v2: confidence scores on INFERRED edges, avg shown in report

graphify/export.py

@@ -195,11 +195,18 @@ LEGEND.forEach(c => {{
 </script>"""
 
 
+_CONFIDENCE_SCORE_DEFAULTS = {"EXTRACTED": 1.0, "INFERRED": 0.5, "AMBIGUOUS": 0.2}
+
+
 def to_json(G: nx.Graph, communities: dict[int, list[str]], output_path: str) -> None:
     node_community = _node_community_map(communities)
     data = json_graph.node_link_data(G, edges="links")
     for node in data["nodes"]:
         node["community"] = node_community.get(node["id"])
+    for link in data["links"]:
+        if "confidence_score" not in link:
+            conf = link.get("confidence", "EXTRACTED")
+            link["confidence_score"] = _CONFIDENCE_SCORE_DEFAULTS.get(conf, 1.0)
     with open(output_path, "w") as f:
         json.dump(data, f, indent=2)
 

graphify/report.py

@@ -24,6 +24,10 @@ def generate(
     inf_pct = round(confidences.count("INFERRED") / total * 100)
     amb_pct = round(confidences.count("AMBIGUOUS") / total * 100)
 
+    inf_edges = [(u, v, d) for u, v, d in G.edges(data=True) if d.get("confidence") == "INFERRED"]
+    inf_scores = [d.get("confidence_score", 0.5) for _, _, d in inf_edges]
+    inf_avg = round(sum(inf_scores) / len(inf_scores), 2) if inf_scores else None
+
     lines = [
         f"# Graph Report - {root}  ({today})",
         "",
@@ -41,7 +45,8 @@ def generate(
         "",
         "## Summary",
         f"- {G.number_of_nodes()} nodes · {G.number_of_edges()} edges · {len(communities)} communities detected",
-        f"- Extraction: {ext_pct}% EXTRACTED · {inf_pct}% INFERRED · {amb_pct}% AMBIGUOUS",
+        f"- Extraction: {ext_pct}% EXTRACTED · {inf_pct}% INFERRED · {amb_pct}% AMBIGUOUS"
+        + (f" · INFERRED: {len(inf_edges)} edges (avg confidence: {inf_avg})" if inf_avg is not None else ""),
         f"- Token cost: {token_cost.get('input', 0):,} input · {token_cost.get('output', 0):,} output",
         "",
         "## God Nodes (most connected - your core abstractions)",
@@ -55,8 +60,14 @@ def generate(
             relation = s.get("relation", "related_to")
             note = s.get("note", "")
             files = s.get("source_files", ["", ""])
+            conf = s.get("confidence", "EXTRACTED")
+            cscore = s.get("confidence_score")
+            if conf == "INFERRED" and cscore is not None:
+                conf_tag = f"INFERRED {cscore:.2f}"
+            else:
+                conf_tag = conf
             lines += [
-                f"- `{s['source']}` --{relation}--> `{s['target']}`  [{s['confidence']}]",
+                f"- `{s['source']}` --{relation}--> `{s['target']}`  [{conf_tag}]",
                 f"  {files[0]} → {files[1]}" + (f"  _{note}_" if note else ""),
             ]
     else:

graphify/skill.md

@@ -210,8 +210,15 @@ DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indire
 If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author,
   contributor onto every node from that file.
 
+confidence_score rules:
+- EXTRACTED edges: confidence_score must be 1.0
+- INFERRED edges: score 0.4-0.9 based on how certain you are.
+  Strong structural inference (e.g. two classes clearly share data): 0.8-0.9.
+  Reasonable but not certain: 0.6-0.7. Weak inference: 0.4-0.5.
+- AMBIGUOUS edges: score 0.1-0.3
+
 Output exactly this JSON (no other text):
-{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","source_file":"relative/path","source_location":null,"weight":1.0}],"input_tokens":0,"output_tokens":0}
+{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"input_tokens":0,"output_tokens":0}
 ```
 
 **Step B3 - Collect, cache, and merge**