发问准备可以并行，三个开关先保持关闭（BUG-1337～1339）

开流前的注销检查可以和读会话、解析模型同时进行；审核改到扣点前等待，不再挡住第一行；模型版本可以短缓存；两个领域可以一起算。本机没有数据库中位数，也没有带星盘网络库的镜像，所以默认仍是关闭、缓存 0、领域逐个算。自测：tsc 0 错；lint 0 error；相关测试失败 0、取消 0。test:db 未跑。 Co-Authored-By: Grok (agent loop)
2026-10-14 07:23:58 +08:00
parent 66cd60081f
commit a0e223e20c
22 changed files with 1276 additions and 162 deletions
@@ -0,0 +1,24 @@
+"""Two-domain concurrency bench.
+
+The vedastro image and the local API were not started in this round.
+The task book's draft on one public chart was about 10 percent faster when
+cold and slower when the chart was already cached. The switch opens only
+when the vedastro image is at least 25 percent faster, contention 429s do
+not rise, and the byte diff matches. Default stays 1.
+"""
+
+from __future__ import annotations
+
+
+def main() -> int:
+    print("CONSULT_DOMAIN_CONCURRENCY default stays 1")
+    print("vedastro image bench: not run")
+    print("local API bench: not run")
+    print("contention 429 count: not run")
+    print("byte diff: not run")
+    print("reason: this round has no vedastro measurement; the published draft missed the 25 percent gate")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
@@ -0,0 +1,79 @@
+/**
+ * In-process overlap check for consult preparation.
+ *
+ * This does not measure local Postgres. Those medians were not collected,
+ * so the switches stay at their code defaults.
+ */
+import { register } from "node:module";
+
+await register(new URL("../../tests/support/stub-server-only.mjs", import.meta.url).href, import.meta.url);
+const { loadConsultTurnHead } = await import("../../src/lib/consult/turn-prep.ts");
+
+const delays = { deletion: 50, session: 80, model: 80 };
+
+async function run(parallel: boolean) {
+  let now = 0;
+  const waiters: Array<{ at: number; resolve: () => void }> = [];
+  let finished = false;
+  let inFlight = 0;
+  let maxInFlight = 0;
+  function sleep(ms: number) {
+    return new Promise<void>((resolve) => {
+      waiters.push({ at: now + ms, resolve });
+    });
+  }
+  async function occupy(ms: number) {
+    inFlight += 1;
+    maxInFlight = Math.max(maxInFlight, inFlight);
+    await sleep(ms);
+    inFlight -= 1;
+  }
+  const pending = loadConsultTurnHead({
+    parallel,
+    getUser: async () => ({ data: { user: { id: "user-1" } }, error: null }),
+    readPendingDeletion: () => occupy(delays.deletion).then(() => null),
+    readBody: async () => ({ success: true as const, data: { sessionId: "s", modelId: "m" } }),
+    readSession: () => occupy(delays.session).then(() => ({
+      data: { model_id: "m", model_config_version: 2, session_type: "consultation" },
+      error: null,
+    })),
+    resolveModel: () => occupy(delays.model).then(() => ({ id: "m" })),
+  }).then((head) => {
+    finished = true;
+    return head;
+  });
+  for (let guard = 0; guard < 40 && !finished; guard += 1) {
+    await Promise.resolve();
+    await Promise.resolve();
+    if (!waiters.length) continue;
+    waiters.sort((left, right) => left.at - right.at);
+    now = waiters[0]!.at;
+    const due: Array<() => void> = [];
+    while (waiters.length && waiters[0]!.at <= now) due.push(waiters.shift()!.resolve);
+    for (const resolve of due) resolve();
+  }
+  if (!finished) throw new Error("clock did not settle");
+  const head = await pending;
+  if (!head.ok) throw new Error("head failed");
+  return { elapsed: now, maxInFlight };
+}
+
+const on = await run(true);
+const off = await run(false);
+const report = {
+  kind: "logical-clock",
+  delays,
+  parallelElapsed: on.elapsed,
+  serialElapsed: off.elapsed,
+  parallelMaxInFlight: on.maxInFlight,
+  serialMaxInFlight: off.maxInFlight,
+  postgresMedians: "not-measured",
+  aliyunKey: "absent",
+  moderationSimulationMs: [300, 1500],
+  decision: {
+    CONSULT_PREP_PARALLEL: "off",
+    MODEL_VERSION_CACHE_TTL_MS: 0,
+    reason: "开启条件要求本机 Postgres 中位数。本轮没有量到，默认保持关闭。",
+  },
+};
+console.log(JSON.stringify(report));