goose Release Notes

✨ Features

• Prompt for goose mode during first-time configure #12629
• HTML session export with an interactive viewer #11977

🐛 Bug Fixes

• Adaptive thinking for Claude Sonnet and Haiku 5.5 #12761
• Treat a client extension selection as the exact session set #12548
• Support hyphenated GPT 6.1 Sol effort aliases #12689
• Use a system Node.js in the Windows npx wrapper #12176
• Show thinking when GOOSE_CLI_SHOW_THINKING is set to any value #12454
• Price Databricks GLM aliases from the zhipuai catalog #12673
• Read messages from config for tom #12634
• Preserve the service total when folding cache input tokens for Bedrock #12586
• Refresh revoked Copilot tokens when listing models #12627
• Refresh revoked GitHub Copilot API token once #12616
• Recognize ASAR when validating update target #12599
• Stamp the implemented protocol version in initialize #12580
• Session naming/"none" reasoning effort fails for gpt-6.1-sol #12605
• Reflect loading state of chats #12603
• Read cache write tokens from Responses API usage #12509

🔧 Improvements

• Route every extension operation through a lease #12723
• Foreground subagents in the state machine loop #12632
• Resolve extensions into a per-inference lease #12161
• Remove Nostr session sharing from goose core #12453
• Detect vision support #12594
• Upgrade rust to 1.99.0 #12714

📚 Documentation

• Update Desktop permission mode instructions #12626
• Clarify self-serve LLM provider path #12552

Original source

Features

Resizable Picture-in-Picture window for MCP Apps #12417

Fetch model metadata from models.dev live with bundled fallback #12560

Quoting action to append selected conversation text to composer #12536

Lean ACP-only Goose binary #11961

Model discovery API for GDK Provider #12497

Meta Muse Code provider #11765

Support for Opus 5.5, GPT-6-sol, GPT-6-luna #12447

Session rename command in CLI #12236

Show working directory in session remove command #12232

GDK agent loop runs on wasm32 #12569

Bug Fixes

Session naming and "none" reasoning effort for GPT-6.1-sol #12605

Strip inert parameters from session snapshots in recipes #11988

Preserve session context across reply lifecycle #12516

Report max_tokens truncation and flush tool calls for Bedrock #11872

Require a terminal for elicitation input in CLI #12542

Keep tool results consecutive when OpenAI-compatible tool images are emitted #12233

GDK tools with no args still advertise empty params input schema #12527

Passing thinking effort to Ollama models #12555

Estimate costs through canonical provider aliases #11916

Resolve vision support from the canonical catalog for all providers #12522

Send Databricks v2 Claude model services through the Anthropic route #12486

Show tool output for tools without a priority annotation #12436

Treat an unavailable prompt classifier as no signal #12452

Guard MCP streamable-HTTP client redirects against SSRF #11501

Resolve vision support from the canonical catalog in GDK so tool result images reach the model #12440

Prevent Extension Manager from disabling itself #12270

Rename deepseek-v4-flash to deepseek-flash #12269

Auto-compact at tool boundaries in the unrolled agent loop #12444

Remediate GHSA-6mg9-3cvh-9939 security vulnerability #12537

Improvements

Suppress warning when ending on a successful tool call #12468

Update rmcp to 3.4.1 #12483

Remove MCP sampling code #12193

Remove production code only reachable from tests #12504

Pin remaining GitHub Actions to commit SHAs #11989

Documentation

Warn about keyring hang in unattended ACP environments #12173

Original source

Features

Live voice conversations in the desktop app #12093

Decisions provider crate with OpenRouter and Jev implementations #12418

Z.AI Coding Plan provider with streaming tool calls #12205

Recipe parameter limits enforcement (max 32 params, 200 select options, 128 KiB) #12259

OpenAI provider custom base URL support in SDK #11967

Support for Opus 5.5, GPT-6-sol, and GPT-6-luna models #12447

Bug Fixes

Cancel elicitation on incomplete CLI input #11403

Protect custom provider configuration files #11438

Prevent duplicate schedules from overwriting recipes #12434

Classify many-image dimension limit errors as context length-exceeded #12208

Set strict:false on chat-completions tools #12272

Show CoreWeave in bundled provider metadata #12149

Allow 60 seconds for provider readiness #12240

Write PATH to login shell files idempotently in installer #12072

De-duplicate @radix-ui packages to fix pointer-events stranded on body #11792

Drive pre-key model lists from the canonical registry #11475

Make todo opt-in and soften its prompts #12123

Prevent updates to unsupported macOS versions #12115

Require recipe consent before session/new spawns extensions #12094

Skills follow working directory updates #11443

Create updater staging atomically #11741

Require opt-in for roaming TCP bridge #11701

Omit unsupported socket MCP servers #11417

Let recipe settings outrank GOOSE_SUBAGENT_MODEL/PROVIDER #12070

Send session usage updates after each provider call #12006

Start a chat with no extensions when the user selects none #11908

Databricks GLM-5.3 and Kimi K3 reasoning effort #12079

Avoid splitting graphemes in skills list #12074

Keep the subagent prompt prefix cacheable #12062

Install libclang and cmake in devcontainer #12091

Improvements

Redesign settings as a full-screen view #12163

Split extension transports out of ExtensionManager #12088

Compress canonical_models.json #12385

Resolve data_dir from Paths::data_dir() instead of config #12203

Documentation

Use the real developer tool names in the hooks guide #12260

Fix stale declarative provider file paths in providers.md #12192

Clarify public crate APIs #12186

Remove Rube extension documentation (service discontinued) #12116

Original source

✨ Features

• Route Desktop to state-machine loop via ACP prompt meta #11247
• EUrouter as a declarative provider #11619
• Connect external backend ACP socket to redirect-resolved backend URL #11829
• GPT-live API support #12011
• Operator allowlist for gateway pairing #11979
• Opt-in terminal bell when a turn finishes or approval is needed #10182
• Report real cause of external backend connection failures #11828
• Scope Toolshim to custom providers #11414

🐛 Bug Fixes

• Treat auto-compact 100% as disabled #11932
• Validate recipes consistently in scheduler #11561
• MCP preferred version and HTTP retries #12066
• Require Developer extension for doctor command #11437
• Keep streamed thinking ahead of text and tool calls #11837
• Preserved-thinking compliance for Anthropic provider layer #11836
• Context management dependency resolution #11768
• Stop mapping Astra Off to reasoning.effort none #11976
• Return failure for interrupted headless runs #11938
• Send session ID header for OpenCode Go #11944
• Pair Google functionResponse names with preceding request #11888
• Show output for failed tool calls in desktop #11940
• Translate session actions menu in missing locales #11894
• Stop re-nudging on every tool call for goals #11697
• Bound image response bodies in developer extension #11411
• Bind MCP app tools to extension owners #11416
• Protect gateway pairing codes #11427
• Bound local audio resampling for dictation #11379
• Restrict session storage permissions #11613
• Build recipes from one validated snapshot #11612
• Filter scheduled session content #11603
• Stream chat completions by default for LiteLLM #11870

🔧 Improvements

• Preserve resource links that cannot be inlined in ACP #11941
• Remove planning mode from the CLI #12061
• Remove create recipe command in CLI #11942
• RTL support for chat content #11851
• Use 词元/詞元 for model tokens in Chinese localization #11945
• Guard recipe-before-inference ordering on scheduled runs #11502

📚 Documentation

• Remove Inkeep search integration #12085
• Clarify extension directory policy #11923
• RISC-V build support #11933

Original source

✨ Features

Support GPT-6 Astra models #11869

Tool calling for goose-agent #11627

Kotlin callers can now configure Databricks AI Gateway path #11631

🐛 Bug Fixes

Require HTTPS for Snowflake connections #11745

Bind CLI session naming to trusted path #11787

Honor content capture opt-out in tracing #11782

Enforce subagent platform guards #11604

Show authoritative tool approval details #11743

Preserve permission revocations across managers #11383

Resolve UI freeze after renaming session #11759

Count durable background turns in summon #11841

Anchor chat-payload breakpoints on the agentic tail #11429

Preserve cwd and child status in node launchers #11753

🔧 Improvements

Prefer latest MCP version #11827

Remove keyring timeout #11798

Publish goose ACP client and acp binary as separate npm packages #11846

Remove managed model registry from local inference #11789

Remove fast model routing #11469

AIML API integration #11758

📚 Documentation

Move ACP reference under GDK section #11805

Generate ACP reference documentation from release schemas #11770

ClawMetry session observability tutorial #11554

Original source

✨ Features

Auto-updater for desktop application #10614

Linux ARM64 desktop release packages #11518

Load extensions in the background so the CLI prompt is immediately usable #10403

Title sessions by subject, not workflow step #11135

Interactive git branch indicator in chat bottom bar #11290

on_failure block for PreToolUse hooks #11449

Web-search and browser-use built-in skills #11233

Model-native audio transcription provider #10589

--with-extension can now name its extension #11127

Auto-focus chat input when user starts typing #11184

Collapse scheduled job sessions into accordion in chat history #11265

Select saved recipes when creating a schedule #10892

Show recent used models in chat footer model picker #11097

PreToolUseResult event and stable tool_call_id across tool lifecycle #11120

Sort configured providers to the top of the provider list #11409

OpenRouter session_id forwarding and app category header #10868

ACP thinking effort derivation and forwarding #10949

GPT-5.6 follow-up support for Codex and Responses API #10460

Pre-registered OAuth clients for streamable_http extensions #11182

OTEL request params, response metadata, tool call parity, and agent identification #11261

New Providers

Opper as a declarative OpenAI-compatible provider #11589

Databricks Unity Catalog model services discovery #11575

TrustedRouter declarative provider #11422

OpenCode Zen gateway as a declarative provider #10939

Gondola as declarative OpenAI-compatible provider #11421

SayGM as declarative OpenAI-compatible provider #11267

Lynkr as declarative OpenAI-compatible provider #11372

PleumRouter declarative provider #10479

Z.ai GLM-5.3 (replacing GLM-5.2) #11226

OpenAI GPT-5.6 (sol/terra/luna) via Bedrock #10502

Custom provider cost fields for cost tracking #11220

🐛 Bug Fixes

Unify context limit resolution behind provider API #11213

Keep using valid MCP access tokens without a refresh token #11324

Provider save no longer overwrites stored config with defaults #11517

Deduplicate parallel tool-pair summaries #11195

Exclude Git metadata from project hints #11148

Honor remote working directory for new chats and allow typed paths #11322

Sanitize hidden Unicode in Bedrock tools #11121

Avoid sending images to non-vision capable models #11496

Reject cmd.exe commands containing newlines #11537

Honest compaction failure message and fast-fail when no tool responses exist #10500

Chat input freeze after opening model picker #11525

Bound non-streaming JSON responses #11109

Reject non-object response schemas in recipes #11478

Coalesce consecutive Thinking blocks in collect_stream #11317

Decouple source file and tool response limits #11391

Discover GGUF repos with non-standard filenames #11005

Flip select menus up when the window clips them #11495

Bedrock prefer HTTP bearer auth when configured #11562

MCP sampling for reasoning-first responses #11092

Keep recalled history agent-visible #11490

Fail closed on invalid default GCP credentials #11363

Bound handoff memo so long sessions stay resumable #11404

Goose unable to work with DeepSeek and Alibaba using OpenAI responses API #11298

Show tool inputs before approval #10932

Deduplicate enabled builtins #11340

Send explicit thinking disabled to adaptive Claude models #11177

Handle error code for context length exceeded #11283

Include required annotations field on replayed output_text items #11263

Isolate concurrent subagent notifications #10772

Validate recipe parameter values #11234

Re-enable minijinja builtins so documented recipe filters work #11310

Security Fixes

Enforce per-turn model tool allowlists #11426

Stop exposing provider secret suffixes #11476

Restrict code mode callback output #11471

Restrict app management tools #11470

Preserve local inference message text #11452

Preserve session extension identities #11420

Bound local image reads in developer extension #11419

Confine agent listing to source roots #11444

Recognize Windows package runners #11466

Fail closed on malformed tool visibility #11474

Give permission denies precedence #11477

Confine recipe library writes #11482

Scope app events by extension #11486

Restrict project updates to visible sessions #11487

Reject symlinked check sources #11489

Honor plugin enablement for skills #11439

Protect system prompt transport in claude-code #11441

Bind ACP permissions to request generations #11415

Honor MCP tool model visibility in Code Mode #11425

Refuse symlink diagnostics outputs #11398

Serialize secret mutations #11388

Suppress sensitive OTLP traces #11381

Bound call graph traversal #11193

Fail closed on invalid Codex ACP mode #11362

Bind Foundry API keys to request origin #11347

Validate memory categories #11191

Bound recursive mention scans #11228

Fail closed on malformed app visibility #11341

Redact Telegram tokens from request errors #11343

Encode session navigation parameters #11232

Redact URLs in provider errors #11230

Confine temporary extraction cleanup #11125

Clear custom provider transition secrets #11467

Pin renderer ACP certificates #11485

Require fresh file parameter input #11455

Escape OAuth callback content #11479

Sanitize Unicode tags in MCP prompts #11453

🔧 Improvements

Improve long chat rendering performance #11583

Limit sessions before counting messages for performance #11521

Enforce locked Cargo dependencies in CI #11560

Move inference operation into goose-agent crate #11294

Make roaming an opt-in goose-cli feature (default-off) #11516

Improve ACP provider setup and unify setup metadata #11100

Create goose-agent crate with unrolled agent loop state machine #11216

Make unrolled loop state machine generic #11139

Compact with main session model, not fast model #11255

Add MCP conformance tests to goose CI #10940

Aura dark theme for Goose #10283

Bedrock routing table with Gemma 4 Mantle support #10297

Gate clear_thinking behind opt-in flag (Z.AI-only) #10439

Include working directory in stop hook context #11112

Keep stdio extensions alive across worker exits #10364

Include thinking tokens in Google usage output_tokens #10354

Give GOOSE_SUBAGENT_PROVIDER/MODEL priority over LLM-injected params #9650

Preserve extensions when adding MCP servers #11339

Preserve platform tool allowlists #11369

Make Gemini plugin installs transactional #11303

📚 Documentation

GDK language param in doc links #11592

Retire Recipe Cookbook security scanner #11597

Require issues before pull requests #11565

GDK API Reference nav item + deep-link anchors #11564

SDK API reference for Rust, Python, and Kotlin #11251

Correct Telegram gateway setup #11527

Keep GitHub comments concise #11447

Original source

✨ Features

Providers

• TrustedRouter declarative provider #11422
• OpenCode Zen gateway as a declarative provider #10939
• Gondola as declarative OpenAI-compatible provider #11421
• SayGM as declarative OpenAI-compatible provider #11267
• Lynkr as a declarative OpenAI-compatible provider #11372
• PleumRouter declarative provider #10479
• Z.ai GLM-5.2 replaced with GLM-5.3 #11226
• Custom provider cost fields drive cost tracking #11220
• Model-native audio transcription provider #10589
• OpenAI GPT-5.6 (sol/terra/luna) routing via AWS Bedrock #10502
• GPT-5.6 follow-up support for Codex and Responses API #10460

Hooks

• on_failure block for PreToolUse hooks #11449
• PreToolUseResult event and stable tool_call_id across tool lifecycle #11120

Desktop & UI

• Select saved recipes when creating a schedule #10892
• Sort configured providers to the top of the provider list #11409
• Collapse scheduled job sessions into accordion in chat history #11265
• Auto-focus chat input when user starts typing #11184
• Interactive git branch indicator in chat bottom bar #11290
• Show recent used models in chat footer model picker #11097

CLI

• --with-extension can now name its extension #11127
• /new command to start a fresh session without restarting #10767

Skills & Extensions

• Web-search and browser-use built-in skills #11233
• Support pre-registered OAuth clients for streamable_http extensions #11182

ACP

• Derive and forward thinking effort from the ACP harness #10949
• Title new sessions from _meta.sessionTitle #10712
• _goose/unstable/session/extensions/apply method #11081

Observability

• OpenTelemetry request params, response metadata, tool call parity, and agent identification #11261
• OpenRouter session_id forwarding and app category header #10868

Other

• Blox run target for the ACP server #11423
• Linux ARM64 desktop release packages #11518
• Roaming as opt-in goose-cli feature #11516
• MCP conformance tests in CI #10940

🐛 Bug Fixes

Security

• Recognize Windows package runners #11466
• Fail closed on malformed tool visibility #11474
• Permission denies take precedence #11477
• Clear custom provider transition secrets #11467
• Require fresh file parameter input #11455
• Escape OAuth callback content #11479
• Sanitize Unicode tags in MCP prompts #11453
• Honor plugin enablement for skills #11439
• Honor MCP tool model visibility in Code Mode #11425
• Suppress sensitive OTLP traces #11381
• Fail closed on invalid default GCP credentials #11363
• Bound call graph traversal #11193
• Fail closed on invalid Codex ACP mode #11362
• Validate memory categories #11191
• Bound recursive mention scans #11228
• Avoid predictable editor symlink #11188
• Fail closed on malformed app visibility #11341
• Encode session navigation parameters #11232
• Redact URLs in provider errors #11230
• Validate recipe parameter values #11234
• Bind Foundry API keys to request origin #11347

Providers

• Stop provider save from overwriting stored config with defaults #11517
• Sanitize hidden Unicode in Bedrock tools #11121
• Bound non-streaming JSON responses #11109
• Inform user of clipboard copy and remove copilot auth retry on timeout #11160
• Escape Gemini tool response ref keys in OpenRouter #11276
• Estimate cost for Azure Foundry models via inferred catalog pricing #11264
• Coalesce consecutive Thinking blocks in collect_stream #11317
• Replace flat model list with routing table, add Gemma 4 Mantle support #10297
• Include thinking tokens in Google usage output_tokens #10354
• Send explicit thinking disabled to adaptive Claude models #11177
• Include required annotations field on replayed output_text items #11263
• Deprecated Gemini OAuth provider #11223
• Stop paying the prompt-cache write premium on one-shot fast-model calls #11179
• Classify byte-size request limit errors as context-length-exceeded #11173
• Bound local image reads #11114
• Map kimi_code provider name and pass correct provider to create_request #11130
• Handle error code for context length exceeded #11283
• DeepSeek and Alibaba compatibility with OpenAI responses API #11298

Desktop & UI

• Honor remote working directory for new chats and allow typed paths #11322
• Scope app events by extension #11486
• Pin renderer ACP certificates #11485
• Bind ACP permissions to request generations #11415
• Chat input freeze after opening model picker #11525
• Gate external URL protocols centrally #11311
• Stop stale microphone test streams #11309
• Prevent recipe parameter form from reloading the app on Enter #10522
• Suppress extension loading toast when all extensions succeed #11016

CLI & Shell

• Reject cmd.exe commands containing newlines #11537
• Refuse symlink diagnostics outputs #11398
• Deduplicate enabled builtins #11340
• Avoid reading file params in recipe explain #11119
• Honor provider overrides on session resume #10810

Core

• Deduplicate parallel tool-pair summaries #11195
• Exclude Git metadata from project hints #11148
• Avoid sending images to non-vision capable models #11496
• Keep recalled history agent-visible #11490
• Honest compaction failure message and fast-fail when no tool responses exist #10500
• Pass complete response to stop hooks #11366
• Contain and bound skill supporting file reads #11342
• Compact with the main session model, not the fast model #11255
• Make Gemini plugin installs transactional #11303
• Include working directory in stop hook context #11112
• Re-enable minijinja builtins so documented recipe filters work #11310
• Show tool inputs before approval #10932
• Reject context commands for context-owning providers #11094
• Bind deeplink recipe parameters to startup session #11123

ACP

• Restrict project updates to visible sessions #11487
• Seed provider handoff history #8941
• Preserve tool result audience metadata #11375
• Bound the handoff memo so long sessions stay resumable #11204
• Return auth error for ACP provider from goose ACP server #11202
• Ignore ACP provider generated title and use goose generated title #11197
• Prevent large-session disconnects #11159

Recipes

• Confine library writes #11482
• Reject non-object response schemas #11478
• Confine temporary extraction cleanup #11125

Extensions & MCP

• Reject symlinked check sources #11489
• Reject socket-backed MCP extensions for Codex #11304
• Keep stdio extensions alive across worker exits #10364
• Preserve extensions when adding MCP servers #11339
• Preserve platform tool allowlists #11369

Other

• Claude-Code: protect system prompt transport #11441
• Fail fast when a recipe's structured response can't reach an ACP-bridged provider #11307
• Fetch attestation bundles from bundle_url #10557
• Contain REVIEW.md discovery #11367
• Sanitize Pi imported output #10990
• Honor RUST_LOG directives for OTEL logs #11360
• Give GOOSE_SUBAGENT_PROVIDER/MODEL priority over LLM-injected params #9650
• Respect ACP audience in bang-shell shortcut #11150
• Redact Telegram tokens from request errors #11343
• Isolate concurrent subagent notifications #10772
• Serialize secret mutations #11388
• Enforce secure OAuth token transport #11183
• Skip local extension spawn when provider manages own context #11203
• Decouple source file and tool response limits #11391
• Bound action-required stream admission #11113
• Bound partial thinking tags #11108
• Enforce review check tool policy #11128
• Secure Copilot API endpoint transport #11129
• Remove goose tui command #11484
• Update SQLite to 3.51.3 #11157
• Narrow desktop file read IPC #11149
• Render visualizer data as text #11186
• Bound XLSX range reads #11190

🔧 Improvements

• Session listing performance: limit sessions before counting messages #11521
• Keep turn-context out of the OpenAI-compatible prefix cache #10937
• Parallelize provider resolution and eagerly init SQLite pool #8899
• Deduplicate _goose/providers/list RPC call at startup #8873
• ACP provider setup and unified setup metadata #11100
• Disable thinking for tool call labels #11207
• Canonicalize mangled tool names before permission inspection #10285
• Gate clear_thinking behind an opt-in flag (Z.AI-only) #10439
• Scan uvx from selectors for malware #10988
• Aura dark theme for Goose #10283
• Unrolled agent loop state machine #11216
• Generic unrolled loop state machine #11139
• Retry ACP handoff context after failed prompts #10660
• Use rmcp ContentBlock in goose-sdk UniFFI #11210
• Upgrade ACP SDK to 1.3.0 #11218
• Mergeable configs and cleanup #8378
• Move mlx deps under macOS for goose-local-inference #11328
• Share axum-server via workspace.dependencies #11326
• Remove automation_script, web_scrape, and cache tools from computercontroller #11198
• Agent provider using explicit type states #8879

📚 Documentation

• SDK API reference for Rust, Python, and Kotlin #11251
• Correct Telegram gateway setup #11527
• Keep GitHub comments concise #11447
• Improve readability in AGENTS.md #8979

Original source

✨ Features

Interactive git branch indicator in chat bottom bar #11290

Support for pre-registered OAuth clients for streamable_http extensions #11182

Show recently used models in chat footer model picker #11097

🐛 Bug Fixes

Isolate concurrent subagent notifications in summon #10772

Validate recipe parameter values #11234

Re-enable minijinja builtins so documented recipe filters work #11310

Send explicit thinking disabled to adaptive Claude models #11177

Handle error code for context length exceeded #11283

Include required annotations field on replayed output_text items #11263

Reject context commands for context-owning providers #11094

Prevent recipe parameter form from reloading the app on Enter #10522

Enforce secure token transport in OAuth #11183

Deprecate Gemini OAuth provider #11223

Stop paying the prompt-cache write premium on one-shot fast-model calls #11179

Skip local Stdio/StreamableHttp extension spawn when provider manages own context #11203

Navigation toggle showing hamburger menu icon to open navigation #11144

Return auth error for ACP provider from goose ACP server #11202

Ignore ACP provider generated title and use goose generated title #11197

Render visualizer data as text #11186

Bound XLSX range reads #11190

Update SQLite to 3.51.3 #11157

Classify byte-size request limit errors as context-length-exceeded #11173

Prevent large-session disconnects in ACP #11159

Narrow desktop file read IPC #11149

Avoid reading file params in recipe explain #11119

Bound local image reads #11114

Bound action-required stream admission #11113

Bound partial thinking tags #11108

Avoid following untracked review symlinks #10995

Bind deeplink recipe parameters to startup session #11123

Rename compare_tasks skill to a spec-valid name #11068

Suppress extension loading toast when all extensions succeed #11016

🔧 Improvements

Improve ACP provider setup and unify setup metadata #11100

Create goose-agent crate with unrolled agent loop state machine #11216

Make the unrolled loop state machine generic #11139

Retry ACP handoff context after failed prompts #10660

Remove automation_script, web_scrape, and cache tools from computercontroller #11198

Upgrade ACP SDK to 1.3.0 #11218

Pin V1 SDK and narrow ACP crate features #11289

Migrate session/delete to the standard ACP SDK #11286

Use rmcp ContentBlock in goose-sdk UniFFI #11210

Original source

Features

Unrolled agent loop #9574

Cache-safe request assembly with append-only turn context and declared cache semantics #11022

Streaming shell output while commands run #10808

Per-message usage stats UI (tokens, cost, TTFT, tok/s) #10210

Per-message usage/cost tracking with derived session totals #10172

Track cache tokens for accurate cost reporting #9752

Markdown format option to session export #10703

Resizable sidebar with drag handle and persisted width #10795

Interactive menu for single select elicitations #10327

Session metadata on sidebar chat hover #10663

Configurable LOCAL_WHISPER_LANGUAGE for multilingual local transcription #10634

Allow disabling built-in skills #10600

Structured summary output with template rendering for compaction #10471

Pass working_dir to the Stop hook context #10296

Surface output-token-limit info #10831

Tab completion and switch provider for model command #10585

Collapse const-union enums in tool schemas #10577

GenAI semantic convention attributes for OTEL #10700

Enrich root span with gen_ai attributes and improve OTEL output format #10816

Forward images and MCP embedded-resource blobs in Anthropic and Google formats #10340

ACP session/new supports Hidden session via _meta.hidden #10811

Stable agent event message identity #10716

OAuth logo_uri in client ID metadata documents #10727

Termux detection in installer to select musl portable build #10568

Hooks feature with PreToolUse denial #9093, #9304

/goal command for agent self-evaluation before finishing #9069

/status slash command #9845

/model slash command to switch session model #8747

--edit session flag to edit conversation before forking #9799

goose review local code review command #9114

Open plugins generalization with skills support #9112

Summon extension: peek mode for async background tasks #9519

Summon extension: context and working_dir parameters for delegate tasks #9518, #9520

Load global hints from ~/.agents/AGENTS.md #9736

Proactive OAuth token refresh to avoid re-auth on every session #8386

GOOSE_OAUTH_CALLBACK_PORT for stable OAuth redirect_uri #9209

Unified thinking effort control across all providers #9242

Projects as backend sources with system prompt injection #8739

Group chat sessions by project in nav panel #10212

Collapsible project group headers in nav panel #10278

Worktree-aware directory switcher #8450

Chat history search feature in navigation panel #8448

Search filter to provider grid #10437

Option to disable automatic update downloads #9872

TUI diff viewer #9260

MAX_CODE_BLOCK_LINES configurable via env vars #9301

GOOSE_MAX_TOOL_RESPONSE_SIZE to configure tool output size limit #9256

GOOSE_FAST_MODEL env var in ModelConfig::with_fast #9296

GOOSE_DOCS_ROOT for air-gapped docs access #10294

Quarterly option for scheduler #9076

Harbor eval runner #9138

goose://new-session and goose://resume deep links #9196, #9343

Initial prompt with goose://new-session #9427

Encrypted Nostr session sharing #8922

Import sessions #9474

Hugging Face OAuth support with auth tab in settings #9552

MLX models support in local inference provider #9154

Linux Vulkan support for local inference #9038

Reconnect desktop ACP sessions after sleep and connection loss #10411

TLS support for ACP serve #10088

Group consecutive tool calls into one summarized chain card #8995

Bind MCP apps to trusted ownership metadata #10747

MCP extensions in open plugins #9471

Skills to the chat composer #8881

Dynamically refresh skill instructions each turn #9217

CLI to list skills with token counts #9326

Image read tool #9607

View model interactions #9806

UniFFI SDK for cross-language bindings #9593

Provider bindings MVP to goose-sdk with Python wheel publishing #10208

Kotlin FFI with build and Maven publish #10375

Create source archive as release artifact #10786

New Providers

Celeris provider #10714

Friendli declarative provider #10762

Azure AI Foundry multi-LLM provider #10622

OllamaCloud provider with dynamic model discovery #10264

Sakana AI provider for OpenAI-compatible Fugu API #10357

iFlytek Spark and Astron MaaS providers #9837

Fireworks AI declarative provider #9990

OpenRouter request parameters support #9276

Together AI declarative provider #9545

OrcaRouter declarative provider #9515

Perplexity declarative provider #9324

Alibaba (Qwen via DashScope) declarative provider #9443

Databricks AI Gateway provider #9274

Scaleway provider #9254

NEAR AI Cloud provider #9352

EmpirioLabs declarative provider #9771

xAI SuperGrok OAuth subscription provider #9420

Vercel AI Gateway #9144

Routstr declarative provider #9175

FuturMix provider #8840

oMLX declarative provider #9177

Atomic Chat declarative provider #9210

Muse Spark 1.1 via Meta Models API #10432

AWS Bedrock support for OpenAI GPT models via mantle endpoint #9707

Azure AD (Entra ID) bearer token auth via AZURE_OPENAI_AD_TOKEN #9716

New Models

GPT-5.6 support #10384, #10349

GPT-5.5 to ChatGPT Codex known models #9292

GLM-5.2 support #9967

Opus5 support with adaptive thinking #10686

Claude-sonnet-5 and claude-fable-5 to known models #10865, #10183

Cursor composer-2.5 models #10618

Cursor-agent models from CLI #10367

Latest Gemini models #10630

Gemini 3.x known locations and KNOWN_MODELS entries #9142

MiniMax-M3 and M2.7 variants #10431

OVHcloud Qwen3.6-27B model #10339

Internationalization

French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, zh-TW desktop locales #10072

Korean localization #9856, #10667

Spanish (es) locale #9833

Japanese locale #9768

Hindi Desktop locale #9733

Russian language support #9406

Turkish desktop locale #9392

Simplified Chinese (zh-CN) translation #8765

Language selection feature #9405

Bug Fixes

Reject invalid subrecipe content #10994

Keep turn-context in place for OpenAI Responses-stack models for prompt caching #10993

Byte-bound the shell truncation preview #10992

Stop silently ignoring thinking effort off for OpenRouter #10991

Dispatch edited queued messages #10933

Contain recipe template paths #10930

Make shell approval titles faithful #10986

Block MCP app form submissions #10985

Sanitize Bedrock tool errors #10934

Implicit OAuth during model discovery #10929

Keep ACP session naming out of live conversations #10963

Sanitize Unicode tags in MCP resources #10746

Preserve RFC 9207 iss from MCP OAuth callback #10678

Shell ACP providers on desktop #10907

Stop killing streaming responses at the total request timeout #10620

Restore final_output_tool when agent is recreated after LRU eviction #10793

Avoid O(n²) cloning during session load #10665

Prefix child stderr log target so it passes the default goose=info filter #10901

Fall back to static model list only for non-models payloads #10189

Stdio extensions silently skipped when name missing or env: used in config #10773

Start scheduler at startup instead of first ACP connection #10766

Respect disabled builtin extensions (developer) at session start #10223

Parse PyPI requirements for OSV checks #10510

Contain voice file extensions in telegram #10456

Preserve denied tool request precedence #10612

Contain subdirectory hint discovery #10545

Clear stale validation error when reopening the schedule modal #10627

Sanitize shell/subprocess call in linux.rs #10748

Unlink destination before copying binaries #10705

Honor timeout_seconds on the Anthropic declarative provider #10440

Allow removing images when editing user messages #9979

Preserve thinking inline for Cerebras models that reject reasoning_content #10774

Make CLI streaming render incremental instead of O(n^2) #10487

Together provider: parse model list response #10576

DeepSeek model names to v4 API #10729

Forward Claude Code and Pi model picker selection to the adapter #10675, #10707

Preserve enabled flag when migrating platform extensions #10690

Pass session working_dir to on_call_tool #10689

Preserve adversary tool arguments #10529

Keep XML snippets inside JSON as data for local-inference #10606

Sync generated chat title in header #10578

Prompt for tool approval in Telegram gateway sessions #10613

Keep CLI provider prompts out of process arguments #10547

Ignore stale inventory for static model lists #10591

Preserve featured model size on delete and backfill missing sizes #10422

Create inventory tables atomically with schema version #10586

Rewrite oneOf to anyOf in tool schemas for OpenAI-compatible backends #10571

Allow custom model as default for non-local providers #10438

Require absolute goose path roots #10454

Scope smart approval by request #10457

Preserve fixed subrecipe values #10452

Bundle git so hermit can clone its package registry in Flatpak #10511

Forward image content chunks to client during live ACP session #10485

Dispatch Code Mode callbacks on main runtime to prevent hangs #10484

Protect OAuth token caches #10516

Preserve content audience boundaries #10493

Bound scheduled recipe validation #10509

Return JSON-RPC errors from dispatch handlers instead of killing the connection #10499

Avoid local inference Metal teardown crash #10508

Enable indexmap serde support for musl builds #10507

Scroll chat to the latest reply on session resume #10501

Secure large response spill files #10482

Register LiteLLM with refresh_only inventory so model picker lists models #10489

Limit provider selector height in CLI #10420

Tighten existing secrets file permissions #10453

Classify image access capabilities in developer extension #10451

Preserve one-time permission scope #10450

Register goose:// scheme handler in Flatpak desktop entry #10461

Reject duplicate recipe parameter keys #10448

Synchronously kill orphaned goose serve backends on GUI close #10292

Break self-referential $ref cycles before Code Mode schema #10469

Stop multiline paste auto-submitting line-by-line on Windows #10326

Hide nested config values in Configuration Editor #10390

Stop resolving TUI scripts from cwd #10449

Exclude MCP App tools from Code Mode callbacks #10290

Apply the default extension timeout to developer shell tool calls #10348

Preserve reasoning_content for DeepSeek thinking mode on multi-turn tool calls #10366

Make prompt timestamps timezone-explicit #10209

Compact disabled during approval #10089

Treat empty-string finish_reason as non-terminal in streaming #10258

Gemini OAuth onboarding #10363, #8905

Retry empty provider turns instead of stopping silently #10360

Guard llama.cpp backend init against SIGILL on x86_64 CPUs without FMA/AVX2 #10105

Sanitize responses function call names #10344

Pick session mode from the ids the agent actually offers #10320

Dedupe duplicate signed thinking blocks to fix Anthropic 400 #10083

Resolve provider default model instead of leaking sentinel "current" #10305

Return effective context limit from /model-info #10165

Gate rcgen aws_lc_rs feature behind rustls-tls #10116

Tolerate partial Responses output items #10108

Always use OpenAI-compatible "parameters" for tools in Databricks #10101

Unescape shell-escaped image paths #10098

Seed mac auto-update config #10132

Send inference config (max_tokens, temperature) on Bedrock Converse #9889

Dedupe Nostr session deep link imports #9918

Don't retry deterministically-permanent 400s (thinking-block immutability) #10005

Use async reqwest client so OTLP export works in goose serve mode #10100

Reject non-object tool-call arguments instead of panicking #9832

Save /edit prompts to history #10011

Use session.message_count for schedule sessions listing #10026

Support streamed tool calls without indexes #10023

Disable extended thinking for fast-model operations #9815

Buffer thinking across stream chunks for DeepSeek/Kimi tool calls #9704

Surface actionable errors for truncated tool-call arguments #9946

Show optimistic toggle state when disabling an extension #9882

Resolve databricks_v2 pricing and surface cost in standard usage update #9925

Publish mac updater metadata #9945

Activate hermit on macOS so STDIO extensions resolve node #9482

Accept JSON-encoded string for autovisualiser data parameter #9838

Send User-Agent on URL image fetches in developer/read_image #9927

Do not pass temperature to ChatGPT Codex provider #9931

Sanitize extension environment maps #9884

GCP: use refreshed gcloud token after reauth (retry Vertex AI on 401/403) #9849

Start a turn when /goal or /grind is set #9801

Pass thinking config to Bedrock Anthropic models #9794

Keep extensions icon visible after switching sessions #9787

Skip non-recipe project config files in summon #9808

Dedup duplicate tool-call ids within a turn #9792

Resolve bundled extensions from discovery #9759

Custom OpenAI provider dropping port when URL scheme is omitted #9730

Preserve Windows backslash paths in custom extension command #9741

Include agentInfo in ACP initialize response #9765

ACP cancel race condition #9804

Inherit login-shell PATH in spawned subagents #9737

Accept string values for GOOSE_CONTEXT_LIMIT #9738

Clear rejected OAuth credentials after refresh #9694

Keep extended thinking within the Anthropic output cap #9814

Disable RPM build-id links #9671

Preserve custom API path in base_url derivation for OpenAI #9649

Handle resume deep links #9298

Repair PATH for plugin hook commands #9615

Restore Cmd/Ctrl+T new chat shortcut #9614

Lead with extension description, shorten HTTP/SSE transport label #9653

Mention menu icon to open the sidebar #9643

Dedupe React to prevent multiple instances in renderer #9631

Add hermit cleanup to uvx and jbang scripts #9616

Use blocking OTLP HTTP exporter #9599

Fall back to default provider when resuming session with unavailable provider #9547

Provide Tokio runtime for OTLP HTTP exporter batch thread #9541

Read meta.n_ctx from /v1/models to fix context limit for local servers #9530

Align session history scrollbar with window edge #9601

Refresh session name in sidebar after rename #9543

Show resolved skill supporting file paths #9584

Implement real Bedrock streaming via ConverseStream API #9579

Record OpenAI-native cached_tokens in usage metering #9829

Add option for overriding API URL for Moonshot provider #9819

Detect image paths with spaces #9387

Restore new chat shortcut navigation #9528

Evict stale completed tasks to prevent unbounded memory growth in summon #9514

OAuth: time out the MCP callback wait instead of hanging in WSL #9536

Warn on unmatched extension names in summon delegate #9513

Deleting a recently created session and then creating a new shows the deleted session's content #9351

Propagate elicitation decline and cancel actions end-to-end #9437

Close modal when canceling recipe parameter form #9195

Ensure tool request timestamp precedes tool response timestamp #9462

Correctly map ollama_cloud to canonical provider #9639

Incorrect max tokens values for groq provider #9790

Mark stream decode errors retryable #9723

Classify Bedrock ValidationException as ExecutionError #9735

Page through all Databricks AI Gateway v2 endpoints when listing models #9753

Preserve unparseable extension entries during config refresh #9439

Sync slash help with builtins in CLI #10173

Treat unicode punctuation as image path terminators #10106

Don't bleed provider-specific request_params into delegate() sessions #9906

Purge empty phantom sessions on startup #9651

Include structuredContent from MCP tool response #10128

Propagate agent cleanup errors on session delete #10112

Prevent login-shell PATH probe from suspending goose on startup #8804

Exclude preprompt from session title generation #8793

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

Model picker stays usable during provider loading #8900

Handle ACP requests concurrently #8781

Apply hermit env directly in node shims so a fish login shell doesn't break MCP startup #10028

Preserve command arguments through extension forms #10527

Enforce manual approval for code mode #10528

Confine app file operations #10481

Preserve recursive schema types with pctx 0.4.1 in code-mode #10572

Use shell working directory on initial launch #10655

Enable inventory refresh for OpenRouter model picker #10641

Preserve read lines and reload tool output in ACP #10662

Surface tool call output in CLI and Desktop #10654

Overlong function names in provider requests #10659

Preserve ACP tool call update fields #10653

Omit disabled OpenRouter reasoning #10517

Clear stale pending ACP connection after terminal recovery failure #10552

Confirm pending steer message on queuedSteer notification #10532

Restore dynamic model discovery and current Grok support #10756

Reuse parent provider for summon delegates #10754

Skip permission mode negotiation for Pi #10701

Freeze turn-context timestamp at turn start to preserve prefix cache #10734

Refresh Moonshot model list with current Kimi lineup #10696

Update Kimi-code known models metadata with current platform lineup #10713

Avoid double loading full conversation on session open #10794

Recover malformed tool calls from GLM/Minimax models instead of rejecting them #10230

Restore cursor when configure exits #4889

Improvements

Keep turn-context out of the OpenAI-compatible prefix cache #10937

Keep turn-context out of the Anthropic prefix cache #10030

Parallelize provider resolution and eagerly init SQLite pool #8899

Deduplicate _goose/providers/list RPC call at startup #8873

Compact tool schema JSON #10409

Drop debug info for dependencies in the dev profile #9843

Use LRU cache for token counting #9586

Mergeable configs with cleanup #8378

Structured per-provider config block with non-destructive provider switching #8977

Linux musl CLI builds #9240

Windows CUDA release artifacts #8750

Linux desktop Vulkan packages #9323

Migrate desktop routing to React Router 8.3.0 #10971

Upgrade to rmcp 3.0 #10789

Handle MCP tool list change notifications #e7088ee

Redesign Extensions page #8940

Redesign skills library #8868

Dark mode inline code styling for message bubbles #10861

Refine dark theme message surfaces #10693

Inline code contrast improvement in light theme #9058

Polish sidebar navigation and project icons #8896

Simplify UI customization #9353

Better parsing of pasted HTML as markdown so agents understand #9190

Remove CLI project support #10838

Deprecate and remove ui/text TUI #10799

Remove MCP sampling support #10087

Make context exceeded checker more precise #9831

Update canonical model inventory #10352, #9709, #9551, #9331

Add canonical thinking modes #9743

Nushell terminal and completion support #8628

Migrate diagnostics to JSON report #9964

Route MCP elicitations through tool streams #9943

Allow unlisted models in search #9933

ACP paginate session list #9199

Flush OTLP traces reliably on exit with configurable timeout #9228

Increase /mcp-app-guest body limit for larger single-file MCP apps #10324

Use current_exe() instead of PATH lookup when spawning goose #9236

Set TCP_USER_TIMEOUT on streamable HTTP clients in extension_manager #9207

Fail closed on unverifiable update provenance #10168

Trim macOS desktop entitlements #10490

Consolidate and harden release workflows #10447

Update Rust toolchain and raise recursion limit #10303

Enhance the uniffi API layer #10427

Bound code-mode execution with timeout and cancellation #10214

Switch local inference MLX backend to use safemlx crate #10304

Preserve thinking content for providers that require it #8857, #9314

Build summon instructions per turn #9329

Refactor local inference around backends #9137

Stricter GGUF requirements with auto detection of tool calling support and fixed thinking output parsing #9442

Prefer goose aliases for Databricks v2 inventory #9430

ACP migration: UI connect to ACP directly instead of goosed #10081

Unified OTLP logging schema for cross-tool detection #9713

Pattern-based detection updates for prompt injection #9350, #9198, #9690, #8546

Enable prompt injection mitigation by default for internal users #9612

OpenAI Responses API store param configurable #10040

GitHub Copilot /responses API #9043

Check for responses API support in Databricks #9347

Honor Retry-After on 429 responses #9161

Coalesce streaming Thinking deltas and list available tools on not-found #9162

Strip chain-of-thought markers from custom provider output #8635

Coalesce streaming chunks under one message id in ACP #8788

Documentation

Document auto-injected GOOSE_SHELL flags #10759

Clarify macOS sandbox feature was removed in post-v1.25.0 cleanup #10900

Update Discord invite #10863

Update environment and config references #10203

Document hook deny contract, matcher regex, tool_input keys, and provider config #10467

Add Code of Conduct #10424

Adopt issue-first contribution workflow #10819

Update docs for ACP clients #9772

Hooks guide #9288

Custom agents guide #9293

Guide for connecting goose Desktop to a remote goosed server #9275

Document summon extension requirement for delegate and load tools #9231

Refresh Ophis extension page (tool list, chains, skills link) #10681

Clean up stale documentation audit findings #10114

Reorganize docs #9310

Blog: Goose with Peekaboo #8884

Blog: Built-in Local Inference #8808

Blog: Orchestrating with Goose #9104

Blog: Self-improving agents #9846

Blog: AAIF migration #9866

Blog: MiniMax and Office QA benchmark findings #8984

Original source

Features

Stable agent event message identity #10716

Tab completion and switch provider for model command #10585

Support latest Gemini models #10630

Configurable GOOSE_DOCS_ROOT for air-gapped docs access #10294

Structured summary output with template rendering for compaction #10471

Allow disabling built-in skills #10600

Gate tool-call label enrichment on ACP client capability #10644

Bug Fixes

Restore dynamic model discovery and current Grok support #10756

Update DeepSeek model names to v4 API #10729

Forward Claude Code model picker selection to the adapter #10675

Forward Pi model selection to the adapter #10707

Preserve enabled flag when migrating platform extensions #10690

Pass session working_dir to on_call_tool #10689

Preserve adversary tool arguments #10529

Keep XML snippets inside JSON as data for local inference #10606

Sync generated chat title in header #10578

Prompt for tool approval in telegram gateway sessions #10613

Keep CLI provider prompts out of process arguments #10547

Ignore stale inventory for static model lists #10591

Use shell working directory on initial desktop launch #10655

Enable inventory refresh for OpenRouter model picker #10641

Preserve read lines and reload tool output in ACP #10662

Surface tool call output in CLI and Desktop #10654

Truncate overlong function names in provider requests #10659

Preserve ACP tool call update fields in desktop #10653

Use configured session manager for tool summaries #10628

Omit disabled OpenRouter reasoning #10517

Clear stale pending ACP connection after terminal recovery failure #10552

Confirm pending steer message on queuedSteer notification #10532

Apply hermit env directly in node shims so fish login shell doesn't break MCP startup #10028

Improvements

Upgrade to rmcp 2.0 #10584

Opus5 support including adaptive thinking #10686

Refine dark theme message surfaces for consistent, compliant dark mode UX #10693

Fix Korean translation errors, untranslated entries, and terminology consistency #10667

Simplify ACP tool-call handling and fix chain summaries #10599

Enhance the uniffi API layer #10427

Disable scheduler by default for ACP #10781

UI cleanup to remove unused components and functions #10761

Bump nostr to 0.44.6 to clear RUSTSEC-2026-0216 #10733

Create source archive as release artifact #10786

Original source

✨ Features

Support for latest Gemini models #10630

Pass working_dir to the Stop hook context #10296

Declarative Sakana AI provider for OpenAI-compatible Fugu API #10357

Model interactions viewer restored #10205

Chunk command-classifier input with overlapping windows for security #10416

Search filter for provider grid #10437

Muse Spark 1.1 support via Meta Models API #10432

GPT-5.6 support #10384

Reconnect desktop ACP sessions after sleep and connection loss #10411

Per-message usage stats UI (tokens, cost, TTFT, tok/s) #10210

OllamaCloudProvider with dynamic model discovery and context limits #10264

Delete support for custom apps from Apps UI #10127

--edit session flag to edit conversation before forking #9799

iFlytek Spark and Astron MaaS providers #9837

Fireworks AI declarative provider #9990

OpenRouter request parameters support #9276

French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, zh-TW desktop locales #10072

MiniMax-M3 and missing M2.7 variants #10431

🐛 Bug Fixes

Preserve command arguments through extension forms #10527

Enforce manual approval for code mode #10528

Confine app file operations #10481

Preserve featured model size on delete and backfill missing sizes #10422

Preserve recursive schema types with pctx 0.4.1 #10572

Create inventory tables atomically with schema version #10586

Rewrite oneOf to anyOf in tool schemas for OpenAI-compatible backends #10571

Allow custom model as default for non-local providers #10438

Require absolute goose path roots #10454

Scope smart approval by request #10457

Preserve fixed subrecipe values #10452

Bundle git in Flatpak so hermit can clone its package registry #10511

Expose AGENT_SESSION_ID to shell commands #10428

Forward image content chunks to client during live session #10485

Dispatch Code Mode callbacks on main runtime to prevent hangs #10484

Protect OAuth token caches #10516

Preserve content audience boundaries #10493

Bound scheduled recipe validation #10509

Return JSON-RPC errors from dispatch handlers instead of killing connection #10499

Isolate prepare tools test state #10504

Avoid local inference Metal teardown crash #10508

Enable indexmap serde support for musl builds #10507

Scroll chat to latest reply on session resume #10501

Secure large response spill files #10482

Register LiteLLM with refresh_only inventory so model picker lists models #10489

Limit provider selector height in CLI #10420

Tighten existing secrets file permissions #10453

Classify image access capabilities #10451

Preserve one-time permission scope #10450

Register goose:// scheme handler in Flatpak desktop entry #10461

Reject duplicate recipe parameter keys #10448

Synchronously kill orphaned goose serve backends on GUI close #10292

Break self-referential $ref cycles before Code Mode schema #10469

Stop multiline paste auto-submitting line-by-line on Windows #10326

Hide nested config values in Configuration Editor #10390

Stop resolving TUI scripts from cwd #10449

Exclude MCP App tools from Code Mode callbacks #10290

Apply default extension timeout to developer shell tool calls #10348

Preserve reasoning_content for DeepSeek thinking mode on multi-turn tool calls #10366

Make prompt timestamps timezone-explicit #10209

Disable compaction during approval #10089

Restore pnpm 11 project configuration #10395

Treat empty-string finish_reason as non-terminal in streaming #10258

Fix Gemini OAuth onboarding #10363

Retry empty provider turns instead of stopping silently #10360

Guard llama.cpp backend init against SIGILL on x86_64 CPUs without FMA/AVX2 #10105

Sanitize responses function call names #10344

Pick session mode from the ids the agent actually offers #10320

Show manual-setup indicator for extensions without install link #10321

Dedupe duplicate signed thinking blocks to fix Anthropic 400 #10083

🔧 Improvements

Extract tool call handling from ACP server #10574

Report cache-aware Harbor costs #10430

Trim macOS desktop entitlements #10490

Consolidate and harden release workflows #10447

TLS backend matrix job for rustls-tls and native-tls #10148

Bound code-mode execution with timeout and cancellation #10214

Recover malformed tool calls from GLM/Minimax models instead of rejecting them #10230

Group chat sessions by project in nav panel #10212

Per-message usage/cost tracking with derived session totals #10172

Return effective context limit from /model-info #10165

Disable thinking preservation for Groq #10284

Clarify terminal color semantics in CLI #10414

📚 Documentation

Clean up stale documentation audit findings #10114

Update environment and config references #10203

Document hook deny contract, matcher regex, tool_input keys, and provider config #10467

Remove stale gooseignore references #10359

Add Code of Conduct #10424

Clarify session --edit context retention #10257

Original source

Features

Reconnect desktop ACP sessions after sleep and connection loss #10411

Per-message usage stats UI (tokens, cost, TTFT, tok/s) #10210

Per-message usage/cost tracking with derived session totals #10172

Group chat sessions by project in nav panel #10212

Show project names in directory switcher dropdown #10207

OllamaCloudProvider with dynamic model discovery and context limits #10264

Delete support for custom apps from Apps UI #10127

--edit session flag to edit conversation before forking #9799

iFlytek Spark and Astron MaaS providers #9837

Fireworks AI declarative provider #9990

OpenRouter request parameters support #9276

OVHcloud Qwen3.6-27B model (262K context) #10339

GPT-5.6 family support #10349

GLM-5.2 support #9967

French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales #10072

Provider bindings MVP to goose-sdk with Python wheel publishing #10208

TLS support for ACP serve #10088

Streamable HTTP support in deeplink generator #9954

Bug Fixes

Exclude MCP App tools from Code Mode callbacks #10290

Preserve reasoning_content for DeepSeek thinking mode on multi-turn tool calls #10366

Compaction disabled during approval #10089

Treat empty-string finish_reason as non-terminal in streaming #10258

Gemini OAuth onboarding failure #10363

Retry empty provider turns instead of stopping silently #10360

Guard llama.cpp backend init against SIGILL on x86_64 CPUs without FMA/AVX2 #10105

Sanitize responses function call names #10344

Pick session mode from the IDs the agent actually offers #10320

Desktop ACP shell PATH #10336

Dedupe duplicate signed thinking blocks to fix Anthropic 400 #10083

Resolve provider default model instead of leaking sentinel "current" #10305

Return effective context limit from /model-info #10165

Gate rcgen aws_lc_rs feature behind rustls-tls #10116

Recover malformed tool calls from GLM/Minimax models instead of rejecting them #10230

Restore cursor when configure exits #10222

Skip scheduled sessions for implicit resume #10178

Sync slash help with builtins #10173

Treat unicode punctuation as image path terminators #10106

Don't bleed provider-specific request_params into delegate() sessions #9906

Purge empty phantom sessions on startup #9651

Include structuredContent from MCP tool response #10128

Propagate agent cleanup errors on session delete #10112

Tolerate partial Responses output items #10108

Always use OpenAI-compatible "parameters" for Databricks tools #10101

Unescape shell-escaped image paths #10098

Send inference config (max_tokens, temperature) on Bedrock Converse #9889

Dedupe Nostr session deep link imports #9918

Don't retry deterministically-permanent 400s (thinking-block immutability) #10005

Use async reqwest client so OTLP export works in goose serve mode #10100

Reject non-object tool-call arguments instead of panicking #9832

Save /edit prompts to history #10011

Buffer thinking across stream chunks for DeepSeek/Kimi tool calls #9704

Surface actionable errors for truncated tool-call arguments #9946

Show optimistic toggle state when disabling an extension #9882

Resolve databricks_v2 pricing and surface cost in standard usage update #9925

Activate hermit on macOS so STDIO extensions resolve node #9482

Prompt timestamps are now timezone-explicit #10209

Improvements

Apply the default extension timeout to developer shell tool calls #10348

Disable thinking preservation for Groq #10284

Bound code-mode execution with timeout and cancellation #10214

Keep turn-context out of the Anthropic prefix cache #10030

Disable extended thinking for fast-model operations #9815

Switch the local inference provider MLX backend to use the safemlx crate #10304

OpenAI Responses API store param configurable #10040

Support streamed tool calls without indexes #10023

Fail closed on unverifiable update provenance #10168

Migrate diagnostics to JSON report #9964

Route MCP elicitations through tool streams #9943

ACP migration for desktop UI #10081

Relabel settings 'Session' tab to 'External Backend' #10318

Show manual-setup indicator for extensions without an install link #10321

Documentation

Clarify session --edit context retention #10257

Name the message field in the hooks payload guide #9913

Custom agents guide #9293

Correct custom agents guide #9947

Original source

Features

OllamaCloudProvider with dynamic model discovery and context limits #10264

Per-message usage stats UI (tokens, cost, TTFT, tok/s) #10210

Per-message usage/cost tracking with derived session totals #10172

Group chat sessions by project in nav panel #10212

Show project names in directory switcher dropdown #10207

Provider bindings MVP to goose-sdk with Python wheel publishing #10208

AskAI bot hints for followups #10291

Bug Fixes

Resolve provider default model instead of leaking sentinel "current" #10305

Return effective context limit from /model-info #10165

Recover malformed tool calls from GLM/Minimax models instead of rejecting them #10230

Restore cursor when configure exits #10222

Sync slash help with builtins #10173

Treat unicode punctuation as image path terminators #10106

Don't bleed provider-specific request_params into delegate() sessions #9906

Purge empty phantom sessions on startup #9651

Include structuredContent from MCP tool response #10128

Gate rcgen aws_lc_rs feature behind rustls-tls #10116

Improvements

Increase /mcp-app-guest body limit for larger single-file MCP apps #10324

Relabel settings 'Session' tab to 'External Backend' #10318

Switch local inference provider MLX backend to use the safemlx crate #10304

Disable thinking preservation for Groq #10284

Bound code-mode execution with timeout and cancellation #10214

Skip scheduled sessions for implicit resume #10178

Fail closed on unverifiable update provenance #10168

Update Rust toolchain and raise recursion limit #10303

Drop unsupported gpt-5.3-codex from chatgpt_codex provider #10271

Move Google provider into goose-providers #10216

Move Snowflake provider #10218

Move Databricks providers into goose-providers crate #10162

Move declarative definitions #10167

Documentation

Clarify session --edit context retention #10257

Simplified the issue templates #10316

Remove stale crates/goose-server and update docs #10224

Original source