v0.6.5
multica-ai/multicav0.6.5Oct 21, 2026by github-actions[bot]
Upgrading?
Full Release Notes
## Changelog * 6dadfc7216d0fc8e746442ee890b3b89755b1fa3 MUL-7857 fix(wakeup): evaluate --until-pr against self-hosted VCS pull requests (#9039) * 9a8c3dec4e95deed45d6032be2d6ae94b23a32f5 MUL-7879: fix(wakeup): clear a rule's last_error once a pass commits (#9069) * 3f657e29cf6c70cd2723fdee88647c9f114f68bc MUL-7890 perf(inbox): fetch the unread summary only while the page is visible (#9085) * 1e01173fb42806c41887293695c0fe5d503123fa MUL-8060 fix(daemon): trust the backend's SSL_CERT_DIR CAs when syncing repos (#9312) * 3c65b18c9998ea8b6b3b5d0474fe781b472ba15e MUL-8118 fix(workflows): edit a new status step before saving (#9385) * a69021482fde59a2b378f556752e5a2f047ebc30 MUL-8119 fix(views): keep workflow name visible in project sidebar (#9387) * 37d360063475dd6d6bbc911b6bbdc7c33069da35 MUL-8121 feat(issues): offer Default workflow statuses for issues outside a project (#9389) * 654b8ca954034f8181eb6bbb4fc298dede760156 MUL-8123 chore(release): 0.6.5 changelog and app versions (#9393) * 74281e313d3cb97c6c7291739c51dc9ccf06cbac fix(agent): deliver the copilot prompt on stdin (MUL-8105) (#9380) * 5b21b63fa89d2f2ea41ac0ca8db584b899b65a9d fix(codex): attribute default-model usage (#9360) * 984d8192ad0c4d9cd0c58dabd65246cc296b6fa5 fix(daemon): preserve Claude effort for unlisted models (MUL-8112) (#9392) * 4caf571aab9fc67d453e48019fe413eabfa224a0 fix(desktop): localize the workspace tab bar menu (#9099) * 4152fed89fc04450a715bff2e028348b603c601c fix(opencode): discover v2 model thinking variants (ZIC-351) (#9365) * 7a81f73ca2cd29a92e3808503dc11fa8a2ffb0fe fix(views): contain absolute sidebar content in its scroller (MUL-8100) (#9361)
Related Repositories
ollama/ollama★ 184,258
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,072
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,646
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,197
The world’s fastest framework for building websites.
junegunn/fzf★ 83,716
:cherry_blossom: A command-line fuzzy finder