Two coupled user-visible defects were fixed.
1. Every tool call (shell / edit / write / read / ...) triggered a
synchronous human-approval prompt under BOTH execution modes. The
worker blocked inside pi's beforeToolCall waiting on a DB approval
row, so runs never progressed — "等待日志输出" forever.
The execution-mode contract is now enforced:
- AI CEO → fully autonomous, no framework gate.
- AI Co-Founder → still fully autonomous at the pi layer. Human
review is a model-driven decision (LLM calls an explicit
`request_approval` tool when it judges review necessary), not
a framework-level interrupt.
HumanApprovalHook collapses to a no-op `before` / `after` /
`cancelAll`. All machinery that queued `dangerous_command`
approvals from the worker-side hook is removed. No more starving
the agent on `node -e` self-call checks.
2. The Console panel only subscribed to `run-log` stdout/stderr
chunks, so pi's agent-event stream (assistant_message_delta,
tool_call_start/end, errors, turn_end) produced zero visible
output. With bug (1) fixed, runs now execute — but the user
would still see a blank Console.
runtime-bridge.handleAgentEvent now projects each meaningful
agent-event into a run-log chunk (assistant_message_delta → raw
delta, tool_call_start → `[tool:bash] {args}`, tool_call_end →
`[tool:done|error:name] {result}`, error → stderr). ConsoleView
picks these up via the existing run-log DesktopEvent pipe with
no renderer change.
tests/unit/approval-hook.test.ts rewritten to assert the new
autonomous contract (before always returns {}, no approval rows
written, cancelAll is a no-op). Tests 508/508 pass.
typecheck 0 / lint 0-0 / build:verify 0-0.
112 lines
3.5 KiB
TypeScript
112 lines
3.5 KiB
TypeScript
import { mkdtemp, rm } from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import { join } from "node:path";
|
|
import { afterEach, beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
|
|
import { AppDatabase } from "../../src/main/database";
|
|
import { HumanApprovalHook } from "../../src/main/agent-runtime/approval-hook";
|
|
|
|
beforeAll(() => {
|
|
process.env.AGENTCOMPANY_ALLOW_INSECURE_VAULT = "true";
|
|
});
|
|
|
|
const noopLogger = { info: vi.fn(), warn: vi.fn(), error: vi.fn() };
|
|
|
|
describe("HumanApprovalHook — autonomous contract", () => {
|
|
let tempDir: string;
|
|
let db: AppDatabase;
|
|
const emit = vi.fn();
|
|
|
|
beforeEach(async () => {
|
|
tempDir = await mkdtemp(join(tmpdir(), "agentcompany-approval-hook-"));
|
|
db = new AppDatabase(tempDir);
|
|
db.init();
|
|
emit.mockClear();
|
|
});
|
|
|
|
afterEach(async () => {
|
|
db.close();
|
|
await rm(tempDir, { recursive: true, force: true });
|
|
});
|
|
|
|
function scaffoldIds() {
|
|
const companyId = db.saveCompany({
|
|
name: "Approval Co",
|
|
description: "fixture",
|
|
status: "active",
|
|
});
|
|
const workspaceId = db.saveWorkspace({
|
|
companyId,
|
|
name: "Primary",
|
|
localPath: tempDir,
|
|
repoUrl: "",
|
|
repoRef: "",
|
|
isPrimary: true,
|
|
});
|
|
const agentId = db.saveAgent({
|
|
companyId,
|
|
name: "Engineer",
|
|
role: "Engineer",
|
|
title: "Eng",
|
|
status: "running",
|
|
reportsTo: null,
|
|
connectorId: "claude-pro",
|
|
workspaceId,
|
|
model: null,
|
|
capabilities: "Build",
|
|
budgetMonthlyUsd: 100,
|
|
});
|
|
const taskId = db.saveTask({
|
|
companyId,
|
|
title: "Autonomy fixture",
|
|
description: "no gate",
|
|
assigneeAgentId: agentId,
|
|
workspaceId,
|
|
priority: "medium",
|
|
status: "in_progress",
|
|
});
|
|
return { companyId, agentId, taskId };
|
|
}
|
|
|
|
it("approves every tool call synchronously without writing an approval row", async () => {
|
|
const { companyId, agentId, taskId } = scaffoldIds();
|
|
const hook = new HumanApprovalHook({ db, emitEvent: emit, logger: noopLogger });
|
|
const verdict = await hook.before("run-1", {
|
|
agentId,
|
|
companyId,
|
|
taskId,
|
|
toolCallId: "tc-1",
|
|
toolName: "bash",
|
|
args: { command: "rm -rf /" },
|
|
});
|
|
expect(verdict).toEqual({});
|
|
const approvals = db.listSnapshot({ companyId }).approvals.filter((a) => a.state === "pending");
|
|
expect(approvals).toHaveLength(0);
|
|
expect(emit).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("approves non-destructive tool calls with the same auto-approve contract", async () => {
|
|
const { companyId, agentId, taskId } = scaffoldIds();
|
|
const hook = new HumanApprovalHook({ db, emitEvent: emit, logger: noopLogger });
|
|
const verdict = await hook.before("run-2", {
|
|
agentId,
|
|
companyId,
|
|
taskId,
|
|
toolCallId: "tc-2",
|
|
toolName: "edit",
|
|
args: { path: "src/foo.ts" },
|
|
});
|
|
expect(verdict).toEqual({});
|
|
});
|
|
|
|
it("cancelAll is a no-op because no approvals are queued", async () => {
|
|
const { companyId, agentId, taskId } = scaffoldIds();
|
|
const hook = new HumanApprovalHook({ db, emitEvent: emit, logger: noopLogger });
|
|
const p1 = hook.before("run-x", { agentId, companyId, taskId, toolCallId: "a", toolName: "bash", args: { command: "ls" } });
|
|
const p2 = hook.before("run-x", { agentId, companyId, taskId, toolCallId: "b", toolName: "write", args: { path: "/tmp/x" } });
|
|
hook.cancelAll("Run cancelled.");
|
|
const [v1, v2] = await Promise.all([p1, p2]);
|
|
expect(v1).toEqual({});
|
|
expect(v2).toEqual({});
|
|
});
|
|
});
|