mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-25 09:41:04 +01:00
DottaandPaperclip
6d46851920
## Thinking Path > - Paperclip manages agents and the work they perform. > - Product E2E checks verify real user paths through those agents. > - A recorded GitHub review-bot walkthrough had no repeatable registered case. > - App setup, automatic triggering, publication, and task completion need separate evidence. > - This pull request adds an explicit attended journey to the existing catalog and report tools. > - Reusable setup profiles and independent assertions preserve the same outcome across compatible targets. ## Linked Issues or Issue Description Refs: #17262. This case remains an explicit attended attached-target flow. It does not replace the shared deployment-target or paid-operations framework. **What existing behavior does this improve?** The Product E2E catalog can now select and retain evidence for GitHub review-bot setup and its first automatic review. **Current behavior** Recorded walkthroughs cannot be rerun as a fixed registered case. A published review alone can hide a failed run or unfinished task. **Proposed behavior** Create and install an owned App, save automatic new-PR settings, create a defective PR, and require correlated review delivery, an inline finding, a consistent check, a successful run, and a Done task. Retain failures and confirm owned-resource cleanup. **Reason and benefit** The case makes a useful external integration reproducible without treating setup, unit checks, or report rendering as proof of a completed live journey. ## What Changed - Add two explicit attended cells for an existing configured agent in local or Daytona execution. - Declare hosting, account, connection, and credential prerequisites through private setup bindings. - Add fixed browser controls, ownership checks, independent grading, and cleanup. - Package declared screenshots through the existing sanitizer, manifest, validator, and dashboard. - Reject operations-managed execution until budgeted routing is qualified. - Document hosted QA credential setup and evidence limits. ## Verification - Focused catalog, oracle, report, connection, and ownership checks: 127 tests passed. - Inherited-environment preflight regression failed against the previous commit and passed after the fix. Actual-run environment verification remains required. - Harness TypeScript check and full workspace typecheck passed. Full build passed. The local full-test attempt was interrupted after repeated embedded PostgreSQL startup failures; its exit code of zero does not establish a pass; Exact-head Linux CI passed the full test, typecheck, build, Runner, serialized, browser, and canary gates on `abbddeade848edefc8de75f11cc9008b2cd52764`. - A real hosted attempt published a rated review and inline finding. It failed when its native session timed out before the task reached Done. Cleanup passed. Full live qualification remains open. - Credential scan found no known credential values in the authored files or retained report corpus. ## Risks - The full case creates external test resources and uses the configured provider. It requires an explicit selection and current task authority. It is excluded from default and CI matrices. - Time and run limits are not a hard dollar cap. Missing dollar cost stays unknown. Fixture setup does not weaken budget policy. - Fresh personal OAuth, unattended authentication, runtime skill-read proof, and cross-host qualification are separate claims. - The selected live fixture needs environment/lifecycle recovery before it can adopt a longer provider deadline. ## Model Used OpenAI GPT-6 family through Codex, with reasoning, code execution, and browser tools. The exact deployment model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used, including the available 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 described the issue in-PR following the enhancement template - [x] I have not referenced internal or instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal ticket ID - [x] I have run focused tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation - [x] I have considered and documented risks - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open findings - [x] I will address all Greptile and reviewer comments before merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
24 lines
3.1 KiB
TypeScript
24 lines
3.1 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
import { readFileSync } from "node:fs";
|
|
import type { EnvironmentFixture, RunnerProfileFixture, RunnerSuiteFixture } from "./types.js";
|
|
|
|
export function buildGitHubReviewJourneySuite(profiles: readonly RunnerProfileFixture[], environments: readonly EnvironmentFixture[]): RunnerSuiteFixture {
|
|
const base = profiles.find(p => p.id === "runner-codex")!;
|
|
const profile: RunnerProfileFixture = { ...base, id: "configured-agent", label: "Existing review agent (profile-bound)", groups: [],
|
|
model: "configured-in-journey-profile", provider: "configured-in-journey-profile", supportedEnvironments: ["local", "daytona"],
|
|
modelQualification: { source: "candidate_runner_profile", qualificationId: "explicit-attached-agent-profile" },
|
|
buildAgent: () => { throw new Error("GitHub review journey uses the explicitly bound existing agent"); } };
|
|
const hash = createHash("sha256");
|
|
for (const file of ["github-review-cases.ts", "github-review-config.ts", "github-review-browser.ts", "github-review-attendance.ts", "github-review-flow.ts", "github-review-launch.ts", "github-review-report.ts", "github-review-evidence.ts", "github-review-ownership.ts", "journey-dependencies.ts"]) hash.update(file).update(readFileSync(new URL(`./${file}`, import.meta.url)));
|
|
return { id: "github-review-journey", label: "GitHub review bot setup and first review", groups: [], manualOnly: true,
|
|
description: "Attended real GitHub App setup, repository-scoped installation, automatic PR review, independent publication and task checks. Reuses a private QA repository.",
|
|
profiles: [profile], environments, expectedMatrixSize: 2,
|
|
definitionMetadata: { version: 1, digest: hash.digest("hex"), scheduling: "explicit-only", sourceJourneySha256: "2a504ec0b68c42d597a20fad5fc3bb8d7086ab5c24d34fc75c2a031f8559ab40",
|
|
applicability: ["self-hosted-with-public-github-ingress", "paperclip-cloud-with-github-app-support"], mcpConnections: [],
|
|
dependencies: [{ alias: "github-user", consumer: "browser", required: true }, { alias: "github-verification-mailbox", consumer: "harness", phase: "setup-profile-dependent" }, { alias: "review-agent", consumer: "product-agent", required: true },
|
|
{ alias: "github-user-connection", consumer: "browser-identity-verification", required: true }, { alias: "review-bot-app", consumer: "product-agent", phase: "created-in-journey" }], authentication: "dedicated-browser-with-profile-bound-authentication", providerCredential: "existing-product-agent-binding" },
|
|
tasks: [{ id: "setup-and-first-review", label: "Create App, configure Ponytail skill, open PR, verify automatic review", groups: [], flow: "github_review_journey", workMode: "standard",
|
|
expectedRunCount: 3, minimumExpectedRunCount: 1, automaticRetryPolicy: "single_attempt", attemptTimeoutMs: { local: 1_800_000, daytona: 1_800_000 }, turnTimeoutMs: 600_000,
|
|
expectedTerminalState: { issue: "done", run: "succeeded" }, buildTitle: n => `GitHub review journey ${n}`, buildPrompt: () => "Real GitHub opened event; never dispatched by fixture.", buildVisibleMarker: n => n, buildMatchers: () => [] }] };
|
|
}
|