Persist chat tools and stream artifact drafts

Warm the active chat prompt shape

Warm WebGPU before first prompt

Use manifest context limits and handle memory exhaustion safely

Assert 4096-token runtime defaults

Fix streamed tool calls and align generation limits

Release v1.2.2 interactive chat workspace

Release v1.2.0 live model telemetry

Release v1.1.3 scored WebGPU evidence

Add Phase 5 benchmark and runtime provenance

Release browser-local Bonsai WebGPU chat