From 0661c2cb83300c68637aaef17cf8218280a50fb0 Mon Sep 17 00:00:00 2001 From: root Date: Wed, 2 Sep 2026 04:05:13 -0500 Subject: [PATCH] auditor: sweep model lanes off lapsed Ollama Cloud onto OpenRouter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Ollama Cloud sub lapsed 2026-09-02 — every ollama_cloud model 402s. Consensus lane -> openrouter/deepseek/deepseek-chat-v3.1 (same lineage), tie-breaker -> openrouter/x-ai/grok-4.3 (4.1-fast deprecated upstream), kimi_architect -> openrouter/moonshotai/kimi-k2.6 via provider default so the Kimi<->Haiku alternation stays intact. maxTokensFor learns the vendor-prefixed kimi id. All three lanes + pr_audit mode runner probed live through the gateway before landing. Co-Authored-By: Claude Fable 5 --- auditor/checks/inference.ts | 15 ++++++++++----- auditor/checks/kimi_architect.ts | 18 ++++++++++-------- 2 files changed, 20 insertions(+), 13 deletions(-) diff --git a/auditor/checks/inference.ts b/auditor/checks/inference.ts index 8103e9d..616a661 100644 --- a/auditor/checks/inference.ts +++ b/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 -// vendor lineage so consensus + tie-break won't fail-correlate). -const MODEL = process.env.LH_AUDITOR_REVIEW_MODEL ?? "deepseek-v3.1:671b"; -const TIEBREAKER_MODEL = process.env.LH_AUDITOR_TIEBREAKER_MODEL ?? "x-ai/grok-4.1-fast"; +// +// 2026-09-02 update: Ollama Cloud subscription lapsed — every +// ollama_cloud model 402s ("requires a subscription"). J's call: sweep +// the auditor to OpenRouter. Same deepseek lineage via OpenRouter; +// 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 diff --git a/auditor/checks/kimi_architect.ts b/auditor/checks/kimi_architect.ts index 7905066..a202298 100644 --- a/auditor/checks/kimi_architect.ts +++ b/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 -// went direct to api.kimi.com, but Ollama Cloud Pro now exposes the -// same model legitimately, so we route there to avoid User-Agent -// gating. The api.kimi.com path (provider=kimi) remains wired in the -// gateway as a fallback for when Ollama Cloud is upstream-broken. -const KIMI_PROVIDER = process.env.LH_AUDITOR_KIMI_PROVIDER ?? "ollama_cloud"; -const KIMI_MODEL = process.env.LH_AUDITOR_KIMI_MODEL ?? "kimi-k2.6"; +// Default provider/model = openrouter/moonshotai/kimi-k2.6. +// History: pre-2026-04-27 direct api.kimi.com (User-Agent gating), +// then ollama_cloud/kimi-k2.6 while the sub was active. 2026-09-02: +// Ollama Cloud subscription lapsed (402 on every cloud model), J's +// call was to sweep the auditor to OpenRouter — same Moonshot model, +// probed live through the gateway. The api.kimi.com path +// (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; }