template-app/modules/agent/__tests__/runs.test.ts

// The agent module's use cases on the in-memory adapter: starting lists and statuses, cancel's
// resume event, and the approval queue — which must surface the EXACT stored proposed arguments.

import { AGENT_ENTITIES } from "@conusai-kit/agent"
import type { TenantScope } from "@conusai-kit/core"
import { createMemoryDataSource } from "@conusai-kit/data"
import { describe, expect, it } from "vitest"
import { cancelRun, getRun, listApprovals, listRuns, reviewApproval, startRun } from "../core/runs.js"

const USER = "01900000-0000-7000-0000-000000000009"
const scope: TenantScope = {
  level: "project",
  actor: { userId: USER },
  orgId: "01900000-0000-7000-0000-000000000001",
  workspaceId: "01900000-0000-7000-0000-000000000002",
  projectId: "01900000-0000-7000-0000-000000000003",
}
const makeDeps = () => ({ data: createMemoryDataSource({ entities: [...AGENT_ENTITIES] }) })

const PLAN = [
  { key: "read", label: "Read the document", tool: "documents.read", args: { fileId: "f-1" } },
  { key: "propose", label: "Propose lines", tool: "documents.extract", args: { fileId: "f-1", schema: "line" } },
]

describe("the agent module's run use cases", () => {
  const deps = makeDeps()
  it("starts a run queued, with the plan visible, and lists it", async () => {
    const run = await startRun(deps, scope, { goal: "Review the contract", plan: PLAN })
    expect(run.status).toBe("queued")
    expect(run.goal).toBe("Review the contract")
    expect(run.plan).toEqual([
      {
        key: "read",
        label: "Read the document",
        tool: "documents.read",
        args: { fileId: "f-1" },
        status: "pending",
        attempts: 0,
        error: null,
      },
      {
        key: "propose",
        label: "Propose lines",
        tool: "documents.extract",
        args: { fileId: "f-1", schema: "line" },
        status: "pending",
        attempts: 0,
        error: null,
      },
    ])
    expect(run.percent).toBe(0)
    const listed = await listRuns(deps, scope, {})
    expect(listed.runs).toHaveLength(1)
    expect((await getRun(deps, scope, run.runId)).runId).toBe(run.runId)
    // The outbox event that enqueues the run job in the worker.
    const pending = await deps.data.outbox.pending(10)
    expect(pending.some((record) => record.name === "agent.runResumeRequested")).toBe(true)
  })

  it("refuses an over-long or repeated plan before anything is written", async () => {
    const fresh = makeDeps()
    const tooLong = await startRun(fresh, scope, {
      goal: "x",
      plan: Array.from({ length: 26 }, (_, at) => ({ key: `s${at}`, label: `Step ${at}`, tool: "t", args: {} })),
    }).catch((error: unknown) => error)
    expect((tooLong as { status?: number }).status).toBe(422)
    const repeated = await startRun(fresh, scope, {
      goal: "x",
      plan: [
        { key: "same", label: "One", tool: "t", args: {} },
        { key: "same", label: "Two", tool: "t", args: {} },
      ],
    }).catch((error: unknown) => error)
    expect((repeated as { status?: number }).status).toBe(422)
    expect((await listRuns(fresh, scope, {})).runs).toHaveLength(0)
  })

  it("cancel persists the request and re-enqueues the resume; a parked approval surfaces its exact arguments", async () => {
    const fresh = makeDeps()
    const run = await startRun(fresh, scope, { goal: "Approve-aware run", plan: PLAN })
    // Simulate the engine parking an approval by writing the step row as the engine would.
    const { dataRunStore } = await import("@conusai-kit/agent")
    const store = dataRunStore(fresh.data, scope)
    await store.beginStep(run.runId, { key: "read", index: 0, label: "Read the document" }, new Date().toISOString())
    await store.parkStepApproval(
      run.runId,
      "read",
      {
        actionId: "act-7",
        tool: "documents.read",
        arguments: { fileId: "f-1", dryRun: false },
        reviewUrl: "https://console/review?action=act-7",
      },
      new Date().toISOString(),
    )
    await fresh.data
      .forScope(scope)
      // biome-ignore lint/suspicious/noExplicitAny: test adjusts the run's status as the engine would.
      .of(AGENT_ENTITIES[0] as any)
      .update(run.runId, { status: "awaiting_approval" }, 1)

    const queue = await listApprovals(fresh, scope)
    expect(queue.approvals).toHaveLength(1)
    expect(queue.approvals[0]).toMatchObject({
      runId: run.runId,
      stepKey: "read",
      tool: "documents.read",
      arguments: { fileId: "f-1", dryRun: false },
      reviewUrl: "https://console/review?action=act-7",
    })

    const cancelled = await cancelRun(fresh, scope, run.runId)
    expect(cancelled.cancelled).toBe(true)
    expect((await getRun(fresh, scope, run.runId)).cancelRequested).toBe(true)
    // The cancel re-published the resume event: a parked run notices the request only when resumed.
    const pending = await fresh.data.outbox.pending(10)
    expect(pending.filter((record) => record.name === "agent.runResumeRequested")).toHaveLength(2)

    const review = await reviewApproval(fresh, scope, { runId: run.runId, stepKey: "read", decision: "approve" })
    expect(["queued", "running", "awaiting_approval", "cancelled"]).toContain(review.status)
    const bad = await reviewApproval(fresh, scope, { runId: run.runId, stepKey: "propose", decision: "approve" }).catch(
      (error: unknown) => error,
    )
    expect((bad as { status?: number }).status).toBe(422)
  })
})