mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-21 08:22:20 +02:00
perf(server): reject shared Git cleanup paths before history scans (#16614)
Check the existing global execution/project shared-path veto before scanning retained run contexts. Preserve the full unshared-path query, lifecycle locks and all deletion-phase rechecks. Verify with 35 focused real PostgreSQL/Git cases, full repository typecheck/build, exact-head full CI/E2E and Greptile Base 5/5. A read-only same-snapshot query pair retained the false verdict while reducing round trip from1089ms to9.4ms; this is not a full-agent latency result. The first security scan was inconclusive after an infrastructure checkout failure; one actual rescan passed. Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
1 parent
564d4e1bce
commit
dc499ae02b
3 files changed
+112
-11
No files matched your search
@@ -0,0 +1,94 @@
|
||||
import { randomUUID } from "node:crypto";
|
||||
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from "vitest";
|
||||
import { eq, sql } from "drizzle-orm";
|
||||
import { agents, companies, createDb, executionWorkspaces, heartbeatRuns, issues, projects, projectWorkspaces } from "@paperclipai/db";
|
||||
import { isGitWorkspaceExpirationEligible } from "../services/git-workspace-expiration.js";
|
||||
import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "./helpers/embedded-postgres.js";
|
||||
|
||||
type Plan = { "Relation Name"?: string; "Actual Loops"?: number; Plans?: Plan[] };
|
||||
const flatten = (plan: Plan): Plan[] => [plan, ...(plan.Plans ?? []).flatMap(flatten)];
|
||||
const support = await getEmbeddedPostgresTestSupport();
|
||||
const describeDatabase = support.supported ? describe : describe.skip;
|
||||
|
||||
describeDatabase("Git expiration eligibility", () => {
|
||||
let database: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>>;
|
||||
let db: ReturnType<typeof createDb>;
|
||||
beforeAll(async () => {
|
||||
database = await startEmbeddedPostgresTestDatabase("git-expiration-eligibility-");
|
||||
db = createDb(database.connectionString, { maxConnections: 1 });
|
||||
});
|
||||
afterEach(async () => { vi.restoreAllMocks(); await db.execute(sql`TRUNCATE TABLE companies CASCADE`); });
|
||||
afterAll(async () => { await db?.$client.end({ timeout: 1 }); await database?.cleanup(); });
|
||||
|
||||
async function fixture() {
|
||||
const companyId = randomUUID(), agentId = randomUUID(), issueId = randomUUID();
|
||||
const now = new Date(), old = new Date(now.getTime() - 3 * 86_400_000);
|
||||
await db.insert(companies).values({ id: companyId, name: "Eligibility", issuePrefix: `EL${companyId.slice(0, 6)}` });
|
||||
await db.insert(agents).values({ id: agentId, companyId, name: "Eligibility" });
|
||||
await db.insert(issues).values({ id: issueId, companyId, title: "Finished root", status: "done", completedAt: old });
|
||||
const [workspace] = await db.insert(executionWorkspaces).values({ companyId, sourceIssueId: issueId,
|
||||
mode: "isolated_workspace", strategyType: "git_worktree", name: "Eligibility", cwd: `/tmp/eligibility-${companyId}` }).returning();
|
||||
await db.insert(heartbeatRuns).values({ companyId, agentId, status: "succeeded", finishedAt: old, contextSnapshot: { issueId } });
|
||||
const eligible = () => db.transaction(tx => isGitWorkspaceExpirationEligible(tx, workspace, now));
|
||||
return { companyId, agentId, issueId, workspace, now, old, eligible };
|
||||
}
|
||||
|
||||
async function alias(f: Awaited<ReturnType<typeof fixture>>, kind: string) {
|
||||
const companyId = randomUUID();
|
||||
await db.insert(companies).values({ id: companyId, name: "Other owner", issuePrefix: `EO${companyId.slice(0, 6)}` });
|
||||
const cwd = kind.endsWith("child") ? `${f.workspace.cwd}/nested` : f.workspace.cwd;
|
||||
if (kind.startsWith("project")) {
|
||||
const [project] = await db.insert(projects).values({ companyId, name: "Other project" }).returning();
|
||||
const [row] = await db.insert(projectWorkspaces).values({ companyId, projectId: project.id, name: "Other checkout", cwd }).returning();
|
||||
return { id: row.id, table: projectWorkspaces };
|
||||
}
|
||||
const [row] = await db.insert(executionWorkspaces).values({ companyId, mode: "isolated_workspace", strategyType: "git_worktree", name: "Other checkout",
|
||||
cwd: kind === "workspace provider" ? `/tmp/unrelated-${companyId}` : cwd,
|
||||
providerRef: kind === "workspace provider" ? f.workspace.cwd : null }).returning();
|
||||
return { id: row.id, table: executionWorkspaces };
|
||||
}
|
||||
|
||||
it.each(["workspace same", "workspace provider", "workspace child", "project same", "project child"])("rejects %s before reading run history", async kind => {
|
||||
const f = await fixture();
|
||||
await alias(f, kind);
|
||||
await db.transaction(async tx => {
|
||||
const execute = vi.spyOn(tx, "execute");
|
||||
expect(await isGitWorkspaceExpirationEligible(tx, f.workspace, f.now)).toBe(false);
|
||||
const query = execute.mock.calls[0]![0];
|
||||
execute.mockRestore();
|
||||
const rows = await tx.execute(sql`EXPLAIN (ANALYZE, FORMAT JSON) ${query}`);
|
||||
const explained = rows[0]["QUERY PLAN"] as Array<{ Plan: Plan }>;
|
||||
const historyScans = flatten(explained[0].Plan).filter(node => node["Relation Name"] === "heartbeat_runs");
|
||||
expect(historyScans.every(node => node["Actual Loops"] === 0)).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
it("rechecks a shared consumer added or removed between eligibility checks", async () => {
|
||||
const f = await fixture();
|
||||
expect(await f.eligible()).toBe(true);
|
||||
const consumer = await alias(f, "workspace same");
|
||||
expect(await f.eligible()).toBe(false);
|
||||
await db.delete(consumer.table).where(eq(consumer.table.id, consumer.id));
|
||||
expect(await f.eligible()).toBe(true);
|
||||
});
|
||||
|
||||
it("does not treat a sibling path prefix as a descendant", async () => {
|
||||
const f = await fixture();
|
||||
await db.insert(executionWorkspaces).values({ companyId: f.companyId, mode: "isolated_workspace", strategyType: "git_worktree", name: "Sibling", cwd: `${f.workspace.cwd}-sibling` });
|
||||
expect(await f.eligible()).toBe(true);
|
||||
});
|
||||
|
||||
it.each(["issueId", "nativeIssueId", "contextIssue", "contextTask", "contextWorkspace", "checkout"])("retains the active-run veto through %s", async route => {
|
||||
const f = await fixture(), runId = randomUUID();
|
||||
await db.insert(heartbeatRuns).values({ id: runId, companyId: f.companyId, agentId: f.agentId, status: "scheduled_retry",
|
||||
...(route === "issueId" ? { scopeKind: "issue" as const, issueId: f.issueId } : {}),
|
||||
...(route === "nativeIssueId" ? { nativeIssueId: f.issueId } : {}),
|
||||
contextSnapshot: route === "contextIssue" ? { issueId: f.issueId } : route === "contextTask" ? { taskId: f.issueId } : route === "contextWorkspace" ? { executionWorkspaceId: f.workspace.id } : null });
|
||||
if (route === "checkout") {
|
||||
await db.insert(issues).values({ companyId: f.companyId, title: "Other finished consumer", status: "done", completedAt: f.old, executionWorkspaceId: f.workspace.id, checkoutRunId: runId });
|
||||
}
|
||||
expect(await f.eligible()).toBe(false);
|
||||
await db.update(heartbeatRuns).set({ status: "succeeded", finishedAt: f.old }).where(eq(heartbeatRuns.id, runId));
|
||||
expect(await f.eligible()).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -32,7 +32,7 @@ export type GitExpirationResult = { candidate: boolean; expired: boolean; reclai
|
||||
candidateBytes: number; baseExpired: boolean; skipReason: string | null };
|
||||
|
||||
/** Re-read the whole tree and every runtime/recovery consumer immediately before deletion. */
|
||||
async function eligible(tx: Tx, workspace: Workspace, now: Date) {
|
||||
export async function isGitWorkspaceExpirationEligible(tx: Tx, workspace: Workspace, now: Date) {
|
||||
if (workspace.metadata?.reopenPendingConsumption === true) return false;
|
||||
const rows = await tx.execute<{ allowed: boolean }>(sql`
|
||||
WITH RECURSIVE tree AS (
|
||||
@@ -50,7 +50,13 @@ async function eligible(tx: Tx, workspace: Workspace, now: Date) {
|
||||
OR r.id IN (SELECT unnest(ARRAY[checkout_run_id, execution_run_id]) FROM ${issues}
|
||||
WHERE company_id = ${workspace.companyId} AND execution_workspace_id = ${workspace.id})
|
||||
)
|
||||
) SELECT (
|
||||
) SELECT CASE WHEN
|
||||
EXISTS (SELECT 1 FROM ${executionWorkspaces} other WHERE other.id <> ${workspace.id}
|
||||
AND (other.cwd = ${workspace.cwd} OR other.provider_ref = ${workspace.cwd}
|
||||
OR left(other.cwd, length(${workspace.cwd}) + 1) = ${workspace.cwd} || '/'))
|
||||
OR EXISTS (SELECT 1 FROM ${projectWorkspaces} WHERE cwd = ${workspace.cwd}
|
||||
OR left(cwd, length(${workspace.cwd}) + 1) = ${workspace.cwd} || '/')
|
||||
THEN false ELSE (
|
||||
EXISTS (SELECT 1 FROM tree)
|
||||
AND NOT EXISTS (SELECT 1 FROM tree WHERE status NOT IN ('done', 'cancelled')
|
||||
OR coalesce(CASE WHEN status = 'done' THEN completed_at ELSE cancelled_at END, updated_at) > ${new Date(now.getTime() - DAY_MS).toISOString()}::timestamptz)
|
||||
@@ -70,12 +76,8 @@ async function eligible(tx: Tx, workspace: Workspace, now: Date) {
|
||||
AND NOT EXISTS (SELECT 1 FROM ${workspaceRuntimeServices} WHERE company_id = ${workspace.companyId}
|
||||
AND (execution_workspace_id = ${workspace.id} OR cwd = ${workspace.cwd}
|
||||
OR left(cwd, length(${workspace.cwd}) + 1) = ${workspace.cwd} || '/') AND status <> 'stopped')
|
||||
AND NOT EXISTS (SELECT 1 FROM ${executionWorkspaces} other WHERE other.id <> ${workspace.id}
|
||||
AND (other.cwd = ${workspace.cwd} OR other.provider_ref = ${workspace.cwd}
|
||||
OR left(other.cwd, length(${workspace.cwd}) + 1) = ${workspace.cwd} || '/'))
|
||||
AND NOT EXISTS (SELECT 1 FROM ${projectWorkspaces} WHERE cwd = ${workspace.cwd}
|
||||
OR left(cwd, length(${workspace.cwd}) + 1) = ${workspace.cwd} || '/')
|
||||
) AS allowed`);
|
||||
|
||||
) END AS allowed`);
|
||||
return rows[0]?.allowed === true;
|
||||
}
|
||||
|
||||
@@ -158,7 +160,7 @@ export async function expireReconstructableGitWorkspace(db: Db, snapshot: Worksp
|
||||
if (!acquired[0]?.locked) throw new Error("lifecycle_busy");
|
||||
let workspace = (await db.select().from(executionWorkspaces).where(and(eq(executionWorkspaces.id, snapshot.id), eq(executionWorkspaces.companyId, snapshot.companyId))))[0];
|
||||
if (!workspace || workspace.updatedAt.getTime() !== snapshot.updatedAt.getTime()) throw new Error("workspace_changed");
|
||||
if (!await eligible(tx, workspace, options.now)) throw new Error("live_or_unresolved_consumer");
|
||||
if (!await isGitWorkspaceExpirationEligible(tx, workspace, options.now)) throw new Error("live_or_unresolved_consumer");
|
||||
let state = ["active", "idle", "in_review"].includes(workspace.status) ? null : readGitCacheExpiration(workspace);
|
||||
// A restored active workspace starts a new expiration cycle and records its new HEAD.
|
||||
if (!hasPendingGitExpiration(workspace) && !["active", "idle", "in_review"].includes(workspace.status)) throw new Error("not_expirable");
|
||||
@@ -204,7 +206,7 @@ export async function expireReconstructableGitWorkspace(db: Db, snapshot: Worksp
|
||||
.where(eq(executionWorkspaces.id, snapshot.id)).returning();
|
||||
};
|
||||
await options.beforeDelete?.(workspace);
|
||||
if (!await eligible(tx, workspace, options.now)) throw new Error("live_or_unresolved_consumer");
|
||||
if (!await isGitWorkspaceExpirationEligible(tx, workspace, options.now)) throw new Error("live_or_unresolved_consumer");
|
||||
if (!state.workspaceRemoved && present) {
|
||||
const { acquireGitWorktreeCleanupLock } = await import("./workspace-runtime.js");
|
||||
const lock = await acquireGitWorktreeCleanupLock(recipe.worktreePath);
|
||||
@@ -224,7 +226,7 @@ export async function expireReconstructableGitWorkspace(db: Db, snapshot: Worksp
|
||||
try {
|
||||
if ((!state.baseTrash || !await exists(state.baseTrash)) && await exists(recipe.sourcePath)) {
|
||||
const bytes = await inspectBase(db, workspace!, options.signal);
|
||||
if (!await eligible(tx, workspace!, options.now)) throw new Error("live_or_unresolved_consumer");
|
||||
if (!await isGitWorkspaceExpirationEligible(tx, workspace!, options.now)) throw new Error("live_or_unresolved_consumer");
|
||||
const trash = path.join(path.dirname(recipe.sourcePath), `.expired-git-base-${snapshot.id}-${state.generation}`);
|
||||
if (await exists(trash)) throw new Error("unknown_base_trash");
|
||||
state.baseTrash = trash;
|
||||
|
||||
Reference in new issue
Block a user