Fix CI review R6: P3 doc + replicate-weight parity polish

- twowayfeweights() now raises NotImplementedError when the resolved
  survey design carries replicate weights, matching fit()'s contract.
  The fit/helper parity promise now holds for unsupported inputs too.
- docs/llms-full.txt and ROADMAP.md no longer claim that Phase 3
  parameters raise NotImplementedError; both now correctly note that
  only `aggregate` remains gated.
- Added a helper-level regression that pins the replicate-weight
  rejection, complementing the existing fit()-level test.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: igerber

ROADMAP.md

@@ -191,7 +191,7 @@ These remain in **Future Estimators** below if/when we choose to extend.
 ### Architectural notes (for plan and PR reviewers)
 
 - **Single `ChaisemartinDHaultfoeuille` class** (alias `DCDH`). Not a family. New features land as `fit()` parameters or fields on the results dataclass. No `DCDHDynamic`, `DCDHCovariate`, etc. Matches the library's idiomatic pattern: `CallawaySantAnna`, `ImputationDiD`, and `EfficientDiD` are all single classes that evolved across many phases.
-- **Forward-compatible API from Phase 1.** `fit(aggregate=None, controls=None, trends_linear=None, L_max=None, ...)` accepts the Phase 2/3 parameters from day one and raises `NotImplementedError` with a clear pointer to the relevant phase until they are implemented. No signature changes between phases.
+- **Forward-compatible API from Phase 1.** `fit(aggregate=None, controls=None, trends_linear=None, L_max=None, ...)` accepts the Phase 2/3 parameters from day one and raised `NotImplementedError` with a clear pointer to the relevant phase until they were implemented. As of the dCDH work, Phase 2, Phase 3, and `survey_design` are all live; only `aggregate` remains gated with `NotImplementedError`. No signature changes between phases.
 - **Conservative CI** under Assumption 8 (independent groups), exact only under iid sampling. Documented in REGISTRY.md as a `**Note:**` deviation from "default nominal coverage." Theorem 1 of the dynamic paper.
 - **Cohort recentering for variance is essential.** Cohorts are defined by the triple `(D_{g,1}, F_g, S_g)`. The plug-in variance subtracts cohort-conditional means, **NOT a single grand mean**. Test fixtures must catch this — a wrong implementation silently produces a smaller, incorrect variance.
 - **No Rust acceleration is planned for any phase.** The estimator's hot path is groupby + BLAS-accelerated matrix-vector products, where NumPy already operates near-optimally. If profiling on large panels (`G > 100K`) reveals a bottleneck post-ship, the existing `_rust_bootstrap_weights` helper can be reused for the bootstrap loop without writing new Rust code.

diff_diff/chaisemartin_dhaultfoeuille.py

@@ -5068,6 +5068,16 @@ def twowayfeweights(
                 f"The TWFE diagnostic under survey uses survey-weighted cell "
                 f"means; other weight types are not supported."
             )
+        if (
+            resolved is not None
+            and resolved.replicate_weights is not None
+            and resolved.replicate_weights.shape[1] > 0
+        ):
+            raise NotImplementedError(
+                "Replicate weight variance for twowayfeweights() is not "
+                "supported. Use strata/PSU/FPC for design-based inference "
+                "via Taylor Series Linearization (matches the fit() path)."
+            )
 
     # Validation + cell aggregation via the same helper used by
     # ChaisemartinDHaultfoeuille.fit() — enforces NaN/binary/within-cell

docs/llms-full.txt

@@ -270,7 +270,7 @@ est.fit(
 ) -> ChaisemartinDHaultfoeuilleResults
 ```
 
-`L_max` controls multi-horizon computation. Phase 3 parameters raise `NotImplementedError`.
+`L_max` controls multi-horizon computation. Phase 3 parameters (`controls`, `trends_linear`, `trends_nonparam`, `honest_did`, `heterogeneity`, `design2`) and `survey_design` are implemented; only `aggregate` remains gated with `NotImplementedError`.
 
 **Usage:**
 

tests/test_survey_dcdh.py

@@ -726,6 +726,28 @@ def test_twfe_helper_rejects_non_pweight(self, base_data):
                 survey_design=sd,
             )
 
+    def test_twfe_helper_rejects_replicate_weights(self, base_data):
+        """Replicate-weight survey designs must be rejected by the helper,
+        matching fit()'s NotImplementedError contract."""
+        from diff_diff.chaisemartin_dhaultfoeuille import twowayfeweights
+
+        df_ = base_data.copy()
+        df_["pw"] = 1.0
+        df_["rep1"] = 1.0
+        df_["rep2"] = 1.0
+        sd = SurveyDesign(
+            weights="pw",
+            replicate_weights=["rep1", "rep2"],
+            replicate_method="BRR",
+        )
+        with pytest.raises(NotImplementedError, match="Replicate"):
+            twowayfeweights(
+                df_,
+                outcome="outcome", group="group",
+                time="period", treatment="treatment",
+                survey_design=sd,
+            )
+
 
 # ── Test: TWFE diagnostic oracle under survey ───────────────────────