Skip to content

Agent Zero AI framework

add number of imgs in vision tool

Alessandro33b88d5731e6
diff --git a/prompts/agent.system.tools_vision.md b/prompts/agent.system.tools_vision.md
index a4ecd1b3f..7611245a4 100644
--- a/prompts/agent.system.tools_vision.md
+++ b/prompts/agent.system.tools_vision.md
@@ -7,6 +7,7 @@ rules:
- load all relevant images in one call when comparing screenshots or pages
- use when the task depends on screenshots, diagrams, scanned documents, charts, or photos
- only bitmaps are supported; convert other formats first if needed
+- the tool result includes loaded/skipped image totals and the corresponding path lists
example:
```json
{
diff --git a/tools/vision_load.py b/tools/vision_load.py
index ee89e69ec..83a7101c7 100644
--- a/tools/vision_load.py
+++ b/tools/vision_load.py
@@ -68,10 +68,14 @@ class VisionLoad(Tool):
# build image data messages for LLMs, or error message
content = []
+ loaded_count = len(self.loaded_paths)
+ skipped_count = len(self.skipped_paths)
loaded_summary = "\n".join(self.loaded_paths) if self.loaded_paths else "none"
skipped_summary = "\n".join(self.skipped_paths) if self.skipped_paths else "none"
summary = (
+ f"Loaded images: {loaded_count}\n"
f"Loaded images:\n{loaded_summary}\n\n"
+ f"Skipped images: {skipped_count}\n"
f"Skipped images (max {self._get_max_embeds()} loaded at a time according to model configuration):\n{skipped_summary}"
)
if self.images_dict:
@@ -103,7 +107,7 @@ class VisionLoad(Tool):
message = (
"No images processed"
if not self.images_dict and not self.skipped_paths
- else f"{len(self.loaded_paths)} images loaded, {len(self.skipped_paths)} skipped"
+ else f"{loaded_count} images loaded, {skipped_count} skipped"
)
PrintStyle(
font_color="#1B4F72", background_color="white", padding=True, bold=True