Files
PaperClipAI/server/src/modules/agent-lifecycle/adapters/postgres.ts
T
Devin FoleyandPaperclip 81ecaf0654 fix(server): bound failed lifecycle verification (#18383)
Failed lifecycle verification could allocate another test environment every minute indefinitely. Count failed host verification tests separately from claims, persist a repair wait for confirmed configuration failures or three generic failed tests, and clear it through authorized retry or execution configuration changes.

Preserve typed temporary execution-target failures through adapter checks so timeouts, transport failures and interrupted probes keep automatic recovery. Retain existing readiness, authorization, termination and cleanup gates. Document the policy and add real PostgreSQL persistence and actual OpenCode adapter regressions.

Verified 398 focused tests (one Windows-only test skipped on macOS), repository-wide typecheck and build, structural checks, fully green current-head CI and Greptile 5/5 with no unresolved comments.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-30 15:29:43 -07:00

206 lines
14 KiB
TypeScript

import { randomUUID } from "node:crypto";
import { and, asc, eq, inArray, sql } from "drizzle-orm";
import { agents, agentApiKeys, companies, budgetPolicies, type Db } from "@paperclipai/db";
import type { AgentLifecycleOperation } from "@paperclipai/shared";
import { AgentLifecycleConflict, compatibilityStatus, isLifecycleWorkPending, transition, type LifecycleCommand } from "../domain/policy.js";
import type { LifecycleEffects } from "./effects.js";
import type { LifecycleStore } from "../application/ports.js";
export function assertRootDatabase(db: Db) {
if ("nestedIndex" in db) throw new AgentLifecycleConflict("Lifecycle commands require the root database connection");
}
type LifecycleRow = typeof agents.$inferSelect;
type ChangeOptions = { version?: number; owner?: string; reason?: string };
// Prepared drafts wait for the wizard; they have no background verification obligation.
export const pendingLifecycleWork = and(
inArray(agents.lifecycleState, ["preparing", "verifying", "pausing", "resuming", "terminating", "cleaning_up"]),
sql`not (${agents.lifecycleState} = 'verifying' and ${agents.lifecycleHolds} @> '["setup"]'::jsonb)`,
sql`not (${agents.lifecycleState} = 'verifying' and coalesce(${agents.lifecycleOperation}->>'retryRequired', 'false') = 'true')`,
);
/** The caller owns the accounting transaction and has locked this agent. */
async function changeLockedAgent(tx: Db, effects: LifecycleEffects, agent: LifecycleRow,
command: LifecycleCommand, options: ChangeOptions = {}, policyHolds?: string[], restartPause = false) {
if (options.version !== undefined && options.version !== agent.lifecycleVersion) return null;
if (command === "resume" && agent.lifecycleHolds.includes("setup")) throw new AgentLifecycleConflict("Finish agent setup before resuming");
if (command === "complete" && (!options.owner || !agent.lifecycleOperation?.leaseUntil || agent.lifecycleOperation?.leaseOwner !== options.owner ||
Date.parse(agent.lifecycleOperation?.leaseUntil ?? "") <= Date.now() ||
!agent.lifecycleOperation.hostComplete || agent.lifecycleRequiredPluginIds === null ||
agent.lifecycleRequiredPluginIds.some(id => !agent.lifecycleOperation!.completedPluginIds.includes(id)))) return null;
if (command === "retry") {
transition(agent.lifecycleState, command);
if (agent.lifecycleOperation?.leaseUntil && Date.parse(agent.lifecycleOperation.leaseUntil) > Date.now()) return agent;
await effects.notifyWork(tx);
const [updated] = await tx.update(agents).set({ lifecycleError: null,
lifecycleOperation: sql`${agents.lifecycleOperation} - 'retryAt' - 'retryRequired' - 'verificationFailures' - 'leaseOwner' - 'leaseUntil'`, updatedAt: new Date() }).where(eq(agents.id, agent.id)).returning();
return updated;
}
if (command === "resume" && !["ready", "paused", "pausing", "resuming"].includes(agent.lifecycleState)) transition(agent.lifecycleState, command);
let holds = policyHolds ?? agent.lifecycleHolds;
const reason = options.reason ?? "manual";
if (command === "reconcile" && policyHolds === undefined) {
if (["pending_approval", "terminating", "cleaning_up", "terminated", "rejected"].includes(agent.lifecycleState)) return agent;
const [company] = await tx.select().from(companies).where(eq(companies.id, agent.companyId));
const policies = await tx.select().from(budgetPolicies).where(and(eq(budgetPolicies.companyId, agent.companyId),
eq(budgetPolicies.scopeType, "agent"), eq(budgetPolicies.scopeId, agent.id)));
let budgetBlocked = false;
for (const policy of policies) if (await effects.policyBlocks(tx, policy)) budgetBlocked = true;
holds = holds.filter(hold => hold !== "budget" && hold !== "company_archived" && hold !== "company_paused");
if (budgetBlocked) holds.push("budget");
if (company.status === "archived") holds.push("company_archived");
if (company.status === "paused") holds.push("company_paused");
}
if (command === "pause") holds = [...new Set([...holds, reason])];
if (command === "resume") holds = holds.filter(hold => reason === "user" ? ["budget", "company_archived", "company_paused"].includes(hold) : hold !== reason);
const blockingHolds = holds.filter(hold => hold !== "setup" || !["preparing", "verifying"].includes(agent.lifecycleState));
let next = command === "reconcile"
? blockingHolds.length && !["pausing", "paused"].includes(agent.lifecycleState) ? "pausing" as const
: !holds.length && agent.lifecycleState === "paused" ? "resuming" as const : agent.lifecycleState
: command === "resume" && (holds.length || agent.lifecycleState === "pausing") ? agent.lifecycleState
: transition(agent.lifecycleState, command, agent.lifecycleOperation?.resumeState);
if (restartPause && next === "paused") next = "pausing";
if (command === "complete" && next === "ready" && holds.length) next = "pausing";
if (command === "complete" && next === "paused" && !holds.length) next = "resuming";
if (["complete", "reconcile"].includes(command) && next === "paused" && holds.length === 1 && holds[0] === "setup"
&& await effects.setupRequiresPreparation(tx, agent.companyId, agent.defaultEnvironmentId)) next = "preparing";
if (next === agent.lifecycleState) {
if (JSON.stringify(holds) !== JSON.stringify(agent.lifecycleHolds) || agent.pauseReason !== (holds[0] ?? null)) {
const [updated] = await tx.update(agents).set({ lifecycleHolds: holds, pauseReason: holds[0] ?? null }).where(eq(agents.id, agent.id)).returning();
return updated;
}
return agent;
}
const operation: AgentLifecycleOperation = {
responsibleUserId: agent.lifecycleOperation?.responsibleUserId,
id: randomUUID(), hostComplete: false, completedPluginIds: [], attempts: 0,
resumeState: next === "pausing"
? agent.lifecycleState === "preparing" || agent.lifecycleState === "verifying" ? agent.lifecycleState : agent.lifecycleOperation?.resumeState ?? "ready"
: agent.lifecycleOperation?.resumeState,
};
if (next === "ready") operation.resumeState = "ready";
const status = compatibilityStatus(next, agent.status);
if (status !== agent.status) await effects.beforeStatusChange(tx, agent.companyId, agent.id, agent.status, status);
if (isLifecycleWorkPending(next)) await effects.notifyWork(tx);
const [updated] = await tx.update(agents).set({
lifecycleHolds: holds, lifecycleState: next, lifecycleVersion: agent.lifecycleVersion + 1, lifecycleError: null,
lifecycleOperation: operation, status,
pauseReason: holds[0] ?? null,
pausedAt: next === "pausing" ? new Date() : next === "ready" ? null : agent.pausedAt,
updatedAt: new Date(),
}).where(eq(agents.id, agent.id)).returning();
if (next === "terminating" || next === "rejected") {
await tx.update(agentApiKeys).set({ revokedAt: new Date() }).where(eq(agentApiKeys.agentId, agent.id));
await effects.clearPrimary(tx, agent.companyId, agent.id);
}
if (command === "approve") await effects.recordCreation(tx, agent.companyId, agent.id);
if (next === "pausing" || next === "resuming" || next === "terminating" || next === "rejected") {
await effects.recordStatus(tx, agent.companyId, agent.id,
next === "resuming" ? "paused" : "idle",
next === "resuming" ? "idle" : next === "pausing" ? "paused" : "terminated");
}
return updated;
}
/** Apply a computed hold without resolving policies or opening another transaction. */
export async function applyAgentPolicyHoldsInTransaction(tx: Db, effects: LifecycleEffects,
companyId: string, agentId: string, patch: { budget?: boolean; companyStatus?: string; restartPause?: boolean }, lockedAgent?: LifecycleRow) {
if (!("nestedIndex" in tx)) throw new AgentLifecycleConflict("Policy holds require the caller's accounting transaction");
const agent = lockedAgent ?? (await tx.select().from(agents).where(and(
eq(agents.id, agentId), eq(agents.companyId, companyId),
)).for("update"))[0];
if (!agent || agent.companyId !== companyId || ["pending_approval", "terminating", "cleaning_up", "terminated", "rejected"].includes(agent.lifecycleState)) return null;
let holds = [...agent.lifecycleHolds];
if (patch.budget !== undefined) {
holds = holds.filter(hold => hold !== "budget");
if (patch.budget) holds.push("budget");
}
if (patch.companyStatus !== undefined) {
holds = holds.filter(hold => hold !== "company_paused" && hold !== "company_archived");
if (patch.companyStatus === "paused") holds.push("company_paused");
if (patch.companyStatus === "archived") holds.push("company_archived");
}
return changeLockedAgent(tx, effects, agent, "reconcile", {}, holds, patch.restartPause);
}
export function createLifecycleStore(db: Db, effects: LifecycleEffects): LifecycleStore {
const get = (id: string) => db.select().from(agents).where(eq(agents.id, id)).then(rows => rows[0] ?? null);
return {
get,
async change(id, command, options = {}) {
const existing = await get(id);
if (!existing) return null;
return effects.transaction(db, existing.companyId, async tx => {
const [agent] = await tx.select().from(agents).where(eq(agents.id, id)).for("update", command === "reconcile" ? { skipLocked: true } : undefined);
if (!agent) return null;
return changeLockedAgent(tx, effects, agent, command, options);
});
},
async claim(id, owner, now) {
const [agent] = await db.update(agents).set({
lifecycleOperation: sql`coalesce(${agents.lifecycleOperation}, '{"id":"", "hostComplete":false, "completedPluginIds":[], "attempts":0}'::jsonb)
|| jsonb_build_object('leaseOwner', ${owner}::text, 'leaseUntil', ${(new Date(now.getTime() + 120_000)).toISOString()}::text,
'attempts', coalesce((${agents.lifecycleOperation}->>'attempts')::integer, 0) + 1)`,
}).where(and(eq(agents.id, id), pendingLifecycleWork,
sql`(${agents.lifecycleState} in ('pausing', 'terminating', 'cleaning_up') or exists (
select 1 from ${companies} where ${companies.id} = ${agents.companyId} and ${companies.status} = 'active'))`,
sql`coalesce((${agents.lifecycleOperation}->>'leaseUntil')::timestamptz, '-infinity') <= ${now.toISOString()}::timestamptz`,
sql`coalesce((${agents.lifecycleOperation}->>'retryAt')::timestamptz, '-infinity') <= ${now.toISOString()}::timestamptz`,
)).returning();
return agent ?? null;
},
async renew(agent, owner, now) {
const rows = await db.update(agents).set({ lifecycleOperation: sql`jsonb_set(${agents.lifecycleOperation}, '{leaseUntil}', ${JSON.stringify(new Date(now.getTime() + 120_000).toISOString())}::jsonb)` })
.where(and(eq(agents.id, agent.id), eq(agents.lifecycleVersion, agent.lifecycleVersion), sql`${agents.lifecycleOperation}->>'leaseOwner' = ${owner}`)).returning({ id: agents.id });
return rows.length > 0;
},
async setRequiredPlugins(agent, owner, pluginIds) {
const rows = await db.update(agents).set({ lifecycleRequiredPluginIds: pluginIds })
.where(and(eq(agents.id, agent.id), eq(agents.lifecycleVersion, agent.lifecycleVersion),
sql`${agents.lifecycleRequiredPluginIds} is null`,
sql`${agents.lifecycleOperation}->>'leaseOwner' = ${owner}`)).returning({ id: agents.id });
return rows.length > 0;
},
async completeHost(agent, owner) {
const rows = await db.update(agents).set({
lifecycleOperation: sql`jsonb_set(${agents.lifecycleOperation}, '{hostComplete}', 'true'::jsonb)`,
}).where(and(eq(agents.id, agent.id), eq(agents.lifecycleVersion, agent.lifecycleVersion),
sql`${agents.lifecycleOperation}->>'leaseOwner' = ${owner}`)).returning({ id: agents.id });
return rows.length > 0;
},
async completePlugin(agent, owner, pluginId) {
const rows = await db.update(agents).set({
lifecycleOperation: sql`jsonb_set(${agents.lifecycleOperation}, '{completedPluginIds}',
coalesce(${agents.lifecycleOperation}->'completedPluginIds', '[]'::jsonb) || ${JSON.stringify([pluginId])}::jsonb)`,
}).where(and(eq(agents.id, agent.id), eq(agents.lifecycleVersion, agent.lifecycleVersion),
sql`${agents.lifecycleRequiredPluginIds} @> ${JSON.stringify([pluginId])}::jsonb`,
sql`${agents.lifecycleOperation}->>'leaseOwner' = ${owner}`)).returning({ id: agents.id });
return rows.length > 0;
},
async defer(agent, owner, error, now, options) {
const retry: Partial<AgentLifecycleOperation> = options?.retryRequired && agent.lifecycleState === "verifying"
? { retryRequired: true }
: { retryAt: new Date(now.getTime() + (error ? 60_000 : 2_000)).toISOString() };
if (options?.verificationFailures !== undefined && agent.lifecycleState === "verifying") {
retry.verificationFailures = options.verificationFailures;
}
const rows = await db.update(agents).set({
lifecycleError: error,
lifecycleOperation: sql`(${agents.lifecycleOperation} - 'leaseOwner' - 'leaseUntil' - 'retryAt' - 'retryRequired')
|| ${JSON.stringify(retry)}::jsonb`,
updatedAt: now,
}).where(and(eq(agents.id, agent.id), eq(agents.lifecycleVersion, agent.lifecycleVersion),
sql`${agents.lifecycleOperation}->>'leaseOwner' = ${owner}`)).returning({ id: agents.id });
return rows.length > 0;
},
async pending(limit, now) {
return db.select({ id: agents.id }).from(agents).where(and(
pendingLifecycleWork,
sql`coalesce((${agents.lifecycleOperation}->>'leaseUntil')::timestamptz, '-infinity') <= ${now.toISOString()}::timestamptz`,
sql`coalesce((${agents.lifecycleOperation}->>'retryAt')::timestamptz, '-infinity') <= ${now.toISOString()}::timestamptz`,
)).orderBy(asc(agents.updatedAt), asc(agents.id)).limit(limit).then(rows => rows.map(row => row.id));
},
};
}