2026-03-19 08:20:12 -05:00
|
|
|
import express from "express";
|
|
|
|
|
import request from "supertest";
|
|
|
|
|
import { beforeEach, describe, expect, it, vi } from "vitest";
|
|
|
|
|
|
|
|
|
|
const agentId = "11111111-1111-4111-8111-111111111111";
|
|
|
|
|
const companyId = "22222222-2222-4222-8222-222222222222";
|
|
|
|
|
|
|
|
|
|
const baseAgent = {
|
|
|
|
|
id: agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
name: "Builder",
|
|
|
|
|
urlKey: "builder",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
title: "Builder",
|
|
|
|
|
icon: null,
|
|
|
|
|
status: "idle",
|
|
|
|
|
reportsTo: null,
|
|
|
|
|
capabilities: null,
|
|
|
|
|
adapterType: "process",
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
runtimeConfig: {},
|
|
|
|
|
budgetMonthlyCents: 0,
|
|
|
|
|
spentMonthlyCents: 0,
|
|
|
|
|
pauseReason: null,
|
|
|
|
|
pausedAt: null,
|
|
|
|
|
permissions: { canCreateAgents: false },
|
|
|
|
|
lastHeartbeatAt: null,
|
|
|
|
|
metadata: null,
|
|
|
|
|
createdAt: new Date("2026-03-19T00:00:00.000Z"),
|
|
|
|
|
updatedAt: new Date("2026-03-19T00:00:00.000Z"),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const mockAgentService = vi.hoisted(() => ({
|
|
|
|
|
getById: 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
|
|
|
list: vi.fn(),
|
2026-03-19 08:20:12 -05:00
|
|
|
create: vi.fn(),
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
activatePendingApproval: vi.fn(),
|
2026-03-19 08:20:12 -05:00
|
|
|
updatePermissions: vi.fn(),
|
|
|
|
|
getChainOfCommand: vi.fn(),
|
|
|
|
|
resolveByReference: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockAccessService = vi.hoisted(() => ({
|
|
|
|
|
canUser: vi.fn(),
|
|
|
|
|
hasPermission: vi.fn(),
|
|
|
|
|
getMembership: vi.fn(),
|
|
|
|
|
ensureMembership: vi.fn(),
|
|
|
|
|
listPrincipalGrants: vi.fn(),
|
|
|
|
|
setPrincipalPermission: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockApprovalService = vi.hoisted(() => ({
|
|
|
|
|
create: vi.fn(),
|
|
|
|
|
getById: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockBudgetService = vi.hoisted(() => ({
|
|
|
|
|
upsertPolicy: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockHeartbeatService = vi.hoisted(() => ({
|
|
|
|
|
listTaskSessions: vi.fn(),
|
|
|
|
|
resetRuntimeSession: vi.fn(),
|
fix(authz): scope import, approvals, activity, and heartbeat routes (#3315)
## Thinking Path
> - Paperclip orchestrates AI agents and company-scoped control-plane
actions for zero-human companies.
> - This change touches the server authz boundary around company
portability, approvals, activity, and heartbeat-run operations.
> - The vulnerability was that board-authenticated callers could cross
company boundaries or create new companies through import paths without
the same authorization checks enforced elsewhere.
> - Once that gap existed, an attacker could chain it into higher-impact
behavior through agent execution paths.
> - The fix needed to harden every confirmed authorization gap in the
reported chain, not just the first route that exposed it.
> - This pull request adds the missing instance-admin and company-access
checks and adds regression tests for each affected route.
> - The benefit is that cross-company actions and new-company import
flows now follow the same control-plane authorization rules as the rest
of the product.
## What Changed
- Required instance-admin access for `new_company` import preview/apply
flows in `server/src/routes/companies.ts`.
- Required company access before approval decision routes in
`server/src/routes/approvals.ts`.
- Required company access for activity creation and heartbeat-run issue
listing in `server/src/routes/activity.ts`.
- Required company access before heartbeat cancellation in
`server/src/routes/agents.ts`.
- Added regression coverage in the corresponding server route tests.
## Verification
- `pnpm --filter @paperclipai/server exec vitest run
src/__tests__/company-portability-routes.test.ts
src/__tests__/approval-routes-idempotency.test.ts
src/__tests__/activity-routes.test.ts
src/__tests__/agent-permissions-routes.test.ts`
- `pnpm --filter @paperclipai/server typecheck`
- Prior verification on the original security patch branch also included
`pnpm build`.
## Risks
- Low code risk: the change is narrow and only adds missing
authorization gates to existing routes.
- Operational risk: the advisory is already public, so this PR should be
merged quickly to minimize the public unpatched window.
- Residual product risk remains around open signup / bootstrap defaults,
which was intentionally left out of this patch because the current
first-user onboarding flow depends on it.
## Model Used
- OpenAI GPT-5 Codex coding agent with tool use and local code execution
in the Codex CLI environment.
## 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 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
- [ ] 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: Forgotten <forgottenrunes@protonmail.com>
2026-04-10 11:55:27 -05:00
|
|
|
getRun: vi.fn(),
|
|
|
|
|
cancelRun: vi.fn(),
|
2026-03-19 08:20:12 -05:00
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockIssueApprovalService = vi.hoisted(() => ({
|
|
|
|
|
linkManyForApproval: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockIssueService = vi.hoisted(() => ({
|
|
|
|
|
list: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockSecretService = vi.hoisted(() => ({
|
|
|
|
|
normalizeAdapterConfigForPersistence: vi.fn(),
|
|
|
|
|
resolveAdapterConfigForRuntime: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
2026-03-20 13:40:53 -05:00
|
|
|
const mockAgentInstructionsService = vi.hoisted(() => ({
|
|
|
|
|
materializeManagedBundle: vi.fn(),
|
|
|
|
|
}));
|
2026-03-20 07:01:42 -05:00
|
|
|
const mockCompanySkillService = vi.hoisted(() => ({
|
|
|
|
|
listRuntimeSkillEntries: vi.fn(),
|
|
|
|
|
resolveRequestedSkillKeys: vi.fn(),
|
|
|
|
|
}));
|
2026-03-19 08:20:12 -05:00
|
|
|
const mockWorkspaceOperationService = vi.hoisted(() => ({}));
|
|
|
|
|
const mockLogActivity = vi.hoisted(() => vi.fn());
|
2026-04-09 06:12:39 -05:00
|
|
|
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());
|
|
|
|
|
|
|
|
|
|
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,
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
ISSUE_LIST_DEFAULT_LIMIT: 500,
|
[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
|
|
|
issueApprovalService: () => mockIssueApprovalService,
|
|
|
|
|
issueService: () => mockIssueService,
|
|
|
|
|
logActivity: mockLogActivity,
|
|
|
|
|
secretService: () => mockSecretService,
|
|
|
|
|
syncInstructionsBundleConfigFromFilePath: mockSyncInstructionsBundleConfigFromFilePath,
|
|
|
|
|
workspaceOperationService: () => mockWorkspaceOperationService,
|
|
|
|
|
}));
|
|
|
|
|
}
|
2026-03-19 08:20:12 -05:00
|
|
|
|
|
|
|
|
function createDbStub() {
|
|
|
|
|
return {
|
|
|
|
|
select: vi.fn().mockReturnValue({
|
|
|
|
|
from: vi.fn().mockReturnValue({
|
|
|
|
|
where: vi.fn().mockReturnValue({
|
|
|
|
|
then: vi.fn().mockResolvedValue([{
|
|
|
|
|
id: companyId,
|
|
|
|
|
name: "Paperclip",
|
|
|
|
|
requireBoardApprovalForNewAgents: false,
|
|
|
|
|
}]),
|
|
|
|
|
}),
|
|
|
|
|
}),
|
|
|
|
|
}),
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
[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
|
|
|
async function createApp(actor: Record<string, unknown>) {
|
|
|
|
|
const [{ errorHandler }, { agentRoutes }] = await Promise.all([
|
|
|
|
|
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
|
|
|
|
vi.importActual<typeof import("../routes/agents.js")>("../routes/agents.js"),
|
|
|
|
|
]);
|
2026-03-19 08:20:12 -05:00
|
|
|
const app = express();
|
|
|
|
|
app.use(express.json());
|
|
|
|
|
app.use((req, _res, next) => {
|
|
|
|
|
(req as any).actor = actor;
|
|
|
|
|
next();
|
|
|
|
|
});
|
|
|
|
|
app.use("/api", agentRoutes(createDbStub() as any));
|
|
|
|
|
app.use(errorHandler);
|
|
|
|
|
return app;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
describe("agent permission routes", () => {
|
|
|
|
|
beforeEach(() => {
|
[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.resetModules();
|
|
|
|
|
vi.doUnmock("@paperclipai/shared/telemetry");
|
|
|
|
|
vi.doUnmock("../telemetry.js");
|
|
|
|
|
vi.doUnmock("../services/index.js");
|
|
|
|
|
vi.doUnmock("../routes/agents.js");
|
|
|
|
|
vi.doUnmock("../middleware/index.js");
|
|
|
|
|
registerModuleMocks();
|
|
|
|
|
vi.clearAllMocks();
|
|
|
|
|
mockSyncInstructionsBundleConfigFromFilePath.mockImplementation((_agent, config) => config);
|
2026-04-09 06:12:39 -05:00
|
|
|
mockGetTelemetryClient.mockReturnValue({ track: vi.fn() });
|
2026-03-19 08:20:12 -05:00
|
|
|
mockAgentService.getById.mockResolvedValue(baseAgent);
|
[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
|
|
|
mockAgentService.list.mockResolvedValue([baseAgent]);
|
2026-03-19 08:20:12 -05:00
|
|
|
mockAgentService.getChainOfCommand.mockResolvedValue([]);
|
|
|
|
|
mockAgentService.resolveByReference.mockResolvedValue({ ambiguous: false, agent: baseAgent });
|
|
|
|
|
mockAgentService.create.mockResolvedValue(baseAgent);
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
mockAgentService.activatePendingApproval.mockResolvedValue(baseAgent);
|
2026-03-19 08:20:12 -05:00
|
|
|
mockAgentService.updatePermissions.mockResolvedValue(baseAgent);
|
|
|
|
|
mockAccessService.getMembership.mockResolvedValue({
|
|
|
|
|
id: "membership-1",
|
|
|
|
|
companyId,
|
|
|
|
|
principalType: "agent",
|
|
|
|
|
principalId: agentId,
|
|
|
|
|
status: "active",
|
|
|
|
|
membershipRole: "member",
|
|
|
|
|
createdAt: new Date("2026-03-19T00:00:00.000Z"),
|
|
|
|
|
updatedAt: new Date("2026-03-19T00:00:00.000Z"),
|
|
|
|
|
});
|
|
|
|
|
mockAccessService.listPrincipalGrants.mockResolvedValue([]);
|
|
|
|
|
mockAccessService.ensureMembership.mockResolvedValue(undefined);
|
|
|
|
|
mockAccessService.setPrincipalPermission.mockResolvedValue(undefined);
|
2026-03-20 07:01:42 -05:00
|
|
|
mockCompanySkillService.listRuntimeSkillEntries.mockResolvedValue([]);
|
|
|
|
|
mockCompanySkillService.resolveRequestedSkillKeys.mockImplementation(async (_companyId, requested) => requested);
|
2026-03-19 08:20:12 -05:00
|
|
|
mockBudgetService.upsertPolicy.mockResolvedValue(undefined);
|
2026-03-20 13:40:53 -05:00
|
|
|
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"] ?? "",
|
|
|
|
|
},
|
|
|
|
|
}),
|
|
|
|
|
);
|
|
|
|
|
mockCompanySkillService.listRuntimeSkillEntries.mockResolvedValue([]);
|
|
|
|
|
mockCompanySkillService.resolveRequestedSkillKeys.mockImplementation(
|
|
|
|
|
async (_companyId: string, requested: string[]) => requested,
|
|
|
|
|
);
|
2026-03-19 08:20:12 -05:00
|
|
|
mockSecretService.normalizeAdapterConfigForPersistence.mockImplementation(async (_companyId, config) => config);
|
|
|
|
|
mockSecretService.resolveAdapterConfigForRuntime.mockImplementation(async (_companyId, config) => ({ config }));
|
|
|
|
|
mockLogActivity.mockResolvedValue(undefined);
|
|
|
|
|
});
|
|
|
|
|
|
[codex] harden authenticated routes and issue editor reliability (#3741)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - The control plane depends on authenticated routes enforcing company
boundaries and role permissions correctly
> - This branch also touches the issue detail and markdown editing flows
operators use while handling advisory and triage work
> - Partial issue cache seeds and fragile rich-editor parsing could
leave important issue content missing or blank at the moment an operator
needed it
> - Blocked issues becoming actionable again should wake their assignee
automatically instead of silently staying idle
> - This pull request rebases the advisory follow-up branch onto current
`master`, hardens authenticated route authorization, and carries the
issue-detail/editor reliability fixes forward with regression tests
> - The benefit is tighter authz on sensitive routes plus more reliable
issue/advisory editing and wakeup behavior on top of the latest base
## What Changed
- Hardened authenticated route authorization across agent, activity,
approval, access, project, plugin, health, execution-workspace,
portability, and related server paths, with new cross-tenant and
runtime-authz regression coverage.
- Switched issue detail queries from `initialData` to placeholder-based
hydration so list/quicklook seeds still refetch full issue bodies.
- Normalized advisory-style HTML images before mounting the markdown
editor and strengthened fallback behavior when the rich editor silently
fails or rejects the content.
- Woke assigned agents when blocked issues move back to `todo`, with
route coverage for reopen and unblock transitions.
- Rebasing note: this branch now sits cleanly on top of the latest
`master` tip used for the PR base.
## Verification
- `pnpm exec vitest run ui/src/lib/issueDetailQuery.test.tsx
ui/src/components/MarkdownEditor.test.tsx
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/activity-routes.test.ts
server/src/__tests__/agent-cross-tenant-authz-routes.test.ts`
- Confirmed `pnpm-lock.yaml` is not part of the PR diff.
- Rebased the branch onto current `public-gh/master` before publishing.
## Risks
- Broad authz tightening may expose existing flows that were relying on
permissive board or agent access and now need explicit grants.
- Markdown editor fallback changes could affect focus or rendering in
edge-case content that mixes HTML-like advisory markup with normal
markdown.
- This verification was intentionally scoped to touched regressions and
did not run the full repository suite.
## Model Used
- OpenAI Codex, GPT-5-based coding agent in the Codex CLI environment
with tool use for terminal, git, and GitHub operations. The exact
runtime model identifier is not exposed inside this session.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, it is behavior-only and does not
need before/after screenshots
- [x] I have updated relevant documentation to reflect my changes, or no
documentation changes were needed for these internal fixes
- [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>
2026-04-15 08:41:15 -05:00
|
|
|
it("redacts agent detail for authenticated company members without agent admin permission", async () => {
|
|
|
|
|
mockAccessService.canUser.mockResolvedValue(false);
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "member-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app).get(`/api/agents/${agentId}`);
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(res.body.adapterConfig).toEqual({});
|
|
|
|
|
expect(res.body.runtimeConfig).toEqual({});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("redacts company agent list for authenticated company members without agent admin permission", async () => {
|
|
|
|
|
mockAccessService.canUser.mockResolvedValue(false);
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "member-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app).get(`/api/companies/${companyId}/agents`);
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(res.body).toEqual([
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
id: agentId,
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
runtimeConfig: {},
|
|
|
|
|
}),
|
|
|
|
|
]);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks agent updates for authenticated company members without agent admin permission", async () => {
|
|
|
|
|
mockAccessService.canUser.mockResolvedValue(false);
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "member-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch(`/api/agents/${agentId}`)
|
|
|
|
|
.send({ title: "Compromised" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks api key creation for authenticated company members without agent admin permission", async () => {
|
|
|
|
|
mockAccessService.canUser.mockResolvedValue(false);
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "member-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/agents/${agentId}/keys`)
|
|
|
|
|
.send({ name: "backdoor" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks wakeups for authenticated company members without agent admin permission", async () => {
|
|
|
|
|
mockAccessService.canUser.mockResolvedValue(false);
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "member-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/agents/${agentId}/wakeup`)
|
|
|
|
|
.send({});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks agent-authenticated self-updates that set host-executed workspace commands", async () => {
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "agent",
|
|
|
|
|
agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
source: "agent_key",
|
|
|
|
|
runId: "run-1",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch(`/api/agents/${agentId}`)
|
|
|
|
|
.send({
|
|
|
|
|
adapterConfig: {
|
|
|
|
|
workspaceStrategy: {
|
|
|
|
|
type: "git_worktree",
|
|
|
|
|
provisionCommand: "touch /tmp/paperclip-rce",
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(res.body.error).toContain("host-executed workspace commands");
|
|
|
|
|
expect(mockLogActivity).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks agent-authenticated self-updates that set instructions bundle roots", async () => {
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "agent",
|
|
|
|
|
agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
source: "agent_key",
|
|
|
|
|
runId: "run-1",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch(`/api/agents/${agentId}`)
|
|
|
|
|
.send({
|
|
|
|
|
adapterConfig: {
|
|
|
|
|
instructionsRootPath: "/etc",
|
|
|
|
|
instructionsEntryFile: "passwd",
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(res.body.error).toContain("instructions path or bundle configuration");
|
|
|
|
|
expect(mockLogActivity).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks agent-authenticated instructions-path updates", async () => {
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "agent",
|
|
|
|
|
agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
source: "agent_key",
|
|
|
|
|
runId: "run-1",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch(`/api/agents/${agentId}/instructions-path`)
|
|
|
|
|
.send({ path: "/etc/passwd" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(res.body.error).toContain("instructions path or bundle configuration");
|
|
|
|
|
expect(mockLogActivity).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("blocks agent-authenticated hires that set instructions bundle config", async () => {
|
|
|
|
|
mockAccessService.hasPermission.mockResolvedValue(true);
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "agent",
|
|
|
|
|
agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
source: "agent_key",
|
|
|
|
|
runId: "run-1",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/agent-hires`)
|
|
|
|
|
.send({
|
|
|
|
|
name: "Injected",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
adapterType: "codex_local",
|
|
|
|
|
adapterConfig: {
|
|
|
|
|
instructionsRootPath: "/etc",
|
|
|
|
|
instructionsEntryFile: "passwd",
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(res.body.error).toContain("instructions path or bundle configuration");
|
|
|
|
|
expect(mockAgentService.create).not.toHaveBeenCalled();
|
|
|
|
|
expect(mockLogActivity).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
2026-03-19 08:20:12 -05:00
|
|
|
it("grants tasks:assign by default when board creates a new agent", async () => {
|
[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 app = await createApp({
|
2026-03-19 08:20:12 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/agents`)
|
|
|
|
|
.send({
|
|
|
|
|
name: "Builder",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
adapterType: "process",
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
});
|
|
|
|
|
|
2026-04-09 06:12:39 -05:00
|
|
|
expect([200, 201]).toContain(res.status);
|
2026-03-19 08:20:12 -05:00
|
|
|
expect(mockAccessService.ensureMembership).toHaveBeenCalledWith(
|
|
|
|
|
companyId,
|
|
|
|
|
"agent",
|
|
|
|
|
agentId,
|
|
|
|
|
"member",
|
|
|
|
|
"active",
|
|
|
|
|
);
|
|
|
|
|
expect(mockAccessService.setPrincipalPermission).toHaveBeenCalledWith(
|
|
|
|
|
companyId,
|
|
|
|
|
"agent",
|
|
|
|
|
agentId,
|
|
|
|
|
"tasks:assign",
|
|
|
|
|
true,
|
|
|
|
|
"board-user",
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
[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("rejects unsupported query parameters on the agent list route", async () => {
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.get(`/api/companies/${companyId}/agents`)
|
|
|
|
|
.query({ urlKey: "builder" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(400);
|
|
|
|
|
expect(res.body.error).toContain("urlKey");
|
|
|
|
|
expect(mockAgentService.list).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
2026-04-08 07:26:34 -05:00
|
|
|
it("normalizes direct agent creation to disable timer heartbeats by default", async () => {
|
[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 app = await createApp({
|
2026-04-08 07:26:34 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/agents`)
|
|
|
|
|
.send({
|
|
|
|
|
name: "Builder",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
adapterType: "process",
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
runtimeConfig: {
|
|
|
|
|
heartbeat: {
|
|
|
|
|
intervalSec: 3600,
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
2026-04-10 22:26:21 -05:00
|
|
|
expect([200, 201]).toContain(res.status);
|
2026-04-08 07:26:34 -05:00
|
|
|
expect(mockAgentService.create).toHaveBeenCalledWith(
|
|
|
|
|
companyId,
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
runtimeConfig: {
|
|
|
|
|
heartbeat: {
|
|
|
|
|
enabled: false,
|
|
|
|
|
intervalSec: 3600,
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
maxConcurrentRuns: 5,
|
2026-04-08 07:26:34 -05:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
}),
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("normalizes hire requests to disable timer heartbeats by default", async () => {
|
[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 app = await createApp({
|
2026-04-08 07:26:34 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/agent-hires`)
|
|
|
|
|
.send({
|
|
|
|
|
name: "Builder",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
adapterType: "process",
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
runtimeConfig: {
|
|
|
|
|
heartbeat: {
|
|
|
|
|
intervalSec: 3600,
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(201);
|
|
|
|
|
expect(mockAgentService.create).toHaveBeenCalledWith(
|
|
|
|
|
companyId,
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
runtimeConfig: {
|
|
|
|
|
heartbeat: {
|
|
|
|
|
enabled: false,
|
|
|
|
|
intervalSec: 3600,
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
maxConcurrentRuns: 5,
|
2026-04-08 07:26:34 -05:00
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
}),
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
it("allows board users to directly approve pending agents", async () => {
|
|
|
|
|
const pendingAgent = {
|
|
|
|
|
...baseAgent,
|
|
|
|
|
status: "pending_approval",
|
|
|
|
|
};
|
|
|
|
|
const approvedAgent = {
|
|
|
|
|
...baseAgent,
|
|
|
|
|
status: "idle",
|
|
|
|
|
};
|
|
|
|
|
mockAgentService.getById.mockResolvedValue(pendingAgent);
|
|
|
|
|
mockAgentService.activatePendingApproval.mockResolvedValue({
|
|
|
|
|
agent: approvedAgent,
|
|
|
|
|
activated: true,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/agents/${agentId}/approve`)
|
|
|
|
|
.send({});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(mockAgentService.activatePendingApproval).toHaveBeenCalledWith(agentId);
|
|
|
|
|
expect(mockLogActivity).toHaveBeenCalledWith(expect.anything(), expect.objectContaining({
|
|
|
|
|
companyId,
|
|
|
|
|
actorType: "user",
|
|
|
|
|
actorId: "board-user",
|
|
|
|
|
action: "agent.approved",
|
|
|
|
|
entityType: "agent",
|
|
|
|
|
entityId: agentId,
|
|
|
|
|
details: { source: "agent_detail" },
|
|
|
|
|
}));
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("rejects direct approval for agents that are not pending approval", async () => {
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.post(`/api/agents/${agentId}/approve`)
|
|
|
|
|
.send({});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(409);
|
|
|
|
|
expect(mockAgentService.activatePendingApproval).not.toHaveBeenCalled();
|
|
|
|
|
expect(mockLogActivity).not.toHaveBeenCalledWith(expect.anything(), expect.objectContaining({
|
|
|
|
|
action: "agent.approved",
|
|
|
|
|
}));
|
|
|
|
|
});
|
|
|
|
|
|
2026-03-19 08:20:12 -05:00
|
|
|
it("exposes explicit task assignment access on agent detail", async () => {
|
|
|
|
|
mockAccessService.listPrincipalGrants.mockResolvedValue([
|
|
|
|
|
{
|
|
|
|
|
id: "grant-1",
|
|
|
|
|
companyId,
|
|
|
|
|
principalType: "agent",
|
|
|
|
|
principalId: agentId,
|
|
|
|
|
permissionKey: "tasks:assign",
|
|
|
|
|
scope: null,
|
|
|
|
|
grantedByUserId: "board-user",
|
|
|
|
|
createdAt: new Date("2026-03-19T00:00:00.000Z"),
|
|
|
|
|
updatedAt: new Date("2026-03-19T00:00:00.000Z"),
|
|
|
|
|
},
|
|
|
|
|
]);
|
|
|
|
|
|
[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 app = await createApp({
|
2026-03-19 08:20:12 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app).get(`/api/agents/${agentId}`);
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(res.body.access.canAssignTasks).toBe(true);
|
|
|
|
|
expect(res.body.access.taskAssignSource).toBe("explicit_grant");
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("keeps task assignment enabled when agent creation privilege is enabled", async () => {
|
|
|
|
|
mockAgentService.updatePermissions.mockResolvedValue({
|
|
|
|
|
...baseAgent,
|
|
|
|
|
permissions: { canCreateAgents: true },
|
|
|
|
|
});
|
|
|
|
|
|
[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 app = await createApp({
|
2026-03-19 08:20:12 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "local_implicit",
|
|
|
|
|
isInstanceAdmin: true,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch(`/api/agents/${agentId}/permissions`)
|
|
|
|
|
.send({ canCreateAgents: true, canAssignTasks: false });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(mockAccessService.setPrincipalPermission).toHaveBeenCalledWith(
|
|
|
|
|
companyId,
|
|
|
|
|
"agent",
|
|
|
|
|
agentId,
|
|
|
|
|
"tasks:assign",
|
|
|
|
|
true,
|
|
|
|
|
"board-user",
|
|
|
|
|
);
|
|
|
|
|
expect(res.body.access.canAssignTasks).toBe(true);
|
|
|
|
|
expect(res.body.access.taskAssignSource).toBe("agent_creator");
|
|
|
|
|
});
|
2026-03-26 20:06:29 -05:00
|
|
|
|
|
|
|
|
it("exposes a dedicated agent route for the inbox mine view", async () => {
|
|
|
|
|
mockIssueService.list.mockResolvedValue([
|
|
|
|
|
{
|
|
|
|
|
id: "issue-1",
|
|
|
|
|
identifier: "PAP-910",
|
|
|
|
|
title: "Inbox follow-up",
|
|
|
|
|
status: "todo",
|
|
|
|
|
},
|
|
|
|
|
]);
|
|
|
|
|
|
[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 app = await createApp({
|
2026-03-26 20:06:29 -05:00
|
|
|
type: "agent",
|
|
|
|
|
agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
runId: "run-1",
|
|
|
|
|
source: "agent_key",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.get("/api/agents/me/inbox/mine")
|
|
|
|
|
.query({ userId: "board-user" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(res.body).toEqual([
|
|
|
|
|
{
|
|
|
|
|
id: "issue-1",
|
|
|
|
|
identifier: "PAP-910",
|
|
|
|
|
title: "Inbox follow-up",
|
|
|
|
|
status: "todo",
|
|
|
|
|
},
|
|
|
|
|
]);
|
[codex] Improve agent runtime recovery and governance (#4086)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.
## What Changed
- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.
## Verification
- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.
> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
harness.
## 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
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:19:48 -05:00
|
|
|
expect(mockIssueService.list).toHaveBeenCalledWith(companyId, {
|
|
|
|
|
touchedByUserId: "board-user",
|
|
|
|
|
inboxArchivedByUserId: "board-user",
|
|
|
|
|
status: "backlog,todo,in_progress,in_review,blocked,done",
|
|
|
|
|
limit: 500,
|
|
|
|
|
});
|
2026-03-26 20:06:29 -05:00
|
|
|
});
|
fix(authz): scope import, approvals, activity, and heartbeat routes (#3315)
## Thinking Path
> - Paperclip orchestrates AI agents and company-scoped control-plane
actions for zero-human companies.
> - This change touches the server authz boundary around company
portability, approvals, activity, and heartbeat-run operations.
> - The vulnerability was that board-authenticated callers could cross
company boundaries or create new companies through import paths without
the same authorization checks enforced elsewhere.
> - Once that gap existed, an attacker could chain it into higher-impact
behavior through agent execution paths.
> - The fix needed to harden every confirmed authorization gap in the
reported chain, not just the first route that exposed it.
> - This pull request adds the missing instance-admin and company-access
checks and adds regression tests for each affected route.
> - The benefit is that cross-company actions and new-company import
flows now follow the same control-plane authorization rules as the rest
of the product.
## What Changed
- Required instance-admin access for `new_company` import preview/apply
flows in `server/src/routes/companies.ts`.
- Required company access before approval decision routes in
`server/src/routes/approvals.ts`.
- Required company access for activity creation and heartbeat-run issue
listing in `server/src/routes/activity.ts`.
- Required company access before heartbeat cancellation in
`server/src/routes/agents.ts`.
- Added regression coverage in the corresponding server route tests.
## Verification
- `pnpm --filter @paperclipai/server exec vitest run
src/__tests__/company-portability-routes.test.ts
src/__tests__/approval-routes-idempotency.test.ts
src/__tests__/activity-routes.test.ts
src/__tests__/agent-permissions-routes.test.ts`
- `pnpm --filter @paperclipai/server typecheck`
- Prior verification on the original security patch branch also included
`pnpm build`.
## Risks
- Low code risk: the change is narrow and only adds missing
authorization gates to existing routes.
- Operational risk: the advisory is already public, so this PR should be
merged quickly to minimize the public unpatched window.
- Residual product risk remains around open signup / bootstrap defaults,
which was intentionally left out of this patch because the current
first-user onboarding flow depends on it.
## Model Used
- OpenAI GPT-5 Codex coding agent with tool use and local code execution
in the Codex CLI environment.
## 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 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
- [ ] 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: Forgotten <forgottenrunes@protonmail.com>
2026-04-10 11:55:27 -05:00
|
|
|
|
|
|
|
|
it("rejects heartbeat cancellation outside the caller company scope", async () => {
|
|
|
|
|
mockHeartbeatService.getRun.mockResolvedValue({
|
|
|
|
|
id: "run-1",
|
|
|
|
|
companyId: "33333333-3333-4333-8333-333333333333",
|
|
|
|
|
agentId,
|
|
|
|
|
status: "running",
|
|
|
|
|
});
|
|
|
|
|
|
[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 app = await createApp({
|
fix(authz): scope import, approvals, activity, and heartbeat routes (#3315)
## Thinking Path
> - Paperclip orchestrates AI agents and company-scoped control-plane
actions for zero-human companies.
> - This change touches the server authz boundary around company
portability, approvals, activity, and heartbeat-run operations.
> - The vulnerability was that board-authenticated callers could cross
company boundaries or create new companies through import paths without
the same authorization checks enforced elsewhere.
> - Once that gap existed, an attacker could chain it into higher-impact
behavior through agent execution paths.
> - The fix needed to harden every confirmed authorization gap in the
reported chain, not just the first route that exposed it.
> - This pull request adds the missing instance-admin and company-access
checks and adds regression tests for each affected route.
> - The benefit is that cross-company actions and new-company import
flows now follow the same control-plane authorization rules as the rest
of the product.
## What Changed
- Required instance-admin access for `new_company` import preview/apply
flows in `server/src/routes/companies.ts`.
- Required company access before approval decision routes in
`server/src/routes/approvals.ts`.
- Required company access for activity creation and heartbeat-run issue
listing in `server/src/routes/activity.ts`.
- Required company access before heartbeat cancellation in
`server/src/routes/agents.ts`.
- Added regression coverage in the corresponding server route tests.
## Verification
- `pnpm --filter @paperclipai/server exec vitest run
src/__tests__/company-portability-routes.test.ts
src/__tests__/approval-routes-idempotency.test.ts
src/__tests__/activity-routes.test.ts
src/__tests__/agent-permissions-routes.test.ts`
- `pnpm --filter @paperclipai/server typecheck`
- Prior verification on the original security patch branch also included
`pnpm build`.
## Risks
- Low code risk: the change is narrow and only adds missing
authorization gates to existing routes.
- Operational risk: the advisory is already public, so this PR should be
merged quickly to minimize the public unpatched window.
- Residual product risk remains around open signup / bootstrap defaults,
which was intentionally left out of this patch because the current
first-user onboarding flow depends on it.
## Model Used
- OpenAI GPT-5 Codex coding agent with tool use and local code execution
in the Codex CLI environment.
## 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 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
- [ ] 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: Forgotten <forgottenrunes@protonmail.com>
2026-04-10 11:55:27 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app).post("/api/heartbeat-runs/run-1/cancel").send({});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(mockHeartbeatService.cancelRun).not.toHaveBeenCalled();
|
|
|
|
|
});
|
2026-03-19 08:20:12 -05:00
|
|
|
});
|