Module runner 

Async test and eval execution: expand fixtures into Case rows, apply mocks or live generation, optionally run evaluators (rules / golden / process / judge), and produce a Run.

Entry points:

• run_fixtures — test-style runs (assertions + optional rules on each case).
• run_eval — eval-style runs with configurable evaluator and multi-run aggregation.

Requires a Tokio runtime (multi-thread recommended for parallel cases).

Structs

EvalConfig

Extends RunnerConfig with evaluation-specific options (evaluator id, judge, thresholds, multi-run seeding, optional progress bar).

RunnerConfig

Tunables for run_fixtures (concurrency, timeouts, mocks directory, offline mode, etc.).

SecretScrubber

Enums

GenerationMode

How synthetic traces are produced for each case.

GeneratorProvider

SandboxError

Functions

run_case

Run a single crate::Case: replay tool expectations against crate::MockEngine, apply output rules when enabled, and return a crate::CaseResult.

run_eval

Like run_fixtures, but runs the eval pipeline (repeated runs, effectiveness threshold, selected crate::Evaluator) and attaches crate::EvalScores when applicable.

run_fixtures

Execute all cases from the given fixtures using RunnerConfig and return a completed Run.