[codex] Harden plugin runtime invocation scope (#6547)

## Thinking Path

> - Paperclip orchestrates AI-agent companies through a company-scoped
control plane.
> - Plugins extend that control plane, but plugin workers still call
back into host APIs.
> - Those worker-to-host calls need the same company boundary guarantees
as normal API routes.
> - Plugin action handlers also need authenticated actor context from
the host instead of trusting caller-supplied params.
> - This pull request hardens plugin bridge/action scope and keeps
plugin operation issues out of normal issue surfaces.
> - The benefit is safer plugin execution with clearer authorization
boundaries and better test coverage.

## What Changed

- Added host-owned invocation context plumbing for nested plugin worker
calls.
- Added actor context to plugin `performAction` calls and test harness
helpers.
- Enforced company invocation scope on worker-to-host calls and filtered
company lists to the active invocation scope.
- Extended plugin action route tests for board and agent actor context,
spoofed company params, and cross-company rejection.
- Extended plugin worker manager coverage for invocation-scope
propagation.
- Filtered typed and legacy plugin operation issue origins from default
issue/inbox lists.

## Verification

- `pnpm --filter @paperclipai/plugin-sdk build`
- `NODE_ENV=test pnpm exec vitest run
packages/plugins/sdk/tests/host-client-factory.test.ts
packages/plugins/sdk/tests/testing-actions.test.ts
server/src/__tests__/plugin-routes-authz.test.ts
server/src/__tests__/plugin-worker-manager.test.ts
server/src/__tests__/issues-service.test.ts`

Note: embedded Postgres issue-service tests reported host-level Postgres
init skip for 47 tests; the non-embedded targeted tests passed.

## Risks

- Medium: plugin host authorization paths are sensitive, and external
plugins may rely on previously loose company params.
- Mitigation: the change only tightens calls when the host attached a
company invocation scope and includes explicit tests for board, agent,
and nested worker calls.

> 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 GPT-5 Codex via `codex_local`, tool-enabled coding session;
exact context window not exposed by this runtime.

## 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
- [x] 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
This commit is contained in:
Dotta 2026-05-22 09:16:24 -05:00 committed by GitHub
parent 38c185fb8b
commit a1835cfa5e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
18 changed files with 749 additions and 30 deletions

View file

@ -57,6 +57,8 @@ import type {
PluginEnvironmentRealizeWorkspaceResult,
PluginEnvironmentExecuteParams,
PluginEnvironmentExecuteResult,
PluginPerformActionActorContext,
PluginPerformActionContext,
} from "./protocol.js";
export interface TestHarnessOptions {
@ -74,6 +76,20 @@ export interface TestHarnessLogEntry {
meta?: Record<string, unknown>;
}
export interface TestHarnessPerformActionOptions {
/**
* Authenticated actor context to expose to the action handler. Omitted fields
* default to null, and `type` defaults to `system`.
*/
actor?: Partial<PluginPerformActionActorContext> | null;
/**
* Host-authorized company scope. When provided, this is injected into
* `params.companyId` so tests match the production bridge's anti-spoofing
* behavior.
*/
companyId?: string | null;
}
export interface TestHarness {
/** Fully-typed in-memory plugin context passed to `plugin.setup(ctx)`. */
ctx: PluginContext;
@ -98,7 +114,11 @@ export interface TestHarness {
/** Invoke a `ctx.data.register(...)` handler by key. */
getData<T = unknown>(key: string, params?: Record<string, unknown>): Promise<T>;
/** Invoke a `ctx.actions.register(...)` handler by key. */
performAction<T = unknown>(key: string, params?: Record<string, unknown>): Promise<T>;
performAction<T = unknown>(
key: string,
params?: Record<string, unknown>,
options?: TestHarnessPerformActionOptions,
): Promise<T>;
/** Execute a registered tool handler via `ctx.tools.execute(...)`. */
executeTool<T = ToolResult>(name: string, params: unknown, runCtx?: Partial<ToolRunContext>): Promise<T>;
/** Read raw in-memory state for assertions. */
@ -491,7 +511,10 @@ export function createTestHarness(options: TestHarnessOptions): TestHarness {
const jobs = new Map<string, (job: PluginJobContext) => Promise<void>>();
const launchers = new Map<string, PluginLauncherRegistration>();
const dataHandlers = new Map<string, (params: Record<string, unknown>) => Promise<unknown>>();
const actionHandlers = new Map<string, (params: Record<string, unknown>) => Promise<unknown>>();
const actionHandlers = new Map<
string,
(params: Record<string, unknown>, context: PluginPerformActionContext) => Promise<unknown>
>();
const toolHandlers = new Map<string, (params: unknown, runCtx: ToolRunContext) => Promise<ToolResult>>();
function localFolderKey(companyId: string, folderKey: string): string {
@ -502,6 +525,41 @@ export function createTestHarness(options: TestHarnessOptions): TestHarness {
return `${localFolderKey(companyId, folderKey)}:${relativePath}`;
}
function stringOrNull(value: unknown): string | null {
return typeof value === "string" && value.trim().length > 0 ? value.trim() : null;
}
function actorTypeOrSystem(value: unknown): PluginPerformActionActorContext["type"] {
return value === "user" || value === "agent" || value === "system" ? value : "system";
}
function actionContextFor(
params: Record<string, unknown>,
options?: TestHarnessPerformActionOptions,
): PluginPerformActionContext {
const actorInput = options?.actor ?? null;
const companyId = stringOrNull(options?.companyId) ?? stringOrNull(actorInput?.companyId) ?? stringOrNull(params.companyId);
const actor = Object.freeze({
type: actorTypeOrSystem(actorInput?.type),
userId: stringOrNull(actorInput?.userId),
agentId: stringOrNull(actorInput?.agentId),
runId: stringOrNull(actorInput?.runId),
companyId,
});
return Object.freeze({ actor, companyId });
}
function paramsWithHostCompanyScope(
params: Record<string, unknown>,
context: PluginPerformActionContext,
options?: TestHarnessPerformActionOptions,
): Record<string, unknown> {
if (Object.prototype.hasOwnProperty.call(options ?? {}, "companyId")) {
return context.companyId ? { ...params, companyId: context.companyId } : { ...params };
}
return params;
}
function normalizeLocalFolderRelativePath(relativePath: string): string {
const parts: string[] = [];
for (const segment of relativePath.split(/[\\/]+/)) {
@ -2302,10 +2360,15 @@ export function createTestHarness(options: TestHarnessOptions): TestHarness {
if (!handler) throw new Error(`No data handler registered for '${key}'`);
return await handler(params) as T;
},
async performAction<T = unknown>(key: string, params: Record<string, unknown> = {}) {
async performAction<T = unknown>(
key: string,
params: Record<string, unknown> = {},
options?: TestHarnessPerformActionOptions,
) {
const handler = actionHandlers.get(key);
if (!handler) throw new Error(`No action handler registered for '${key}'`);
return await handler(params) as T;
const context = actionContextFor(params, options);
return await handler(paramsWithHostCompanyScope(params, context, options), context) as T;
},
async executeTool<T = ToolResult>(name: string, params: unknown, runCtx: Partial<ToolRunContext> = {}) {
const handler = toolHandlers.get(name);