Persist chat tools and stream artifact drafts

Collapse live reasoning and suppress warm prepare

Clarify warm inference preparation

Keep model resident on cancel and harden artifact tools

Persist tool logs and recover chats with invalid artifacts

Warm WebGPU before first prompt

Use manifest context limits and handle memory exhaustion safely

Set 8K context defaults and add artifact ZIP export

Add persistent multi-file artifact workspaces

Render ordered agent flow and edit messages

Add agentic artifact tools and live diagnostics

Use 4096-token release defaults

Fix streamed tool calls and align generation limits

Release v1.2.2 interactive chat workspace

Release v1.2.0 live model telemetry

Release v1.1.4 manifest progress fix

Select the flagship 27B tier by default

Add Phase 5 benchmark and runtime provenance

Release browser-local Bonsai WebGPU chat