feat: support attached images for all providers

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

View File

@@ -19,6 +19,7 @@ import path from 'path';
import { query } from '@anthropic-ai/claude-agent-sdk';
import { buildClaudeUserContent, normalizeImageDescriptors } from './shared/image-attachments.js';
import { CLAUDE_FALLBACK_MODELS } from './modules/providers/list/claude/claude-models.provider.js';
import { providerModelsService } from './modules/providers/services/provider-models.service.js';
import { resolveClaudeCodeExecutablePath } from './shared/claude-cli-path.js';
@@ -236,16 +237,13 @@ function mapCliOptionsToSDK(options = {}) {
* Adds a session to the active sessions map
* @param {string} sessionId - Session identifier
* @param {Object} queryInstance - SDK query instance
* @param {Array<string>} tempImagePaths - Temp image file paths for cleanup
* @param {string} tempDir - Temp directory for cleanup
* @param {Object} writer - WebSocket writer for reconnect support
*/
function addSession(sessionId, queryInstance, tempImagePaths = [], tempDir = null, writer = null) {
function addSession(sessionId, queryInstance, writer = null) {
activeSessions.set(sessionId, {
instance: queryInstance,
startTime: Date.now(),
status: 'active',
tempImagePaths,
tempDir,
writer
});
}
@@ -364,90 +362,35 @@ function extractTokenBudget(sdkMessage) {
}
/**
* Handles image processing for SDK queries
* Saves base64 images to temporary files and returns modified prompt with file paths
* @param {string} command - Original user prompt
* @param {Array} images - Array of image objects with base64 data
* @param {string} cwd - Working directory for temp file creation
* @returns {Promise<Object>} {modifiedCommand, tempImagePaths, tempDir}
* Builds the SDK `prompt` payload for one turn.
*
* Plain text turns pass the string through unchanged. Turns with image
* attachments use the SDK's streaming-input mode: a single SDKUserMessage
* whose content carries the prompt text plus one base64 `image` block per
* attachment (read from the global `~/.cloudcli/assets` folder).
*
* @param {string} command - User prompt
* @param {Array} images - Image descriptors ({ path, name?, mimeType? })
* @param {string} cwd - Project working directory image paths resolve against
* @returns {Promise<string|AsyncIterable>} SDK prompt payload
*/
async function handleImages(command, images, cwd) {
const tempImagePaths = [];
let tempDir = null;
if (!images || images.length === 0) {
return { modifiedCommand: command, tempImagePaths, tempDir };
async function buildPromptPayload(command, images, cwd) {
if (normalizeImageDescriptors(images).length === 0) {
return command;
}
try {
// Create temp directory in the project directory
const workingDir = cwd || process.cwd();
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,(.+)$/);
if (!matches) {
console.error('Invalid image data format');
continue;
}
const [, mimeType, base64Data] = matches;
const extension = mimeType.split('/')[1] || 'png';
const filename = `image_${index}.${extension}`;
const filepath = path.join(tempDir, filename);
// Write base64 data to file
await fs.writeFile(filepath, Buffer.from(base64Data, 'base64'));
tempImagePaths.push(filepath);
}
// Include the full image paths in the prompt
let modifiedCommand = command;
if (tempImagePaths.length > 0 && command && command.trim()) {
const imageNote = `\n\n[Images provided at the following paths:]\n${tempImagePaths.map((p, i) => `${i + 1}. ${p}`).join('\n')}`;
modifiedCommand = command + imageNote;
}
// Images processed
return { modifiedCommand, tempImagePaths, tempDir };
} catch (error) {
console.error('Error processing images for SDK:', error);
return { modifiedCommand: command, tempImagePaths, tempDir };
}
}
/**
* Cleans up temporary image files
* @param {Array<string>} tempImagePaths - Array of temp file paths to delete
* @param {string} tempDir - Temp directory to remove
*/
async function cleanupTempFiles(tempImagePaths, tempDir) {
if (!tempImagePaths || tempImagePaths.length === 0) {
return;
}
try {
// Delete individual temp files
for (const imagePath of tempImagePaths) {
await fs.unlink(imagePath).catch(err =>
console.error(`Failed to delete temp image ${imagePath}:`, err)
);
}
// Delete temp directory
if (tempDir) {
await fs.rm(tempDir, { recursive: true, force: true }).catch(err =>
console.error(`Failed to delete temp directory ${tempDir}:`, err)
);
}
// Temp files cleaned
} catch (error) {
console.error('Error during temp file cleanup:', error);
}
const content = await buildClaudeUserContent(command, images, cwd);
return (async function* () {
yield {
type: 'user',
message: {
role: 'user',
content
},
parent_tool_use_id: null,
timestamp: new Date().toISOString()
};
})();
}
/**
@@ -518,8 +461,6 @@ async function queryClaudeSDK(command, options = {}, ws) {
const { sessionId, sessionSummary } = options;
let capturedSessionId = sessionId;
let sessionCreatedSent = false;
let tempImagePaths = [];
let tempDir = null;
const emitNotification = (event) => {
notifyUserIfEnabled({
@@ -553,10 +494,10 @@ async function queryClaudeSDK(command, options = {}, ws) {
sdkOptions.mcpServers = mcpServers;
}
const imageResult = await handleImages(command, options.images, options.cwd);
const finalCommand = imageResult.modifiedCommand;
tempImagePaths = imageResult.tempImagePaths;
tempDir = imageResult.tempDir;
// Turns with image attachments switch to streaming input so the images
// ride along as real content blocks. Built per query attempt because an
// async generator cannot be replayed once consumed.
const createPrompt = () => buildPromptPayload(command, options.images, options.cwd);
sdkOptions.hooks = {
Notification: [{
@@ -663,7 +604,7 @@ async function queryClaudeSDK(command, options = {}, ws) {
let queryInstance;
try {
queryInstance = query({
prompt: finalCommand,
prompt: await createPrompt(),
options: sdkOptions
});
} catch (hookError) {
@@ -672,7 +613,7 @@ async function queryClaudeSDK(command, options = {}, ws) {
console.warn('Failed to initialize Claude query with hooks, retrying without hooks:', hookError?.message || hookError);
delete sdkOptions.hooks;
queryInstance = query({
prompt: finalCommand,
prompt: await createPrompt(),
options: sdkOptions
});
}
@@ -686,7 +627,7 @@ async function queryClaudeSDK(command, options = {}, ws) {
// Track the query instance for abort capability
if (capturedSessionId) {
addSession(capturedSessionId, queryInstance, tempImagePaths, tempDir, ws);
addSession(capturedSessionId, queryInstance, ws);
}
// Process streaming messages
@@ -696,7 +637,7 @@ async function queryClaudeSDK(command, options = {}, ws) {
if (message.session_id && !capturedSessionId) {
capturedSessionId = message.session_id;
addSession(capturedSessionId, queryInstance, tempImagePaths, tempDir, ws);
addSession(capturedSessionId, queryInstance, ws);
// Set session ID on writer
if (ws.setSessionId && typeof ws.setSessionId === 'function') {
@@ -738,9 +679,6 @@ async function queryClaudeSDK(command, options = {}, ws) {
removeSession(capturedSessionId);
}
// Clean up temporary image files
await cleanupTempFiles(tempImagePaths, tempDir);
// Send the terminal completion event — skipped for aborted runs, whose
// terminal `complete` (aborted: true) was already sent by abort-session.
const wasAborted = capturedSessionId ? abortedSessionIds.delete(capturedSessionId) : false;
@@ -764,9 +702,6 @@ async function queryClaudeSDK(command, options = {}, ws) {
removeSession(capturedSessionId);
}
// Clean up temporary image files on error
await cleanupTempFiles(tempImagePaths, tempDir);
const wasAborted = capturedSessionId ? abortedSessionIds.delete(capturedSessionId) : false;
if (wasAborted) {
// The abort already produced the terminal complete; a generator throw
@@ -819,9 +754,6 @@ async function abortClaudeSDKSession(sessionId) {
// Update session status
session.status = 'aborted';
// Clean up temporary image files
await cleanupTempFiles(session.tempImagePaths, session.tempDir);
// Clean up session
removeSession(sessionId);