Releasesby IbisCoCo Desktop v1.21.7
Update11 days agoUnverifiedAdded Oct 17, 2026
CoCo Desktop v1.21.7 lets the agent manage your automations and makes MCP connections easier to control:
Topics: AI agents, MCP, Coding agents
More Cortex Code releases
Every Cortex Code releaseEnforce CoCo policy with MDM (Preview)
Enforcing CoCo policy with Mobile Device Management (MDM) is now available in preview. Administrators can deliver account restrictions, allowed authentication methods, and minimum version requirements for CoCo CLI and CoCo Desktop through a macOS configuration profile, Windows Group Policy or Intune, or managed-settings.json .
CoCo Desktop v1.21.6
CoCo Desktop v1.21.6 refines everyday chat controls and shores up connectivity:
CoCo Desktop v1.21.5
CoCo Desktop v1.21.5 is a small quality release on top of v1.21.4, focused on error messages that tell you what to do next:
CoCo Desktop v1.21.4
CoCo Desktop v1.21.4 is a polish and reliability release on top of v1.21.3:
CoCo Desktop v1.21.3
CoCo Desktop v1.21.3 isolates the Snowflake session that agent SQL runs in, adds full-text search across past sessions, and makes the redesigned dbt workspace the standard dbt experience:
CoCo Desktop v1.21.2
CoCo Desktop v1.21.2 adds new ways to visualize query results and create automations, and fixes reliability problems in long-running sessions and at startup on managed machines:
CoCo in the Snowflake Extension for Visual Studio Code (General availability)
CoCo in the Snowflake Extension for Visual Studio Code is now generally available. CoCo runs in a side panel next to the extension's existing SQL and Snowpark Python workflows, so you can work locally while you stay connected to your Snowflake account.
CoCo Desktop v1.21.1
CoCo Desktop v1.21.1 is a stability and polish release that focuses on automation schedules, native HTML report publishing, and reliability:
Also shipped on Oct 13, 2026
Snowflake 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 .