ZacharyZhang-NY
14dc9a4897
Cost was written through three independent paths: worker-runner shipped `finalUsage.costUsd` in run-finished -> finishRun wrote `runs.cost_usd`, `tasks.cost_usd += costUsd`, `agents.spent_monthly_usd += costUsd`, and inserted a per-run aggregate row in cost_entries. CostWriter additionally inserted per-message rows in cost_entries from main. Any CostWriter failure created silent drift between `SUM(cost_entries)` (read by budget enforcement) and `runs.cost_usd` (read by the UI). Make CostWriter the single writer, finishRun the single reader. - Add `db.recordCostEntry(...)` as the first-class insert path for per-message cost rows. CostWriter calls it; tests call it directly. - Remove the aggregate INSERT from finishRun. finishRun now reads `SELECT COALESCE(SUM(amount_usd), 0) FROM cost_entries WHERE run_id=? AND unattributed=0` and writes that as the authoritative run total to runs.cost_usd, tasks.cost_usd, and agents.spent_monthly_usd. - Drop `costUsd` from `finishRun` input, the worker `run-finished` ChildMessage shape, the automation `RunFinishedEvent` type, and every caller + test fixture. Cost is owned by the per-message path. - worker-runner stops extracting `usage.cost.total` — token counts stay for session accumulation, cost comes from pi-ai via CostWriter. - run-finished-helpers now gates budget incident checks on `event.status === "succeeded"` instead of a cost field that no longer exists on the event. - automation-run-completion fires `budget_threshold` on every succeeded run (post-run spent_monthly_usd already reflects the SUM path). - Update budget tests to write a `recordCostEntry` before `finishRun` to simulate the per-message cost path; drop `costUsd` from cross- subsystem, edge-case-budget, database, and related fixtures. One writer, one reader, one source of truth. No drift.
66 lines
2.0 KiB
TypeScript
66 lines
2.0 KiB
TypeScript
/**
|
|
* Step 6: Run failure escalation (database layer).
|
|
* Physically extracted from autonomous-chain.spec.ts without behavior changes.
|
|
*/
|
|
|
|
import { describe, expect, it } from "vitest";
|
|
import { installSharedSetup } from "./shared-setup";
|
|
|
|
const shared = installSharedSetup();
|
|
const { createAgent } = shared;
|
|
|
|
describe("Step 6: Run failure escalation (database layer)", () => {
|
|
it("finishRun marks run as failed and returns outcome", () => {
|
|
const agentId = createAgent({ name: "IC", role: "Engineer" });
|
|
const taskId = shared.db.saveTask({
|
|
companyId: shared.companyId,
|
|
title: "Failing task",
|
|
description: "Will fail",
|
|
assigneeAgentId: agentId,
|
|
workspaceId: shared.workspaceId,
|
|
priority: "medium",
|
|
status: "in_progress",
|
|
});
|
|
|
|
const run = shared.db.createRun({
|
|
companyId: shared.companyId,
|
|
taskId,
|
|
agentId,
|
|
workspaceId: shared.workspaceId,
|
|
connectorId: "openai-codex",
|
|
});
|
|
|
|
shared.db.markRunStatus(run.id, "running", "Started");
|
|
|
|
const outcome = shared.db.finishRun({
|
|
runId: run.id,
|
|
status: "failed",
|
|
summary: null,
|
|
errorMessage: "Process crashed",
|
|
exitCode: 1,
|
|
signal: null,
|
|
model: "gpt-5-codex",
|
|
sessionDisplayId: null,
|
|
unattributedCost: false,
|
|
});
|
|
|
|
expect(outcome.budgetHardStopped).toBe(false);
|
|
|
|
const snapshot = shared.db.listSnapshot();
|
|
const finishedRun = snapshot.runs.find((r) => r.id === run.id);
|
|
expect(finishedRun?.status).toBe("failed");
|
|
expect(finishedRun?.errorMessage).toBe("Process crashed");
|
|
});
|
|
|
|
it("getChainOfCommand returns manager for failure escalation", () => {
|
|
const ceoId = createAgent({ name: "CEO", role: "CEO" });
|
|
const ctoId = createAgent({ name: "CTO", role: "CTO", reportsTo: ceoId });
|
|
const icId = createAgent({ name: "Dev", role: "Engineer", reportsTo: ctoId });
|
|
|
|
const chain = shared.db.getChainOfCommand(icId);
|
|
// First in chain is the immediate manager (CTO)
|
|
expect(chain.length).toBeGreaterThan(0);
|
|
expect(chain[0].name).toBe("CTO");
|
|
});
|
|
});
|