mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 00:26:28 +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>
60 lines
5.1 KiB
TypeScript
60 lines
5.1 KiB
TypeScript
import { chatPrivateInputRequirements, chatPrivateInputNameIdentity } from "./chat-private-inputs.js";
|
|
import { createHash } from "node:crypto";
|
|
import { readFileSync, realpathSync } from "node:fs";
|
|
import path from "node:path";
|
|
import { findPackageJSON } from "node:module";
|
|
import { fileURLToPath, pathToFileURL } from "node:url";
|
|
import { fingerprintChatDependencyClosure } from "./chat-catalog-fingerprint.js";
|
|
import type { ChatCatalogDescriptor } from "./chat-catalog-registry.js";
|
|
import type { MatrixExecution } from "./types.js";
|
|
|
|
/** The campaign ledger is mutable; only this selected frozen scenario is
|
|
* definition metadata. Executable sources and unknown closure stay byte-bound.
|
|
*/
|
|
export function boundaryScenarioMetadata(manifest: unknown, scenarioId: string) {
|
|
const rows = (manifest as { scenarios?: unknown } | null)?.scenarios;
|
|
if (!scenarioId.trim() || !Array.isArray(rows)) throw new Error(`Missing frozen boundary scenario: ${scenarioId}`);
|
|
const matches = rows.filter(row => row && typeof row === "object" && row.id === scenarioId);
|
|
if (matches.length !== 1) throw new Error(`Missing or duplicate frozen boundary scenario: ${scenarioId}`);
|
|
const { id, capabilities, context, query, expected_outcome } = matches[0];
|
|
if (!Array.isArray(capabilities) || !capabilities.every(value => typeof value === "string")
|
|
|| [context, query, expected_outcome].some(value => typeof value !== "string" || !value.trim()))
|
|
throw new Error(`Invalid frozen boundary scenario: ${scenarioId}`);
|
|
return { id, capabilities, context, query, expected_outcome };
|
|
}
|
|
|
|
/** Independent boundary lane: never relax assertChatCatalogFingerprintLane. */
|
|
export function chatBoundaryFingerprint(descriptor: ChatCatalogDescriptor, execution: MatrixExecution, env: NodeJS.ProcessEnv = process.env, retainedPrivateInputNames?: ReturnType<typeof chatPrivateInputNameIdentity>) {
|
|
if (descriptor.journeyKind !== "browser-boundary" || execution.environment.id !== "local" || execution.suite.id !== "chat-features")
|
|
throw new Error("Boundary fingerprint requires an explicitly selected local browser boundary");
|
|
const privateInputNameIdentity = retainedPrivateInputNames === undefined ? chatPrivateInputNameIdentity(execution.id, env) : retainedPrivateInputNames;
|
|
let installedIdentity: unknown = null;
|
|
if (descriptor.boundaryTarget === "empty-installed-target") {
|
|
const cli = env.PAPERCLIP_CHAT_BOUNDARY_CLI; const expectedCli = env.PAPERCLIP_CHAT_BOUNDARY_CLI_SHA256;
|
|
const expectedServer = env.PAPERCLIP_CHAT_BOUNDARY_SERVER_SHA256;
|
|
if (!cli || !path.isAbsolute(cli) || !expectedCli || !expectedServer) throw new Error("Empty-installation boundary requires actual immutable installed CLI and server identity pins");
|
|
if (realpathSync(cli) !== cli) throw new Error("Boundary installed CLI must be canonical and unlinked");
|
|
const cliManifest = JSON.parse(readFileSync(path.resolve(path.dirname(cli), "../package.json"), "utf8"));
|
|
const serverManifestPath = findPackageJSON("@paperclipai/server", pathToFileURL(cli));
|
|
if (!serverManifestPath) throw new Error("Boundary CLI has no resolvable installed server");
|
|
const serverManifest = JSON.parse(readFileSync(serverManifestPath, "utf8"));
|
|
const serverEntry = path.join(path.dirname(serverManifestPath), "dist/index.js");
|
|
const digest = (name: string) => createHash("sha256").update(readFileSync(name)).digest("hex");
|
|
const cliSha256 = digest(cli); const serverSha256 = digest(serverEntry);
|
|
if (cliManifest.name !== "paperclipai" || serverManifest.name !== "@paperclipai/server" || cliManifest.version !== serverManifest.version
|
|
|| cliSha256 !== expectedCli || serverSha256 !== expectedServer) throw new Error("Boundary installed CLI/server differ from their declared pins");
|
|
installedIdentity = { version: cliManifest.version, cliSha256, serverSha256 };
|
|
} else if (descriptor.boundaryTarget !== "authenticated-harness") throw new Error("Boundary target identity is undeclared");
|
|
const scenario = boundaryScenarioMetadata(JSON.parse(readFileSync(new URL("./chat-campaign-manifest.json", import.meta.url), "utf8")), descriptor.scenarioId);
|
|
const root = fileURLToPath(new URL("../../", import.meta.url));
|
|
const result = fingerprintChatDependencyClosure({ root,
|
|
entries: [`tests/runner-e2e/${descriptor.modulePath.slice(2)}`, "tests/runner-e2e/chat-boundary-flow.ts", "tests/runner-e2e/chat-boundary-fingerprint.ts",
|
|
"tests/runner-e2e/runner.spec.ts", "tests/runner-e2e/launch.ts", ...descriptor.sourceFiles.map(file => `tests/runner-e2e/${file}`)],
|
|
selected: { descriptor, scenario, journeyKind: "browser-boundary", executionId: execution.id, privateInputRequirements: chatPrivateInputRequirements(descriptor), privateInputNameIdentity, requiredCredentialNames: execution.requiredCredentials, environment: execution.environment.id, installedIdentity },
|
|
selectedDispatchFile: "tests/runner-e2e/chat-catalog-registry.ts",
|
|
normalizedMetadata: { "tests/runner-e2e/chat-catalog-descriptors.json": descriptor,
|
|
"tests/runner-e2e/chat-campaign-manifest.json": scenario },
|
|
});
|
|
return { ...result, privateInputNameIdentity, privateInputRequirements: chatPrivateInputRequirements(descriptor) };
|
|
}
|