{"messages":[{"content":"You are a constitutional council ranking individual git commits for ownership allocation.\n\nCompare these two commits. Decide which contributed more lasting value to the project.\n\nJudge substance, not spectacle:\n- Prefer correct, lasting design and real bugfixes over churn, formatting, renames, or generated noise.\n- Prefer clarity and necessity over sheer line count. A small precise change can beat a large diffuse one.\n- Do not favor a side merely because its patch is longer or noisier.\n- Weight what the change does for the project, not the contributor's name.\n\nReturn ONLY a JSON object: {\"winner\": \"A\" or \"B\", \"ratio\": \"N:M\", \"explanation\": \"...\"}\nThe explanation must cite concrete differences in the patches (1-3 sentences).\n\nSide A — contributor: tommy-mor\nSide A — commit message:\n[0d3270d1] Fix GitHub OAuth callback NameError on missing API base URL.\n\nCo-authored-by: Cursor <cursoragent@cursor.com>\n\nSide A — unified diff (full patch):\ndiff --git a/constitution.py b/constitution.py\nindex f819007252f435680b8356fb4da83469b21e33af..4dd5b9dfbba231d46289c490f91b1dd5b1018bcf 100644\n--- a/constitution.py\n+++ b/constitution.py\n@@ -119,6 +119,9 @@ JSONL_PATH = pathlib.Path(os.environ.get(\"JSONL_PATH\", \"/data/ledger.jsonl\"))\n \n GITHUB_CLIENT_ID = os.environ.get(\"GITHUB_CLIENT_ID\", \"\")\n GITHUB_CLIENT_SECRET = os.environ.get(\"GITHUB_CLIENT_SECRET\", \"\")\n+GITHUB_API_BASE_URL = os.environ.get(\n+    \"GITHUB_API_BASE_URL\", \"https://api.github.com\"\n+).rstrip(\"/\")\n \n OPENROUTER_API_KEY = os.environ.get(\"OPENROUTER_API_KEY\", \"\")\n OPENROUTER_BASE_URL = os.environ.get(\"OPENROUTER_BASE_URL\", \"https://openrouter.ai\").rstrip(\"/\")\n\n\nSide B — contributor: tommy-mor\nSide B — commit message:\n[14749a34] Show graph topology with pair suggestions\n\nExpose existing connectivity statistics in CLI output so voters can see sparse or disconnected scopes before adding an edge.\n\nCo-authored-by: Cursor <cursoragent@cursor.com>\n\nSide B — unified diff (full patch):\ndiff --git a/cli/src/main.rs b/cli/src/main.rs\nindex 70435b412188a151c5e89e842a5de57f7480ddf2..abb5a55b49f60fe28fbfd4ec02715cb94ea0b4ec 100644\n--- a/cli/src/main.rs\n+++ b/cli/src/main.rs\n@@ -397,6 +397,29 @@ fn print_item_response(resp: &ItemResponse) {\n     }\n }\n \n+fn format_connectivity_stats(stats: &ConnectivityStats) -> String {\n+    let density = if stats.pairs_possible == 0 {\n+        0.0\n+    } else {\n+        stats.pairs_voted as f64 / stats.pairs_possible as f64 * 100.0\n+    };\n+    let component_label = if stats.components == 1 { \"component\" } else { \"components\" };\n+    let connection_status = if stats.comparisons_until_connected == 0 {\n+        \"connected\".to_string()\n+    } else {\n+        let comparison_label = if stats.comparisons_until_connected == 1 {\n+            \"comparison\"\n+        } else {\n+            \"comparisons\"\n+        };\n+        format!(\"{} {comparison_label} to connect\", stats.comparisons_until_connected)\n+    };\n+    format!(\n+        \"graph: {} items, {}/{} pairs ({density:.1}% density), {} {component_label}, {connection_status}\",\n+        stats.items, stats.pairs_voted, stats.pairs_possible, stats.components,\n+    )\n+}\n+\n fn print_pair_response(resp: &PairResponse) {\n     println!(\"{}  vs  {}\", resp.left, resp.right);\n     if let Some(b) = &resp.left_body {\n@@ -413,6 +436,10 @@ fn print_pair_response(resp: &PairResponse) {\n         println!();\n         println!(\"threads: {}\", resp.threads.iter().map(|t| format!(\"#{t}\")).collect::<Vec<_>>().join(\" \"));\n     }\n+    if let Some(stats) = &resp.connectivity {\n+        println!();\n+        println!(\"{}\", format_connectivity_stats(stats));\n+    }\n     println!();\n     println!(\"---\");\n     println!(\"Before writing your comparison, talk to your human. Ask them about their relationship to these two items — which one has meant more to them, whether their perspective has changed over time, and where they land now. Listen to what they say. Then write a comparison that synthesizes their perspective with your own analysis. The best submissions on slug.social carry both voices — your reasoning and their experience.\");\n@@ -816,6 +843,43 @@ fn write_secret_file(name: &str, contents: &str) -> Result<()> {\n     Ok(())\n }\n \n+#[cfg(test)]\n+mod tests {\n+    use super::*;\n+\n+    #[test]\n+    fn connectivity_stats_show_sparse_disconnected_graph() {\n+        let stats = ConnectivityStats {\n+            items: 9,\n+            components: 3,\n+            comparisons_until_connected: 2,\n+            pairs_voted: 8,\n+            pairs_possible: 36,\n+        };\n+\n+        assert_eq!(\n+            format_connectivity_stats(&stats),\n+            \"graph: 9 items, 8/36 pairs (22.2% density), 3 components, 2 comparisons to connect\"\n+        );\n+    }\n+\n+    #[test]\n+    fn connectivity_stats_show_connected_graph() {\n+        let stats = ConnectivityStats {\n+            items: 4,\n+            components: 1,\n+            comparisons_until_connected: 0,\n+            pairs_voted: 3,\n+            pairs_possible: 6,\n+        };\n+\n+        assert_eq!(\n+            format_connectivity_stats(&stats),\n+            \"graph: 4 items, 3/6 pairs (50.0% density), 1 component, connected\"\n+        );\n+    }\n+}\n+\n async fn run_scoped(base: &str, room: &str, sub: ScopedCmd) -> Result<()> {\n     let room = room.trim();\n     let client = http_client()?;\n","role":"user"}],"model":"openai/gpt-chat-latest"}