fix(dispatch): let the answer to the agent's own question continue the task it blocked on (#20931)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - An agent can ask the person a question (`request_human_input`) and
wait for the answer
> - A later comment from the person moves an open question into history
(#15392). The agent still needs the answer, so it reports a blocker and
the task becomes Blocked
> - The person then answers. Dispatch cancels the answer's continuation
with `issue_not_in_progress`, because only a dependency-blocked task may
take an answer while Blocked
> - The task rests Blocked with a failed run and a Retry. The answer is
lost until a person clicks Retry
> - This pull request lets the answer continue the task when the same
agent blocked it to wait for that answer, proven from durable records
> - The benefit is that the person's answer always reaches the agent
that asked, without a Retry

## Linked Issues or Issue Description

Refs #15392, Refs #20872

**What happened?**
Restart-chaos waves with no fault injected fail every W2Q task on every
provider (Claude, OpenCode, Codex) with `R3:retry_needed`. For Claude
task t03 on master 7e8901aa60: run 5aeb9244 asks a question and the task
goes `in_review`. A board comment ("I will answer shortly; do not write
the brief yet") wakes run d728886f. That comment makes the question
historical, so `paperclip_finish` with a `response_wake` wait is
rejected ("without a pending wait condition"). The agent then calls
`paperclip_block`; the status decision `current_track_blocker_waiting`
sets the task Blocked. The board answers. Continuation run adbda5de is
cancelled: "resolved-interaction continuation issue is no longer
in_progress (current status: blocked)". The task rests blocked/failed
with Retry.

**What did you expect to happen?**
The answer continues the task. The agent writes the brief with the
answer and finishes.

**Steps to reproduce**
1. An agent asks a question on its task.
2. The person posts a comment before answering.
3. The agent reports a blocker while it waits for the answer.
4. The person answers the question.
5. The answer's continuation run is cancelled with
`issue_not_in_progress`.

## What Changed

- Status committer (`status-decision-committer.ts`): when it applies an
agent-reported, board-owned blocker (`current_track_blocker_waiting` or
`task_wide_blocker_bound`), it records the agent's own pending,
undismissed ordinary questions on the task as `awaitingInteractionIds`
in the decision JSON, in the same transaction under the issue lock
(`questionsAwaitedByAgentBlock`).
- New `agentBlockingQuestionState`
(`server/src/services/blocked-question-answer.ts`). It reads only
server-owned rows. It returns the verified `lastStatusDecisionId` and
`statusVersion` when: the answered interaction was created by this agent
on this task and resolved by a person; the task is Blocked and still
assigned to the agent; the task's `lastStatusDecisionId` is an applied
Blocked decision with one of the two reason codes, made by a run of the
same agent, whose `awaitingInteractionIds` contains this interaction;
and the task's `statusVersion` still equals that decision's
`projectedStatusVersion` (nothing changed the status since).
- `decideQueuedRunStaleness`
(`server/src/modules/run-dispatch/domain/policy.ts`): the Blocked
exemption for an answer continuation also accepts this fact
(`isAgentBlockingQuestionAnswer`). The postgres adapter loads it under
the issue lock.
- `heartbeat.ts` resolved-interaction checkout: for that answer,
`blocked` is an accepted expected status, and the verified state is
passed to `issues.checkout` as `blockedState`.
- `issues.checkout`: with `blockedState`, the guarded update accepts a
Blocked row only when `lastStatusDecisionId` and `statusVersion` still
match, so a person who re-blocks the task in between keeps the new
block. When the expected statuses include `blocked`, a checkout from
Blocked also clears `unblockDescriptor`, `blockedTransitionAt` and
`blockedOwnerNotifiedAt`, as an ordinary status change from Blocked
does.
- `doc/execution-semantics.md` describes the rule.

## Verification

- New integration test
`server/src/__tests__/heartbeat-blocked-question-answer.test.ts`
(embedded Postgres, real `commitNativeStatusDecision`): the agent's
blocker decision makes the task Blocked, the person answers, the answer
is delivered through `heartbeat.wakeup` with the same context shape as
staging.
- Red on master (product hunks removed, test kept): `delivers the answer
when the agent blocked the task to wait for it` fails with `status:
cancelled, errorCode: issue_not_in_progress`, the same code as the chaos
run.
- Green: 5/5 pass. The answer run succeeds, the adapter runs, and the
blocker fields are cleared. Negative cases still cancel with
`issue_not_in_progress`: a person re-blocked the task after the agent,
the question did not exist when the agent blocked, and the task is done.
A checkout with a stale verified state conflicts and keeps the person's
new blocker.
- `policy.test.ts`: new case for the fact (continue when set, cancel
when unset, reassignment, backlog/done/cancelled).
- `cd server && pnpm exec vitest run src/modules/run-dispatch
src/__tests__/heartbeat-dependency-scheduling.test.ts`: 208 passed.
- `cd server && pnpm exec vitest run
src/__tests__/issues-service.test.ts
src/__tests__/heartbeat-stale-queue-invalidation.test.ts
src/services/explicit-native-continuation.test.ts`: 656 passed.
- `cd server && pnpm exec tsc --noEmit -p tsconfig.json`: passes.
- Chaos, local, seed 5101, `--workloads W2Q --faults K0 --adapters
codex,claude --lifecycle warm`, on 722303e4a2 (first head): wave
w-20261111T204405-s5101, 6/6 PASS (3 Codex, 3 Claude). Every task went
in_review -> blocked -> in_progress -> done without Retry. Before: the
same local seed on master (w-20261111T190352-s5101) failed 3/3 Codex W2Q
cells with `R3:retry_needed`, and Daytona Claude wave
w-20261111T200553-s6101 failed 2/3 W2Q cells the same way.

## Risks

- Low to medium. Only a resolved interaction continuation on a Blocked
task changes behavior, and only when the durable linkage holds. If a
board-owned blocker about something else and the agent's own question
are open together, the answer resumes the agent; it then reports its
blocker again. The blocker report carries no interaction reference, so
the server cannot tell them apart; cancelling the answer instead loses
it. A person's Blocked status, a block from before the question,
dependency blocks, reassignment, done and cancelled keep the old cancel.
- State saved by an older release: no schema change and no migration. A
Blocked decision saved before this change has no
`awaitingInteractionIds`, so its answer keeps the old behavior (cancel,
Retry works).
- The checkout change only applies when a caller passes `blocked` as an
expected status.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`), with tool use and code execution
in an agent harness.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
DottaandClaude Opus 5.5 authored and GitHub committed 2026-11-11 15:54:33 -06:00
1 parent b01959cb15
commit 228b0169be
9 files changed
+327 -2

No files matched your search

@@ -0,0 +1,197 @@
import { randomUUID } from "node:crypto";
import { eq } from "drizzle-orm";
import { afterAll, beforeAll, describe, expect, it, vi } from "vitest";
import {
agents,
authUsers,
companies,
companyMemberships,
completionContracts,
createDb,
heartbeatRuns,
issueThreadInteractions,
issues,
nativeRunFinalizations,
nativeRunResults,
statusDecisions,
workAssessments,
} from "@paperclipai/db";
import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "./helpers/embedded-postgres.js";
import { heartbeatService } from "../services/heartbeat.ts";
import { issueService } from "../services/issues.ts";
import { commitNativeStatusDecision } from "../services/native-runtime/status-decision-committer.js";
import { NATIVE_STATUS_ARBITER_POLICY_VERSION } from "../services/native-runtime/status-arbiter.js";
const mockAdapterExecute = vi.hoisted(() => vi.fn(async () => ({
exitCode: 0, signal: null, timedOut: false, errorMessage: null,
summary: "Wrote the brief with the answer.", provider: "test", model: "test-model",
})));
vi.mock("../adapters/index.ts", async () => {
const actual = await vi.importActual<typeof import("../adapters/index.ts")>("../adapters/index.ts");
return { ...actual, getServerAdapter: vi.fn(() => ({ supportsLocalAgentJwt: false, execute: mockAdapterExecute })) };
});
const support = await getEmbeddedPostgresTestSupport();
const describeEmbeddedPostgres = support.supported ? describe : describe.skip;
describeEmbeddedPostgres("an answer to the agent's own question continues the task it blocked on", () => {
let db!: ReturnType<typeof createDb>;
let heartbeat!: ReturnType<typeof heartbeatService>;
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
const userId = "blocked-question-user";
beforeAll(async () => {
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-blocked-question-answer-");
db = createDb(tempDb.connectionString);
await db.insert(authUsers).values({ id: userId, name: "Board", email: "board@example.test",
createdAt: new Date(), updatedAt: new Date() });
heartbeat = heartbeatService(db);
}, 30_000);
afterAll(async () => {
await heartbeat?.drainActiveRunExecutions();
await db?.$client.end();
await tempDb?.cleanup();
});
async function seed(options: { askAfterBlock?: boolean } = {}) {
const companyId = randomUUID(), agentId = randomUUID(), issueId = randomUUID();
await db.insert(companies).values({ id: companyId, name: "Question fixture",
issuePrefix: `Q${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
requireBoardApprovalForNewAgents: false, defaultResponsibleUserId: userId });
await db.insert(companyMemberships).values({ companyId, principalType: "user", principalId: userId,
status: "active", membershipRole: "owner" });
await db.insert(agents).values({ id: agentId, companyId, name: "Writer", role: "engineer", status: "active",
adapterType: "codex_local", adapterConfig: {}, permissions: {},
runtimeConfig: { heartbeat: { wakeOnDemand: true, maxConcurrentRuns: 1 } } });
await db.insert(issues).values({ id: issueId, companyId, title: "Write the brief", status: "in_review",
assigneeAgentId: agentId, responsibleUserId: userId });
if (options.askAfterBlock) await agentReportsBlocker({ companyId, agentId, issueId });
const askingRunId = randomUUID();
await db.insert(heartbeatRuns).values({ id: askingRunId, companyId, agentId, status: "succeeded",
runtimeMode: "native", nativeIssueId: issueId, invocationSource: "assignment", triggerDetail: "system",
contextSnapshot: { issueId }, finishedAt: new Date() });
const [question] = await db.insert(issueThreadInteractions).values({ companyId, issueId,
createdByAgentId: agentId, sourceRunId: askingRunId, kind: "ask_user_questions", status: "pending",
continuationPolicy: "wake_assignee", title: "Pick a codename",
payload: { version: 1, questions: [{ id: "codename", prompt: "Which codename?", selectionMode: "single",
options: [{ id: "alpha", label: "ALPHA" }, { id: "bravo", label: "BRAVO" }] }] },
}).returning();
return { companyId, agentId, issueId, question: question! };
}
async function agentReportsBlocker(input: { companyId: string; agentId: string; issueId: string }): Promise<void> {
const runId = randomUUID(), contractId = randomUUID(), resultId = randomUUID(), assessmentId = randomUUID();
await db.insert(completionContracts).values({ id: contractId, companyId: input.companyId, issueId: input.issueId,
revision: 1, schemaVersion: "paperclip.completion-contract.v1", policyVersion: "test", risk: "standard",
completionAuthority: "server_arbiter", incompleteCriteriaPolicy: "preserve_non_terminal",
contractJson: {}, canonicalSha256: contractId, createdByActorType: "system", createdByActorId: "test" });
await db.insert(heartbeatRuns).values({ id: runId, companyId: input.companyId, agentId: input.agentId,
status: "running", runtimeMode: "native", nativeIssueId: input.issueId, invocationSource: "automation",
triggerDetail: "system", completionContractId: contractId, contextSnapshot: { issueId: input.issueId } });
await db.insert(nativeRunResults).values({ id: resultId, companyId: input.companyId, issueId: input.issueId,
runId, completionContractId: contractId, serverFingerprint: resultId, schemaStatus: "accepted",
resultJson: {}, canonicalSha256: resultId });
const [snapshot] = await db.select().from(issues).where(eq(issues.id, input.issueId));
await db.insert(workAssessments).values({ id: assessmentId, companyId: input.companyId, issueId: input.issueId,
runId, contractId, resultId, triggerKind: "native_result", triggerActorCompanyId: input.companyId,
priorIssueStatus: snapshot!.status, priorStatusVersion: snapshot!.statusVersion,
policyVersion: NATIVE_STATUS_ARBITER_POLICY_VERSION, assessmentJson: {}, inputDigest: assessmentId });
await db.insert(nativeRunFinalizations).values({ runId, companyId: input.companyId, issueId: input.issueId,
phase: "arbitrating", resultId, assessmentId });
await commitNativeStatusDecision({
db, companyId: input.companyId, issueId: input.issueId, runId, assessmentId,
priorStatus: snapshot!.status, priorStatusVersion: Number(snapshot!.statusVersion),
priorDecisionId: snapshot!.lastStatusDecisionId,
decision: { policyVersion: NATIVE_STATUS_ARBITER_POLICY_VERSION, statusAction: "blocked", toStatus: "blocked",
reasonCode: "current_track_blocker_waiting",
unblockDescriptor: { owner: "board", action: "Answer the pending codename question." },
effects: [{ kind: "release_checkout" }] },
});
await db.update(heartbeatRuns).set({ status: "succeeded", finishedAt: new Date() }).where(eq(heartbeatRuns.id, runId));
}
async function answer(question: typeof issueThreadInteractions.$inferSelect) {
await db.update(issueThreadInteractions).set({ status: "answered", resolvedByUserId: userId, resolvedAt: new Date(),
result: { version: 1, answers: [{ questionId: "codename", optionIds: ["bravo"] }] } })
.where(eq(issueThreadInteractions.id, question.id));
}
async function deliverAnswer(input: { agentId: string; issueId: string; questionId: string }) {
const context = { issueId: input.issueId, mutation: "interaction", interactionId: input.questionId,
interactionKind: "ask_user_questions", interactionStatus: "answered",
interactionResolvedAt: new Date().toISOString(), wakeReason: "issue_commented" };
const run = await heartbeat.wakeup(input.agentId, { source: "automation", triggerDetail: "system",
reason: "issue_commented", payload: context, contextSnapshot: context,
requestedByActorType: "user", requestedByActorId: userId });
await heartbeat.drainActiveRunExecutions();
return run ? (await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, run.id)))[0]! : null;
}
it("delivers the answer when the agent blocked the task to wait for it", async () => {
mockAdapterExecute.mockClear();
const { agentId, issueId, question, companyId } = await seed();
await agentReportsBlocker({ companyId, agentId, issueId });
const [blocked] = await db.select().from(issues).where(eq(issues.id, issueId));
expect(blocked!.status).toBe("blocked");
const [decision] = await db.select().from(statusDecisions).where(eq(statusDecisions.id, blocked!.lastStatusDecisionId!));
expect(decision!.decisionJson).toMatchObject({ awaitingInteractionIds: [question.id] });
await answer(question);
const run = await deliverAnswer({ agentId, issueId, questionId: question.id });
expect({ status: run?.status, errorCode: run?.errorCode ?? null, error: run?.error ?? null })
.toEqual({ status: "succeeded", errorCode: null, error: null });
expect(run?.startedAt).not.toBeNull();
expect(run?.contextSnapshot).toMatchObject({ interactionId: question.id, interactionStatus: "answered" });
expect(mockAdapterExecute).toHaveBeenCalled();
const [issue] = await db.select().from(issues).where(eq(issues.id, issueId));
expect(issue).toMatchObject({ blockedTransitionAt: null, unblockDescriptor: null });
}, 60_000);
it("keeps cancelling the answer when a person blocked the task after the agent", async () => {
mockAdapterExecute.mockClear();
const { agentId, issueId, question, companyId } = await seed();
await agentReportsBlocker({ companyId, agentId, issueId });
await db.update(issues).set({ status: "in_review" }).where(eq(issues.id, issueId));
await db.update(issues).set({ status: "blocked", blockedTransitionAt: new Date() }).where(eq(issues.id, issueId));
await answer(question);
const run = await deliverAnswer({ agentId, issueId, questionId: question.id });
expect(run).toMatchObject({ status: "cancelled", errorCode: "issue_not_in_progress" });
expect(mockAdapterExecute).not.toHaveBeenCalled();
}, 60_000);
it("keeps cancelling the answer when the question did not exist when the agent blocked", async () => {
mockAdapterExecute.mockClear();
const { agentId, issueId, question } = await seed({ askAfterBlock: true });
await answer(question);
const run = await deliverAnswer({ agentId, issueId, questionId: question.id });
expect(run).toMatchObject({ status: "cancelled", errorCode: "issue_not_in_progress" });
expect(mockAdapterExecute).not.toHaveBeenCalled();
}, 60_000);
it("keeps cancelling the answer once the task is done", async () => {
mockAdapterExecute.mockClear();
const { agentId, issueId, question, companyId } = await seed();
await agentReportsBlocker({ companyId, agentId, issueId });
await db.update(issues).set({ status: "done" }).where(eq(issues.id, issueId));
await answer(question);
const run = await deliverAnswer({ agentId, issueId, questionId: question.id });
if (run) expect(run).toMatchObject({ status: "cancelled" });
expect(mockAdapterExecute).not.toHaveBeenCalled();
}, 60_000);
it("does not check out a task whose verified block changed before checkout", async () => {
const { agentId, issueId, question, companyId } = await seed();
await agentReportsBlocker({ companyId, agentId, issueId });
await answer(question);
const [verified] = await db.select().from(issues).where(eq(issues.id, issueId));
const blockedState = { lastStatusDecisionId: verified!.lastStatusDecisionId!, statusVersion: Number(verified!.statusVersion) };
await db.update(issues).set({ status: "in_review" }).where(eq(issues.id, issueId));
await db.update(issues).set({ status: "blocked", unblockDescriptor: { owner: "board", action: "Person's new blocker" } })
.where(eq(issues.id, issueId));
await expect(issueService(db).checkout(issueId, agentId, ["in_progress", "in_review", "blocked"], null, { blockedState }))
.rejects.toThrow();
expect((await db.select().from(issues).where(eq(issues.id, issueId)))[0])
.toMatchObject({ status: "blocked", unblockDescriptor: { owner: "board", action: "Person's new blocker" } });
}, 60_000);
});