auditor/checks/inference.ts

@@ -28,11 +28,16 @@ const GATEWAY = process.env.LH_GATEWAY_URL ?? "http://localhost:3100";
 // retries — verified with trivial 8-token probes). Swapped default to
 // deepseek-v3.1:671b which is proven working end-to-end through the
 // pr_audit mode runner during Phase 5 distillation acceptance testing.
-// kimi-k2:1t can be re-selected via LH_AUDITOR_REVIEW_MODEL env when
+//
-// the upstream returns. Tie-breaker stays grok-4.1-fast (different
+// 2026-09-02 update: Ollama Cloud subscription lapsed — every
-// vendor lineage so consensus + tie-break won't fail-correlate).
+// ollama_cloud model 402s ("requires a subscription"). J's call: sweep
-const MODEL = process.env.LH_AUDITOR_REVIEW_MODEL ?? "deepseek-v3.1:671b";
+// the auditor to OpenRouter. Same deepseek lineage via OpenRouter;
-const TIEBREAKER_MODEL = process.env.LH_AUDITOR_TIEBREAKER_MODEL ?? "x-ai/grok-4.1-fast";
+// tie-breaker moves to grok-4.3 because OpenRouter 404s grok-4.1-fast
+// as deprecated. Both probed live through the gateway before landing.
+// Vendor lineages stay distinct so consensus + tie-break won't
+// fail-correlate.
+const MODEL = process.env.LH_AUDITOR_REVIEW_MODEL ?? "openrouter/deepseek/deepseek-chat-v3.1";
+const TIEBREAKER_MODEL = process.env.LH_AUDITOR_TIEBREAKER_MODEL ?? "openrouter/x-ai/grok-4.3";
 const N_CONSENSUS = Number(process.env.LH_AUDITOR_CONSENSUS_N ?? 3);
 const AUDIT_DISCREPANCIES_JSONL = "/home/profit/lakehouse/data/_kb/audit_discrepancies.jsonl";
 // 40KB comfortably fits the consensus models' context windows

auditor/checks/kimi_architect.ts

@@ -51,13 +51,15 @@ const CALL_TIMEOUT_MS = 900_000;
 const CACHE_TTL_MS = 24 * 60 * 60 * 1000;
 const MAX_DIFF_CHARS = 180_000;
 const MAX_PRIOR_FINDINGS = 50;
-// Default provider/model = ollama_cloud/kimi-k2.6. Pre-2026-04-27 we
+// Default provider/model = openrouter/moonshotai/kimi-k2.6.
-// went direct to api.kimi.com, but Ollama Cloud Pro now exposes the
+// History: pre-2026-04-27 direct api.kimi.com (User-Agent gating),
-// same model legitimately, so we route there to avoid User-Agent
+// then ollama_cloud/kimi-k2.6 while the sub was active. 2026-09-02:
-// gating. The api.kimi.com path (provider=kimi) remains wired in the
+// Ollama Cloud subscription lapsed (402 on every cloud model), J's
-// gateway as a fallback for when Ollama Cloud is upstream-broken.
+// call was to sweep the auditor to OpenRouter — same Moonshot model,
-const KIMI_PROVIDER = process.env.LH_AUDITOR_KIMI_PROVIDER ?? "ollama_cloud";
+// probed live through the gateway. The api.kimi.com path
-const KIMI_MODEL = process.env.LH_AUDITOR_KIMI_MODEL ?? "kimi-k2.6";
+// (provider=kimi) remains wired in the gateway as a fallback.
+const KIMI_PROVIDER = process.env.LH_AUDITOR_KIMI_PROVIDER ?? "openrouter";
+const KIMI_MODEL = process.env.LH_AUDITOR_KIMI_MODEL ?? "moonshotai/kimi-k2.6";
 // Cross-lineage alternation. 2026-04-27 J's call: Opus is too
 // expensive to auto-fire (~$0.30/audit). Kimi K2.6 via Go-sub is
 // effectively free; Haiku 4.5 via Zen is ~$0.04. Alternate between
@@ -111,7 +113,7 @@ function maxTokensFor(model: string): number {
   if (MAX_TOKENS_OVERRIDE > 0) return MAX_TOKENS_OVERRIDE;
   if (model.startsWith("claude-opus")) return 32_000;
   if (model.startsWith("claude-haiku") || model.startsWith("claude-sonnet")) return 8_192;
-  if (model.startsWith("kimi-")) return 128_000;
+  if (model.startsWith("kimi-") || model.includes("/kimi-")) return 128_000;
   if (model.startsWith("gpt-5") || model.startsWith("o1") || model.startsWith("o3") || model.startsWith("o4")) return 32_000;
   return 16_000;
 }