[codex] Add run liveness continuations (#4083)

## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Heartbeat runs are the control-plane record of each agent execution window. > - Long-running local agents can exhaust context or stop while still holding useful next-step state. > - Operators need that stop reason, next action, and continuation path to be durable and visible. > - This pull request adds run liveness metadata, continuation summaries, and UI surfaces for issue run ledgers. > - The benefit is that interrupted or long-running work can resume with clearer context instead of losing the agent's last useful handoff. ## What Changed - Added heartbeat-run liveness fields, continuation attempt tracking, and an idempotent `0058` migration. - Added server services and tests for run liveness, continuation summaries, stop metadata, and activity backfill. - Wired local and HTTP adapters to surface continuation/liveness context through shared adapter utilities. - Added shared constants, validators, and heartbeat types for liveness continuation state. - Added issue-detail UI surfaces for continuation handoffs and the run ledger, with component tests. - Updated agent runtime docs, heartbeat protocol docs, prompt guidance, onboarding assets, and skills instructions to explain continuation behavior. - Addressed Greptile feedback by scoping document evidence by run, excluding system continuation-summary documents from liveness evidence, importing shared liveness types, surfacing hidden ledger run counts, documenting bounded retry behavior, and moving run-ledger liveness backfill off the request path. ## Verification - `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts server/src/__tests__/run-continuations.test.ts server/src/__tests__/run-liveness.test.ts server/src/__tests__/activity-service.test.ts server/src/__tests__/documents-service.test.ts server/src/__tests__/issue-continuation-summary.test.ts server/src/services/heartbeat-stop-metadata.test.ts ui/src/components/IssueRunLedger.test.tsx ui/src/components/IssueContinuationHandoff.test.tsx ui/src/components/IssueDocumentsSection.test.tsx` - `pnpm --filter @paperclipai/db build` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm --filter @paperclipai/ui typecheck` - `pnpm --filter @paperclipai/server typecheck` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/run-continuations.test.ts ui/src/components/IssueRunLedger.test.tsx` - `pnpm exec vitest run server/src/__tests__/heartbeat-process-recovery.test.ts -t "treats a plan document update"` - `pnpm exec vitest run server/src/__tests__/activity-service.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts -t "activity service|treats a plan document update"` - Remote PR checks on head `e53b1a1d`: `verify`, `e2e`, `policy`, and Snyk all passed. - Confirmed `public-gh/master` is an ancestor of this branch after fetching `public-gh master`. - Confirmed `pnpm-lock.yaml` is not included in the branch diff. - Confirmed migration `0058_wealthy_starbolt.sql` is ordered after `0057` and uses `IF NOT EXISTS` guards for repeat application. - Greptile inline review threads are resolved. ## Risks - Medium risk: this touches heartbeat execution, liveness recovery, activity rendering, issue routes, shared contracts, docs, and UI. - Migration risk is mitigated by additive columns/indexes and idempotent guards. - Run-ledger liveness backfill is now asynchronous, so the first ledger response can briefly show historical missing liveness until the background backfill completes. - UI screenshot coverage is not included in this packaging pass; validation is currently through focused component tests. > 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-5.4, local tool-use coding agent with terminal, git, GitHub connector, GitHub CLI, and Paperclip API access. ## 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 Screenshot note: no before/after screenshots were captured in this PR packaging pass; the UI changes are covered by focused component tests listed above. --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-20 06:01:49 -05:00
parent b9a80dcf22
commit 236d11d36f
71 changed files with 18254 additions and 85 deletions
@@ -0,0 +1,153 @@
+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.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.",
+    });
+  });
+
+  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("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");
+    }
+  });
+});