paperclip/server/src/__tests__/recovery-classifiers.test.ts
Dotta 57229d0f24
[codex] Add issue monitor liveness controls (#4988)
## Thinking Path

> - Paperclip is a control plane for autonomous AI companies where work
must stay observable, governable, and recoverable.
> - The task/heartbeat subsystem owns agent execution continuity, issue
state transitions, and visible recovery behavior.
> - Waiting on an external service is not the same as being blocked when
the assignee still owns a future check.
> - The gap was that agents had no first-class one-shot monitor state
for external-service waits, so recovery could look stalled or require ad
hoc comments.
> - This pull request adds bounded issue monitors that can wake the
owner, clear exhausted waits, and produce explicit recovery behavior.
> - It also surfaces monitor status in the board UI and documents when
to use monitors versus `blocked`.
> - The benefit is clearer liveness semantics for asynchronous waits
without weakening single-assignee task ownership.

## What Changed

- Added issue monitor fields, shared types, validators, constants, and
an idempotent `0075` migration for scheduled monitor state.
- Added server-side monitor scheduling, dispatch, recovery bounds,
activity logging, and external-ref redaction.
- Added board/agent route coverage for monitor permissions and child
monitor scheduling.
- Added issue detail/property UI for monitor state, a monitor activity
card, and Storybook stories for review surfaces.
- Documented monitor semantics and recovery policy behavior in
`doc/execution-semantics.md`.
- Addressed Greptile review feedback by preserving monitor state in
skipped-stage builders and making board monitor saves send `scheduledBy:
"board"`.

## Verification

- `pnpm install --frozen-lockfile`
- `pnpm run preflight:workspace-links && pnpm exec vitest run
server/src/__tests__/issue-execution-policy-routes.test.ts
server/src/__tests__/issue-execution-policy.test.ts
server/src/__tests__/issue-monitor-scheduler.test.ts
server/src/__tests__/recovery-classifiers.test.ts
ui/src/components/IssueMonitorActivityCard.test.tsx
ui/src/components/IssueProperties.test.tsx
ui/src/lib/activity-format.test.ts`
- First run passed 5 files and failed to collect 2 server suites because
the worktree was missing the optional `acpx/runtime` dependency.
- After `pnpm install --frozen-lockfile`, reran the 2 failed suites
successfully.
- `pnpm exec vitest run
server/src/__tests__/issue-monitor-scheduler.test.ts
server/src/__tests__/recovery-classifiers.test.ts`
- `pnpm --filter @paperclipai/shared typecheck && pnpm --filter
@paperclipai/db typecheck && pnpm --filter @paperclipai/server typecheck
&& pnpm --filter @paperclipai/ui typecheck`
- `pnpm exec vitest run
server/src/__tests__/issue-execution-policy.test.ts
ui/src/components/IssueProperties.test.tsx`
- `pnpm --filter @paperclipai/server typecheck && pnpm --filter
@paperclipai/ui typecheck`
- `pnpm exec vitest run
ui/src/components/IssueMonitorActivityCard.test.tsx
ui/src/components/IssueProperties.test.tsx`
- `pnpm --filter @paperclipai/ui typecheck`
- Storybook screenshot captured from
`http://127.0.0.1:6006/iframe.html?viewMode=story&id=product-issue-monitor-surfaces--monitor-surfaces`
with Playwright.

## Screenshots

![Issue monitor Storybook
surfaces](https://raw.githubusercontent.com/paperclipai/paperclip/PAP-2945-when-a-task-is-waiting-for-an-_external-service_-what-state-should-it-be-in-and-what-recovery-method-could-it-h/docs/pr-screenshots/pap-2945/monitor-surfaces.png)

## Risks

- Medium: this changes heartbeat recovery behavior for scheduled
external-service waits, so regressions could affect wake timing or
recovery issue creation.
- Migration risk is reduced by using `IF NOT EXISTS` for the new issue
monitor columns and index.
- External monitor references are treated as secret-adjacent and are
intentionally omitted from visible activity/wake payloads.

> 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 coding agent with repository tool use and terminal
execution.

## 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 or Storybook review surfaces
- [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>
2026-05-03 08:58:53 -05:00

248 lines
7.3 KiB
TypeScript

import { describe, expect, it } from "vitest";
import { classifyIssueGraphLiveness as classifyIssueGraphLivenessCompat } from "../services/issue-liveness.ts";
import { decideRunLivenessContinuation as decideRunLivenessContinuationCompat } from "../services/run-continuations.ts";
import {
RECOVERY_KEY_PREFIXES,
RECOVERY_ORIGIN_KINDS,
RECOVERY_REASON_KINDS,
buildIssueGraphLivenessIncidentKey,
buildIssueGraphLivenessLeafKey,
buildRunLivenessContinuationIdempotencyKey,
classifyIssueGraphLiveness,
decideRunLivenessContinuation,
isStrandedIssueRecoveryOriginKind,
parseIssueGraphLivenessIncidentKey,
} from "../services/recovery/index.ts";
const companyId = "company-1";
const agentId = "agent-1";
const managerId = "manager-1";
const issueId = "issue-1";
const blockerId = "blocker-1";
const runId = "run-1";
describe("recovery classifier boundary", () => {
it("keeps issue graph liveness classifier parity with the compatibility export", () => {
const input = {
issues: [
{
id: issueId,
companyId,
identifier: "PAP-2073",
title: "Centralize recovery classifiers",
status: "blocked",
assigneeAgentId: agentId,
assigneeUserId: null,
createdByAgentId: null,
createdByUserId: null,
executionState: null,
},
{
id: blockerId,
companyId,
identifier: "PAP-2074",
title: "Move recovery side effects",
status: "todo",
assigneeAgentId: null,
assigneeUserId: null,
createdByAgentId: null,
createdByUserId: null,
executionState: null,
},
],
relations: [{ companyId, blockerIssueId: blockerId, blockedIssueId: issueId }],
agents: [
{
id: agentId,
companyId,
name: "Coder",
role: "engineer",
status: "idle",
reportsTo: managerId,
},
{
id: managerId,
companyId,
name: "CTO",
role: "cto",
status: "idle",
reportsTo: null,
},
],
};
expect(classifyIssueGraphLiveness(input)).toEqual(classifyIssueGraphLivenessCompat(input));
});
it("treats a scheduled monitor as an explicit review action path", () => {
const findings = classifyIssueGraphLiveness({
now: "2026-04-30T18:00:00.000Z",
issues: [
{
id: issueId,
companyId,
identifier: "PAP-2945",
title: "Wait for external review",
status: "in_review",
assigneeAgentId: agentId,
assigneeUserId: null,
createdByAgentId: null,
createdByUserId: null,
executionState: null,
monitorNextCheckAt: "2026-04-30T19:00:00.000Z",
},
],
relations: [],
agents: [
{
id: agentId,
companyId,
name: "Coder",
role: "engineer",
status: "idle",
reportsTo: managerId,
},
],
});
expect(findings).toEqual([]);
});
it("does not treat overdue or exhausted monitors as explicit waiting paths", () => {
const baseIssue = {
id: issueId,
companyId,
identifier: "PAP-2945",
title: "Wait for external review",
status: "in_review",
assigneeAgentId: agentId,
assigneeUserId: null,
createdByAgentId: null,
createdByUserId: null,
};
const agents = [
{
id: agentId,
companyId,
name: "Coder",
role: "engineer",
status: "idle",
reportsTo: managerId,
},
];
const overdue = classifyIssueGraphLiveness({
now: "2026-04-30T20:00:00.000Z",
issues: [
{
...baseIssue,
executionState: null,
monitorNextCheckAt: "2026-04-30T19:00:00.000Z",
},
],
relations: [],
agents,
});
const exhausted = classifyIssueGraphLiveness({
now: "2026-04-30T18:00:00.000Z",
issues: [
{
...baseIssue,
executionPolicy: {
monitor: {
nextCheckAt: "2026-04-30T19:00:00.000Z",
maxAttempts: 1,
},
},
executionState: null,
monitorNextCheckAt: "2026-04-30T19:00:00.000Z",
monitorAttemptCount: 1,
},
],
relations: [],
agents,
});
expect(overdue[0]?.state).toBe("in_review_without_action_path");
expect(exhausted[0]?.state).toBe("in_review_without_action_path");
});
it("keeps run liveness continuation decision parity with the compatibility export", () => {
const input = {
run: {
id: runId,
companyId,
agentId,
continuationAttempt: 0,
} as never,
issue: {
id: issueId,
companyId,
identifier: "PAP-2073",
title: "Centralize recovery classifiers",
status: "in_progress",
assigneeAgentId: agentId,
executionState: null,
projectId: null,
} as never,
agent: {
id: agentId,
companyId,
status: "idle",
} as never,
livenessState: "plan_only" as const,
livenessReason: "Planned without acting",
nextAction: "Take the first concrete action.",
budgetBlocked: false,
idempotentWakeExists: false,
};
expect(decideRunLivenessContinuation(input)).toEqual(decideRunLivenessContinuationCompat(input));
});
it("keeps recovery origin and idempotency keys stable", () => {
expect(RECOVERY_ORIGIN_KINDS).toMatchObject({
issueGraphLivenessEscalation: "harness_liveness_escalation",
strandedIssueRecovery: "stranded_issue_recovery",
staleActiveRunEvaluation: "stale_active_run_evaluation",
});
expect(RECOVERY_REASON_KINDS.runLivenessContinuation).toBe("run_liveness_continuation");
expect(RECOVERY_KEY_PREFIXES.issueGraphLivenessIncident).toBe("harness_liveness");
expect(RECOVERY_KEY_PREFIXES.issueGraphLivenessLeaf).toBe("harness_liveness_leaf");
const incidentKey = buildIssueGraphLivenessIncidentKey({
companyId,
issueId,
state: "blocked_by_unassigned_issue",
blockerIssueId: blockerId,
});
expect(incidentKey).toBe(
"harness_liveness:company-1:issue-1:blocked_by_unassigned_issue:blocker-1",
);
expect(parseIssueGraphLivenessIncidentKey(incidentKey)).toEqual({
companyId,
issueId,
state: "blocked_by_unassigned_issue",
leafIssueId: blockerId,
});
expect(buildIssueGraphLivenessLeafKey({
companyId,
state: "blocked_by_unassigned_issue",
leafIssueId: blockerId,
})).toBe("harness_liveness_leaf:company-1:blocked_by_unassigned_issue:blocker-1");
expect(buildRunLivenessContinuationIdempotencyKey({
issueId,
sourceRunId: runId,
livenessState: "plan_only",
nextAttempt: 1,
})).toBe("run_liveness_continuation:issue-1:run-1:plan_only:1");
});
it("classifies stranded recovery origins as recovery-owned work", () => {
expect(isStrandedIssueRecoveryOriginKind("stranded_issue_recovery")).toBe(true);
expect(isStrandedIssueRecoveryOriginKind("harness_liveness_escalation")).toBe(false);
expect(isStrandedIssueRecoveryOriginKind("manual")).toBe(false);
expect(isStrandedIssueRecoveryOriginKind(null)).toBe(false);
});
});