Python API

These pages are maintainer-facing interfaces, not a separately versioned third-party SDK.

Versioned YAML configuration for MUDIDI commands.

The models in this module are the public configuration boundary. Runtime credentials deliberately remain outside these models and are loaded from the environment by the LLM client.

InferenceConfig

Bases: _ExtractionConfig

Production inference configuration.

BenchmarkRunConfig

Bases: _ExtractionConfig

Benchmark extraction configuration.

Stage1EvaluationConfig

Bases: _EvaluationConfig

Stage2EvaluationConfig

Bases: _EvaluationConfig

load_yaml_config(path, *, expected_kind=None)

Load and validate a MUDIDI YAML configuration file.

merge_explicit_overrides(config, overrides)

Return config with sparse dotted-path CLI overrides applied.

Generic bounded verifier-rewriter loop.

The loop is deliberately small and stage-agnostic. Stage-specific code supplies the verifier and rewriter callables; this module owns stop criteria and audit artifacts.

AgenticLoopConfig

Bases: BaseModel

Loop controls shared by Stage 1 and Stage 2 agentic modes.

AgenticVerifierDecision

Bases: BaseModel

Structured verifier response used by both stages.

run_bounded_verifier_loop(*, stage, initial_output, artifact_dir, output_suffix, verify, rewrite, config)

Run a bounded stage-local verifier-rewriter loop.

max_iterations counts rewrite attempts after the initial output. Attempt 0 is always the normal stage output; attempt 1 is the first correction.