Address PR #356 CI review round 15 (1 P1 guide)

§4.10 repeated-cross-section wording tightened. The earlier text
("most estimators remain applicable") overstated the RCS support
surface: only CallawaySantAnna(panel=False), TripleDifference, and
StaggeredTripleDifference have documented RCS-capable contracts
(REGISTRY.md §CallawaySantAnna; docs/choosing_estimator.rst DDD
cross-sectional use cases). EfficientDiD and HeterogeneousAdoptionDiD
explicitly reject RCS per REGISTRY.md. SyntheticDiD and ContinuousDiD
are panel-only by construction. Under the old wording an autonomous
agent could silently route RCS data to a panel-only estimator.

Rewrote §4.10 into three explicit blocks:
- "Explicit RCS support": the three RCS-capable estimators.
- "Explicitly rejected for RCS (panel-only)": names EfficientDiD,
  HeterogeneousAdoptionDiD, SyntheticDiD, ContinuousDiD.
- "Treat other estimators in this guide as panel-only unless their
  own docs explicitly say otherwise."

Kept the clustered-SE note and added a cluster-vs-respondent
treatment-assignment check.

Regression test: asserts the guide does not contain the "most
estimators remain applicable" phrase, names `panel=False` as the
explicit CS RCS mode, and that the §4.10 section explicitly lists
both EfficientDiD and HeterogeneousAdoptionDiD as panel-only
rejected.

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

Author: igerber

diff_diff/guides/llms-autonomous.txt

@@ -500,13 +500,39 @@ intensity of exposure differs):
 ### §4.10 Repeated cross-sections (no panel structure)
 
 `profile_panel` assumes long-format panel data. When the same units are
-not observed across time (true repeated cross-sections), most estimators
-remain applicable but:
-
-- Clustered SE must cluster on the unit proxy (state, region) rather
-  than individual.
-- The `CallawaySantAnna` estimator has an explicit repeated-cross-
-  section mode; see its `panel` kwarg.
+not observed across time (true repeated cross-sections), only the
+estimators whose documented contract explicitly admits RCS are
+applicable. Do not route RCS data to any other estimator in the suite -
+most of them are panel-only by construction and will either raise at
+fit time or estimate under a misspecified identifying assumption.
+
+Explicit RCS support in this library:
+
+- `CallawaySantAnna(panel=False)` - repeated-cross-section mode per
+  REGISTRY.md §CallawaySantAnna; use this variant on RCS data.
+- `TripleDifference` / `StaggeredTripleDifference` - DDD cross-sectional
+  use cases are documented in `docs/choosing_estimator.rst`; the DDD
+  estimators do not require within-unit tracking when the third
+  comparison axis carries the identification.
+
+Explicitly rejected for RCS (panel-only):
+
+- `EfficientDiD` - REGISTRY notes "does not handle ... repeated
+  cross-sections."
+- `HeterogeneousAdoptionDiD` - panel-only (requires a balanced panel
+  with per-unit adoption timing).
+- `SyntheticDiD` - requires balanced panel with per-unit donor matching.
+- `ContinuousDiD` - requires balanced panel with per-unit constant
+  dose.
+
+Treat other estimators in this guide as panel-only unless their own
+docs explicitly say otherwise. When routing, also:
+
+- Cluster SE on the unit proxy (state, region) rather than the
+  individual cross-section respondent.
+- Confirm the treatment assignment is at the cluster level, not at
+  the individual-respondent level, before interpreting the estimate
+  as a group-time ATT.
 
 
 ## §5. Post-fit validation utilities

tests/test_profile_panel.py

@@ -745,6 +745,30 @@ def test_guide_api_strings_resolve_against_public_api():
             f"{phrase!r}: SUTVA is assumed across the estimator suite."
         )
 
+    # Repeated-cross-section (§4.10) must not claim broad
+    # applicability. The documented RCS-capable estimators are
+    # CallawaySantAnna(panel=False), TripleDifference, and
+    # StaggeredTripleDifference; EfficientDiD and
+    # HeterogeneousAdoptionDiD explicitly reject RCS per REGISTRY.md.
+    assert "most estimators remain applicable" not in text, (
+        "§4.10 must not claim broad RCS applicability; only the "
+        "explicitly documented RCS-capable subset is applicable."
+    )
+    assert "panel=False" in text, (
+        "§4.10 must point at CallawaySantAnna(panel=False) as the " "explicit RCS mode"
+    )
+    # The section must explicitly name at least one panel-only
+    # estimator as rejected for RCS, so agents do not silently route
+    # RCS data to it.
+    rcs_section_start = text.find("§4.10 Repeated cross-sections")
+    assert rcs_section_start >= 0
+    rcs_section = text[rcs_section_start : rcs_section_start + 2500]
+    for panel_only in ("EfficientDiD", "HeterogeneousAdoptionDiD"):
+        assert panel_only in rcs_section, (
+            f"§4.10 must explicitly name {panel_only!r} as panel-only "
+            "so RCS data is not routed to it"
+        )
+
 
 def test_min_pre_post_use_per_unit_observed_support():
     """On an unbalanced panel where one treated unit is missing its