Reasoning models on OpenAI-compatible custom endpoints (e.g. GLM / Kimi)
often reason and reply with prose instead of emitting native tool calls
under the default auto tool choice, stalling the tool-driven scan loop
while burning tokens. Default force_required_tool_choice to auto (None):
enable tool_choice=required when an api_base is set (still gated to
models that accept it), off otherwise. Explicit 0/1 overrides.
feat(inputs): implement logic for required tool choice based on model
test(inputs): add tests for force_required_tool_choice behavior
test(runner): update tests to include force_required_tool_choice in settings
Alex Schapiro