fix: reduce codex supervisor output noise

2026-05-22 14:52:38 +00:00
parent b9185e0379
commit 2ed9e79d67
7 changed files with 474 additions and 42 deletions
@@ -0,0 +1,164 @@
+import { codexTasksQueryForTest } from "./src/code-queue";
+
+type JsonRecord = Record<string, unknown>;
+
+function assertCondition(condition: unknown, message: string, detail: JsonRecord = {}): void {
+  if (!condition) throw new Error(`${message}: ${JSON.stringify(detail)}`);
+}
+
+function asRecord(value: unknown): JsonRecord {
+  assertCondition(typeof value === "object" && value !== null && !Array.isArray(value), "expected JSON object", { value });
+  return value as JsonRecord;
+}
+
+function asArray(value: unknown): unknown[] {
+  assertCondition(Array.isArray(value), "expected JSON array", { value });
+  return value as unknown[];
+}
+
+function longText(marker: string, repeat: number): string {
+  return Array.from({ length: repeat }, (_, index) => `${marker}-${index} #132 Gate report diagnostic review evidence direct workbench fix`).join("\n");
+}
+
+function task(id: string, status: string, updatedAt: string, readAt: string | null = null): JsonRecord {
+  return {
+    id,
+    queueId: "default",
+    status,
+    currentAttempt: status === "running" ? 2 : 1,
+    updatedAt,
+    finishedAt: status === "succeeded" ? updatedAt : null,
+    readAt,
+    prompt: longText(`prompt-${id}`, 90),
+    basePrompt: longText(`base-${id}`, 70),
+    displayPrompt: longText(`display-${id}`, 80),
+    lastAssistantMessage: {
+      at: updatedAt,
+      seq: 99,
+      source: "assistant",
+      text: longText(`assistant-${id}`, 120),
+    },
+  };
+}
+
+function fixtureResponse(path: string): JsonRecord {
+  if (path.includes("/summary")) {
+    const taskId = decodeURIComponent(path.split("/api/tasks/")[1]?.split("/")[0] ?? "unknown");
+    return {
+      ok: true,
+      status: 200,
+      body: {
+        ok: true,
+        summary: {
+          id: taskId,
+          queueId: "default",
+          status: taskId.includes("running") ? "running" : "succeeded",
+          currentAttempt: 1,
+          maxAttempts: 99,
+          prompt: longText(`summary-prompt-${taskId}`, 100),
+          basePrompt: longText(`summary-base-${taskId}`, 80),
+          lastAssistantMessage: {
+            at: "2026-05-22T00:00:00.000Z",
+            seq: 120,
+            source: "assistant",
+            text: longText(`summary-assistant-${taskId}`, 130),
+          },
+          commands: {
+            show: `bun scripts/cli.ts codex task ${taskId}`,
+            trace: `bun scripts/cli.ts codex task ${taskId} --trace --tail --limit 80`,
+          },
+        },
+      },
+    };
+  }
+  assertCondition(path.startsWith("/api/microservices/code-queue/proxy/api/tasks/overview"), "unexpected path", { path });
+  return {
+    ok: true,
+    status: 200,
+    body: {
+      ok: true,
+      queue: {
+        executionDiagnostics: {
+          effectiveLiveness: "live",
+          splitBrainLive: true,
+          recommendedAction: "continue-supervision",
+        },
+      },
+      pagination: {
+        limit: 200,
+        returned: 15,
+        total: 15,
+        hasMore: false,
+        nextBeforeId: null,
+        includeActive: true,
+      },
+      tasks: [
+        task("task-running", "running", "2026-05-22T00:09:00.000Z"),
+        task("task-succeeded-1", "succeeded", "2026-05-22T00:08:00.000Z"),
+        task("task-succeeded-2", "succeeded", "2026-05-22T00:07:00.000Z"),
+        task("task-succeeded-3", "succeeded", "2026-05-22T00:06:00.000Z"),
+        task("task-succeeded-4", "succeeded", "2026-05-22T00:05:00.000Z"),
+        task("task-succeeded-5", "succeeded", "2026-05-22T00:04:00.000Z"),
+        task("task-succeeded-6", "succeeded", "2026-05-22T00:03:00.000Z"),
+        task("task-succeeded-7", "succeeded", "2026-05-22T00:02:00.000Z"),
+        task("task-read-1", "succeeded", "2026-05-22T00:01:50.000Z", "2026-05-22T00:01:55.000Z"),
+        task("task-read-2", "succeeded", "2026-05-22T00:01:40.000Z", "2026-05-22T00:01:45.000Z"),
+        task("task-read-3", "succeeded", "2026-05-22T00:01:30.000Z", "2026-05-22T00:01:35.000Z"),
+        task("task-read-4", "succeeded", "2026-05-22T00:01:20.000Z", "2026-05-22T00:01:25.000Z"),
+        task("task-read-5", "succeeded", "2026-05-22T00:01:10.000Z", "2026-05-22T00:01:15.000Z"),
+        task("task-read-6", "succeeded", "2026-05-22T00:01:05.000Z", "2026-05-22T00:01:09.000Z"),
+        task("task-queued", "queued", "2026-05-22T00:01:00.000Z"),
+      ],
+    },
+  };
+}
+
+export function runCodeQueueSupervisorDisclosureContract(): JsonRecord {
+  const supervisor = codexTasksQueryForTest(["--view", "supervisor", "--limit", "20"], fixtureResponse);
+  const full = codexTasksQueryForTest(["--view", "full", "--limit", "20"], fixtureResponse);
+
+  const supervisorBody = JSON.stringify(supervisor);
+  const fullBody = JSON.stringify(full);
+  const supervisorData = asRecord(supervisor);
+  const supervisorView = asRecord(supervisorData.supervisor);
+  const disclosure = asRecord(supervisorView.disclosure);
+  const runningItem = asRecord(asArray(asRecord(supervisorView.running).items)[0]);
+  const recentCompleted = asRecord(supervisorView.recentCompleted);
+  const recentItems = asArray(recentCompleted.items);
+  const prompt = asRecord(runningItem.prompt);
+  const lastMessage = asRecord(runningItem.lastMessage);
+  const commands = asRecord(runningItem.commands);
+  const fullItem = asRecord(asArray(asRecord(asRecord(full).tasks).items)[0]);
+  const completedUnread = asRecord(supervisorView.completedUnread);
+  const fullTasks = asRecord(asRecord(full).tasks);
+
+  assertCondition(supervisorBody.length < fullBody.length * 0.55, "supervisor output should be materially smaller than full output", { supervisorChars: supervisorBody.length, fullChars: fullBody.length });
+  assertCondition(recentItems.length === 5, "recentCompleted should be capped below --limit by default", { returned: recentItems.length });
+  assertCondition(asArray(completedUnread.items).length === 7, "completedUnread should keep unread terminal tasks separate from recentCompleted", completedUnread);
+  assertCondition(recentItems.every((item) => asRecord(item).unreadTerminal === false), "recentCompleted should not duplicate unread terminal tasks", { recentItems });
+  assertCondition(asArray(runningItem.issueRefs).includes("#132"), "supervisor row should expose issue refs for triage", runningItem);
+  assertCondition(Number(prompt.chars) > String(prompt.text ?? "").length && prompt.truncated === true, "supervisor prompt must be a short preview with original char count", prompt);
+  assertCondition(Number(lastMessage.chars) > String(lastMessage.text ?? "").length && lastMessage.truncated === true, "supervisor body must be a short preview with original char count", lastMessage);
+  assertCondition(commands.show !== undefined && commands.trace !== undefined && commands.output !== undefined && commands.full !== undefined, "supervisor row must keep progressive drill-down commands", commands);
+  assertCondition(runningItem.promptPreview === undefined && runningItem.lastAssistantMessage === undefined, "supervisor rows must not expose legacy long list fields", runningItem);
+  assertCondition(asRecord(fullItem.promptPreview).chars !== undefined && fullItem.lastAssistantMessage !== undefined, "full view must retain detailed task row fields", fullItem);
+  assertCondition(fullTasks.returned === 15, "full view must not inherit supervisor recentCompleted cap", fullTasks);
+  assertCondition(asRecord(disclosure.outputBudget).recentCompletedReturnedLimit === 5, "supervisor must expose output budget metadata", disclosure);
+
+  return {
+    ok: true,
+    checks: [
+      "supervisor output materially smaller than full",
+      "recentCompleted capped",
+      "prompt/body previews bounded",
+      "drill-down commands preserved",
+      "full view remains detailed",
+    ],
+    supervisorChars: supervisorBody.length,
+    fullChars: fullBody.length,
+  };
+}
+
+if (import.meta.main) {
+  process.stdout.write(`${JSON.stringify(runCodeQueueSupervisorDisclosureContract(), null, 2)}\n`);
+}