[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

@ -47,7 +47,7 @@ import { queueIssueAssignmentWakeup, type IssueAssignmentWakeupDeps } from "./is
import { logActivity } from "./activity-log.js";
const OPEN_ISSUE_STATUSES = ["backlog", "todo", "in_progress", "in_review", "blocked"];
const LIVE_HEARTBEAT_RUN_STATUSES = ["queued", "running"];
const LIVE_HEARTBEAT_RUN_STATUSES = ["queued", "running", "scheduled_retry"];
const TERMINAL_ISSUE_STATUSES = new Set(["done", "cancelled"]);
const MAX_CATCH_UP_RUNS = 25;
const WEEKDAY_INDEX: Record<string, number> = {
@ -320,6 +320,37 @@ function mergeRoutineRunPayload(
};
}
function normalizeRoutineDispatchFingerprintValue(value: unknown): unknown {
if (value === undefined) return null;
if (value == null || typeof value === "string" || typeof value === "number" || typeof value === "boolean") {
return value;
}
if (value instanceof Date) return value.toISOString();
if (Array.isArray(value)) return value.map((item) => normalizeRoutineDispatchFingerprintValue(item));
if (isPlainRecord(value)) {
return Object.fromEntries(
Object.keys(value)
.sort()
.map((key) => [key, normalizeRoutineDispatchFingerprintValue(value[key])]),
);
}
return String(value);
}
function createRoutineDispatchFingerprint(input: {
payload: Record<string, unknown> | null;
projectId: string | null;
assigneeAgentId: string | null;
executionWorkspaceId?: string | null;
executionWorkspacePreference?: string | null;
executionWorkspaceSettings?: Record<string, unknown> | null;
title: string;
description: string | null;
}) {
const canonical = JSON.stringify(normalizeRoutineDispatchFingerprintValue(input));
return crypto.createHash("sha256").update(canonical).digest("hex");
}
function routineUsesWorkspaceBranch(routine: typeof routines.$inferSelect) {
return (routine.variables ?? []).some((variable) => variable.name === WORKSPACE_BRANCH_ROUTINE_VARIABLE)
|| extractRoutineVariableNames([routine.title, routine.description]).includes(WORKSPACE_BRANCH_ROUTINE_VARIABLE);
@ -426,6 +457,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt: routineRuns.triggeredAt,
idempotencyKey: routineRuns.idempotencyKey,
triggerPayload: routineRuns.triggerPayload,
dispatchFingerprint: routineRuns.dispatchFingerprint,
linkedIssueId: routineRuns.linkedIssueId,
coalescedIntoRunId: routineRuns.coalescedIntoRunId,
failureReason: routineRuns.failureReason,
@ -458,6 +490,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt: row.triggeredAt,
idempotencyKey: row.idempotencyKey,
triggerPayload: row.triggerPayload as Record<string, unknown> | null,
dispatchFingerprint: row.dispatchFingerprint,
linkedIssueId: row.linkedIssueId,
coalescedIntoRunId: row.coalescedIntoRunId,
failureReason: row.failureReason,
@ -606,7 +639,22 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
}
}
async function findLiveExecutionIssue(routine: typeof routines.$inferSelect, executor: Db = db) {
function routineExecutionFingerprintCondition(dispatchFingerprint?: string | null) {
if (!dispatchFingerprint) return null;
// The "default" arm preserves coalescing against pre-migration open issues.
// It becomes inert once those legacy routine execution issues drain out.
return or(
eq(issues.originFingerprint, dispatchFingerprint),
eq(issues.originFingerprint, "default"),
);
}
async function findLiveExecutionIssue(
routine: typeof routines.$inferSelect,
executor: Db = db,
dispatchFingerprint?: string | null,
) {
const fingerprintCondition = routineExecutionFingerprintCondition(dispatchFingerprint);
const executionBoundIssue = await executor
.select()
.from(issues)
@ -624,6 +672,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
eq(issues.originId, routine.id),
inArray(issues.status, OPEN_ISSUE_STATUSES),
isNull(issues.hiddenAt),
...(fingerprintCondition ? [fingerprintCondition] : []),
),
)
.orderBy(desc(issues.updatedAt), desc(issues.createdAt))
@ -649,6 +698,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
eq(issues.originId, routine.id),
inArray(issues.status, OPEN_ISSUE_STATUSES),
isNull(issues.hiddenAt),
...(fingerprintCondition ? [fingerprintCondition] : []),
),
)
.orderBy(desc(issues.updatedAt), desc(issues.createdAt))
@ -745,6 +795,16 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
const title = interpolateRoutineTemplate(input.routine.title, allVariables) ?? input.routine.title;
const description = interpolateRoutineTemplate(input.routine.description, allVariables);
const triggerPayload = mergeRoutineRunPayload(input.payload, { ...automaticVariables, ...resolvedVariables });
const dispatchFingerprint = createRoutineDispatchFingerprint({
payload: triggerPayload,
projectId,
assigneeAgentId,
executionWorkspaceId: input.executionWorkspaceId ?? null,
executionWorkspacePreference: input.executionWorkspacePreference ?? null,
executionWorkspaceSettings: input.executionWorkspaceSettings ?? null,
title,
description,
});
const run = await db.transaction(async (tx) => {
const txDb = tx as unknown as Db;
await tx.execute(
@ -782,6 +842,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt,
idempotencyKey: input.idempotencyKey ?? null,
triggerPayload,
dispatchFingerprint,
})
.returning();
@ -791,7 +852,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
let createdIssue: Awaited<ReturnType<typeof issueSvc.create>> | null = null;
try {
const activeIssue = await findLiveExecutionIssue(input.routine, txDb);
const activeIssue = await findLiveExecutionIssue(input.routine, txDb, dispatchFingerprint);
if (activeIssue && input.routine.concurrencyPolicy !== "always_enqueue") {
const status = input.routine.concurrencyPolicy === "skip_if_active" ? "skipped" : "coalesced";
const updated = await finalizeRun(createdRun.id, {
@ -824,6 +885,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
originKind: "routine_execution",
originId: input.routine.id,
originRunId: createdRun.id,
originFingerprint: dispatchFingerprint,
executionWorkspaceId: input.executionWorkspaceId ?? null,
executionWorkspacePreference: input.executionWorkspacePreference ?? null,
executionWorkspaceSettings: input.executionWorkspaceSettings ?? null,
@ -840,7 +902,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
throw error;
}
const existingIssue = await findLiveExecutionIssue(input.routine, txDb);
const existingIssue = await findLiveExecutionIssue(input.routine, txDb, dispatchFingerprint);
if (!existingIssue) throw error;
const status = input.routine.concurrencyPolicy === "skip_if_active" ? "skipped" : "coalesced";
const updated = await finalizeRun(createdRun.id, {
@ -994,6 +1056,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt: routineRuns.triggeredAt,
idempotencyKey: routineRuns.idempotencyKey,
triggerPayload: routineRuns.triggerPayload,
dispatchFingerprint: routineRuns.dispatchFingerprint,
linkedIssueId: routineRuns.linkedIssueId,
coalescedIntoRunId: routineRuns.coalescedIntoRunId,
failureReason: routineRuns.failureReason,
@ -1025,6 +1088,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt: run.triggeredAt,
idempotencyKey: run.idempotencyKey,
triggerPayload: run.triggerPayload as Record<string, unknown> | null,
dispatchFingerprint: run.dispatchFingerprint,
linkedIssueId: run.linkedIssueId,
coalescedIntoRunId: run.coalescedIntoRunId,
failureReason: run.failureReason,
@ -1437,6 +1501,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt: routineRuns.triggeredAt,
idempotencyKey: routineRuns.idempotencyKey,
triggerPayload: routineRuns.triggerPayload,
dispatchFingerprint: routineRuns.dispatchFingerprint,
linkedIssueId: routineRuns.linkedIssueId,
coalescedIntoRunId: routineRuns.coalescedIntoRunId,
failureReason: routineRuns.failureReason,
@ -1468,6 +1533,7 @@ export function routineService(db: Db, deps: { heartbeat?: IssueAssignmentWakeup
triggeredAt: row.triggeredAt,
idempotencyKey: row.idempotencyKey,
triggerPayload: row.triggerPayload as Record<string, unknown> | null,
dispatchFingerprint: row.dispatchFingerprint,
linkedIssueId: row.linkedIssueId,
coalescedIntoRunId: row.coalescedIntoRunId,
failureReason: row.failureReason,