Changelog

Your coding agent's model picker now shows only the model it can actually use, instead of dozens that error.

Fixes a provider error when chatting with your coding agent on included credits.

Updating Claude Code, Codex or OpenCode from inside your agent now works.

It was failing with a permissions error.

Your coding agent can now use the paid tools you've enabled, the same way your other agents do.

Turn tools on from the agent's page and it picks them up natively.

Restarting your coding agent now reliably brings it back up, including when you restart one that is already shutting down. Also updates the agent to the latest core.

Core 0.0.40.

Opening a file in Drive now keeps it open, instead of sliding to the folder's first file a moment later, and a link straight to a file lands on that file. Menus also close again when you click the button that opened them.

Long conversations load faster and the agent stays responsive while it is working through them. If your agent restarts mid-answer, the reply it owed you is picked up again instead of being dropped.

Also: updates apply more safely, skills stay in one place across workspaces, and you can share a read-only link to a conversation.

Core 2026.9.4. See the upstream changelog shipped in the package for the complete list.

Telling your agent to stop halts the task it is working on, not just the helpers it started.

Also: errors in chat read more clearly, and research answers can carry images from their sources.

Core 1.2.5 · upstream notes.

Updates your agent to the latest Hermes release. Chat history, sessions and search are markedly more reliable, and a long conversation is far less likely to break.

Core v2026.9.11 · upstream notes.

A file someone sends you now downloads instead of opening in the page, unless it is a photo, a PDF or plain text.

When another connected agent writes into one of your conversations, its messages are labelled as theirs, so your own history never reads as though you said something you did not.

Messages you queue while Nova is working stay in the order you typed them, and a queue you paused waits for you rather than emptying itself.

Messages you queue while Nova is working now go out one after another, each waiting for the last answer to finish. They used to leave together the moment Nova finished, and only the first one got answered.

Type while Nova is answering and your message waits in a list instead of disappearing. Send it straight into the answer being written, stop the answer and send it, or leave it and it goes on its own the moment Nova finishes.

Stop now really stops, instead of only clearing your screen while the work carried on.

Leaving a chat while Nova is answering no longer loses the reply. Come back and it is there.

Scheduled tasks now carry memory between runs, so a daily briefing knows what it already told you. Agents can also message each other directly, and long-running helpers can be steered or stopped mid-task.

Also: more models to pick from, tighter protection of the agent's own instruction files, and steadier Telegram connections that recover on their own.

Core v2026.8.31 · upstream notes.

Charts and diagrams now render right inside your conversations, and your agent starts up faster. Updates are safer too: if an update goes wrong, your agent rolls back on its own and keeps working with its configuration intact.

Plus a large batch of fixes across Telegram, WhatsApp, Signal, and the other channels.

Core 2026.9.1. See the upstream changelog shipped in the package for the complete list.

If Nova ever stops accepting your messages, it now sorts itself out and comes back on its own, instead of sitting there until someone restarts it.

Fixes an issue where updating your agent could occasionally fail. Plus small bug fixes.

Core v2026.8.27 · upstream notes.

Fixes an issue where changing your agent's model in the dashboard could appear to do nothing. Your agent now always follows the model you chose.

Core v2026.8.27 · upstream notes.

Reconnecting a channel with a fresh credential now brings it back straight away. Plus reliability improvements.

Core v2026.8.27 · upstream notes.

A messaging channel that stops working is now turned off cleanly while the rest of your agent keeps running. Your credential and settings are kept safe so you can restore the channel, and the channels list tells you what happened and when.

Core v2026.8.27 · upstream notes.

If one of your messaging channels stops working, your agent now keeps running. The channel shows as disconnected with the reason, and everything else carries on.

Core v2026.8.27 · upstream notes.