LlmBackend

Abstract interface for an LLM CLI backend.

Usage

LlmBackend()

Concrete backends map abstract model sizes to provider-specific model names and encapsulate how to invoke the provider’s CLI and parse the raw response.

Attributes

models: dict[TModel, str]: Mapping from abstract model size to the provider’s model name.

Methods

Name	Description
build_command()	Build the CLI argv for a single invocation (prompt delivered via stdin).
env()	Return extra environment variables for the CLI invocation, merged over the inherited environment.
parse_response()	Parse raw CLI stdout into text or a validated model.

build_command()

Build the CLI argv for a single invocation (prompt delivered via stdin).

Usage

Source

build_command(model, schema_path, agent)

Parameters

model: str: Provider-specific model name.
schema_path: str | None: Schema argument for structured output, or None.
agent: bool: Whether the invocation may use tools / agent capabilities.

Returns

list[str]: The argv list to execute.

env()

Return extra environment variables for the CLI invocation, merged over the inherited environment.

Usage

Source

env()

parse_response()

Parse raw CLI stdout into text or a validated model.

Usage

Source

parse_response(raw, response_model)

Parameters

raw: str: Raw stdout from the backend CLI.
response_model: type[BaseModel] | None: Model to validate against, or None for raw text.

Returns

str | BaseModel: raw when response_model is None, else a validated instance.