2026-03-10 11:32:12 +05:30
|
|
|
import express from "express";
|
|
|
|
|
import request from "supertest";
|
2026-03-14 22:00:12 -05:00
|
|
|
import { beforeEach, describe, expect, it, vi } from "vitest";
|
Sync/master post pap1497 followups 2026 04 15 (#3779)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - The board depends on issue, inbox, cost, and company-skill surfaces
to stay accurate and fast while agents are actively working
> - The PAP-1497 follow-up branch exposed a few rough edges in those
surfaces: stale active-run state on completed issues, missing creator
filters, oversized issue payload scans, and placeholder issue-route
parsing
> - Those gaps make the control plane harder to trust because operators
can see misleading run state, miss the right subset of work, or pay
extra query/render cost on large issue records
> - This pull request tightens those follow-ups across server and UI
code, and adds regression coverage for the affected paths
> - The benefit is a more reliable issue workflow, safer high-volume
cost aggregation, and clearer board/operator navigation
## What Changed
- Added the `v2026.415.0` release changelog entry.
- Fixed stale issue-run presentation after completion and reused the
shared issue-path parser so literal route placeholders no longer become
issue links.
- Added creator filters to the Issues page and Inbox, including
persisted filter-state normalization and regression coverage.
- Bounded issue detail/list project-mention scans and trimmed large
issue-list payload fields to keep issue reads lighter.
- Hardened company-skill list projection and cost/finance aggregation so
large markdown blobs and large summed values do not leak into list
responses or overflow 32-bit casts.
- Added targeted server/UI regression tests for company skills,
costs/finance, issue mention scanning, creator filters, inbox
normalization, and issue reference parsing.
## Verification
- `pnpm exec vitest run
server/src/__tests__/company-skills-service.test.ts
server/src/__tests__/costs-service.test.ts
server/src/__tests__/issues-goal-context-routes.test.ts
server/src/__tests__/issues-service.test.ts ui/src/lib/inbox.test.ts
ui/src/lib/issue-filters.test.ts ui/src/lib/issue-reference.test.ts`
- `gh pr checks 3779`
Current pass set on the PR head: `policy`, `verify`, `e2e`,
`security/snyk (cryppadotta)`, `Greptile Review`
## Risks
- Creator filter options are derived from the currently loaded
issue/agent data, so very sparse result sets may not surface every
historical creator until they appear in the active dataset.
- Cost/finance aggregate casts now use `double precision`; that removes
the current overflow risk, but future schema changes should keep
large-value aggregation behavior under review.
- Issue detail mention scanning now skips comment-body scans on the
detail route, so any consumer that relied on comment-only project
mentions there would need to fetch them separately.
## Model Used
- OpenAI Codex, GPT-5-based coding agent with terminal tool use and
local code execution in the Paperclip workspace. Exact internal model
ID/context-window exposure is not surfaced in 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
- [ ] 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>
2026-04-15 21:13:56 -05:00
|
|
|
import { afterAll, afterEach, beforeAll } from "vitest";
|
|
|
|
|
import { randomUUID } from "node:crypto";
|
|
|
|
|
import { createDb, companies, agents, costEvents, financeEvents, projects } from "@paperclipai/db";
|
|
|
|
|
import { costService } from "../services/costs.ts";
|
|
|
|
|
import { financeService } from "../services/finance.ts";
|
|
|
|
|
import {
|
|
|
|
|
getEmbeddedPostgresTestSupport,
|
|
|
|
|
startEmbeddedPostgresTestDatabase,
|
|
|
|
|
} from "./helpers/embedded-postgres.js";
|
2026-03-10 11:32:12 +05:30
|
|
|
|
|
|
|
|
function makeDb(overrides: Record<string, unknown> = {}) {
|
|
|
|
|
const selectChain = {
|
|
|
|
|
from: vi.fn().mockReturnThis(),
|
|
|
|
|
where: vi.fn().mockReturnThis(),
|
|
|
|
|
leftJoin: vi.fn().mockReturnThis(),
|
|
|
|
|
innerJoin: vi.fn().mockReturnThis(),
|
|
|
|
|
groupBy: vi.fn().mockReturnThis(),
|
|
|
|
|
orderBy: vi.fn().mockReturnThis(),
|
2026-03-14 22:00:12 -05:00
|
|
|
limit: vi.fn().mockReturnThis(),
|
2026-03-10 11:32:12 +05:30
|
|
|
then: vi.fn().mockResolvedValue([]),
|
|
|
|
|
};
|
2026-03-14 22:00:12 -05:00
|
|
|
|
2026-03-10 11:32:12 +05:30
|
|
|
const thenableChain = Object.assign(Promise.resolve([]), selectChain);
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
select: vi.fn().mockReturnValue(thenableChain),
|
|
|
|
|
insert: vi.fn().mockReturnValue({
|
|
|
|
|
values: vi.fn().mockReturnValue({ returning: vi.fn().mockResolvedValue([]) }),
|
|
|
|
|
}),
|
|
|
|
|
update: vi.fn().mockReturnValue({
|
|
|
|
|
set: vi.fn().mockReturnValue({ where: vi.fn().mockResolvedValue([]) }),
|
|
|
|
|
}),
|
|
|
|
|
...overrides,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const mockCompanyService = vi.hoisted(() => ({
|
|
|
|
|
getById: vi.fn(),
|
2026-03-16 15:41:48 -05:00
|
|
|
update: vi.fn(),
|
2026-03-10 11:32:12 +05:30
|
|
|
}));
|
|
|
|
|
const mockAgentService = vi.hoisted(() => ({
|
|
|
|
|
getById: vi.fn(),
|
|
|
|
|
update: vi.fn(),
|
|
|
|
|
}));
|
2026-03-16 08:12:50 -05:00
|
|
|
const mockHeartbeatService = vi.hoisted(() => ({
|
|
|
|
|
cancelBudgetScopeWork: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
}));
|
2026-03-10 11:32:12 +05:30
|
|
|
const mockLogActivity = vi.hoisted(() => vi.fn());
|
|
|
|
|
const mockFetchAllQuotaWindows = vi.hoisted(() => vi.fn());
|
2026-03-14 22:00:12 -05:00
|
|
|
const mockCostService = vi.hoisted(() => ({
|
|
|
|
|
createEvent: vi.fn(),
|
|
|
|
|
summary: vi.fn().mockResolvedValue({ spendCents: 0 }),
|
|
|
|
|
byAgent: vi.fn().mockResolvedValue([]),
|
|
|
|
|
byAgentModel: vi.fn().mockResolvedValue([]),
|
|
|
|
|
byProvider: vi.fn().mockResolvedValue([]),
|
|
|
|
|
byBiller: vi.fn().mockResolvedValue([]),
|
|
|
|
|
windowSpend: vi.fn().mockResolvedValue([]),
|
|
|
|
|
byProject: vi.fn().mockResolvedValue([]),
|
|
|
|
|
}));
|
|
|
|
|
const mockFinanceService = vi.hoisted(() => ({
|
|
|
|
|
createEvent: vi.fn(),
|
|
|
|
|
summary: vi.fn().mockResolvedValue({ debitCents: 0, creditCents: 0, netCents: 0, estimatedDebitCents: 0, eventCount: 0 }),
|
|
|
|
|
byBiller: vi.fn().mockResolvedValue([]),
|
|
|
|
|
byKind: vi.fn().mockResolvedValue([]),
|
|
|
|
|
list: vi.fn().mockResolvedValue([]),
|
|
|
|
|
}));
|
|
|
|
|
const mockBudgetService = vi.hoisted(() => ({
|
|
|
|
|
overview: vi.fn().mockResolvedValue({
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
policies: [],
|
|
|
|
|
activeIncidents: [],
|
|
|
|
|
pausedAgentCount: 0,
|
|
|
|
|
pausedProjectCount: 0,
|
|
|
|
|
pendingApprovalCount: 0,
|
|
|
|
|
}),
|
|
|
|
|
upsertPolicy: vi.fn(),
|
|
|
|
|
resolveIncident: vi.fn(),
|
|
|
|
|
}));
|
2026-03-10 11:32:12 +05:30
|
|
|
|
[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
|
|
|
function registerModuleMocks() {
|
|
|
|
|
vi.doMock("../services/index.js", () => ({
|
|
|
|
|
budgetService: () => mockBudgetService,
|
|
|
|
|
costService: () => mockCostService,
|
|
|
|
|
financeService: () => mockFinanceService,
|
|
|
|
|
companyService: () => mockCompanyService,
|
|
|
|
|
agentService: () => mockAgentService,
|
|
|
|
|
heartbeatService: () => mockHeartbeatService,
|
|
|
|
|
logActivity: mockLogActivity,
|
|
|
|
|
}));
|
2026-04-10 22:26:21 -05:00
|
|
|
|
[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.doMock("../services/quota-windows.js", () => ({
|
|
|
|
|
fetchAllQuotaWindows: mockFetchAllQuotaWindows,
|
|
|
|
|
}));
|
|
|
|
|
}
|
2026-03-10 11:32:12 +05:30
|
|
|
|
2026-04-09 06:12:39 -05:00
|
|
|
async function createApp() {
|
|
|
|
|
const [{ costRoutes }, { errorHandler }] = await Promise.all([
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
vi.importActual<typeof import("../routes/costs.js")>("../routes/costs.js"),
|
|
|
|
|
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
2026-04-09 06:12:39 -05:00
|
|
|
]);
|
2026-03-10 11:32:12 +05:30
|
|
|
const app = express();
|
|
|
|
|
app.use(express.json());
|
|
|
|
|
app.use((req, _res, next) => {
|
|
|
|
|
req.actor = { type: "board", userId: "board-user", source: "local_implicit" };
|
|
|
|
|
next();
|
|
|
|
|
});
|
|
|
|
|
app.use("/api", costRoutes(makeDb() as any));
|
|
|
|
|
app.use(errorHandler);
|
|
|
|
|
return app;
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-09 06:12:39 -05:00
|
|
|
async function createAppWithActor(actor: any) {
|
|
|
|
|
const [{ costRoutes }, { errorHandler }] = await Promise.all([
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
vi.importActual<typeof import("../routes/costs.js")>("../routes/costs.js"),
|
|
|
|
|
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
2026-04-09 06:12:39 -05:00
|
|
|
]);
|
2026-03-16 15:41:48 -05:00
|
|
|
const app = express();
|
|
|
|
|
app.use(express.json());
|
|
|
|
|
app.use((req, _res, next) => {
|
|
|
|
|
req.actor = actor;
|
|
|
|
|
next();
|
|
|
|
|
});
|
|
|
|
|
app.use("/api", costRoutes(makeDb() as any));
|
|
|
|
|
app.use(errorHandler);
|
|
|
|
|
return app;
|
|
|
|
|
}
|
|
|
|
|
|
2026-04-10 22:26:21 -05:00
|
|
|
async function loadCostParsers() {
|
|
|
|
|
const { parseCostDateRange, parseCostLimit } = await import("../routes/costs.js");
|
|
|
|
|
return { parseCostDateRange, parseCostLimit };
|
|
|
|
|
}
|
|
|
|
|
|
2026-03-14 22:00:12 -05:00
|
|
|
beforeEach(() => {
|
2026-04-09 06:12:39 -05:00
|
|
|
vi.resetModules();
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
vi.doUnmock("../services/index.js");
|
|
|
|
|
vi.doUnmock("../services/quota-windows.js");
|
|
|
|
|
vi.doUnmock("../routes/costs.js");
|
|
|
|
|
vi.doUnmock("../middleware/index.js");
|
|
|
|
|
registerModuleMocks();
|
|
|
|
|
vi.clearAllMocks();
|
2026-03-16 15:41:48 -05:00
|
|
|
mockCompanyService.update.mockResolvedValue({
|
|
|
|
|
id: "company-1",
|
|
|
|
|
name: "Paperclip",
|
|
|
|
|
budgetMonthlyCents: 100,
|
|
|
|
|
spentMonthlyCents: 0,
|
|
|
|
|
});
|
|
|
|
|
mockAgentService.update.mockResolvedValue({
|
|
|
|
|
id: "agent-1",
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
name: "Budget Agent",
|
|
|
|
|
budgetMonthlyCents: 100,
|
|
|
|
|
spentMonthlyCents: 0,
|
|
|
|
|
});
|
|
|
|
|
mockBudgetService.upsertPolicy.mockResolvedValue(undefined);
|
2026-03-14 22:00:12 -05:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe("cost routes", () => {
|
2026-04-10 22:26:21 -05:00
|
|
|
it("accepts valid ISO date strings", async () => {
|
|
|
|
|
const { parseCostDateRange } = await loadCostParsers();
|
|
|
|
|
expect(parseCostDateRange({
|
|
|
|
|
from: "2026-01-01T00:00:00.000Z",
|
|
|
|
|
to: "2026-01-31T23:59:59.999Z",
|
|
|
|
|
})).toEqual({
|
|
|
|
|
from: new Date("2026-01-01T00:00:00.000Z"),
|
|
|
|
|
to: new Date("2026-01-31T23:59:59.999Z"),
|
|
|
|
|
});
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns 400 for an invalid 'from' date string", async () => {
|
2026-04-10 22:26:21 -05:00
|
|
|
const { parseCostDateRange } = await loadCostParsers();
|
|
|
|
|
expect(() => parseCostDateRange({ from: "not-a-date" })).toThrow(/invalid 'from' date/i);
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("returns 400 for an invalid 'to' date string", async () => {
|
2026-04-10 22:26:21 -05:00
|
|
|
const { parseCostDateRange } = await loadCostParsers();
|
|
|
|
|
expect(() => parseCostDateRange({ to: "banana" })).toThrow(/invalid 'to' date/i);
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
|
|
|
|
|
2026-03-14 22:00:12 -05:00
|
|
|
it("returns finance summary rows for valid requests", async () => {
|
2026-04-09 06:12:39 -05:00
|
|
|
const app = await createApp();
|
2026-03-14 22:00:12 -05:00
|
|
|
const res = await request(app)
|
|
|
|
|
.get("/api/companies/company-1/costs/finance-summary")
|
|
|
|
|
.query({ from: "2026-02-01T00:00:00.000Z", to: "2026-02-28T23:59:59.999Z" });
|
2026-03-10 11:32:12 +05:30
|
|
|
expect(res.status).toBe(200);
|
2026-03-14 22:00:12 -05:00
|
|
|
expect(mockFinanceService.summary).toHaveBeenCalled();
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
|
|
|
|
|
2026-03-14 22:00:12 -05:00
|
|
|
it("returns 400 for invalid finance event list limits", async () => {
|
2026-04-10 22:26:21 -05:00
|
|
|
const { parseCostLimit } = await loadCostParsers();
|
|
|
|
|
expect(() => parseCostLimit({ limit: "0" })).toThrow(/invalid 'limit'/i);
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
|
|
|
|
|
2026-03-14 22:00:12 -05:00
|
|
|
it("accepts valid finance event list limits", async () => {
|
2026-04-10 22:26:21 -05:00
|
|
|
const { parseCostLimit } = await loadCostParsers();
|
|
|
|
|
expect(parseCostLimit({ limit: "25" })).toBe(25);
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
2026-03-16 15:41:48 -05:00
|
|
|
|
|
|
|
|
it("rejects company budget updates for board users outside the company", async () => {
|
2026-04-09 06:12:39 -05:00
|
|
|
const app = await createAppWithActor({
|
2026-03-16 15:41:48 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: ["company-2"],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch("/api/companies/company-1/budgets")
|
|
|
|
|
.send({ budgetMonthlyCents: 2500 });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(mockCompanyService.update).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("rejects agent budget updates for board users outside the agent company", async () => {
|
|
|
|
|
mockAgentService.getById.mockResolvedValue({
|
|
|
|
|
id: "agent-1",
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
name: "Budget Agent",
|
|
|
|
|
budgetMonthlyCents: 100,
|
|
|
|
|
spentMonthlyCents: 0,
|
|
|
|
|
});
|
2026-04-09 06:12:39 -05:00
|
|
|
const app = await createAppWithActor({
|
2026-03-16 15:41:48 -05:00
|
|
|
type: "board",
|
|
|
|
|
userId: "board-user",
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: ["company-2"],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const res = await request(app)
|
|
|
|
|
.patch("/api/agents/agent-1/budgets")
|
|
|
|
|
.send({ budgetMonthlyCents: 2500 });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(403);
|
|
|
|
|
expect(mockAgentService.update).not.toHaveBeenCalled();
|
|
|
|
|
});
|
2026-03-10 11:32:12 +05:30
|
|
|
});
|
Sync/master post pap1497 followups 2026 04 15 (#3779)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - The board depends on issue, inbox, cost, and company-skill surfaces
to stay accurate and fast while agents are actively working
> - The PAP-1497 follow-up branch exposed a few rough edges in those
surfaces: stale active-run state on completed issues, missing creator
filters, oversized issue payload scans, and placeholder issue-route
parsing
> - Those gaps make the control plane harder to trust because operators
can see misleading run state, miss the right subset of work, or pay
extra query/render cost on large issue records
> - This pull request tightens those follow-ups across server and UI
code, and adds regression coverage for the affected paths
> - The benefit is a more reliable issue workflow, safer high-volume
cost aggregation, and clearer board/operator navigation
## What Changed
- Added the `v2026.415.0` release changelog entry.
- Fixed stale issue-run presentation after completion and reused the
shared issue-path parser so literal route placeholders no longer become
issue links.
- Added creator filters to the Issues page and Inbox, including
persisted filter-state normalization and regression coverage.
- Bounded issue detail/list project-mention scans and trimmed large
issue-list payload fields to keep issue reads lighter.
- Hardened company-skill list projection and cost/finance aggregation so
large markdown blobs and large summed values do not leak into list
responses or overflow 32-bit casts.
- Added targeted server/UI regression tests for company skills,
costs/finance, issue mention scanning, creator filters, inbox
normalization, and issue reference parsing.
## Verification
- `pnpm exec vitest run
server/src/__tests__/company-skills-service.test.ts
server/src/__tests__/costs-service.test.ts
server/src/__tests__/issues-goal-context-routes.test.ts
server/src/__tests__/issues-service.test.ts ui/src/lib/inbox.test.ts
ui/src/lib/issue-filters.test.ts ui/src/lib/issue-reference.test.ts`
- `gh pr checks 3779`
Current pass set on the PR head: `policy`, `verify`, `e2e`,
`security/snyk (cryppadotta)`, `Greptile Review`
## Risks
- Creator filter options are derived from the currently loaded
issue/agent data, so very sparse result sets may not surface every
historical creator until they appear in the active dataset.
- Cost/finance aggregate casts now use `double precision`; that removes
the current overflow risk, but future schema changes should keep
large-value aggregation behavior under review.
- Issue detail mention scanning now skips comment-body scans on the
detail route, so any consumer that relied on comment-only project
mentions there would need to fetch them separately.
## Model Used
- OpenAI Codex, GPT-5-based coding agent with terminal tool use and
local code execution in the Paperclip workspace. Exact internal model
ID/context-window exposure is not surfaced in 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
- [ ] 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>
2026-04-15 21:13:56 -05:00
|
|
|
|
|
|
|
|
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
|
|
|
|
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
|
|
|
|
|
|
|
|
|
|
describeEmbeddedPostgres("cost and finance aggregate overflow handling", () => {
|
|
|
|
|
let db!: ReturnType<typeof createDb>;
|
|
|
|
|
let costs!: ReturnType<typeof costService>;
|
|
|
|
|
let finance!: ReturnType<typeof financeService>;
|
|
|
|
|
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
|
|
|
|
|
|
|
|
|
beforeAll(async () => {
|
|
|
|
|
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-costs-service-");
|
|
|
|
|
db = createDb(tempDb.connectionString);
|
|
|
|
|
costs = costService(db);
|
|
|
|
|
finance = financeService(db);
|
|
|
|
|
}, 20_000);
|
|
|
|
|
|
|
|
|
|
afterEach(async () => {
|
|
|
|
|
await db.delete(financeEvents);
|
|
|
|
|
await db.delete(costEvents);
|
|
|
|
|
await db.delete(projects);
|
|
|
|
|
await db.delete(agents);
|
|
|
|
|
await db.delete(companies);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
afterAll(async () => {
|
|
|
|
|
await tempDb?.cleanup();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("aggregates cost event sums above int32 without raising Postgres integer overflow", async () => {
|
|
|
|
|
const companyId = randomUUID();
|
|
|
|
|
const agentId = randomUUID();
|
|
|
|
|
const projectId = randomUUID();
|
|
|
|
|
|
|
|
|
|
await db.insert(companies).values({
|
|
|
|
|
id: companyId,
|
|
|
|
|
name: "Paperclip",
|
|
|
|
|
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
|
|
|
|
requireBoardApprovalForNewAgents: false,
|
|
|
|
|
});
|
|
|
|
|
await db.insert(agents).values({
|
|
|
|
|
id: agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
name: "Cost Agent",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
status: "active",
|
|
|
|
|
adapterType: "codex_local",
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
runtimeConfig: {},
|
|
|
|
|
permissions: {},
|
|
|
|
|
});
|
|
|
|
|
await db.insert(projects).values({
|
|
|
|
|
id: projectId,
|
|
|
|
|
companyId,
|
|
|
|
|
name: "Overflow Project",
|
|
|
|
|
status: "active",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await db.insert(costEvents).values([
|
|
|
|
|
{
|
|
|
|
|
companyId,
|
|
|
|
|
agentId,
|
|
|
|
|
projectId,
|
|
|
|
|
provider: "openai",
|
|
|
|
|
biller: "openai",
|
|
|
|
|
billingType: "metered_api",
|
|
|
|
|
model: "gpt-5",
|
|
|
|
|
inputTokens: 2_000_000_000,
|
|
|
|
|
cachedInputTokens: 0,
|
|
|
|
|
outputTokens: 200_000_000,
|
|
|
|
|
costCents: 2_000_000_000,
|
|
|
|
|
occurredAt: new Date("2026-04-10T00:00:00.000Z"),
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
companyId,
|
|
|
|
|
agentId,
|
|
|
|
|
projectId,
|
|
|
|
|
provider: "openai",
|
|
|
|
|
biller: "openai",
|
|
|
|
|
billingType: "metered_api",
|
|
|
|
|
model: "gpt-5",
|
|
|
|
|
inputTokens: 2_000_000_000,
|
|
|
|
|
cachedInputTokens: 10,
|
|
|
|
|
outputTokens: 200_000_000,
|
|
|
|
|
costCents: 2_000_000_000,
|
|
|
|
|
occurredAt: new Date("2026-04-11T00:00:00.000Z"),
|
|
|
|
|
},
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
const range = {
|
|
|
|
|
from: new Date("2026-04-01T00:00:00.000Z"),
|
|
|
|
|
to: new Date("2026-04-15T23:59:59.999Z"),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const [byAgentRow] = await costs.byAgent(companyId, range);
|
|
|
|
|
const [byProjectRow] = await costs.byProject(companyId, range);
|
|
|
|
|
const [byAgentModelRow] = await costs.byAgentModel(companyId, range);
|
|
|
|
|
|
|
|
|
|
expect(byAgentRow?.costCents).toBe(4_000_000_000);
|
|
|
|
|
expect(byAgentRow?.inputTokens).toBe(4_000_000_000);
|
|
|
|
|
expect(byProjectRow?.costCents).toBe(4_000_000_000);
|
|
|
|
|
expect(byAgentModelRow?.costCents).toBe(4_000_000_000);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("aggregates finance event sums above int32 without raising Postgres integer overflow", async () => {
|
|
|
|
|
const companyId = randomUUID();
|
|
|
|
|
|
|
|
|
|
await db.insert(companies).values({
|
|
|
|
|
id: companyId,
|
|
|
|
|
name: "Paperclip",
|
|
|
|
|
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
|
|
|
|
requireBoardApprovalForNewAgents: false,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await db.insert(financeEvents).values([
|
|
|
|
|
{
|
|
|
|
|
companyId,
|
|
|
|
|
biller: "openai",
|
|
|
|
|
eventKind: "invoice",
|
|
|
|
|
amountCents: 2_000_000_000,
|
|
|
|
|
currency: "USD",
|
|
|
|
|
direction: "debit",
|
|
|
|
|
estimated: false,
|
|
|
|
|
occurredAt: new Date("2026-04-10T00:00:00.000Z"),
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
companyId,
|
|
|
|
|
biller: "openai",
|
|
|
|
|
eventKind: "invoice",
|
|
|
|
|
amountCents: 2_000_000_000,
|
|
|
|
|
currency: "USD",
|
|
|
|
|
direction: "debit",
|
|
|
|
|
estimated: true,
|
|
|
|
|
occurredAt: new Date("2026-04-11T00:00:00.000Z"),
|
|
|
|
|
},
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
const range = {
|
|
|
|
|
from: new Date("2026-04-01T00:00:00.000Z"),
|
|
|
|
|
to: new Date("2026-04-15T23:59:59.999Z"),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const summary = await finance.summary(companyId, range);
|
|
|
|
|
const [byKindRow] = await finance.byKind(companyId, range);
|
|
|
|
|
|
|
|
|
|
expect(summary.debitCents).toBe(4_000_000_000);
|
|
|
|
|
expect(summary.estimatedDebitCents).toBe(2_000_000_000);
|
|
|
|
|
expect(byKindRow?.debitCents).toBe(4_000_000_000);
|
|
|
|
|
expect(byKindRow?.netCents).toBe(4_000_000_000);
|
|
|
|
|
});
|
|
|
|
|
});
|