Add sandbox environment support (#4415)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The environment/runtime layer decides where agent work executes and
how the control plane reaches those runtimes.
> - Today Paperclip can run locally and over SSH, but sandboxed
execution needs a first-class environment model instead of one-off
adapter behavior.
> - We also want sandbox providers to be pluggable so the core does not
hardcode every provider implementation.
> - This branch adds the Sandbox environment path, the provider
contract, and a deterministic fake provider plugin.
> - That required synchronized changes across shared contracts, plugin
SDK surfaces, server runtime orchestration, and the UI
environment/workspace flows.
> - The result is that sandbox execution becomes a core control-plane
capability while keeping provider implementations extensible and
testable.
## What Changed
- Added sandbox runtime support to the environment execution path,
including runtime URL discovery, sandbox execution targeting,
orchestration, and heartbeat integration.
- Added plugin-provider support for sandbox environments so providers
can be supplied via plugins instead of hardcoded server logic.
- Added the fake sandbox provider plugin with deterministic behavior
suitable for local and automated testing.
- Updated shared types, validators, plugin protocol definitions, and SDK
helpers to carry sandbox provider and workspace-runtime contracts across
package boundaries.
- Updated server routes and services so companies can create sandbox
environments, select them for work, and execute work through the sandbox
runtime path.
- Updated the UI environment and workspace surfaces to expose sandbox
environment configuration and selection.
- Added test coverage for sandbox runtime behavior, provider seams,
environment route guards, orchestration, and the fake provider plugin.
## Verification
- Ran locally before the final fixture-only scrub:
- `pnpm -r typecheck`
- `pnpm test:run`
- `pnpm build`
- Ran locally after the final scrub amend:
- `pnpm vitest run server/src/__tests__/runtime-api.test.ts`
- Reviewer spot checks:
- create a sandbox environment backed by the fake provider plugin
- run work through that environment
- confirm sandbox provider execution does not inherit host secrets
implicitly
## Risks
- This touches shared contracts, plugin SDK plumbing, server runtime
orchestration, and UI environment/workspace flows, so regressions would
likely show up as cross-layer mismatches rather than isolated type
errors.
- Runtime URL discovery and sandbox callback selection are sensitive to
host/bind configuration; if that logic is wrong, sandbox-backed
callbacks may fail even when execution succeeds.
- The fake provider plugin is intentionally deterministic and
test-oriented; future providers may expose capability gaps that this
branch does not yet cover.
## Model Used
- OpenAI Codex coding agent on a GPT-5-class backend in the
Paperclip/Codex harness. Exact backend model ID is not exposed
in-session. Tool-assisted workflow with shell execution, file editing,
git history inspection, and local test execution.
## 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
2026-04-24 12:15:53 -07:00
|
|
|
import { randomUUID } from "node:crypto";
|
|
|
|
|
import type {
|
|
|
|
|
EnvironmentLeaseStatus,
|
|
|
|
|
EnvironmentProbeResult,
|
|
|
|
|
FakeSandboxEnvironmentConfig,
|
|
|
|
|
SandboxEnvironmentConfig,
|
|
|
|
|
SandboxEnvironmentProvider,
|
|
|
|
|
} from "@paperclipai/shared";
|
|
|
|
|
|
|
|
|
|
export interface SandboxProviderValidationResult {
|
|
|
|
|
ok: boolean;
|
|
|
|
|
summary: string;
|
|
|
|
|
details?: Record<string, unknown>;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface AcquireSandboxLeaseInput {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
environmentId: string;
|
|
|
|
|
heartbeatRunId: string;
|
|
|
|
|
issueId: string | null;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface ResumeSandboxLeaseInput {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface ReleaseSandboxLeaseInput {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string | null;
|
|
|
|
|
status: Extract<EnvironmentLeaseStatus, "released" | "expired" | "failed">;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface DestroySandboxLeaseInput {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string | null;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface PrepareSandboxWorkspaceInput {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string | null;
|
|
|
|
|
workspace: {
|
|
|
|
|
localPath?: string;
|
|
|
|
|
remotePath?: string;
|
|
|
|
|
mode?: string;
|
|
|
|
|
metadata?: Record<string, unknown>;
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface SandboxExecuteInput {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string | null;
|
|
|
|
|
command: string;
|
|
|
|
|
args?: string[];
|
|
|
|
|
cwd?: string;
|
|
|
|
|
env?: Record<string, string>;
|
|
|
|
|
stdin?: string;
|
|
|
|
|
timeoutMs?: number;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface SandboxLeaseHandle {
|
|
|
|
|
providerLeaseId: string;
|
|
|
|
|
metadata: Record<string, unknown>;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface PreparedSandboxWorkspace {
|
|
|
|
|
remotePath?: string | null;
|
|
|
|
|
metadata?: Record<string, unknown>;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface SandboxExecuteResult {
|
|
|
|
|
exitCode: number | null;
|
|
|
|
|
stdout: string;
|
|
|
|
|
stderr: string;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export interface SandboxProvider {
|
|
|
|
|
readonly provider: SandboxEnvironmentProvider;
|
|
|
|
|
validateConfig(config: SandboxEnvironmentConfig): Promise<SandboxProviderValidationResult>;
|
|
|
|
|
probe(config: SandboxEnvironmentConfig): Promise<EnvironmentProbeResult>;
|
|
|
|
|
acquireLease(input: AcquireSandboxLeaseInput): Promise<SandboxLeaseHandle>;
|
|
|
|
|
resumeLease(input: ResumeSandboxLeaseInput): Promise<SandboxLeaseHandle | null>;
|
|
|
|
|
releaseLease(input: ReleaseSandboxLeaseInput): Promise<void>;
|
|
|
|
|
destroyLease(input: DestroySandboxLeaseInput): Promise<void>;
|
|
|
|
|
matchesReusableLease(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
lease: { providerLeaseId: string | null; metadata: Record<string, unknown> | null };
|
|
|
|
|
}): boolean;
|
|
|
|
|
configFromLeaseMetadata(metadata: Record<string, unknown>): SandboxEnvironmentConfig | null;
|
|
|
|
|
prepareWorkspace?(input: PrepareSandboxWorkspaceInput): Promise<PreparedSandboxWorkspace>;
|
|
|
|
|
execute?(input: SandboxExecuteInput): Promise<SandboxExecuteResult>;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function assertProviderConfig<T extends SandboxEnvironmentConfig>(
|
|
|
|
|
provider: SandboxEnvironmentProvider,
|
|
|
|
|
config: SandboxEnvironmentConfig,
|
|
|
|
|
): asserts config is T {
|
|
|
|
|
if (config.provider !== provider) {
|
|
|
|
|
throw new Error(`Sandbox provider "${provider}" received config for provider "${config.provider}".`);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function buildFakeSandboxProbe(config: FakeSandboxEnvironmentConfig): EnvironmentProbeResult {
|
|
|
|
|
return {
|
|
|
|
|
ok: true,
|
|
|
|
|
driver: "sandbox",
|
|
|
|
|
summary: `Fake sandbox provider is ready for image ${config.image}.`,
|
|
|
|
|
details: {
|
|
|
|
|
provider: config.provider,
|
|
|
|
|
image: config.image,
|
|
|
|
|
reuseLease: config.reuseLease,
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
class FakeSandboxProvider implements SandboxProvider {
|
|
|
|
|
readonly provider = "fake" as const;
|
|
|
|
|
|
|
|
|
|
async validateConfig(config: SandboxEnvironmentConfig): Promise<SandboxProviderValidationResult> {
|
|
|
|
|
assertProviderConfig<FakeSandboxEnvironmentConfig>(this.provider, config);
|
|
|
|
|
return {
|
|
|
|
|
ok: true,
|
|
|
|
|
summary: `Fake sandbox provider config is valid for image ${config.image}.`,
|
|
|
|
|
details: {
|
|
|
|
|
provider: config.provider,
|
|
|
|
|
image: config.image,
|
|
|
|
|
reuseLease: config.reuseLease,
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async probe(config: SandboxEnvironmentConfig): Promise<EnvironmentProbeResult> {
|
|
|
|
|
assertProviderConfig<FakeSandboxEnvironmentConfig>(this.provider, config);
|
|
|
|
|
return buildFakeSandboxProbe(config);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async acquireLease(input: AcquireSandboxLeaseInput): Promise<SandboxLeaseHandle> {
|
|
|
|
|
assertProviderConfig<FakeSandboxEnvironmentConfig>(this.provider, input.config);
|
|
|
|
|
const providerLeaseId = input.config.reuseLease
|
|
|
|
|
? `sandbox://fake/${input.environmentId}`
|
|
|
|
|
: `sandbox://fake/${input.heartbeatRunId}/${randomUUID()}`;
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
providerLeaseId,
|
|
|
|
|
metadata: {
|
|
|
|
|
provider: input.config.provider,
|
|
|
|
|
image: input.config.image,
|
|
|
|
|
reuseLease: input.config.reuseLease,
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async resumeLease(input: ResumeSandboxLeaseInput): Promise<SandboxLeaseHandle | null> {
|
|
|
|
|
assertProviderConfig<FakeSandboxEnvironmentConfig>(this.provider, input.config);
|
|
|
|
|
return {
|
|
|
|
|
providerLeaseId: input.providerLeaseId,
|
|
|
|
|
metadata: {
|
|
|
|
|
provider: input.config.provider,
|
|
|
|
|
image: input.config.image,
|
|
|
|
|
reuseLease: input.config.reuseLease,
|
|
|
|
|
resumedLease: true,
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async releaseLease(): Promise<void> {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async destroyLease(): Promise<void> {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
matchesReusableLease(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
lease: { providerLeaseId: string | null; metadata: Record<string, unknown> | null };
|
|
|
|
|
}): boolean {
|
|
|
|
|
assertProviderConfig<FakeSandboxEnvironmentConfig>(this.provider, input.config);
|
|
|
|
|
return (
|
|
|
|
|
typeof input.lease.providerLeaseId === "string" &&
|
|
|
|
|
input.lease.providerLeaseId.length > 0 &&
|
|
|
|
|
input.lease.metadata?.provider === input.config.provider &&
|
|
|
|
|
input.lease.metadata?.reuseLease === true &&
|
|
|
|
|
input.lease.metadata?.image === input.config.image
|
|
|
|
|
);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
configFromLeaseMetadata(metadata: Record<string, unknown>): SandboxEnvironmentConfig | null {
|
|
|
|
|
if (metadata.provider !== this.provider || typeof metadata.image !== "string") {
|
|
|
|
|
return null;
|
|
|
|
|
}
|
|
|
|
|
return {
|
|
|
|
|
provider: this.provider,
|
|
|
|
|
image: metadata.image,
|
|
|
|
|
reuseLease: metadata.reuseLease === true,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// ---------------------------------------------------------------------------
|
|
|
|
|
// Provider registry — built-in providers only.
|
|
|
|
|
// Plugin-backed providers are resolved through the plugin environment driver
|
|
|
|
|
// system at the environment-runtime layer.
|
|
|
|
|
// ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
const registeredSandboxProviders = new Map<SandboxEnvironmentProvider, SandboxProvider>([
|
|
|
|
|
["fake", new FakeSandboxProvider()],
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Returns a built-in sandbox provider, or null if the provider key is not
|
|
|
|
|
* registered. Plugin-backed providers are not returned here — they are
|
|
|
|
|
* resolved through the plugin worker manager at the environment-runtime level.
|
|
|
|
|
*/
|
|
|
|
|
export function getSandboxProvider(provider: string): SandboxProvider | null {
|
|
|
|
|
return registeredSandboxProviders.get(provider as SandboxEnvironmentProvider) ?? null;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export function requireSandboxProvider(provider: string): SandboxProvider {
|
|
|
|
|
const sandboxProvider = getSandboxProvider(provider);
|
|
|
|
|
if (!sandboxProvider) {
|
|
|
|
|
throw new Error(`Sandbox provider "${provider}" is not registered as a built-in provider.`);
|
|
|
|
|
}
|
|
|
|
|
return sandboxProvider;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Returns true if the given provider key is handled by a built-in sandbox
|
|
|
|
|
* provider (as opposed to a plugin-backed provider).
|
|
|
|
|
*/
|
|
|
|
|
export function isBuiltinSandboxProvider(provider: string): boolean {
|
|
|
|
|
return registeredSandboxProviders.has(provider as SandboxEnvironmentProvider);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export function listSandboxProviders(): SandboxProvider[] {
|
|
|
|
|
return [...registeredSandboxProviders.values()];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export async function validateSandboxProviderConfig(
|
|
|
|
|
config: SandboxEnvironmentConfig,
|
|
|
|
|
): Promise<SandboxProviderValidationResult> {
|
|
|
|
|
return await requireSandboxProvider(config.provider).validateConfig(config);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export function sandboxConfigFromLeaseMetadata(
|
|
|
|
|
lease: Pick<{ metadata: Record<string, unknown> | null }, "metadata">,
|
|
|
|
|
): SandboxEnvironmentConfig | null {
|
|
|
|
|
const metadata = lease.metadata ?? {};
|
|
|
|
|
const provider = typeof metadata.provider === "string" ? getSandboxProvider(metadata.provider) : null;
|
|
|
|
|
return provider?.configFromLeaseMetadata(metadata) ?? null;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Reconstruct a sandbox environment config from lease metadata, including
|
|
|
|
|
* plugin-backed providers. For plugin-backed providers, the
|
|
|
|
|
* config is synthesized from lease metadata fields without requiring the
|
|
|
|
|
* built-in provider to be registered.
|
|
|
|
|
*/
|
|
|
|
|
export function sandboxConfigFromLeaseMetadataLoose(
|
|
|
|
|
lease: Pick<{ metadata: Record<string, unknown> | null }, "metadata">,
|
|
|
|
|
): SandboxEnvironmentConfig | null {
|
|
|
|
|
const metadata = lease.metadata ?? {};
|
|
|
|
|
const providerKey = typeof metadata.provider === "string" ? metadata.provider : null;
|
|
|
|
|
if (!providerKey) return null;
|
|
|
|
|
|
|
|
|
|
// Try built-in provider first.
|
|
|
|
|
const builtinProvider = getSandboxProvider(providerKey);
|
|
|
|
|
if (builtinProvider) {
|
|
|
|
|
return builtinProvider.configFromLeaseMetadata(metadata);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
...metadata,
|
|
|
|
|
provider: providerKey,
|
|
|
|
|
reuseLease: metadata.reuseLease === true,
|
|
|
|
|
} satisfies SandboxEnvironmentConfig;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export function findReusableSandboxProviderLeaseId(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
leases: Array<{ providerLeaseId: string | null; metadata: Record<string, unknown> | null }>;
|
|
|
|
|
}): string | null {
|
|
|
|
|
const provider = getSandboxProvider(input.config.provider);
|
|
|
|
|
if (!provider) {
|
|
|
|
|
for (const lease of input.leases) {
|
|
|
|
|
const metadata = lease.metadata ?? {};
|
|
|
|
|
if (
|
|
|
|
|
typeof lease.providerLeaseId === "string" &&
|
|
|
|
|
lease.providerLeaseId.length > 0 &&
|
|
|
|
|
metadata.provider === input.config.provider &&
|
Generalize sandbox provider core for plugin-only providers (#4449)
## Thinking Path
> - Paperclip is a control plane, so optional execution providers should
sit at the plugin edge instead of hardcoding provider-specific behavior
into core shared/server/ui layers.
> - Sandbox environments are already first-class, and the fake provider
proves the built-in path; the remaining gap was that real providers
still leaked provider-specific config and runtime assumptions into core.
> - That coupling showed up in config normalization, secret persistence,
capabilities reporting, lease reconstruction, and the board UI form
fields.
> - As long as core knew about those provider-shaped details, shipping a
provider as a pure third-party plugin meant every new provider would
still require host changes.
> - This pull request generalizes the sandbox provider seam around
schema-driven plugin metadata and generic secret-ref handling.
> - The runtime and UI now consume provider metadata generically, so
core only special-cases the built-in fake provider while third-party
providers can live entirely in plugins.
## What Changed
- Added generic sandbox-provider capability metadata so plugin-backed
providers can expose `configSchema` through shared environment support
and the environments capabilities API.
- Reworked sandbox config normalization/persistence/runtime resolution
to handle schema-declared secret-ref fields generically, storing them as
Paperclip secrets and resolving them for probe/execute/release flows.
- Generalized plugin sandbox runtime handling so provider validation,
reusable-lease matching, lease reconstruction, and plugin worker calls
all operate on provider-agnostic config instead of provider-shaped
branches.
- Replaced hardcoded sandbox provider form fields in Company Settings
with schema-driven rendering and blocked agent environment selection
from the built-in fake provider.
- Added regression coverage for the generic seam across shared support
helpers plus environment config, probe, routes, runtime, and
sandbox-provider runtime tests.
## Verification
- `pnpm vitest --run packages/shared/src/environment-support.test.ts
server/src/__tests__/environment-config.test.ts
server/src/__tests__/environment-probe.test.ts
server/src/__tests__/environment-routes.test.ts
server/src/__tests__/environment-runtime.test.ts
server/src/__tests__/sandbox-provider-runtime.test.ts`
- `pnpm -r typecheck`
## Risks
- Plugin sandbox providers now depend more heavily on accurate
`configSchema` declarations; incorrect schemas can misclassify
secret-bearing fields or omit required config.
- Reusable lease matching is now metadata-driven for plugin-backed
providers, so providers that fail to persist stable metadata may
reprovision instead of resuming an existing lease.
- The UI form is now fully schema-driven for plugin-backed sandbox
providers; provider manifests without good defaults or descriptions may
produce a rougher operator experience.
## Model Used
- OpenAI Codex via `codex_local`
- Model ID: `gpt-5.4`
- Reasoning effort: `high`
- Context window observed in runtime session metadata: `258400` tokens
- Capabilities used: terminal tool execution, git, and local code/test
inspection
## 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
2026-04-24 18:03:41 -07:00
|
|
|
metadataMatchesPluginSandboxConfig(input.config, metadata)
|
Add sandbox environment support (#4415)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The environment/runtime layer decides where agent work executes and
how the control plane reaches those runtimes.
> - Today Paperclip can run locally and over SSH, but sandboxed
execution needs a first-class environment model instead of one-off
adapter behavior.
> - We also want sandbox providers to be pluggable so the core does not
hardcode every provider implementation.
> - This branch adds the Sandbox environment path, the provider
contract, and a deterministic fake provider plugin.
> - That required synchronized changes across shared contracts, plugin
SDK surfaces, server runtime orchestration, and the UI
environment/workspace flows.
> - The result is that sandbox execution becomes a core control-plane
capability while keeping provider implementations extensible and
testable.
## What Changed
- Added sandbox runtime support to the environment execution path,
including runtime URL discovery, sandbox execution targeting,
orchestration, and heartbeat integration.
- Added plugin-provider support for sandbox environments so providers
can be supplied via plugins instead of hardcoded server logic.
- Added the fake sandbox provider plugin with deterministic behavior
suitable for local and automated testing.
- Updated shared types, validators, plugin protocol definitions, and SDK
helpers to carry sandbox provider and workspace-runtime contracts across
package boundaries.
- Updated server routes and services so companies can create sandbox
environments, select them for work, and execute work through the sandbox
runtime path.
- Updated the UI environment and workspace surfaces to expose sandbox
environment configuration and selection.
- Added test coverage for sandbox runtime behavior, provider seams,
environment route guards, orchestration, and the fake provider plugin.
## Verification
- Ran locally before the final fixture-only scrub:
- `pnpm -r typecheck`
- `pnpm test:run`
- `pnpm build`
- Ran locally after the final scrub amend:
- `pnpm vitest run server/src/__tests__/runtime-api.test.ts`
- Reviewer spot checks:
- create a sandbox environment backed by the fake provider plugin
- run work through that environment
- confirm sandbox provider execution does not inherit host secrets
implicitly
## Risks
- This touches shared contracts, plugin SDK plumbing, server runtime
orchestration, and UI environment/workspace flows, so regressions would
likely show up as cross-layer mismatches rather than isolated type
errors.
- Runtime URL discovery and sandbox callback selection are sensitive to
host/bind configuration; if that logic is wrong, sandbox-backed
callbacks may fail even when execution succeeds.
- The fake provider plugin is intentionally deterministic and
test-oriented; future providers may expose capability gaps that this
branch does not yet cover.
## Model Used
- OpenAI Codex coding agent on a GPT-5-class backend in the
Paperclip/Codex harness. Exact backend model ID is not exposed
in-session. Tool-assisted workflow with shell execution, file editing,
git history inspection, and local test execution.
## 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
2026-04-24 12:15:53 -07:00
|
|
|
) {
|
|
|
|
|
return lease.providerLeaseId;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return null;
|
|
|
|
|
}
|
|
|
|
|
for (const lease of input.leases) {
|
|
|
|
|
if (provider.matchesReusableLease({ config: input.config, lease })) {
|
|
|
|
|
return lease.providerLeaseId;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return null;
|
|
|
|
|
}
|
|
|
|
|
|
Generalize sandbox provider core for plugin-only providers (#4449)
## Thinking Path
> - Paperclip is a control plane, so optional execution providers should
sit at the plugin edge instead of hardcoding provider-specific behavior
into core shared/server/ui layers.
> - Sandbox environments are already first-class, and the fake provider
proves the built-in path; the remaining gap was that real providers
still leaked provider-specific config and runtime assumptions into core.
> - That coupling showed up in config normalization, secret persistence,
capabilities reporting, lease reconstruction, and the board UI form
fields.
> - As long as core knew about those provider-shaped details, shipping a
provider as a pure third-party plugin meant every new provider would
still require host changes.
> - This pull request generalizes the sandbox provider seam around
schema-driven plugin metadata and generic secret-ref handling.
> - The runtime and UI now consume provider metadata generically, so
core only special-cases the built-in fake provider while third-party
providers can live entirely in plugins.
## What Changed
- Added generic sandbox-provider capability metadata so plugin-backed
providers can expose `configSchema` through shared environment support
and the environments capabilities API.
- Reworked sandbox config normalization/persistence/runtime resolution
to handle schema-declared secret-ref fields generically, storing them as
Paperclip secrets and resolving them for probe/execute/release flows.
- Generalized plugin sandbox runtime handling so provider validation,
reusable-lease matching, lease reconstruction, and plugin worker calls
all operate on provider-agnostic config instead of provider-shaped
branches.
- Replaced hardcoded sandbox provider form fields in Company Settings
with schema-driven rendering and blocked agent environment selection
from the built-in fake provider.
- Added regression coverage for the generic seam across shared support
helpers plus environment config, probe, routes, runtime, and
sandbox-provider runtime tests.
## Verification
- `pnpm vitest --run packages/shared/src/environment-support.test.ts
server/src/__tests__/environment-config.test.ts
server/src/__tests__/environment-probe.test.ts
server/src/__tests__/environment-routes.test.ts
server/src/__tests__/environment-runtime.test.ts
server/src/__tests__/sandbox-provider-runtime.test.ts`
- `pnpm -r typecheck`
## Risks
- Plugin sandbox providers now depend more heavily on accurate
`configSchema` declarations; incorrect schemas can misclassify
secret-bearing fields or omit required config.
- Reusable lease matching is now metadata-driven for plugin-backed
providers, so providers that fail to persist stable metadata may
reprovision instead of resuming an existing lease.
- The UI form is now fully schema-driven for plugin-backed sandbox
providers; provider manifests without good defaults or descriptions may
produce a rougher operator experience.
## Model Used
- OpenAI Codex via `codex_local`
- Model ID: `gpt-5.4`
- Reasoning effort: `high`
- Context window observed in runtime session metadata: `258400` tokens
- Capabilities used: terminal tool execution, git, and local code/test
inspection
## 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
2026-04-24 18:03:41 -07:00
|
|
|
function metadataMatchesPluginSandboxConfig(
|
|
|
|
|
config: SandboxEnvironmentConfig,
|
|
|
|
|
metadata: Record<string, unknown>,
|
|
|
|
|
): boolean {
|
|
|
|
|
if (metadata.reuseLease !== true) return false;
|
|
|
|
|
for (const [key, value] of Object.entries(config)) {
|
|
|
|
|
if (key === "provider" || key === "reuseLease") continue;
|
|
|
|
|
if (value === undefined) continue;
|
|
|
|
|
if (JSON.stringify(metadata[key]) !== JSON.stringify(value)) {
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
|
Add sandbox environment support (#4415)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The environment/runtime layer decides where agent work executes and
how the control plane reaches those runtimes.
> - Today Paperclip can run locally and over SSH, but sandboxed
execution needs a first-class environment model instead of one-off
adapter behavior.
> - We also want sandbox providers to be pluggable so the core does not
hardcode every provider implementation.
> - This branch adds the Sandbox environment path, the provider
contract, and a deterministic fake provider plugin.
> - That required synchronized changes across shared contracts, plugin
SDK surfaces, server runtime orchestration, and the UI
environment/workspace flows.
> - The result is that sandbox execution becomes a core control-plane
capability while keeping provider implementations extensible and
testable.
## What Changed
- Added sandbox runtime support to the environment execution path,
including runtime URL discovery, sandbox execution targeting,
orchestration, and heartbeat integration.
- Added plugin-provider support for sandbox environments so providers
can be supplied via plugins instead of hardcoded server logic.
- Added the fake sandbox provider plugin with deterministic behavior
suitable for local and automated testing.
- Updated shared types, validators, plugin protocol definitions, and SDK
helpers to carry sandbox provider and workspace-runtime contracts across
package boundaries.
- Updated server routes and services so companies can create sandbox
environments, select them for work, and execute work through the sandbox
runtime path.
- Updated the UI environment and workspace surfaces to expose sandbox
environment configuration and selection.
- Added test coverage for sandbox runtime behavior, provider seams,
environment route guards, orchestration, and the fake provider plugin.
## Verification
- Ran locally before the final fixture-only scrub:
- `pnpm -r typecheck`
- `pnpm test:run`
- `pnpm build`
- Ran locally after the final scrub amend:
- `pnpm vitest run server/src/__tests__/runtime-api.test.ts`
- Reviewer spot checks:
- create a sandbox environment backed by the fake provider plugin
- run work through that environment
- confirm sandbox provider execution does not inherit host secrets
implicitly
## Risks
- This touches shared contracts, plugin SDK plumbing, server runtime
orchestration, and UI environment/workspace flows, so regressions would
likely show up as cross-layer mismatches rather than isolated type
errors.
- Runtime URL discovery and sandbox callback selection are sensitive to
host/bind configuration; if that logic is wrong, sandbox-backed
callbacks may fail even when execution succeeds.
- The fake provider plugin is intentionally deterministic and
test-oriented; future providers may expose capability gaps that this
branch does not yet cover.
## Model Used
- OpenAI Codex coding agent on a GPT-5-class backend in the
Paperclip/Codex harness. Exact backend model ID is not exposed
in-session. Tool-assisted workflow with shell execution, file editing,
git history inspection, and local test execution.
## 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
2026-04-24 12:15:53 -07:00
|
|
|
export async function probeSandboxProvider(
|
|
|
|
|
config: SandboxEnvironmentConfig,
|
|
|
|
|
): Promise<EnvironmentProbeResult> {
|
|
|
|
|
return await requireSandboxProvider(config.provider).probe(config);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export async function acquireSandboxProviderLease(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
environmentId: string;
|
|
|
|
|
heartbeatRunId: string;
|
|
|
|
|
issueId: string | null;
|
|
|
|
|
reusableProviderLeaseId?: string | null;
|
|
|
|
|
}): Promise<SandboxLeaseHandle> {
|
|
|
|
|
const provider = requireSandboxProvider(input.config.provider);
|
|
|
|
|
if (input.config.reuseLease && input.reusableProviderLeaseId) {
|
|
|
|
|
const resumedLease = await provider.resumeLease({
|
|
|
|
|
config: input.config,
|
|
|
|
|
providerLeaseId: input.reusableProviderLeaseId,
|
|
|
|
|
});
|
|
|
|
|
if (resumedLease) {
|
|
|
|
|
return resumedLease;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return await provider.acquireLease({
|
|
|
|
|
config: input.config,
|
|
|
|
|
environmentId: input.environmentId,
|
|
|
|
|
heartbeatRunId: input.heartbeatRunId,
|
|
|
|
|
issueId: input.issueId,
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export async function resumeSandboxProviderLease(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string;
|
|
|
|
|
}): Promise<SandboxLeaseHandle | null> {
|
|
|
|
|
return await requireSandboxProvider(input.config.provider).resumeLease(input);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export async function releaseSandboxProviderLease(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string | null;
|
|
|
|
|
status: Extract<EnvironmentLeaseStatus, "released" | "expired" | "failed">;
|
|
|
|
|
}): Promise<void> {
|
|
|
|
|
await requireSandboxProvider(input.config.provider).releaseLease(input);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
export async function destroySandboxProviderLease(input: {
|
|
|
|
|
config: SandboxEnvironmentConfig;
|
|
|
|
|
providerLeaseId: string | null;
|
|
|
|
|
}): Promise<void> {
|
|
|
|
|
await requireSandboxProvider(input.config.provider).destroyLease(input);
|
|
|
|
|
}
|