fix: bound codex task supervisor output

This commit is contained in:
Codex
2026-05-22 18:06:14 +00:00
parent 05b77151b8
commit f54645ba07
4 changed files with 227 additions and 109 deletions
@@ -138,59 +138,106 @@ function fixtureResponse(path: string): JsonRecord {
};
}
function manyRunningFixtureResponse(path: string): JsonRecord {
if (path.includes("/summary")) return fixtureResponse(path);
assertCondition(path.startsWith("/api/microservices/code-queue/proxy/api/tasks/overview"), "unexpected path", { path });
const tasks = Array.from({ length: 40 }, (_, index) => task(
`task-running-${String(index + 1).padStart(2, "0")}`,
"running",
`2026-05-22T00:${String(59 - index).padStart(2, "0")}:00.000Z`,
));
return {
ok: true,
status: 200,
body: {
ok: true,
queue: {
executionDiagnostics: {
state: "healthy",
databaseActiveTaskCount: 40,
databaseActiveTaskIds: manyIds("running-active", 40),
activeHeartbeatCount: 40,
activeHeartbeatTaskIds: manyIds("running-heartbeat", 40),
heartbeatFreshTaskIds: manyIds("running-fresh", 40),
},
},
pagination: {
limit: 200,
returned: 40,
total: 40,
hasMore: false,
nextBeforeId: null,
includeActive: true,
},
tasks,
},
};
}
export function runCodeQueueSupervisorDisclosureContract(): JsonRecord {
const supervisor = codexTasksQueryForTest(["--view", "supervisor", "--limit", "20"], fixtureResponse);
const full = codexTasksQueryForTest(["--view", "full", "--limit", "20"], fixtureResponse);
const runningFiltered = codexTasksQueryForTest(["--status", "running", "--limit", "40"], manyRunningFixtureResponse);
const unreadFiltered = codexTasksQueryForTest(["--unread", "--limit", "20"], fixtureResponse);
const supervisorBody = JSON.stringify(supervisor);
const fullBody = JSON.stringify(full);
const runningFilteredBody = JSON.stringify(runningFiltered);
const unreadFilteredBody = JSON.stringify(unreadFiltered);
const supervisorData = asRecord(supervisor);
const supervisorView = asRecord(supervisorData.supervisor);
const runningFilteredView = asRecord(asRecord(runningFiltered).supervisor);
const runningFilteredSection = asRecord(runningFilteredView.running);
const unreadFilteredView = asRecord(asRecord(unreadFiltered).supervisor);
const unreadFilteredSection = asRecord(unreadFilteredView.completedUnread);
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);
const diagnostics = asRecord(supervisorView.executionDiagnostics);
const liveness = asRecord(diagnostics.liveness);
const listBudget = asRecord(diagnostics.listBudget);
const omittedCounts = asRecord(listBudget.omittedCounts);
assertCondition(supervisorBody.length < fullBody.length * 0.55, "supervisor output should be materially smaller than full output", { supervisorChars: supervisorBody.length, fullChars: fullBody.length });
assertCondition(supervisorBody.length < 70_000, "supervisor output should remain bounded even with large diagnostics", { supervisorChars: supervisorBody.length });
assertCondition(supervisorBody.length < 45_000, "supervisor output should remain bounded even with large diagnostics", { supervisorChars: supervisorBody.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(asArray(completedUnread.items).length === 5, "completedUnread should be locally paged and kept separate from recentCompleted", completedUnread);
assertCondition(recentItems.every((item) => asRecord(item).unreadTerminal === false), "recentCompleted should not duplicate unread terminal tasks", { recentItems });
assertCondition(asArray(diagnostics.databaseActiveTaskIds).length === 12, "diagnostic task id lists should be capped", diagnostics);
assertCondition(omittedCounts.databaseActiveTaskIds === 68, "diagnostic omitted counts should preserve full visibility metadata", omittedCounts);
assertCondition(liveness.effectiveLiveness === "live", "supervisor liveness summary should keep split-brain live explicit", liveness);
assertCondition(liveness.recommendedAction === "continue-supervision", "supervisor liveness summary should recommend continued supervision", liveness);
assertCondition(liveness.splitBrainLive === true, "supervisor liveness summary should mark splitBrainLive", liveness);
assertCondition(liveness.activeHeartbeatCount === 80, "supervisor liveness summary should foreground active heartbeat count", liveness);
assertCondition(asArray(liveness.heartbeatFreshTaskIds).length === 12, "supervisor liveness summary should keep heartbeatFreshTaskIds bounded", liveness);
assertCondition(String(liveness.interpretation ?? "").includes("continue supervision"), "supervisor liveness interpretation should not imply scheduler stoppage", liveness);
assertCondition(asArray(diagnostics.reasons).length === 6, "diagnostic reasons should be capped", diagnostics);
assertCondition(diagnostics.livenessSummaryTruncated === true, "long diagnostic liveness summary should be previewed", diagnostics);
assertCondition(diagnostics.databaseActiveTaskIds === undefined, "supervisor diagnostics should not expose verbose databaseActiveTaskIds by default", diagnostics);
assertCondition(omittedCounts.databaseActiveTaskIds === 77, "diagnostic omitted counts should preserve full visibility metadata", omittedCounts);
assertCondition(diagnostics.effectiveLiveness === "live", "supervisor liveness summary should keep split-brain live explicit", diagnostics);
assertCondition(diagnostics.recommendedAction === "continue-supervision", "supervisor liveness summary should recommend continued supervision", diagnostics);
assertCondition(diagnostics.splitBrainLive === true, "supervisor liveness summary should mark splitBrainLive", diagnostics);
assertCondition(diagnostics.activeHeartbeatCount === 80, "supervisor liveness summary should foreground active heartbeat count", diagnostics);
assertCondition(asArray(diagnostics.heartbeatFreshTaskIds).length === 3, "supervisor diagnostics should keep heartbeatFreshTaskIds bounded", diagnostics);
assertCondition(String(diagnostics.interpretation ?? "").includes("continue supervision"), "supervisor liveness interpretation should not imply scheduler stoppage", diagnostics);
assertCondition(asArray(diagnostics.reasons).length === 2, "diagnostic reasons should be capped", diagnostics);
assertCondition(diagnostics.livenessSummary === undefined, "supervisor diagnostics should omit liveness summary preview by default", diagnostics);
assertCondition(listBudget.truncated === true && typeof listBudget.rawCommand === "string", "diagnostic list budget should disclose raw command", listBudget);
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(asArray(runningItem.issues).includes("#132"), "supervisor row should expose issue refs for triage", runningItem);
assertCondition(Number(runningItem.promptChars) > String(runningItem.prompt ?? "").length && runningItem.promptTruncated === true, "supervisor prompt must be a short flat preview with original char count", runningItem);
assertCondition(Number(runningItem.lastChars) > String(runningItem.last ?? "").length && runningItem.lastTruncated === true, "supervisor body must be a short flat preview with original char count", runningItem);
assertCondition(runningItem.commands === undefined && runningItem.promptPreview === undefined && runningItem.lastAssistantMessage === undefined, "supervisor rows must not expose repeated commands or 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);
const budget = asRecord(disclosure.outputBudget);
assertCondition(budget.recentCompletedReturnedLimit === 5 && budget.sectionReturnedLimit === 5, "supervisor must expose output budget metadata", disclosure);
assertCondition(asArray(runningFilteredSection.items).length === 5, "running status filter should be locally paged below --limit", runningFilteredSection);
assertCondition(runningFilteredSection.count === 40 && runningFilteredSection.hasMore === true, "running status filter should preserve count and hasMore", runningFilteredSection);
assertCondition(String(asRecord(runningFilteredSection.commands).next ?? "").includes("--before-id task-running-05"), "running status filter should provide next page command", runningFilteredSection);
assertCondition(runningFilteredBody.length < 14_000, "running status filter output should remain bounded", { chars: runningFilteredBody.length });
assertCondition(asArray(unreadFilteredSection.items).length <= 5, "unread list should be locally paged below --limit", unreadFilteredSection);
assertCondition(unreadFilteredBody.length < 14_000, "unread output should remain bounded", { chars: unreadFilteredBody.length });
return {
ok: true,
checks: [
"supervisor output materially smaller than full",
"recentCompleted capped",
"running/unread locally paged",
"split-brain diagnostics capped",
"prompt/body previews bounded",
"drill-down commands preserved",