#000052 §3.1: diagnose_coherence — lexical answer-shape sidecar

Per-sentence shape check (no model) emitting kind ∈
{phrase_component_reuse, circular, vacuous, ok, empty}:
  - circular: subject content-tokens ⊆ predicate's and the predicate
    leads with a subject token ("Water is water").
  - phrase_component_reuse: subject quotes a phrase, predicate reuses
    one of that phrase's own tokens as a bare "the/a/an <token>"
    referent — the 2026-05-12 field case ("the phrase 'Zionist entity'
    is used as the entity"), a token collision the verifier +
    deflection + title-relevance all pass and NLI returns neutral on.
    Copulas inside a quoted span are skipped so 'war is peace' doesn't
    break the subject/predicate split.
  - vacuous: predicate is only placeholder hypernyms + filler ("X is
    a thing").

Conservative — no full token-salad parsing; legit definitions pass ok.
Surfaced in inspect_cache_key + the `arborist inspect` human view
(· incoherent: <kind>). Advisory only — never writes providence_cache
/ audit_events / run_dag_root; demote-only verifier hook deliberately
not wired. 9 tests; full suite green (2500 passed).

tests/test_inspect.py

@@ -21,6 +21,7 @@ import pytest
 from arborist.qa.inspect import (
     _classify_span,
     _normalize,
+    diagnose_coherence,
     diagnose_deflection,
     diagnose_metaphor_deflection,
     diagnose_title_relevance,
@@ -852,3 +853,88 @@ def test_inspect_authorship_repo_owner_tier(tmp_path):
     )
     result = inspect_cache_key("03" * 32, qa_db=qa_db, shards_dir=tmp_path)
     assert result["authorship"]["tier"] == "AUTHOR_REPOSITORY_OWNER"
+
+
+# --- diagnose_coherence (#000052 §3.1) ----------------------------------
+
+
+def test_coherence_phrase_component_reuse_zionist_field_case():
+    # The 2026-05-12 field case: a phrase defined in terms of a word
+    # inside it. Lexical verifier scored it EVIDENCE-WARRANTED-PARTIAL;
+    # deflection/title-relevance both waved it through; NLI returns
+    # neutral. This sidecar is the one that catches it.
+    d = diagnose_coherence(
+        "The phrase 'Zionist entity' is sometimes used as the entity, "
+        "referring to the State of Israel."
+    )
+    assert d["kind"] == "phrase_component_reuse"
+    assert d["evidence"]["reused_tokens"] == ["entity"]
+    assert "entity" in d["evidence"]["quoted_phrase_tokens"]
+
+
+def test_coherence_circular_x_is_x():
+    d = diagnose_coherence("Water is water.")
+    assert d["kind"] == "circular"
+    assert d["evidence"]["subject_tokens"] == ["water"]
+
+
+def test_coherence_circular_subject_subset_of_predicate():
+    d = diagnose_coherence(
+        "The entity is the entity referring to the State of Israel."
+    )
+    assert d["kind"] == "circular"
+
+
+def test_coherence_vacuous_predicate_only_hypernyms():
+    d = diagnose_coherence("Happiness refers to a concept used in some contexts.")
+    assert d["kind"] == "vacuous"
+    d2 = diagnose_coherence("Gravity is a thing.")
+    assert d2["kind"] == "vacuous"
+
+
+def test_coherence_ok_on_well_formed_definitions():
+    for ans in (
+        "Paris is the capital of France.",
+        "A poodle is a type of dog.",
+        "The Beatles were a band formed in Liverpool in 1960.",
+        "The term 'open source' refers to software whose source code is "
+        "publicly available.",
+        "The phrase 'break a leg' is used as an idiom meaning good luck.",
+    ):
+        assert diagnose_coherence(ans)["kind"] == "ok", ans
+
+
+def test_coherence_copula_inside_quotes_does_not_break_split():
+    # 'war is peace' contains "is" — the split must not fire on it.
+    d = diagnose_coherence(
+        "The phrase 'war is peace' is a slogan from the novel "
+        "Nineteen Eighty-Four."
+    )
+    assert d["kind"] == "ok"
+
+
+def test_coherence_empty_and_pronoun_subject_are_not_flagged():
+    assert diagnose_coherence("")["kind"] == "empty"
+    assert diagnose_coherence("   \n  ")["kind"] == "empty"
+    # pronoun subject → no real topic token → conservatively not flagged
+    assert diagnose_coherence("It is something used in various contexts.")[
+        "kind"
+    ] == "ok"
+
+
+def test_coherence_reports_all_findings_and_worst_kind():
+    d = diagnose_coherence(
+        "- The phrase 'Zionist entity' is used as the entity.\n"
+        "- Happiness is a concept."
+    )
+    assert d["kind"] == "phrase_component_reuse"  # most severe wins
+    kinds = {f["kind"] for f in d["findings"]}
+    assert kinds == {"phrase_component_reuse", "vacuous"}
+    assert d["n_sentences"] == 2
+
+
+def test_coherence_is_pure_no_side_effects():
+    # No DB, no files — diagnose_coherence is a pure function over text.
+    before = diagnose_coherence("Water is water.")
+    after = diagnose_coherence("Water is water.")
+    assert before == after