test_providence_query: assert merkle_proof carries context_root + sources

tests/test_providence_query.py

@@ -7,6 +7,7 @@ Covers Phase 2 step 1 + step 2 of #000072:
 """
 from __future__ import annotations
 
+import json
 import sqlite3
 from pathlib import Path
 from typing import Iterator
@@ -76,6 +77,39 @@ def test_first_call_persists_with_audit_event(setup):
     qaro.close()
 
 
+def test_persisted_merkle_proof_has_context_root_and_sources(setup):
+    """merkle_proof column must hold the legacy-shape proof_obj:
+    {context_root, sources: [{document_root, ...}], retrieval_purity}.
+    arborist-viz Merkle Command Center reads this to synthesize the
+    leaf set under a multi-source context root — an empty list shows
+    0 leaves in the 3D lattice."""
+    corpus, qa = setup
+    stub = 'The core principle of anarchism is the "abolition of authority". [E1]'
+    r = providence_query(
+        corpus, "what is the core principle of anarchism?",
+        StubClient(answer=stub),
+        qa_db=qa, model_id="stub", top_k=2,
+    )
+    qaro = sqlite3.connect(f"file:{qa}?mode=ro", uri=True)
+    proof_str = qaro.execute(
+        "SELECT merkle_proof FROM providence_cache WHERE cache_key = ?",
+        (r["cache_key"],),
+    ).fetchone()[0]
+    qaro.close()
+    proof = json.loads(proof_str)
+    assert isinstance(proof, dict), "merkle_proof must be a dict (was list/empty)"
+    assert proof["context_root"] == r["context_root"]
+    assert len(proof["sources"]) >= 1
+    s0 = proof["sources"][0]
+    assert s0["document_root"]
+    assert "title" in s0 and "document_uri" in s0
+    assert "source_role" in s0
+    assert "used" in s0 and "used_pointer_ids" in s0
+    assert "retrieval_purity" in proof
+    rp = proof["retrieval_purity"]
+    assert rp["total_sources"] == len(proof["sources"])
+
+
 def test_second_call_returns_cache_hit(setup):
     """Second call with the SAME question + model + corpus must hit
     the cache and ignore the (different) stub answer."""