forked from farhoodlabs/paperclip
7f893ac4ec
## 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>
117 lines
3.3 KiB
TypeScript
117 lines
3.3 KiB
TypeScript
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 { activityService } from "../services/activity.ts";
|
|
|
|
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
|
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
|
|
|
|
if (!embeddedPostgresSupport.supported) {
|
|
console.warn(
|
|
`Skipping embedded Postgres activity service tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
|
);
|
|
}
|
|
|
|
describeEmbeddedPostgres("activity service", () => {
|
|
let db!: ReturnType<typeof createDb>;
|
|
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
|
|
|
beforeAll(async () => {
|
|
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-activity-service-");
|
|
db = createDb(tempDb.connectionString);
|
|
}, 20_000);
|
|
|
|
afterEach(async () => {
|
|
await db.delete(heartbeatRuns);
|
|
await db.delete(agents);
|
|
await db.delete(companies);
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await tempDb?.cleanup();
|
|
});
|
|
|
|
it("returns compact usage and result summaries for issue runs", async () => {
|
|
const companyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const issueId = randomUUID();
|
|
const runId = randomUUID();
|
|
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Paperclip",
|
|
issuePrefix: `T${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",
|
|
contextSnapshot: { issueId },
|
|
usageJson: {
|
|
inputTokens: 11,
|
|
output_tokens: 7,
|
|
cache_read_input_tokens: 3,
|
|
billingType: "metered",
|
|
costUsd: 0.42,
|
|
enormousBlob: "x".repeat(256_000),
|
|
},
|
|
resultJson: {
|
|
billing_type: "metered",
|
|
total_cost_usd: 0.42,
|
|
summary: "done",
|
|
nestedHuge: { payload: "y".repeat(256_000) },
|
|
},
|
|
});
|
|
|
|
const runs = await activityService(db).runsForIssue(companyId, issueId);
|
|
|
|
expect(runs).toHaveLength(1);
|
|
expect(runs[0]).toMatchObject({
|
|
runId,
|
|
agentId,
|
|
invocationSource: "assignment",
|
|
});
|
|
expect(runs[0]?.usageJson).toEqual({
|
|
inputTokens: 11,
|
|
input_tokens: 11,
|
|
outputTokens: 7,
|
|
output_tokens: 7,
|
|
cachedInputTokens: 3,
|
|
cached_input_tokens: 3,
|
|
cache_read_input_tokens: 3,
|
|
billingType: "metered",
|
|
billing_type: "metered",
|
|
costUsd: 0.42,
|
|
cost_usd: 0.42,
|
|
total_cost_usd: 0.42,
|
|
});
|
|
expect(runs[0]?.resultJson).toEqual({
|
|
billingType: "metered",
|
|
billing_type: "metered",
|
|
costUsd: 0.42,
|
|
cost_usd: 0.42,
|
|
total_cost_usd: 0.42,
|
|
});
|
|
});
|
|
});
|