spencrmartin
487f5cd243
GOOSE-2, GOOSE-3, GOOSE-4: Backend infrastructure for background processes ## What's New ### Shell Tool Enhancement (GOOSE-3) - Added `background: Option<bool>` parameter to ShellParams - When `background: true`, command spawns and returns immediately with process ID - Agent loop can continue processing new messages while process runs ### Background Process Tracking (GOOSE-2) - New `BackgroundProcess` struct with id, command, pid, status, output buffer - `BackgroundProcessStatus` enum: Running, Completed, Failed, Cancelled - Ring buffer (1000 lines) captures stdout/stderr for later retrieval - Real-time output streaming via notify_logging_message ### Process Management Tools (GOOSE-4) - `list_background_processes`: Shows all tracked processes with status/runtime - `get_background_process_output`: Retrieves last N lines from output buffer - `stop_background_process`: Sends SIGTERM to terminate running process ## Why This Matters This solves the core UX issue where long-running commands (npm run dev, etc.) block the chat. Now Goose can: 1. Start a dev server with `background: true` 2. Return immediately with process ID 3. Continue processing new user messages 4. User can check/stop the process later ## Files Changed - crates/goose-mcp/Cargo.toml (added uuid dependency) - crates/goose-mcp/src/developer/rmcp_developer.rs (main implementation) ## Testing All 182 existing tests pass. Background process functionality ready for integration testing with the desktop app.
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
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! 🚀