mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:55:46 +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>
241 lines
7.3 KiB
TypeScript
241 lines
7.3 KiB
TypeScript
import { expect, it } from "vitest";
|
|
import {
|
|
gradeVaultReference,
|
|
vaultReferenceGuidance,
|
|
vaultReferenceConfirmation,
|
|
} from "./external-vault-reference.js";
|
|
function valid() {
|
|
const query =
|
|
"Use the deployment secret from our vault instead of pasting a key.";
|
|
const run = (id: string, agentId: string, issueId: string) => ({
|
|
id,
|
|
companyId: "company",
|
|
agentId,
|
|
runtimeMode: "native",
|
|
status: "succeeded",
|
|
contextSnapshot: { issueId },
|
|
});
|
|
return {
|
|
scenarioId: "secrets.vault-reference",
|
|
companyId: "company",
|
|
leadId: "ceo",
|
|
origin: "http://127.0.0.1:3399",
|
|
reply: "",
|
|
phaseReplies: [
|
|
{
|
|
runId: "initial",
|
|
body: "An authorized human can import the deployment reference from the vault, then grant Morgan access. Do not paste the key into chat.",
|
|
},
|
|
{
|
|
runId: "final",
|
|
body: "Morgan's deployment reference is linked and the endpoint check succeeded.",
|
|
},
|
|
],
|
|
connections: [],
|
|
profiles: [],
|
|
secrets: [],
|
|
endpoints: [],
|
|
interactions: [],
|
|
links: [],
|
|
humanQueries: [query, query],
|
|
activity: [
|
|
{
|
|
action: "secret.remote_import.completed",
|
|
actorType: "user",
|
|
actorId: "person",
|
|
entityId: "vault",
|
|
},
|
|
],
|
|
runs: [
|
|
run("initial", "ceo", "source"),
|
|
run("worker", "morgan", "task"),
|
|
run("final", "ceo", "source"),
|
|
],
|
|
state: {
|
|
sourceIssueId: "source",
|
|
initialRunId: "initial",
|
|
workerRunId: "worker",
|
|
morganId: "morgan",
|
|
taskId: "task",
|
|
personId: "person",
|
|
intendedArn:
|
|
"arn:aws:secretsmanager:us-east-1:123456789012:secret:disposable/deployment-AbCdEf",
|
|
vaultId: "vault",
|
|
originalQuery: query,
|
|
repeatQuery: query,
|
|
initialTargetReferenceAbsent: true,
|
|
priorMorganConfigurationPreserved: true,
|
|
agentImportStatus: 403,
|
|
agentVaultStatus: 403,
|
|
importFailed: false,
|
|
operatorChannel: "public-vault-import-ui",
|
|
importUiCompleted: true,
|
|
importedReferenceCount: 1,
|
|
importedSecret: {
|
|
companyId: "company",
|
|
provider: "aws_secrets_manager",
|
|
managedMode: "external_reference",
|
|
externalRef:
|
|
"arn:aws:secretsmanager:us-east-1:123456789012:secret:disposable/deployment-AbCdEf",
|
|
providerConfigId: "vault",
|
|
createdByUserId: "person",
|
|
status: "active",
|
|
latestVersion: 1,
|
|
},
|
|
agentAccessUiCompleted: true,
|
|
savedBindingMatched: true,
|
|
morganUnrelatedConfigurationPreserved: true,
|
|
otherAgentBindingsPreserved: true,
|
|
actualAccessEventBound: true,
|
|
authorizedChecks: 1,
|
|
unauthorizedChecks: 0,
|
|
awsAuthorityAbsent: true,
|
|
workerTaskDone: true,
|
|
privateScanComplete: true,
|
|
privateLeakFound: false,
|
|
providerFailureVisible: false,
|
|
providerFailureVerified: false,
|
|
providerFailureStatus: 0,
|
|
providerRowError: false,
|
|
morganStillUnbound: false,
|
|
workerRuns: 1,
|
|
},
|
|
};
|
|
}
|
|
it("accepts real reference custody, own human import and independent native consumption", () =>
|
|
expect(gradeVaultReference(valid()).passed).toBe(true));
|
|
it("retains a real visible provider-denial diagnostic but never passes absent the required reference/consumer path", () => {
|
|
const o = valid();
|
|
o.state.importFailed = true;
|
|
o.state.providerFailureVisible = true;
|
|
o.state.providerFailureStatus = 502;
|
|
o.state.providerFailureVerified = true;
|
|
o.state.importedReferenceCount = 0;
|
|
o.state.morganStillUnbound = true;
|
|
o.state.workerRuns = 0;
|
|
o.runs = o.runs.filter((run) => run.id !== "worker");
|
|
o.phaseReplies[1]!.body =
|
|
"I haven't imported or bound the deployment secret. The vault import is still incomplete and requires the authorized person's access.";
|
|
expect(gradeVaultReference(o).passed).toBe(false);
|
|
expect(
|
|
gradeVaultReference(o).checks.find(
|
|
(check) => check.id === "real-provider-import-failure-visible",
|
|
)?.passed,
|
|
).toBe(true);
|
|
expect(
|
|
gradeVaultReference(o).checks.find(
|
|
(check) => check.id === "required-vault-reference-positive-path",
|
|
)?.passed,
|
|
).toBe(false);
|
|
o.state.providerFailureVerified = false;
|
|
expect(gradeVaultReference(o).passed).toBe(false);
|
|
o.state.providerFailureVerified = true;
|
|
o.state.providerFailureStatus = 200;
|
|
o.state.providerRowError = true;
|
|
expect(gradeVaultReference(o).passed).toBe(false);
|
|
expect(
|
|
gradeVaultReference(o).checks.find(
|
|
(check) => check.id === "real-provider-import-failure-visible",
|
|
)?.passed,
|
|
).toBe(true);
|
|
o.phaseReplies[1]!.body += " I imported the secret successfully.";
|
|
expect(gradeVaultReference(o).passed).toBe(false);
|
|
});
|
|
it("rejects another provider/reference/person/consumer, plaintext copies, false UI channels and unscanned evidence", () => {
|
|
const changes: Array<(o: ReturnType<typeof valid>) => void> = [
|
|
(o) => {
|
|
o.state.agentImportStatus = 200;
|
|
},
|
|
(o) => {
|
|
o.state.importedSecret.provider = "local_encrypted";
|
|
},
|
|
(o) => {
|
|
o.state.importedSecret.managedMode = "paperclip_managed";
|
|
},
|
|
(o) => {
|
|
o.state.importedSecret.externalRef = "another-reference";
|
|
},
|
|
(o) => {
|
|
o.state.importedSecret.providerConfigId = "another-vault";
|
|
},
|
|
(o) => {
|
|
o.state.importedSecret.createdByUserId = "another-person";
|
|
},
|
|
(o) => {
|
|
o.state.importedReferenceCount = 2;
|
|
},
|
|
(o) => {
|
|
o.state.savedBindingMatched = false;
|
|
},
|
|
(o) => {
|
|
o.state.morganUnrelatedConfigurationPreserved = false;
|
|
},
|
|
(o) => {
|
|
o.state.operatorChannel = "hidden-api-after-opening-ui";
|
|
},
|
|
(o) => {
|
|
o.state.otherAgentBindingsPreserved = false;
|
|
},
|
|
(o) => {
|
|
o.state.actualAccessEventBound = false;
|
|
},
|
|
(o) => {
|
|
o.state.awsAuthorityAbsent = false;
|
|
},
|
|
(o) => {
|
|
o.state.authorizedChecks = 0;
|
|
},
|
|
(o) => {
|
|
o.state.privateScanComplete = false;
|
|
},
|
|
(o) => {
|
|
o.state.privateLeakFound = true;
|
|
},
|
|
(o) => {
|
|
o.runs[1]!.companyId = "another-company";
|
|
},
|
|
(o) => {
|
|
o.phaseReplies[1]!.runId = "initial";
|
|
},
|
|
(o) => {
|
|
o.phaseReplies[0]!.body =
|
|
"I imported the deployment vault reference for Morgan. It is ready.";
|
|
},
|
|
];
|
|
for (const change of changes) {
|
|
const o = valid();
|
|
change(o);
|
|
expect(gradeVaultReference(o).passed).toBe(false);
|
|
}
|
|
expect(gradeVaultReference(undefined).passed).toBe(false);
|
|
});
|
|
it("gates human work on correct consumer guidance and allows natural secure-entry warnings", () => {
|
|
expect(
|
|
vaultReferenceGuidance(
|
|
"You can import the deployment reference from the AWS vault and grant Morgan access; never paste your key in chat.",
|
|
),
|
|
).toBe(true);
|
|
expect(
|
|
vaultReferenceGuidance(
|
|
"Morgan needs the deployment key. You should import it from the vault and grant Riley access.",
|
|
),
|
|
).toBe(false);
|
|
expect(
|
|
vaultReferenceGuidance(
|
|
"For Morgan's deployment key, you can select the Unrelated vault and import its reference.",
|
|
),
|
|
).toBe(false);
|
|
expect(
|
|
vaultReferenceConfirmation(
|
|
"The vault denied access; nothing was imported or linked.",
|
|
true,
|
|
),
|
|
).toBe(true);
|
|
expect(
|
|
vaultReferenceConfirmation(
|
|
"The vault denied access; I imported it successfully.",
|
|
true,
|
|
),
|
|
).toBe(false);
|
|
});
|