mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-18 11:40:39 +09:00
[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
This commit is contained in:
Dotta
GitHub
parent
ab9051b595
commit
09d0678840
61 changed files with 17622 additions and 456 deletions
|
|
@ -7,6 +7,7 @@ const mockIssueService = vi.hoisted(() => ({
|
|||
assertCheckoutOwner: vi.fn(),
|
||||
update: vi.fn(),
|
||||
addComment: vi.fn(),
|
||||
getDependencyReadiness: vi.fn(),
|
||||
findMentionedAgents: vi.fn(),
|
||||
listWakeableBlockedDependents: vi.fn(),
|
||||
getWakeableParentAfterChildCompletion: vi.fn(),
|
||||
|
|
@ -199,6 +200,7 @@ describe("issue comment reopen routes", () => {
|
|||
mockIssueService.assertCheckoutOwner.mockReset();
|
||||
mockIssueService.update.mockReset();
|
||||
mockIssueService.addComment.mockReset();
|
||||
mockIssueService.getDependencyReadiness.mockReset();
|
||||
mockIssueService.findMentionedAgents.mockReset();
|
||||
mockIssueService.listWakeableBlockedDependents.mockReset();
|
||||
mockIssueService.getWakeableParentAfterChildCompletion.mockReset();
|
||||
|
|
@ -255,6 +257,14 @@ describe("issue comment reopen routes", () => {
|
|||
authorUserId: "local-board",
|
||||
});
|
||||
mockIssueService.findMentionedAgents.mockResolvedValue([]);
|
||||
mockIssueService.getDependencyReadiness.mockResolvedValue({
|
||||
issueId: "11111111-1111-4111-8111-111111111111",
|
||||
blockerIssueIds: [],
|
||||
unresolvedBlockerIssueIds: [],
|
||||
unresolvedBlockerCount: 0,
|
||||
allBlockersDone: true,
|
||||
isDependencyReady: true,
|
||||
});
|
||||
mockIssueService.listWakeableBlockedDependents.mockResolvedValue([]);
|
||||
mockIssueService.getWakeableParentAfterChildCompletion.mockResolvedValue(null);
|
||||
mockIssueService.assertCheckoutOwner.mockResolvedValue({ adoptedFromRunId: null });
|
||||
|
|
@ -442,6 +452,75 @@ describe("issue comment reopen routes", () => {
|
|||
);
|
||||
});
|
||||
|
||||
it("moves assigned blocked issues back to todo via POST comments", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("blocked"));
|
||||
mockIssueService.update.mockImplementation(async (_id: string, patch: Record<string, unknown>) => ({
|
||||
...makeIssue("blocked"),
|
||||
...patch,
|
||||
}));
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.post("/api/issues/11111111-1111-4111-8111-111111111111/comments")
|
||||
.send({ body: "please continue" });
|
||||
|
||||
expect(res.status).toBe(201);
|
||||
expect(mockIssueService.update).toHaveBeenCalledWith(
|
||||
"11111111-1111-4111-8111-111111111111",
|
||||
{ status: "todo" },
|
||||
);
|
||||
expect(mockHeartbeatService.wakeup).toHaveBeenCalledWith(
|
||||
"22222222-2222-4222-8222-222222222222",
|
||||
expect.objectContaining({
|
||||
reason: "issue_reopened_via_comment",
|
||||
payload: expect.objectContaining({
|
||||
commentId: "comment-1",
|
||||
reopenedFrom: "blocked",
|
||||
mutation: "comment",
|
||||
}),
|
||||
contextSnapshot: expect.objectContaining({
|
||||
issueId: "11111111-1111-4111-8111-111111111111",
|
||||
wakeCommentId: "comment-1",
|
||||
wakeReason: "issue_reopened_via_comment",
|
||||
reopenedFrom: "blocked",
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it("does not move dependency-blocked issues to todo via POST comments", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("blocked"));
|
||||
mockIssueService.getDependencyReadiness.mockResolvedValue({
|
||||
issueId: "11111111-1111-4111-8111-111111111111",
|
||||
blockerIssueIds: ["33333333-3333-4333-8333-333333333333"],
|
||||
unresolvedBlockerIssueIds: ["33333333-3333-4333-8333-333333333333"],
|
||||
unresolvedBlockerCount: 1,
|
||||
allBlockersDone: false,
|
||||
isDependencyReady: false,
|
||||
});
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.post("/api/issues/11111111-1111-4111-8111-111111111111/comments")
|
||||
.send({ body: "what is happening?" });
|
||||
|
||||
expect(res.status).toBe(201);
|
||||
expect(mockIssueService.update).not.toHaveBeenCalled();
|
||||
expect(mockHeartbeatService.wakeup).toHaveBeenCalledWith(
|
||||
"22222222-2222-4222-8222-222222222222",
|
||||
expect.objectContaining({
|
||||
reason: "issue_commented",
|
||||
payload: expect.objectContaining({
|
||||
commentId: "comment-1",
|
||||
mutation: "comment",
|
||||
}),
|
||||
contextSnapshot: expect.objectContaining({
|
||||
issueId: "11111111-1111-4111-8111-111111111111",
|
||||
wakeCommentId: "comment-1",
|
||||
wakeReason: "issue_commented",
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it("does not implicitly reopen closed issues via POST comments when no agent is assigned", async () => {
|
||||
mockIssueService.getById.mockResolvedValue({
|
||||
...makeIssue("done"),
|
||||
|
|
@ -457,6 +536,82 @@ describe("issue comment reopen routes", () => {
|
|||
expect(mockIssueService.update).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("moves assigned blocked issues back to todo via the PATCH comment path", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("blocked"));
|
||||
mockIssueService.update.mockImplementation(async (_id: string, patch: Record<string, unknown>) => ({
|
||||
...makeIssue("blocked"),
|
||||
...patch,
|
||||
}));
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.patch("/api/issues/11111111-1111-4111-8111-111111111111")
|
||||
.send({ comment: "please continue" });
|
||||
|
||||
expect(res.status).toBe(200);
|
||||
expect(mockIssueService.update).toHaveBeenCalledWith(
|
||||
"11111111-1111-4111-8111-111111111111",
|
||||
expect.objectContaining({
|
||||
status: "todo",
|
||||
actorAgentId: null,
|
||||
actorUserId: "local-board",
|
||||
}),
|
||||
);
|
||||
expect(mockHeartbeatService.wakeup).toHaveBeenCalledWith(
|
||||
"22222222-2222-4222-8222-222222222222",
|
||||
expect.objectContaining({
|
||||
reason: "issue_reopened_via_comment",
|
||||
payload: expect.objectContaining({
|
||||
commentId: "comment-1",
|
||||
reopenedFrom: "blocked",
|
||||
mutation: "comment",
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it("does not move dependency-blocked issues to todo via the PATCH comment path", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("blocked"));
|
||||
mockIssueService.getDependencyReadiness.mockResolvedValue({
|
||||
issueId: "11111111-1111-4111-8111-111111111111",
|
||||
blockerIssueIds: ["33333333-3333-4333-8333-333333333333"],
|
||||
unresolvedBlockerIssueIds: ["33333333-3333-4333-8333-333333333333"],
|
||||
unresolvedBlockerCount: 1,
|
||||
allBlockersDone: false,
|
||||
isDependencyReady: false,
|
||||
});
|
||||
mockIssueService.update.mockImplementation(async (_id: string, patch: Record<string, unknown>) => ({
|
||||
...makeIssue("blocked"),
|
||||
...patch,
|
||||
}));
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.patch("/api/issues/11111111-1111-4111-8111-111111111111")
|
||||
.send({ comment: "what is happening?" });
|
||||
|
||||
expect(res.status).toBe(200);
|
||||
expect(mockIssueService.update).toHaveBeenCalledWith(
|
||||
"11111111-1111-4111-8111-111111111111",
|
||||
expect.objectContaining({
|
||||
actorAgentId: null,
|
||||
actorUserId: "local-board",
|
||||
}),
|
||||
);
|
||||
expect(mockIssueService.update).not.toHaveBeenCalledWith(
|
||||
"11111111-1111-4111-8111-111111111111",
|
||||
expect.objectContaining({ status: "todo" }),
|
||||
);
|
||||
expect(mockHeartbeatService.wakeup).toHaveBeenCalledWith(
|
||||
"22222222-2222-4222-8222-222222222222",
|
||||
expect.objectContaining({
|
||||
reason: "issue_commented",
|
||||
payload: expect.objectContaining({
|
||||
commentId: "comment-1",
|
||||
mutation: "comment",
|
||||
}),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it("wakes the assignee when an assigned blocked issue moves back to todo", async () => {
|
||||
const issue = makeIssue("blocked");
|
||||
mockIssueService.getById.mockResolvedValue(issue);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue