Releasesby IbisApprove every tool from a chat connector at once
UpdateyesterdayUnverifiedAdded Oct 14, 2026
You can now select Always allow all tools from this connection when Lovable asks you to approve a tool from a chat connector , and every tool from that connection runs without asking from then on, including tools the server adds later. The choice applies to your own approvals only, and you can change it in the connection's settings in Connectors .
Topics: Data integration
More Lovable releases
Every Lovable releaseLet browser agents use your app
You can now let browser agents use your app . When you enable agent integrations, Lovable also adds WebMCP tools to your app, so an AI agent built into the browser can act on the page a person has open, such as marking a task as done or filtering a list.
Gemini 4 Argon for your app's AI features
Your app's AI features can now use Google's Gemini 4 Argon ( google/gemini-4-argon ), a frontier model for long-horizon coding, reasoning, and knowledge work. It accepts text, image, audio, and video input and comes at a premium price. Ask Lovable to use it in your app, or describe what you want and let Lovable pick.
Supported PostgreSQL extensions on Lovable Cloud
Lovable Cloud databases support a fixed set of PostgreSQL extensions , such as pg_cron , pg_net , vector , and postgis . Lovable now refuses CREATE EXTENSION for any other extension, in the project chat, the SQL editor, and the Lovable API, and builds the feature with plain SQL instead. Extensions already installed in your database keep working.
Search for individual settings
You can now search for individual settings in workspace settings. Start typing in the search box at the top of the settings sidebar, and the results list the matching settings grouped by settings page, with the matching words highlighted. Select a result to open that setting.
Edit images directly in the Files tab
You can now mark a change directly on an image in your project's Files tab. Open the image and select Edit , then draw over an area and describe the change, pin a comment where you want something changed, erase what you want removed, or remove the background. Lovable saves the result as a new file next to the original.
See how much usage your free allowances cover
On Free, Pro, and Business plans, you can now see how much of your usage the free allowances covered . Usage details shows the covered credits next to the total above the chart, and the By coverage view splits each bar into what the daily build credits, the daily chat allowance, and the monthly Cloud, AI, and connector grants paid for, and what drew on your...
Connect your app to Loops
You can now connect your Lovable app to Loops to create and update contacts, send events that start your Loops automations, and send transactional email you manage in Loops. It fits waitlists, signup forms, and product notifications that should reach people from your Loops audience. Add it from Connectors , or ask Lovable in a project to connect it.
Publish every app in your workspace under your own domain
Workspace admins and owners on Enterprise plans can now set a publishing domain for the workspace, so projects publish at your-app.yourdomain.com instead of your-app.lovable.app . Pick a domain you bought through Lovable, or a subdomain of it, with no DNS setup. You can also connect a domain or subdomain you own elsewhere.
Also shipped on Oct 13, 2026
Lovable in October 2026What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
The AI.AGG function is generally available (GA)
The AI.AGG function is generally available (GA). You can use this function to semantically aggregate unstructured input data based on natural language instructions.
BigQuery generative AI functions now support the gemini-4-argon model
BigQuery generative AI functions now support the gemini-4-argon model. This model is generally available .
Gemini 4 Argon in CodeMender (Preview)
CodeMender now supports Gemini 4 Argon. To use it, pass --model gemini-4-argon to cm find , cm verify , or cm fix . Gemini 3.8 Flash remains the default model. For more information, see Specifying the model .
Gemini 4 Argon and Gemini 4 Argon Cyber Permissive
Gemini 4 Argon ( gemini-4-argon ) is available in General Availability (GA) . Gemini 4 Argon is Google's frontier model that excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.
On-demand state repartitioning is now generally available
On-demand state repartitioning is now generally available. You can resize the number of shuffle partitions for a stateful Structured Streaming query or Lakeflow pipeline without losing checkpoint state. See On-demand state repartitioning for stateful streaming queries .