feat: add view_image tool and optimize web fetch tools

Add image viewing capability for vision-enabled models with ViewImageMiddleware and view_image_tool. Limit web_fetch tool output to 4096 characters to prevent excessive content. Update model config to support vision capability flag.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

backend/src/tools/builtins/__init__.py

@@ -1,4 +1,5 @@
 from .clarification_tool import ask_clarification_tool
 from .present_file_tool import present_file_tool
+from .view_image_tool import view_image_tool
 
-__all__ = ["present_file_tool", "ask_clarification_tool"]
+__all__ = ["present_file_tool", "ask_clarification_tool", "view_image_tool"]

backend/src/tools/builtins/present_file_tool.py

@@ -28,15 +28,12 @@ def present_file_tool(
 
     Notes:
     - You should call this tool after creating files and moving them to the `/mnt/user-data/outputs` directory.
-    - IMPORTANT: Do NOT call this tool in parallel with other tools. Call it separately.
+    - This tool can be safely called in parallel with other tools. State updates are handled by a reducer to prevent conflicts.
 
     Args:
         filepaths: List of absolute file paths to present to the user. **Only** files in `/mnt/user-data/outputs` can be presented.
     """
-    existing_artifacts = runtime.state.get("artifacts") or []
-    # Use dict.fromkeys to deduplicate while preserving order
-    new_artifacts = list(dict.fromkeys(existing_artifacts + filepaths))
-    runtime.state["artifacts"] = new_artifacts
+    # The merge_artifacts reducer will handle merging and deduplication
     return Command(
-        update={"artifacts": new_artifacts, "messages": [ToolMessage("Successfully presented files", tool_call_id=tool_call_id)]},
+        update={"artifacts": filepaths, "messages": [ToolMessage("Successfully presented files", tool_call_id=tool_call_id)]},
     )

backend/src/tools/builtins/view_image_tool.py

@@ -0,0 +1,94 @@
+import base64
+import mimetypes
+from pathlib import Path
+from typing import Annotated
+
+from langchain.tools import InjectedToolCallId, ToolRuntime, tool
+from langchain_core.messages import ToolMessage
+from langgraph.types import Command
+from langgraph.typing import ContextT
+
+from src.agents.thread_state import ThreadState
+from src.sandbox.tools import get_thread_data, replace_virtual_path
+
+
+@tool("view_image", parse_docstring=True)
+def view_image_tool(
+    runtime: ToolRuntime[ContextT, ThreadState],
+    image_path: str,
+    tool_call_id: Annotated[str, InjectedToolCallId],
+) -> Command:
+    """Read an image file.
+
+    Use this tool to read an image file and make it available for display.
+
+    When to use the view_image tool:
+    - When you need to view an image file.
+
+    When NOT to use the view_image tool:
+    - For non-image files (use present_files instead)
+    - For multiple files at once (use present_files instead)
+
+    Args:
+        image_path: Absolute path to the image file. Common formats supported: jpg, jpeg, png, webp.
+    """
+    # Replace virtual path with actual path
+    # /mnt/user-data/* paths are mapped to thread-specific directories
+    thread_data = get_thread_data(runtime)
+    actual_path = replace_virtual_path(image_path, thread_data)
+
+    # Validate that the path is absolute
+    path = Path(actual_path)
+    if not path.is_absolute():
+        return Command(
+            update={"messages": [ToolMessage(f"Error: Path must be absolute, got: {image_path}", tool_call_id=tool_call_id)]},
+        )
+
+    # Validate that the file exists
+    if not path.exists():
+        return Command(
+            update={"messages": [ToolMessage(f"Error: Image file not found: {image_path}", tool_call_id=tool_call_id)]},
+        )
+
+    # Validate that it's a file (not a directory)
+    if not path.is_file():
+        return Command(
+            update={"messages": [ToolMessage(f"Error: Path is not a file: {image_path}", tool_call_id=tool_call_id)]},
+        )
+
+    # Validate image extension
+    valid_extensions = {".jpg", ".jpeg", ".png", ".webp"}
+    if path.suffix.lower() not in valid_extensions:
+        return Command(
+            update={"messages": [ToolMessage(f"Error: Unsupported image format: {path.suffix}. Supported formats: {', '.join(valid_extensions)}", tool_call_id=tool_call_id)]},
+        )
+
+    # Detect MIME type from file extension
+    mime_type, _ = mimetypes.guess_type(actual_path)
+    if mime_type is None:
+        # Fallback to default MIME types for common image formats
+        extension_to_mime = {
+            ".jpg": "image/jpeg",
+            ".jpeg": "image/jpeg",
+            ".png": "image/png",
+            ".webp": "image/webp",
+        }
+        mime_type = extension_to_mime.get(path.suffix.lower(), "application/octet-stream")
+
+    # Read image file and convert to base64
+    try:
+        with open(actual_path, "rb") as f:
+            image_data = f.read()
+            image_base64 = base64.b64encode(image_data).decode("utf-8")
+    except Exception as e:
+        return Command(
+            update={"messages": [ToolMessage(f"Error reading image file: {str(e)}", tool_call_id=tool_call_id)]},
+        )
+
+    # Update viewed_images in state
+    # The merge_viewed_images reducer will handle merging with existing images
+    new_viewed_images = {image_path: {"base64": image_base64, "mime_type": mime_type}}
+
+    return Command(
+        update={"viewed_images": new_viewed_images, "messages": [ToolMessage("Successfully read image", tool_call_id=tool_call_id)]},
+    )