learnharness/tests/model-catalog.test.ts

import { describe, it } from "node:test";
import assert from "node:assert/strict";
import { modelCatalog, validateChatSettings, catalogDefaults, toModelDto } from "../src/server/model-catalog.ts";
import { clampThinkingLevel, getSupportedThinkingLevels } from "@earendil-works/pi-ai";
import { MODELS } from "../config.ts";
import { piEngineFor } from "../src/agent/models.ts";

// The model-control wave (2026-09-12): pi-ai owns the registry — these pins
// hold our projection + validation honest against the shipped catalog, and
// pin pi's per-model thinking truth so a pi-ai upgrade can't silently change
// what we send.

describe("the model catalog projection", () => {
	it("serves pi-ai's OpenRouter catalog with the picker's DTO shape", () => {
		const { models, defaults } = modelCatalog();
		// 0.85.1 ships 366 OpenRouter models — the exact count is pi's, but
		// the shape and the config models' presence are ours to pin.
		assert.ok(models.length > 300, `expected a full catalog, got ${models.length}`);
		for (const m of models.slice(0, 25)) {
			assert.equal(typeof m.id, "string");
			assert.equal(typeof m.name, "string");
			assert.ok(Array.isArray(m.supportedLevels));
			assert.ok(typeof m.cost.input === "number" && typeof m.cost.output === "number");
			assert.ok(m.contextWindow > 0);
		}
		const glm = models.find((m) => m.id === "z-ai/glm-5.3-flash");
		assert.ok(glm, "glm-5.3-flash in catalog");
		assert.deepEqual(glm!.supportedLevels, ["low", "high", "max"]);
		assert.deepEqual(glm!.input, ["text", "image"]);
		// pi's current glm price (our old table said 0.15/0.5 — stale)
		assert.deepEqual(glm!.cost, { input: 0.075, output: 0.25, cacheRead: 0.015, cacheWrite: 0 });
	});

	it("defaults mirror the conversation agents' config pin", () => {
		const d = catalogDefaults();
		assert.deepEqual(d, { model: { provider: "openrouter", id: MODELS.prober.model }, thinkingLevel: MODELS.prober.effort });
		assert.equal(d.model.id, MODELS.teacher.model, "one controller: prober and teacher share the pin");
	});

	it("toModelDto projects the raw catalog model verbatim", () => {
		const raw = piEngineFor("prober").model; // the catalog's glm entry
		const dto = toModelDto(raw);
		assert.equal(dto.id, raw.id);
		assert.equal(dto.name, raw.name);
		assert.deepEqual(dto.supportedLevels, getSupportedThinkingLevels(raw));
		assert.equal(dto.cost.input, raw.cost.input);
		assert.equal(dto.contextWindow, raw.contextWindow);
	});
});

describe("the settings validation gate", () => {
	it("accepts a supported level and rejects an unsupported one with the list", () => {
		const ok = validateChatSettings({ model: { provider: "openrouter", id: "z-ai/glm-5.3-flash" }, thinkingLevel: "max" });
		assert.deepEqual(ok, { ok: true });
		const bad = validateChatSettings({ model: { provider: "openrouter", id: "z-ai/glm-5.3-flash" }, thinkingLevel: "minimal" });
		assert.equal(bad.ok, false);
		if (!bad.ok) {
			assert.match(bad.error, /does not support thinking level/);
			assert.deepEqual(bad.supported, ["low", "high", "max"]);
		}
	});

	it("resolves a bare thinking level against the config default model", () => {
		assert.deepEqual(validateChatSettings({ thinkingLevel: "high" }), { ok: true });
		// "minimal" is unsupported on config's glm — rejected even with no model set
		assert.equal(validateChatSettings({ thinkingLevel: "minimal" }).ok, false);
	});

	it("rejects unknown providers and models", () => {
		assert.equal(validateChatSettings({ model: { provider: "nope", id: "x/y" } }).ok, false);
		assert.equal(validateChatSettings({ model: { provider: "openrouter", id: "nope/nope" } }).ok, false);
	});

	it("accepts empty settings (the clear-overrides write)", () => {
		assert.deepEqual(validateChatSettings({}), { ok: true });
	});
});

describe("pi thinking truth (pinned against pi-ai upgrades)", () => {
	it("glm-5.3-flash: low|high|max; anything else clamps to the nearest", () => {
		const glm = piEngineFor("prober").model;
		assert.deepEqual(getSupportedThinkingLevels(glm), ["low", "high", "max"]);
		assert.equal(clampThinkingLevel(glm, "minimal"), "low");
		assert.equal(clampThinkingLevel(glm, "off"), "low", "GLM cannot disable thinking (map: off → null)");
		assert.equal(clampThinkingLevel(glm, "xhigh"), "max");
		assert.equal(clampThinkingLevel(glm, "high"), "high");
	});

	it("the engine factory honors settings, falls back to config, clamps", () => {
		// override both fields
		const over = piEngineFor("teacher", { model: { provider: "openrouter", id: "qwen/qwen3.8-flash" }, thinkingLevel: "high" });
		assert.equal(over.model.id, "qwen/qwen3.8-flash");
		assert.equal(over.level, "high");
		// no settings → config pin
		const pinned = piEngineFor("prober");
		assert.equal(pinned.model.id, MODELS.prober.model);
		assert.equal(pinned.level, MODELS.prober.effort);
		// settings level unsupported by the settings model → clamped honestly
		const clamped = piEngineFor("teacher", { model: { provider: "openrouter", id: "z-ai/glm-5.3-flash" }, thinkingLevel: "minimal" });
		assert.equal(clamped.level, "low");
		// bare level resolves against the config default model
		assert.equal(piEngineFor("prober", { thinkingLevel: "max" }).level, "max");
		// unknown model → honest throw, never a silent fallback
		assert.throws(() => piEngineFor("teacher", { model: { provider: "openrouter", id: "nope/nope" } }), /catalog has no model/);
	});
});