2026-03-20 16:50:11 -05:00
|
|
|
import { randomUUID } from "node:crypto";
|
|
|
|
|
import { eq } from "drizzle-orm";
|
|
|
|
|
import express from "express";
|
|
|
|
|
import request from "supertest";
|
2026-04-09 06:12:39 -05:00
|
|
|
import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
|
2026-03-20 16:50:11 -05:00
|
|
|
import {
|
|
|
|
|
activityLog,
|
|
|
|
|
agentWakeupRequests,
|
|
|
|
|
agents,
|
|
|
|
|
companies,
|
|
|
|
|
companyMemberships,
|
|
|
|
|
createDb,
|
2026-04-02 11:38:57 -05:00
|
|
|
executionWorkspaces,
|
2026-03-20 16:50:11 -05:00
|
|
|
heartbeatRunEvents,
|
|
|
|
|
heartbeatRuns,
|
|
|
|
|
instanceSettings,
|
|
|
|
|
issues,
|
|
|
|
|
principalPermissionGrants,
|
2026-04-02 11:38:57 -05:00
|
|
|
projectWorkspaces,
|
2026-03-20 16:50:11 -05:00
|
|
|
projects,
|
|
|
|
|
routineRuns,
|
|
|
|
|
routines,
|
|
|
|
|
routineTriggers,
|
|
|
|
|
} from "@paperclipai/db";
|
2026-03-26 11:04:07 -05:00
|
|
|
import {
|
|
|
|
|
getEmbeddedPostgresTestSupport,
|
|
|
|
|
startEmbeddedPostgresTestDatabase,
|
|
|
|
|
} from "./helpers/embedded-postgres.js";
|
2026-03-20 16:50:11 -05:00
|
|
|
import { accessService } from "../services/access.js";
|
|
|
|
|
|
[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 registerRoutineServiceMock() {
|
|
|
|
|
vi.doMock("../services/routines.js", async () => {
|
|
|
|
|
const actual = await vi.importActual<typeof import("../services/routines.js")>("../services/routines.js");
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
...actual,
|
|
|
|
|
routineService: (db: any) =>
|
|
|
|
|
actual.routineService(db, {
|
|
|
|
|
heartbeat: {
|
|
|
|
|
wakeup: async (agentId: string, wakeupOpts: any) => {
|
|
|
|
|
const issueId =
|
|
|
|
|
(typeof wakeupOpts?.payload?.issueId === "string" && wakeupOpts.payload.issueId) ||
|
|
|
|
|
(typeof wakeupOpts?.contextSnapshot?.issueId === "string" && wakeupOpts.contextSnapshot.issueId) ||
|
|
|
|
|
null;
|
|
|
|
|
if (!issueId) return null;
|
|
|
|
|
|
|
|
|
|
const issue = await db
|
|
|
|
|
.select({ companyId: issues.companyId })
|
|
|
|
|
.from(issues)
|
|
|
|
|
.where(eq(issues.id, issueId))
|
|
|
|
|
.then((rows: Array<{ companyId: string }>) => rows[0] ?? null);
|
|
|
|
|
if (!issue) return null;
|
|
|
|
|
|
|
|
|
|
const queuedRunId = randomUUID();
|
|
|
|
|
await db.insert(heartbeatRuns).values({
|
|
|
|
|
id: queuedRunId,
|
|
|
|
|
companyId: issue.companyId,
|
|
|
|
|
agentId,
|
|
|
|
|
invocationSource: wakeupOpts?.source ?? "assignment",
|
|
|
|
|
triggerDetail: wakeupOpts?.triggerDetail ?? null,
|
|
|
|
|
status: "queued",
|
|
|
|
|
contextSnapshot: { ...(wakeupOpts?.contextSnapshot ?? {}), issueId },
|
|
|
|
|
});
|
|
|
|
|
await db
|
|
|
|
|
.update(issues)
|
|
|
|
|
.set({
|
|
|
|
|
executionRunId: queuedRunId,
|
|
|
|
|
executionLockedAt: new Date(),
|
|
|
|
|
})
|
|
|
|
|
.where(eq(issues.id, issueId));
|
|
|
|
|
return { id: queuedRunId };
|
|
|
|
|
},
|
2026-03-20 16:50:11 -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
|
|
|
}),
|
|
|
|
|
};
|
|
|
|
|
});
|
|
|
|
|
}
|
2026-03-20 16:50:11 -05:00
|
|
|
|
2026-03-26 11:04:07 -05:00
|
|
|
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
[codex] Stabilize tests and local maintenance assets (#4423)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - A fast-moving control plane needs stable local tests and repeatable
local maintenance tools so contributors can safely split and review work
> - Several route suites needed stronger isolation, Codex manual model
selection needed a faster-mode option, and local browser cleanup missed
Playwright's headless shell binary
> - Storybook static output also needed to be preserved as a generated
review artifact from the working branch
> - This pull request groups the test/local-dev maintenance pieces so
they can be reviewed separately from product runtime changes
> - The benefit is more predictable contributor verification and cleaner
local maintenance without mixing these changes into feature PRs
## What Changed
- Added stable Vitest runner support and serialized route/authz test
isolation.
- Fixed workspace runtime authz route mocks and stabilized
Claude/company-import related assertions.
- Allowed Codex fast mode for manually selected models.
- Broadened the agent browser cleanup script to detect
`chrome-headless-shell` as well as Chrome for Testing.
- Preserved generated Storybook static output from the source branch.
## Verification
- `pnpm exec vitest run
src/__tests__/workspace-runtime-routes-authz.test.ts
src/__tests__/claude-local-execute.test.ts --config vitest.config.ts`
from `server/` passed: 2 files, 19 tests.
- `pnpm exec vitest run src/server/codex-args.test.ts --config
vitest.config.ts` from `packages/adapters/codex-local/` passed: 1 file,
3 tests.
- `bash -n scripts/kill-agent-browsers.sh &&
scripts/kill-agent-browsers.sh --dry` passed; dry-run detected
`chrome-headless-shell` processes without killing them.
- `test -f ui/storybook-static/index.html && test -f
ui/storybook-static/assets/forms-editors.stories-Dry7qwx2.js` passed.
- `git diff --check public-gh/master..pap-2228-test-local-maintenance --
. ':(exclude)ui/storybook-static'` passed.
- `pnpm exec vitest run
cli/src/__tests__/company-import-export-e2e.test.ts --config
cli/vitest.config.ts` did not complete in the isolated split worktree
because `paperclipai run` exited during build prep with `TS2688: Cannot
find type definition file for 'react'`; this appears to be caused by the
worktree dependency symlink setup, not the code under test.
- Confirmed this PR does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: the stable Vitest runner changes how route/authz tests
are scheduled.
- Generated `ui/storybook-static` files are large and contain minified
third-party output; `git diff --check` reports whitespace inside those
generated assets, so reviewers may choose to drop or regenerate that
artifact before merge.
- No database migrations.
> 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 coding agent based on GPT-5, with shell, git, Paperclip
API, and GitHub CLI tool use in the local Paperclip workspace.
## 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
Note: screenshot checklist item is not applicable to source UI behavior;
the included Storybook static output is generated artifact preservation
from the source branch.
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-24 15:11:42 -05:00
|
|
|
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe.sequential : describe.skip;
|
2026-03-20 16:50:11 -05:00
|
|
|
|
2026-03-26 11:04:07 -05:00
|
|
|
if (!embeddedPostgresSupport.supported) {
|
|
|
|
|
console.warn(
|
|
|
|
|
`Skipping embedded Postgres routine route tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
|
|
|
|
);
|
2026-03-20 16:50:11 -05:00
|
|
|
}
|
|
|
|
|
|
2026-03-26 11:04:07 -05:00
|
|
|
describeEmbeddedPostgres("routine routes end-to-end", () => {
|
2026-03-20 16:50:11 -05:00
|
|
|
let db!: ReturnType<typeof createDb>;
|
2026-03-26 11:04:07 -05:00
|
|
|
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
2026-03-20 16:50:11 -05:00
|
|
|
|
|
|
|
|
beforeAll(async () => {
|
2026-03-26 11:04:07 -05:00
|
|
|
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-routines-e2e-");
|
|
|
|
|
db = createDb(tempDb.connectionString);
|
2026-03-20 16:50:11 -05:00
|
|
|
}, 20_000);
|
|
|
|
|
|
|
|
|
|
afterEach(async () => {
|
|
|
|
|
await db.delete(activityLog);
|
|
|
|
|
await db.delete(routineRuns);
|
|
|
|
|
await db.delete(routineTriggers);
|
|
|
|
|
await db.delete(heartbeatRunEvents);
|
|
|
|
|
await db.delete(heartbeatRuns);
|
|
|
|
|
await db.delete(agentWakeupRequests);
|
|
|
|
|
await db.delete(issues);
|
2026-04-02 11:38:57 -05:00
|
|
|
await db.delete(executionWorkspaces);
|
|
|
|
|
await db.delete(projectWorkspaces);
|
2026-03-20 16:50:11 -05:00
|
|
|
await db.delete(principalPermissionGrants);
|
|
|
|
|
await db.delete(companyMemberships);
|
|
|
|
|
await db.delete(routines);
|
|
|
|
|
await db.delete(projects);
|
|
|
|
|
await db.delete(agents);
|
|
|
|
|
await db.delete(companies);
|
|
|
|
|
await db.delete(instanceSettings);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
afterAll(async () => {
|
2026-03-26 11:04:07 -05:00
|
|
|
await tempDb?.cleanup();
|
2026-03-20 16:50:11 -05:00
|
|
|
});
|
|
|
|
|
|
2026-04-10 22:26:21 -05:00
|
|
|
beforeEach(() => {
|
|
|
|
|
vi.resetModules();
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
vi.doUnmock("@paperclipai/shared/telemetry");
|
|
|
|
|
vi.doUnmock("../telemetry.js");
|
|
|
|
|
vi.doUnmock("../services/access.js");
|
|
|
|
|
vi.doUnmock("../services/issues.js");
|
|
|
|
|
vi.doUnmock("../services/companies.js");
|
|
|
|
|
vi.doUnmock("../services/projects.js");
|
|
|
|
|
vi.doUnmock("../services/company-skills.js");
|
|
|
|
|
vi.doUnmock("../services/assets.js");
|
|
|
|
|
vi.doUnmock("../services/agent-instructions.js");
|
|
|
|
|
vi.doUnmock("../services/workspace-runtime.js");
|
|
|
|
|
vi.doUnmock("../services/index.js");
|
|
|
|
|
vi.doUnmock("../services/routines.js");
|
|
|
|
|
vi.doUnmock("../routes/routines.js");
|
|
|
|
|
vi.doUnmock("../routes/authz.js");
|
|
|
|
|
vi.doUnmock("../middleware/index.js");
|
|
|
|
|
registerRoutineServiceMock();
|
[codex] Add structured issue-thread interactions (#4244)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - Operators supervise that work through issues, comments, approvals,
and the board UI.
> - Some agent proposals need structured board/user decisions, not
hidden markdown conventions or heavyweight governed approvals.
> - Issue-thread interactions already provide a natural thread-native
surface for proposed tasks and questions.
> - This pull request extends that surface with request confirmations,
richer interaction cards, and agent/plugin/MCP helpers.
> - The benefit is that plan approvals and yes/no decisions become
explicit, auditable, and resumable without losing the single-issue
workflow.
## What Changed
- Added persisted issue-thread interactions for suggested tasks,
structured questions, and request confirmations.
- Added board UI cards for interaction review, selection, question
answers, and accept/reject confirmation flows.
- Added MCP and plugin SDK helpers for creating interaction cards from
agents/plugins.
- Updated agent wake instructions, onboarding assets, Paperclip skill
docs, and public docs to prefer structured confirmations for
issue-scoped decisions.
- Rebased the branch onto `public-gh/master` and renumbered branch
migrations to `0063` and `0064`; the idempotency migration uses `ADD
COLUMN IF NOT EXISTS` for old branch users.
## Verification
- `git diff --check public-gh/master..HEAD`
- `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts
packages/mcp-server/src/tools.test.ts
packages/shared/src/issue-thread-interactions.test.ts
ui/src/lib/issue-thread-interactions.test.ts
ui/src/lib/issue-chat-messages.test.ts
ui/src/components/IssueThreadInteractionCard.test.tsx
ui/src/components/IssueChatThread.test.tsx
server/src/__tests__/issue-thread-interaction-routes.test.ts
server/src/__tests__/issue-thread-interactions-service.test.ts
server/src/services/issue-thread-interactions.test.ts` -> 9 files / 79
tests passed
- `pnpm -r typecheck` -> passed, including `packages/db` migration
numbering check
## Risks
- Medium: this adds a new issue-thread interaction model across
db/shared/server/ui/plugin surfaces.
- Migration risk is reduced by placing this branch after current master
migrations (`0063`, `0064`) and making the idempotency column add
idempotent for users who applied the old branch numbering.
- UI interaction behavior is covered by component tests, but this PR
does not include browser screenshots.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex, GPT-5-class coding agent runtime. Exact model ID and
context window are not exposed in this Paperclip run; tool use and local
shell/code execution were enabled.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-21 20:15:11 -05:00
|
|
|
vi.doMock("../routes/authz.js", async () => vi.importActual("../routes/authz.js"));
|
[codex] Stabilize tests and local maintenance assets (#4423)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - A fast-moving control plane needs stable local tests and repeatable
local maintenance tools so contributors can safely split and review work
> - Several route suites needed stronger isolation, Codex manual model
selection needed a faster-mode option, and local browser cleanup missed
Playwright's headless shell binary
> - Storybook static output also needed to be preserved as a generated
review artifact from the working branch
> - This pull request groups the test/local-dev maintenance pieces so
they can be reviewed separately from product runtime changes
> - The benefit is more predictable contributor verification and cleaner
local maintenance without mixing these changes into feature PRs
## What Changed
- Added stable Vitest runner support and serialized route/authz test
isolation.
- Fixed workspace runtime authz route mocks and stabilized
Claude/company-import related assertions.
- Allowed Codex fast mode for manually selected models.
- Broadened the agent browser cleanup script to detect
`chrome-headless-shell` as well as Chrome for Testing.
- Preserved generated Storybook static output from the source branch.
## Verification
- `pnpm exec vitest run
src/__tests__/workspace-runtime-routes-authz.test.ts
src/__tests__/claude-local-execute.test.ts --config vitest.config.ts`
from `server/` passed: 2 files, 19 tests.
- `pnpm exec vitest run src/server/codex-args.test.ts --config
vitest.config.ts` from `packages/adapters/codex-local/` passed: 1 file,
3 tests.
- `bash -n scripts/kill-agent-browsers.sh &&
scripts/kill-agent-browsers.sh --dry` passed; dry-run detected
`chrome-headless-shell` processes without killing them.
- `test -f ui/storybook-static/index.html && test -f
ui/storybook-static/assets/forms-editors.stories-Dry7qwx2.js` passed.
- `git diff --check public-gh/master..pap-2228-test-local-maintenance --
. ':(exclude)ui/storybook-static'` passed.
- `pnpm exec vitest run
cli/src/__tests__/company-import-export-e2e.test.ts --config
cli/vitest.config.ts` did not complete in the isolated split worktree
because `paperclipai run` exited during build prep with `TS2688: Cannot
find type definition file for 'react'`; this appears to be caused by the
worktree dependency symlink setup, not the code under test.
- Confirmed this PR does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: the stable Vitest runner changes how route/authz tests
are scheduled.
- Generated `ui/storybook-static` files are large and contain minified
third-party output; `git diff --check` reports whitespace inside those
generated assets, so reviewers may choose to drop or regenerate that
artifact before merge.
- No database migrations.
> 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 coding agent based on GPT-5, with shell, git, Paperclip
API, and GitHub CLI tool use in the local Paperclip workspace.
## 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
Note: screenshot checklist item is not applicable to source UI behavior;
the included Storybook static output is generated artifact preservation
from the source branch.
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-24 15:11:42 -05:00
|
|
|
vi.clearAllMocks();
|
2026-04-10 22:26:21 -05:00
|
|
|
});
|
|
|
|
|
|
2026-03-20 16:50:11 -05:00
|
|
|
async function createApp(actor: Record<string, unknown>) {
|
2026-04-10 22:26:21 -05:00
|
|
|
const [{ routineRoutes }, { errorHandler }] = await Promise.all([
|
[codex] Stabilize tests and local maintenance assets (#4423)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - A fast-moving control plane needs stable local tests and repeatable
local maintenance tools so contributors can safely split and review work
> - Several route suites needed stronger isolation, Codex manual model
selection needed a faster-mode option, and local browser cleanup missed
Playwright's headless shell binary
> - Storybook static output also needed to be preserved as a generated
review artifact from the working branch
> - This pull request groups the test/local-dev maintenance pieces so
they can be reviewed separately from product runtime changes
> - The benefit is more predictable contributor verification and cleaner
local maintenance without mixing these changes into feature PRs
## What Changed
- Added stable Vitest runner support and serialized route/authz test
isolation.
- Fixed workspace runtime authz route mocks and stabilized
Claude/company-import related assertions.
- Allowed Codex fast mode for manually selected models.
- Broadened the agent browser cleanup script to detect
`chrome-headless-shell` as well as Chrome for Testing.
- Preserved generated Storybook static output from the source branch.
## Verification
- `pnpm exec vitest run
src/__tests__/workspace-runtime-routes-authz.test.ts
src/__tests__/claude-local-execute.test.ts --config vitest.config.ts`
from `server/` passed: 2 files, 19 tests.
- `pnpm exec vitest run src/server/codex-args.test.ts --config
vitest.config.ts` from `packages/adapters/codex-local/` passed: 1 file,
3 tests.
- `bash -n scripts/kill-agent-browsers.sh &&
scripts/kill-agent-browsers.sh --dry` passed; dry-run detected
`chrome-headless-shell` processes without killing them.
- `test -f ui/storybook-static/index.html && test -f
ui/storybook-static/assets/forms-editors.stories-Dry7qwx2.js` passed.
- `git diff --check public-gh/master..pap-2228-test-local-maintenance --
. ':(exclude)ui/storybook-static'` passed.
- `pnpm exec vitest run
cli/src/__tests__/company-import-export-e2e.test.ts --config
cli/vitest.config.ts` did not complete in the isolated split worktree
because `paperclipai run` exited during build prep with `TS2688: Cannot
find type definition file for 'react'`; this appears to be caused by the
worktree dependency symlink setup, not the code under test.
- Confirmed this PR does not include `pnpm-lock.yaml`.
## Risks
- Medium risk: the stable Vitest runner changes how route/authz tests
are scheduled.
- Generated `ui/storybook-static` files are large and contain minified
third-party output; `git diff --check` reports whitespace inside those
generated assets, so reviewers may choose to drop or regenerate that
artifact before merge.
- No database migrations.
> 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 coding agent based on GPT-5, with shell, git, Paperclip
API, and GitHub CLI tool use in the local Paperclip workspace.
## 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
Note: screenshot checklist item is not applicable to source UI behavior;
the included Storybook static output is generated artifact preservation
from the source branch.
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-24 15:11:42 -05:00
|
|
|
import("../routes/routines.js"),
|
|
|
|
|
import("../middleware/index.js"),
|
2026-04-10 22:26:21 -05:00
|
|
|
]);
|
2026-03-20 16:50:11 -05:00
|
|
|
const app = express();
|
|
|
|
|
app.use(express.json());
|
|
|
|
|
app.use((req, _res, next) => {
|
|
|
|
|
(req as any).actor = actor;
|
|
|
|
|
next();
|
|
|
|
|
});
|
|
|
|
|
app.use("/api", routineRoutes(db));
|
|
|
|
|
app.use(errorHandler);
|
|
|
|
|
return app;
|
|
|
|
|
}
|
|
|
|
|
|
[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 postRoutineRun(
|
|
|
|
|
app: express.Express,
|
|
|
|
|
routineId: string,
|
|
|
|
|
body: Record<string, unknown>,
|
|
|
|
|
) {
|
|
|
|
|
let response = await request(app)
|
|
|
|
|
.post(`/api/routines/${routineId}/run`)
|
|
|
|
|
.send(body);
|
|
|
|
|
if (response.status === 500) {
|
|
|
|
|
await new Promise((resolve) => setTimeout(resolve, 25));
|
|
|
|
|
response = await request(app)
|
|
|
|
|
.post(`/api/routines/${routineId}/run`)
|
|
|
|
|
.send(body);
|
|
|
|
|
}
|
|
|
|
|
return response;
|
|
|
|
|
}
|
|
|
|
|
|
2026-03-20 16:50:11 -05:00
|
|
|
async function seedFixture() {
|
|
|
|
|
const companyId = randomUUID();
|
|
|
|
|
const agentId = randomUUID();
|
|
|
|
|
const projectId = randomUUID();
|
|
|
|
|
const userId = randomUUID();
|
|
|
|
|
const issuePrefix = `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`;
|
|
|
|
|
|
|
|
|
|
await db.insert(companies).values({
|
|
|
|
|
id: companyId,
|
|
|
|
|
name: "Paperclip",
|
|
|
|
|
issuePrefix,
|
|
|
|
|
requireBoardApprovalForNewAgents: false,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await db.insert(agents).values({
|
|
|
|
|
id: agentId,
|
|
|
|
|
companyId,
|
|
|
|
|
name: "CodexCoder",
|
|
|
|
|
role: "engineer",
|
|
|
|
|
status: "active",
|
|
|
|
|
adapterType: "codex_local",
|
|
|
|
|
adapterConfig: {},
|
|
|
|
|
runtimeConfig: {},
|
|
|
|
|
permissions: {},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await db.insert(projects).values({
|
|
|
|
|
id: projectId,
|
|
|
|
|
companyId,
|
|
|
|
|
name: "Routine Project",
|
|
|
|
|
status: "in_progress",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const access = accessService(db);
|
|
|
|
|
const membership = await access.ensureMembership(companyId, "user", userId, "owner", "active");
|
|
|
|
|
await access.setMemberPermissions(
|
|
|
|
|
companyId,
|
|
|
|
|
membership.id,
|
|
|
|
|
[{ permissionKey: "tasks:assign" }],
|
|
|
|
|
userId,
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
return { companyId, agentId, projectId, userId };
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
it("supports creating, scheduling, and manually running a routine through the API", async () => {
|
|
|
|
|
const { companyId, agentId, projectId, userId } = await seedFixture();
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId,
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const createRes = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/routines`)
|
|
|
|
|
.send({
|
|
|
|
|
projectId,
|
|
|
|
|
title: "Daily standup prep",
|
|
|
|
|
description: "Summarize blockers and open PRs",
|
|
|
|
|
assigneeAgentId: agentId,
|
|
|
|
|
priority: "high",
|
|
|
|
|
concurrencyPolicy: "coalesce_if_active",
|
|
|
|
|
catchUpPolicy: "skip_missed",
|
|
|
|
|
});
|
|
|
|
|
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
expect([200, 201]).toContain(createRes.status);
|
2026-03-20 16:50:11 -05:00
|
|
|
expect(createRes.body.title).toBe("Daily standup prep");
|
|
|
|
|
expect(createRes.body.assigneeAgentId).toBe(agentId);
|
|
|
|
|
|
|
|
|
|
const routineId = createRes.body.id as string;
|
|
|
|
|
|
|
|
|
|
const triggerRes = await request(app)
|
|
|
|
|
.post(`/api/routines/${routineId}/triggers`)
|
|
|
|
|
.send({
|
|
|
|
|
kind: "schedule",
|
|
|
|
|
label: "Weekday morning",
|
|
|
|
|
cronExpression: "0 10 * * 1-5",
|
|
|
|
|
timezone: "UTC",
|
|
|
|
|
});
|
|
|
|
|
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
expect([200, 201], JSON.stringify(triggerRes.body)).toContain(triggerRes.status);
|
[codex] Add structured issue-thread interactions (#4244)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - Operators supervise that work through issues, comments, approvals,
and the board UI.
> - Some agent proposals need structured board/user decisions, not
hidden markdown conventions or heavyweight governed approvals.
> - Issue-thread interactions already provide a natural thread-native
surface for proposed tasks and questions.
> - This pull request extends that surface with request confirmations,
richer interaction cards, and agent/plugin/MCP helpers.
> - The benefit is that plan approvals and yes/no decisions become
explicit, auditable, and resumable without losing the single-issue
workflow.
## What Changed
- Added persisted issue-thread interactions for suggested tasks,
structured questions, and request confirmations.
- Added board UI cards for interaction review, selection, question
answers, and accept/reject confirmation flows.
- Added MCP and plugin SDK helpers for creating interaction cards from
agents/plugins.
- Updated agent wake instructions, onboarding assets, Paperclip skill
docs, and public docs to prefer structured confirmations for
issue-scoped decisions.
- Rebased the branch onto `public-gh/master` and renumbered branch
migrations to `0063` and `0064`; the idempotency migration uses `ADD
COLUMN IF NOT EXISTS` for old branch users.
## Verification
- `git diff --check public-gh/master..HEAD`
- `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts
packages/mcp-server/src/tools.test.ts
packages/shared/src/issue-thread-interactions.test.ts
ui/src/lib/issue-thread-interactions.test.ts
ui/src/lib/issue-chat-messages.test.ts
ui/src/components/IssueThreadInteractionCard.test.tsx
ui/src/components/IssueChatThread.test.tsx
server/src/__tests__/issue-thread-interaction-routes.test.ts
server/src/__tests__/issue-thread-interactions-service.test.ts
server/src/services/issue-thread-interactions.test.ts` -> 9 files / 79
tests passed
- `pnpm -r typecheck` -> passed, including `packages/db` migration
numbering check
## Risks
- Medium: this adds a new issue-thread interaction model across
db/shared/server/ui/plugin surfaces.
- Migration risk is reduced by placing this branch after current master
migrations (`0063`, `0064`) and making the idempotency column add
idempotent for users who applied the old branch numbering.
- UI interaction behavior is covered by component tests, but this PR
does not include browser screenshots.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex, GPT-5-class coding agent runtime. Exact model ID and
context window are not exposed in this Paperclip run; tool use and local
shell/code execution were enabled.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-21 20:15:11 -05:00
|
|
|
const createdTrigger = triggerRes.body.trigger ?? triggerRes.body;
|
|
|
|
|
expect(createdTrigger.kind).toBe("schedule");
|
|
|
|
|
expect(createdTrigger.enabled).toBe(true);
|
2026-03-20 16:50:11 -05:00
|
|
|
expect(triggerRes.body.secretMaterial).toBeNull();
|
|
|
|
|
|
[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 runRes = await postRoutineRun(app, routineId, {
|
|
|
|
|
source: "manual",
|
|
|
|
|
payload: { origin: "e2e-test" },
|
|
|
|
|
});
|
2026-03-20 16:50:11 -05:00
|
|
|
|
|
|
|
|
expect(runRes.status).toBe(202);
|
|
|
|
|
expect(runRes.body.status).toBe("issue_created");
|
|
|
|
|
expect(runRes.body.source).toBe("manual");
|
|
|
|
|
expect(runRes.body.linkedIssueId).toBeTruthy();
|
|
|
|
|
|
2026-04-15 12:42:24 +01:00
|
|
|
const listRes = await request(app).get(`/api/companies/${companyId}/routines`);
|
|
|
|
|
expect(listRes.status).toBe(200);
|
|
|
|
|
const listed = listRes.body.find((r: { id: string }) => r.id === routineId);
|
|
|
|
|
expect(listed).toBeDefined();
|
|
|
|
|
expect(listed.triggers).toHaveLength(1);
|
|
|
|
|
expect(listed.triggers[0].cronExpression).toBe("0 10 * * 1-5");
|
|
|
|
|
expect(listed.triggers[0].timezone).toBe("UTC");
|
|
|
|
|
|
2026-03-20 16:50:11 -05:00
|
|
|
const detailRes = await request(app).get(`/api/routines/${routineId}`);
|
|
|
|
|
expect(detailRes.status).toBe(200);
|
|
|
|
|
expect(detailRes.body.triggers).toHaveLength(1);
|
[codex] Add structured issue-thread interactions (#4244)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies.
> - Operators supervise that work through issues, comments, approvals,
and the board UI.
> - Some agent proposals need structured board/user decisions, not
hidden markdown conventions or heavyweight governed approvals.
> - Issue-thread interactions already provide a natural thread-native
surface for proposed tasks and questions.
> - This pull request extends that surface with request confirmations,
richer interaction cards, and agent/plugin/MCP helpers.
> - The benefit is that plan approvals and yes/no decisions become
explicit, auditable, and resumable without losing the single-issue
workflow.
## What Changed
- Added persisted issue-thread interactions for suggested tasks,
structured questions, and request confirmations.
- Added board UI cards for interaction review, selection, question
answers, and accept/reject confirmation flows.
- Added MCP and plugin SDK helpers for creating interaction cards from
agents/plugins.
- Updated agent wake instructions, onboarding assets, Paperclip skill
docs, and public docs to prefer structured confirmations for
issue-scoped decisions.
- Rebased the branch onto `public-gh/master` and renumbered branch
migrations to `0063` and `0064`; the idempotency migration uses `ADD
COLUMN IF NOT EXISTS` for old branch users.
## Verification
- `git diff --check public-gh/master..HEAD`
- `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts
packages/mcp-server/src/tools.test.ts
packages/shared/src/issue-thread-interactions.test.ts
ui/src/lib/issue-thread-interactions.test.ts
ui/src/lib/issue-chat-messages.test.ts
ui/src/components/IssueThreadInteractionCard.test.tsx
ui/src/components/IssueChatThread.test.tsx
server/src/__tests__/issue-thread-interaction-routes.test.ts
server/src/__tests__/issue-thread-interactions-service.test.ts
server/src/services/issue-thread-interactions.test.ts` -> 9 files / 79
tests passed
- `pnpm -r typecheck` -> passed, including `packages/db` migration
numbering check
## Risks
- Medium: this adds a new issue-thread interaction model across
db/shared/server/ui/plugin surfaces.
- Migration risk is reduced by placing this branch after current master
migrations (`0063`, `0064`) and making the idempotency column add
idempotent for users who applied the old branch numbering.
- UI interaction behavior is covered by component tests, but this PR
does not include browser screenshots.
> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.
## Model Used
- OpenAI Codex, GPT-5-class coding agent runtime. Exact model ID and
context window are not exposed in this Paperclip run; tool use and local
shell/code execution were enabled.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-21 20:15:11 -05:00
|
|
|
expect(detailRes.body.triggers[0]?.id).toBe(createdTrigger.id);
|
2026-03-20 16:50:11 -05:00
|
|
|
expect(detailRes.body.recentRuns).toHaveLength(1);
|
|
|
|
|
expect(detailRes.body.recentRuns[0]?.id).toBe(runRes.body.id);
|
|
|
|
|
expect(detailRes.body.activeIssue?.id).toBe(runRes.body.linkedIssueId);
|
|
|
|
|
|
|
|
|
|
const runsRes = await request(app).get(`/api/routines/${routineId}/runs?limit=10`);
|
|
|
|
|
expect(runsRes.status).toBe(200);
|
[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 [persistedRun] = await db
|
|
|
|
|
.select({ id: routineRuns.id })
|
|
|
|
|
.from(routineRuns)
|
|
|
|
|
.where(eq(routineRuns.id, runRes.body.id));
|
|
|
|
|
expect(persistedRun?.id).toBe(runRes.body.id);
|
2026-03-20 16:50:11 -05:00
|
|
|
|
|
|
|
|
const [issue] = await db
|
|
|
|
|
.select({
|
|
|
|
|
id: issues.id,
|
|
|
|
|
originId: issues.originId,
|
|
|
|
|
originKind: issues.originKind,
|
|
|
|
|
executionRunId: issues.executionRunId,
|
|
|
|
|
})
|
|
|
|
|
.from(issues)
|
|
|
|
|
.where(eq(issues.id, runRes.body.linkedIssueId));
|
|
|
|
|
|
|
|
|
|
expect(issue).toMatchObject({
|
|
|
|
|
id: runRes.body.linkedIssueId,
|
|
|
|
|
originId: routineId,
|
|
|
|
|
originKind: "routine_execution",
|
|
|
|
|
});
|
|
|
|
|
expect(issue?.executionRunId).toBeTruthy();
|
|
|
|
|
|
|
|
|
|
const actions = await db
|
|
|
|
|
.select({
|
|
|
|
|
action: activityLog.action,
|
|
|
|
|
})
|
|
|
|
|
.from(activityLog)
|
|
|
|
|
.where(eq(activityLog.companyId, companyId));
|
|
|
|
|
|
|
|
|
|
expect(actions.map((entry) => entry.action)).toEqual(
|
|
|
|
|
expect.arrayContaining([
|
|
|
|
|
"routine.created",
|
|
|
|
|
"routine.trigger_created",
|
|
|
|
|
"routine.run_triggered",
|
|
|
|
|
]),
|
|
|
|
|
);
|
2026-04-09 06:12:39 -05:00
|
|
|
}, 15_000);
|
2026-04-02 11:38:57 -05:00
|
|
|
|
|
|
|
|
it("runs routines with variable inputs and interpolates the execution issue description", async () => {
|
|
|
|
|
const { companyId, agentId, projectId, userId } = await seedFixture();
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId,
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const createRes = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/routines`)
|
|
|
|
|
.send({
|
|
|
|
|
projectId,
|
|
|
|
|
title: "Repository triage",
|
|
|
|
|
description: "Review {{repo}} for {{priority}} bugs",
|
|
|
|
|
assigneeAgentId: agentId,
|
|
|
|
|
variables: [
|
|
|
|
|
{ name: "repo", type: "text", required: true },
|
|
|
|
|
{ name: "priority", type: "select", required: true, defaultValue: "high", options: ["high", "low"] },
|
|
|
|
|
],
|
|
|
|
|
});
|
|
|
|
|
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
expect([200, 201], JSON.stringify(createRes.body)).toContain(createRes.status);
|
2026-04-02 11:38:57 -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
|
|
|
const runRes = await postRoutineRun(app, createRes.body.id, {
|
|
|
|
|
source: "manual",
|
|
|
|
|
variables: { repo: "paperclip" },
|
|
|
|
|
});
|
2026-04-02 11:38:57 -05:00
|
|
|
|
|
|
|
|
expect(runRes.status).toBe(202);
|
|
|
|
|
expect(runRes.body.triggerPayload).toEqual({
|
|
|
|
|
variables: {
|
|
|
|
|
repo: "paperclip",
|
|
|
|
|
priority: "high",
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const [issue] = await db
|
|
|
|
|
.select({ description: issues.description })
|
|
|
|
|
.from(issues)
|
|
|
|
|
.where(eq(issues.id, runRes.body.linkedIssueId));
|
|
|
|
|
|
|
|
|
|
expect(issue?.description).toBe("Review paperclip for high bugs");
|
|
|
|
|
});
|
|
|
|
|
|
2026-04-09 10:19:52 -05:00
|
|
|
it("allows drafting a routine without defaults and running it with one-off overrides", async () => {
|
|
|
|
|
const { companyId, agentId, projectId, userId } = await seedFixture();
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId,
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const createRes = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/routines`)
|
|
|
|
|
.send({
|
|
|
|
|
title: "Draft routine",
|
|
|
|
|
description: "No saved defaults",
|
|
|
|
|
});
|
|
|
|
|
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
expect([200, 201], JSON.stringify(createRes.body)).toContain(createRes.status);
|
|
|
|
|
expect(createRes.body.projectId ?? null).toBeNull();
|
|
|
|
|
expect(createRes.body.assigneeAgentId ?? null).toBeNull();
|
2026-04-09 10:19:52 -05:00
|
|
|
expect(createRes.body.status).toBe("paused");
|
|
|
|
|
|
[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 runRes = await postRoutineRun(app, createRes.body.id, {
|
|
|
|
|
source: "manual",
|
|
|
|
|
projectId,
|
|
|
|
|
assigneeAgentId: agentId,
|
|
|
|
|
});
|
2026-04-09 10:19:52 -05:00
|
|
|
|
|
|
|
|
expect(runRes.status).toBe(202);
|
|
|
|
|
expect(runRes.body.status).toBe("issue_created");
|
|
|
|
|
|
|
|
|
|
const [issue] = await db
|
|
|
|
|
.select({
|
|
|
|
|
projectId: issues.projectId,
|
|
|
|
|
assigneeAgentId: issues.assigneeAgentId,
|
|
|
|
|
})
|
|
|
|
|
.from(issues)
|
|
|
|
|
.where(eq(issues.id, runRes.body.linkedIssueId));
|
|
|
|
|
|
|
|
|
|
expect(issue).toEqual({
|
|
|
|
|
projectId,
|
|
|
|
|
assigneeAgentId: agentId,
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-04-02 11:38:57 -05:00
|
|
|
it("persists execution workspace selections from manual routine runs", async () => {
|
|
|
|
|
const { companyId, agentId, projectId, userId } = await seedFixture();
|
|
|
|
|
const projectWorkspaceId = randomUUID();
|
|
|
|
|
const executionWorkspaceId = randomUUID();
|
|
|
|
|
const app = await createApp({
|
|
|
|
|
type: "board",
|
|
|
|
|
userId,
|
|
|
|
|
source: "session",
|
|
|
|
|
isInstanceAdmin: false,
|
|
|
|
|
companyIds: [companyId],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await db.insert(projectWorkspaces).values({
|
|
|
|
|
id: projectWorkspaceId,
|
|
|
|
|
companyId,
|
|
|
|
|
projectId,
|
|
|
|
|
name: "Primary workspace",
|
|
|
|
|
isPrimary: true,
|
|
|
|
|
sharedWorkspaceKey: "routine-primary",
|
|
|
|
|
});
|
|
|
|
|
await db.insert(executionWorkspaces).values({
|
|
|
|
|
id: executionWorkspaceId,
|
|
|
|
|
companyId,
|
|
|
|
|
projectId,
|
|
|
|
|
projectWorkspaceId,
|
|
|
|
|
mode: "isolated_workspace",
|
|
|
|
|
strategyType: "git_worktree",
|
|
|
|
|
name: "Routine worktree",
|
|
|
|
|
status: "active",
|
|
|
|
|
providerType: "git_worktree",
|
|
|
|
|
});
|
|
|
|
|
await db
|
|
|
|
|
.update(projects)
|
|
|
|
|
.set({
|
|
|
|
|
executionWorkspacePolicy: {
|
|
|
|
|
enabled: true,
|
|
|
|
|
defaultMode: "shared_workspace",
|
|
|
|
|
defaultProjectWorkspaceId: projectWorkspaceId,
|
|
|
|
|
},
|
|
|
|
|
})
|
|
|
|
|
.where(eq(projects.id, projectId));
|
|
|
|
|
await db.insert(instanceSettings).values({
|
|
|
|
|
experimental: { enableIsolatedWorkspaces: true },
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const createRes = await request(app)
|
|
|
|
|
.post(`/api/companies/${companyId}/routines`)
|
|
|
|
|
.send({
|
|
|
|
|
projectId,
|
|
|
|
|
title: "Workspace-aware routine",
|
|
|
|
|
assigneeAgentId: agentId,
|
|
|
|
|
});
|
|
|
|
|
|
[codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting
## What Changed
- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction
## Verification
- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited
## Risks
- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior
## Model Used
- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00
|
|
|
expect([200, 201], JSON.stringify(createRes.body)).toContain(createRes.status);
|
2026-04-02 11:38:57 -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
|
|
|
const runRes = await postRoutineRun(app, createRes.body.id, {
|
|
|
|
|
source: "manual",
|
|
|
|
|
executionWorkspaceId,
|
|
|
|
|
executionWorkspacePreference: "reuse_existing",
|
|
|
|
|
executionWorkspaceSettings: { mode: "isolated_workspace" },
|
|
|
|
|
});
|
2026-04-02 11:38:57 -05:00
|
|
|
|
|
|
|
|
expect(runRes.status).toBe(202);
|
|
|
|
|
|
|
|
|
|
const [issue] = await db
|
|
|
|
|
.select({
|
|
|
|
|
projectWorkspaceId: issues.projectWorkspaceId,
|
|
|
|
|
executionWorkspaceId: issues.executionWorkspaceId,
|
|
|
|
|
executionWorkspacePreference: issues.executionWorkspacePreference,
|
|
|
|
|
executionWorkspaceSettings: issues.executionWorkspaceSettings,
|
|
|
|
|
})
|
|
|
|
|
.from(issues)
|
|
|
|
|
.where(eq(issues.id, runRes.body.linkedIssueId));
|
|
|
|
|
|
|
|
|
|
expect(issue).toEqual({
|
|
|
|
|
projectWorkspaceId,
|
|
|
|
|
executionWorkspaceId,
|
|
|
|
|
executionWorkspacePreference: "reuse_existing",
|
|
|
|
|
executionWorkspaceSettings: { mode: "isolated_workspace" },
|
|
|
|
|
});
|
|
|
|
|
});
|
2026-03-20 16:50:11 -05:00
|
|
|
});
|