# Goose changelog

> An extensible on-machine AI agent that runs and edits code through MCP tools.

- Vendor: Block
- Category: AI
- Official site: https://block.github.io/goose/
- Tracked by: What's New (https://whatsnew.fyi/product/goose)
- Harvested from: GitHub (block/goose)
- Entries below: 10 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

## Releases

### v1.45.0

- Date: 2026-07-29
- Version: v1.45.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.45.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.45.0

- **added** — Stable agent event message identity
- **added** — Tab completion and switch provider for model command
- **added** — Support latest Gemini models
- **added** — Configurable GOOSE_DOCS_ROOT for air-gapped docs access
- **added** — Structured summary output with template rendering for compaction
- **added** — Allow disabling built-in skills
- **added** — Gate tool-call label enrichment on ACP client capability
- **fixed** — Restore dynamic model discovery and current Grok support
- **fixed** — Update DeepSeek model names to v4 API
- **fixed** — Forward Claude Code model picker selection to the adapter
- **fixed** — Forward Pi model selection to the adapter
- **fixed** — Preserve enabled flag when migrating platform extensions
- **fixed** — Pass session working_dir to on_call_tool
- **fixed** — Preserve adversary tool arguments
- **fixed** — Keep XML snippets inside JSON as data for local inference
- **fixed** — Sync generated chat title in header
- **fixed** — Prompt for tool approval in telegram gateway sessions
- **fixed** — Keep CLI provider prompts out of process arguments
- **fixed** — Ignore stale inventory for static model lists
- **fixed** — Use shell working directory on initial desktop launch

##### ✨ Features

- Stable agent event message identity [#10716](https://github.com/aaif-goose/goose/pull/10716)
- Tab completion and switch provider for `model` command [#10585](https://github.com/aaif-goose/goose/pull/10585)
- Support latest Gemini models [#10630](https://github.com/aaif-goose/goose/pull/10630)
- Configurable GOOSE_DOCS_ROOT for air-gapped docs access [#10294](https://github.com/aaif-goose/goose/pull/10294)
- Structured summary output with template rendering for compaction [#10471](https://github.com/aaif-goose/goose/pull/10471)
- Allow disabling built-in skills [#10600](https://github.com/aaif-goose/goose/pull/10600)
- Gate tool-call label enrichment on ACP client capability [#10644](https://github.com/aaif-goose/goose/pull/10644)

##### 🐛 Bug Fixes

- Restore dynamic model discovery and current Grok support [#10756](https://github.com/aaif-goose/goose/pull/10756)
- Update DeepSeek model names to v4 API [#10729](https://github.com/aaif-goose/goose/pull/10729)
- Forward Claude Code model picker selection to the adapter [#10675](https://github.com/aaif-goose/goose/pull/10675)
- Forward Pi model selection to the adapter [#10707](https://github.com/aaif-goose/goose/pull/10707)
- Preserve enabled flag when migrating platform extensions [#10690](https://github.com/aaif-goose/goose/pull/10690)
- Pass session working_dir to on_call_tool [#10689](https://github.com/aaif-goose/goose/pull/10689)
- Preserve adversary tool arguments [#10529](https://github.com/aaif-goose/goose/pull/10529)
- Keep XML snippets inside JSON as data for local inference [#10606](https://github.com/aaif-goose/goose/pull/10606)
- Sync generated chat title in header [#10578](https://github.com/aaif-goose/goose/pull/10578)
- Prompt for tool approval in telegram gateway sessions [#10613](https://github.com/aaif-goose/goose/pull/10613)
- Keep CLI provider prompts out of process arguments [#10547](https://github.com/aaif-goose/goose/pull/10547)
- Ignore stale inventory for static model lists [#10591](https://github.com/aaif-goose/goose/pull/10591)
- Use shell working directory on initial desktop launch [#10655](https://github.com/aaif-goose/goose/pull/10655)
- Enable inventory refresh for OpenRouter model picker [#10641](https://github.com/aaif-goose/goose/pull/10641)
- Preserve read lines and reload tool output in ACP [#10662](https://github.com/aaif-goose/goose/pull/10662)
- Surface tool call output in CLI and Desktop [#10654](https://github.com/aaif-goose/goose/pull/10654)
- Truncate overlong function names in provider requests [#10659](https://github.com/aaif-goose/goose/pull/10659)
- Preserve ACP tool call update fields in desktop [#10653](https://github.com/aaif-goose/goose/pull/10653)
- Use configured session manager for tool summaries [#10628](https://github.com/aaif-goose/goose/pull/10628)
- Omit disabled OpenRouter reasoning [#10517](https://github.com/aaif-goose/goose/pull/10517)
- Clear stale pending ACP connection after terminal recovery failure [#10552](https://github.com/aaif-goose/goose/pull/10552)
- Confirm pending steer message on queuedSteer notification [#10532](https://github.com/aaif-goose/goose/pull/10532)
- Apply hermit env directly in node shims so fish login shell doesn't break MCP startup [#10028](https://github.com/aaif-goose/goose/pull/10028)

##### 🔧 Improvements

- Upgrade to rmcp 2.0 [#10584](https://github.com/aaif-goose/goose/pull/10584)
- Opus5 support including adaptive thinking [#10686](https://github.com/aaif-goose/goose/pull/10686)
- Refine dark theme message surfaces for consistent, compliant dark mode UX [#10693](https://github.com/aaif-goose/goose/pull/10693)
- Fix Korean translation errors, untranslated entries, and terminology consistency [#10667](https://github.com/aaif-goose/goose/pull/10667)
- Simplify ACP tool-call handling and fix chain summaries [#10599](https://github.com/aaif-goose/goose/pull/10599)
- Enhance the uniffi API layer [#10427](https://github.com/aaif-goose/goose/pull/10427)
- Disable

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.45.0]_

### v1.44.0

- Date: 2026-07-23
- Version: v1.44.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.44.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.44.0

- **security** — Fix arbitrary command execution in goose CLI via goose review through git core.fsmonitor config
- **added** — Support for latest Gemini models
- **added** — Pass working_dir to the Stop hook context
- **added** — Declarative Sakana AI provider for OpenAI-compatible Fugu API
- **added** — Model interactions viewer restored
- **added** — Chunk command-classifier input with overlapping windows for security
- **added** — Search filter for provider grid
- **added** — Muse Spark 1.1 support via Meta Models API
- **added** — GPT-5.6 support
- **added** — Reconnect desktop ACP sessions after sleep and connection loss
- **added** — Per-message usage stats UI showing tokens, cost, TTFT, and tok/s
- **added** — OllamaCloudProvider with dynamic model discovery and context limits
- **added** — Delete support for custom apps from Apps UI
- **added** — --edit session flag to edit conversation before forking
- **added** — iFlytek Spark and Astron MaaS providers
- **added** — Fireworks AI declarative provider
- **added** — OpenRouter request parameters support
- **added** — French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and zh-TW desktop locales
- **added** — MiniMax-M3 and missing M2.7 variants
- **fixed** — Preserve command arguments through extension forms

##### Security fixes

- Arbitrary command execution in goose CLI via `goose review` (via git core.fsmonitor config) - [GHSA-r5pp-p5r8-466r](https://github.com/aaif-goose/goose/security/advisories/GHSA-r5pp-p5r8-466r) (credit to @0xmagic0)

##### ✨ Features

- Support for latest Gemini models [#10630](https://github.com/aaif-goose/goose/pull/10630)
- Pass working_dir to the Stop hook context [#10296](https://github.com/aaif-goose/goose/pull/10296)
- Declarative Sakana AI provider for OpenAI-compatible Fugu API [#10357](https://github.com/aaif-goose/goose/pull/10357)
- Model interactions viewer restored [#10205](https://github.com/aaif-goose/goose/pull/10205)
- Chunk command-classifier input with overlapping windows for security [#10416](https://github.com/aaif-goose/goose/pull/10416)
- Search filter for provider grid [#10437](https://github.com/aaif-goose/goose/pull/10437)
- Muse Spark 1.1 support via Meta Models API [#10432](https://github.com/aaif-goose/goose/pull/10432)
- GPT-5.6 support [#10384](https://github.com/aaif-goose/goose/pull/10384)
- Reconnect desktop ACP sessions after sleep and connection loss [#10411](https://github.com/aaif-goose/goose/pull/10411)
- Per-message usage stats UI (tokens, cost, TTFT, tok/s) [#10210](https://github.com/aaif-goose/goose/pull/10210)
- OllamaCloudProvider with dynamic model discovery and context limits [#10264](https://github.com/aaif-goose/goose/pull/10264)
- Delete support for custom apps from Apps UI [#10127](https://github.com/aaif-goose/goose/pull/10127)
- `--edit` session flag to edit conversation before forking [#9799](https://github.com/aaif-goose/goose/pull/9799)
- iFlytek Spark and Astron MaaS providers [#9837](https://github.com/aaif-goose/goose/pull/9837)
- Fireworks AI declarative provider [#9990](https://github.com/aaif-goose/goose/pull/9990)
- OpenRouter request parameters support [#9276](https://github.com/aaif-goose/goose/pull/9276)
- French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, zh-TW desktop locales [#10072](https://github.com/aaif-goose/goose/pull/10072)
- MiniMax-M3 and missing M2.7 variants [#10431](https://github.com/aaif-goose/goose/pull/10431)

##### 🐛 Bug Fixes

- Preserve command arguments through extension forms [#10527](https://github.com/aaif-goose/goose/pull/10527)
- Enforce manual approval for code mode [#10528](https://github.com/aaif-goose/goose/pull/10528)
- Confine app file operations [#10481](https://github.com/aaif-goose/goose/pull/10481)
- Preserve featured model size on delete and backfill missing sizes [#10422](https://github.com/aaif-goose/goose/pull/10422)
- Preserve recursive schema types with pctx 0.4.1 [#10572](https://github.com/aaif-goose/goose/pull/10572)
- Create inventory tables atomically with schema version [#10586](https://github.com/aaif-goose/goose/pull/10586)
- Rewrite oneOf to anyOf in tool schemas for OpenAI-compatible backends [#10571](https://github.com/aaif-goose/goose/pull/10571)
- Allow custom model as default for non-local providers [#10438](https://github.com/aaif-goose/goose/pull/10438)
- Require absolute goose path roots [#10454](https://github.com/aaif-goose/goose/pull/10454)
- Scope smart approval by request [#10457](https://github.com/aaif-goose/goose/pull/10457)
- Preserve fixed subrecipe values [#10452](https://github.com/aaif-goose/goose/pull/10452)
- Bundle git in Flatpak so hermit can clone its package registry [#10511](https://github.com/aaif-goose/goose/pull/10511)
- Expose AGENT_SESSION_ID to shell commands [#10428](https://github.com/aaif-goose/goose/pull/10428)
- Forward image content chunks to client during live session [#10485](https://github.com/aaif-goose/goose/pull/10485)
- Dispatch Code Mode callbacks on main runtime to prevent hangs [#10484](https://github.com/aaif-goose/goose/pull/10484)
- Protect OAuth token caches [#10516](https://github.com/aaif-goose/goose/pull/10516)
- Preserve content audience boundaries [#10493](https://gith

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.44.0]_

### v1.43.0

- Date: 2026-07-14
- Version: v1.43.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.43.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.43.0

- **added** — Reconnect desktop ACP sessions after sleep and connection loss
- **added** — Per-message usage stats UI displaying tokens, cost, TTFT, and tok/s
- **added** — Per-message usage and cost tracking with derived session totals
- **added** — Group chat sessions by project in nav panel
- **added** — Show project names in directory switcher dropdown
- **added** — OllamaCloudProvider with dynamic model discovery and context limits
- **added** — Delete support for custom apps from Apps UI
- **added** — --edit session flag to edit conversation before forking
- **added** — iFlytek Spark and Astron MaaS providers
- **added** — Fireworks AI declarative provider
- **added** — OpenRouter request parameters support
- **added** — OVHcloud Qwen3.6-27B model with 262K context
- **added** — GPT-5.6 family support
- **added** — GLM-5.2 support
- **added** — French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales
- **added** — Provider bindings MVP to goose-sdk with Python wheel publishing
- **added** — TLS support for ACP serve
- **added** — Streamable HTTP support in deeplink generator
- **fixed** — Exclude MCP App tools from Code Mode callbacks
- **fixed** — Preserve reasoning_content for DeepSeek thinking mode on multi-turn tool calls

##### ✨ Features

- Reconnect desktop ACP sessions after sleep and connection loss [#10411](https://github.com/aaif-goose/goose/pull/10411)
- Per-message usage stats UI (tokens, cost, TTFT, tok/s) [#10210](https://github.com/aaif-goose/goose/pull/10210)
- Per-message usage/cost tracking with derived session totals [#10172](https://github.com/aaif-goose/goose/pull/10172)
- Group chat sessions by project in nav panel [#10212](https://github.com/aaif-goose/goose/pull/10212)
- Show project names in directory switcher dropdown [#10207](https://github.com/aaif-goose/goose/pull/10207)
- OllamaCloudProvider with dynamic model discovery and context limits [#10264](https://github.com/aaif-goose/goose/pull/10264)
- Delete support for custom apps from Apps UI [#10127](https://github.com/aaif-goose/goose/pull/10127)
- `--edit` session flag to edit conversation before forking [#9799](https://github.com/aaif-goose/goose/pull/9799)
- iFlytek Spark and Astron MaaS providers [#9837](https://github.com/aaif-goose/goose/pull/9837)
- Fireworks AI declarative provider [#9990](https://github.com/aaif-goose/goose/pull/9990)
- OpenRouter request parameters support [#9276](https://github.com/aaif-goose/goose/pull/9276)
- OVHcloud Qwen3.6-27B model (262K context) [#10339](https://github.com/aaif-goose/goose/pull/10339)
- GPT-5.6 family support [#10349](https://github.com/aaif-goose/goose/pull/10349)
- GLM-5.2 support [#9967](https://github.com/aaif-goose/goose/pull/9967)
- French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales [#10072](https://github.com/aaif-goose/goose/pull/10072)
- Provider bindings MVP to goose-sdk with Python wheel publishing [#10208](https://github.com/aaif-goose/goose/pull/10208)
- TLS support for ACP serve [#10088](https://github.com/aaif-goose/goose/pull/10088)
- Streamable HTTP support in deeplink generator [#9954](https://github.com/aaif-goose/goose/pull/9954)

##### 🐛 Bug Fixes

- Exclude MCP App tools from Code Mode callbacks [#10290](https://github.com/aaif-goose/goose/pull/10290)
- Preserve reasoning_content for DeepSeek thinking mode on multi-turn tool calls [#10366](https://github.com/aaif-goose/goose/pull/10366)
- Compaction disabled during approval [#10089](https://github.com/aaif-goose/goose/pull/10089)
- Treat empty-string finish_reason as non-terminal in streaming [#10258](https://github.com/aaif-goose/goose/pull/10258)
- Gemini OAuth onboarding failure [#10363](https://github.com/aaif-goose/goose/pull/10363)
- Retry empty provider turns instead of stopping silently [#10360](https://github.com/aaif-goose/goose/pull/10360)
- Guard llama.cpp backend init against SIGILL on x86_64 CPUs without FMA/AVX2 [#10105](https://github.com/aaif-goose/goose/pull/10105)
- Sanitize responses function call names [#10344](https://github.com/aaif-goose/goose/pull/10344)
- Pick session mode from the IDs the agent actually offers [#10320](https://github.com/aaif-goose/goose/pull/10320)
- Desktop ACP shell PATH [#10336](https://github.com/aaif-goose/goose/pull/10336)
- Dedupe duplicate signed thinking blocks to fix Anthropic 400 [#10083](https://github.com/aaif-goose/goose/pull/10083)
- Resolve provider default model instead of leaking sentinel "current" [#10305](https://github.com/aaif-goose/goose/pull/10305)
- Return effective context limit from /model-info [#10165](https://github.com/aaif-goose/goose/pull/10165)
- Gate rcgen aws_lc_rs feature behind rustls-tls [#10116](https://github.com/aaif-goose/goose/pull/10116)
- Recover malformed tool calls from GLM/Minimax models instead of rejecting them [#10230](https://github.com/aaif-goose/goose/pull/10230)
- Restore cursor when configure exits [#10222](https://github.com/aaif-goose/goose/pull/10222)
- Skip scheduled sessions for implicit resume [#10178](https://github.com/aaif-goose/goose/pull/10178)
- Sync slash help with builtins [#10173](https://github.com/aaif-goose/goose/pull/10173)
- Treat unicode punctuation as image path termina

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.43.0]_

### v1.42.0

- Date: 2026-07-13
- Version: v1.42.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.42.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.42.0

- **added** — OllamaCloudProvider with dynamic model discovery and context limits
- **added** — Per-message usage stats UI showing tokens, cost, TTFT, and tok/s
- **added** — Per-message usage and cost tracking with derived session totals
- **added** — Group chat sessions by project in navigation panel
- **added** — Show project names in directory switcher dropdown
- **added** — Provider bindings MVP to goose-sdk with Python wheel publishing
- **added** — AskAI bot hints for followups
- **fixed** — Resolve provider default model instead of leaking sentinel "current"
- **fixed** — Return effective context limit from /model-info
- **fixed** — Recover malformed tool calls from GLM/Minimax models instead of rejecting them
- **fixed** — Restore cursor when configure exits
- **fixed** — Sync slash help with builtins
- **fixed** — Treat unicode punctuation as image path terminators
- **fixed** — Don't bleed provider-specific request_params into delegate() sessions
- **fixed** — Purge empty phantom sessions on startup
- **fixed** — Include structuredContent from MCP tool response
- **changed** — Increase /mcp-app-guest body limit for larger single-file MCP apps
- **changed** — Relabel settings 'Session' tab to 'External Backend'
- **changed** — Switch local inference provider MLX backend to use the safemlx crate
- **changed** — Disable thinking preservation for Groq

##### ✨ Features

- OllamaCloudProvider with dynamic model discovery and context limits [#10264](https://github.com/aaif-goose/goose/pull/10264)
- Per-message usage stats UI (tokens, cost, TTFT, tok/s) [#10210](https://github.com/aaif-goose/goose/pull/10210)
- Per-message usage/cost tracking with derived session totals [#10172](https://github.com/aaif-goose/goose/pull/10172)
- Group chat sessions by project in nav panel [#10212](https://github.com/aaif-goose/goose/pull/10212)
- Show project names in directory switcher dropdown [#10207](https://github.com/aaif-goose/goose/pull/10207)
- Provider bindings MVP to goose-sdk with Python wheel publishing [#10208](https://github.com/aaif-goose/goose/pull/10208)
- AskAI bot hints for followups [#10291](https://github.com/aaif-goose/goose/pull/10291)

##### 🐛 Bug Fixes

- Resolve provider default model instead of leaking sentinel "current" [#10305](https://github.com/aaif-goose/goose/pull/10305)
- Return effective context limit from /model-info [#10165](https://github.com/aaif-goose/goose/pull/10165)
- Recover malformed tool calls from GLM/Minimax models instead of rejecting them [#10230](https://github.com/aaif-goose/goose/pull/10230)
- Restore cursor when configure exits [#10222](https://github.com/aaif-goose/goose/pull/10222)
- Sync slash help with builtins [#10173](https://github.com/aaif-goose/goose/pull/10173)
- Treat unicode punctuation as image path terminators [#10106](https://github.com/aaif-goose/goose/pull/10106)
- Don't bleed provider-specific request_params into delegate() sessions [#9906](https://github.com/aaif-goose/goose/pull/9906)
- Purge empty phantom sessions on startup [#9651](https://github.com/aaif-goose/goose/pull/9651)
- Include structuredContent from MCP tool response [#10128](https://github.com/aaif-goose/goose/pull/10128)
- Gate rcgen aws_lc_rs feature behind rustls-tls [#10116](https://github.com/aaif-goose/goose/pull/10116)

##### 🔧 Improvements

- Increase /mcp-app-guest body limit for larger single-file MCP apps [#10324](https://github.com/aaif-goose/goose/pull/10324)
- Relabel settings 'Session' tab to 'External Backend' [#10318](https://github.com/aaif-goose/goose/pull/10318)
- Switch local inference provider MLX backend to use the safemlx crate [#10304](https://github.com/aaif-goose/goose/pull/10304)
- Disable thinking preservation for Groq [#10284](https://github.com/aaif-goose/goose/pull/10284)
- Bound code-mode execution with timeout and cancellation [#10214](https://github.com/aaif-goose/goose/pull/10214)
- Skip scheduled sessions for implicit resume [#10178](https://github.com/aaif-goose/goose/pull/10178)
- Fail closed on unverifiable update provenance [#10168](https://github.com/aaif-goose/goose/pull/10168)
- Update Rust toolchain and raise recursion limit [#10303](https://github.com/aaif-goose/goose/pull/10303)
- Drop unsupported gpt-5.3-codex from chatgpt_codex provider [#10271](https://github.com/aaif-goose/goose/pull/10271)
- Move Google provider into goose-providers [#10216](https://github.com/aaif-goose/goose/pull/10216)
- Move Snowflake provider [#10218](https://github.com/aaif-goose/goose/pull/10218)
- Move Databricks providers into goose-providers crate [#10162](https://github.com/aaif-goose/goose/pull/10162)
- Move declarative definitions [#10167](https://github.com/aaif-goose/goose/pull/10167)

##### 📚 Documentation

- Clarify session --edit context retention [#10257](https://github.com/aaif-goose/goose/pull/10257)
- Simplified the issue templates [#10316](https://github.com/aaif-goose/goose/pull/10316)
- Remove stale crates/goose-server and update docs [#10224](https://github.com/aaif-goose/goose/pull/10224)

### v1.41.0

- Date: 2026-07-03
- Version: v1.41.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.41.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.41.0

- **added** — iFlytek Spark and Astron MaaS providers
- **added** — --edit session flag to edit conversation before forking
- **added** — Fireworks AI declarative provider
- **added** — OpenRouter request parameters support
- **added** — French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales
- **added** — Spanish locale support
- **added** — Korean localization for desktop app
- **added** — Japanese locale support
- **added** — Hindi desktop locale
- **added** — Language selection feature in desktop
- **added** — /status slash command in CLI
- **added** — Streamable HTTP support in deeplink generator
- **added** — GLM-5.2 model support
- **added** — Global hints loading from ~/.agents/AGENTS.md
- **added** — Azure Entra ID bearer token auth via AZURE_OPENAI_AD_TOKEN
- **added** — Together AI declarative provider
- **added** — OrcaRouter as declarative OpenAI-compatible provider
- **added** — EmpirioLabs AI declarative provider
- **added** — MLX model support for local inference provider
- **added** — Summon peek mode for async background tasks

##### ✨ Features

- iFlytek Spark and Astron MaaS providers (#9837)
- `--edit` session flag to edit conversation before forking (#9799)
- Fireworks AI declarative provider (#9990)
- OpenRouter request parameters support (#9276)
- French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales (#10072)
- Spanish (es) locale support (#9833)
- Korean localization for desktop app (#9856)
- Japanese locale support (#9768)
- Hindi desktop locale (#9733)
- Language selection feature in desktop (#9405)
- `/status` slash command in CLI (#9845)
- Streamable HTTP support in deeplink generator (#9954)
- GLM-5.2 model support (#9967)
- Global hints loading from `~/.agents/AGENTS.md` (#9736)
- Azure Entra ID bearer token auth via `AZURE_OPENAI_AD_TOKEN` (#9716)
- Together AI declarative provider (#9545)
- OrcaRouter as declarative OpenAI-compatible provider (#9515)
- EmpirioLabs AI declarative provider (#9771)
- MLX model support for local inference provider (#9154)
- Summon peek mode for async background tasks (#9519)
- Summon context parameter for delegate tasks (#9518)
- Summon working_dir override for delegate tasks (#9520)
- Structured metadata for summon task load results (#9521)
- TLS support for ACP serve (#10088)
- OpenAI Responses API store param configurability (#10040)
- Exposed available tools in ACP schema (#10097)
- ACP thinking effort config option (#10711)
- Last message snippets for ACP sessions (#9798)
- OTLP logging schema for cross-tool detection (#9713)
- Option to disable automatic update downloads (#9872)
- Cache token tracking for accurate cost reporting (#9752)
- Session import functionality (#9474)
- xAI SuperGrok OAuth subscription provider (#9420)
- Perplexity as declarative OpenAI-compatible provider (#9324)
- Alibaba (Qwen via DashScope) declarative provider (#9443)
- Configurable tool output size limit via `GOOSE_MAX_TOOL_RESPONSE_SIZE` (#9256)
- `/model` slash command for session model switching (#8747)
- Databricks AI Gateway provider (#9274)
- Russian language support (#9406)
- Turkish desktop locale (#9392)
- NEAR AI Cloud provider (#9352)
- Scaleway provider (#9254)
- Harbor eval runner (#9138)
- `/goal` command for agent self-evaluation before finishing (#9069)
- Summon subagent instructions (#9325)
- Open-plugins generalization + skills (#9112)
- PreToolUse denial in hooks (#9304)
- Optional api_key configuration for declarative openai-engine providers (#9202)
- `goose review` local code review command (#9114)
- TUI diff viewer (#9260)
- Paginated session list in ACP (#9199)
- Structured per-provider config block with non-destructive provider switching (#8977)
- `tui` command on goose-cli (#9385)
- Configurable `MAX_CODE_BLOCK_LINES` via env vars (#9301)
- `goose://resume` session deep link (#9343)
- `GOOSE_FAST_MODEL` env var support (#9296)
- Vercel AI Gateway provider (#9144)
- Quarterly option for scheduler (#9076)
- Hooks feature (#9093)
- Projects as backend sources with system prompt injection (#8739)
- Worktree-aware directory switcher (#8450)
- Chat history search feature (#8448)
- Optional `--parameters` for scheduled recipes (#8741)
- GitHub Copilot `/responses` API (#9043)
- Unified thinking effort control across all providers (#9242)
- Slash commands (built-in, skill, recipe) in ACP server (#9238)
- Nushell terminal and completion support (#8628)
- Simplified Chinese (zh-CN) translation (#8765)
- Atomic Chat as declarative OpenAI-compatible provider (#9210)
- `GOOSE_OAUTH_CALLBACK_PORT` for stable OAuth redirect_uri (#9209)
- Proactive OAuth token refresh to avoid re-auth on every session (#8386)
- `goose://new-session` deep link for fresh chat (#9196)
- Routstr as declarative provider (#9175)
- FuturMix provider (#8840)
- oMLX declarative provider (#9177)
- Declarative provider support in goose-providers crate (#9992)
- ACP elicitation improvements (#9797)
- Image read tool (#9607)
- `gpt-5.5` model support for ChatGPT Codex provider (#9292)

##

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.41.0]_

### v1.40.0

- Date: 2026-07-02
- Version: v1.40.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.40.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.40.0

- **added** — Language selection in desktop app
- **added** — French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales
- **added** — Korean localization for desktop app
- **added** — Japanese locale support
- **added** — Spanish (es) locale support
- **added** — Hindi desktop locale
- **added** — /status slash command in CLI
- **added** — /model slash command for session model switching
- **added** — /goal command for agent self-evaluation before finishing
- **added** — goose review local code review command
- **added** — Peek mode for async background tasks in summon
- **added** — Context parameter and working_dir override for delegate tasks
- **added** — GLM-5.2 support
- **added** — Together AI declarative provider
- **added** — EmpirioLabs as declarative OpenAI-compatible provider
- **added** — OrcaRouter as declarative OpenAI-compatible provider
- **added** — NEAR AI Cloud provider
- **added** — Perplexity as declarative OpenAI-compatible provider
- **added** — Alibaba (Qwen via DashScope) declarative provider
- **added** — Databricks AI Gateway provider

##### ✨ Features

- Language selection in desktop app [#9405](https://github.com/aaif-goose/goose/pull/9405)
- French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, Traditional Chinese desktop locales [#10072](https://github.com/aaif-goose/goose/pull/10072)
- Korean localization for desktop app [#9856](https://github.com/aaif-goose/goose/pull/9856)
- Japanese locale support [#9768](https://github.com/aaif-goose/goose/pull/9768)
- Spanish (es) locale support [#9833](https://github.com/aaif-goose/goose/pull/9833)
- Hindi desktop locale [#9733](https://github.com/aaif-goose/goose/pull/9733)
- `/status` slash command in CLI [#9845](https://github.com/aaif-goose/goose/pull/9845)
- `/model` slash command for session model switching [#8747](https://github.com/aaif-goose/goose/pull/8747)
- `/goal` command for agent self-evaluation before finishing [#9069](https://github.com/aaif-goose/goose/pull/9069)
- `goose review` local code review command [#9114](https://github.com/aaif-goose/goose/pull/9114)
- Peek mode for async background tasks in summon [#9519](https://github.com/aaif-goose/goose/pull/9519)
- Context parameter and working_dir override for delegate tasks [#9518](https://github.com/aaif-goose/goose/pull/9518) [#9520](https://github.com/aaif-goose/goose/pull/9520)
- GLM-5.2 support [#9967](https://github.com/aaif-goose/goose/pull/9967)
- Together AI declarative provider [#9545](https://github.com/aaif-goose/goose/pull/9545)
- EmpirioLabs as declarative OpenAI-compatible provider [#9771](https://github.com/aaif-goose/goose/pull/9771)
- OrcaRouter as declarative OpenAI-compatible provider [#9515](https://github.com/aaif-goose/goose/pull/9515)
- NEAR AI Cloud provider [#9352](https://github.com/aaif-goose/goose/pull/9352)
- Perplexity as declarative OpenAI-compatible provider [#9324](https://github.com/aaif-goose/goose/pull/9324)
- Alibaba (Qwen via DashScope) declarative provider [#9443](https://github.com/aaif-goose/goose/pull/9443)
- Databricks AI Gateway provider [#9274](https://github.com/aaif-goose/goose/pull/9274)
- Scaleway provider [#9254](https://github.com/aaif-goose/goose/pull/9254)
- Vercel AI Gateway [#9144](https://github.com/aaif-goose/goose/pull/9144)
- xAI SuperGrok OAuth subscription provider [#9420](https://github.com/aaif-goose/goose/pull/9420)
- OpenAI GPT models via AWS Bedrock mantle endpoint [#9707](https://github.com/aaif-goose/goose/pull/9707)
- Azure Entra ID bearer token auth via AZURE_OPENAI_AD_TOKEN [#9716](https://github.com/aaif-goose/goose/pull/9716)
- MLX models support for local inference provider [#9154](https://github.com/aaif-goose/goose/pull/9154)
- Streamable HTTP support for deeplink generator [#9954](https://github.com/aaif-goose/goose/pull/9954)
- Global hints loading from ~/.agents/AGENTS.md [#9736](https://github.com/aaif-goose/goose/pull/9736)
- Unified thinking effort control across all providers [#9242](https://github.com/aaif-goose/goose/pull/9242)
- Canonical thinking modes [#9743](https://github.com/aaif-goose/goose/pull/9743)
- Hooks system for extensibility [#9093](https://github.com/aaif-goose/goose/pull/9093)
- PreToolUse denial in hooks [#9304](https://github.com/aaif-goose/goose/pull/9304)
- Honor blocking Stop hook decisions [#9468](https://github.com/aaif-goose/goose/pull/9468)
- Option to disable automatic update downloads [#9872](https://github.com/aaif-goose/goose/pull/9872)
- Track cache tokens for accurate cost reporting [#9752](https://github.com/aaif-goose/goose/pull/9752)
- Configurable tool output size limit via GOOSE_MAX_TOOL_RESPONSE_SIZE [#9256](https://github.com/aaif-goose/goose/pull/9256)
- Configurable MAX_CODE_BLOCK_LINES via env vars [#9301](https://github.com/aaif-goose/goose/pull/9301)
- GOOSE_FAST_MODEL env var support [#9296](https://github.com/aaif-goose/goose/pull/9296)
- Hugging Face OAuth support with auth tab in settings [#9552](https://github.com/aaif-goose/goose/pull/9552)
- Chat history search in navigation panel [#8448](https://

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.40.0]_

### v1.39.0

- Date: 2026-06-25
- Version: v1.39.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.39.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.39.0

- **added** — ACP method for managing recipes and UI changes
- **added** — Use ACP to manage global config and session extensions
- **added** — Recipe handling in new_session
- **added** — /status slash command in CLI
- **added** — ACP new session on desktop for non-recipe sessions
- **added** — Typed request/response for add and get session extensions in ACP
- **added** — Option to disable automatic update downloads
- **added** — Change cwd using ACP and refactor extension in bottom menubar
- **added** — Track cache tokens for accurate cost reporting
- **added** — Load session using ACP
- **added** — View model interactions
- **added** — Support OpenAI GPT models via AWS Bedrock mantle endpoint
- **added** — Peek mode for async background tasks in summon
- **added** — Korean localization for desktop app
- **added** — Chat reply UI with ACP
- **added** — Durable ACP chat session state for desktop UI
- **added** — MCP extensions support in open plugins
- **added** — Initial prompt with goose://new-session deep link
- **added** — Configurable Open Model Gym output dir
- **added** — Spanish locale support

##### ✨ Features

- ACP method for managing recipes and UI changes [#9951](https://github.com/aaif-goose/goose/pull/9951)
- Use ACP to manage global config and session extensions [#9948](https://github.com/aaif-goose/goose/pull/9948)
- Recipe handling in new_session [#9935](https://github.com/aaif-goose/goose/pull/9935)
- `/status` slash command in CLI [#9845](https://github.com/aaif-goose/goose/pull/9845)
- ACP new session on desktop (non-recipe sessions) [#9914](https://github.com/aaif-goose/goose/pull/9914)
- Typed request/response for add, get session extensions in ACP [#9890](https://github.com/aaif-goose/goose/pull/9890)
- Option to disable automatic update downloads [#9872](https://github.com/aaif-goose/goose/pull/9872)
- Change cwd using ACP and refactor extension in bottom menubar [#9887](https://github.com/aaif-goose/goose/pull/9887)
- Track cache tokens for accurate cost reporting [#9752](https://github.com/aaif-goose/goose/pull/9752)
- Load session using ACP [#9875](https://github.com/aaif-goose/goose/pull/9875)
- View model interactions [#9806](https://github.com/aaif-goose/goose/pull/9806)
- Support OpenAI GPT models via AWS Bedrock mantle endpoint [#9707](https://github.com/aaif-goose/goose/pull/9707)
- Peek mode for async background tasks in summon [#9519](https://github.com/aaif-goose/goose/pull/9519)
- Korean localization for desktop app [#9856](https://github.com/aaif-goose/goose/pull/9856)
- Chat reply UI with ACP [#9857](https://github.com/aaif-goose/goose/pull/9857)
- Durable ACP chat session state for desktop UI [#9852](https://github.com/aaif-goose/goose/pull/9852)
- ACP for desktop chat prompt (feature toggle off) [#9802](https://github.com/aaif-goose/goose/pull/9802)
- MCP extensions support in open plugins [#9471](https://github.com/aaif-goose/goose/pull/9471)
- Initial prompt with goose://new-session deep link [#9427](https://github.com/aaif-goose/goose/pull/9427)
- Configurable Open Model Gym output dir [#9789](https://github.com/aaif-goose/goose/pull/9789)
- Spanish (es) locale support [#9833](https://github.com/aaif-goose/goose/pull/9833)
- EmpirioLabs as a declarative OpenAI-compatible provider [#9771](https://github.com/aaif-goose/goose/pull/9771)
- MLX models support for local inference provider [#9154](https://github.com/aaif-goose/goose/pull/9154)
- Elicitation method for ACP with improvements [#9797](https://github.com/aaif-goose/goose/pull/9797)
- View JSON [#9678](https://github.com/aaif-goose/goose/pull/9678)
- Load global hints from ~/.agents/AGENTS.md [#9736](https://github.com/aaif-goose/goose/pull/9736)
- Configurable per-agent timeout (GYM_AGENT_TIMEOUT) [#9791](https://github.com/aaif-goose/goose/pull/9791)
- Azure Entra ID bearer token auth via AZURE_OPENAI_AD_TOKEN [#9716](https://github.com/aaif-goose/goose/pull/9716)
- `_meta.conversationBefore` for ACP forking session [#9821](https://github.com/aaif-goose/goose/pull/9821)
- Quarterly option for scheduler [#9076](https://github.com/aaif-goose/goose/pull/9076)
- Together AI declarative provider [#9545](https://github.com/aaif-goose/goose/pull/9545)
- Image read tool [#9607](https://github.com/aaif-goose/goose/pull/9607)
- Context parameter for summon delegate tasks [#9518](https://github.com/aaif-goose/goose/pull/9518)
- Structured metadata for summon task load results [#9521](https://github.com/aaif-goose/goose/pull/9521)
- Working_dir override for summon delegate tasks [#9520](https://github.com/aaif-goose/goose/pull/9520)
- OrcaRouter as a declarative OpenAI-compatible provider [#9515](https://github.com/aaif-goose/goose/pull/9515)
- Elicitation decline and cancel actions propagation [#9437](https://github.com/aaif-goose/goose/pull/9437)
- ACP opt-in last message snippets [#9798](https://github.com/aaif-goose/goose/pull/9798)
- Japanese locale support [#9768](https://github.com/aaif-goose/goose/pull/9768)
- Unified OTLP logging schema for cross-tool detection [#9713](https://github.com/aaif-goose/goose/pull/9713)
- Canonical

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.39.0]_

### v1.38.0

- Date: 2026-06-17
- Version: v1.38.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.38.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.38.0

- **added** — Opt-in ACP last message snippets for sessions
- **added** — Unified OTLP logging schema for cross-tool detection
- **added** — Canonical thinking modes across providers
- **added** — Custom ACP method to get session info
- **added** — ACP secret key support at goose serve endpoint
- **added** — Surface Anthropic stream refusals as visible errors
- **added** — ACP search session support in Desktop
- **added** — Steering messages with ACP
- **added** — ACP list sessions with keyword and type filter
- **added** — ACP thinking effort config option
- **added** — ACP session management in Desktop
- **added** — Image read tool
- **added** — ACP methods for config extensions
- **added** — Custom notifications only when ACP client specifies capability
- **added** — Minimal uniffi setup for cross-language SDK
- **added** — Hugging Face OAuth support with auth tab in settings
- **added** — Session import functionality
- **added** — Replay ACP images on session load
- **added** — Raw provider supported models over ACP
- **added** — ACP session system prompt setter

##### ✨ Features

- Opt-in ACP last message snippets for sessions [#9798](https://github.com/aaif-goose/goose/pull/9798)
- Unified OTLP logging schema for cross-tool detection [#9713](https://github.com/aaif-goose/goose/pull/9713)
- Canonical thinking modes across providers [#9743](https://github.com/aaif-goose/goose/pull/9743)
- Custom ACP method to get session info [#9729](https://github.com/aaif-goose/goose/pull/9729)
- ACP secret key support at goose serve endpoint [#9726](https://github.com/aaif-goose/goose/pull/9726)
- Surface Anthropic stream refusals as visible errors [#9724](https://github.com/aaif-goose/goose/pull/9724)
- ACP search session support in Desktop [#9717](https://github.com/aaif-goose/goose/pull/9717)
- Steering messages with ACP [#9560](https://github.com/aaif-goose/goose/pull/9560)
- ACP list sessions with keyword and type filter [#9695](https://github.com/aaif-goose/goose/pull/9695)
- ACP thinking effort config option [#9711](https://github.com/aaif-goose/goose/pull/9711)
- ACP session management in Desktop [#9687](https://github.com/aaif-goose/goose/pull/9687)
- Image read tool [#9607](https://github.com/aaif-goose/goose/pull/9607)
- ACP methods for config extensions [#9581](https://github.com/aaif-goose/goose/pull/9581)
- Custom notifications only when ACP client specifies capability [#9596](https://github.com/aaif-goose/goose/pull/9596)
- Minimal uniffi setup for cross-language SDK [#9593](https://github.com/aaif-goose/goose/pull/9593)
- Hugging Face OAuth support with auth tab in settings [#9552](https://github.com/aaif-goose/goose/pull/9552)
- Session import functionality [#9474](https://github.com/aaif-goose/goose/pull/9474)
- Replay ACP images on session load [#9496](https://github.com/aaif-goose/goose/pull/9496)
- Raw provider supported models over ACP [#9475](https://github.com/aaif-goose/goose/pull/9475)
- ACP session system prompt setter [#9478](https://github.com/aaif-goose/goose/pull/9478)
- Scholar Sidekick MCP extension [#9433](https://github.com/aaif-goose/goose/pull/9433)
- TUI feature flag to gate tui command [#9428](https://github.com/aaif-goose/goose/pull/9428)
- CLI to list skills with token counts [#9326](https://github.com/aaif-goose/goose/pull/9326)
- xAI SuperGrok OAuth subscription provider [#9420](https://github.com/aaif-goose/goose/pull/9420)
- Perplexity as declarative OpenAI-compatible provider [#9324](https://github.com/aaif-goose/goose/pull/9324)
- Alibaba (Qwen via DashScope) declarative provider [#9443](https://github.com/aaif-goose/goose/pull/9443)
- Configurable tool output size limit via GOOSE_MAX_TOOL_RESPONSE_SIZE [#9256](https://github.com/aaif-goose/goose/pull/9256)
- /model slash command in CLI for session model switching [#8747](https://github.com/aaif-goose/goose/pull/8747)
- Databricks AI Gateway provider [#9274](https://github.com/aaif-goose/goose/pull/9274)
- TUI command on goose-cli [#9385](https://github.com/aaif-goose/goose/pull/9385)
- Configurable MAX_CODE_BLOCK_LINES via env vars [#9301](https://github.com/aaif-goose/goose/pull/9301)
- NEAR AI Cloud provider [#9352](https://github.com/aaif-goose/goose/pull/9352)
- goose://resume session deep link [#9343](https://github.com/aaif-goose/goose/pull/9343)
- Scaleway provider [#9254](https://github.com/aaif-goose/goose/pull/9254)
- Honor GOOSE_FAST_MODEL env var in ModelConfig::with_fast [#9296](https://github.com/aaif-goose/goose/pull/9296)
- `goose review` local code review command [#9114](https://github.com/aaif-goose/goose/pull/9114)
- TUI diff viewer [#9260](https://github.com/aaif-goose/goose/pull/9260)
- ACP paginate session list [#9199](https://github.com/aaif-goose/goose/pull/9199)
- Structured per-provider config block, non-destructive provider switching [#8977](https://github.com/aaif-goose/goose/pull/8977)
- Pass session cwd param to ACP providers [#9229](https://github.com/aaif-goose/goose/pull/9229)
- gpt-5.5 added to known models [#9292](https://github.com/aaif-goose/goose/pull/9292)
- Opt-i

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.38.0]_

### v1.37.0

- Date: 2026-06-03
- Version: v1.37.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.37.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.37.0

- **added** — xAI SuperGrok OAuth subscription provider
- **added** — Replay ACP images on session load
- **added** — Expose raw provider supported models over ACP
- **added** — ACP session system prompt setter
- **added** — Scholar Sidekick MCP extension
- **added** — tui feature flag to gate the TUI command
- **added** — CLI to list skills with token counts
- **added** — Perplexity as a declarative OpenAI-compatible provider
- **added** — Alibaba (Qwen via DashScope) declarative provider
- **added** — Configurable tool output size limit via GOOSE_MAX_TOOL_RESPONSE_SIZE
- **added** — /model slash command to CLI for session model switching
- **added** — Databricks AI Gateway provider
- **added** — Russian language support
- **added** — Turkish desktop locale
- **added** — TUI command on goose-cli
- **added** — Configurable MAX_CODE_BLOCK_LINES via env vars
- **added** — NEAR AI Cloud provider
- **added** — goose://resume session deep link
- **added** — Scaleway provider
- **added** — GOOSE_FAST_MODEL env var support in ModelConfig::with_fast
- **fixed** — Forward custom headers through OAuth connect path

##### ✨ Features

- xAI SuperGrok OAuth subscription provider [#9420](https://github.com/aaif-goose/goose/pull/9420)
- Replay ACP images on session load [#9496](https://github.com/aaif-goose/goose/pull/9496)
- Expose raw provider supported models over ACP [#9475](https://github.com/aaif-goose/goose/pull/9475)
- ACP session system prompt setter [#9478](https://github.com/aaif-goose/goose/pull/9478)
- Scholar Sidekick MCP extension [#9433](https://github.com/aaif-goose/goose/pull/9433)
- `tui` feature flag to gate the TUI command [#9428](https://github.com/aaif-goose/goose/pull/9428)
- CLI to list skills with token counts [#9326](https://github.com/aaif-goose/goose/pull/9326)
- Perplexity as a declarative OpenAI-compatible provider [#9324](https://github.com/aaif-goose/goose/pull/9324)
- Alibaba (Qwen via DashScope) declarative provider [#9443](https://github.com/aaif-goose/goose/pull/9443)
- Configurable tool output size limit via GOOSE_MAX_TOOL_RESPONSE_SIZE [#9256](https://github.com/aaif-goose/goose/pull/9256)
- `/model` slash command to CLI for session model switching [#8747](https://github.com/aaif-goose/goose/pull/8747)
- Databricks AI Gateway provider [#9274](https://github.com/aaif-goose/goose/pull/9274)
- Russian language support [#9406](https://github.com/aaif-goose/goose/pull/9406)
- Turkish desktop locale [#9392](https://github.com/aaif-goose/goose/pull/9392)
- TUI command on goose-cli [#9385](https://github.com/aaif-goose/goose/pull/9385)
- Configurable MAX_CODE_BLOCK_LINES via env vars [#9301](https://github.com/aaif-goose/goose/pull/9301)
- NEAR AI Cloud provider [#9352](https://github.com/aaif-goose/goose/pull/9352)
- `goose://resume` session deep link [#9343](https://github.com/aaif-goose/goose/pull/9343)
- Scaleway provider [#9254](https://github.com/aaif-goose/goose/pull/9254)
- GOOSE_FAST_MODEL env var support in ModelConfig::with_fast [#9296](https://github.com/aaif-goose/goose/pull/9296)
- Harbor eval runner [#9138](https://github.com/aaif-goose/goose/pull/9138)
- Slash commands (built-in, skill, recipe) in ACP server [#9238](https://github.com/aaif-goose/goose/pull/9238)
- `/goal` command for agent self-evaluation before finishing [#9069](https://github.com/aaif-goose/goose/pull/9069)
- Summon subagent instructions [#9325](https://github.com/aaif-goose/goose/pull/9325)
- Open-plugins generalization + skills [#9112](https://github.com/aaif-goose/goose/pull/9112)
- PreToolUse denial hooks [#9304](https://github.com/aaif-goose/goose/pull/9304)
- ACP session list pagination [#9199](https://github.com/aaif-goose/goose/pull/9199)
- `goose review` local code review command [#9114](https://github.com/aaif-goose/goose/pull/9114)
- TUI diff viewer [#9260](https://github.com/aaif-goose/goose/pull/9260)
- `goose://new-session` deep link to open fresh chat [#9196](https://github.com/aaif-goose/goose/pull/9196)
- Atomic Chat as declarative OpenAI-compatible provider [#9210](https://github.com/aaif-goose/goose/pull/9210)
- GOOSE_OAUTH_CALLBACK_PORT for stable OAuth redirect_uri [#9209](https://github.com/aaif-goose/goose/pull/9209)
- Proactive OAuth token refresh to avoid re-auth on every session [#8386](https://github.com/aaif-goose/goose/pull/8386)
- GPT-5.5 added to ChatGPT Codex known models [#9292](https://github.com/aaif-goose/goose/pull/9292)
- Opt-in to Vercel AI gateway leaderboard [#9259](https://github.com/aaif-goose/goose/pull/9259)
- ACP pass session cwd param to providers [#9229](https://github.com/aaif-goose/goose/pull/9229)
- Routstr as a declarative provider [#9175](https://github.com/aaif-goose/goose/pull/9175)
- FuturMix provider [#8840](https://github.com/aaif-goose/goose/pull/8840)
- oMLX declarative provider [#9177](https://github.com/aaif-goose/goose/pull/9177)
- Strip chain-of-thought markers from custom provider output [#8635](https://github.com/aaif-goose/goose/pull/8635)
- Encrypted Nostr session sharing [#8922](https://github.com/aaif-goose/goose/pull/8922)
- Simplified Chinese (zh-CN) transl

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.37.0]_

### v1.36.0

- Date: 2026-05-27
- Version: v1.36.0
- Original notes: https://github.com/aaif-goose/goose/releases/tag/v1.36.0
- Permalink: https://whatsnew.fyi/product/goose/releases/v1.36.0

- **added** — TUI command on goose-cli
- **added** — TUI diff viewer
- **added** — goose review local code review command
- **added** — /goal command for agent self-evaluation before finishing
- **added** — Hooks system for PreToolUse denial and extensibility
- **added** — Slash commands (built-in, skill, recipe) in ACP server
- **added** — Open-plugins generalization with skills
- **added** — Summon subagent instructions
- **added** — Unified thinking effort control across all providers
- **added** — NEAR AI Cloud provider
- **added** — Scaleway provider
- **added** — Vercel AI Gateway provider
- **added** — Atomic Chat declarative OpenAI-compatible provider
- **added** — Routstr declarative provider
- **added** — FuturMix provider
- **added** — oMLX declarative provider
- **added** — Harbor eval runner
- **added** — goose://resume and goose://new-session deep links
- **added** — MAX_CODE_BLOCK_LINES configurable via env vars
- **added** — Honor GOOSE_FAST_MODEL env var in ModelConfig
- **added** — GPT-5.5 in known models
- **added** — Paginate ACP session list
- **added** — Pass session cwd param to ACP providers
- **added** — Opt-in to Vercel AI gateway leaderboard
- **added** — GOOSE_OAUTH_CALLBACK_PORT for stable OAuth redirect_uri
- **added** — Proactive OAuth token refresh to avoid re-auth on every session
- **added** — Strip chain-of-thought markers from custom provider output
- **added** — Encrypted Nostr session sharing
- **added** — Simplified Chinese (zh-CN) translation
- **added** — Russian language support
- **added** — Turkish desktop locale
- **added** — Nushell terminal and completion support
- **added** — Optional --parameters flag for scheduled recipes
- **added** — Quarterly option for scheduler
- **added** — GitHub Copilot /responses API support
- **added** — Worktree-aware directory switcher
- **added** — Chat history search feature
- **added** — Projects as backend sources with system prompt injection
- **added** — Linux Vulkan support for local inference
- **added** — Linux musl CLI builds
- **added** — Windows CUDA release artifacts
- **added** — GOOSE_DISABLE_TOOL_CALL_SUMMARY env var
- **fixed** — Tolerate missing responses output
- **fixed** — Stop main window growing taller on every launch
- **fixed** — Desktop chat search session limiting
- **fixed** — Serialize per-session agent creation to stop duplicate MCP init
- **fixed** — Respect GOOSE_MAX_TURNS in gateway sessions
- **fixed** — Send empty object instead of null for Anthropic tool_use input
- **fixed** — Preserve thinking content for provider context
- **fixed** — Mention configurable timeout env vars in Ollama stream stall error
- **fixed** — Include full recipe parameter details in load/discovery output
- **security** — Remove unused fetch-metadata IPC handler (SSRF)
- **fixed** — Use context limit from /model/info for LiteLLM custom models
- **fixed** — Plain > prompt instead of goose emoji in CLI
- **fixed** — Stop killing goosed when a window closes
- **fixed** — Emit trace_output as span attribute instead of event
- **fixed** — Check file fallback when keyring has no entry
- **fixed** — Align sidebar hamburger in macOS fullscreen
- **fixed** — Use current_exe() instead of PATH lookup when spawning goose

##### ✨ Features

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

_[Truncated at 4000 characters — full notes: https://github.com/aaif-goose/goose/releases/tag/v1.36.0]_