forked from farhoodlabs/paperclip
454edfe81e
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Agent runs can end productively while the source issue still lacks a durable final disposition. > - That leaves the control plane unsure whether to resume, escalate, or close the work. > - Issue comments also need a presentation contract so system-authored recovery notices can render as first-class thread messages without overloading normal comments. > - This pull request adds successful-run handoff recovery, comment presentation metadata, and system notice rendering. > - The benefit is stricter task liveness with clearer operator-facing recovery state. ## What Changed - Added successful-run handoff decisions, wake payloads, escalation behavior, and recovery tests. - Added issue comment presentation metadata with migration `0078_white_darwin.sql` and shared/server/company portability support. - Rendered recovery/system notices in issue chat with dedicated UI components, fixtures, tests, and storybook/lab coverage. - Included the current recovery model-profile hint patch so automatic recovery follow-ups use the cheap profile. ## Verification - `pnpm install --frozen-lockfile` - `pnpm exec vitest run server/src/services/recovery/successful-run-handoff.test.ts ui/src/components/SystemNotice.test.tsx ui/src/lib/system-notice-comment.test.ts ui/src/components/IssueChatThreadSystemNotice.test.tsx` ## Risks - Migration-bearing PR: merge this before any other branch that might later add a migration. - The branch touches both recovery services and issue-thread rendering, so review should pay attention to recovery wake idempotency and comment metadata compatibility. ## Model Used - OpenAI GPT-5 Codex via Paperclip `codex_local` adapter, with shell/git/GitHub CLI tool use. ## 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
174 lines
5.3 KiB
TypeScript
174 lines
5.3 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import {
|
|
DEFAULT_MAX_LIVENESS_CONTINUATION_ATTEMPTS,
|
|
RUN_LIVENESS_CONTINUATION_REASON,
|
|
buildRunLivenessContinuationIdempotencyKey,
|
|
decideRunLivenessContinuation,
|
|
} from "../services/run-continuations.ts";
|
|
|
|
const companyId = "company-1";
|
|
const agentId = "agent-1";
|
|
const issueId = "issue-1";
|
|
const runId = "run-1";
|
|
|
|
function run(overrides: Record<string, unknown> = {}) {
|
|
return {
|
|
id: runId,
|
|
companyId,
|
|
agentId,
|
|
continuationAttempt: 0,
|
|
...overrides,
|
|
} as never;
|
|
}
|
|
|
|
function issue(overrides: Record<string, unknown> = {}) {
|
|
return {
|
|
id: issueId,
|
|
companyId,
|
|
identifier: "PAP-1577",
|
|
title: "Add bounded liveness continuation wakes",
|
|
status: "in_progress",
|
|
assigneeAgentId: agentId,
|
|
executionState: null,
|
|
projectId: null,
|
|
...overrides,
|
|
} as never;
|
|
}
|
|
|
|
function agent(overrides: Record<string, unknown> = {}) {
|
|
return {
|
|
id: agentId,
|
|
companyId,
|
|
status: "idle",
|
|
...overrides,
|
|
} as never;
|
|
}
|
|
|
|
describe("run liveness continuations", () => {
|
|
it("enqueues the first plan_only continuation for the same issue and assignee", () => {
|
|
const decision = decideRunLivenessContinuation({
|
|
run: run(),
|
|
issue: issue(),
|
|
agent: agent(),
|
|
livenessState: "plan_only",
|
|
livenessReason: "Planned without acting",
|
|
nextAction: "Take the first concrete action now.",
|
|
budgetBlocked: false,
|
|
idempotentWakeExists: false,
|
|
});
|
|
|
|
expect(decision.kind).toBe("enqueue");
|
|
if (decision.kind !== "enqueue") return;
|
|
expect(decision.nextAttempt).toBe(1);
|
|
expect(decision.idempotencyKey).toBe(
|
|
buildRunLivenessContinuationIdempotencyKey({
|
|
issueId,
|
|
sourceRunId: runId,
|
|
livenessState: "plan_only",
|
|
nextAttempt: 1,
|
|
}),
|
|
);
|
|
expect(decision.payload).toMatchObject({
|
|
issueId,
|
|
sourceRunId: runId,
|
|
livenessState: "plan_only",
|
|
livenessReason: "Planned without acting",
|
|
continuationAttempt: 1,
|
|
maxContinuationAttempts: DEFAULT_MAX_LIVENESS_CONTINUATION_ATTEMPTS,
|
|
instruction: "Take the first concrete action now.",
|
|
modelProfile: "cheap",
|
|
});
|
|
expect(decision.contextSnapshot).toMatchObject({
|
|
issueId,
|
|
wakeReason: RUN_LIVENESS_CONTINUATION_REASON,
|
|
modelProfile: "cheap",
|
|
livenessContinuationAttempt: 1,
|
|
livenessContinuationMaxAttempts: DEFAULT_MAX_LIVENESS_CONTINUATION_ATTEMPTS,
|
|
livenessContinuationSourceRunId: runId,
|
|
livenessContinuationState: "plan_only",
|
|
livenessContinuationReason: "Planned without acting",
|
|
livenessContinuationInstruction: "Take the first concrete action now.",
|
|
});
|
|
});
|
|
|
|
it("enqueues the second empty_response continuation", () => {
|
|
const decision = decideRunLivenessContinuation({
|
|
run: run({ continuationAttempt: 1 }),
|
|
issue: issue(),
|
|
agent: agent(),
|
|
livenessState: "empty_response",
|
|
livenessReason: "No useful output",
|
|
nextAction: null,
|
|
budgetBlocked: false,
|
|
idempotentWakeExists: false,
|
|
});
|
|
|
|
expect(decision.kind).toBe("enqueue");
|
|
if (decision.kind !== "enqueue") return;
|
|
expect(decision.nextAttempt).toBe(2);
|
|
});
|
|
|
|
it("leaves advanced terminal runs to stranded issue recovery instead of bounded liveness continuation", () => {
|
|
const decision = decideRunLivenessContinuation({
|
|
run: run(),
|
|
issue: issue(),
|
|
agent: agent(),
|
|
livenessState: "advanced",
|
|
livenessReason: "Run produced concrete action evidence: created an issue comment",
|
|
nextAction: "Resume the implementation from the remaining acceptance criteria.",
|
|
budgetBlocked: false,
|
|
idempotentWakeExists: false,
|
|
});
|
|
|
|
expect(decision).toEqual({
|
|
kind: "skip",
|
|
reason: "liveness state is not actionable for continuation",
|
|
});
|
|
});
|
|
|
|
it("does not enqueue a third continuation and returns an exhaustion comment", () => {
|
|
const decision = decideRunLivenessContinuation({
|
|
run: run({ continuationAttempt: 2 }),
|
|
issue: issue(),
|
|
agent: agent(),
|
|
livenessState: "plan_only",
|
|
livenessReason: "Still planning",
|
|
nextAction: null,
|
|
budgetBlocked: false,
|
|
idempotentWakeExists: false,
|
|
});
|
|
|
|
expect(decision.kind).toBe("exhausted");
|
|
if (decision.kind !== "exhausted") return;
|
|
expect(decision.comment).toContain("Bounded liveness continuation exhausted");
|
|
expect(decision.comment).toContain("Attempts used: 2/2");
|
|
});
|
|
|
|
it("skips non-actionable and guarded issues", () => {
|
|
const guardedCases = [
|
|
{ livenessState: "advanced" as const },
|
|
{ issue: issue({ status: "done" }) },
|
|
{ issue: issue({ assigneeAgentId: "other-agent" }) },
|
|
{ issue: issue({ executionState: { status: "pending" } }) },
|
|
{ agent: agent({ status: "paused" }) },
|
|
{ budgetBlocked: true },
|
|
{ idempotentWakeExists: true },
|
|
];
|
|
|
|
for (const guarded of guardedCases) {
|
|
const decision = decideRunLivenessContinuation({
|
|
run: run(),
|
|
issue: guarded.issue ?? issue(),
|
|
agent: guarded.agent ?? agent(),
|
|
livenessState: guarded.livenessState ?? "plan_only",
|
|
livenessReason: "No progress",
|
|
nextAction: null,
|
|
budgetBlocked: guarded.budgetBlocked ?? false,
|
|
idempotentWakeExists: guarded.idempotentWakeExists ?? false,
|
|
});
|
|
|
|
expect(decision.kind).toBe("skip");
|
|
}
|
|
});
|
|
});
|