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>
37 lines
4.9 KiB
TypeScript
37 lines
4.9 KiB
TypeScript
import {createHash} from "node:crypto";
|
|
import {describe,it,expect} from "vitest";
|
|
import {gradeSlackThread} from "./external-slack-thread.js";
|
|
function valid(){
|
|
const body="<!doctype html><html><body><h1>Acorn Notes</h1><p>A calm notebook.</p></body></html>",sha256=createHash("sha256").update(body).digest("hex");
|
|
const receipt={query:"Ask Morgan to build the launch page and let me know here when it is ready.",endpointId:"endpoint",conversationId:"source-conversation",issueId:"source",humanCommentId:"human-comment",linkedPaperclipUserId:"person",providerCalls:1,provider:{workspaceId:"T123",channelId:"C123",threadId:"1234567890.000001",canonicalMessageId:"1234567890.000002",senderUserId:"U123"}};
|
|
const other={...receipt,query:"Other status query",conversationId:"other-conversation",issueId:"other",runId:"other-run",provider:{...receipt.provider,threadId:"1234567889.000001"}};
|
|
const run=(id:string,agentId:string,issueId:string)=>({id,companyId:"company",agentId,runtimeMode:"native",status:"succeeded",contextSnapshot:{issueId}});
|
|
const message={id:"1234567889.000002",user:"UBOT",text:"No projects are blocked.",files:[] as string[]};
|
|
return {scenarioId:"chat-channels.reply-in-thread",companyId:"company",leadId:"ceo",origin:"http://127.0.0.1:3399",reply:"Morgan finished. ACORN-3 is ready.",state:{worker:{id:"morgan"},project:{id:"project"},originalQuery:receipt.query,botUserId:"UBOT"},phaseReplies:[{runId:"completion",body:"Morgan finished. ACORN-3 is ready."}],tasks:[{id:"build",companyId:"company",identifier:"ACORN-3",assigneeAgentId:"morgan",projectId:"project",status:"done"}],runs:[run("other-run","ceo","other"),run("source-run","ceo","source"),run("build-run","morgan","build"),run("completion","ceo","source")],connections:[],profiles:[],secrets:[],endpoints:[],interactions:[],activity:[{action:"issue.created",entityId:"build",actorType:"agent",agentId:"ceo"}],links:[],humanQueries:[receipt.query],thread:{source:receipt,other,before:[message],after:[structuredClone(message)],messages:[{id:"1234567890.000003",user:"UBOT",text:"Morgan finished. ACORN-3 is ready.",files:[] as string[]}],duplicate:{canonicalDeliveryCaptured:true,duplicateReplayed:true},activity:[{kind:"delivery",status:"processed",summary:"message processed · 1 duplicate ignored"},{kind:"publication",status:"published",summary:"Response to external conversation"}],attachments:[{id:"attachment",issueId:"build",originatingRunId:"build-run",sha256}],products:[{issueId:"build",createdByRunId:"build-run",type:"artifact",status:"active",metadata:{attachmentId:"attachment"}}],files:[{id:"attachment",hash:sha256,body,rendered:{sha256,usableSignup:true,nodes:[{tag:"H1",text:"Acorn Notes",role:null,href:null,inNavigation:false,color:"rgb(0, 0, 0)",background:"rgb(255, 255, 255)"},{tag:"P",text:"A calm notebook for the whole research team.",role:null,href:null,inNavigation:false,color:"rgb(0, 0, 0)",background:"rgb(255, 255, 255)"}]}}]}};
|
|
}
|
|
describe("real Slack native handoff, result and duplicate isolation",()=>{
|
|
it("accepts independently attributed build bytes and one actual original-thread completion",()=>expect(gradeSlackThread(valid()).passed).toBe(true));
|
|
it("rejects another task/thread/person, extra runs, stale or fabricated files and duplicate completions",()=>{
|
|
for(const mutate of [
|
|
(o:ReturnType<typeof valid>)=>{o.thread.other.provider.threadId=o.thread.source.provider.threadId;},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.other.linkedPaperclipUserId="another-person";},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.after.push({id:"leak",user:"UBOT",text:"ACORN-3 is ready",files:[]});},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.before=[];o.thread.after=[];},
|
|
(o:ReturnType<typeof valid>)=>{o.tasks.push({...o.tasks[0]!,id:"duplicate-task"});},
|
|
(o:ReturnType<typeof valid>)=>{o.runs.push({...o.runs[0]!,id:"unrelated-run",contextSnapshot:{issueId:"unrelated"}});},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.files[0]!.body="<html><h1>Previous Acorn Notes page</h1></html>";},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.attachments[0]!.originatingRunId="older-run";},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.messages.push({...o.thread.messages[0]!,id:"duplicate-response"});},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.duplicate.duplicateReplayed=false;},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.files[0]!.rendered.nodes=[];},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.files[0]!.rendered.usableSignup=false;},
|
|
(o:ReturnType<typeof valid>)=>{o.thread.messages[0]!.text="I'll let you know here when ACORN-3 is ready.";},
|
|
]){const o=valid();mutate(o);expect(gradeSlackThread(o).passed).toBe(false);}
|
|
});
|
|
it("requires actual evidence rather than a truthful prose-only status",()=>{
|
|
expect(gradeSlackThread(undefined).passed).toBe(false);
|
|
const o=valid();expect(gradeSlackThread({...o,thread:{...o.thread,products:undefined}}).passed).toBe(false);
|
|
expect(gradeSlackThread({...o,thread:{...o.thread,source:undefined}}).passed).toBe(false);
|
|
});
|
|
});
|