d8dfun/claudecodeui
1
0
Fork 0
mirror of https://github.com/siteboon/claudecodeui.git synced 2026-07-07 06:02:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: support attached images for all providers

Browse Source
This commit is contained in:
Haileyesus
2026-07-03 15:42:29 +03:00
parent 3ade1a1105
commit a253a2bda4
33 changed files with 1467 additions and 321 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
server/gemini-cli.js
View File

@@ -7,10 +7,11 @@ import crossSpawn from 'cross-spawn';
import sessionManager from './sessionManager.js';
import GeminiResponseHandler from './gemini-response-handler.js';
import { appendImagesInputTag } from './shared/image-attachments.js';
import { notifyRunFailed, notifyRunStopped } from './services/notification-orchestrator.js';
import { providerAuthService } from './modules/providers/services/provider-auth.service.js';
import { providerModelsService } from './modules/providers/services/provider-models.service.js';
import { createCompleteMessage, createNormalizedMessage } from './shared/utils.js';
import { createCompleteMessage, createNormalizedMessage, flattenPromptForWindowsShell } from './shared/utils.js';
// Use cross-spawn on Windows for correct .cmd resolution (same pattern as cursor-cli.js)
const spawnFunction = process.platform === 'win32' ? crossSpawn : spawn;
@@ -143,9 +144,17 @@ async function spawnGemini(command, options = {}, ws) {
// Build Gemini CLI command - start with print/resume flags first
const args = [];
// Image attachments ride along as an <images_input> path list appended to
// the prompt; session history readers strip the tag back out for display.
// gemini is a .cmd shim on Windows, so the whole argument must be
// newline-free or cmd.exe silently truncates it at the first newline.
const finalCommand = command && command.trim()
? flattenPromptForWindowsShell(appendImagesInputTag(command, images))
: command;
// Add prompt flag with command if we have a command
if (command && command.trim()) {
args.push('--prompt', command);
if (finalCommand && finalCommand.trim()) {
args.push('--prompt', finalCommand);
}
// If we have a sessionId, we want to resume
@@ -161,53 +170,6 @@ async function spawnGemini(command, options = {}, ws) {
const cleanPath = (cwd || projectPath || process.cwd()).replace(/[^\x20-\x7E]/g, '').trim();
const workingDir = cleanPath;
// Handle images by saving them to temporary files and passing paths to Gemini
const tempImagePaths = [];
let tempDir = null;
if (images && images.length > 0) {
try {
// Create temp directory in the project directory so Gemini can access it
tempDir = path.join(workingDir, '.tmp', 'images', Date.now().toString());
await fs.mkdir(tempDir, { recursive: true });
// Save each image to a temp file
for (const [index, image] of images.entries()) {
// Extract base64 data and mime type
const matches = image.data.match(/^data:([^;]+);base64,(.+)$/);
if (!matches) {
continue;
}
const [, mimeType, base64Data] = matches;
const extension = mimeType.split('/')[1] || 'png';
const filename = `image_${index}.${extension}`;
const filepath = path.join(tempDir, filename);
// Write base64 data to file
await fs.writeFile(filepath, Buffer.from(base64Data, 'base64'));
tempImagePaths.push(filepath);
}
// Include the full image paths in the prompt for Gemini to reference
// Gemini CLI can read images from file paths in the prompt
if (tempImagePaths.length > 0 && command && command.trim()) {
const imageNote = `\n\n[Images given: ${tempImagePaths.length} images are located at the following paths:]\n${tempImagePaths.map((p, i) => `${i + 1}. ${p}`).join('\n')}`;
const modifiedCommand = command + imageNote;
// Update the command in args
const promptIndex = args.indexOf('--prompt');
if (promptIndex !== -1 && args[promptIndex + 1] === command) {
args[promptIndex + 1] = modifiedCommand;
} else if (promptIndex !== -1) {
// If we're using context, update the full prompt
args[promptIndex + 1] = args[promptIndex + 1] + imageNote;
}
}
} catch (error) {
console.error('Error processing images for Gemini:', error);
}
}
// Add basic flags for Gemini
if (options.debug) {
args.push('--debug');
@@ -322,10 +284,6 @@ async function spawnGemini(command, options = {}, ws) {
});
};
// Attach temp file info to process for cleanup later
geminiProcess.tempImagePaths = tempImagePaths;
geminiProcess.tempDir = tempDir;
// Store process reference for potential abort
const processKey = capturedSessionId || sessionId || Date.now().toString();
activeGeminiProcesses.set(processKey, geminiProcess);
@@ -496,16 +454,6 @@ async function spawnGemini(command, options = {}, ws) {
ws.send(createCompleteMessage({ provider: 'gemini', sessionId: finalSessionId, exitCode: code }));
}
// Clean up temporary image files if any
if (geminiProcess.tempImagePaths && geminiProcess.tempImagePaths.length > 0) {
for (const imagePath of geminiProcess.tempImagePaths) {
await fs.unlink(imagePath).catch(err => { });
}
if (geminiProcess.tempDir) {
await fs.rm(geminiProcess.tempDir, { recursive: true, force: true }).catch(err => { });
}
}
if (code === 0) {
notifyTerminalState({ code });
resolve();