mirror of
https://github.com/wassname/pi-plan.git
synced 2026-09-26 14:10:23 +08:00
1124 lines
64 KiB
TypeScript
1124 lines
64 KiB
TypeScript
import { existsSync, mkdirSync, mkdtempSync, readdirSync, readFileSync, renameSync, rmSync, writeFileSync } from "node:fs";
|
|
import { access, readFile, writeFile } from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import { basename, join, relative } from "node:path";
|
|
import { createEditTool, type ExtensionAPI, SessionManager, withFileMutationQueue } from "@earendil-works/pi-coding-agent";
|
|
import { afterEach, expect, it, vi } from "vitest";
|
|
import goalsExtension from "../src/index.js";
|
|
import { upkeep } from "../src/prompts.js";
|
|
|
|
const roots: string[] = [];
|
|
const shutdowns: Array<() => void> = [];
|
|
afterEach(() => { for (const shutdown of shutdowns.splice(0)) shutdown(); vi.unstubAllEnvs(); for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }); });
|
|
const delay = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
|
|
async function waitFor(predicate: () => boolean, ms = 1500): Promise<void> {
|
|
const start = Date.now();
|
|
while (!predicate()) {
|
|
if (Date.now() - start > ms) throw new Error("timed out waiting for condition");
|
|
await delay(10);
|
|
}
|
|
}
|
|
function fixture(child = false) {
|
|
vi.stubEnv("PI_SUBAGENT_AGENT", child ? "goals-worker" : "");
|
|
const cwd = mkdtempSync(join(tmpdir(), "goals-main-test-")); roots.push(cwd);
|
|
const entries: any[] = []; const hooks = new Map<string, any>(); const commands = new Map<string, any>(); const tools = new Map<string, any>();
|
|
const messages: any[] = [];
|
|
const ctx = { cwd, sessionManager: { getBranch: () => entries, getSessionId: () => "copy-only" }, hasUI: true, hasPendingMessages: vi.fn(() => false), ui: {
|
|
theme: { fg: (_color: string, text: string) => text }, notify: vi.fn(), setStatus: vi.fn(), setWidget: vi.fn(), select: vi.fn(async (_title: string, _options: string[]) => "Ready"), editor: vi.fn(),
|
|
} };
|
|
const pi = {
|
|
on: (event: string, hook: any) => hooks.set(event, hook),
|
|
appendEntry: (customType: string, data: any) => entries.push({ type: "custom", customType, data }),
|
|
registerCommand: (name: string, definition: any) => commands.set(name, definition),
|
|
registerTool: (definition: any) => tools.set(definition.name, definition),
|
|
registerMarkdownTransformer: vi.fn(),
|
|
registerEntryRenderer: vi.fn(),
|
|
sendMessage: (message: any, options: any) => messages.push({ message, options }),
|
|
sendUserMessage: (content: string, options: any) => messages.push({ message: { content }, options, savedPrompt: true }),
|
|
events: { emit: vi.fn() },
|
|
getAllTools: vi.fn(() => [
|
|
{ name: "subagent", parameters: { properties: { agent: {}, title: {} } } },
|
|
{ name: "subagent_resume", parameters: { properties: { sessionFile: {} } } },
|
|
{ name: "subagent_kill", parameters: { properties: { id: {} } } },
|
|
]),
|
|
};
|
|
goalsExtension(pi as unknown as ExtensionAPI);
|
|
hooks.get("session_start")({}, ctx);
|
|
let path = "";
|
|
const command = async (value: string) => {
|
|
await commands.get("goals").handler(value, ctx);
|
|
const planDir = join(cwd, ".pi", "plan");
|
|
if (!path && existsSync(planDir)) {
|
|
const firstPlan = readdirSync(planDir).find(name => name.endsWith(".md"));
|
|
if (firstPlan) path = join(planDir, firstPlan);
|
|
}
|
|
};
|
|
const plan = "# Plan\n- [ ] goal: first output\n- [ ] goal: second output\n\n## Log\n";
|
|
const draft = async () => { await command("new two outputs"); writeFileSync(path, plan); };
|
|
const shutdown = () => hooks.get("session_shutdown")();
|
|
shutdowns.push(shutdown);
|
|
const changed = () => messages.filter((m) => m.message?.content?.includes("Plan changed")).length;
|
|
const atomicWrite = async (text: string) => {
|
|
const tmp = `${path}.tmp`;
|
|
writeFileSync(tmp, text);
|
|
renameSync(tmp, path);
|
|
await delay(25);
|
|
};
|
|
const start = (toolCallId: string, input: any = { agent: "goals-worker", title: "Implement" }, toolName = "subagent") => hooks.get("tool_call")({ toolCallId, toolName, input }, ctx);
|
|
const finish = (toolCallId: string, details: any, toolName = "subagent", isError = false) => hooks.get("tool_execution_end")({ toolCallId, toolName, result: { content: [], details }, isError }, ctx);
|
|
const launch = (details: any, agent = "goals-worker", toolName = "subagent") => {
|
|
start(details.id, { agent, title: "Work", sessionFile: details.sessionFile }, toolName);
|
|
finish(details.id, details, toolName);
|
|
};
|
|
return { ctx, pi, hooks, tools, commands, messages, command, get path() { return path; }, plan, draft, shutdown, changed, atomicWrite, get entries() { return entries.filter(entry => entry.customType === "pi-goals-main-supervisor-v1"); }, start, finish, launch };
|
|
}
|
|
|
|
it.each([
|
|
["chat", ["new", "attach", "help", "quit"]],
|
|
["planning", ["edit", "discuss", "ready", "model", "help", "quit"]],
|
|
["supervising", ["review", "stop", "model", "help", "quit"]],
|
|
["paused", ["resume", "model", "help", "quit"]],
|
|
["solo", ["stop", "help", "quit"]],
|
|
])("shows only applicable %s actions without starting work", async (mode, expected) => {
|
|
const f = fixture();
|
|
if (mode !== "chat") await f.draft();
|
|
if (mode === "supervising" || mode === "paused") await f.command("ready");
|
|
if (mode === "paused") await f.command("stop");
|
|
if (mode === "solo") { f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo"); }
|
|
const before = f.messages.length;
|
|
f.ctx.ui.select.mockResolvedValueOnce(undefined as any);
|
|
await f.command("");
|
|
const actions = f.ctx.ui.select.mock.calls.at(-1)![1];
|
|
expect(actions.map(action => action.split(" — ")[0])).toEqual(expected);
|
|
expect(actions.at(-1)).toBe("quit — Exit and clear goals");
|
|
expect(f.messages).toHaveLength(before);
|
|
expect(f.commands.get("goals").getArgumentCompletions("res")).toEqual([{ value: "resume", label: "resume" }]);
|
|
});
|
|
|
|
it.each(["redy", "start", "two outputs", "status extra", "attach some.md solo extra"])("rejects %s without changing the plan or sending a model prompt", async (text) => {
|
|
const f = fixture(); await f.draft();
|
|
const before = readFileSync(f.path, "utf8");
|
|
const entries = f.entries.length; const messages = f.messages.length;
|
|
await f.command(text);
|
|
expect(readFileSync(f.path, "utf8")).toBe(before);
|
|
expect(f.entries).toHaveLength(entries);
|
|
expect(f.messages).toHaveLength(messages);
|
|
});
|
|
|
|
it("requires a model argument without clearing the preference", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("model provider/model");
|
|
const before = readFileSync(f.path, "utf8");
|
|
await f.command("model");
|
|
expect(readFileSync(f.path, "utf8")).toBe(before);
|
|
});
|
|
|
|
it.each(["menu", "command"])("enters planning conversation through %s without a worker launch", async (route) => {
|
|
const f = fixture();
|
|
f.ctx.ui.select.mockResolvedValueOnce("new — New plan…");
|
|
f.ctx.ui.editor.mockResolvedValueOnce("supplied instructions");
|
|
await f.command(route === "menu" ? "" : "new");
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
expect(f.ctx.ui.editor).toHaveBeenCalledTimes(route === "menu" ? 1 : 0);
|
|
expect(f.messages).toHaveLength(1);
|
|
expect(f.messages[0].message.content).toContain(route === "menu" ? "Initial idea: supplied instructions" : "Use the existing conversation");
|
|
expect(f.hooks.get("tool_call")({ toolName: "subagent" }).block).toBe(true);
|
|
});
|
|
|
|
it("cancelled menu New creates nothing and sends nothing", async () => {
|
|
const f = fixture();
|
|
f.ctx.ui.select.mockResolvedValueOnce("new — New plan…");
|
|
await f.command(""); // editor returns undefined on Cancel
|
|
expect(f.entries).toHaveLength(0); expect(f.messages).toHaveLength(0);
|
|
expect(existsSync(join(f.ctx.cwd, ".pi/plan"))).toBe(false);
|
|
});
|
|
|
|
it("new names use six session characters, skip deletion holes and suffix collisions, and preserve old files", async () => {
|
|
const f = fixture(); f.ctx.sessionManager.getSessionId = () => "first-abc123";
|
|
const directory = join(f.ctx.cwd, ".pi/plan"); mkdirSync(directory, { recursive: true });
|
|
const old = ["2026-09-14-000000Z-descriptive-plan-v1.md", "abc123-v1.md", "abc123-v2.md", "abc123-v10.md"];
|
|
for (const name of old) writeFileSync(join(directory, name), name);
|
|
rmSync(join(directory, "abc123-v2.md"));
|
|
await f.command("new Preserve the descriptive title");
|
|
const first = f.entries.at(-1).data.plan;
|
|
expect(basename(first)).toBe("abc123-v11.md");
|
|
expect(readFileSync(first, "utf8")).toContain("# Preserve the descriptive title\n");
|
|
f.ctx.sessionManager.getSessionId = () => "another-abc123";
|
|
await f.command("new Different session with same suffix");
|
|
expect(basename(f.entries.at(-1).data.plan)).toBe("abc123-v12.md");
|
|
expect(readFileSync(first, "utf8")).toContain("# Preserve the descriptive title\n");
|
|
for (const name of old.filter(name => name !== "abc123-v2.md")) expect(readFileSync(join(directory, name), "utf8")).toBe(name);
|
|
expect(readdirSync(directory)).toHaveLength(5);
|
|
});
|
|
|
|
it("edits even an empty draft directly without a model call", async () => {
|
|
const f = fixture(); await f.command("new"); const before = f.messages.length;
|
|
f.ctx.ui.editor.mockResolvedValueOnce(f.plan);
|
|
f.ctx.ui.select.mockResolvedValueOnce("edit — Edit plan…"); await f.command("");
|
|
expect(readFileSync(f.path, "utf8")).toBe(f.plan);
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
expect(f.messages).toHaveLength(before);
|
|
});
|
|
|
|
it("clear preserves the plan without a backup, warns for misbound jobs and allows a separate new draft", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "stale", sessionFile: "/tmp/old-worker.jsonl" });
|
|
const jobs = [
|
|
{ id: "owned", name: "goals-copy-only", session: "copy-only", enabled: true },
|
|
{ id: "older", name: "older-plan", session: "copy-only", enabled: true },
|
|
{ id: "foreign", name: "goals-copy-only", session: "other", enabled: true },
|
|
{ id: "unbound", name: "goals-copy-only", enabled: true },
|
|
];
|
|
const schedule = join(f.ctx.cwd, ".pi/schedule-prompts.json"); writeFileSync(schedule, JSON.stringify({ version: 1, jobs }));
|
|
const before = f.messages.length; await f.command("clear");
|
|
expect(f.messages).toHaveLength(before);
|
|
expect(f.entries.at(-1).data).toEqual({ mode: "chat", helpers: [], signoffs: {} });
|
|
expect(JSON.parse(readFileSync(schedule, "utf8")).jobs).toEqual(jobs.slice(1));
|
|
expect(f.pi.events.emit).toHaveBeenCalledExactlyOnceWith("cron:change", { type: "remove", jobId: "owned" });
|
|
expect(f.ctx.ui.notify).toHaveBeenCalledWith("Goal check-ins left unchanged (session binding missing or different): foreign, unbound. Inspect /schedule-prompt.", "warning");
|
|
const directory = join(f.ctx.cwd, ".pi/plan");
|
|
expect(readdirSync(directory)).toEqual([basename(f.path)]);
|
|
expect(readFileSync(f.path, "utf8")).toBe(f.plan);
|
|
await f.command("new a different objective");
|
|
const next = f.entries.at(-1).data;
|
|
expect(next.mode).toBe("planning"); expect(next.worker).toBeUndefined(); expect(next.plan).not.toBe(f.path);
|
|
expect(readFileSync(next.plan, "utf8")).toContain("a different objective");
|
|
expect(readFileSync(next.plan, "utf8")).not.toContain("first output");
|
|
expect(readFileSync(f.path, "utf8")).toBe(f.plan);
|
|
expect(readdirSync(directory)).toHaveLength(2);
|
|
expect(f.messages).toHaveLength(before + 1); // New alone queues its normal planning turn.
|
|
});
|
|
|
|
it.each(["missing", "empty"])("clear resets a %s plan without a model call", async kind => {
|
|
const f = fixture(); await f.draft(); const before = f.messages.length;
|
|
if (kind === "missing") rmSync(f.path); else writeFileSync(f.path, "");
|
|
await f.command("clear");
|
|
expect(f.entries.at(-1).data).toEqual({ mode: "chat", helpers: [], signoffs: {} });
|
|
expect(f.messages).toHaveLength(before);
|
|
});
|
|
|
|
it("discusses plan changes only during planning", async () => {
|
|
const f = fixture(); await f.command("discuss"); expect(f.messages).toHaveLength(0);
|
|
await f.draft(); const sent = f.messages.length;
|
|
f.ctx.ui.select.mockResolvedValueOnce("discuss — Discuss changes to the plan"); await f.command("");
|
|
expect(f.messages).toHaveLength(sent);
|
|
expect(readFileSync(f.path, "utf8")).toBe(f.plan);
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
await f.command("ready"); const before = f.messages.length;
|
|
await f.command("discuss"); expect(f.messages).toHaveLength(before);
|
|
});
|
|
|
|
it("automatically proposes a changed settled draft once and preserves Discuss", async () => {
|
|
const f = fixture(); await f.draft();
|
|
f.ctx.ui.select.mockResolvedValueOnce("Discuss");
|
|
await f.hooks.get("agent_settled")({}, f.ctx);
|
|
expect(f.messages.some(m => m.message.customType === "goal-plan-proposal" && m.message.content === f.plan)).toBe(true);
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
const calls = f.ctx.ui.select.mock.calls.length;
|
|
await f.hooks.get("agent_settled")({}, f.ctx);
|
|
expect(f.ctx.ui.select).toHaveBeenCalledTimes(calls);
|
|
writeFileSync(f.path, f.plan.replace("first output", "revised output"));
|
|
f.ctx.ui.select.mockResolvedValueOnce("Ready");
|
|
await f.hooks.get("agent_settled")({}, f.ctx);
|
|
expect(f.entries.at(-1).data.mode).toBe("supervising");
|
|
});
|
|
|
|
it("does not propose an empty draft or a delegated worker's plan", async () => {
|
|
const f = fixture(); await f.command("new");
|
|
await f.hooks.get("agent_settled")({}, f.ctx);
|
|
expect(f.ctx.ui.select).not.toHaveBeenCalled();
|
|
const child = fixture(true); await child.hooks.get("agent_settled")({}, child.ctx);
|
|
expect(child.ctx.ui.select).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("keeps Ready in the same chat, sends saved notices and never installs a context hook", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("review");
|
|
expect(f.entries.at(-1).data.mode).toBe("supervising");
|
|
expect(f.messages.at(-1).options).toEqual({ deliverAs: "followUp" });
|
|
expect(f.messages.at(-1).savedPrompt).toBe(true);
|
|
expect(f.messages.at(-1).message.content).toContain("goals-worker");
|
|
expect(f.hooks.has("context")).toBe(false);
|
|
const event = { systemPrompt: "original system" };
|
|
expect(f.hooks.get("before_agent_start")(event, f.ctx).systemPrompt).toContain("original system");
|
|
f.hooks.get("session_compact")();
|
|
expect(f.hooks.get("before_agent_start")(event, f.ctx).message.content).toContain("Current goal mode: supervising");
|
|
f.shutdown();
|
|
});
|
|
|
|
it("preserves a draft when the wrong subagent package is loaded, and offers explicit solo", async () => {
|
|
const f = fixture(); await f.draft(); f.pi.getAllTools.mockReturnValue([]);
|
|
await f.command("ready"); expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped");
|
|
await f.command("solo"); expect(f.entries.at(-1).data.mode).toBe("solo");
|
|
});
|
|
|
|
it("rejects a plan changed while the human was reviewing it", async () => {
|
|
const f = fixture(); await f.draft();
|
|
f.ctx.ui.select.mockImplementation(async () => { writeFileSync(f.path, "- [ ] goal: substituted\n"); return "Ready"; });
|
|
await f.command("review"); expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
});
|
|
|
|
it("reloads a paused plan without launching, and retains the public worker session handle", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "child-1", sessionFile: "/tmp/child.jsonl" });
|
|
await f.command("stop");
|
|
expect(f.messages.at(-1).message.content).toContain("Remote stop is NOT yet confirmed");
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
expect(f.hooks.get("tool_call")({ toolName: "subagent_resume" }).block).toBe(true);
|
|
await f.command("resume");
|
|
expect(f.messages.at(-1).message.content).toContain("/tmp/child.jsonl");
|
|
await f.command("exit"); expect(f.entries.at(-1).data.mode).toBe("chat");
|
|
expect(readFileSync(f.path, "utf8")).toContain("first output");
|
|
});
|
|
|
|
it.each(["FIRST OUTPUT", "renamed output", "duplicate", "historical"])("completion uses exact current subjects (%s)", async (subject) => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
const evidence = join(f.ctx.cwd, "verification.txt"); writeFileSync(evidence, "PASS");
|
|
const suffix = subject === "duplicate" ? "- [ ] goal: first output\n" : "";
|
|
const history = "## Log\n- [ ] goal: first output\n";
|
|
writeFileSync(f.path, "- [ ] goal: first output\n - [ ] unrelated task\n" + suffix + history);
|
|
const before = readFileSync(f.path, "utf8");
|
|
const params = { goal: subject === "duplicate" || subject === "historical" ? "first output" : subject, evidence: [evidence], observation: "Read actual output" };
|
|
const first = await f.tools.get("CompleteGoal").execute("c", params, undefined, undefined, f.ctx);
|
|
if (first.content[0].text.includes("Final review queued")) {
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
await f.tools.get("CompleteGoal").execute("c", params, undefined, undefined, f.ctx);
|
|
}
|
|
const after = readFileSync(f.path, "utf8");
|
|
if (subject === "renamed output" || subject === "duplicate") expect(after).toBe(before);
|
|
else { expect(after).toContain("- [x] goal: first output"); expect(after.split("## Log")[1]).toContain("\n- [ ] goal: first output\n"); expect(after).toContain("- [ ] unrelated task"); }
|
|
});
|
|
|
|
it("rejects an existing zero-byte evidence file", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
const evidence = join(f.ctx.cwd, "empty.log"); writeFileSync(evidence, "");
|
|
const before = readFileSync(f.path, "utf8");
|
|
const result = await f.tools.get("CompleteGoal").execute("c", { goal: "first output", evidence: [evidence], observation: "claim" }, undefined, undefined, f.ctx);
|
|
expect(result.content[0].text).toContain("Empty evidence"); expect(readFileSync(f.path, "utf8")).toBe(before);
|
|
});
|
|
|
|
it("requires actual nonempty evidence, distinguishes manual ticks, and retains signoffs on reload", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
const complete = (goal: string, evidence: string[], signal?: AbortSignal) => f.tools.get("CompleteGoal").execute("t", { goal, evidence, observation: "Inspected exact saved bytes" }, signal, undefined, f.ctx);
|
|
expect((await complete("first output", ["missing.log"])).content[0].text).toContain("Evidence unavailable");
|
|
mkdirSync(join(f.ctx.cwd, "evidence")); writeFileSync(join(f.ctx.cwd, "evidence/pass.log"), "actual fixture bytes\n");
|
|
expect((await complete("first output", ["evidence/pass.log"], AbortSignal.abort())).content[0].text).toContain("Cancelled");
|
|
await complete("first output", ["evidence/pass.log"]);
|
|
writeFileSync(f.path, readFileSync(f.path, "utf8").replace("[ ] goal: second", "[x] goal: second"));
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
expect(f.ctx.ui.setStatus).toHaveBeenLastCalledWith("goals", "👀 1/2 goals");
|
|
expect(f.ctx.ui.setWidget.mock.lastCall?.[1]).toContain("✓ G1: first output");
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
for (let i = 0; i < 9; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
const reminder = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message.content;
|
|
expect(reminder).toContain("[x] goal: second output");
|
|
expect(reminder).not.toContain("first output");
|
|
writeFileSync(f.path, readFileSync(f.path, "utf8").replace("[x] goal: first", "[ ] goal: first"));
|
|
f.hooks.get("agent_end")({}, f.ctx);
|
|
expect(f.ctx.ui.setStatus).toHaveBeenLastCalledWith("goals", "👀 0/2 goals");
|
|
f.shutdown();
|
|
});
|
|
|
|
it("reviews a plan replaced atomically with a current-file notice, and ignores writes that keep the same content", async () => {
|
|
const f = fixture(); await f.draft();
|
|
const plan = `# Context title
|
|
|
|
A short introduction for ordinary reminders.
|
|
|
|
## User-visible result
|
|
A visible artifact.
|
|
|
|
## User voice
|
|
- > "The full requirement must survive resync."
|
|
|
|
## Goals
|
|
- [ ] goal: produce the artifact
|
|
- tasks:
|
|
- [ ] run the detailed check
|
|
|
|
## Log
|
|
old progress`;
|
|
writeFileSync(f.path, plan); await f.command("ready");
|
|
const revised = plan.replace("A visible artifact.", "A revised visible artifact.");
|
|
await f.atomicWrite(revised);
|
|
await waitFor(() => f.changed() === 1);
|
|
const review = f.messages.find((m) => m.message.content.includes("Plan changed"))?.message.content;
|
|
expect(review).toContain("inspect current requirements");
|
|
expect(review).toContain(f.path);
|
|
expect(review).not.toContain("The full requirement must survive resync.");
|
|
expect(review).not.toContain("run the detailed check");
|
|
f.hooks.get("message_end")({ message: { role: "user", content: review } });
|
|
await f.atomicWrite(revised.replace("A revised", "A second revised"));
|
|
await waitFor(() => f.changed() === 2);
|
|
// Rewriting identical bytes must not retrigger the review event hook.
|
|
const same = revised.replace("A revised", "A second revised");
|
|
writeFileSync(f.path, same); await delay(300);
|
|
expect(f.changed()).toBe(2);
|
|
f.shutdown();
|
|
});
|
|
|
|
it("delivers changed plans while coalescing only its own pending notice", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.ctx.hasPendingMessages.mockReturnValue(true); // An unrelated queued prompt must not suppress the notice.
|
|
await f.atomicWrite(f.plan.replace("## Log", "- discriminator: first burst edit\n## Log"));
|
|
await f.atomicWrite(f.plan.replace("## Log", "- discriminator: second burst edit\n## Log"));
|
|
await waitFor(() => f.changed() === 1);
|
|
f.hooks.get("message_end")({ message: { role: "user", content: "unrelated input" } });
|
|
await f.atomicWrite(f.plan.replace("## Log", "- discriminator: later queued edit\n## Log"));
|
|
await delay(200);
|
|
expect(f.changed()).toBe(1);
|
|
f.hooks.get("message_end")({ message: { role: "user", content: f.messages.at(-1).message.content } });
|
|
await f.atomicWrite(f.plan.replace("## Log", "- discriminator: after same-run delivery\n## Log"));
|
|
await waitFor(() => f.changed() === 2);
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message.content).toContain("after same-run delivery");
|
|
f.hooks.get("message_end")({ message: { role: "user", content: f.messages.at(-1).message.content } });
|
|
await f.atomicWrite(f.plan.replaceAll("[ ] goal:", "[-] goal:"));
|
|
await waitFor(() => f.changed() === 3); // Cancelling the last goals must still notify an ongoing run.
|
|
f.shutdown();
|
|
});
|
|
|
|
it("stops plan watching on shutdown and re-arms it on reload without duplicating events", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.shutdown();
|
|
await f.atomicWrite(f.plan.replace("## Log", "- discriminator: ignored while shut down\n## Log"));
|
|
await delay(150);
|
|
expect(f.changed()).toBe(0);
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
await f.atomicWrite(f.plan.replace("## Log", "- discriminator: seen after reload\n## Log"));
|
|
await waitFor(() => f.changed() === 1);
|
|
expect(f.changed()).toBe(1);
|
|
f.shutdown();
|
|
});
|
|
|
|
it("does not retrigger a review for its own CompleteGoal plan write", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
mkdirSync(join(f.ctx.cwd, "evidence")); writeFileSync(join(f.ctx.cwd, "evidence/pass.log"), "bytes\n");
|
|
await f.tools.get("CompleteGoal").execute("t", { goal: "first output", evidence: ["evidence/pass.log"], observation: "inspected" }, undefined, undefined, f.ctx);
|
|
await delay(200);
|
|
expect(f.changed()).toBe(0);
|
|
f.shutdown();
|
|
});
|
|
|
|
it("gives pause scheduler guidance but clears on exit without a model prompt", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
await f.command("stop");
|
|
const stop = f.messages.at(-1).message.content;
|
|
expect(stop).toContain('goals-copy-only"');
|
|
expect(stop).toContain("Do not add, enable or recreate any job");
|
|
expect(stop).not.toContain("interval '1h'");
|
|
expect(stop).toContain("Remote stop is NOT yet confirmed");
|
|
await f.command("resume");
|
|
const before = f.messages.length;
|
|
await f.command("exit");
|
|
expect(f.messages).toHaveLength(before);
|
|
expect(f.entries.at(-1).data).toEqual({ mode: "chat", helpers: [], signoffs: {} });
|
|
});
|
|
|
|
it("requires a full-plan review turn before recording the final goal", async () => {
|
|
const f = fixture(); await f.draft();
|
|
const plan = `# Final review fixture
|
|
- [ ] goal: first output
|
|
- discriminator: first output has exact saved bytes
|
|
- [ ] goal: second output
|
|
- discriminator: second output has exact saved bytes
|
|
|
|
## Log
|
|
- worker evidence: keep this history in the final review`;
|
|
writeFileSync(f.path, plan); await f.command("ready");
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
mkdirSync(join(f.ctx.cwd, "evidence")); writeFileSync(join(f.ctx.cwd, "evidence/pass.log"), "bytes\n");
|
|
const complete = (goal: string) => f.tools.get("CompleteGoal").execute("t", { goal, evidence: ["evidence/pass.log"], observation: "inspected" }, undefined, undefined, f.ctx);
|
|
await complete("first output");
|
|
const queued = await complete("second output");
|
|
expect(queued.content[0].text).toContain("Final review queued");
|
|
expect(readFileSync(f.path, "utf8")).toContain("- [ ] goal: second output");
|
|
const direct = f.messages.at(-1);
|
|
expect(direct.savedPrompt).toBe(true);
|
|
expect(direct.message.content).toContain("Read the complete file at");
|
|
expect(direct.message.content).not.toContain("worker evidence: keep this history");
|
|
// A queued follow-up may be consumed without another before_agent_start.
|
|
f.hooks.get("message_end")({ message: { role: "user", content: direct.message.content } });
|
|
expect(readFileSync(f.path, "utf8")).toContain("second output has exact saved bytes");
|
|
f.hooks.get("turn_end")({}, f.ctx); // Evidence-reading tool round must not invalidate this review.
|
|
const finalText = (await complete("second output")).content[0].text;
|
|
expect(finalText).toContain("All non-cancelled goals are reviewed.");
|
|
expect(finalText).toContain('job named "goals-copy-only"');
|
|
expect(finalText).toContain("leave other jobs untouched");
|
|
for (let i = 0; i < 10; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message).toBeUndefined();
|
|
f.shutdown();
|
|
});
|
|
|
|
it("recovers a queued final review and invalidates it when the plan changes", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
const complete = (goal: string) => f.tools.get("CompleteGoal").execute("t", { goal, evidence: ["proof.log"], observation: "inspected" }, undefined, undefined, f.ctx);
|
|
await complete("first output");
|
|
await complete("second output");
|
|
const oldPrompt = f.messages.at(-1).message.content;
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
const recovered = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message;
|
|
expect(recovered).toMatchObject({ customType: "pi-goals-final-review" });
|
|
expect(recovered.content).toContain("- [ ] goal: second output");
|
|
writeFileSync(f.path, readFileSync(f.path, "utf8").replace("## Log", " - discriminator: changed exact bytes\n## Log"));
|
|
const invalidated = await complete("second output");
|
|
expect(invalidated.content[0].text).toContain("plan changed since the final review");
|
|
const changed = await complete("second output");
|
|
expect(changed.content[0].text).toContain("Final review queued");
|
|
expect(readFileSync(f.path, "utf8")).toContain("- [ ] goal: second output");
|
|
expect(f.messages.at(-1).message.content).toContain("second output");
|
|
f.hooks.get("message_end")({ message: { role: "user", content: oldPrompt } });
|
|
expect((await complete("second output")).content[0].text).toContain("Final review queued");
|
|
f.shutdown();
|
|
});
|
|
|
|
it("restores the active plan above Log after session restore", async () => {
|
|
const f = fixture(); await f.draft();
|
|
const plan = `${f.plan.replace("## Log", "## User voice\n- > \"Keep the user voice after restore.\"\n## Log")}old progress`;
|
|
writeFileSync(f.path, plan); await f.command("ready");
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
const restored = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(restored.message.content).toContain("Keep the user voice after restore.");
|
|
expect(restored.message.content).not.toContain("old progress");
|
|
});
|
|
|
|
it("restores the active plan above Log after compaction without reinstalling or overriding scheduler jobs", async () => {
|
|
const f = fixture(); await f.draft();
|
|
const plan = `${f.plan.replace("## Log", "## User voice\n- > \"Keep this exact requirement.\"\n - task detail\n## Log")}old progress`;
|
|
writeFileSync(f.path, plan); await f.command("ready");
|
|
f.hooks.get("session_compact")();
|
|
const result = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(result.systemPrompt).not.toContain("add one session-bound");
|
|
expect(result.message.content).toContain("Keep this exact requirement.");
|
|
expect(result.message.content).toContain("task detail");
|
|
expect(result.message.content).not.toContain("old progress");
|
|
expect(result.message.content).toContain(f.path);
|
|
});
|
|
|
|
it("recovers from an unreadable plan after compaction instead of restarting work", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
rmSync(f.path);
|
|
f.hooks.get("session_compact")();
|
|
const result = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(result.systemPrompt).toContain("ENOENT");
|
|
expect(result.systemPrompt).toContain("do not restart completed work");
|
|
writeFileSync(f.path, f.plan);
|
|
const restored = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message.content;
|
|
expect(restored).toContain("- [ ] goal: first output");
|
|
expect(restored).toContain(f.path);
|
|
f.shutdown();
|
|
});
|
|
|
|
it("requires confirmed worker stop before solo takeover and never lets two writers run together", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "child-1", sessionFile: "/tmp/child.jsonl" });
|
|
f.ctx.ui.select.mockResolvedValueOnce("Cancel");
|
|
await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("supervising"); // cancelled
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped");
|
|
await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("solo");
|
|
expect(f.hooks.get("tool_call")({ toolName: "subagent" }).block).toBe(true);
|
|
expect(f.hooks.get("tool_call")({ toolName: "subagent_resume" }).block).toBe(true);
|
|
expect(f.hooks.get("tool_call")({ toolName: "subagent_kill" })).toBeUndefined();
|
|
mkdirSync(join(f.ctx.cwd, "evidence")); writeFileSync(join(f.ctx.cwd, "evidence/pass.log"), "bytes\n");
|
|
const text = (await f.tools.get("CompleteGoal").execute("t", { goal: "first output", evidence: ["evidence/pass.log"], observation: "inspected" }, undefined, undefined, f.ctx)).content[0].text;
|
|
expect(text).toContain("self-verification");
|
|
});
|
|
|
|
it("attaches an existing plan without restarting completed work, and restores its noted worker session", async () => {
|
|
const f = fixture();
|
|
const existing = join(f.ctx.cwd, "existing.md");
|
|
writeFileSync(existing, "# Plan\n- preferred worker model: deepseek flash\n- worker session: /tmp/attach-child.jsonl\n- [ ] goal: attached goal\n\n## Log\n- previous progress kept\n");
|
|
f.ctx.ui.select.mockResolvedValueOnce("Previous supervisor confirmed stopped");
|
|
await f.command(`attach ${existing}`);
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
expect(f.entries.at(-1).data.plan).toBe(existing);
|
|
expect(f.messages.at(-1).message.content).toContain("without restarting completed work");
|
|
expect(f.messages.at(-1).message.content).toContain("/tmp/attach-child.jsonl");
|
|
});
|
|
|
|
it("attaches directly into solo mode and reports the recorded session in status", async () => {
|
|
const f = fixture();
|
|
const existing = join(f.ctx.cwd, "existing.md");
|
|
writeFileSync(existing, "# Plan\n- worker session: /tmp/attach-child.jsonl\n- [ ] goal: attached goal\n\n## Log\n");
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped");
|
|
await f.command(`attach ${existing} solo`);
|
|
expect(f.entries.at(-1).data.mode).toBe("solo");
|
|
expect(f.entries.at(-1).data.worker?.sessionFile).toBe("/tmp/attach-child.jsonl");
|
|
await f.command("status");
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("/tmp/attach-child.jsonl"), "info");
|
|
});
|
|
|
|
it("rejects attaching a missing or goal-less file", async () => {
|
|
const f = fixture();
|
|
await f.command("attach /no/such/plan.md");
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("Cannot read plan"), "error");
|
|
const goalLess = join(f.ctx.cwd, "notes.md");
|
|
writeFileSync(goalLess, "# notes\n");
|
|
await f.command(`attach ${goalLess}`);
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("has no '- [ ] goal:' lines"), "warning");
|
|
expect(f.entries).toEqual([]); // nothing saved: the session was not attached
|
|
});
|
|
|
|
it.each(["exit", "quit", "clear", "menu"])("%s exits planning with the draft preserved and nothing implemented", async command => {
|
|
const f = fixture(); await f.draft();
|
|
await f.command("stop");
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("A draft cannot pause"), "warning");
|
|
const before = f.messages.length;
|
|
if (command === "menu") f.ctx.ui.select.mockResolvedValueOnce("quit — Exit and clear goals");
|
|
await f.command(command === "menu" ? "" : command);
|
|
expect(f.entries.at(-1).data.mode).toBe("chat");
|
|
expect(f.ctx.ui.setWidget).toHaveBeenLastCalledWith("goals", undefined);
|
|
expect(readFileSync(f.path, "utf8")).toContain("first output");
|
|
expect(f.messages.length).toBe(before); // notify only, no model turn started
|
|
f.ctx.ui.select.mockResolvedValueOnce("Previous supervisor confirmed stopped");
|
|
await f.command(`attach ${f.path}`);
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
});
|
|
|
|
it("records the preferred worker model as a visible plan preference", async () => {
|
|
const f = fixture(); await f.draft();
|
|
await f.command("model deepseek flash");
|
|
expect(readFileSync(f.path, "utf8")).toContain("- preferred worker model: deepseek flash");
|
|
await f.command("status");
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("deepseek flash"), "info");
|
|
});
|
|
|
|
it.each(["solo", "attach"])("%s takeover cannot bypass confirmation or survive a lifecycle change during the menu", async kind => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "child", sessionFile: "/tmp/prior.jsonl" });
|
|
let answer!: (choice: string) => void;
|
|
f.ctx.ui.select.mockImplementationOnce(() => new Promise(resolve => { answer = resolve; }));
|
|
const takeover = f.command(kind === "solo" ? "solo" : `attach ${f.path} solo`);
|
|
expect(f.entries.at(-1).data.mode).toBe("supervising");
|
|
await f.command("stop");
|
|
answer("Worker confirmed stopped"); await takeover;
|
|
expect(f.entries.at(-1).data.mode).toBe("paused");
|
|
expect(f.entries.at(-1).data.workerStopped).not.toBe(true);
|
|
});
|
|
|
|
it("attach solo requires stop confirmation for a noted worker even in a fresh session", async () => {
|
|
const f = fixture(); const path = join(f.ctx.cwd, "saved.md");
|
|
writeFileSync(path, `# Plan\n- worker session: /tmp/known.jsonl\n${f.plan}`);
|
|
f.ctx.ui.select.mockResolvedValueOnce("Cancel");
|
|
await f.command(`attach ${path} solo`);
|
|
expect(f.entries).toHaveLength(0);
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped");
|
|
await f.command(`attach ${path} solo`);
|
|
expect(f.entries.at(-1).data).toMatchObject({ mode: "solo", workerStopped: true, worker: { sessionFile: "/tmp/known.jsonl" } });
|
|
expect(readFileSync(path, "utf8")).toContain("worker session: /tmp/known.jsonl");
|
|
});
|
|
|
|
it("retains the stopped session reference without permanently blocking another plan", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "child", sessionFile: "/tmp/prior.jsonl" });
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
const other = join(f.ctx.cwd, "another.md"); writeFileSync(other, "- [ ] goal: next\n## Log\n");
|
|
f.ctx.ui.select.mockResolvedValueOnce("Previous supervisor confirmed stopped");
|
|
await f.command(`attach ${other}`);
|
|
expect(f.entries.at(-1).data).toMatchObject({ mode: "planning", plan: other, workerStopped: true, worker: { sessionFile: "/tmp/prior.jsonl" } });
|
|
await f.command("ready");
|
|
f.start("resume", { sessionFile: "/tmp/prior.jsonl" }, "subagent_resume");
|
|
expect(f.entries.at(-1).data.workerStopped).toBe(false);
|
|
await f.command("solo");
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("still pending"), "warning");
|
|
});
|
|
|
|
it("solo closes a pending plan watcher and sends removal-only scheduler guidance", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
await f.atomicWrite(f.plan.replace("first output", "changed output"));
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
expect(f.messages.at(-1).message.content).toContain('job named "goals-copy-only" bound to session "copy-only"');
|
|
expect(f.messages.at(-1).message.content).toContain("Do not add, enable or recreate any job");
|
|
await delay(250);
|
|
await f.atomicWrite(f.plan.replace("first output", "solo output"));
|
|
await delay(250);
|
|
expect(f.changed()).toBe(0);
|
|
});
|
|
|
|
it.each(["missing", "empty", "directory"])("%s plan snapshots never erase signoffs and resync retries after repair", async failure => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
await f.tools.get("CompleteGoal").execute("c", { goal: "first output", evidence: ["proof.log"], observation: "Observed PASS" }, undefined, undefined, f.ctx);
|
|
const signed = readFileSync(f.path, "utf8");
|
|
if (failure === "empty") writeFileSync(f.path, "");
|
|
else { rmSync(f.path); if (failure === "directory") mkdirSync(f.path); }
|
|
await delay(250); // also exercise unavailable read after debounce has expired
|
|
f.hooks.get("agent_end")({}, f.ctx);
|
|
expect(f.entries.at(-1).data.signoffs["first output"]).toBeDefined();
|
|
f.hooks.get("session_compact")();
|
|
const unavailable = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(unavailable.systemPrompt).toContain("unavailable");
|
|
expect(unavailable.message).toBeUndefined();
|
|
if (failure === "directory") rmSync(f.path, { recursive: true });
|
|
writeFileSync(f.path, signed);
|
|
const resync = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(resync.message.content).toContain("- [x] goal: first output");
|
|
expect(readFileSync(f.path, "utf8")).toContain("Observed PASS");
|
|
await delay(250);
|
|
expect(f.entries.at(-1).data.signoffs["first output"]).toBeDefined();
|
|
expect(f.changed()).toBe(0);
|
|
});
|
|
|
|
it("ignores post-completion maintenance but reviews evidence, requirement or manual reopening changes", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
for (const goal of ["first output", "second output"]) await f.tools.get("CompleteGoal").execute("c", { goal, evidence: ["proof.log"], observation: "PASS" }, undefined, undefined, f.ctx);
|
|
const signed = readFileSync(f.path, "utf8");
|
|
await f.atomicWrite(signed.replace("## Log", "## Log\n- recap: finished"));
|
|
await delay(250);
|
|
expect(f.changed()).toBe(0); // Log-only edits are history, not requirements
|
|
// Worker-authored evidence above the Log must surface: a supervisor caught a worker's
|
|
// contradictory evidence block through exactly this event (LUCID3, 2026-09-10).
|
|
await f.atomicWrite(signed.replace("## Log", " - evidence: proof.log\n## Log\n- recap: finished"));
|
|
await waitFor(() => f.changed() === 1);
|
|
f.hooks.get("message_end")({ message: { role: "user", content: f.messages.at(-1).message.content } });
|
|
await f.atomicWrite(signed.replace("## Log", "- discriminator: exact bytes and trailing newline\n## Log"));
|
|
await waitFor(() => f.changed() === 2);
|
|
f.hooks.get("message_end")({ message: { role: "user", content: f.messages.at(-1).message.content } });
|
|
await f.atomicWrite(signed.replace("[x] goal: first", "[ ] goal: first"));
|
|
await waitFor(() => f.changed() === 3);
|
|
expect(f.entries.at(-1).data.signoffs["first output"]).toBeUndefined();
|
|
});
|
|
|
|
it("cancelled goals do not prevent final cleanup, and solo writes self-verification in Log", async () => {
|
|
const f = fixture(); await f.draft();
|
|
writeFileSync(f.path, f.plan.replace("[ ] goal: second", "[-] goal: second") + "\n## Appendix\nPreserved context\n");
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
const params = { goal: "first output", evidence: ["proof.log"], observation: "Exact bytes observed" };
|
|
const queued = await f.tools.get("CompleteGoal").execute("c", params, undefined, undefined, f.ctx);
|
|
expect(queued.content[0].text).toContain("Final review queued");
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
const done = await f.tools.get("CompleteGoal").execute("c", params, undefined, undefined, f.ctx);
|
|
expect(done.content[0].text).toContain("All non-cancelled goals are reviewed");
|
|
const text = readFileSync(f.path, "utf8");
|
|
expect(text).toContain("Solo self-verification:");
|
|
expect(text).not.toContain("Parent review:");
|
|
expect(text.indexOf("Solo self-verification:")).toBeLessThan(text.indexOf("## Appendix"));
|
|
expect(text).toContain("Preserved context");
|
|
});
|
|
|
|
it("prefixes single and batch launch titles with the project without changing handles or duplicating prefixes", () => {
|
|
const f = fixture();
|
|
const single = { name: "report-worker", title: "Restore PCA" };
|
|
const event = { toolName: "subagent", input: single };
|
|
f.hooks.get("tool_call")(event, f.ctx);
|
|
const expected = `${f.ctx.cwd.split("/").at(-1)} · Restore PCA`;
|
|
expect(single).toEqual({ name: "report-worker", title: expected });
|
|
f.hooks.get("tool_call")(event, f.ctx);
|
|
expect(single.title).toBe(expected);
|
|
const children = [{ name: "test-worker", title: "Check results" }, { ...single }];
|
|
f.hooks.get("tool_call")({ toolName: "subagent", input: { children } }, f.ctx);
|
|
expect(children[0].title).toBe(`${f.ctx.cwd.split("/").at(-1)} · Check results`);
|
|
expect(children[1]).toEqual(single);
|
|
});
|
|
|
|
it("lineage-only child attaches its plan without a widget, retains task context, and cannot complete", async () => {
|
|
const f = fixture(true);
|
|
const supplied = join(f.ctx.cwd, "supplied.md");
|
|
const text = "- [/] goal: exact file\n - [ ] verify bytes\n## Log\n - [ ] archived task\n";
|
|
writeFileSync(supplied, text);
|
|
const before = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(before.systemPrompt).toContain("AttachGoalPlan");
|
|
const attach = f.tools.get("AttachGoalPlan");
|
|
await attach.execute("a", { path: "supplied.md" }, undefined, undefined, f.ctx);
|
|
expect(f.entries.at(-1).data.plan).toBeUndefined(); // no cwd heuristics
|
|
await attach.execute("a", { path: supplied }, undefined, undefined, f.ctx);
|
|
expect(f.ctx.ui.setWidget).toHaveBeenLastCalledWith("goals", undefined);
|
|
expect(readFileSync(supplied, "utf8")).toBe(text);
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
expect(f.ctx.ui.setWidget).toHaveBeenLastCalledWith("goals", undefined);
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message.content).toContain("exact file");
|
|
const completion = await f.tools.get("CompleteGoal").execute("c", { goal: "exact file", evidence: [], observation: "claim" }, undefined, undefined, f.ctx);
|
|
expect(completion.content[0].text).toContain("only to the active parent");
|
|
});
|
|
|
|
it("prioritizes unfinished goals and says when the widget list is truncated", async () => {
|
|
const f = fixture(); await f.draft();
|
|
writeFileSync(f.path, "- [x] goal: completed one\n- [x] goal: completed two\n- [/] goal: active work\n- [ ] goal: open one\n- [ ] goal: open two\n");
|
|
await f.command("ready");
|
|
expect(f.ctx.ui.setWidget.mock.lastCall?.[1]).toEqual([relative(f.ctx.cwd, f.path), "◼ G3: active work", "◻ G4: open one", "◻ G5: open two", "… 2 ✓"]);
|
|
f.shutdown();
|
|
});
|
|
|
|
it.each([
|
|
["[x]", "[ ]", "[ ]", "… 1 ✓, 2 ◻"],
|
|
["[/]", "[x]", "[-]", "… 1 ✓, 1 ◼, 1 ✗"],
|
|
["[ ]", "[ ]", "[ ]", "… 3 ◻"],
|
|
])("summarizes only hidden goal statuses: %s %s %s", async (first, second, third, summary) => {
|
|
const f = fixture(); await f.draft();
|
|
const marks = ["[/]", "[/]", "[/]", first, second, third];
|
|
writeFileSync(f.path, marks.map((mark, index) => `- ${mark} goal: output ${index + 1}`).join("\n"));
|
|
await f.command("ready");
|
|
expect(f.ctx.ui.setWidget.mock.lastCall?.[1]).toEqual([
|
|
relative(f.ctx.cwd, f.path), "◼ G1: output 1", "◼ G2: output 2", "◼ G3: output 3", summary,
|
|
]);
|
|
f.shutdown();
|
|
});
|
|
|
|
it.each(["solo", "supervising"])("%s widget omits long tasks without altering the plan", async mode => {
|
|
const f = fixture(); await f.draft();
|
|
const text = "- [/] goal: first output\n - [ ] a long task that should never take widget space\n- [ ] goal: second output\n## Log\n";
|
|
writeFileSync(f.path, text);
|
|
if (mode === "solo") { f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo"); }
|
|
else await f.command("ready");
|
|
expect(f.ctx.ui.setWidget.mock.lastCall?.[1]).toEqual([relative(f.ctx.cwd, f.path), "◼ G1: first output", "◻ G2: second output"]);
|
|
expect(readFileSync(f.path, "utf8")).toBe(text);
|
|
});
|
|
|
|
it.each(["solo", "supervising"])("%s upkeep is turn-driven, folds Log, and joins the next ordinary prompt once", async mode => {
|
|
const f = fixture(); await f.draft();
|
|
if (mode === "solo") { f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo"); }
|
|
else await f.command("ready");
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
const reminders = () => f.messages.filter(m => m.message.customType === "pi-goals-upkeep");
|
|
f.hooks.get("turn_end")({}, f.ctx); // observe initial working set
|
|
for (let i = 0; i < 7; i++) {
|
|
writeFileSync(f.path, f.plan + `- historical recap ${i}\n`);
|
|
f.hooks.get("turn_end")({}, f.ctx);
|
|
}
|
|
expect(reminders()).toHaveLength(0);
|
|
f.hooks.get("turn_end")({}, f.ctx);
|
|
for (let i = 0; i < 16; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
expect(reminders()).toHaveLength(0); // No direct send, even after the run would finish.
|
|
const reminder = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message;
|
|
expect(reminder.customType).toBe("pi-goals-upkeep");
|
|
expect(reminder.content).toContain(f.path);
|
|
expect(reminder.content).toContain("first output");
|
|
expect(reminder.content).not.toContain("historical recap");
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message).toBeUndefined();
|
|
writeFileSync(f.path, f.plan.replace("first output", "refined output"));
|
|
f.hooks.get("turn_end")({}, f.ctx);
|
|
for (let i = 0; i < 7; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message.content).toContain("refined output");
|
|
await f.command("stop");
|
|
for (let i = 0; i < 10; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
expect(reminders()).toHaveLength(0);
|
|
});
|
|
|
|
it("injects only unfinished goal lines after the bounded unchanged-turn reminder", async () => {
|
|
const f = fixture(); await f.draft();
|
|
const plan = `# Context title
|
|
|
|
A short introduction.
|
|
|
|
## User-visible result
|
|
A visible artifact.
|
|
|
|
## User voice
|
|
- > "Keep this exact user requirement."
|
|
|
|
## Goals
|
|
- [/] goal: produce the artifact
|
|
- tasks:
|
|
- [ ] run the detailed check
|
|
- evidence: proof.log
|
|
|
|
## Log
|
|
old progress`;
|
|
writeFileSync(f.path, plan); await f.command("ready");
|
|
// Consume active context before observing the routine reminder.
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
for (let i = 0; i < 9; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
const reminder = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message;
|
|
expect(reminder.customType).toBe("pi-goals-upkeep");
|
|
expect(reminder.content).not.toContain("Keep this exact user requirement.");
|
|
expect(reminder.content).toContain("goal: produce the artifact");
|
|
expect(reminder.content).not.toContain("run the detailed check");
|
|
expect(reminder.content).not.toContain("proof.log");
|
|
expect(reminder.content).not.toContain("old progress");
|
|
});
|
|
|
|
it.each(["supervising", "solo"])("%s repeats concise upkeep every eight unchanged turns", async mode => {
|
|
const f = fixture(); await f.draft();
|
|
if (mode === "solo") { f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo"); }
|
|
else await f.command("ready");
|
|
const prepare = () => f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
prepare();
|
|
for (let i = 0; i < 9; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
f.hooks.get("session_compact")();
|
|
expect(prepare().message.customType).toBe("pi-goals-plan");
|
|
const sent = f.messages.length;
|
|
for (let round = 0; round < 2; round++) {
|
|
for (let turn = 0; turn < 7; turn++) f.hooks.get("turn_end")({}, f.ctx);
|
|
expect(prepare().message).toBeUndefined();
|
|
f.hooks.get("turn_end")({}, f.ctx);
|
|
expect(f.messages).toHaveLength(sent);
|
|
expect(prepare().message).toMatchObject({
|
|
customType: "pi-goals-upkeep",
|
|
content: upkeep(f.path, f.plan.split("\n").filter(line => line.includes("goal:")).join("\n")),
|
|
});
|
|
expect(prepare().message).toBeUndefined();
|
|
}
|
|
});
|
|
|
|
it("extra subagent launches are recorded as helpers and never steal the implementation identity", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "impl", sessionFile: "/tmp/impl.jsonl" });
|
|
expect(f.entries.at(-1).data).toMatchObject({ worker: { id: "impl", sessionFile: "/tmp/impl.jsonl" }, helpers: [] });
|
|
f.launch({ id: "reviewer", sessionFile: "/tmp/review.jsonl" }, "reviewer");
|
|
expect(f.entries.at(-1).data).toMatchObject({ worker: { id: "impl" }, helpers: [{ id: "reviewer", sessionFile: "/tmp/review.jsonl" }] });
|
|
// a repeated helper launch updates its record instead of duplicating it
|
|
f.launch({ id: "reviewer-2", sessionFile: "/tmp/review.jsonl" }, "reviewer");
|
|
expect(f.entries.at(-1).data.helpers).toEqual([{ id: "reviewer-2", sessionFile: "/tmp/review.jsonl" }]);
|
|
// resuming the worker keeps the binding and refreshes its id
|
|
f.launch({ id: "impl-2", sessionFile: "/tmp/impl.jsonl" }, "goals-worker", "subagent_resume");
|
|
expect(f.entries.at(-1).data).toMatchObject({ worker: { id: "impl-2", sessionFile: "/tmp/impl.jsonl" }, helpers: [{ id: "reviewer-2" }] });
|
|
});
|
|
|
|
it("pending call IDs survive concurrent launches until every execution ends", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.start("call-a");
|
|
f.start("call-b", { agent: "reviewer", title: "Review" });
|
|
f.finish("call-a", { id: "a", sessionFile: "/tmp/a.jsonl" });
|
|
f.finish("untracked", { id: "noise", sessionFile: "/tmp/noise.jsonl" });
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped");
|
|
await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("supervising"); // one launch still pending
|
|
expect(f.ctx.notify ?? f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("still pending"), "warning");
|
|
f.finish("call-b", { id: "b", sessionFile: "/tmp/b.jsonl" });
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped");
|
|
await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("solo");
|
|
expect(f.entries.at(-1).data).toMatchObject({ worker: { id: "a" }, helpers: [{ id: "b" }] });
|
|
});
|
|
|
|
it("a launch started during takeover invalidates the menu without disabling plan watching", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
let answer!: (choice: string) => void;
|
|
f.ctx.ui.select.mockImplementationOnce(() => new Promise(resolve => { answer = resolve; }));
|
|
const solo = f.command("solo");
|
|
f.launch({ id: "late-child", sessionFile: "/tmp/late.jsonl" });
|
|
answer("Worker confirmed stopped"); await solo;
|
|
expect(f.entries.at(-1).data.mode).toBe("supervising");
|
|
expect(f.entries.at(-1).data.workerStopped).toBe(false);
|
|
await f.atomicWrite(f.plan.replace("first output", "new requirement"));
|
|
await waitFor(() => f.changed() === 1);
|
|
});
|
|
|
|
it("changed plan or shutdown during takeover never grants solo permission", async () => {
|
|
const f = fixture(); await f.draft();
|
|
f.ctx.ui.select.mockImplementationOnce(async () => { writeFileSync(f.path, f.plan.replace("first", "changed")); return "Worker confirmed stopped"; });
|
|
await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("Plan changed during takeover"), "warning");
|
|
f.ctx.ui.select.mockImplementationOnce(async () => { f.shutdown(); return "Worker confirmed stopped"; });
|
|
await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
});
|
|
|
|
it("requires explicit supervisor ownership confirmation when attaching an existing plan", async () => {
|
|
const f = fixture(); const path = join(f.ctx.cwd, "shared.md");
|
|
writeFileSync(path, f.plan);
|
|
f.ctx.ui.select.mockResolvedValueOnce("Cancel");
|
|
await f.command(`attach ${path}`);
|
|
expect(f.entries).toHaveLength(0);
|
|
f.ctx.ui.select.mockResolvedValueOnce("Previous supervisor confirmed stopped");
|
|
await f.command(`attach ${path}`);
|
|
expect(f.entries.at(-1).data).toMatchObject({ mode: "planning", plan: path });
|
|
});
|
|
|
|
it("does not approve cancelled goals or display current completion for an unavailable plan", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(f.path, "- [-] goal: cancelled output\n## Log\n");
|
|
writeFileSync(join(f.ctx.cwd, "evidence.log"), "verified\n");
|
|
const reply = await f.tools.get("CompleteGoal").execute("t", { goal: "cancelled output", evidence: ["evidence.log"], observation: "read" }, undefined, undefined, f.ctx);
|
|
expect(reply.content[0].text).toContain("no sign-off recorded");
|
|
expect(readFileSync(f.path, "utf8")).toContain("[-]");
|
|
rmSync(f.path);
|
|
f.hooks.get("agent_end")({}, f.ctx);
|
|
expect(f.ctx.ui.setWidget).toHaveBeenLastCalledWith("goals", [expect.stringContaining("unavailable")]);
|
|
});
|
|
|
|
it("keeps interactive workers open", () => {
|
|
const agent = readFileSync(new URL("../agents/goals-worker.md", import.meta.url), "utf8");
|
|
expect(agent).toContain("auto-exit: false");
|
|
});
|
|
|
|
it.each(["stop", "exit", "edit", "session_tree"])("discards pending upkeep after %s instead of reviving stale work", async change => {
|
|
const f = fixture(); await f.draft();
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
for (let i = 0; i < 9; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
if (change === "edit") writeFileSync(f.path, f.plan.replace("first output", "changed requirement"));
|
|
else if (change === "session_tree") f.hooks.get("session_tree")({}, f.ctx);
|
|
else await f.command(change);
|
|
const prepared = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(prepared?.message?.customType).not.toBe("pi-goals-upkeep");
|
|
if (change === "stop") expect(prepared.systemPrompt).toContain("Goal work is paused");
|
|
if (change === "exit") expect(prepared).toBeUndefined();
|
|
expect(f.messages.filter(m => m.message.customType === "pi-goals-upkeep")).toHaveLength(0);
|
|
});
|
|
|
|
it("coalesces pending upkeep with a repaired post-compaction plan, retaining the user's latest requirements", async () => {
|
|
const f = fixture(); await f.draft();
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
for (let i = 0; i < 9; i++) f.hooks.get("turn_end")({}, f.ctx);
|
|
f.hooks.get("session_compact")();
|
|
rmSync(f.path);
|
|
const unavailable = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(unavailable.message).toBeUndefined();
|
|
expect(unavailable.systemPrompt).toContain("unavailable");
|
|
const repaired = f.plan.replace("first output", "the human's latest exact result");
|
|
writeFileSync(f.path, repaired);
|
|
const ready = f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx);
|
|
expect(ready.message).toMatchObject({ customType: "pi-goals-plan" });
|
|
expect(ready.message.content).toContain("the human's latest exact result");
|
|
expect(readFileSync(f.path, "utf8")).toBe(repaired);
|
|
expect(ready.message.content).not.toContain("Plan upkeep:");
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).message).toBeUndefined();
|
|
});
|
|
|
|
it("real SessionManager preserves historical state and restores draft authority before Ready", async () => {
|
|
const f = fixture();
|
|
const session = SessionManager.inMemory(f.ctx.cwd);
|
|
f.pi.appendEntry = (type: string, data: unknown) => { session.appendCustomEntry(type, data); return 0; };
|
|
f.ctx.sessionManager.getBranch = () => session.getBranch();
|
|
await f.draft();
|
|
const latestState = () => session.getBranch().filter(entry => entry.type === "custom" && entry.customType === "pi-goals-main-supervisor-v1").at(-1) as any;
|
|
const planned = latestState();
|
|
await f.command("ready");
|
|
expect(planned.data.mode).toBe("planning");
|
|
expect(latestState().data).not.toBe(planned.data);
|
|
expect(latestState().data.mode).toBe("supervising");
|
|
session.branch(planned.id);
|
|
f.hooks.get("session_tree")({ newLeafId: planned.id }, f.ctx);
|
|
expect(f.start("after-tree")?.block).toBe(true);
|
|
expect(f.hooks.get("before_agent_start")({ systemPrompt: "base" }, f.ctx).systemPrompt).toContain("Plan only in");
|
|
});
|
|
|
|
it("serializes CompleteGoal after a real built-in edit without losing either successful update", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
let reportRead!: () => void; const readStarted = new Promise<void>(resolve => { reportRead = resolve; });
|
|
let release!: () => void; const continueRead = new Promise<void>(resolve => { release = resolve; });
|
|
const edit = createEditTool(f.ctx.cwd, { operations: {
|
|
access: path => access(path),
|
|
readFile: async path => { const bytes = await readFile(path); reportRead(); await continueRead; return bytes; },
|
|
writeFile: (path, text) => writeFile(path, text, "utf8"),
|
|
} });
|
|
const editing = edit.execute("edit", { path: f.path, edits: [{ oldText: "# Plan", newText: "# Plan with progress note" }] });
|
|
await readStarted;
|
|
const completing = f.tools.get("CompleteGoal").execute("complete", { goal: "first output", evidence: ["proof.log"], observation: "Read PASS" }, undefined, undefined, f.ctx);
|
|
release();
|
|
await editing; await completing;
|
|
const text = readFileSync(f.path, "utf8");
|
|
expect(text).toContain("# Plan with progress note");
|
|
expect(text).toContain("- [x] goal: first output");
|
|
expect(text).toContain("Parent review:");
|
|
expect(f.entries.at(-1).data.signoffs["first output"]).toBeDefined();
|
|
});
|
|
|
|
it.each(["pause", "replace", "tree", "cancel"])("rejects queued completion after %s while waiting for a file mutation", async change => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
let entered!: () => void; const held = new Promise<void>(resolve => { entered = resolve; });
|
|
let release!: () => void; const wait = new Promise<void>(resolve => { release = resolve; });
|
|
const holding = withFileMutationQueue(f.path, async () => { entered(); await wait; });
|
|
await held;
|
|
const abort = new AbortController();
|
|
const completing = f.tools.get("CompleteGoal").execute("complete", { goal: "first output", evidence: ["proof.log"], observation: "Read PASS" }, abort.signal, undefined, f.ctx);
|
|
if (change === "pause") await f.command("stop");
|
|
if (change === "replace") { await f.command("exit"); await f.command("new different output"); }
|
|
if (change === "tree") f.hooks.get("session_tree")({}, f.ctx);
|
|
if (change === "cancel") abort.abort();
|
|
const current = f.entries.at(-1).data.plan;
|
|
const before = readFileSync(current, "utf8");
|
|
release(); await holding;
|
|
const response = await completing;
|
|
expect(response.content[0].text).not.toContain("Recorded parent judgment");
|
|
expect(readFileSync(f.path, "utf8")).toBe(f.plan);
|
|
expect(readFileSync(current, "utf8")).toBe(before);
|
|
expect(f.entries.at(-1).data.signoffs).toEqual({});
|
|
});
|
|
|
|
it.each([true, false])("solo stop/reload/resume preserves ownership with companion tools=%s", async tools => {
|
|
const f = fixture(); await f.draft();
|
|
if (!tools) f.pi.getAllTools.mockReturnValue([]);
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
await f.command("stop"); await f.command("stop");
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
expect(f.entries.at(-1).data.pausedFrom).toBe("solo");
|
|
await f.command("resume");
|
|
expect(f.entries.at(-1).data.mode).toBe("solo");
|
|
expect(f.start("forbidden")?.block).toBe(true);
|
|
});
|
|
|
|
it("rejects blank goal subjects on Ready and CompleteGoal", async () => {
|
|
const f = fixture(); await f.draft();
|
|
writeFileSync(f.path, "# Plan\n- [ ] goal: \n- [ ] goal: valid\n## Log\n");
|
|
await f.command("ready");
|
|
expect(f.entries.at(-1).data.mode).toBe("planning");
|
|
writeFileSync(f.path, f.plan); await f.command("ready");
|
|
writeFileSync(f.path, "# Plan\n- [ ] goal: \n## Log\n");
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
const before = readFileSync(f.path, "utf8");
|
|
await f.tools.get("CompleteGoal").execute("blank", { goal: " ", evidence: ["proof.log"], observation: "Read PASS" }, undefined, undefined, f.ctx);
|
|
expect(readFileSync(f.path, "utf8")).toBe(before);
|
|
expect(f.entries.at(-1).data.signoffs).toEqual({});
|
|
});
|
|
|
|
it.each(["denied", "cancelled"])("settles a %s preflight on execution_end without tool_result", async reason => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.start("refused");
|
|
f.finish("refused", { error: reason }, "subagent", true);
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
expect(f.entries.at(-1).data.mode).toBe("solo");
|
|
expect(f.entries.at(-1).data.worker).toBeUndefined();
|
|
});
|
|
|
|
it("batch results and a reviewer arriving first do not take the implementation binding", async () => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.launch({ id: "early", sessionFile: "/tmp/early.jsonl", agent: "reviewer" }, "reviewer");
|
|
expect(f.entries.at(-1).data.worker).toBeUndefined();
|
|
f.start("batch", { children: [{ agent: "reviewer", title: "Review" }, { agent: "goals-worker", title: "Implement" }] });
|
|
f.finish("batch", { status: "started", children: [
|
|
{ id: "review", sessionFile: "/tmp/review.jsonl", agent: "reviewer" },
|
|
{ id: "impl", sessionFile: "/tmp/impl.jsonl", agent: "goals-worker" },
|
|
] });
|
|
expect(f.entries.at(-1).data.worker).toEqual({ id: "impl", sessionFile: "/tmp/impl.jsonl" });
|
|
expect(f.entries.at(-1).data.helpers).toHaveLength(2);
|
|
await f.command("stop");
|
|
expect(f.messages.at(-1).message.content).toContain("impl");
|
|
});
|
|
|
|
it.each(["replace", "tree", "pause"])("does not attach a launch result after %s changed its originating generation", async change => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
f.start("old");
|
|
if (change === "replace") { await f.command("exit"); await f.command("new next output"); }
|
|
if (change === "tree") f.hooks.get("session_tree")({}, f.ctx);
|
|
if (change === "pause") await f.command("stop");
|
|
f.finish("old", { id: "old-worker", sessionFile: "/tmp/old-worker.jsonl", agent: "goals-worker" });
|
|
expect(f.entries.at(-1).data.worker).toBeUndefined();
|
|
expect(f.entries.at(-1).data.helpers).toEqual([]);
|
|
});
|
|
|
|
it.each([
|
|
["criterion", false], ["scope", false], ["other goal", true], ["task", true], ["evidence", true], ["Log", true],
|
|
])("%s edits retain signoff=%s according to reviewed acceptance", async (change, retained) => {
|
|
const f = fixture(); await f.draft(); await f.command("ready");
|
|
writeFileSync(f.path, f.plan.replace("# Plan", "# Plan\nShared scope: exact bytes").replace("goal: first output\n", "goal: first output\n - discriminator: original criterion\n - tasks:\n - [ ] original task\n - evidence: original evidence\n"));
|
|
writeFileSync(join(f.ctx.cwd, "proof.log"), "PASS\n");
|
|
await f.tools.get("CompleteGoal").execute("complete", { goal: "first output", evidence: ["proof.log"], observation: "Read PASS" }, undefined, undefined, f.ctx);
|
|
const signed = readFileSync(f.path, "utf8");
|
|
const replacements: Record<string, [string, string]> = {
|
|
criterion: ["original criterion", "new criterion"], scope: ["exact bytes", "two files"], "other goal": ["second output", "new second output"],
|
|
task: ["[ ] original task", "[x] maintained task"], evidence: ["original evidence", "additional evidence"], Log: ["## Log", "## Log\n- historical note"],
|
|
};
|
|
writeFileSync(f.path, signed.replace(...replacements[change as string]));
|
|
f.hooks.get("agent_end")({}, f.ctx);
|
|
expect(Boolean(f.entries.at(-1).data.signoffs["first output"])).toBe(retained);
|
|
f.hooks.get("session_start")({}, f.ctx);
|
|
expect(Boolean(f.entries.at(-1).data.signoffs["first output"])).toBe(retained);
|
|
});
|
|
|
|
it("passive pause is visible immediately while its model notice waits safely for the next prompt", async () => {
|
|
const f = fixture(); await f.draft();
|
|
f.ctx.ui.select.mockResolvedValueOnce("Worker confirmed stopped"); await f.command("solo");
|
|
await f.command("stop");
|
|
expect(f.messages.at(-1).options).toEqual({ deliverAs: "nextTurn" });
|
|
expect(f.ctx.ui.notify).toHaveBeenLastCalledWith(expect.stringContaining("Remote stop is NOT yet confirmed"), "info");
|
|
});
|