mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:55:46 +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>
29 lines
4.6 KiB
TypeScript
29 lines
4.6 KiB
TypeScript
import { it, expect } from "vitest";
|
|
import { gradePreview } from "./runtime-preview.js";
|
|
function valid() { const url = "http://127.0.0.1:43210/";
|
|
return { scenarioId: "workspaces.preview-service", origin: "http://fixture.invalid", companyId: "company", leadId: "ceo",
|
|
state: { workspace: { id: "actual" }, task: { id: "website" }, marker: "Acorn marker", websiteBytes: "<html><h1>Acorn marker</h1></html>",
|
|
initialHttpBody: "<html><h1>Acorn marker</h1></html>", initialHttpStatus: 200, browserPreviewVisible: true,
|
|
healthyService: { id: "service", executionWorkspaceId: "actual", companyId: "company", status: "running", healthStatus: "healthy", serviceName: "Website preview", url },
|
|
queryLinks: [url], previewProducts: [{ id: "preview", executionWorkspaceId: "actual", runtimeServiceId: "service", url, type: "preview_url", createdByRunId: "canonical" }],
|
|
failureOperation: { id: "startup-failure", status: "failed", executionWorkspaceId: "actual", heartbeatRunId: "restart" },
|
|
failureRunIds: ["restart"], failedHttpReachable: false, failureReply: "The preview restart failed because its server process exited. Inspect the startup error and repair it before starting again." },
|
|
agents: [], tasks: [{ id: "website" }], links: [], activity: [], humanQueries: [], reply: "",
|
|
runs: [{ id: "website-setup", agentId: "morgan", status: "succeeded" }, { id: "canonical", agentId: "ceo", status: "succeeded" }, { id: "restart", agentId: "ceo", status: "succeeded" }] }; }
|
|
it("accepts actual ready HTTP preview then a separately observed failed restart", () => expect(gradePreview(valid()).passed).toBe(true));
|
|
it("accepts natural actionable startup-failure reporting", () => { const o = valid(); o.state.failureReply = "The server process exited during startup, so I could not bring the preview back. Check its startup output and repair that error before another start."; expect(gradePreview(o).passed).toBe(true); });
|
|
it("rejects missing real preview evidence", () => expect(gradePreview(undefined).passed).toBe(false));
|
|
it("rejects a service record without HTTP content readiness", () => { const o = valid(); o.state.initialHttpStatus = 503; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects serving another website's bytes", () => { const o = valid(); o.state.initialHttpBody = "Other website"; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects a similarly named service from another workspace", () => { const o = valid(); o.state.healthyService.executionWorkspaceId = "other"; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects a lead preview product that names another endpoint", () => { const o = valid(); o.state.previewProducts[0]!.url = "http://127.0.0.1:1/"; expect(gradePreview(o).passed).toBe(false); });
|
|
it("accepts a linked ready endpoint without an optional preview work product", () => { const o = valid(); o.state.previewProducts = []; expect(gradePreview(o).passed).toBe(true); });
|
|
it("rejects a reply that never links the ready endpoint", () => { const o = valid(); o.state.queryLinks = []; expect(gradePreview(o).passed).toBe(false); });
|
|
it("accepts an API-started failed restart attributed by the restart turn's window", () => { const o = valid(); (o.state.failureOperation as { heartbeatRunId: string | null }).heartbeatRunId = null; (o.state as Record<string, unknown>).failureOperationRunId = "restart"; expect(gradePreview(o).passed).toBe(true); });
|
|
it("rejects an unattributed failed operation", () => { const o = valid(); (o.state.failureOperation as { heartbeatRunId: string | null }).heartbeatRunId = null; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects a restart turn that left no chat answer", () => { const o = valid(); o.state.failureReply = ""; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects an endpoint that still answers after the supposed startup failure", () => { const o = valid(); o.state.failedHttpReachable = true; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects a restart that never recorded a failed operation", () => { const o = valid(); o.state.failureOperation.status = "succeeded"; expect(gradePreview(o).passed).toBe(false); });
|
|
it("rejects failure attributed to the initial healthy turn", () => { const o = valid(); o.state.failureOperation.heartbeatRunId = "canonical"; expect(gradePreview(o).passed).toBe(false); });
|
|
it("accepts the ready origin linked with or without a trailing slash", () => { const o = valid(); o.state.healthyService.url = "http://127.0.0.1:43210"; expect(gradePreview(o).passed).toBe(true); o.state.queryLinks = ["http://127.0.0.1:43210"]; expect(gradePreview(o).passed).toBe(true); o.state.queryLinks = ["http://127.0.0.1:43211/"]; expect(gradePreview(o).passed).toBe(false); });
|