paperclip/server/src/routes/activity.ts
Dotta 09d0678840
[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
2026-04-21 12:24:11 -05:00

98 lines
3.2 KiB
TypeScript

import { Router } from "express";
import { z } from "zod";
import type { Db } from "@paperclipai/db";
import { validate } from "../middleware/validate.js";
import { activityService, normalizeActivityLimit } from "../services/activity.js";
import { assertAuthenticated, assertBoard, assertCompanyAccess } from "./authz.js";
import { heartbeatService, issueService } from "../services/index.js";
import { sanitizeRecord } from "../redaction.js";
const createActivitySchema = z.object({
actorType: z.enum(["agent", "user", "system", "plugin"]).optional().default("system"),
actorId: z.string().min(1),
action: z.string().min(1),
entityType: z.string().min(1),
entityId: z.string().min(1),
agentId: z.string().uuid().optional().nullable(),
details: z.record(z.unknown()).optional().nullable(),
});
export function activityRoutes(db: Db) {
const router = Router();
const svc = activityService(db);
const heartbeat = heartbeatService(db);
const issueSvc = issueService(db);
async function resolveIssueByRef(rawId: string) {
if (/^[A-Z]+-\d+$/i.test(rawId)) {
return issueSvc.getByIdentifier(rawId);
}
return issueSvc.getById(rawId);
}
router.get("/companies/:companyId/activity", async (req, res) => {
const companyId = req.params.companyId as string;
assertCompanyAccess(req, companyId);
const filters = {
companyId,
agentId: req.query.agentId as string | undefined,
entityType: req.query.entityType as string | undefined,
entityId: req.query.entityId as string | undefined,
limit: normalizeActivityLimit(Number(req.query.limit)),
};
const result = await svc.list(filters);
res.json(result);
});
router.post("/companies/:companyId/activity", validate(createActivitySchema), async (req, res) => {
assertBoard(req);
const companyId = req.params.companyId as string;
assertCompanyAccess(req, companyId);
const event = await svc.create({
companyId,
...req.body,
details: req.body.details ? sanitizeRecord(req.body.details) : null,
});
res.status(201).json(event);
});
router.get("/issues/:id/activity", async (req, res) => {
const rawId = req.params.id as string;
const issue = await resolveIssueByRef(rawId);
if (!issue) {
res.status(404).json({ error: "Issue not found" });
return;
}
assertCompanyAccess(req, issue.companyId);
const result = await svc.forIssue(issue.id);
res.json(result);
});
router.get("/issues/:id/runs", async (req, res) => {
const rawId = req.params.id as string;
const issue = await resolveIssueByRef(rawId);
if (!issue) {
res.status(404).json({ error: "Issue not found" });
return;
}
assertCompanyAccess(req, issue.companyId);
const result = await svc.runsForIssue(issue.companyId, issue.id);
res.json(result);
});
router.get("/heartbeat-runs/:runId/issues", async (req, res) => {
assertAuthenticated(req);
const runId = req.params.runId as string;
const run = await heartbeat.getRun(runId);
if (!run) {
res.json([]);
return;
}
assertCompanyAccess(req, run.companyId);
const result = await svc.issuesForRun(runId);
res.json(result);
});
return router;
}