Tyler Longwell
17796c0abd
Complete implementation of goose-cli-acp — an interactive terminal client for the goose AI agent via Agent Client Protocol (JSON-RPC 2.0). Architecture (19 files, ~4,770 LOC, 68 tests): - SessionMode enum (Rich/Plain/Pipe) — zero boolean flags in stream loop - Viewport-rewrite markdown streaming at 30fps with SynchronizedUpdate - Permission handler with cached/auto → interactive two-phase resolution - Terminal escape sanitization (CSI/OSC/C0/C1/DEL) at every display boundary - RAII RawModeGuard + panic hook for terminal safety - Monotonic tool output IDs with VecDeque eviction Features: - Interactive REPL with reedline, streaming markdown, syntax highlighting - Tool call approval UI with per-tool memory (y/n/a/v/Esc) - Slash commands (/help, /theme, /alias, /show, /clear, /commands) - User-defined commands with YAML frontmatter (Claude Code compatible) - 4 built-in themes + custom YAML themes with semantic color tokens - Session resume, history replay, recipe support - Context %, model name, git branch in adaptive prompt - Ctrl+O to open $EDITOR for large input buffers - Server mode (--server) and one-shot/piped modes - Ctrl+C at prompt (hint), Esc/Ctrl+C during streaming (cancel turn) Server changes (goose-acp): - Custom _goose/session/new_with_recipe request handler - build_tool_call_content reuse for direct tool calls Triple-reviewed by Codex (9/10), Opus (9/10), Gemini 3.1 Pro (10/10). All three APPROVE. Build/clippy/fmt/test clean.
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
- Responsible AI-Assisted Coding Guide
- 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! 🚀