mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-25 09:41:04 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Paperclip uses adapter and sandbox code to start agents and run sandbox work > - The current sandbox spans use mixed names and do not group related run-time work > - Mixed names make traces harder to read and compare across providers > - This pull request renames provider spans, adds run-time wrapper spans, and keeps the host allowlist closed > - The benefit is clearer traces with the same sandbox behavior and trust boundary ## Linked Issues or Issue Description **What existing behavior does this improve?** This improves OpenTelemetry span names and grouping for sandbox startup, execution, callback relay, and agent session work. **Subsystem affected** Cross-cutting (multiple of the above): adapter utilities, sandbox providers, shared telemetry documentation, and server instrumentation. **Current behavior** Sandbox provider spans use mixed names. Related run-time operations expose inner `sandbox.exec` spans without a named wrapper span. The host mapper uses a closed allowlist for provider span names. **Proposed behavior** Use descriptive provider-scoped span names. Add wrapper spans for agent session input, agent session output polling, and callback relay. Keep the host mapper allowlist closed and map unknown names to `other`. **Reason and benefit** Clear names make traces easier to read and reduce ambiguity during sandbox operation analysis. Wrapper spans show the full operation while preserving the inner execution spans. **Breaking changes** None. This change updates telemetry span names and grouping only. It does not change sandbox behavior, endpoint behavior, or the host trust boundary. **Additional context** Related prior work: [#10758](https://github.com/paperclipai/paperclip/pull/10758). ## What Changed - Rename Daytona provider sync and session spans with descriptive provider-scoped names. - Add three run-time wrapper spans for agent session input, output polling, and callback relay. - Add a shared span runner that preserves no-op behavior without a real tracer. - Keep the host mapper allowlist closed and map unknown names to `other`. - Update telemetry documentation and span-name tests. ## Verification - Focused adapter-utils span tests pass for startup timing, callback relay, and sandbox execution. - Focused Daytona plugin span tests pass for renamed leaf spans and session open or close spans. - Focused server tests pass for host mapping and instrumentation. - The stacked diff contains one commit on top of `feat/daytona-persistent-session-model`. ## Risks - Span names change for existing telemetry consumers. - The wrapper spans add trace structure but do not change sandbox execution. - The host mapper keeps the existing closed allowlist and `other` bucket. > 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 GPT-5 (Codex agent); exact deployment revision and context window are not exposed in this run; tool use and code execution enabled. ## 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] 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>
315 lines
11 KiB
TypeScript
315 lines
11 KiB
TypeScript
import { beforeEach, describe, expect, it, vi } from "vitest";
|
|
import { createHostClientHandlers } from "../../../packages/plugins/sdk/src/host-client-factory.js";
|
|
import type { WorkerHostCallContext } from "../../../packages/plugins/sdk/src/protocol.js";
|
|
import { SANDBOX_STARTUP_SPAN_ATTRS as A } from "@paperclipai/adapter-utils/acpx-engine/startup-timing";
|
|
import {
|
|
buildHostServices,
|
|
clampProviderSpanAttributes,
|
|
parseTraceparent,
|
|
} from "../services/plugin-host-services.js";
|
|
|
|
// Capture every span the host trust boundary hands to the real tracer.
|
|
const mockRecordSpan = vi.hoisted(() => vi.fn());
|
|
|
|
vi.mock("../instrumentation.js", () => ({
|
|
recordProviderPluginSpan: mockRecordSpan,
|
|
traceparentFromContextToken: () => undefined,
|
|
}));
|
|
|
|
function createEventBusStub() {
|
|
return {
|
|
forPlugin() {
|
|
return { emit: vi.fn(), subscribe: vi.fn() };
|
|
},
|
|
} as never;
|
|
}
|
|
|
|
// A well-formed W3C traceparent (the host mints it; the handler validates it).
|
|
const VALID_TRACEPARENT = "00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01";
|
|
|
|
function servicesFor() {
|
|
return buildHostServices({} as never, "plugin-record-id", "daytona", createEventBusStub());
|
|
}
|
|
|
|
function handlersFor(capabilities: readonly string[]) {
|
|
return createHostClientHandlers({
|
|
pluginId: "daytona",
|
|
capabilities: capabilities as never,
|
|
services: servicesFor(),
|
|
});
|
|
}
|
|
|
|
describe("plugin provider span host handler", () => {
|
|
beforeEach(() => {
|
|
mockRecordSpan.mockReset();
|
|
});
|
|
|
|
it("records a span with the clamped name and the allowlisted attributes", async () => {
|
|
const services = servicesFor();
|
|
await services.tracer.record(
|
|
{
|
|
name: "pack",
|
|
attributes: {
|
|
[A.provider]: "daytona",
|
|
[A.packWallMs]: 12,
|
|
},
|
|
},
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
|
|
expect(mockRecordSpan).toHaveBeenCalledTimes(1);
|
|
const call = mockRecordSpan.mock.calls[0]![0] as {
|
|
name: string;
|
|
parent: { traceId: string; spanId: string; traceFlags: number };
|
|
attributes: Record<string, unknown>;
|
|
};
|
|
expect(call.name).toBe("sandbox.daytona.pack");
|
|
expect(call.parent).toEqual({
|
|
traceId: "0af7651916cd43dd8448eb211c80319c",
|
|
spanId: "b7ad6b7169203331",
|
|
traceFlags: 1,
|
|
});
|
|
expect(call.attributes[A.provider]).toBe("daytona");
|
|
expect(call.attributes[A.packWallMs]).toBe(12);
|
|
});
|
|
|
|
it("drops every forbidden attribute before the span reaches the tracer", async () => {
|
|
const services = servicesFor();
|
|
await services.tracer.record(
|
|
{
|
|
name: "transfer",
|
|
attributes: {
|
|
[A.transferGuardCount]: 2,
|
|
// Forbidden fields that must never ride a span.
|
|
[A.execCommand]: "bash",
|
|
command: "rm -rf /",
|
|
args: "--force",
|
|
stdout: "secret output",
|
|
stderr: "secret error",
|
|
path: "/etc/passwd",
|
|
extra: "leak",
|
|
},
|
|
},
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
|
|
expect(mockRecordSpan).toHaveBeenCalledTimes(1);
|
|
const attributes = (mockRecordSpan.mock.calls[0]![0] as { attributes: Record<string, unknown> })
|
|
.attributes;
|
|
// Only the allowlisted key survives; every forbidden key is dropped.
|
|
expect(attributes).toEqual({ [A.transferGuardCount]: 2 });
|
|
for (const forbidden of [A.execCommand, "command", "args", "stdout", "stderr", "path", "extra"]) {
|
|
expect(attributes).not.toHaveProperty(forbidden);
|
|
}
|
|
});
|
|
|
|
it("drops a status message (it could carry standard-stream text)", async () => {
|
|
const services = servicesFor();
|
|
await services.tracer.record(
|
|
{ name: "transfer", status: { code: 2, message: "secret error text" } },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
const call = mockRecordSpan.mock.calls[0]![0] as { status?: { code: number; message?: string } };
|
|
expect(call.status).toEqual({ code: 2 });
|
|
expect(call.status).not.toHaveProperty("message");
|
|
});
|
|
|
|
it("clamps an unknown span name to sandbox.daytona.other", async () => {
|
|
const services = servicesFor();
|
|
await services.tracer.record(
|
|
{ name: "rm -rf / --no-preserve-root" },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
expect((mockRecordSpan.mock.calls[0]![0] as { name: string }).name).toBe(
|
|
"sandbox.daytona.other",
|
|
);
|
|
});
|
|
|
|
it("admits each per-round-trip span name to sandbox.daytona.<name>", async () => {
|
|
const services = servicesFor();
|
|
for (const name of [
|
|
"ensureDirectory",
|
|
"checkSymlinkEscape",
|
|
"promote",
|
|
"extractTarball",
|
|
"postUploadCommand",
|
|
]) {
|
|
await services.tracer.record(
|
|
{ name },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
}
|
|
const recorded = mockRecordSpan.mock.calls.map((c) => (c[0] as { name: string }).name);
|
|
expect(recorded).toEqual([
|
|
"sandbox.daytona.ensureDirectory",
|
|
"sandbox.daytona.checkSymlinkEscape",
|
|
"sandbox.daytona.promote",
|
|
"sandbox.daytona.extractTarball",
|
|
"sandbox.daytona.postUploadCommand",
|
|
]);
|
|
});
|
|
|
|
it("admits the session open and close span names", async () => {
|
|
const services = servicesFor();
|
|
for (const name of ["session.open", "session.close"]) {
|
|
await services.tracer.record(
|
|
{ name },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
}
|
|
const recorded = mockRecordSpan.mock.calls.map((c) => (c[0] as { name: string }).name);
|
|
expect(recorded).toEqual([
|
|
"sandbox.daytona.session.open",
|
|
"sandbox.daytona.session.close",
|
|
]);
|
|
});
|
|
|
|
it("forwards a valid start-time and end-time pair to the recorder", async () => {
|
|
const services = servicesFor();
|
|
const startTimeMs = Date.now() - 4500;
|
|
const endTimeMs = startTimeMs + 4500;
|
|
await services.tracer.record(
|
|
{ name: "ensureDirectory", startTimeMs, endTimeMs },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
const call = mockRecordSpan.mock.calls[0]![0] as {
|
|
startTimeMs?: number;
|
|
endTimeMs?: number;
|
|
};
|
|
expect(call.startTimeMs).toBe(startTimeMs);
|
|
expect(call.endTimeMs).toBe(endTimeMs);
|
|
});
|
|
|
|
it("accepts a pair whose end is a small skew ahead of the host clock", async () => {
|
|
const services = servicesFor();
|
|
// The worker clock leads the host clock by a few seconds. This small skew
|
|
// is within the allowed bound, so the host keeps the native width.
|
|
const startTimeMs = Date.now() + 5000;
|
|
const endTimeMs = startTimeMs + 1000;
|
|
await services.tracer.record(
|
|
{ name: "ensureDirectory", startTimeMs, endTimeMs },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
const call = mockRecordSpan.mock.calls[0]![0] as {
|
|
startTimeMs?: number;
|
|
endTimeMs?: number;
|
|
};
|
|
expect(call.startTimeMs).toBe(startTimeMs);
|
|
expect(call.endTimeMs).toBe(endTimeMs);
|
|
});
|
|
|
|
it("drops an invalid timestamp pair so the synchronous path runs", async () => {
|
|
const services = servicesFor();
|
|
const now = Date.now();
|
|
const invalidPairs: Array<{ startTimeMs?: unknown; endTimeMs?: unknown; why: string }> = [
|
|
{ startTimeMs: now, endTimeMs: now - 1000, why: "reversed order" },
|
|
{ startTimeMs: Number.NaN, endTimeMs: now, why: "non-finite start" },
|
|
{ startTimeMs: now, endTimeMs: Number.POSITIVE_INFINITY, why: "non-finite end" },
|
|
{ startTimeMs: now, endTimeMs: now + 11 * 60 * 1000, why: "over-ceiling duration" },
|
|
{ startTimeMs: now - 2 * 60 * 60 * 1000, endTimeMs: now - 2 * 60 * 60 * 1000 + 10, why: "over-age start" },
|
|
{ startTimeMs: now, endTimeMs: now + 2 * 60 * 1000, why: "end far in the future" },
|
|
{ startTimeMs: now + 5 * 60 * 1000, endTimeMs: now + 5 * 60 * 1000 + 10, why: "start and end in the future" },
|
|
];
|
|
for (const pair of invalidPairs) {
|
|
mockRecordSpan.mockReset();
|
|
await services.tracer.record(
|
|
{ name: "ensureDirectory", startTimeMs: pair.startTimeMs, endTimeMs: pair.endTimeMs } as never,
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
// The span still records (the synchronous path), but without a timestamp.
|
|
const call = mockRecordSpan.mock.calls[0]![0] as {
|
|
startTimeMs?: number;
|
|
endTimeMs?: number;
|
|
};
|
|
expect(call.startTimeMs, pair.why).toBeUndefined();
|
|
expect(call.endTimeMs, pair.why).toBeUndefined();
|
|
}
|
|
});
|
|
|
|
it("records the synchronous path when the timestamp pair is absent", async () => {
|
|
const services = servicesFor();
|
|
await services.tracer.record(
|
|
{ name: "pack" },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
const call = mockRecordSpan.mock.calls[0]![0] as {
|
|
startTimeMs?: number;
|
|
endTimeMs?: number;
|
|
};
|
|
expect(call.startTimeMs).toBeUndefined();
|
|
expect(call.endTimeMs).toBeUndefined();
|
|
});
|
|
|
|
it("rejects a malformed traceparent — no span is recorded", async () => {
|
|
const services = servicesFor();
|
|
for (const bad of [
|
|
undefined,
|
|
"not-a-traceparent",
|
|
"00-xyz-b7ad6b7169203331-01",
|
|
"00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331", // missing flags
|
|
"00-00000000000000000000000000000000-b7ad6b7169203331-01", // all-zero trace id
|
|
]) {
|
|
await services.tracer.record(
|
|
{ name: "pack" },
|
|
{ traceparent: bad } as WorkerHostCallContext,
|
|
);
|
|
}
|
|
expect(mockRecordSpan).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("rejects a span from a plugin that lacks the environment-driver capability", async () => {
|
|
const handlers = handlersFor([]);
|
|
await expect(
|
|
handlers["span.record"](
|
|
{ name: "pack" },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
),
|
|
).rejects.toThrow(/capabilit/i);
|
|
expect(mockRecordSpan).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("admits a span from a plugin that holds the environment-driver capability", async () => {
|
|
const handlers = handlersFor(["environment.drivers.register"]);
|
|
await handlers["span.record"](
|
|
{ name: "pack", attributes: { [A.provider]: "daytona" } },
|
|
{ traceparent: VALID_TRACEPARENT } as WorkerHostCallContext,
|
|
);
|
|
expect(mockRecordSpan).toHaveBeenCalledTimes(1);
|
|
});
|
|
});
|
|
|
|
describe("parseTraceparent", () => {
|
|
it("accepts a well-formed traceparent and returns the parts", () => {
|
|
expect(parseTraceparent(VALID_TRACEPARENT)).toEqual({
|
|
traceId: "0af7651916cd43dd8448eb211c80319c",
|
|
spanId: "b7ad6b7169203331",
|
|
traceFlags: 1,
|
|
});
|
|
});
|
|
|
|
it("rejects malformed, all-zero, and forbidden-version traceparents", () => {
|
|
expect(parseTraceparent(undefined)).toBeNull();
|
|
expect(parseTraceparent("garbage")).toBeNull();
|
|
expect(parseTraceparent("00-0af7651916cd43dd8448eb211c80319c-0000000000000000-01")).toBeNull();
|
|
expect(parseTraceparent("ff-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01")).toBeNull();
|
|
});
|
|
});
|
|
|
|
describe("clampProviderSpanAttributes", () => {
|
|
it("keeps only allowlisted keys and normalizes the provider family", () => {
|
|
expect(
|
|
clampProviderSpanAttributes({
|
|
[A.provider]: "some-operator-key",
|
|
[A.packWallMs]: 7,
|
|
[A.transferWallMs]: Number.NaN,
|
|
[A.execCommand]: "bash",
|
|
}),
|
|
).toEqual({
|
|
// An unknown provider key maps to `plugin`, never the raw key.
|
|
[A.provider]: "plugin",
|
|
[A.packWallMs]: 7,
|
|
// A non-finite number yields no attribute; `exec.command` is not allowed.
|
|
});
|
|
});
|
|
});
|