Files
PaperClipAI/server/src/services/remote-agent-profiles.ts
T
Dotta fdf8c8464d feat(runner): add managed provider backends (#12699)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - The Paperclip Runner provides durable, provider-neutral agent
execution.
> - The current stack supports qualified local providers but omits the
managed provider paths from the integration branch.
> - Claude Managed Agents and AWS AgentCore need explicit profile
qualification, durable recovery, usage accounting, and cleanup controls.
> - This pull request adds those managed backends as the third part of
the Runner parity stack.
> - The benefit is managed execution without weakening the default-off
Runner rollout gate.

## Linked Issues or Issue Description

**Subsystem affected**

Cross-cutting: Runner, server orchestration, database profiles, CLI, and
adapter configuration UI.

**Problem or motivation**

The current Runner stack cannot select or execute the managed Claude
Agents API or AWS Bedrock AgentCore Harness backends. It also lacks
qualified profile storage and recovery checks for those remote
resources.

**Proposed solution**

Add qualified managed and remote profiles, API and CLI management, exact
provider selection, durable lifecycle handling, cumulative usage
accounting, bounded cleanup, and retention acknowledgement. Keep
`enableNativeRunner` default-off.

**Alternatives considered**

A direct copy of the old integration branch was rejected because its
provider contracts, model values, credential flow, and migration history
no longer match the current base. A single large parity pull request was
also rejected because stacked review keeps each subsystem bounded.

**Roadmap alignment**

This continues the existing Runner architecture and rollout work. It
does not introduce a separate execution system.

**Additional context**

This pull request is based on the merged #12691 and #12685 stack. It
also closes the delayed security-review findings reported on #12691 by
binding qualified ACPX and OpenCode launch artifacts to the bytes
actually executed. A GitHub search for managed agent, AgentCore, and
Claude managed work found no duplicate public issue or pull request.

## What Changed

- Add Claude Managed Agents and AWS AgentCore provider executors to
runnerd.
- Add qualified managed and remote profile storage, routes, OpenAPI
contracts, CLI commands, and migration 0237.
- Validate profile ownership, enabled state, exact qualified revision,
model, agent version, and secret binding before persistence and
recovery.
- Persist durable provider session and owned skill state for
restart-safe cleanup.
- Reconcile uncertain create responses and delete remote sessions before
owned skills.
- Track cumulative provider usage and enforce positive session spend
caps.
- Recover interrupted AgentCore usage at the next turn boundary by
charging the prior invocation ceiling exactly once; keep the session
gated until an explicit monotonic budget raise.
- Isolate AgentCore AWS configuration from host profiles and
credential-process/SSO configuration while preserving workload identity.
- Require OpenCode 1.18.17 and fixed build-owned provider-pack artifact
paths; remove the ambient executable override.
- Snapshot and content-verify ACPX and OpenCode commands, scripts, and
provider executables before launch. Linux executes sealed inherited
descriptors; macOS uses authenticated private snapshots with retry-safe
rematerialization at the spawn boundary.
- Persist canonical ACPX and OpenCode launch-profile digests, reject
drift across fresh recovery, and make recovery failures sticky.
- Close and journal unsafe ACPX active-turn recovery before any provider
bootstrap or reconnect.
- Add managed provider fields to the Runner configuration UI and
permission projection.
- Preserve the default-off `enableNativeRunner` experimental flag.

## Verification

- `pnpm -r typecheck`
- `pnpm build`
- Focused managed server, database, CLI, Runner TypeScript, Rust,
Claude, AgentCore, ACPX, OpenCode, process-supervisor, and
durable-recovery tests passed.
- `cargo test -p paperclip-runner-core --lib --locked` (160 tests)
- `cargo check --workspace --all-targets --locked`
- Native Codex integration tests passed (60 tests); native provider
tests passed (7 tests); server native-runtime tests passed (87 tests).
- Verified-launch replacement, nested-spawn retry, exact-version,
profile-drift, sticky-failure, and no-bootstrap active-recovery tests
passed.
- `git diff --check`
- The PR changes 91 files. `pnpm-lock.yaml` is unchanged. The Rust
workspace lockfile adds the approved `rustix` dependency used for safe
descriptor handling while `#![forbid(unsafe_code)]` remains enabled.

## Risks

- The provider APIs can change while they are in beta. Exact
qualification and fail-closed recovery checks limit drift.
- Remote cleanup can fail after a partial create. Durable ownership
inventories and retry-safe deletion preserve recovery state.
- Migration 0237 adds profile tables. The generated migration and
snapshot pass the repository migration checks.
- Managed execution can incur provider cost. Positive default spend caps
and explicit retention acknowledgement limit accidental use.
- An interrupted AgentCore invocation without final metadata is
conservatively charged to its active session ceiling. This can overstate
cost, but cannot undercount it; later work requires an explicit budget
increase.
- Linux qualified launches use sealed memory descriptors. macOS lacks
executable-descriptor APIs, so the runner uses owner-only private
snapshots and minimizes linked-path lifetime; hostile same-UID processes
remain outside the documented local-host trust boundary.
- The global Runner feature remains default-off.

> 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, with tool use, code execution, and subagent review.

## 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 searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change and contains no internal
Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
2026-09-02 00:48:30 -05:00

291 lines
9.4 KiB
TypeScript

import { and, asc, eq } from "drizzle-orm";
import type { Db } from "@paperclipai/db";
import { remoteAgentProfiles } from "@paperclipai/db";
import { conflict, notFound, unprocessable } from "../errors.js";
import {
AGENTCORE_QUALIFIED_MODEL,
AGENTCORE_QUALIFICATION_SUITE,
assertAgentCoreQualification,
assertProfileMetadataContainsNoSecrets,
computeQualifiedProfileRevision,
isQualifiedProfileRevision,
} from "./provider-profile-qualification.js";
export { assertProfileMetadataContainsNoSecrets } from "./provider-profile-qualification.js";
export type RemoteAgentService = "aws_bedrock_agentcore_harness";
const UUID_RE = /^[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/i;
export interface RemoteAgentProfileInput {
profileKey: string;
displayName: string;
service: RemoteAgentService;
configuration: Record<string, unknown>;
enabled: boolean;
retentionAcknowledged: boolean;
qualification?: Record<string, unknown>;
}
function required(value: unknown, label: string): string {
if (typeof value !== "string" || value.trim().length === 0) {
throw unprocessable(`${label} is required`);
}
return value.trim();
}
const AGENTCORE_CONFIGURATION_KEYS = new Set([
"region",
"accountId",
"harnessArn",
"harnessVersion",
"endpointArn",
"endpointQualifier",
"agentRuntimeArn",
"memoryArn",
"memoryId",
"invocationRoleArn",
"contextBucket",
"contextPrefix",
"contextKmsKeyArn",
"qualificationRevision",
"defaultModel",
"eventExpiryDays",
"defaultMaxEstimatedSessionCostUsd",
]);
function validateConfiguration(service: RemoteAgentService, configuration: Record<string, unknown>) {
if (service !== "aws_bedrock_agentcore_harness") {
throw unprocessable("Unsupported remote agent service");
}
const requiredKeys = [
"region",
"accountId",
"harnessArn",
"harnessVersion",
"endpointArn",
"endpointQualifier",
"agentRuntimeArn",
"memoryArn",
"memoryId",
"invocationRoleArn",
"contextBucket",
"contextPrefix",
"contextKmsKeyArn",
"qualificationRevision",
"defaultModel",
];
const unknownKeys = Object.keys(configuration).filter((key) => !AGENTCORE_CONFIGURATION_KEYS.has(key));
if (unknownKeys.length > 0) {
throw unprocessable(`Unsupported configuration field: ${unknownKeys.sort()[0]}`);
}
assertProfileMetadataContainsNoSecrets(configuration, "Remote Agent configuration");
for (const key of requiredKeys) required(configuration[key], `configuration.${key}`);
if (configuration.eventExpiryDays !== 90) {
throw unprocessable("AWS AgentCore profile requires a 90-day Memory expiry");
}
if (
configuration.qualificationRevision !== AGENTCORE_QUALIFICATION_SUITE
) {
throw unprocessable("AWS AgentCore profile requires the qualified harness revision");
}
if (configuration.defaultModel !== AGENTCORE_QUALIFIED_MODEL) {
throw unprocessable(`Remote Agent model must be ${AGENTCORE_QUALIFIED_MODEL}`);
}
if (
typeof configuration.defaultMaxEstimatedSessionCostUsd !== "number"
|| !Number.isFinite(configuration.defaultMaxEstimatedSessionCostUsd)
|| configuration.defaultMaxEstimatedSessionCostUsd <= 0
) {
throw unprocessable("AWS AgentCore default estimated spend ceiling must be positive");
}
}
export function computeRemoteAgentProfileRevision(input: {
service: RemoteAgentService;
configuration: Record<string, unknown>;
retentionAcknowledged: boolean;
qualification: Record<string, unknown>;
}): string {
const immutableConfigurationKeys = [
"region",
"accountId",
"harnessArn",
"harnessVersion",
"endpointArn",
"endpointQualifier",
"agentRuntimeArn",
"memoryArn",
"memoryId",
"invocationRoleArn",
"contextBucket",
"contextPrefix",
"contextKmsKeyArn",
"qualificationRevision",
"eventExpiryDays",
];
const immutableConfiguration = Object.fromEntries(
immutableConfigurationKeys.map((key) => [key, input.configuration[key]]),
);
return computeQualifiedProfileRevision({
service: input.service,
configuration: immutableConfiguration,
retentionAcknowledged: input.retentionAcknowledged,
qualification: input.qualification,
});
}
function assertQualifiedRevisionUnchanged(
existing: typeof remoteAgentProfiles.$inferSelect | null,
revision: string | null,
): void {
if (!existing?.qualifiedAt) return;
if (!revision || existing.qualifiedRevision !== revision) {
throw conflict("Qualified Remote Agent configuration revision is immutable; create a new profile key");
}
}
export function remoteAgentProfileService(db: Db) {
async function list(companyId: string, service?: RemoteAgentService) {
return db
.select()
.from(remoteAgentProfiles)
.where(
service
? and(eq(remoteAgentProfiles.companyId, companyId), eq(remoteAgentProfiles.service, service))
: eq(remoteAgentProfiles.companyId, companyId),
)
.orderBy(asc(remoteAgentProfiles.displayName));
}
async function get(companyId: string, profileIdOrKey: string) {
const isUuid = UUID_RE.test(profileIdOrKey);
const rows = await db
.select()
.from(remoteAgentProfiles)
.where(and(
eq(remoteAgentProfiles.companyId, companyId),
isUuid
? eq(remoteAgentProfiles.id, profileIdOrKey)
: eq(remoteAgentProfiles.profileKey, profileIdOrKey),
))
.limit(1);
return rows[0] ?? null;
}
async function getByProfileKey(companyId: string, profileKey: string) {
const rows = await db
.select()
.from(remoteAgentProfiles)
.where(and(
eq(remoteAgentProfiles.companyId, companyId),
eq(remoteAgentProfiles.profileKey, profileKey),
))
.limit(1);
return rows[0] ?? null;
}
async function requireQualified(
companyId: string,
profileIdOrKey: string,
service?: RemoteAgentService,
) {
const profile = await get(companyId, profileIdOrKey);
if (!profile || (service && profile.service !== service)) {
throw notFound("Remote Agent profile not found");
}
if (!profile.enabled || !profile.retentionAcknowledged || !profile.qualifiedAt) {
throw conflict("Remote Agent profile is not enabled and qualified");
}
try {
validateConfiguration(profile.service as RemoteAgentService, profile.configuration);
} catch {
throw conflict("Remote Agent profile configuration is not qualified");
}
try {
assertAgentCoreQualification(profile.configuration, profile.qualification, { required: true });
} catch {
throw conflict("Remote Agent profile qualification attestation is invalid");
}
const currentRevision = computeRemoteAgentProfileRevision({
service: profile.service as RemoteAgentService,
configuration: profile.configuration,
retentionAcknowledged: profile.retentionAcknowledged,
qualification: profile.qualification,
});
if (
!isQualifiedProfileRevision(profile.qualifiedRevision)
|| profile.qualifiedRevision !== currentRevision
) {
throw conflict("Remote Agent profile configuration does not match its qualified revision");
}
return profile;
}
async function upsert(companyId: string, input: RemoteAgentProfileInput) {
if ("credentialSecretId" in (input as unknown as Record<string, unknown>)) {
throw unprocessable("AWS AgentCore profiles use workload identity, not a credential secret");
}
const profileKey = required(input.profileKey, "Profile key");
if (UUID_RE.test(profileKey)) {
throw unprocessable("Profile key must not be UUID-shaped");
}
const displayName = required(input.displayName, "Display name");
const configuration = structuredClone(input.configuration);
const qualification = structuredClone(input.qualification ?? {});
assertProfileMetadataContainsNoSecrets(
{ profileKey, displayName },
"Remote Agent profile",
);
validateConfiguration(input.service, configuration);
if (input.enabled && !input.retentionAcknowledged) {
throw unprocessable("Enabling a remote agent requires retention acknowledgement");
}
const qualificationAttested = assertAgentCoreQualification(
configuration,
qualification,
{ required: input.enabled },
);
const existing = await getByProfileKey(companyId, profileKey);
const qualifiedRevision = qualificationAttested
? computeRemoteAgentProfileRevision({
service: input.service,
configuration,
retentionAcknowledged: input.retentionAcknowledged,
qualification,
})
: null;
assertQualifiedRevisionUnchanged(existing, qualifiedRevision);
const values = {
companyId,
profileKey,
displayName,
service: input.service,
configuration,
enabled: input.enabled,
retentionAcknowledged: input.retentionAcknowledged,
qualification,
qualifiedAt: existing?.qualifiedAt ?? (input.enabled && qualificationAttested ? new Date() : null),
qualifiedRevision:
existing?.qualifiedAt || (input.enabled && qualificationAttested)
? qualifiedRevision
: null,
updatedAt: new Date(),
} as const;
const [row] = await db
.insert(remoteAgentProfiles)
.values(values)
.onConflictDoUpdate({
target: [remoteAgentProfiles.companyId, remoteAgentProfiles.profileKey],
set: values,
})
.returning();
return row!;
}
return { list, get, requireQualified, upsert };
}