mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-13 15:38:22 +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>
222 lines
9.1 KiB
TypeScript
222 lines
9.1 KiB
TypeScript
import { Profiler, useCallback, useEffect, useLayoutEffect, useMemo, useRef, useState, type ProfilerOnRenderCallback } from "react";
|
|
import { Badge } from "@/components/ui/badge";
|
|
import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card";
|
|
import { IssueChatThread } from "../components/IssueChatThread";
|
|
import {
|
|
issueChatLongThreadAgentMap,
|
|
issueChatLongThreadComments,
|
|
issueChatLongThreadEvents,
|
|
issueChatLongThreadFixtureContext,
|
|
issueChatLongThreadLinkedRuns,
|
|
issueChatLongThreadLiveRuns,
|
|
issueChatLongThreadMarkdownCommentIds,
|
|
issueChatLongThreadTranscriptsByRunId,
|
|
LONG_THREAD_COMMENT_COUNT,
|
|
LONG_THREAD_MARKDOWN_COMMENT_COUNT,
|
|
} from "../fixtures/issueChatLongThreadFixture";
|
|
|
|
const noop = async () => {};
|
|
|
|
type RenderMetrics = {
|
|
commitCount: number;
|
|
mountActualDuration: number | null;
|
|
latestActualDuration: number | null;
|
|
maxActualDuration: number;
|
|
totalActualDuration: number;
|
|
};
|
|
|
|
const initialMetrics: RenderMetrics = {
|
|
commitCount: 0,
|
|
mountActualDuration: null,
|
|
latestActualDuration: null,
|
|
maxActualDuration: 0,
|
|
totalActualDuration: 0,
|
|
};
|
|
|
|
function formatMs(value: number | null) {
|
|
if (value === null || !Number.isFinite(value)) return "pending";
|
|
return `${value.toFixed(1)} ms`;
|
|
}
|
|
|
|
function MetricTile({ label, value, testId }: { label: string; value: string; testId: string }) {
|
|
return (
|
|
<div className="rounded-md border border-border bg-background px-3 py-2">
|
|
<div className="text-(length:--text-micro) font-medium uppercase tracking-(--tracking-eyebrow) text-muted-foreground">
|
|
{label}
|
|
</div>
|
|
<div data-testid={testId} className="mt-1 font-mono text-sm text-foreground">
|
|
{value}
|
|
</div>
|
|
</div>
|
|
);
|
|
}
|
|
|
|
export function IssueChatLongThreadPerf() {
|
|
const [metrics, setMetrics] = useState<RenderMetrics>(initialMetrics);
|
|
const metricsRef = useRef<RenderMetrics>(initialMetrics);
|
|
const renderStartedAtRef = useRef(performance.now());
|
|
const publishTimerRef = useRef<number | null>(null);
|
|
const publishedRef = useRef(false);
|
|
const fixture = issueChatLongThreadFixtureContext;
|
|
const rowTarget = useMemo(
|
|
() => LONG_THREAD_COMMENT_COUNT + issueChatLongThreadEvents.length + issueChatLongThreadLinkedRuns.length,
|
|
[],
|
|
);
|
|
|
|
const schedulePublication = useCallback(() => {
|
|
if (publishedRef.current || publishTimerRef.current !== null) return;
|
|
publishTimerRef.current = window.setTimeout(() => {
|
|
publishTimerRef.current = null;
|
|
publishedRef.current = true;
|
|
setMetrics(metricsRef.current);
|
|
}, 0);
|
|
}, []);
|
|
|
|
useEffect(() => {
|
|
if (metricsRef.current.commitCount > 0) schedulePublication();
|
|
return () => {
|
|
if (publishTimerRef.current !== null) {
|
|
window.clearTimeout(publishTimerRef.current);
|
|
publishTimerRef.current = null;
|
|
}
|
|
};
|
|
}, [schedulePublication]);
|
|
|
|
useLayoutEffect(() => {
|
|
if (publishedRef.current || metricsRef.current.commitCount > 0) return;
|
|
const mountDuration = performance.now() - renderStartedAtRef.current;
|
|
const next = {
|
|
commitCount: 1,
|
|
mountActualDuration: mountDuration,
|
|
latestActualDuration: mountDuration,
|
|
maxActualDuration: mountDuration,
|
|
totalActualDuration: mountDuration,
|
|
};
|
|
metricsRef.current = next;
|
|
publishedRef.current = true;
|
|
setMetrics(next);
|
|
}, []);
|
|
|
|
const handleRender: ProfilerOnRenderCallback = (_id, phase, actualDuration) => {
|
|
const current = metricsRef.current;
|
|
metricsRef.current = {
|
|
commitCount: current.commitCount + 1,
|
|
mountActualDuration: phase === "mount" && current.mountActualDuration === null
|
|
? actualDuration
|
|
: current.mountActualDuration,
|
|
latestActualDuration: actualDuration,
|
|
maxActualDuration: Math.max(current.maxActualDuration, actualDuration),
|
|
totalActualDuration: current.totalActualDuration + actualDuration,
|
|
};
|
|
|
|
schedulePublication();
|
|
};
|
|
|
|
return (
|
|
<div data-testid="issue-chat-long-thread-perf" className="space-y-5">
|
|
<div className="flex flex-col gap-3 border-b border-border pb-5 lg:flex-row lg:items-end lg:justify-between">
|
|
<div className="min-w-0">
|
|
<div className="flex flex-wrap items-center gap-2">
|
|
<Badge variant="outline" className="font-mono text-(length:--text-micro)">
|
|
{fixture.issue.identifier}
|
|
</Badge>
|
|
<Badge variant="secondary">{fixture.issue.status.replace(/_/g, " ")}</Badge>
|
|
<Badge variant="outline">{fixture.issue.projectName}</Badge>
|
|
</div>
|
|
<h1 className="mt-3 text-2xl font-semibold tracking-tight">{fixture.issue.title}</h1>
|
|
<p className="mt-2 max-w-3xl text-sm leading-6 text-muted-foreground">
|
|
Deterministic local fixture for measuring the current direct-render issue chat path with
|
|
hundreds of merged thread rows, markdown-heavy assistant bodies, linked runs, documents,
|
|
sub-issues, and sidebar context.
|
|
</p>
|
|
</div>
|
|
<div className="grid min-w-(--sz-280px) grid-cols-2 gap-2">
|
|
<MetricTile label="Fixture rows" value={String(rowTarget)} testId="perf-fixture-row-target" />
|
|
<MetricTile label="Markdown rows" value={String(LONG_THREAD_MARKDOWN_COMMENT_COUNT)} testId="perf-fixture-markdown-rows" />
|
|
</div>
|
|
</div>
|
|
|
|
<div className="grid gap-4 xl:grid-cols-(--gtc-40)">
|
|
<main className="min-w-0 space-y-4">
|
|
<Card className="border-border/70">
|
|
<CardHeader className="pb-2">
|
|
<CardTitle className="text-base">Issue documents</CardTitle>
|
|
</CardHeader>
|
|
<CardContent className="grid gap-2 sm:grid-cols-2">
|
|
{fixture.documents.map((document) => (
|
|
<div key={document} className="rounded-md border border-border bg-muted/30 px-3 py-2 text-sm">
|
|
{document}
|
|
</div>
|
|
))}
|
|
</CardContent>
|
|
</Card>
|
|
|
|
<Card className="border-border/70">
|
|
<CardHeader className="pb-2">
|
|
<CardTitle className="text-base">Sub-issues</CardTitle>
|
|
</CardHeader>
|
|
<CardContent className="space-y-2">
|
|
{fixture.subIssues.map((subIssue, index) => (
|
|
<div key={subIssue} className="flex items-center gap-3 rounded-md border border-border bg-background px-3 py-2 text-sm">
|
|
<span className="font-mono text-xs text-muted-foreground">#{index + 1}</span>
|
|
<span>{subIssue}</span>
|
|
</div>
|
|
))}
|
|
</CardContent>
|
|
</Card>
|
|
|
|
<Profiler id="issue-chat-long-thread" onRender={handleRender}>
|
|
<IssueChatThread
|
|
comments={issueChatLongThreadComments}
|
|
linkedRuns={issueChatLongThreadLinkedRuns}
|
|
timelineEvents={issueChatLongThreadEvents}
|
|
liveRuns={issueChatLongThreadLiveRuns}
|
|
issueStatus="in_progress"
|
|
agentMap={issueChatLongThreadAgentMap}
|
|
currentUserId="user-board"
|
|
onAdd={noop}
|
|
showComposer={false}
|
|
showJumpToLatest={false}
|
|
enableLiveTranscriptPolling={false}
|
|
transcriptsByRunId={issueChatLongThreadTranscriptsByRunId}
|
|
hasOutputForRun={(runId) => issueChatLongThreadTranscriptsByRunId.has(runId)}
|
|
/>
|
|
</Profiler>
|
|
</main>
|
|
|
|
<aside className="space-y-4 xl:sticky xl:top-4 xl:self-start">
|
|
<Card className="border-border/70">
|
|
<CardHeader className="pb-2">
|
|
<CardTitle className="text-base">Baseline metrics</CardTitle>
|
|
</CardHeader>
|
|
<CardContent className="grid gap-2">
|
|
<MetricTile label="Profiler commits" value={String(metrics.commitCount)} testId="perf-commit-count" />
|
|
<MetricTile label="Mount duration" value={formatMs(metrics.mountActualDuration)} testId="perf-mount-duration" />
|
|
<MetricTile label="Latest duration" value={formatMs(metrics.latestActualDuration)} testId="perf-latest-duration" />
|
|
<MetricTile label="Max duration" value={formatMs(metrics.maxActualDuration)} testId="perf-max-duration" />
|
|
<MetricTile label="Total duration" value={formatMs(metrics.totalActualDuration)} testId="perf-total-duration" />
|
|
</CardContent>
|
|
</Card>
|
|
|
|
<Card className="border-border/70">
|
|
<CardHeader className="pb-2">
|
|
<CardTitle className="text-base">Fixture shape</CardTitle>
|
|
</CardHeader>
|
|
<CardContent className="space-y-2">
|
|
{fixture.sidebarStats.map(([label, value]) => (
|
|
<div key={label} className="flex items-center justify-between gap-3 text-sm">
|
|
<span className="text-muted-foreground">{label}</span>
|
|
<span className="font-mono">{value}</span>
|
|
</div>
|
|
))}
|
|
<div className="hidden" data-testid="perf-markdown-comment-id-sample">
|
|
{[...issueChatLongThreadMarkdownCommentIds].slice(0, 3).join(",")}
|
|
</div>
|
|
</CardContent>
|
|
</Card>
|
|
</aside>
|
|
</div>
|
|
</div>
|
|
);
|
|
}
|