From 893acb19df532376b4eda06eb73885ce7f3b4e18 Mon Sep 17 00:00:00 2001
From: Safi <safishamsi98@gmail.com>
Date: Sat, 2 May 2026 18:09:32 +0100
Subject: [PATCH] Fix #664: filter thin communities from GRAPH_REPORT.md by
 default

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 graphify/__main__.py |  5 ++++-
 graphify/report.py   | 15 +++++++++------
 tests/test_report.py |  2 +-
 3 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/graphify/__main__.py b/graphify/__main__.py
index 6dae11e8..638df197 100644
--- a/graphify/__main__.py
+++ b/graphify/__main__.py
@@ -1463,6 +1463,8 @@ def main() -> None:
     elif cmd == "cluster-only":
         watch_path = Path(sys.argv[2]) if len(sys.argv) > 2 else Path(".")
         no_viz = "--no-viz" in sys.argv
+        _min_cs_arg = next((a for a in sys.argv if a.startswith("--min-community-size=")), None)
+        min_community_size = int(_min_cs_arg.split("=")[1]) if _min_cs_arg else 3
         graph_json = watch_path / "graphify-out" / "graph.json"
         if not graph_json.exists():
             print(f"error: no graph found at {graph_json} — run /graphify first", file=sys.stderr)
@@ -1488,7 +1490,8 @@ def main() -> None:
         tokens = {"input": 0, "output": 0}
         report = generate(G, communities, cohesion, labels, gods, surprises,
                           {"warning": "cluster-only mode — file stats not available"},
-                          tokens, str(watch_path), suggested_questions=questions)
+                          tokens, str(watch_path), suggested_questions=questions,
+                          min_community_size=min_community_size)
         out = watch_path / "graphify-out"
         (out / "GRAPH_REPORT.md").write_text(report, encoding="utf-8")
         to_json(G, communities, str(out / "graph.json"))
diff --git a/graphify/report.py b/graphify/report.py
index 103765dc..7183b18f 100644
--- a/graphify/report.py
+++ b/graphify/report.py
@@ -23,6 +23,7 @@ def generate(
     token_cost: dict,
     root: str,
     suggested_questions: list[dict] | None = None,
+    min_community_size: int = 3,
 ) -> str:
     today = date.today().isoformat()
 
@@ -108,7 +109,11 @@ def generate(
             conf_tag = f"{conf} {cscore:.2f}" if cscore is not None else conf
             lines.append(f"- **{h.get('label', h.get('id', ''))}** — {node_labels} [{conf_tag}]")
 
-    lines += ["", "## Communities"]
+    thin_count = sum(
+        1 for nodes in communities.values()
+        if 0 < sum(1 for n in nodes if not _ifn(G, n)) < min_community_size
+    )
+    lines += ["", f"## Communities ({len(communities)} total, {thin_count} thin omitted)"]
     for cid, nodes in communities.items():
         label = community_labels.get(cid, f"Community {cid}")
         score = cohesion_scores.get(cid, 0.0)
@@ -116,6 +121,8 @@ def generate(
         real_nodes = [n for n in nodes if not _ifn(G, n)]
         if not real_nodes:
             continue
+        if len(real_nodes) < min_community_size:
+            continue
         display = [G.nodes[n].get("label", n) for n in real_nodes[:8]]
         suffix = f" (+{len(real_nodes)-8} more)" if len(real_nodes) > 8 else ""
         lines += [
@@ -157,11 +164,7 @@ def generate(
             lines.append(f"- **{len(isolated)} isolated node(s):** {', '.join(f'`{l}`' for l in isolated_labels)}{suffix}")
             lines.append("  These have ≤1 connection - possible missing edges or undocumented components.")
         if thin_communities:
-            for cid, nodes in thin_communities.items():
-                label = community_labels.get(cid, f"Community {cid}")
-                node_labels = [G.nodes[n].get("label", n) for n in nodes]
-                lines.append(f"- **Thin community `{label}`** ({len(nodes)} nodes): {', '.join(f'`{l}`' for l in node_labels)}")
-                lines.append("  Too small to be a meaningful cluster - may be noise or needs more connections extracted.")
+            lines.append(f"- **{len(thin_communities)} thin communities (<{min_community_size} nodes) omitted from report** — run `graphify query` to explore isolated nodes.")
         if amb_pct > 20:
             lines.append(f"- **High ambiguity: {amb_pct}% of edges are AMBIGUOUS.** Review the Ambiguous Edges section above.")
 
diff --git a/tests/test_report.py b/tests/test_report.py
index 7afbea87..a5b3916a 100644
--- a/tests/test_report.py
+++ b/tests/test_report.py
@@ -57,7 +57,7 @@ def test_report_shows_token_cost():
 
 def test_report_shows_raw_cohesion_scores():
     G, communities, cohesion, labels, gods, surprises, detection, tokens = make_inputs()
-    report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, "./project")
+    report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, "./project", min_community_size=1)
     assert "Cohesion:" in report
     assert "✓" not in report
     assert "⚠" not in report