paperclip/tests/e2e/onboarding.spec.ts

182 lines
6.5 KiB
TypeScript
Raw Normal View History

import { test, expect } from "@playwright/test";
/**
* E2E: Onboarding wizard flow (skip_llm mode).
*
* Walks through the 4-step OnboardingWizard:
* Step 1 Name your company
* Step 2 Create your first agent (adapter selection + config)
* Step 3 Give it something to do (task creation)
* Step 4 Ready to launch (summary + open issue)
*
* By default this runs in skip_llm mode: we do NOT assert that an LLM
* heartbeat fires. Set PAPERCLIP_E2E_SKIP_LLM=false to enable LLM-dependent
* assertions (requires a valid ANTHROPIC_API_KEY).
*/
const SKIP_LLM = process.env.PAPERCLIP_E2E_SKIP_LLM !== "false";
const COMPANY_NAME = `E2E-Test-${Date.now()}`;
const AGENT_NAME = "CEO";
const TASK_TITLE = "E2E test task";
test.describe("Onboarding wizard", () => {
test("completes full wizard flow", async ({ page }) => {
2026-04-07 18:20:35 -05:00
await page.goto("/onboarding");
const wizardHeading = page.locator("h3", { hasText: "Name your company" });
await expect(wizardHeading).toBeVisible({ timeout: 5_000 });
const companyNameInput = page.locator('input[placeholder="Acme Corp"]');
await companyNameInput.fill(COMPANY_NAME);
const nextButton = page.getByRole("button", { name: "Next" });
await nextButton.click();
await expect(
page.locator("h3", { hasText: "Create your first agent" })
2026-04-07 18:20:35 -05:00
).toBeVisible({ timeout: 30_000 });
const agentNameInput = page.locator('input[placeholder="CEO"]');
await expect(agentNameInput).toHaveValue(AGENT_NAME);
await expect(
page.locator("button", { hasText: "Claude Code" }).locator("..")
).toBeVisible();
2026-03-18 08:00:02 -05:00
await page.getByRole("button", { name: "More Agent Adapter Types" }).click();
await expect(page.getByRole("button", { name: "Process" })).toHaveCount(0);
await page.getByRole("button", { name: "Next" }).click();
await expect(
page.locator("h3", { hasText: "Give it something to do" })
2026-04-07 18:20:35 -05:00
).toBeVisible({ timeout: 30_000 });
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## Model Used - OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact deployed model ID is not exposed in this environment), reasoning enabled, tool use and local code execution enabled ## 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) - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
const baseUrl = page.url().split("/").slice(0, 3).join("/");
if (SKIP_LLM) {
const companiesAfterAgentRes = await page.request.get(`${baseUrl}/api/companies`);
expect(companiesAfterAgentRes.ok()).toBe(true);
const companiesAfterAgent = await companiesAfterAgentRes.json();
const companyAfterAgent = companiesAfterAgent.find(
(c: { name: string }) => c.name === COMPANY_NAME
);
expect(companyAfterAgent).toBeTruthy();
const agentsAfterCreateRes = await page.request.get(
`${baseUrl}/api/companies/${companyAfterAgent.id}/agents`
);
expect(agentsAfterCreateRes.ok()).toBe(true);
const agentsAfterCreate = await agentsAfterCreateRes.json();
const ceoAgentAfterCreate = agentsAfterCreate.find(
(a: { name: string }) => a.name === AGENT_NAME
);
expect(ceoAgentAfterCreate).toBeTruthy();
const disableWakeRes = await page.request.patch(
`${baseUrl}/api/agents/${ceoAgentAfterCreate.id}?companyId=${encodeURIComponent(companyAfterAgent.id)}`,
{
data: {
runtimeConfig: {
heartbeat: {
enabled: false,
intervalSec: 300,
wakeOnDemand: false,
cooldownSec: 10,
[codex] Improve agent runtime recovery and governance (#4086) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - The heartbeat runtime, agent import path, and agent configuration defaults determine whether work is dispatched safely and predictably. > - Several accumulated fixes all touched agent execution recovery, wake routing, import behavior, and runtime concurrency defaults. > - Those changes need to land together so the heartbeat service and agent creation defaults stay internally consistent. > - This pull request groups the runtime/governance changes from the split branch into one standalone branch. > - The benefit is safer recovery for stranded runs, bounded high-volume reads, imported-agent approval correctness, skill-template support, and a clearer default concurrency policy. ## What Changed - Fixed stranded continuation recovery so successful automatic retries are requeued instead of incorrectly blocking the issue. - Bounded high-volume issue/log reads across issue, heartbeat, agent, project, and workspace paths. - Fixed imported-agent approval and instruction-path permission handling. - Quarantined seeded worktree execution state during worktree provisioning. - Queued approval follow-up wakes and hardened SQL_ASCII heartbeat output handling. - Added reusable agent instruction templates for hiring flows. - Set the default max concurrent agent runs to five and updated related UI/tests/docs. ## Verification - `pnpm install --frozen-lockfile` - `pnpm exec vitest run server/src/__tests__/company-portability.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/heartbeat-comment-wake-batching.test.ts server/src/__tests__/heartbeat-list.test.ts server/src/__tests__/issues-service.test.ts server/src/__tests__/agent-permissions-routes.test.ts packages/adapter-utils/src/server-utils.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - Split integration check: merged this branch first, followed by the other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge conflicts. - Confirmed this branch does not include `pnpm-lock.yaml`. ## Risks - Medium risk: touches heartbeat recovery, queueing, and issue list bounds in central runtime paths. - Imported-agent and concurrency default behavior changes may affect existing automation that assumes one-at-a-time default runs. - No database migrations are included. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, GPT-5.4 tool-enabled coding model, agentic code-editing/runtime with local shell and GitHub CLI access; exact context window and reasoning mode are not exposed by the Paperclip harness. ## 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 run tests locally and they pass - [x] I have added or updated tests where applicable - [x] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
maxConcurrentRuns: 5,
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## Model Used - OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact deployed model ID is not exposed in this environment), reasoning enabled, tool use and local code execution enabled ## 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) - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
},
},
},
}
);
expect(disableWakeRes.ok()).toBe(true);
}
const taskTitleInput = page.locator(
'input[placeholder="e.g. Research competitor pricing"]'
);
await taskTitleInput.clear();
await taskTitleInput.fill(TASK_TITLE);
await page.getByRole("button", { name: "Next" }).click();
await expect(
page.locator("h3", { hasText: "Ready to launch" })
2026-04-07 18:20:35 -05:00
).toBeVisible({ timeout: 30_000 });
await expect(page.locator("text=" + COMPANY_NAME)).toBeVisible();
await expect(page.locator("text=" + AGENT_NAME)).toBeVisible();
await expect(page.locator("text=" + TASK_TITLE)).toBeVisible();
2026-03-18 08:00:02 -05:00
await page.getByRole("button", { name: "Create & Open Issue" }).click();
2026-04-07 18:20:35 -05:00
await expect(page).toHaveURL(/\/issues\//, { timeout: 30_000 });
const companiesRes = await page.request.get(`${baseUrl}/api/companies`);
expect(companiesRes.ok()).toBe(true);
const companies = await companiesRes.json();
const company = companies.find(
(c: { name: string }) => c.name === COMPANY_NAME
);
expect(company).toBeTruthy();
const agentsRes = await page.request.get(
`${baseUrl}/api/companies/${company.id}/agents`
);
expect(agentsRes.ok()).toBe(true);
const agents = await agentsRes.json();
const ceoAgent = agents.find(
(a: { name: string }) => a.name === AGENT_NAME
);
expect(ceoAgent).toBeTruthy();
expect(ceoAgent.role).toBe("ceo");
expect(ceoAgent.adapterType).not.toBe("process");
const instructionsBundleRes = await page.request.get(
`${baseUrl}/api/agents/${ceoAgent.id}/instructions-bundle?companyId=${company.id}`
);
expect(instructionsBundleRes.ok()).toBe(true);
const instructionsBundle = await instructionsBundleRes.json();
expect(
instructionsBundle.files.map((file: { path: string }) => file.path).sort()
).toEqual(["AGENTS.md", "HEARTBEAT.md", "SOUL.md", "TOOLS.md"]);
const issuesRes = await page.request.get(
`${baseUrl}/api/companies/${company.id}/issues`
);
expect(issuesRes.ok()).toBe(true);
const issues = await issuesRes.json();
const task = issues.find(
(i: { title: string }) => i.title === TASK_TITLE
);
expect(task).toBeTruthy();
expect(task.assigneeAgentId).toBe(ceoAgent.id);
expect(task.description).toContain(
"You are the CEO. You set the direction for the company."
);
expect(task.description).not.toContain("github.com/paperclipai/companies");
if (!SKIP_LLM) {
await expect(async () => {
const res = await page.request.get(
`${baseUrl}/api/issues/${task.id}`
);
const issue = await res.json();
expect(["in_progress", "done"]).toContain(issue.status);
}).toPass({ timeout: 120_000, intervals: [5_000] });
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## Model Used - OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact deployed model ID is not exposed in this environment), reasoning enabled, tool use and local code execution enabled ## 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) - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
} else {
await expect
.poll(async () => {
const runsRes = await page.request.get(
`${baseUrl}/api/companies/${company.id}/heartbeat-runs?agentId=${ceoAgent.id}`
);
expect(runsRes.ok()).toBe(true);
const runs = await runsRes.json();
return Array.isArray(runs) ? runs.length : -1;
}, { timeout: 10_000, intervals: [500, 1_000, 2_000] })
.toBe(0);
}
});
});