forked from farhoodlabs/paperclip
[codex] Improve transient recovery and Codex model refresh (#4383)
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Adapter execution and retry classification decide whether agent work pauses, retries, or recovers automatically > - Transient provider failures need to be classified precisely so Paperclip does not convert retryable upstream conditions into false hard failures > - At the same time, operators need an up-to-date model list for Codex-backed agents and prompts should nudge agents toward targeted verification instead of repo-wide sweeps > - This pull request tightens transient recovery classification for Claude and Codex, updates the agent prompt guidance, and adds Codex model refresh support end-to-end > - The benefit is better automatic retry behavior plus fresher operator-facing model configuration ## What Changed - added Codex usage-limit retry-window parsing and Claude extra-usage transient classification - normalized the heartbeat transient-recovery contract across adapter executions and heartbeat scheduling - documented that deferred comment wakes only reopen completed issues for human/comment-reopen interactions, while system follow-ups leave closed work closed - updated adapter-utils prompt guidance to prefer targeted verification - added Codex model refresh support in the server route, registry, shared types, and agent config form - added adapter/server tests covering the new parsing, retry scheduling, and model-refresh behavior ## Verification - `pnpm exec vitest run --project @paperclipai/adapter-utils packages/adapter-utils/src/server-utils.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-claude-local packages/adapters/claude-local/src/server/parse.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-codex-local packages/adapters/codex-local/src/server/parse.test.ts` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/adapter-model-refresh-routes.test.ts server/src/__tests__/adapter-models.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/codex-local-execute.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts` ## Risks - Moderate behavior risk: retry classification affects whether runs auto-recover or block, so mistakes here could either suppress needed retries or over-retry real failures - Low workflow risk: deferred comment wake reopening is intentionally scoped to human/comment-reopen interactions so system follow-ups do not revive completed issues unexpectedly > 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-based coding agent with tool use and code execution in the Codex CLI 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 - [ ] If this change affects the UI, I have included before/after screenshots - [ ] 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
@@ -0,0 +1,185 @@
|
||||
import express from "express";
|
||||
import request from "supertest";
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import type { ServerAdapterModule } from "../adapters/index.js";
|
||||
|
||||
const mockAccessService = vi.hoisted(() => ({
|
||||
canUser: vi.fn(),
|
||||
hasPermission: vi.fn(),
|
||||
ensureMembership: vi.fn(),
|
||||
setPrincipalPermission: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockCompanySkillService = vi.hoisted(() => ({
|
||||
listRuntimeSkillEntries: vi.fn(),
|
||||
resolveRequestedSkillKeys: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockSecretService = vi.hoisted(() => ({
|
||||
normalizeAdapterConfigForPersistence: vi.fn(async (_companyId: string, config: Record<string, unknown>) => config),
|
||||
resolveAdapterConfigForRuntime: vi.fn(async (_companyId: string, config: Record<string, unknown>) => ({ config })),
|
||||
}));
|
||||
|
||||
const mockAgentInstructionsService = vi.hoisted(() => ({
|
||||
materializeManagedBundle: vi.fn(),
|
||||
getBundle: vi.fn(),
|
||||
readFile: vi.fn(),
|
||||
updateBundle: vi.fn(),
|
||||
writeFile: vi.fn(),
|
||||
deleteFile: vi.fn(),
|
||||
exportFiles: vi.fn(),
|
||||
ensureManagedBundle: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockBudgetService = vi.hoisted(() => ({
|
||||
upsertPolicy: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockHeartbeatService = vi.hoisted(() => ({
|
||||
cancelActiveForAgent: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockIssueApprovalService = vi.hoisted(() => ({
|
||||
linkManyForApproval: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockApprovalService = vi.hoisted(() => ({
|
||||
create: vi.fn(),
|
||||
getById: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockInstanceSettingsService = vi.hoisted(() => ({
|
||||
getGeneral: vi.fn(async () => ({ censorUsernameInLogs: false })),
|
||||
}));
|
||||
|
||||
const mockLogActivity = vi.hoisted(() => vi.fn());
|
||||
|
||||
function registerModuleMocks() {
|
||||
vi.doMock("../services/index.js", () => ({
|
||||
agentService: () => ({}),
|
||||
agentInstructionsService: () => mockAgentInstructionsService,
|
||||
accessService: () => mockAccessService,
|
||||
approvalService: () => mockApprovalService,
|
||||
companySkillService: () => mockCompanySkillService,
|
||||
budgetService: () => mockBudgetService,
|
||||
heartbeatService: () => mockHeartbeatService,
|
||||
issueApprovalService: () => mockIssueApprovalService,
|
||||
issueService: () => ({}),
|
||||
logActivity: mockLogActivity,
|
||||
secretService: () => mockSecretService,
|
||||
syncInstructionsBundleConfigFromFilePath: vi.fn((_agent, config) => config),
|
||||
workspaceOperationService: () => ({}),
|
||||
}));
|
||||
|
||||
vi.doMock("../services/instance-settings.js", () => ({
|
||||
instanceSettingsService: () => mockInstanceSettingsService,
|
||||
}));
|
||||
}
|
||||
|
||||
const refreshableAdapterType = "refreshable_adapter_route_test";
|
||||
|
||||
async function createApp() {
|
||||
const [{ agentRoutes }, { errorHandler }] = await Promise.all([
|
||||
vi.importActual<typeof import("../routes/agents.js")>("../routes/agents.js"),
|
||||
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
||||
]);
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.use((req, _res, next) => {
|
||||
(req as any).actor = {
|
||||
type: "board",
|
||||
userId: "local-board",
|
||||
companyIds: ["company-1"],
|
||||
source: "local_implicit",
|
||||
isInstanceAdmin: false,
|
||||
};
|
||||
next();
|
||||
});
|
||||
app.use("/api", agentRoutes({} as any));
|
||||
app.use(errorHandler);
|
||||
return app;
|
||||
}
|
||||
|
||||
async function requestApp(
|
||||
app: express.Express,
|
||||
buildRequest: (baseUrl: string) => request.Test,
|
||||
) {
|
||||
const { createServer } = await vi.importActual<typeof import("node:http")>("node:http");
|
||||
const server = createServer(app);
|
||||
try {
|
||||
await new Promise<void>((resolve) => {
|
||||
server.listen(0, "127.0.0.1", resolve);
|
||||
});
|
||||
const address = server.address();
|
||||
if (!address || typeof address === "string") {
|
||||
throw new Error("Expected HTTP server to listen on a TCP port");
|
||||
}
|
||||
return await buildRequest(`http://127.0.0.1:${address.port}`);
|
||||
} finally {
|
||||
if (server.listening) {
|
||||
await new Promise<void>((resolve, reject) => {
|
||||
server.close((error) => {
|
||||
if (error) reject(error);
|
||||
else resolve();
|
||||
});
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function unregisterTestAdapter(type: string) {
|
||||
const { unregisterServerAdapter } = await import("../adapters/index.js");
|
||||
unregisterServerAdapter(type);
|
||||
}
|
||||
|
||||
describe("adapter model refresh route", () => {
|
||||
beforeEach(async () => {
|
||||
vi.resetModules();
|
||||
vi.doUnmock("../routes/agents.js");
|
||||
vi.doUnmock("../routes/authz.js");
|
||||
vi.doUnmock("../middleware/index.js");
|
||||
registerModuleMocks();
|
||||
vi.clearAllMocks();
|
||||
mockCompanySkillService.listRuntimeSkillEntries.mockResolvedValue([]);
|
||||
mockCompanySkillService.resolveRequestedSkillKeys.mockResolvedValue([]);
|
||||
mockAccessService.canUser.mockResolvedValue(true);
|
||||
mockAccessService.hasPermission.mockResolvedValue(true);
|
||||
mockAccessService.ensureMembership.mockResolvedValue(undefined);
|
||||
mockAccessService.setPrincipalPermission.mockResolvedValue(undefined);
|
||||
mockLogActivity.mockResolvedValue(undefined);
|
||||
await unregisterTestAdapter(refreshableAdapterType);
|
||||
});
|
||||
|
||||
afterEach(async () => {
|
||||
await unregisterTestAdapter(refreshableAdapterType);
|
||||
});
|
||||
|
||||
it("uses refreshModels when refresh=1 is requested", async () => {
|
||||
const listModels = vi.fn(async () => [{ id: "stale-model", label: "stale-model" }]);
|
||||
const refreshModels = vi.fn(async () => [{ id: "fresh-model", label: "fresh-model" }]);
|
||||
const { registerServerAdapter } = await import("../adapters/index.js");
|
||||
const adapter: ServerAdapterModule = {
|
||||
type: refreshableAdapterType,
|
||||
execute: async () => ({ exitCode: 0, signal: null, timedOut: false }),
|
||||
testEnvironment: async () => ({
|
||||
adapterType: refreshableAdapterType,
|
||||
status: "pass",
|
||||
checks: [],
|
||||
testedAt: new Date(0).toISOString(),
|
||||
}),
|
||||
listModels,
|
||||
refreshModels,
|
||||
};
|
||||
registerServerAdapter(adapter);
|
||||
|
||||
const app = await createApp();
|
||||
const res = await requestApp(app, (baseUrl) =>
|
||||
request(baseUrl).get(`/api/companies/company-1/adapters/${refreshableAdapterType}/models?refresh=1`),
|
||||
);
|
||||
|
||||
expect(res.status, JSON.stringify(res.body)).toBe(200);
|
||||
expect(res.body).toEqual([{ id: "fresh-model", label: "fresh-model" }]);
|
||||
expect(refreshModels).toHaveBeenCalledTimes(1);
|
||||
expect(listModels).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user