4 people f0f9dd6656 feat(setup): ask whether OpenAI-compatible gateway models support thinking (#3428) ...

The "Other OpenAI-compatible" wizard provider lets users supply a custom base_url and model name but never asked whether that model supports thinking/reasoning, so the generated config.yaml always left supports_thinking at its default of false — even for reasoning models behind the gateway.

Add an explicit ask_thinking_support flag on LLMProvider (enabled for the "other" provider) plus a pure with_thinking_support() helper. When the flag is set, the LLM step prompts via ask_yes_no; confirming wires the standard OpenAI-compatible enable/disable thinking toggles, declining records supports_thinking=false. Provider definitions are copied with dataclasses.replace, never mutated. Adds unit tests for the helper and the interactive step.

Closes #3162

Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-07-05 19:55:39 +08:00

..

steps

feat(setup): ask whether OpenAI-compatible gateway models support thinking (#3428)

2026-07-05 19:55:39 +08:00

__init__.py

feat(dx): Setup Wizard + doctor command — closes #2030 (#2034)

2026-04-10 17:43:39 +08:00

providers.py

feat(setup): ask whether OpenAI-compatible gateway models support thinking (#3428)

2026-07-05 19:55:39 +08:00

ui.py

feat(im): Add user-owned IM channel connections (#3487)

2026-06-12 15:24:58 +08:00

writer.py

fix(wizard): update DeepSeek provider models to v4 (#3939)

2026-07-04 21:44:22 +08:00