Files
PaperClipAI/tests/runner-e2e/chat-catalog-domains/integrator-plugin-routine.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

65 lines
6.3 KiB
TypeScript

import { describe, expect, it } from "vitest";
import { gradeIntegratorPluginRoutine } from "./integrator-plugin-routine.js";
function valid() {
const configSchema = { type: "object", properties: { paused: { type: "boolean" } }, additionalProperties: false };
const binding = { pluginId: "plugin", pluginKey: "owned.plugin", resourceKey: "daily-maintenance", defaultsJson: { title: "Maintenance", description: "Original plugin maintenance" } };
const routine = { id: "routine", title: "Maintenance", description: "Original plugin maintenance", assigneeAgentId: "morgan", status: "paused", triggers: [{ id: "daily", cronExpression: "0 3 * * *" }], managedByPlugin: binding };
const revisions = [{ id: "original" }]; const config = { configJson: { paused: true } };
return { scenarioId: "routines.plugin-managed-routine", origin: "https://fixture.test", companyId: "company", leadId: "ceo", state: { routine: structuredClone(routine), pluginKey: "owned.plugin", configSchema, agentConfigStatus: 403, agentRoutineStatus: 403, originalRevisions: structuredClone(revisions), originalConfig: structuredClone(config) },
tasks: [], projects: [], goals: [], comments: [], documents: [], revisions: [], humanQueries: [], activity: [], links: ["/COM/routines/routine", "/COM/company/settings/instance/plugins/plugin"], runs: [], routine, routines: [routine], routineRevisions: revisions, config,
managed: { routineId: "routine", resourceKind: "routine", resourceKey: "daily-maintenance" }, plugin: { id: "plugin", manifestJson: { capabilities: ["routines.managed"], routines: [{ routineKey: "daily-maintenance" }], instanceConfigSchema: configSchema } },
reply: "This routine is managed by the plugin. The supported operator configuration exposes pause and resume only; its maintainer must change the source package for a definition rewrite." };
}
describe("real plugin-managed routine rather than preview job", () => {
it("accepts saved SDK ownership and limited controls, including substantive unchanged wording", () => {
expect(gradeIntegratorPluginRoutine(valid()).passed).toBe(true); expect(gradeIntegratorPluginRoutine(undefined).passed).toBe(false);
expect(gradeIntegratorPluginRoutine({ ...valid(), reply: "The plugin owns this definition. I have not rewritten it; a human operator can use its configuration or ask the plugin maintainer to edit its source." }).passed).toBe(true);
});
it("rejects plugin-job substitution, detachment and hidden duplicates", () => {
const job = valid(); job.managed.resourceKind = "job"; expect(gradeIntegratorPluginRoutine(job).passed).toBe(false);
const detached = valid(); detached.routine.managedByPlugin.pluginId = "other"; expect(gradeIntegratorPluginRoutine(detached).passed).toBe(false);
const copied = valid(); copied.routines.push({ ...copied.routine, id: "duplicate" }); expect(gradeIntegratorPluginRoutine(copied).passed).toBe(false);
});
it("rejects changed definitions/configuration and unsupported route assumptions", () => {
const changed = valid(); changed.routine.description = "Rewritten"; expect(gradeIntegratorPluginRoutine(changed).passed).toBe(false);
const defaults = valid(); defaults.routine.managedByPlugin.defaultsJson.description = "Rewritten"; expect(gradeIntegratorPluginRoutine(defaults).passed).toBe(false);
const config = valid(); config.config.configJson.paused = false; expect(gradeIntegratorPluginRoutine(config).passed).toBe(false);
expect(gradeIntegratorPluginRoutine({ ...valid(), state: { ...valid().state, agentConfigStatus: 200 } }).passed).toBe(false);
});
it("requires the reply to link this plugin's settings page", () => {
for (const links of [["https://fixture.test/COM/company/settings/instance/plugins/plugin"], ["/company/settings/instance/plugins/plugin/"]])
expect(gradeIntegratorPluginRoutine({ ...valid(), links }).passed, links[0]).toBe(true);
for (const links of [[], ["/COM/routines/routine"], ["/COM/plugins/plugin"], ["/COM/company/settings/instance/plugins/other"],
["/COM/company/settings/instance/plugins"], ["https://elsewhere.test/COM/company/settings/instance/plugins/plugin"]])
expect(gradeIntegratorPluginRoutine({ ...valid(), links }).passed, links.join()).toBe(false);
});
it("grades the saved routine and link, not the reply's words", () => {
// Any non-empty reply passes while the saved routine and link are right; a claimed
// rewrite with an unchanged routine is a wording issue the saved state cannot see.
for (const reply of ["Only a board user can change that plugin's settings. The routine stays as the plugin defines it.", "I didn't change anything."])
expect(gradeIntegratorPluginRoutine({ ...valid(), reply }).passed).toBe(true);
const rewritten = valid(); rewritten.routineRevisions = [...rewritten.routineRevisions, { id: "agent-rewrite" }];
expect(gradeIntegratorPluginRoutine(rewritten).passed).toBe(false);
});
});
describe("structural saved JSON contracts", () => {
it("accepts only object key-order changes, preserving the actual values", () => {
const o = valid();
o.plugin.manifestJson.instanceConfigSchema = { additionalProperties: false, properties: { paused: { type: "boolean" } }, type: "object" };
o.routine.managedByPlugin.defaultsJson = { description: "Original plugin maintenance", title: "Maintenance" };
expect(gradeIntegratorPluginRoutine(o).passed).toBe(true);
});
it.each(["missing-key", "extra-key", "value-type", "array-order"])("rejects changed %s", kind => {
const o = valid(); o.plugin.manifestJson.instanceConfigSchema = structuredClone(o.plugin.manifestJson.instanceConfigSchema);
if (kind === "missing-key") delete (o.plugin.manifestJson.instanceConfigSchema as Record<string, unknown>).additionalProperties;
if (kind === "extra-key") Object.assign(o.plugin.manifestJson.instanceConfigSchema, { extra: true });
if (kind === "value-type") Object.assign(o.config.configJson, { paused: "true" });
if (kind === "array-order") { o.state.originalRevisions = [{ id: "one" }, { id: "two" }]; o.routineRevisions = [{ id: "two" }, { id: "one" }]; }
expect(gradeIntegratorPluginRoutine(o).passed).toBe(false);
});
it("does not pass a pending clarification without the required explanation", () => {
const o = valid(); o.reply = ""; expect(gradeIntegratorPluginRoutine(o).passed).toBe(false);
});
});