can1357 4d3d181d8e fix(coding-agent): changed local tiny-model default to CPU inference ...

- Changed tiny-device preference resolution to always default to CPU instead of platform-specific DirectML/CUDA heuristics.
- Updated settings schema, documentation, and changelog text to describe the CPU default while keeping accelerated providers behind explicit `providers.tinyModelDevice`/`PI_TINY_DEVICE` choices.

2026-05-31 03:39:38 +02:00

..

device.ts

fix(coding-agent): changed local tiny-model default to CPU inference

2026-05-31 03:39:38 +02:00

dtype.ts

feat(tiny): added providers.tinyModelDevice and tinyModelDtype settings

2026-05-31 02:14:58 +02:00

models.ts

feat(coding-agent): added per-turn AUTO_THINKING in coding-agent session

2026-05-31 03:32:21 +02:00

text.ts

feat(tiny/text): added code block stripping for session title generation

2026-05-30 23:13:11 +02:00

title-client.ts

feat(tiny): added providers.tinyModelDevice and tinyModelDtype settings

2026-05-31 02:14:58 +02:00

title-protocol.ts

feat(coding-agent): added local model registry for title completion

2026-05-30 18:41:48 +02:00

worker.ts

feat(tiny): added GPU-first device selection with CPU fallback for local models

2026-05-31 01:57:59 +02:00