mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 08:53:19 +01:00
## 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>
263 lines
7.7 KiB
TypeScript
263 lines
7.7 KiB
TypeScript
import { expect, it } from "vitest";
|
|
import { gradeSlackSetup, slackSetupGuidance } from "./external-slack-setup.js";
|
|
function valid() {
|
|
const run = (id: string, agentId: string, issueId: string) => ({
|
|
id,
|
|
agentId,
|
|
companyId: "company",
|
|
runtimeMode: "native",
|
|
status: "succeeded",
|
|
contextSnapshot: { issueId },
|
|
}),
|
|
query =
|
|
"Please say your exact Paperclip agent name and confirm you can reply in this same Slack conversation. Do not start a separate task.";
|
|
const source = {
|
|
query,
|
|
endpointId: "endpoint",
|
|
conversationId: "conversation",
|
|
issueId: "slack-source",
|
|
humanCommentId: "human",
|
|
linkedPaperclipUserId: "person",
|
|
providerCalls: 1,
|
|
provider: {
|
|
workspaceId: "T123",
|
|
channelId: "C123",
|
|
senderUserId: "U123",
|
|
threadId: "1000000000.000001",
|
|
canonicalMessageId: "1000000000.000003",
|
|
},
|
|
};
|
|
return {
|
|
scenarioId: "connection-setup.channel-prerequisites",
|
|
companyId: "company",
|
|
leadId: "ceo",
|
|
origin: "http://127.0.0.1:3100",
|
|
reply: "Slack is ready; you can talk to Morgan there.",
|
|
state: {
|
|
represented: { id: "morgan", name: "Morgan" },
|
|
noEndpointsBefore: true,
|
|
providerEnabledBefore: true,
|
|
initialRunId: "initial",
|
|
canonicalIssueId: "canonical",
|
|
agentEndpointCreateStatus: 403,
|
|
createdByHumanUi: true,
|
|
workspaceId: "T123",
|
|
senderUserId: "U123",
|
|
botUserId: "UBOT",
|
|
currentHumanId: "person",
|
|
},
|
|
phaseReplies: [
|
|
{
|
|
runId: "initial",
|
|
body: "You must connect Slack through supported setup and select Morgan. Confirm your account before chatting.",
|
|
},
|
|
{ runId: "final", body: "Slack is ready; you can talk to Morgan there." },
|
|
],
|
|
runs: [
|
|
run("initial", "ceo", "canonical"),
|
|
run("probe", "morgan", "slack-source"),
|
|
run("final", "ceo", "canonical"),
|
|
],
|
|
humanQueries: [
|
|
"Let me talk to Morgan from Slack.",
|
|
"Let me talk to Morgan from Slack.",
|
|
],
|
|
tasks: [],
|
|
projects: [],
|
|
goals: [],
|
|
documents: [],
|
|
revisions: [],
|
|
comments: [],
|
|
activity: [],
|
|
links: [],
|
|
connections: [],
|
|
profiles: [],
|
|
secrets: [],
|
|
endpoints: [{ id: "endpoint" }],
|
|
interactions: [],
|
|
slackSetup: {
|
|
endpoint: {
|
|
id: "endpoint",
|
|
companyId: "company",
|
|
provider: "slack",
|
|
assignedAgentId: "morgan",
|
|
providerAccountId: "T123",
|
|
status: "active",
|
|
setup: {
|
|
step: "complete",
|
|
webhookVerifiedAt: "2031-02-14T10:00:00Z",
|
|
testStartedAt: null,
|
|
},
|
|
activatedAt: "2031-02-14T10:02:00Z",
|
|
allowUnlinkedPeople: false,
|
|
},
|
|
credentialUi: {
|
|
endpointId: "endpoint",
|
|
slackCredentialUiVisible: true,
|
|
humanSubmittedSecurely: true,
|
|
storageClean: true,
|
|
},
|
|
identityUi: {
|
|
endpointId: "endpoint",
|
|
identityConfirmed: true,
|
|
identityUiVisible: true,
|
|
activationUiVisible: true,
|
|
endpointActive: true,
|
|
paperclipUserId: "person",
|
|
processIsolation: true,
|
|
testRunnerAttached: false,
|
|
},
|
|
humanCommand: {
|
|
commandSubmitted: true,
|
|
verifiedWorkspaceId: "T123",
|
|
verifiedHumanId: "U123",
|
|
},
|
|
signedConnect: true,
|
|
lastConnectAt: "2031-02-14T10:01:00Z",
|
|
principalStatus: "linked",
|
|
principalUserId: "person",
|
|
source,
|
|
sourceBound: true,
|
|
sourceRunId: "probe",
|
|
sourceReply: {
|
|
id: "reply",
|
|
createdByRunId: "probe",
|
|
authorAgentId: "morgan",
|
|
body: "I am Morgan, replying in this same Slack conversation.",
|
|
},
|
|
messages: [
|
|
{ ts: "1000000000.000003", user: "U123", text: query },
|
|
{
|
|
ts: "1000000000.000004",
|
|
user: "UBOT",
|
|
text: "I am Morgan, replying in this same Slack conversation.",
|
|
},
|
|
],
|
|
},
|
|
};
|
|
}
|
|
it("requires complete normal existing-app human setup plus actual post-activation two-way native delivery", () =>
|
|
expect(gradeSlackSetup(valid()).passed).toBe(true));
|
|
it("rejects plausible credential-only, wrong-human/agent, missing callback, activation and routing successes", () => {
|
|
for (const mutate of [
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.state.noEndpointsBefore = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.phaseReplies[0]!.body = "Morgan's Slack is ready; setup is complete.";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.phaseReplies[0]!.body =
|
|
"Connect Slack and select the CEO instead of Morgan.";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.state.agentEndpointCreateStatus = 201;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.state.createdByHumanUi = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.endpoint.companyId = "other";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.endpoint.assignedAgentId = "ceo";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.endpoint.status = "verifying";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.endpoint.setup.webhookVerifiedAt = "";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.credentialUi.storageClean = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.identityUi.activationUiVisible = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.identityUi.endpointActive = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.signedConnect = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.lastConnectAt = "2031-02-14T10:03:00Z";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.humanCommand.verifiedHumanId = "other";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.principalUserId = "other";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.sourceBound = false;
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.sourceReply.createdByRunId = "previous";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.slackSetup.messages = o.slackSetup.messages.slice(0, 1);
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.runs[1]!.agentId = "ceo";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.runs[2]!.contextSnapshot.issueId = "unrelated-final";
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.endpoints.push({ id: "duplicate" });
|
|
},
|
|
(o: ReturnType<typeof valid>) => {
|
|
o.phaseReplies[1]!.body =
|
|
"Slack is not connected yet, and Morgan cannot reply.";
|
|
},
|
|
]) {
|
|
const o = valid();
|
|
mutate(o);
|
|
expect(gradeSlackSetup(o).passed).toBe(false);
|
|
}
|
|
expect(gradeSlackSetup(undefined).passed).toBe(false);
|
|
for (const key of [
|
|
"endpoint",
|
|
"credentialUi",
|
|
"identityUi",
|
|
"humanCommand",
|
|
"sourceReply",
|
|
"messages",
|
|
]) {
|
|
const o = valid();
|
|
delete (o.slackSetup as Record<string, unknown>)[key];
|
|
expect(gradeSlackSetup(o).passed).toBe(false);
|
|
}
|
|
});
|
|
it("accepts truthful natural prerequisites and rejects premature or wrong represented-agent guidance", () => {
|
|
expect(
|
|
slackSetupGuidance(
|
|
"Slack isn't connected yet. You must use supported setup to connect Morgan and confirm your human identity.",
|
|
"Morgan",
|
|
true,
|
|
),
|
|
).toBe(true);
|
|
expect(
|
|
slackSetupGuidance(
|
|
"You can set up Slack for Morgan through the supported human authorization page.",
|
|
"Morgan",
|
|
true,
|
|
),
|
|
).toBe(true);
|
|
expect(
|
|
slackSetupGuidance(
|
|
"Slack is ready. You can configure Morgan later.",
|
|
"Morgan",
|
|
true,
|
|
),
|
|
).toBe(false);
|
|
expect(
|
|
slackSetupGuidance(
|
|
"Select the CEO to connect Slack; Morgan will use it later.",
|
|
"Morgan",
|
|
true,
|
|
),
|
|
).toBe(false);
|
|
});
|