0.15.2 — Easier connections, safer starts, and useful failures

0.15.2 makes local model serving easier to connect, harder to misconfigure, and much more useful when startup fails.

• Connect an agent without hunting for server details. Desktop now puts the local endpoint and copy-ready connection information first, followed by guided integration choices. The server’s purpose is visible as soon as it is running.
• More capable local model paths. GLM-5.3 Flash can participate in the QuickSilver pool and gains an explicit default reasoning-effort control. Qwen4 can load validated PLE rows from a bounded sidecar. Laya and CLM System One are supported, and LFM2.5-VL gains a qualified DSpark companion.
• The default port no longer turns a healthy launch into a dead end. If port 8000 is occupied and you did not explicitly choose a port, rapid-mlx serve selects the next free port from a bounded range and prints the choice. An explicit --port remains strict, and inherited listeners remain validated.
• Missing optional support is actionable. Vision, image, video, and audio startup failures identify the exact extra and can offer to install it. Use --yes for unattended setup.
• Startup failures keep their real cause. Hugging Face access failures, invalid configs, tokenizer failures, incompatible weights, quantization mismatches, and insufficient memory retain stable categories across CLI and Desktop instead of collapsing into a generic error.
• Crash diagnostics survive the process. Fatal server tracebacks are persisted, and the next launch can report that the previous startup ended before reaching a terminal state instead of leaving a silent gap.

Telemetry remains restricted to the documented closed event schema. Crash details stay local on the Mac and are not uploaded as telemetry.