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.