[codex] Harden dashboard run activity charts (#4126)
## Thinking Path
> - Paperclip gives operators a live view of agent work across
dashboards, transcripts, and run activity charts
> - Those views consume live run updates and aggregate run activity from
backend dashboard data
> - Missing or partial run data could make charts brittle, and live
transcript updates were heavier than needed
> - Operators need dashboard data to stay stable even when recent run
payloads are incomplete
> - This pull request hardens dashboard run aggregation, guards chart
rendering, and lightens live run update handling
> - The benefit is a more reliable dashboard during active agent
execution
## What Changed
- Added dashboard run activity types and backend aggregation coverage.
- Guarded activity chart rendering when run data is missing or partial.
- Reduced live transcript update churn in active agent and run chat
surfaces.
- Fixed issue chat avatar alignment in the thread renderer.
- Added focused dashboard, activity chart, and live transcript tests.
## Verification
- `pnpm install --frozen-lockfile --ignore-scripts`
- `pnpm exec vitest run server/src/__tests__/dashboard-service.test.ts
ui/src/components/ActivityCharts.test.tsx
ui/src/components/transcript/useLiveRunTranscripts.test.tsx`
- Result: 8 tests passed, 1 skipped. The embedded Postgres dashboard
service test skipped on this host with the existing PGlite/Postgres init
warning; UI chart and transcript tests passed.
## Risks
- Medium-low risk: aggregation semantics changed, but the UI remains
guarded around incomplete data.
- The dashboard service test is host-skipped here, so CI should confirm
the embedded database path.
> 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, tool-enabled local shell and
GitHub workflow, exact runtime context window not exposed in this
session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have 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, or documented why targeted component tests are sufficient
here
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 10:34:21 -05:00
|
|
|
// @vitest-environment jsdom
|
|
|
|
|
|
|
|
|
|
import { act } from "react";
|
|
|
|
|
import type { ReactNode } from "react";
|
|
|
|
|
import { createRoot, type Root } from "react-dom/client";
|
|
|
|
|
import type { HeartbeatRun } from "@paperclipai/shared";
|
|
|
|
|
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
|
|
|
|
import { RunActivityChart, SuccessRateChart } from "./ActivityCharts";
|
|
|
|
|
|
|
|
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
|
|
|
(globalThis as any).IS_REACT_ACT_ENVIRONMENT = true;
|
|
|
|
|
|
|
|
|
|
let container: HTMLDivElement;
|
|
|
|
|
let root: Root;
|
|
|
|
|
|
|
|
|
|
beforeEach(() => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
vi.setSystemTime(new Date("2026-04-20T12:00:00.000Z"));
|
|
|
|
|
container = document.createElement("div");
|
|
|
|
|
document.body.appendChild(container);
|
|
|
|
|
root = createRoot(container);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
afterEach(() => {
|
|
|
|
|
act(() => root.unmount());
|
|
|
|
|
container.remove();
|
|
|
|
|
vi.useRealTimers();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
function render(ui: ReactNode) {
|
|
|
|
|
act(() => {
|
|
|
|
|
root.render(ui);
|
|
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function createRun(overrides: Partial<HeartbeatRun> = {}): HeartbeatRun {
|
|
|
|
|
return {
|
|
|
|
|
id: "run-1",
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
agentId: "agent-1",
|
|
|
|
|
invocationSource: "on_demand",
|
|
|
|
|
triggerDetail: "manual",
|
|
|
|
|
status: "succeeded",
|
|
|
|
|
startedAt: new Date("2026-04-20T11:58:00.000Z"),
|
|
|
|
|
finishedAt: new Date("2026-04-20T11:59:00.000Z"),
|
|
|
|
|
error: null,
|
|
|
|
|
wakeupRequestId: null,
|
|
|
|
|
exitCode: 0,
|
|
|
|
|
signal: null,
|
|
|
|
|
usageJson: null,
|
|
|
|
|
resultJson: null,
|
|
|
|
|
sessionIdBefore: null,
|
|
|
|
|
sessionIdAfter: null,
|
|
|
|
|
logStore: null,
|
|
|
|
|
logRef: null,
|
|
|
|
|
logBytes: null,
|
|
|
|
|
logSha256: null,
|
|
|
|
|
logCompressed: false,
|
2026-04-24 15:50:32 -05:00
|
|
|
lastOutputAt: null,
|
|
|
|
|
lastOutputSeq: 0,
|
|
|
|
|
lastOutputStream: null,
|
|
|
|
|
lastOutputBytes: null,
|
[codex] Harden dashboard run activity charts (#4126)
## Thinking Path
> - Paperclip gives operators a live view of agent work across
dashboards, transcripts, and run activity charts
> - Those views consume live run updates and aggregate run activity from
backend dashboard data
> - Missing or partial run data could make charts brittle, and live
transcript updates were heavier than needed
> - Operators need dashboard data to stay stable even when recent run
payloads are incomplete
> - This pull request hardens dashboard run aggregation, guards chart
rendering, and lightens live run update handling
> - The benefit is a more reliable dashboard during active agent
execution
## What Changed
- Added dashboard run activity types and backend aggregation coverage.
- Guarded activity chart rendering when run data is missing or partial.
- Reduced live transcript update churn in active agent and run chat
surfaces.
- Fixed issue chat avatar alignment in the thread renderer.
- Added focused dashboard, activity chart, and live transcript tests.
## Verification
- `pnpm install --frozen-lockfile --ignore-scripts`
- `pnpm exec vitest run server/src/__tests__/dashboard-service.test.ts
ui/src/components/ActivityCharts.test.tsx
ui/src/components/transcript/useLiveRunTranscripts.test.tsx`
- Result: 8 tests passed, 1 skipped. The embedded Postgres dashboard
service test skipped on this host with the existing PGlite/Postgres init
warning; UI chart and transcript tests passed.
## Risks
- Medium-low risk: aggregation semantics changed, but the UI remains
guarded around incomplete data.
- The dashboard service test is host-skipped here, so CI should confirm
the embedded database path.
> 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, tool-enabled local shell and
GitHub workflow, exact runtime context window not exposed in this
session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have 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, or documented why targeted component tests are sufficient
here
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 10:34:21 -05:00
|
|
|
stdoutExcerpt: null,
|
|
|
|
|
stderrExcerpt: null,
|
|
|
|
|
errorCode: null,
|
|
|
|
|
externalRunId: null,
|
|
|
|
|
processPid: null,
|
|
|
|
|
processGroupId: null,
|
|
|
|
|
processStartedAt: null,
|
|
|
|
|
retryOfRunId: null,
|
|
|
|
|
processLossRetryCount: 0,
|
[codex] Harden heartbeat scheduling and runtime controls (#4223)
## Thinking Path
> - Paperclip orchestrates AI agents through issue checkout, heartbeat
runs, routines, and auditable control-plane state
> - The runtime path has to recover from lost local processes, transient
adapter failures, blocked dependencies, and routine coalescing without
stranding work
> - The existing branch carried several reliability fixes across
heartbeat scheduling, issue runtime controls, routine dispatch, and
operator-facing run state
> - These changes belong together because they share backend contracts,
migrations, and runtime status semantics
> - This pull request groups the control-plane/runtime slice so it can
merge independently from board UI polish and adapter sandbox work
> - The benefit is safer heartbeat recovery, clearer runtime controls,
and more predictable recurring execution behavior
## What Changed
- Adds bounded heartbeat retry scheduling, scheduled retry state, and
Codex transient failure recovery handling.
- Tightens heartbeat process recovery, blocker wake behavior, issue
comment wake handling, routine dispatch coalescing, and
activity/dashboard bounds.
- Adds runtime-control MCP tools and Paperclip skill docs for issue
workspace runtime management.
- Adds migrations `0061_lively_thor_girl.sql` and
`0062_routine_run_dispatch_fingerprint.sql`.
- Surfaces retry state in run ledger/agent UI and keeps related shared
types synchronized.
## Verification
- `pnpm exec vitest run
server/src/__tests__/heartbeat-retry-scheduling.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/routines-service.test.ts`
- `pnpm exec vitest run src/tools.test.ts` from `packages/mcp-server`
## Risks
- Medium risk: this touches heartbeat recovery and routine dispatch,
which are central execution paths.
- Migration order matters if split branches land out of order: merge
this PR before branches that assume the new runtime/routine fields.
- Runtime retry behavior should be watched in CI and in local operator
smoke tests because it changes how transient failures are resumed.
> 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-based coding agent runtime, shell/git tool use
enabled. Exact hosted model build and context window are not exposed in
this Paperclip heartbeat environment.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
2026-04-21 12:24:11 -05:00
|
|
|
scheduledRetryAt: null,
|
|
|
|
|
scheduledRetryAttempt: 0,
|
|
|
|
|
scheduledRetryReason: null,
|
[codex] Harden dashboard run activity charts (#4126)
## Thinking Path
> - Paperclip gives operators a live view of agent work across
dashboards, transcripts, and run activity charts
> - Those views consume live run updates and aggregate run activity from
backend dashboard data
> - Missing or partial run data could make charts brittle, and live
transcript updates were heavier than needed
> - Operators need dashboard data to stay stable even when recent run
payloads are incomplete
> - This pull request hardens dashboard run aggregation, guards chart
rendering, and lightens live run update handling
> - The benefit is a more reliable dashboard during active agent
execution
## What Changed
- Added dashboard run activity types and backend aggregation coverage.
- Guarded activity chart rendering when run data is missing or partial.
- Reduced live transcript update churn in active agent and run chat
surfaces.
- Fixed issue chat avatar alignment in the thread renderer.
- Added focused dashboard, activity chart, and live transcript tests.
## Verification
- `pnpm install --frozen-lockfile --ignore-scripts`
- `pnpm exec vitest run server/src/__tests__/dashboard-service.test.ts
ui/src/components/ActivityCharts.test.tsx
ui/src/components/transcript/useLiveRunTranscripts.test.tsx`
- Result: 8 tests passed, 1 skipped. The embedded Postgres dashboard
service test skipped on this host with the existing PGlite/Postgres init
warning; UI chart and transcript tests passed.
## Risks
- Medium-low risk: aggregation semantics changed, but the UI remains
guarded around incomplete data.
- The dashboard service test is host-skipped here, so CI should confirm
the embedded database path.
> 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, tool-enabled local shell and
GitHub workflow, exact runtime context window not exposed in this
session.
## Checklist
- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have 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, or documented why targeted component tests are sufficient
here
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 10:34:21 -05:00
|
|
|
livenessState: null,
|
|
|
|
|
livenessReason: null,
|
|
|
|
|
continuationAttempt: 0,
|
|
|
|
|
lastUsefulActionAt: null,
|
|
|
|
|
nextAction: null,
|
|
|
|
|
contextSnapshot: null,
|
|
|
|
|
createdAt: new Date("2026-04-20T11:58:00.000Z"),
|
|
|
|
|
updatedAt: new Date("2026-04-20T11:59:00.000Z"),
|
|
|
|
|
...overrides,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
describe("ActivityCharts", () => {
|
|
|
|
|
it("renders empty run charts when dashboard aggregate data is temporarily missing", () => {
|
|
|
|
|
render(<RunActivityChart activity={undefined} />);
|
|
|
|
|
expect(container.textContent).toContain("No runs yet");
|
|
|
|
|
|
|
|
|
|
render(<SuccessRateChart activity={undefined} />);
|
|
|
|
|
expect(container.textContent).toContain("No runs yet");
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("still aggregates raw agent runs for detail charts", () => {
|
|
|
|
|
render(
|
|
|
|
|
<RunActivityChart
|
|
|
|
|
runs={[
|
|
|
|
|
createRun({ id: "run-success", status: "succeeded" }),
|
|
|
|
|
createRun({ id: "run-failed", status: "failed" }),
|
|
|
|
|
]}
|
|
|
|
|
/>,
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(container.textContent).not.toContain("No runs yet");
|
|
|
|
|
expect(container.querySelector("[title='2026-04-20: 2 runs']")).not.toBeNull();
|
|
|
|
|
});
|
|
|
|
|
});
|