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>
58 lines
4.3 KiB
TypeScript
58 lines
4.3 KiB
TypeScript
import type { ChatCatalogContext } from "../chat-catalog-contract.js";
|
|
import type { IssueDocument, IssueAttachment } from "../../../packages/shared/src/types/issue.js";
|
|
import type { Entity } from "./internal-support.js";
|
|
import { uploadFactualQueryAttachment } from "../chat-query-attachments.js";
|
|
|
|
/** Visible source metadata plus an actual human query attachment: conversation
|
|
* descriptions alone are intentionally omitted from native wake context. */
|
|
export async function selectDocumentSource(ctx: ChatCatalogContext, input: {
|
|
task: Entity;
|
|
document?: { id: string; key: string; latestRevisionId: string | null };
|
|
annotationId?: string;
|
|
attachment?: IssueAttachment;
|
|
workspaceFilename?: string;
|
|
}) {
|
|
const { api, fixtures } = ctx.input;
|
|
const target = await api.get<Entity>(`/api/issues/${input.task.id}`);
|
|
if (target.id !== input.task.id || target.companyId !== fixtures.company.id || target.projectId !== input.task.projectId)
|
|
throw new Error("Selected document source does not belong to the expected task/company/project");
|
|
const taskHref = `/${fixtures.company.issuePrefix}/issues/${target.identifier ?? target.id}`;
|
|
const lines = [`Selected source: [${target.title}](${taskHref}).`];
|
|
if (input.document) {
|
|
const doc = await api.get<IssueDocument>(`/api/issues/${target.id}/documents/${encodeURIComponent(input.document.key)}`);
|
|
if (doc.id !== input.document.id || doc.issueId !== target.id || doc.latestRevisionId !== input.document.latestRevisionId)
|
|
throw new Error("Selected source document or revision changed before the canonical turn");
|
|
lines.push(`Selected document: [${doc.title ?? doc.key}](${taskHref}#document-${encodeURIComponent(doc.key)}).`);
|
|
if (input.annotationId) {
|
|
const annotations = await api.get<Entity[]>(`/api/issues/${target.id}/documents/${encodeURIComponent(doc.key)}/annotations?status=all&includeComments=true`);
|
|
const annotation = annotations.find(row => row.id === input.annotationId);
|
|
if (!annotation || annotation.documentId !== doc.id || annotation.originalRevisionId !== doc.latestRevisionId || annotation.status !== "open")
|
|
throw new Error("Selected review annotation is not open on the actual source revision");
|
|
lines.push(`Selected review comment: ${annotation.id} on this document.`);
|
|
}
|
|
} else if (input.annotationId) throw new Error("A selected annotation requires its actual document");
|
|
if (input.attachment) {
|
|
const file = (await api.get<IssueAttachment[]>(`/api/issues/${target.id}/attachments`)).find(row => row.id === input.attachment!.id);
|
|
if (!file || file.issueId !== target.id || file.sha256 !== input.attachment.sha256 || file.contentPath !== input.attachment.contentPath)
|
|
throw new Error("Selected prior delivery is not the original source attachment");
|
|
lines.push(`Selected existing delivery: [${file.originalFilename}](${file.contentPath}).`);
|
|
}
|
|
if (input.workspaceFilename) lines.push(`Selected workspace file: ${input.workspaceFilename}, in the selected task's authorized workspace.`);
|
|
const description = lines.join("\n\n");
|
|
await api.post(`/api/companies/${fixtures.company.id}/chats/${fixtures.agent.id}`);
|
|
await ctx.refreshIssue();
|
|
const source = ctx.issue();
|
|
if (!source || source.id === target.id) throw new Error("Source selection requires the actual separate standing conversation");
|
|
await api.patch(`/api/issues/${source.id}`, { projectId: target.projectId, description });
|
|
const saved = await api.get<Entity>(`/api/issues/${source.id}`);
|
|
if (saved.id !== source.id || saved.companyId !== fixtures.company.id || saved.projectId !== target.projectId || saved.description !== description)
|
|
throw new Error("Visible source selection did not persist on the canonical conversation");
|
|
await ctx.refreshIssue();
|
|
const factualContextAttachment = await uploadFactualQueryAttachment(ctx, { filename: "selected-source.md", body: description });
|
|
const receipt = { sourceIssueId: saved.id, targetIssueId: target.id, projectId: target.projectId, description,
|
|
documentId: input.document?.id, revisionId: input.document?.latestRevisionId, annotationId: input.annotationId,
|
|
attachmentId: input.attachment?.id, attachmentSha256: input.attachment?.sha256, workspaceFilename: input.workspaceFilename, factualContextAttachment };
|
|
await ctx.input.evidence("chat-catalog-selected-document-source.json", receipt);
|
|
return receipt;
|
|
}
|