mirror of
https://github.com/wassname/pi-plan.git
synced 2026-09-25 14:00:15 +08:00
wassnameandPi Codex
bf50d9bbc8
Stop steward checkpoints after all goals close. Co-Authored-By: Pi Codex <288921227+claudypoo@users.noreply.github.com>
373 lines
17 KiB
TypeScript
373 lines
17 KiB
TypeScript
import { mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
|
|
import { tmpdir } from "node:os";
|
|
import { join } from "node:path";
|
|
import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
|
|
import { describe, expect, it, vi } from "vitest";
|
|
import piGoalsExtension from "../src/index.js";
|
|
|
|
function setup(
|
|
selectChoices: Array<string | undefined>,
|
|
editorChoices: Array<string | undefined> = [],
|
|
editPlan?: () => Promise<string | undefined>,
|
|
) {
|
|
const cwd = mkdtempSync(join(tmpdir(), "pi-goals-flow-"));
|
|
const commands = new Map<string, any>();
|
|
const hooks = new Map<string, any>();
|
|
const tools = new Map<string, any>();
|
|
const entries: Array<{ type: string; customType: string; data: unknown }> = [];
|
|
const eventLog: string[] = [];
|
|
const messages: Array<{ content: string; display?: boolean }> = [];
|
|
const rpcRequests: any[] = [];
|
|
const eventHandlers = new Map<string, Set<(data: unknown) => void>>();
|
|
const eventBus = {
|
|
on(name: string, handler: (data: unknown) => void) {
|
|
const handlers = eventHandlers.get(name) ?? new Set();
|
|
handlers.add(handler);
|
|
eventHandlers.set(name, handlers);
|
|
return () => handlers.delete(handler);
|
|
},
|
|
emit(name: string, data: unknown) {
|
|
for (const handler of [...(eventHandlers.get(name) ?? [])]) handler(data);
|
|
},
|
|
};
|
|
let asyncRun = 0;
|
|
eventBus.on("pi-subagents:runtime-agent-register:v1", (raw) => {
|
|
(raw as any).result = { ok: true, registration: { dispose() {} } };
|
|
});
|
|
eventBus.on("subagents:rpc:v1:request", (raw) => {
|
|
const request = raw as any;
|
|
rpcRequests.push(request);
|
|
asyncRun++;
|
|
eventBus.emit(`subagents:rpc:v1:reply:${request.requestId}`, { success: true, data: { text: "started", details: { asyncId: `steward-${asyncRun}` } } });
|
|
});
|
|
const ctx = {
|
|
cwd,
|
|
hasUI: true,
|
|
isIdle: () => true,
|
|
sessionManager: { getSessionId: () => "session-a", getEntries: () => entries },
|
|
ui: {
|
|
theme: { fg: (_kind: string, text: string) => text },
|
|
setStatus: () => {},
|
|
setWidget: () => {},
|
|
notify: () => {},
|
|
select: async () => {
|
|
eventLog.push("select");
|
|
return selectChoices.shift();
|
|
},
|
|
editor: async () => {
|
|
eventLog.push("editor");
|
|
return editPlan ? editPlan() : editorChoices.shift();
|
|
},
|
|
},
|
|
};
|
|
const pi = {
|
|
events: eventBus,
|
|
registerCommand: (name: string, command: any) => commands.set(name, command),
|
|
on: (name: string, handler: any) => hooks.set(name, handler),
|
|
appendEntry: (customType: string, data: unknown) => entries.push({ type: "custom", customType, data }),
|
|
registerTool: (tool: any) => tools.set(tool.name, tool),
|
|
sendMessage: (message: { content: string; display?: boolean }) => {
|
|
eventLog.push("display");
|
|
messages.push(message);
|
|
},
|
|
sendUserMessage: (message: string) => messages.push({ content: message }),
|
|
};
|
|
piGoalsExtension(pi as unknown as ExtensionAPI);
|
|
return { commands, ctx, cwd, entries, events: eventLog, eventBus, hooks, messages, rpcRequests, tools };
|
|
}
|
|
|
|
describe("/goals draft flow", () => {
|
|
it("preserves prior drafts, displays the plan before Refine, and records editor notes", async () => {
|
|
const flow = setup(["Refine"], ["Keep two columns.\nDo not add a filter."]);
|
|
try {
|
|
const legacy = join(flow.cwd, ".pi/plan/session-a.md");
|
|
mkdirSync(join(flow.cwd, ".pi/plan"), { recursive: true });
|
|
writeFileSync(legacy, "old plan");
|
|
await flow.commands.get("goals").handler("first objective", flow.ctx);
|
|
const v1 = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
expect(readFileSync(v1, "utf-8")).toBe("");
|
|
expect(readFileSync(legacy, "utf-8")).toBe("old plan");
|
|
const plan = "# First plan\n\n## Goals\n\n1. [ ] goal: preserve this\n\n## Appendix (context, not approved)\nold context\n";
|
|
mkdirSync(join(flow.cwd, ".pi/plan"), { recursive: true });
|
|
writeFileSync(v1, plan);
|
|
await flow.hooks.get("input")({ text: "The result must preserve column order.", source: "interactive" }, flow.ctx);
|
|
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
expect(flow.events).toEqual(["display", "select", "editor"]);
|
|
expect(flow.messages.at(-1)?.content).toContain("Revise the plan at");
|
|
expect(flow.messages.find((message) => message.display)?.content).toContain("goal: preserve this");
|
|
const interviewedPlan = readFileSync(v1, "utf-8");
|
|
expect(interviewedPlan).toContain("> The result must preserve column order.");
|
|
expect(interviewedPlan).toMatch(/## Interview\n\n### .+\n\n> The result must preserve column order\.[\s\S]+> Keep two columns\.\n> Do not add a filter\./);
|
|
const refineSnapshot = await flow.hooks.get("before_agent_start")({}, flow.ctx);
|
|
expect(refineSnapshot.message.content).toContain("[PLANNING MODE]");
|
|
const blocked = await flow.hooks.get("tool_call")({ toolName: "edit", input: { path: "README.md" } }, flow.ctx);
|
|
expect(blocked?.block).toBe(true);
|
|
|
|
await flow.commands.get("goals").handler("second objective", flow.ctx);
|
|
expect(readFileSync(v1, "utf-8")).toBe(interviewedPlan);
|
|
expect(readFileSync(join(flow.cwd, ".pi/plan/session-a-v2.md"), "utf-8")).toBe("");
|
|
expect(flow.messages.at(-1)?.content).toContain("session-a-v2.md");
|
|
|
|
await flow.commands.get("goals").handler("judge the vendor options", flow.ctx);
|
|
expect(readFileSync(join(flow.cwd, ".pi/plan/session-a-v3.md"), "utf-8")).toBe("");
|
|
expect(flow.messages.at(-1)?.content).toContain("Objective: judge the vendor options");
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("disconnects without deleting the active plan", async () => {
|
|
const flow = setup([]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [ ] goal: preserve this\n");
|
|
|
|
await flow.commands.get("goals").handler("clear", flow.ctx);
|
|
|
|
expect(readFileSync(planPath, "utf-8")).toContain("goal: preserve this");
|
|
expect(flow.entries.at(-1)?.data).toMatchObject({ phase: null, planVersion: null });
|
|
|
|
await flow.commands.get("goals").handler("next objective", flow.ctx);
|
|
expect(readFileSync(join(flow.cwd, ".pi/plan/session-a-v2.md"), "utf-8")).toBe("");
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("waits for Refine notes before starting a revision turn", async () => {
|
|
let submitNotes: (notes: string) => void;
|
|
const flow = setup(["Refine"], [], () => new Promise((resolve) => {
|
|
submitNotes = resolve;
|
|
}));
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [ ] goal: make this specific\n");
|
|
|
|
const review = flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await new Promise((resolve) => setImmediate(resolve));
|
|
expect(flow.events).toEqual(["display", "select", "editor"]);
|
|
expect(flow.messages.filter((message) => !message.display)).toHaveLength(1);
|
|
|
|
submitNotes!("Name the output artifact.");
|
|
await review;
|
|
expect(flow.messages.at(-1)?.content).toContain("Revise the plan at");
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("starts work only when the human chooses Ready", async () => {
|
|
const flow = setup(["Ready"]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [ ] goal: work on this\n");
|
|
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
|
|
expect(flow.events).toEqual(["display", "select"]);
|
|
expect(flow.messages.filter((message) => !message.display)).toHaveLength(2);
|
|
expect(flow.messages.at(-1)?.content).toContain("Work the goals");
|
|
await flow.hooks.get("session_start")({}, flow.ctx);
|
|
expect(await flow.hooks.get("before_agent_start")({}, flow.ctx)).toBeUndefined();
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("edits a plan in Pi and cancels without starting work", async () => {
|
|
const original = "# Plan\n\n## Goals\n\n1. [ ] goal: original\n";
|
|
const edited = "# Plan\n\n## Goals\n\n1. [ ] goal: edited\n";
|
|
const flow = setup(["Edit", "Cancel"], [edited]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, original);
|
|
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
|
|
expect(flow.events).toEqual(["display", "select", "editor", "display", "select"]);
|
|
expect(() => readFileSync(planPath, "utf-8")).toThrow();
|
|
expect(flow.messages.filter((message) => !message.display)).toHaveLength(1);
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("reminds every eight unchanged working-set turns, ignoring log-only edits", async () => {
|
|
const flow = setup(["Ready"]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: make the output\n\n## Log\n");
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
|
|
await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
for (let turn = 0; turn < 3; turn++) await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: make the output\n\n## Log\n- checked input\n");
|
|
for (let turn = 0; turn < 5; turn++) await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
|
|
const reminder = await flow.hooks.get("context")({ messages: [] }, flow.ctx);
|
|
expect(reminder.messages.at(-1).content[0].text).toContain(".pi/plan/session-a-v1.md");
|
|
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: make the output\n - [x] inspect input\n\n## Log\n- checked input\n");
|
|
await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
for (let turn = 0; turn < 7; turn++) await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
expect((await flow.hooks.get("context")({ messages: [] }, flow.ctx)).messages).toHaveLength(0);
|
|
await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
expect((await flow.hooks.get("context")({ messages: [] }, flow.ctx)).messages.at(-1).content[0].text).toContain("make the output");
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("auto-continues once on stop, then pauses after two no-progress wakes", async () => {
|
|
vi.useFakeTimers();
|
|
const flow = setup(["Ready"]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: make the output\n");
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await flow.commands.get("goals").handler("auto 1", flow.ctx);
|
|
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await vi.advanceTimersByTimeAsync(0);
|
|
const autoMessages = () => flow.messages.filter((message) => message.content.includes("Auto-continue is enabled"));
|
|
expect(autoMessages()).toHaveLength(1);
|
|
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await vi.advanceTimersByTimeAsync(60_000);
|
|
expect(autoMessages()).toHaveLength(2);
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await vi.advanceTimersByTimeAsync(60_000);
|
|
expect(autoMessages()).toHaveLength(2);
|
|
} finally {
|
|
vi.useRealTimers();
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("delays auto-continuation after a known background start", async () => {
|
|
vi.useFakeTimers();
|
|
const flow = setup(["Ready"]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: make the output\n");
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await flow.commands.get("goals").handler("auto 1", flow.ctx);
|
|
await flow.hooks.get("agent_start")({}, flow.ctx);
|
|
await flow.hooks.get("tool_call")({ toolName: "process", input: { action: "start" } }, flow.ctx);
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
await vi.advanceTimersByTimeAsync(0);
|
|
const autoMessages = () => flow.messages.filter((message) => message.content.includes("Auto-continue is enabled"));
|
|
expect(autoMessages()).toHaveLength(0);
|
|
await vi.advanceTimersByTimeAsync(60_000);
|
|
expect(autoMessages()).toHaveLength(1);
|
|
} finally {
|
|
vi.useRealTimers();
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("does not checkpoint after every goal is closed", async () => {
|
|
const flow = setup(["Ready"]);
|
|
try {
|
|
await flow.hooks.get("session_start")({}, flow.ctx);
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: produce report\n");
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
flow.eventBus.emit("subagent:async-complete", { runId: "steward-1" });
|
|
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [x] goal: produce report\n");
|
|
await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
for (let turn = 0; turn < 8; turn++) await flow.hooks.get("turn_end")({}, flow.ctx);
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
|
|
expect(flow.rpcRequests).toHaveLength(1);
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("resumes the same steward lineage for sign-off and persists the latest run", async () => {
|
|
const flow = setup(["Ready"]);
|
|
try {
|
|
await flow.hooks.get("session_start")({}, flow.ctx);
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
writeFileSync(planPath, "# Plan\n\n## Goals\n\n1. [/] goal: produce report\n - discriminator: report.txt contains PASS\n - evidence:\n - report.txt: `PASS`\n\n## Log\n");
|
|
await flow.hooks.get("agent_settled")({}, flow.ctx);
|
|
expect(flow.rpcRequests[0]).toMatchObject({ method: "spawn", params: { agent: "goal-steward" } });
|
|
flow.eventBus.emit("subagent:async-complete", {
|
|
runId: "steward-1",
|
|
results: [{ success: true, structuredOutput: { verdict: "let_run", summary: "Start work." } }],
|
|
});
|
|
|
|
const signoff = flow.tools.get("CompleteGoal").execute("", { goal: "produce report" }, undefined, undefined, flow.ctx);
|
|
await new Promise((resolve) => setImmediate(resolve));
|
|
expect(flow.rpcRequests[1]).toMatchObject({ method: "resume", params: { id: "steward-1" } });
|
|
flow.eventBus.emit("subagent:async-complete", {
|
|
runId: "steward-2",
|
|
results: [{ success: true, structuredOutput: { verdict: "accept", summary: "report.txt contains PASS." } }],
|
|
});
|
|
const outcome = await signoff;
|
|
|
|
expect(outcome.isError).toBe(false);
|
|
expect(readFileSync(planPath, "utf-8")).toContain("1. [x] goal: produce report");
|
|
expect(flow.entries.at(-1)?.data).toMatchObject({ stewardRunId: "steward-2", stewardPending: false });
|
|
|
|
await flow.hooks.get("session_start")({}, flow.ctx);
|
|
const afterReload = flow.tools.get("CompleteGoal").execute("", { goal: "produce report" }, undefined, undefined, flow.ctx);
|
|
await new Promise((resolve) => setImmediate(resolve));
|
|
expect(flow.rpcRequests[2]).toMatchObject({ method: "resume", params: { id: "steward-2" } });
|
|
flow.eventBus.emit("subagent:async-complete", {
|
|
runId: "steward-3",
|
|
results: [{ success: true, structuredOutput: { verdict: "reject", summary: "Already complete.", missingEvidence: ["No second sign-off needed"] } }],
|
|
});
|
|
expect((await afterReload).isError).toBe(true);
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
it("gives the agent a planning snapshot and blocks work routes", async () => {
|
|
const flow = setup([]);
|
|
try {
|
|
await flow.commands.get("goals").handler("objective", flow.ctx);
|
|
const planPath = join(flow.cwd, ".pi/plan/session-a-v1.md");
|
|
expect(flow.entries.at(-1)?.data).toMatchObject({ phase: "planning" });
|
|
await flow.hooks.get("session_start")({}, flow.ctx);
|
|
const snapshot = await flow.hooks.get("before_agent_start")({}, flow.ctx);
|
|
expect(snapshot.message.content).toContain("[PLANNING MODE]");
|
|
expect(snapshot.message.content).toContain(planPath);
|
|
|
|
const writePlan = await flow.hooks.get("tool_call")({ toolName: "write", input: { path: planPath } }, flow.ctx);
|
|
const writeCode = await flow.hooks.get("tool_call")({ toolName: "write", input: { path: "README.md" } }, flow.ctx);
|
|
const readShell = await flow.hooks.get("tool_call")({ toolName: "bash", input: { command: "pwd && ls && git log" } }, flow.ctx);
|
|
const changeDirectoryThenRead = await flow.hooks.get("tool_call")({ toolName: "bash", input: { command: "cd . && ls -la" } }, flow.ctx);
|
|
const pipeShell = await flow.hooks.get("tool_call")({ toolName: "bash", input: { command: "ls | head" } }, flow.ctx);
|
|
const pythonWrite = await flow.hooks.get("tool_call")({ toolName: "bash", input: { command: "python -c \"open('README.md', 'w')\"" } }, flow.ctx);
|
|
const signoff = await flow.tools.get("CompleteGoal").execute("", { goal: "work" }, undefined, undefined, flow.ctx);
|
|
await flow.hooks.get("session_compact")({}, flow.ctx);
|
|
const compacted = await flow.hooks.get("context")({ messages: [] }, flow.ctx);
|
|
|
|
expect(writePlan).toBeUndefined();
|
|
expect(writeCode?.block).toBe(true);
|
|
expect(readShell).toBeUndefined();
|
|
expect(changeDirectoryThenRead).toBeUndefined();
|
|
expect(pipeShell?.block).toBe(true);
|
|
expect(pythonWrite?.block).toBe(true);
|
|
expect(signoff.isError).toBe(true);
|
|
expect(compacted.messages.at(-1).content[0].text).toContain("[PLANNING MODE]");
|
|
} finally {
|
|
rmSync(flow.cwd, { recursive: true, force: true });
|
|
}
|
|
});
|
|
});
|