paperclip/server/src/__tests__/issue-execution-policy.test.ts

1450 lines
47 KiB
TypeScript
Raw Normal View History

import { describe, expect, it } from "vitest";
import { applyIssueExecutionPolicyTransition, normalizeIssueExecutionPolicy, parseIssueExecutionState } from "../services/issue-execution-policy.ts";
import type { IssueExecutionPolicy, IssueExecutionState } from "@paperclipai/shared";
const coderAgentId = "11111111-1111-4111-8111-111111111111";
const qaAgentId = "22222222-2222-4222-8222-222222222222";
const ctoAgentId = "33333333-3333-4333-8333-333333333333";
const ctoUserId = "cto-user";
const boardUserId = "board-user";
function makePolicy(
stages: Array<{ type: "review" | "approval"; participants: Array<{ type: "agent" | "user"; agentId?: string; userId?: string }> }>,
) {
return normalizeIssueExecutionPolicy({ stages })!;
}
function twoStagePolicy() {
return makePolicy([
{ type: "review", participants: [{ type: "agent", agentId: qaAgentId }] },
{ type: "approval", participants: [{ type: "user", userId: ctoUserId }] },
]);
}
function reviewOnlyPolicy() {
return makePolicy([
{ type: "review", participants: [{ type: "agent", agentId: qaAgentId }] },
]);
}
function approvalOnlyPolicy() {
return makePolicy([
{ type: "approval", participants: [{ type: "user", userId: ctoUserId }] },
]);
}
describe("normalizeIssueExecutionPolicy", () => {
it("returns null for null/undefined input", () => {
expect(normalizeIssueExecutionPolicy(null)).toBeNull();
expect(normalizeIssueExecutionPolicy(undefined)).toBeNull();
});
it("returns null when stages are empty", () => {
expect(normalizeIssueExecutionPolicy({ stages: [] })).toBeNull();
});
it("throws when all participants are invalid (missing agentId)", () => {
expect(() =>
normalizeIssueExecutionPolicy({
stages: [{ type: "review", participants: [{ type: "agent" }] }],
}),
).toThrow("Invalid execution policy");
});
it("deduplicates participants within a stage", () => {
const result = normalizeIssueExecutionPolicy({
stages: [
{
type: "review",
participants: [
{ type: "agent", agentId: qaAgentId },
{ type: "agent", agentId: qaAgentId },
],
},
],
});
expect(result!.stages[0].participants).toHaveLength(1);
});
it("assigns UUIDs to stages and participants", () => {
const result = normalizeIssueExecutionPolicy({
stages: [
{ type: "review", participants: [{ type: "agent", agentId: qaAgentId }] },
],
});
expect(result!.stages[0].id).toBeDefined();
expect(result!.stages[0].participants[0].id).toBeDefined();
});
it("always sets commentRequired to true", () => {
const result = normalizeIssueExecutionPolicy({
commentRequired: false,
stages: [
{ type: "review", participants: [{ type: "agent", agentId: qaAgentId }] },
],
});
expect(result!.commentRequired).toBe(true);
});
it("defaults mode to normal", () => {
const result = normalizeIssueExecutionPolicy({
stages: [
{ type: "review", participants: [{ type: "agent", agentId: qaAgentId }] },
],
});
expect(result!.mode).toBe("normal");
});
it("rejects approvalsNeeded values above 1", () => {
expect(() =>
normalizeIssueExecutionPolicy({
stages: [
{
type: "review",
approvalsNeeded: 2,
participants: [{ type: "agent", agentId: qaAgentId }],
},
],
}),
).toThrow("Invalid execution policy");
});
it("throws for invalid input", () => {
expect(() => normalizeIssueExecutionPolicy({ stages: [{ type: "invalid_type" }] })).toThrow();
});
[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
it("keeps monitor-only policies", () => {
const result = normalizeIssueExecutionPolicy({
monitor: {
nextCheckAt: "2026-04-11T12:30:00.000Z",
notes: "Check deployment",
externalRef: "https://example.test/deploy?token=secret",
},
stages: [],
});
expect(result).toMatchObject({
stages: [],
monitor: {
nextCheckAt: "2026-04-11T12:30:00.000Z",
notes: "Check deployment",
scheduledBy: "assignee",
externalRef: "[redacted]",
},
});
});
});
describe("parseIssueExecutionState", () => {
it("returns null for null/undefined", () => {
expect(parseIssueExecutionState(null)).toBeNull();
expect(parseIssueExecutionState(undefined)).toBeNull();
});
it("returns null for invalid shape", () => {
expect(parseIssueExecutionState({ status: "bogus" })).toBeNull();
});
it("parses a valid state", () => {
const state = parseIssueExecutionState({
status: "pending",
currentStageId: "aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa",
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
});
expect(state).not.toBeNull();
expect(state!.status).toBe("pending");
});
});
describe("issue execution policy transitions", () => {
describe("happy path: executor → review → approval → done", () => {
const policy = twoStagePolicy();
it("routes executor completion into review", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Implemented the feature",
});
expect(result.patch.status).toBe("in_review");
expect(result.patch.assigneeAgentId).toBe(qaAgentId);
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageType: "review",
returnAssignee: { type: "agent", agentId: coderAgentId },
});
expect(result.decision).toBeUndefined();
});
[codex] Improve issue thread review flow (#4381) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Issue detail is where operators coordinate review, approvals, and follow-up work with active runs > - That thread UI needs to surface blockers, descendants, review handoffs, and reply ergonomics clearly enough for humans to guide agent work > - Several small gaps in the issue-thread flow were making review and navigation clunkier than necessary > - This pull request improves the reply composer, descendant/blocker presentation, interaction folding, and review-request handoff plumbing together as one cohesive issue-thread workflow slice > - The benefit is a cleaner operator review loop without changing the broader task model ## What Changed - restored and refined the floating reply composer behavior in the issue thread - folded expired confirmation interactions and improved post-submit thread scrolling behavior - surfaced descendant issue context and inline blocker/paused-assignee notices on the issue detail view - tightened large-board first paint behavior in `IssuesList` - added loose review-request handoffs through the issue execution-policy/update path and covered them with tests ## Verification - `pnpm vitest run ui/src/pages/IssueDetail.test.tsx` - `pnpm vitest run server/src/__tests__/issues-service.test.ts server/src/__tests__/issue-execution-policy.test.ts` - `pnpm exec vitest run --project @paperclipai/ui ui/src/components/IssueChatThread.test.tsx ui/src/components/IssueProperties.test.tsx ui/src/components/IssuesList.test.tsx ui/src/lib/issue-tree.test.ts ui/src/api/issues.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-utils packages/adapter-utils/src/server-utils.test.ts` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/issue-comment-reopen-routes.test.ts -t "coerces executor handoff patches into workflow-controlled review wakes|wakes the return assignee with execution_changes_requested"` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/issue-execution-policy.test.ts server/src/__tests__/issues-service.test.ts` ## Visual Evidence - UI layout changes are covered by the focused issue-thread component and issue-detail tests listed above. Browser screenshots were not attachable from this automated greploop environment, so reviewers should use the running preview for final visual confirmation. ## Risks - Moderate UI-flow risk: these changes touch the issue detail experience in multiple spots, so regressions would most likely show up as thread-layout quirks or incorrect review-handoff behavior > 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-based coding agent with tool use and code execution in the Codex CLI environment ## 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 documented the visual verification path - [ ] 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>
2026-04-24 08:02:45 -05:00
it("carries loose review instructions on the pending handoff", () => {
const reviewInstructions = [
"Please focus on whether the migration path is reversible.",
"",
"- Check failure handling",
"- Call out any unclear operator instructions",
].join("\n");
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Implemented the migration",
reviewRequest: { instructions: reviewInstructions },
});
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
reviewRequest: { instructions: reviewInstructions },
});
});
it("clears loose review instructions with explicit null during a stage transition", () => {
const reviewStageId = policy.stages[0].id;
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
reviewRequest: { instructions: "Old review request" },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "in_review",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Ready for review",
reviewRequest: null,
});
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
reviewRequest: null,
});
});
it("reviewer approves → advances to approval stage", () => {
const reviewStageId = policy.stages[0].id;
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: "QA signoff complete",
});
expect(result.patch.status).toBe("in_review");
expect(result.patch.assigneeAgentId).toBeNull();
expect(result.patch.assigneeUserId).toBe(ctoUserId);
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageType: "approval",
completedStageIds: [reviewStageId],
currentParticipant: { type: "user", userId: ctoUserId },
});
expect(result.decision).toMatchObject({
stageId: reviewStageId,
stageType: "review",
outcome: "approved",
});
});
[codex] Improve issue thread review flow (#4381) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Issue detail is where operators coordinate review, approvals, and follow-up work with active runs > - That thread UI needs to surface blockers, descendants, review handoffs, and reply ergonomics clearly enough for humans to guide agent work > - Several small gaps in the issue-thread flow were making review and navigation clunkier than necessary > - This pull request improves the reply composer, descendant/blocker presentation, interaction folding, and review-request handoff plumbing together as one cohesive issue-thread workflow slice > - The benefit is a cleaner operator review loop without changing the broader task model ## What Changed - restored and refined the floating reply composer behavior in the issue thread - folded expired confirmation interactions and improved post-submit thread scrolling behavior - surfaced descendant issue context and inline blocker/paused-assignee notices on the issue detail view - tightened large-board first paint behavior in `IssuesList` - added loose review-request handoffs through the issue execution-policy/update path and covered them with tests ## Verification - `pnpm vitest run ui/src/pages/IssueDetail.test.tsx` - `pnpm vitest run server/src/__tests__/issues-service.test.ts server/src/__tests__/issue-execution-policy.test.ts` - `pnpm exec vitest run --project @paperclipai/ui ui/src/components/IssueChatThread.test.tsx ui/src/components/IssueProperties.test.tsx ui/src/components/IssuesList.test.tsx ui/src/lib/issue-tree.test.ts ui/src/api/issues.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-utils packages/adapter-utils/src/server-utils.test.ts` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/issue-comment-reopen-routes.test.ts -t "coerces executor handoff patches into workflow-controlled review wakes|wakes the return assignee with execution_changes_requested"` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/issue-execution-policy.test.ts server/src/__tests__/issues-service.test.ts` ## Visual Evidence - UI layout changes are covered by the focused issue-thread component and issue-detail tests listed above. Browser screenshots were not attachable from this automated greploop environment, so reviewers should use the running preview for final visual confirmation. ## Risks - Moderate UI-flow risk: these changes touch the issue detail experience in multiple spots, so regressions would most likely show up as thread-layout quirks or incorrect review-handoff behavior > 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-based coding agent with tool use and code execution in the Codex CLI environment ## 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 documented the visual verification path - [ ] 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>
2026-04-24 08:02:45 -05:00
it("lets a reviewer provide loose instructions for the next approval stage", () => {
const reviewStageId = policy.stages[0].id;
const approvalInstructions = "Please decide whether this is ready to ship, with any launch caveats.";
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
reviewRequest: { instructions: "Review the implementation details." },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: "QA signoff complete",
reviewRequest: { instructions: approvalInstructions },
});
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageType: "approval",
currentParticipant: { type: "user", userId: ctoUserId },
reviewRequest: { instructions: approvalInstructions },
});
});
it("approver approves → marks completed (allows done)", () => {
const reviewStageId = policy.stages[0].id;
const approvalStageId = policy.stages[1].id;
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: null,
assigneeUserId: ctoUserId,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: approvalStageId,
currentStageIndex: 1,
currentStageType: "approval",
currentParticipant: { type: "user", userId: ctoUserId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [reviewStageId],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { userId: ctoUserId },
commentBody: "Approved, ship it",
});
expect(result.patch.executionState).toMatchObject({
status: "completed",
completedStageIds: expect.arrayContaining([reviewStageId, approvalStageId]),
lastDecisionOutcome: "approved",
});
expect(result.decision).toMatchObject({
stageId: approvalStageId,
stageType: "approval",
outcome: "approved",
});
// status should NOT be overridden — caller can set done
expect(result.patch.status).toBeUndefined();
});
});
describe("changes requested flow", () => {
const policy = twoStagePolicy();
const reviewStageId = policy.stages[0].id;
it("reviewer requests changes → returns to executor", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "in_progress",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: "Needs another pass on edge cases",
});
expect(result.patch.status).toBe("in_progress");
expect(result.patch.assigneeAgentId).toBe(coderAgentId);
expect(result.patch.executionState).toMatchObject({
status: "changes_requested",
currentStageType: "review",
returnAssignee: { type: "agent", agentId: coderAgentId },
lastDecisionOutcome: "changes_requested",
});
expect(result.decision).toMatchObject({
stageId: reviewStageId,
stageType: "review",
outcome: "changes_requested",
});
});
it("executor re-submits after changes → returns to same review stage", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "changes_requested",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: "changes_requested",
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Fixed edge cases",
});
expect(result.patch.status).toBe("in_review");
expect(result.patch.assigneeAgentId).toBe(qaAgentId);
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageId: reviewStageId,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
});
});
});
describe("review-only policy (no approval stage)", () => {
const policy = reviewOnlyPolicy();
const reviewStageId = policy.stages[0].id;
it("reviewer approval completes the policy", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: "LGTM",
});
expect(result.patch.executionState).toMatchObject({
status: "completed",
completedStageIds: [reviewStageId],
lastDecisionOutcome: "approved",
});
expect(result.decision).toMatchObject({
stageType: "review",
outcome: "approved",
});
});
});
describe("approval-only policy (no review stage)", () => {
const policy = approvalOnlyPolicy();
it("executor completion routes directly to approval", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Done",
});
expect(result.patch.status).toBe("in_review");
expect(result.patch.assigneeUserId).toBe(ctoUserId);
expect(result.patch.executionState).toMatchObject({
status: "pending",
currentStageType: "approval",
});
});
});
describe("access control", () => {
const policy = twoStagePolicy();
const reviewStageId = policy.stages[0].id;
it("non-participant cannot advance the active stage", () => {
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: { assigneeUserId: boardUserId },
actor: { agentId: coderAgentId },
commentBody: "Trying to bypass review",
}),
).toThrow("Only the active reviewer or approver can advance");
});
it("non-participant can still post non-advancing updates", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: undefined,
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Just a note",
});
// No error — just no patch modifications
expect(result.patch).toEqual({});
});
});
describe("comment requirements", () => {
const policy = twoStagePolicy();
const reviewStageId = policy.stages[0].id;
it("approval without comment throws", () => {
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: "",
}),
).toThrow("requires a comment");
});
it("changes requested without comment throws", () => {
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "in_progress",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: null,
}),
).toThrow("requires a comment");
});
it("whitespace-only comment is treated as empty", () => {
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: " ",
}),
).toThrow("requires a comment");
});
});
describe("policy removal mid-flow", () => {
it("clears execution state when policy removed and returns to executor", () => {
// Use a real UUID for currentStageId so parseIssueExecutionState succeeds
const stageId = "aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa";
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: null,
executionState: {
status: "pending",
currentStageId: stageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy: null,
requestedStatus: undefined,
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
});
expect(result.patch.executionState).toBeNull();
expect(result.patch.status).toBe("in_progress");
expect(result.patch.assigneeAgentId).toBe(coderAgentId);
});
it("clears execution state without assignee change when not in_review", () => {
const stageId = "aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa";
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: null,
executionState: {
status: "changes_requested",
currentStageId: stageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: "changes_requested",
},
},
policy: null,
requestedStatus: undefined,
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
});
expect(result.patch.executionState).toBeNull();
// Not in_review, so no status/assignee change
expect(result.patch.status).toBeUndefined();
});
});
describe("reopening from done/cancelled clears state", () => {
it("reopening a done issue clears execution state", () => {
const policy = twoStagePolicy();
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "done",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "completed",
currentStageId: null,
currentStageIndex: null,
currentStageType: null,
currentParticipant: null,
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [policy.stages[0].id, policy.stages[1].id],
lastDecisionId: null,
lastDecisionOutcome: "approved",
},
},
policy,
requestedStatus: "todo",
requestedAssigneePatch: {},
actor: { userId: boardUserId },
});
expect(result.patch.executionState).toBeNull();
});
});
describe("no-op transitions", () => {
const policy = twoStagePolicy();
const reviewStageId = policy.stages[0].id;
it("non-done status change without review context is a no-op", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "blocked",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
});
expect(result.patch).toEqual({});
});
it("coerces a malformed executor in_review patch into the first policy stage", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "in_review",
requestedAssigneePatch: { assigneeUserId: boardUserId },
actor: { agentId: coderAgentId },
});
expect(result.patch).toMatchObject({
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionState: {
status: "pending",
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
},
});
});
it("reasserts the active stage when issue status drifted out of in_review", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "in_progress",
requestedAssigneePatch: { assigneeAgentId: coderAgentId },
actor: { agentId: coderAgentId },
});
expect(result.patch).toMatchObject({
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
},
});
});
it("no policy and no state is a no-op", () => {
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: null,
executionState: null,
},
policy: null,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
});
expect(result.patch).toEqual({});
});
it("does not auto-start workflow when policy is added to an already in_review issue", () => {
const reviewOnly = reviewOnlyPolicy();
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: null,
assigneeUserId: boardUserId,
executionPolicy: null,
executionState: null,
},
policy: reviewOnly,
requestedStatus: undefined,
requestedAssigneePatch: {},
actor: { userId: boardUserId },
});
expect(result.patch).toEqual({});
});
});
describe("multi-participant stages", () => {
it("selects the preferred participant when explicitly requested", () => {
const policy = makePolicy([
{
type: "review",
participants: [
{ type: "agent", agentId: qaAgentId },
{ type: "agent", agentId: ctoAgentId },
],
},
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: { assigneeAgentId: ctoAgentId },
actor: { agentId: coderAgentId },
commentBody: "Ready for review",
});
expect(result.patch.assigneeAgentId).toBe(ctoAgentId);
});
it("falls back to first participant when no preference given", () => {
const policy = makePolicy([
{
type: "review",
participants: [
{ type: "agent", agentId: qaAgentId },
{ type: "agent", agentId: ctoAgentId },
],
},
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Ready for review",
});
expect(result.patch.assigneeAgentId).toBe(qaAgentId);
});
it("excludes the return assignee from participant selection", () => {
const policy = makePolicy([
{
type: "review",
participants: [
{ type: "agent", agentId: coderAgentId },
{ type: "agent", agentId: qaAgentId },
],
},
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Done",
});
// coderAgentId is the returnAssignee, so QA should be selected
expect(result.patch.assigneeAgentId).toBe(qaAgentId);
});
[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
it("skips a self-review-only stage and completes the workflow", () => {
const policy = makePolicy([
{
type: "review",
participants: [{ type: "agent", agentId: coderAgentId }],
},
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Done",
});
expect(result.patch).toMatchObject({
executionState: {
status: "completed",
currentStageType: null,
currentParticipant: null,
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [policy.stages[0].id],
},
});
expect(result.patch.status).toBeUndefined();
expect(result.patch.assigneeAgentId).toBeUndefined();
});
it("skips a self-review-only review stage and advances to approval", () => {
const policy = makePolicy([
{
type: "review",
participants: [{ type: "agent", agentId: coderAgentId }],
},
{
type: "approval",
participants: [{ type: "user", userId: ctoUserId }],
},
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Done",
});
expect(result.patch).toMatchObject({
status: "in_review",
assigneeAgentId: null,
assigneeUserId: ctoUserId,
executionState: {
status: "pending",
currentStageType: "approval",
currentParticipant: { type: "user", userId: ctoUserId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [policy.stages[0].id],
},
});
});
});
describe("changes requested with no return assignee", () => {
it("throws when requesting changes with no return assignee", () => {
const policy = twoStagePolicy();
const reviewStageId = policy.stages[0].id;
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: reviewStageId,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: null,
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "in_progress",
requestedAssigneePatch: {},
actor: { agentId: qaAgentId },
commentBody: "Changes needed",
}),
).toThrow("no return assignee");
});
});
describe("approval stage changes requested → bounces back to executor", () => {
it("approver requests changes during approval stage", () => {
const policy = twoStagePolicy();
const reviewStageId = policy.stages[0].id;
const approvalStageId = policy.stages[1].id;
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: null,
assigneeUserId: ctoUserId,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: approvalStageId,
currentStageIndex: 1,
currentStageType: "approval",
currentParticipant: { type: "user", userId: ctoUserId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [reviewStageId],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy,
requestedStatus: "in_progress",
requestedAssigneePatch: {},
actor: { userId: ctoUserId },
commentBody: "Not happy with the approach, needs rework",
});
expect(result.patch.status).toBe("in_progress");
expect(result.patch.assigneeAgentId).toBe(coderAgentId);
expect(result.patch.executionState).toMatchObject({
status: "changes_requested",
currentStageType: "approval",
lastDecisionOutcome: "changes_requested",
});
expect(result.decision).toMatchObject({
stageId: approvalStageId,
stageType: "approval",
outcome: "changes_requested",
});
});
});
describe("user participants", () => {
it("handles user-type reviewer participant correctly", () => {
const policy = makePolicy([
{ type: "review", participants: [{ type: "user", userId: boardUserId }] },
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: null,
},
policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
commentBody: "Done",
});
expect(result.patch.status).toBe("in_review");
expect(result.patch.assigneeAgentId).toBeNull();
expect(result.patch.assigneeUserId).toBe(boardUserId);
});
});
describe("policy edits while a stage is active", () => {
it("clears the active execution state when its stage is removed from the policy", () => {
const reviewAndApproval = twoStagePolicy();
const approvalOnly = approvalOnlyPolicy();
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: reviewAndApproval,
executionState: {
status: "pending",
currentStageId: reviewAndApproval.stages[0].id,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy: approvalOnly,
requestedStatus: undefined,
requestedAssigneePatch: {},
actor: { userId: boardUserId },
});
expect(result.patch).toMatchObject({
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionState: null,
});
});
it("reassigns the active stage when the current participant is removed", () => {
const policy = makePolicy([
{
type: "review",
participants: [
{ type: "agent", agentId: qaAgentId },
{ type: "agent", agentId: ctoAgentId },
],
},
]);
const updatedPolicy = makePolicy([
{
type: "review",
participants: [{ type: "agent", agentId: ctoAgentId }],
},
]);
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: qaAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "pending",
currentStageId: policy.stages[0].id,
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: qaAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
},
policy: {
...updatedPolicy,
stages: [{ ...updatedPolicy.stages[0], id: policy.stages[0].id }],
},
requestedStatus: undefined,
requestedAssigneePatch: {},
actor: { userId: boardUserId },
});
expect(result.patch).toMatchObject({
status: "in_review",
assigneeAgentId: ctoAgentId,
assigneeUserId: null,
executionState: {
status: "pending",
currentStageId: policy.stages[0].id,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: ctoAgentId },
returnAssignee: { type: "agent", agentId: coderAgentId },
},
});
});
});
[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
describe("monitor policy", () => {
it("schedules a one-shot monitor on an active agent-owned issue", () => {
const policy = normalizeIssueExecutionPolicy({
stages: [],
monitor: {
nextCheckAt: "2026-04-11T12:30:00.000Z",
notes: "Check deployment",
scheduledBy: "board",
},
})!;
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: null,
executionState: null,
monitorAttemptCount: 0,
monitorNextCheckAt: null,
monitorLastTriggeredAt: null,
monitorNotes: null,
monitorScheduledBy: null,
},
policy,
previousPolicy: null,
requestedAssigneePatch: {},
actor: { userId: boardUserId },
monitorExplicitlyUpdated: true,
});
expect(result.patch.monitorNextCheckAt).toEqual(new Date("2026-04-11T12:30:00.000Z"));
expect(result.patch.monitorScheduledBy).toBe("board");
expect(result.patch.executionState).toMatchObject({
status: "idle",
monitor: {
status: "scheduled",
nextCheckAt: "2026-04-11T12:30:00.000Z",
notes: "Check deployment",
scheduledBy: "board",
},
});
});
it("auto-clears a scheduled monitor when the issue moves to done", () => {
const policy = normalizeIssueExecutionPolicy({
stages: [],
monitor: {
nextCheckAt: "2026-04-11T12:30:00.000Z",
notes: "Check deployment",
scheduledBy: "assignee",
},
})!;
const result = applyIssueExecutionPolicyTransition({
issue: {
status: "in_progress",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: policy,
executionState: {
status: "idle",
currentStageId: null,
currentStageIndex: null,
currentStageType: null,
currentParticipant: null,
returnAssignee: null,
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
monitor: {
status: "scheduled",
nextCheckAt: "2026-04-11T12:30:00.000Z",
lastTriggeredAt: null,
attemptCount: 0,
notes: "Check deployment",
scheduledBy: "assignee",
clearedAt: null,
clearReason: null,
},
},
monitorAttemptCount: 0,
monitorNextCheckAt: new Date("2026-04-11T12:30:00.000Z"),
monitorLastTriggeredAt: null,
monitorNotes: "Check deployment",
monitorScheduledBy: "assignee",
},
policy,
previousPolicy: policy,
requestedStatus: "done",
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
});
expect(result.patch.executionPolicy).toBeNull();
expect(result.patch.monitorNextCheckAt).toBeNull();
expect(result.patch.executionState).toMatchObject({
monitor: {
status: "cleared",
clearReason: "done",
},
});
});
it("rejects explicitly scheduling a monitor on an invalid issue state", () => {
const policy = normalizeIssueExecutionPolicy({
stages: [],
monitor: {
nextCheckAt: "2026-04-11T12:30:00.000Z",
notes: "Check deployment",
},
})!;
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "blocked",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: null,
executionState: null,
},
policy,
previousPolicy: null,
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
monitorExplicitlyUpdated: true,
}),
).toThrow("Monitor can only be scheduled");
});
it("rejects explicitly re-arming a monitor after max attempts are exhausted", () => {
const policy = normalizeIssueExecutionPolicy({
stages: [],
monitor: {
nextCheckAt: "2099-04-11T12:30:00.000Z",
maxAttempts: 1,
scheduledBy: "assignee",
},
})!;
expect(() =>
applyIssueExecutionPolicyTransition({
issue: {
status: "in_review",
assigneeAgentId: coderAgentId,
assigneeUserId: null,
executionPolicy: null,
executionState: null,
monitorAttemptCount: 1,
monitorNextCheckAt: null,
monitorLastTriggeredAt: null,
monitorNotes: null,
monitorScheduledBy: "assignee",
},
policy,
previousPolicy: null,
requestedAssigneePatch: {},
actor: { agentId: coderAgentId },
monitorExplicitlyUpdated: true,
}),
).toThrow("Monitor bounds are already exhausted");
});
});
});