Goose

v1.43.0 Feature

This release adds 5 notable features for engineering teams evaluating rollout.

Published 12d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

acp ai ai-agents mcp

Affected surfaces

crypto_tls

Summary

AI summary

Broad release touches 🐛 Bug Fixes, ✨ Features, 🔧 Improvements, and 📚 Documentation.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Low	Adds per-message usage stats UI (tokens, cost, TTFT, tok/s). Adds per-message usage stats UI (tokens, cost, TTFT, tok/s). Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds per-message usage and cost tracking with derived session totals. Adds per-message usage and cost tracking with derived session totals. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds OllamaCloudProvider with dynamic model discovery and context limits. Adds OllamaCloudProvider with dynamic model discovery and context limits. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds iFlytek Spark and Astron MaaS providers. Adds iFlytek Spark and Astron MaaS providers. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds Fireworks AI declarative provider. Adds Fireworks AI declarative provider. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds OpenRouter request parameters support. Adds OpenRouter request parameters support. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds OVHcloud Qwen3.6-27B model (262K context). Adds OVHcloud Qwen3.6-27B model (262K context). Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds GPT‑5.6 family support. Adds GPT‑5.6 family support. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Adds GLM‑5.2 support. Adds GLM‑5.2 support. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Reconnects desktop ACP sessions after sleep or connection loss. Reconnects desktop ACP sessions after sleep or connection loss. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Groups chat sessions by project in the navigation panel. Groups chat sessions by project in the navigation panel. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Displays project names in the directory switcher dropdown. Displays project names in the directory switcher dropdown. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Removes custom app delete support from the Apps UI. Removes custom app delete support from the Apps UI. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Adds `--edit` flag to edit a conversation before forking it. Adds `--edit` flag to edit a conversation before forking it. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Adds French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese locales for the desktop app. Adds French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese locales for the desktop app. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Introduces provider bindings MVP to goose‑sdk with Python wheel publishing. Introduces provider bindings MVP to goose‑sdk with Python wheel publishing. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Enables TLS support for ACP serve. Enables TLS support for ACP serve. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Feature	Low	Adds streamable HTTP support in the deeplink generator. Adds streamable HTTP support in the deeplink generator. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix
Bugfix	Medium	Fixes Gemini OAuth onboarding failure. Fixes Gemini OAuth onboarding failure. Source: llm_adapter@2026-07-14 Confidence: low	—
Bugfix	Low	Excludes MCP App tools from Code Mode callbacks. Excludes MCP App tools from Code Mode callbacks. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Preserves reasoning_content for DeepSeek thinking mode on multi‑turn tool calls. Preserves reasoning_content for DeepSeek thinking mode on multi‑turn tool calls. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Disables compaction during approval flow. Disables compaction during approval flow. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Treats empty‑string finish_reason as non‑terminal in streaming responses. Treats empty‑string finish_reason as non‑terminal in streaming responses. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Retries empty provider turns instead of stopping silently. Retries empty provider turns instead of stopping silently. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Protects llama.cpp backend initialization against SIGILL on CPUs lacking FMA/AVX2. Protects llama.cpp backend initialization against SIGILL on CPUs lacking FMA/AVX2. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Sanitizes function call names in responses. Sanitizes function call names in responses. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Selects session mode from IDs actually offered by the agent. Selects session mode from IDs actually offered by the agent. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Corrects desktop ACP shell PATH configuration. Corrects desktop ACP shell PATH configuration. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Deduplicates duplicate signed thinking blocks to avoid Anthropic 400 errors. Deduplicates duplicate signed thinking blocks to avoid Anthropic 400 errors. Source: granite4.1:30b@2026-07-14-audit Confidence: low	—
Bugfix	Low	Resolves provider default model instead of leaking sentinel "current". Resolves provider default model instead of leaking sentinel "current". Source: granite4.1:30b@2026-07-14-audit Confidence: low	—

Full changelog

✨ 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

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Goose

Get notified when new releases ship.

About Goose

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

All releases →