mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 04:12:10 +03:00
* 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>
127 lines
5.1 KiB
TypeScript
127 lines
5.1 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import fs from "node:fs";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
|
|
// ── 1. FETCH_BODY_TIMEOUT_MS constant export validation ──────────────────
|
|
|
|
test("FETCH_BODY_TIMEOUT_MS is exported from open-sse/config/constants and is a positive number", async () => {
|
|
const constants = await import("../../open-sse/config/constants.ts");
|
|
assert.ok("FETCH_BODY_TIMEOUT_MS" in constants, "FETCH_BODY_TIMEOUT_MS should be exported");
|
|
assert.equal(typeof constants.FETCH_BODY_TIMEOUT_MS, "number");
|
|
assert.ok(constants.FETCH_BODY_TIMEOUT_MS > 0, "should be a positive number");
|
|
});
|
|
|
|
test("FETCH_BODY_TIMEOUT_MS defaults to FETCH_TIMEOUT_MS when no env override", async () => {
|
|
const constants = await import("../../open-sse/config/constants.ts");
|
|
assert.equal(
|
|
constants.FETCH_BODY_TIMEOUT_MS,
|
|
constants.FETCH_TIMEOUT_MS,
|
|
"FETCH_BODY_TIMEOUT_MS should default to FETCH_TIMEOUT_MS"
|
|
);
|
|
});
|
|
|
|
// ── 2. BodyTimeoutError classification in chatCore ──────────────────────
|
|
|
|
test("chatCore error classification maps BodyTimeoutError to 504 GATEWAY_TIMEOUT", () => {
|
|
// Read the source to verify the error classification logic includes BodyTimeoutError
|
|
const content = fs.readFileSync("open-sse/handlers/chatCore.ts", "utf8");
|
|
|
|
// The error classification block should include BodyTimeoutError alongside TimeoutError
|
|
const classificationPattern =
|
|
/error\.name === ["']TimeoutError["']\s*\|\|\s*error\.name === ["']BodyTimeoutError["']/;
|
|
assert.ok(
|
|
classificationPattern.test(content),
|
|
"chatCore should classify BodyTimeoutError as GATEWAY_TIMEOUT (504)"
|
|
);
|
|
});
|
|
|
|
test("chatCore catch block decrements pending requests for all error types", () => {
|
|
const content = fs.readFileSync("open-sse/handlers/chatCore.ts", "utf8");
|
|
|
|
// The catch block should call trackPendingRequest with false before error classification
|
|
const catchBlockPattern = /catch\s*\(error\)\s*\{[^}]*trackPendingRequest\([^)]*,\s*false\)/;
|
|
assert.ok(
|
|
catchBlockPattern.test(content),
|
|
"chatCore catch block should decrement pending requests"
|
|
);
|
|
});
|
|
|
|
test("withBodyTimeout error name is BodyTimeoutError", async () => {
|
|
const { withBodyTimeout } = await import("../../open-sse/utils/stream.ts");
|
|
|
|
const neverResolves = new Promise<string>(() => {});
|
|
try {
|
|
await withBodyTimeout(neverResolves, 20);
|
|
assert.fail("should have thrown");
|
|
} catch (error) {
|
|
assert.ok(error instanceof Error);
|
|
assert.equal(error.name, "BodyTimeoutError");
|
|
}
|
|
});
|
|
|
|
// ── 3. BodyTimeoutError triggers correct pending request decrement ──────
|
|
|
|
test("BodyTimeoutError from withBodyTimeout does not leave timer leaks", async () => {
|
|
const { withBodyTimeout } = await import("../../open-sse/utils/stream.ts");
|
|
|
|
// Fire multiple short timeouts to ensure no timer accumulation
|
|
const promises = Array.from({ length: 10 }, () =>
|
|
withBodyTimeout(new Promise(() => {}), 10).catch(() => {})
|
|
);
|
|
await Promise.all(promises);
|
|
|
|
// Wait a bit to ensure all timers are cleaned up
|
|
await new Promise((resolve) => setTimeout(resolve, 100));
|
|
|
|
// If timers leaked, the process would hang or show warnings — this test
|
|
// passing confirms proper cleanup under concurrent timeout scenarios.
|
|
assert.ok(true, "all timers cleaned up successfully");
|
|
});
|
|
|
|
// ── 4. clearPendingRequests + trackPendingRequest integration ────────────
|
|
|
|
test("trackPendingRequest followed by clearPendingRequests zeroes all counts", async () => {
|
|
const usageHistory = await import("../../src/lib/usage/usageHistory.ts");
|
|
|
|
usageHistory.trackPendingRequest("m1", "p1", "c1", true);
|
|
usageHistory.trackPendingRequest("m1", "p1", "c1", true);
|
|
usageHistory.trackPendingRequest("m2", "p2", "c2", true);
|
|
|
|
const before = usageHistory.getPendingRequests();
|
|
assert.equal(before.byModel["m1 (p1)"], 2);
|
|
assert.equal(before.byModel["m2 (p2)"], 1);
|
|
|
|
usageHistory.clearPendingRequests();
|
|
|
|
const after = usageHistory.getPendingRequests();
|
|
assert.equal(Object.keys(after.byModel).length, 0);
|
|
assert.equal(Object.keys(after.byAccount).length, 0);
|
|
assert.equal(Object.keys(after.details).length, 0);
|
|
});
|
|
|
|
test("clearPendingRequests allows subsequent tracking to work correctly", async () => {
|
|
const usageHistory = await import("../../src/lib/usage/usageHistory.ts");
|
|
|
|
usageHistory.trackPendingRequest("m1", "p1", "c1", true);
|
|
usageHistory.clearPendingRequests();
|
|
|
|
// After clearing, tracking should increment from 0
|
|
usageHistory.trackPendingRequest("m3", "p3", "c3", true);
|
|
usageHistory.trackPendingRequest("m3", "p3", "c3", true);
|
|
|
|
const pending = usageHistory.getPendingRequests();
|
|
assert.equal(pending.byModel["m3 (p3)"], 2);
|
|
assert.ok(pending.details["c3"]);
|
|
|
|
// Decrement should also work
|
|
usageHistory.trackPendingRequest("m3", "p3", "c3", false);
|
|
assert.equal(pending.byModel["m3 (p3)"], 1);
|
|
|
|
// Final decrement should clear details
|
|
usageHistory.trackPendingRequest("m3", "p3", "c3", false);
|
|
assert.equal(pending.byModel["m3 (p3)"], 0);
|
|
assert.equal(pending.details["c3"], undefined);
|
|
});
|