mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-14 08:53:19 +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>
55 lines
4.3 KiB
TypeScript
55 lines
4.3 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
import { it, expect } from "vitest";
|
|
import { gradeBuiltInConfiguration } from "./runtime-built-in.js";
|
|
const ORIGINAL = "You are Summarizer, a built-in reporting agent.\n\n## Core responsibilities\n\n- Read the scope.\n- Open with 1-3 actions.\n- Follow with a paragraph or two of status prose.\n- Keep summaries short.";
|
|
const TUNED = ORIGINAL.replace("a paragraph or two of status prose", "one paragraph of status prose") + "\n\n## Length budget\n\n- Target 100 words; hard ceiling 150.";
|
|
const hash = (content: string) => createHash("sha256").update(content).digest("hex");
|
|
function valid() {
|
|
const builtIn = { definition: { key: "summarizer" }, agentId: "summarizer" };
|
|
const task = { id: "history", title: "Summary history", companyId: "company", assigneeAgentId: "summarizer", status: "backlog" };
|
|
// Reads report a content token stamped with the reader, and history is empty (design change 14420).
|
|
const token = { id: "token", companyId: "company", agentId: "summarizer", actorAgentId: null, sourceRunId: null, source: "api" };
|
|
return { scenarioId: "agents.configure-required-agent", origin: "http://fixture.invalid", companyId: "company", leadId: "ceo",
|
|
state: { builtInBefore: builtIn, builtInAfter: { ...builtIn }, originalInstruction: { path: "AGENTS.md", content: ORIGINAL, revision: token }, agentCountBefore: 2, historicalTask: task },
|
|
instruction: { path: "AGENTS.md", content: TUNED, revision: { ...token, id: "token-2" } },
|
|
instructionHistory: { revisions: [] as unknown[] },
|
|
agents: [{ id: "ceo", name: "CEO", companyId: "company" }, { id: "summarizer", name: "Summarizer", companyId: "company" }], tasks: [task],
|
|
links: ["/RUN/agents/summarizer"], reply: "Updated the [Summarizer](/RUN/agents/summarizer) instructions with a hard length budget.",
|
|
activity: [{ id: "write", companyId: "company", action: "agent.files_updated", entityType: "agent", entityId: "summarizer", actorType: "agent", actorId: "ceo",
|
|
agentId: "ceo", runId: "run", details: { path: "AGENTS.md", source: "api", created: false, contentHash: hash(TUNED) } }],
|
|
runs: [{ id: "run", companyId: "company", agentId: "ceo" }], humanQueries: [] };
|
|
}
|
|
const grade = (o: unknown) => gradeBuiltInConfiguration(o).passed;
|
|
it("accepts the run's saved, attributed tuning of the existing summarizer", () => expect(grade(valid())).toBe(true));
|
|
it("accepts a reworded reply that names the summarizer without a link", () => {
|
|
const o = valid(); o.links = []; o.reply = "Done: Summarizer now has a tighter word ceiling, effective on its next run."; expect(grade(o)).toBe(true);
|
|
});
|
|
it("accepts a saved write through the dedicated instruction tool", () => {
|
|
const o = valid(); o.activity[0].details.source = "tool"; expect(grade(o)).toBe(true);
|
|
});
|
|
it("rejects missing built-in evidence", () => expect(grade(undefined)).toBe(false));
|
|
it("rejects replacing the protected identity with an ordinary hire", () => {
|
|
const o = valid(); o.state.builtInAfter.agentId = "replacement"; expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects an extra ordinary hire", () => {
|
|
const o = valid(); o.agents.push({ id: "hire", name: "Short Summarizer", companyId: "company" }); expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects a reply that claims a change the product never saved", () => {
|
|
const o = valid(); o.instruction.content = ORIGINAL; expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects instructions changed by someone other than the chat run", () => {
|
|
const o = valid(); Object.assign(o.activity[0], { actorType: "user", actorId: "local-board", agentId: null, runId: null }); expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects an audit row for different bytes than the product now serves", () => {
|
|
const o = valid(); o.activity[0].details.contentHash = hash(`${TUNED}\nlater edit`); expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects wholesale replacement of the bundled summarizer instructions", () => {
|
|
const o = valid(); o.instruction.content = "Write two-sentence updates."; o.activity[0].details.contentHash = hash(o.instruction.content); expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects erasing the old attributed task", () => {
|
|
const o = valid(); o.tasks = []; expect(grade(o)).toBe(false);
|
|
});
|
|
it("rejects a reply that does not identify the configured agent", () => {
|
|
const o = valid(); o.links = []; o.reply = "Done."; expect(grade(o)).toBe(false);
|
|
});
|