426e9eeabd
Voice Workbench / headless workbench (mocked backends) (push) Has been cancelled
Voice Workbench / real acoustic lane (nightly, provisioned only) (push) Has been cancelled
ci / test (push) Has been cancelled
ci / lint-and-format (push) Has been cancelled
ci / build (push) Has been cancelled
ci / dev-startup (push) Has been cancelled
gitleaks / gitleaks (push) Has been cancelled
Markdown Links / Relative Markdown Links (push) Has been cancelled
Quality (Extended) / Homepage Build (PR smoke) (push) Has been cancelled
Quality (Extended) / Comment-only diff guard (push) Has been cancelled
Quality (Extended) / Format + Type Safety Ratchet (push) Has been cancelled
Quality (Extended) / Develop Gate (secret scan + UI determinism) (push) Has been cancelled
Quality (Extended) / Develop Gate (lint) (push) Has been cancelled
Chat shell gestures / Chat shell gesture + parity e2e (push) Has been cancelled
Cloud Gateway Discord / Test (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx @biomejs/biome check packages/lifeops-bench/src, benchmark-lint) (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx vitest run --config packages/lifeops-bench/vitest.config.ts --root packages/lifeops-bench --passWithNoTests, benchmark-tests) (push) Has been cancelled
Build Agent Image / build-and-push (push) Has been cancelled
Dev Smoke / bun run dev onboarding chat (push) Has been cancelled
Dev Smoke / Vite HMR dependency-level smoke (push) Has been cancelled
Electrobun Submodule Guard / electrobun gitlink is fetchable (push) Has been cancelled
Publish @elizaos/example-code / check_npm (push) Has been cancelled
Publish @elizaos/example-code / publish_npm (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / verify_version (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / publish_npm (push) Has been cancelled
Sandbox Live Smoke / Sandbox live smoke (push) Has been cancelled
Snap Build & Test / Build Snap (amd64) (push) Has been cancelled
Snap Build & Test / Build Snap (arm64) (push) Has been cancelled
Test Packaging / elizaos CLI global-install smoke (node + bun) (push) Has been cancelled
Cloud Gateway Webhook / Test (push) Has been cancelled
Cloud Tests / lint-and-types (push) Has been cancelled
Cloud Tests / unit-tests (push) Has been cancelled
Cloud Tests / integration-tests (push) Has been cancelled
Cloud Tests / e2e-tests (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Deploy Apps Worker (Product 2) / Determine environment (push) Has been cancelled
Deploy Apps Worker (Product 2) / Deploy apps worker to apps-control host (${{ needs.determine-env.outputs.environment }}) (push) Has been cancelled
Deploy Eliza Provisioning Worker / Determine environment (push) Has been cancelled
Deploy Eliza Provisioning Worker / Deploy worker to Hetzner host (${{ needs.determine-env.outputs.environment }} @ ${{ needs.determine-env.outputs.deployment_sha }}) (push) Has been cancelled
Dev Smoke / Classify changed paths (push) Has been cancelled
supply-chain / sbom (push) Has been cancelled
supply-chain / vulnerability-scan (push) Has been cancelled
Build, Push & Deploy to Phala Cloud / build-and-push (push) Has been cancelled
Test Packaging / Validate Packaging Configs (push) Has been cancelled
Test Packaging / Build & Test PyPI Package (push) Has been cancelled
Test Packaging / PyPI on Python ${{ matrix.python }} (push) Has been cancelled
Test Packaging / Pack & Test JS Tarballs (push) Has been cancelled
UI Fixture E2E / ui-fixture-e2e (push) Has been cancelled
UI Fixture E2E / fixture-e2e (push) Has been cancelled
UI Story Gate / story-gate (push) Has been cancelled
vault-ci / test (macos-latest) (push) Has been cancelled
vault-ci / test (ubuntu-latest) (push) Has been cancelled
vault-ci / test (windows-latest) (push) Has been cancelled
vault-ci / app-core wiring tests (push) Has been cancelled
verify-patches / verify patches/CHECKSUMS.sha256 (push) Has been cancelled
Voice Benchmark Smoke / voice-emotion fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voiceagentbench fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench-quality unit smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench TypeScript unit (no audio) (push) Has been cancelled
Voice Benchmark Smoke / voice bench smoke summary (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/app-core test bun run --cwd packages/elizaos test bun run --cwd packages/cloud/shared test], app-and-cli) (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/scenario-runner test bun run --cwd packages/vault test bun run --cwd packages/security test bun run --cwd plugins/plugin-coding-tools test], framework-packages) (push) Has been cancelled
Windows CI / windows ([bun run --cwd plugins/plugin-elizacloud test bun run --cwd plugins/plugin-discord test bun run --cwd plugins/plugin-anthropic test bun run --cwd plugins/plugin-openai test bun run --cwd plugins/plugin-app-control test bun run --cwd plugins/pl… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run build --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/agent --concurrency=4 node packages/scripts/run-bash-linux-only.mjs scripts/verify-riscv64-buildpaths.sh node packages/scripts/run… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run typecheck --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/cloud-shared --concurrency=4 bun run --cwd packages/core test bun run --cwd packages/shared test], core-runtime, 75) (push) Has been cancelled
178 lines
6.0 KiB
TypeScript
178 lines
6.0 KiB
TypeScript
#!/usr/bin/env bun
|
|
/**
|
|
* One real chat turn against the deployed E2E agent, through the production
|
|
* message path: the cloud Worker's bridge route (`POST
|
|
* /api/v1/eliza/agents/{agentId}/bridge`, JSON-RPC `message.send`) forwards to
|
|
* the sandbox bridge, which reaches the agent runtime on the Hetzner box over
|
|
* the tailnet. The `status.get` healthcheck alone lets "agent provisioned but
|
|
* chat dead-ends" regressions (#15347) pass the nightly — this step closes
|
|
* that gap by requiring an actual assistant reply. Exit 0 = the agent replied.
|
|
*
|
|
* The runtime answers HTTP 200 with canned text (`failureKind` set) when its
|
|
* model path is dead, and the bridge fabricates text (`fallback: true`) when
|
|
* the runtime produced no reply — exactly the dead-ends this step exists to
|
|
* catch (#15616). classifyBridgeReply rejects both, rejects known canned
|
|
* strings from pre-`failureKind` runtimes, and requires the per-run proof
|
|
* token in the reply — so a pass means a live model round-tripped THIS
|
|
* message. Attempts retry until HETZNER_E2E_CHAT_TIMEOUT_MS (default 240s) to
|
|
* absorb a cold model path and the occasional paraphrase that drops the token.
|
|
* The success log names which bridge rung (conversation REST, OpenAI-compat,
|
|
* central-channel, …) replied, so a conversation-route-only regression cannot
|
|
* hide behind a fallback rung.
|
|
*/
|
|
|
|
import { randomBytes } from "node:crypto";
|
|
import { classifyBridgeReply } from "../bridge-reply-verdict";
|
|
import { readState } from "./state-file";
|
|
|
|
const DEFAULT_BASE_URL = "https://api-staging.elizacloud.ai";
|
|
const DEFAULT_TIMEOUT_MS = 240_000;
|
|
const RETRY_DELAY_MS = 5_000;
|
|
// Per-attempt cap: the Worker's bridge tries up to four inner transports at
|
|
// 60-120s each, so a single POST can legitimately take minutes.
|
|
const ATTEMPT_TIMEOUT_MS = 130_000;
|
|
|
|
function requireEnv(name: string): string {
|
|
const value = process.env[name];
|
|
if (!value) {
|
|
console.error(`[hetzner-e2e-chat] missing env: ${name}`);
|
|
process.exit(1);
|
|
}
|
|
return value;
|
|
}
|
|
|
|
function sleep(ms: number): Promise<void> {
|
|
return new Promise((resolve) => setTimeout(resolve, ms));
|
|
}
|
|
|
|
interface BridgeChatEnvelope {
|
|
result?: Record<string, unknown>;
|
|
error?: { code?: number; message?: string };
|
|
}
|
|
|
|
async function sendChatTurn(
|
|
baseUrl: string,
|
|
apiKey: string,
|
|
agentId: string,
|
|
prompt: string,
|
|
roomId: string,
|
|
token: string,
|
|
): Promise<{ reply: string; transport: string }> {
|
|
const response = await fetch(
|
|
`${baseUrl}/api/v1/eliza/agents/${agentId}/bridge`,
|
|
{
|
|
method: "POST",
|
|
headers: {
|
|
authorization: `Bearer ${apiKey}`,
|
|
"content-type": "application/json",
|
|
accept: "application/json",
|
|
"user-agent": "hetzner-e2e/1.0",
|
|
},
|
|
body: JSON.stringify({
|
|
jsonrpc: "2.0",
|
|
id: `chat-${Date.now()}`,
|
|
method: "message.send",
|
|
params: {
|
|
text: prompt,
|
|
roomId,
|
|
userId: `${roomId}-user`,
|
|
source: "hetzner-e2e",
|
|
mode: "simple",
|
|
},
|
|
}),
|
|
signal: AbortSignal.timeout(ATTEMPT_TIMEOUT_MS),
|
|
},
|
|
);
|
|
const text = await response.text();
|
|
if (!response.ok) {
|
|
throw new Error(`Chat HTTP ${response.status}: ${text.slice(0, 300)}`);
|
|
}
|
|
const body = JSON.parse(text) as BridgeChatEnvelope;
|
|
if (body.error) {
|
|
throw new Error(
|
|
`Chat JSON-RPC error: ${JSON.stringify(body.error).slice(0, 300)}`,
|
|
);
|
|
}
|
|
const verdict = classifyBridgeReply(body.result, token);
|
|
if (!verdict.ok) {
|
|
throw new Error(
|
|
`${verdict.reason} (transport: ${verdict.transport})` +
|
|
(verdict.reply ? ` — reply: ${verdict.reply.slice(0, 200)}` : ""),
|
|
);
|
|
}
|
|
return { reply: verdict.reply, transport: verdict.transport };
|
|
}
|
|
|
|
async function main(): Promise<void> {
|
|
const apiKey = requireEnv("CLOUD_E2E_API_KEY");
|
|
const baseUrl = (
|
|
process.env.CLOUD_SMOKE_BASE_URL ?? DEFAULT_BASE_URL
|
|
).replace(/\/+$/, "");
|
|
const timeoutMs = Number.parseInt(
|
|
process.env.HETZNER_E2E_CHAT_TIMEOUT_MS ?? String(DEFAULT_TIMEOUT_MS),
|
|
10,
|
|
);
|
|
|
|
const state = readState();
|
|
const agentId = state.agent_id;
|
|
if (!agentId) {
|
|
throw new Error(
|
|
"state file missing agent_id; deploy-agent step must run first",
|
|
);
|
|
}
|
|
|
|
const runId =
|
|
state.run_id ??
|
|
`${Date.now().toString(36)}${randomBytes(3).toString("hex")}`;
|
|
const roomId = `hetzner-e2e-chat-${runId}`;
|
|
// A per-run token proves the reply is a live model round-trip of THIS
|
|
// message, not a canned string. Phrased without quotes so it cannot match
|
|
// the bridge's fallback-text extraction patterns.
|
|
const token = `hetzner-pong-${runId}`;
|
|
const prompt =
|
|
`You are part of an automated end-to-end test. ` +
|
|
`Reply with one short sentence that contains the token ${token}.`;
|
|
|
|
console.log(
|
|
`[hetzner-e2e-chat] sending chat turn to agent ${agentId} (room ${roomId}, timeout ${timeoutMs}ms)`,
|
|
);
|
|
|
|
const deadline = Date.now() + timeoutMs;
|
|
let attempt = 0;
|
|
let lastFailure = "no attempt completed";
|
|
while (Date.now() < deadline) {
|
|
attempt += 1;
|
|
try {
|
|
const { reply, transport } = await sendChatTurn(
|
|
baseUrl,
|
|
apiKey,
|
|
agentId,
|
|
prompt,
|
|
roomId,
|
|
token,
|
|
);
|
|
console.log(
|
|
`[hetzner-e2e-chat] agent replied on attempt ${attempt} ` +
|
|
`(${reply.length} chars, transport: ${transport}, token echoed): ${reply.slice(0, 300)}`,
|
|
);
|
|
return;
|
|
} catch (error) {
|
|
// error-policy:J1 retry boundary — each failed attempt is logged and the
|
|
// loop fails loudly at the deadline with the last observed failure.
|
|
lastFailure = error instanceof Error ? error.message : String(error);
|
|
console.log(
|
|
`[hetzner-e2e-chat] attempt ${attempt} failed: ${lastFailure}`,
|
|
);
|
|
}
|
|
if (Date.now() + RETRY_DELAY_MS >= deadline) break;
|
|
await sleep(RETRY_DELAY_MS);
|
|
}
|
|
|
|
throw new Error(
|
|
`Agent ${agentId} never produced a real chat reply echoing ${token} within ${timeoutMs}ms ` +
|
|
`(${attempt} attempt${attempt === 1 ? "" : "s"}). Last failure: ${lastFailure}`,
|
|
);
|
|
}
|
|
|
|
await main();
|