Files
learnharness/tests/tool-toggles-bridge.test.ts
T
amosblomqvist bfa906e2f8 feat(models): BYOK all the way down — factory pins deleted, per-need refusal gates
Owner decision 2026-09-22: 'it doesn't make sense to have any default
model configured anywhere; the application is bring your own keys.'

config.ts: MODELS deleted; ModelRole becomes an explicit 9-role union;
DEFAULT_THINKING_ORDER (medium, low, high, minimal, xhigh, max) bakes
the unset-level default — first entry the model supports; explicitly
set levels keep pi's native nearest-clamp.

core/settings-resolution: the factory layer dissolves — the chain is
role override → slot → NOTHING. resolveSettings(record) takes no
factory. Empty chains resolve to null/undefined; a thinkingLevel-only
slot is inert (stored, never run). resolveConversationSpec: chat.model
override over the strong slot, null when both empty. resolveRoleSpec
spans all nine roles for the job/extraction engines.

Refusal envelope (core/settings.ts): modelsNotConfigured(missing) —
{error, code: 'models_not_configured', missing: [slot tiers]} +
ModelsNotConfiguredError with .envelope. Per-need gates, each honest:
- chat-handler: universal turn gate (new + continuing turns) returns
  503 before beginTurn — no liveness, no write-ahead persist, no graph
  trigger before the gate fires.
- runner.runJob: unresolvable engine lands the job as error with the
  envelope wording; no phantom loop, no result steer.
- extraction: refuseIfStagesUnconfigured throws before any stage
  (turn-service info-skips so coverage retries next turn; the import
  route surfaces per-file code+missing); labeler-less runs skip
  cluster naming with a console line and still merge.

Write side: slot entries must carry a model — level-only slot writes
are 400s (absent slot key = clear). piEngineForSpec resolves unset
thinking levels via DEFAULT_THINKING_ORDER; piEngineFor now throws
honestly; thinkingLevelFor/modelIdFor deleted; teacher-agent, pi-run,
visual-maker, pdf-reader all read engine.level.

model-catalog: defaults/slots/rolePins null when the chain is empty
(contracts nullable) — no phantom ids in payloads. Stores drop
MODEL_PINS entirely.

Tests: pin-leaners converted to explicit injection (per-chat model
pins on scripted chats — exactly what the setup flow writes; faux
engines for agent-construction tests). New coverage: the 503 gate
envelope, the runner refusal, the extraction refusal + labeler skip.

Gates: typecheck, lint, 815/815, build.
2026-09-22 16:59:16 +03:00

90 lines
3.9 KiB
TypeScript

/**
* The P2 tool-toggle bridge (2026-09-19): AgentBuildOptions.toolToggles is
* first-class — the agent constructors thread it to the factories' enabled?
* param (an explicit opts.tools registry is never filtered), and the
* settings write side rejects unknown tool keys against TOGGLEABLE_TOOLS
* (the definitive adjudicated list — a persisted `quiz: false` would
* genuinely drop the quiz once the bridge honors the delta).
*
* Parser tests are PURE (no fs — parallel-test discipline); the agent
* construction tests use an in-memory chat fixture like
* question-tools.test.ts.
*/
import assert from "node:assert/strict";
import { z } from "zod";
import { describe, it } from "node:test";
import { createProberAgent, createTeacherAgent } from "../src/agent/teacher-agent.ts";
import type { ProberToolContext } from "../src/agent/tools.ts";
import { jobStore } from "../src/store/jobs.ts";
import { parseAgentSettingsBody } from "../src/server/settings-body.ts";
import { chatStore } from "../src/store/chats.ts";
import { createFauxCore } from "@earendil-works/pi-ai";
import type { PiEngine } from "../src/agent/models.ts";
/** A scripted pi engine — the agent builds need an injected engine since
* BYOK removed the factory pins (owner, 2026-09-22). */
function fauxEngine(): PiEngine {
const faux = createFauxCore({});
return { model: faux.getModel(), streamFn: faux.streamSimple };
}
import type { AgentSettings } from "../src/core/settings.ts";
describe("AgentBuildOptions.toolToggles (the P2 bridge)", () => {
const toolNames = (agent: { state: { tools: Array<{ name: string }> } }) =>
agent.state.tools.map((t) => t.name).sort();
it("flows into the teacher's registry: a job-tool delta is a no-op on the bare set", () => {
// No ctx → bare agent: quiz/ask only. A job-tool delta names tools
// that don't exist there — the bridge must not crash on it.
const bare = createTeacherAgent(undefined, { engine: fauxEngine(), toolToggles: { research: false } });
assert.deepEqual(toolNames(bare), ["ask_user_question", "quiz"]);
});
it("flows into the prober's registry; probe_done survives everything", () => {
const chatId = chatStore.createChat("Toggle bridge test").id;
const ctx: ProberToolContext = { chatId, chatStore, deliver: () => {}, jobStore, spawn: () => {} };
const prober = createProberAgent(ctx, { engine: fauxEngine(), toolToggles: { ask_user_question: false } });
const names = toolNames(prober);
assert.ok(!names.includes("ask_user_question"), "the delta dropped the tool");
assert.ok(names.includes("probe_done"), "probe_done always-on");
});
it("an explicitly injected opts.tools registry is NEVER toggle-filtered", () => {
const teacher = createTeacherAgent(undefined, {
engine: fauxEngine(),
tools: {
quiz: { name: "quiz", description: "test", clientQuestion: true, schema: z.object({}) },
},
toolToggles: { quiz: false },
});
assert.deepEqual(toolNames(teacher), ["quiz"]);
});
});
describe("parseAgentSettingsBody: tool keys validate at write time", () => {
const parse = (tools: Record<string, boolean>) =>
parseAgentSettingsBody({ tools }) as
| { ok: true; settings: AgentSettings }
| { ok: false; error: string };
it("a valid job-tool delta parses", () => {
const r = parse({ research: false, pdf: false });
assert.equal(r.ok, true);
assert.deepEqual(r.ok && r.settings.tools, { research: false, pdf: false });
});
it("unknown keys are rejected with the supported list (the quiz wedge never persists)", () => {
const r = parse({ quiz: false });
assert.equal(r.ok, false);
assert.match(!r.ok && r.error, /unknown tool "quiz" \(supported: research, demo, visual, pdf\)/);
const typo = parse({ reasearch: false });
assert.equal(typo.ok, false);
assert.match(!typo.ok && typo.error, /unknown tool "reasearch"/);
});
it("absent tools field is fine (absent = enabled everywhere)", () => {
const r = parseAgentSettingsBody({}) as { ok: boolean };
assert.equal(r.ok, true);
});
});