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>
29 lines
3.6 KiB
TypeScript
29 lines
3.6 KiB
TypeScript
import { describe,expect,it } from "vitest";
|
|
import { runScopedCompanion } from "./external-assistant-model.js";
|
|
const query="Create a website task for Morgan in Acorn.",credential="fixture-private-provider-key";
|
|
const tool={name:"paperclip_create_task",description:"Create a task",inputSchema:{type:"object"}};
|
|
const response=(id:string,output:unknown[],extra:Record<string,unknown>={})=>new Response(JSON.stringify({id,model:"gpt-5.4-mini",usage:{input_tokens:40,output_tokens:20},output,...extra}));
|
|
describe("finite real-provider companion driver controls",()=>{
|
|
it("sends the exact canonical input, dispatches only model-selected admitted calls and preserves provider/model/usage evidence",async()=>{
|
|
const requests:Record<string,unknown>[]=[],calls:string[]=[];let n=0;
|
|
const result=await runScopedCompanion({query,credential,tools:[tool],signal:new AbortController().signal,observe:async()=>{},call:async(name,args)=>{calls.push(name);return {task:{id:"task",title:args.title},url:"http://fixture.invalid/ACORN/issues/TASK-1"};},fetcher:async(_url,init)=>{requests.push(JSON.parse(String(init?.body)));return n++===0?response("resp_one",[{type:"function_call",name:tool.name,call_id:"call",arguments:JSON.stringify({title:"Website",requestId:"request"})}]):response("resp_two",[{type:"message",content:[{type:"output_text",text:"Created http://fixture.invalid/ACORN/issues/TASK-1"}]}]);}});
|
|
expect(requests[0]!.input).toEqual([{role:"user",content:query}]);expect(JSON.stringify(requests)).not.toContain(credential);expect(result.messages.filter(row=>row.role==="user")).toEqual([{role:"user",content:query}]);expect(calls).toEqual([tool.name]);expect(result.providerResponseIds).toEqual(["resp_one","resp_two"]);expect(result.usage).toEqual({inputTokens:80,outputTokens:40});expect(result.links).toEqual(["http://fixture.invalid/ACORN/issues/TASK-1"]);expect(result.reply).not.toContain("requestId");
|
|
});
|
|
it("rejects missing response identity/model/usage, excessive output and unavailable tools before any such tool executes",async()=>{
|
|
for(const body of [
|
|
{id:"",model:"gpt-5.4-mini",usage:{input_tokens:1,output_tokens:1},output:[]},
|
|
{id:"resp_id",model:"another-model",usage:{input_tokens:1,output_tokens:1},output:[]},
|
|
{id:"resp_id",model:"gpt-5.4-mini",output:[]},
|
|
{id:"resp_id",model:"gpt-5.4-mini",usage:{input_tokens:1,output_tokens:2049},output:[]},
|
|
{id:"resp_id",model:"gpt-5.4-mini",usage:{input_tokens:1,output_tokens:1},output:[{type:"function_call",name:"board_rest",call_id:"bad",arguments:"{}"}]},
|
|
]){let called=false;await expect(runScopedCompanion({query,credential,tools:[tool],signal:new AbortController().signal,observe:async()=>{},call:async()=>{called=true;},fetcher:async()=>new Response(JSON.stringify(body))})).rejects.toThrow();expect(called).toBe(false);}
|
|
});
|
|
it("bounds four actual tool invocations and observes even failed or aborted workflows",async()=>{
|
|
let calls=0,observed=0;
|
|
await expect(runScopedCompanion({query,credential,tools:[tool],signal:new AbortController().signal,observe:async()=>{observed++;},call:async()=>{calls++;return {};},fetcher:async()=>response("resp_loop",Array.from({length:5},(_,i)=>({type:"function_call",name:tool.name,call_id:`call${i}`,arguments:"{}"})))})).rejects.toThrow(/tool-call bound/);
|
|
expect(calls).toBe(4);expect(observed).toBeGreaterThan(0);
|
|
const controller=new AbortController();controller.abort();let fetched=false;
|
|
await expect(runScopedCompanion({query,credential,tools:[tool],signal:controller.signal,observe:async()=>{observed++;},call:async()=>({}),fetcher:async()=>{fetched=true;return response("resp_unexpected",[]);}})).rejects.toThrow();expect(fetched).toBe(false);
|
|
});
|
|
});
|