- src/agent/lh-tool.ts deleted: the zod-wrapped LhTool + toPiTool bridge (z.toJSONSchema per call, clientQuestion flag, hand-rolled result mapping) is gone. Tools are pi-agent-core native AgentTools now. - New src/agent/tool-execute.ts owns what the wrapper added: the abort guard (runWithAbortGuard: run signal + 30s per-call timeout + 250ms grace, 'Operation aborted' / timeout wording preserved), ToolInputError (the retryable '- problem at path' format), result mapping (string verbatim / object JSON / image parts, details rides the record's tool part output), and questionResult() — placeholder + terminate:true (owner Option A: belt of terminate + slim makeQuestionStopper with the clean-question rule; maxTurns deleted from the teaching turn entirely per owner). - All 11 tool files + tools.ts registries converted to TypeBox parameters (typebox@1.3.7, pinned to pi-agent-core's copy). zod refinements (quizInputProblems, askOptionProblems, live-nodeId) moved from schemas into execute — the model sees the same retryable error shape. - question-core + contracts/probe TypeBox-authored (single source shared with the UI); tool-parts parse seam runs the boundary's full chain (Convert → Check → Clean → refinement), fixing the live-smoke lockout: pi's boundary Value.Converts correctAnswer: 17 → '17' but the record keeps raw args, so a parse without Convert rejected a posed quiz (invisible pending question, turn ended). Pinned with the real smoke emission shape. - Subagents converted: demo-builder/researcher AgentTool-native, visual-maker/pdf-reader declaration-only pi-ai Tools with local execute fns, extraction submit schemas re-authored in TypeBox (owner option 2: zod defaults → Type.Optional + fill at the submit seam). - Accepted delta, flagged: TypeBox-native schemas skip pi's JSON-Schema primitive coercion fast path... (boundary still Value.Converts), and prober-quiz unknown keys ride through (Value.Clean strips at display). - Tests: 988 passing (was 967 at the recon baseline); tool-abort and read-tool rewritten against the native seams; question-core/question- tools/tool-parts/demos/web-search/graph-tools/plan-tree/probe-done/ tool-toggles converted to Value.Check/execute pins. Live smoke (PORT=3004, real model): native ls turn streams end-to-end; a real quiz pose (first attempt missing correctAnswer → tool-input-error → model retry → posed) terminates the turn cleanly and persists pending.
118 lines
4.4 KiB
TypeScript
118 lines
4.4 KiB
TypeScript
/**
|
|
* probe_done — the probe→planning seam tool (docs/probe-teach-split.md §2).
|
|
* Server-side; three outcomes: refusal while a question is open, refusal
|
|
* after the probe is already concluded, ok + handoff queued. The handoff
|
|
* rides the wake pipeline (deliver injected here — no server seam import).
|
|
*/
|
|
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 { probeDoneTool } from "../src/agent/tools/probe.ts";
|
|
import type { ProbeHandoffSteerMessage } from "../src/core/contracts.ts";
|
|
import { chatStore } from "../src/store/chats.ts";
|
|
import { PATHS } from "../config.ts";
|
|
|
|
const dataDir = path.join(PATHS.root, "data");
|
|
fs.mkdirSync(dataDir, { recursive: true });
|
|
|
|
const createdChats: string[] = [];
|
|
after(() => {
|
|
for (const id of createdChats) {
|
|
try {
|
|
fs.unlinkSync(path.join(PATHS.chats, `${id}.json`));
|
|
} catch {
|
|
/* scratch cleanup, best effort */
|
|
}
|
|
}
|
|
});
|
|
|
|
function newChat(title: string): string {
|
|
const chat = chatStore.createChat(title);
|
|
createdChats.push(chat.id);
|
|
return chat.id;
|
|
}
|
|
|
|
const ASSESSMENT = {
|
|
strands: [
|
|
{ strand: "the derivative as a limit", assessment: "Floor: slope intuition. Ceiling: formal ε–δ." },
|
|
],
|
|
summary: "Enter at the formal definition.",
|
|
};
|
|
|
|
async function execute(tools: ReturnType<typeof probeDoneTool>, input: unknown) {
|
|
const t = tools.probe_done!;
|
|
assert.ok(typeof t.execute === "function");
|
|
return t.execute("test", input).then((r) => r.details as { ok: boolean; error?: string });
|
|
}
|
|
|
|
describe("probe_done: the probe→planning seam", () => {
|
|
it("ok path: records the assessment and queues the handoff steer (deterministic id)", async () => {
|
|
const chatId = newChat("Probe: ok");
|
|
const delivered: ProbeHandoffSteerMessage[] = [];
|
|
const tools = probeDoneTool({ chatId, chatStore, deliver: (s) => delivered.push(s) });
|
|
|
|
const res = await execute(tools, { assessment: ASSESSMENT });
|
|
assert.equal(res.ok, true);
|
|
assert.equal(res.error, undefined);
|
|
assert.equal(delivered.length, 1, "the handoff is queued exactly once");
|
|
assert.equal(delivered[0]!.id, `steer_probe_${chatId}`);
|
|
assert.equal((delivered[0]!.metadata as { probeHandoff: { chatId: string } }).probeHandoff.chatId, chatId);
|
|
});
|
|
|
|
it("REFUSES while a question is still open — resolve it first", async () => {
|
|
const chatId = newChat("Probe: open question");
|
|
chatStore.saveMessages(chatId, [
|
|
{
|
|
id: "m1",
|
|
role: "assistant",
|
|
parts: [{ type: "tool-quiz", state: "input-available", input: { question: "q?" } }],
|
|
} as never,
|
|
]);
|
|
const delivered: ProbeHandoffSteerMessage[] = [];
|
|
const tools = probeDoneTool({ chatId, chatStore, deliver: (s) => delivered.push(s) });
|
|
|
|
const res = await execute(tools, { assessment: ASSESSMENT });
|
|
assert.equal(res.ok, false);
|
|
assert.match(res.error!, /question is still open/i);
|
|
assert.equal(delivered.length, 0, "nothing queued on refusal");
|
|
});
|
|
|
|
it("REFUSES a second conclusion — probe_done fires exactly once", async () => {
|
|
const chatId = newChat("Probe: twice");
|
|
chatStore.saveMessages(chatId, [
|
|
{
|
|
id: "m1",
|
|
role: "assistant",
|
|
parts: [{ type: "tool-probe_done", state: "output-available", input: { assessment: ASSESSMENT }, output: { ok: true } }],
|
|
} as never,
|
|
]);
|
|
const delivered: ProbeHandoffSteerMessage[] = [];
|
|
const tools = probeDoneTool({ chatId, chatStore, deliver: (s) => delivered.push(s) });
|
|
|
|
const res = await execute(tools, { assessment: ASSESSMENT });
|
|
assert.equal(res.ok, false);
|
|
assert.match(res.error!, /already concluded/i);
|
|
assert.equal(delivered.length, 0);
|
|
});
|
|
|
|
it("REFUSES an unknown chat defensively", async () => {
|
|
const tools = probeDoneTool({ chatId: "chat_nonexistent", chatStore, deliver: () => {} });
|
|
const res = await execute(tools, { assessment: ASSESSMENT });
|
|
assert.equal(res.ok, false);
|
|
assert.match(res.error!, /not found/i);
|
|
});
|
|
|
|
it("a deliver failure never fails the call — the assessment records; the wake is recoverable-by-design", async () => {
|
|
const chatId = newChat("Probe: deliver crash");
|
|
const tools = probeDoneTool({
|
|
chatId,
|
|
chatStore,
|
|
deliver: () => {
|
|
throw new Error("queue exploded");
|
|
},
|
|
});
|
|
const res = await execute(tools, { assessment: ASSESSMENT });
|
|
assert.equal(res.ok, true, "ok:true even when the queue is lost — the next client message constructs the teacher off the transcript seam");
|
|
});
|
|
}); |