feat(F-15): citation graph — PageRank, coupling, co-citation, CLI

- codex/graph.py: build_citation_graph (DiGraph from DB), citation_pagerank
  (graceful uniform fallback < 5 nodes), find_related (bibliographic coupling),
  find_co_cited, dangling_citations
- codex/config.py: graph_cite_boost_alpha=0.3, graph_min_corpus_size=15
- codex/cli.py: graph report [--top-n] [--json], graph related <paper-id>
  [--min-shared]; search paper --cite-boost (PageRank score weighting)
- tests/graph/: 39 tests (graph functions + CLI) — 326 total green

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/graph/test_cli.py

@@ -0,0 +1,176 @@
+"""CLI tests for `codex graph` sub-commands (F-15)."""
+
+from __future__ import annotations
+
+from contextlib import contextmanager
+from unittest.mock import MagicMock, patch
+
+import networkx as nx
+import numpy as np
+from typer.testing import CliRunner
+
+from codex.cli import app
+
+runner = CliRunner()
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _make_conn_cm(conn: MagicMock):
+    @contextmanager
+    def _cm():
+        yield conn
+
+    return _cm
+
+
+def _make_conn_with_paper_ids(*paper_ids: str) -> MagicMock:
+    """Mock conn that returns paper rows for SELECT id FROM papers."""
+    conn = MagicMock()
+    conn.execute.return_value.fetchall.return_value = [{"id": pid} for pid in paper_ids]
+    return conn
+
+
+def _sample_graph() -> nx.DiGraph:
+    """A→B, A→C, B→C, B→D, C→D — 5 nodes, D is dangling (not in papers)."""
+    g = nx.DiGraph()
+    g.add_edges_from([("A", "B"), ("A", "C"), ("B", "C"), ("B", "D"), ("C", "D")])
+    return g
+
+
+# ---------------------------------------------------------------------------
+# codex graph report
+# ---------------------------------------------------------------------------
+
+
+class TestGraphReport:
+    def _run(self, graph=None, known_ids=("A", "B", "C"), *extra_args):
+        if graph is None:
+            graph = _sample_graph()
+        conn = _make_conn_with_paper_ids(*known_ids)
+
+        with (
+            patch("codex.db.get_conn", side_effect=_make_conn_cm(conn)),
+            patch("codex.graph.build_citation_graph", return_value=graph),
+        ):
+            return runner.invoke(app, ["graph", "report"])
+
+    def test_exit_zero(self):
+        assert self._run().exit_code == 0
+
+    def test_shows_hub_section(self):
+        assert "HUB" in self._run().output.upper()
+
+    def test_shows_dangling_section(self):
+        assert "DANGLING" in self._run().output.upper()
+
+    def test_dangling_node_in_output(self):
+        # D is cited but not in known_ids
+        assert "D" in self._run().output
+
+    def test_json_output_valid(self):
+        import json
+
+        graph = _sample_graph()
+        conn = _make_conn_with_paper_ids("A", "B", "C")
+        with (
+            patch("codex.db.get_conn", side_effect=_make_conn_cm(conn)),
+            patch("codex.graph.build_citation_graph", return_value=graph),
+        ):
+            result = runner.invoke(app, ["graph", "report", "--json"])
+        assert result.exit_code == 0
+        data = json.loads(result.output)
+        assert "hubs" in data
+        assert "dangling" in data
+        assert "nodes" in data
+        assert data["dangling_count"] == 1
+
+    def test_empty_graph_message(self):
+        conn = _make_conn_with_paper_ids()
+        with (
+            patch("codex.db.get_conn", side_effect=_make_conn_cm(conn)),
+            patch("codex.graph.build_citation_graph", return_value=nx.DiGraph()),
+        ):
+            result = runner.invoke(app, ["graph", "report"])
+        assert result.exit_code == 0
+        assert "empty" in result.output.lower()
+
+    def test_top_n_respected(self):
+        # Build graph with 8 nodes, ask for top 3
+        g = nx.DiGraph()
+        for i in range(8):
+            g.add_edge(f"P{i}", "HUB")
+        conn = _make_conn_with_paper_ids(*[f"P{i}" for i in range(8)], "HUB")
+        with (
+            patch("codex.db.get_conn", side_effect=_make_conn_cm(conn)),
+            patch("codex.graph.build_citation_graph", return_value=g),
+        ):
+            result = runner.invoke(app, ["graph", "report", "--top-n", "3"])
+        assert result.exit_code == 0
+
+
+# ---------------------------------------------------------------------------
+# codex graph related
+# ---------------------------------------------------------------------------
+
+
+class TestGraphRelated:
+    def _run(self, paper_id: str, graph=None, *extra_args):
+        if graph is None:
+            graph = _sample_graph()
+        conn = MagicMock()
+        with (
+            patch("codex.db.get_conn", side_effect=_make_conn_cm(conn)),
+            patch("codex.graph.build_citation_graph", return_value=graph),
+        ):
+            return runner.invoke(app, ["graph", "related", paper_id, *extra_args])
+
+    def test_exit_zero_known_paper(self):
+        assert self._run("A").exit_code == 0
+
+    def test_unknown_paper_graceful(self):
+        result = self._run("UNKNOWN_ID")
+        assert result.exit_code == 0
+        assert "No papers" in result.output
+
+    def test_no_results_message_when_min_shared_high(self):
+        result = self._run("A", _sample_graph(), "--min-shared", "99")
+        assert "No papers" in result.output
+
+    def test_related_papers_shown(self):
+        # A cites {B,C}; B also cites C → shared=1 with A
+        result = self._run("A", _sample_graph(), "--min-shared", "1")
+        assert result.exit_code == 0
+        # B shares C with A; should appear
+        assert "B" in result.output
+
+
+# ---------------------------------------------------------------------------
+# codex search paper --cite-boost
+# ---------------------------------------------------------------------------
+
+
+class TestSearchCiteBoost:
+    def test_cite_boost_exits_zero(self):
+        conn = MagicMock()
+        paper_rows = [
+            {"id": "A", "title": "Paper A", "year": 2020, "distance": 0.2},
+        ]
+        graph = _sample_graph()
+
+        conn.execute.return_value.fetchall.return_value = paper_rows
+
+        def _fake_encode(texts):
+            return np.zeros((len(texts), 1024), dtype="float32")
+
+        with (
+            patch("codex.db.get_conn", side_effect=_make_conn_cm(conn)),
+            patch("codex.embed.get_embedder") as mock_emb,
+            patch("codex.graph.build_citation_graph", return_value=graph),
+        ):
+            mock_emb.return_value.encode_dense.side_effect = _fake_encode
+            result = runner.invoke(app, ["search", "paper", "hodge star", "--cite-boost"])
+        assert result.exit_code == 0