image input pipeline: content-hash cache, data-url vision, picture_edit real

fjerkroa_bot/ai_responder.py

@@ -12,6 +12,7 @@ from pathlib import Path
 from pprint import pformat
 from typing import Any, Dict, List, Optional, Tuple, Union
 
+from .images import ImageCache
 from .memory import MemoryManager
 from .persistence import PersistentStore
 
@@ -153,17 +154,16 @@ class AIResponder(AIResponderBase):
             if stored_memory is not None:
                 self.memory = stored_memory
         self.memory_manager = MemoryManager(self.store, lambda: self.config, self.consolidate, self.channel)
+        self.image_cache: Optional[ImageCache] = None
+        if self.store is not None:
+            self.image_cache = ImageCache(self.store, Path(self.config["history-directory"]).expanduser() / "images", lambda: self.config)
         logging.info(f"memmory:\n{self.memory}")
 
     # Dynamic values move to a context suffix so the persona prefix
     # stays byte-stable for the prompt cache (ENV-20)
     DYNAMIC_PLACEHOLDERS = ("{date}", "{time}", "{news}", "{memory}")
 
-    def message(self, message: AIMessage, limit: Optional[int] = None) -> List[Dict[str, Any]]:
-        messages = []
-        persona = self.config.get(self.channel, self.config["system"])
-        for placeholder in self.DYNAMIC_PLACEHOLDERS:
-            persona = persona.replace(placeholder, "")
+    def _context_lines(self, message: AIMessage) -> List[str]:
         context = [f"date: {time.strftime('%Y-%m-%d')} ({time.strftime('%A')})", f"time: {time.strftime('%H:%M:%S')}"]
         news_feed = self.config.get("news")
         if news_feed and os.path.exists(news_feed):
@@ -173,7 +173,19 @@ class AIResponder(AIResponderBase):
         memory_block = self.memory_manager.memory_block(participants, self.memory)
         if memory_block:
             context.append("memory:\n" + memory_block)
-        system = persona.rstrip() + "\n\n## Context\n" + "\n".join(context)
+        if self.image_cache is not None:
+            recent_images = self.image_cache.recent(message.channel, 4)
+            if recent_images:
+                # the model cannot use picture_edit unless told images exist (IMG-16)
+                context.append(f"recent images in this channel: {len(recent_images)} (set picture_edit=true to edit/remix the newest)")
+        return context
+
+    def message(self, message: AIMessage, limit: Optional[int] = None) -> List[Dict[str, Any]]:
+        messages = []
+        persona = self.config.get(self.channel, self.config["system"])
+        for placeholder in self.DYNAMIC_PLACEHOLDERS:
+            persona = persona.replace(placeholder, "")
+        system = persona.rstrip() + "\n\n## Context\n" + "\n".join(self._context_lines(message))
         messages.append({"role": "system", "content": system})
         if limit is not None:
             while len(self.history) > limit: