@c4t4/heyamigo 0.8.2 → 0.8.4

package/config/memory-instructions.md

@@ -206,7 +206,7 @@ If you see `[Async tasks in progress]` in your preamble, a worker is already run
 
 ## Sending files
 
-To send a file (screenshot, image, video, PDF, audio) to the chat, save it to `storage/temp/` and include this tag in your reply:
+To send a file (screenshot, image, video, PDF, audio) to the chat, save it to `storage/outbox/` and include this tag in your reply:
 
 ```
 [FILE: /absolute/path/to/file.png]
@@ -216,7 +216,7 @@ Aliases (all behave the same): `[IMAGE: path]`, `[VIDEO: path]`, `[AUDIO: path]`
 
 Rules:
 - Always use absolute paths.
-- Always save under `storage/temp/`. Never save to the project root or anywhere else. Files are auto-deleted after sending.
+- Always save under `storage/outbox/`. Never save to the project root or anywhere else. Files are auto-deleted after sending.
 - Media type is detected from the file extension.
 - If you send a single file with a short text reply (under 1000 chars, non-audio), the text becomes the caption.
 
@@ -226,4 +226,4 @@ A shared Chrome runs on the server at `localhost:9222` with the owner's real ses
 
 **Never call `browser_*` / `mcp__*playwright*` tools inline.** All browser work goes via `[ASYNC-BROWSER:...]`. See the two-track section above.
 
-To send a screenshot back: the browser worker takes it (saving to `storage/temp/`), then includes `[IMAGE: /absolute/path.png]` in its result message.
+To send a screenshot back: the browser worker takes it (saving to `storage/outbox/`), then includes `[IMAGE: /absolute/path.png]` in its result message.

package/dist/gateway/outgoing.js

@@ -165,8 +165,10 @@ function compactTokens(n) {
     return `${Math.round(n / 1000)}k`;
 }
 // Proactive outbound: send a message to a chat without an incoming trigger.
-// Chunks, persists to the message log, never throws. Callers are responsible
-// for the canSendProactive() gate — this function does not re-check it.
+// Extracts [FILE:]/[IMAGE:]/etc tags the same way handleReply does — files
+// get sent as WhatsApp media, remaining text sent normally. Chunks, persists
+// to the message log, never throws. Callers are responsible for the
+// canSendProactive() gate — this function does not re-check it.
 export async function initiate(params) {
     const sock = getSocket();
     if (!sock) {
@@ -176,26 +178,68 @@ export async function initiate(params) {
     const raw = params.text.replaceAll('—', ', ').replaceAll('–', '-');
     if (!raw.trim())
         return false;
+    const { text, files } = extractFiles(raw);
     try {
-        const chunks = chunkText(raw, config.reply.chunkChars);
-        for (let i = 0; i < chunks.length; i++) {
-            const chunk = chunks[i];
-            await sendText(sock, params.jid, chunk);
+        // Send any files first — images, video, PDFs, audio, etc.
+        for (const filePath of files) {
+            const isFirst = filePath === files[0];
+            const mediaType = detectMediaType(filePath);
+            const supportsCaption = mediaType !== 'audio';
+            const caption = isFirst &&
+                text &&
+                text.length <= 1000 &&
+                files.length === 1 &&
+                supportsCaption
+                ? text
+                : undefined;
+            await sendFile(sock, params.jid, filePath, caption);
             await append({
-                id: `initiate-${Date.now()}-${i}`,
+                id: `initiate-file-${Date.now()}`,
                 jid: params.jid,
                 direction: 'out',
                 fromMe: true,
                 sender: sock.user?.id ?? '',
                 senderNumber: config.owner.number,
                 timestamp: Math.floor(Date.now() / 1000),
-                text: chunk,
-                messageType: 'conversation',
+                text: caption || `[${mediaType}: ${filePath}]`,
+                messageType: `${mediaType}Message`,
+                mediaPath: filePath,
+                mediaType,
             });
-            if (i < chunks.length - 1)
+            logger.info({ jid: params.jid, path: filePath, mediaType }, 'proactive file sent');
+            try {
+                unlinkSync(filePath);
+            }
+            catch { }
+            if (files.length > 1)
                 await sleep(config.reply.chunkDelayMs);
         }
-        logger.info({ jid: params.jid, chars: raw.length }, 'proactive message sent');
+        // Send text — skip only when it was used as the caption on a single file
+        const textAlreadySent = files.length === 1 &&
+            text &&
+            text.length <= 1000 &&
+            detectMediaType(files[0]) !== 'audio';
+        if (text && !textAlreadySent) {
+            const chunks = chunkText(text, config.reply.chunkChars);
+            for (let i = 0; i < chunks.length; i++) {
+                const chunk = chunks[i];
+                await sendText(sock, params.jid, chunk);
+                await append({
+                    id: `initiate-${Date.now()}-${i}`,
+                    jid: params.jid,
+                    direction: 'out',
+                    fromMe: true,
+                    sender: sock.user?.id ?? '',
+                    senderNumber: config.owner.number,
+                    timestamp: Math.floor(Date.now() / 1000),
+                    text: chunk,
+                    messageType: 'conversation',
+                });
+                if (i < chunks.length - 1)
+                    await sleep(config.reply.chunkDelayMs);
+            }
+        }
+        logger.info({ jid: params.jid, files: files.length, chars: text.length }, 'proactive message sent');
         return true;
     }
     catch (err) {

package/dist/memory/preamble.js

@@ -61,7 +61,7 @@ export function buildMemoryPreamble(params) {
         'The tag will be stripped from the message. Use absolute paths only.\n\n' +
         'Browser (Playwright MCP): a real Chrome at localhost:9222 with the owner\'s sessions logged in (TikTok, Instagram, etc.). DO NOT call browser tools yourself — they belong to the BROWSER TRACK, a parallel Claude worker with its own persistent session on that Chrome. ' +
         'When a request needs browser work: send a short ack AND append [ASYNC-BROWSER: <self-sufficient task description>] at the END of your reply. The browser worker picks it up, does the work in the logged-in Chrome, sends the result back to this chat as a new message. Single URL, quick check, full scrape — all go via [ASYNC-BROWSER:...]. No exceptions.\n\n' +
-        'File storage: if you need to save any files (screenshots, research, notes), always save them to storage/temp/. Never save files to the project root.');
+        'File storage: if you need to save files to send to the chat (screenshots, downloaded media), save them to storage/outbox/ — they auto-delete after send. For scratch/research/notes that should not be sent, use storage/temp/. Never save to the project root.');
     // Critical section
     sections.push(buildCriticalSection({
         senderNumber: params.senderNumber,

package/dist/store/media.js

@@ -24,13 +24,41 @@ export function detectMediaType(msg) {
         return null;
     return MEDIA_TYPES[type] ?? null;
 }
+// Baileys' extensionForMediaMessage throws when the media's mimetype is
+// undefined — happens on some forwarded documents (notably PDFs shared in
+// contexts that strip metadata). Fall back to the filename's extension,
+// then to .bin. Never throws.
+function resolveMediaExtension(msg) {
+    try {
+        const ext = extensionForMediaMessage(msg.message);
+        if (ext)
+            return ext;
+    }
+    catch {
+        // baileys tripped on missing mimetype — try fileName instead
+    }
+    const content = msg.message;
+    if (content) {
+        const type = getContentType(content);
+        if (type) {
+            const mediaMsg = content[type];
+            const fileName = mediaMsg?.fileName;
+            if (fileName) {
+                const m = fileName.match(/\.([a-zA-Z0-9]+)$/);
+                if (m && m[1])
+                    return m[1].toLowerCase();
+            }
+        }
+    }
+    return 'bin';
+}
 export async function downloadAndSave(msg, jid) {
     const mediaType = detectMediaType(msg);
     if (!mediaType)
         return null;
     try {
         const buffer = await downloadMediaMessage(msg, 'buffer', {});
-        const ext = extensionForMediaMessage(msg.message) || 'bin';
+        const ext = resolveMediaExtension(msg);
         const id = msg.key.id || `${Date.now()}`;
         const dir = mediaDir(jid);
         await mkdir(dir, { recursive: true });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@c4t4/heyamigo",
-  "version": "0.8.2",
+  "version": "0.8.4",
   "description": "WhatsApp AI bot powered by Claude with long-term memory, browser control, and role-based access",
   "type": "module",
   "main": "dist/index.js",