Files
paperclip/packages/db/src/schema/heartbeat_runs.ts
T
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

69 lines
3.3 KiB
TypeScript

import { type AnyPgColumn, pgTable, uuid, text, timestamp, jsonb, index, integer, bigint, boolean } from "drizzle-orm/pg-core";
import { companies } from "./companies.js";
import { agents } from "./agents.js";
import { agentWakeupRequests } from "./agent_wakeup_requests.js";
export const heartbeatRuns = pgTable(
"heartbeat_runs",
{
id: uuid("id").primaryKey().defaultRandom(),
companyId: uuid("company_id").notNull().references(() => companies.id),
agentId: uuid("agent_id").notNull().references(() => agents.id),
invocationSource: text("invocation_source").notNull().default("on_demand"),
triggerDetail: text("trigger_detail"),
status: text("status").notNull().default("queued"),
startedAt: timestamp("started_at", { withTimezone: true }),
finishedAt: timestamp("finished_at", { withTimezone: true }),
error: text("error"),
wakeupRequestId: uuid("wakeup_request_id").references(() => agentWakeupRequests.id),
exitCode: integer("exit_code"),
signal: text("signal"),
usageJson: jsonb("usage_json").$type<Record<string, unknown>>(),
resultJson: jsonb("result_json").$type<Record<string, unknown>>(),
sessionIdBefore: text("session_id_before"),
sessionIdAfter: text("session_id_after"),
logStore: text("log_store"),
logRef: text("log_ref"),
logBytes: bigint("log_bytes", { mode: "number" }),
logSha256: text("log_sha256"),
logCompressed: boolean("log_compressed").notNull().default(false),
stdoutExcerpt: text("stdout_excerpt"),
stderrExcerpt: text("stderr_excerpt"),
errorCode: text("error_code"),
externalRunId: text("external_run_id"),
processPid: integer("process_pid"),
processGroupId: integer("process_group_id"),
processStartedAt: timestamp("process_started_at", { withTimezone: true }),
retryOfRunId: uuid("retry_of_run_id").references((): AnyPgColumn => heartbeatRuns.id, {
onDelete: "set null",
}),
processLossRetryCount: integer("process_loss_retry_count").notNull().default(0),
scheduledRetryAt: timestamp("scheduled_retry_at", { withTimezone: true }),
scheduledRetryAttempt: integer("scheduled_retry_attempt").notNull().default(0),
scheduledRetryReason: text("scheduled_retry_reason"),
issueCommentStatus: text("issue_comment_status").notNull().default("not_applicable"),
issueCommentSatisfiedByCommentId: uuid("issue_comment_satisfied_by_comment_id"),
issueCommentRetryQueuedAt: timestamp("issue_comment_retry_queued_at", { withTimezone: true }),
livenessState: text("liveness_state"),
livenessReason: text("liveness_reason"),
continuationAttempt: integer("continuation_attempt").notNull().default(0),
lastUsefulActionAt: timestamp("last_useful_action_at", { withTimezone: true }),
nextAction: text("next_action"),
contextSnapshot: jsonb("context_snapshot").$type<Record<string, unknown>>(),
createdAt: timestamp("created_at", { withTimezone: true }).notNull().defaultNow(),
updatedAt: timestamp("updated_at", { withTimezone: true }).notNull().defaultNow(),
},
(table) => ({
companyAgentStartedIdx: index("heartbeat_runs_company_agent_started_idx").on(
table.companyId,
table.agentId,
table.startedAt,
),
companyLivenessIdx: index("heartbeat_runs_company_liveness_idx").on(
table.companyId,
table.livenessState,
table.createdAt,
),
}),
);