bfe6369ef5
## Thinking Path > - Paperclip is the control plane that coordinates AI-agent work through issues, heartbeats, comments, approvals, and auditable recovery paths. > - The affected subsystem is heartbeat/recovery orchestration, especially the optional cheap model profile used for operational recovery overhead. > - Cheap recovery should repair status and liveness, but it must not become the worker lane that writes deliverables, continues source work, or propagates cheap execution hints into downstream retries. > - The gap was that cheap-profile hints could follow recovery wake contexts and assignment overrides farther than intended, making real work eligible to run on the cheap model. > - This pull request separates status-only cheap recovery from normal source-work continuations, adds route guards for deliverable mutations during cheap status-only runs, and documents the invariant. > - The benefit is safer retry/recovery behavior: cheap runs can clean up control-plane state, while any remaining source work resumes through a normal/original model path. ## What Changed - Added recovery model-profile work classes so status-only recovery carries explicit guard context and normal-model continuations scrub cheap hints. - Updated heartbeat, productivity review, liveness continuation, and recovery service wakeups to request cheap only for bounded status-only recovery work. - Blocked cheap status-only recovery runs from writing issue documents, plans, attachments, work products, or assigning downstream work back to `modelProfile: "cheap"`. - Added/updated server tests for cheap profile propagation, artifact/document guards, route authorization, retry scheduling, and successful-run handoff behavior. - Documented the recovery model-profile lane in `doc/SPEC-implementation.md` and `doc/execution-semantics.md`. - After rebasing onto current `public-gh/master`, stabilized the new `InstanceSidebar` plugin-filter tests so the PR check lane stays green. ## Verification - Local: `pnpm exec vitest run --config vitest.config.ts src/services/recovery/model-profile-hint.test.ts src/__tests__/issue-agent-mutation-ownership-routes.test.ts src/__tests__/issue-document-restore-routes.test.ts` from `server/` - 3 files, 37 tests passed after final edits. - Local: `pnpm exec vitest run --config vitest.config.ts src/__tests__/heartbeat-process-recovery.test.ts` from `server/` - 44 tests passed after rerunning the cleanup-sensitive file alone. - Local: `pnpm --filter @paperclipai/ui exec vitest run src/components/InstanceSidebar.test.tsx` - 4 tests passed. - Local: `pnpm --filter @paperclipai/server typecheck` - passed. - Local: `pnpm --filter @paperclipai/ui typecheck` - passed. - PR checks on latest head `6f8c3b1380f5bd872c6f49f6f7188ecf3bb6d263` - all green, including `verify`, build, typecheck, server/general/serialized tests, e2e, Snyk, and policy. - Greptile: pass 3 returned Confidence Score 5/5 with zero unresolved Greptile review threads. ## Risks - Medium risk: recovery behavior is intentionally stricter, so any path that incorrectly relies on cheap recovery to keep doing source work will now need to hand back to a normal-model run. - Low migration risk: no schema changes. - No product UI changes; the UI file touched is a test-only stabilization after rebasing onto current `master`. > 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, GPT-5 model family (`gpt-5`), tool use and local code execution enabled; context window not exposed in this 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 - [x] If this change affects the UI, I have included before/after screenshots (N/A: no product UI changes) - [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
174 lines
5.4 KiB
TypeScript
174 lines
5.4 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.",
|
|
});
|
|
expect(decision.payload).not.toHaveProperty("modelProfile");
|
|
expect(decision.contextSnapshot).toMatchObject({
|
|
issueId,
|
|
wakeReason: RUN_LIVENESS_CONTINUATION_REASON,
|
|
livenessContinuationAttempt: 1,
|
|
livenessContinuationMaxAttempts: DEFAULT_MAX_LIVENESS_CONTINUATION_ATTEMPTS,
|
|
livenessContinuationSourceRunId: runId,
|
|
livenessContinuationState: "plan_only",
|
|
livenessContinuationReason: "Planned without acting",
|
|
livenessContinuationInstruction: "Take the first concrete action now.",
|
|
});
|
|
expect(decision.contextSnapshot).not.toHaveProperty("modelProfile");
|
|
});
|
|
|
|
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");
|
|
}
|
|
});
|
|
});
|