[codex] Improve agent runtime recovery and governance (#4086)

## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies.
> - The heartbeat runtime, agent import path, and agent configuration
defaults determine whether work is dispatched safely and predictably.
> - Several accumulated fixes all touched agent execution recovery, wake
routing, import behavior, and runtime concurrency defaults.
> - Those changes need to land together so the heartbeat service and
agent creation defaults stay internally consistent.
> - This pull request groups the runtime/governance changes from the
split branch into one standalone branch.
> - The benefit is safer recovery for stranded runs, bounded high-volume
reads, imported-agent approval correctness, skill-template support, and
a clearer default concurrency policy.

## What Changed

- Fixed stranded continuation recovery so successful automatic retries
are requeued instead of incorrectly blocking the issue.
- Bounded high-volume issue/log reads across issue, heartbeat, agent,
project, and workspace paths.
- Fixed imported-agent approval and instruction-path permission
handling.
- Quarantined seeded worktree execution state during worktree
provisioning.
- Queued approval follow-up wakes and hardened SQL_ASCII heartbeat
output handling.
- Added reusable agent instruction templates for hiring flows.
- Set the default max concurrent agent runs to five and updated related
UI/tests/docs.

## Verification

- `pnpm install --frozen-lockfile`
- `pnpm exec vitest run server/src/__tests__/company-portability.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-comment-wake-batching.test.ts
server/src/__tests__/heartbeat-list.test.ts
server/src/__tests__/issues-service.test.ts
server/src/__tests__/agent-permissions-routes.test.ts
packages/adapter-utils/src/server-utils.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- Split integration check: merged this branch first, followed by the
other [PAP-1614](/PAP/issues/PAP-1614) branches, with no merge
conflicts.
- Confirmed this branch does not include `pnpm-lock.yaml`.

## Risks

- Medium risk: touches heartbeat recovery, queueing, and issue list
bounds in central runtime paths.
- Imported-agent and concurrency default behavior changes may affect
existing automation that assumes one-at-a-time default runs.
- No database migrations are included.

> 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 tool-enabled coding model, agentic
code-editing/runtime with local shell and GitHub CLI access; exact
context window and reasoning mode are not exposed by the Paperclip
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 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>
This commit is contained in:
Dotta 2026-04-20 06:19:48 -05:00 committed by GitHub
parent 057fee4836
commit 16b2b84d84
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
38 changed files with 1569 additions and 240 deletions

View file

@ -3,12 +3,15 @@ import os from "node:os";
import path from "node:path";
import { execFileSync } from "node:child_process";
import { randomUUID } from "node:crypto";
import { eq } from "drizzle-orm";
import { afterEach, describe, expect, it, vi } from "vitest";
import {
agents,
authUsers,
companies,
createDb,
issueComments,
issues,
projects,
routines,
routineTriggers,
@ -17,6 +20,7 @@ import {
copyGitHooksToWorktreeGitDir,
copySeededSecretsKey,
pauseSeededScheduledRoutines,
quarantineSeededWorktreeExecutionState,
readSourceAttachmentBody,
rebindWorkspaceCwd,
resolveSourceConfigPath,
@ -282,6 +286,138 @@ describe("worktree helpers", () => {
expect(full.nullifyColumns).toEqual({});
});
itEmbeddedPostgres("quarantines copied live execution state in seeded worktree databases", async () => {
const tempDb = await startEmbeddedPostgresTestDatabase("paperclip-worktree-quarantine-");
const db = createDb(tempDb.connectionString);
const companyId = randomUUID();
const agentId = randomUUID();
const idleAgentId = randomUUID();
const inProgressIssueId = randomUUID();
const todoIssueId = randomUUID();
const reviewIssueId = randomUUID();
const userIssueId = randomUUID();
try {
await db.insert(companies).values({
id: companyId,
name: "Paperclip",
issuePrefix: "WTQ",
requireBoardApprovalForNewAgents: false,
});
await db.insert(agents).values([
{
id: agentId,
companyId,
name: "CodexCoder",
role: "engineer",
status: "running",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {
heartbeat: { enabled: true, intervalSec: 60 },
wakeOnDemand: true,
},
permissions: {},
},
{
id: idleAgentId,
companyId,
name: "Reviewer",
role: "reviewer",
status: "idle",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: { heartbeat: { enabled: false, intervalSec: 300 } },
permissions: {},
},
]);
await db.insert(issues).values([
{
id: inProgressIssueId,
companyId,
title: "Copied in-flight issue",
status: "in_progress",
priority: "medium",
assigneeAgentId: agentId,
issueNumber: 1,
identifier: "WTQ-1",
executionAgentNameKey: "codexcoder",
executionLockedAt: new Date("2026-04-18T00:00:00.000Z"),
},
{
id: todoIssueId,
companyId,
title: "Copied assigned todo issue",
status: "todo",
priority: "medium",
assigneeAgentId: agentId,
issueNumber: 2,
identifier: "WTQ-2",
},
{
id: reviewIssueId,
companyId,
title: "Copied assigned review issue",
status: "in_review",
priority: "medium",
assigneeAgentId: idleAgentId,
issueNumber: 3,
identifier: "WTQ-3",
},
{
id: userIssueId,
companyId,
title: "Copied user issue",
status: "todo",
priority: "medium",
assigneeUserId: "user-1",
issueNumber: 4,
identifier: "WTQ-4",
},
]);
await expect(quarantineSeededWorktreeExecutionState(tempDb.connectionString)).resolves.toEqual({
disabledTimerHeartbeats: 1,
resetRunningAgents: 1,
quarantinedInProgressIssues: 1,
unassignedTodoIssues: 1,
unassignedReviewIssues: 1,
});
const [quarantinedAgent] = await db.select().from(agents).where(eq(agents.id, agentId));
expect(quarantinedAgent?.status).toBe("idle");
expect(quarantinedAgent?.runtimeConfig).toMatchObject({
heartbeat: { enabled: false, intervalSec: 60 },
wakeOnDemand: true,
});
const [inProgressIssue] = await db.select().from(issues).where(eq(issues.id, inProgressIssueId));
expect(inProgressIssue?.status).toBe("blocked");
expect(inProgressIssue?.assigneeAgentId).toBeNull();
expect(inProgressIssue?.executionAgentNameKey).toBeNull();
expect(inProgressIssue?.executionLockedAt).toBeNull();
const [todoIssue] = await db.select().from(issues).where(eq(issues.id, todoIssueId));
expect(todoIssue?.status).toBe("todo");
expect(todoIssue?.assigneeAgentId).toBeNull();
const [reviewIssue] = await db.select().from(issues).where(eq(issues.id, reviewIssueId));
expect(reviewIssue?.status).toBe("in_review");
expect(reviewIssue?.assigneeAgentId).toBeNull();
const [userIssue] = await db.select().from(issues).where(eq(issues.id, userIssueId));
expect(userIssue?.status).toBe("todo");
expect(userIssue?.assigneeUserId).toBe("user-1");
const comments = await db.select().from(issueComments).where(eq(issueComments.issueId, inProgressIssueId));
expect(comments).toHaveLength(1);
expect(comments[0]?.body).toContain("Quarantined during worktree seed");
} finally {
await db.$client?.end?.({ timeout: 5 }).catch(() => undefined);
await tempDb.cleanup();
}
}, 20_000);
it("copies the source local_encrypted secrets key into the seeded worktree instance", () => {
const tempRoot = fs.mkdtempSync(path.join(os.tmpdir(), "paperclip-worktree-secrets-"));
const originalInlineMasterKey = process.env.PAPERCLIP_SECRETS_MASTER_KEY;