Files
PaperClipAI/tests/runner-e2e/chat-catalog-domains/runtime-infrastructure.test.ts
T
f4337bb5fb test(evals): land the chat catalog eval harness on master (#19614)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - The chat-feature evals measure whether agents complete real chat
requests through the product
> - The chat catalog eval harness and its repairs live on the
`chat-eval/master-candidate` branch, not on master
> - Today's work made 139 of 242 chat evals pass in verified single-case
live runs. Each product fix landed on master as its own pull request
> - The eval-side changes (setups, graders, fault seams, evidence
capture) still exist only on the candidate
> - This pull request lands the harness on master. Master stays the
source of truth for product behavior
> - The benefit is one tree: evals run against master commits, and
product fixes reach the evals as soon as they merge

## Linked Issues or Issue Description

Refs #19441, Refs #19599, Refs #20270, Refs #20334, Refs #20342, Refs
#20344, Refs #20354, Refs #20360, Refs #20373, Refs #20382, Refs #20409

**What existing behavior does this improve?**
The chat catalog eval harness and the product it evaluates live on a
long-running branch outside master. Eval fixes do not reach master, so
master-based eval runs use old setups and graders.

**Subsystem affected**
`tests/runner-e2e` chat catalog harness, plus a small set of product
changes that exist only on the candidate.

**Proposed change**
Land the harness on master. Every product fix from this eval work
already merged to master as its own pull request. Conflicts keep
master's product behavior.

## What Changed

- Most of the diff (808 of 851 files) is under `tests/runner-e2e/`:
chat-catalog domains, scenarios, descriptors, the TestOps manifest,
private evidence tooling, and their tests.
- Graders now check saved state, setup literals and rendered or clicked
links. Many keyword and regex checks on free-form replies are removed.
Each changed grader has a bumped `oracleVersion` and calibration tests
(a valid reply, a reworded valid reply, and broken variants that must
fail).
- The shared link helper `hasLink` no longer treats a list link (for
example `/COM/issues?view=mine`) as a link to every task without a URL
key.
- Setup fixes build real state through supported product routes: routine
history, agent grants through the board grant route, budget holds with a
real cap, and a storage-layer archive fault for
`inbox-search.archive-partial-failure`.
- Browser boundary journeys (sign-in, chat-disabled, onboarding) now
write the standard pass evidence files.
- Retargeted cases, approved by the maintainer:
`agent-chat.chat-disabled` (Conference Room gate),
`agents.restore-instructions` (no saved instruction history),
`access.manage-membership` (member permission edits stay board-only).
- The private evidence trusted files (`manual-private-handoff.ts`,
`manual-private-retention.ts`, `manual-private-report-assets.ts`) are
byte-identical to master.
- Product files outside `tests/` (43 files, +1,328 −49) carry
candidate-only changes that master does not yet have. Most are tests.
The main code changes are in `request-human-input.ts`,
`heartbeat-run-summary.ts`, `native-completion-feedback.ts`,
`native-run-finalizer.ts`, `openapi.ts`, `secrets.ts` and
`IssueChatLongThreadPerf.tsx`.

## Verification

- `pnpm vitest run chat-catalog-domains chat-catalog-contract.test.ts
chat-catalog-consistency.test.ts unit-launcher.test.mjs
--testTimeout=180000` in `tests/runner-e2e`: 269 files pass, 3,550 tests
pass.
- `node --test chat-full-catalog-testops-manifest.test.mjs`: 10 pass.
- `node tests/runner-e2e/source-sdk-public-inputs.mjs <HEAD> --check`:
no change.
- `tsc` for `server` and `tests/runner-e2e`: clean.
- Live single-case verification: 139 of 242 cases passed on paid runs,
and a person read the saved evidence for each. These are single-case
runs, not one full-cohort run.

## Risks

- Large diff. Most of it is test-only, but the 43 non-test files change
product code paths. Review those files first.
- Some graders are now less strict on reply wording. A person must read
replies for meaning on those cases.
- 42 cases need disposable outside accounts (Notion, Slack, GitHub,
Daytona and others) and stay blocked. `access.invite-teammate` stays
failing until local agent isolation lands, because the runner's durable
state keeps a live invite token.
- The paid workflow compares the trusted private-evidence files with
master. They are unchanged, so this risk is low.

## Model Used

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

## 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>
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-11-10 08:02:11 -06:00

93 lines
11 KiB
TypeScript

import { expect, it } from "vitest";
import { exhaustedSourceRecovery, gradeInfrastructureRecovery, readSourceRecoveryRecord, sameRecoveryAction } from "./runtime-infrastructure.js";
import { savedCall } from "./api-read-receipts.test-fixtures.js";
function valid(id = "recovery.explain-stall") {
const recovery = { id: "recovery", companyId: "company", sourceIssueId: "website", kind: "active_run_watchdog", cause: "native_session_retry_exhausted", ownerType: "board", ownerAgentId: null,
returnOwnerAgentId: "morgan", recoveryIssueId: null, evidence: { runId: "run", coordinatorAttempt: 3, recoveryDisposition: "native_session_retry_exhausted" }, maxAttempts: 3, wakePolicy: null, nextAction: "Inspect the provider trace and explicitly choose a replacement run or provider configuration; automatic provider work is stopped." };
return { scenarioId: id, origin: "http://paperclip.test", companyId: "company", leadId: "ceo", agents: [], links: ["/COM/issues/COM-2"], humanQueries: [], reply: "", tasks: [{ id: "website" }], activity: [],
runs: [{ id: "run", agentId: "morgan", status: "failed" }, { id: "source", agentId: "ceo", status: "succeeded" }],
state: { task: { id: "website", identifier: "COM-2" }, queryRecoveryRead: true, worker: { id: "morgan" }, failure: { id: "run", status: "failed", nativePhase: "terminal_failure" }, recoveryBefore: recovery, recoveryAfter: { ...recovery },
setupFaults: [1, 2, 3].map(pid => ({ runId: "run", pid, errorCode: "native_runner_process_exited" })), sourceRecoveryVisible: true,
queryReply: "Website stopped after three native Runner infrastructure attempts exhausted recovery. The original task's recovery action belongs to the board: an operator must inspect its provider trace and explicitly choose a replacement run or provider configuration." } };
}
it("accepts actual bounded process failure and truthful source-scoped diagnosis", () => expect(gradeInfrastructureRecovery(valid()).passed).toBe(true));
it("accepts a natural factual explanation", () => { const o = valid(); o.state.queryReply = "The Website's native session hit its limit of 3 resume attempts after process loss. You can open the run details and inspect the provider trace before authorizing a retry; this needs operator action."; expect(gradeInfrastructureRecovery(o).passed).toBe(true); });
it("accepts actual original source recovery identification", () => { const o = valid("recovery.source-action"); o.state.queryReply = "Use the recovery action on the original Website task. Its board owner must inspect the run details and choose an explicit retry. A separate repair task is unnecessary."; expect(gradeInfrastructureRecovery(o).passed).toBe(true); });
it("rejects relabelled unavailable-model failure as infrastructure loss", () => { const o = valid(); o.state.setupFaults[0]!.errorCode = "native_provider_model_rejected"; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects an invented exhaustion counter", () => { const o = valid(); o.state.recoveryBefore.evidence.coordinatorAttempt = 1; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects three receipts for one reused PID", () => { const o = valid(); o.state.setupFaults[1]!.pid = 1; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects silently transferring the action owner", () => { const o = valid(); o.state.recoveryAfter.ownerType = "agent"; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects a foreign source action", () => { const o = valid(); o.state.recoveryAfter.sourceIssueId = "other"; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("does not grade reply wording", () => { const o = valid(); o.state.queryReply = "Short answer: see the task."; expect(gradeInfrastructureRecovery(o).passed).toBe(true); });
it("rejects an answer whose run never read the saved recovery record", () => { const o = valid(); o.state.queryRecoveryRead = false; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects an answer that does not link the original task", () => { const o = valid(); o.links = ["/COM/issues/COM-9"]; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("accepts a genuine call_api recovery read after the port redacts its body, bound to the source task or failed run", () => {
const read = (operationId: string, pathParams: Record<string, string>, status = 200) => savedCall({ operationId, pathParams }, status, "3", "run-1", { sourceIssueId: "website", runId: "run" });
expect(readSourceRecoveryRecord(read("GET /api/issues/{id}/recovery-actions", { id: "website" }), "website", "run", "COM-1")).toBe(true);
expect(readSourceRecoveryRecord(read("GET /api/issues/{id}", { id: "COM-1" }), "website", "run", "COM-1")).toBe(true);
expect(readSourceRecoveryRecord(read("GET /api/heartbeat-runs/{runId}", { runId: "run" }), "website", "run", "COM-1")).toBe(true);
expect(readSourceRecoveryRecord(read("GET /api/issues/{id}", { id: "COM-2" }), "website", "run", "COM-1")).toBe(false);
expect(readSourceRecoveryRecord(read("GET /api/heartbeat-runs/{runId}", { runId: "other" }), "website", "run", "COM-1")).toBe(false);
expect(readSourceRecoveryRecord(read("GET /api/issues/{id}/recovery-actions", { id: "website" }, 403), "website", "run", "COM-1")).toBe(false);
});
it("reads the recovery record only from exact product tool output", () => {
const event = (output: string, status = "completed") => ({ eventType: "tool.execution.completed", payload: { prpEvent: { sourceKind: "runner", payload: { status, output } } } });
const actions = '{"apiOperationId":"GET /api/issues/{id}/recovery-actions","body":{"active":{"sourceIssueId":"website"}}}';
const run = '{\\"apiOperationId\\": \\"GET /api/heartbeat-runs/{runId}\\", \\"id\\": \\"run\\"}';
expect(readSourceRecoveryRecord([event(actions)], "website", "run")).toBe(true);
expect(readSourceRecoveryRecord([event(run)], "website", "run")).toBe(true);
expect(readSourceRecoveryRecord([event(actions, "failed")], "website", "run")).toBe(false);
expect(readSourceRecoveryRecord([event(actions)], "other", "run")).toBe(false);
expect(readSourceRecoveryRecord([event('{"apiOperationId":"GET /api/issues/{id}/recovery-actions/x"} website')], "website", "run")).toBe(false);
expect(readSourceRecoveryRecord([event("I read the website recovery actions")], "website", "run")).toBe(false);
// The task read counts only when its saved blocker names this failed run.
const task = (body: string) => `{"apiOperationId":"GET /api/issues/{id}","data":${body}}`;
expect(readSourceRecoveryRecord([event(task('{"id":"website","executionBlocker":{"runId":"run","cause":"native_session_retry_exhausted"}}'))], "website", "run")).toBe(true);
expect(readSourceRecoveryRecord([event(task('{"id":"website","executionBlocker":null}'))], "website", "run")).toBe(false);
expect(readSourceRecoveryRecord([event(task('{"id":"other","executionBlocker":{"runId":"run"}}'))], "website", "run")).toBe(false);
expect(readSourceRecoveryRecord([event(task('{"id":"website","executionBlocker":{"runId":"run"}}'), "failed")], "website", "run")).toBe(false);
expect(readSourceRecoveryRecord([event('{"apiOperationId":"GET /api/issues/{id}/documents/{key}","data":"website run"}')], "website", "run")).toBe(false);
});
it("rejects duplicate repair chains", () => { const o = valid(); o.tasks.push({ id: "repair" }); expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects concealing resumed work as still failed", () => { const o = valid(); o.runs[0]!.status = "running"; expect(gradeInfrastructureRecovery(o).passed).toBe(false); });
it("rejects missing actual source recovery evidence", () => expect(gradeInfrastructureRecovery(undefined).passed).toBe(false));
// The product settles an exhausted native action as resolved/blocked under
// preserve_without_replay_v1 and blocks the task, where the human Retry lives.
function settled(overrides: Record<string, unknown> = {}, automatic: Record<string, unknown> = {}) {
const { recoveryBefore } = valid().state;
return { ...recoveryBefore, status: "resolved", outcome: "blocked", createdAt: "2026-11-09T15:13:11.000Z", wakePolicy: null,
nextAction: "Automatic recovery stopped. Recorded work is preserved; actions with unverified outcomes will not be repeated.",
evidence: { ...recoveryBefore.evidence, automaticRecovery: { policy: "preserve_without_replay_v1", runId: "run", replay: "blocked", ...automatic } }, ...overrides };
}
const run = { id: "run", status: "failed", nativePhase: "terminal_failure" } as never;
const select = (actions: unknown[], status = "blocked", active?: unknown) =>
exhaustedSourceRecovery({ active: active as never, actions: actions as never }, { status } as never, run, "company", "website", "morgan");
it("accepts the exhausted action settled as blocked without replay on a blocked task", () => {
const action = settled();
expect(select([action])?.id).toBe("recovery");
const o = valid(); o.state.recoveryBefore = action as never; o.state.recoveryAfter = { ...action } as never;
expect(gradeInfrastructureRecovery(o).passed).toBe(true);
});
it("still accepts the exhausted action while it is active", () => expect(select([], "blocked", { ...valid().state.recoveryBefore, status: "active" })?.id).toBe("recovery"));
it.each([
["a cancelled settlement", settled({ outcome: "cancelled" })],
["a settlement without the preserve-without-replay marker", settled({ evidence: { ...valid().state.recoveryBefore.evidence } })],
["a settlement for another run", settled({}, { runId: "other" })],
["a settlement under another policy", settled({}, { policy: "replay_v1" })],
["a settled action that kept a wake policy", settled({ wakePolicy: { kind: "resume_native_run", runId: "run" } })],
["a settled action for another attempt count", settled({ evidence: { ...settled().evidence, coordinatorAttempt: 2 } })],
])("rejects %s", (_label, action) => expect(select([action])).toBeUndefined());
it("rejects a settled exhaustion while the task is not blocked", () => expect(select([settled()], "todo")).toBeUndefined());
it("judges only the newest source action", () => {
const older = settled({ id: "older", createdAt: "2026-11-09T15:00:00.000Z" }), newer = settled({ id: "newer", outcome: "cancelled" });
expect(select([older, newer])).toBeUndefined();
});
it("reads before and after as the same action by ID, so a replacement is detected", () => {
const before = settled(), replacement = settled({ id: "replacement", createdAt: "2026-11-09T15:20:00.000Z" });
expect(sameRecoveryAction({ actions: [before as never] }, "recovery")?.id).toBe("recovery");
expect(sameRecoveryAction({ actions: [replacement as never] }, "recovery")).toBeUndefined();
const o = valid(); o.state.recoveryBefore = before as never; o.state.recoveryAfter = replacement as never;
expect(gradeInfrastructureRecovery(o).passed).toBe(false);
});