Skip to content
DevAgentRadarDevAgentRadar
Sign in

Goose v1.32.0

Released · Block

What the release notes say

✨ Features

  • Exa AI-powered search tool #8487

  • Desktop notification when goose finishes a task #8647

  • @agent mention support in chat #8571

  • /skills command #8600

  • Associate threads with projects #8745

  • Auto-compaction for goose2 context window UX #8721

  • Message bubble + action tray in goose2 #8720

  • Voice dictation via direct-ACP pattern in goose2 #8609

  • Context window usage in goose2 chat input #8613

  • Unix domain socket transport for StreamableHttp MCP #7860

  • Cash App extension in Extensions Library #8622

  • /edit command for on-demand prompt editing #8566

  • Novita AI as declarative provider #8432

  • Kimi Code provider with OAuth device flow authentication #8466

  • Extension management screen in TUI #8536

  • Extensions settings page and context panel widget #8540

  • Client ID Metadata Document (CIMD) support for OAuth #8550

  • Context window usage inline in status bar #7607

  • Chat attachments in goose2 #8534

  • Husky git hooks for ui/goose2 #8577

🐛 Bug Fixes

  • Cache TLS cert to disk to avoid slow startup on first launch #8174

  • Preprompt would show after loading session #8744

  • Handle missing delta field in streaming chunks #8700

  • Accept streaming chunks with both reasoning fields in OpenAI provider #8715

  • strict:false for Responses API tools and gpt-5.4 to known models #8636

  • Correct grammar in apps view description #8679

  • Links in chat could not be opened #8544

  • Run shell tool under bash/sh regardless of login shell #8659

  • Append /chat/completions for prefixed v1 base URLs #8521

  • Align Kimicode model metadata with live Kimi Code API #8588

  • Stop idle 300ms re-render loop that could OOM the TUI #8616

  • Chat loading-state model placeholder #8431

  • Expand tool calls by default when Response Style is Detailed #8478

  • Create logs dir before writing LLM request log #8522

  • Enable token usage tracking and configurable stream timeout for Ollama provider #8493

  • Use sqlx chrono decode for thread timestamps instead of manual parsing #8575

  • Remove double border on content in chat #8545

  • Accept self-signed certs from configured external goosed host #8400

  • Sync sidebar sessions after chat history deletion #7707

  • Prevent session hang when tool approval required in headless mode #7915

  • Eliminate ~5s delay when opening Switch Models panel with local provider #8626

  • Removed hardcoded dependency of goose-acp-macro #8753

  • Stop load openai fast model for openapi compatible custom endpoint #8644

🔧 Improvements

  • Split agent setup into staged phases to reduce startup blocking #8746

  • Extensions management migrated to ACP+ #8733

  • Harden code review skill for async state and default-resolution bugs #8740

  • Persist and reliably apply chat model selection #8734

  • Overhaul provider inventory and agent/model selection #8652

  • Consolidate provider ACP methods onto inventory #8710

  • Manage skills as sources over ACP #8675

  • Extract shared OAuth device-flow helper #8619

  • Full width assistant message in goose2 #8760

  • TUI improvements #8736

  • Goose2 agent management flows #8737

  • Sidebar polish: search copy, dividers, project reorder, DnD fixes #8568

  • Sidebar activity indicators, placeholder token, and search field refinements #8606

Continue at github.com ↗