test(restart-chaos): count inherited Daytona sandboxes as warm only when the agent's lifecycle allows it; bind verify tasks to the project

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
DottaandClaude Opus 5.5 committed 2026-11-08 08:41:24 -06:00
1 parent 3ff56d6446
commit b1b644ff0a
3 files changed
+30 -8

No files matched your search

@@ -1,6 +1,6 @@
import { describe, expect, it } from "vitest";
import {
baselineRows, daytonaBaselineHolders, distribution, parseBaselineEnvironment, openShellExecutions, percentile, rankPreTurnSteps, recoverySamples, runMetrics, runWarmth,
baselineRows, daytonaBaselineHolders, daytonaRetainsSandboxes, distribution, parseBaselineEnvironment, openShellExecutions, percentile, rankPreTurnSteps, recoverySamples, runMetrics, runWarmth,
type BaselineEvent, type BaselineRun,
} from "./ttft-baseline-stats.js";
@@ -91,6 +91,15 @@ describe("ttft baseline statistics", () => {
expect(daytonaBaselineHolders({ adapters: 2, samples: 0, phases: new Set(["postfault"]), restarts: 0, retainsSandboxes: true })).toBe(2);
});
it("treats an inheriting environment as warm only when the agent's lifecycle is not pinned per-turn", () => {
expect(daytonaRetainsSandboxes({ warmEnvironment: true, inheritEnvironment: false, lifecycle: undefined })).toBe(true);
expect(daytonaRetainsSandboxes({ warmEnvironment: false, inheritEnvironment: true, lifecycle: undefined })).toBe(false);
expect(daytonaRetainsSandboxes({ warmEnvironment: false, inheritEnvironment: true, lifecycle: "per_turn" })).toBe(false);
expect(daytonaRetainsSandboxes({ warmEnvironment: false, inheritEnvironment: true, lifecycle: "default" })).toBe(true);
expect(daytonaRetainsSandboxes({ warmEnvironment: false, inheritEnvironment: true, lifecycle: "warm" })).toBe(true);
expect(daytonaRetainsSandboxes({ warmEnvironment: false, inheritEnvironment: false, lifecycle: "warm" })).toBe(false);
});
it("rejects contradictory or out-of-range environment options", () => {
const base = { env: "daytona", image: "img", cpu: "4", warm: false, inherit: false };
expect(parseBaselineEnvironment(base)).toEqual({ env: "daytona", cpu: 4 });
@@ -236,6 +236,17 @@ export function openShellExecutions(events: readonly BaselineEvent[], marker?: s
return [...open.entries()].map(([executionId, entry]) => ({ executionId, matched: entry.matched, unlabelled: !entry.labelled }));
}
/**
* Whether finished tasks keep their Daytona sandbox for the idle window. The warm
* fixture always does. An inheriting environment defers to the agent, whose catalog
* profile pins per_turn unless --lifecycle warm or default (the product's warm
* default on a remote sandbox) replaces it.
*/
export function daytonaRetainsSandboxes(input: { warmEnvironment: boolean; inheritEnvironment: boolean; lifecycle: string | undefined }): boolean {
if (input.warmEnvironment) return true;
return input.inheritEnvironment && (input.lifecycle === "warm" || input.lifecycle === "default");
}
/** Daytona sandboxes a TTFT baseline can hold at once, for the vCPU budget check. */
export function daytonaBaselineHolders(input: { adapters: number; samples: number; phases: ReadonlySet<string>; restarts: number;
retainsSandboxes: boolean }): number {
+9 -7
View File
@@ -30,7 +30,7 @@ import { DaytonaWaveSweeper } from "./daytona-sweep.js";
import { Timeline } from "./timeline.js";
import type { AdapterId, FaultKind } from "./types.js";
import {
baselineRows, rankPreTurnSteps, recoverySamples, distribution, openShellExecutions, daytonaBaselineHolders, parseBaselineEnvironment,
baselineRows, rankPreTurnSteps, recoverySamples, distribution, openShellExecutions, daytonaBaselineHolders, daytonaRetainsSandboxes, parseBaselineEnvironment,
type BaselineEvent, type BaselineFault, type BaselineRun,
} from "./ttft-baseline-stats.js";
@@ -269,11 +269,16 @@ async function main() {
const requested = values.adapters!.split(",").map(value => value.trim()) as AdapterId[];
const samples = Math.max(1, Number(values.samples));
const restarts = Math.max(0, Number(values.restarts));
const lifecycle = values.lifecycle;
if (lifecycle !== undefined && lifecycle !== "per_turn" && lifecycle !== "warm" && lifecycle !== "default") {
throw new Error("--lifecycle must be per_turn, warm or default");
}
const { env, cpu } = parseBaselineEnvironment({ env: values.env, image: values["daytona-image"], cpu: values["daytona-cpu"],
warm: values["daytona-warm"] === true, inherit: values["daytona-inherit"] === true });
if (env === "daytona") {
const budget = Number(process.env.RESTART_CHAOS_DAYTONA_VCPU_BUDGET ?? DAYTONA_VCPU_BUDGET);
const retainsSandboxes = values["daytona-warm"] === true || values["daytona-inherit"] === true;
const retainsSandboxes = daytonaRetainsSandboxes({ warmEnvironment: values["daytona-warm"] === true,
inheritEnvironment: values["daytona-inherit"] === true, lifecycle });
const holders = daytonaBaselineHolders({ adapters: requested.length, samples, phases, restarts, retainsSandboxes });
if (holders * cpu > budget) {
throw new Error(`${holders} ${retainsSandboxes ? "sampled tasks (warm sandboxes outlive their task)" : "concurrent tasks"} × --daytona-cpu ${cpu} vCPU can be held at once, `
@@ -290,10 +295,6 @@ async function main() {
if (midturnFault && midturnMode !== "steer") throw new Error("--midturn-fault applies to --midturn-mode steer");
const verifyFault = values["verify-fault"] as FaultKind | undefined;
if (verifyFault !== undefined && !["K1", "K2", "K6"].includes(verifyFault)) throw new Error("--verify-fault must be K1, K2 or K6");
const lifecycle = values.lifecycle;
if (lifecycle !== undefined && lifecycle !== "per_turn" && lifecycle !== "warm" && lifecycle !== "default") {
throw new Error("--lifecycle must be per_turn, warm or default");
}
// default removes the catalog's pinned per_turn so the server resolves the
// product default; absent keeps the catalog setting.
const adapterConfigOverrides = lifecycle === "warm"
@@ -409,7 +410,8 @@ async function main() {
const hired = await api.post<Json>(`/api/companies/${lab.companyId}/agents`, { ...source.body, name: `${source.name} verify ${nonce}` });
const agentId = String(hired.id);
const issue = await api.post<Json>(`/api/companies/${lab.companyId}/issues`, {
title: `TTFT verify ${nonce}`, description: coldTask(nonce), status: "todo", priority: "medium", assigneeAgentId: agentId });
title: `TTFT verify ${nonce}`, description: coldTask(nonce), status: "todo", priority: "medium", assigneeAgentId: agentId,
...(projectScopedTasks ? { projectId: lab.projectId } : {}) });
const issueId = String(issue.id);
tasks.push({ issueId, adapter, phase: "verify" });
let fault: Awaited<ReturnType<typeof supervisor.fault>> | null = null;