feat: add pitrader_script step type + image vision for pipeline triggers

Add pitrader_script executor for running PITrader scripts (pi-scan,
playbook, execute_trades) as pipeline steps with vault credential
injection and JSON output capture.

Extend claude_prompt step with vision support (image_b64 in trigger
context). Add image pipeline trigger to on_image_message handler.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

bot.py

@@ -2123,6 +2123,15 @@ class Bot:
         if time.time() - server_ts > 30:
             return
 
+        # Check for pipeline file_upload triggers (before DM/mention check)
+        source = event.source or {}
+        content = source.get("content", {})
+        info = content.get("info", {})
+        img_mime = info.get("mimetype", "image/png")
+        img_filename = content.get("body", "image.png")
+        if self.cron_scheduler:
+            await self._check_pipeline_file_trigger(room, event, img_filename, img_mime)
+
         await self._load_room_settings(room.room_id)
 
         # In DMs respond to all images; in groups only if bot was recently @mentioned
@@ -2280,13 +2289,17 @@ class Bot:
             # Download file content for trigger data
             mxc_url = event.url if hasattr(event, "url") else None
             file_text = ""
+            image_b64 = ""
             if mxc_url:
                 try:
                     resp = await self.client.download(mxc=mxc_url)
                     if hasattr(resp, "body"):
                         file_bytes = resp.body
                         ext = os.path.splitext(filename.lower())[1]
-                        if ext == ".pdf":
+                        if mime_type.startswith("image/"):
+                            # Encode image as base64 for vision analysis in claude_prompt steps
+                            image_b64 = base64.b64encode(file_bytes).decode("utf-8")
+                        elif ext == ".pdf":
                             file_text = self._extract_pdf_text(file_bytes)
                         elif ext == ".docx":
                             file_text = self._extract_docx_text(file_bytes)
@@ -2301,6 +2314,7 @@ class Bot:
                 "filename": filename,
                 "mime_type": mime_type,
                 "file_content": file_text,
+                "image_b64": image_b64,
                 "sender": event.sender,
                 "room_id": room.room_id,
             }