Expand description
LLM backend abstraction (ADR 0016; an engine module since ADR 0018).
Nothing else in the engine may reach into subprocess machinery: grouping
and the pipeline consume only LlmBackend/CommandBackend from here.
The grouping stage needs exactly one capability from a model: one-shot text completion — prompt in, raw text out. The contract is deliberately that narrow: no tools, no streaming, no chat state. Every observed hard failure of the evaluated grouping tools was a model CLI stopping to call a tool (ADR 0010); a backend that cannot express tools cannot fail that way.
Structs§
- Command
Backend - A subprocess backend: prompt on stdin, completion on stdout.
Enums§
Traits§
- LlmBackend
- One-shot completion: prompt in, raw text out.