* 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>
20 KiB
Referensi API (Bahasa Indonesia)
🌐 Languages: 🇺🇸 English · 🇸🇦 ar · 🇧🇬 bg · 🇧🇩 bn · 🇨🇿 cs · 🇩🇰 da · 🇩🇪 de · 🇪🇸 es · 🇮🇷 fa · 🇫🇮 fi · 🇫🇷 fr · 🇮🇳 gu · 🇮🇱 he · 🇮🇳 hi · 🇭🇺 hu · 🇮🇩 id · 🇮🇹 it · 🇯🇵 ja · 🇰🇷 ko · 🇮🇳 mr · 🇲🇾 ms · 🇳🇱 nl · 🇳🇴 no · 🇵🇭 phi · 🇵🇱 pl · 🇵🇹 pt · 🇧🇷 pt-BR · 🇷🇴 ro · 🇷🇺 ru · 🇸🇰 sk · 🇸🇪 sv · 🇰🇪 sw · 🇮🇳 ta · 🇮🇳 te · 🇹🇭 th · 🇹🇷 tr · 🇺🇦 uk-UA · 🇵🇰 ur · 🇻🇳 vi · 🇨🇳 zh-CN
Referensi lengkap untuk semua titik akhir API OmniRoute.
Daftar Isi
- Chat Completions
- Embeddings
- Pembuatan Gambar
- Daftar Model
- Titik Akhir Kompatibilitas
- Cache Semantik
- Dasbor & Manajemen
- Pemrosesan Permintaan
- Otentikasi
Chat Completions
POST /v1/chat/completions
Authorization: Bearer your-api-key
Content-Type: application/json
{
"model": "cc/claude-opus-4-6",
"messages": [
{"role": "user", "content": "Write a function to..."}
],
"stream": true
}
Header Kustom
| Header | Arah | Deskripsi |
|---|---|---|
X-OmniRoute-No-Cache |
Permintaan | Atur ke true untuk melewati cache |
X-OmniRoute-Progress |
Permintaan | Atur ke true untuk event progres |
X-Session-Id |
Permintaan | Kunci sesi tetap untuk afinitas sesi eksternal |
x_session_id |
Permintaan | Varian garis bawah juga diterima (HTTP langsung) |
Idempotency-Key |
Permintaan | Kunci deduplikasi (jendela 5 detik) |
X-Request-Id |
Permintaan | Kunci deduplikasi alternatif |
X-OmniRoute-Cache |
Respons | HIT atau MISS (non-streaming) |
X-OmniRoute-Idempotent |
Respons | true jika dideduplikasi |
X-OmniRoute-Progress |
Respons | enabled jika pelacakan progres aktif |
X-OmniRoute-Session-Id |
Respons | ID sesi efektif yang digunakan OmniRoute |
Catatan Nginx: jika Anda mengandalkan header bergaris bawah (misalnya
x_session_id), aktifkanunderscores_in_headers on;.
Embeddings
POST /v1/embeddings
Authorization: Bearer your-api-key
Content-Type: application/json
{
"model": "nebius/Qwen/Qwen3-Embedding-8B",
"input": "The food was delicious"
}
Penyedia yang tersedia: Nebius, OpenAI, Mistral, Together AI, Fireworks, NVIDIA, OpenRouter, GitHub Models.
# List all embedding models
GET /v1/embeddings
Image Generation
POST /v1/images/generations
Authorization: Bearer your-api-key
Content-Type: application/json
{
"model": "openai/gpt-image-2",
"prompt": "A beautiful sunset over mountains",
"size": "1024x1024"
}
Penyedia yang tersedia: OpenAI (GPT Image 2), xAI (Grok Image), Together AI (FLUX), Fireworks AI, Nebius (FLUX), Hyperbolic, NanoBanana, OpenRouter, SD WebUI (lokal), ComfyUI (lokal).
# List all image models
GET /v1/images/generations
Daftar Model
GET /v1/models
Authorization: Bearer your-api-key
→ Returns all chat, embedding, and image models + combos in OpenAI format
Titik Akhir Kompatibilitas
| Metode | Path | Format |
|---|---|---|
| POST | /v1/chat/completions |
OpenAI |
| POST | /v1/messages |
Anthropic |
| POST | /v1/responses |
OpenAI Responses |
| POST | /v1/embeddings |
OpenAI |
| POST | /v1/images/generations |
OpenAI |
| GET | /v1/models |
OpenAI |
| POST | /v1/messages/count_tokens |
Anthropic |
| GET | /v1beta/models |
Gemini |
| POST | /v1beta/models/{...path} |
Gemini generateContent |
| POST | /v1/api/chat |
Ollama |
Rute Penyedia Khusus
POST /v1/providers/{provider}/chat/completions
POST /v1/providers/{provider}/embeddings
POST /v1/providers/{provider}/images/generations
Prefiks penyedia ditambahkan secara otomatis jika tidak ada. Model yang tidak cocok mengembalikan 400.
Cache Semantik
# Get cache stats
GET /api/cache/stats
# Clear all caches
DELETE /api/cache/stats
Contoh respons:
{
"semanticCache": {
"memorySize": 42,
"memoryMaxSize": 500,
"dbSize": 128,
"hitRate": 0.65
},
"idempotency": {
"activeKeys": 3,
"windowMs": 5000
}
}
Dasbor & Manajemen
Otentikasi
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/auth/login |
POST | Masuk |
/api/auth/logout |
POST | Keluar |
/api/settings/require-login |
GET/PUT | Aktifkan/nonaktifkan wajib login |
Manajemen Penyedia
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/providers |
GET/POST | Daftar / buat penyedia |
/api/providers/[id] |
GET/PUT/DELETE | Kelola penyedia |
/api/providers/[id]/test |
POST | Uji koneksi penyedia |
/api/providers/[id]/models |
GET | Daftar model penyedia |
/api/providers/validate |
POST | Validasi konfigurasi penyedia |
/api/provider-nodes* |
Berbagai | Manajemen simpul penyedia |
/api/provider-models |
GET/POST/PATCH/DELETE | Model kustom (tambah, perbarui, sembunyikan/tampilkan, hapus) |
Alur OAuth
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/oauth/[provider]/[action] |
Berbagai | OAuth khusus penyedia |
Perutean & Konfigurasi
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/models/alias |
GET/POST | Alias model |
/api/models/catalog |
GET | Semua model berdasarkan penyedia + tipe |
/api/combos* |
Berbagai | Manajemen combo |
/api/keys* |
Berbagai | Manajemen kunci API |
/api/pricing |
GET | Harga model |
Penggunaan & Analitik
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/usage/history |
GET | Riwayat penggunaan |
/api/usage/logs |
GET | Log penggunaan |
/api/usage/request-logs |
GET | Log tingkat permintaan |
/api/usage/[connectionId] |
GET | Penggunaan per koneksi |
Pengaturan
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/settings |
GET/PUT/PATCH | Pengaturan umum |
/api/settings/proxy |
GET/PUT | Konfigurasi proksi jaringan |
/api/settings/proxy/test |
POST | Uji koneksi proksi |
/api/settings/ip-filter |
GET/PUT | Daftar izin/blokir IP |
/api/settings/thinking-budget |
GET/PUT | Anggaran token penalaran |
/api/settings/system-prompt |
GET/PUT | Prompt sistem global |
Pemantauan
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/sessions |
GET | Pelacakan sesi aktif |
/api/rate-limits |
GET | Batas laju per akun |
/api/monitoring/health |
GET | Pemeriksaan kesehatan + ringkasan penyedia (catalogCount, configuredCount, activeCount, monitoredCount) |
/api/cache/stats |
GET/DELETE | Statistik cache / hapus |
Cadangan & Ekspor/Impor
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/db-backups |
GET | Daftar cadangan yang tersedia |
/api/db-backups |
PUT | Buat cadangan manual |
/api/db-backups |
POST | Pulihkan dari cadangan tertentu |
/api/db-backups/export |
GET | Unduh database sebagai file .sqlite |
/api/db-backups/import |
POST | Unggah file .sqlite untuk mengganti database |
/api/db-backups/exportAll |
GET | Unduh cadangan lengkap sebagai arsip .tar.gz |
Sinkronisasi Cloud
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/sync/cloud |
Berbagai | Operasi sinkronisasi cloud |
/api/sync/initialize |
POST | Inisialisasi sinkronisasi |
/api/cloud/* |
Berbagai | Manajemen cloud |
Terowongan
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/tunnels/cloudflared |
GET | Baca status instalasi/runtime Cloudflare Quick Tunnel untuk dasbor |
/api/tunnels/cloudflared |
POST | Aktifkan atau nonaktifkan Cloudflare Quick Tunnel (action=enable/disable) |
Alat CLI
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/cli-tools/claude-settings |
GET | Status CLI Claude |
/api/cli-tools/codex-settings |
GET | Status CLI Codex |
/api/cli-tools/droid-settings |
GET | Status CLI Droid |
/api/cli-tools/openclaw-settings |
GET | Status CLI OpenClaw |
/api/cli-tools/runtime/[toolId] |
GET | Runtime CLI generik |
Respons CLI mencakup: installed, runnable, command, commandPath, runtimeMode, reason.
Agen ACP
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/acp/agents |
GET | Daftar semua agen yang terdeteksi (bawaan + kustom) beserta status |
/api/acp/agents |
POST | Tambah agen kustom atau segarkan cache deteksi |
/api/acp/agents |
DELETE | Hapus agen kustom berdasarkan parameter kueri id |
Respons GET mencakup agents[] (id, name, binary, version, installed, protocol, isCustom) dan summary (total, installed, notFound, builtIn, custom).
Ketahanan & Batas Laju
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/resilience |
GET/PATCH | Ambil/perbarui antrean permintaan, cooldown koneksi, pemutus sirkuit penyedia, dan pengaturan tunggu |
/api/resilience/reset |
POST | Reset pemutus sirkuit penyedia |
/api/rate-limits |
GET | Status batas laju per akun |
/api/rate-limit |
GET | Konfigurasi batas laju global |
Eval
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/evals |
GET/POST | Daftar suite eval / jalankan evaluasi |
Kebijakan
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/policies |
GET/POST/DELETE | Kelola kebijakan perutean |
Kepatuhan
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/compliance/audit-log |
GET | Log audit kepatuhan (N terakhir) |
v1beta (Kompatibel dengan Gemini)
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/v1beta/models |
GET | Daftar model dalam format Gemini |
/v1beta/models/{...path} |
POST | Titik akhir generateContent Gemini |
Titik akhir ini mencerminkan format API Gemini untuk klien yang mengharapkan kompatibilitas SDK Gemini asli.
API Internal / Sistem
| Titik Akhir | Metode | Deskripsi |
|---|---|---|
/api/init |
GET | Pemeriksaan inisialisasi aplikasi (digunakan saat pertama kali) |
/api/tags |
GET | Tag model kompatibel Ollama (untuk klien Ollama) |
/api/restart |
POST | Picu restart server secara halus |
/api/shutdown |
POST | Picu penghentian server secara halus |
/api/system/env/repair |
POST | Perbaiki variabel lingkungan penyedia OAuth |
/api/system-info |
GET | Buat laporan diagnostik sistem |
Catatan: Titik akhir ini digunakan secara internal oleh sistem atau untuk kompatibilitas klien Ollama. Biasanya tidak dipanggil langsung oleh pengguna akhir.
Perbaikan Lingkungan OAuth (v3.6.1+)
POST /api/system/env/repair
Content-Type: application/json
{
"provider": "claude-code"
}
Memperbaiki variabel lingkungan OAuth yang hilang atau rusak untuk penyedia tertentu. Mengembalikan:
{
"success": true,
"repaired": ["CLAUDE_CODE_OAUTH_CLIENT_ID", "CLAUDE_CODE_OAUTH_CLIENT_SECRET"],
"backupPath": "/home/user/.omniroute/backups/env-repair-2026-04-11.bak"
}
Transkripsi Audio
POST /v1/audio/transcriptions
Authorization: Bearer your-api-key
Content-Type: multipart/form-data
Transkripsi file audio menggunakan Deepgram atau AssemblyAI.
Permintaan:
curl -X POST http://localhost:20128/v1/audio/transcriptions \
-H "Authorization: Bearer your-api-key" \
-F "file=@recording.mp3" \
-F "model=deepgram/nova-3"
Respons:
{
"text": "Hello, this is the transcribed audio content.",
"task": "transcribe",
"language": "en",
"duration": 12.5
}
Penyedia yang didukung: deepgram/nova-3, assemblyai/best.
Format yang didukung: mp3, wav, m4a, flac, ogg, webm.
Kompatibilitas Ollama
Untuk klien yang menggunakan format API Ollama:
# Chat endpoint (Ollama format)
POST /v1/api/chat
# Model listing (Ollama format)
GET /api/tags
Permintaan diterjemahkan secara otomatis antara format Ollama dan format internal.
Telemetri
# Get latency telemetry summary (p50/p95/p99 per provider)
GET /api/telemetry/summary
Respons:
{
"providers": {
"claudeCode": { "p50": 245, "p95": 890, "p99": 1200, "count": 150 },
"github": { "p50": 180, "p95": 620, "p99": 950, "count": 320 }
}
}
Anggaran
# Get budget status for all API keys
GET /api/usage/budget
# Set or update a budget
POST /api/usage/budget
Content-Type: application/json
{
"keyId": "key-123",
"limit": 50.00,
"period": "monthly"
}
Pemrosesan Permintaan
- Klien mengirim permintaan ke
/v1/* - Handler rute memanggil
handleChat,handleEmbedding,handleAudioTranscription, atauhandleImageGeneration - Model diselesaikan (penyedia/model langsung, alias, atau combo)
- Kredensial dipilih dari DB lokal dengan penyaringan ketersediaan akun
- Untuk chat:
handleChatCore— deteksi format, translasi, pemeriksaan cache, pemeriksaan idempoten - Eksekutor penyedia mengirim permintaan upstream
- Respons diterjemahkan kembali ke format klien (chat) atau dikembalikan apa adanya (embeddings/gambar/audio)
- Penggunaan/logging dicatat
- Fallback diterapkan pada error sesuai aturan combo
Referensi arsitektur lengkap: ARCHITECTURE.md
Otentikasi
- Rute dasbor (
/dashboard/*) menggunakan cookieauth_token - Login menggunakan hash kata sandi yang tersimpan; fallback ke
INITIAL_PASSWORD requireLogindapat diaktifkan/nonaktifkan melalui/api/settings/require-login- Rute
/v1/*secara opsional memerlukan kunci API Bearer saatREQUIRE_API_KEY=true