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 +1,68 @@
import { and, eq, inArray, isNotNull, isNull, sql } from "drizzle-orm";
import { heartbeatRuns, issueThreadInteractions, issues, statusDecisions, type Db } from "@paperclipai/db";
import { queuedInteractionId } from "./queued-interaction-response.js";
import { ordinaryQuestionCondition } from "./issue-question-context.js";
const AGENT_REPORTED_BLOCKER_REASON_CODES = ["current_track_blocker_waiting", "task_wide_blocker_bound"];
export type AgentBlockingQuestionState = { lastStatusDecisionId: string; statusVersion: number };
export async function questionsAwaitedByAgentBlock(db: Pick<Db, "select">, input: {
companyId: string; issueId: string; agentId: string | null | undefined; reasonCode: string | null;
toStatus: string; unblockOwner: unknown;
}): Promise<string[]> {
if (!input.agentId || input.toStatus !== "blocked" || input.unblockOwner !== "board"
|| !AGENT_REPORTED_BLOCKER_REASON_CODES.includes(input.reasonCode ?? "")) return [];
const rows = await db.select({ id: issueThreadInteractions.id }).from(issueThreadInteractions).where(and(
eq(issueThreadInteractions.companyId, input.companyId),
eq(issueThreadInteractions.issueId, input.issueId),
eq(issueThreadInteractions.createdByAgentId, input.agentId),
eq(issueThreadInteractions.status, "pending"),
isNull(issueThreadInteractions.dismissedAt),
ordinaryQuestionCondition(),
));
return rows.map((row) => row.id).sort();
}
export async function agentBlockingQuestionState(db: Pick<Db, "select">, input: {
companyId: string; issueId: string; agentId: string; context: unknown;
}): Promise<AgentBlockingQuestionState | null> {
const interactionId = queuedInteractionId(input.context);
if (!interactionId) return null;
const interactionStatus = (input.context as Record<string, unknown>).interactionStatus;
const [row] = await db
.select({ lastStatusDecisionId: statusDecisions.id, statusVersion: issues.statusVersion })
.from(issueThreadInteractions)
.innerJoin(issues, and(
eq(issues.id, issueThreadInteractions.issueId),
eq(issues.companyId, issueThreadInteractions.companyId),
))
.innerJoin(statusDecisions, and(
eq(statusDecisions.id, issues.lastStatusDecisionId),
eq(statusDecisions.companyId, issues.companyId),
eq(statusDecisions.issueId, issues.id),
))
.innerJoin(heartbeatRuns, and(
eq(heartbeatRuns.id, statusDecisions.runId),
eq(heartbeatRuns.companyId, statusDecisions.companyId),
))
.where(and(
eq(issueThreadInteractions.id, interactionId),
eq(issueThreadInteractions.companyId, input.companyId),
eq(issueThreadInteractions.issueId, input.issueId),
eq(issueThreadInteractions.createdByAgentId, input.agentId),
eq(issueThreadInteractions.status, String(interactionStatus)),
isNotNull(issueThreadInteractions.resolvedByUserId),
isNotNull(issueThreadInteractions.resolvedAt),
eq(issues.status, "blocked"),
eq(issues.assigneeAgentId, input.agentId),
eq(statusDecisions.applicationState, "applied"),
eq(statusDecisions.toStatus, "blocked"),
inArray(statusDecisions.reasonCode, AGENT_REPORTED_BLOCKER_REASON_CODES),
sql`coalesce(${statusDecisions.decisionJson}->'awaitingInteractionIds', '[]'::jsonb) ? ${interactionId}`,
sql`${statusDecisions.decisionJson}->>'projectedStatusVersion' = ${issues.statusVersion}::text`,
eq(heartbeatRuns.agentId, input.agentId),
))
.limit(1);
return row ? { lastStatusDecisionId: row.lastStatusDecisionId, statusVersion: Number(row.statusVersion) } : null;
}
+7 -1
View File
@@ -7,6 +7,7 @@ import { isProcessRunAdmissionClosed } from "./heartbeat/run-admission.js";
import type { StopInvocationOptions } from "./heartbeat/run-control.js";
import { isContextCompactionRun } from "./context-compaction.js";
import { isUnstartedTaskQuestionAnswer } from "./unstarted-task-question-answer.js";
import { agentBlockingQuestionState } from "./blocked-question-answer.js";
import { isVerifiedDependencyInteractionResponse } from "./queued-interaction-response.js";
import { registerDeferredReceiptWork } from "./heartbeat/deferred-receipt-work.js";
import { registerProviderLimitResumeWork, type PrepareChatRetry } from "./native-runtime/provider-limit-resume.js";
@@ -2304,11 +2305,16 @@ export function heartbeatService(
await timePreparation("issue_checkout", async () => {
const startsUnstartedTask = issueStatus === "todo" &&
await isUnstartedTaskQuestionAnswer(db, { companyId: agent.companyId, issueId, interactionId: context.interactionId });
const blockedState = issueStatus === "blocked"
? await agentBlockingQuestionState(db, { companyId: agent.companyId, issueId, agentId: agent.id, context })
: null;
await issuesSvc.checkout(
issueId,
agent.id,
[...resolvedInteractionCheckoutExpectedStatuses(), ...(startsUnstartedTask ? ["todo"] : [])],
[...resolvedInteractionCheckoutExpectedStatuses(), ...(startsUnstartedTask ? ["todo"] : []),
...(blockedState ? ["blocked"] : [])],
run.id,
blockedState ? { blockedState } : undefined,
);
});
context[PAPERCLIP_HARNESS_CHECKOUT_KEY] = true;
+11
View File
@@ -12550,6 +12550,7 @@ export function issueService(db: Db) {
agentId: string,
expectedStatuses: string[],
checkoutRunId: string | null,
options: { blockedState?: { lastStatusDecisionId: string; statusVersion: number } } = {},
) => {
const issueCompany = await db
.select({ companyId: issues.companyId })
@@ -12651,11 +12652,21 @@ export function issueService(db: Db) {
status: "in_progress",
startedAt: now,
updatedAt: now,
...(expectedStatuses.includes("blocked") ? {
unblockDescriptor: sql`case when ${issues.status} = 'blocked' then null else ${issues.unblockDescriptor} end`,
blockedTransitionAt: sql`case when ${issues.status} = 'blocked' then null else ${issues.blockedTransitionAt} end`,
blockedOwnerNotifiedAt: sql`case when ${issues.status} = 'blocked' then null else ${issues.blockedOwnerNotifiedAt} end`,
} : {}),
})
.where(
and(
eq(issues.id, id),
inArray(issues.status, expectedStatuses),
options.blockedState ? or(
ne(issues.status, "blocked"),
and(eq(issues.lastStatusDecisionId, options.blockedState.lastStatusDecisionId),
eq(issues.statusVersion, options.blockedState.statusVersion)),
) : undefined,
or(isNull(issues.assigneeAgentId), sameRunAssigneeCondition),
executionLockCondition,
),
@@ -26,6 +26,7 @@ import { normalizePrpResultSignals, type PrpStructuredRunResult } from "../../ve
import { readNativeMonitorDelivery, readNativePreservedMonitorWait, readNativeSupersededMonitorWait, type NativeSupersededMonitorWait, type NativeMonitorDelivery, type NativePreservedMonitorWait } from "./native-monitor-delivery.js";
import { readNativePlanWait, type NativePlanWaitSource } from "./native-plan-wait.js";
import { activeIssueInteractionCondition } from "../issue-question-context.js";
import { questionsAwaitedByAgentBlock } from "../blocked-question-answer.js";
import { isConversation } from "../agent-conversations.js";
import { hasPendingNativeChildCompletion, type NativeChildCompletionRecipient } from "./native-child-completion-delivery.js";
import { and, asc, desc, eq, inArray, notInArray, or, sql } from "drizzle-orm";
@@ -2159,12 +2160,17 @@ export async function commitNativeStatusDecision(input: {
})
.where(eq(nativeRunFinalizations.runId, input.runId));
};
const awaitingInteractionIds = await questionsAwaitedByAgentBlock(tx as unknown as Db, {
companyId: input.companyId, issueId: input.issueId, agentId: originRun?.agentId, reasonCode,
toStatus: input.decision.toStatus, unblockOwner: input.decision.unblockDescriptor?.owner,
});
const decisionJson = {
statusAction: input.decision.statusAction,
toStatus: input.decision.toStatus,
reasonCode,
unblockDescriptor: input.decision.unblockDescriptor,
effects: input.decision.effects,
...(awaitingInteractionIds.length ? { awaitingInteractionIds } : {}),
...(externalChatReviewPresentation
? { externalChatReviewPresentation }
: {}),