mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
* chore(release): open v3.8.14 development cycle Version bump 3.8.13 -> 3.8.14 (root + electron + open-sse + openapi + lockfiles). Seed the v3.8.14 changelog with the four post-tag hotfixes that shipped to Docker/Electron in v3.8.13 but missed the immutable npm 3.8.13 (#3336 SSRF / CodeQL #323, #3334/#3335/#3339 Electron packaging). i18n CHANGELOG mirrors get the in-progress placeholder section. * feat: add per-provider custom headers support for OpenAI/Anthropic-compatible nodes (#3338) Integrated into release/v3.8.14 * fix: Kiro Builder ID token import fails with Bad credentials (#3333) Integrated into release/v3.8.14 — adds Builder ID cached-creds + OIDC refresh path for Kiro token import, with regression tests (#3333). * Improve code quality: auto-pr/docstrings-1780792063 (#3337) Integrated into release/v3.8.14 — docstring for context analytics route re-export. * fix(catalog): remove minimaxai/minimax-m3 from NVIDIA NIM tier (404 upstream) (#3329) (#3341) NVIDIA NIM does not host minimaxai/minimax-m3 — every request returns 404 page not found, while sibling minimaxai/minimax-m2.7 on the same provider works. Advertising a model that 404s is a catalog bug; remove it from the nvidia tier (it remains on the tiers that actually serve MiniMax M3). Re-add only once NVIDIA serves it. Co-authored-by: mikmaneggahommie <mikmaneggahommie@users.noreply.github.com> * fix(cli): write OpenCode config to ~/.config on all platforms incl. Windows (#3330) (#3343) resolveOpencodeConfigDir used %APPDATA% on Windows, but OpenCode reads its config from XDG ~/.config/opencode/ on every platform (on Windows: %USERPROFILE%\.config\opencode\, NOT %APPDATA%). So a Windows user who configured OpenCode via the dashboard had the file written where OpenCode never looks — it silently had no effect. Use the XDG path (XDG_CONFIG_HOME || ~/.config) unconditionally. Update the UI note + route JSDoc, and flip the three tests that encoded the old %APPDATA% behavior (t40 per-platform + card-note, cli-runtime-extended getCliConfigPaths). Co-authored-by: abdulkadirozyurt <abdulkadirozyurt@users.noreply.github.com> * fix(proxy): make auto-selection fallback opt-in (#3332) (#3344) selectWorkingProxyFallback (Step 11 of resolveProxyForConnection) listed ALL registry proxies, ignoring assignments and per-connection proxy_enabled, and returned the first working one with level:'autoSelect'. So a single proxy added to the registry silently became a global fallback for every connection's traffic. Gate it behind a new PROXY_AUTO_SELECT_ENABLED feature flag (default off): the fallback now no-ops unless the operator opts in. No registry proxy becomes a silent global default anymore. Co-authored-by: hertznsk <hertznsk@users.noreply.github.com> * fix(sse): treat MiniMax M3 as multimodal so vision isn't stripped (#3328) (#3342) MiniMax M3 via the opencode provider (oc/minimax-m3-free) appeared blind: image inputs didn't reach the model, while the same model in Cline could see them. Verified empirically that MiniMax M3 on the opencode upstream IS multimodal -- a base64 image is described correctly (it returns 403 only for remote image URLs, which it doesn't accept). Root cause: OmniRoute treated MiniMax M3 as a non-vision model in two places, so when compression was active the image was replaced with a text placeholder before dispatch: - compression's modelSupportsVision() heuristic (lite.ts) only matched gpt-4/4o/claude-3/gemini/vision -- minimax was absent -> replaceImageUrls stripped the image. - the opencode minimax-m3-free catalog entry lacked supportsVision, so the combo vision-capability gate could also exclude/mishandle it. Add 'minimax-m3' to the vision heuristic and supportsVision: true to the opencode minimax-m3-free entry. TDD: a failing-then-passing test in compression/lite.test.ts proves replaceImageUrls now keeps images for minimax-m3 ids, plus a registry assertion mirroring the #2822 qwen test. Reported-by: @mikmaneggahommie * docs(i18n): translate 25 core documentation files to Indonesian (#3348) Integrated into release/v3.8.14 — Indonesian i18n docs. * fix(review): resolve /review-reviews battery findings (LEDGER-1..11) on v3.8.14 (#3350) Integrated into release/v3.8.14 — /review-reviews battery hardening (LEDGER-1..11) for #3338 custom-headers + #3333 kiro, plus cycle-test drift fixes (#3329/#3330/#3332). * fix(provider-proxy): honor per-account proxy toggles (#3349) Integrated into release/v3.8.14 — honor per-account proxy toggles + auto-fallback opt-in via PROXY_AUTO_SELECT_ENABLED. * fix(dashboard): remove duplicate Distribute Proxies button on provider page (#3352) * fix(providers): reduce proxy label noise (#3346) Integrated into release/v3.8.14 — reduce proxy label noise + a11y (aria-label/sr-only). * fix(duckduckgo): restore bare Response contract and rebase onto release/v3.8.14 (#3323) Integrated into release/v3.8.14 — browser-backed cookie providers (duckduckgo/claude-web) with restored executor contract + unit tests. * fix(noauth): expose only usable model aliases (#3345) Integrated into release/v3.8.14 — noauth usable-alias filtering + registry alias plumbing (veo-free). * fix(dashboard): stop infinite config-load loop on Hermes Agent detail page (#3353) * fix(electron): tree-kill the server on exit/update to release the omniroute.exe lock (#3347) (#3354) * chore(release): finalize v3.8.14 changelog + clear release-gate drift - CHANGELOG: finalize the v3.8.14 section (date, full New Features/Bug Fixes/ Maintenance coverage of all 16 cycle commits, Contributors hall of 12). - docs: document OMNIROUTE_BROWSER_POOL + WEB_COOKIE_USE_BROWSER (#3323) in .env.example + ENVIRONMENT.md; regenerate the id/llm.txt strict mirror (#3348 had translated it; llm.txt mirrors must match root). - test(proxy-fetch): #3323 made tlsClient.available a computed getter — stub it via Object.defineProperty instead of assignment (5 tests were red on the base). * fix(translator): coerce Gemini functionDeclaration parameters to an OBJECT schema (#3357) (#3360) * fix(gemini): resolve truncation/suppression of false positive textual tool call markers in backticks (#3358) Integrated into release/v3.8.14 — Gemini/Antigravity textual tool-call marker normalization (no false-positive suppression + split-chunk buffering). * docs(changelog): add #3358 Gemini textual tool-call normalization to v3.8.14 * fix(dashboard): surface real analytics error instead of generic placeholder (#3356) (#3361) The Analytics page discarded the server's error body on a non-OK response and rendered a generic "An error occurred", so users (and maintainers) could not see why /api/usage/analytics 500'd after an upgrade. Now the route returns the real reason via buildErrorBody (sanitized, Hard Rule #12) and the page surfaces it via a new readFetchErrorMessage helper that handles both the OpenAI-style and legacy error shapes. Reported-by: @superti4r --------- Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com> Co-authored-by: Someres <168349709+quanturbo@users.noreply.github.com> Co-authored-by: Dong Mengzhe <154944819+Lang-Qiu@users.noreply.github.com> Co-authored-by: mikmaneggahommie <mikmaneggahommie@users.noreply.github.com> Co-authored-by: abdulkadirozyurt <abdulkadirozyurt@users.noreply.github.com> Co-authored-by: hertznsk <hertznsk@users.noreply.github.com> Co-authored-by: Krisna Santosa <54174372+KrisnaSantosa15@users.noreply.github.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Wilson <pedbookmed@gmail.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Ardem2025 <ardemb22@gmail.com>
251 lines
8.0 KiB
TypeScript
251 lines
8.0 KiB
TypeScript
import { describe, it } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import {
|
|
applyLiteCompression,
|
|
collapseWhitespace,
|
|
dedupSystemPrompt,
|
|
compressToolResults,
|
|
removeRedundantContent,
|
|
replaceImageUrls,
|
|
} from "../../../open-sse/services/compression/lite.ts";
|
|
import { applyCompression } from "../../../open-sse/services/compression/strategySelector.ts";
|
|
|
|
describe("collapseWhitespace", () => {
|
|
it("collapses 3+ newlines to 2", () => {
|
|
const body = { messages: [{ role: "user", content: "hello\n\n\n\nworld" }] };
|
|
const result = collapseWhitespace(body);
|
|
assert.equal(result.applied, true);
|
|
assert.equal(result.body.messages![0].content as string, "hello\n\nworld");
|
|
});
|
|
|
|
it("does not modify already-normal whitespace", () => {
|
|
const body = { messages: [{ role: "user", content: "hello\n\nworld" }] };
|
|
const result = collapseWhitespace(body);
|
|
assert.equal(result.applied, false);
|
|
});
|
|
|
|
it("trims trailing spaces", () => {
|
|
const body = { messages: [{ role: "user", content: "hello " }] };
|
|
const result = collapseWhitespace(body);
|
|
assert.equal(result.applied, true);
|
|
assert.equal(result.body.messages![0].content as string, "hello");
|
|
});
|
|
|
|
it("returns unchanged when no messages", () => {
|
|
const body = {};
|
|
const result = collapseWhitespace(body);
|
|
assert.equal(result.applied, false);
|
|
});
|
|
|
|
it("skips non-string content", () => {
|
|
const body = { messages: [{ role: "user", content: [{ type: "text", text: "hello" }] }] };
|
|
const result = collapseWhitespace(body);
|
|
assert.equal(result.applied, false);
|
|
});
|
|
});
|
|
|
|
describe("dedupSystemPrompt", () => {
|
|
it("removes duplicate system prompts", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "system", content: "You are helpful." },
|
|
{ role: "system", content: "You are helpful." },
|
|
{ role: "user", content: "hi" },
|
|
],
|
|
};
|
|
const result = dedupSystemPrompt(body);
|
|
assert.equal(result.applied, true);
|
|
assert.equal(result.body.messages!.length, 2);
|
|
});
|
|
|
|
it("keeps different system prompts", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "system", content: "You are helpful." },
|
|
{ role: "system", content: "Be concise." },
|
|
],
|
|
};
|
|
const result = dedupSystemPrompt(body);
|
|
assert.equal(result.applied, false);
|
|
assert.equal(result.body.messages!.length, 2);
|
|
});
|
|
|
|
it("returns unchanged when no messages", () => {
|
|
const result = dedupSystemPrompt({});
|
|
assert.equal(result.applied, false);
|
|
});
|
|
});
|
|
|
|
describe("compressToolResults", () => {
|
|
it("truncates long tool results", () => {
|
|
const longContent = "x".repeat(3000);
|
|
const body = { messages: [{ role: "tool", content: longContent }] };
|
|
const result = compressToolResults(body);
|
|
assert.equal(result.applied, true);
|
|
const content = result.body.messages![0].content as string;
|
|
assert.ok(content.length < 3000);
|
|
assert.ok(content.includes("[truncated]"));
|
|
});
|
|
|
|
it("keeps short tool results unchanged", () => {
|
|
const body = { messages: [{ role: "tool", content: "short result" }] };
|
|
const result = compressToolResults(body);
|
|
assert.equal(result.applied, false);
|
|
});
|
|
|
|
it("skips non-tool messages", () => {
|
|
const body = { messages: [{ role: "user", content: "x".repeat(3000) }] };
|
|
const result = compressToolResults(body);
|
|
assert.equal(result.applied, false);
|
|
});
|
|
});
|
|
|
|
describe("removeRedundantContent", () => {
|
|
it("removes consecutive duplicate messages", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "user", content: "hello" },
|
|
{ role: "user", content: "hello" },
|
|
],
|
|
};
|
|
const result = removeRedundantContent(body);
|
|
assert.equal(result.applied, true);
|
|
assert.equal(result.body.messages!.length, 1);
|
|
});
|
|
|
|
it("keeps non-duplicate messages", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "user", content: "hello" },
|
|
{ role: "user", content: "world" },
|
|
],
|
|
};
|
|
const result = removeRedundantContent(body);
|
|
assert.equal(result.applied, false);
|
|
assert.equal(result.body.messages!.length, 2);
|
|
});
|
|
|
|
it("only removes same-role consecutive duplicates", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "system", content: "hello" },
|
|
{ role: "user", content: "hello" },
|
|
],
|
|
};
|
|
const result = removeRedundantContent(body);
|
|
assert.equal(result.applied, false);
|
|
});
|
|
});
|
|
|
|
describe("replaceImageUrls", () => {
|
|
it("replaces base64 images for non-vision models", () => {
|
|
const body = {
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [{ type: "image_url", image_url: { url: "data:image/png;base64,iVBOR" } }],
|
|
},
|
|
],
|
|
};
|
|
const result = replaceImageUrls(body, "gpt-3.5-turbo");
|
|
assert.equal(result.applied, true);
|
|
const content = result.body.messages![0].content as Array<Record<string, unknown>>;
|
|
assert.equal(content[0].type, "text");
|
|
assert.ok((content[0].text as string).includes("[image:"));
|
|
});
|
|
|
|
it("keeps images for vision models", () => {
|
|
const body = {
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [{ type: "image_url", image_url: { url: "data:image/png;base64,iVBOR" } }],
|
|
},
|
|
],
|
|
};
|
|
const result = replaceImageUrls(body, "gpt-4o");
|
|
assert.equal(result.applied, false);
|
|
});
|
|
|
|
// #3328: MiniMax M3 is multimodal (verified: it describes a base64 image via the
|
|
// opencode upstream). It must not be treated as a non-vision model, or compression
|
|
// strips the image and the model goes "blind".
|
|
it("keeps images for MiniMax M3 (incl. provider-prefixed / free ids)", () => {
|
|
const mkBody = () => ({
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [{ type: "image_url", image_url: { url: "data:image/png;base64,iVBOR" } }],
|
|
},
|
|
],
|
|
});
|
|
for (const id of ["minimax-m3", "minimax-m3-free", "oc/minimax-m3-free"]) {
|
|
const result = replaceImageUrls(mkBody(), id);
|
|
assert.equal(result.applied, false, `expected images kept for ${id}`);
|
|
}
|
|
});
|
|
|
|
it("skips non-image content", () => {
|
|
const body = {
|
|
messages: [{ role: "user", content: "just text" }],
|
|
};
|
|
const result = replaceImageUrls(body, "gpt-3.5-turbo");
|
|
assert.equal(result.applied, false);
|
|
});
|
|
});
|
|
|
|
describe("applyLiteCompression", () => {
|
|
it("applies all techniques that match", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "system", content: "You are helpful." },
|
|
{ role: "system", content: "You are helpful." },
|
|
{ role: "user", content: "hello\n\n\n\nworld" },
|
|
{ role: "user", content: "hello\n\n\n\nworld" },
|
|
],
|
|
};
|
|
const result = applyLiteCompression(body);
|
|
assert.equal(result.compressed, true);
|
|
assert.ok(result.stats);
|
|
assert.ok(result.stats.techniquesUsed.length >= 2);
|
|
assert.ok(result.stats.savingsPercent > 0);
|
|
});
|
|
|
|
it("preserves system prompt text when preserveSystemPrompt is enabled", () => {
|
|
const body = {
|
|
messages: [
|
|
{ role: "system", content: "Policy. Keep exact.\n\n\nDo not change." },
|
|
{ role: "user", content: "Please normalize this.\n\n\nThanks." },
|
|
],
|
|
};
|
|
const result = applyCompression(body, "lite", {
|
|
config: {
|
|
enabled: true,
|
|
defaultMode: "lite",
|
|
autoTriggerTokens: 0,
|
|
cacheMinutes: 5,
|
|
preserveSystemPrompt: true,
|
|
comboOverrides: {},
|
|
},
|
|
});
|
|
const messages = result.body.messages as typeof body.messages;
|
|
assert.equal(messages[0].content, body.messages[0].content);
|
|
assert.notEqual(messages[1].content, body.messages[1].content);
|
|
});
|
|
|
|
it("returns no compression for clean input", () => {
|
|
const body = {
|
|
messages: [{ role: "user", content: "clean message" }],
|
|
};
|
|
const result = applyLiteCompression(body);
|
|
assert.equal(result.compressed, false);
|
|
assert.equal(result.stats, null);
|
|
});
|
|
|
|
it("handles empty messages array", () => {
|
|
const body = { messages: [] };
|
|
const result = applyLiteCompression(body);
|
|
assert.equal(result.compressed, false);
|
|
});
|
|
});
|