v3: AI SDK pivot — pi removed, Next.js 16 + AI SDK 7 + AI Elements teacher app

The teaching agent no longer runs on pi. Stack:
- ToolLoopAgent (ai@7) + OpenRouter (OPENROUTER_API_KEY), model via LH_MODEL,
  default anthropic/claude-sonnet-4.5 with reasoning tokens
- quiz/ask_user_question = client-side tools (no server execute): the call
  lands as a typed tool part in input-available state; the card grades via
  src/core/question-core.ts; addToolOutput sends the verdict; the teacher's
  reaction continues the same assistant message
- resume-mid-quiz is free: the pending tool part persists in the transcript
- persistence: one JSON per chat (data/chats/), full UIMessage transcripts,
  saved onFinish (also on abort)
- UI: AI Elements (owned copy-paste components, pruned to the five in use)
  + button-based QuizCard/AnsweredCard (ask answers never graded)
- pi fully removed: TUI, extensions, Fastify+WS server, bridge, custom
  protocol all deleted (recoverable from git history)
- tests: question-core units carry over; chat-flow integration drives
  handleChatRequest with MockLanguageModelV4 (48 tests, zero tokens);
  render smoke tests guard the cards (renderToStaticMarkup)

Carried over unchanged: teacher system prompt, question-core, schema/
ledger/derive/extract pipeline, data model.
This commit is contained in:
Amos
2026-08-22 02:18:27 +03:00
parent e127a9bfbd
commit a72c902d30
81 changed files with 9643 additions and 10860 deletions
-484
View File
@@ -1,484 +0,0 @@
/**
* web server — Fastify + WebSocket server embedding the teacher agent via the
* pi SDK (web dispatch mode: quiz/ask return immediately, answers arrive as
* user messages — nothing blocks, so sessions can be exited/resumed mid-question).
*
* Delivery model (the part that must never double-send or drop):
* - ONE append-only entry log per active session (`entryLog`), plus a cursor
* (`syncedCount`) into the session manager's entries.
* - Every entry enters the log exactly once — either at activation (seeded
* from history, no broadcast) or live via syncEntries (broadcast to all
* connected sockets).
* - A socket connecting at ANY time receives the whole log as backfill.
* There is no per-socket marking and no window in which an entry can be
* both backfilled and broadcast — the duplication race from v1 is
* structurally impossible now.
*
* - Streaming: thinking and text deltas are forwarded as they happen;
* ephemeral (a socket that connects mid-turn gets `streaming: true` in its
* snapshot and the entries when they land).
*
* v1 scope: one active session at a time; extraction pipeline NOT wired yet.
*/
import fs from "node:fs";
import path from "node:path";
import Fastify from "fastify";
import fastifyWebsocket from "@fastify/websocket";
import fastifyStatic from "@fastify/static";
import {
type AgentSessionEvent,
type AgentSessionRuntimeDiagnostic,
createAgentSessionRuntime,
SessionManager,
} from "@earendil-works/pi-coding-agent";
import { PATHS } from "../../config.ts";
import { buildTeacherRuntimeFactory } from "../teacher/create-session.ts";
import {
QUESTION_ANSWERED_ENTRY,
QUESTION_ENTRY,
findPendingQuestion,
type QuestionAnswerData,
type QuestionData,
toClientQuestion,
} from "../../extensions/core/question-core.ts";
import { getBridge } from "../../extensions/core/bridge.ts";
import type { ClientEntry, ServerMessage, SessionSummary } from "../shared/protocol.ts";
/** What the server needs from a teacher runtime (real or scripted). */
export interface RuntimeLike {
session: {
subscribe(listener: (evt: AgentSessionEvent) => void): () => void;
dispose(): void;
isStreaming: boolean;
prompt(text: string): Promise<void>;
abort(): unknown;
setSessionName(name: string): unknown;
sessionManager: SessionManager;
};
diagnostics: readonly AgentSessionRuntimeDiagnostic[];
}
export type RuntimeFactory = (options: {
cwd: string;
agentDir: string;
sessionManager: SessionManager;
}) => Promise<RuntimeLike>;
export interface ServerOptions {
/** TCP port; 0 = pick a free port (tests). Default: LH_PORT or 8787. */
port?: number;
/** Teacher runtime factory — inject a scripted one in tests. */
runtimeFactory?: RuntimeFactory;
}
const defaultRuntimeFactory: RuntimeFactory = (options) =>
createAgentSessionRuntime(buildTeacherRuntimeFactory("web"), options) as unknown as Promise<RuntimeLike>;
// ─── entry serialization ────────────────────────────────────────────────────
function extractText(content: unknown[]): string {
return content
.filter((c): c is { type: "text"; text: string } => (c as { type?: string }).type === "text")
.map((c) => c.text)
.join("");
}
function extractThinking(content: unknown[]): string {
return content
.filter(
(c): c is { type: "thinking"; thinking: string } => (c as { type?: string }).type === "thinking",
)
.map((c) => c.thinking)
.join("\n");
}
function serializeEntry(entry: {
type: string;
id: string;
customType?: string;
data?: unknown;
// eslint-disable-next-line @typescript-eslint/no-explicit-any
message?: any;
}): ClientEntry | null {
if (entry.type === "message" && entry.message) {
const m = entry.message;
if (m.role === "user") {
return { type: "user", id: entry.id, text: extractText(m.content ?? []) };
}
if (m.role === "assistant") {
const toolCalls = ((m.content ?? []) as unknown[])
.filter(
(c): c is { type: "toolCall"; name: string; arguments?: unknown } =>
(c as { type?: string }).type === "toolCall",
)
.map((c) => ({ name: c.name, args: (c.arguments ?? {}) as Record<string, unknown> }));
const thinking = extractThinking(m.content ?? []);
return {
type: "assistant",
id: entry.id,
text: extractText(m.content ?? []),
thinking: thinking || undefined,
toolCalls,
};
}
if (m.role === "toolResult") {
return { type: "toolResult", id: entry.id, toolName: m.toolName ?? "", text: extractText(m.content ?? []) };
}
return null;
}
if (entry.type === "custom" && entry.customType === QUESTION_ENTRY) {
const data = entry.data as QuestionData | undefined;
if (!data) return null;
return { type: "question", id: entry.id, data: toClientQuestion(data) };
}
if (entry.type === "custom" && entry.customType === QUESTION_ANSWERED_ENTRY) {
const data = entry.data as QuestionAnswerData | undefined;
if (!data) return null;
return { type: "questionAnswered", id: entry.id, data };
}
return { type: "meta", id: entry.id, kind: entry.type };
}
// ─── session listing (reads data/sessions/*.jsonl) ──────────────────────────
function listSessions(): SessionSummary[] {
const dir = PATHS.sessions;
const files = fs.existsSync(dir) ? fs.readdirSync(dir).filter((f) => f.endsWith(".jsonl")) : [];
const summaries: SessionSummary[] = [];
for (const file of files) {
try {
const lines = fs.readFileSync(path.join(dir, file), "utf8").split("\n").filter(Boolean);
if (lines.length === 0) continue;
const header = JSON.parse(lines[0] ?? "") as { id?: string; timestamp?: string };
const id = header.id;
if (!id) continue;
let name: string | undefined;
let preview: string | undefined;
let updatedAt = header.timestamp ?? "";
let messageCount = 0;
for (const line of lines.slice(1)) {
let entry: { type?: string; message?: { role?: string; content?: unknown[] }; timestamp?: string; name?: string };
try {
entry = JSON.parse(line);
} catch {
continue;
}
if (entry.timestamp) updatedAt = entry.timestamp;
if (entry.type === "session_info" && entry.name) name = entry.name;
if (entry.type === "message" && entry.message?.role === "user") {
messageCount++;
if (!preview) preview = extractText(entry.message.content ?? []).slice(0, 120);
}
}
summaries.push({
id,
file,
name,
createdAt: header.timestamp ?? "",
updatedAt,
messageCount,
preview,
});
} catch {
// unreadable session file — skip
}
}
summaries.sort((a, b) => b.updatedAt.localeCompare(a.updatedAt));
return summaries;
}
// ─── server ─────────────────────────────────────────────────────────────────
export async function startServer(options: ServerOptions = {}): Promise<{
port: number;
close: () => Promise<void>;
}> {
const runtimeFactory = options.runtimeFactory ?? defaultRuntimeFactory;
// Active session state. `entryLog` is the single source of truth for what
// clients have been able to see; `syncedCount` is how many session entries
// it reflects. Both reset together on activation.
interface ActiveSession {
runtime: RuntimeLike;
sessionId: string;
file: string;
}
let active: ActiveSession | null = null;
let unsubscribeEvents: (() => void) | null = null;
let entryLog: ClientEntry[] = [];
let syncedCount = 0;
const sockets = new Set<WebSocket>();
function broadcast(msg: ServerMessage): void {
const raw = JSON.stringify(msg);
for (const ws of sockets) {
if (ws.readyState === ws.OPEN) ws.send(raw);
}
}
function broadcastPending(): void {
if (!active) return;
const pending = findPendingQuestion(active.runtime.session.sessionManager.getEntries());
broadcast({ type: "pending", question: pending });
}
/** Append every not-yet-logged session entry to the log (broadcasting each). */
function syncEntries(): void {
if (!active) return;
const entries = active.runtime.session.sessionManager.getEntries();
for (; syncedCount < entries.length; syncedCount++) {
const entry = entries[syncedCount]!;
const client = serializeEntry(entry as never);
if (client) {
entryLog.push(client);
broadcast({ type: "entry", entry: client });
}
if (
entry.type === "custom" &&
((entry as { customType?: string }).customType === QUESTION_ENTRY ||
(entry as { customType?: string }).customType === QUESTION_ANSWERED_ENTRY)
) {
broadcastPending();
}
}
}
function handleSessionEvent(evt: AgentSessionEvent): void {
if (!active) return;
switch (evt.type) {
case "message_update": {
const e = evt.assistantMessageEvent;
if (e?.type === "text_delta") {
broadcast({ type: "delta", kind: "text", delta: e.delta });
} else if (e?.type === "thinking_delta") {
broadcast({ type: "delta", kind: "thinking", delta: e.delta });
}
break;
}
case "agent_start":
broadcast({ type: "streaming", value: true });
break;
case "agent_settled":
broadcast({ type: "streaming", value: false });
break;
}
syncEntries();
}
async function activate(sessionManager: SessionManager): Promise<ActiveSession> {
if (unsubscribeEvents) {
unsubscribeEvents();
unsubscribeEvents = null;
}
if (active) {
active.runtime.session.dispose();
active = null;
}
const runtime = await runtimeFactory({
cwd: PATHS.root,
agentDir: PATHS.agentDir,
sessionManager,
});
for (const d of runtime.diagnostics) {
if (d.type === "error") console.error(`[teacher] ${d.message}`);
}
unsubscribeEvents = runtime.session.subscribe(handleSessionEvent);
const file = path.basename(sessionManager.getSessionFile() ?? "");
active = { runtime, sessionId: sessionManager.getSessionId(), file };
// Seed the log from history WITHOUT broadcasting: sockets that connect
// later get it via their connect-backfill; sockets already connected get
// it via the hello+backfill below. Either way, exactly once.
entryLog = sessionManager
.getEntries()
.map((e) => serializeEntry(e as never))
.filter((e): e is ClientEntry => e !== null);
syncedCount = sessionManager.getEntries().length;
broadcast({ type: "hello", sessionId: active.sessionId });
broadcast({ type: "backfill", entries: entryLog });
broadcastPending();
broadcast({ type: "streaming", value: runtime.session.isStreaming });
return active;
}
async function createSession(topic: string): Promise<ActiveSession> {
const sessionManager = SessionManager.create(PATHS.root, PATHS.sessions);
const result = await activate(sessionManager);
// Name the session after the topic (shown in the session list).
const name = topic.trim().slice(0, 60) || "New session";
result.runtime.session.setSessionName(name);
// Fire the first prompt (don't await — clients follow along via WS).
void result.runtime.session.prompt(topic).catch((err) => {
console.error("[teacher] prompt failed:", err);
broadcast({ type: "error", message: String(err) });
});
return result;
}
async function resumeSession(file: string): Promise<ActiveSession> {
const sessionManager = SessionManager.open(path.join(PATHS.sessions, file), PATHS.sessions, PATHS.root);
return activate(sessionManager);
}
// ─── HTTP ────────────────────────────────────────────────────────────────
const app = Fastify({ logger: false });
await app.register(fastifyWebsocket);
// Serve the built frontend (web/dist) when it exists.
const distDir = path.join(PATHS.root, "web", "dist");
if (fs.existsSync(distDir)) {
await app.register(fastifyStatic, { root: distDir });
app.setNotFoundHandler((req, reply) => {
if (req.url.startsWith("/api") || req.url.startsWith("/ws")) {
reply.code(404).send({ error: "not found" });
} else {
reply.sendFile("index.html");
}
});
}
app.get("/api/sessions", async () => ({
sessions: listSessions(),
activeId: active?.sessionId ?? null,
}));
app.post<{ Body: { topic?: string } }>("/api/sessions", async (req, reply) => {
const topic = (req.body?.topic ?? "").trim();
if (!topic) return reply.code(400).send({ error: "topic is required" });
const result = await createSession(topic);
return { id: result.sessionId, file: result.file };
});
app.post<{ Params: { file: string } }>("/api/sessions/:file/resume", async (req, reply) => {
const file = req.params.file;
const full = path.join(PATHS.sessions, file);
if (!file.endsWith(".jsonl") || !fs.existsSync(full)) {
return reply.code(404).send({ error: "session not found" });
}
try {
const result = await resumeSession(file);
return { id: result.sessionId, file: result.file };
} catch (err) {
return reply.code(500).send({ error: String(err) });
}
});
// ─── WebSocket ───────────────────────────────────────────────────────────
app.get("/ws", { websocket: true }, (socket) => {
sockets.add(socket);
socket.on("close", () => sockets.delete(socket));
// Initial snapshot: everything the session has produced so far.
socket.send(JSON.stringify({ type: "hello", sessionId: active?.sessionId ?? null } satisfies ServerMessage));
socket.send(JSON.stringify({ type: "backfill", entries: entryLog } satisfies ServerMessage));
if (active) {
socket.send(
JSON.stringify({
type: "pending",
question: findPendingQuestion(active.runtime.session.sessionManager.getEntries()),
} satisfies ServerMessage),
);
socket.send(
JSON.stringify({ type: "streaming", value: active.runtime.session.isStreaming } satisfies ServerMessage),
);
}
socket.on("message", (raw: Buffer) => {
let msg: { type?: string } & Record<string, unknown>;
try {
msg = JSON.parse(raw.toString());
} catch {
return;
}
if (!active) {
socket.send(JSON.stringify({ type: "error", message: "no active session" } satisfies ServerMessage));
return;
}
const session = active.runtime.session;
switch (msg.type) {
case "prompt": {
const text = String(msg.text ?? "").trim();
if (!text) return;
// One question at a time: don't accept prompts while a question
// is waiting to be answered.
if (findPendingQuestion(session.sessionManager.getEntries())) {
socket.send(
JSON.stringify({
type: "error",
message: "Answer the pending question first (or dismiss it).",
} satisfies ServerMessage),
);
return;
}
void session.prompt(text).catch((err) => {
console.error("[teacher] prompt failed:", err);
broadcast({ type: "error", message: String(err) });
});
break;
}
case "answer": {
const outcome = getBridge().answer(String(msg.questionId ?? ""), {
dontKnow: Boolean(msg.dontKnow),
values: Array.isArray(msg.values) ? msg.values.map(String) : undefined,
other: msg.other ? String(msg.other) : undefined,
text: msg.text ? String(msg.text) : undefined,
note: msg.note ? String(msg.note) : undefined,
});
if (!outcome.ok) {
socket.send(
JSON.stringify({ type: "error", message: outcome.error ?? "answer failed" } satisfies ServerMessage),
);
}
break;
}
case "dismiss": {
const outcome = getBridge().dismiss(String(msg.questionId ?? ""));
if (!outcome.ok) {
socket.send(
JSON.stringify({ type: "error", message: outcome.error ?? "dismiss failed" } satisfies ServerMessage),
);
}
break;
}
case "abort": {
void session.abort();
break;
}
}
});
});
const port = options.port ?? Number(process.env.LH_PORT ?? 8787);
await app.listen({ port, host: "127.0.0.1" });
const actualPort = (app.server.address() as { port: number }).port;
return {
port: actualPort,
close: async () => {
if (unsubscribeEvents) unsubscribeEvents();
if (active) active.runtime.session.dispose();
for (const ws of sockets) ws.close();
sockets.clear();
await app.close();
},
};
}
// ─── entrypoint ─────────────────────────────────────────────────────────────
async function main(): Promise<void> {
const server = await startServer();
console.log(`learning-harness web server: http://127.0.0.1:${server.port}`);
}
if (process.argv[1] && process.argv[1].endsWith("server/index.ts")) {
main().catch((err) => {
console.error(err);
process.exit(1);
});
}