paperclip/server/src/__tests__/heartbeat-list.test.ts

205 lines
6.1 KiB
TypeScript
Raw Normal View History

import { randomUUID } from "node:crypto";
import { afterAll, afterEach, beforeAll, describe, expect, it } from "vitest";
import { agents, companies, createDb, heartbeatRuns } from "@paperclipai/db";
import {
getEmbeddedPostgresTestSupport,
startEmbeddedPostgresTestDatabase,
} from "./helpers/embedded-postgres.js";
import { heartbeatService } from "../services/heartbeat.ts";
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
if (!embeddedPostgresSupport.supported) {
console.warn(
`Skipping embedded Postgres heartbeat list tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
);
}
describeEmbeddedPostgres("heartbeat list", () => {
let db!: ReturnType<typeof createDb>;
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
beforeAll(async () => {
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-heartbeat-list-");
db = createDb(tempDb.connectionString);
}, 20_000);
afterEach(async () => {
await db.delete(heartbeatRuns);
await db.delete(agents);
await db.delete(companies);
});
afterAll(async () => {
await tempDb?.cleanup();
});
it("returns runs even when the linked db schema lacks processGroupId", async () => {
const companyId = randomUUID();
const agentId = randomUUID();
const runId = randomUUID();
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
requireBoardApprovalForNewAgents: false,
});
await db.insert(agents).values({
id: agentId,
companyId,
name: "CodexCoder",
role: "engineer",
status: "running",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {},
permissions: {},
});
await db.insert(heartbeatRuns).values({
id: runId,
companyId,
agentId,
invocationSource: "assignment",
status: "running",
[codex] Add run liveness continuations (#4083) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Heartbeat runs are the control-plane record of each agent execution window. > - Long-running local agents can exhaust context or stop while still holding useful next-step state. > - Operators need that stop reason, next action, and continuation path to be durable and visible. > - This pull request adds run liveness metadata, continuation summaries, and UI surfaces for issue run ledgers. > - The benefit is that interrupted or long-running work can resume with clearer context instead of losing the agent's last useful handoff. ## What Changed - Added heartbeat-run liveness fields, continuation attempt tracking, and an idempotent `0058` migration. - Added server services and tests for run liveness, continuation summaries, stop metadata, and activity backfill. - Wired local and HTTP adapters to surface continuation/liveness context through shared adapter utilities. - Added shared constants, validators, and heartbeat types for liveness continuation state. - Added issue-detail UI surfaces for continuation handoffs and the run ledger, with component tests. - Updated agent runtime docs, heartbeat protocol docs, prompt guidance, onboarding assets, and skills instructions to explain continuation behavior. - Addressed Greptile feedback by scoping document evidence by run, excluding system continuation-summary documents from liveness evidence, importing shared liveness types, surfacing hidden ledger run counts, documenting bounded retry behavior, and moving run-ledger liveness backfill off the request path. ## Verification - `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts server/src/__tests__/run-continuations.test.ts server/src/__tests__/run-liveness.test.ts server/src/__tests__/activity-service.test.ts server/src/__tests__/documents-service.test.ts server/src/__tests__/issue-continuation-summary.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/components/IssueContinuationHandoff.test.tsx ui/src/components/IssueDocumentsSection.test.tsx` - `pnpm --filter @paperclipai/db build` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm --filter @paperclipai/ui typecheck` - `pnpm --filter @paperclipai/server typecheck` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/run-continuations.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm exec vitest run server/src/__tests__/heartbeat-process-recovery.test.ts -t "treats a plan document update"` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts -t "activity service|treats a plan document update"` - Remote PR checks on head `e53b1a1d`: `verify`, `e2e`, `policy`, and Snyk all passed. - Confirmed `public-gh/master` is an ancestor of this branch after fetching `public-gh master`. - Confirmed `pnpm-lock.yaml` is not included in the branch diff. - Confirmed migration `0058_wealthy_starbolt.sql` is ordered after `0057` and uses `IF NOT EXISTS` guards for repeat application. - Greptile inline review threads are resolved. ## Risks - Medium risk: this touches heartbeat execution, liveness recovery, activity rendering, issue routes, shared contracts, docs, and UI. - Migration risk is mitigated by additive columns/indexes and idempotent guards. - Run-ledger liveness backfill is now asynchronous, so the first ledger response can briefly show historical missing liveness until the background backfill completes. - UI screenshot coverage is not included in this packaging pass; validation is currently through focused component tests. > 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, local tool-use coding agent with terminal, git, GitHub connector, GitHub CLI, and Paperclip API access. ## 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 Screenshot note: no before/after screenshots were captured in this PR packaging pass; the UI changes are covered by focused component tests listed above. --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:01:49 -05:00
livenessState: "advanced",
livenessReason: "run produced action evidence",
continuationAttempt: 1,
lastUsefulActionAt: new Date("2026-04-18T12:00:00Z"),
nextAction: "continue implementation",
contextSnapshot: { issueId: randomUUID() },
});
const originalDescriptor = Object.getOwnPropertyDescriptor(heartbeatRuns, "processGroupId");
Object.defineProperty(heartbeatRuns, "processGroupId", {
value: undefined,
configurable: true,
writable: true,
});
try {
const runs = await heartbeatService(db).list(companyId, agentId, 5);
expect(runs).toHaveLength(1);
expect(runs[0]?.id).toBe(runId);
expect(runs[0]?.processGroupId ?? null).toBeNull();
[codex] Add run liveness continuations (#4083) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Heartbeat runs are the control-plane record of each agent execution window. > - Long-running local agents can exhaust context or stop while still holding useful next-step state. > - Operators need that stop reason, next action, and continuation path to be durable and visible. > - This pull request adds run liveness metadata, continuation summaries, and UI surfaces for issue run ledgers. > - The benefit is that interrupted or long-running work can resume with clearer context instead of losing the agent's last useful handoff. ## What Changed - Added heartbeat-run liveness fields, continuation attempt tracking, and an idempotent `0058` migration. - Added server services and tests for run liveness, continuation summaries, stop metadata, and activity backfill. - Wired local and HTTP adapters to surface continuation/liveness context through shared adapter utilities. - Added shared constants, validators, and heartbeat types for liveness continuation state. - Added issue-detail UI surfaces for continuation handoffs and the run ledger, with component tests. - Updated agent runtime docs, heartbeat protocol docs, prompt guidance, onboarding assets, and skills instructions to explain continuation behavior. - Addressed Greptile feedback by scoping document evidence by run, excluding system continuation-summary documents from liveness evidence, importing shared liveness types, surfacing hidden ledger run counts, documenting bounded retry behavior, and moving run-ledger liveness backfill off the request path. ## Verification - `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts server/src/__tests__/run-continuations.test.ts server/src/__tests__/run-liveness.test.ts server/src/__tests__/activity-service.test.ts server/src/__tests__/documents-service.test.ts server/src/__tests__/issue-continuation-summary.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/components/IssueContinuationHandoff.test.tsx ui/src/components/IssueDocumentsSection.test.tsx` - `pnpm --filter @paperclipai/db build` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm --filter @paperclipai/ui typecheck` - `pnpm --filter @paperclipai/server typecheck` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/run-continuations.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm exec vitest run server/src/__tests__/heartbeat-process-recovery.test.ts -t "treats a plan document update"` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts -t "activity service|treats a plan document update"` - Remote PR checks on head `e53b1a1d`: `verify`, `e2e`, `policy`, and Snyk all passed. - Confirmed `public-gh/master` is an ancestor of this branch after fetching `public-gh master`. - Confirmed `pnpm-lock.yaml` is not included in the branch diff. - Confirmed migration `0058_wealthy_starbolt.sql` is ordered after `0057` and uses `IF NOT EXISTS` guards for repeat application. - Greptile inline review threads are resolved. ## Risks - Medium risk: this touches heartbeat execution, liveness recovery, activity rendering, issue routes, shared contracts, docs, and UI. - Migration risk is mitigated by additive columns/indexes and idempotent guards. - Run-ledger liveness backfill is now asynchronous, so the first ledger response can briefly show historical missing liveness until the background backfill completes. - UI screenshot coverage is not included in this packaging pass; validation is currently through focused component tests. > 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, local tool-use coding agent with terminal, git, GitHub connector, GitHub CLI, and Paperclip API access. ## 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 Screenshot note: no before/after screenshots were captured in this PR packaging pass; the UI changes are covered by focused component tests listed above. --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:01:49 -05:00
expect(runs[0]).toMatchObject({
livenessState: "advanced",
livenessReason: "run produced action evidence",
continuationAttempt: 1,
nextAction: "continue implementation",
});
expect(runs[0]?.lastUsefulActionAt).toEqual(new Date("2026-04-18T12:00:00Z"));
} finally {
if (originalDescriptor) {
Object.defineProperty(heartbeatRuns, "processGroupId", originalDescriptor);
} else {
delete (heartbeatRuns as Record<string, unknown>).processGroupId;
}
}
});
[codex] harden heartbeat run summaries and recovery context (#3742) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Heartbeat runs are the control-plane record of what agents did, why they woke up, and what operators should see next > - Run lists, stranded issue comments, and live log polling all depend on compact but accurate heartbeat summaries > - The current branch had a focused backend slice that improves how run result JSON is summarized, how stale process recovery comments are written, and how live log polling resolves the active run > - This pull request isolates that heartbeat/runtime reliability work from the unrelated UI and dev-tooling changes > - The benefit is more reliable issue context and cheaper run lookups without dragging unrelated board UI changes into the same review ## What Changed - Include the latest run failure in stranded issue comments during orphaned process recovery. - Bound heartbeat `result_json` payloads for list responses while preserving the raw stored payloads. - Narrow heartbeat log endpoint lookups so issue polling resolves the relevant active run with less unnecessary scanning. - Add focused tests for heartbeat list summaries, live run polling, orphaned process recovery, and the run context/result summary helpers. ## Verification - `pnpm vitest run server/src/__tests__/heartbeat-context-summary.test.ts server/src/__tests__/heartbeat-list.test.ts server/src/__tests__/agent-live-run-routes.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts` ## Risks - The main risk is accidentally hiding a field that some client still expects from summarized `result_json`, or over-constraining the live log lookup path for edge-case run routing. - Recovery comments now surface the latest failure more aggressively, so wording changes may affect downstream expectations if anyone parses those comments too strictly. ## Model Used - OpenAI Codex, GPT-5-based coding agent in the Codex CLI environment. Exact backend model deployment ID was not exposed in-session. Tool-assisted editing and shell execution were used. ## 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 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
2026-04-15 09:48:39 -05:00
it("returns small result json payloads unchanged from getRun", async () => {
const companyId = randomUUID();
const agentId = randomUUID();
const runId = randomUUID();
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
requireBoardApprovalForNewAgents: false,
});
await db.insert(agents).values({
id: agentId,
companyId,
name: "CodexCoder",
role: "engineer",
status: "running",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {},
permissions: {},
});
await db.insert(heartbeatRuns).values({
id: runId,
companyId,
agentId,
invocationSource: "assignment",
status: "succeeded",
resultJson: {
summary: "done",
structured: { ok: true },
},
});
const run = await heartbeatService(db).getRun(runId);
expect(run?.resultJson).toEqual({
summary: "done",
structured: { ok: true },
});
});
it("bounds oversized legacy result json payloads on getRun", async () => {
const companyId = randomUUID();
const agentId = randomUUID();
const runId = randomUUID();
const oversizedStdout = Array.from({ length: 8_000 }, (_, index) =>
`${index.toString(16).padStart(4, "0")}-${randomUUID()}`,
).join("|");
const oversizedNestedPayload = Array.from({ length: 6_000 }, (_, index) =>
`${index.toString(16).padStart(4, "0")}:${randomUUID()}`,
).join("|");
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
requireBoardApprovalForNewAgents: false,
});
await db.insert(agents).values({
id: agentId,
companyId,
name: "CodexCoder",
role: "engineer",
status: "running",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {},
permissions: {},
});
await db.insert(heartbeatRuns).values({
id: runId,
companyId,
agentId,
invocationSource: "assignment",
status: "succeeded",
resultJson: {
summary: "completed",
stdout: oversizedStdout,
nestedHuge: { payload: oversizedNestedPayload },
},
});
const run = await heartbeatService(db).getRun(runId);
const result = run?.resultJson as Record<string, unknown> | null;
expect(result).toMatchObject({
summary: "completed",
truncated: true,
truncationReason: "oversized_result_json",
stdoutTruncated: true,
});
expect(typeof result?.stdout).toBe("string");
expect((result?.stdout as string).length).toBeLessThan(oversizedStdout.length);
expect(result).not.toHaveProperty("nestedHuge");
});
});