mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-31 22:24:16 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Agent adapters run agent sessions through the ACPX engine > - The ACPX engine handled one run attempt as a long implicit procedure > - That shape made resource ownership, cleanup order, and failure behavior hard to verify > - This pull request gives the attempt a coordinator, a typed resource ledger, separate run sites, and explicit turn and settlement sequences > - The benefit is clear ownership, one cleanup path, safer session reuse, and testable failure behavior ## Linked Issues or Issue Description **What existing behavior does this improve?** The ACPX engine manages startup, turn execution, session reuse, and cleanup inside one large run procedure. **Current behavior** The run procedure owns several resources through implicit control flow. Cleanup and session reuse behavior depend on lane-specific branches and error paths. **Proposed behavior** The coordinator owns the run attempt. A typed ledger records six resources and their states. Host and sandbox run sites own lane-specific acquisition. Turn and settlement sequences expose typed outcomes. The engine emits allowlisted phase telemetry. **Reason and benefit** Explicit ownership makes cleanup and failure behavior easier to inspect. The fault matrix and characterization tests protect the external result while the refactor reduces hidden control flow. **Breaking changes** None to the public adapter contract. The host warm-save path now closes and relaunches the runtime because a transferred runtime could retain a run-scoped credential. A cold session-handshake failure now closes the created runtime. **Additional context** This pull request contains the ACPX engine lifecycle refactor, its tests, and the lifecycle document. ## What Changed - Add a run coordinator for startup, turn execution, settlement, and result reproduction. - Add a typed resource ledger with open, sealed, and consumed states. - Add host and sandbox run sites for lane-specific resource acquisition. - Replace separate runtime maps with a generic session reuse store. - Split session fingerprint identity from the outer session key. - Add typed turn and settlement sequences with one cleanup owner. - Add a closed allowlist for phase telemetry. - Add characterization tests and a 17-case fault matrix. - Add `doc/acp-run-lifecycle.md`. ## Verification - `npx vitest run packages/adapter-utils/src/acpx-engine/` passes 18 files and 286 tests at the submitted commit. - `pnpm --filter @paperclipai/adapter-utils typecheck` reports 0 errors at the submitted commit. - Run the full pull request checks after GitHub starts CI. - Run Greptile review after the pull request opens. ## Risks - The refactor changes internal control flow across the ACPX engine. - Host warm-save behavior now closes and relaunches the runtime. - Settlement changes the handling of a cold session-handshake failure from a leak to a close. - The characterization baselines and fault matrix reduce the risk of an external behavior change. > Paperclip is the open source app people use to manage AI agents for work > The adapter layer runs agent sessions through the ACPX engine > The engine needs explicit lifecycle ownership for reliable cleanup > This pull request adds coordinator-owned phases and a typed resource ledger > The result makes lifecycle behavior easier to test and review ## Model Used OpenAI GPT-5 Codex. Exact model ID: GPT-5. The model used tool execution, repository inspection, and code review support. The implementation author supplied the submitted code. ## 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 searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
114 lines
4.1 KiB
TypeScript
114 lines
4.1 KiB
TypeScript
// Tests for the host run site (Phase 18).
|
|
//
|
|
// The host site is the null path with a warm-runtime store. These tests pin its
|
|
// warm-hit and warm-save behavior against the baseline warm sets, and confirm
|
|
// the null-path operations: host cwd plan, no staging failures, no transport,
|
|
// and no sync-back.
|
|
|
|
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
|
import { createHostRunSite, type RuntimeCacheEntry } from "./run-site-host.js";
|
|
import type { AcpRunContext, ReadyRunResources } from "./run-contracts.js";
|
|
|
|
function makeEntry(id: string, lastUsedAt: number): RuntimeCacheEntry {
|
|
return {
|
|
runtime: { id, close: async () => {} } as never,
|
|
handle: { sessionKey: id } as never,
|
|
childStderrState: { logPath: null, pendingLiveLine: "" },
|
|
processIdentitySink: { current: undefined, latest: null },
|
|
fingerprint: `fp-${id}`,
|
|
lastUsedAt,
|
|
};
|
|
}
|
|
|
|
describe("host run site", () => {
|
|
beforeEach(() => {
|
|
vi.useFakeTimers();
|
|
});
|
|
afterEach(() => {
|
|
vi.useRealTimers();
|
|
});
|
|
|
|
it("test_host_site_warm_hit_and_warm_save_match_baseline_sets", async () => {
|
|
const warmHandles = new Map<string, RuntimeCacheEntry>();
|
|
const closed: RuntimeCacheEntry[] = [];
|
|
const site = createHostRunSite({
|
|
warmHandles,
|
|
now: () => Date.now(),
|
|
idleMs: 60_000,
|
|
closeWarmEntry: async (entry) => {
|
|
closed.push(entry);
|
|
},
|
|
});
|
|
const store = site.reuse();
|
|
|
|
// Warm save: the entry lands in the caller's map as the sole warm entry, the
|
|
// same set the baseline warm-save path produces (`warmHandles.size` is 1).
|
|
const entry = makeEntry("paperclip:c:a:t:fp", Date.now());
|
|
store.save(entry.handle.sessionKey, entry);
|
|
expect(new Set(warmHandles.keys())).toEqual(new Set(["paperclip:c:a:t:fp"]));
|
|
expect(warmHandles.get("paperclip:c:a:t:fp")).toBe(entry);
|
|
// The save armed a per-entry idle timer.
|
|
expect(entry.cleanupTimer).toBeDefined();
|
|
|
|
// Warm hit: a borrow returns the same entry and leaves it in the map, so an
|
|
// overlapping run of the same session still reads it. The borrow cleared the
|
|
// idle timer, so the reused runtime does not expire while it is in use.
|
|
expect(store.borrow("paperclip:c:a:t:fp")).toBe(entry);
|
|
expect(warmHandles.size).toBe(1);
|
|
await vi.advanceTimersByTimeAsync(120_000);
|
|
expect(closed).toEqual([]);
|
|
expect(warmHandles.get("paperclip:c:a:t:fp")).toBe(entry);
|
|
|
|
// A discard drops the entry and closes its runtime once, matching the
|
|
// baseline drop set (empty map, one close).
|
|
await store.discard("paperclip:c:a:t:fp");
|
|
expect(warmHandles.size).toBe(0);
|
|
expect(closed).toEqual([entry]);
|
|
});
|
|
|
|
it("test_host_site_plan_and_null_path_operations", async () => {
|
|
const site = createHostRunSite({
|
|
warmHandles: new Map(),
|
|
now: () => 0,
|
|
idleMs: 0,
|
|
closeWarmEntry: async () => {},
|
|
});
|
|
|
|
const context = {
|
|
fingerprintIdentity: { cwd: "/work/dir" },
|
|
} as unknown as AcpRunContext;
|
|
|
|
// The plan binds the session to the host cwd, names no relay-proxy spawn cwd,
|
|
// and disables sandbox tracing.
|
|
expect(site.plan(context)).toEqual({
|
|
sessionCwd: "/work/dir",
|
|
spawnCwd: undefined,
|
|
tracingEnabled: false,
|
|
});
|
|
|
|
// The host runs in place, so it places nothing, starts no transport, and
|
|
// syncs nothing back.
|
|
expect(await site.placeWorkspace(context)).toEqual({ referencedProjectStagingFailures: [] });
|
|
expect(await site.startTransport(context)).toEqual({ controlBridge: null, agentBridge: null });
|
|
await expect(site.syncBack(context)).resolves.toBeUndefined();
|
|
});
|
|
|
|
it("test_host_site_reuse_candidate_names_runtime_and_session_handle", () => {
|
|
const site = createHostRunSite({
|
|
warmHandles: new Map(),
|
|
now: () => 0,
|
|
idleMs: 0,
|
|
closeWarmEntry: async () => {},
|
|
});
|
|
|
|
const runtime = { id: "rt" };
|
|
const sessionHandle = { id: "handle" };
|
|
const resources = {
|
|
get: (id: string) =>
|
|
id === "acp_runtime" ? { runtime, sessionHandle, childProcessPid: 42 } : undefined,
|
|
} as unknown as ReadyRunResources;
|
|
|
|
expect(site.reuseCandidate(resources)).toEqual({ runtime, sessionHandle });
|
|
});
|
|
});
|