Files
PaperClipAI/tests/runner-e2e/chat-catalog-failure-retirement.test.ts
T
DottaandClaude Opus 5.5 f1aef0cb58 fix(evals): grade full cohort 3 false failures on saved state, read receipts and rendered links (#21008)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - The chat eval catalog runs real chat journeys against real agents
and grades saved product state
> - Full cohort 3 failed six cases where the product behaved correctly
and the eval was wrong
> - A wrong failure hides real product failures in the noise, so each
check must accept valid behavior
> - Each check must still fail the broken product behavior it exists to
catch
> - This pull request replaces those checks with checks of saved state,
read receipts and rendered links
> - The benefit is fewer false failures, with no case made easier

## Linked Issues or Issue Description

Refs #21000

**What happened?**
- `projects.project-work`, `tasks.private-task`,
`status-cards.other-authors-card` and part of
`task-coordination.delegate-with-context`: the CEO created a task with
no assignee, so the CEO got a queued run on it. The CEO then reassigned
the task. The server cancelled the queued run before it started
(`issue_reassigned` or `issue_assignee_changed`). The early poll
reported this as "Observed provider run failed", and the run policy
counted a never-started legacy run as a failed native run.
- `budgets-costs.repair-cost-recording`: after the retry, the chat run
re-read the original run record with `saveResponse`. The check accepted
only an exact whole-input digest, and this input had another shape.
- `secrets.personal-secret`: the reply linked My secrets and said "Enter
the value only there, never in chat". `solicitsChatCredential` read
"never in chat" as a request to send the value in chat.
- `companies.import-preview`: the reply linked
`/COM/agents/morgan-package`. The check accepted only `/agents/<uuid>`.
- `cases.close-case`: the closure was correct. The result turn said
"Case COM-C1 is saved as closed". A keyword pattern did not match that
sentence.

**Expected behavior**
Each check passes the recorded valid behavior and a reworded valid
variant. Each check fails the broken behavior.

**Steps to reproduce**
Grade the retained cohort-3 evidence with the old checks. They fail. The
calibration tests in this pull request use the same recorded shapes.

## What Changed

- Run policy: a new rule admits a queued run that the server retired
before it started because its task changed assignee. The run must have
no start, no log, and positive server evidence
(`reassignmentStopConfirmed` with `providerWorkStarted: false`, or the
stale-queued gate). The task must not be the source chat. A later run by
another agent on the same task must exist. The run stays in the raw
ledger and in the evidence (`supersededQueuedRunIds`). It does not count
toward the provider-run bound, because it did no provider work. A case
can have at most one such run (`catalog-superseded-queued-runs`). The
early poll defers it to the grade instead of failing at once. Cases read
the ledger without it. Other cancellations stay failures.
- `budgets-costs.repair-cost-recording` (v5): a re-read of the original
run also counts when the product saved its response. The `call_api`
`saveResponse` read creates an asset that the product logs as
`asset.created` by that run. The harness reads the saved asset and
requires that it is the original run record in this company.
- `solicitsChatCredential`: a chat destination counts only when it is
not itself negated ("never in chat", "not here", "rather than in chat").
This is a scope rule, not a new phrase exception. "Paste it here" and
mixed requests still fail. `secrets.personal-secret` is v18.
- `companies.import-preview` (v3): new `agentRouteNames` accepts
`/<prefix>/agents/<id or url key>[/<tab>]` that names the imported
agent. It rejects the existing Morgan, other companies and other
origins.
- `cases.close-case` (v2): the result turn is graded on its own saved
replies. Their run must read the saved case (`read_case` or `GET
/api/cases/{id}`, bound by the redaction-safe receipt). The reply must
render a link to that case. The case must be done. The wording is not
matched. `api-read-receipts` now binds the dedicated `read_case` tool.
- The four reassignment cases get new oracle versions. Descriptors are
updated. No scenario yaml changed, so the TestOps manifest does not
change.

## Verification

- `npx vitest run --config tests/runner-e2e/vitest.config.ts` on the 17
affected test files: 516 tests pass. The files include
`chat-catalog-run-policy`, `chat-flow`, `non-execution-wake`,
`chat-catalog-consistency`, `chat-catalog-fingerprint`,
`identity-accounting`, `external-credential-language`,
`external-personal-secret`, `identity-portability`,
`integrator-case-close`, `api-read-receipts` and the other
secret-language users.
- Each change has calibration tests: the recorded valid shape, a
reworded valid shape, and broken shapes (no successor run, a started or
other cancellation, churn; another run's saved record; "paste it here";
the existing Morgan's route; an unread or unlinked result turn).
- `npx tsc -p tests/runner-e2e/tsconfig.json --noEmit` passes.
- `node tests/runner-e2e/source-sdk-public-inputs.mjs <HEAD> --check`
reports no change.
- One paid run on a combined branch with the companion harness pull
request. The result is in a comment on this pull request.

## Risks

- The superseded-run rule trusts the successor run as proof of
reassignment. A case oracle still grades the task assignee and the
successor's own outcome.
- The close-case result turn no longer checks the reply's words. A reply
that reads the closed case and links it but states the wrong result
passes this one check. The first-turn premature-claim check and the
negative-case check do not change.
- The credential grader change also affects other secret cases. It only
removes the negated-destination false positive.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, with tool use and code
execution in Claude Code.

## 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
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:07:06 -06:00

97 lines
8.0 KiB
TypeScript

import { readFile } from "node:fs/promises";
import { stripTypeScriptTypes } from "node:module";
import { afterEach, beforeEach, expect, it, vi } from "vitest";
const control = vi.hoisted(() => ({
collectorEntered: Promise.resolve(), collectorRelease: Promise.resolve(), enter: () => {}, release: () => {}, completeQuery: false, stall: true, savedState: { label: "before cleanup" },
}));
beforeEach(() => {
control.completeQuery = false; control.stall = true; control.savedState = { label: "before cleanup" };
control.collectorEntered = new Promise<void>(resolve => { control.enter = resolve; });
control.collectorRelease = new Promise<void>(resolve => { control.release = resolve; });
});
afterEach(() => vi.useRealTimers());
vi.mock("./sdk-canary-prefixture.js", () => ({ assertSdkCanaryFingerprintMatches: () => {} }));
vi.mock("./chat-catalog-registry.js", () => ({
findChatCatalogCase: () => ({}),
loadChatCatalogImplementation: async () => ({ scenarioId: "questions-and-approvals.multi-part-question", attemptTimeoutMs: 300000,
expectedRunCount: 2, turnTimeoutMs: 300000, setupPolicy: { readiness: "preserve-scenario", funding: "preserve-scenario" }, setup: async () => control.savedState, cleanup: async () => { control.savedState.label = "after cleanup"; }, observe: async () => ({ state: control.savedState }), grade: () => ({ passed: false, checks: [{ id: "not-completed", passed: false, detail: "Pending native continuation" }] }) }),
}));
vi.mock("./chat-catalog-fingerprint.js", () => ({ chatCatalogCaseFingerprint: () => ({}), normalizedChatCatalogExecution: () => ({}) }));
vi.mock("./chat-query-bindings.js", () => ({ resolveChatCatalogQuery: async () => { if (control.completeQuery) return { renderedQuery: "Original request" }; throw new Error("Original attempt failed"); } }));
vi.mock("./chat-rendered-links.js", () => ({ collectConversationLinks: async () => [] }));
vi.mock("./chat-catalog-run-policy.js", () => ({ gradeChatCatalogRuns: () => ({ checks: [] }), CHAT_CATALOG_MAX_SUPERSEDED_QUEUED_RUNS: 1,
chatCatalogProviderRuns: (runs: unknown[]) => runs, chatCatalogSupersededQueuedRuns: () => [], chatCatalogReassignedQueuedRun: () => false }));
vi.mock("./chat-flow.js", () => ({ sendChatMessage: async () => {}, collectChatRunEvidence: async () => { control.enter(); if (control.stall) await control.collectorRelease; return {}; } }));
vi.mock("./api.js", () => ({ pollUntil: async ({ load }: { load: () => Promise<unknown> }) => { await load(); throw new Error("Original attempt failed"); } }));
import { runChatCatalogFlow } from "./chat-catalog-flow.js";
it("does not let a stalled failure collector prevent outer retirement of an owned pending native", async () => {
let retired = false;
const run = { id: "pending-native", companyId: "company", agentId: "ceo", status: "running", runtimeMode: "native" };
const context = { scenario: { id: "questions-and-approvals.multi-part-question", query: "Original question-form request" },
input: { execution: { task: { turnTimeoutMs: 0 } }, fixtures: { company: { id: "company", issuePrefix: "RUN" }, agent: { id: "ceo" } },
api: { baseURL: "http://127.0.0.1", get: async () => [] }, page: { locator: () => ({ count: async () => 0 }) }, evidence: async () => {} },
refreshIssue: async () => {}, issue: () => ({ id: "source", companyId: "company" }), allRuns: async () => [run] };
Object.assign(context.input, { retireFailedAttempt: async () => { retired = true; run.status = "cancelled"; } });
const attempt = runChatCatalogFlow(context as never).finally(async () => { retired = true; run.status = "cancelled"; });
const rejected = expect(attempt).rejects.toThrow("Original attempt failed");
await control.collectorEntered;
const retiredBeforeCollectorReleased = retired;
control.release();
await rejected;
expect(retired).toBe(true);
expect(retiredBeforeCollectorReleased).toBe(true);
});
it("bounds failed collection and cannot write evidence after the collector later resolves", async () => {
vi.useFakeTimers();
const writes: string[] = [], order: string[] = [];
const context = { scenario: { id: "questions-and-approvals.multi-part-question", query: "Original request" },
input: { execution: { task: { turnTimeoutMs: 0 } }, fixtures: { company: { id: "company" }, agent: { id: "ceo" } },
api: { baseURL: "http://127.0.0.1", get: async () => [] }, page: { locator: () => ({ count: async () => 0 }) }, evidence: async (name: string) => { writes.push(name); },
retireFailedAttempt: async () => { order.push("retired"); } },
refreshIssue: async () => {}, issue: () => ({ id: "source", companyId: "company" }), allRuns: async () => [{ id: "pending", companyId: "company", status: "cancelled" }] };
const attempt = runChatCatalogFlow(context as never);
const rejected = expect(attempt).rejects.toThrow("Original attempt failed");
await control.collectorEntered;
expect(order).toEqual(["retired"]);
await vi.advanceTimersByTimeAsync(5000);
await rejected;
expect(writes).toContain("chat-catalog-evidence-error.json");
const finishedWrites = [...writes];
control.release();
await vi.advanceTimersByTimeAsync(0);
expect(writes).toEqual(finishedWrites);
});
it("preserves the primary failure when retirement and failure evidence persistence fail", async () => {
const context = { scenario: { id: "questions-and-approvals.multi-part-question", query: "Original request" },
input: { execution: { task: { turnTimeoutMs: 0 } }, evidence: async (name: string) => {
if (name === "chat-catalog-evidence-error.json") throw new Error("Evidence storage failed");
}, retireFailedAttempt: async () => { throw new Error("Retirement failed"); } } };
await expect(runChatCatalogFlow(context as never)).rejects.toThrow("Original attempt failed");
});
it("retains completed observation and conversation before scenario cleanup mutates state", async () => {
control.completeQuery = true; control.stall = false;
const snapshots: Record<string, any> = {};
const context = { scenario: { id: "questions-and-approvals.multi-part-question", query: "Original request" },
input: { execution: { task: { turnTimeoutMs: 0 } }, fixtures: { company: { id: "company", issuePrefix: "RUN" }, agent: { id: "ceo" } },
api: { baseURL: "http://127.0.0.1", get: async (route: string) => route.endsWith("/budgets/overview") ? { policies: [] } : route.startsWith("/api/agents/") ? { adapterConfig: { timeoutSec: 0 } } : route.endsWith("/interactions") ? [{ id: "question" }] : [] },
page: { locator: () => ({ count: async () => 0 }) }, evidence: async (name: string, value: unknown) => { snapshots[name] = structuredClone(value); }, retireFailedAttempt: async () => {} },
refreshIssue: async () => {}, issue: () => ({ id: "source", companyId: "company" }), allRuns: async () => [] };
await expect(runChatCatalogFlow(context as never)).rejects.toThrow("Original attempt failed");
expect(snapshots["api-state.json"]).toMatchObject({ issue: { id: "source" }, comments: [], interactions: [{ id: "question" }], observation: { state: { label: "before cleanup" } } });
expect(control.savedState.label).toBe("after cleanup");
});
it("executes the real outer failure-capture guard without entering a held duplicate API read", async () => {
const source = await readFile(new URL("./runner.spec.ts", import.meta.url), "utf8");
const start = source.indexOf(" const captureApiState = async (capturePhase: \"failure\" | \"final\" = \"failure\") => {"), end = source.indexOf("\n\n page.on", start);
const body = stripTypeScriptTypes(source.slice(start, end), { mode: "strip" });
let reads = 0;
const capture = new Function("catalogFailureCaptureAttempted", "fixtures", "api", body + "; return captureApiState;")(true, { company: { id: "company" } }, { get: async () => { reads++; return new Promise(() => {}); } });
const primary = new Error("Original attempt failed");
const caller = (async () => { try { throw primary; } catch (error) { await capture(); throw error; } })();
await expect(caller).rejects.toBe(primary);
expect(reads).toBe(0);
expect(source).toContain("if (!(error instanceof SetupHealthAbort)) await captureApiState();");
});