paperclip/server/src/__tests__/heartbeat-stale-queue-invalidation.test.ts

700 lines
22 KiB
TypeScript
Raw Normal View History

import { randomUUID } from "node:crypto";
import { eq, sql } from "drizzle-orm";
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from "vitest";
import {
activityLog,
agents,
agentRuntimeState,
agentWakeupRequests,
companies,
companySkills,
createDb,
documentRevisions,
documents,
heartbeatRunEvents,
heartbeatRuns,
issueComments,
issueDocuments,
issueRelations,
issueTreeHolds,
issues,
} from "@paperclipai/db";
import {
getEmbeddedPostgresTestSupport,
startEmbeddedPostgresTestDatabase,
} from "./helpers/embedded-postgres.js";
[codex] Retry max-turn exhausted heartbeats (#5096) ## Thinking Path > - Paperclip orchestrates AI agents for autonomous companies, and heartbeat execution is the control-plane loop that keeps assigned work moving. > - Max-turn exhaustion is a recoverable local-adapter stop condition for Claude and Gemini agents when a run needs another heartbeat to continue safely. > - The previous behavior could leave max-turn continuation details hard to inspect, and duplicate/stale continuation wakes could keep running after issue state changed. > - The adapter layer also needed to avoid trusting arbitrary stdout/stderr text as scheduler control metadata. > - This pull request adds bounded max-turn continuation scheduling, visible retry state, structured stop metadata handling, and stale/duplicate continuation guards. > - The benefit is safer automatic continuation after max-turn stops, clearer operator visibility, and fewer duplicate or stale agent runs. ## What Changed - Replaces closed PR #4952, whose head repository was deleted. - Rebases the recovered max-turn continuation branch onto current `paperclipai/paperclip:master`. - Adds max-turn continuation scheduling and retry-state plumbing for heartbeat runs. - Adds stale/duplicate continuation suppression when issue status, ownership, or execution locks change. - Normalizes Claude/Gemini max-turn detection around structured stop metadata instead of unstructured stdout/stderr text. - Surfaces max-turn continuation settings and retry visibility in the board UI. - Adds focused server, adapter, and UI tests for max-turn stop metadata, retry scheduling, stale queued-run invalidation, adapter parsing/execution, run ledger display, and agent config patching. ## Verification - `pnpm install --no-frozen-lockfile` to refresh local dependencies after rebasing onto current `master`. - `pnpm run preflight:workspace-links && pnpm exec vitest run server/src/__tests__/claude-local-adapter.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/gemini-local-adapter.test.ts server/src/__tests__/gemini-local-execute.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-stale-queue-invalidation.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/lib/agent-config-patch.test.ts ui/src/lib/runRetryState.test.ts --testTimeout=20000` - `pnpm --filter @paperclipai/adapter-claude-local typecheck && pnpm --filter @paperclipai/adapter-gemini-local typecheck && pnpm --filter @paperclipai/server typecheck && pnpm --filter @paperclipai/ui typecheck` - UI screenshot note: the UI changes are limited to config/ledger state rendering rather than layout changes; component/unit coverage above verifies the rendered behavior. ## Risks - Medium behavior risk: heartbeat retry gating now suppresses max-turn continuations when issue state or execution locks drift, so any callers that relied on stale continuations running will now see cancellation instead. - Low adapter risk: Claude/Gemini unstructured text no longer triggers max-turn scheduler metadata, so only structured stop signals and Gemini exit code 53 are trusted. - No database migrations. > 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 coding agent, GPT-5-class model, tool-enabled local repository editing and command 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 (not applicable: state/default rendering only; covered by component/unit tests) - [x] I have updated relevant documentation to reflect my changes (not applicable: no user-facing command or docs contract changed) - [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 11:30:48 -05:00
import {
MAX_TURN_CONTINUATION_RETRY_REASON,
MAX_TURN_CONTINUATION_WAKE_REASON,
heartbeatService,
} from "../services/heartbeat.ts";
import { runningProcesses } from "../adapters/index.ts";
const mockAdapterExecute = vi.hoisted(() =>
vi.fn(async () => ({
exitCode: 0,
signal: null,
timedOut: false,
errorMessage: null,
summary: "Stale-queue invalidation test run.",
provider: "test",
model: "test-model",
})),
);
vi.mock("../adapters/index.ts", async () => {
const actual = await vi.importActual<typeof import("../adapters/index.ts")>("../adapters/index.ts");
return {
...actual,
getServerAdapter: vi.fn(() => ({
supportsLocalAgentJwt: false,
execute: mockAdapterExecute,
})),
};
});
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
if (!embeddedPostgresSupport.supported) {
console.warn(
`Skipping embedded Postgres heartbeat stale-queue invalidation tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
);
}
async function ensureIssueRelationsTable(db: ReturnType<typeof createDb>) {
await db.execute(sql.raw(`
CREATE TABLE IF NOT EXISTS "issue_relations" (
"id" uuid PRIMARY KEY DEFAULT gen_random_uuid(),
"company_id" uuid NOT NULL,
"issue_id" uuid NOT NULL,
"related_issue_id" uuid NOT NULL,
"type" text NOT NULL,
"created_by_agent_id" uuid,
"created_by_user_id" text,
"created_at" timestamptz NOT NULL DEFAULT now(),
"updated_at" timestamptz NOT NULL DEFAULT now()
);
`));
}
async function waitForCondition(fn: () => Promise<boolean>, timeoutMs = 3_000) {
const deadline = Date.now() + timeoutMs;
while (Date.now() < deadline) {
if (await fn()) return true;
await new Promise((resolve) => setTimeout(resolve, 50));
}
return fn();
}
type SeedOptions = {
agentName?: string;
agentRole?: string;
maxConcurrentRuns?: number;
};
type SeedResult = {
companyId: string;
agentId: string;
};
describeEmbeddedPostgres("heartbeat stale queued-run invalidation", () => {
let db!: ReturnType<typeof createDb>;
let heartbeat!: ReturnType<typeof heartbeatService>;
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
beforeAll(async () => {
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-heartbeat-stale-queue-");
db = createDb(tempDb.connectionString);
heartbeat = heartbeatService(db);
await ensureIssueRelationsTable(db);
}, 20_000);
afterEach(async () => {
mockAdapterExecute.mockReset();
mockAdapterExecute.mockImplementation(async () => ({
exitCode: 0,
signal: null,
timedOut: false,
errorMessage: null,
summary: "Stale-queue invalidation test run.",
provider: "test",
model: "test-model",
}));
runningProcesses.clear();
let idlePolls = 0;
for (let attempt = 0; attempt < 100; attempt += 1) {
const runs = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns);
const hasActiveRun = runs.some((run) => run.status === "queued" || run.status === "running");
if (!hasActiveRun) {
idlePolls += 1;
if (idlePolls >= 3) break;
} else {
idlePolls = 0;
}
await new Promise((resolve) => setTimeout(resolve, 50));
}
await new Promise((resolve) => setTimeout(resolve, 50));
await db.delete(companySkills);
await db.delete(issueComments);
await db.delete(issueDocuments);
await db.delete(documentRevisions);
await db.delete(documents);
await db.delete(issueRelations);
await db.delete(issueTreeHolds);
await db.delete(issues);
await db.delete(heartbeatRunEvents);
await db.delete(activityLog);
await db.delete(heartbeatRuns);
await db.delete(agentWakeupRequests);
await db.delete(agentRuntimeState);
await db.delete(agents);
await db.delete(companies);
});
afterAll(async () => {
await tempDb?.cleanup();
});
async function seedCompanyAndAgent(opts: SeedOptions = {}): Promise<SeedResult> {
const companyId = randomUUID();
const agentId = 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: opts.agentName ?? "ClaudeCoder",
role: opts.agentRole ?? "engineer",
status: "active",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {
heartbeat: {
wakeOnDemand: true,
maxConcurrentRuns: opts.maxConcurrentRuns ?? 1,
},
},
permissions: {},
});
return { companyId, agentId };
}
async function seedQueuedRun(input: {
companyId: string;
agentId: string;
issueId: string;
wakeReason: string;
contextExtras?: Record<string, unknown>;
invocationSource?: "assignment" | "automation";
[codex] Retry max-turn exhausted heartbeats (#5096) ## Thinking Path > - Paperclip orchestrates AI agents for autonomous companies, and heartbeat execution is the control-plane loop that keeps assigned work moving. > - Max-turn exhaustion is a recoverable local-adapter stop condition for Claude and Gemini agents when a run needs another heartbeat to continue safely. > - The previous behavior could leave max-turn continuation details hard to inspect, and duplicate/stale continuation wakes could keep running after issue state changed. > - The adapter layer also needed to avoid trusting arbitrary stdout/stderr text as scheduler control metadata. > - This pull request adds bounded max-turn continuation scheduling, visible retry state, structured stop metadata handling, and stale/duplicate continuation guards. > - The benefit is safer automatic continuation after max-turn stops, clearer operator visibility, and fewer duplicate or stale agent runs. ## What Changed - Replaces closed PR #4952, whose head repository was deleted. - Rebases the recovered max-turn continuation branch onto current `paperclipai/paperclip:master`. - Adds max-turn continuation scheduling and retry-state plumbing for heartbeat runs. - Adds stale/duplicate continuation suppression when issue status, ownership, or execution locks change. - Normalizes Claude/Gemini max-turn detection around structured stop metadata instead of unstructured stdout/stderr text. - Surfaces max-turn continuation settings and retry visibility in the board UI. - Adds focused server, adapter, and UI tests for max-turn stop metadata, retry scheduling, stale queued-run invalidation, adapter parsing/execution, run ledger display, and agent config patching. ## Verification - `pnpm install --no-frozen-lockfile` to refresh local dependencies after rebasing onto current `master`. - `pnpm run preflight:workspace-links && pnpm exec vitest run server/src/__tests__/claude-local-adapter.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/gemini-local-adapter.test.ts server/src/__tests__/gemini-local-execute.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-stale-queue-invalidation.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/lib/agent-config-patch.test.ts ui/src/lib/runRetryState.test.ts --testTimeout=20000` - `pnpm --filter @paperclipai/adapter-claude-local typecheck && pnpm --filter @paperclipai/adapter-gemini-local typecheck && pnpm --filter @paperclipai/server typecheck && pnpm --filter @paperclipai/ui typecheck` - UI screenshot note: the UI changes are limited to config/ledger state rendering rather than layout changes; component/unit coverage above verifies the rendered behavior. ## Risks - Medium behavior risk: heartbeat retry gating now suppresses max-turn continuations when issue state or execution locks drift, so any callers that relied on stale continuations running will now see cancellation instead. - Low adapter risk: Claude/Gemini unstructured text no longer triggers max-turn scheduler metadata, so only structured stop signals and Gemini exit code 53 are trusted. - No database migrations. > 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 coding agent, GPT-5-class model, tool-enabled local repository editing and command 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 (not applicable: state/default rendering only; covered by component/unit tests) - [x] I have updated relevant documentation to reflect my changes (not applicable: no user-facing command or docs contract changed) - [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 11:30:48 -05:00
scheduledRetryReason?: string | null;
}) {
const wakeupRequestId = randomUUID();
const runId = randomUUID();
await db.insert(agentWakeupRequests).values({
id: wakeupRequestId,
companyId: input.companyId,
agentId: input.agentId,
source: input.invocationSource ?? "assignment",
triggerDetail: "system",
reason: input.wakeReason,
payload: { issueId: input.issueId },
status: "queued",
});
await db.insert(heartbeatRuns).values({
id: runId,
companyId: input.companyId,
agentId: input.agentId,
invocationSource: input.invocationSource ?? "assignment",
triggerDetail: "system",
status: "queued",
wakeupRequestId,
[codex] Retry max-turn exhausted heartbeats (#5096) ## Thinking Path > - Paperclip orchestrates AI agents for autonomous companies, and heartbeat execution is the control-plane loop that keeps assigned work moving. > - Max-turn exhaustion is a recoverable local-adapter stop condition for Claude and Gemini agents when a run needs another heartbeat to continue safely. > - The previous behavior could leave max-turn continuation details hard to inspect, and duplicate/stale continuation wakes could keep running after issue state changed. > - The adapter layer also needed to avoid trusting arbitrary stdout/stderr text as scheduler control metadata. > - This pull request adds bounded max-turn continuation scheduling, visible retry state, structured stop metadata handling, and stale/duplicate continuation guards. > - The benefit is safer automatic continuation after max-turn stops, clearer operator visibility, and fewer duplicate or stale agent runs. ## What Changed - Replaces closed PR #4952, whose head repository was deleted. - Rebases the recovered max-turn continuation branch onto current `paperclipai/paperclip:master`. - Adds max-turn continuation scheduling and retry-state plumbing for heartbeat runs. - Adds stale/duplicate continuation suppression when issue status, ownership, or execution locks change. - Normalizes Claude/Gemini max-turn detection around structured stop metadata instead of unstructured stdout/stderr text. - Surfaces max-turn continuation settings and retry visibility in the board UI. - Adds focused server, adapter, and UI tests for max-turn stop metadata, retry scheduling, stale queued-run invalidation, adapter parsing/execution, run ledger display, and agent config patching. ## Verification - `pnpm install --no-frozen-lockfile` to refresh local dependencies after rebasing onto current `master`. - `pnpm run preflight:workspace-links && pnpm exec vitest run server/src/__tests__/claude-local-adapter.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/gemini-local-adapter.test.ts server/src/__tests__/gemini-local-execute.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-stale-queue-invalidation.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/lib/agent-config-patch.test.ts ui/src/lib/runRetryState.test.ts --testTimeout=20000` - `pnpm --filter @paperclipai/adapter-claude-local typecheck && pnpm --filter @paperclipai/adapter-gemini-local typecheck && pnpm --filter @paperclipai/server typecheck && pnpm --filter @paperclipai/ui typecheck` - UI screenshot note: the UI changes are limited to config/ledger state rendering rather than layout changes; component/unit coverage above verifies the rendered behavior. ## Risks - Medium behavior risk: heartbeat retry gating now suppresses max-turn continuations when issue state or execution locks drift, so any callers that relied on stale continuations running will now see cancellation instead. - Low adapter risk: Claude/Gemini unstructured text no longer triggers max-turn scheduler metadata, so only structured stop signals and Gemini exit code 53 are trusted. - No database migrations. > 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 coding agent, GPT-5-class model, tool-enabled local repository editing and command 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 (not applicable: state/default rendering only; covered by component/unit tests) - [x] I have updated relevant documentation to reflect my changes (not applicable: no user-facing command or docs contract changed) - [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 11:30:48 -05:00
scheduledRetryReason: input.scheduledRetryReason ?? null,
contextSnapshot: {
issueId: input.issueId,
wakeReason: input.wakeReason,
...(input.contextExtras ?? {}),
},
});
await db
.update(agentWakeupRequests)
.set({ runId })
.where(eq(agentWakeupRequests.id, wakeupRequestId));
return { runId, wakeupRequestId };
}
it("cancels queued runs when the issue assignee changes before the run starts", async () => {
const { companyId, agentId } = await seedCompanyAndAgent({ agentName: "OriginalCoder" });
const replacementAgentId = randomUUID();
await db.insert(agents).values({
id: replacementAgentId,
companyId,
name: "ReplacementCoder",
role: "engineer",
status: "active",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {
heartbeat: {
wakeOnDemand: true,
maxConcurrentRuns: 1,
},
},
permissions: {},
});
const issueId = randomUUID();
await db.insert(issues).values({
id: issueId,
companyId,
title: "Reassigned task",
status: "in_progress",
priority: "high",
assigneeAgentId: replacementAgentId,
});
const { runId, wakeupRequestId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: "issue_assigned",
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "cancelled";
});
const [run, wakeup] = await Promise.all([
db
.select({
status: heartbeatRuns.status,
errorCode: heartbeatRuns.errorCode,
resultJson: heartbeatRuns.resultJson,
})
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null),
db
.select({ status: agentWakeupRequests.status, error: agentWakeupRequests.error })
.from(agentWakeupRequests)
.where(eq(agentWakeupRequests.id, wakeupRequestId))
.then((rows) => rows[0] ?? null),
]);
expect(run?.status).toBe("cancelled");
expect(run?.errorCode).toBe("issue_assignee_changed");
expect(run?.resultJson).toMatchObject({ stopReason: "issue_assignee_changed" });
expect(wakeup?.status).toBe("skipped");
expect(wakeup?.error).toContain("assignee changed");
expect(mockAdapterExecute).not.toHaveBeenCalled();
});
it("cancels queued runs when the issue reaches a terminal status before the run starts", async () => {
const { companyId, agentId } = await seedCompanyAndAgent();
const issueId = randomUUID();
await db.insert(issues).values({
id: issueId,
companyId,
title: "Already-completed task",
status: "done",
priority: "medium",
assigneeAgentId: agentId,
});
const { runId, wakeupRequestId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: "issue_assigned",
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "cancelled";
});
const [run, wakeup] = await Promise.all([
db
.select({ status: heartbeatRuns.status, errorCode: heartbeatRuns.errorCode })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null),
db
.select({ status: agentWakeupRequests.status })
.from(agentWakeupRequests)
.where(eq(agentWakeupRequests.id, wakeupRequestId))
.then((rows) => rows[0] ?? null),
]);
expect(run?.status).toBe("cancelled");
expect(run?.errorCode).toBe("issue_terminal_status");
expect(wakeup?.status).toBe("skipped");
expect(mockAdapterExecute).not.toHaveBeenCalled();
});
[codex] Retry max-turn exhausted heartbeats (#5096) ## Thinking Path > - Paperclip orchestrates AI agents for autonomous companies, and heartbeat execution is the control-plane loop that keeps assigned work moving. > - Max-turn exhaustion is a recoverable local-adapter stop condition for Claude and Gemini agents when a run needs another heartbeat to continue safely. > - The previous behavior could leave max-turn continuation details hard to inspect, and duplicate/stale continuation wakes could keep running after issue state changed. > - The adapter layer also needed to avoid trusting arbitrary stdout/stderr text as scheduler control metadata. > - This pull request adds bounded max-turn continuation scheduling, visible retry state, structured stop metadata handling, and stale/duplicate continuation guards. > - The benefit is safer automatic continuation after max-turn stops, clearer operator visibility, and fewer duplicate or stale agent runs. ## What Changed - Replaces closed PR #4952, whose head repository was deleted. - Rebases the recovered max-turn continuation branch onto current `paperclipai/paperclip:master`. - Adds max-turn continuation scheduling and retry-state plumbing for heartbeat runs. - Adds stale/duplicate continuation suppression when issue status, ownership, or execution locks change. - Normalizes Claude/Gemini max-turn detection around structured stop metadata instead of unstructured stdout/stderr text. - Surfaces max-turn continuation settings and retry visibility in the board UI. - Adds focused server, adapter, and UI tests for max-turn stop metadata, retry scheduling, stale queued-run invalidation, adapter parsing/execution, run ledger display, and agent config patching. ## Verification - `pnpm install --no-frozen-lockfile` to refresh local dependencies after rebasing onto current `master`. - `pnpm run preflight:workspace-links && pnpm exec vitest run server/src/__tests__/claude-local-adapter.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/gemini-local-adapter.test.ts server/src/__tests__/gemini-local-execute.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-stale-queue-invalidation.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/lib/agent-config-patch.test.ts ui/src/lib/runRetryState.test.ts --testTimeout=20000` - `pnpm --filter @paperclipai/adapter-claude-local typecheck && pnpm --filter @paperclipai/adapter-gemini-local typecheck && pnpm --filter @paperclipai/server typecheck && pnpm --filter @paperclipai/ui typecheck` - UI screenshot note: the UI changes are limited to config/ledger state rendering rather than layout changes; component/unit coverage above verifies the rendered behavior. ## Risks - Medium behavior risk: heartbeat retry gating now suppresses max-turn continuations when issue state or execution locks drift, so any callers that relied on stale continuations running will now see cancellation instead. - Low adapter risk: Claude/Gemini unstructured text no longer triggers max-turn scheduler metadata, so only structured stop signals and Gemini exit code 53 are trusted. - No database migrations. > 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 coding agent, GPT-5-class model, tool-enabled local repository editing and command 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 (not applicable: state/default rendering only; covered by component/unit tests) - [x] I have updated relevant documentation to reflect my changes (not applicable: no user-facing command or docs contract changed) - [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 11:30:48 -05:00
it("cancels queued max-turn continuations when the issue is no longer in_progress before the run starts", async () => {
const { companyId, agentId } = await seedCompanyAndAgent();
const issueId = randomUUID();
await db.insert(issues).values({
id: issueId,
companyId,
title: "Parked max-turn continuation",
status: "blocked",
priority: "medium",
assigneeAgentId: agentId,
});
const { runId, wakeupRequestId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: MAX_TURN_CONTINUATION_WAKE_REASON,
invocationSource: "automation",
scheduledRetryReason: MAX_TURN_CONTINUATION_RETRY_REASON,
contextExtras: {
retryReason: MAX_TURN_CONTINUATION_RETRY_REASON,
},
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "cancelled";
});
const [run, wakeup] = await Promise.all([
db
.select({
status: heartbeatRuns.status,
errorCode: heartbeatRuns.errorCode,
resultJson: heartbeatRuns.resultJson,
})
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null),
db
.select({ status: agentWakeupRequests.status, error: agentWakeupRequests.error })
.from(agentWakeupRequests)
.where(eq(agentWakeupRequests.id, wakeupRequestId))
.then((rows) => rows[0] ?? null),
]);
expect(run?.status).toBe("cancelled");
expect(run?.errorCode).toBe("issue_not_in_progress");
expect(run?.resultJson).toMatchObject({ stopReason: "issue_not_in_progress" });
expect(wakeup?.status).toBe("skipped");
expect(wakeup?.error).toContain("no longer in_progress");
expect(mockAdapterExecute).not.toHaveBeenCalled();
});
it("cancels queued max-turn continuations when another continuation owns the issue lock", async () => {
const { companyId, agentId } = await seedCompanyAndAgent();
const issueId = randomUUID();
const lockOwnerRunId = randomUUID();
await db.insert(heartbeatRuns).values({
id: lockOwnerRunId,
companyId,
agentId,
invocationSource: "automation",
triggerDetail: "system",
status: "scheduled_retry",
scheduledRetryReason: MAX_TURN_CONTINUATION_RETRY_REASON,
scheduledRetryAttempt: 1,
scheduledRetryAt: new Date("2026-04-20T12:00:00.000Z"),
contextSnapshot: {
issueId,
wakeReason: MAX_TURN_CONTINUATION_WAKE_REASON,
retryReason: MAX_TURN_CONTINUATION_RETRY_REASON,
},
});
await db.insert(issues).values({
id: issueId,
companyId,
title: "Duplicate max-turn continuation",
status: "in_progress",
priority: "medium",
assigneeAgentId: agentId,
executionRunId: lockOwnerRunId,
executionAgentNameKey: "claudecoder",
executionLockedAt: new Date("2026-04-20T11:59:00.000Z"),
});
const { runId, wakeupRequestId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: MAX_TURN_CONTINUATION_WAKE_REASON,
invocationSource: "automation",
scheduledRetryReason: MAX_TURN_CONTINUATION_RETRY_REASON,
contextExtras: {
retryReason: MAX_TURN_CONTINUATION_RETRY_REASON,
},
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "cancelled";
});
const [run, wakeup, issue] = await Promise.all([
db
.select({
status: heartbeatRuns.status,
errorCode: heartbeatRuns.errorCode,
resultJson: heartbeatRuns.resultJson,
})
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null),
db
.select({ status: agentWakeupRequests.status, error: agentWakeupRequests.error })
.from(agentWakeupRequests)
.where(eq(agentWakeupRequests.id, wakeupRequestId))
.then((rows) => rows[0] ?? null),
db
.select({ executionRunId: issues.executionRunId })
.from(issues)
.where(eq(issues.id, issueId))
.then((rows) => rows[0] ?? null),
]);
expect(run?.status).toBe("cancelled");
expect(run?.errorCode).toBe("issue_execution_lock_changed");
expect(run?.resultJson).toMatchObject({ stopReason: "issue_execution_lock_changed" });
expect(wakeup?.status).toBe("skipped");
expect(wakeup?.error).toContain("execution lock");
expect(issue?.executionRunId).toBe(lockOwnerRunId);
expect(mockAdapterExecute).not.toHaveBeenCalled();
});
it("cancels queued in_review runs when the current participant changes before the run starts", async () => {
const { companyId, agentId } = await seedCompanyAndAgent();
const otherAgentId = randomUUID();
await db.insert(agents).values({
id: otherAgentId,
companyId,
name: "ReviewerAgent",
role: "qa",
status: "active",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: { heartbeat: { wakeOnDemand: true, maxConcurrentRuns: 1 } },
permissions: {},
});
const issueId = randomUUID();
await db.insert(issues).values({
id: issueId,
companyId,
title: "In-review task now owned by reviewer",
status: "in_review",
priority: "medium",
assigneeAgentId: agentId,
executionState: {
status: "pending",
currentStageId: randomUUID(),
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: otherAgentId, userId: null },
returnAssignee: { type: "agent", agentId, userId: null },
reviewRequest: null,
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
});
const { runId, wakeupRequestId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: "issue_assigned",
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "cancelled";
});
const [run, wakeup] = await Promise.all([
db
.select({
status: heartbeatRuns.status,
errorCode: heartbeatRuns.errorCode,
resultJson: heartbeatRuns.resultJson,
})
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null),
db
.select({ status: agentWakeupRequests.status, error: agentWakeupRequests.error })
.from(agentWakeupRequests)
.where(eq(agentWakeupRequests.id, wakeupRequestId))
.then((rows) => rows[0] ?? null),
]);
expect(run?.status).toBe("cancelled");
expect(run?.errorCode).toBe("issue_review_participant_changed");
expect(run?.resultJson).toMatchObject({ stopReason: "issue_review_participant_changed" });
expect(wakeup?.status).toBe("skipped");
expect(wakeup?.error).toContain("in-review participant changed");
expect(mockAdapterExecute).not.toHaveBeenCalled();
});
it("still runs comment-driven wakes on in_review issues even when the agent is no longer the current participant", async () => {
const { companyId, agentId } = await seedCompanyAndAgent();
const otherAgentId = randomUUID();
await db.insert(agents).values({
id: otherAgentId,
companyId,
name: "ReviewerAgent",
role: "qa",
status: "active",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: { heartbeat: { wakeOnDemand: true, maxConcurrentRuns: 1 } },
permissions: {},
});
const issueId = randomUUID();
const commentId = randomUUID();
await db.insert(issues).values({
id: issueId,
companyId,
title: "In-review task with comment feedback",
status: "in_review",
priority: "medium",
assigneeAgentId: agentId,
executionState: {
status: "pending",
currentStageId: randomUUID(),
currentStageIndex: 0,
currentStageType: "review",
currentParticipant: { type: "agent", agentId: otherAgentId, userId: null },
returnAssignee: { type: "agent", agentId, userId: null },
reviewRequest: null,
completedStageIds: [],
lastDecisionId: null,
lastDecisionOutcome: null,
},
});
await db.insert(issueComments).values({
id: commentId,
companyId,
issueId,
authorAgentId: otherAgentId,
body: "Review feedback comment",
});
const { runId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: "issue_commented",
invocationSource: "automation",
contextExtras: {
commentId,
wakeCommentId: commentId,
source: "issue.comment",
},
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "succeeded";
});
const run = await db
.select({ status: heartbeatRuns.status, errorCode: heartbeatRuns.errorCode })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
expect(run?.status).toBe("succeeded");
expect(run?.errorCode).toBeNull();
});
it("baseline: runs queued runs when the issue is in_progress with the same assignee", async () => {
const { companyId, agentId } = await seedCompanyAndAgent();
const issueId = randomUUID();
await db.insert(issues).values({
id: issueId,
companyId,
title: "Still actionable",
status: "in_progress",
priority: "medium",
assigneeAgentId: agentId,
});
const { runId } = await seedQueuedRun({
companyId,
agentId,
issueId,
wakeReason: "issue_assigned",
});
await heartbeat.resumeQueuedRuns();
await waitForCondition(async () => {
const run = await db
.select({ status: heartbeatRuns.status })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
return run?.status === "succeeded";
});
const run = await db
.select({ status: heartbeatRuns.status, errorCode: heartbeatRuns.errorCode })
.from(heartbeatRuns)
.where(eq(heartbeatRuns.id, runId))
.then((rows) => rows[0] ?? null);
expect(run?.status).toBe("succeeded");
expect(run?.errorCode).toBeNull();
expect(mockAdapterExecute).toHaveBeenCalledTimes(1);
});
});