Files
PaperClipAI/tests/runner-e2e/chat-runtime-profile.test.ts
T
f4337bb5fb test(evals): land the chat catalog eval harness on master (#19614)
## 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>
2026-11-10 08:02:11 -06:00

78 lines
6.3 KiB
TypeScript

import { expect, it } from "vitest";
import { CHAT_OPENCODE_MODEL, reviewedChatProfile, reviewedChatExecutionIds } from "./chat-runtime-profile.js";
import { runnerMatrix, runnerProfiles } from "./catalog.js";
import { CHAT_NATIVE_TIMEOUT_POLICY } from "./chat-native-timeout-policy.js";
import { chatFeatureProfile } from "./chat-feature-cases.js";
import type { RunnerProfileFixture } from "./types.js";
import { setupLiveFixtures } from "./live-fixtures.js";
import type { RunnerApi } from "./api.js";
import { missingTeamAccountEnvironment } from "./chat-catalog-domains/external-team-configure.js";
const profile = { id: "runner-opencode", provider: "opencode", model: CHAT_OPENCODE_MODEL, adapterType: "paperclip_runner", credential: "OPENROUTER_API_KEY" };
it("pins the new controller identity and rejects model/provider/credential substitution", () => {
expect(reviewedChatProfile(profile)).toBe(true);
for (const patch of [{ id: "runner-unknown" }, { provider: "codex" }, { model: "openrouter/other/model" }, { credential: "CODEX_AUTH_JSON" }, { adapterType: "opencode_local" }])
expect(reviewedChatProfile({ ...profile, ...patch })).toBe(false);
expect(reviewedChatExecutionIds("secrets.vault-reference")).toEqual(["chat-features.runner-codex-subscription.local.secrets.vault-reference", "chat-features.runner-opencode.local.secrets.vault-reference"]);
});
it("changes the complete chat matrix without relabeling the existing global qualification model", () => {
const cells = runnerMatrix.filter(cell => cell.suite.id === "chat-features" && cell.profile.id === "runner-opencode");
expect(cells.length).toBe(244);
expect(cells.every(cell => cell.profile.model === CHAT_OPENCODE_MODEL && reviewedChatProfile(cell.profile))).toBe(true);
expect(runnerProfiles.find(row => row.id === "runner-opencode")!.model).not.toBe(CHAT_OPENCODE_MODEL);
const cell = cells[0]!;
const payload = cell.profile.buildAgent({ environmentId: "environment", environmentFixtureId: "local", workspacePath: "/owned", secretRefs: { OPENROUTER_API_KEY: { type: "secret_ref", secretId: "22222222-2222-4222-8222-222222222222", version: "latest" } }, executionId: "owned" });
expect(payload.adapterConfig).toMatchObject({ provider: "opencode", model: CHAT_OPENCODE_MODEL });
expect(payload.adapterConfig).not.toHaveProperty("modelReasoningEffort");
expect(payload.adapterConfig).not.toHaveProperty("codexPermissionMode");
expect(payload.adapterConfig).toMatchObject({ opencodePermissionMode: "allow", env: {
OPENROUTER_API_KEY: { type: "secret_ref", secretId: "22222222-2222-4222-8222-222222222222", version: "latest" },
} });
const env = (payload.adapterConfig as { env: Record<string, string> }).env;
expect(JSON.parse(env.OPENCODE_CONFIG_CONTENT!)).toEqual({ provider: { openrouter: { models: {
"deepseek/deepseek-v4.1-flash-1017": { options: { provider: { sort: "throughput" } } },
} } } });
expect(Object.keys(env).sort()).toEqual(["OPENCODE_CONFIG_CONTENT", "OPENROUTER_API_KEY"]);
});
it("withholds only the selected account from the missing OpenRouter member", () => {
expect(missingTeamAccountEnvironment(false, "/owned/empty")).toEqual({ OPENROUTER_API_KEY: "" });
expect(missingTeamAccountEnvironment(true, "/owned/empty")).toEqual({ CODEX_HOME: "/owned/empty", OPENAI_API_KEY: "", CODEX_API_KEY: "" });
});
it("scopes routing preference to the reviewed chat profile while preserving its configured environment", () => {
const input = { environmentId: "environment", environmentFixtureId: "local" as const, workspacePath: "/owned", secretRefs: {}, executionId: "owned" };
const config = { provider: "opencode", model: CHAT_OPENCODE_MODEL, opencodePermissionMode: "ask", env: { CUSTOM_SETTING: "kept" } };
const base = { ...runnerProfiles.find(row => row.id === "runner-opencode")!, ...profile,
buildAgent: () => ({ adapterConfig: structuredClone(config), runtimeConfig: {} }) } as RunnerProfileFixture;
const selected = chatFeatureProfile(base).buildAgent(input);
expect(selected.adapterConfig).toMatchObject(config);
expect((selected.adapterConfig as {env: Record<string,string>}).env.OPENCODE_CONFIG_CONTENT).toBeDefined();
for (const patch of [{id:"runner-opencode-deepseek-1017"},{provider:"codex"},{model:"openrouter/other/model"},{adapterType:"opencode_local"},{credential:"OPENAI_API_KEY"}]) {
const excluded = chatFeatureProfile({...base,...patch} as RunnerProfileFixture).buildAgent(input);
expect(excluded.adapterConfig).toEqual({...config,timeoutSec:patch.id ? 120 : CHAT_NATIVE_TIMEOUT_POLICY.savedAgentTimeoutSec,...(patch.provider === "codex" ? {modelReasoningEffort:"low"} : {})});
}
const global = runnerProfiles.find(row => row.id === "runner-opencode")!;
const payload = global.buildAgent({...input,secretRefs:{OPENROUTER_API_KEY:{type:"secret_ref",secretId:"22222222-2222-4222-8222-222222222222",version:"latest"}}});
expect(payload.adapterConfig).not.toHaveProperty("env.OPENCODE_CONFIG_CONTENT");
});
it("posts the reviewed routing configuration through the ordinary agent fixture boundary", async () => {
const execution = runnerMatrix.find(cell => cell.suite.id === "chat-features" && cell.profile.id === "runner-opencode")!;
let saved: Record<string, unknown> | undefined;
const api = {
async get() { return [{id:"local",driver:"local"}]; },
async postSensitive() { return {id:"encrypted-account"}; },
async post(url: string, body: Record<string, unknown>) {
if (url === "/api/companies") return {id:"company",name:"Fixture"};
if (url === "/api/companies/company/agents") { saved=body; return {id:"ceo",...body}; }
throw new Error("Unexpected fixture route");
},
} as unknown as RunnerApi;
const fixtures = await setupLiveFixtures({api,execution,executionNonce:"routing",workspacePath:"/owned",credentials:{OPENROUTER_API_KEY:"synthetic-account-input"}});
try {
const config=saved!.adapterConfig as {provider:string;model:string;env:Record<string,unknown>};
expect(config).toMatchObject({provider:"opencode",model:CHAT_OPENCODE_MODEL});
expect(config.env.OPENROUTER_API_KEY).toEqual({type:"secret_ref",secretId:"encrypted-account",version:"latest"});
expect(JSON.parse(config.env.OPENCODE_CONFIG_CONTENT as string)).toEqual({provider:{openrouter:{models:{"deepseek/deepseek-v4.1-flash-1017":{options:{provider:{sort:"throughput"}}}}}}});
} finally { await fixtures.teardown(); }
});