sklearn metadata routing: let `treatment` reach a learner inside a Pipeline

Part of #980 (v1.0 M1). Closes #854 when it lands.

Reordering fit to (X, y, treatment, …) is necessary but not sufficient for #854. Pipeline.fit(X, y) passes exactly two things; treatment is a third required array with nowhere to ride. After the flip a CausalML learner still can't be a Pipeline step without an adapter — the reordering just removes the first obstacle.

The mechanism sklearn provides is metadata routing: fit(X, y, **fit_params) with set_fit_request(treatment=True), so a caller writes pipe.fit(X, y, treatment=treatment) and the router delivers treatment to the step that asked for it.

Prerequisite

#985, the signature flip. Until then Pipeline's positional y binds to treatment, so an end-to-end test cannot be written. #985 is unblocked and targets v1.0 (Jun 2027).

Scope for the first pass

• Meta-learners only — they are the classes users most want inside a Pipeline.
• Integration tests and documentation before any custom MetadataRouter. BaseLearner subclasses BaseEstimator and the fit signatures declare treatment and p explicitly, so set_fit_request should be generated automatically; confirm that against sklearn.utils.metadata_routing before writing any routing code.
• Cover an S-learner pipeline plus one propensity-consuming learner.
• Cover both paths: routing enabled via sklearn.set_config(enable_metadata_routing=True), and the prefixed routing-disabled form.
• Row-preserving transformers only. Resampling has to move X, y, treatment and p together and belongs in its own design.

Out of scope for the first pass: whether p should route into a learner's wrapped estimator, rather than being consumed by the learner itself.

Why it's separate

The argument order is a breaking change on a deadline (v1.0 API freeze); routing is additive and can land any time after. Coupling them would put a design-heavy feature on the critical path of a mechanical rename.

Acceptance

• A documented, tested example of a CausalML learner as a Pipeline final step with treatment routed, no adapter class.
• #854's original reproduction works.

Start with sklearn.utils.metadata_routing and Pipeline, then inspect BaseLearner and the meta-learner fit signatures after #985 lands. Add integration coverage for an S-learner and a propensity-consuming learner with enabled and prefixed routing, plus the documented Pipeline example. Done means treatment reaches the final learner without an adapter and #854's reproduction works.