goose Release Notes

✨ Features

• TUI command on goose-cli #9385
• TUI diff viewer #9260
• goose review local code review command #9114
• /goal command for agent self-evaluation before finishing #9069
• Hooks system for PreToolUse denial and extensibility #9093, #9304
• Slash commands (built-in, skill, recipe) in ACP server #9238
• Open-plugins generalization + skills #9112
• Summon subagent instructions #9325
• Unified thinking effort control across all providers #9242
• NEAR AI Cloud provider #9352
• Scaleway provider #9254
• Vercel AI Gateway provider #9144
• Atomic Chat declarative OpenAI-compatible provider #9210
• Routstr declarative provider #9175
• FuturMix provider #8840
• oMLX declarative provider #9177
• Harbor eval runner #9138
• goose://resume and goose://new-session deep links #9343, #9196
• MAX_CODE_BLOCK_LINES configurable via env vars #9301
• Honor GOOSE_FAST_MODEL env var in ModelConfig #9296
• GPT-5.5 in known models #9292
• Paginate ACP session list #9199
• Pass session cwd param to ACP providers #9229
• Opt-in to Vercel AI gateway leaderboard #9259
• GOOSE_OAUTH_CALLBACK_PORT for stable OAuth redirect_uri #9209
• Proactive OAuth token refresh to avoid re-auth on every session #8386
• Strip chain-of-thought markers from custom provider output #8635
• Encrypted Nostr session sharing #8922
• Simplified Chinese (zh-CN) translation #8765
• Russian language support #9406
• Turkish desktop locale #9392
• Nushell terminal and completion support #8628
• Optional --parameters flag for scheduled recipes #8741
• Quarterly option for scheduler #9076
• GitHub Copilot /responses API support #9043
• Worktree-aware directory switcher #8450
• Chat history search feature #8448
• Projects as backend sources with system prompt injection #8739
• Linux Vulkan support for local inference #9038
• Linux musl CLI builds #9240
• Windows CUDA release artifacts #8750
• GOOSE_DISABLE_TOOL_CALL_SUMMARY env var #8947

🐛 Bug Fixes

• Tolerate missing responses output #9449
• Stop main window growing taller on every launch #9409
• Desktop chat search session limiting #9366
• Serialize per-session agent creation to stop duplicate MCP init #9357
• Respect GOOSE_MAX_TURNS in gateway sessions #9354
• Send empty object instead of null for Anthropic tool_use input #9355
• Preserve thinking content for provider context #9314
• Mention configurable timeout env vars in Ollama stream stall error #9246
• Include full recipe parameter details in load/discovery output #9233
• Remove unused fetch-metadata IPC handler (SSRF) #9340
• Use context limit from /model/info for LiteLLM custom models #9303
• Plain > prompt instead of goose emoji in CLI #9305
• Stop killing goosed when a window closes #9302
• Emit trace_output as span attribute instead of event #9255
• Check file fallback when keyring has no entry #9279
• Align sidebar hamburger in macOS fullscreen #9257
• Use current_exe() instead of PATH lookup when spawning goose #9236
• Set TCP_USER_TIMEOUT on streamable HTTP clients #9207
• Activate custom provider after adding via configure #9213
• Flush OTLP traces reliably on exit with configurable timeout #9228
• Reduce excessive MISSING_TRANSLATION warnings for fallback locales #9294
• Eliminate cross-window deep link contamination #9273
• Improve Telegram gateway error reporting and connection reliability #9223
• Enable VT processing on Windows Console Host #9248
• Zero out cost for local providers (ollama, local) #9219
• Resolve Azure CLI on Windows by using az.cmd #9215
• Handle non-interactive terminal in goose configure on Windows #9214
• Persist accumulated cost in session DB to survive reload #9191
• Prevent tool-use marker leakage in toolshim output #8310
• Re-apply canonical limits when delegate overrides model #9183
• Report cumulative total_tokens in stream-json/json output #8910
• Refresh GCP metadata server token on expiration #8929
• Apply request_params to outgoing OpenAI API payload #9151
• Gemini 3.x known_location Global routing entries #9142
• Coalesce streaming Thinking deltas + list available tools on not-found #9162
• Honor Retry-After on 429 responses #9161
• Preserve user-set session name for recipe-based chats #9079
• Enforce exp independently of MAX_TOKEN_AGE_SECONDS in OIDC proxy #8839
• Improve inline code contrast in light theme #9058
• Omit max_tokens for OpenAI-compatible requests when unset #9123
• Set correct MCP-app host capabilities #9116
• Normalize nullable schemas for Vertex Gemini compatibility #8930
• Isolate GitHub recipe temp paths #8878
• Set X-Initiator header on GitHub Copilot requests #8809
• Honor dynamic_models: false in declarative provider configs #8795
• Cache trailing message for stable prefix across Bedrock agent turns #8916
• Case-insensitive model name lookup for context_limit #8906
• Handle Bedrock ReasoningContent blocks gracefully #8843
• Ensure parallel tool image responses don't interleave on Databricks #9241
• Insert tool pair summaries at chronological position in conversation #9087
• Enable SQLite foreign key enforcement in session pool #9121
• Deleted chat session still appears in sidebar list #8674
• Correct WSL2 OS detection by removing PWD-based Windows override #8869
• Accept null tool_call arguments in OpenAI streaming chunks #9035
• Use python3 in developer extension instructions for macOS/Linux #8784
• Synchronously reap ACP child to avoid SIGCHLD race #9023
• Elicitation fixes #8999
• Return 400 instead of panicking on invalid CSP header value #8810
• Keep SSE reconnect loop alive on long disconnects #8846
• Convert quoted numeric config values to numbers if needed #8844
• Use appInfo instead of clientInfo in MCP Apps init handshake #9249
• Use mkdir -p for self-test workspace initialization #9247
• Exclude preprompt from session title generation #8793
• Prevent login-shell PATH probe from suspending goose on startup #8804

🔧 Improvements

• Local inference: stricter GGUF requirements, auto detection of tool calling support, fixed thinking output parsing #9442
• Simplify UI customization #9353
• Build summon instructions per turn #9329
• Protocol cleanup #9147
• Dependency hygiene #9360
• Preserve selected branch across project chats #9010
• Prompt injection mitigation: update pattern-based detection to reduce FPs #9350
• Surface resolved Databricks model metadata #9206
• Include request URL in provider error messages #9232
• Flag for login shell PATH #9313
• Remove popular chat topics from new chat screen #9307
• Structured per-provider config block, non-destructive provider switching #8977
• TUI spacing/layout improvements #9243
• Preserve thinking content for providers that require it #8857
• Dynamically refresh skill instructions each turn #9217
• Better parsing of pasted HTML as markdown #9190
• Show tool name in approval prompt #9216
• Localize hardcoded strings in provider settings UI #8931
• Move settings into app shell #9047
• Location column in CLI skills table #8785
• Consolidate logging setup into shared helper #8817
• Support optional api_key configuration for declarative openai-engine providers #9202
• Remove vendored Windows binaries #9318
• Polish sidebar and context panel #9059
• Polish inline code snippet styling #9011
• Refresh onboarding when provider catalog loads #9051
• Recipe discovery/execution in ACP server #8925
• Group consecutive tool calls into one summarized chain card #8995
• Replace artifact heuristics/regexes with protocol messages #8996
• Improvements to LM Studio declarative provider #8973
• Parallelize provider resolution and eagerly init SQLite pool #8899
• Deduplicate _goose/providers/list RPC call at startup #8873
• Native arm64 runners for Linux artifact builds #9075
• ACP streamable HTTP spec compliance #9034
• Provider-first onboarding #9039
• Redesign extensions page #8940
• Redesign skills library #8868
• Skills in chat composer #8881
• Mergeable configs cleanup #8378

📚 Documentation

• Stats update #9410
• Hooks guide #9288
• Hooks feature blog post #9227
• Document summon extension requirement for delegate and load tools #9231
• Guide for connecting goose Desktop to a remote goosed server #9275
• SaladCloud AI Gateway provider documentation #9253
• Reorganize documentation #9310
• Fix internal documentation anchors #9094
• Tunnel remote access documentation update #9077
• Linux desktop Vulkan packages #9323
• Orchestrating with goose blog #9104
• Goose with Peekaboo blog #8884
• Built-in local inference blog post #8808
• MiniMax and office QA benchmark blog post #8984
• Repology badge in README #9245

Original source

✨ Features

Hooks support for customizable agent behavior #9093
Agents CRUD operations #9084
Projects as backend sources with system prompt injection #8739
Auto-updating for plugins #9061
Linux Vulkan support for local inference #9038
ACP streamable HTTP spec compliance #9034
Expose built-in skills through sources list ACP calls #9045
Provider-first onboarding flow #9039
Move goose2 provider catalog behind ACP layer #9030
Group consecutive tool calls into one summarized chain card #8995
Replace raw config and secret methods in ACP #9000
goose2 support for custom providers in UI & ACP #8924
Configurable Ollama host in goose2 #8912
Update provider row after saving credentials #8914
Google model inventory refresh support #8913
Skills in the chat composer #8881
Mergeable configs #8378
MCP Apps: hydrate and replay app payloads in goose2 #8632
MCP Apps: translate ACP host capabilities into MCP initialization #8623
Windows CUDA release artifacts #8750
goose2 compact settings modal headers #8950
goose-tui binary #9089

🐛 Bug Fixes

Insert tool pair summaries at chronological position in conversation #9087
Enable SQLite foreign key enforcement in session pool #9121
Deleted chat session still appears in sidebar list #8674
Revert unexpected change from ui/goose2 work #9098
Require extension_name on read_resource #8989
Queued message lost when clicking send now #9074
Keep model picker and session config in sync #9048
Read prompted file parameters in recipes #8504
Accept null tool_call arguments in OpenAI streaming chunks #9035
Use python3 in developer extension instructions for macOS/Linux compatibility #8784
Synchronously reap ACP child to avoid SIGCHLD race #9023
goose2 small-window chat and settings layouts #9019
Elicitation fixes #8999
SACP notifies clients of generated session names #8983
Unscheduling a recipe should not delete them #8978
Seed provider handoff history in ACP #8941
Respect goose2 interface density settings #8953
Make goose2 respect accent color #8952
Preserve replay message timestamps #8942
goose2 window minimum sizing #8946
Avoid transform-rasterized dialog text in goose2 #8937
Keep renamed skills open in detail view #8935
Gemini OAuth onboarding failure #8905
Copy and content improvements in goose2 #8886
Model picker stays usable during provider loading #8900
Handle ACP requests concurrently #8781
CRT linkage in Windows CUDA build #8987
Exclude preprompt from session title generation #8793
Prevent login-shell PATH probe from suspending goose on startup #8804
Remove defaults yaml #8854

🔧 Improvements

Keep thread tables + column #9156
Refactor local inference around backends #9137
Remove threads layer, use sessions directly for ACP #9078
Install plugins to ~/.agents/plugins #9088
Switch to official new rust-sdk for ACP #9062
Remove attachment preamble in goose2 #9052
goose2 UI state refactor (part 1) #9049
Clean up types #9057
Use native arm64 runners for Linux artifact builds #9075
Redesign Extensions page, remove enable toggle, treat Extension Manager as core MCP enabler per session #8940
Extensions page styling alignment #9003
Replace artifact heuristics/regexes with protocol messages #8996
Fold UI refactor review into code review skill #8982
LM Studio declarative provider improvements #8973
Remove artifacts dir handling #8945
Install plugins #8949
Render MCP apps inline in goose2 #8877
Remove skill categories #9008
goose2 distribution bundling #8911
goose2 used ACP session id #8985
Clean up goose2 settings headers #8951
Break up acp/server.rs #8932
goose2 skill refactor #8897
Update patterns for pattern-based command injection #8546
Polish sidebar navigation and project icons #8896
Parallelize provider resolution and eagerly init SQLite pool #8899
Update goose2 credential management behind provider-scoped ACP/core API #8887
Deduplicate _goose/providers/list RPC call at startup #8873
Agent provider to use explicit type states #8879
Redesign skills library #8868
Revert client-side autocompaction #9055
Set LLAMA_STATIC_CRT for Windows CUDA #8901
Disable spellcheck in model search #8889

📚 Documentation

Blog: orchestrating with goose #9104
Remove old goose bench documentation #9054
Updated tunnel remote access documentation #9077
Blog: findings with minimax and office QA benchmark #8984
Align CODEOWNERS with pull request review rules in GOVERNANCE.md #9056
Bring MAINTAINERS.md up to date #9053
Improve AGENTS.md readability #8979
Improve goose2 AGENTS.md #9028
Add CLAUDE.mds to mirror AGENTS.mds #9029
Blog: goose with peekaboo #8884
Blog: Built-in Local Inference #8808
Hide Windows CUDA download links until release #8874

Original source

✨ 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

Warm shell PATH lookup during session init #8631

Gate perf logs and dedup build_config_update on first message #8627

Use default fallback provider and model if default are set #8650

Show individual untracked files in git changes widget #8574

Goose2 session working dir #8624

Update rmcp to 1.5.0 #8618

Merge goose-acp crate into goose #8726

Upgrade goose SDK and TUI to be compatible with the latest agentclientprotocol/sdk package #8667

Declare and enforce MSRV of 1.91.1 #8670

Pass globally unique conversation identifier as sessionId in Databricks API call #8576

Move agent skills to repo root for tool discoverability #8535

Reset ChatGPT Codex auth during OAuth setup #8569

Isolate gym scenario Cargo projects from parent workspace #8640

📚 Documentation

AGENTS.md section on goose2 desktop backend architecture #8732

Rendex MCP Server extension tutorial #8541

Blog post about Mesh LLM provider option #8655

Remove stale gemini-acp references #8572

Replace deprecated Claude ACP package links #8625

Original source