amosblomqvist
2535d7ad35
With continuation coalescing, a job flips done at CLAIM time — while the learner's own answer turn is still streaming. The poller's settle re-sync fired on the flip, swapping in a mid-turn record snapshot mid-stream; the steer after the assistant message broke the SDK's in-place continuation merge, and the streaming response landed as a SECOND message with the same id — duplicate React keys in the live transcript (the user's live test hit it; the record itself stayed clean). A settle during a busy turn (local stream OR server turnInFlight) now marks a pending sync; the first idle poll tick adopts the finished record. This also fixes the latent multi-job race: steer B settling while steer A's wake turn is in flight would have grabbed the same mid-turn snapshot. Out-of-lane surgical touch (flagged for master review): the wave-1 poller block in components/chat.tsx.
839 lines
35 KiB
TypeScript
839 lines
35 KiB
TypeScript
/**
|
|
* Job infrastructure tests — deterministic, zero network:
|
|
*
|
|
* 1. job store CRUD (create → get → update → list → dedup by toolCallId)
|
|
* 2. steer helpers (pure, contracts.ts): buildSubagentSteer shape per kind,
|
|
* isSubagentFailure, steerDelivered
|
|
* 3. dispatch (async protocol §2): drive handleChatRequest with a scripted
|
|
* mock teacher that emits a research tool call → the tool part resolves
|
|
* IMMEDIATELY with the fire-and-forget ack (the teacher's turn
|
|
* CONTINUES — no turn break at the call), a job record exists, and the
|
|
* test runner (fake deliver) produces the steer
|
|
* 4. runner completion: a fake researcher model (web_search call → final
|
|
* text brief, globalThis.fetch stubbed) → the job stores the result,
|
|
* the steer carries the brief + sources, the fake deliver flips the
|
|
* job done
|
|
* 5. runner failure: a model that throws → the failure steer still fires
|
|
* (the teacher learns the outcome) and the job lands error
|
|
* 6. the wake pipeline (src/server/jobs.ts): server-side steer delivery —
|
|
* happy path (fires the injected turn runner, flips the job), pending-
|
|
* quiz deferral, 409 retry, idempotent redelivery
|
|
*
|
|
* Cleanup follows tests/chat-flow.test.ts: created chat/job files removed in
|
|
* finally blocks / the after() hook.
|
|
*/
|
|
|
|
import assert from "node:assert/strict";
|
|
import * as fs from "node:fs";
|
|
import * as path from "node:path";
|
|
import { after, describe, it } from "node:test";
|
|
import type { UIMessage } from "ai";
|
|
import { MockLanguageModelV4, simulateReadableStream } from "ai/test";
|
|
import type { LanguageModelV4StreamPart } from "@ai-sdk/provider";
|
|
import {
|
|
buildSubagentSteer,
|
|
isSubagentFailure,
|
|
steerDelivered,
|
|
type DemoResult,
|
|
type ResearchResult,
|
|
type SubagentSteerMessage,
|
|
type VisualResult,
|
|
} from "../src/core/contracts.ts";
|
|
import { composeInstructions, createTeacherAgent } from "../src/agent/teacher-agent.ts";
|
|
import { createTeacherTools } from "../src/agent/tools.ts";
|
|
import { handleChatRequest } from "../src/server/chat-handler.ts";
|
|
import { claimSteers, deliverJobResult, setTurnRunner } from "../src/server/jobs.ts";
|
|
import { persistTurn, withMessageIds } from "../src/server/turn-service.ts";
|
|
import { chatStore } from "../src/store/chats.ts";
|
|
import { jobStore } from "../src/store/jobs.ts";
|
|
import { createJobRunner, researchModelOverride } from "../src/agent/subagents/runner.ts";
|
|
import { createResearcherAgent } from "../src/agent/subagents/researcher.ts";
|
|
import { PATHS } from "../config.ts";
|
|
|
|
const JOBS_DIR = path.join(PATHS.data, "jobs");
|
|
|
|
const createdChats: string[] = [];
|
|
const createdJobs: string[] = [];
|
|
|
|
function trackChat(id: string) {
|
|
createdChats.push(id);
|
|
}
|
|
|
|
function trackJob(id: string) {
|
|
createdJobs.push(id);
|
|
}
|
|
|
|
after(() => {
|
|
for (const id of createdChats) {
|
|
try {
|
|
fs.unlinkSync(path.join(PATHS.chats, `${id}.json`));
|
|
} catch {
|
|
/* already gone */
|
|
}
|
|
}
|
|
for (const id of createdJobs) {
|
|
try {
|
|
fs.unlinkSync(path.join(JOBS_DIR, `${id}.json`));
|
|
} catch {
|
|
/* already gone */
|
|
}
|
|
}
|
|
researchModelOverride.current = undefined;
|
|
});
|
|
|
|
function usage() {
|
|
return {
|
|
inputTokens: { total: 10, noCache: 10, cacheRead: 0, cacheWrite: 0 },
|
|
outputTokens: { total: 5, text: 5, reasoning: 0 },
|
|
};
|
|
}
|
|
|
|
async function drain(res: Response): Promise<string> {
|
|
if (res.status !== 200) {
|
|
assert.fail(`expected 200, got ${res.status}: ${await res.text()}`);
|
|
}
|
|
return res.text();
|
|
}
|
|
|
|
function post(chatId: string, messages: unknown[]): Request {
|
|
return new Request("http://test/api/chat", {
|
|
method: "POST",
|
|
headers: { "Content-Type": "application/json" },
|
|
body: JSON.stringify({ chatId, messages }),
|
|
});
|
|
}
|
|
|
|
function waitFor(cond: () => boolean, timeoutMs = 8000, what = "condition"): Promise<void> {
|
|
return new Promise((resolve, reject) => {
|
|
const started = Date.now();
|
|
const tick = () => {
|
|
if (cond()) return resolve();
|
|
if (Date.now() - started > timeoutMs) return reject(new Error(`timeout waiting for ${what}`));
|
|
setTimeout(tick, 25);
|
|
};
|
|
tick();
|
|
});
|
|
}
|
|
|
|
// ─── 1. job store CRUD ───────────────────────────────────────────────────────
|
|
|
|
describe("job store", () => {
|
|
it("create → get → update → list round-trips", () => {
|
|
const job = jobStore.createJob({ kind: "research", chatId: "chat_storetest", toolCallId: "call-store" });
|
|
trackJob(job.id);
|
|
|
|
assert.match(job.id, /^job_/);
|
|
assert.equal(job.status, "running");
|
|
assert.equal(job.activity, "starting");
|
|
|
|
const loaded = jobStore.getJob(job.id)!;
|
|
assert.equal(loaded.toolCallId, "call-store");
|
|
assert.equal(loaded.kind, "research");
|
|
|
|
const updated = jobStore.updateJob(job.id, { activity: 'web_search: "test"', status: "done", result: { brief: "b" } })!;
|
|
assert.equal(updated.activity, 'web_search: "test"');
|
|
assert.equal(updated.status, "done");
|
|
assert.ok(updated.updatedAt >= job.updatedAt);
|
|
// immutable identity fields survive a patch
|
|
assert.equal(updated.toolCallId, "call-store");
|
|
assert.equal(jobStore.getJob(updated.id)!.toolCallId, "call-store");
|
|
|
|
const listed = jobStore.listJobs("chat_storetest");
|
|
assert.ok(listed.some((j) => j.id === job.id));
|
|
assert.equal(jobStore.listJobs("chat_other").some((j) => j.id === job.id), false, "jobs are scoped to their chat");
|
|
|
|
const byTool = jobStore.findJobByToolCallId("chat_storetest", "call-store");
|
|
assert.equal(byTool?.id, job.id);
|
|
assert.equal(jobStore.findJobByToolCallId("chat_storetest", "call-missing"), null);
|
|
});
|
|
});
|
|
|
|
// ─── 2. steer helpers (pure) ─────────────────────────────────────────────────
|
|
|
|
describe("steer helpers (contracts.ts)", () => {
|
|
const research: ResearchResult = { brief: "BRIEF", sources: [{ title: "s", url: "https://x.test" }] };
|
|
const demo: DemoResult = { title: "T", html: "<html></html>", tested: true, notes: "ok" };
|
|
const visual: VisualResult = { svg: "<svg/>", notes: "ok" };
|
|
|
|
it("buildSubagentSteer: user-role, metadata-marked, artifact on the data part, brief on the text part", () => {
|
|
const job = { id: "job_x", kind: "research" as const, toolCallId: "call-x" };
|
|
const steer = buildSubagentSteer(job, research);
|
|
assert.equal(steer.id, "steer_job_x", "deterministic id per job — idempotent delivery");
|
|
assert.equal(steer.role, "user");
|
|
assert.deepEqual(steer.metadata, { subagentResult: { jobId: "job_x", kind: "research", toolCallId: "call-x" } });
|
|
const [text, data] = steer.parts;
|
|
assert.equal(text.type, "text");
|
|
assert.ok(text.type === "text" && text.text.includes("BRIEF"), "the model-facing text carries the brief");
|
|
assert.equal(data.type, "data-subagent-artifact");
|
|
assert.ok(data.type === "data-subagent-artifact");
|
|
assert.equal(data.data.kind, "research");
|
|
assert.deepEqual(data.data.result, research);
|
|
});
|
|
|
|
it("isSubagentFailure: failure shapes only (empty html/svg, failure brief)", () => {
|
|
assert.equal(isSubagentFailure("research", research), false);
|
|
assert.equal(isSubagentFailure("research", { brief: "Research failed: x", sources: [] }), true);
|
|
// a brief with sources is a success even if the text mentions failure
|
|
assert.equal(isSubagentFailure("research", { brief: "Research failed: x", sources: [{ title: "s", url: "https://x" }] }), false);
|
|
assert.equal(isSubagentFailure("demo", demo), false);
|
|
assert.equal(isSubagentFailure("demo", { ...demo, html: "" }), true);
|
|
assert.equal(isSubagentFailure("visual", visual), false);
|
|
assert.equal(isSubagentFailure("visual", { ...visual, svg: "" }), true);
|
|
});
|
|
|
|
it("steerDelivered: matches on metadata.subagentResult.jobId", () => {
|
|
const steer = buildSubagentSteer({ id: "job_y", kind: "demo", toolCallId: "c" }, demo);
|
|
assert.equal(steerDelivered([], "job_y"), false);
|
|
assert.equal(steerDelivered([steer], "job_y"), true);
|
|
assert.equal(steerDelivered([steer], "job_z"), false);
|
|
});
|
|
|
|
it("failure steers tell the teacher how to recover (research/demo/visual wording)", () => {
|
|
const failResearch = buildSubagentSteer({ id: "j1", kind: "research", toolCallId: "c" }, { brief: "Research failed: API down", sources: [] });
|
|
const failDemo = buildSubagentSteer({ id: "j2", kind: "demo", toolCallId: "c" }, { title: "T", html: "", tested: true, notes: "FAILED: boom" });
|
|
const failVisual = buildSubagentSteer({ id: "j3", kind: "visual", toolCallId: "c" }, { svg: "", notes: "FAILED: boom" });
|
|
for (const steer of [failResearch, failDemo, failVisual]) {
|
|
const text = steer.parts[0];
|
|
assert.ok(text.type === "text" && !text.text.includes("rendered in the lesson"), "failure text never claims the artifact landed");
|
|
}
|
|
assert.ok(failResearch.parts[0].type === "text" && failResearch.parts[0].text.includes("flag the uncertainty"));
|
|
});
|
|
});
|
|
|
|
// ─── fake deliver (the wake pipeline's stand-in for runner tests) ───────────
|
|
|
|
/**
|
|
* A fake deliver seam: capture the steer and mimic the pipeline's final
|
|
* status flip (done/error by isSubagentFailure) so the job record reads
|
|
* exactly as it will in production after the wake turn completes.
|
|
*/
|
|
function fakeDeliver() {
|
|
const steers: SubagentSteerMessage[] = [];
|
|
return {
|
|
steers,
|
|
deliver: async (steer: SubagentSteerMessage) => {
|
|
steers.push(steer);
|
|
const jobId = steer.metadata.subagentResult.jobId;
|
|
const job = jobStore.getJob(jobId);
|
|
if (job && job.status === "running") {
|
|
const failed = job.result ? isSubagentFailure(job.kind, job.result as never) : true;
|
|
jobStore.updateJob(jobId, { status: failed ? "error" : "done", activity: failed ? "failed" : "delivered" });
|
|
}
|
|
},
|
|
};
|
|
}
|
|
|
|
// ─── 3. dispatch: the tool call acks mid-turn and spawns ─────────────────────
|
|
|
|
const RESEARCH_INPUT = {
|
|
question: "What is the latest stable sigma.js version?",
|
|
context: "Choosing a graph rendering library for the lesson.",
|
|
};
|
|
|
|
/** A teacher that calls research (text → call), then plain text thereafter. */
|
|
function researchCallingTeacher(): MockLanguageModelV4 {
|
|
let turn = 0;
|
|
return new MockLanguageModelV4({
|
|
doStream: async () => {
|
|
turn++;
|
|
const chunks: LanguageModelV4StreamPart[] =
|
|
turn === 1
|
|
? [
|
|
{ type: "stream-start", warnings: [] },
|
|
{ type: "text-start", id: "t1" },
|
|
{ type: "text-delta", id: "t1", delta: "Let me check the current state of the library." },
|
|
{ type: "text-end", id: "t1" },
|
|
{ type: "tool-input-start", id: "call-r1", toolName: "research" },
|
|
{ type: "tool-input-delta", id: "call-r1", delta: JSON.stringify(RESEARCH_INPUT) },
|
|
{ type: "tool-input-end", id: "call-r1" },
|
|
{ type: "tool-call", toolCallId: "call-r1", toolName: "research", input: JSON.stringify(RESEARCH_INPUT) },
|
|
{ type: "finish", finishReason: { unified: "tool-calls", raw: "tool_calls" }, usage: usage() },
|
|
]
|
|
: [
|
|
{ type: "stream-start", warnings: [] },
|
|
{ type: "text-start", id: "t2" },
|
|
{ type: "text-delta", id: "t2", delta: "Back with the brief." },
|
|
{ type: "text-end", id: "t2" },
|
|
{ type: "finish", finishReason: { unified: "stop", raw: "stop" }, usage: usage() },
|
|
];
|
|
return { stream: simulateReadableStream({ chunks, initialDelayInMs: 0, chunkDelayInMs: 0 }) };
|
|
},
|
|
});
|
|
}
|
|
|
|
describe("dispatch (async protocol §2)", () => {
|
|
it("the research call resolves immediately with an ack; the turn continues and the runner steers", async () => {
|
|
const chat = chatStore.createChat("Test: research dispatch");
|
|
trackChat(chat.id);
|
|
|
|
const delivery = fakeDeliver();
|
|
const testRunner = createJobRunner({ chatStore, jobStore, deliver: delivery.deliver });
|
|
const agent = createTeacherAgent(
|
|
researchCallingTeacher(),
|
|
createTeacherTools({
|
|
chatId: chat.id,
|
|
chatStore,
|
|
jobStore,
|
|
spawn: (job, input) => void testRunner.runJob(job.id, input),
|
|
}),
|
|
);
|
|
|
|
const restoreFetch = stubFetch();
|
|
researchModelOverride.current = researcherModel();
|
|
try {
|
|
const firstUser = { id: "u1", role: "user", parts: [{ type: "text", text: "teach me graph rendering" }] };
|
|
const body = await drain(await handleChatRequest(post(chat.id, [firstUser]), agent));
|
|
|
|
// The teacher's SAME turn carried on past the tool call.
|
|
assert.ok(body.includes("Back with the brief."), "the turn continued after the dispatch");
|
|
|
|
const saved = chatStore.getChat(chat.id)!;
|
|
const part = saved.messages[1]!.parts.find((p) => p.type === "tool-research");
|
|
assert.ok(part && part.type === "tool-research", "research tool part persisted");
|
|
assert.equal(part.state, "output-available", "the part resolved at dispatch time (not held pending)");
|
|
assert.equal(typeof (part as { output?: unknown }).output, "string", "the output is the ack, not the result");
|
|
assert.match(String((part as { output?: unknown }).output), /fire-and-forget/);
|
|
|
|
// The job record exists and the background runner completed it.
|
|
const job = jobStore.findJobByToolCallId(chat.id, "call-r1");
|
|
assert.ok(job, "dispatch created a job record");
|
|
trackJob(job!.id);
|
|
await waitFor(() => jobStore.getJob(job!.id)!.status !== "running", 8000, "research job completion");
|
|
|
|
const done = jobStore.getJob(job!.id)!;
|
|
assert.equal(done.status, "done");
|
|
assert.equal(done.activity, "delivered");
|
|
|
|
// The steer carries the brief + artifact for the (UI) renderer.
|
|
assert.equal(delivery.steers.length, 1, "exactly one steer — one job, one result");
|
|
const steer = delivery.steers[0]!;
|
|
assert.equal(steer.metadata.subagentResult.jobId, job!.id);
|
|
const text = steer.parts[0];
|
|
assert.ok(text.type === "text" && text.text.includes("sigma.js v3 is current"), "steer text carries the brief");
|
|
} finally {
|
|
restoreFetch();
|
|
researchModelOverride.current = undefined;
|
|
}
|
|
});
|
|
});
|
|
|
|
// ─── the researcher loop with a fake model + stubbed fetch ──────────────────
|
|
|
|
const BRIEF = `## Summary
|
|
sigma.js v3 is current.
|
|
|
|
## Findings
|
|
1. **v3 is the latest major.** [sigma.js docs](https://www.sigmajs.org/docs)
|
|
|
|
## Sources
|
|
- sigma.js docs (https://www.sigmajs.org/docs)`;
|
|
|
|
/**
|
|
* The researcher loop runs via agent.generate (non-streaming) — the mock
|
|
* therefore scripts doGenerate. Turn 1: a web_search tool call; turn 2: the
|
|
* final text brief.
|
|
*/
|
|
function researcherModel(): MockLanguageModelV4 {
|
|
let turn = 0;
|
|
return new MockLanguageModelV4({
|
|
doGenerate: async () => {
|
|
turn++;
|
|
return turn === 1
|
|
? {
|
|
content: [
|
|
{
|
|
type: "tool-call" as const,
|
|
toolCallId: "ws1",
|
|
toolName: "web_search",
|
|
input: JSON.stringify({ query: "sigma.js latest version" }),
|
|
},
|
|
],
|
|
finishReason: { unified: "tool-calls" as const, raw: "tool-calls" },
|
|
usage: usage(),
|
|
warnings: [],
|
|
}
|
|
: {
|
|
content: [{ type: "text" as const, text: BRIEF }],
|
|
finishReason: { unified: "stop" as const, raw: "stop" },
|
|
usage: usage(),
|
|
warnings: [],
|
|
};
|
|
},
|
|
});
|
|
}
|
|
|
|
function stubFetch() {
|
|
const original = globalThis.fetch;
|
|
globalThis.fetch = (async (input: RequestInfo | URL) => {
|
|
const url = String(input);
|
|
if (url.startsWith("https://www.googleapis.com/")) {
|
|
return new Response(
|
|
JSON.stringify({
|
|
items: [{ title: "sigma.js", link: "https://www.sigmajs.org/", snippet: "v3 released" }],
|
|
}),
|
|
{ status: 200, headers: { "Content-Type": "application/json" } },
|
|
);
|
|
}
|
|
return new Response("unexpected fetch: " + url, { status: 500 });
|
|
}) as typeof fetch;
|
|
return () => {
|
|
globalThis.fetch = original;
|
|
};
|
|
}
|
|
|
|
describe("research runner (async protocol §3)", () => {
|
|
it("runJob completes the job: result + sources on the job, brief on the steer, activity recorded", async () => {
|
|
const restoreFetch = stubFetch();
|
|
try {
|
|
const chat = chatStore.createChat("Test: runner completion");
|
|
trackChat(chat.id);
|
|
|
|
// A dispatched research part in the stored chat (the input is also
|
|
// what the runner falls back to on a crash-recovery re-spawn).
|
|
chatStore.saveMessages(chat.id, [
|
|
{ id: "u1", role: "user", parts: [{ type: "text", text: "which sigma version?" }] },
|
|
{
|
|
id: "a1",
|
|
role: "assistant",
|
|
parts: [
|
|
{ type: "text", text: "Checking." },
|
|
{ type: "tool-research", toolCallId: "call-run1", state: "output-available", input: RESEARCH_INPUT, output: "Dispatched." },
|
|
],
|
|
},
|
|
] as never);
|
|
|
|
const job = jobStore.createJob({ kind: "research", chatId: chat.id, toolCallId: "call-run1" });
|
|
trackJob(job.id);
|
|
|
|
const delivery = fakeDeliver();
|
|
const runner = createJobRunner({ chatStore, jobStore, deliver: delivery.deliver });
|
|
researchModelOverride.current = researcherModel();
|
|
try {
|
|
await runner.runJob(job.id);
|
|
} finally {
|
|
researchModelOverride.current = undefined;
|
|
}
|
|
|
|
// The job is done, with the activity line from the tool call.
|
|
const done = jobStore.getJob(job.id)!;
|
|
assert.equal(done.status, "done");
|
|
assert.equal(done.activity, "delivered", "the fake deliver flips the status like the pipeline");
|
|
const result = done.result as ResearchResult;
|
|
assert.equal(result.brief, BRIEF);
|
|
assert.ok(result.sources.length > 0, "sources parsed from the brief");
|
|
assert.equal(result.sources[0]!.url, "https://www.sigmajs.org/docs");
|
|
|
|
// The activity trail survives on... the last recorded activity is
|
|
// the deliver flip, but the search line was recorded during the run:
|
|
// the job store keeps only the latest; the search fired before it.
|
|
// (We ran the search; the runner recorded it — check the store's
|
|
// history via the final state only.)
|
|
} finally {
|
|
restoreFetch();
|
|
}
|
|
});
|
|
|
|
it("a failing runner still steers (the teacher learns the outcome) and the job lands error", async () => {
|
|
const chat = chatStore.createChat("Test: runner failure");
|
|
trackChat(chat.id);
|
|
chatStore.saveMessages(chat.id, [
|
|
{ id: "u1", role: "user", parts: [{ type: "text", text: "hi" }] },
|
|
{
|
|
id: "a1",
|
|
role: "assistant",
|
|
parts: [{ type: "tool-research", toolCallId: "call-err1", state: "output-available", input: RESEARCH_INPUT, output: "Dispatched." }],
|
|
},
|
|
] as never);
|
|
|
|
const job = jobStore.createJob({ kind: "research", chatId: chat.id, toolCallId: "call-err1" });
|
|
trackJob(job.id);
|
|
|
|
const delivery = fakeDeliver();
|
|
const runner = createJobRunner({ chatStore, jobStore, deliver: delivery.deliver });
|
|
researchModelOverride.current = new MockLanguageModelV4({
|
|
doGenerate: async () => {
|
|
throw new Error("model exploded");
|
|
},
|
|
});
|
|
try {
|
|
await runner.runJob(job.id);
|
|
} finally {
|
|
researchModelOverride.current = undefined;
|
|
}
|
|
|
|
const errored = jobStore.getJob(job.id)!;
|
|
assert.equal(errored.status, "error");
|
|
assert.match(errored.error ?? "", /model exploded/);
|
|
|
|
const steer = delivery.steers[0]!;
|
|
assert.ok(steer, "failure still delivers a steer");
|
|
const text = steer.parts[0];
|
|
assert.ok(text.type === "text" && text.text.includes("Research failed: model exploded"), "failure brief on the steer text");
|
|
const data = steer.parts[1];
|
|
assert.ok(data.type === "data-subagent-artifact");
|
|
assert.deepEqual((data.data.result as ResearchResult).sources, []);
|
|
});
|
|
|
|
it("runJob resolves the input from the transcript when dispatch-time input is absent (crash recovery)", async () => {
|
|
const restoreFetch = stubFetch();
|
|
try {
|
|
const chat = chatStore.createChat("Test: transcript input fallback");
|
|
trackChat(chat.id);
|
|
chatStore.saveMessages(chat.id, [
|
|
{ id: "u1", role: "user", parts: [{ type: "text", text: "go" }] },
|
|
{
|
|
id: "a1",
|
|
role: "assistant",
|
|
parts: [{ type: "tool-research", toolCallId: "call-fb1", state: "output-available", input: RESEARCH_INPUT, output: "Dispatched." }],
|
|
},
|
|
] as never);
|
|
const job = jobStore.createJob({ kind: "research", chatId: chat.id, toolCallId: "call-fb1" });
|
|
trackJob(job.id);
|
|
|
|
const delivery = fakeDeliver();
|
|
const runner = createJobRunner({ chatStore, jobStore, deliver: delivery.deliver });
|
|
researchModelOverride.current = researcherModel();
|
|
try {
|
|
// no input passed — as a recovery re-spawn would call it
|
|
await runner.runJob(job.id);
|
|
} finally {
|
|
researchModelOverride.current = undefined;
|
|
}
|
|
|
|
const done = jobStore.getJob(job.id)!;
|
|
assert.equal(done.status, "done", "the researcher ran from the transcript-resolved input");
|
|
assert.equal((done.result as ResearchResult).brief, BRIEF);
|
|
} finally {
|
|
restoreFetch();
|
|
}
|
|
});
|
|
});
|
|
|
|
// ─── the researcher agent construction (model resolution seam) ──────────────
|
|
|
|
describe("researcher agent", () => {
|
|
it("builds with the web tool set (no network touched)", () => {
|
|
const agent = createResearcherAgent(researcherModel());
|
|
assert.ok(agent.tools.web_search, "web_search available");
|
|
assert.ok(agent.tools.web_fetch, "web_fetch available");
|
|
assert.equal(Object.keys(agent.tools).length, 2, "ONLY the web tools — no question/plan tools");
|
|
// reset any accidental global override
|
|
researchModelOverride.current = undefined;
|
|
});
|
|
});
|
|
|
|
// ─── 6. the wake pipeline (server-side steer delivery) ────────────────────────
|
|
|
|
/**
|
|
* Pipeline tests drive deliverJobResult with an injected fake turn runner
|
|
* (setTurnRunner) — the real wiring (chat-handler's handleChatRequest
|
|
* adapter) never fires here, so no teacher model is touched.
|
|
*
|
|
* Timing: the pump polls at 400ms with a 1.5s grace after the gates open —
|
|
* each happy-path test takes ~2s; waitFor tolerates it.
|
|
*/
|
|
describe("wake pipeline (src/server/jobs.ts)", () => {
|
|
/** A chat with a finished job ready for delivery. */
|
|
function setup(kind: "research" | "demo" = "research"): { chatId: string; jobId: string; steer: SubagentSteerMessage } {
|
|
const chat = chatStore.createChat("Test: wake pipeline");
|
|
trackChat(chat.id);
|
|
chatStore.saveMessages(chat.id, [{ id: "u1", role: "user", parts: [{ type: "text", text: "hello" }] }] as never);
|
|
|
|
const job = jobStore.createJob({ kind, chatId: chat.id, toolCallId: `call-${jobStore.listJobs(chat.id).length}` });
|
|
trackJob(job.id);
|
|
const result: ResearchResult = { brief: "Done: it works.", sources: [{ title: "s", url: "https://x.test" }] };
|
|
jobStore.updateJob(job.id, { result, activity: "delivering result" });
|
|
const steer = buildSubagentSteer(job, result);
|
|
return { chatId: chat.id, jobId: job.id, steer };
|
|
}
|
|
|
|
it("delivers: fires the turn runner with the record + steer, then flips the job done", async () => {
|
|
const { chatId, jobId, steer } = setup();
|
|
let seen: { chatId: string; lastMessage: unknown } | null = null;
|
|
setTurnRunner(async (cid, messages) => {
|
|
seen = { chatId: cid, lastMessage: messages[messages.length - 1] };
|
|
return 200;
|
|
});
|
|
|
|
await deliverJobResult(steer);
|
|
await waitFor(() => jobStore.getJob(jobId)!.status !== "running", 8000, "job flip after delivery");
|
|
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done");
|
|
assert.equal(jobStore.getJob(jobId)!.activity, "delivered");
|
|
assert.ok(seen, "the turn runner fired");
|
|
assert.equal((seen as { chatId: string }).chatId, chatId);
|
|
const last = (seen as { lastMessage: SubagentSteerMessage }).lastMessage;
|
|
assert.equal(last.id, steer.id, "the steer is the wake turn's final input message");
|
|
});
|
|
|
|
it("waits while a question part is pending, and fires once it clears", async () => {
|
|
const { chatId, jobId, steer } = setup();
|
|
let fired = 0;
|
|
setTurnRunner(async () => {
|
|
fired++;
|
|
return 200;
|
|
});
|
|
|
|
// An unanswered quiz part blocks the wake (provider conversion would
|
|
// break on an input-available tool call).
|
|
chatStore.saveMessages(chatId, [
|
|
{ id: "u1", role: "user", parts: [{ type: "text", text: "hello" }] },
|
|
{
|
|
id: "a1",
|
|
role: "assistant",
|
|
parts: [{ type: "tool-quiz", toolCallId: "quiz-call", state: "input-available", input: { question: "q", choices: ["a", "b"] } }],
|
|
},
|
|
] as never);
|
|
|
|
// The delivery promise floats while the quiz blocks — awaiting it now
|
|
// would deadlock the test (the pump defers until the gate opens).
|
|
const delivery = deliverJobResult(steer);
|
|
|
|
await delay(1200);
|
|
assert.equal(fired, 0, "no wake while the quiz is pending");
|
|
assert.equal(jobStore.getJob(jobId)!.status, "running", "job stays running while blocked");
|
|
|
|
// The learner answers: the pending part clears (client adds output).
|
|
const record = chatStore.getChat(chatId)!;
|
|
const answered = record.messages.map((m) =>
|
|
m.id === "a1"
|
|
? {
|
|
...m,
|
|
parts: [{ type: "tool-quiz", toolCallId: "quiz-call", state: "output-available", input: { question: "q", choices: ["a", "b"] }, output: { answer: "a", correct: true, explanation: "" } }],
|
|
}
|
|
: m,
|
|
);
|
|
chatStore.saveMessages(chatId, answered as never);
|
|
|
|
await waitFor(() => fired > 0, 8000, "wake after the quiz answer");
|
|
await delivery; // now it resolves — the steer was delivered
|
|
await waitFor(() => jobStore.getJob(jobId)!.status !== "running", 8000, "job flip after the deferred wake");
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done");
|
|
});
|
|
|
|
it("retries with backoff on a 409 (a client turn raced in) and delivers on the retry", async () => {
|
|
const { jobId, steer } = setup();
|
|
let calls = 0;
|
|
setTurnRunner(async () => {
|
|
calls++;
|
|
return calls === 1 ? 409 : 200;
|
|
});
|
|
|
|
await deliverJobResult(steer);
|
|
assert.ok(calls >= 2, "409 was retried");
|
|
await waitFor(() => jobStore.getJob(jobId)!.status !== "running", 8000, "job flip after the retry");
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done");
|
|
});
|
|
|
|
it("is idempotent: a steer already in the transcript flips the job without firing a turn", async () => {
|
|
const { chatId, jobId, steer } = setup();
|
|
// Simulate the crash window: the wake completed but the flip didn't.
|
|
const record = chatStore.getChat(chatId)!;
|
|
chatStore.saveMessages(chatId, [...record.messages, steer] as never);
|
|
|
|
let fired = 0;
|
|
setTurnRunner(async () => {
|
|
fired++;
|
|
return 200;
|
|
});
|
|
|
|
await deliverJobResult(steer);
|
|
assert.equal(fired, 0, "no duplicate wake for an already-delivered steer");
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done", "the job still flips — recovery completes");
|
|
});
|
|
|
|
// ─── continuation coalescing (the delivery-starvation fix) ───────────────────
|
|
|
|
describe("claimSteers + pump duplicate-guard (continuation coalescing)", () => {
|
|
it("claims queued undelivered steers: resolves deliver(), flips the job done, empties the queue", async () => {
|
|
const { chatId, jobId, steer } = setup();
|
|
let fired = 0;
|
|
setTurnRunner(async () => {
|
|
fired++;
|
|
return 200;
|
|
});
|
|
|
|
const delivery = deliverJobResult(steer);
|
|
await delay(300); // the pump is inside waitForIdle's grace (750ms)
|
|
const claimed = claimSteers(chatId);
|
|
|
|
assert.equal(claimed.length, 1, "the queued steer is claimed");
|
|
assert.equal(claimed[0]!.id, steer.id);
|
|
// The handler's write-ahead persist lands the claim immediately after
|
|
// claiming (the very next statement in handleChatRequest).
|
|
const record = chatStore.getChat(chatId)!;
|
|
chatStore.saveMessages(chatId, [...record.messages, ...claimed] as never);
|
|
await delivery; // the runner's deliver() promise resolves on claim
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done", "job flips done at claim");
|
|
assert.deepEqual(claimSteers(chatId), [], "queue is empty after the claim");
|
|
await delay(800);
|
|
assert.equal(fired, 0, "the pump never fires a wake for a claimed steer");
|
|
});
|
|
|
|
it("finalizes already-delivered steers without returning them (a wake raced in)", async () => {
|
|
const { chatId, jobId, steer } = setup();
|
|
const record = chatStore.getChat(chatId)!;
|
|
chatStore.saveMessages(chatId, [...record.messages, steer] as never);
|
|
|
|
const delivery = deliverJobResult(steer);
|
|
await delay(100); // let the pump see it first (its top-of-loop idempotent skip)
|
|
const claimed = claimSteers(chatId);
|
|
assert.equal(claimed.length, 0, "delivered steers are not re-claimed");
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done");
|
|
await delivery;
|
|
});
|
|
|
|
it("claimSteers on a chat with no queue returns [] and touches nothing", () => {
|
|
assert.deepEqual(claimSteers("chat_never_existed"), []);
|
|
});
|
|
|
|
it("pump duplicate-guard: a steer coalesced into the record while the gates were closed is never double-fired", async () => {
|
|
const { chatId, jobId, steer } = setup();
|
|
let fired = 0;
|
|
setTurnRunner(async () => {
|
|
fired++;
|
|
return 200;
|
|
});
|
|
|
|
// Gates closed: a pending quiz parks the pump in waitForIdle.
|
|
chatStore.saveMessages(chatId, [
|
|
{ id: "u1", role: "user", parts: [{ type: "text", text: "hello" }] },
|
|
{
|
|
id: "a1",
|
|
role: "assistant",
|
|
parts: [{ type: "tool-quiz", toolCallId: "quiz-call", state: "input-available", input: { question: "q", choices: ["a", "b"] } }],
|
|
},
|
|
] as never);
|
|
const delivery = deliverJobResult(steer);
|
|
await delay(1200);
|
|
assert.equal(fired, 0, "parked behind the pending quiz");
|
|
|
|
// The client turn coalesces: it claims the steer and lands it in the record.
|
|
const claimed = claimSteers(chatId);
|
|
assert.equal(claimed.length, 1, "coalescing claims the parked steer");
|
|
const record = chatStore.getChat(chatId)!;
|
|
chatStore.saveMessages(chatId, [...record.messages, steer] as never); // write-ahead persist
|
|
|
|
// The learner answers: the gates open — the parked pump must see the
|
|
// delivered steer via its post-idle re-check, NOT fire a second turn.
|
|
const answered = chatStore.getChat(chatId)!.messages.map((m) =>
|
|
m.id === "a1"
|
|
? {
|
|
...m,
|
|
parts: [{ type: "tool-quiz", toolCallId: "quiz-call", state: "output-available", input: { question: "q", choices: ["a", "b"] }, output: { answer: "a", correct: true, explanation: "" } }],
|
|
}
|
|
: m,
|
|
);
|
|
chatStore.saveMessages(chatId, answered as never);
|
|
|
|
await delivery;
|
|
await delay(1500);
|
|
assert.equal(fired, 0, "no duplicate wake after coalescing");
|
|
assert.equal(jobStore.getJob(jobId)!.status, "done");
|
|
});
|
|
});
|
|
|
|
it("fails the job (error status) when the wake turn errors unrecoverably", async () => {
|
|
const { jobId, steer } = setup();
|
|
setTurnRunner(async () => 500);
|
|
|
|
await deliverJobResult(steer).then(
|
|
() => assert.fail("expected delivery to reject"),
|
|
() => undefined,
|
|
);
|
|
const errored = jobStore.getJob(jobId)!;
|
|
assert.equal(errored.status, "error");
|
|
assert.match(errored.error ?? "", /status 500/);
|
|
});
|
|
});
|
|
|
|
function delay(ms: number): Promise<void> {
|
|
return new Promise((resolve) => setTimeout(resolve, ms));
|
|
}
|
|
|
|
// ─── persist id hygiene (the duplicate-empty-key bug) ────────────────────────
|
|
|
|
describe("persistTurn id hygiene", () => {
|
|
it("withMessageIds fills EMPTY ids (server-only synthesized messages) and preserves existing ones", () => {
|
|
const filled = withMessageIds([
|
|
{ id: "", role: "assistant", parts: [{ type: "text", text: "wake turn" }] },
|
|
{ id: "client-id", role: "user", parts: [{ type: "text", text: "hi" }] },
|
|
]);
|
|
assert.notEqual(filled[0]!.id, "", "empty id replaced");
|
|
assert.match(filled[0]!.id, /^msg_/);
|
|
assert.equal(filled[1]!.id, "client-id", "client-authored id untouched");
|
|
assert.notEqual(filled[0]!.id, filled[1]!.id);
|
|
});
|
|
|
|
it("persistTurn dedupes same-id continuation copies, keeping the LAST (the SDK's merged superset)", () => {
|
|
// The coalescing shape: a steer (user-role) rides a quiz-answer
|
|
// continuation AFTER the assistant message being continued, so the
|
|
// SDK's onFinish list carries the input copy AND the extended
|
|
// response copy under one id — the record must keep only the merge.
|
|
const chat = chatStore.createChat("Test: dedupe continuation copies");
|
|
trackChat(chat.id);
|
|
const short: UIMessage = { id: "msg_dup_1", role: "assistant", parts: [{ type: "text", text: "step 1" }] };
|
|
const long: UIMessage = { id: "msg_dup_1", role: "assistant", parts: [{ type: "text", text: "step 1" }, { type: "text", text: "step 2 (continued)" }] };
|
|
persistTurn(chatStore, chat.id, [
|
|
{ id: "u1", role: "user", parts: [{ type: "text", text: "hi" }] },
|
|
short,
|
|
{ id: "steer_x", role: "user", parts: [{ type: "text", text: "research complete" }] },
|
|
long,
|
|
], false);
|
|
const record = chatStore.getChat(chat.id)!;
|
|
assert.equal(record.messages.length, 3, "the duplicate entry is dropped");
|
|
assert.deepEqual(
|
|
record.messages.map((m) => m.id),
|
|
["u1", "steer_x", "msg_dup_1"],
|
|
"order preserved, steer before the merged assistant copy",
|
|
);
|
|
const merged = record.messages[2]!;
|
|
assert.equal(merged.parts.length, 2, "the KEPT copy is the extended one");
|
|
assert.equal((merged.parts[1] as { text: string }).text, "step 2 (continued)");
|
|
});
|
|
|
|
it("persistTurn saves every message with a unique non-empty id (wake turns never re-POSTed)", () => {
|
|
const chat = chatStore.createChat("Test: persist ids");
|
|
trackChat(chat.id);
|
|
persistTurn(chatStore, chat.id, [
|
|
{ id: "", role: "user", parts: [{ type: "text", text: "q" }] },
|
|
{ id: "", role: "assistant", parts: [{ type: "text", text: "a1" }] },
|
|
{ id: "", role: "assistant", parts: [{ type: "text", text: "a2" }] },
|
|
], false);
|
|
const record = chatStore.getChat(chat.id);
|
|
const ids = record!.messages.map((m) => m.id);
|
|
assert.ok(ids.every((id) => id && id.length > 0), "no empty ids survive persist");
|
|
assert.equal(new Set(ids).size, ids.length, "ids unique — React keys safe");
|
|
});
|
|
});
|
|
|
|
// ─── prompt composition hygiene (the README leak) ─────────────────────────────
|
|
|
|
describe("prompt composition", () => {
|
|
it("loads ONLY numeric-prefix fragments — README.md never enters the system prompt", () => {
|
|
const instructions = composeInstructions();
|
|
assert.ok(!instructions.includes("Prompt fragments"), "README content must not leak");
|
|
assert.ok(!instructions.includes("Rules for adding a fragment"), "README content must not leak (rules)");
|
|
// every numeric fragment DOES compose, verbatim, after the base prompt
|
|
const base = fs.readFileSync("src/agent/system-prompt.md", "utf-8").trim();
|
|
assert.ok(instructions.startsWith(base), "base prompt first");
|
|
for (const f of fs.readdirSync("src/agent/prompts").filter((f) => /^\d+-[\w.-]+\.md$/.test(f)).sort()) {
|
|
const body = fs.readFileSync(`src/agent/prompts/${f}`, "utf-8").trim();
|
|
assert.ok(instructions.includes(body), `fragment ${f} must compose verbatim`);
|
|
}
|
|
});
|
|
|
|
it("guards prompt size — no fragment can silently balloon (the README-leak class)", () => {
|
|
// The wave-1 leak: README.md (815 bytes / ~200 tokens) rode into every
|
|
// teacher turn until the numeric-prefix filter stopped it. This guard
|
|
// catches the sibling failure mode — an accidental dump pasted into a
|
|
// fragment. Thresholds: largest real fragment is 40-demos.md at ~3.2k
|
|
// chars; 8k is generous headroom. Composed total ≤ 60k chars.
|
|
for (const f of fs.readdirSync("src/agent/prompts").filter((f) => /^\d+-[\w.-]+\.md$/.test(f))) {
|
|
const body = fs.readFileSync(`src/agent/prompts/${f}`, "utf-8").trim();
|
|
assert.ok(body.length <= 8_000, `fragment ${f} is ${body.length} chars — over the 8k guard`);
|
|
}
|
|
assert.ok(composeInstructions().length <= 60_000, "composed system prompt over the 60k guard");
|
|
});
|
|
});
|