mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-04 19:28:46 +01:00
test(runner): exercise correction deadlines with virtual time
This commit is contained in:
1 parent
55be2a8bc8
commit
6ba01c52b3
1 file changed
+50
-13
@@ -1,11 +1,11 @@
|
||||
import { chmod, copyFile, mkdtemp, rm } from "node:fs/promises";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join, resolve } from "node:path";
|
||||
import { expect, it } from "vitest";
|
||||
import { expect, it, vi } from "vitest";
|
||||
import { OpenCodeServerDriver } from "./opencode-server-driver.js";
|
||||
import type { PrpEvent } from "../../protocol/replay-contract.js";
|
||||
|
||||
it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "idle-stall", "tool-idle-stall", "empty-again", "request-fails", "normal", "foreign-idle", "queued-tool"] as const)("handles an empty OpenCode response: %s", async mode => {
|
||||
it.each(["reply", "reply-no-finish", "reply-tool-finish", "two-turn-idle", "slow-native-tool", "idle-stall", "tool-idle-stall", "empty-again", "request-fails", "normal", "foreign-idle", "queued-tool"] as const)("handles an empty OpenCode response: %s", async mode => {
|
||||
const root = await mkdtemp(join(tmpdir(), "opencode-empty-response-"));
|
||||
const command = join(root, "fake-opencode.mjs");
|
||||
await copyFile(resolve("test/fixtures/fake-opencode-server.mjs"), command);
|
||||
@@ -13,6 +13,8 @@ it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "i
|
||||
const prompts: Record<string, any>[] = [];
|
||||
let toolTimer: ReturnType<typeof setTimeout> | undefined;
|
||||
let stream: ReadableStreamDefaultController<Uint8Array> | undefined;
|
||||
let streamOpened!: () => void;
|
||||
const opened = new Promise<void>(resolve => { streamOpened = resolve; });
|
||||
const queued: Uint8Array[] = [];
|
||||
const emit = (value: unknown) => { const frame = new TextEncoder().encode(`data: ${JSON.stringify(value)}\n\n`); if (stream) stream.enqueue(frame); else queued.push(frame); };
|
||||
const driver = new OpenCodeServerDriver({
|
||||
@@ -20,7 +22,7 @@ it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "i
|
||||
environment: { PATH: process.env.PATH, OPENROUTER_API_KEY: "controlled-fixture-key" },
|
||||
fetch: async (input, init) => {
|
||||
const url = new URL(String(input));
|
||||
if (url.pathname === "/event") return new Response(new ReadableStream<Uint8Array>({ start(controller) { stream = controller; for (const frame of queued.splice(0)) controller.enqueue(frame); } }), { headers: { "Content-Type": "text/event-stream" } });
|
||||
if (url.pathname === "/event") return new Response(new ReadableStream<Uint8Array>({ start(controller) { stream = controller; for (const frame of queued.splice(0)) controller.enqueue(frame); streamOpened(); } }), { headers: { "Content-Type": "text/event-stream" } });
|
||||
if (url.pathname.endsWith("/prompt_async")) {
|
||||
const prompt = JSON.parse(String(init?.body)); prompts.push(prompt);
|
||||
if (prompts.length === 2 && mode === "request-fails") throw new Error("controlled correction request failed");
|
||||
@@ -28,9 +30,13 @@ it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "i
|
||||
const number = prompts.length, messageID = `assistant-${number}`;
|
||||
queueMicrotask(() => {
|
||||
if (mode === "foreign-idle") emit({ type: "session.idle", properties: { sessionID: "foreign-session" } });
|
||||
const incompleteHeader = number === 2 && ["reply-no-finish", "reply-tool-finish", "idle-stall", "tool-idle-stall"].includes(mode);
|
||||
const incompleteHeader = number === 2 && ["reply-no-finish", "reply-tool-finish", "idle-stall", "tool-idle-stall", "two-turn-idle"].includes(mode)
|
||||
|| mode === "two-turn-idle" && number === 4;
|
||||
const toolFinish = ["reply-tool-finish", "tool-idle-stall"].includes(mode) || mode === "two-turn-idle" && number === 2;
|
||||
emit({ type: "message.updated", properties: { info: { id: messageID, sessionID, role: "assistant",
|
||||
...(incompleteHeader ? ["reply-tool-finish", "tool-idle-stall"].includes(mode) ? { finish: "tool-calls" } : {} : { finish: "stop", time: { completed: Date.now() } }) } } });
|
||||
...(incompleteHeader ? toolFinish ? { finish: "tool-calls" } : {} : { finish: "stop", time: { completed: Date.now() } }) } } });
|
||||
// Arm the first turn's idle grace before its late completed answer.
|
||||
if (mode === "two-turn-idle" && number === 2) emit({ type: "session.idle", properties: { sessionID } });
|
||||
if (mode === "slow-native-tool" && number === 2 || mode === "queued-tool") {
|
||||
const toolPart = { id: `native-${number}`, messageID, sessionID, type: "tool", tool: "bash", callID: `call-${number}`,
|
||||
state: { status: mode === "queued-tool" ? "pending" : "running", input: { command: "owned-controlled-command" } } };
|
||||
@@ -45,7 +51,7 @@ it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "i
|
||||
return;
|
||||
}
|
||||
}
|
||||
const answer = mode === "normal" || mode === "foreign-idle" || mode === "queued-tool" || number === 2 && ["reply", "reply-no-finish", "reply-tool-finish"].includes(mode);
|
||||
const answer = mode === "normal" || mode === "foreign-idle" || mode === "queued-tool" || number === 2 && ["reply", "reply-no-finish", "reply-tool-finish", "two-turn-idle"].includes(mode);
|
||||
emit({ type: "message.part.updated", properties: { sessionID, part: { id: `part-${number}`, messageID,
|
||||
type: answer ? "text" : "reasoning", text: answer ? "Here is the actual final answer." : "Synthetic reasoning must not become the answer.", time: { start: 1, end: 2 } } } });
|
||||
emit({ type: "session.idle", properties: { sessionID } });
|
||||
@@ -59,14 +65,33 @@ it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "i
|
||||
const session = await driver.openSession({ runId: "owned-run", normalizedSessionId: "owned-session", workingDirectory: root });
|
||||
let deadline: ReturnType<typeof setTimeout> | undefined;
|
||||
try {
|
||||
const collected = (async () => { const rows: PrpEvent[] = []; for await (const event of session.events()) {
|
||||
rows.push(event); if (["turn.completed", "turn.failed"].includes(event.eventType)) break;
|
||||
} return rows; })();
|
||||
await opened;
|
||||
// Real process/HTTP setup is complete. Only the controlled event stream
|
||||
// and production grace/tool timers advance on this virtual clock.
|
||||
vi.useFakeTimers({ toFake: ["setTimeout", "clearTimeout"] });
|
||||
const observed: PrpEvent[] = [];
|
||||
const collect = async () => { const rows: PrpEvent[] = []; for await (const event of session.events()) {
|
||||
rows.push(event); observed.push(event); if (["turn.completed", "turn.failed"].includes(event.eventType)) break;
|
||||
} return rows; };
|
||||
const guard = (work: Promise<PrpEvent[]>, milliseconds: number) => {
|
||||
clearTimeout(deadline);
|
||||
const result = Promise.race([work, new Promise<PrpEvent[]>((_, reject) => {
|
||||
deadline = setTimeout(() => reject(new Error("Controlled provider produced no terminal event")), milliseconds);
|
||||
})]);
|
||||
void result.catch(() => {});
|
||||
return result;
|
||||
};
|
||||
const collected = collect();
|
||||
const { turnId } = await session.startTurn({ message: { role: "user", text: "Answer the current request." }, reasoningMode: "disabled" });
|
||||
const events = await Promise.race([collected, new Promise<PrpEvent[]>((_, reject) => {
|
||||
deadline = setTimeout(() => reject(new Error("Controlled provider produced no terminal event")), mode.endsWith("idle-stall") || mode === "slow-native-tool" ? 26_000 : 5_000);
|
||||
})]);
|
||||
const succeeds = ["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "normal", "foreign-idle", "queued-tool"].includes(mode);
|
||||
const completed = guard(collected, mode.endsWith("idle-stall") || mode === "slow-native-tool" ? 26_000 : 5_000);
|
||||
await vi.advanceTimersByTimeAsync(0);
|
||||
if (mode === "slow-native-tool") {
|
||||
await vi.advanceTimersByTimeAsync(20_001);
|
||||
expect(observed.some(event => ["turn.completed", "turn.failed"].includes(event.eventType))).toBe(false);
|
||||
}
|
||||
await vi.advanceTimersByTimeAsync(mode.endsWith("idle-stall") ? 20_001 : mode === "slow-native-tool" ? 1_999 : 5_001);
|
||||
const events = await completed;
|
||||
const succeeds = ["reply", "reply-no-finish", "reply-tool-finish", "two-turn-idle", "slow-native-tool", "normal", "foreign-idle", "queued-tool"].includes(mode);
|
||||
expect(events.at(-1)?.eventType).toBe(succeeds ? "turn.completed" : "turn.failed");
|
||||
expect(events.filter(event => event.eventType === "turn.started")).toHaveLength(1);
|
||||
expect(events.every(event => !event.turnId || event.turnId === turnId)).toBe(true);
|
||||
@@ -77,9 +102,21 @@ it.each(["reply", "reply-no-finish", "reply-tool-finish", "slow-native-tool", "i
|
||||
expect(prompts[1]).toMatchObject({ providerID: prompts[0]!.providerID, modelID: prompts[0]!.modelID, system: prompts[0]!.system, variant: "paperclip-no-reasoning" });
|
||||
expect(JSON.stringify(prompts[1]!.parts)).toContain("Do not repeat completed actions");
|
||||
}
|
||||
if (mode === "two-turn-idle") {
|
||||
const nextEvents = collect();
|
||||
const next = await session.startTurn({ message: { role: "user", text: "Answer the next request." }, reasoningMode: "disabled" });
|
||||
const nextCompleted = guard(nextEvents, 26_000);
|
||||
await vi.advanceTimersByTimeAsync(0);
|
||||
await vi.advanceTimersByTimeAsync(20_001);
|
||||
const rows = await nextCompleted;
|
||||
expect(rows.at(-1)?.eventType).toBe("turn.failed");
|
||||
expect(rows.every(event => !event.turnId || event.turnId === next.turnId)).toBe(true);
|
||||
expect(prompts).toHaveLength(4);
|
||||
}
|
||||
} finally {
|
||||
clearTimeout(deadline);
|
||||
clearTimeout(toolTimer);
|
||||
vi.useRealTimers();
|
||||
await session.close({ reason: "controlled test complete" });
|
||||
await rm(root, { recursive: true, force: true });
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user