Files
clawdbot/src/auto-reply/reply.directive.directive-behavior.defaults-think-low-reasoning-capable-models-no.test.ts
2026-01-17 08:28:09 +00:00

271 lines
8.3 KiB
TypeScript

import path from "node:path";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { withTempHome as withTempHomeBase } from "../../test/helpers/temp-home.js";
import { loadModelCatalog } from "../agents/model-catalog.js";
import { runEmbeddedPiAgent } from "../agents/pi-embedded.js";
import { loadSessionStore } from "../config/sessions.js";
import { getReplyFromConfig } from "./reply.js";
const MAIN_SESSION_KEY = "agent:main:main";
vi.mock("../agents/pi-embedded.js", () => ({
abortEmbeddedPiRun: vi.fn().mockReturnValue(false),
runEmbeddedPiAgent: vi.fn(),
queueEmbeddedPiMessage: vi.fn().mockReturnValue(false),
resolveEmbeddedSessionLane: (key: string) => `session:${key.trim() || "main"}`,
isEmbeddedPiRunActive: vi.fn().mockReturnValue(false),
isEmbeddedPiRunStreaming: vi.fn().mockReturnValue(false),
}));
vi.mock("../agents/model-catalog.js", () => ({
loadModelCatalog: vi.fn(),
}));
async function withTempHome<T>(fn: (home: string) => Promise<T>): Promise<T> {
return withTempHomeBase(
async (home) => {
return await fn(home);
},
{
env: {
CLAWDBOT_AGENT_DIR: (home) => path.join(home, ".clawdbot", "agent"),
PI_CODING_AGENT_DIR: (home) => path.join(home, ".clawdbot", "agent"),
},
prefix: "clawdbot-reply-",
},
);
}
function _assertModelSelection(
storePath: string,
selection: { model?: string; provider?: string } = {},
) {
const store = loadSessionStore(storePath);
const entry = store[MAIN_SESSION_KEY];
expect(entry).toBeDefined();
expect(entry?.modelOverride).toBe(selection.model);
expect(entry?.providerOverride).toBe(selection.provider);
}
describe("directive behavior", () => {
beforeEach(() => {
vi.mocked(runEmbeddedPiAgent).mockReset();
vi.mocked(loadModelCatalog).mockResolvedValue([
{ id: "claude-opus-4-5", name: "Opus 4.5", provider: "anthropic" },
{ id: "claude-sonnet-4-1", name: "Sonnet 4.1", provider: "anthropic" },
{ id: "gpt-4.1-mini", name: "GPT-4.1 Mini", provider: "openai" },
]);
});
afterEach(() => {
vi.restoreAllMocks();
});
it("defaults /think to low for reasoning-capable models when no default set", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
vi.mocked(loadModelCatalog).mockResolvedValueOnce([
{
id: "claude-opus-4-5",
name: "Opus 4.5",
provider: "anthropic",
reasoning: true,
},
]);
const res = await getReplyFromConfig(
{ Body: "/think", From: "+1222", To: "+1222", CommandAuthorized: true },
{},
{
agents: {
defaults: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
},
session: { store: path.join(home, "sessions.json") },
},
);
const text = Array.isArray(res) ? res[0]?.text : res?.text;
expect(text).toContain("Current thinking level: low");
expect(text).toContain("Options: off, minimal, low, medium, high.");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});
it("shows off when /think has no argument and model lacks reasoning", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockReset();
vi.mocked(loadModelCatalog).mockResolvedValueOnce([
{
id: "claude-opus-4-5",
name: "Opus 4.5",
provider: "anthropic",
reasoning: false,
},
]);
const res = await getReplyFromConfig(
{ Body: "/think", From: "+1222", To: "+1222", CommandAuthorized: true },
{},
{
agents: {
defaults: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
},
session: { store: path.join(home, "sessions.json") },
},
);
const text = Array.isArray(res) ? res[0]?.text : res?.text;
expect(text).toContain("Current thinking level: off");
expect(text).toContain("Options: off, minimal, low, medium, high.");
expect(runEmbeddedPiAgent).not.toHaveBeenCalled();
});
});
it("strips reply tags and maps reply_to_current to MessageSid", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockResolvedValue({
payloads: [{ text: "hello [[reply_to_current]]" }],
meta: {
durationMs: 5,
agentMeta: { sessionId: "s", provider: "p", model: "m" },
},
});
const res = await getReplyFromConfig(
{
Body: "ping",
From: "+1004",
To: "+2000",
MessageSid: "msg-123",
},
{},
{
agents: {
defaults: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
session: { store: path.join(home, "sessions.json") },
},
);
const payload = Array.isArray(res) ? res[0] : res;
expect(payload?.text).toBe("hello");
expect(payload?.replyToId).toBe("msg-123");
});
});
it("strips reply tags with whitespace and maps reply_to_current to MessageSid", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockResolvedValue({
payloads: [{ text: "hello [[ reply_to_current ]]" }],
meta: {
durationMs: 5,
agentMeta: { sessionId: "s", provider: "p", model: "m" },
},
});
const res = await getReplyFromConfig(
{
Body: "ping",
From: "+1004",
To: "+2000",
MessageSid: "msg-123",
},
{},
{
agents: {
defaults: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
session: { store: path.join(home, "sessions.json") },
},
);
const payload = Array.isArray(res) ? res[0] : res;
expect(payload?.text).toBe("hello");
expect(payload?.replyToId).toBe("msg-123");
});
});
it("prefers explicit reply_to id over reply_to_current", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockResolvedValue({
payloads: [
{
text: "hi [[reply_to_current]] [[reply_to:abc-456]]",
},
],
meta: {
durationMs: 5,
agentMeta: { sessionId: "s", provider: "p", model: "m" },
},
});
const res = await getReplyFromConfig(
{
Body: "ping",
From: "+1004",
To: "+2000",
MessageSid: "msg-123",
},
{},
{
agents: {
defaults: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
session: { store: path.join(home, "sessions.json") },
},
);
const payload = Array.isArray(res) ? res[0] : res;
expect(payload?.text).toBe("hi");
expect(payload?.replyToId).toBe("abc-456");
});
});
it("applies inline think and still runs agent content", async () => {
await withTempHome(async (home) => {
vi.mocked(runEmbeddedPiAgent).mockResolvedValue({
payloads: [{ text: "done" }],
meta: {
durationMs: 5,
agentMeta: { sessionId: "s", provider: "p", model: "m" },
},
});
const res = await getReplyFromConfig(
{
Body: "please sync /think:high now",
From: "+1004",
To: "+2000",
},
{},
{
agents: {
defaults: {
model: "anthropic/claude-opus-4-5",
workspace: path.join(home, "clawd"),
},
},
channels: { whatsapp: { allowFrom: ["*"] } },
session: { store: path.join(home, "sessions.json") },
},
);
const texts = (Array.isArray(res) ? res : [res]).map((entry) => entry?.text).filter(Boolean);
expect(texts).toContain("done");
expect(runEmbeddedPiAgent).toHaveBeenCalledOnce();
});
});
});