Files
PaperClipAI/packages/shared/src/validators/agent.ts
T
DottaandDev Agent 25cf079ec5 feat(runner): add Codex-native application integration (#12591)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner package is useful only when the application can start,
observe, and recover a native Codex run safely.
> - Existing direct adapters must keep their current execution and
finalization paths.
> - The application boundary therefore needs additive persistence,
authorization, coordination, and recovery behind an explicit
experimental adapter.
> - This pull request adds that Codex-only boundary without activating
generalized providers, remote environments, or the later task/SDK
surfaces.

## Linked Issues or Issue Description

**Subsystem affected**

Shared contracts, database persistence, adapter utilities, server
native-runtime services, and the experimental Paperclip Runner adapter.

**Problem or motivation**

The already-landed runner package has a qualified Codex path, but the
application needs durable native-run state, guarded runtime selection,
authenticated coordination, tool security, finalization, and recovery
before the experimental adapter can be exercised safely.

**Proposed solution**

Add a Codex-only `paperclip_runner` application path behind the existing
default-off native-runner setting. Bind native state and coordination to
company/run identity, preserve persisted-run recovery, and leave every
direct adapter on its existing legacy execution path.

**Alternatives considered**

The earlier stack boundary introduced a generalized executor and
remote-environment lifecycle here. That made this PR depend on
implementations in higher PRs and changed reusable sandbox behavior
globally. Those pieces are now deferred together to #12592.

**Roadmap alignment**

ROADMAP.md does not list a conflicting native-runner integration
project. This change adds the application boundary for the existing
Runner architecture.

## What Changed

- Added native run/result/finalization/provider-trace persistence,
shared validators, and idempotent migration/replay coverage.
- Added guarded Codex-only runtime selection, authenticated PRP
coordination, recovery, finalization, and interaction services.
- Added run/company-bound tool-gateway authorization, credential
redaction, SSRF protections, and replay-safe behavior.
- Added the explicit `paperclip_runner` adapter behind the default-off
rollout setting.
- Preserved legacy answered-question wake projection and direct-adapter
execution/finalization paths.
- Hardened cancellation so only owned in-memory child processes are
signaled; persisted recycled PIDs/process groups are never trusted.
- Retained the narrow Claude ACPX isolated-context security follow-up
discovered after #12590.
- Deferred the generalized executor, provider ingress, remote lifecycle,
SDK/lab/eval work, release-process changes, and lockfile.

## Verification

- Changed-file delta against `master`: 133 files.
- GitHub Actions is the authoritative verification environment for this
PR.
- Full CI, security, and Greptile review will run on this lowest
unmerged stack PR.
- Local tests/build/typecheck were not run because this checkout is
resource constrained.
- Static diff/reference checks pass, and `pnpm-lock.yaml` is unchanged.

## Risks

- This touches central heartbeat and agent-route code, so legacy
compatibility is the primary risk.
- Runtime selection remains Codex-only and explicit; direct Codex,
Claude, OpenCode, process, HTTP, and plugin adapters remain on their
existing paths.
- Fresh native starts fail closed while the rollout flag is off;
persisted native records remain readable and recoverable.
- Cancellation, company/run binding, tool calls, status decisions, and
completion writes are guarded or replay-safe.

> 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.

## Model Used

OpenAI Codex, GPT-5.6, with repository tools, code execution, and
parallel agent 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 linked existing issues or described the issue in-PR
following the relevant issue template
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch name describes the change and contains no internal
Paperclip ticket id
- [ ] I have run tests locally and they pass — GitHub Actions is
authoritative for this resource-constrained checkout
- [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 risks above
- [ ] All Paperclip CI and security gates are green
- [ ] Greptile is 5/5 with no open actionable findings
- [x] I will address all Greptile and reviewer comments before merge

## Stack

- Position: 3 of 5 overall; lowest of 3 currently unmerged
- Base: `master`
- Previous:
[#12590](https://github.com/paperclipai/paperclip/pull/12590), qualified
Claude ACPX runtime — merged
- Next: [#12592](https://github.com/paperclipai/paperclip/pull/12592),
generalized Codex executor, task experience, and developer SDKs

---------

Co-authored-by: Dev Agent <dev@paperclip.ing>
2026-08-31 14:38:38 -05:00

254 lines
9.9 KiB
TypeScript

import { z } from "zod";
import {
AGENT_ICON_NAMES,
AGENT_ROLES,
AGENT_STATUSES,
INBOX_MINE_ISSUE_STATUS_FILTER,
} from "../constants.js";
import { agentAdapterTypeSchema } from "../adapter-type.js";
import { envConfigSchema } from "./secret.js";
import { trustAuthorizationPolicySchema, trustPresetSchema } from "./trust-policy.js";
import { agentDesiredSkillSelectionSchema } from "./adapter-skills.js";
import { objectWithoutDefaults } from "./partial.js";
export const agentPermissionsSchema = z.object({
canCreateAgents: z.boolean().optional().default(false),
canCreateSkills: z.boolean().optional().default(true),
trustPreset: trustPresetSchema.optional(),
authorizationPolicy: trustAuthorizationPolicySchema.optional(),
}).catchall(z.unknown());
export const agentInstructionsBundleModeSchema = z.enum(["managed", "external"]);
export const updateAgentInstructionsBundleSchema = z.object({
mode: agentInstructionsBundleModeSchema.optional(),
rootPath: z.string().trim().min(1).nullable().optional(),
entryFile: z.string().trim().min(1).optional(),
clearLegacyPromptTemplate: z.boolean().optional().default(false),
});
export type UpdateAgentInstructionsBundle = z.infer<typeof updateAgentInstructionsBundleSchema>;
export const upsertAgentInstructionsFileSchema = z.object({
path: z.string().trim().min(1),
content: z.string(),
clearLegacyPromptTemplate: z.boolean().optional().default(false),
});
export type UpsertAgentInstructionsFile = z.infer<typeof upsertAgentInstructionsFileSchema>;
const adapterConfigSchema = z.record(z.string(), z.unknown()).superRefine((value, ctx) => {
const envValue = value.env;
if (envValue === undefined) return;
const parsed = envConfigSchema.safeParse(envValue);
if (!parsed.success) {
ctx.addIssue({
code: z.ZodIssueCode.custom,
message: "adapterConfig.env must be a map of valid env bindings",
path: ["env"],
});
}
});
export const createAgentInstructionsBundleSchema = z.object({
entryFile: z.string().trim().min(1).optional(),
files: z.record(z.string(), z.string()).refine((files) => Object.keys(files).length > 0, {
message: "instructionsBundle.files must contain at least one file",
}),
});
const agentModelProfileConfigSchema = z.object({
enabled: z.boolean().optional(),
label: z.string().trim().min(1).optional(),
// Disabled profiles created before model-profile editing may not have an
// adapter payload yet. Keep them valid so unrelated runtime settings (such
// as debug capture) can be updated without fabricating model configuration.
adapterConfig: adapterConfigSchema.optional().default({}),
}).strict();
export const agentRuntimeConfigSchema = z.object({
modelProfiles: z.object({
cheap: agentModelProfileConfigSchema.optional(),
}).strict().optional(),
debug: z.object({
providerTrace: z.literal("raw").optional(),
}).strict().optional(),
}).catchall(z.unknown());
export const createAgentSchema = z.object({
name: z.string().min(1),
role: z.enum(AGENT_ROLES).optional().default("general"),
title: z.string().optional().nullable(),
icon: z.enum(AGENT_ICON_NAMES).optional().nullable(),
reportsTo: z.string().guid().optional().nullable(),
capabilities: z.string().optional().nullable(),
desiredSkills: z.array(agentDesiredSkillSelectionSchema).optional(),
adapterType: agentAdapterTypeSchema,
adapterConfig: adapterConfigSchema.optional().default({}),
instructionsBundle: createAgentInstructionsBundleSchema.optional(),
runtimeConfig: agentRuntimeConfigSchema.optional().default({}),
defaultEnvironmentId: z.string().guid().optional().nullable(),
budgetMonthlyCents: z.number().int().nonnegative().optional().default(0),
permissions: agentPermissionsSchema.optional(),
metadata: z.record(z.string(), z.unknown()).optional().nullable(),
// The optional stored-session claim from a completed Claude login session. It
// is the non-secret `storedSessionId`; it carries no token. The agent-create
// transaction consumes it as the one-time stored-session claim.
storedSessionId: z.string().min(1).max(256).optional(),
// The optional apply-existing flag. When true, the caller binds the fixed
// Claude OAuth token reference to the owner stored value with no new login
// round trip. The server permits the no-claim bind only for a user actor and
// only when that owner already has a stored value. It carries no token.
applyStoredClaudeLogin: z.boolean().optional(),
});
export type CreateAgent = z.infer<typeof createAgentSchema>;
export const builtInAgentProvisionSchema = z.object({
adapterType: agentAdapterTypeSchema.optional(),
adapterConfig: adapterConfigSchema.optional(),
budgetMonthlyCents: z.number().int().nonnegative().optional(),
}).strict();
export type BuiltInAgentProvision = z.infer<typeof builtInAgentProvisionSchema>;
export const builtInAgentEmptyMutationSchema = z.object({}).strict().default({});
export type BuiltInAgentEmptyMutation = z.infer<typeof builtInAgentEmptyMutationSchema>;
export const builtInAgentResetSchema = z.object({
resources: z.array(z.enum(["agent", "instructions", "skill", "routine"])).optional(),
}).strict().default({});
export type BuiltInAgentReset = z.infer<typeof builtInAgentResetSchema>;
export const createAgentHireSchema = createAgentSchema.extend({
sourceIssueId: z.string().guid().optional().nullable(),
sourceIssueIds: z.array(z.string().guid()).optional(),
});
export type CreateAgentHire = z.infer<typeof createAgentHireSchema>;
export const updateAgentSchema = objectWithoutDefaults(
createAgentSchema.omit({ permissions: true }),
)
.partial()
.extend({
permissions: z.never().optional(),
replaceAdapterConfig: z.boolean().optional(),
status: z.enum(AGENT_STATUSES).optional(),
spentMonthlyCents: z.number().int().nonnegative().optional(),
});
export type UpdateAgent = z.infer<typeof updateAgentSchema>;
export const updateAgentInstructionsPathSchema = z.object({
path: z.string().trim().min(1).nullable(),
adapterConfigKey: z.string().trim().min(1).optional(),
});
export type UpdateAgentInstructionsPath = z.infer<typeof updateAgentInstructionsPathSchema>;
export const taskBridgeAgentKeyScopeSchema = z.object({
kind: z.literal("task_bridge"),
projectId: z.string().guid().optional().nullable(),
projectIds: z.array(z.string().guid()).max(50).optional(),
parentIssueId: z.string().guid().optional().nullable(),
parentIssueIds: z.array(z.string().guid()).max(50).optional(),
allowedAssigneeAgentIds: z.array(z.string().guid()).max(50).optional(),
}).strict().superRefine((value, ctx) => {
const hasProjectBoundary = Boolean(value.projectId) || Boolean(value.projectIds?.length);
const hasParentBoundary = Boolean(value.parentIssueId) || Boolean(value.parentIssueIds?.length);
if (!hasProjectBoundary && !hasParentBoundary) {
ctx.addIssue({
code: z.ZodIssueCode.custom,
message: "task_bridge keys require at least one project or parent issue boundary",
path: ["projectId"],
});
}
});
export const standardAgentKeyScopeSchema = z.object({
kind: z.literal("standard"),
}).strict();
export const skillTestAgentKeyScopeSchema = z.object({
kind: z.literal("skill_test"),
issueId: z.string().guid(),
}).strict();
export const agentApiKeyScopeSchema = z.union([
standardAgentKeyScopeSchema,
taskBridgeAgentKeyScopeSchema,
skillTestAgentKeyScopeSchema,
]);
export type AgentApiKeyScope = z.infer<typeof agentApiKeyScopeSchema>;
export type TaskBridgeAgentKeyScope = z.infer<typeof taskBridgeAgentKeyScopeSchema>;
export type SkillTestAgentKeyScope = z.infer<typeof skillTestAgentKeyScopeSchema>;
export function normalizeAgentApiKeyScope(value: unknown): AgentApiKeyScope {
const parsed = agentApiKeyScopeSchema.safeParse(value);
return parsed.success ? parsed.data : { kind: "standard" };
}
export const createAgentKeySchema = z.object({
name: z.string().min(1).default("default"),
scope: agentApiKeyScopeSchema.optional().default({ kind: "standard" }),
});
export type CreateAgentKey = z.infer<typeof createAgentKeySchema>;
export const agentMineInboxQuerySchema = z.object({
userId: z.string().trim().min(1),
status: z.string().trim().min(1).optional().default(INBOX_MINE_ISSUE_STATUS_FILTER),
});
export type AgentMineInboxQuery = z.infer<typeof agentMineInboxQuerySchema>;
export const wakeAgentSchema = z.object({
source: z.enum(["timer", "assignment", "on_demand", "automation"]).optional().default("on_demand"),
triggerDetail: z.enum(["manual", "ping", "callback", "system"]).optional(),
reason: z.string().optional().nullable(),
payload: z.record(z.string(), z.unknown()).optional().nullable(),
idempotencyKey: z.string().optional().nullable(),
forceFreshSession: z.preprocess(
(value) => (value === null ? undefined : value),
z.boolean().optional().default(false),
),
debug: z.object({
providerTrace: z.literal("raw"),
}).strict().optional(),
});
export type WakeAgent = z.infer<typeof wakeAgentSchema>;
export const resetAgentSessionSchema = z.object({
taskKey: z.string().min(1).optional().nullable(),
});
export type ResetAgentSession = z.infer<typeof resetAgentSessionSchema>;
export const testAdapterEnvironmentSchema = z.object({
adapterConfig: adapterConfigSchema.optional().default({}),
/**
* Optional environment to run the adapter test inside. When omitted, the
* test runs against the local Paperclip host. When provided and the
* environment is non-local (SSH/sandbox), the test probes are executed
* inside that environment so the result reflects real agent execution.
*/
environmentId: z.string().guid().optional().nullable(),
});
export type TestAdapterEnvironment = z.infer<typeof testAdapterEnvironmentSchema>;
export const updateAgentPermissionsSchema = z.object({
canCreateAgents: z.boolean(),
canCreateSkills: z.boolean().optional(),
canAssignTasks: z.boolean(),
trustPreset: trustPresetSchema.optional(),
authorizationPolicy: trustAuthorizationPolicySchema.optional(),
});
export type UpdateAgentPermissions = z.infer<typeof updateAgentPermissionsSchema>;