[codex] Harden heartbeat scheduling and runtime controls (#4223)

## Thinking Path

> - Paperclip orchestrates AI agents through issue checkout, heartbeat
runs, routines, and auditable control-plane state
> - The runtime path has to recover from lost local processes, transient
adapter failures, blocked dependencies, and routine coalescing without
stranding work
> - The existing branch carried several reliability fixes across
heartbeat scheduling, issue runtime controls, routine dispatch, and
operator-facing run state
> - These changes belong together because they share backend contracts,
migrations, and runtime status semantics
> - This pull request groups the control-plane/runtime slice so it can
merge independently from board UI polish and adapter sandbox work
> - The benefit is safer heartbeat recovery, clearer runtime controls,
and more predictable recurring execution behavior

## What Changed

- Adds bounded heartbeat retry scheduling, scheduled retry state, and
Codex transient failure recovery handling.
- Tightens heartbeat process recovery, blocker wake behavior, issue
comment wake handling, routine dispatch coalescing, and
activity/dashboard bounds.
- Adds runtime-control MCP tools and Paperclip skill docs for issue
workspace runtime management.
- Adds migrations `0061_lively_thor_girl.sql` and
`0062_routine_run_dispatch_fingerprint.sql`.
- Surfaces retry state in run ledger/agent UI and keeps related shared
types synchronized.

## Verification

- `pnpm exec vitest run
server/src/__tests__/heartbeat-retry-scheduling.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/routines-service.test.ts`
- `pnpm exec vitest run src/tools.test.ts` from `packages/mcp-server`

## Risks

- Medium risk: this touches heartbeat recovery and routine dispatch,
which are central execution paths.
- Migration order matters if split branches land out of order: merge
this PR before branches that assume the new runtime/routine fields.
- Runtime retry behavior should be watched in CI and in local operator
smoke tests because it changes how transient failures are resumed.

> 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 runtime, shell/git tool use
enabled. Exact hosted model build and context window are not exposed in
this Paperclip heartbeat 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
- [ ] 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
This commit is contained in:
Dotta 2026-04-21 12:24:11 -05:00 committed by GitHub
parent ab9051b595
commit 09d0678840
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
61 changed files with 17622 additions and 456 deletions

View file

@ -1,11 +1,9 @@
import { useEffect, useMemo, useState } from "react";
import { useQuery } from "@tanstack/react-query";
import type { ActivityEvent, Agent } from "@paperclipai/shared";
import { activityApi } from "../api/activity";
import { accessApi } from "../api/access";
import { agentsApi } from "../api/agents";
import { issuesApi } from "../api/issues";
import { projectsApi } from "../api/projects";
import { goalsApi } from "../api/goals";
import { buildCompanyUserProfileMap } from "../lib/company-members";
import { useCompany } from "../context/CompanyContext";
import { useBreadcrumbs } from "../context/BreadcrumbContext";
@ -21,7 +19,29 @@ import {
SelectValue,
} from "@/components/ui/select";
import { History } from "lucide-react";
import type { Agent } from "@paperclipai/shared";
const ACTIVITY_PAGE_LIMIT = 200;
function detailString(event: ActivityEvent, ...keys: string[]) {
const details = event.details;
for (const key of keys) {
const value = details?.[key];
if (typeof value === "string" && value.trim()) return value;
}
return null;
}
function activityEntityName(event: ActivityEvent) {
if (event.entityType === "issue") return detailString(event, "identifier", "issueIdentifier");
if (event.entityType === "project") return detailString(event, "projectName", "name", "title");
if (event.entityType === "goal") return detailString(event, "goalTitle", "title", "name");
return detailString(event, "name", "title");
}
function activityEntityTitle(event: ActivityEvent) {
if (event.entityType === "issue") return detailString(event, "issueTitle", "title");
return null;
}
export function Activity() {
const { selectedCompanyId } = useCompany();
@ -33,8 +53,8 @@ export function Activity() {
}, [setBreadcrumbs]);
const { data, isLoading, error } = useQuery({
queryKey: queryKeys.activity(selectedCompanyId!),
queryFn: () => activityApi.list(selectedCompanyId!),
queryKey: [...queryKeys.activity(selectedCompanyId!), { limit: ACTIVITY_PAGE_LIMIT }],
queryFn: () => activityApi.list(selectedCompanyId!, { limit: ACTIVITY_PAGE_LIMIT }),
enabled: !!selectedCompanyId,
});
@ -44,24 +64,6 @@ export function Activity() {
enabled: !!selectedCompanyId,
});
const { data: issues } = useQuery({
queryKey: queryKeys.issues.list(selectedCompanyId!),
queryFn: () => issuesApi.list(selectedCompanyId!),
enabled: !!selectedCompanyId,
});
const { data: projects } = useQuery({
queryKey: queryKeys.projects.list(selectedCompanyId!),
queryFn: () => projectsApi.list(selectedCompanyId!),
enabled: !!selectedCompanyId,
});
const { data: goals } = useQuery({
queryKey: queryKeys.goals.list(selectedCompanyId!),
queryFn: () => goalsApi.list(selectedCompanyId!),
enabled: !!selectedCompanyId,
});
const { data: companyMembers } = useQuery({
queryKey: queryKeys.access.companyUserDirectory(selectedCompanyId!),
queryFn: () => accessApi.listUserDirectory(selectedCompanyId!),
@ -81,18 +83,22 @@ export function Activity() {
const entityNameMap = useMemo(() => {
const map = new Map<string, string>();
for (const i of issues ?? []) map.set(`issue:${i.id}`, i.identifier ?? i.id.slice(0, 8));
for (const a of agents ?? []) map.set(`agent:${a.id}`, a.name);
for (const p of projects ?? []) map.set(`project:${p.id}`, p.name);
for (const g of goals ?? []) map.set(`goal:${g.id}`, g.title);
for (const event of data ?? []) {
const name = activityEntityName(event);
if (name) map.set(`${event.entityType}:${event.entityId}`, name);
}
return map;
}, [issues, agents, projects, goals]);
}, [data, agents]);
const entityTitleMap = useMemo(() => {
const map = new Map<string, string>();
for (const i of issues ?? []) map.set(`issue:${i.id}`, i.title);
for (const event of data ?? []) {
const title = activityEntityTitle(event);
if (title) map.set(`${event.entityType}:${event.entityId}`, title);
}
return map;
}, [issues]);
}, [data]);
if (!selectedCompanyId) {
return <EmptyState icon={History} message="Select a company to view activity." />;

View file

@ -43,6 +43,7 @@ import { PackageFileTree, buildFileTree } from "../components/PackageFileTree";
import { ScrollToBottom } from "../components/ScrollToBottom";
import { formatCents, formatDate, relativeTime, formatTokens, visibleRunCostUsd } from "../lib/utils";
import { cn } from "../lib/utils";
import { describeRunRetryState } from "../lib/runRetryState";
import { Button } from "@/components/ui/button";
import { Skeleton } from "@/components/ui/skeleton";
import { Tabs } from "@/components/ui/tabs";
@ -104,6 +105,7 @@ const runStatusIcons: Record<string, { icon: typeof CheckCircle2; color: string
failed: { icon: XCircle, color: "text-red-600 dark:text-red-400" },
running: { icon: Loader2, color: "text-cyan-600 dark:text-cyan-400" },
queued: { icon: Clock, color: "text-yellow-600 dark:text-yellow-400" },
scheduled_retry: { icon: Clock, color: "text-sky-600 dark:text-sky-400" },
timed_out: { icon: Timer, color: "text-orange-600 dark:text-orange-400" },
cancelled: { icon: Slash, color: "text-neutral-500 dark:text-neutral-400" },
};
@ -2342,26 +2344,39 @@ function PromptsTab({
</p>
</div>
</div>
{selectedFileExists && !selectedFileSummary?.deprecated && selectedOrEntryFile !== currentEntryFile && (
<Button
type="button"
size="sm"
variant="outline"
onClick={() => {
if (confirm(`Delete ${selectedOrEntryFile}?`)) {
deleteFile.mutate(selectedOrEntryFile, {
onSuccess: () => {
setSelectedFile(currentEntryFile);
setDraft(null);
},
});
}
}}
disabled={deleteFile.isPending}
>
Delete
</Button>
)}
<div className="flex items-center gap-2">
{!fileLoading && (
<CopyText
text={displayValue}
ariaLabel="Copy instructions file as markdown"
title="Copy as markdown"
copiedLabel="Copied"
className="inline-flex h-8 w-8 items-center justify-center rounded-md border border-border text-muted-foreground hover:bg-accent hover:text-foreground"
>
<Copy className="h-3.5 w-3.5" />
</CopyText>
)}
{selectedFileExists && !selectedFileSummary?.deprecated && selectedOrEntryFile !== currentEntryFile && (
<Button
type="button"
size="sm"
variant="outline"
onClick={() => {
if (confirm(`Delete ${selectedOrEntryFile}?`)) {
deleteFile.mutate(selectedOrEntryFile, {
onSuccess: () => {
setSelectedFile(currentEntryFile);
setDraft(null);
},
});
}
}}
disabled={deleteFile.isPending}
>
Delete
</Button>
)}
</div>
</div>
{selectedFileExists && fileLoading && !selectedFileDetail ? (
@ -3141,6 +3156,7 @@ function RunDetail({ run: initialRun, agentRouteId, adapterType, adapterConfig }
const sessionChanged = run.sessionIdBefore && run.sessionIdAfter && run.sessionIdBefore !== run.sessionIdAfter;
const sessionId = run.sessionIdAfter || run.sessionIdBefore;
const hasNonZeroExit = run.exitCode !== null && run.exitCode !== 0;
const retryState = describeRunRetryState(run);
return (
<div className="space-y-4 min-w-0">
@ -3295,6 +3311,30 @@ function RunDetail({ run: initialRun, agentRouteId, adapterType, adapterConfig }
{run.signal && <span className="text-muted-foreground ml-1">(signal: {run.signal})</span>}
</div>
)}
{retryState && (
<div className="rounded-md border border-border/70 bg-accent/20 px-3 py-2 text-xs leading-5">
<div className="flex flex-wrap items-center gap-2">
<span
className={cn(
"rounded-md border px-1.5 py-0.5 text-[11px] font-medium",
retryState.tone,
)}
>
{retryState.badgeLabel}
</span>
{retryState.retryOfRunId ? (
<Link
to={`/agents/${agentRouteId}/runs/${retryState.retryOfRunId}`}
className="font-mono text-foreground hover:underline"
>
{retryState.retryOfRunId.slice(0, 8)}
</Link>
) : null}
</div>
{retryState.detail ? <p className="mt-2 text-muted-foreground">{retryState.detail}</p> : null}
{retryState.secondary ? <p className="text-muted-foreground">{retryState.secondary}</p> : null}
</div>
)}
</div>
{/* Right column: metrics */}

View file

@ -27,6 +27,8 @@ import { PageSkeleton } from "../components/PageSkeleton";
import type { Agent, Issue } from "@paperclipai/shared";
import { PluginSlotOutlet } from "@/plugins/slots";
const DASHBOARD_ACTIVITY_LIMIT = 10;
function getRecentIssues(issues: Issue[]): Issue[] {
return [...issues]
.sort((a, b) => new Date(b.updatedAt).getTime() - new Date(a.updatedAt).getTime());
@ -58,8 +60,8 @@ export function Dashboard() {
});
const { data: activity } = useQuery({
queryKey: queryKeys.activity(selectedCompanyId!),
queryFn: () => activityApi.list(selectedCompanyId!),
queryKey: [...queryKeys.activity(selectedCompanyId!), { limit: DASHBOARD_ACTIVITY_LIMIT }],
queryFn: () => activityApi.list(selectedCompanyId!, { limit: DASHBOARD_ACTIVITY_LIMIT }),
enabled: !!selectedCompanyId,
});