paperclip/server/src/__tests__/execution-workspaces-service.test.ts

448 lines
14 KiB
TypeScript
Raw Normal View History

import { execFile } from "node:child_process";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { randomUUID } from "node:crypto";
import { promisify } from "node:util";
import { afterAll, afterEach, beforeAll, describe, expect, it } from "vitest";
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
import { inArray } from "drizzle-orm";
import {
companies,
createDb,
executionWorkspaces,
issues,
projectWorkspaces,
projects,
} from "@paperclipai/db";
import {
getEmbeddedPostgresTestSupport,
startEmbeddedPostgresTestDatabase,
} from "./helpers/embedded-postgres.js";
import {
executionWorkspaceService,
mergeExecutionWorkspaceConfig,
readExecutionWorkspaceConfig,
} from "../services/execution-workspaces.ts";
const execFileAsync = promisify(execFile);
describe("execution workspace config helpers", () => {
it("reads typed config from persisted metadata", () => {
expect(readExecutionWorkspaceConfig({
source: "project_primary",
config: {
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
environmentId: "32e0464c-2a0b-4ce9-886d-2cc99e6f3e7b",
provisionCommand: "bash ./scripts/provision-worktree.sh",
teardownCommand: "bash ./scripts/teardown-worktree.sh",
cleanupCommand: "pkill -f vite || true",
workspaceRuntime: {
services: [{ name: "web", command: "pnpm dev", port: 3100 }],
},
},
})).toEqual({
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
environmentId: "32e0464c-2a0b-4ce9-886d-2cc99e6f3e7b",
provisionCommand: "bash ./scripts/provision-worktree.sh",
teardownCommand: "bash ./scripts/teardown-worktree.sh",
cleanupCommand: "pkill -f vite || true",
desiredState: null,
[codex] Improve workspace runtime and navigation ergonomics (#3680) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - That operator experience depends not just on issue chat, but also on how workspaces, inbox groups, and navigation state behave over long-running sessions > - The current branch included a separate cluster of workspace-runtime controls, inbox grouping, sidebar ordering, and worktree lifecycle fixes > - Those changes cross server, shared contracts, database state, and UI navigation, but they still form one coherent operator workflow area > - This pull request isolates the workspace/runtime and navigation ergonomics work into one standalone branch > - The benefit is better workspace recovery and navigation persistence without forcing reviewers through the unrelated issue-detail/chat work ## What Changed - Improved execution workspace and project workspace controls, request wiring, layout, and JSON editor ergonomics - Hardened linked worktree reuse/startup behavior and documented the `worktree repair` flow for recovering linked worktrees safely - Added inbox workspace grouping, mobile collapse, archive undo, keyboard navigation, shared group-header styling, and persisted collapsed-group behavior - Added persistent sidebar order preferences with the supporting DB migration, shared/server contracts, routes, services, hooks, and UI integration - Scoped issue-list preferences by context and added targeted UI/server tests for workspace controls, inbox behavior, sidebar preferences, and worktree validation ## Verification - `pnpm vitest run server/src/__tests__/sidebar-preferences-routes.test.ts ui/src/pages/Inbox.test.tsx ui/src/components/ProjectWorkspaceSummaryCard.test.tsx ui/src/components/WorkspaceRuntimeControls.test.tsx ui/src/api/workspace-runtime-control.test.ts` - `server/src/__tests__/workspace-runtime.test.ts` was attempted, but the embedded Postgres suite self-skipped/hung on this host after reporting an init-script issue, so it is not counted as a local pass here ## Risks - Medium: this branch includes migration-backed preference storage plus worktree/runtime behavior, so merge review should pay attention to state persistence and worktree recovery semantics - The sidebar preference migration is standalone, but it should still be watched for conflicts if another migration lands first ## Model Used - OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact deployed model ID is not exposed in this environment), reasoning enabled, tool use and local code execution enabled ## 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) - [ ] 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 12:57:11 -05:00
serviceStates: null,
workspaceRuntime: {
services: [{ name: "web", command: "pnpm dev", port: 3100 }],
},
});
});
it("merges config patches without dropping unrelated metadata", () => {
expect(mergeExecutionWorkspaceConfig(
{
source: "project_primary",
createdByRuntime: false,
config: {
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
environmentId: "32e0464c-2a0b-4ce9-886d-2cc99e6f3e7b",
provisionCommand: "bash ./scripts/provision-worktree.sh",
cleanupCommand: "pkill -f vite || true",
},
},
{
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
environmentId: "6286d5a9-9ea7-42b9-98b3-18ee904c26d7",
teardownCommand: "bash ./scripts/teardown-worktree.sh",
workspaceRuntime: {
services: [{ name: "web", command: "pnpm dev" }],
},
},
)).toEqual({
source: "project_primary",
createdByRuntime: false,
config: {
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
environmentId: "6286d5a9-9ea7-42b9-98b3-18ee904c26d7",
provisionCommand: "bash ./scripts/provision-worktree.sh",
teardownCommand: "bash ./scripts/teardown-worktree.sh",
cleanupCommand: "pkill -f vite || true",
desiredState: null,
[codex] Improve workspace runtime and navigation ergonomics (#3680) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - That operator experience depends not just on issue chat, but also on how workspaces, inbox groups, and navigation state behave over long-running sessions > - The current branch included a separate cluster of workspace-runtime controls, inbox grouping, sidebar ordering, and worktree lifecycle fixes > - Those changes cross server, shared contracts, database state, and UI navigation, but they still form one coherent operator workflow area > - This pull request isolates the workspace/runtime and navigation ergonomics work into one standalone branch > - The benefit is better workspace recovery and navigation persistence without forcing reviewers through the unrelated issue-detail/chat work ## What Changed - Improved execution workspace and project workspace controls, request wiring, layout, and JSON editor ergonomics - Hardened linked worktree reuse/startup behavior and documented the `worktree repair` flow for recovering linked worktrees safely - Added inbox workspace grouping, mobile collapse, archive undo, keyboard navigation, shared group-header styling, and persisted collapsed-group behavior - Added persistent sidebar order preferences with the supporting DB migration, shared/server contracts, routes, services, hooks, and UI integration - Scoped issue-list preferences by context and added targeted UI/server tests for workspace controls, inbox behavior, sidebar preferences, and worktree validation ## Verification - `pnpm vitest run server/src/__tests__/sidebar-preferences-routes.test.ts ui/src/pages/Inbox.test.tsx ui/src/components/ProjectWorkspaceSummaryCard.test.tsx ui/src/components/WorkspaceRuntimeControls.test.tsx ui/src/api/workspace-runtime-control.test.ts` - `server/src/__tests__/workspace-runtime.test.ts` was attempted, but the embedded Postgres suite self-skipped/hung on this host after reporting an init-script issue, so it is not counted as a local pass here ## Risks - Medium: this branch includes migration-backed preference storage plus worktree/runtime behavior, so merge review should pay attention to state persistence and worktree recovery semantics - The sidebar preference migration is standalone, but it should still be watched for conflicts if another migration lands first ## Model Used - OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact deployed model ID is not exposed in this environment), reasoning enabled, tool use and local code execution enabled ## 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) - [ ] 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 12:57:11 -05:00
serviceStates: null,
workspaceRuntime: {
services: [{ name: "web", command: "pnpm dev" }],
},
},
});
});
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
it("clears a persisted environment selection when patching it to null", () => {
expect(mergeExecutionWorkspaceConfig(
{
source: "project_primary",
config: {
environmentId: "32e0464c-2a0b-4ce9-886d-2cc99e6f3e7b",
},
},
{
environmentId: null,
},
)).toEqual({
source: "project_primary",
});
});
it("clears the nested config block when requested", () => {
expect(mergeExecutionWorkspaceConfig(
{
source: "project_primary",
config: {
provisionCommand: "bash ./scripts/provision-worktree.sh",
},
},
null,
)).toEqual({
source: "project_primary",
});
});
});
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
if (!embeddedPostgresSupport.supported) {
console.warn(
`Skipping embedded Postgres execution workspace service tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
);
}
async function runGit(cwd: string, args: string[]) {
await execFileAsync("git", ["-C", cwd, ...args], { cwd });
}
async function createTempRepo() {
const repoRoot = await fs.mkdtemp(path.join(os.tmpdir(), "paperclip-execution-workspace-"));
await runGit(repoRoot, ["init"]);
await runGit(repoRoot, ["config", "user.name", "Paperclip Test"]);
await runGit(repoRoot, ["config", "user.email", "test@paperclip.local"]);
await fs.writeFile(path.join(repoRoot, "README.md"), "# Test repo\n", "utf8");
await runGit(repoRoot, ["add", "README.md"]);
await runGit(repoRoot, ["commit", "-m", "Initial commit"]);
await runGit(repoRoot, ["branch", "-M", "main"]);
return repoRoot;
}
describeEmbeddedPostgres("executionWorkspaceService.getCloseReadiness", () => {
let db!: ReturnType<typeof createDb>;
let svc!: ReturnType<typeof executionWorkspaceService>;
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
const tempDirs = new Set<string>();
beforeAll(async () => {
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-execution-workspaces-service-");
db = createDb(tempDb.connectionString);
svc = executionWorkspaceService(db);
}, 20_000);
afterEach(async () => {
await db.delete(issues);
await db.delete(executionWorkspaces);
await db.delete(projectWorkspaces);
await db.delete(projects);
await db.delete(companies);
for (const dir of tempDirs) {
await fs.rm(dir, { recursive: true, force: true });
}
tempDirs.clear();
});
afterAll(async () => {
await tempDb?.cleanup();
});
it("allows archiving shared workspace sessions with warnings even when issues are still open", async () => {
const companyId = randomUUID();
const projectId = randomUUID();
const projectWorkspaceId = randomUUID();
const executionWorkspaceId = randomUUID();
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: "PAP",
requireBoardApprovalForNewAgents: false,
});
await db.insert(projects).values({
id: projectId,
companyId,
name: "Workspaces",
status: "in_progress",
executionWorkspacePolicy: {
enabled: true,
},
});
await db.insert(projectWorkspaces).values({
id: projectWorkspaceId,
companyId,
projectId,
name: "Primary",
sourceType: "local_path",
isPrimary: true,
cwd: "/tmp/paperclip-primary",
});
await db.insert(executionWorkspaces).values({
id: executionWorkspaceId,
companyId,
projectId,
projectWorkspaceId,
mode: "shared_workspace",
strategyType: "project_primary",
name: "Shared workspace",
status: "active",
providerType: "local_fs",
cwd: "/tmp/paperclip-primary",
metadata: {
config: {
teardownCommand: "bash ./scripts/teardown.sh",
},
},
});
await db.insert(issues).values({
id: randomUUID(),
companyId,
projectId,
title: "Still working",
status: "todo",
priority: "medium",
executionWorkspaceId,
});
const readiness = await svc.getCloseReadiness(executionWorkspaceId);
expect(readiness).toMatchObject({
workspaceId: executionWorkspaceId,
state: "ready_with_warnings",
isSharedWorkspace: true,
isProjectPrimaryWorkspace: true,
isDestructiveCloseAllowed: true,
});
expect(readiness?.blockingReasons).toEqual([]);
expect(readiness?.warnings).toEqual(expect.arrayContaining([
"This workspace is still linked to an open issue. Archiving it will detach this shared workspace session from those issues, but keep the underlying project workspace available.",
"This shared workspace session points at project workspace infrastructure. Archiving it only removes the session record.",
]));
});
Add SSH environment support (#4358) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The environments subsystem already models execution environments, but before this branch there was no end-to-end SSH-backed runtime path for agents to actually run work against a remote box > - That meant agents could be configured around environment concepts without a reliable way to execute adapter sessions remotely, sync workspace state, and preserve run context across supported adapters > - We also need environment selection to participate in normal Paperclip control-plane behavior: agent defaults, project/issue selection, route validation, and environment probing > - Because this capability is still experimental, the UI surface should be easy to hide and easy to remove later without undoing the underlying implementation > - This pull request adds SSH environment execution support across the runtime, adapters, routes, schema, and tests, then puts the visible environment-management UI behind an experimental flag > - The benefit is that we can validate real SSH-backed agent execution now while keeping the user-facing controls safely gated until the feature is ready to come out of experimentation ## What Changed - Added SSH-backed execution target support in the shared adapter runtime, including remote workspace preparation, skill/runtime asset sync, remote session handling, and workspace restore behavior after runs. - Added SSH execution coverage for supported local adapters, plus remote execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi. - Added environment selection and environment-management backend support needed for SSH execution, including route/service work, validation, probing, and agent default environment persistence. - Added CLI support for SSH environment lab verification and updated related docs/tests. - Added the `enableEnvironments` experimental flag and gated the environment UI behind it on company settings, agent configuration, and project configuration surfaces. ## Verification - `pnpm exec vitest run packages/adapters/claude-local/src/server/execute.remote.test.ts packages/adapters/cursor-local/src/server/execute.remote.test.ts packages/adapters/gemini-local/src/server/execute.remote.test.ts packages/adapters/opencode-local/src/server/execute.remote.test.ts packages/adapters/pi-local/src/server/execute.remote.test.ts` - `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/instance-settings-routes.test.ts` - `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts ui/src/lib/new-agent-runtime-config.test.ts` - `pnpm -r typecheck` - `pnpm build` - Manual verification on a branch-local dev server: - enabled the experimental flag - created an SSH environment - created a Linux Claude agent using that environment - confirmed a run executed on the Linux box and synced workspace changes back ## Risks - Medium: this touches runtime execution flow across multiple adapters, so regressions would likely show up in remote session setup, workspace sync, or environment selection precedence. - The UI flag reduces exposure, but the underlying runtime and route changes are still substantial and rely on migration correctness. - The change set is broad across adapters, control-plane services, migrations, and UI gating, so review should pay close attention to environment-selection precedence and remote workspace lifecycle behavior. ## Model Used - OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding model with tool use and code execution in the local repo workspace. The local adapter does not surface a more specific public model version string in this branch workflow. ## 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
2026-04-23 19:15:22 -07:00
it("clears matching environment selections transactionally without touching other workspaces", async () => {
const companyId = randomUUID();
const projectId = randomUUID();
const matchingWorkspaceId = randomUUID();
const otherWorkspaceId = randomUUID();
const untouchedWorkspaceId = randomUUID();
const environmentId = randomUUID();
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: "PAP",
requireBoardApprovalForNewAgents: false,
});
await db.insert(projects).values({
id: projectId,
companyId,
name: "Workspace cleanup",
status: "in_progress",
executionWorkspacePolicy: {
enabled: true,
},
});
await db.insert(executionWorkspaces).values([
{
id: matchingWorkspaceId,
companyId,
projectId,
mode: "isolated_workspace",
strategyType: "directory",
name: "Matching workspace",
status: "active",
providerType: "local_fs",
cwd: "/tmp/workspace-a",
metadata: {
source: "manual",
config: {
environmentId,
cleanupCommand: "echo clean",
},
},
},
{
id: otherWorkspaceId,
companyId,
projectId,
mode: "isolated_workspace",
strategyType: "directory",
name: "Different environment",
status: "active",
providerType: "local_fs",
cwd: "/tmp/workspace-b",
metadata: {
source: "manual",
config: {
environmentId: randomUUID(),
},
},
},
{
id: untouchedWorkspaceId,
companyId,
projectId,
mode: "isolated_workspace",
strategyType: "directory",
name: "No environment",
status: "active",
providerType: "local_fs",
cwd: "/tmp/workspace-c",
metadata: {
source: "manual",
},
},
]);
const cleared = await svc.clearEnvironmentSelection(companyId, environmentId);
expect(cleared).toBe(1);
const rows = await db
.select({
id: executionWorkspaces.id,
metadata: executionWorkspaces.metadata,
})
.from(executionWorkspaces)
.where(inArray(executionWorkspaces.id, [matchingWorkspaceId, otherWorkspaceId, untouchedWorkspaceId]));
const byId = new Map(rows.map((row) => [row.id, row.metadata as Record<string, unknown> | null]));
expect(readExecutionWorkspaceConfig(byId.get(matchingWorkspaceId) ?? null)).toMatchObject({
environmentId: null,
cleanupCommand: "echo clean",
});
expect(readExecutionWorkspaceConfig(byId.get(otherWorkspaceId) ?? null)).toMatchObject({
environmentId: expect.any(String),
});
expect(readExecutionWorkspaceConfig(byId.get(untouchedWorkspaceId) ?? null)).toBeNull();
});
it("warns about dirty and unmerged git worktrees and reports cleanup actions", async () => {
const repoRoot = await createTempRepo();
tempDirs.add(repoRoot);
const worktreePath = path.join(path.dirname(repoRoot), `paperclip-worktree-${randomUUID()}`);
tempDirs.add(worktreePath);
await runGit(repoRoot, ["branch", "paperclip-close-check"]);
await runGit(repoRoot, ["worktree", "add", worktreePath, "paperclip-close-check"]);
await fs.writeFile(path.join(worktreePath, "feature.txt"), "hello\n", "utf8");
await runGit(worktreePath, ["add", "feature.txt"]);
await runGit(worktreePath, ["commit", "-m", "Feature commit"]);
await fs.writeFile(path.join(worktreePath, "untracked.txt"), "left behind\n", "utf8");
const companyId = randomUUID();
const projectId = randomUUID();
const projectWorkspaceId = randomUUID();
const executionWorkspaceId = randomUUID();
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: "PAP",
requireBoardApprovalForNewAgents: false,
});
await db.insert(projects).values({
id: projectId,
companyId,
name: "Workspaces",
status: "in_progress",
executionWorkspacePolicy: {
enabled: true,
workspaceStrategy: {
type: "git_worktree",
teardownCommand: "bash ./scripts/project-teardown.sh",
},
},
});
await db.insert(projectWorkspaces).values({
id: projectWorkspaceId,
companyId,
projectId,
name: "Primary",
sourceType: "git_repo",
isPrimary: true,
cwd: repoRoot,
cleanupCommand: "printf 'project cleanup\\n'",
});
await db.insert(executionWorkspaces).values({
id: executionWorkspaceId,
companyId,
projectId,
projectWorkspaceId,
mode: "isolated_workspace",
strategyType: "git_worktree",
name: "Feature workspace",
status: "active",
providerType: "git_worktree",
cwd: worktreePath,
providerRef: worktreePath,
branchName: "paperclip-close-check",
baseRef: "main",
metadata: {
createdByRuntime: true,
config: {
cleanupCommand: "printf 'workspace cleanup\\n'",
},
},
});
const readiness = await svc.getCloseReadiness(executionWorkspaceId);
expect(readiness).toMatchObject({
workspaceId: executionWorkspaceId,
state: "ready_with_warnings",
isSharedWorkspace: false,
isProjectPrimaryWorkspace: false,
isDestructiveCloseAllowed: true,
git: {
workspacePath: worktreePath,
branchName: "paperclip-close-check",
baseRef: "main",
createdByRuntime: true,
hasDirtyTrackedFiles: false,
hasUntrackedFiles: true,
aheadCount: 1,
behindCount: 0,
isMergedIntoBase: false,
},
});
expect(readiness?.warnings).toEqual(expect.arrayContaining([
"The workspace has 1 untracked file.",
"This workspace is 1 commit ahead of main and is not merged.",
]));
expect(readiness?.plannedActions.map((action) => action.kind)).toEqual(expect.arrayContaining([
"archive_record",
"cleanup_command",
"teardown_command",
"git_worktree_remove",
"git_branch_delete",
]));
}, 20_000);
});