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>
50 lines
4.0 KiB
TypeScript
50 lines
4.0 KiB
TypeScript
import { expect, it } from "vitest";
|
|
import { runnerMatrix, runnerSuites } from "./catalog.js";
|
|
import { chatCatalogCases } from "./chat-catalog-registry.js";
|
|
import { chatFeatureProfile } from "./chat-feature-cases.js";
|
|
import { CHAT_NATIVE_TIMEOUT_POLICY, chatNativeTimeoutEvidence } from "./chat-native-timeout-policy.js";
|
|
import type { RunnerProfileFixture } from "./types.js";
|
|
|
|
it("uses the production native cap only in the catalog while preserving every finite scenario budget and run bound", () => {
|
|
const cells = runnerMatrix.filter(row => row.suite.id === "chat-features" && row.profile.id === "runner-opencode");
|
|
expect(cells).toHaveLength(244);
|
|
for (const cell of cells) {
|
|
expect(cell.task.turnTimeoutMs).toBe(["create-backlog", "delegate-announcement"].includes(cell.task.id) ? 120_000 : 0);
|
|
const declaration = chatCatalogCases.find(row => row.scenarioId === cell.task.id);
|
|
if (declaration) {
|
|
expect(cell.task.attemptTimeoutMs).toEqual({ local: declaration.attemptTimeoutMs, daytona: declaration.attemptTimeoutMs });
|
|
expect(cell.task.expectedRunCount).toBe(declaration.expectedRunCount);
|
|
expect(cell.task.minimumExpectedRunCount).toBe(declaration.minimumRunCount);
|
|
expect(declaration.turnTimeoutMs).toBeGreaterThan(0);
|
|
}
|
|
expect(cell.task.automaticRetryPolicy).toBe("single_attempt");
|
|
}
|
|
const byId = (id: string) => cells.find(row => row.task.id === id)!;
|
|
expect(byId("projects.create-project").task).toMatchObject({ expectedRunCount: 2, attemptTimeoutMs: { local: 420_000 } });
|
|
expect(byId("projects.project-work").task).toMatchObject({ expectedRunCount: 3, minimumExpectedRunCount: 1, attemptTimeoutMs: { local: 300_000 } });
|
|
expect(byId("tasks.organize-open-work").task.attemptTimeoutMs.local).toBe(900_000);
|
|
expect(runnerSuites.find(row => row.id === "chat-features")?.definitionMetadata).toMatchObject({ nativeTimeoutPolicy: CHAT_NATIVE_TIMEOUT_POLICY });
|
|
expect(runnerMatrix.filter(row => row.suite.id !== "chat-features").some(row => (row.task.turnTimeoutMs ?? 0) > 0)).toBe(true);
|
|
});
|
|
|
|
it("saves the actual catalog profile with no native cap without removing funding, daily admission or unrelated adapter settings", () => {
|
|
const original = { adapterConfig: { provider: "opencode", model: "openrouter/deepseek/deepseek-v4.1-flash-1017", timeoutSec: 120, retained: true }, runtimeConfig: { retained: true } };
|
|
const profile = { id: "runner-opencode", provider: "opencode", buildAgent: () => structuredClone(original) } as unknown as RunnerProfileFixture;
|
|
const input = {} as Parameters<RunnerProfileFixture["buildAgent"]>[0];
|
|
const saved = chatFeatureProfile(profile).buildAgent(input);
|
|
expect(saved.adapterConfig).toEqual({ ...original.adapterConfig, timeoutSec: 0 });
|
|
expect(saved.budgetMonthlyCents).toBe(500);
|
|
expect(saved.runtimeConfig).toEqual({ retained: true, heartbeat: { enabled: false, maxConcurrentRuns: 1, maxDailyRuns: 3, maxDailyCostCents: 500 } });
|
|
expect(profile.buildAgent(input)).toEqual(original);
|
|
});
|
|
|
|
it("reports zero as no per-turn cap alongside real finite lifetime and rejects mismatched saved or selected settings", () => {
|
|
const input = { selectedTurnTimeoutMs: 0, savedAgentTimeoutSec: 0, authoredLegacyTurnTimeoutMs: 120_000, attemptTimeoutMs: 300_000, observationBudgetMs: 270_000 };
|
|
expect(chatNativeTimeoutEvidence(input)).toMatchObject({ effectiveNativeTurnTimeoutMs: 0,
|
|
scenarioCellBudgetMs: 300_000, scenarioObservationBudgetMs: 270_000, playwrightBudgetMs: 390_000,
|
|
launcherWatchdogMs: 690_000, activeRunCancellationWaitMs: 45_000, ownedProcessShutdownGraceMs: 45_000, ownedProcessKillGraceMs: 5_000 });
|
|
for (const change of [{ selectedTurnTimeoutMs: 120_000 }, { savedAgentTimeoutSec: 120 }, { savedAgentTimeoutSec: undefined },
|
|
{ observationBudgetMs: Infinity }, { observationBudgetMs: 0 }, { observationBudgetMs: 300_000 }, { attemptTimeoutMs: 0 }, { attemptTimeoutMs: Infinity }, { authoredLegacyTurnTimeoutMs: 0 }])
|
|
expect(() => chatNativeTimeoutEvidence({ ...input, ...change })).toThrow();
|
|
});
|