auditor/checks/inference.ts

@@ -112,9 +112,19 @@ export async function runInferenceCheck(claims: Claim[], diff: string): Promise<
           { role: "system", content: systemMsg },
           { role: "user", content: userMsg },
         ],
-        max_tokens: 3000,
+        // Deterministic classification mode — temp=0 is greedy-sample,
-        temperature: 0.2,
+        // so identical input → identical output on the same model
-        think: true, // T3 overseer should reason — JSON shape is still required
+        // version. think=false disables the reasoning trace that was
+        // letting variable prose leak into the classification output
+        // and inflate the audit_lessons signature set (observed as
+        // sig_count creep across the 9-run empirical test).
+        //
+        // max_tokens tightened to 1500 — the structured JSON response
+        // fits comfortably in 1500 tokens for typical PRs (~7 claims);
+        // the old 3000 just gave the model room to wander.
+        max_tokens: 1500,
+        temperature: 0,
+        think: false,
       }),
       signal: AbortSignal.timeout(CALL_TIMEOUT_MS),
     });

tests/real-world/nine_consecutive_audits.ts

@@ -28,7 +28,7 @@ const AUDIT_LESSONS = `${REPO}/data/_kb/audit_lessons.jsonl`;
 const VERDICTS_DIR = `${REPO}/data/_auditor/verdicts`;
 const POLL_INTERVAL_MS = 5_000;
 const AUDIT_TIMEOUT_MS = 180_000;
-const RUNS = 9;
+const RUNS = Number(process.env.LH_AUDIT_RUNS ?? 9);
 const TARGET_PR = Number(process.env.LH_AUDIT_PR ?? 8);
 
 async function sh(cmd: string): Promise<{ stdout: string; stderr: string; code: number }> {