Files
OmniRoute/tests/integration/active-request-completion.test.ts
Diego Rodrigues de Sa e Souza 8169b97d84 Release v3.8.18 (#3482)
* chore(release): open v3.8.18 development cycle

* fix(catalog): stop Codex CLI model-catalog refresh from erroring (#3481)

Codex's model-catalog refresh (codex_models_manager) does
GET /v1/models?client_version=<v> and decodes a JSON object with a
TOP-LEVEL `models` array. OmniRoute answers in the OpenAI-standard
`{object,data}` shape, so codex fails with "missing field `models`"
and logs "failed to refresh available models" on every startup.

Detect codex clients via the `originator` / `user-agent` = `codex_*`
headers they send and add an EMPTY top-level `models: []` so the decode
succeeds. Non-codex OpenAI clients keep the byte-identical `{object,data}`
response.

The array is intentionally empty: codex replaces its built-in per-model
agent prompt (`base_instructions`, ~21k chars) with whatever a populated
entry carries for the selected model, so emitting our catalog would drop
the agent prompt to nothing and break codex's agent behaviour (verified
empirically against codex 0.137). An empty list keeps codex on its
built-in model info — same inference as before, minus the error.

Validated end-to-end with the real handler against codex 0.137:
"failed to refresh available models" → 0 occurrences, instructions
preserved (built-in Codex agent prompt, not empty).

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: ignore quality reports and local prompt artifacts

Add generated quality gate reports, metrics files, and local setup prompt
artifacts to .gitignore to prevent committing environment-specific or
temporary files.

* fix(provider): detect Responses API format when body has `input` but … (#3490)

Integrated into release/v3.8.18

* fix(sse): normalize numeric provider ids to strings (#3451)

Integrated into release/v3.8.18

* feat(browserPool): resolve Playwright proxy from proxy_registry DB (#3492)

Integrated into release/v3.8.18

* fix(theoldllm): generate X-Request-Token server-side, drop Playwright (#3491)

Integrated into release/v3.8.18

* feat(plugins): add lifecycle hooks and theme-manager plugin (#3473)

Integrated into release/v3.8.18

* fix(combo): parallel pre-screen + circuit-breaker fast-exit for priority combos (#3169)

Integrated into release/v3.8.18

* feat(ui): unifi active and finished requests into single view #1422 (#3401)

Integrated into release/v3.8.18

* docs(changelog): record #3401, #3473, #3492, #3490, #3451, #3491, #3169 under v3.8.18

* feat(docs): add doc accuracy gate + refresh AGENTS.md counts (#3510)

Integrated into release/v3.8.18

* fix(sse): drop empty-choices chunks without usage instead of injecting retry text (#3513)

PR #3422 ('allow OpenAI usage-only empty choices chunks') reintroduced the
assistant-content injection '[OmniRoute] Upstream returned an empty response.
Please retry.' for empty `choices: []` chunks that carry no valid usage. Clients
(Goose/opencode) feed that text back as a turn and spin in a retry loop -- the
exact regression #3400 had fixed by dropping the chunk.

Restore the drop behavior for the no-usage case while preserving #3422's
standards-compliant forwarding of usage-only `include_usage` final chunks.
Realign the mislabeled stream-utils test (it asserted the injection) and add a
dedicated regression guard.

Reported-by: @mochizzan
Refs: #3502, #3388, #3400, #3422

* fix(authz): fall back to URL token when Authorization isn't a usable Bearer (#3504)

Integrated into release/v3.8.18

* fix(playground): authenticate via session, test key policy by id (#3503)

Integrated into release/v3.8.18

* docs(changelog): record #3510, #3504, #3503 under v3.8.18

* fix: llama base url normalization (#3519)

* docs(changelog): reconcile v3.8.18 — add #3519, #3513, #3435-repair, gitignore chore (full commit↔changelog coverage)

* fix(opencode-plugin): bound regex quantifiers in normaliseFreeLabel (polynomial-ReDoS)

CodeQL js/polynomial-redos: unbounded \s* before an anchored \s*$ allowed
O(n²) backtracking on attacker-influenced display names. Bounded to {0,8}/{1,8}
(ample for any real label spacing). Plugin builds + 254 tests green.

* fix(types): restore clean typecheck:core for v3.8.18 release gate

- getPendingRequests() typed to real shape (was widened to object) → fixes
  unknown 'count' in the unified-requests view (#3401)
- streamChunks log payload cast to its declared type (callLogs.ts)
- preScreenTargets aligned to canonical IsModelAvailable signature (#3169),
  Promise.resolve-normalized so .catch never hits a bare boolean

All 5 gates green: lint(0 err) + typecheck:core + cycles + docs-all + unit + vitest(146).

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Andrey Borodulin <borodulin@gmail.com>
Co-authored-by: Dmitrii Safronov <zimniy@cyberbrain.cc>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: Felipe Almeman <4226997+zhiru@users.noreply.github.com>
2026-06-09 15:56:24 -03:00

154 lines
5.2 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
const API_KEY = process.env.OMNIROUTE_API_KEY;
const BASE_URL = process.env.OMNIROUTE_URL || "http://localhost:20128";
const MODEL = process.env.TEST_GEMINI_MODEL || "default";
const skip = !API_KEY ? "OMNIROUTE_API_KEY not set — skipping live test" : undefined;
// Simple SSE reader (compatible with streamed chat completions)
async function readSSEStream(response: Response, onChunk?: (chunk: string) => void) {
const reader = response.body!.getReader();
const decoder = new TextDecoder();
let buffer = "";
let fullContent = "";
let finishReason = "unknown";
let totalTokens = 0;
while (true) {
const { done, value } = await reader.read();
if (done) break;
buffer += decoder.decode(value, { stream: true });
const lines = buffer.split("\n");
buffer = lines.pop() || "";
for (const line of lines) {
if (!line.startsWith("data: ")) continue;
const data = line.slice(6).trim();
if (data === "[DONE]") continue;
try {
const parsed = JSON.parse(data) as Record<string, unknown>;
const choice = ((parsed?.choices ?? []) as Array<Record<string, unknown>>)[0];
if (choice) {
const delta = choice.delta as Record<string, unknown> | undefined;
if (delta?.content) {
let chunk = delta.content as string;
fullContent += chunk;
onChunk?.(chunk);
}
if (choice.finish_reason) finishReason = choice.finish_reason as string;
}
const usage = parsed.usage as Record<string, number> | undefined;
if (usage) {
totalTokens =
usage.total_tokens ?? (usage.prompt_tokens ?? 0) + (usage.completion_tokens ?? 0);
}
} catch {
// ignore malformed
}
}
}
return { fullContent, finishReason, totalTokens };
}
test("live request returns streamChunks", { skip }, async () => {
console.log("[TEST] BASE_URL=", BASE_URL, "OMNIROUTE_URL=", process.env.OMNIROUTE_URL, "API_KEY set=", !!API_KEY);
const messages = [
{ role: "system", content: "Execute the user prompt and provide a detailed explanation." },
{ role: "user", content: "Ackermann(4,3) step by step" },
];
const controller = new AbortController();
const timeout = setTimeout(() => controller.abort(), 60_000);
try {
const completionsResponse = await fetch(`${BASE_URL}/v1/chat/completions`, {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${API_KEY}`,
},
body: JSON.stringify({ model: MODEL, messages, stream: true, max_tokens: 512 }),
signal: controller.signal,
});
assert.equal(
completionsResponse.status,
200,
`expected 200 from chat/completions, got ${completionsResponse.status}`
);
const requestId = completionsResponse.headers.get("x-omniroute-request-id");
assert.ok(requestId, "expected x-omniroute-request-id header in response");
let streamFinished = false;
let streamPromise = readSSEStream(completionsResponse).finally(() => {
streamFinished = true;
});
const postPollStart = Date.now();
const postPollTimeout = 60_000;
let sawLogChunksWhileStreaming = false;
while (Date.now() - postPollStart < postPollTimeout) {
try {
const activeRequestResponse = await fetch(
`${BASE_URL}/api/logs/${encodeURIComponent(requestId!)}`,
{
headers: { Authorization: `Bearer ${API_KEY}` },
cache: "no-store",
}
);
if (activeRequestResponse.ok) {
let activeRequest = await activeRequestResponse.json();
if (activeRequest.active &&
Array.isArray(activeRequest.pipelinePayloads.streamChunks.provider) &&
activeRequest.pipelinePayloads.streamChunks.provider.length > 0
) {
console.log("Stream chunks:", activeRequest.pipelinePayloads.streamChunks.provider);
sawLogChunksWhileStreaming = true;
break;
}
}
} catch (e) {
// ignore
}
if (streamFinished) {
break;
}
await new Promise((r) => setTimeout(r, 250));
}
assert.ok(sawLogChunksWhileStreaming, "streamChunks never appeared while request was active");
await streamPromise;
const logDetailResponse = await fetch(
`${BASE_URL}/api/logs/${encodeURIComponent(requestId!)}`,
{
headers: { Authorization: `Bearer ${API_KEY}` },
cache: "no-store",
}
);
assert.ok(logDetailResponse.ok, `failed to fetch log detail: ${logDetailResponse.status}`);
let finishedRequest = await logDetailResponse.json();
assert.equal(finishedRequest.id, requestId, "log detail id should match request id");
assert.equal(finishedRequest.active, false, "request should be marked as inactive after completion");
assert.ok(Array.isArray(finishedRequest.pipelinePayloads.streamChunks.provider) );
assert.ok(Array.isArray(finishedRequest.pipelinePayloads.streamChunks.client));
assert.ok(finishedRequest.pipelinePayloads.streamChunks.provider.length > 0);
assert.ok(finishedRequest.pipelinePayloads.streamChunks.client.length > 0);
} finally {
clearTimeout(timeout);
}
});