paperclip/server/src/__tests__/agent-skills-routes.test.ts

545 lines
18 KiB
TypeScript
Raw Normal View History

import express from "express";
import request from "supertest";
import { beforeEach, describe, expect, it, vi } from "vitest";
const mockAgentService = vi.hoisted(() => ({
getById: vi.fn(),
update: vi.fn(),
create: vi.fn(),
resolveByReference: vi.fn(),
}));
const mockAccessService = vi.hoisted(() => ({
canUser: vi.fn(),
hasPermission: vi.fn(),
getMembership: vi.fn(),
listPrincipalGrants: vi.fn(),
ensureMembership: vi.fn(),
setPrincipalPermission: vi.fn(),
}));
const mockApprovalService = vi.hoisted(() => ({
create: vi.fn(),
}));
const mockBudgetService = vi.hoisted(() => ({}));
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
const mockEnvironmentService = vi.hoisted(() => ({
getById: vi.fn(),
}));
const mockHeartbeatService = vi.hoisted(() => ({}));
const mockIssueApprovalService = vi.hoisted(() => ({
linkManyForApproval: vi.fn(),
}));
const mockWorkspaceOperationService = vi.hoisted(() => ({}));
const mockAgentInstructionsService = vi.hoisted(() => ({
getBundle: vi.fn(),
readFile: vi.fn(),
updateBundle: vi.fn(),
writeFile: vi.fn(),
deleteFile: vi.fn(),
exportFiles: vi.fn(),
ensureManagedBundle: vi.fn(),
materializeManagedBundle: vi.fn(),
}));
const mockCompanySkillService = vi.hoisted(() => ({
listRuntimeSkillEntries: vi.fn(),
resolveRequestedSkillKeys: vi.fn(),
}));
const mockSecretService = vi.hoisted(() => ({
resolveAdapterConfigForRuntime: vi.fn(),
normalizeAdapterConfigForPersistence: vi.fn(async (_companyId: string, config: Record<string, unknown>) => config),
}));
const mockLogActivity = vi.hoisted(() => vi.fn());
const mockTrackAgentCreated = vi.hoisted(() => vi.fn());
const mockGetTelemetryClient = vi.hoisted(() => vi.fn());
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
const mockSyncInstructionsBundleConfigFromFilePath = vi.hoisted(() => vi.fn());
const mockAdapter = vi.hoisted(() => ({
listSkills: vi.fn(),
syncSkills: vi.fn(),
}));
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
vi.mock("@paperclipai/shared/telemetry", () => ({
trackAgentCreated: mockTrackAgentCreated,
trackErrorHandlerCrash: vi.fn(),
}));
vi.mock("../telemetry.js", () => ({
getTelemetryClient: mockGetTelemetryClient,
}));
vi.mock("../services/index.js", () => ({
agentService: () => mockAgentService,
agentInstructionsService: () => mockAgentInstructionsService,
accessService: () => mockAccessService,
approvalService: () => mockApprovalService,
companySkillService: () => mockCompanySkillService,
budgetService: () => mockBudgetService,
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
environmentService: () => mockEnvironmentService,
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
heartbeatService: () => mockHeartbeatService,
issueApprovalService: () => mockIssueApprovalService,
issueService: () => ({}),
logActivity: mockLogActivity,
secretService: () => mockSecretService,
syncInstructionsBundleConfigFromFilePath: mockSyncInstructionsBundleConfigFromFilePath,
workspaceOperationService: () => mockWorkspaceOperationService,
}));
vi.mock("../adapters/index.js", () => ({
findServerAdapter: vi.fn(() => mockAdapter),
findActiveServerAdapter: vi.fn(() => mockAdapter),
listAdapterModels: vi.fn(),
detectAdapterModel: vi.fn(),
}));
function registerModuleMocks() {
vi.doMock("@paperclipai/shared/telemetry", () => ({
trackAgentCreated: mockTrackAgentCreated,
trackErrorHandlerCrash: vi.fn(),
}));
vi.doMock("../telemetry.js", () => ({
getTelemetryClient: mockGetTelemetryClient,
}));
vi.doMock("../services/index.js", () => ({
agentService: () => mockAgentService,
agentInstructionsService: () => mockAgentInstructionsService,
accessService: () => mockAccessService,
approvalService: () => mockApprovalService,
companySkillService: () => mockCompanySkillService,
budgetService: () => mockBudgetService,
heartbeatService: () => mockHeartbeatService,
issueApprovalService: () => mockIssueApprovalService,
issueService: () => ({}),
logActivity: mockLogActivity,
secretService: () => mockSecretService,
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
syncInstructionsBundleConfigFromFilePath: mockSyncInstructionsBundleConfigFromFilePath,
workspaceOperationService: () => mockWorkspaceOperationService,
}));
vi.doMock("../adapters/index.js", () => ({
findServerAdapter: vi.fn(() => mockAdapter),
findActiveServerAdapter: vi.fn(() => mockAdapter),
listAdapterModels: vi.fn(),
detectAdapterModel: vi.fn(),
}));
}
function createDb(requireBoardApprovalForNewAgents = false) {
return {
select: vi.fn(() => ({
from: vi.fn(() => ({
where: vi.fn(async () => [
{
id: "company-1",
requireBoardApprovalForNewAgents,
},
]),
})),
})),
};
}
async function createApp(db: Record<string, unknown> = createDb()) {
const [{ agentRoutes }, { errorHandler }] = await Promise.all([
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
vi.importActual<typeof import("../routes/agents.js")>("../routes/agents.js"),
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
]);
const app = express();
app.use(express.json());
app.use((req, _res, next) => {
(req as any).actor = {
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
};
next();
});
app.use("/api", agentRoutes(db as any));
app.use(errorHandler);
return app;
}
function makeAgent(adapterType: string) {
return {
id: "11111111-1111-4111-8111-111111111111",
companyId: "company-1",
name: "Agent",
role: "engineer",
title: "Engineer",
status: "active",
reportsTo: null,
capabilities: null,
adapterType,
adapterConfig: {},
runtimeConfig: {},
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
defaultEnvironmentId: null,
permissions: null,
updatedAt: new Date(),
};
}
describe("agent skill routes", () => {
beforeEach(() => {
vi.resetModules();
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
vi.doUnmock("../routes/agents.js");
vi.doUnmock("../routes/authz.js");
vi.doUnmock("../middleware/index.js");
registerModuleMocks();
vi.resetAllMocks();
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
mockSyncInstructionsBundleConfigFromFilePath.mockImplementation((_agent, config) => config);
mockGetTelemetryClient.mockReturnValue({ track: vi.fn() });
mockAgentService.resolveByReference.mockResolvedValue({
ambiguous: false,
agent: makeAgent("claude_local"),
});
mockSecretService.resolveAdapterConfigForRuntime.mockResolvedValue({ config: { env: {} } });
mockCompanySkillService.listRuntimeSkillEntries.mockResolvedValue([
{
key: "paperclipai/paperclip/paperclip",
runtimeName: "paperclip",
source: "/tmp/paperclip",
required: true,
requiredReason: "required",
},
]);
mockCompanySkillService.resolveRequestedSkillKeys.mockImplementation(
async (_companyId: string, requested: string[]) =>
requested.map((value) =>
value === "paperclip"
? "paperclipai/paperclip/paperclip"
: value,
),
);
mockAdapter.listSkills.mockResolvedValue({
adapterType: "claude_local",
supported: true,
mode: "ephemeral",
desiredSkills: ["paperclipai/paperclip/paperclip"],
entries: [],
warnings: [],
});
mockAdapter.syncSkills.mockResolvedValue({
adapterType: "claude_local",
supported: true,
mode: "ephemeral",
desiredSkills: ["paperclipai/paperclip/paperclip"],
entries: [],
warnings: [],
});
mockAgentService.update.mockImplementation(async (_id: string, patch: Record<string, unknown>) => ({
...makeAgent("claude_local"),
adapterConfig: patch.adapterConfig ?? {},
}));
mockAgentService.create.mockImplementation(async (_companyId: string, input: Record<string, unknown>) => ({
...makeAgent(String(input.adapterType ?? "claude_local")),
...input,
adapterConfig: input.adapterConfig ?? {},
runtimeConfig: input.runtimeConfig ?? {},
budgetMonthlyCents: Number(input.budgetMonthlyCents ?? 0),
permissions: null,
}));
mockApprovalService.create.mockImplementation(async (_companyId: string, input: Record<string, unknown>) => ({
id: "approval-1",
companyId: "company-1",
type: "hire_agent",
status: "pending",
payload: input.payload ?? {},
}));
mockAgentInstructionsService.materializeManagedBundle.mockImplementation(
async (agent: Record<string, unknown>, files: Record<string, string>) => ({
bundle: null,
adapterConfig: {
...((agent.adapterConfig as Record<string, unknown> | undefined) ?? {}),
instructionsBundleMode: "managed",
instructionsRootPath: `/tmp/${String(agent.id)}/instructions`,
instructionsEntryFile: "AGENTS.md",
instructionsFilePath: `/tmp/${String(agent.id)}/instructions/AGENTS.md`,
promptTemplate: files["AGENTS.md"] ?? "",
},
}),
);
mockLogActivity.mockResolvedValue(undefined);
mockAccessService.canUser.mockResolvedValue(true);
mockAccessService.hasPermission.mockResolvedValue(true);
mockAccessService.getMembership.mockResolvedValue(null);
mockAccessService.listPrincipalGrants.mockResolvedValue([]);
mockAccessService.ensureMembership.mockResolvedValue(undefined);
mockAccessService.setPrincipalPermission.mockResolvedValue(undefined);
});
it("skips runtime materialization when listing Claude skills", async () => {
mockAgentService.getById.mockResolvedValue(makeAgent("claude_local"));
const res = await request(await createApp())
.get("/api/agents/11111111-1111-4111-8111-111111111111/skills?companyId=company-1");
expect(res.status, JSON.stringify(res.body)).toBe(200);
expect(mockAdapter.listSkills).toHaveBeenCalledWith(
expect.objectContaining({
adapterType: "claude_local",
config: expect.objectContaining({
paperclipRuntimeSkills: expect.any(Array),
}),
}),
);
}, 10_000);
it("skips runtime materialization when listing Codex skills", async () => {
mockAgentService.getById.mockResolvedValue(makeAgent("codex_local"));
mockAdapter.listSkills.mockResolvedValue({
adapterType: "codex_local",
supported: true,
mode: "ephemeral",
desiredSkills: ["paperclipai/paperclip/paperclip"],
entries: [],
warnings: [],
});
const res = await request(await createApp())
.get("/api/agents/11111111-1111-4111-8111-111111111111/skills?companyId=company-1");
expect(res.status, JSON.stringify(res.body)).toBe(200);
});
it("keeps runtime materialization for persistent skill adapters", async () => {
mockAgentService.getById.mockResolvedValue(makeAgent("cursor"));
mockAdapter.listSkills.mockResolvedValue({
adapterType: "cursor",
supported: true,
mode: "persistent",
desiredSkills: ["paperclipai/paperclip/paperclip"],
entries: [],
warnings: [],
});
const res = await request(await createApp())
.get("/api/agents/11111111-1111-4111-8111-111111111111/skills?companyId=company-1");
expect(res.status, JSON.stringify(res.body)).toBe(200);
});
it("skips runtime materialization when syncing Claude skills", async () => {
mockAgentService.getById.mockResolvedValue(makeAgent("claude_local"));
const res = await request(await createApp())
.post("/api/agents/11111111-1111-4111-8111-111111111111/skills/sync?companyId=company-1")
.send({ desiredSkills: ["paperclipai/paperclip/paperclip"] });
expect(res.status, JSON.stringify(res.body)).toBe(200);
expect(mockAdapter.syncSkills).toHaveBeenCalled();
});
it("canonicalizes desired skill references before syncing", async () => {
mockAgentService.getById.mockResolvedValue(makeAgent("claude_local"));
const res = await request(await createApp())
.post("/api/agents/11111111-1111-4111-8111-111111111111/skills/sync?companyId=company-1")
.send({ desiredSkills: ["paperclip"] });
expect(res.status, JSON.stringify(res.body)).toBe(200);
expect(mockAgentService.update).toHaveBeenCalledWith(
expect.any(String),
expect.objectContaining({
adapterConfig: expect.objectContaining({
paperclipSkillSync: expect.objectContaining({
desiredSkills: ["paperclipai/paperclip/paperclip"],
}),
}),
}),
expect.any(Object),
);
});
it("persists canonical desired skills when creating an agent directly", async () => {
const res = await request(await createApp())
.post("/api/companies/company-1/agents")
.send({
name: "QA Agent",
role: "engineer",
adapterType: "claude_local",
desiredSkills: ["paperclip"],
adapterConfig: {},
});
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockAgentService.create).toHaveBeenCalledWith(
"company-1",
expect.objectContaining({
adapterConfig: expect.objectContaining({
paperclipSkillSync: expect.objectContaining({
desiredSkills: ["paperclipai/paperclip/paperclip"],
}),
}),
}),
);
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
expect(mockTrackAgentCreated).toHaveBeenCalledWith(
expect.anything(),
expect.objectContaining({
agentId: "11111111-1111-4111-8111-111111111111",
agentRole: "engineer",
}),
);
});
it("materializes a managed AGENTS.md for directly created local agents", async () => {
const res = await request(await createApp())
.post("/api/companies/company-1/agents")
.send({
name: "QA Agent",
role: "engineer",
adapterType: "claude_local",
adapterConfig: {
promptTemplate: "You are QA.",
},
});
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockAgentService.update).toHaveBeenCalledWith(
"11111111-1111-4111-8111-111111111111",
expect.objectContaining({
adapterConfig: expect.objectContaining({
instructionsBundleMode: "managed",
instructionsEntryFile: "AGENTS.md",
instructionsFilePath: "/tmp/11111111-1111-4111-8111-111111111111/instructions/AGENTS.md",
}),
}),
);
expect(mockAgentService.update.mock.calls.at(-1)?.[1]).not.toMatchObject({
adapterConfig: expect.objectContaining({
promptTemplate: expect.anything(),
}),
});
});
it("materializes the bundled CEO instruction set for default CEO agents", async () => {
const res = await request(await createApp())
.post("/api/companies/company-1/agents")
.send({
name: "CEO",
role: "ceo",
adapterType: "claude_local",
adapterConfig: {},
});
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockAgentInstructionsService.materializeManagedBundle).toHaveBeenCalledWith(
expect.objectContaining({
id: "11111111-1111-4111-8111-111111111111",
role: "ceo",
adapterType: "claude_local",
}),
expect.objectContaining({
"AGENTS.md": expect.stringContaining("You are the CEO."),
"HEARTBEAT.md": expect.stringContaining("CEO Heartbeat Checklist"),
"SOUL.md": expect.stringContaining("CEO Persona"),
"TOOLS.md": expect.stringContaining("# Tools"),
}),
{ entryFile: "AGENTS.md", replaceExisting: false },
);
});
it("materializes the bundled default instruction set for non-CEO agents with no prompt template", async () => {
const res = await request(await createApp())
.post("/api/companies/company-1/agents")
.send({
name: "Engineer",
role: "engineer",
adapterType: "claude_local",
adapterConfig: {},
});
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
await vi.waitFor(() => {
expect(mockAgentInstructionsService.materializeManagedBundle).toHaveBeenCalledWith(
expect.objectContaining({
id: "11111111-1111-4111-8111-111111111111",
role: "engineer",
adapterType: "claude_local",
}),
expect.objectContaining({
[codex] Add run liveness continuations (#4083) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Heartbeat runs are the control-plane record of each agent execution window. > - Long-running local agents can exhaust context or stop while still holding useful next-step state. > - Operators need that stop reason, next action, and continuation path to be durable and visible. > - This pull request adds run liveness metadata, continuation summaries, and UI surfaces for issue run ledgers. > - The benefit is that interrupted or long-running work can resume with clearer context instead of losing the agent's last useful handoff. ## What Changed - Added heartbeat-run liveness fields, continuation attempt tracking, and an idempotent `0058` migration. - Added server services and tests for run liveness, continuation summaries, stop metadata, and activity backfill. - Wired local and HTTP adapters to surface continuation/liveness context through shared adapter utilities. - Added shared constants, validators, and heartbeat types for liveness continuation state. - Added issue-detail UI surfaces for continuation handoffs and the run ledger, with component tests. - Updated agent runtime docs, heartbeat protocol docs, prompt guidance, onboarding assets, and skills instructions to explain continuation behavior. - Addressed Greptile feedback by scoping document evidence by run, excluding system continuation-summary documents from liveness evidence, importing shared liveness types, surfacing hidden ledger run counts, documenting bounded retry behavior, and moving run-ledger liveness backfill off the request path. ## Verification - `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts server/src/__tests__/run-continuations.test.ts server/src/__tests__/run-liveness.test.ts server/src/__tests__/activity-service.test.ts server/src/__tests__/documents-service.test.ts server/src/__tests__/issue-continuation-summary.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/components/IssueContinuationHandoff.test.tsx ui/src/components/IssueDocumentsSection.test.tsx` - `pnpm --filter @paperclipai/db build` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm --filter @paperclipai/ui typecheck` - `pnpm --filter @paperclipai/server typecheck` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/run-continuations.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm exec vitest run server/src/__tests__/heartbeat-process-recovery.test.ts -t "treats a plan document update"` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts -t "activity service|treats a plan document update"` - Remote PR checks on head `e53b1a1d`: `verify`, `e2e`, `policy`, and Snyk all passed. - Confirmed `public-gh/master` is an ancestor of this branch after fetching `public-gh master`. - Confirmed `pnpm-lock.yaml` is not included in the branch diff. - Confirmed migration `0058_wealthy_starbolt.sql` is ordered after `0057` and uses `IF NOT EXISTS` guards for repeat application. - Greptile inline review threads are resolved. ## Risks - Medium risk: this touches heartbeat execution, liveness recovery, activity rendering, issue routes, shared contracts, docs, and UI. - Migration risk is mitigated by additive columns/indexes and idempotent guards. - Run-ledger liveness backfill is now asynchronous, so the first ledger response can briefly show historical missing liveness until the background backfill completes. - UI screenshot coverage is not included in this packaging pass; validation is currently through focused component tests. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, GPT-5.4, local tool-use coding agent with terminal, git, GitHub connector, GitHub CLI, and Paperclip API access. ## 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 Screenshot note: no before/after screenshots were captured in this PR packaging pass; the UI changes are covered by focused component tests listed above. --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:01:49 -05:00
"AGENTS.md": expect.stringMatching(/Start actionable work in the same heartbeat\.[\s\S]*Keep the work moving until it is done\./),
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
}),
{ entryFile: "AGENTS.md", replaceExisting: false },
);
[codex] Add structured issue-thread interactions (#4244) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Operators supervise that work through issues, comments, approvals, and the board UI. > - Some agent proposals need structured board/user decisions, not hidden markdown conventions or heavyweight governed approvals. > - Issue-thread interactions already provide a natural thread-native surface for proposed tasks and questions. > - This pull request extends that surface with request confirmations, richer interaction cards, and agent/plugin/MCP helpers. > - The benefit is that plan approvals and yes/no decisions become explicit, auditable, and resumable without losing the single-issue workflow. ## What Changed - Added persisted issue-thread interactions for suggested tasks, structured questions, and request confirmations. - Added board UI cards for interaction review, selection, question answers, and accept/reject confirmation flows. - Added MCP and plugin SDK helpers for creating interaction cards from agents/plugins. - Updated agent wake instructions, onboarding assets, Paperclip skill docs, and public docs to prefer structured confirmations for issue-scoped decisions. - Rebased the branch onto `public-gh/master` and renumbered branch migrations to `0063` and `0064`; the idempotency migration uses `ADD COLUMN IF NOT EXISTS` for old branch users. ## Verification - `git diff --check public-gh/master..HEAD` - `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts packages/mcp-server/src/tools.test.ts packages/shared/src/issue-thread-interactions.test.ts ui/src/lib/issue-thread-interactions.test.ts ui/src/lib/issue-chat-messages.test.ts ui/src/components/IssueThreadInteractionCard.test.tsx ui/src/components/IssueChatThread.test.tsx server/src/__tests__/issue-thread-interaction-routes.test.ts server/src/__tests__/issue-thread-interactions-service.test.ts server/src/services/issue-thread-interactions.test.ts` -> 9 files / 79 tests passed - `pnpm -r typecheck` -> passed, including `packages/db` migration numbering check ## Risks - Medium: this adds a new issue-thread interaction model across db/shared/server/ui/plugin surfaces. - Migration risk is reduced by placing this branch after current master migrations (`0063`, `0064`) and making the idempotency column add idempotent for users who applied the old branch numbering. - UI interaction behavior is covered by component tests, but this PR does not include browser screenshots. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, GPT-5-class coding agent runtime. Exact model ID and context window are not exposed in this Paperclip run; tool use and local shell/code execution were 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) - [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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-21 20:15:11 -05:00
expect(mockAgentInstructionsService.materializeManagedBundle).toHaveBeenCalledWith(
expect.any(Object),
expect.objectContaining({
"AGENTS.md": expect.stringContaining('kind: "request_confirmation"'),
}),
expect.any(Object),
);
expect(mockAgentInstructionsService.materializeManagedBundle).toHaveBeenCalledWith(
expect.any(Object),
expect.objectContaining({
"AGENTS.md": expect.stringContaining("confirmation:{issueId}:plan:{revisionId}"),
}),
expect.any(Object),
);
[codex] Harden execution reliability and heartbeat tooling (#3679) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Reliable execution depends on heartbeat routing, issue lifecycle semantics, telemetry, and a fast enough local verification loop to keep regressions visible > - The remaining commits on this branch were mostly server/runtime correctness fixes plus test and documentation follow-ups in that area > - Those changes are logically separate from the UI-focused issue-detail and workspace/navigation branches even when they touch overlapping issue APIs > - This pull request groups the execution reliability, heartbeat, telemetry, and tooling changes into one standalone branch > - The benefit is a focused review of the control-plane correctness work, including the follow-up fix that restored the implicit comment-reopen helpers after branch splitting ## What Changed - Hardened issue/heartbeat execution behavior, including self-review stage skipping, deferred mention wakes during active execution, stranded execution recovery, active-run scoping, assignee resolution, and blocked-to-todo wake resumption - Reduced noisy polling/logging overhead by trimming issue run payloads, compacting persisted run logs, silencing high-volume request logs, and capping heartbeat-run queries in dashboard/inbox surfaces - Expanded telemetry and status semantics with adapter/model fields on task completion plus clearer status guidance in docs/onboarding material - Updated test infrastructure and verification defaults with faster route-test module isolation, cheaper default `pnpm test`, e2e isolation from local state, and repo verification follow-ups - Included docs/release housekeeping from the branch and added a small follow-up commit restoring the implicit comment-reopen helpers that were dropped during branch reconstruction ## Verification - `pnpm vitest run server/src/__tests__/issue-comment-reopen-routes.test.ts server/src/__tests__/issue-telemetry-routes.test.ts` - `pnpm vitest run server/src/__tests__/http-log-policy.test.ts server/src/__tests__/heartbeat-run-log.test.ts server/src/__tests__/health.test.ts` - `server/src/__tests__/activity-service.test.ts`, `server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and `server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted on this host but the embedded Postgres harness reported init-script/data-dir problems and skipped or failed to start, so they are noted as environment-limited ## Risks - Medium: this branch changes core issue/heartbeat routing and reopen/wakeup behavior, so regressions would affect agent execution flow rather than isolated UI polish - Because it also updates verification infrastructure, reviewers should pay attention to whether the new tests are asserting the right failure modes and not just reshaping harness behavior ## 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 13:34:52 -05:00
});
});
it("includes canonical desired skills in hire approvals", async () => {
const db = createDb(true);
const res = await request(await createApp(db))
.post("/api/companies/company-1/agent-hires")
.send({
name: "QA Agent",
role: "engineer",
adapterType: "claude_local",
desiredSkills: ["paperclip"],
adapterConfig: {},
});
expect(res.status, JSON.stringify(res.body)).toBe(201);
expect(mockApprovalService.create).toHaveBeenCalledWith(
"company-1",
expect.objectContaining({
payload: expect.objectContaining({
desiredSkills: ["paperclipai/paperclip/paperclip"],
requestedConfigurationSnapshot: expect.objectContaining({
desiredSkills: ["paperclipai/paperclip/paperclip"],
}),
}),
}),
);
});
it("uses managed AGENTS config in hire approval payloads", async () => {
const res = await request(await createApp(createDb(true)))
.post("/api/companies/company-1/agent-hires")
.send({
name: "QA Agent",
role: "engineer",
adapterType: "claude_local",
adapterConfig: {
promptTemplate: "You are QA.",
},
});
expect(res.status, JSON.stringify(res.body)).toBe(201);
expect(mockApprovalService.create).toHaveBeenCalledWith(
"company-1",
expect.objectContaining({
payload: expect.objectContaining({
adapterConfig: expect.objectContaining({
instructionsBundleMode: "managed",
instructionsEntryFile: "AGENTS.md",
instructionsFilePath: "/tmp/11111111-1111-4111-8111-111111111111/instructions/AGENTS.md",
}),
}),
}),
);
const approvalInput = mockApprovalService.create.mock.calls.at(-1)?.[1] as
| { payload?: { adapterConfig?: Record<string, unknown> } }
| undefined;
expect(approvalInput?.payload?.adapterConfig?.promptTemplate).toBeUndefined();
});
});