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

@@ -2,6 +2,7 @@ package api
import (
"errors"
"slices"
"sync"
"github.com/google/uuid"
@@ -153,6 +154,7 @@ func cloneStoreMessage(msg *store.Message) *store.Message {
// Clone Message
cloned := *msg
cloned.Images = slices.Clone(msg.Images)
if msg.Stats != nil {
stats := *msg.Stats
cloned.Stats = &stats

View File

@@ -325,7 +325,7 @@ func (a *API) PostChat(w http.ResponseWriter, r *http.Request) {
}
// Start Message
chunk, err := a.startMessageGeneration(chat.ID, genReq.Model, genReq.Prompt)
chunk, err := a.startMessageGeneration(chat.ID, genReq.Model, genReq.Prompt, genReq.Images)
if err != nil {
log.WithError(err).WithField("chat_id", chat.ID).Error("failed to start message generation")
http.Error(w, "Failed to start message generation", http.StatusInternalServerError)
@@ -493,7 +493,7 @@ func (a *API) PostChatMessage(w http.ResponseWriter, r *http.Request) {
}
// Start Message
chunk, err := a.startMessageGeneration(chatID, genReq.Model, genReq.Prompt)
chunk, err := a.startMessageGeneration(chatID, genReq.Model, genReq.Prompt, genReq.Images)
if err != nil {
log.WithError(err).WithField("chat_id", chatID).Error("failed to start message generation")
if errors.Is(err, errGenerationActive) {
@@ -533,7 +533,7 @@ func (a *API) getClient() (*client.Client, error) {
return a.client, nil
}
func (a *API) startMessageGeneration(chatID uuid.UUID, chatModel, userMessage string) (*MessageChunk, error) {
func (a *API) startMessageGeneration(chatID uuid.UUID, chatModel, userMessage string, images []string) (*MessageChunk, error) {
apiClient, err := a.getClient()
if err != nil {
return nil, fmt.Errorf("failed to get client: %w", err)
@@ -548,7 +548,7 @@ func (a *API) startMessageGeneration(chatID uuid.UUID, chatModel, userMessage st
// persisted, preventing concurrent completions from creating duplicate rows.
if err := a.generationManager.start(chatID, func(_ *generation) error {
// Create User Message
userMsg = &store.Message{ChatID: chatID, Role: "user", Content: userMessage}
userMsg = &store.Message{ChatID: chatID, Role: "user", Content: userMessage, Images: images}
if err := a.store.SaveChatMessage(userMsg); err != nil {
return fmt.Errorf("failed to add user message to chat: %w", err)
}

View File

@@ -69,16 +69,17 @@ type ImageRecord struct {
}
type GenerateTextRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
Model string `json:"model"`
Prompt string `json:"prompt"`
Images []string `json:"images,omitempty"`
}
func (r *GenerateTextRequest) Validate() error {
if r.Model == "" {
return errors.New("model is required")
}
if r.Prompt == "" {
return errors.New("prompt is required")
if r.Prompt == "" && len(r.Images) == 0 {
return errors.New("prompt or images are required")
}
return nil
}