *MessageChunk) error {
if mc.Message != nil {
t.Logf("Received: %s", *mc.Message)
}
return nil
})
if err != nil {
t.Fatalf("Failed to generate text stream: %v", err)
}
}