omp-wechat 1.2.0 → 1.3.0

package/README.md

@@ -31,6 +31,7 @@ For boot-time persistence, install a launchd/systemd service via `/wechat instal
 - **Singleton**: port lock guarantees one poll loop across all concurrent OMP/Pi processes — no duplicate replies
 - **Failover**: 30s timer takes over automatically if the lock holder crashes
 - **Bidirectional**: receive and reply to WeChat text messages
+- **Image recognition**: inbound images are downloaded from WeChat CDN, AES-decrypted, and passed to the vision model
 - **Per-chat sessions**: each WeChat chat gets an independent AI session (concurrent, isolated)
 - **LRU pool**: caps memory usage by evicting least-recently-used sessions (default: 50)
 - **Typing indicator**: native WeChat "Typing..." shown during AI processing
@@ -108,6 +109,8 @@ systemPrompt: |
 | `systemPrompt` | Built-in | System prompt for WeChat chat sessions |
 
 > **Model and tools are managed by OMP/Pi.** `createAgentSession()` automatically calls `discoverAuthStorage()`, reusing your existing `omp login` / `pi login` OAuth, `~/.omp/agent/agent.db` API keys, or `models.yml` config. This project never touches API keys.
+>
+> **Image recognition** requires a vision model role configured in OMP (e.g. `omp model role vision xfyun/xopkimik25`). If no vision role is set, inbound images are skipped — only the text placeholder is sent to the AI.
 
 ## Slash Commands
 
@@ -188,11 +191,12 @@ OMP-Wechat/
 - **Reply-only**: iLink requires `context_token` from an inbound message; you cannot initiate conversations
 - **1:1 only**: iLink Bot API does not support group chats
 - **Single instance**: iLink allows only one bot connection per account
-- **Text only (Phase 1)**: images/voice/video are represented as `(image)` / `(voice)` placeholders; media support is planned
+- **Media**: inbound images are downloaded from WeChat CDN, AES-decrypted, and passed to the vision model (if `modelRoles.vision` is configured); voice/video remain as placeholders
 
 ## Roadmap
 
-- [ ] **Phase 2**: Media support (inbound images as base64, voice transcription)
+- [x] **Phase 2a**: Inbound image support (CDN download + AES decrypt + vision model)
+- [ ] **Phase 2b**: Voice transcription / video support
 - [x] **Phase 3**: Persistent sessions — `SessionManager.continueRecent()` per chat, context survives restarts
 - [x] **Phase 4**: Per-chat model selection — `/model` `/models` chat commands for manual switching
 - [ ] **Phase 5**: Fine-grained permissions (per-user tool restrictions, bash approval via WeChat)

package/dist/index.js

@@ -1322,7 +1322,7 @@ function saveSyncBuf(buf) {
   mkdirSync2(STATE_DIR, { recursive: true });
   writeFileSync(SYNC_BUF_FILE, buf);
 }
-function extractInboundText(msg) {
+function extractInboundText(msg, includeImagePlaceholder = true) {
   const items = msg.item_list ?? [];
   const parts = [];
   let imgCount = 0;
@@ -1346,9 +1346,9 @@ function extractInboundText(msg) {
         break;
     }
   }
-  if (imgCount > 0 && parts.length === 0) {
+  if (includeImagePlaceholder && imgCount > 0 && parts.length === 0) {
     parts.push(`(user sent ${imgCount} image${imgCount > 1 ? "s" : ""})`);
-  } else if (imgCount > 0) {
+  } else if (includeImagePlaceholder && imgCount > 0) {
     parts.push(`(+${imgCount} image${imgCount > 1 ? "s" : ""})`);
   }
   return parts.join(`
@@ -1758,17 +1758,15 @@ function decryptAesEcb(ciphertext, key) {
   const decipher = createDecipheriv("aes-128-ecb", key, null);
   return Buffer.concat([decipher.update(ciphertext), decipher.final()]);
 }
-function buildCdnUrl(fileUrl, fullUrl) {
+function buildCdnUrl(encryptQueryParam, fullUrl) {
   if (fullUrl)
     return fullUrl;
-  if (!fileUrl)
+  if (!encryptQueryParam)
     return null;
-  if (fileUrl.startsWith("http"))
-    return fileUrl;
-  return `${CDN_BASE_URL}/download?encrypted_query_param=${encodeURIComponent(fileUrl)}`;
+  return `${CDN_BASE_URL}/download?encrypted_query_param=${encodeURIComponent(encryptQueryParam)}`;
 }
-async function downloadAndDecrypt(fileUrl, fullUrl, aeskeyHex, aesKeyBase64, label = "media") {
-  const url = buildCdnUrl(fileUrl, fullUrl);
+async function downloadAndDecrypt(encryptQueryParam, fullUrl, aeskeyHex, aesKeyBase64, label = "media") {
+  const url = buildCdnUrl(encryptQueryParam, fullUrl);
   if (!url) {
     logger.warn(`[${label}] No CDN URL available`);
     return null;
@@ -2357,34 +2355,42 @@ class WeChatBridge {
     if (result.action === "pair") {
       if (contextToken) {
         const lead = result.isResend ? "Still waiting for pairing" : "Pairing required";
-        const text2 = `${lead} \u2014 approve in OMP with: /wechat pair ${result.code}`;
-        await sendMessage(creds, senderId, text2, contextToken).catch((err) => {
+        const text = `${lead} \u2014 approve in OMP with: /wechat pair ${result.code}`;
+        await sendMessage(creds, senderId, text, contextToken).catch((err) => {
           logger.warn("Pairing reply send failed:", err);
         });
       }
       return;
     }
-    const text = extractInboundText(msg);
-    if (!text)
+    if (!(msg.item_list ?? []).length)
       return;
-    const dedupKey = makeDedupKey(senderId, msg.create_time_ms, text);
+    const rawText = (msg.item_list ?? []).filter((item) => item.type === 1).map((item) => item.text_item?.text ?? "").filter(Boolean).join(`
+`);
+    const hasImages = (msg.item_list ?? []).some((item) => item.type === 2);
+    const dedupKey = makeDedupKey(senderId, msg.create_time_ms, rawText || "(image)");
     if (dedupKey && isDuplicate(dedupKey)) {
-      logger.info(`[${senderId}] Skipping duplicate message: ${text.slice(0, 80)}`);
+      logger.info(`[${senderId}] Skipping duplicate message: ${(rawText || "(image)").slice(0, 80)}`);
       return;
     }
     const config = loadConfig();
-    logger.info(`[${senderId}] Inbound (ts=${msg.create_time_ms ?? "n/a"}): ${text.slice(0, 80)}`);
-    const invocation = this.commands.tryParse(text);
-    if (invocation) {
-      const reply = await invocation.execute({ pool: this.pool, config, chatId: senderId }).catch((err) => `Command failed: ${err instanceof Error ? err.message : String(err)}`);
-      await sendMessage(creds, senderId, reply, contextToken).catch((err) => {
-        logger.warn(`[${senderId}] Command reply send failed:`, err);
-      });
-      return;
+    logger.info(`[${senderId}] Inbound (ts=${msg.create_time_ms ?? "n/a"}): ${(rawText || "(image)").slice(0, 80)}`);
+    if (rawText) {
+      const invocation = this.commands.tryParse(rawText);
+      if (invocation) {
+        const reply = await invocation.execute({ pool: this.pool, config, chatId: senderId }).catch((err) => `Command failed: ${err instanceof Error ? err.message : String(err)}`);
+        await sendMessage(creds, senderId, reply, contextToken).catch((err) => {
+          logger.warn(`[${senderId}] Command reply send failed:`, err);
+        });
+        return;
+      }
     }
     await sendTyping(creds, senderId, 1).catch(() => {});
     try {
       const session = await this.pool.ensure(senderId, contextToken, config);
+      const hasVision = session.supportsVision();
+      const text = extractInboundText(msg, !hasVision);
+      if (!text && !hasImages)
+        return;
       const images = await this.downloadImages(creds, msg, senderId);
       await session.prompt(text, images);
     } catch (err) {
@@ -2403,7 +2409,8 @@ class WeChatBridge {
     const results = [];
     for (const item of imageItems) {
       const img = item.image_item;
-      const buf = await downloadAndDecrypt(img.file_url, img.full_url, img.aeskey, img.aes_key ?? img.media?.aes_key, `image[${chatId}]`);
+      logger.debug(`[${chatId}] image_item raw: ${JSON.stringify(img)}`);
+      const buf = await downloadAndDecrypt(img.media?.encrypt_query_param, img.media?.full_url, img.aeskey, img.media?.aes_key, `image[${chatId}]`);
       if (buf) {
         const mimeType = buf.length > 4 && buf[0] === 137 && buf[1] === 80 ? "image/png" : "image/jpeg";
         results.push({

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omp-wechat",
-  "version": "1.2.0",
+  "version": "1.3.0",
   "description": "OMP/Pi extension: bridge WeChat messages to OMP's AI engine via the iLink Bot API",
   "type": "module",
   "main": "dist/index.js",