feat: optimize vision tools and image handling

- Add model-aware vision tool loading based on supports_vision flag
- Move view_image_tool from config to builtin tools for dynamic inclusion
- Add timeout to image search to prevent hanging requests
- Optimize image search results format using thumbnails
- Add image validation for reference images in generation
- Improve error handling with detailed messages

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
hetao
2026-01-29 14:57:26 +08:00
parent 3cbf54b2eb
commit 7aa10b980f
5 changed files with 59 additions and 19 deletions

View File

@@ -2,6 +2,29 @@ import base64
import os
import requests
from PIL import Image
def validate_image(image_path: str) -> bool:
"""
Validate if an image file can be opened and is not corrupted.
Args:
image_path: Path to the image file
Returns:
True if the image is valid and can be opened, False otherwise
"""
try:
with Image.open(image_path) as img:
img.verify() # Verify that it's a valid image
# Re-open to check if it can be fully loaded (verify() may not catch all issues)
with Image.open(image_path) as img:
img.load() # Force load the image data
return True
except Exception as e:
print(f"Warning: Image '{image_path}' is invalid or corrupted: {e}")
return False
def generate_image(
@@ -14,7 +37,19 @@ def generate_image(
prompt = f.read()
parts = []
i = 0
for reference_image in reference_images:
# Filter out invalid reference images
valid_reference_images = []
for ref_img in reference_images:
if validate_image(ref_img):
valid_reference_images.append(ref_img)
else:
print(f"Skipping invalid reference image: {ref_img}")
if len(valid_reference_images) < len(reference_images):
print(f"Note: {len(reference_images) - len(valid_reference_images)} reference image(s) were skipped due to validation failure.")
for reference_image in valid_reference_images:
i += 1
with open(reference_image, "rb") as f:
image_b64 = base64.b64encode(f.read()).decode("utf-8")
@@ -41,6 +76,7 @@ def generate_image(
"contents": [{"parts": [*parts, {"text": prompt}]}],
},
)
response.raise_for_status()
json = response.json()
parts: list[dict] = json["candidates"][0]["content"]["parts"]
image_parts = [part for part in parts if part.get("inlineData", False)]
@@ -92,5 +128,5 @@ if __name__ == "__main__":
args.aspect_ratio,
)
)
except Exception:
print("Error while generating image.")
except Exception as e:
print(f"Error while generating image: {e}")