Persist chat tools and stream artifact drafts

Keep model resident on cancel and harden artifact tools

Remove duplicate shard verification pass

Warm the active chat prompt shape

Warm WebGPU before first prompt

Use manifest context limits and handle memory exhaustion safely

Set 8K context defaults and add artifact ZIP export

Assert 4096-token runtime defaults

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 v1.1.3 scored WebGPU evidence

Release v1.1.2 benchmark runtime evidence

Add Phase 5 benchmark and runtime provenance

Release browser-local Bonsai WebGPU chat