Will Pfleger b1fd5f534a feat(acp): add ACP methods to support programmatic goose clients
The ACP protocol was missing several capabilities needed by external
clients that talk to goosed over the network.

Adds:
- `_goose/health` — startup health check for clients that poll before
  accepting traffic
- `_goose/session/set_instructions` — injects a system prompt into an
  active session under the "recipe" key, replacing the two-call HTTP
  pattern of start_agent + update_from_session
- `session/set_model` now accepts an optional `provider` field for full
  provider+model switching; empty string is filtered out to avoid opaque
  registry lookup errors
- `_goose/session/get` verified to already return token metrics
  (input_tokens, output_tokens, accumulated_*, model_config) via the
  Session struct serialization — confirmed with a new test
2026-03-09 14:19:28 -04:00
2026-02-11 14:35:24 +00:00
2026-02-11 14:35:24 +00:00
2026-03-07 17:09:05 +00:00
2025-12-23 15:38:26 -06:00
2026-02-11 14:35:24 +00:00
2026-03-07 17:16:19 +00:00
2026-02-11 14:35:24 +00:00
2024-09-09 14:56:30 -04:00
2026-01-22 11:45:27 +11:00
2025-09-26 23:44:38 -05:00

goose

a local, extensible, open source AI agent that automates engineering tasks

Discord CI

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.

Watch the video

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! 🚀

goose around with us

S
Description
an open-source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Readme Apache-2.0 2 GiB
Languages
Rust 63.6%
TypeScript 29.6%
JavaScript 1.7%
Shell 1.6%
Python 1.5%
Other 1.8%