Files
PaperClipAI/tests/runner-e2e/github-operating-usage.test.ts
T
DottaandPaperclip 59d1b7b43d fix(evals): collect usage when GitHub skips jobs without a runner (#17352)
## Thinking Path

> - Paperclip manages AI agents and their operating budgets.
> - Product E2E runs retain accounting for each campaign.
> - The usage collector reads completed GitHub jobs without rerunning
paid work.
> - GitHub returns a null runner ID for jobs that it skips before
assigning a runner.
> - The collector rejected those jobs and could not retain the completed
campaign inventory.
> - This change accepts that skipped-job representation while preserving
started-job checks.

## Linked Issues or Issue Description

Refs #17009.

**What happened?**

The usage collector rejected completed qualification run 39971835384.
GitHub returned skipped jobs with null runner IDs. The collector
accepted only zero for jobs without a runner.

**Expected behavior**

Retain completed run usage when skipped jobs have a null or zero runner
ID. Do not count VM time for those jobs. Continue to reject missing
runner identity for started jobs.

**Steps to reproduce**

Read the completed first-attempt Product E2E run with
operating-receipts.ts github. Before this fix, a skipped job with
runner_id set to null throws Invalid workflow job identity.

**Paperclip version or commit**

ed3f067dbd.

## What Changed

- Accept a null or zero runner ID only for completed skipped jobs.
- Keep run, attempt, labels and started-job identity validation.
- Test both skipped-job forms and reject absent runner IDs.
- Document the treatment of skipped jobs.

## Verification

- Reproduced the observed null-runner failure: 1 failed, 4 passed.
- Usage collector and operating receipt tests: 17 passed.
- Eval TypeScript check passed.
- Read the same completed hosted run successfully without dispatching or
retrying tests. The inventory retained 1,303 job seconds and 290,156,153
artifact bytes.
- Full hosted CI passed at fb57826c22,
including typecheck, tests, build and browser shards.
- Greptile and Paperclip reviews rated the exact commit 5/5 with no
actionable findings.

## Risks

- The exception applies only when GitHub reports a completed skipped job
and an explicit null or zero runner ID.
- Current usage remains an inventory. This change does not convert it to
a bill, release cost holds, or enable recurrence.

## Model Used

- OpenAI GPT-6 in Codex, with reasoning, repository inspection, code
execution and test tools. The exact backend model identifier and
context-window size are not exposed in this session.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-10-23 11:35:35 -07:00

67 lines
4.7 KiB
TypeScript

import { expect, it } from "vitest";
import { readGitHubOperatingUsage } from "./github-operating-usage.js";
const now = Date.parse("2026-10-21T12:00:00Z"), sha = "a".repeat(40);
const run = { id: 123, repository: { id: 456, full_name: "paperclipai/paperclip" },
path: ".github/workflows/runner-full-stack-e2e.yml", run_attempt: 1, status: "completed", conclusion: "failure", head_sha: sha,
created_at: "2026-10-21T10:00:00Z", run_started_at: "2026-10-21T10:01:00Z", updated_at: "2026-10-21T10:10:00Z" };
const job = (id = 1) => ({ id, run_id: 123, run_attempt: 1, status: "completed", conclusion: "success", runner_id: 1,
runner_name: "GitHub Actions 1", runner_group_name: "GitHub Actions", labels: ["ubuntu-latest"],
started_at: "2026-10-21T10:01:00Z", completed_at: "2026-10-21T10:02:00Z", name: "unretained arbitrary user text" });
const artifact = { id: 9, workflow_run: { id: 123, head_sha: sha }, size_in_bytes: 1024, expired: false,
created_at: "2026-10-21T10:03:00Z", expires_at: "2026-11-20T10:03:00Z", name: "unretained arbitrary artifact text" };
function api(overrides: Record<string, any> = {}) {
const reads: string[] = [];
return { reads, read: async (endpoint: string) => {
reads.push(endpoint);
if (endpoint === "repos/paperclipai/paperclip") return { id: 456, full_name: "paperclipai/paperclip", private: false, ...overrides.repo };
if (endpoint.endsWith("/runs/123")) return { ...run, ...overrides.run, ...(reads.filter(row => row.endsWith("/runs/123")).length === 2 ? overrides.finalRun : {}) };
if (endpoint.includes("/jobs?")) {
const jobs = overrides.jobs ?? [job()];
const page = Number(new URL(`https://api.github.com/${endpoint}`).searchParams.get("page"));
return { total_count: jobs.length, jobs: jobs.slice((page - 1) * 100, page * 100), ...overrides.jobPage };
}
if (endpoint.includes("/artifacts?")) return { total_count: 1, artifacts: [artifact], ...overrides.artifactPage };
throw new Error("Unexpected read");
} };
}
it("collects failed-run usage without equating job time, current rates or inventory with billed cost", async () => {
const source = api();
const usage = await readGitHubOperatingUsage("123", source.read, now);
expect(usage).toMatchObject({ runAttempt: 1, sourceSha: sha, queueSeconds: 60, summedJobSeconds: 60,
allStartedJobsStandardHosted: true, artifacts: { retainedBytes: 1024, lifetimeCoverage: "incomplete" },
billing: { ciComputeUsd: null, artifactStorageUsd: null, publicStandardComputeRateUsdPerMinute: "0" } });
expect(JSON.stringify(usage)).not.toContain("unretained");
expect(source.reads).toHaveLength(5);
});
it("paginates all jobs and preserves nonstandard compute as unpriced", async () => {
const jobs = Array.from({ length: 101 }, (_, index) => job(index + 1));
jobs[100]!.runner_group_name = "custom-fleet";
const source = api({ jobs });
expect(await readGitHubOperatingUsage("123", source.read, now)).toMatchObject({ summedJobSeconds: 6060,
allStartedJobsStandardHosted: false, billing: { publicStandardComputeRateUsdPerMinute: null } });
expect(source.reads.some(endpoint => endpoint.includes("page=2"))).toBe(true);
expect((await readGitHubOperatingUsage("123", api({ repo: { private: true } }).read, now)).billing.publicStandardComputeRateUsdPerMinute).toBeNull();
});
it("rejects changing, truncated, duplicated, misattributed, rerun and uncompleted evidence", async () => {
for (const override of [{ run: { run_attempt: 2 } }, { run: { status: "in_progress" } }, { run: { path: "other.yml" } },
{ finalRun: { head_sha: "b".repeat(40) } }, { jobPage: { total_count: 2 } }, { jobs: [job(), job()] },
{ jobs: [{ ...job(), run_id: 999 }] }, { jobs: [{ ...job(), runner_id: null }] },
{ jobs: [{ ...job(), runner_id: undefined }] }, { jobs: [{ ...job(), conclusion: "skipped", runner_id: undefined }] },
{ jobs: [{ ...job(), completed_at: null }] }, { jobPage: { total_count: 1001 } },
{ artifactPage: { artifacts: [{ ...artifact, workflow_run: { id: 999, head_sha: sha } }] } },
{ artifactPage: { artifacts: [{ ...artifact, size_in_bytes: -1 }] } }]) {
await expect(readGitHubOperatingUsage("123", api(override).read, now)).rejects.toThrow();
}
});
it.each([0, null])("accounts skipped jobs with runner ID %s without requiring a fictitious VM", async (runnerId) => {
const source = api({ jobs: [{ ...job(), conclusion: "skipped", runner_id: runnerId, started_at: null, completed_at: null }],
artifactPage: { artifacts: [{ ...artifact, expired: true }] } });
expect(await readGitHubOperatingUsage("123", source.read, now)).toMatchObject({ summedJobSeconds: 0,
jobs: [{ runner: "not_started" }], artifacts: { retainedBytes: 0, inventory: [{ id: 9, expired: true }] } });
});