forked from farhoodlabs/paperclip
09d0678840
## 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
115 lines
5.9 KiB
TypeScript
115 lines
5.9 KiB
TypeScript
import {
|
|
boolean,
|
|
index,
|
|
integer,
|
|
jsonb,
|
|
pgTable,
|
|
text,
|
|
timestamp,
|
|
uniqueIndex,
|
|
uuid,
|
|
} from "drizzle-orm/pg-core";
|
|
import { agents } from "./agents.js";
|
|
import { companies } from "./companies.js";
|
|
import { companySecrets } from "./company_secrets.js";
|
|
import { issues } from "./issues.js";
|
|
import { projects } from "./projects.js";
|
|
import { goals } from "./goals.js";
|
|
import type { RoutineVariable } from "@paperclipai/shared";
|
|
|
|
export const routines = pgTable(
|
|
"routines",
|
|
{
|
|
id: uuid("id").primaryKey().defaultRandom(),
|
|
companyId: uuid("company_id").notNull().references(() => companies.id, { onDelete: "cascade" }),
|
|
projectId: uuid("project_id").references(() => projects.id, { onDelete: "cascade" }),
|
|
goalId: uuid("goal_id").references(() => goals.id, { onDelete: "set null" }),
|
|
parentIssueId: uuid("parent_issue_id").references(() => issues.id, { onDelete: "set null" }),
|
|
title: text("title").notNull(),
|
|
description: text("description"),
|
|
assigneeAgentId: uuid("assignee_agent_id").references(() => agents.id),
|
|
priority: text("priority").notNull().default("medium"),
|
|
status: text("status").notNull().default("active"),
|
|
concurrencyPolicy: text("concurrency_policy").notNull().default("coalesce_if_active"),
|
|
catchUpPolicy: text("catch_up_policy").notNull().default("skip_missed"),
|
|
variables: jsonb("variables").$type<RoutineVariable[]>().notNull().default([]),
|
|
createdByAgentId: uuid("created_by_agent_id").references(() => agents.id, { onDelete: "set null" }),
|
|
createdByUserId: text("created_by_user_id"),
|
|
updatedByAgentId: uuid("updated_by_agent_id").references(() => agents.id, { onDelete: "set null" }),
|
|
updatedByUserId: text("updated_by_user_id"),
|
|
lastTriggeredAt: timestamp("last_triggered_at", { withTimezone: true }),
|
|
lastEnqueuedAt: timestamp("last_enqueued_at", { withTimezone: true }),
|
|
createdAt: timestamp("created_at", { withTimezone: true }).notNull().defaultNow(),
|
|
updatedAt: timestamp("updated_at", { withTimezone: true }).notNull().defaultNow(),
|
|
},
|
|
(table) => ({
|
|
companyStatusIdx: index("routines_company_status_idx").on(table.companyId, table.status),
|
|
companyAssigneeIdx: index("routines_company_assignee_idx").on(table.companyId, table.assigneeAgentId),
|
|
companyProjectIdx: index("routines_company_project_idx").on(table.companyId, table.projectId),
|
|
}),
|
|
);
|
|
|
|
export const routineTriggers = pgTable(
|
|
"routine_triggers",
|
|
{
|
|
id: uuid("id").primaryKey().defaultRandom(),
|
|
companyId: uuid("company_id").notNull().references(() => companies.id, { onDelete: "cascade" }),
|
|
routineId: uuid("routine_id").notNull().references(() => routines.id, { onDelete: "cascade" }),
|
|
kind: text("kind").notNull(),
|
|
label: text("label"),
|
|
enabled: boolean("enabled").notNull().default(true),
|
|
cronExpression: text("cron_expression"),
|
|
timezone: text("timezone"),
|
|
nextRunAt: timestamp("next_run_at", { withTimezone: true }),
|
|
lastFiredAt: timestamp("last_fired_at", { withTimezone: true }),
|
|
publicId: text("public_id"),
|
|
secretId: uuid("secret_id").references(() => companySecrets.id, { onDelete: "set null" }),
|
|
signingMode: text("signing_mode"),
|
|
replayWindowSec: integer("replay_window_sec"),
|
|
lastRotatedAt: timestamp("last_rotated_at", { withTimezone: true }),
|
|
lastResult: text("last_result"),
|
|
createdByAgentId: uuid("created_by_agent_id").references(() => agents.id, { onDelete: "set null" }),
|
|
createdByUserId: text("created_by_user_id"),
|
|
updatedByAgentId: uuid("updated_by_agent_id").references(() => agents.id, { onDelete: "set null" }),
|
|
updatedByUserId: text("updated_by_user_id"),
|
|
createdAt: timestamp("created_at", { withTimezone: true }).notNull().defaultNow(),
|
|
updatedAt: timestamp("updated_at", { withTimezone: true }).notNull().defaultNow(),
|
|
},
|
|
(table) => ({
|
|
companyRoutineIdx: index("routine_triggers_company_routine_idx").on(table.companyId, table.routineId),
|
|
companyKindIdx: index("routine_triggers_company_kind_idx").on(table.companyId, table.kind),
|
|
nextRunIdx: index("routine_triggers_next_run_idx").on(table.nextRunAt),
|
|
publicIdIdx: index("routine_triggers_public_id_idx").on(table.publicId),
|
|
publicIdUq: uniqueIndex("routine_triggers_public_id_uq").on(table.publicId),
|
|
}),
|
|
);
|
|
|
|
export const routineRuns = pgTable(
|
|
"routine_runs",
|
|
{
|
|
id: uuid("id").primaryKey().defaultRandom(),
|
|
companyId: uuid("company_id").notNull().references(() => companies.id, { onDelete: "cascade" }),
|
|
routineId: uuid("routine_id").notNull().references(() => routines.id, { onDelete: "cascade" }),
|
|
triggerId: uuid("trigger_id").references(() => routineTriggers.id, { onDelete: "set null" }),
|
|
source: text("source").notNull(),
|
|
status: text("status").notNull().default("received"),
|
|
triggeredAt: timestamp("triggered_at", { withTimezone: true }).notNull().defaultNow(),
|
|
idempotencyKey: text("idempotency_key"),
|
|
triggerPayload: jsonb("trigger_payload").$type<Record<string, unknown>>(),
|
|
dispatchFingerprint: text("dispatch_fingerprint"),
|
|
linkedIssueId: uuid("linked_issue_id").references(() => issues.id, { onDelete: "set null" }),
|
|
coalescedIntoRunId: uuid("coalesced_into_run_id"),
|
|
failureReason: text("failure_reason"),
|
|
completedAt: timestamp("completed_at", { withTimezone: true }),
|
|
createdAt: timestamp("created_at", { withTimezone: true }).notNull().defaultNow(),
|
|
updatedAt: timestamp("updated_at", { withTimezone: true }).notNull().defaultNow(),
|
|
},
|
|
(table) => ({
|
|
companyRoutineIdx: index("routine_runs_company_routine_idx").on(table.companyId, table.routineId, table.createdAt),
|
|
triggerIdx: index("routine_runs_trigger_idx").on(table.triggerId, table.createdAt),
|
|
dispatchFingerprintIdx: index("routine_runs_dispatch_fingerprint_idx").on(table.routineId, table.dispatchFingerprint),
|
|
linkedIssueIdx: index("routine_runs_linked_issue_idx").on(table.linkedIssueId),
|
|
idempotencyIdx: index("routine_runs_trigger_idempotency_idx").on(table.triggerId, table.idempotencyKey),
|
|
}),
|
|
);
|