feat: add SSE event feed for llama-swap api/events

This commit is contained in:
2026-08-14 10:43:03 -06:00
parent b54eeeadc4
commit 79917cd054
2 changed files with 171 additions and 0 deletions
+105
View File
@@ -0,0 +1,105 @@
import { type LlamaSwapConfig } from "./util";
import { parseSse, type SseMessage } from "./sse";
import { type FeedEvent, type InflightRequest, type ModelState } from "./inflight-tracker";
export function decodeEvent(msg: SseMessage): FeedEvent | null {
try {
const outer = JSON.parse(msg.data) as { type?: string; data?: string };
if (!outer.data) return null;
const inner = JSON.parse(outer.data) as Record<string, unknown>;
if (outer.type === "inflight") {
const requests: InflightRequest[] =
(inner.requests as InflightRequest[]) ?? (inner.request ? [inner.request as InflightRequest] : []);
return {
type: "inflight",
operation: inner.operation as "snapshot" | "add" | "remove",
requests,
};
}
if (outer.type === "modelStatus") {
return { type: "modelStatus", models: inner as unknown as ModelState[] };
}
return null;
} catch {
return null;
}
}
const MAX_RETRY_MS = 30000;
const INITIAL_RETRY_MS = 1000;
export class EventFeed {
private controller?: AbortController;
private closed = false;
private retryMs = INITIAL_RETRY_MS;
private statusHandler?: (connected: boolean) => void;
constructor(
private cfg: LlamaSwapConfig,
private onEvent: (ev: FeedEvent) => void,
) {}
setStatusHandler(fn: (connected: boolean) => void): void {
this.statusHandler = fn;
}
start(): void {
void this.connect();
}
stop(): void {
this.closed = true;
this.controller?.abort();
}
private async connect(): Promise<void> {
while (!this.closed) {
this.controller = new AbortController();
try {
const headers: Record<string, string> = { Accept: "text/event-stream" };
if (this.cfg.apiKey) headers["Authorization"] = `Bearer ${this.cfg.apiKey}`;
const res = await fetch(`${this.cfg.baseUrl}/api/events`, {
headers,
signal: this.controller.signal,
});
if (!res.ok || !res.body) throw new Error(`events HTTP ${res.status}`);
this.statusHandler?.(true);
this.retryMs = INITIAL_RETRY_MS;
await this.readStream(res.body.getReader());
} catch {
if (this.closed) return;
}
this.statusHandler?.(false);
if (this.closed) return;
await sleep(this.retryMs);
this.retryMs = Math.min(this.retryMs * 2, MAX_RETRY_MS);
}
}
private async readStream(reader: ReadableStreamDefaultReader<Uint8Array>): Promise<void> {
const decoder = new TextDecoder();
let buffer = "";
try {
while (!this.closed) {
const { done, value } = await reader.read();
if (done) break;
buffer += decoder.decode(value, { stream: true });
const { messages, rest } = parseSse(buffer);
buffer = rest;
for (const msg of messages) {
const ev = decodeEvent(msg);
if (ev) this.onEvent(ev);
}
}
} finally {
reader.releaseLock();
}
}
}
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
+66
View File
@@ -0,0 +1,66 @@
import assert from "node:assert/strict";
import { test } from "node:test";
import { decodeEvent } from "../src/lib/event-feed";
import type { SseMessage } from "../src/lib/sse";
test("decodeEvent parses an inflight snapshot", () => {
const msg: SseMessage = {
event: "message",
data: JSON.stringify({
type: "inflight",
data: JSON.stringify({
operation: "snapshot",
requests: [{ id: "14", model: "Qwen3.8-27B-NVFP4", req_path: "/v1/chat/completions", elapsed_ms: 165510 }],
}),
}),
};
const ev = decodeEvent(msg);
assert.ok(ev);
assert.equal(ev.type, "inflight");
if (ev.type === "inflight") {
assert.equal(ev.operation, "snapshot");
assert.equal(ev.requests.length, 1);
assert.equal(ev.requests[0].model, "Qwen3.8-27B-NVFP4");
assert.equal(ev.requests[0].elapsed_ms, 165510);
}
});
test("decodeEvent parses an inflight add with a singular request field", () => {
const msg: SseMessage = {
event: "message",
data: JSON.stringify({
type: "inflight",
data: JSON.stringify({ operation: "add", request: { id: "9", model: "A" } }),
}),
};
const ev = decodeEvent(msg);
assert.ok(ev && ev.type === "inflight");
if (ev && ev.type === "inflight") {
assert.equal(ev.operation, "add");
assert.equal(ev.requests[0].model, "A");
}
});
test("decodeEvent parses modelStatus", () => {
const msg: SseMessage = {
event: "message",
data: JSON.stringify({
type: "modelStatus",
data: JSON.stringify([
{ id: "DeepSeek-V4-Flash-0731", state: "ready" },
{ id: "Qwen3.8-27B-NVFP4", state: "stopped" },
]),
}),
};
const ev = decodeEvent(msg);
assert.ok(ev && ev.type === "modelStatus");
if (ev && ev.type === "modelStatus") {
assert.equal(ev.models.length, 2);
assert.equal(ev.models[0].state, "ready");
}
});
test("decodeEvent returns null for unrelated or malformed events", () => {
assert.equal(decodeEvent({ event: "message", data: JSON.stringify({ type: "logData", data: "{}" }) }), null);
assert.equal(decodeEvent({ event: "message", data: "not json" }), null);
});