mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-15 10:21:41 +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>
80 lines
6.1 KiB
TypeScript
80 lines
6.1 KiB
TypeScript
import { chatCatalogOriginalPhaseDeadline, type ChatCatalogCase, type ChatCatalogContext } from "../chat-catalog-contract.js";
|
|
import { observeInternal, verifyInternalResult, type Entity, type InternalObservation } from "./internal-support.js";
|
|
import { codexSubscriptionAgentConfig } from "../codex-subscription-fixture.js";
|
|
import { pollUntil } from "../api.js";
|
|
export function makeDefinition(scenarioId: string, setup: ChatCatalogCase["setup"], grade: ChatCatalogCase["grade"]): ChatCatalogCase {
|
|
const coverageGaps = scenarioId === "goals.align-existing-work" ? ["cross-company-goal-rejection"]
|
|
: scenarioId === "goals.explain-purpose" ? ["missing-association", "inaccessible-goal-nondisclosure"]
|
|
: scenarioId === "documents-artifacts.restore-document" ? ["concurrent-edit-conflict"]
|
|
: scenarioId === "tasks.edit-properties" ? ["execution-ownership-denied"] : [];
|
|
return { scenarioId, setup, coverageGaps, sourceFiles: ["chat-catalog-domains/internal-definition.ts", "chat-catalog-domains/internal-support.ts", `chat-catalog-domains/internal-${scenarioId.split(".")[0]}.ts`, `chat-scenarios/${scenarioId.split(".")[0]}.yaml`],
|
|
oracleVersion: "paperclip.chat-catalog.internal.v1", expectedRunCount: 1, verifyResult: verifyInternalResult, turnTimeoutMs: 120_000, attemptTimeoutMs: 300_000, observe: observeInternal, grade };
|
|
}
|
|
|
|
export async function fixtureWorker(ctx: ChatCatalogContext) {
|
|
const originalDeadline = chatCatalogOriginalPhaseDeadline(ctx);
|
|
const { execution, fixtures, workspacePath, nonce, api } = ctx.input;
|
|
const base = execution.profile.buildAgent({ environmentId: fixtures.environment.id, environmentFixtureId: execution.environment.id,
|
|
workspacePath, secretRefs: fixtures.secretRefs, executionId: nonce });
|
|
const payload = { ...base, name: "Morgan", role: "engineer", title: "Frontend engineer", reportsTo: fixtures.agent.id,
|
|
capabilities: "Builds accessible websites.", runtimeConfig: { ...(base.runtimeConfig as Record<string, unknown>), heartbeat: { enabled: false, maxConcurrentRuns: 1 } } };
|
|
const worker = await api.post<Entity>(`/api/companies/${fixtures.company.id}/agents`, execution.profile.credential === "CODEX_AUTH_JSON"
|
|
? codexSubscriptionAgentConfig(payload, process.env, fixtures.company.id) : payload);
|
|
const deadlineAt = originalDeadline ?? Date.now() + 45_000;
|
|
const observations: Record<string, unknown>[] = [];
|
|
let previous: string | undefined;
|
|
try {
|
|
await pollUntil({ label: "Morgan runtime readiness", deadlineAt,
|
|
load: async () => {
|
|
const row = await api.get<{ id: string; companyId: string; lifecycleState: string; status?: string; lifecycleError?: string | null }>(`/api/agents/${worker.id}`,
|
|
{ timeout: Math.max(1, Math.min(5_000, deadlineAt - Date.now())) });
|
|
const state = { id: row.id, companyId: row.companyId, lifecycleState: row.lifecycleState, status: row.status,
|
|
errorPresent: !!row.lifecycleError,
|
|
automaticRecovery: /\b(?:Paperclip will|It will) retry automatically\./.test(row.lifecycleError ?? ""),
|
|
verificationPaused: row.lifecycleError?.includes("Automatic verification is paused.") ?? false };
|
|
const current = JSON.stringify(state);
|
|
if (current !== previous) { observations.push({ ...state, observedAt: new Date().toISOString() }); previous = current; }
|
|
return row;
|
|
},
|
|
accept: row => Date.now() < deadlineAt && row.id === worker.id && row.companyId === fixtures.company.id
|
|
&& row.lifecycleState === "ready" && !row.lifecycleError,
|
|
reject: row => {
|
|
if (row.id !== worker.id || row.companyId !== fixtures.company.id) return "Morgan runtime identity changed";
|
|
if (["pending_approval", "paused", "rejected", "terminated", "terminating", "cleaning_up"].includes(row.lifecycleState)) return "Morgan runtime setup stopped";
|
|
// Public agent rows omit lifecycleOperation. The lifecycle owner exposes its
|
|
// automatic-recovery promise and manual-repair boundary in fixed diagnostics.
|
|
const recovering = originalDeadline !== undefined && row.lifecycleState === "verifying"
|
|
&& /\b(?:Paperclip will|It will) retry automatically\./.test(row.lifecycleError ?? "")
|
|
&& !row.lifecycleError?.includes("Automatic verification is paused.");
|
|
return row.lifecycleError && !recovering ? "Morgan runtime setup failed" : undefined;
|
|
} });
|
|
} finally {
|
|
await ctx.input.evidence(`chat-catalog-worker-readiness-${worker.id}.json`, {
|
|
policy: originalDeadline === undefined ? "authored-45s" : "original-native-case-clock",
|
|
deadlineAt, agentId: worker.id, companyId: fixtures.company.id, observations,
|
|
});
|
|
}
|
|
return worker;
|
|
}
|
|
|
|
export function retryDefinition(scenarioId: string, grade: ChatCatalogCase["grade"], initialOutcome: (observation: InternalObservation) => boolean, observeInitial = observeInternal): ChatCatalogCase {
|
|
const definition = makeDefinition(scenarioId, async ctx => ({ retryQuery: ctx.scenario.query }), grade);
|
|
return { ...definition, expectedRunCount: 2, expectedHumanMessageCount: 2, attemptTimeoutMs: 420_000,
|
|
async act(ctx, state) {
|
|
const first = await pollUntil({ label: "Initial creation before explicit user retry", deadlineAt: Date.now() + 150_000,
|
|
load: () => observeInitial(ctx, state),
|
|
accept: o => {
|
|
const rows = scenarioId === "projects.create-project" ? o.projects.filter(row => row.name === "Launch") : o.goals;
|
|
return rows.length === (scenarioId === "projects.create-project" ? 1 : 2) && initialOutcome(o) && ctx.issue()?.conversationState === "waiting"
|
|
&& o.runs.length === 1 && o.runs.every(row => row.status === "succeeded");
|
|
},
|
|
});
|
|
state.firstCreation = { ...first, state: structuredClone(state) };
|
|
state.firstIds = (scenarioId === "projects.create-project" ? first.projects.filter(row => row.name === "Launch") : first.goals).map(row => row.id);
|
|
await ctx.input.evidence("chat-catalog-before-explicit-retry.json", { firstIds: state.firstIds, observation: first });
|
|
const { sendChatMessage } = await import("../chat-flow.js");
|
|
await sendChatMessage(ctx.input.page, ctx.scenario.query);
|
|
},
|
|
};
|
|
}
|