jh-block
3b24bb33cf
When code mode wraps tools in a JS sandbox, non-text content (resources, images, blobs) couldn't round-trip through the JSON return value. This fix: 1. Stores non-text content in a ContentStore keyed by unique tokens 2. Returns token references in the JSON payload to the JS runtime 3. After execution, collects referenced tokens and appends resolved content This allows tools like Autovisualiser to return rich HTML visualizations that survive the JS sandbox boundary. The model's return value stays intact with token references, while the actual content is restored alongside. Also removed stdout/stderr from the tool output channel—console.log is now ignored and only return values are used, simplifying the interface. Fixes #6167 Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
goose
a local, extensible, open source AI agent that automates engineering tasks
goose is your on-machine AI agent, capable of automating complex development tasks from start to finish. More than just code suggestions, goose can build entire projects from scratch, write and execute code, debug failures, orchestrate workflows, and interact with external APIs - autonomously.
Whether you're prototyping an idea, refining existing code, or managing intricate engineering pipelines, goose adapts to your workflow and executes tasks with precision.
Designed for maximum flexibility, goose works with any LLM and supports multi-model configuration to optimize performance and cost, seamlessly integrates with MCP servers, and is available as both a desktop app as well as CLI - making it the ultimate AI assistant for developers who want to move faster and focus on innovation.
Quick Links
- Quickstart
- Installation
- Tutorials
- Documentation
- Governance
- Custom Distributions - build your own goose distro with preconfigured providers, extensions, and branding
Need Help?
a little goose humor 🪿
Why did the developer choose goose as their AI agent?
Because it always helps them "migrate" their code to production! 🚀