mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-11-16 17:09:09 +00:00
4389 lines
250 KiB
Plaintext
4389 lines
250 KiB
Plaintext
# ┌─────────────────────────────────────────────────────────────────────────────┐
|
||
# │ OmniRoute — .env Contract │
|
||
# │ This file documents EVERY environment variable read by the runtime. │
|
||
# │ Copy to .env and adjust values. Lines starting with # are commented out │
|
||
# │ (optional / off-by-default). Uncomment only what you need. │
|
||
# │ Reference: docs/ENVIRONMENT.md for full details and usage scenarios. │
|
||
# └─────────────────────────────────────────────────────────────────────────────┘
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 1. REQUIRED SECRETS — Must be set before first run!
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# These secrets are critical for security. Generate strong, unique values.
|
||
|
||
# JWT signing key for dashboard session tokens.
|
||
# Used by: src/lib/auth — signs/verifies all authenticated session cookies.
|
||
# Generate: openssl rand -base64 48
|
||
JWT_SECRET=
|
||
|
||
# Encryption key for API keys stored in the database.
|
||
# Used by: src/lib/db/apiKeys.ts — encrypts API key values at rest in SQLite.
|
||
# Generate: openssl rand -hex 32
|
||
API_KEY_SECRET=
|
||
|
||
# Initial admin login password — CHANGE THIS before first use!
|
||
# Used by: src/lib/auth/managementPassword.ts — sets the dashboard password at startup
|
||
# while none is saved yet; ignored once a password is saved.
|
||
# After first login you can change it from Dashboard → Settings → Security.
|
||
# CHANGEME (this template's value) is publicly known. npm and source installs copy this
|
||
# file to .env, so replace CHANGEME there before first boot, or set INITIAL_PASSWORD=
|
||
# (empty) there to create the password in the dashboard's onboarding wizard instead.
|
||
INITIAL_PASSWORD=CHANGEME
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 2. STORAGE & DATABASE
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# OmniRoute uses SQLite for all persistence. These variables control where
|
||
# data lives, encryption, and cleanup policies.
|
||
|
||
# Base directory for all persistent data (SQLite DB, logs, backups).
|
||
# Used by: src/lib/db/core.ts — resolves the SQLite database file path.
|
||
# Default: ~/.omniroute/ | Override for Docker or custom installations.
|
||
# Hint: When running in Docker, consider mounting a host directory here for data persistence across container restarts
|
||
# also if you want to share the same database as "npm run dev" use "./data"
|
||
# DATA_DIR=/var/lib/omniroute
|
||
|
||
# Fallback alias for DATA_DIR, checked only when DATA_DIR is unset.
|
||
# Used by: open-sse/executors/promptql/threadSticky.ts — locates the PromptQL
|
||
# executor's on-disk thread-sticky session cache. Leave unset to rely on DATA_DIR.
|
||
# OMNIROUTE_DATA_DIR=/var/lib/omniroute
|
||
|
||
# Directory the runtime plugin scanner reads, overriding the home-derived default (#11827).
|
||
# Used by: src/lib/plugins/scanner.ts — getDefaultPluginDir(); it is also the root the
|
||
# plugin manager installs into. Set it in Docker/K8s to point straight at the bind-mounted
|
||
# plugin tree, instead of moving HOME (which changes every other HOME-relative behaviour)
|
||
# just to relocate the scan path. Unset = <HOME>/.omniroute/plugins, and
|
||
# /tmp/.omniroute/plugins when the process exports no home at all.
|
||
# Distinct from the CLI-only variable in section 9 that points the omniroute-cmd-* command
|
||
# loader (bin/cli/plugins.mjs) at a package tree — this one drives the server-side scanner.
|
||
# OMNIROUTE_PLUGINS_DIR=/opt/omniroute/plugins
|
||
|
||
# Escape hatch for the test/eval DATA_DIR guard (#10428). A test or node eval/print
|
||
# probe (-e/--eval/-p/--print, including --eval=/--print=) that never chose a DATA_DIR
|
||
# is redirected to a throwaway temp dir so it cannot open the operator's real database.
|
||
# Set to 1 only for a deliberate run against the real DATA_DIR — never for CI.
|
||
# Used by: src/lib/dataPaths.ts
|
||
# OMNIROUTE_ALLOW_DEFAULT_DATA_DIR=1
|
||
|
||
# Build provenance (#10427). OMNIROUTE_BUILD_SHA lets a container inject the artifact's git
|
||
# SHA when the dist/BUILD_SHA sentinel is absent; it is also what `npm run build:release`
|
||
# stamps. OMNIROUTE_RELEASE_REF is the ref the pack gate checks ancestry against, and
|
||
# OMNIROUTE_ALLOW_CANARY_BUILD=1
|
||
|
||
# API key the canary-deploy smoke uses when the target gateway requires auth (#10429).
|
||
# Used by: scripts/ops/deploy-canary.mjs — sent as `Authorization: Bearer` on the
|
||
# /v1/chat/completions probe. Never needed by the server itself.
|
||
# OMNIROUTE_SMOKE_API_KEY=sk-... records a deliberate off-release-line build instead of
|
||
# failing it. Used by: scripts/build/buildProvenance.ts, src/lib/monitoring/buildSha.ts
|
||
# OMNIROUTE_BUILD_SHA=abc1234
|
||
# OMNIROUTE_RELEASE_REF=origin/main
|
||
# OMNIROUTE_ALLOW_CANARY_BUILD=1
|
||
|
||
# Build-phase signal (#10060). Set to 1 by scripts/build/build-next-isolated.mjs and
|
||
# inherited by every spawned build worker so the DB layer returns a no-op stub instead
|
||
# of loading the native better-sqlite3 addon (which aborts the worker on exit).
|
||
# Never set this for the running server. Used by: src/lib/buildPhase.ts, src/lib/db/core.ts
|
||
# OMNIROUTE_BUILDING=1
|
||
|
||
# Skip the optional native-dependency prebuild check for exotic vendored trees.
|
||
# This does not make a missing dependency buildable. Used by: scripts/check/check-native-deps.mjs
|
||
# Default: 0 | Set to 1 only when native dependencies are supplied out of band.
|
||
# OMNIROUTE_SKIP_NATIVE_DEP_CHECK=0
|
||
|
||
# Encryption key for SQLite database encryption at rest.
|
||
# Used by: src/lib/db/encryption.ts — encrypts the entire SQLite database.
|
||
# Generate: openssl rand -hex 32 | Leave empty to disable DB encryption.
|
||
STORAGE_ENCRYPTION_KEY=
|
||
|
||
# Version tag for the encryption key — allows future key rotation.
|
||
# Used by: scripts/bootstrap-env.mjs, electron/main.js — persists key version.
|
||
# Default: v1 | Increment when rotating STORAGE_ENCRYPTION_KEY.
|
||
STORAGE_ENCRYPTION_KEY_VERSION=v1
|
||
|
||
# Routine/pre-write SQLite backups.
|
||
# Used by: src/lib/db/backup.ts. Set true only when those backups are managed externally.
|
||
# This never disables the migration runner's mandatory, content-addressed safety snapshot
|
||
# or its mass-migration guard for an existing persistent database.
|
||
# Default: false (routine backups enabled).
|
||
DISABLE_SQLITE_AUTO_BACKUP=false
|
||
|
||
# Opt-in synchronous SQLite adapter timing. Unset means off.
|
||
# Used by: src/lib/db/adapters/slowDiagnostics.ts
|
||
# OMNIROUTE_SQLITE_SLOW_MS=200
|
||
|
||
# Background SQLite planner statistics maintenance, independent of retention cleanup.
|
||
# Used by: src/lib/db/sqlitePlannerStats.ts via the cleanup scheduler.
|
||
# First pass: 30s after startup, after migrations; then every 6 hours.
|
||
# Default: true. Set false or 0 to disable all planner-statistics maintenance.
|
||
OMNIROUTE_SQLITE_OPTIMIZE_ENABLED=true
|
||
# Analysis row sampling limit: default 400; 0 = unlimited, exact analysis.
|
||
# Unlimited mode also disables SQLite's periodic optimize sampling cap.
|
||
# Decimal integers clamped to [0, 100000]; invalid values fall back to 400.
|
||
OMNIROUTE_SQLITE_ANALYSIS_LIMIT=400
|
||
|
||
# ── Redis (Rate Limiting) ──
|
||
# Redis connection URL for the rate limiter backend. OPT-IN: leave this
|
||
# commented out to use the built-in in-memory rate limiter. Setting it to a
|
||
# non-running localhost (#4878) makes ioredis flood "[REDIS] Error:" logs.
|
||
# Used by: src/shared/utils/rateLimiter.ts
|
||
# Example: redis://localhost:6379 (or redis://redis:6379 in Docker)
|
||
# REDIS_URL=redis://localhost:6379
|
||
# Namespace prefix for ALL OmniRoute Redis keys (rate limiter + auth cache +
|
||
# quota store + warmup circuit breaker). Prevents key collisions when OmniRoute
|
||
# shares a Redis instance with other apps (e.g. on 127.0.0.1:6379). Default when
|
||
# unset: omniroute:
|
||
# REDIS_KEY_PREFIX=omniroute:
|
||
# Optional shared session -> account affinity (slice 1a). Default: sqlite.
|
||
# redis requires REDIS_URL; uses the same client and REDIS_KEY_PREFIX.
|
||
# sessionAffinityTtlMs must remain positive; Redis calls fall back to SQLite after 100 ms.
|
||
# The timeout bounds waiting, not a sent EVAL, which may land after fallback.
|
||
# Each Redis affinity store caps outstanding operations at 8; full stores use SQLite immediately.
|
||
# SQLite routing keeps the legacy four-field JSON; Redis pins include hashed identity.
|
||
# Shared writes CAS against the routing observation (SQLite fallback records count as a miss).
|
||
# Redis alone is authoritative while it answers; confirmed mutations never write SQLite.
|
||
# Confirmed upserts/touches/deletes remove local entries; eviction uses the local identity guard.
|
||
# Only Redis errors, timeouts or admission saturation write local outage decisions,
|
||
# with the existing bounded TTL.
|
||
# Rejected upsert adopts a still-live eligible winner; unavailable winners keep the local candidate.
|
||
# On rejection, lease commits keep the claimed account for this request only, leaving shared unchanged.
|
||
# Late sent-mutation replies clean their timeout row by exact serialized-value compare-and-delete.
|
||
# During outage instances may re-pin independently; stickiness re-converges when Redis recovers.
|
||
# Known account identity overrides contradictory local IDs in resolution and guarded eviction.
|
||
# Shared liveness uses atomic value/PTTL reads; local snapshots map Redis's remaining TTL.
|
||
# JSON expiresAt is informational on Redis; existing keys retain their format and CAS bytes.
|
||
# Guarded eviction clears the failed account locally even when Redis is down.
|
||
# Successful shared replies can only remove local pins, never resurrect an evicted account.
|
||
# Does not share combo stickiness, native turn pins, concurrency or spend limits.
|
||
# OMNIROUTE_SESSION_AFFINITY_STORE=sqlite
|
||
# Host interface docker-compose publishes the Redis sidecar on.
|
||
# Default: 127.0.0.1 (loopback only). The compose Redis runs WITHOUT
|
||
# `requirepass`, and app containers reach it over the compose network
|
||
# (redis:6379) — the published port is only for host-side tooling. Setting this
|
||
# to 0.0.0.0 exposes an unauthenticated Redis to your whole LAN.
|
||
# REDIS_BIND_HOST=127.0.0.1
|
||
# Host port for the compose Redis sidecar. Default: 6379.
|
||
# REDIS_PORT=6379
|
||
|
||
# Host interface docker-compose publishes the app's own ports (dashboard,
|
||
# API, live-WS) on for the base/web/cli/host profiles and docker-compose.prod.yml.
|
||
# Default: 127.0.0.1 (loopback only). Combined with REQUIRE_API_KEY=false
|
||
# (the default below), an unqualified publish spec would expose the anonymous
|
||
# /v1 LLM proxy to your whole LAN/WAN. Only set this to 0.0.0.0 once you've
|
||
# confirmed REQUIRE_API_KEY=true, or that a reverse proxy in front of this
|
||
# instance already enforces its own authentication. (#12568)
|
||
# APP_BIND_HOST=127.0.0.1
|
||
# Host interface docker-compose publishes the Qdrant memory sidecar on.
|
||
# Default: 127.0.0.1 (loopback only). Same LAN-exposure reasoning as Redis.
|
||
# QDRANT_BIND_HOST=127.0.0.1
|
||
# Host interface docker-compose publishes the Bifrost router sidecar on.
|
||
# Default: 127.0.0.1 (loopback only). Same LAN-exposure reasoning as Redis.
|
||
# BIFROST_BIND_HOST=127.0.0.1
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 3. NETWORK & PORTS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# OmniRoute can run on a single port (default) or split Dashboard/API ports.
|
||
|
||
# Canonical port for both Dashboard UI and API (single-port mode).
|
||
# Used by: src/lib/runtime/ports.ts — base port for the Next.js server.
|
||
# Default: 20128
|
||
PORT=20128
|
||
|
||
# Base path (URL subpath) when serving OmniRoute behind a reverse proxy under a subpath.
|
||
# Used by: next.config.mjs — sets Next.js `basePath`; auth redirects are basePath-aware.
|
||
# Also mirrored to NEXT_PUBLIC_OMNIROUTE_BASE_PATH at build time so the dashboard
|
||
# endpoint display (useDisplayBaseUrl) shows https://host/omniroute/v1 instead of
|
||
# https://host/v1. Rebuild after changing this value (Next basePath is build-time).
|
||
# Default: "" (served at the domain root). Example: /omniroute to serve under https://host/omniroute
|
||
# Docker: baked at image build time via build-arg; root-path images can also apply this at
|
||
# container start (see docs/guides/DOCKER_GUIDE.md).
|
||
# OMNIROUTE_BASE_PATH=
|
||
# Client fetch/EventSource under this path are rewritten via installBasePathFetch
|
||
# (src/shared/utils/basePathFetch.ts) so absolute `/api/*` and `/v1/*` hits work
|
||
# without a reverse-proxy rewrite. Rebuild after changing (Next basePath is build-time).
|
||
#
|
||
# Browser-visible mirror of OMNIROUTE_BASE_PATH, inlined at build time so the
|
||
# dashboard endpoint display can read it client-side. Set it to the same value
|
||
# as OMNIROUTE_BASE_PATH; when unset the hook falls back to OMNIROUTE_BASE_PATH.
|
||
# Used by: src/shared/hooks/useDisplayBaseUrl.ts
|
||
# NEXT_PUBLIC_OMNIROUTE_BASE_PATH=
|
||
#
|
||
# Optional: set the public origin *with* the same path so OAuth and display URLs
|
||
# stay consistent without relying on window.location.origin alone:
|
||
# NEXT_PUBLIC_BASE_URL=https://host/omniroute
|
||
#
|
||
# Client-side fallback port for display URLs when no origin is known (SSR/tests):
|
||
# read before PORT so a browser bundle built with a different public port still
|
||
# renders the right http://localhost:<port> links (src/shared/hooks/useDisplayBaseUrl.ts).
|
||
# NEXT_PUBLIC_PORT=20128
|
||
#
|
||
# Explicit path probed by the container health check. Unset, the probe derives it
|
||
# from OMNIROUTE_BASE_PATH; setting it opts back into the deep monitoring endpoint.
|
||
# Used by: scripts/dev/healthcheck.mjs
|
||
# OMNIROUTE_HEALTHCHECK_PATH=/api/monitoring/health
|
||
|
||
# Opt-in iframe embedding of the OmniRoute HTML pages (issue #10273). Off by default:
|
||
# every route ships `frame-ancestors 'none'` + `X-Frame-Options: DENY`, which is why the
|
||
# VS Code Simple Browser (used by the OmniCopilot extension's "Open Dashboard → editor"
|
||
# mode) renders a blank tab. Set this to `vscode` to switch the HTML pages — dashboard,
|
||
# login, docs, landing — to `frame-ancestors 'self' vscode-webview:` and drop
|
||
# X-Frame-Options for them (XFO cannot express a custom scheme). The API surface
|
||
# (/api, /v1, /v1beta, /a2a, /healthz and the root-level aliases) keeps the strict
|
||
# headers regardless. Only `vscode` is recognised; `1`/`true` do NOT enable it.
|
||
# Used by: next.config.mjs via scripts/build/dashboardEmbed.mjs — build-time, rebuild after changing.
|
||
# Docker: pass it as a build arg (`docker build --build-arg DASHBOARD_ALLOW_EMBED=vscode`);
|
||
# setting it on an already-built server or image does nothing.
|
||
# DASHBOARD_ALLOW_EMBED=vscode
|
||
|
||
# Split-port mode: serve Dashboard and API on separate ports for network isolation.
|
||
# Used by: src/lib/runtime/ports.ts — overrides PORT for each service.
|
||
# API_PORT=20129
|
||
# API_HOST=0.0.0.0
|
||
# DASHBOARD_PORT=20128
|
||
|
||
# Connection backpressure: cap concurrent in-flight chat connections (503 + Retry-After when full).
|
||
# Used by: src/sse/utils/backpressure.ts — disabled when unset/0.
|
||
# OMNI_MAX_CONCURRENT_CONNECTIONS=0
|
||
|
||
# Optional OmniRoute-to-OmniRoute peer chaining guard. Give every instance a
|
||
# unique ID and allowlist only the other OmniRoute base URLs it may call.
|
||
# Requests to allowlisted peers carry X-OmniRoute-Peer-Trace; repeated instances
|
||
# and exhausted hop budgets are rejected with HTTP 508 before provider routing.
|
||
# OMNIROUTE_INSTANCE_ID=gateway-a
|
||
# OMNIROUTE_PEER_URLS=http://gateway-b:20128/v1
|
||
# OMNIROUTE_PEER_MAX_HOPS=4
|
||
|
||
# Port for the real-time WebSocket live monitoring server.
|
||
# Used by: src/server/ws/liveServer.ts, src/app/api/v1/ws/route.ts
|
||
# Default: 20132
|
||
# LIVE_WS_PORT=20132
|
||
|
||
# Bind address for the live WebSocket server.
|
||
# Default: 127.0.0.1 (loopback only). Set to 0.0.0.0 to expose on LAN —
|
||
# remember to also configure LIVE_WS_ALLOWED_ORIGINS when doing so.
|
||
# LIVE_WS_HOST=127.0.0.1
|
||
|
||
# Comma-separated extra origins allowed to open a live WebSocket. The
|
||
# loopback dashboard origins are already permitted by default; use this
|
||
# var when fronting the server with a domain (e.g. https://omni.local).
|
||
# ⚠️ When using NEXT_PUBLIC_LIVE_WS_PUBLIC_URL or exposing the WS server
|
||
# beyond loopback, this MUST include the public origin(s) — otherwise
|
||
# the Origin allow-list check will reject all browser connections.
|
||
# Example: LIVE_WS_ALLOWED_ORIGINS=https://omni.local,https://dashboard.example.com,https://ws.my-ai.com
|
||
# LIVE_WS_ALLOWED_ORIGINS=https://omni.local,https://dashboard.example.com
|
||
|
||
# Comma-separated extra hostnames allowed to open a live WebSocket (LAN/Tailscale).
|
||
# Unlike LIVE_WS_ALLOWED_ORIGINS (which matches full origin URLs), this matches
|
||
# only the host portion — useful for wildcard-ish LAN/Tailscale setups.
|
||
# Used by: src/server/ws/liveServerAllowList.ts
|
||
# Example: LIVE_WS_ALLOWED_HOSTS=omni.local,tailscale-host,192.168.1.50
|
||
# LIVE_WS_ALLOWED_HOSTS=omni.local,tailscale-host,192.168.1.50
|
||
|
||
# Public URL for the live dashboard WebSocket (client-side, browser only).
|
||
# Set this when fronting the WS server with a reverse proxy or Cloudflare Tunnel.
|
||
# The browser will connect to this URL instead of ws://hostname:20132.
|
||
# The path portion of this URL (e.g. ws://localhost:20132/live-ws -> /live-ws) is also used by the dev proxy
|
||
# (scripts/dev/standalone-server-ws.mjs) and the handshake response to route
|
||
# WebSocket upgrades. Default path: /live-ws.
|
||
# Used by: src/hooks/useLiveDashboard.ts, src/app/api/v1/ws/route.ts,
|
||
# scripts/dev/standalone-server-ws.mjs, and scripts/start-ws-server.mjs.
|
||
# Example: NEXT_PUBLIC_LIVE_WS_PUBLIC_URL=wss://ws.my-ai.com/live-ws
|
||
# NEXT_PUBLIC_LIVE_WS_PUBLIC_URL=ws://localhost:20132/live-ws
|
||
|
||
# Enable the real-time dashboard WebSocket server.
|
||
# Used by: src/server/ws/liveServer.ts, scripts/start-ws-server.mjs
|
||
# Default: ON. Set to 0 or false to disable startup of the live WS server.
|
||
# Combine with LIVE_WS_HOST / LIVE_WS_ALLOWED_ORIGINS above when exposing
|
||
# beyond loopback.
|
||
# OMNIROUTE_ENABLE_LIVE_WS=1
|
||
|
||
# Per-(token,IP) relay rate limit, requests/minute. In-memory, per instance.
|
||
# 0 or negative disables the IP-dimension gate (per-token DB limit still applies).
|
||
# Default: 30
|
||
# Used by: src/app/api/v1/relay/chat/completions/route.ts
|
||
# RELAY_IP_PER_MINUTE=30
|
||
|
||
# Bundler selection for `npm run dev` and `npm run build`. Set to 0 to fall back to webpack.
|
||
# Default is 1 (Turbopack). PR #4092 had forced webpack because earlier
|
||
# Turbopack 16.2.x panicked on the OmniRoute module graph with "internal error:
|
||
# entered unreachable code: there must be a path to a root"
|
||
# (turbopack-core/module_graph/mod.rs:662). That panic no longer reproduces on
|
||
# the pinned Next 16.2.9 — verified across a broad cold-compile sweep (36
|
||
# dashboard routes + open-sse-heavy API routes incl. /api/v1/chat/completions,
|
||
# /api/v1/models, /api/mcp) and repeated HMR rebuilds: zero panics. Turbopack
|
||
# also keeps dev memory far lower on the edit→rebuild loop (HMR rebuild RSS stays
|
||
# ~flat vs webpack's monotonic growth), which mitigates the dev-server OOM on
|
||
# this 60+ route app. The production build (scripts/build/build-next-isolated.mjs)
|
||
# reads the same flag: Turbopack by default, 0 builds with webpack (`npm run
|
||
# build:contributor` sets it for you).
|
||
OMNIROUTE_USE_TURBOPACK=1
|
||
|
||
# Webpack production builds (OMNIROUTE_USE_TURBOPACK=0) skip webpack's
|
||
# persistent filesystem cache by default: writing it adds about 2.5 GB of peak
|
||
# build memory at a 6144 MB heap cap. Set to 1 to keep .build/next/cache/webpack
|
||
# for faster repeat builds on a machine with RAM to spare (Docker: pass it as
|
||
# --build-arg). Read by next.config.mjs.
|
||
# OMNIROUTE_WEBPACK_BUILD_CACHE=1
|
||
|
||
# Disable systemd sd_notify (Type=notify / WatchdogSec=) even when running
|
||
# under a systemd unit with NOTIFY_SOCKET set.
|
||
# Used by: scripts/dev/systemd-notify.mjs. Set to 1 to disable.
|
||
# OMNIROUTE_DISABLE_SD_NOTIFY=1
|
||
|
||
# Injected by systemd when running under a service unit (sd_notify protocol).
|
||
# Read by scripts/dev/systemd-notify.mjs — never set this yourself.
|
||
# NOTIFY_SOCKET=/run/systemd/notify
|
||
|
||
# Skip the SQLite integrity health check on startup (faster boot on large DBs).
|
||
# Used by: src/lib/db/core.ts, src/lib/db/healthCheck.ts. Set to 1 to skip.
|
||
# OMNIROUTE_SKIP_DB_HEALTHCHECK=1
|
||
|
||
# Interval (ms) for the background credential health check scheduler.
|
||
# Default: 3600000 (60 minutes). Minimum: 10000 (10 seconds).
|
||
# Used by: open-sse/config/constants.ts, src/lib/credentialHealth/scheduler.ts
|
||
# CREDENTIAL_HEALTH_CHECK_INTERVAL=3600000
|
||
|
||
# TTL (ms) for cached credential health status.
|
||
# Default: 300000 (5 minutes).
|
||
# Used by: open-sse/config/constants.ts, src/lib/credentialHealth/cache.ts
|
||
# CREDENTIAL_HEALTH_CACHE_TTL=300000
|
||
|
||
# Set to 1 or true to disable background periodic testing of provider connections.
|
||
# Default: false
|
||
# Used by: src/lib/credentialHealth/scheduler.ts
|
||
# OMNIROUTE_DISABLE_CREDENTIAL_HEALTH_CHECK=false
|
||
|
||
# DEEP_HEALTH_CHECK_ENABLED: set to 1 to let an authenticated caller append ?deep=1 to
|
||
# /api/monitoring/health and sample the completions surface (cached per TTL). Off by default;
|
||
# anonymous callers never trigger a probe.
|
||
# DEEP_HEALTH_CHECK_ENABLED=0
|
||
|
||
# Stall threshold (ms) for the boot event-loop recorder: a freeze longer than
|
||
# this logs one line at resume and bumps the counter/maximum on
|
||
# /api/monitoring/health. Set to 0 to disable; unreadable or negative falls
|
||
# back to 5000.
|
||
# Used by: src/lib/healthzLag.ts
|
||
# OMNIROUTE_EVENT_LOOP_STALL_THRESHOLD_MS=5000
|
||
|
||
# Set to "true" to emit `[ProxyFetch]` debug logs from the Vercel relay path
|
||
# in open-sse/utils/proxyFetch.ts. Off by default to avoid leaking routing
|
||
# hints in production logs.
|
||
# OMNIROUTE_PROXY_FETCH_DEBUG=true
|
||
|
||
# Absolute path of the local proxy core binary (a file named `sing-box` for `.json` targets,
|
||
# or `mihomo` for `.yaml`/`.yml` targets) used to check a
|
||
# generated core configuration before it replaces the adopted file. Unset = write
|
||
# `<path>.generated` beside the adopted file only. Host environment only: never stored in the
|
||
# database nor accepted through the management API, because the binary is executed.
|
||
# A binary that doesn't match the target's core writes beside the adopted file with a warning.
|
||
# Used by: src/lib/proxySubscription/coreConfig/sync.ts.
|
||
# OMNIROUTE_PROXY_CORE_BINARY_PATH=/usr/bin/sing-box
|
||
# OMNIROUTE_PROXY_CORE_BINARY_PATH=/usr/local/bin/mihomo
|
||
|
||
# How the local proxy core reloads after a verified config replacement.
|
||
# Either a JSON argument array run without a shell, e.g.
|
||
# ["systemctl-reload-sing-box"] is NOT valid (must be an absolute path array),
|
||
# or exactly `external` when an outside observer applies the file.
|
||
# Never stored in the database nor exposed via the API.
|
||
# Used by: src/lib/proxySubscription/coreConfig/reload.ts.
|
||
# OMNIROUTE_PROXY_CORE_RELOAD_COMMAND=["/usr/bin/systemctl","--user","reload","sing-box"]
|
||
|
||
# Set to "true" or "1" to include client/egress IPs and the account prefix in
|
||
# the verbose `[ProxyEgress]` process-log line (src/lib/proxyLogger.ts). Kept
|
||
# OFF by default so the process log does not leak IPs or the account prefix.
|
||
# PROXY_LOG_INCLUDE_IPS=true
|
||
|
||
# Set to any non-empty value to emit `[omniroute completion]` diagnostics from
|
||
# the CLI shell-completion cache paths (read/refresh/write) in
|
||
# bin/cli/commands/completion.mjs. Off by default — these caches fail silently
|
||
# so a missing/corrupt cache never breaks tab-completion.
|
||
# OMNIROUTE_DEBUG_COMPLETION=1
|
||
|
||
# Set to 1 to print the full stack trace when a CLI command fails, instead of the
|
||
# concise error message. CLI-only diagnostics; HTTP error responses never include stacks.
|
||
# Used by: bin/cli/utils/formatCliError.mjs
|
||
# OMNIROUTE_DEBUG_STACK=1
|
||
|
||
# Optional Gemini CLI home used by `omniroute setup-gemini`. `omniroute run
|
||
# gemini` always replaces it with a private temporary home for that child.
|
||
# Default: the current user's home. Used by: bin/cli/commands/setup-gemini.mjs
|
||
# GEMINI_CLI_HOME=/path/to/isolated-gemini-home
|
||
|
||
# Grace period in milliseconds after forwarding SIGINT/SIGTERM/SIGHUP to a CLI
|
||
# child before OmniRoute escalates termination. Default: 5000.
|
||
# Used by: bin/cli/commands/run.mjs, launch.mjs, launch-codex.mjs
|
||
# OMNIROUTE_CHILD_SIGNAL_TIMEOUT_MS=5000
|
||
|
||
# Hermetic CLI/test escape hatch. When set to 1, an explicit DATA_DIR does not
|
||
# fall through to the user's default ~/.omniroute/.env credential file.
|
||
# Default: unset. Used by: bin/omniroute.mjs
|
||
# OMNIROUTE_CLI_SKIP_DEFAULT_DATA_ENV=1
|
||
|
||
# Set to 1 to print per-request timing diagnostics from the CLI quota commands
|
||
# to stderr (`[omniroute] GET <path> completed in Nms`).
|
||
# Used by: bin/cli/commands/quota.mjs
|
||
# OMNIROUTE_DEBUG=1
|
||
|
||
# Docker production port mappings (docker-compose.prod.yml only).
|
||
# These set the HOST-side published ports. Container ports use PORT/API_PORT.
|
||
# PROD_DASHBOARD_PORT=20130
|
||
# PROD_API_PORT=20131
|
||
|
||
# Runtime override used by Electron and wrapped environments.
|
||
# OMNIROUTE_PORT takes precedence over PORT when running inside wrappers.
|
||
# Used by: src/lib/runtime/ports.ts — preserves canonical port in Electron.
|
||
# OMNIROUTE_PORT=20128
|
||
|
||
# Hostname/bind address for the Next.js server.
|
||
# Used by: scripts/dev/run-next.mjs (HOST), Playwright runner (HOSTNAME).
|
||
# Default: 0.0.0.0 (HOST) / 127.0.0.1 (HOSTNAME inside tests).
|
||
# NOTE: Do NOT use `HOSTNAME` — it is a POSIX shell variable automatically set to
|
||
# the machine name by bash/zsh. The .env loader cannot override it (first-wins
|
||
# semantics). Use OMNIROUTE_SERVER_HOST instead for `omniroute serve`.
|
||
# See: https://github.com/diegosouzapw/OmniRoute/issues/6194
|
||
# HOST=0.0.0.0
|
||
# HOSTNAME=127.0.0.1
|
||
# OMNIROUTE_SERVER_HOST=0.0.0.0
|
||
|
||
# Environment mode — affects Next.js behavior, logging verbosity, and caching.
|
||
# Values: production | development | Default: production
|
||
NODE_ENV=production
|
||
|
||
# Container runtime — controls startup script behavior (permissions, advice).
|
||
# Values: docker | podman | Default: docker
|
||
# Set to "podman" for any Podman topology. The entrypoint cannot determine
|
||
# whether the engine is local or reached through Podman Machine, so it prints
|
||
# topology-neutral guidance and links contrib/podman/README.md.
|
||
CONTAINER_HOST=docker
|
||
|
||
# Container runtime override for skill sandboxing.
|
||
# Used by: src/lib/skills/sandbox.ts + src/lib/skills/containerProvider.ts
|
||
# Values: auto | docker | apple | wsl | orbstack | podman
|
||
# - auto: OS-aware auto-detect (apple/orbstack on macOS, wsl on Windows, podman on Linux)
|
||
# - apple: Apple Container (native OCI on macOS 26+)
|
||
# - wsl: WSL Container CLI (wslc.exe on Windows)
|
||
# - orbstack: OrbStack (high-perf Linux VM + docker shim on macOS)
|
||
# - podman: Podman (rootless, daemonless)
|
||
# - docker: Docker (default fallback)
|
||
# (defined under SKILLS & SANDBOXING section below)
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 4. SECURITY & AUTHENTICATION
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
|
||
# Salt for generating unique machine IDs (fingerprint diversification).
|
||
# Used by: src/lib/auth — combined with hardware identifiers for machine-id hash.
|
||
# Default: endpoint-proxy-salt | Change per-deployment for isolation.
|
||
MACHINE_ID_SALT=endpoint-proxy-salt
|
||
|
||
# Salt for deriving CLI machine-ID auth tokens (HMAC-SHA256).
|
||
# Used by: src/lib/machineToken.ts — rotates the local CLI auth token without
|
||
# touching code. Set to a new value to invalidate existing CLI tokens.
|
||
# Default: omniroute-cli-auth-v1
|
||
# OMNIROUTE_CLI_SALT=omniroute-cli-auth-v1
|
||
|
||
# Set true when running behind HTTPS (reverse proxy with TLS termination).
|
||
# Used by: src/lib/auth — sets the Secure flag on session cookies.
|
||
# Default: false | MUST be true in any non-localhost deployment.
|
||
AUTH_COOKIE_SECURE=false
|
||
|
||
# Require an API key for all /v1/* proxy endpoints.
|
||
# Used by: API middleware — rejects unauthenticated requests to the proxy API.
|
||
# Default: false | Set true for multi-user/public deployments.
|
||
# On: true, 1 or yes (case and surrounding spaces ignored). Any other value is off.
|
||
# Leaving this false is only safe when the app is reachable on loopback only
|
||
# (see APP_BIND_HOST above) or sits behind a reverse proxy doing its own auth.
|
||
REQUIRE_API_KEY=false
|
||
|
||
# Allow revealing full API key values in the Dashboard UI.
|
||
# Used by: src/shared/constants/featureFlagDefinitions.ts — controls show/hide of key values.
|
||
# Also configurable from Dashboard > Settings > Feature Flags.
|
||
# Default: false | Security risk if enabled on shared instances.
|
||
ALLOW_API_KEY_REVEAL=false
|
||
|
||
# Shared secret for the internal Codex Responses WebSocket bridge.
|
||
# Used by: src/app/api/internal/codex-responses-ws/route.ts — authenticates
|
||
# bridge requests between the Electron/browser WS relay and OmniRoute.
|
||
# ⚠️ REQUIRED for production — if unset, all WS bridge requests are rejected.
|
||
# Generate: openssl rand -base64 32
|
||
# OMNIROUTE_WS_BRIDGE_SECRET=
|
||
|
||
# Per-process secret that proves the trusted peer-IP stamp came from OmniRoute's
|
||
# own HTTP server (scripts/dev/peer-stamp.mjs). The custom server stamps the real
|
||
# TCP peer IP as `<token>|<ip>`; the authz middleware trusts the locality only
|
||
# when the token matches. Used by: src/server/authz/policies/management.ts.
|
||
# Auto-generated per boot — leave UNSET in normal use. Only set it to pin a fixed
|
||
# value across processes (e.g. a multi-process setup that must share the stamp).
|
||
# OMNIROUTE_PEER_STAMP_TOKEN=
|
||
|
||
# Comma-separated API key IDs that skip request logging (GDPR/compliance).
|
||
# Used by: src/lib/compliance/index.ts — suppresses logs for specific keys.
|
||
# NO_LOG_API_KEY_IDS=key_abc123,key_def456
|
||
|
||
# Fallback per-day request budget applied to API keys whose `rate_limits`
|
||
# column is null. Default (unset/empty) is unlimited (no implicit caps).
|
||
# Malformed values preserve the legacy 1000/day, 5000/week, 20000/month windows.
|
||
# Set explicitly to "0" to opt out entirely (unlimited fallback). Any
|
||
# positive integer N enables N/day, 5N/week, 20N/month.
|
||
# Used by: src/shared/utils/apiKeyPolicy.ts — checkRateLimit() fallback.
|
||
# DEFAULT_RATE_LIMIT_PER_DAY=1000
|
||
|
||
# Maximum request body size in bytes (rejects larger payloads). A saved maxBodySizeMb wins.
|
||
# Chat Completions and Responses keep a 50 MB default until a limit is saved.
|
||
# Used by: src/shared/middleware/bodySizeGuard.ts — prevents oversized uploads.
|
||
# Default: 10485760 (10 MB)
|
||
# MAX_BODY_SIZE_BYTES=10485760
|
||
|
||
# Atomic admission for POST /v1/chat/completions (#7846). Large request bodies
|
||
# amplify into multiple transient representations during parsing, compression, and
|
||
# provider dispatch. Heavyweight capacity is reserved before parsing; excess work
|
||
# receives 503 + Retry-After instead of overlapping until the process OOMs.
|
||
# Used by: src/shared/middleware/chatBodyAdmission.ts
|
||
# Actual bodies at or above this size take the heavyweight lease (BYTE path,
|
||
# including POST /v1/responses) and use the same #10437 healthy-headroom escape
|
||
# as structure-heavy. Default 262144 (256 KB).
|
||
# OMNIROUTE_CHAT_LARGE_BODY_BYTES=262144
|
||
# Actual-byte hard cap enforced during bounded ingestion. Default 52428800 (50 MB).
|
||
# A saved maxBodySizeMb replaces the default; when set here, this also caps that saved value.
|
||
# OMNIROUTE_CHAT_HARD_MAX_BODY_BYTES=52428800
|
||
# Legacy request-COUNT cap (#503-fanout). Now binds only when explicitly set here —
|
||
# left unset, heavyweight admission is gated by OMNIROUTE_CHAT_MAX_INFLIGHT_BYTES below
|
||
# instead (an auto-derived byte budget), fixing coding-agent fan-out (multiple
|
||
# subagents/CLIs) collapsing to an effective concurrency of ~1 and 503ing.
|
||
# Two overlapping ~750k-token /v1/responses abort ~12 Gi heaps (#7849) — a
|
||
# memory-budget warning, not a hard product max of 2. A healthy heap may admit
|
||
# more via HEALTHY_HEADROOM. Tens of long SSE clients (40-50) is heap +
|
||
# OMNIROUTE_CHAT_MAX_INFLIGHT_BYTES / #10110. Multiply heaps with N independent
|
||
# DATA_DIRs (#11024); never replicas>1 on one SQLite.
|
||
# OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT=1
|
||
# Override for the auto-derived ingest byte budget (#503-fanout). Default: 25% of the
|
||
# process's effective memory ceiling (V8 heap limit, or the tighter cgroup/container
|
||
# limit) divided by an 8x transient-amplification factor, clamped between 8 MiB and
|
||
# 2 GiB; explicit overrides are clamped to the same safe range. Read
|
||
# chatAdmission.maxInflightBytes/budgetSource at /api/monitoring/health before overriding.
|
||
# OMNIROUTE_CHAT_MAX_INFLIGHT_BYTES=134217728
|
||
# Heap-pressure shed ratio (heapUsed/heap_size_limit) for BYTE and STRUCTURE
|
||
# heavyweight admission (#10183, #10268, #10437): a concurrent heavyweight request
|
||
# past OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT is only shed with a retryable 503 when the
|
||
# heap is ALSO under this much pressure — on a healthy heap it is admitted via
|
||
# healthy-headroom instead. Range (0, 1]. Default 0.75.
|
||
# OMNIROUTE_CHAT_ADMISSION_HEAP_SHED_RATIO=0.75
|
||
# Bounded extra capacity for the healthy-heap fast path above OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT
|
||
# (#10437, BYTE + STRUCTURE, including bodies >= OMNIROUTE_CHAT_LARGE_BODY_BYTES):
|
||
# once this many concurrent leases are active through the healthy-heap bypass,
|
||
# further busy requests fall through to the same bounded-wait/shed path used under real heap
|
||
# pressure. 0 disables the bypass entirely. Default 1.
|
||
# OMNIROUTE_CHAT_ADMISSION_HEALTHY_HEADROOM=1
|
||
# Message count that classifies an otherwise small body as heavyweight. Default 200.
|
||
# OMNIROUTE_CHAT_HEAVY_MESSAGE_COUNT=200
|
||
# Tool count that classifies an otherwise small body as heavyweight. Default 64.
|
||
# OMNIROUTE_CHAT_HEAVY_TOOL_COUNT=64
|
||
# Conservative string-size token estimate that classifies a request as heavyweight. Default 32000.
|
||
# OMNIROUTE_CHAT_HEAVY_ESTIMATED_TOKENS=32000
|
||
# Optional opt-in hard message-count cap; excess receives compact-required 413 before
|
||
# compression can run. Unset/0 (the default) means no history cap: heap growth is bounded
|
||
# by OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT and the heap-pressure shed instead. Set a positive
|
||
# value only on memory-constrained deployments that need a hard ceiling.
|
||
# OMNIROUTE_CHAT_HARD_MAX_MESSAGES=0
|
||
|
||
# Skip OmniRoute's local context-window and max-input-token check for direct
|
||
# single-model requests. Default: false (dangerous opt-in).
|
||
# The upstream provider still enforces its real limits, so enabling this can
|
||
# replace an early OmniRoute 400 with an upstream context-length error.
|
||
# Prompt compression and the model's own output-token cap remain active.
|
||
# Also configurable from Dashboard > Settings > Feature Flags; no restart is
|
||
# required. Used by: src/shared/utils/featureFlags.ts and open-sse/handlers/chatCore.ts.
|
||
# DISABLE_CONTEXT_WINDOW_CHECKS=false
|
||
# How long a heavy request waits for heavyweight capacity before a retryable 503.
|
||
# A short bounded wait serializes agent bursts instead of an instant 503; 0 = instant.
|
||
# Defaults to RATE_LIMIT_MAX_WAIT_MS (see that var elsewhere in this file for its
|
||
# current value), the same budget the resilience layer gives the upstream turn that
|
||
# holds the slot — a shorter wait cannot bridge it.
|
||
# OMNIROUTE_CHAT_ADMISSION_QUEUE_MS=20000 # example override; default tracks RATE_LIMIT_MAX_WAIT_MS
|
||
# Queued-bytes budget for the admission wait: bounds total buffered body bytes parked
|
||
# per lane so the wait cannot amplify the heap (#4380). Over-budget waits 503 immediately.
|
||
# Default 4194304 (4 MB).
|
||
# OMNIROUTE_CHAT_ADMISSION_MAX_QUEUED_BYTES=4194304
|
||
# Per-connection virtual admission lanes (#9654): idle-lane eviction TTL. Default 60000 (60s).
|
||
# OMNIROUTE_CHAT_VIRTUAL_TTL_MS=60000
|
||
# Per-connection virtual admission lanes (#9654): max concurrent sessions (lanes). Default 64.
|
||
# OMNIROUTE_CHAT_VIRTUAL_MAX_SESSIONS=64
|
||
# Adaptive runtime virtual admission lanes (#9654): master switch for the per-tenant
|
||
# adaptive gate (system 2, open-sse/services/admission). NOTE: the TTL/MAX_SESSIONS
|
||
# vars above tune the byte-level per-connection lanes (system 1); this switch enables
|
||
# the adaptive runtime lanes. Dashboard feature flag of the same name; env wins over
|
||
# the dashboard override; restart required. Default: off.
|
||
# OMNIROUTE_CHAT_VIRTUAL_LANES=1
|
||
|
||
# Hard cap (bytes) for a non-streaming upstream response buffered fully into memory
|
||
# (#5152). Past this the upstream reader is cancelled and the request fails fast
|
||
# instead of growing an unbounded string until the V8 heap is exhausted.
|
||
# Used by: open-sse/handlers/chatCore/nonStreamingResponseBody.ts
|
||
# Default: 67108864 (64 MB)
|
||
# OMNIROUTE_FORWARDING_HEADER_BUDGET_BYTES=768
|
||
# OMNIROUTE_MAX_NONSTREAMING_RESPONSE_BYTES=67108864
|
||
|
||
# Most quota-recovery tickets (pending, running or awaiting confirmation) one
|
||
# API key may hold. At the limit, new turns get the original quota error.
|
||
# Used by: src/lib/quota/quotaSessionRecovery.ts
|
||
# Default: 64
|
||
# OMNIROUTE_QUOTA_RECOVERY_MAX_PER_KEY=64
|
||
|
||
# CORS configuration — controls which cross-origin browser clients can call the API.
|
||
# Used by: src/server/cors/origins.ts — sets Access-Control-Allow-Origin.
|
||
# Same-origin dashboard requests behind a reverse proxy do not need CORS; they
|
||
# use session-bound CSRF protection. No wildcard is sent unless CORS_ALLOW_ALL=true.
|
||
# CORS_ALLOWED_ORIGINS=https://your-frontend.example.com
|
||
# CORS_ORIGIN=https://your-frontend.example.com # legacy single-origin alias
|
||
# CORS_ALLOW_ALL=false
|
||
|
||
# Turns off the outbound URL guard's host checks, cloud-metadata block included, on the
|
||
# provider paths that follow the guard mode: URL validation, model discovery, provider-node
|
||
# base URLs (including remote rerank nodes), and the proxy-fallback test, among other
|
||
# provider-adjacent outbound paths such as remote image/media fetch. It also allows
|
||
# private webhook targets, except cloud-metadata/link-local endpoints, which stay
|
||
# blocked even with this flag on. Local providers work with the defaults:
|
||
# OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS below (default true) already allows local and LAN
|
||
# URLs. A value saved from the dashboard toggle takes precedence over this variable.
|
||
# Details: docs/reference/ENVIRONMENT.md.
|
||
# Used by: src/shared/network/outboundUrlGuardPolicy.ts
|
||
# Default: false
|
||
# OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS=true
|
||
|
||
# Allow provider URLs on local and private addresses (127.0.0.1, localhost, LAN).
|
||
# Default: true (OmniRoute is local-first); the guard then blocks cloud-metadata
|
||
# endpoints — all of 169.254.0.0/16 plus the known metadata hostnames. Set false to
|
||
# block private and loopback hosts too (public-only mode). The guard checks the
|
||
# hostname or IP literal as written first; in public-only mode the safe-fetch
|
||
# wrapper (validation, model discovery) also resolves the name and refuses
|
||
# private answers.
|
||
# Built-in local providers skip these checks for key validation and chat.
|
||
# A value saved from the dashboard toggle takes precedence over this variable.
|
||
# Used by: src/shared/network/outboundUrlGuardPolicy.ts
|
||
# OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS=false
|
||
|
||
# Legacy alias; its dashboard toggle (a DB override) is read before this environment value.
|
||
# "false", "0", "no", or "off" in either turns the host checks off the way
|
||
# OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS=true does, even when that flag's dashboard toggle
|
||
# is saved off. Other values leave the guard to the two flags above.
|
||
# Used by: src/shared/network/outboundUrlGuardPolicy.ts
|
||
# OUTBOUND_SSRF_GUARD_ENABLED=true
|
||
|
||
# ── Self-hosted unified OpenAI-compatible entry (RIC-738, D4) ────────────────────
|
||
# When set, /v1/chat/completions diverts to the self-hosted provider adapters
|
||
# (open-sse/services/selfHostedEntry.ts) instead of the cloud pipeline. YAML inline
|
||
# (example) — or point OMNIROUTE_SELF_HOSTED_PROVIDERS_FILE at a YAML file. Secrets
|
||
# are runtime-only, never logged. While ANY of these is set, the entry is active;
|
||
# config present but unparseable returns a 500 (never silently falls through).
|
||
# OMNIROUTE_SELF_HOSTED_PROVIDERS='
|
||
# providers:
|
||
# - id: local
|
||
# kind: openai
|
||
# baseUrl: http://127.0.0.1:11434/v1
|
||
# model: llama3
|
||
# - id: claude
|
||
# kind: anthropic
|
||
# baseUrl: http://127.0.0.1:8080
|
||
# model: claude-sonnet
|
||
# '
|
||
# OMNIROUTE_SELF_HOSTED_PROVIDERS_FILE=/etc/omniroute/providers.yaml
|
||
# Optional shared API key for the unified entry (D5 reserved). When set, require
|
||
# `Authorization: Bearer <key>`; empty = open loopback/trusted-network route.
|
||
# OMNIROUTE_SELF_HOSTED_API_KEY=
|
||
|
||
# ── Deterministic routing strategies (M2 / RIC-740, D3 可审计路由) ─────────────
|
||
# Optional `strategy:` block — either inline in the providers document above, or a
|
||
# standalone document via these env vars. One rule per line; every decision is
|
||
# explainable via the `x-omniroute-route-decision` response header. No ML/predict.
|
||
# Malformed strategy config returns a 500 (never silently becomes a no-op).
|
||
# Example (inline, same shape as `strategy:` inside the providers YAML):
|
||
# OMNIROUTE_SELF_HOSTED_STRATEGY='
|
||
# blacklist: []
|
||
# whitelist: [cheap, fast, premium]
|
||
# costPriority: true
|
||
# latencyAware:
|
||
# enabled: true
|
||
# cooldown:
|
||
# consecutiveFailures: 2
|
||
# cooldownMs: 30000
|
||
# fallbackChain: [cheap, fast, premium]
|
||
# '
|
||
# OMNIROUTE_SELF_HOSTED_STRATEGY_FILE=/etc/omniroute/strategy.yaml
|
||
# See docs/routing/DETERMINISTIC_ROUTING.md for the full strategy surface.
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 5. INPUT SANITIZATION & PII PROTECTION (FASE-01)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Multi-layer defense: request-side injection guard + response-side PII sanitizer.
|
||
|
||
# ── Request-Side: Prompt Injection Guard ──
|
||
# Scans incoming messages for prompt injection patterns before routing.
|
||
# Used by: src/middleware/promptInjectionGuard.ts
|
||
# Default ON when unset. Set to false/0/no/off to disable. Truthy: true/1/yes/on.
|
||
# INPUT_SANITIZER_ENABLED=false
|
||
# INPUT_SANITIZER_MODE=warn # warn = log only | block = reject request | redact = legacy (does NOT strip injection; use PII_REDACTION_ENABLED for request PII)
|
||
# INPUT_SANITIZER_BLOCK_THRESHOLD=high # high (default) | medium | low — severities at/above this are blocked in block mode
|
||
|
||
# Legacy aliases for INPUT_SANITIZER_MODE / INPUT_SANITIZER_BLOCK_THRESHOLD (same effect).
|
||
# INJECTION_GUARD_MODE=warn
|
||
# INJECTION_GUARD_BLOCK_THRESHOLD=high
|
||
|
||
# PII detection in incoming requests (emails, phone numbers, SSNs, etc.).
|
||
# Used by: src/middleware/promptInjectionGuard.ts — extends injection guard.
|
||
# PII_REDACTION_ENABLED=false
|
||
|
||
# Reversible PII vault (needs PII_REDACTION_ENABLED=true). Request PII becomes per-request
|
||
# surrogate tokens such as <<PII_EMAIL_QWERTYUI_1>> instead of [EMAIL_REDACTED]; the chat
|
||
# handler restores the original values in 2xx responses (SSE and JSON). Error bodies keep the
|
||
# tokens. A DB override on the dashboard toggle wins over this value.
|
||
# Used by: src/lib/pii/requestTokenVaultScope.ts.
|
||
# PII_REVERSIBLE_VAULT_ENABLED=false
|
||
|
||
# Redacts well-known API-key / secret-token patterns (OpenAI, Anthropic, GitHub,
|
||
# Slack, etc.) from request/response payloads before they reach providers/clients.
|
||
# Opt-in; mirrors PII_REDACTION_ENABLED. Used by: src/lib/guardrails/credentialMasker.ts.
|
||
# CREDENTIAL_REDACTION_ENABLED=false
|
||
|
||
# Minimum streaming window size for PII detection (bytes). Default: 200.
|
||
# Used by: src/lib/streamingPiiTransform.ts.
|
||
# PII_WINDOW_SIZE=200
|
||
|
||
# Test bypass: allow setting PII_WINDOW_SIZE below minimum. Default: false.
|
||
# Used by: src/lib/streamingPiiTransform.ts.
|
||
# PII_TEST_BYPASS_MIN_WINDOW=false
|
||
|
||
# ── Response-Side: PII Sanitizer ──
|
||
# Scans LLM responses for leaked PII before returning to the client.
|
||
# Used by: src/lib/piiSanitizer.ts
|
||
# PII_RESPONSE_SANITIZATION=false
|
||
# PII_RESPONSE_SANITIZATION_MODE=redact # redact = mask PII | warn = log only | block = drop response
|
||
|
||
# ── VS Code Tokenized-Route Context Sanitizer ──
|
||
# Strips implicit active-editor context (editorContext/activeEditor/currentFile/
|
||
# selection/openTabs…) from requests on the /v1/vscode/[token]/* routes before
|
||
# forwarding upstream, and redacts the content of explicitly-attached sensitive
|
||
# files (.env, private keys, kubeconfig, credentials/secrets). Explicit
|
||
# attachments otherwise pass through. Secure-by-default: ON unless set to 0.
|
||
# Used by: src/app/api/v1/vscode/contextSanitizer.ts
|
||
# OMNIROUTE_VSCODE_SANITIZE_CONTEXT=1 # set to 0 to disable
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 6. TOOL & ROUTING POLICIES
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
|
||
# Tool policy mode — controls which tools LLMs can invoke via function calling.
|
||
# Used by: src/lib/toolPolicy.ts — enforces allowlist/denylist on tool_choice.
|
||
# Values: allowlist | denylist | disabled | Default: disabled
|
||
# TOOL_POLICY_MODE=disabled
|
||
|
||
# Payload manipulation rules JSON file.
|
||
# Used by: open-sse/services/payloadRules.ts — injects/removes upstream payload fields per model/protocol.
|
||
# Default: ./config/payloadRules.json
|
||
# OMNIROUTE_PAYLOAD_RULES_PATH=./config/payloadRules.json
|
||
|
||
# Reload interval for payloadRules.json mtime checks in milliseconds.
|
||
# Used by: open-sse/services/payloadRules.ts — keeps file-based rules hot-reloadable without restart.
|
||
# Default: 5000 | Minimum: 1000
|
||
# OMNIROUTE_PAYLOAD_RULES_RELOAD_MS=5000
|
||
|
||
# Prefer Claude Code OAuth for unprefixed Claude-family model IDs such as
|
||
# claude-sonnet-4-6 or newly released IDs like claude-fable-5.
|
||
# Used by: open-sse/services/model.ts. Explicit provider prefixes still win.
|
||
# Default: false
|
||
# OMNIROUTE_PREFER_CLAUDE_CODE_FOR_UNPREFIXED_CLAUDE_MODELS=false
|
||
|
||
# Set to false to stop OmniRoute adding the redact-thinking-2026-02-12 Anthropic beta
|
||
# on its own (thinking text is then returned instead of empty signature-only blocks).
|
||
# Requests with thinking.display "summarized" already skip it; client-negotiated or
|
||
# CC-compatible requestDefaults.redactThinking opt-ins keep it. Claude OAuth requests keep
|
||
# the beta (Claude Code OAuth fingerprint) unless the default-off feature flag
|
||
# CLAUDE_OAUTH_SUMMARIZED_THINKING_UNREDACTED is enabled.
|
||
# Used by: open-sse/executors/base/redactThinkingBeta.ts
|
||
# Default: true
|
||
# OMNIROUTE_REDACT_THINKING=true
|
||
|
||
# Feature flag (also settable from the dashboard Feature Flags page): let Claude OAuth
|
||
# requests that ask for thinking.display "summarized" drop the redact-thinking beta.
|
||
# Off by default — the beta is part of the Claude Code OAuth wire fingerprint.
|
||
# Used by: open-sse/executors/base/redactThinkingBeta.ts
|
||
# Default: false
|
||
# CLAUDE_OAUTH_SUMMARIZED_THINKING_UNREDACTED=false
|
||
|
||
# Legacy resolveBareModelToConnectionDefault behaviour (#4825): replace ANY bare
|
||
# model name (not only "auto"/empty) with the selected connection's defaultModel.
|
||
# Off by default: a concrete bare name such as claude-haiku-4-5 is kept.
|
||
# Used by: open-sse/services/model.ts.
|
||
# Default: false
|
||
# BARE_MODEL_DEFAULT_OVERRIDE_LEGACY=false
|
||
|
||
# Per-model concurrency cap for round-robin combos (#9100).
|
||
# Used by: open-sse/services/comboConfig.ts — the round-robin combo semaphore
|
||
# was hard-capped at 3 concurrent requests per model with no override, which
|
||
# serialized higher-concurrency traffic behind that cap.
|
||
# Validated to >= 1, clamped to <= 32. | Default: 3
|
||
# COMBO_CONCURRENCY_PER_MODEL=3
|
||
|
||
# Opt-in sub-budget for stream-readiness deadline failures in a combo run.
|
||
# A stalled upstream fails the readiness window on EVERY target while the
|
||
# combo rotates (each rotation re-dispatches the full body after tens of
|
||
# seconds to minutes of waiting), multiplying user latency and gateway memory
|
||
# before the global-attempts cap — calibrated for fast failures — kicks in.
|
||
# Unset/0 (default) = disabled, no behavior change. A positive integer
|
||
# terminates the combo with a clean 504 once that many readiness-deadline
|
||
# failures accumulated (504 with error.code STREAM_READINESS_TIMEOUT; the
|
||
# target that exhausts the budget is still locked out / cooled down).
|
||
# Used by: open-sse/services/combo/comboPredicates.ts + executeTargetAttempt.ts
|
||
# OMNIROUTE_COMBO_MAX_DEADLINE_FAILURES=3
|
||
|
||
# Agentic-stall combo failover (opt-in, default OFF).
|
||
# Used by: open-sse/services/combo/agenticStall.ts + agenticStallFailover.ts — a combo
|
||
# member answering a tool-result turn with "finish: stop + narration + zero tool calls"
|
||
# fails over to the next target; if none does better, the stalled answer is returned.
|
||
# Streamed turns are held back from the client until the verdict is settled.
|
||
# Set to 1 (or true) to enable. | Default: false
|
||
# OMNIROUTE_AGENTIC_STALL_FAILOVER=false
|
||
|
||
# Disable conversation-history tracking (#13150).
|
||
# Used by: open-sse/services/conversationTracker.ts. resolveConversationId()
|
||
# returns an untracked result before it reads SQLite or parses message history,
|
||
# and the switch also covers client-supplied session IDs. Routing sessions are
|
||
# unaffected and existing records are not deleted. Use it when the dashboard's
|
||
# conversation view is unused and the turn table has grown large.
|
||
# Set to 1 to disable. | Default: unset (tracking enabled)
|
||
# OMNIROUTE_DISABLE_CONVERSATION_TRACKING=1
|
||
|
||
# Unpriced successful usage in per-API-key USD limits. Leave unset to use the
|
||
# upstream boolean opt-out below, otherwise the default fails closed.
|
||
# An explicit enum (DB override before env) takes precedence over the boolean.
|
||
# Values: fail_closed | count_as_zero. Lookup failures always fail closed.
|
||
# Used by: src/shared/utils/featureFlags.ts (enforcement and admin report).
|
||
# UNPRICED_USAGE_BUDGET_POLICY=fail_closed
|
||
# USAGE_LIMIT_IGNORE_UNPRICED=false
|
||
|
||
# Nadir API key for the opt-in `nadir` auto-combo router strategy.
|
||
# Used by: open-sse/services/autoCombo/nadirStrategy.ts — fallback for the combo's
|
||
# config.nadir.apiKey. Only read when a combo opts in with "routerStrategy": "nadir".
|
||
# Optional: keyless calls land on Nadir's anonymous tier, which is rate-limited per IP
|
||
# and so is not usable behind a shared gateway.
|
||
# Sensitive; prefer the per-combo config.nadir.apiKey when combos use different accounts.
|
||
# OMNIROUTE_NADIR_API_KEY=
|
||
|
||
# Base origin of the Nadir decision API.
|
||
# Used by: open-sse/services/autoCombo/nadirStrategy.ts — fallback for the combo's
|
||
# config.nadir.baseUrl. Only needed for a self-hosted Nadir, which keeps prompt heads
|
||
# inside your own network. A trailing /v1 is tolerated and stripped.
|
||
# Default: https://api.getnadir.com
|
||
# OMNIROUTE_NADIR_BASE_URL=https://api.getnadir.com
|
||
|
||
# Weekly window for per-API-key USD usage limits.
|
||
# Used by: src/lib/usage/apiKeyUsageLimits.ts (request enforcement, key usage-limit
|
||
# status, @@om-usage). Values: provider | calendar | Default: provider
|
||
# provider: the week ends at the earliest weekly reset among the upstream
|
||
# connections the key can reach (rolling 7 days when none is known).
|
||
# calendar: the local week, Monday 00:00 to the next Monday 00:00, the same for
|
||
# every key. Recommended when one pool of upstream accounts is shared
|
||
# by many individually budgeted keys.
|
||
# OMNIROUTE_API_KEY_WEEKLY_WINDOW=calendar
|
||
|
||
# IANA timezone for the calendar weekly window (e.g. Asia/Shanghai, UTC).
|
||
# Used by: src/lib/usage/apiKeyUsageLimits.ts. Unset or invalid: the timezone of
|
||
# the OmniRoute process (the TZ of the host or container). Ignored in provider mode.
|
||
# OMNIROUTE_API_KEY_WEEKLY_WINDOW_TIMEZONE=Asia/Shanghai
|
||
|
||
# Default maximum number of tools allowed in a request (OpenAI default 128).
|
||
# Used by: open-sse/config/constants.ts (MAX_TOOLS_LIMIT) — caps the tool list
|
||
# sent upstream when a provider has no known/proactive limit of its own; a
|
||
# provider with a known limit (e.g. grok-cli 200, nvidia 1536) still applies its
|
||
# own cap. Positive integers only; unset or invalid values keep 128.
|
||
# OMNIROUTE_MAX_TOOLS_LIMIT=128
|
||
|
||
# Responses -> Chat translation re-sends tool-output images (function_call_output,
|
||
# custom_tool_call_output, role "tool") as user image parts. Only the newest images within
|
||
# both budgets are kept; each older one becomes a text placeholder with its tool_call_id,
|
||
# and the cap logs one warning per request.
|
||
# Used by: open-sse/translator/request/openai-responses.ts (selectDroppedToolOutputImages).
|
||
# Positive integers only; unset or invalid values keep the defaults.
|
||
# OMNIROUTE_TOOL_OUTPUT_IMAGE_MAX_COUNT=16
|
||
# OMNIROUTE_TOOL_OUTPUT_IMAGE_MAX_BYTES=20971520
|
||
|
||
# Inconsistent Responses tool history (an output with no call, a call with no output, a missing,
|
||
# overlong or invalid call_id, malformed historical arguments). Off: OmniRoute repairs it and
|
||
# dispatches (#15216). On: the request gets a 400 before dispatch instead.
|
||
# Used by: open-sse/translator/helpers/responsesToolHistory.ts (isStrictResponsesToolHistoryEnabled).
|
||
# Accepts true or 1; anything else keeps the default.
|
||
# OMNIROUTE_RESPONSES_STRICT_TOOL_HISTORY=false
|
||
|
||
# SYNTX.ai prompt-emulated tool calling. Unset = on: SYNTX chat injects the local
|
||
# tool catalog into the prompt and parses <tool_call> blocks back into OpenAI
|
||
# tool_calls. Set to 0/false/off to skip the local-tool catalog injection.
|
||
# Used by: open-sse/executors/syntxChat.ts (isSyntxPromptToolEmulationEnabled).
|
||
# OMNIROUTE_PROMPT_EMULATE_TOOLS=1
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 7. URLS & CLOUD SYNC
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# URLs used for internal sync jobs, OAuth callbacks, and cloud relay.
|
||
|
||
# Internal base URL — used by server-side sync jobs to call /api/sync/cloud.
|
||
# Keep this as a loopback/container URL even when the app is publicly proxied.
|
||
# A2A skills refuse to send an API key over plain http outside the private network.
|
||
# Used by: src/lib/cloudSync.ts, src/lib/initCloudSync.ts
|
||
# Default: http://localhost:20128
|
||
BASE_URL=http://localhost:20128
|
||
|
||
# Cloud relay URL — premium feature for remote config sync.
|
||
# Used by: src/lib/cloudSync.ts — pushes/pulls settings from OmniRoute Cloud.
|
||
CLOUD_URL=
|
||
|
||
# Timeout for cloud sync HTTP requests in milliseconds.
|
||
# Used by: src/lib/cloudSync.ts — fetchWithTimeout wrapper.
|
||
# Default: 12000 (12 seconds)
|
||
# CLOUD_SYNC_TIMEOUT_MS=12000
|
||
|
||
# Public-facing base URL — required for stable reverse proxy / OAuth callback setups.
|
||
# Used by: OAuth redirect_uri computation, Dashboard UI links, and generated public URLs.
|
||
# Set to your stable public URL when OAuth callbacks or generated browser links need a
|
||
# canonical host behind nginx/Caddy (e.g., https://omniroute.example.com).
|
||
#
|
||
# Dashboard display behavior: when this variable is unset, the dashboard
|
||
# auto-detects the base URL shown in curl examples and CLI tool snippets
|
||
# from window.location.origin (the host the user is browsing). Setting it
|
||
# explicitly is only required when running behind a reverse proxy with a
|
||
# different public hostname, or when OAuth callbacks / generated browser links must point
|
||
# to a canonical URL. Authenticated dashboard writes use same-origin requests plus
|
||
# session-bound CSRF protection and do not require a static public base URL.
|
||
#
|
||
# Default: http://localhost:20128
|
||
NEXT_PUBLIC_BASE_URL=http://localhost:20128
|
||
|
||
# Highest-priority OmniRoute public origin override, also used by non-dashboard
|
||
# public-origin validation. Set it when external clients reach OmniRoute through
|
||
# a stable LAN, tunnel, or public origin that differs from its internal URL.
|
||
# Do not include /v1; if included accidentally it will be normalized away.
|
||
# OMNIROUTE_PUBLIC_BASE_URL=http://192.168.0.15:20128
|
||
|
||
# Absolute provider plugin manifest URL advertised to sidecar clients.
|
||
# Used by: open-sse/config/providerPluginManifestUrl.ts. When unset, OmniRoute
|
||
# derives the URL from request origin or HOST/PORT using OMNIROUTE_PUBLIC_PROTOCOL.
|
||
# OMNIROUTE_PROVIDER_MANIFEST_URL=https://omniroute.example.com/api/v1/provider-plugin-manifest
|
||
|
||
# Protocol used when deriving provider plugin manifest URLs without a request origin.
|
||
# Used by: open-sse/config/providerPluginManifestUrl.ts. Defaults to http.
|
||
# OMNIROUTE_PUBLIC_PROTOCOL=http
|
||
|
||
# Public cloud URL — client-side mirror of CLOUD_URL.
|
||
NEXT_PUBLIC_CLOUD_URL=
|
||
|
||
# Legacy alias — fallback for NEXT_PUBLIC_BASE_URL in sync schedulers.
|
||
# NEXT_PUBLIC_APP_URL=http://localhost:20128
|
||
|
||
# Advanced reverse-proxy trust mode for deriving public origin from Forwarded /
|
||
# X-Forwarded-* headers when no explicit public base URL is set. Prefer setting
|
||
# NEXT_PUBLIC_BASE_URL. Only enable if direct client access to OmniRoute is blocked
|
||
# and your proxy strips/rebuilds incoming forwarded headers.
|
||
# Values: true/loopback (trust loopback proxy peers), private/lan (also trust LAN peers).
|
||
# OMNIROUTE_TRUST_PROXY=
|
||
|
||
# Proxy addresses whose X-Forwarded-For / X-Real-IP the IP allow/deny list may believe, on top
|
||
# of loopback, private-network addresses and Cloudflare edges, which are always trusted. Needed
|
||
# only when the reverse proxy in front of OmniRoute has any other (public) address; without
|
||
# it that proxy's own address is what the filter judges. Comma-separated IPs or CIDR ranges.
|
||
# Used by: scripts/dev/peer-stamp.mjs.
|
||
# OMNIROUTE_TRUSTED_PROXIES=198.51.100.7,203.0.113.0/24
|
||
|
||
# Public callback URL for asynchronous image/audio jobs (kie.ai, etc.).
|
||
# Used by: open-sse/utils/kieTask.ts — overrides callbackUrlFromBaseUrl().
|
||
# Honor order: KIE_CALLBACK_URL → OMNIROUTE_KIE_CALLBACK_URL → OMNIROUTE_PUBLIC_URL.
|
||
#KIE_CALLBACK_URL=
|
||
#OMNIROUTE_KIE_CALLBACK_URL=
|
||
#OMNIROUTE_PUBLIC_URL=
|
||
|
||
# Headroom token-saver proxy URL. The dashboard lifecycle (api/headroom/*) spawns
|
||
# a local headroom-ai CLI on loopback by default; override only to point at an
|
||
# external Docker sidecar proxy. Defaults to http://localhost:8787 when unset.
|
||
# Used by: src/lib/headroom/detect.ts.
|
||
#HEADROOM_URL=http://localhost:8787
|
||
|
||
# Upstream quota endpoints used by the Usage page. Override only for
|
||
# debugging or when routing through a corporate mirror. Used by:
|
||
# open-sse/services/usage.ts.
|
||
#OMNIROUTE_CROF_USAGE_URL=https://crof.ai/usage_api/
|
||
# ClinePass 5h/weekly/monthly quota endpoint (open-sse/services/usage/clinepass.ts).
|
||
#OMNIROUTE_CLINEPASS_USAGE_URL=https://api.cline.bot/api/v1/users/me/plan/usage-limits
|
||
#OMNIROUTE_CODEWHISPERER_BASE_URL=https://codewhisperer.us-east-1.amazonaws.com
|
||
# Official OpenCode Go usage endpoint, authenticated with the connection API key.
|
||
# Override only for relays or test fixtures.
|
||
#OMNIROUTE_OPENCODE_QUOTA_URL=https://opencode.ai/zen/go/v1/usage
|
||
#OMNIROUTE_OLLAMA_CLOUD_USAGE_URL=https://ollama.com/settings
|
||
# Ollama Cloud documented balance endpoint, authenticated with the connection API key
|
||
# (open-sse/services/ollamaCloudBalance.ts). Tried before the settings-page scraper.
|
||
# Override only for relays or test fixtures.
|
||
#OMNIROUTE_OLLAMA_CLOUD_BALANCE_URL=https://ollama.com/api/balance
|
||
|
||
# OpenCode Go/Zen VPS egress (#5997): on a datacenter VPS, Cloudflare in front of
|
||
# opencode.ai/zen/go 403s chat requests that lack OpenCode CLI identity headers.
|
||
# When your clients don't already send them, set this to synthesize the CLI headers
|
||
# (User-Agent, x-opencode-client, x-opencode-project, canonical request/session ids) on
|
||
# absent keys. ON by default — a client value always wins, these only fill gaps.
|
||
# Values are overridable via OPENCODE_GO_USER_AGENT / OPENCODE_USER_AGENT / OPENCODE_CLIENT /
|
||
# OPENCODE_PROJECT (defaults: opencode/1.18.31 / desktop / global).
|
||
#OPENCODE_SYNTHESIZE_CLI_HEADERS=true
|
||
#OPENCODE_USER_AGENT=opencode/1.18.31
|
||
#OPENCODE_CLIENT=desktop
|
||
#OPENCODE_PROJECT=global
|
||
|
||
# Forward client app-attribution headers (x-session-id / x-title / http-referer) to
|
||
# upstream providers, so requests keep their app identity through the router
|
||
# (OpenRouter publisher gates key on them). ON by default; operator custom headers
|
||
# always win. Set to 0/false/no/off to keep the operator identity instead.
|
||
#OMNIROUTE_FORWARD_ATTRIBUTION=1
|
||
|
||
# Keyless OpenCode models are answered only when the request declares a non-empty tool
|
||
# list, and the upstream inspects which names it carries. OmniRoute reuses the list a
|
||
# request of the same conversation was last seen getting through, so a request that
|
||
# carries none — a title or a summary — goes out with the list its own client already
|
||
# declared. Set to off to stop adjusting request bodies entirely; headers are unaffected.
|
||
#OPENCODE_FREE_TIER_REQUEST_CONTRACT=off
|
||
|
||
# Tool names to declare when nothing has been observed yet for a model, comma-separated.
|
||
# Empty falls back to a single placeholder the model is told not to call. Only useful on
|
||
# an install where no client sends tools, since there is then nothing to learn from.
|
||
#OPENCODE_FREE_TIER_PLACEHOLDER_TOOLS=glob,grep,read
|
||
|
||
# Credential used on the gated free-tier lane (https://opencode.ai/inference/v1, the base
|
||
# every free model is routed to). Since 2026-10-21 that lane answers 403 "Model access is
|
||
# disabled" to a real API key and serves the anonymous literal instead, so the default is
|
||
# "public". Set to "key" to keep sending the operator's API key (an upstream that re-opens
|
||
# free-tier access to keyed accounts), "none" to send no credential header, or any other
|
||
# literal to send it as the bearer token.
|
||
#OPENCODE_FREE_TIER_CREDENTIAL=public
|
||
|
||
# Bun relay for the keyless OpenCode models. The upstream answers 429 to every HTTP client but
|
||
# Bun's native fetch, and only when messages[0] is the genuine OpenCode CLI prompt with the
|
||
# CLI tool set declared. With this set, gated requests are rewritten that way (the caller's
|
||
# system text follows, its tools are kept, calls to CLI tools it never declared are dropped
|
||
# from the reply) and sent to the relay, which re-sends them with Bun. Loopback URLs are
|
||
# started with the server when `bun` is on PATH (override: OPENCODE_FREE_RELAY_BUN); otherwise
|
||
# run `bun scripts/ops/opencode-free-relay.ts` as a sidecar. Port: OPENCODE_FREE_RELAY_PORT.
|
||
# An egress proxy assigned to the request is forwarded to the relay (http/https proxies only).
|
||
#OPENCODE_FREE_TIER_RELAY_URL=http://127.0.0.1:20199
|
||
# Relay tuning (all optional): OPENCODE_FREE_RELAY_BUN (bun binary), OPENCODE_FREE_RELAY_SCRIPT
|
||
# (relay script path), OPENCODE_FREE_RELAY_HOST / OPENCODE_FREE_RELAY_PORT (listen address,
|
||
# default 127.0.0.1:20199), OPENCODE_FREE_RELAY_UPSTREAM (default https://opencode.ai).
|
||
#OPENCODE_FREE_RELAY_BUN=
|
||
#OPENCODE_FREE_RELAY_SCRIPT=
|
||
#OPENCODE_FREE_RELAY_HOST=127.0.0.1
|
||
#OPENCODE_FREE_RELAY_PORT=20199
|
||
# Non-loopback relay: OPENCODE_FREE_TIER_RELAY_URL must be https:// unless the host is loopback
|
||
# (localhost, 127.0.0.0/8, ::1). A relay bound to a non-loopback OPENCODE_FREE_RELAY_HOST refuses
|
||
# to start without OPENCODE_FREE_RELAY_TOKEN (sent by OmniRoute, required by the relay) and only
|
||
# honours caller proxies listed in OPENCODE_FREE_RELAY_PROXY_ALLOWLIST (host or host:port, comma-separated).
|
||
#OPENCODE_FREE_RELAY_TOKEN=
|
||
#OPENCODE_FREE_RELAY_PROXY_ALLOWLIST=
|
||
#OPENCODE_FREE_RELAY_UPSTREAM=https://opencode.ai
|
||
|
||
# Egress-IP lockout scope (#9611). By default the free-tier opencode family
|
||
# (opencode, opencode-go, opencode-cli) is bucketed by egress IP: one upstream
|
||
# 429 parks every sibling connection sharing that IP. PAID plans are
|
||
# account-bucketed upstream, so operators on paid subscriptions can disable the
|
||
# cascade or narrow it to the providers that actually need it.
|
||
# unset → default free-tier set (opencode, opencode-go, opencode-cli)
|
||
# none / off / false / 0 → egress-IP lockout disabled entirely
|
||
# "a,b,c" → exact replacement set (comma-separated provider IDs)
|
||
# Used by: open-sse/config/providerErrorRules.ts (isEgressBucketedLockScope)
|
||
# OMNIROUTE_EGRESS_IP_LOCK_PROVIDERS=none
|
||
|
||
# Quota-refusal egress rotation scope. By default only the IP-bucketed family above
|
||
# sets a pool member aside when it answers 429 through the member, so the next pick
|
||
# egresses elsewhere. The free and keyless providers answer 429 per IP too (there is
|
||
# no account key to bucket by), and `all` extends that write to every provider.
|
||
# unset → the IP-bucketed family only (default)
|
||
# all → every provider; any other value is ignored rather than guessed
|
||
# Needs PROXY_SKIP_RECENTLY_FAILED (on by default) for the set-aside to be read.
|
||
# The refusal store is keyed by egress address, not by (provider, address), so a widened
|
||
# 429 parks that member for every provider until the period elapses (5 min, up to 15).
|
||
# Used by: open-sse/config/providerErrorRules.ts (rotatesEgressOnQuotaRefusal)
|
||
# OMNIROUTE_EGRESS_QUOTA_ROTATION_PROVIDERS=all
|
||
|
||
# Ollama Cloud quota scraping. Prefer configuring this per connection in
|
||
# Dashboard → Providers → Ollama Cloud. The cookie is sensitive.
|
||
#OLLAMA_USAGE_COOKIE=__Secure-session=...
|
||
#OLLAMA_CLOUD_USAGE_COOKIE=__Secure-session=...
|
||
#OMNIROUTE_OLLAMA_USAGE_COOKIE=__Secure-session=...
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 8. OUTBOUND PROXY (Upstream Provider Calls)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Route upstream LLM API calls through an HTTP/SOCKS5 proxy.
|
||
# Useful for corporate egress, geo-routing, or IP masking.
|
||
|
||
# Enable SOCKS5 proxy support in both server and client components.
|
||
# Used by: open-sse/executors — wraps fetch() calls through the proxy agent.
|
||
ENABLE_SOCKS5_PROXY=true
|
||
NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
|
||
|
||
# On-by-default feature flag (a dashboard DB override wins over this value): proxy pools
|
||
# and per-account rotation stop re-serving a member that just failed (TCP probe refused, or a
|
||
# 429 received through it) for a period that doubles on each repeat, up to a cap. No proxy
|
||
# status is written. Unset keeps skipping; PROXY_SKIP_RECENTLY_FAILED=false restores plain selection.
|
||
# PROXY_SKIP_RECENTLY_FAILED=true
|
||
|
||
# Allow-list for local-core selector-control targets beyond loopback (comma/space
|
||
# separated hosts or IPs, "*" opens LAN/private but never metadata/link-local).
|
||
# Loopback (127.0.0.1, ::1, localhost) over http/https is allowed by default.
|
||
# A dashboard DB value wins over this variable when set and non-empty.
|
||
# Used by: src/lib/proxySubscription/selectorGuard.ts.
|
||
# SELECTOR_CONTROL_ALLOWLIST=
|
||
|
||
# Curve of the 429 set-aside (read once at startup; restart to apply).
|
||
# Base period for the first refusal through a proxy, doubled on each repeat.
|
||
# Bounded to 1000..3600000; out-of-range or unreadable falls back to 300000 with a warning.
|
||
# Used by: open-sse/utils/proxyRefusalMemory.ts.
|
||
# PROXY_QUOTA_429_BASE_MS=300000
|
||
|
||
# Cap of the 429 set-aside (read once at startup; restart to apply).
|
||
# Bounded to 1000..3600000; out-of-range or unreadable falls back to 900000 with a warning.
|
||
# When the cap is below the base, it falls back to the default 900000.
|
||
# Lowering the cap also shortens streak forgetting: entries purge 2 x max after expiry.
|
||
# PROXY_QUOTA_429_MAX_MS=900000
|
||
|
||
# Opt-in feature flag (default off; a dashboard DB override wins over this value): for
|
||
# providers whose quota is bucketed by egress address, rank a pool member sharing a recently
|
||
# refused member's observed egress address just below healthy members. Order only, never
|
||
# excluded. Needs PROXY_SKIP_RECENTLY_FAILED, which produces the refusal signal it reads.
|
||
# PROXY_POOL_SHARED_EGRESS_ORDER=false
|
||
|
||
# Rebound window capping repeat set-aside webhook alerts per pool member (read on each emit; no restart needed).
|
||
# Bounded to 1000..3600000; out-of-range or unreadable falls back to 300000 with a silent default.
|
||
# Used by: src/lib/proxyEvents/proxyTransitionBridge.ts.
|
||
# PROXY_WEBHOOK_REBOUND_MS=300000
|
||
|
||
# Standard proxy variables (lowercase variants also supported).
|
||
# HTTP_PROXY=http://127.0.0.1:7890
|
||
# HTTPS_PROXY=http://127.0.0.1:7890
|
||
# ALL_PROXY=socks5://127.0.0.1:7890
|
||
# NO_PROXY=localhost,127.0.0.1
|
||
|
||
# Pin the echo-IP target used by proxy egress probes. Unset, the probe tries
|
||
# api64.ipify.org then api4.ipify.org so IPv4-only tunnels are not reported dead.
|
||
# Used by: src/lib/proxyEchoTarget.ts.
|
||
# OMNIROUTE_PROXY_ECHO_URL=https://api4.ipify.org?format=json
|
||
|
||
# Max concurrent sockets per cached HTTP/SOCKS proxy dispatcher.
|
||
# Long-lived SSE streams such as Codex /v1/responses need more than one
|
||
# connection when multiple requests share the same account-level proxy.
|
||
# Set to 1 only for legacy diagnostics. Values above 256 are capped.
|
||
# OMNIROUTE_PROXY_DISPATCHER_CONNECTIONS=32
|
||
|
||
# HTTP/2 negotiation for Undici upstream dispatchers (direct, HTTP/SOCKS proxies,
|
||
# relays and their retries). Explicit false/0/no/off forces HTTP/1.1.
|
||
# Does not control wreq TLS fingerprinting or provider-specific transports.
|
||
# Restart OmniRoute after changing this value; dispatchers are cached.
|
||
# OMNIROUTE_UPSTREAM_HTTP2_ENABLED=true
|
||
# Gzip the request body sent to the official api.anthropic.com (bodies of 4096+ characters, direct
|
||
# connections only; skipped behind a proxy, TLS impersonation or NODE_EXTRA_CA_CERTS). The API accepts
|
||
# gzip only (br/zstd/deflate answer 415). A refusal is resent uncompressed once and that origin stays
|
||
# uncompressed for one hour. Default on; set 0/false/off/no to disable.
|
||
# Used by: open-sse/executors/base/gzipRequestBody.ts
|
||
# OMNIROUTE_GZIP_REQUEST_BODIES=1
|
||
# Extra CA bundle for Node TLS (read by Node at startup). When set, outbound gzip request bodies
|
||
# are skipped, as Claude Code does, because a TLS-inspecting middlebox may not decode them.
|
||
# NODE_EXTRA_CA_CERTS=
|
||
|
||
# SOCKS5 handshake (connect) timeout in ms (default 10000, capped at 120000).
|
||
# Raise it when a single residential gateway host is hit by high concurrency
|
||
# (e.g. 100 simultaneous requests): the real SOCKS5 handshake can exceed 10s
|
||
# under a saturated pool even though the proxy is reachable, which otherwise
|
||
# surfaces as a false "[Proxy Fast-Fail] Proxy unreachable".
|
||
# SOCKS_HANDSHAKE_TIMEOUT_MS=10000
|
||
|
||
# Proxy fail-open mode (default: false = fail-closed).
|
||
# When false, a request whose assigned proxy fails to resolve is REFUSED rather than
|
||
# falling back to a direct connection — prevents real-IP leaks in egress-controlled
|
||
# deployments. Set true to restore the legacy DIRECT fallback (legacy behaviour).
|
||
# Used by: src/sse/handlers/chatHelpers.ts
|
||
# PROXY_FAIL_OPEN=false
|
||
|
||
# TLS fingerprint spoofing (opt-in) — mimics Chrome 124 TLS handshake via wreq-js.
|
||
# Reduces risk of JA3/JA4 fingerprint-based blocking by providers (e.g., Google).
|
||
# Used by: open-sse/executors — replaces Node.js default TLS fingerprint.
|
||
# ENABLE_TLS_FINGERPRINT=true
|
||
# New proxied TLS routing requires an explicit, comma-separated provider allowlist.
|
||
# Direct TLS keeps its legacy behavior when this is unset.
|
||
# TLS_FINGERPRINT_PROVIDERS=codex,openai
|
||
|
||
# Allow the Claude Turnstile Playwright browser context to ignore HTTPS certificate errors.
|
||
# Only enable for local debugging or trusted MITM/corporate proxy environments.
|
||
# Used by: open-sse/services/claudeTurnstileSolver.ts
|
||
# OMNIROUTE_TURNSTILE_IGNORE_TLS_ERRORS=false
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 9. CLI TOOL INTEGRATION
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Control how OmniRoute discovers and launches CLI sidecars (Claude, Codex, etc.).
|
||
# Used by: src/shared/services/cliRuntime.ts
|
||
|
||
# CLI discovery mode: auto = search PATH | manual = use explicit paths below.
|
||
# CLI_MODE=auto
|
||
|
||
# Additional PATH entries for finding CLI binaries (colon-separated).
|
||
# CLI_EXTRA_PATHS=/host-cli/bin:/usr/local/bin
|
||
|
||
# Home directory override for reading CLI config files (~/.claude, etc.).
|
||
# CLI_CONFIG_HOME=/root
|
||
|
||
# Allow OmniRoute to write CLI config files (token refresh, etc.).
|
||
# CLI_ALLOW_CONFIG_WRITES=true
|
||
|
||
# Force container detection on (1/true) or off (0/false). Leave unset for auto-detect
|
||
# via /.dockerenv, /run/.containerenv, cgroup markers, or KUBERNETES_SERVICE_HOST.
|
||
# Used by: src/shared/utils/containerEnv.ts — gates ephemeral-home CLI config writes.
|
||
# OMNIROUTE_CONTAINER=1
|
||
|
||
# Allow CLI-tool config writes into an unmounted container path anyway (default off).
|
||
# Prefer host-side `omniroute configure` / Remote Mode, or a bind-mounted CLI_CONFIG_HOME.
|
||
# CLI equivalent: --allow-container-write. Used by: src/shared/utils/containerEnv.ts
|
||
# OMNIROUTE_ALLOW_CONTAINER_CONFIG_WRITE=true
|
||
|
||
# Docker image only: dashboard "Update Now" writes a JSON update request to this file (it must
|
||
# be inside DATA_DIR; relative paths resolve against it). A host-side watcher pulls the image and
|
||
# recreates the container — no Docker socket is mounted. Unset = the dashboard shows the manual
|
||
# host command instead. Used by: src/lib/system/autoUpdate.ts (see docs/guides/DOCKER_GUIDE.md).
|
||
# DOCKER_UPDATE_TRIGGER_FILE=/app/data/update/docker-update.request
|
||
|
||
# Auto-sync CLI profile files after provider model discovery changes. OPT-IN, default OFF for
|
||
# both. When enabled, writes only the tool's profile files (~/.codex/*.config.toml or
|
||
# ~/.claude/profiles/<name>/settings.json); never changes the active/default config. Both also
|
||
# require CLI_ALLOW_CONFIG_WRITES (default on). Toggle from the CLI Code dashboard, or set here.
|
||
# Leave unset to disable. (Feature flags — a DB/dashboard override takes precedence over env.)
|
||
# OMNIROUTE_AUTO_SYNC_CODEX_PROFILES=true
|
||
# OMNIROUTE_AUTO_SYNC_CLAUDE_PROFILES=true
|
||
|
||
# Override binary paths for individual CLI tools.
|
||
# CLI_CLAUDE_BIN=claude
|
||
# CLI_CODEX_BIN=codex
|
||
# CLI_DROID_BIN=droid
|
||
# CLI_OPENCLAW_BIN=openclaw
|
||
# CLI_CURSOR_BIN=agent
|
||
# CLI_CLINE_BIN=cline
|
||
# CLI_CONTINUE_BIN=cn
|
||
# CLI_QODER_BIN=qodercli
|
||
# CLI_QWEN_BIN=qwen
|
||
# CLI_AIDER_BIN=aider
|
||
# CLI_GOOSE_BIN=goose
|
||
# CLI_GEMINI_BIN=gemini
|
||
# CLI_KILO_BIN=kilocode
|
||
# CLI_OPENCODE_BIN=opencode
|
||
# CLI_HERMES_BIN=hermes
|
||
# CLI_FORGE_BIN=forge
|
||
# CLI_JCODE_BIN=jcode
|
||
# CLI_DEEPSEEK_TUI_BIN=deepseek-tui
|
||
# CLI_CODEWHALE_BIN=codewhale
|
||
# CLI_SMELT_BIN=smelt
|
||
# CLI_PI_BIN=pi
|
||
# CLI_CRUSH_BIN=crush
|
||
# CLI_OMP_BIN=omp
|
||
# CLI_LETTA_BIN=letta
|
||
# CLI_PRIME_AGENT_BIN=prime-agent
|
||
# CLI_WHYCODES_BIN=whycodes
|
||
# Windsurf has no default binary — set this to enable binary detection for it.
|
||
# CLI_WINDSURF_BIN=windsurf
|
||
# CLI_AUGGIE_BIN=auggie
|
||
# CLI_5DIVE_BIN=5dive
|
||
# 5dive keeps root-owned auth profiles under a system state dir (its own STATE_DIR,
|
||
# default /var/lib/5dive); override here when it lives elsewhere.
|
||
# CLI_5DIVE_STATE_DIR=/var/lib/5dive
|
||
# AUGGIE_BIN=auggie
|
||
|
||
# ── ZCode (Z.ai GLM coding-plan CLI) local provider ──
|
||
# The local "zcode" provider talks to the authenticated ZCode app-server over a
|
||
# custom framed stdio protocol. Overrides below tune that stdio lifecycle.
|
||
# Transport: "app-server" (default) or "gateway". The gateway is EXPERIMENTAL and
|
||
# unsupported: it calls the Z.AI Coding Plan HTTP endpoint directly by reproducing
|
||
# the ZCode client protocol (pinned to client 0.16.9) and can break on a ZCode update.
|
||
# ZCODE_TRANSPORT=app-server
|
||
# ZCODE_BIN=zcode
|
||
# ZCODE_ARGS=["--some-flag"]
|
||
# ZCODE_CWD=
|
||
# If unset, native model selection uses the Individual Plan account profile and
|
||
# falls back to builtin:zai-coding-plan. Set an exact provider ID to pin one profile.
|
||
# ZCODE_PROVIDER_ID=account:zai-individual-coding-plan
|
||
# Examples: account:zai-start-plan or builtin:zai-coding-plan
|
||
# ZCODE_SERVER_RUNTIME_ROOT=~/.zcode/server
|
||
# ZCODE_SERVER_NODE=~/.zcode/server/node
|
||
# ZCODE_SERVER_ENTRY=~/.zcode/server/zcode-server.cjs
|
||
# ZCODE_STARTUP_TIMEOUT_MS=10000
|
||
# ZCODE_RPC_TIMEOUT_MS=30000
|
||
# ZCODE_TURN_TIMEOUT_MS=120000
|
||
# ZCODE_POLL_INTERVAL_MS=250
|
||
|
||
# ── MiniMax Code provider ──
|
||
# The "minimax-code" provider talks to the managed MiniMax subscription gateway
|
||
# (native tool calling) and keeps the credential in the user's own MiniMax
|
||
# profile (~/.minimax): it reads that profile to authenticate a request and
|
||
# writes the rotated credential back to it.
|
||
# Endpoint of the managed MiniMax gateway. This is an internal endpoint of
|
||
# the MiniMax Code app, not a documented public API: it can change without
|
||
# notice, and the request then fails with a 502 that names the transport.
|
||
# MINIMAX_CODE_GATEWAY_URL=https://agent.minimax.io/mavis/api/v1/llm/v1/messages
|
||
# MINIMAX_CODE_GATEWAY_TIMEOUT_MS=60000
|
||
# MINIMAX_CODE_GATEWAY_RETRIES=1
|
||
# Ceiling (in input tokens) of one request that is sent to the managed
|
||
# MiniMax gateway. A larger request is refused locally with a 413 instead
|
||
# of being forwarded. The default is the context window of the gateway
|
||
# (1000000, the window the gateway answers in); this value can lower that
|
||
# ceiling, never raise it above the window.
|
||
# MINIMAX_CODE_MAX_INPUT_TOKENS=1000000
|
||
# The context window the managed gateway is asked for. The default is the
|
||
# window the gateway answers in (1000000). Set it to 512000 to narrow the
|
||
# request to the window the MiniMax Code model catalog declares as the
|
||
# default of the models — the plan counts less of a request in it. Every
|
||
# other value is ignored.
|
||
# MINIMAX_CODE_CONTEXT_WINDOW=1000000
|
||
# MINIMAX_CODE_MAX_TOKENS=8192
|
||
# Path of the MiniMax Code auth profile, and of the profile directory it
|
||
# lives in.
|
||
# MINIMAX_CODE_AUTH_FILE=
|
||
# MINIMAX_CODE_PROFILE_DIR=
|
||
# Record of the profile to use when it holds several accounts. Empty picks
|
||
# the newest generation, which is the one the CLI itself refreshes.
|
||
# MINIMAX_CODE_AUTH_RECORD=
|
||
# Region of the MiniMax account: it decides the account endpoint that
|
||
# refreshes the token and the profile directory the credential is read from.
|
||
# MINIMAX_CODE_REGION=en
|
||
|
||
# Override the Hermes Agent home directory (where OmniRoute reads/writes the
|
||
# Hermes CLI config). Matches the env var the Hermes PowerShell installer sets
|
||
# on Windows (%LOCALAPPDATA%\hermes); defaults to ~/.hermes when unset.
|
||
# Used by: src/lib/cli-helper/config-generator/hermesHome.ts
|
||
# HERMES_HOME=~/.hermes
|
||
|
||
# Override the WhyCodes instance root (config.toml, sessions, memory). Same env
|
||
# var WhyCodes itself reads; defaults to ~/.whycodes (%USERPROFILE%\.whycodes on
|
||
# Windows) when unset.
|
||
# Used by: src/lib/cli-helper/config-generator/whycodesHome.ts
|
||
# WHYCODES_HOME=~/.whycodes
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 10. INTERNAL AGENT & MCP INTEGRATIONS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Used by MCP server, A2A skills, and CLI sidecars to call the running instance.
|
||
|
||
# Explicit base URL for MCP/A2A tools to reach OmniRoute (overrides localhost auto-detect).
|
||
# For browser-visible generated image URLs, prefer OMNIROUTE_PUBLIC_BASE_URL above.
|
||
# Used by: open-sse/mcp-server/server.ts, src/lib/a2a/
|
||
# OMNIROUTE_BASE_URL=http://localhost:20128
|
||
|
||
# API key for internal tool calls (MCP tools, A2A skills).
|
||
# OMNIROUTE_API_KEY=
|
||
|
||
# API key ID for MCP audit logging.
|
||
# Used by: open-sse/mcp-server/audit.ts — tags audit events with a key identity.
|
||
# OMNIROUTE_API_KEY_ID=
|
||
|
||
# Legacy alias for OMNIROUTE_API_KEY.
|
||
# ROUTER_API_KEY=
|
||
|
||
# Days of A2A task history to keep before the daily purge deletes a row.
|
||
# Used by: src/lib/a2a/taskManager.ts (historyRetentionDays). Unset, non-numeric,
|
||
# or <= 0 falls back to the default.
|
||
# OMNIROUTE_A2A_HISTORY_RETENTION_DAYS=30
|
||
|
||
# Kill-switch for the A2A memory-hits observability feature (Orchestration Canvas
|
||
# Fase 2). Set to "0" to skip the memory recall lookup entirely; any other value
|
||
# (including unset) keeps it enabled.
|
||
# Used by: src/lib/a2a/taskExecution.ts (collectMemoryHits).
|
||
# OMNIROUTE_A2A_MEMORY_HITS=1
|
||
|
||
# Enable the offline/local Issue Agent recorded-triage endpoint.
|
||
# Used by: src/app/api/issue-agent/runs/route.ts. Default: disabled.
|
||
# OMNIROUTE_ISSUE_AGENT_ENABLED=false
|
||
|
||
# Timeout (ms) for a single Issue Agent recorded-triage run. Clamped to an internal
|
||
# maximum; falls back to the built-in default when unset or invalid.
|
||
# Used by: src/lib/issueAgent/execution.ts.
|
||
# OMNIROUTE_ISSUE_AGENT_TIMEOUT_MS=
|
||
|
||
# CLI remote-mode context/profile for `omniroute` commands (overrides the active
|
||
# context in the local contexts store). Equivalent to the `--context <name>` flag.
|
||
# Used by: bin/cli/program.mjs, bin/cli/api.mjs (remote mode).
|
||
# OMNIROUTE_CONTEXT=
|
||
|
||
# Disable the optional OS keychain backend for CLI remote-context credentials.
|
||
# When enabled, context tokens stay in config.json with mode 0600 and the CLI
|
||
# prints a one-time fallback warning. Useful for deliberate headless/container
|
||
# operation; leave unset to use keytar when the native backend is available.
|
||
# Used by: bin/cli/contexts.mjs.
|
||
# OMNIROUTE_CONTEXT_KEYCHAIN_DISABLED=0
|
||
|
||
# Enforce scope-based access control on MCP tool calls.
|
||
# Used by: open-sse/mcp-server/server.ts — rejects calls outside allowed scopes.
|
||
# OMNIROUTE_MCP_ENFORCE_SCOPES=false
|
||
|
||
# Comma-separated scopes granted to this MCP connection.
|
||
# Full list: admin, combos, health, models, routing, budget, metrics, pricing, memory, skills
|
||
# OMNIROUTE_MCP_SCOPES=admin,combos,health
|
||
|
||
# Register the Perplexity Deep Research MCP tool. Unset or any value other
|
||
# than 1 leaves it unregistered. A research run holds one connection for up to
|
||
# 45 minutes, so it stays off unless an operator turns it on.
|
||
# Used by: open-sse/mcp-server/tools/perplexityResearch.ts.
|
||
# OMNIROUTE_PPLX_RESEARCH_ENABLED=0
|
||
|
||
# Compress MCP tool descriptions before serializing the manifest.
|
||
# Used by: open-sse/mcp-server/descriptionCompressor.ts — reduces token spend
|
||
# for clients that read the full tool catalog.
|
||
# Accepted disabling values: 0, false, off. Default: enabled.
|
||
# OMNIROUTE_MCP_COMPRESS_DESCRIPTIONS=1
|
||
|
||
# Algorithm/profile used when description compression is enabled.
|
||
# Used by: open-sse/mcp-server/descriptionCompressor.ts
|
||
# Set to 0/false/off to skip compression entirely. Default: rtk
|
||
# OMNIROUTE_MCP_DESCRIPTION_COMPRESSION=rtk
|
||
|
||
# Abort budget (ms) for MCP-server internal management reads (health, resilience,
|
||
# combos, quota, usage). Default: 10000. Used by: open-sse/mcp-server/fetchTimeout.ts
|
||
# OMNIROUTE_MCP_FETCH_TIMEOUT_MS=10000
|
||
|
||
# Abort budget (ms) for MCP hops that wait on a provider (route_request, web_search,
|
||
# web_fetch). Default: 60000. Used by: open-sse/mcp-server/fetchTimeout.ts
|
||
# OMNIROUTE_MCP_UPSTREAM_TIMEOUT_MS=60000
|
||
|
||
# Idle TTL (ms) before the sweep reaps an idle MCP streamable session. A session
|
||
# with an open stream or an in-flight request is never reaped. Unset,
|
||
# non-integer, or non-positive values fall back to the default. Default: 300000.
|
||
# Used by: open-sse/mcp-server/httpTransport.ts
|
||
# OMNIROUTE_MCP_SESSION_IDLE_MS=300000
|
||
|
||
# Maximum number of local-corpus index instances cached in memory.
|
||
# Used by: src/lib/localCorpus/configured.ts — bounds the LRU cache of
|
||
# LocalCorpusIndex objects (one per indexed root directory). Default: 5.
|
||
# OMNIROUTE_CORPUS_CACHE_SIZE=5
|
||
|
||
# Model catalog sync interval in hours.
|
||
# Used by: src/shared/services/modelSyncScheduler.ts — periodic model refresh.
|
||
# Default: 24
|
||
# MODEL_SYNC_INTERVAL_HOURS=6
|
||
|
||
# Provider limits sync interval in minutes (rate limit windows, quotas).
|
||
# Used by: src/lib/usage/providerLimits.ts — polls provider health endpoints.
|
||
# Default: 70
|
||
PROVIDER_LIMITS_SYNC_INTERVAL_MINUTES=70
|
||
|
||
# Gap (ms) between consecutive OAuth quota fetches in a bulk provider-limits sync.
|
||
# OAuth providers are fetched one at a time with this spacing so a single host
|
||
# never bursts simultaneous usage/refresh requests to the same upstream. Set to 0
|
||
# to opt out (restores fully concurrent fetches). Default: 1500
|
||
PROVIDER_LIMITS_SYNC_SPACING_MS=1500
|
||
|
||
# Min interval (ms) between consecutive UPSTREAM quota fetches on the per-request
|
||
# preflight/monitor path (e.g. Codex /wham/usage), complementing the bulk-sync
|
||
# spacing above. Many accounts on one IP fetching quota in the same second can look
|
||
# like automation to the upstream and get an OAuth token revoked (#6009). This gate
|
||
# serializes genuine network calls (cache hits are unaffected). Set to 0 to disable.
|
||
# Default: 250 (clamped 0..60000).
|
||
# OMNIROUTE_QUOTA_FETCH_MIN_INTERVAL_MS=250
|
||
# Extra random spacing (ms) per quota request. Default: 120 (clamped 0..60000).
|
||
# For multiple Codex accounts, increase the minimum interval first; jitter adds
|
||
# unpredictable spacing. This cannot guarantee the upstream won't revoke a token.
|
||
# OMNIROUTE_QUOTA_FETCH_JITTER_MS=120
|
||
|
||
# Timeout (ms) for one Codex quota fetch (chatgpt.com /wham/usage). The preflight
|
||
# waits for this fetch before sending the request. On a timeout the last recent
|
||
# snapshot is reused unless its window is exhausted or has reset; with none, the
|
||
# quota is unknown, not exhausted. Raise it on slow links. Positive integer.
|
||
# Default: 8000
|
||
# CODEX_QUOTA_FETCH_TIMEOUT_MS=8000
|
||
|
||
# Delay (ms) before refreshing provider limits after a real usage event (e.g. a
|
||
# completed request). Gives the upstream quota API time to register the consumption
|
||
# before the dashboard polls. Default: 5000
|
||
#PROVIDER_LIMITS_POST_USAGE_REFRESH_DELAY_MS=5000
|
||
|
||
# Disable all background services (sync, pricing, model refresh, connection recovery,
|
||
# credential health, retention cleanup, scheduled VACUUM, settings hot-reload poll).
|
||
# Used by: src/lib/env/backgroundServices.ts, src/lib/initCloudSync.ts
|
||
# Useful for: CI builds, test environments, or resource-constrained containers.
|
||
# OMNIROUTE_DISABLE_BACKGROUND_SERVICES=false
|
||
# Source directory for the explicit --prepare Video Bridge validation command.
|
||
# Must be an absolute directory containing storage.sqlite. The source is opened
|
||
# read-only; copied credentials and test keys stay in a private temporary directory.
|
||
# Used only by: scripts/ad-hoc/video-live-isolation.ts (not normal server startup).
|
||
# OMNIROUTE_VIDEO_LIVE_SOURCE_DIR=
|
||
|
||
# Headless mode (R0.1): boot only the proxy engine (/v1/*, /api/monitoring/health,
|
||
# auth). Optional boot subsystems are skipped and /dashboard + /home answer 404.
|
||
# Same as `omniroute serve --headless`. See docs/guides/HEADLESS.md.
|
||
# Used by: src/lib/system/headless.ts. Default: unset (full server).
|
||
# OMNIROUTE_HEADLESS=1
|
||
|
||
# Force runtime background tasks (healthchecks/sync) even under automated test
|
||
# detection. Used by: src/lib/config/runtimeSettings.ts — overrides the test
|
||
# heuristic in instrumentation-node.ts. Default: unset (tests skip background).
|
||
#OMNIROUTE_ENABLE_RUNTIME_BACKGROUND_TASKS=1
|
||
|
||
# Proactive connection-cooldown recovery (#8): re-validates connections whose
|
||
# transient `rate_limited_until` window has elapsed OUTSIDE the request hot path,
|
||
# so the first request after a cooldown does not pay the probe latency. Lazy
|
||
# recovery in getProviderCredentials still applies regardless. Used by:
|
||
# src/lib/quota/connectionRecovery.ts.
|
||
# Tick cadence (ms). Default 60000, floor 5000.
|
||
# OMNIROUTE_CONNECTION_RECOVERY_INTERVAL_MS=60000
|
||
# Disable the proactive recovery scheduler entirely (default: false).
|
||
# OMNIROUTE_DISABLE_CONNECTION_RECOVERY=false
|
||
|
||
# Proactive Claude warmup scheduler (#8848): fires a trivial request to opted-in
|
||
# OAuth connections on a cron schedule (America/Los_Angeles) so accounts do not
|
||
# hit the 5-hour sliding window cold. Off by default — set ENABLED=1 and flip
|
||
# per-connection flags in settings.claudeWarmup.connections to activate.
|
||
# Used by: src/lib/warmupScheduler.ts.
|
||
# OMNIROUTE_WARMUP_ENABLED=false
|
||
# OMNIROUTE_WARMUP_CRON="0 7 * * *"
|
||
# OMNIROUTE_WARMUP_CONCURRENCY=3
|
||
# OMNIROUTE_WARMUP_MODEL=
|
||
|
||
# Background job interval for budget reset checks (ms). Default: 600000 (10m).
|
||
# Used by: src/lib/jobs/budgetResetJob.ts. Floor: 10000.
|
||
#OMNIROUTE_BUDGET_RESET_JOB_INTERVAL_MS=600000
|
||
|
||
# Cron expression for the call-log export job (destinations configured in the
|
||
# dashboard under Integrations > Log export). Default: hourly, on the hour.
|
||
# Used by: src/lib/jobs/logExportJob.ts. Timezone: UTC.
|
||
#OMNIROUTE_LOG_EXPORT_CRON=0 * * * *
|
||
|
||
# Isolated log-export child: per-destination wall-clock timeout and V8 old-space cap.
|
||
# Prefer a minute-level cron (e.g. */5 * * * *) when exporting request/response bodies.
|
||
# Used by: src/lib/logExport/childRunner.ts. Positive integers only; invalid values use defaults.
|
||
#OMNIROUTE_LOG_EXPORT_RUN_TIMEOUT_MS=900000
|
||
#OMNIROUTE_LOG_EXPORT_CHILD_MAX_OLD_SPACE_MB=1024
|
||
|
||
# Emergency budget-exhaustion fallback (set false or 0 to disable the reroute to
|
||
# nvidia/nvidia/nemotron-3.5-super-vl-120b-a12b when a request fails with a 402 budget error).
|
||
# Used by: open-sse/services/emergencyFallback.ts. Default: enabled.
|
||
#OMNIROUTE_EMERGENCY_FALLBACK=true
|
||
|
||
# Reasoning cache cleanup cadence (ms). Default: 1800000 (30m). Floor: 60000.
|
||
# Used by: src/lib/jobs/reasoningCacheCleanupJob.ts.
|
||
#OMNIROUTE_REASONING_CACHE_CLEANUP_INTERVAL_MS=1800000
|
||
|
||
# Recover from a reasoning_effort 4xx whose body names no accepted set, by
|
||
# probing one tier down and learning that tier when the probe is answered.
|
||
# Comma-separated provider ids, or * for all. Default: unset (disabled).
|
||
# Off by default because an opaque 4xx carries no signal that the *effort* was
|
||
# the cause — a 2xx on the probe could mask an unrelated validation failure and
|
||
# pin a reasoning cap that was never proven. Upstreams that DO name their
|
||
# accepted set are already handled without this flag.
|
||
#OMNIROUTE_REASONING_EFFORT_PROBE_PROVIDERS=
|
||
|
||
# Opt-in minimum output budget (tokens) for reasoning models (#10281 follow-up).
|
||
# When set, a caller max_tokens in [256, floor) on a thinking-capable model is
|
||
# raised to the floor so reasoning tokens cannot consume the whole budget
|
||
# (zero-content finish_reason=length turns). Unset = never enlarge client budgets (#9507).
|
||
#OMNIROUTE_REASONING_MIN_BUDGET=4096
|
||
|
||
# Spend write batcher cadence (ms) and buffer size before forced flush.
|
||
# Used by: src/lib/spend/batchWriter.ts. Defaults: 60000 ms / 1000 entries.
|
||
#OMNIROUTE_SPEND_FLUSH_INTERVAL_MS=60000
|
||
#OMNIROUTE_SPEND_MAX_BUFFER_SIZE=1000
|
||
|
||
# Batch request processor retry, backoff, and concurrency settings.
|
||
# Used by: open-sse/services/batchProcessor.ts. Defaults shown.
|
||
#BATCH_RETRY_DURATION_MS=86400000
|
||
#BATCH_BACKOFF_BASE_MS=5000
|
||
#BATCH_BACKOFF_MAX_MS=3600000
|
||
#BATCH_MAX_CONCURRENT=1
|
||
|
||
# Config hot-reload polling interval (ms). Default: 5000.
|
||
# Used by: src/lib/config/hotReload.ts. Lower than 1000ms is rejected.
|
||
#OMNIROUTE_CONFIG_HOT_RELOAD_MS=5000
|
||
|
||
# Override the migrations directory used by src/lib/db/migrationRunner.ts.
|
||
# Default: <repo>/src/lib/db/migrations.
|
||
#OMNIROUTE_MIGRATIONS_DIR=
|
||
|
||
# Additional migration directories, as `namespace=dir` entries separated by the
|
||
# platform path delimiter (`:` on POSIX, `;` on Windows). Files found there are
|
||
# recorded as `<namespace>-<number>` (e.g. `ee-134`), a version space that cannot
|
||
# collide with the upstream numeric slots — so a distribution shipping its own
|
||
# migrations never silently loses one to a number the upstream set also claimed.
|
||
# A malformed entry, an invalid namespace or a missing directory aborts startup
|
||
# rather than skipping the schema. Unset = no extra directories (the default).
|
||
#OMNIROUTE_EXTRA_MIGRATIONS_DIRS=ee=/opt/app/enterprise/db/migrations
|
||
|
||
# Mass-pending-migrations safety threshold (#3416). If more than this many
|
||
# migrations are pending on an existing DB, startup aborts (a wiped tracking
|
||
# table could cause data loss). Raise it to restore an older backup; set to 0
|
||
# to disable the check. Used by: src/lib/db/migrationRunner.ts. Default: 50.
|
||
#OMNIROUTE_MAX_PENDING_MIGRATIONS=50
|
||
|
||
# Working directory for the check:install-upgrade release gate. It builds two ~3 GB
|
||
# install trees plus a ~275 MB tarball, so it needs roughly 12 GB — more than the
|
||
# 12 GB RAM-backed tmpfs that /tmp is on the self-hosted runner, where it exhausted
|
||
# the tmpfs and npm silently truncated the package. Defaults to <repo>/.install-upgrade
|
||
# on real disk. Used by: scripts/check/check-install-upgrade.mjs. Default: <repo>/.install-upgrade.
|
||
#OMNIROUTE_INSTALL_UPGRADE_WORKDIR=/var/tmp/omniroute-install-upgrade
|
||
|
||
# Trust user-managed RTK project filter rules without strict signature checks.
|
||
# Used by: open-sse/services/compression/engines/rtk/filterLoader.ts. Default: 0.
|
||
#OMNIROUTE_RTK_TRUST_PROJECT_FILTERS=0
|
||
|
||
# Character cap for Lite proactive tool-result truncation when lite.maxToolLength
|
||
# is unset. Range 256-1000000. Dashboard setting wins over this env.
|
||
# Used by: open-sse/services/compression/lite.ts. Default: 2000.
|
||
#OMNIROUTE_LITE_MAX_TOOL_LENGTH=2000
|
||
|
||
# Maximum concurrent synchronous compression workers. Excess jobs wait FIFO.
|
||
# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 2.
|
||
#OMNI_COMPRESSION_WORKERS=2
|
||
# Per-job worker timeout (ms). A timed-out worker is terminated and the request fails open.
|
||
# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 120000.
|
||
#OMNI_COMPRESSION_WORKER_TIMEOUT_MS=120000
|
||
# Terminate idle compression workers after this many milliseconds.
|
||
# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 60000.
|
||
#OMNI_COMPRESSION_WORKER_IDLE_MS=60000
|
||
# V8 old-generation heap cap (MB) for each compression worker (all modes; floor 128). A job that
|
||
# exceeds it fails open (request goes upstream uncompressed) instead of growing the gateway heap.
|
||
# Used by: open-sse/services/compression/compressionWorkerPool.ts. Default: 1024.
|
||
#OMNI_COMPRESSION_WORKER_MAX_OLD_MB=1024
|
||
|
||
# T02 stacked-pipeline engine circuit-breaker (OPT-IN, default off). When enabled, a compression
|
||
# engine that throws repeatedly across requests is skipped (fail-open) for a cooldown.
|
||
# Used by: open-sse/services/compression/pipelineEngineBreaker.ts.
|
||
#COMPRESSION_PIPELINE_BREAKER_ENABLED=false # master switch (default false)
|
||
#COMPRESSION_PIPELINE_BREAKER_THRESHOLD=3 # consecutive failures before the engine opens
|
||
#COMPRESSION_PIPELINE_BREAKER_COOLDOWN_MS=30000 # ms the engine stays skipped before a probe
|
||
|
||
# T08/H8 — CCR retrieval-feedback ramp factor. Each prior retrieval of a stored block raises its
|
||
# effective minChars linearly, so frequently-retrieved content is compressed progressively less
|
||
# (>= 3 retrievals = never compressed). 1 disables the ramp (binary skip at the threshold only).
|
||
# Used by: open-sse/services/compression/engines/ccr/index.ts. Default: 2.
|
||
#COMPRESSION_CCR_RETRIEVAL_RAMP_FACTOR=2
|
||
# CCR durable block store (#9061). The in-memory store loses blocks to LRU eviction, the TTL, a
|
||
# restart, or a retrieve landing on another instance, while the model is told it can retrieve them
|
||
# verbatim. Set to false to keep blocks in memory only, at the cost of that promise. Blocks over
|
||
# 512KB and cloud runtimes are memory-only regardless.
|
||
# Used by: open-sse/services/compression/engines/ccr/index.ts. Default: true.
|
||
#COMPRESSION_CCR_DURABLE_STORE=true
|
||
# T08/H5 — usage-observed prefix freeze (OPT-IN, default off). When enabled, a system prompt seen
|
||
# >= THRESHOLD times is treated as a stable cacheable prefix and preserved from compression even
|
||
# for providers the static cache-aware heuristic does not recognize (freeze = preserve, never
|
||
# mutates). Used by: open-sse/services/compression/prefixFreeze.ts.
|
||
#COMPRESSION_PREFIX_FREEZE_ENABLED=false # master switch (default false)
|
||
#COMPRESSION_PREFIX_FREEZE_THRESHOLD=3 # observations before a prefix is frozen
|
||
|
||
# Skip the postinstall native-runtime warm-up (useful in CI / headless installs). Default: 0.
|
||
# Used by: scripts/postinstall.mjs.
|
||
#OMNIROUTE_SKIP_POSTINSTALL=0
|
||
|
||
# Operator-supplied JSON credentials for the offline compression-eval CLI
|
||
# (parsed with JSON.parse; leave unset for a dry run). Developer tooling only.
|
||
# Used by: scripts/compression-eval/index.ts. Default: {} (empty).
|
||
#OMNIROUTE_EVAL_CREDENTIALS={}
|
||
|
||
# Skip the DB healthcheck entirely on startup (useful for short-lived tasks / tests).
|
||
# Used by: src/lib/db/core.ts, src/lib/db/healthCheck.ts. Set to 1 to disable. Default: 0.
|
||
#OMNIROUTE_SKIP_DB_HEALTHCHECK=0
|
||
|
||
# Force a DB healthcheck regardless of cadence. Default: 0.
|
||
# Used by: src/lib/db/core.ts::shouldRunDbHealthCheck().
|
||
#OMNIROUTE_FORCE_DB_HEALTHCHECK=0
|
||
|
||
# DB healthcheck cadence override (ms). Default: 21600000 (6h).
|
||
# Used by: src/lib/db/core.ts::getDbHealthCheckIntervalMs().
|
||
#OMNIROUTE_DB_HEALTHCHECK_INTERVAL_MS=21600000
|
||
|
||
# Removed: periodic live wal_checkpoint(TRUNCATE) could SIGBUS the process (issue
|
||
# #13973). The variable is inert: a positive value logs a one-time deprecation warning,
|
||
# while 0 or unset stays silent. The WAL is kept small
|
||
# by the PASSIVE scheduler below and truncated by the shutdown checkpoint.
|
||
#OMNIROUTE_WAL_TRUNCATE_INTERVAL_MS=21600000
|
||
|
||
# Frequent wal_checkpoint(PASSIVE) cadence (ms). Set to 0 to disable. Default: 300000 (5m).
|
||
# Used by: src/lib/db/walMaintenance.ts.
|
||
#OMNIROUTE_WAL_PASSIVE_INTERVAL_MS=300000
|
||
|
||
# WAL size (MB) above which a PASSIVE tick runs wal_checkpoint(RESTART) so the
|
||
# WAL starts over without rewriting the mapped wal-index. Default: 256.
|
||
# Used by: src/lib/db/walMaintenance.ts.
|
||
#OMNIROUTE_WAL_GUARD_MAX_MB=256
|
||
|
||
# Explicit path to sql-wasm.wasm for the sql.js fallback adapter. Default: auto-detect.
|
||
# Used by: src/lib/db/adapters/sqljsAdapter.ts.
|
||
#OMNIROUTE_SQLJS_WASM_PATH=
|
||
# Days a terminal (completed/failed/cancelled/expired) Batch API job's checkpoints,
|
||
# referenced files, and row are kept by the automatic cleanup sweep. Default: 30
|
||
# (matches OpenAI's own Batch API output retention window). Only takes effect once
|
||
# BATCH_AND_FILE_AUTO_CLEANUP_ENABLED is turned on.
|
||
# Used by: src/lib/db/cleanup.ts::getBatchRetentionDays().
|
||
#OMNIROUTE_BATCH_RETENTION_DAYS=30
|
||
|
||
# Let the automatic cleanup sweep delete terminal Batch API jobs (and their
|
||
# checkpoints) past OMNIROUTE_BATCH_RETENTION_DAYS, and clear the content of
|
||
# uploaded files past their own expires_at. Off by default: every existing
|
||
# install keeps this data exactly as before until an operator opts in.
|
||
# Used by: src/lib/db/cleanup.ts (feature flag; see docs/reference/FEATURE_FLAGS.md).
|
||
#BATCH_AND_FILE_AUTO_CLEANUP_ENABLED=false
|
||
|
||
# Skip the Redis-backed auth cache used by API key lookups (forces DB reads).
|
||
# Used by: src/lib/db/apiKeys.ts. Set to 1 to disable. Default: enabled.
|
||
#OMNIROUTE_DISABLE_REDIS_AUTH_CACHE=0
|
||
|
||
# Flag set by bootstrap script after initial setup is complete.
|
||
# Used by: src/app/(dashboard)/dashboard/page.tsx — shows setup wizard vs. dashboard.
|
||
# OMNIROUTE_BOOTSTRAPPED=false
|
||
|
||
# Allow request body to override the Antigravity project field.
|
||
# Used by: open-sse/executors/antigravity.ts — escape hatch for multi-project setups.
|
||
# OMNIROUTE_ALLOW_BODY_PROJECT_OVERRIDE=0
|
||
|
||
# Control Antigravity Google One AI credit usage. Used by:
|
||
# open-sse/services/antigravityCredits.ts — accepts off, retry, or always.
|
||
# off (default): never use credits; retry: use credits once after eligible quota 429;
|
||
# always: use credits on the first request (higher account and spend risk).
|
||
#ANTIGRAVITY_CREDITS=off
|
||
|
||
# Upstream 429s tolerated per Antigravity (agy/antigravity) request, across all
|
||
# hosts, before the 429 is returned to the caller (1..12). A request body that
|
||
# spent this budget is answered locally on re-send for 2 min (doubling up to
|
||
# 30 min, or the upstream retry hint) so a client retry loop never reaches Google.
|
||
# Used by: open-sse/services/antigravity429Guard.ts. Default: 2.
|
||
#ANTIGRAVITY_MAX_429_ATTEMPTS=2
|
||
|
||
# Preferred API-key account response-start failover (opt-in, all providers).
|
||
# Only when an eligible sibling exists; one hop, no shared-account cooldown.
|
||
# Default: 20s; Antigravity/agy: 5s; Antigravity Gemini 3.8 Flash: 12s.
|
||
# Per-provider and per-model overrides are available in Settings > Resilience.
|
||
# An environment change requires restart; saved UI settings do not.
|
||
# OMNIROUTE_PREFERRED_ACCOUNT_FAILOVER_ENABLED=false
|
||
|
||
# Override the path to the Antigravity CLI (agy) token file read by the
|
||
# "auto-detect local login" import. Used by:
|
||
# src/app/api/providers/agy-auth/apply-local/route.ts — for non-standard installs.
|
||
# Default: ~/.gemini/antigravity-cli/antigravity-oauth-token
|
||
#AGY_TOKEN_FILE=
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 11. OAUTH PROVIDER CREDENTIALS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Built-in default credentials for localhost development.
|
||
# For remote/VPS deployments, register your own at each provider's developer console.
|
||
# The bootstrap-env script auto-populates these in .env if missing.
|
||
# Can also be overridden via data/provider-credentials.json where supported.
|
||
|
||
# ── Claude Code (Anthropic) ──
|
||
CLAUDE_OAUTH_CLIENT_ID=9d1c250a-e61b-44d9-88ed-5944d1962f5e
|
||
# Custom redirect URI override for Claude OAuth callback.
|
||
# CLAUDE_CODE_REDIRECT_URI=https://platform.claude.com/oauth/code/callback
|
||
|
||
# ── Codex / OpenAI ──
|
||
CODEX_OAUTH_CLIENT_ID=app_EMoamEEZ73f0CkXaXp7hrann
|
||
|
||
# Milliseconds to wait between consecutive Codex token refreshes.
|
||
# Used by: open-sse/services/refreshSerializer.ts. Default: 0 (no spacing).
|
||
# CODEX_REFRESH_SPACING_MS=0
|
||
|
||
# ── Trae (ByteDance) ──
|
||
# Trae stream idle timeout (ms). Default: 300000 (5 min).
|
||
# Used by: open-sse/executors/trae.ts.
|
||
# TRAE_STREAM_TIMEOUT_MS=300000
|
||
|
||
# Trae OAuth token override. Used by: open-sse/executors/trae.ts.
|
||
# TRAE_TOKEN=
|
||
|
||
# Trae web client Origin/Referer override (fleet-wide bump if Trae moves hosts
|
||
# again without a code change). Default: https://work.trae.ai.
|
||
# Used by: open-sse/executors/trae.ts.
|
||
# TRAE_WEB_ORIGIN=https://work.trae.ai
|
||
|
||
# ── Gemini / Antigravity (Google-based) ──
|
||
# These providers ship public OAuth client_id/secret values embedded in their
|
||
# public CLIs. Defaults are baked into the code via
|
||
# open-sse/utils/publicCreds.ts — leave the env vars unset to use them. Only
|
||
# set these if you registered your own OAuth app and want to use your own
|
||
# credentials instead. See docs/security/PUBLIC_CREDS.md for context.
|
||
#
|
||
# GEMINI_OAUTH_CLIENT_ID=
|
||
# GEMINI_OAUTH_CLIENT_SECRET=
|
||
# ANTIGRAVITY_OAUTH_CLIENT_ID=
|
||
# ANTIGRAVITY_OAUTH_CLIENT_SECRET=
|
||
|
||
# ── Kimi Coding (Moonshot) ──
|
||
KIMI_CODING_OAUTH_CLIENT_ID=17e5f671-d194-4dfb-9706-5516cb48c098
|
||
|
||
# ── Muse Code (Meta) ──
|
||
# Public device-flow client id is baked into open-sse/utils/publicCreds.ts (muse_id).
|
||
# Set this only to override the Muse CLI client. Do not put the public id here.
|
||
# MUSE_CODE_OAUTH_CLIENT_ID=
|
||
|
||
# ── GitHub Copilot ──
|
||
GITHUB_OAUTH_CLIENT_ID=Iv1.b507a08c87ecfe98
|
||
|
||
# ── GitHub Enterprise (GHE) Copilot ──
|
||
# Optional override for GHE Copilot's OAuth client id. Falls back to the public
|
||
# GITHUB_OAUTH_CLIENT_ID default when unset. Used by: src/lib/oauth/constants/oauth.ts.
|
||
# GHE_COPILOT_OAUTH_CLIENT_ID=
|
||
|
||
# ── GitLab Duo ──
|
||
# Register an OAuth app at: https://gitlab.com/-/profile/applications
|
||
# Set redirect URI to: http://localhost:20128/callback (or your NEXT_PUBLIC_BASE_URL + /callback)
|
||
# Required scopes: ai_features, read_user (matches GITLAB_DUO_CONFIG.scope in src/lib/oauth/constants/oauth.ts)
|
||
# GITLAB_DUO_OAUTH_CLIENT_ID=***
|
||
# GITLAB_DUO_OAUTH_CLIENT_SECRET=*** # optional — PKCE flow does not require a secret
|
||
#
|
||
# Self-managed GitLab Duo instance overrides.
|
||
# Used by: src/lib/oauth/gitlab.ts and src/lib/oauth/constants/oauth.ts —
|
||
# fall back to these when the _DUO_ variants above are unset.
|
||
#GITLAB_DUO_BASE_URL=https://gitlab.com
|
||
#GITLAB_BASE_URL=https://gitlab.com
|
||
#GITLAB_OAUTH_CLIENT_ID=
|
||
#GITLAB_OAUTH_CLIENT_SECRET=
|
||
|
||
# ── Qoder ──
|
||
# Public OAuth client secret embedded in the Qoder CLI binary. Required only
|
||
# when QODER_OAUTH_AUTHORIZE_URL / TOKEN_URL / USERINFO_URL / CLIENT_ID are
|
||
# also set (see QODER_CONFIG.enabled in src/lib/oauth/constants/oauth.ts).
|
||
# Extract the value from the public Qoder CLI binary if you intend to use it.
|
||
# QODER_OAUTH_CLIENT_SECRET=
|
||
|
||
# ── Qoder Browser OAuth (experimental) ──
|
||
# OmniRoute only enables the browser OAuth flow when ALL 5 variables below are set:
|
||
# - QODER_OAUTH_AUTHORIZE_URL
|
||
# - QODER_OAUTH_TOKEN_URL
|
||
# - QODER_OAUTH_USERINFO_URL
|
||
# - QODER_OAUTH_CLIENT_ID
|
||
# - QODER_OAUTH_CLIENT_SECRET
|
||
#
|
||
# Redirect URI to register in the Qoder OAuth app:
|
||
# - Localhost dev with PORT=20128: http://localhost:20128/callback
|
||
# - LAN access (example): http://192.168.0.15:20128/callback
|
||
# - Public domain (recommended): https://omniroute.example.com/callback
|
||
#
|
||
# Behind reverse proxy / public domain, also set NEXT_PUBLIC_BASE_URL to the same public origin.
|
||
# If these values are not available, prefer QODER_PERSONAL_ACCESS_TOKEN below.
|
||
# QODER_OAUTH_AUTHORIZE_URL=
|
||
# QODER_OAUTH_TOKEN_URL=
|
||
# QODER_OAUTH_USERINFO_URL=
|
||
# QODER_OAUTH_CLIENT_ID=
|
||
# QODER_OAUTH_CLIENT_SECRET=
|
||
|
||
# ── Qoder Personal Access Token (direct API key fallback) ──
|
||
# Used by: open-sse/executors/qoder.ts — bypasses OAuth when set.
|
||
# QODER_PERSONAL_ACCESS_TOKEN=
|
||
# QODER_CLI_WORKSPACE=
|
||
# OMNIROUTE_QODER_WORKSPACE=
|
||
# Override the Qoder CLI config dir (isolated PAT session, avoids clobbering a browser login).
|
||
# QODER_CLI_CONFIG_DIR=
|
||
# Every qodercli --print run is a separate ~750 MB Node process. Set a cap to
|
||
# bound how many run at once (others queue FIFO) and how long a request may wait
|
||
# for a slot (then 429 qodercli_busy + Retry-After). Unset = no cap (default).
|
||
# QODER_CLI_MAX_CONCURRENCY=2
|
||
# QODER_CLI_QUEUE_TIMEOUT_MS=120000
|
||
# "acp" keeps one persistent `qodercli --acp` process per PAT and runs each request
|
||
# as an ACP session instead of spawning qodercli per request (default: print).
|
||
# QODER_CLI_TRANSPORT=print
|
||
# QODER_CLI_ACP_IDLE_TIMEOUT_MS=600000
|
||
# QODER_CLI_ACP_STARTUP_TIMEOUT_MS=60000
|
||
# QODER_CLI_ACP_MAX_SESSIONS_PER_PROCESS=500
|
||
|
||
# ── Blackbox Web validated-token override (issue #2252) ──
|
||
# Used by: open-sse/executors/blackbox-web.ts. Blackbox `/api/chat` rejects
|
||
# requests whose `validated` field doesn't match the frontend `tk` token,
|
||
# returning HTTP 403 even with a valid session cookie + active subscription.
|
||
# Set this to the `tk` value exported from app.blackbox.ai's Next.js bundle
|
||
# to bypass the random-UUID fallback. Leave empty to keep the legacy behavior.
|
||
# BLACKBOX_WEB_VALIDATED_TOKEN=
|
||
|
||
# ── Vision Bridge OpenAI-compatible endpoint override (issue #2232) ──
|
||
# Used by: src/lib/guardrails/visionBridgeHelpers.ts. By default the
|
||
# vision-bridge guardrail sends non-Anthropic image-description calls to
|
||
# `https://api.openai.com/v1`, which fails with 401 if your operator doesn't
|
||
# have an OpenAI key or wants to use a different vision model
|
||
# (e.g., `google/gemini-2.0-flash` via the Gemini OpenAI-compat endpoint, or
|
||
# any model registered in OmniRoute via the self-loop endpoint).
|
||
#
|
||
# Set these two env vars to point the bridge at any OpenAI-compatible URL:
|
||
# - VISION_BRIDGE_BASE_URL=http://localhost:20128/v1 (OmniRoute self-loop)
|
||
# - VISION_BRIDGE_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai
|
||
# - VISION_BRIDGE_BASE_URL=https://openrouter.ai/api/v1
|
||
# Anthropic models (anthropic/*) keep their dedicated path and are unaffected.
|
||
# VISION_BRIDGE_BASE_URL=
|
||
# VISION_BRIDGE_API_KEY=
|
||
|
||
# How long a "no usable vision candidate" outcome is remembered, in ms.
|
||
# Invalid or negative values fall back to the default; 0 disables the negative cache.
|
||
# OMNIROUTE_VISION_BRIDGE_NEGATIVE_CACHE_MS=30000
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# ⚠️ GOOGLE OAUTH (Antigravity) & OTHER PROVIDERS — REMOTE SERVERS
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# The default Client IDs above ONLY work when OmniRoute runs on localhost.
|
||
# For remote/VPS hosting (including Docker containers on remote servers):
|
||
# 1. By default, the browser will attempt OAuth redirects back to localhost, which will fail.
|
||
# 2. Set NEXT_PUBLIC_BASE_URL=https://your-domain.com to fix the redirect URI.
|
||
# 3. You MUST create your own OAuth App in each provider's developer console (Google Cloud, etc.)
|
||
# and set the Authorized redirect URI to your domain (e.g., https://your-domain.com/callback).
|
||
# 4. Replace the _OAUTH_CLIENT_ID and _SECRET values above with your own credentials.
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
|
||
# ── OAuth sidecar/CLI bridge (internal) ──
|
||
# Used by: src/lib/oauth/config/index.ts — internal CLI↔OmniRoute auth bridge.
|
||
# OMNIROUTE_SERVER=http://localhost:20128
|
||
# OMNIROUTE_TOKEN=
|
||
# OMNIROUTE_USER_ID=cli
|
||
# CLI_TOKEN= # legacy alias for OMNIROUTE_TOKEN
|
||
# CLI_USER_ID= # legacy alias for OMNIROUTE_USER_ID
|
||
# SERVER_URL= # legacy alias for OMNIROUTE_SERVER
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 12. PROVIDER USER-AGENT OVERRIDES
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Customize the User-Agent header sent to each upstream provider.
|
||
# Format: {PROVIDER_ID}_USER_AGENT=custom-value
|
||
# Used by: open-sse/executors/base.ts — buildHeaders() dynamic lookup.
|
||
# Update these when providers release new CLI versions to avoid blocks.
|
||
|
||
# Optional override (leave unset: the built-in pinned version is used; prefer CLAUDE_CODE_CLIENT_VERSION).
|
||
# A claude-cli/X.Y.Z value older than the pinned version is ignored at runtime (#15740).
|
||
# CLAUDE_USER_AGENT="claude-cli/2.1.280 (external, cli)"
|
||
|
||
# Disable the deterministic tool-name cloak applied on both Anthropic-bound paths
|
||
# (executors/base.ts native OAuth + executors/cliproxyapi.ts CLIProxyAPI) —
|
||
# third-party-harness tool names are aliased to
|
||
# Claude Code canonical or PascalCase forms so Anthropic does not refuse the
|
||
# stream with a misleading 400 out-of-extra-usage placeholder. Set to true to
|
||
# forward the original names verbatim (debugging only).
|
||
# CLAUDE_DISABLE_TOOL_NAME_CLOAK=false
|
||
# Optional override; leave unset to follow the shared Codex client version.
|
||
# CODEX_USER_AGENT="codex-cli/0.155.0 (Windows 10.0.26200; x64)"
|
||
GITHUB_USER_AGENT="GitHubCopilotChat/0.54.0"
|
||
# Optional override for the Antigravity CLI (`agy`) build changelist reported as `cl=` in
|
||
# the CLI User-Agent. Google's Piper changelist is not derivable from the version and is not
|
||
# exposed by the public auto-updater manifests, so it is seeded from a live capture per
|
||
# version (1.4.4 -> 1003595037). Unset on an unknown version omits `cl=` entirely rather
|
||
# than advertising another build's changelist.
|
||
# ANTIGRAVITY_CLI_CL=1003595037
|
||
KIRO_USER_AGENT="AWS-SDK-JS/3.0.0 kiro-ide/1.0.0"
|
||
# KIRO_VERIFY_FULL_CRC=false # opt-in: full per-frame message CRC validation on the Kiro event stream (debug corrupted streams; prelude CRC + TLS already protect framing)
|
||
# Optional override for the Kiro social device-code OAuth clientId. Kiro's
|
||
# device endpoint accepts any non-empty string and behaves like a User-Agent
|
||
# rather than a secret. Only override if AWS ever starts enforcing this field.
|
||
# Used by: src/lib/oauth/constants/oauth.ts (KIRO_CONFIG.socialClientId).
|
||
# KIRO_OAUTH_CLIENT_ID=kiro-cli
|
||
# Enable full per-frame message CRC validation for Kiro streams. Off by default
|
||
# because it is O(frame bytes) on the main thread; use only for debugging
|
||
# suspected corrupted-stream issues.
|
||
# Used by: open-sse/executors/kiro.ts
|
||
# KIRO_VERIFY_FULL_CRC=false
|
||
# USD price of one Kiro credit. Kiro bills each request in credits reported by
|
||
# `meteringEvent` frames; they are converted with this price into the exact
|
||
# per-request cost used by quotas, budgets and analytics.
|
||
# Used by: open-sse/executors/kiroCredits.ts
|
||
# KIRO_CREDIT_PRICE_USD=0.02
|
||
# Fail a Kiro response that ends without credit metering (and validate every
|
||
# metering frame strictly) instead of recording it with no billable cost.
|
||
# Used by: open-sse/executors/kiro.ts
|
||
# KIRO_REQUIRE_CREDITS=false
|
||
QODER_USER_AGENT="Qoder-Cli"
|
||
CURSOR_USER_AGENT="Cursor/3.4"
|
||
|
||
# Override Codex client version sent in headers independently of the
|
||
# CODEX_USER_AGENT string. Used by: open-sse/config/codexClient.ts.
|
||
# CODEX_CLIENT_VERSION=0.155.0
|
||
#
|
||
# Override x-grok-client-version for inference, model sync, and device-code OAuth,
|
||
# plus the default User-Agent for inference and model sync. Accepts SemVer (including
|
||
# prerelease/build metadata), up to 128 characters; surrounding spaces are trimmed.
|
||
# Unset, empty, invalid, or line-break-containing values fall back to the shipped pin.
|
||
# Used by: open-sse/config/grokBuild.ts. GROK_CLI_USER_AGENT still overrides the full UA.
|
||
# GROK_CLI_CLIENT_VERSION=1.0.41
|
||
#
|
||
# Override the advertised Claude Code client version independently of
|
||
# CLAUDE_USER_AGENT. Anthropic gates some models (Fable 5.1) on this
|
||
# value; a UA-only override is not enough (#12417). Used by:
|
||
# src/shared/constants/claudeCodeClient.ts.
|
||
# CLAUDE_CODE_CLIENT_VERSION=2.1.259
|
||
#
|
||
# Override the 3-character suffix OmniRoute appends to `cc_version=` in the
|
||
# Claude billing block (captured pin: `1e2`). Bump it alongside the version:
|
||
# pinning only the version advertises a `version.revision` pair that no real
|
||
# binary emits. Used by: src/shared/constants/claudeCodeClient.ts.
|
||
# CLAUDE_CODE_CLIENT_BUILD_REVISION=1e2
|
||
#
|
||
# Override the advertised GitHub Copilot CLI version independently of
|
||
# GITHUB_USER_AGENT. Used by: open-sse/config/providerHeaderProfiles.ts.
|
||
# GITHUB_COPILOT_CLI_VERSION=1.0.91
|
||
#
|
||
# Pin the `copilot-integration-id` header sent to standard GitHub Copilot,
|
||
# overriding the default copilot-developer-cli identity (and disabling the
|
||
# automatic 403-identity fallback to copilot-chat). Set this only if your
|
||
# Copilot account/org requires a specific integration id. Used by:
|
||
# open-sse/config/providerHeaderProfiles.ts, open-sse/executors/copilotIdentityFallback.ts.
|
||
# COPILOT_INTEGRATION_ID=copilot-chat
|
||
|
||
# Kill-switch to strip non-standard `codex.*` SSE events (e.g. codex.rate_limits)
|
||
# from the Codex Responses stream. These frames break the OpenAI SDK's
|
||
# responses.stream() with a 502 "Controller is already closed". Off by default;
|
||
# set to true/1/yes to enable. Used by: open-sse/executors/codex.ts.
|
||
# OMNIROUTE_CODEX_DROP_NONSTANDARD_EVENTS=true
|
||
|
||
# Codex app-server WebSocket transport (opt-in). When a WebSocket URL and a
|
||
# capability token are both provided, Codex requests are routed through a local
|
||
# `codex app-server` sidecar over JSON-RPC instead of the HTTP Responses API.
|
||
# Each var is also settable per-connection via providerSpecificData; the env var
|
||
# is the process-wide fallback. Used by:
|
||
# open-sse/executors/codex/appServerConfig.ts.
|
||
#
|
||
# WebSocket endpoint of the codex app-server (ws:// or wss://). Required to
|
||
# enable the transport; leaving it unset keeps Codex on its HTTP transports.
|
||
# OMNIROUTE_CODEX_APPSERVER_WS=ws://127.0.0.1:8081
|
||
# Inline capability/bearer token presented to the app-server.
|
||
# OMNIROUTE_CODEX_APPSERVER_WS_TOKEN=deadbeef...
|
||
# Path to a file holding the capability token (produced by
|
||
# `codex app-server --ws-token-file <path>`). Used when the inline token above
|
||
# is not set.
|
||
# OMNIROUTE_CODEX_APPSERVER_WS_TOKEN_FILE=/run/codex-ws-token
|
||
# Working directory the app-server turn runs in (defaults to /tmp).
|
||
# OMNIROUTE_CODEX_APPSERVER_CWD=/tmp
|
||
# Approval policy passed to the app-server turn (e.g. never, on-request).
|
||
# OMNIROUTE_CODEX_APPSERVER_APPROVAL=never
|
||
# Sandbox policy passed to the app-server turn (e.g. read-only,
|
||
# workspace-write, danger-full-access). When unset, the executor defaults to
|
||
# "workspace-write" (hardened; used to be "danger-full-access").
|
||
# OMNIROUTE_CODEX_APPSERVER_SANDBOX=read-only
|
||
# Auto-approve the app-server's own approval prompts (command/file/permission
|
||
# execution on the host). Defaults to OFF — prompts are auto-denied. Set to
|
||
# true/1/yes only when you trust the deployment to run codex-decided host
|
||
# commands. Per-connection override: providerSpecificData.codexAppServerAutoApprove.
|
||
# OMNIROUTE_CODEX_APPSERVER_AUTO_APPROVE=false
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 13. CLI FINGERPRINT COMPATIBILITY (Anti-Detection)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# When enabled, OmniRoute reorders HTTP headers and JSON body fields to match
|
||
# the exact signature of official CLI tools, reducing account flagging risk.
|
||
# Your proxy IP is preserved — you get both stealth AND IP masking.
|
||
# Used by: open-sse/config/cliFingerprints.ts, open-sse/executors/base.ts
|
||
|
||
# Enable per-provider:
|
||
# CLI_COMPAT_CODEX=1
|
||
# CLI_COMPAT_CLAUDE=1
|
||
# CLI_COMPAT_GITHUB=1
|
||
# CLI_COMPAT_ANTIGRAVITY=1
|
||
# CLI_COMPAT_CURSOR=1
|
||
# CLI_COMPAT_KIMI_CODING=1
|
||
# CLI_COMPAT_KILOCODE=1
|
||
# CLI_COMPAT_CLINE=1
|
||
# Or enable for all providers at once:
|
||
# CLI_COMPAT_ALL=1
|
||
|
||
# Allow the Antigravity request translator to skip its strict CLI request-signature
|
||
# validation when the upstream refuses real signatures (debug/antiquated-CLI mode).
|
||
# Default: real signatures enforced (unset) — signature bypass disabled.
|
||
# Used by: open-sse/translator/request/openai-to-gemini.ts
|
||
# ANTIGRAVITY_ALLOW_SIGNATURE_BYPASS=0
|
||
|
||
# ── Kimi Coding CLI identity overrides ──
|
||
# Used by: src/lib/oauth/providers/kimi-coding.ts — sent in OAuth + API headers.
|
||
# Leave unset to use the captured defaults baked into the OmniRoute build.
|
||
#KIMI_CLI_VERSION=1.36.0
|
||
#KIMI_CODING_DEVICE_ID=
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 14. API KEY PROVIDERS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# API keys for direct-authentication providers.
|
||
# Preferred setup: Dashboard → Providers → Add API Key.
|
||
# Setting here is an alternative for Docker/headless deployments.
|
||
|
||
# Static API keys for direct-authentication providers wired through the runtime.
|
||
# OmniRoute loads provider credentials from the encrypted database or
|
||
# data/provider-credentials.json. The variables below are documented escape
|
||
# hatches that are referenced in code today.
|
||
# DEEPSEEK_API_KEY=
|
||
# NVIDIA_API_KEY=
|
||
# Jina Foundation API + Reader fallback when no dashboard jina-ai / jina-reader
|
||
# connection exists. Dashboard keys always win (fill-first).
|
||
# JINA_AI_API_KEY=
|
||
# JINA_API_KEY=
|
||
# Gemini / Google AI Studio embeddings fallback when no dashboard gemini
|
||
# connection exists. Dashboard keys always win (fill-first).
|
||
# GEMINI_API_KEY=
|
||
# GOOGLE_API_KEY=
|
||
|
||
# Windsurf / Devin CLI direct API key.
|
||
# Used by: open-sse/executors/devin-cli.ts — bypasses OAuth when set.
|
||
# WINDSURF_API_KEY=
|
||
|
||
# Embedding Providers (optional — used by /v1/embeddings)
|
||
# OpenAI/Mistral/Together/Fireworks/NVIDIA configured via Dashboard → Providers
|
||
# also work for embeddings.
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 15. TIMEOUT SETTINGS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# All timeout values are in milliseconds.
|
||
# Used by: src/shared/utils/runtimeTimeouts.ts — centralized timeout resolution.
|
||
#
|
||
# Hierarchy: REQUEST_TIMEOUT_MS acts as a global override.
|
||
# If set, it becomes the default for FETCH_TIMEOUT_MS, STREAM_IDLE_TIMEOUT_MS,
|
||
# and STREAM_READINESS_TIMEOUT_MS. STREAM_ACTIVE_TIMEOUT_MS is independent.
|
||
# The fine-grained variables below override their respective defaults only when set.
|
||
|
||
# ── Global shortcut ──
|
||
# REQUEST_TIMEOUT_MS=600000 # Overrides both fetch and stream idle defaults
|
||
|
||
# ── Upstream fetch (provider calls) ──
|
||
# FETCH_TIMEOUT_MS=600000 # Total request timeout (default: 600000 = 10 min)
|
||
# # Also drives anthropic-compatible-cc-* X-Stainless-Timeout.
|
||
# FETCH_HEADERS_TIMEOUT_MS=600000 # Time to receive response headers
|
||
# Maximum response-header wait (ms) for streaming requests. Default: 110000; 0 disables.
|
||
# OMNIROUTE_FETCH_START_TIMEOUT_CAP_MS=110000
|
||
# FETCH_BODY_TIMEOUT_MS=600000 # Time to receive full response body
|
||
# FETCH_CONNECT_TIMEOUT_MS=30000 # TCP connection establishment (default: 30s)
|
||
# FETCH_KEEPALIVE_TIMEOUT_MS=4000 # Keep-alive socket idle timeout (default: 4s)
|
||
# OMNIROUTE_CODEX_IMAGE_RESPONSE_START_TIMEOUT_MS=600000 # First response headers for
|
||
# # dedicated Codex images/generations and images/edits
|
||
# # POSTs (ms; 10 min by default). These long-running
|
||
# # paid submissions are never replayed after a timeout
|
||
# # or transport failure, including when proxied.
|
||
# # Edge relays stay single-attempt too, but keep their
|
||
# # own OMNIROUTE_RELAY_FETCH_TIMEOUT_MS deadline.
|
||
# OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS=30000 # Bounded response-start window per direct
|
||
# # (no-proxy) attempt (#10214). A silently-dropped
|
||
# # pooled keep-alive socket surfaces no transport
|
||
# # error, so without this bound a direct request can
|
||
# # stall until undici's headersTimeout (600s) or the
|
||
# # caller's deadline; on expiry the request retries
|
||
# # once on a fresh no-keep-alive socket. 0 disables
|
||
# # the bound (default: 30000 = 30s).
|
||
# OMNIROUTE_LOCAL_DIRECT_HEADERS_TIMEOUT_MS=300000 # Floor for local/self-hosted targets
|
||
# # (host.docker.internal, 192.168.x.x, localhost).
|
||
# # Used when the direct upstream URL is private/LAN
|
||
# # so native Ollama cold-start TTFB can exceed 30s.
|
||
# # Default: 300000 = 5 min. See docs/guides/LOCAL_OLLAMA_DOCKER.md
|
||
# OMNIROUTE_DIRECT_IMAGE_HEADERS_TIMEOUT_MS=300000 # Floor for direct image requests: image
|
||
# # generation/edit endpoints (/images/generations,
|
||
# # /images/edits, ...) and bodies with a hosted
|
||
# # "image_generation" tool. Raise-only; 0 removes it.
|
||
# # Codex image POSTs use their own deadline
|
||
# # (OMNIROUTE_CODEX_IMAGE_RESPONSE_START_TIMEOUT_MS).
|
||
# # Default: 300000 = 5 min.
|
||
# OMNIROUTE_DIRECT_HEADERS_VOLUME_ADAPTIVE=1 # Raise the direct response-start window by
|
||
# # payload tier (>512KB ×2, >2MB ×3, capped at 180s,
|
||
# # never lowering a higher floor). Set 0/false/off
|
||
# # to pin the flat window. Default: 1.
|
||
# OMNIROUTE_DIRECT_RESPONSE_RETRY_TIMEOUT_MS=600000 # Ceiling (ms) for the fresh-socket
|
||
# # RETRY attempt above (#13703). Only applies when
|
||
# # the caller already attached its own deadline
|
||
# # signal (the resolved connection/model/provider/
|
||
# # FETCH_TIMEOUT_MS cascade) — that signal is the
|
||
# # real bound and fires first in the intended path,
|
||
# # so this is a generous backstop rather than a flat
|
||
# # cap: without it the retry reused the same short
|
||
# # OMNIROUTE_DIRECT_HEADERS_TIMEOUT_MS window as the
|
||
# # pooled attempt and 504'd healthy slow-TTFB
|
||
# # reasoning models. Never allowed below the flat
|
||
# # floor above (default: 600000 = 10 min).
|
||
|
||
# Default timeout (ms) for src/shared/utils/fetchTimeout.ts. Acts as the
|
||
# fallback when FETCH_TIMEOUT_MS is unset. Default: 120000 (2 min).
|
||
# OMNIROUTE_DEFAULT_FETCH_TIMEOUT_MS=120000
|
||
|
||
# ── Provider probe (credential validation / model discovery) ──
|
||
# Timeout in ms for provider validationRead and modelsProbe presets.
|
||
# Default: 8000 (was 5000). Raise it if slow endpoints (Cerebras, Cloudflare AI, Groq)
|
||
# cause flapping between active/error in the dashboard.
|
||
# Used by: src/shared/network/safeOutboundFetch.ts — centralized timeout resolution.
|
||
# OMNIROUTE_PROVIDER_PROBE_TIMEOUT_MS=8000
|
||
|
||
# ── Proxy/relay fetch (connection pooling, #9158) ──
|
||
# Used by: open-sse/utils/proxyFetch.ts.
|
||
# A hung relay must fail BEFORE the client/agent timeout (typically 30s) so the
|
||
# caller sees a relay-specific failure instead of a generic upstream timeout.
|
||
# Capped at 29000ms so this timeout always fires first. Default: 25000 (25s).
|
||
# OMNIROUTE_RELAY_FETCH_TIMEOUT_MS=25000
|
||
|
||
# Shared retry backoff (ms) for the direct/relay/proxy retry-once paths.
|
||
# 0 = retry immediately. Default: 10.
|
||
# OMNIROUTE_RETRY_BACKOFF_MS=10
|
||
|
||
# ── Firecrawl web-fetch executor ──
|
||
# Point at a self-hosted Firecrawl instance (defaults to the public cloud API).
|
||
# When set to a non-cloud base URL, the API key becomes optional.
|
||
# FIRECRAWL_BASE_URL=https://api.firecrawl.dev
|
||
# FIRECRAWL_TIMEOUT_MS=30000 # Per-request timeout (default: 30000 = 30s)
|
||
|
||
# ── Tavily quota tracker ──
|
||
# Point the Tavily /usage quota fetcher at a self-hosted or proxied Tavily-compatible
|
||
# base URL (ignored when it points at api.tavily.com; unset = use the connection's base URL).
|
||
# TAVILY_BASE_URL=
|
||
|
||
# ── Claude TLS transport (Chromium-fingerprinted client) ──
|
||
# Used by: open-sse/services/claudeTlsClient.ts — native wreq-js request timeout
|
||
# plus the absolute JS hard-deadline grace when the native request is wedged.
|
||
# OMNIROUTE_CLAUDE_TLS_TIMEOUT_MS=60000
|
||
# OMNIROUTE_CLAUDE_TLS_GRACE_MS=10000
|
||
|
||
# ── Perplexity TLS transport (Firefox-fingerprinted client) ──
|
||
# Used by: open-sse/services/perplexityTlsClient.ts — native wreq-js request
|
||
# timeout plus the absolute JS hard-deadline grace.
|
||
# OMNIROUTE_PPLX_TLS_TIMEOUT_MS=30000
|
||
# OMNIROUTE_PPLX_TLS_GRACE_MS=10000
|
||
|
||
# ── Perplexity web: built-in-search hint ──
|
||
# Used by: open-sse/executors/perplexity-web/protocol.ts — appends "You have
|
||
# built-in web search. Answer questions directly using search results." to the
|
||
# caller's system message. Off by default: Perplexity's answer engine searches
|
||
# anyway, and for coding clients the sentence leaks into replies as
|
||
# meta-commentary. Set to 1/true/yes/on to restore the old behavior.
|
||
# OMNIROUTE_PPLX_SEARCH_HINT=0
|
||
|
||
# ── Grok web TLS transport (Chrome-fingerprinted client) ──
|
||
# Used by: open-sse/services/grokTlsClient.ts — native wreq-js request timeout
|
||
# plus the absolute JS hard-deadline grace.
|
||
# OMNIROUTE_GROK_TLS_TIMEOUT_MS=60000
|
||
# OMNIROUTE_GROK_TLS_GRACE_MS=10000
|
||
|
||
# ── Notion web TLS transport (Chrome-fingerprinted client) ──
|
||
# Used by: open-sse/services/notionTlsClient.ts — native wreq-js request timeout
|
||
# plus the absolute JS hard-deadline grace. The notion-web executor raises the
|
||
# native timeout per request to 180000 for long generations.
|
||
# OMNIROUTE_NOTION_TLS_TIMEOUT_MS=30000
|
||
# OMNIROUTE_NOTION_TLS_GRACE_MS=10000
|
||
|
||
# ── Grok web quota fetcher (auth.json override) ──
|
||
# Used by: open-sse/services/grokQuotaFetcher.ts — path of the Grok CLI
|
||
# auth.json used to fetch the grok-web weekly quota. Defaults to
|
||
# ~/.grok/auth.json; override for tests or a non-standard CLI install.
|
||
# GROK_AUTH_PATH=
|
||
|
||
# ── Browser-backed web-cookie chat (Playwright shared pool) ──
|
||
# Used by: open-sse/services/browserPool.ts + browserBackedChat.ts. The shared
|
||
# browser pool warms a headless context for web-cookie providers (e.g. claude-web)
|
||
# that need a real browser to satisfy anti-bot challenges. Set OMNIROUTE_BROWSER_POOL=off
|
||
# to fully disable the pool; set WEB_COOKIE_USE_BROWSER=1 to opt a web-cookie chat
|
||
# request into the browser-backed path.
|
||
# OMNIROUTE_BROWSER_POOL=on
|
||
# WEB_COOKIE_USE_BROWSER=0
|
||
# Gemini Web (gweb) opt-in for gemini-4-argon (#16573). Used by:
|
||
# open-sse/config/providers/registry/gemini/web/index.ts and
|
||
# open-sse/executors/gemini-web/modeSelection.ts. Off by default: its mode-menu
|
||
# selectors are not yet checked against a live Gemini Web account. Set 1 to list
|
||
# the model and allow its mode selection; read at startup (restart to apply).
|
||
# OMNIROUTE_GEMINI_WEB_ARGON_ENABLED=0
|
||
# Obscura (https://github.com/h4ckf0r0day/obscura) is the primary headless
|
||
# engine: a lightweight CDP server the pool and cloudflare-playground connect
|
||
# to before falling back to Chromium. Unset OBSCURA_BIN to auto-detect from
|
||
# PATH; set OBSCURA_CDP_ENDPOINT to reuse an already-running Obscura instead
|
||
# of spawning one; set OBSCURA_PORT to pin the spawned serve port.
|
||
# Used by: open-sse/services/obscura.ts
|
||
# OBSCURA_BIN=
|
||
# OBSCURA_CDP_ENDPOINT=
|
||
# OBSCURA_PORT=
|
||
|
||
# ── Kimi Web (international kimi.ai Connect-RPC) ──
|
||
# Used by: open-sse/executors/kimi-web.ts. Override the base/chat URLs only if
|
||
# you need a mirror or proxy endpoint; defaults target https://www.kimi.ai with
|
||
# the Connect-RPC chat path /apiv2/kimi.gateway.chat.v1.ChatService/Chat.
|
||
# KIMI_WEB_BASE_URL=https://www.kimi.ai
|
||
# KIMI_WEB_CHAT_URL=https://www.kimi.ai/apiv2/kimi.gateway.chat.v1.ChatService/Chat
|
||
|
||
# When OIDC is enabled, disable password login so users can only authenticate
|
||
# via OIDC Single Sign-On. The bare alias OIDC_DISABLE_PASSWORD_LOGIN is also
|
||
# accepted; the Dashboard Feature Flag takes precedence. Used by:
|
||
# src/app/api/auth/login/route.ts, src/app/api/settings/require-login/route.ts.
|
||
# OMNIROUTE_OIDC_DISABLE_PASSWORD_LOGIN=false
|
||
# OIDC_DISABLE_PASSWORD_LOGIN=false
|
||
|
||
# Lost-device recovery for the opt-in dashboard two-factor login (TOTP).
|
||
# When true, the second factor is skipped ONLY for a sign-in from the host itself
|
||
# (loopback peer + loopback Host); every other origin still needs the code.
|
||
# Sign in locally, disable two-factor under Settings > Security (the code may be
|
||
# left blank while this is set; the password is still required), then unset it.
|
||
# Used by: src/server/auth/dashboardMfa.ts.
|
||
# OMNIROUTE_DISABLE_MFA=false
|
||
|
||
# ── Adobe Firefly browser sign-in (system Chrome/Edge CDP) ──
|
||
# Used by: open-sse/services/adobeFireflyBrowserLogin.ts. The Firefly login
|
||
# flow drives a real, system-installed Chrome or Microsoft Edge via CDP so the
|
||
# user can sign in interactively; the executable is auto-detected from common
|
||
# install paths per OS. Set this to override that detection (e.g. a portable
|
||
# install or a non-standard path) when auto-detection fails.
|
||
# OMNIROUTE_LOGIN_BROWSER_PATH=
|
||
|
||
# ── Circuit breaker thresholds and reset windows ──
|
||
# Used by: open-sse/config/constants.ts → src/lib/resilience/settings.ts.
|
||
# Defaults match historical PROVIDER_PROFILES values (post-scaling for
|
||
# 500+ connections). Lower the threshold to react faster, raise it to
|
||
# tolerate more transient failures before short-circuiting.
|
||
# OMNIROUTE_CIRCUIT_BREAKER_OAUTH_THRESHOLD=8
|
||
# OMNIROUTE_CIRCUIT_BREAKER_OAUTH_RESET_MS=60000
|
||
# OMNIROUTE_CIRCUIT_BREAKER_API_KEY_THRESHOLD=12
|
||
# OMNIROUTE_CIRCUIT_BREAKER_API_KEY_RESET_MS=30000
|
||
# OMNIROUTE_CIRCUIT_BREAKER_LOCAL_THRESHOLD=2
|
||
# OMNIROUTE_CIRCUIT_BREAKER_LOCAL_RESET_MS=15000
|
||
|
||
# Per-key cooldown (ms) for multi-key API-key rotation when a 429 carries no
|
||
# Retry-After. Used by: open-sse/services/apiKeyRotator.ts (#14573). Default 60000.
|
||
# OMNIROUTE_API_KEY_COOLDOWN_MS=60000
|
||
|
||
# ── Anti-avalanche failover guard (opt-in, off by default) ──
|
||
# Used by: open-sse/services/accountFallback/antiAvalanche.ts → src/sse/handlers/chat.ts.
|
||
# Only an explicit "true" enables it. When on, a 429 that names a tokens-per-minute limit
|
||
# (or a context-overflow 400) stops the cascading failover across the remaining keys of the
|
||
# provider. A quota-exhausted 429 keeps failing over however large the prompt is, 413 keeps
|
||
# the #13350 retry-on-another-account behaviour, and the burst cooldown never shortens a
|
||
# longer upstream reset.
|
||
# OMNIROUTE_AVALANCHE_PROTECTION_ENABLED=false
|
||
# OMNIROUTE_AVALANCHE_BURST_COOLDOWN_MS=60000
|
||
|
||
# ── Provider-level circuit breaker thresholds and cooldowns ──
|
||
# Used by: open-sse/config/constants.ts (PROVIDER_PROFILES → accountFallback).
|
||
# These control the provider-level fuse (entire provider cooldown after repeated
|
||
# failures) — distinct from the per-key breaker above. Defaults match the
|
||
# historical PROVIDER_PROFILES values. Raise to tolerate transient upstream
|
||
# sheds without blacklisting the provider; lower to fail over faster.
|
||
# OMNIROUTE_PROVIDER_BREAKER_OAUTH_FAILURE_THRESHOLD=10
|
||
# OMNIROUTE_PROVIDER_BREAKER_OAUTH_FAILURE_WINDOW_MS=900000
|
||
# OMNIROUTE_PROVIDER_BREAKER_OAUTH_COOLDOWN_MS=300000
|
||
# OMNIROUTE_PROVIDER_BREAKER_OAUTH_DEGRADATION_THRESHOLD=5
|
||
# OMNIROUTE_PROVIDER_BREAKER_OAUTH_MAX_BACKOFF_MULTIPLIER=8
|
||
# OMNIROUTE_PROVIDER_BREAKER_OAUTH_BACKOFF_ESCALATION_COUNT=2
|
||
# OMNIROUTE_PROVIDER_BREAKER_API_KEY_FAILURE_THRESHOLD=15
|
||
# OMNIROUTE_PROVIDER_BREAKER_API_KEY_FAILURE_WINDOW_MS=1800000
|
||
# OMNIROUTE_PROVIDER_BREAKER_API_KEY_COOLDOWN_MS=600000
|
||
# OMNIROUTE_PROVIDER_BREAKER_API_KEY_DEGRADATION_THRESHOLD=7
|
||
# OMNIROUTE_PROVIDER_BREAKER_API_KEY_MAX_BACKOFF_MULTIPLIER=4
|
||
# OMNIROUTE_PROVIDER_BREAKER_API_KEY_BACKOFF_ESCALATION_COUNT=3
|
||
# OMNIROUTE_PROVIDER_BREAKER_LOCAL_FAILURE_THRESHOLD=2
|
||
# OMNIROUTE_PROVIDER_BREAKER_LOCAL_FAILURE_WINDOW_MS=300000
|
||
# OMNIROUTE_PROVIDER_BREAKER_LOCAL_COOLDOWN_MS=60000
|
||
|
||
# ── Context-cache pin health gate ──
|
||
# Used by: open-sse/services/combo.ts. When a context-cache pin points at a
|
||
# provider that is durably unhealthy, the pin is dropped to allow failover.
|
||
# PIN_DROP_BACKOFF_LEVEL gates how deep a connection's backoff must be before the
|
||
# pin is considered durably unhealthy; PIN_DROP_GRACE_MS is the anti-flap window
|
||
# that tolerates brief transient cooldowns before dropping the pin.
|
||
# PIN_DROP_BACKOFF_LEVEL=2
|
||
# PIN_DROP_GRACE_MS=20000
|
||
|
||
# Whether OmniRoute may emit SSE `:` comment lines (e.g. the `: keepalive` heartbeat).
|
||
# Some strict OpenAI-compatible clients parse every SSE line as JSON and crash on `:`
|
||
# comments. Set to `off` to suppress comment-shaped heartbeats (they become a no-op);
|
||
# `data:` heartbeats are unaffected. Default: enabled.
|
||
# Used by: open-sse/utils/sseHeartbeat.ts.
|
||
# OMNIROUTE_SSE_COMMENTS=off
|
||
|
||
# ── Opt-in SSE output coalescing (all OFF by default; the default stream is unchanged) ──
|
||
# Merge consecutive Claude `content_block_delta` events (same block index + same delta type)
|
||
# sent to Claude clients into one event per window, losslessly. Helps clients that render one
|
||
# UI update per SSE event (e.g. the Claude Code VS Code extension) keep up with fast upstreams.
|
||
# SSE_COALESCE_MS sets every delta type; the per-type vars override it. 0/unset = off.
|
||
# Used by: open-sse/utils/sseDeltaCoalesce.ts.
|
||
# SSE_COALESCE_MS=0
|
||
# SSE_COALESCE_THINKING_MS=0
|
||
# SSE_COALESCE_TEXT_MS=0
|
||
# SSE_COALESCE_INPUT_JSON_MS=0
|
||
# Batch SSE frames forwarded within this window into ONE write to the client (fewer socket
|
||
# writes under high concurrency). The first frame and terminal frames are never delayed.
|
||
# 0/unset = off (one write per frame). Used by: open-sse/utils/sseOutputSink.ts.
|
||
# SSE_FRAME_COALESCE_MS=0
|
||
# Byte-stall watchdog implementation: `timer` (default, one timer re-armed per upstream chunk)
|
||
# or `interval` (one low-frequency check per stream; fires within the stall budget + 1-5s).
|
||
# Used by: open-sse/utils/streamStallWatchdog.ts.
|
||
# SSE_STALL_WATCHDOG=timer
|
||
|
||
# ── Stream idle detection ──
|
||
# STREAM_IDLE_TIMEOUT_MS=600000 # Max silence between SSE chunks (default: 600000)
|
||
# # Extended-thinking models rarely pause >90s.
|
||
# STREAM_ACTIVE_TIMEOUT_MS=1260000 # Max total active SSE lifetime (default: 21 min = the largest registered model timeoutMs + 1 min; 0 disables)
|
||
# # Unset: a target that declares a longer timeoutMs (connection, model or provider,
|
||
# # e.g. GLM) gets that budget + 1 min instead. Set: a hard cap for every target.
|
||
# # Independent of REQUEST_TIMEOUT_MS and byte activity.
|
||
# STREAM_READINESS_TIMEOUT_MS=80000 # Time to receive the first non-ping SSE event
|
||
# STREAM_READINESS_MAX_TIMEOUT_MS=180000 # Cap for adaptive first-event extensions
|
||
# # (large/tool-heavy/high-reasoning requests).
|
||
# OMNIROUTE_AGENT_GOAL_POLICY_ENABLED=true # Kill-switch for the /goal heuristic below.
|
||
# # Set to false to fully disable detection —
|
||
# # readiness timeouts and stream recovery are
|
||
# # never elevated by request body/headers when off.
|
||
# OMNIROUTE_AGENT_GOAL_READINESS_MAX_TIMEOUT_MS=600000 # Auto cap for detected /goal agent runs
|
||
# OMNIROUTE_AGENT_GOAL_STREAM_RECOVERY=true # Auto early stream recovery for /goal runs.
|
||
# # NOTE: this can only ADD recovery on top of the
|
||
# # operator default — it never overrides an explicit
|
||
# # STREAM_RECOVERY_ENABLED / DB settings opt-out.
|
||
|
||
# ── TLS client (wreq-js fingerprint proxy) ──
|
||
# TLS_CLIENT_TIMEOUT_MS=600000 # Inherits from FETCH_TIMEOUT_MS by default
|
||
# TLS_FIRST_BYTE_WATCHDOG_MS=10000 # #12656: bounds time-to-first-byte on the wreq body (0 disables)
|
||
# OPENCODE_RESPONSES_STALL_ROTATION=false # #13484 feature flag (Settings → Feature Flags wins): rotate once when a streamed Responses reply stalls before its first byte
|
||
# OPENCODE_PARK_AND_RESUME=false # #13924 feature flag (Settings → Feature Flags wins): park the request with a heartbeat after repeated transient 429s, then replay one capped leg of up to 3 accounts
|
||
# OPENCODE_PARK_REPLAY_SERVE_SETASIDE=false # #14851 opt-in: when every cooldown-ready account in the park replay leg is set aside, serve them anyway instead of an empty leg
|
||
# STREAM_READINESS_STALL_RETRY=false # feature flag (Settings → Feature Flags wins): when a streaming first body stalls before usable output, issue one bounded second attempt through the same routing path
|
||
#OPENCODE_POOL_STRAIN_MARKER_PATH=/tmp/opencode-pool-strain.json # #13924: pool-strain marker path (JSON {since, reason, ttl_s}); fresh marker parks without recounting
|
||
# OPENCODE_POOL_RESELECT=false # feature flag (Settings → Feature Flags wins): after a 429 from an egress-bucketed provider on a proxy-less account under an ambient pool context, ask the pool for another member for the next attempt instead of retrying the same address
|
||
# RESPONSES_FIRST_BYTE_TIMEOUT_MS=15000 # #13484: OpenCode Responses first-byte window, only used when the OPENCODE_RESPONSES_STALL_ROTATION flag is on (0 disables)
|
||
# OPENCODE_RESPONSES_HEADERS_WAIT_MS=30000 # opt-in bound on waiting for upstream response headers on streamed Responses calls before moving to the next account (0 = off, suggested 30000)
|
||
# OPENCODE_RESPONSES_HEADERS_WAIT_MAX_ROTATIONS=2 # rotation budget for the headers-wait bound above
|
||
# FLUSH_EMPTY_RETRY_ENABLED=false # #14213 feature flag (Settings → Feature Flags wins): retry empty translated streaming turns through the normal credential path (up to STREAM_RECOVERY.EMPTY_TURN_RETRY_MAX retries)
|
||
# EMPTY_STREAM_SIBLING_RECOVERY_ENABLED=false # #16438 feature flag (Settings → Feature Flags wins): Claude/Codex empty-stream content probe + bounded retry on a sibling connection (no cooldown/lockout)
|
||
# STREAM_LATE_OUTPUT_PROBE_ENABLED=false # #16927 feature flag (Settings → Feature Flags wins): keep sampling 1 forwarded chunk in 16 after chunk 64 so late output counts as emitted (lone post-output 5xx stays request-scoped)
|
||
|
||
# ── API Bridge (/v1 proxy server) ──
|
||
# API_BRIDGE_PROXY_TIMEOUT_MS=600000 # Proxy hop timeout (default: 10min)
|
||
# API_BRIDGE_SERVER_REQUEST_TIMEOUT_MS=600000 # Overall server request timeout (default: 10min)
|
||
# API_BRIDGE_SERVER_HEADERS_TIMEOUT_MS=60000 # Time to send response headers
|
||
# API_BRIDGE_SERVER_KEEPALIVE_TIMEOUT_MS=5000 # Keep-alive idle timeout
|
||
# API_BRIDGE_SERVER_SOCKET_TIMEOUT_MS=0 # Raw socket timeout (0 = disabled)
|
||
|
||
# ── Graceful shutdown ──
|
||
# Time to wait for in-flight requests before force-exiting on SIGTERM/SIGINT.
|
||
# Used by: src/lib/gracefulShutdown.ts
|
||
# Default: 30000 (30 seconds)
|
||
# SHUTDOWN_TIMEOUT_MS=30000
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 16. LOGGING
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Used by: src/lib/logEnv.ts, src/lib/logRotation.ts, src/shared/utils/logger.ts
|
||
|
||
# Application log level — controls console and file log verbosity.
|
||
# Values: debug | info | warn | error | Default: info
|
||
# APP_LOG_LEVEL=info
|
||
|
||
# Log output format.
|
||
# Values: text | json | Default: text
|
||
# APP_LOG_FORMAT=text
|
||
|
||
# Write logs to file in addition to stdout.
|
||
# Default: true | Set false to disable file logging.
|
||
APP_LOG_TO_FILE=true
|
||
|
||
# Path to the application log file.
|
||
# Default: <DATA_DIR>/logs/application/app.log (DATA_DIR defaults to ~/.omniroute)
|
||
# APP_LOG_FILE_PATH=logs/application/app.log
|
||
|
||
# Maximum single log file size before rotation.
|
||
# Accepts: plain bytes or suffixed (50M, 1G, 512K). Default: 50M
|
||
# APP_LOG_MAX_FILE_SIZE=50M
|
||
|
||
# Days to keep rotated application log files before auto-deletion.
|
||
# Default: 7
|
||
# APP_LOG_RETENTION_DAYS=7
|
||
|
||
# Maximum number of rotated log file backups to keep.
|
||
# Default: 20
|
||
# APP_LOG_MAX_FILES=20
|
||
|
||
# How often OmniRoute checks whether the active log file has exceeded
|
||
# APP_LOG_MAX_FILE_SIZE and triggers a rotation. Set lower for very verbose
|
||
# services to prevent log files from growing large between checks.
|
||
# Accepts milliseconds. Default: 60000 (1 minute)
|
||
# APP_LOG_ROTATION_CHECK_INTERVAL_MS=60000
|
||
|
||
# Days to keep request/call log entries in the database before auto-cleanup.
|
||
# Default: 7
|
||
# CALL_LOG_RETENTION_DAYS=7
|
||
|
||
# Maximum call log entries stored in-memory buffer.
|
||
# Default: 10000
|
||
# CALL_LOG_MAX_ENTRIES=10000
|
||
|
||
# Maximum rows in the call_logs SQLite table before oldest entries are pruned.
|
||
# Default: 100000
|
||
# CALL_LOGS_TABLE_MAX_ROWS=100000
|
||
|
||
# Size cap, in MiB, for the generated media kept under DATA_DIR/media (video results). When a
|
||
# new file pushes the folder past the cap, the oldest files are removed first. The file just
|
||
# written always stays. Whole number above 0; any other value is ignored.
|
||
# When set, it wins over the Storage setting "Media store size cap" in the dashboard.
|
||
# Used by: src/lib/media/mediaStore.ts. Default: 2048 (2 GiB)
|
||
# MEDIA_STORE_MAX_MB=2048
|
||
|
||
# Force detailed request logging on or off, overriding the dashboard setting.
|
||
# Values: true | false | Default: unset (follow dashboard setting)
|
||
# ENABLE_REQUEST_LOGS=false
|
||
|
||
# Maximum age for orphaned active request log entries before the in-memory
|
||
# pending-request reaper removes them. Accepts milliseconds.
|
||
# Default: 3600000 (1 hour)
|
||
# MAX_PENDING_REQUEST_AGE_MS=3600000
|
||
|
||
# Maximum number of pending request details retained in memory. The count cap is applied
|
||
# by the 5-minute sweep (the 256 MiB byte ceiling applies at insert); the pending-id
|
||
# correlation map is capped at insert. Must be a positive integer.
|
||
# Default: 5000
|
||
# MAX_PENDING_DETAILS=5000
|
||
|
||
# Whether call log pipeline capture stores stream chunks when enabled in settings.
|
||
# Only applies when call_log_pipeline_enabled=true.
|
||
# Default: false (opt-in — saves disk: stream chunks are the biggest call-log artifact)
|
||
# CALL_LOG_PIPELINE_CAPTURE_STREAM_CHUNKS=true
|
||
|
||
# Maximum call log artifact size for pipeline captures, in KB.
|
||
# Only applies when call_log_pipeline_enabled=true.
|
||
# Default: 512
|
||
# CALL_LOG_PIPELINE_MAX_SIZE_KB=512
|
||
|
||
# Minimum free disk space, in MB, on the volume that holds the call log artifacts
|
||
# (DATA_DIR/call_logs, next to storage.sqlite). Below it, artifact writes are skipped and the
|
||
# row shows detail_state "missing", so artifacts cannot take the last bytes that the usage
|
||
# ledger and call log row writes need. 0 turns the check off. A failed check never drops a log.
|
||
# Used by: src/lib/usage/callLogArtifacts.ts (hasRoomForCallLogArtifact)
|
||
# Default: 512
|
||
# CALL_LOG_MIN_FREE_DISK_MB=512
|
||
|
||
# Call log payload truncation limits — controls how much of request/response
|
||
# bodies is retained in the database.
|
||
# Used by: open-sse/handlers/chatCore.ts — cloneBoundedChatLogPayload()
|
||
# CHAT_LOG_TEXT_LIMIT=65536 # Max string length before truncation (default: 64 KB)
|
||
# CHAT_LOG_ARRAY_TAIL_ITEMS=1000 # Number of array items retained from tail (default: 1000)
|
||
# CHAT_LOG_MAX_DEPTH=20 # Max nesting depth before truncation (default: 20)
|
||
# CHAT_LOG_MAX_OBJECT_KEYS=80 # Max object keys retained (default: 80, 0 = no limit)
|
||
# CHAT_LOG_MAX_BODY_KB=1024 # Whole request/response body size before it's replaced by a bare
|
||
# {_truncated, messageCount, ...} summary instead of the full clone
|
||
# (default: 1024 KB / 1MB). Raise this if the dashboard's "Full
|
||
# Conversation" transcript panel shows a placeholder instead of the
|
||
# actual messages for long agentic conversations.
|
||
|
||
# Maximum rows in the proxy_logs SQLite table.
|
||
# Default: 100000
|
||
# PROXY_LOGS_TABLE_MAX_ROWS=100000
|
||
|
||
# Include client/egress IPs and account prefixes in [ProxyEgress] console logs.
|
||
# Default: false (the dashboard/database proxy-log records retain full details).
|
||
# PROXY_LOG_INCLUDE_IPS=false
|
||
|
||
# Record the time to the first useful body byte of each upstream send on its
|
||
# proxy-log row (first_chunk_ms). Opt-in: when on, every upstream body is piped
|
||
# through a lazy passthrough stream and the row is patched once the byte lands.
|
||
# Default: false (only the free headers timing, headers_ms, is recorded).
|
||
# PROXY_LOG_FIRST_CHUNK_TIMING=false
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 17. MEMORY OPTIMIZATION (Low-RAM / Docker)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
|
||
# Node.js V8 heap limit in MB, passed to the server via --max-old-space-size.
|
||
# Used by the standalone launcher (Docker CMD) and `omniroute serve`.
|
||
# Clamped to [64, 16384]. Default: 512 (safe for a 1 GB / 1 core VPS). Size it to
|
||
# roughly half the box's RAM, leaving the rest for native memory (better-sqlite3,
|
||
# buffers — ~300 MB) and the OS:
|
||
# 1 GB RAM → 512 (default)
|
||
# 2 GB RAM → 1024
|
||
# 4 GB RAM → 2048
|
||
# In a memory-capped container, set this EXPLICITLY: Node reads the HOST's RAM,
|
||
# not the cgroup limit, so leaving it to a RAM heuristic can oversize the heap and
|
||
# get the container OOM-killed. (#2939)
|
||
# OMNIROUTE_MEMORY_MB=512
|
||
|
||
# Log compact V8 heap metrics only when heapUsed exceeds a configured threshold.
|
||
# Used by: src/lib/healthzLag.ts (event-loop stall sampler). Disabled by default;
|
||
# logs sizes and inflight count only, never bodies or heap snapshots.
|
||
# OMNIROUTE_EVENT_LOOP_STALL_THRESHOLD_MS=0 stops that sampler, and this diagnostic with it.
|
||
# OMNIROUTE_HEAP_DIAGNOSTICS_ENABLED=0
|
||
# Heap-use threshold in MiB for the opt-in diagnostic (default: 900).
|
||
# A high-heap log is rate-limited to once per 60 seconds.
|
||
# OMNIROUTE_HEAP_DIAGNOSTICS_THRESHOLD_MB=900
|
||
|
||
# Absolute process-RSS fuse (MB) for native/external memory invisible to V8 heapUsed — new requests
|
||
# get 503 resource_pressure above it. Only active when OMNIROUTE_MEMORY_MB is set (default
|
||
# max(3072, 2 x OMNIROUTE_MEMORY_MB)); set this to override. RSS rarely falls after a spike, so
|
||
# pair it with OMNIROUTE_PRESSURE_SELF_RESTART. Used by: open-sse/utils/resourcePressure.ts.
|
||
# OMNIROUTE_RSS_PRESSURE_MB=3072
|
||
|
||
# Heap-pressure shed threshold (MB) — chatCore returns 503 when V8 heapUsed exceeds
|
||
# it, to avoid hard OOM under concurrent large-context load.
|
||
# LEAVE UNSET: it now AUTO-CALIBRATES to 85% of the actual V8 heap ceiling, so it
|
||
# tracks OMNIROUTE_MEMORY_MB above and never sits below the ~260 MB runtime baseline
|
||
# (a fixed 200 here used to reject every request). Used by: open-sse/utils/heapPressure.ts.
|
||
# Override only to hand-tune for a known workload.
|
||
# HEAP_PRESSURE_THRESHOLD_MB=
|
||
|
||
# Exit the process after critical resource pressure persists, so a supervisor
|
||
# (systemd Restart=always, Docker restart policy) brings back a clean process.
|
||
# Accepts 1/true/yes/on. Default: false. Used by: open-sse/utils/resourcePressure.ts.
|
||
# OMNIROUTE_PRESSURE_SELF_RESTART=false
|
||
# How long (ms) critical pressure must persist before that exit fires. Default: 120000 (2m).
|
||
# OMNIROUTE_PRESSURE_SELF_RESTART_AFTER_MS=120000
|
||
# Ignore host-wide memory PSI (/proc/pressure/memory: psi_some / psi_full) for a
|
||
# noisy-neighbor host where this process is fine (#13124). Cgroup and V8 heap
|
||
# guards stay on, and PSI also stops counting as kernel throttle proof for the
|
||
# cgroup_high guard: a raw cgroup total above memory.high then only turns
|
||
# critical on a memory.events high/max increase. Accepts 1/true/yes/on.
|
||
# Default: false. Used by: open-sse/utils/resourcePressurePolicy.ts.
|
||
# OMNIROUTE_PRESSURE_PSI_DISABLED=false
|
||
|
||
# ── CLI helpers (bin/cli/) ──
|
||
# Override UI language for CLI output. Accepts BCP-47 locale (e.g. en, pt-BR).
|
||
# Falls back to LC_ALL / LC_MESSAGES / LANG / en if unset.
|
||
# OMNIROUTE_LANG=en
|
||
|
||
# Show server logs inline when running in supervised mode (omniroute serve).
|
||
# Set to "1" to forward server stdout/stderr to the terminal.
|
||
# Equivalent to the --log flag on `omniroute serve`.
|
||
# OMNIROUTE_SHOW_LOG=1
|
||
|
||
# Bearer token injected as x-omniroute-cli-token header for machine-auth (task 8.12).
|
||
# Auto-generated on first run if machine-id is available; set manually to override.
|
||
# OMNIROUTE_CLI_TOKEN=
|
||
|
||
# Sync token used by `omniroute sync bundle` (GET /api/sync/bundle accepts only a sync token,
|
||
# not an API key). Create one with `omniroute sync tokens create --name <name>`.
|
||
# Equivalent to the --token flag. Used by: bin/cli/commands/sync.mjs.
|
||
# OMNIROUTE_SYNC_TOKEN=
|
||
|
||
# Per-attempt HTTP timeout for CLI → server calls (milliseconds). Default: 30000.
|
||
# OMNIROUTE_HTTP_TIMEOUT_MS=30000
|
||
|
||
# How long `omniroute serve` waits for the health endpoint before printing the
|
||
# readiness-timeout warning (milliseconds). Also --ready-timeout. Default: 60000.
|
||
# OMNIROUTE_READY_TIMEOUT_MS=60000
|
||
|
||
# Set to 1 to print retry/backoff details to stderr during CLI commands.
|
||
# OMNIROUTE_VERBOSE=0
|
||
|
||
# Custom directory for CLI plugin discovery (omniroute-cmd-* packages).
|
||
# Default: ~/.omniroute/plugins/ Override in dev/CI to point at a local plugin tree.
|
||
# CLI-only: the server-side plugin scanner is pointed by OMNIROUTE_PLUGINS_DIR (section 2).
|
||
# OMNIROUTE_PLUGIN_PATH=
|
||
|
||
# Suppress the CLI's update notification when the process exits.
|
||
# Default: unset. Any non-empty value disables the notice.
|
||
# Used by: bin/omniroute.mjs
|
||
# OMNIROUTE_NO_UPDATE_NOTIFIER=1
|
||
|
||
# Override the liveness URL probed by `omniroute doctor`.
|
||
# Default: the local dashboard's /api/health/degradation endpoint. A programmatic
|
||
# livenessUrl option takes precedence; otherwise this value is used verbatim.
|
||
# Used by: bin/cli/commands/doctor.mjs
|
||
# OMNIROUTE_DOCTOR_LIVENESS_URL=http://127.0.0.1:20128/api/health/degradation
|
||
|
||
# Override the provider catalog path used by CLI provider commands. Absolute paths
|
||
# are used as-is; relative paths resolve from the project root. A programmatic
|
||
# catalogPath option takes precedence. Default: src/shared/constants/providers/.
|
||
# Used by: bin/cli/provider-catalog.mjs
|
||
# OMNIROUTE_PROVIDER_CATALOG_PATH=src/shared/constants/providers
|
||
|
||
# Global fallback model for CLI provider connection tests. Resolution order is:
|
||
# configured connection model, provider-specific override, this value, then the
|
||
# provider's built-in test model. Default: provider-specific built-in model.
|
||
# Used by: bin/cli/provider-test.mjs
|
||
# OMNIROUTE_PROVIDER_TEST_MODEL=
|
||
|
||
# ── Prompt cache (system prompt deduplication) ──
|
||
# Used by: open-sse/services — caches identical system prompts across requests.
|
||
# PROMPT_CACHE_MAX_SIZE=50 # Max cached entries (default: 50)
|
||
# PROMPT_CACHE_MAX_BYTES=2097152 # Max total cache size in bytes (default: 2 MB)
|
||
# PROMPT_CACHE_TTL_MS=300000 # Cache entry TTL (default: 5 minutes)
|
||
|
||
# ── Semantic cache (deterministic response dedup, temperature=0) ──
|
||
# Used by: open-sse/services — caches identical temperature=0 responses.
|
||
# SEMANTIC_CACHE_MAX_SIZE=100 # Max cached entries (default: 100)
|
||
# SEMANTIC_CACHE_MAX_BYTES=4194304 # Max total cache size in bytes (default: 4 MB)
|
||
# SEMANTIC_CACHE_MAX_ENTRY_BYTES=262144 # Max size of one in-memory entry; larger answers stay in SQLite only (default: 256 KB)
|
||
# SEMANTIC_CACHE_TTL_MS=1800000 # Cache entry TTL (default: 30 minutes)
|
||
# SQLite pruning only; does not change TTL, memory LRU or vector cache behavior.
|
||
# All four: empty/non-numeric/non-finite/negative values use defaults; fractions round down.
|
||
# Interval 0 disables both startup and periodic pruning; other values below 60000 use 1800000.
|
||
# Values above 2147483647ms clamp to Node's maximum timer delay to avoid 1ms overflow polling.
|
||
# OMNIROUTE_SEMANTIC_CACHE_PRUNE_INTERVAL_MS=1800000
|
||
# Rows per DELETE, clamped to [100, 50000].
|
||
# OMNIROUTE_SEMANTIC_CACHE_PRUNE_BATCH_SIZE=2000
|
||
# Shared DELETE batch budget per run (expiry + optional cap), clamped to [1, 10000].
|
||
# OMNIROUTE_SEMANTIC_CACHE_PRUNE_MAX_BATCHES=50
|
||
# 0 = no row cap. Positive caps evict oldest created_at then rowid, including live rows.
|
||
# OMNIROUTE_SEMANTIC_CACHE_MAX_ROWS=0
|
||
# Expiry uses expires_at <= run start; first run after 1s, then every interval.
|
||
# A bounded run may leave backlog/rows above the cap for later runs.
|
||
|
||
# ── Local corpus index cache ──
|
||
# How many local-corpus roots keep a live in-memory index at once. The cache is
|
||
# LRU: reaching the limit evicts the least-recently-used root's index, which is
|
||
# then rebuilt on its next query. Clamped to a minimum of 1; a non-numeric value
|
||
# falls back to the default. Used by: src/lib/localCorpus/configured.ts
|
||
# OMNIROUTE_CORPUS_CACHE_SIZE=5
|
||
|
||
# ── In-memory log buffers ──
|
||
# Maximum recent stream events kept in memory for the Dashboard live view.
|
||
# STREAM_HISTORY_MAX=50
|
||
|
||
# ── Context length default ──
|
||
# Global context-length override (tokens) for every provider without a
|
||
# per-provider variable; when set it replaces catalog/registry values for them.
|
||
# Unset = built-in chain (last resort 128000).
|
||
# Per-provider form: CONTEXT_LENGTH_ + provider ID upper-cased, non [A-Z0-9]
|
||
# chars replaced by an underscore (agentrouter -> ..._AGENTROUTER). It wins over
|
||
# the global value. See docs/reference/ENVIRONMENT.md, "Per-provider context length".
|
||
# Used by: open-sse/services/contextManager.ts
|
||
# CONTEXT_LENGTH_DEFAULT=128000
|
||
|
||
# ── Usage token buffer ──
|
||
# Extra token headroom reserved when tracking usage quotas (prevents over-limit).
|
||
# Used by: open-sse/utils/usageTracking.ts
|
||
# USAGE_TOKEN_BUFFER=100
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 18. PRICING SYNC
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Automatic model pricing synchronization from external sources.
|
||
# Used by: src/lib/pricingSync.ts
|
||
|
||
# Enable periodic pricing data sync. Default: false (opt-in only).
|
||
# PRICING_SYNC_ENABLED=false
|
||
|
||
# Sync interval in seconds. Default: 86400 (24 hours).
|
||
# PRICING_SYNC_INTERVAL=86400
|
||
|
||
# Comma-separated data sources. Default: litellm
|
||
# PRICING_SYNC_SOURCES=litellm
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 18b. ARENA ELO SYNC
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Auto-update model intelligence from Arena AI leaderboard ELO scores (powers the
|
||
# Free Provider Rankings page). ON by default — fetches from api.wulong.dev on startup
|
||
# (non-blocking, never fatal). Set to false to opt out of the outbound sync.
|
||
# Also configurable from Dashboard > Settings > Feature Flags.
|
||
# Used by: src/shared/constants/featureFlagDefinitions.ts, src/lib/arenaEloSync.ts
|
||
# ARENA_ELO_SYNC_ENABLED=true
|
||
|
||
# How model ids are prefixed in GET /v1/models. "dual" (default) advertises BOTH the
|
||
# short alias prefix and the canonical provider prefix for each model (cc/claude-sonnet-4-6
|
||
# AND claude/claude-sonnet-4-6) so client configs that hardcoded either form keep working —
|
||
# which roughly doubles the catalog. "alias" emits one id per model; "canonical" emits only
|
||
# the full provider-id prefix (providers whose alias is already canonical keep their one id).
|
||
# A client can override per request with GET /v1/models?prefix=alias instead.
|
||
# Also configurable from Dashboard > Settings > Feature Flags.
|
||
# Used by: src/shared/constants/featureFlagDefinitions.ts, src/app/api/v1/models/catalog.ts
|
||
# MODELS_CATALOG_PREFIX_MODE=dual
|
||
|
||
# Sync interval in seconds. Default: 86400 (24 hours).
|
||
# ARENA_ELO_SYNC_INTERVAL=86400
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 19. MODEL SYNC (Dev)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Enable the models.dev capability sync. Default: false (opt-in only).
|
||
# Also settable from Dashboard > Settings > AI. This variable wins over that
|
||
# setting whenever it is set to anything non-empty, in either direction, so a
|
||
# deployment can pin the sync on or off without depending on database state
|
||
# surviving a rebuild. Leave it unset to let the dashboard toggle decide.
|
||
# On: 1, true, yes or on (any casing). Any other value is off.
|
||
# Used by: src/lib/modelsDevSync.ts
|
||
# MODELS_DEV_SYNC_ENABLED=false
|
||
|
||
# Development-time model catalog sync interval in seconds.
|
||
# Used by: src/lib/modelsDevSync.ts
|
||
# Default: 86400 (24 hours)
|
||
# MODELS_DEV_SYNC_INTERVAL=86400
|
||
|
||
# Self-correcting context-window reconciler interval in seconds (feature 5004).
|
||
# Pins provider-declared windows from /models discovery as auto:discovery overrides
|
||
# when they diverge from the catalog. Set to 0 to disable. Never overwrites manual overrides.
|
||
# Used by: src/lib/contextWindowResolver.ts
|
||
# Default: 86400 (24 hours)
|
||
# CONTEXT_WINDOW_RECONCILE_INTERVAL=86400
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 20. PROVIDER-SPECIFIC SETTINGS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
|
||
# ── Strict system-message-first providers ──
|
||
# Comma-separated, case-insensitive provider ids that require the `system`
|
||
# role message to be the first message (any later `system` message is
|
||
# rejected with HTTP 400 by the upstream chat template) — the same
|
||
# constraint documented for xiaomi-mimo/mimo (#6135, #7293). Extends the
|
||
# built-in list without a source change; useful for self-hosted connections
|
||
# in front of Qwen3.5+/3.6 or other strict-template backends.
|
||
# Used by: src/lib/memory/injection.ts::systemMessageMustBeFirst
|
||
# Default: unset (only xiaomi-mimo/mimo are flagged)
|
||
# OMNIROUTE_STRICT_SYSTEM_PROVIDERS=coding-agent
|
||
|
||
# ── OpenRouter ──
|
||
# OpenRouter model catalog cache TTL in ms.
|
||
# Used by: src/lib/catalog/openrouterCatalog.ts
|
||
# Default: 86400000 (24 hours)
|
||
# OPENROUTER_CATALOG_TTL_MS=86400000
|
||
|
||
# Enrich the dashboard providers list with OpenRouter weekly ranking stats.
|
||
# ON by default; set false to skip the background fetch entirely (#9324).
|
||
# Used by: src/lib/catalog/openrouterProviderStats.ts
|
||
# OPENROUTER_PROVIDER_STATS_ENABLED=true
|
||
# Cache TTL for the OpenRouter provider stats snapshot, in ms.
|
||
# Default: 86400000 (24 hours)
|
||
# OPENROUTER_PROVIDER_STATS_TTL_MS=86400000
|
||
|
||
# ── Model catalog response shape ──
|
||
# Include display-friendly name fields in /v1/models responses.
|
||
# Disable for clients that expect model IDs only.
|
||
# Defined in: src/shared/constants/featureFlagDefinitions.ts
|
||
# Used by: src/app/api/v1/models/catalog.ts
|
||
# Default: true
|
||
# MODEL_CATALOG_INCLUDE_NAMES=true
|
||
|
||
# Cold-path wait bound for a coalesced GET /v1/models catalog rebuild (#12627).
|
||
# Used by: src/app/api/v1/models/catalogCache.ts
|
||
# Default: 8000 (8 seconds). On timeout, a last-good 200 is served when available.
|
||
# CATALOG_BUILD_TIMEOUT_MS=8000
|
||
|
||
# Age after which a connection's synced model list stops being authoritative for routing (#12849).
|
||
# A stale (or never-timestamped) synced catalog fails open to the provider registry.
|
||
# Used by: src/lib/db/models/activeSyncedCatalog.ts
|
||
# Default: 2592000000 (30 days)
|
||
# OMNIROUTE_SYNCED_CATALOG_STALE_AFTER_MS=2592000000
|
||
|
||
# Response cache for GET /api/usage/analytics (#15629). Only responses that took at
|
||
# least MIN_COMPUTE_MS to build are kept, per query string, for TTL_MS.
|
||
# Used by: src/lib/usage/analyticsResponseCache.ts
|
||
# Default: 60000 (60 seconds; 0 disables) and 100 (100 ms)
|
||
# OMNIROUTE_ANALYTICS_CACHE_TTL_MS=60000
|
||
# OMNIROUTE_ANALYTICS_CACHE_MIN_COMPUTE_MS=100
|
||
|
||
# Opt-in: serve the usage-history part of GET /api/cache (prompt-cache totals
|
||
# and trend) from the shared analytics response cache. Unset (default) = the
|
||
# history is read live on every request. Set to N >= 0 to keep history payloads
|
||
# that took at least N ms to build, per clamped trendHours window, for
|
||
# OMNIROUTE_ANALYTICS_CACHE_TTL_MS (history may then lag up to that TTL;
|
||
# semantic/idempotency counters stay live; DELETE /api/cache invalidates it).
|
||
# Used by: src/app/api/cache/route.ts via src/lib/usage/analyticsResponseCache.ts
|
||
# Default: unset (off). Example: 1000 matches the analytics minimum.
|
||
# OMNIROUTE_CACHE_METRICS_MIN_COMPUTE_MS=1000
|
||
|
||
# ── NanoBanana (Image Generation) ──
|
||
# Polling config for async image generation jobs.
|
||
# Used by: open-sse/handlers/imageGeneration.ts
|
||
# NANOBANANA_POLL_TIMEOUT_MS=120000 # Max wait for job completion (default: 120s)
|
||
# NANOBANANA_POLL_INTERVAL_MS=2500 # Poll frequency (default: 2.5s)
|
||
|
||
# ── Adobe Firefly (Image / Video Generation) ──
|
||
# Optional absolute path to a system Chrome or Edge executable used for interactive sign-in
|
||
# and off-screen risk-session renewal. Auto-detected when unset.
|
||
# OMNIROUTE_LOGIN_BROWSER_PATH=
|
||
# Browser renewal and durable session cache are enabled by default; set either to 0 to opt out.
|
||
# ADOBE_FIREFLY_BROWSER_REFRESH=1
|
||
# ADOBE_FIREFLY_SESSION_DISK=1
|
||
# Minimum gap between generate submissions and extra gap after every third success (ms).
|
||
# ADOBE_FIREFLY_MIN_SUBMIT_GAP_MS=12000
|
||
# ADOBE_FIREFLY_BATCH_EXTRA_GAP_MS=15000
|
||
# Base backoff after a transient 408 response (ms); five attempts maximum.
|
||
# ADOBE_FIREFLY_SUBMIT_BASE_DELAY_MS=8000
|
||
|
||
# ── Adobe Firefly (Image Upscale) ──
|
||
# Base delay (ms) for the submit-retry exponential backoff when Adobe Firefly's
|
||
# upscale job submission is rate-limited. Used by:
|
||
# open-sse/services/adobeFireflyUpscale.ts::submitRetryDelayMs.
|
||
# Default: 8000 (20 under NODE_ENV=test/VITEST/NODE_TEST_CONTEXT).
|
||
# ADOBE_FIREFLY_SUBMIT_BASE_DELAY_MS=8000
|
||
|
||
# ── AWS Bedrock (Kiro / Audio) ──
|
||
# Region used to construct AWS Bedrock endpoints. Used by:
|
||
# src/lib/providers/validation.ts and open-sse/handlers/audioSpeech.ts.
|
||
# AWS_REGION takes precedence over AWS_DEFAULT_REGION when both are set.
|
||
# AWS_REGION=us-east-1
|
||
# AWS_DEFAULT_REGION=us-east-1
|
||
|
||
# ── Cloudflare Workers AI ──
|
||
# Account ID override for Cloudflare Workers AI executor.
|
||
# Used by: open-sse/executors/cloudflare-ai.ts
|
||
# CLOUDFLARE_ACCOUNT_ID=
|
||
|
||
# ── Cloudflare AI Playground ──
|
||
# Full desktop Chrome binary path, used when Playwright's bundled Chromium is
|
||
# blocked by the headless fingerprint check.
|
||
# Used by: open-sse/executors/cloudflare-playground.ts
|
||
# CLOUDFLARE_PLAYGROUND_CHROME_PATH=
|
||
|
||
# ── CodeBuddy (CN + International) system-prompt length cap ──
|
||
# CodeBuddy swaps a caller system prompt for a short neutral one when it carries
|
||
# a coding-agent identity marker (Tencent's content filter rejects those). Long
|
||
# system prompts are kept by default. Set an integer > 0 to also replace any
|
||
# system prompt longer than that many characters; unset, 0 or any non-integer
|
||
# value disables the length cap. Each replacement logs which rule fired.
|
||
# Used by: open-sse/executors/codebuddy/shared.ts
|
||
# CODEBUDDY_SYSTEM_PROMPT_MAX_LEN=
|
||
|
||
# ── Deno Deploy proxy relay (#4643 / 9router#1437) ──
|
||
# Override the Deno Deploy REST API base used by the proxy-pool relay deployer.
|
||
# Default: https://api.deno.com/v2 (omit unless mocking).
|
||
# Used by: src/app/api/settings/proxy/deno-deploy/route.ts
|
||
# DENO_DEPLOY_API_BASE=https://api.deno.com/v2
|
||
|
||
# Default Deno Deploy app name suggested in the "Deploy Relay" modal.
|
||
# Used by: src/app/(dashboard)/dashboard/settings/components/proxy/DenoRelayModal.tsx
|
||
# NEXT_PUBLIC_DENO_RELAY_DEFAULT_PROJECT=omniroute-deno-relay
|
||
|
||
# Set to "false" to hide the Deno Deploy relay option from the Proxy Pool tab.
|
||
# Used by: src/app/(dashboard)/dashboard/settings/components/proxy/ProxyPoolTab.tsx
|
||
# NEXT_PUBLIC_DENO_RELAY_ENABLED=true
|
||
|
||
# ── Cloudflare Workers proxy relay (#4640 / 9router#1360) ──
|
||
# Override the Cloudflare REST API base used by the proxy-pool relay deployer.
|
||
# Default: https://api.cloudflare.com/client/v4 (omit unless mocking).
|
||
# Used by: src/app/api/settings/proxy/cloudflare-deploy/route.ts
|
||
# CLOUDFLARE_API_BASE=https://api.cloudflare.com/client/v4
|
||
|
||
# Default worker project name suggested in the "Deploy Relay" modal.
|
||
# Used by: src/app/(dashboard)/dashboard/settings/components/proxy/CloudflareRelayModal.tsx
|
||
# NEXT_PUBLIC_CLOUDFLARE_RELAY_DEFAULT_PROJECT=omniroute-relay
|
||
|
||
# Set to "false" to hide the Cloudflare Workers relay option from the Proxy Pool tab.
|
||
# Used by: src/app/(dashboard)/dashboard/settings/components/proxy/ProxyPoolTab.tsx
|
||
# NEXT_PUBLIC_CLOUDFLARE_RELAY_ENABLED=true
|
||
|
||
# ── Cloudflare Tunnel (cloudflared) ──
|
||
# Custom path to cloudflared binary for tunnel management.
|
||
# Used by: src/lib/cloudflaredTunnel.ts
|
||
# CLOUDFLARED_BIN=/usr/local/bin/cloudflared
|
||
#
|
||
# Transport protocol for the tunnel. One of: http2 (default), quic, auto.
|
||
# CLOUDFLARED_PROTOCOL=http2
|
||
#
|
||
# ── Named / persistent tunnel (stable hostname) ──
|
||
# By default OmniRoute runs an ephemeral quick tunnel (random *.trycloudflare.com
|
||
# URL that changes on every restart). To bind a stable, named hostname instead,
|
||
# create a locally-managed tunnel with the cloudflared CLI:
|
||
# cloudflared tunnel login
|
||
# cloudflared tunnel create <name>
|
||
# cloudflared tunnel route dns <name> ai.example.com
|
||
# then write a ~/.cloudflared/config.yml with `tunnel:`, `credentials-file:`, and
|
||
# `ingress:` rules routing your hostname to http://localhost:<PORT> (default 20128).
|
||
# Point OmniRoute at that config to switch into named-tunnel mode — it runs
|
||
# `cloudflared tunnel --config <path> run`.
|
||
# CLOUDFLARED_CONFIG=/home/you/.cloudflared/config.yml
|
||
# CLOUDFLARED_HOSTNAME is optional — when unset, OmniRoute reads the public hostname
|
||
# from the config's first ingress rule. Set it to override what is reported as
|
||
# publicUrl/apiUrl.
|
||
# CLOUDFLARED_HOSTNAME=ai.example.com
|
||
|
||
# ── Search cache ──
|
||
# TTL for search API response caching (Perplexity, Brave, etc.).
|
||
# Used by: open-sse/services/searchCache.ts
|
||
# Default: 300000 (5 minutes)
|
||
# SEARCH_CACHE_TTL_MS=300000
|
||
|
||
|
||
# ── CC-compatible provider (experimental) ──
|
||
# Enable the Claude Code compatible provider endpoint.
|
||
# This is only for third-party relays that accept Claude Code clients exclusively.
|
||
# OmniRoute rewrites requests to pass those relays' Claude Code client validation.
|
||
# If you only want to use Claude Code CLI, or you are not sure what these relays are,
|
||
# keep this disabled and add a regular Anthropic-compatible provider instead.
|
||
# Used by: src/shared/utils/featureFlags.ts
|
||
# ENABLE_CC_COMPATIBLE_PROVIDER=false
|
||
|
||
# ── 9router embedded service ──
|
||
# Override the host/port where the embedded 9router instance listens.
|
||
# Rarely needed — defaults match the bootstrap config (127.0.0.1:20130).
|
||
# Used by: open-sse/executors/ninerouter.ts
|
||
# NINEROUTER_HOST=127.0.0.1
|
||
# NINEROUTER_PORT=20130
|
||
|
||
# ── Embedded service WebSocket proxy ──
|
||
# Standalone WebSocket proxy that tunnels WS connections to embedded services.
|
||
# Binds to loopback by default. Only change EMBED_WS_PROXY_HOST if you know
|
||
# what you are doing — exposing this to non-loopback bypasses local-only policy.
|
||
# Used by: src/lib/services/embedWsProxy.ts
|
||
# EMBED_WS_PROXY_HOST=127.0.0.1
|
||
# EMBED_WS_PROXY_PORT=20131
|
||
|
||
# ── opencode CLI server (opencode-server provider) ──
|
||
# The provider talks to the opencode CLI's local headless server (`opencode serve`)
|
||
# Requests never start it: launch it from Providers > Services > OpenCode (the
|
||
# local-only /api/services/opencode-server/* routes; loopback URLs only) or run
|
||
# `opencode serve` yourself. The CLI binary is env-only (never a dashboard setting)
|
||
# and the started server gets a minimal environment, not OmniRoute's secrets.
|
||
# Used by: open-sse/executors/opencodeServer.ts, open-sse/services/opencodeServerLauncher.ts
|
||
# Server URL (the opencode_server_url dashboard setting is the fallback). Default: http://127.0.0.1:4096
|
||
# OPENCODE_SERVER_URL=http://127.0.0.1:4096
|
||
# Absolute path to the opencode executable when it is not on PATH.
|
||
# OPENCODE_SERVER_BIN=
|
||
# Working directory of the server started from the dashboard. Default: the OmniRoute process cwd.
|
||
# OPENCODE_SERVER_CWD=
|
||
# Per-request timeout and server start-up timeout, in milliseconds.
|
||
# OPENCODE_SERVER_TIMEOUT_MS=180000
|
||
# OPENCODE_SERVER_START_TIMEOUT_MS=45000
|
||
# Directory for opencode-serve.log / opencode-serve.err.log. Default: ~/.omniroute/logs
|
||
# OMNIROUTE_LOG_DIR=
|
||
|
||
# ── CLIProxyAPI bridge (legacy) ──
|
||
# Connection settings for external CLIProxyAPI instances.
|
||
# Used by: open-sse/executors/cliproxyapi.ts
|
||
# CLIPROXYAPI_HOST=127.0.0.1
|
||
# CLIPROXYAPI_PORT=5544
|
||
# CLIPROXYAPI_CONFIG_DIR=~/.cli-proxy-api
|
||
# Data-plane key fallback; the cliproxyapi_api_key setting takes precedence.
|
||
# CLIPROXYAPI_API_KEY=
|
||
# Management key for an externally managed instance. Embedded instances use
|
||
# OmniRoute's encrypted service key.
|
||
# CLIPROXYAPI_MANAGEMENT_KEY=
|
||
# Host interface docker-compose publishes the cliproxyapi sidecar on (the
|
||
# --profile cliproxyapi Docker service, port 8317). Default: 127.0.0.1
|
||
# (loopback only) — its data volume holds provider OAuth/API credentials, and
|
||
# the pinned image has no env-based data-plane api-keys override (only a
|
||
# mounted config.yaml), so an unqualified publish spec would put a
|
||
# credential-bearing service on your whole LAN. (#12578)
|
||
# CLIPROXY_BIND_HOST=127.0.0.1
|
||
|
||
# ── Mux embedded service ──
|
||
# Override the port where the embedded Mux (coder/mux) agent-orchestration
|
||
# daemon listens. Always bound to 127.0.0.1 — never configurable to 0.0.0.0.
|
||
# Rarely needed — defaults to 8322.
|
||
# Used by: src/lib/services/bootstrap.ts, src/app/api/services/mux/_lib.ts
|
||
# MUX_SERVICE_PORT=8322
|
||
|
||
# ── open-wa embedded service ──
|
||
# Override the port where the embedded open-wa (WhatsApp Web automation)
|
||
# daemon listens. Always bound to 127.0.0.1 — never configurable to 0.0.0.0.
|
||
# Rarely needed — defaults to 8323.
|
||
# Used by: src/lib/services/bootstrap.ts
|
||
# OPENWA_SERVICE_PORT=8323
|
||
|
||
# ── Dario embedded service ──
|
||
# Override the host/port the embedded Dario (Claude Code subscription proxy)
|
||
# daemon binds to and is reached at. Always bound to 127.0.0.1 — never
|
||
# configurable to 0.0.0.0. Rarely needed — defaults to 127.0.0.1:3456.
|
||
# Used by: src/lib/services/installers/dario.ts, src/lib/services/bootstrap.ts,
|
||
# src/app/api/services/dario/_lib.ts, src/app/api/services/dario/admin/_lib.ts,
|
||
# open-sse/executors/dario.ts
|
||
# DARIO_HOST=127.0.0.1
|
||
# DARIO_PORT=3456
|
||
|
||
# ── LLMLingua embedded service ──
|
||
# Override the port and base URL for the embedded LLMLingua-2 prompt compression
|
||
# sidecar daemon. Always bound to 127.0.0.1 — never configurable to 0.0.0.0.
|
||
# Defaults to port 20135 and http://127.0.0.1:20135.
|
||
# Used by: src/lib/services/bootstrap.ts, src/lib/services/installers/llmlingua.ts,
|
||
# open-sse/services/compression/engines/llmlingua/index.ts
|
||
# LLMLINGUA_PORT=20135
|
||
# LLMLINGUA_BASE_URL=http://127.0.0.1:20135
|
||
# Hugging Face model id the sidecar loads (LLMLingua-2 JS port).
|
||
# LLMLINGUA_MODEL=atjsh/llmlingua-2-js-tinybert-meetingbank
|
||
|
||
# ── Local hostnames (Docker networking) ──
|
||
# Comma-separated additional hostnames treated as "local" for provider routing.
|
||
# Used by: open-sse/config/providerRegistry.ts — allows Docker service names.
|
||
# LOCAL_HOSTNAMES=omlx,mlx-audio
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 21. PROXY HEALTH
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Fine-tune proxy health checking behavior.
|
||
# Used by: src/lib/proxyHealth.ts
|
||
|
||
# Timeout for fast-fail health checks (ms). Default: 2000
|
||
# PROXY_FAST_FAIL_TIMEOUT_MS=2000
|
||
|
||
# Time window (hours) for calculating the average latency of candidate proxies
|
||
# in the latency-optimized pool strategy. Default: 3
|
||
# Used by: src/lib/db/proxies.ts
|
||
# PROXY_LATENCY_WINDOW_HOURS=3
|
||
|
||
# Health check result cache TTL (ms). Default: 30000 (30s)
|
||
# PROXY_HEALTH_CACHE_TTL_MS=30000
|
||
|
||
# Trailing window (hours) for the reasoning_effort=none compliance reader on
|
||
# GET /v1/models/health. Default: 24
|
||
# Used by: src/lib/db/reasoningEffortCompliance.ts
|
||
# NONE_HONORED_WINDOW_HOURS=24
|
||
|
||
# Cache TTL (ms) for the none-compliance snapshot (15-30s). Default: 20000
|
||
# Used by: src/lib/db/reasoningEffortCompliance.ts
|
||
# NONE_HONORED_CACHE_TTL_MS=20000
|
||
|
||
# Minimum none requests before a model reads honored/not-honored; below this
|
||
# the model reads unknown. Default: 3
|
||
# Used by: src/lib/db/reasoningEffortCompliance.ts
|
||
# NONE_HONORED_MIN_SAMPLE=3
|
||
|
||
# Unhealthy health check result cache TTL (ms). Default: 2000 (2s)
|
||
# Keeps transient fast-fail timeouts from poisoning a proxy for the full
|
||
# healthy-result cache window under high concurrency.
|
||
# PROXY_HEALTH_UNHEALTHY_CACHE_TTL_MS=2000
|
||
|
||
# Background proxy health scheduler (src/lib/proxyHealth/scheduler.ts).
|
||
# Periodically probes every registered proxy and (optionally) removes dead ones.
|
||
# Set "false" to disable the scheduler entirely. Default: enabled.
|
||
# PROXY_HEALTH_ENABLED=true
|
||
# Sweep interval in ms (minimum 60000). Default: 600000 (10min).
|
||
# PROXY_HEALTH_INTERVAL_MS=600000
|
||
# Probe interval in ms for edge-relay proxies (deno/vercel/cloudflare), whose probes wake a
|
||
# billed serverless isolate (#14984). Minimum 60000. Default: 21600000 (6h).
|
||
# PROXY_HEALTH_RELAY_INTERVAL_MS=21600000
|
||
|
||
# Background recovery-pass interval in ms: how often the scheduler re-probes proxies it
|
||
# previously marked unhealthy, so a proxy that comes back is picked up without a restart.
|
||
# Values below 60000 fall back to the default.
|
||
# PROXY_HEALTH_RECOVERY_INTERVAL_MS=600000
|
||
# Reachability probe target for the scheduler and the auto-test endpoint.
|
||
# Point it at an internal/self-hosted URL to avoid the public default.
|
||
# PROXY_HEALTH_TEST_URL=https://httpbin.org/ip
|
||
# Probes started at once per batch, for the scheduler and the auto-test endpoint.
|
||
# Floored at 1 and capped at 50. Default: 10.
|
||
# PROXY_HEALTH_TEST_CONCURRENCY=10
|
||
# Delay in ms between two probe departures inside a batch. Without it the whole batch
|
||
# leaves at once and a shared egress IP can trip a rate-limited target. 0 disables the
|
||
# spacing; capped at 5000. Default: 100.
|
||
# PROXY_HEALTH_TEST_STAGGER_MS=100
|
||
# Set "false" to stop probing the real host of a proxy's assigned provider (GET /models,
|
||
# no API key) and always use the generic target above instead. Default: enabled.
|
||
# PROXY_HEALTH_USE_PROVIDER_TARGET=true
|
||
# Set "true" to let the scheduler auto-remove proxies after repeated failures.
|
||
# PROXY_AUTO_REMOVE=false
|
||
# Consecutive failures before an auto-remove fires. Default: 3.
|
||
# PROXY_AUTO_REMOVE_AFTER=3
|
||
# Set "true" to let the scheduler auto-disable (status "dead") proxies after
|
||
# repeated failures instead of deleting them. Non-destructive alternative to
|
||
# PROXY_AUTO_REMOVE — the row stays in the registry, drops out of pool/rotation
|
||
# resolution immediately, and is automatically re-activated once it starts
|
||
# answering probes again. Shares the PROXY_AUTO_REMOVE_AFTER threshold above.
|
||
# If both PROXY_AUTO_REMOVE and PROXY_AUTO_DISABLE are "true", auto-remove wins.
|
||
# PROXY_AUTO_DISABLE=false
|
||
# Let automated reachability probes (the scheduler + the "Test All" button) WRITE
|
||
# a proxy's status. Default "false": probes are read-only and never deactivate a
|
||
# proxy — only the operator sets active/inactive (a flaky probe must not strand an
|
||
# assigned proxy; #6246). Set "true" to restore the legacy test-and-set behaviour.
|
||
# PROXY_HEALTH_AUTO_DEACTIVATE=false
|
||
# Opt-in feature flag (default off; a dashboard DB override wins over this value): show,
|
||
# under a proxy pool in the dashboard, how many observed egress IPs served its members over
|
||
# the last 24 h and how many connections used them (read-only, computed from the proxy log,
|
||
# never used for routing). "true" (or 1, yes) enables it.
|
||
# PROXY_POOL_EGRESS_OBSERVATION=false
|
||
|
||
# Opt-in: skip the scheduler probe for proxies already proven by recent
|
||
# production traffic (single provider, no recent proxy failure). Default: off.
|
||
# PROXY_HEALTH_PASSIVE_SKIP=false
|
||
# Window in ms of production traffic the passive skip looks at (60000..599999).
|
||
# Default: 300000 (5min).
|
||
# PROXY_PASSIVE_WINDOW_MS=300000
|
||
# Opt-in feature flag (default off; a dashboard DB override wins over this value): accept
|
||
# operator-pushed dated observed addresses per pool member and merge them with the journal
|
||
# read for display and pool order. "true" (or 1, yes) enables the push route and the merge.
|
||
# PROXY_OPERATOR_EGRESS_ENABLED=false
|
||
|
||
# Observation window for operator-pushed egress rows (read on every read; no restart
|
||
# needed). Bounded to 1..168; out-of-range, non-numeric, or empty falls back to 24 with a
|
||
# single process-wide warning, never a throw.
|
||
# Used by: src/lib/db/proxyOperatorEgress.ts.
|
||
# PROXY_OPERATOR_EGRESS_WINDOW_HOURS=24
|
||
|
||
# Allow OAuth and provider validation flows to bypass a pinned proxy and connect
|
||
# directly when proxy reachability pre-checks fail. Default: false.
|
||
# Also configurable from Dashboard > Settings > Feature Flags.
|
||
# OMNIROUTE_CONTROL_PLANE_PROXY_DIRECT_FALLBACK=false
|
||
|
||
# Rate limit maximum wait time before failing a request (ms). Default: 30000 (30s)
|
||
# Used by: open-sse/services/rateLimitManager.ts
|
||
# RATE_LIMIT_MAX_WAIT_MS=30000
|
||
|
||
# Limiter-managed execution backstop (Bottleneck `expiration`): bounds a job's
|
||
# post-dispatch execution, never queue wait. Must stay ABOVE upstream
|
||
# fetch-start timeouts on non-incremental gateways. Default: 600000 (10 min)
|
||
# Used by: open-sse/services/rateLimitManager.ts
|
||
# RATE_LIMIT_EXECUTION_MAX_WAIT_MS=600000
|
||
|
||
# Rate limit queue admission cap: reject with 429 queue_full once this many requests
|
||
# are already queued (0 = disabled/unbounded, the default). Used by: open-sse/services/rateLimitManager.ts
|
||
# RATE_LIMIT_MAX_QUEUE_DEPTH=0
|
||
|
||
# Force the auto-enable rate limit safety net on/off regardless of the persisted
|
||
# Dashboard setting. Used by: open-sse/services/rateLimitManager.ts.
|
||
# Accepted values: true|1|on (force on), false|0|off (force off), unset (use Dashboard).
|
||
# RATE_LIMIT_AUTO_ENABLE=
|
||
|
||
# Provider cooldown tracking: minimum time (ms) before a failed provider/connection
|
||
# can be retried. Prevents subsequent requests from re-walking failing providers.
|
||
# Scaled exponentially: minCooldown * 2^(failures-1), capped at maxRetryCooldownMs.
|
||
# Used by: open-sse/services/providerCooldownTracker.ts
|
||
# PROVIDER_COOLDOWN_MIN_MS=5000
|
||
|
||
# Provider cooldown tracking: maximum time (ms) before a failed provider/connection
|
||
# is retried regardless. Hard cap to prevent providers from being skipped indefinitely.
|
||
# Used by: open-sse/services/providerCooldownTracker.ts
|
||
# PROVIDER_COOLDOWN_MAX_MS=300000
|
||
|
||
# Enable/disable global provider cooldown tracking. Opt-in: this global
|
||
# cross-request cooldown overlaps the existing Connection Cooldown / Provider
|
||
# Circuit Breaker layers, so it is OFF by default. When disabled, only the
|
||
# existing per-request/per-connection cooldown state is used (previous behavior).
|
||
# Used by: open-sse/services/providerCooldownTracker.ts
|
||
# Accepted values: true|1|on (enable). Unset or anything else = disabled (default).
|
||
# PROVIDER_COOLDOWN_ENABLED=true
|
||
|
||
# Transparent stream recovery (free-claude-code port). When enabled, the opening SSE
|
||
# window is briefly held (up to STREAM_RECOVERY.HOLDBACK_MS) so an upstream truncation
|
||
# before any byte reaches the client can be retried invisibly. Opt-in: holding the
|
||
# window adds up to that much time-to-first-token latency on every stream, so it is
|
||
# OFF by default. Seeds ResilienceSettings.streamRecovery.enabled.
|
||
# Used by: open-sse/services/streamRecovery.ts, open-sse/handlers/chatCore.ts
|
||
# Accepted values: true|1|on (enable). Unset or anything else = disabled (default).
|
||
# STREAM_RECOVERY_ENABLED=true
|
||
|
||
# Mid-stream continuation (Fase 4.4): when an upstream stream truncates AFTER bytes
|
||
# already reached the client, re-request with the partial text as an assistant prefill
|
||
# and stitch the missing suffix (plain-text OpenAI-compatible streams only; never with a
|
||
# tool call in flight). OFF by default — the recovered tail arrives as one burst, not
|
||
# token-by-token. Independent of STREAM_RECOVERY_ENABLED (different risk profile).
|
||
# Seeds ResilienceSettings.streamRecovery.continueMidStream.
|
||
# Used by: open-sse/services/streamRecovery.ts, open-sse/handlers/chatCore.ts
|
||
# Accepted values: true|1|on (enable). Unset or anything else = disabled (default).
|
||
# STREAM_RECOVERY_MIDSTREAM_ENABLED=true
|
||
|
||
# Active-stream throughput watchdog (#9709). Detects streams that keep sending
|
||
# heartbeats/chunks but produce too little useful assistant text. Separate from
|
||
# STREAM_IDLE_TIMEOUT_MS (silence) and the hard upstream attempt deadline. OFF by
|
||
# default. Tool-call/reasoning phases suspend judgement; post-commit streams are
|
||
# never blindly replayed.
|
||
# STREAM_THROUGHPUT_WATCHDOG_ENABLED=true
|
||
# STREAM_THROUGHPUT_WATCHDOG_WARMUP_MS=30000
|
||
# STREAM_THROUGHPUT_WATCHDOG_WINDOW_MS=30000
|
||
# STREAM_THROUGHPUT_WATCHDOG_MIN_BYTES_PER_SECOND=4
|
||
# STREAM_THROUGHPUT_WATCHDOG_MIN_USEFUL_BYTES=1
|
||
|
||
# Stagger interval (ms) between provider token healthchecks at startup.
|
||
# Used by: src/lib/tokenHealthCheck.ts. Default: 3000.
|
||
# HEALTHCHECK_STAGGER_MS=3000
|
||
|
||
# Randomized jitter range (ms) added on top of HEALTHCHECK_STAGGER_MS between
|
||
# provider token healthchecks, to prevent bursting (Issue #1220).
|
||
# Used by: src/lib/tokenHealthCheck.ts. Defaults: min=500, max=5000.
|
||
# HEALTHCHECK_JITTER_MIN_MS=500
|
||
# HEALTHCHECK_JITTER_MAX_MS=5000
|
||
|
||
# Concurrent-check batch size for the startup token-healthcheck sweep. Larger
|
||
# values check more connections in parallel; smaller values reduce burst load.
|
||
# Used by: src/lib/tokenHealthCheck.ts. Default: 20 (Issue #7875, regression of #7719).
|
||
# HEALTHCHECK_BATCH_SIZE=20
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 22. DEBUGGING
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# These variables enable verbose debugging output. NEVER enable in production.
|
||
|
||
# Cursor executor verbose debug (decoded SSE chunks, etc.).
|
||
# CURSOR_STREAM_DEBUG is kept as a backward-compatible alias.
|
||
# Used by: open-sse/executors/cursor.ts
|
||
# CURSOR_DEBUG=1
|
||
|
||
# Enable verbose trace logging for OmniRoute internals.
|
||
# Used by: open-sse/handlers/chatCore.ts.
|
||
# OMNIROUTE_TRACE=true
|
||
|
||
# Standard DEBUG flag (same effect as OMNIROUTE_TRACE).
|
||
# DEBUG=true
|
||
# CURSOR_STREAM_DEBUG=1
|
||
|
||
# When CURSOR_DEBUG=1, also append raw decoded chunks to this file path.
|
||
# CURSOR_DUMP_FILE=/tmp/cursor-stream.log
|
||
|
||
# Cursor stream idle timeout (ms). Default: 300000 (5 min).
|
||
# Used by: open-sse/executors/cursor.ts.
|
||
# CURSOR_STREAM_TIMEOUT_MS=300000
|
||
# Grace window (ms) after a composer kv_after_text soft terminator when bytes remain
|
||
# buffered — gives a trailing exec_mcp tool call time to complete its frame. 2s covers
|
||
# every exec_mcp-behind-kv ordering observed live.
|
||
# CURSOR_KV_GRACE_MS=2000
|
||
|
||
# Cursor tool-commit directive toggle. Default-on: when a request declares
|
||
# tools, a directive is prepended so composer-2.5 reliably issues tool calls
|
||
# instead of narrating intent. Set to 0 to disable.
|
||
# Used by: open-sse/executors/cursor.ts.
|
||
# CURSOR_TOOL_DIRECTIVE=1
|
||
|
||
# Operator-defined system prompt text appended to the system message AFTER
|
||
# translation (post-translation injection), so it reaches codex/Responses and
|
||
# /v1/messages paths. Also used as the directive prefix stripped from echoed
|
||
# system preamble blocks. Leave unset to disable.
|
||
# Used by: open-sse/translator/request/claude-to-openai.ts, open-sse/translator/response/openai-to-claude.ts.
|
||
# OMNIROUTE_SYSTEM_INSTRUCTION_APPEND=
|
||
|
||
# Set to "1" to also strip echoed system-prompt PREAMBLE blocks
|
||
# (<analysis>/<system-reminder>/<summary> blocks, prose reproductions of the skill
|
||
# section) from the start of an openai->claude stream. OFF by default: it recognises
|
||
# constructs by English-prose heuristics and DOES mutate the response payload, so a
|
||
# reply that genuinely opens with such a section would lose it. Turn it on only when
|
||
# you actually hit the system-echo leak.
|
||
# Used by: open-sse/translator/response/openai-to-claude.ts, open-sse/utils/directivePreambleStripper.ts.
|
||
# OMNIROUTE_STRIP_SYSTEM_PREAMBLE=0
|
||
|
||
# Per-image fetch timeout (ms) for remote image_url vision input. Default: 15000.
|
||
# Used by: open-sse/utils/cursorImages.ts.
|
||
# CURSOR_IMAGE_FETCH_TIMEOUT_MS=15000
|
||
|
||
# Cursor state DB path override (for IDE cursor version detection).
|
||
# Used by: open-sse/utils/cursorVersionDetector.ts. Default: probed automatically.
|
||
# CURSOR_STATE_DB_PATH=
|
||
|
||
# Cursor Agent CLI build id for AgentService/Run impersonation (YYYY.MM.DD-<hash>).
|
||
# Used by: open-sse/utils/cursorAgentCliVersion.ts. Default: detect local install, else pin.
|
||
# CURSOR_AGENT_CLI_VERSION=2026.07.08-0c04a8a
|
||
|
||
# Path to the Cursor Agent binary used for image generation.
|
||
# Used by: open-sse/handlers/imageGeneration/providers (CURSOR_IMAGE.md).
|
||
# CURSOR_AGENT_BIN=/path/to/agent
|
||
|
||
# Cursor image-generation wall clock (ms). Default: 210000.
|
||
# CURSOR_IMG_TIMEOUT_MS=210000
|
||
|
||
# UC (uncensored.com) image-generation result-poll cadence + wall clock (ms).
|
||
# Used by: open-sse/handlers/imageGeneration/providers/ucImage.ts. Defaults: 2000 / 60000.
|
||
# UC_IMAGE_POLL_INTERVAL_MS=2000
|
||
# UC_IMAGE_POLL_TIMEOUT_MS=60000
|
||
|
||
# UC (uncensored.com) video-generation result-poll cadence + wall clock (ms).
|
||
# Used by: open-sse/handlers/videoGeneration/providers/ucVideo.ts. Defaults: 3000 / 300000.
|
||
# UC_VIDEO_POLL_INTERVAL_MS=3000
|
||
# UC_VIDEO_POLL_TIMEOUT_MS=300000
|
||
|
||
# Shared-seat concurrency gate for Cursor image jobs. Default: 2.
|
||
# CURSOR_IMG_MAX_CONCURRENT=2
|
||
|
||
# Override Cursor CLI --model for image jobs. Default: request model / auto.
|
||
# CURSOR_IMG_MODEL=auto
|
||
|
||
# Cursor Agent CLI data directory override (versions live under <dir>/versions/).
|
||
# Used by: open-sse/utils/cursorAgentCliVersion.ts. Default: ~/.local/share/cursor-agent (unix)
|
||
# or %LOCALAPPDATA%\cursor-agent (win32). Official agent CLI also honors this var.
|
||
# CURSOR_DATA_DIR=
|
||
|
||
# Direct Cursor bearer token used by scripts/ad-hoc/cursor-tap.cjs (developer tooling).
|
||
# CURSOR_TOKEN=
|
||
|
||
# Log Responses API SSE-to-JSON translation details.
|
||
# DEBUG_RESPONSES_SSE_TO_JSON=true
|
||
|
||
# Log request shape (content-type + content-length) for large chat payloads.
|
||
# Used by: src/app/api/v1/chat/completions/route.ts. Set to "0" to silence.
|
||
# Default: disabled (opt-in).
|
||
# OMNIROUTE_LOG_REQUEST_SHAPE=1
|
||
|
||
# Write raw (untruncated) request/response JSON in call log artifacts.
|
||
# When enabled, serializeArtifactForStorage skips size-based truncation.
|
||
# Also enabled automatically when APP_LOG_LEVEL=debug.
|
||
# WARNING: produces large files — use only for temporary debugging.
|
||
# CHAT_DEBUG_FILE=true
|
||
|
||
# Surf empty textContent chunks in the Claude response translation path for debugging.
|
||
# Used by: open-sse/handlers/responseTranslator.ts. Set to "true" to enable.
|
||
# Default: disabled (opt-in).
|
||
# DEBUG_CLAUDE_NONSTREAM=true
|
||
|
||
# Enable E2E test mode — relaxes auth and enables test harness hooks.
|
||
# NEXT_PUBLIC_OMNIROUTE_E2E_MODE=true
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 23. GITHUB INTEGRATION (Issue Reporting)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Allow users to report issues directly from the Dashboard to GitHub.
|
||
# Used by: src/app/api/v1/issues/report/route.ts
|
||
|
||
# GitHub repository in owner/repo format.
|
||
# GITHUB_ISSUES_REPO=owner/repo
|
||
|
||
# GitHub Personal Access Token with issues:write scope.
|
||
# GITHUB_ISSUES_TOKEN=ghp_xxxx
|
||
|
||
# Generic GitHub access token consumed by issue triage / agent helpers.
|
||
# Used by: src/app/api/v1/issues/* and src/lib/cloudAgent/* — falls back to
|
||
# GITHUB_ISSUES_TOKEN when unset.
|
||
# GITHUB_TOKEN=
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 24. PROVIDER QUOTAS, TUNNELS & SANDBOXED SKILLS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Provider quota endpoints, network tunnels (Tailscale, Ngrok, MITM debug
|
||
# proxy), 1Proxy egress pool, skills sandbox runtime, and miscellaneous CLI
|
||
# binaries referenced by the executor layer or the dashboard runtime.
|
||
|
||
# ── Alibaba (Bailian) coding plan quota ──
|
||
# Host/full URL override used by: open-sse/services/bailianQuotaFetcher.ts.
|
||
# When unset the fetcher uses the production Alibaba endpoints.
|
||
# ALIBABA_CODING_PLAN_HOST=
|
||
# ALIBABA_CODING_PLAN_QUOTA_URL=
|
||
|
||
# ── Qwen Cloud / Model Studio personal Token Plan quota ──
|
||
# Cookie-authenticated console-gateway fetcher (issue #9603). Used by:
|
||
# open-sse/services/qwenTokenPlanQuotaFetcher.ts. Prefer the per-connection
|
||
# Dashboard fields (qwenCloudCookie / qwenCloudSecToken) — these env vars are
|
||
# global fallbacks. Cookie/sec_token are SENSITIVE session credentials.
|
||
# Getting the cookie: log in to home.qwencloud.com > Billing > Subscription,
|
||
# press F12 > Network, reload, filter by api.json, click any request to
|
||
# cs-data.qwencloud.com and copy the WHOLE Cookie value from Request Headers
|
||
# (it contains login_qwencloud_ticket). Paste it on ONE line — the value may
|
||
# contain '=' and ';'. It expires with the browser session; re-paste it when
|
||
# the dashboard reports an expired session.
|
||
# QWEN_CLOUD_COOKIE=
|
||
# QWEN_CLOUD_SEC_TOKEN=
|
||
# QWEN_TOKEN_PLAN_HOST=
|
||
# QWEN_TOKEN_PLAN_DASHBOARD_URL=
|
||
|
||
# ── Xiaomi MiMo Token Plan quota ──
|
||
# Console-cookie live fetch + self-tracked fallback (issue #15753). Used by:
|
||
# open-sse/services/usage/xiaomi-mimo.ts. Prefer the per-connection Dashboard
|
||
# fields (xiaomiMimoConsoleCookie / monthlyTokenLimit) — these env vars are
|
||
# global fallbacks. The cookie is a SENSITIVE session credential.
|
||
# Getting the cookie: log in to platform.xiaomimimo.com, open the Token Plan
|
||
# page, press F12 > Network, reload, click any request to
|
||
# platform.xiaomimimo.com and copy the WHOLE Cookie value from Request Headers
|
||
# (it contains api-platform_serviceToken and userId). Paste it on ONE line —
|
||
# the value may contain '=' and ';'. It expires with the browser session;
|
||
# re-paste it when the dashboard reports an expired session.
|
||
# XIAOMI_MIMO_CONSOLE_COOKIE=
|
||
# Monthly budget (Credits) for the OmniRoute-tracked fallback without a cookie.
|
||
# Default: 4100000000 (Lite tier). Standard 11000000000 / Pro 38000000000 /
|
||
# Max 82000000000.
|
||
# XIAOMI_MIMO_MONTHLY_TOKEN_LIMIT=
|
||
|
||
# ── Alibaba Model Studio free-tier quota sync ──
|
||
# Console front-end path overrides for the free-tier quota fetcher. Used by:
|
||
# open-sse/services/alibabaFreeTierQuotaFetcher.ts. When unset, the fetcher
|
||
# uses the production Bailian console paths.
|
||
# ALIBABA_FREE_TIER_VISION_FE_PATH=
|
||
# ALIBABA_FREE_TIER_MULTIMODAL_FE_PATH=
|
||
# ALIBABA_FREE_TIER_AUDIO_FE_PATH=
|
||
# Optional path to a local JSON override for the built-in text free-tier
|
||
# allowlist. Used by: open-sse/services/alibabaFreeTierAllowlist.ts. When
|
||
# unset, the fetcher falls back to $DATA_DIR/alibaba-free-tier-allowlist.json
|
||
# then config/alibaba-free-tier-allowlist.json.
|
||
# ALIBABA_FREE_TIER_ALLOWLIST_PATH=
|
||
|
||
# ── Context window tuning ──
|
||
# Tokens reserved for completion output when computing prompt budgets.
|
||
# Used by: open-sse/services/contextManager.ts. Default: 1024.
|
||
# CONTEXT_RESERVE_TOKENS=1024
|
||
# How many of the newest inline images to keep when pruning older ones to fit
|
||
# the context window (#8560). Used by: open-sse/services/contextManager.ts.
|
||
# Default: 2.
|
||
# CONTEXT_KEEP_LATEST_IMAGES=2
|
||
|
||
# ── Model alias rewriting (legacy compatibility) ──
|
||
# Toggle the legacy model-alias compatibility layer used by older clients.
|
||
# Used by: open-sse/services/model.ts. Default: enabled.
|
||
# MODEL_ALIAS_COMPAT_ENABLED=true
|
||
|
||
# ── Devin CLI binary path ──
|
||
# Used by: open-sse/executors/devin-cli.ts. Default: looked up via PATH.
|
||
# CLI_DEVIN_BIN=devin
|
||
# Agentic bridge-only binary override. The bridge still executes ACP stdio only.
|
||
# CLI_DEVIN_AGENTIC_BIN=devin
|
||
# Required isolated HOME for the agentic Devin child process.
|
||
# DEVIN_AGENTIC_HOME=/home/bridge
|
||
# Bounded ACP turn timeout in milliseconds. Default: 120000.
|
||
# DEVIN_AGENTIC_ACP_TIMEOUT_MS=120000
|
||
# Agentic bridge model aliases. Values must keep the devin-cli-agentic/ prefix.
|
||
# DEVIN_BRIDGE_MODEL=devin-cli-agentic/swe-1-7
|
||
# DEVIN_BRIDGE_SONNET_MODEL=devin-cli-agentic/swe-1-7
|
||
# DEVIN_BRIDGE_OPUS_MODEL=devin-cli-agentic/swe-1-7
|
||
# DEVIN_BRIDGE_HAIKU_MODEL=devin-cli-agentic/swe-1-7
|
||
# DEVIN_BRIDGE_SUBAGENT_MODEL=devin-cli-agentic/swe-1-7
|
||
|
||
# ── Devin Desktop upstream compatibility versions ──
|
||
# Desktop ide_version. Must use x.y.z format; invalid/unset values use 3.6.27.
|
||
# DEVIN_DESKTOP_VERSION=3.6.27
|
||
# Bundled Codeium/language-server extension_version, distinct from Desktop.
|
||
# Must use x.y.z format; invalid/unset values use the bundled default 1.48.2.
|
||
# DEVIN_DESKTOP_EXTENSION_VERSION=1.48.2
|
||
# Optional override for the Codeium seat-management API used by Devin CLI quota.
|
||
# Used by: open-sse/services/usage/devinCli.ts. Default: https://server.codeium.com
|
||
# DEVIN_SEAT_API_URL=https://server.codeium.com
|
||
|
||
# ── Command Code (custom CLI) callback ──
|
||
# Local port used for OAuth-style callbacks from the Command Code CLI helper.
|
||
# Used by: src/app/api/providers/command-code/auth/shared.ts.
|
||
# COMMAND_CODE_CALLBACK_PORT=
|
||
|
||
# ── Command Code CLI version header ──
|
||
# Value sent as the x-command-code-version header to the Command Code upstream.
|
||
# Overrides the built-in default; bump if the upstream requires a newer CLI version.
|
||
# Used by: open-sse/executors/commandCode.ts
|
||
# Default: 0.33.2
|
||
# COMMAND_CODE_VERSION=0.33.2
|
||
|
||
# Base URL for the Command Code usage/quota upstream, used by smartphone
|
||
# quota-fetcher telemetry.
|
||
# Used by: open-sse/services/usage/command-code.ts
|
||
# Default: https://api.commandcode.ai
|
||
# COMMANDCODE_API_URL=https://api.commandcode.ai
|
||
|
||
# ── MITM debug proxy (development only) ──
|
||
# Used by: src/mitm/server.cjs — captures upstream traffic for inspection.
|
||
# MITM_LOCAL_PORT=443
|
||
# MITM_DISABLE_TLS_VERIFY=0
|
||
# Idle socket timeout (ms) for proxied connections; sockets idle past this are torn
|
||
# down to avoid leaking half-open tunnels (src/mitm/socketTimeouts.ts, server.cjs).
|
||
# MITM_IDLE_TIMEOUT_MS=60000
|
||
# Routing-decision log verbosity: 0 silences, higher values log more bypass/route
|
||
# decisions (src/mitm/server.cjs, _internal/bypass.cjs).
|
||
# MITM_VERBOSE=1
|
||
# Strip the leading `sudo` from MITM cert-trust commands (src/mitm/systemCommands.ts) —
|
||
# for root-less / user-namespaced deployments (e.g. rootless Docker/Podman)
|
||
# where the operator trusts the CA manually (e.g. via Node's extra-CA-certs mechanism).
|
||
# OMNIROUTE_NO_SUDO=0
|
||
|
||
# ── Antigravity MITM bridge (bin/antigravity-bridge.mjs) ──
|
||
# Local HTTPS listener that fronts the Antigravity IDE and forwards to the router.
|
||
# BRIDGE_PORT: port the bridge listens on. Defaults to 20129.
|
||
# ROUTER_URL: where it forwards /v1/antigravity traffic. Defaults to the local router.
|
||
# CERT_DIR: directory holding server.key/server.crt for the bridge's TLS listener.
|
||
# Defaults to ~/.omniroute/mitm (the MITM CA directory).
|
||
# BRIDGE_PORT=20129
|
||
# ROUTER_URL=http://127.0.0.1:20128/v1/antigravity
|
||
# CERT_DIR=~/.omniroute/mitm
|
||
# Explicit opt-out: skip provisioning /etc/hosts DNS entries for the Antigravity
|
||
# proxy hostnames entirely (containers with no sudo/root available).
|
||
# Used by: src/mitm/dns/provision.ts.
|
||
# SKIP_ANTIGRAVITY_DNS=true
|
||
# Skip writing to the hosts file when adding/removing DNS entries (e.g. sandboxed
|
||
# or read-only test environments). Used by: src/mitm/dns/dnsConfig.ts.
|
||
# OMNIROUTE_SKIP_DNS_WRITE=1
|
||
# Opt in to the root-CA + per-host-leaf cert model for the MITM proxy (#6684).
|
||
# Fresh installs and installs with this set to "true" get a persisted root CA that
|
||
# signs per-host leaves; installs with a pre-existing trusted legacy leaf keep the
|
||
# legacy fixed-SAN cert unless opted in. Used by: src/mitm/manager.ts.
|
||
# MITM_ROOT_CA_ENABLED=true
|
||
# Set BY the MITM manager for the spawned proxy process ("root-ca" | "legacy") —
|
||
# reflects the migration decision above; not meant to be set manually.
|
||
# Read by: src/mitm/server.cjs.
|
||
# MITM_CERT_MODE=legacy
|
||
|
||
# ── Test/CI-only guards (never needed in production) ──
|
||
# Set automatically by tests/_setup/isolateDataDir.ts and the CI workflows: the
|
||
# test suite must NEVER mutate the OS trust store (a fake test PEM installed via
|
||
# update-ca-certificates broke all system TLS on a persistent runner, 2026-07-05).
|
||
# OMNIROUTE_SKIP_SYSTEM_TRUST=1
|
||
# check-changelog-integrity.mjs (anti CHANGELOG-eat gate): explicit base ref override.
|
||
# Intentional transformations require an exact reviewed entry in
|
||
# config/release/changelog-reconciliations.json; there is no runtime bypass.
|
||
# CHANGELOG_BASE_REF=origin/release/v0.0.0
|
||
# check-migration-numbering.mjs: explicit base ref for the comparison with the base
|
||
# (defaults in CI to the PR merge ref's first parent / merge_group.base_sha / merge-base).
|
||
# MIGRATION_BASE_REF=origin/release/v0.0.0
|
||
# Test-only: stand-in for scripts/check/migration-commutation.ts in the gate's tests.
|
||
# MIGRATION_COMMUTATION_SCRIPT=
|
||
|
||
# ── Remote audio provider nodes ──
|
||
# Used by: src/app/api/v1/_shared/audioProviderNodes.ts — lets the /v1/audio/*
|
||
# routes use an OpenAI-compatible provider node hosted outside localhost.
|
||
# OFF by default: routing audio to a remote host changes egress identity, so it
|
||
# must be an explicit operator decision. Loopback/private nodes (localhost,
|
||
# 127.0.0.1, 172.16-31.x) are always allowed and unaffected by this flag.
|
||
# When enabled, the node authenticates with the API key stored on its connection.
|
||
# AUDIO_REMOTE_PROVIDER_NODES=false
|
||
|
||
# Used by: src/app/api/v1/_shared/rerankProviderNodes.ts — lets POST /v1/rerank (and
|
||
# the memory engine's loopback rerank step) use an OpenAI-compatible provider node
|
||
# hosted outside localhost, e.g. a LAN box or Tailscale peer running TEI/Infinity/vLLM.
|
||
# OFF by default: routing to a remote host changes egress identity, so it must be an
|
||
# explicit operator decision. Loopback/private nodes (localhost, 127.0.0.1,
|
||
# 172.16-31.x) are always allowed and unaffected by this flag. A remote node's base URL
|
||
# must also pass the provider outbound URL policy (see OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS).
|
||
# RERANK_REMOTE_PROVIDER_NODES=false
|
||
|
||
# Used by: src/shared/network/localNodeHosts.ts — hostnames (comma or whitespace
|
||
# separated) that provider-node routing treats as local, e.g. the Docker/Compose service
|
||
# name of a reranker or TEI sidecar on OmniRoute's own Docker network, so the node does
|
||
# not need a hard-coded container IP. Listed hosts are eligible for the /v1/rerank and
|
||
# /v1/audio/* provider-node routes and the local health check without turning on
|
||
# RERANK_/AUDIO_REMOTE_PROVIDER_NODES for every remote node, and are called directly
|
||
# (never through HTTP(S)_PROXY or a connection's pinned proxy). They still send the
|
||
# connection's API key. Only single-label names and .internal/.local names are
|
||
# accepted; public FQDNs, IP literals and cloud-metadata names are ignored with a warning.
|
||
# Empty by default (no change).
|
||
# OMNIROUTE_LOCAL_PROVIDER_NODE_HOSTS=reranker,tei
|
||
|
||
# ── Free Proxy Pool (auto-sync scheduler) ──
|
||
# Background refresh of the free-proxy pool. Opt-in, OFF by default (parallels
|
||
# Hard Rule #20's default-off posture for data-mutating background features).
|
||
# Used by: src/lib/freeProxyProviders/scheduler.ts
|
||
# FREE_PROXY_AUTO_SYNC_ENABLED=true
|
||
# Sync interval in ms (default: 1800000 = 30 min).
|
||
# FREE_PROXY_AUTO_SYNC_INTERVAL_MS=1800000
|
||
|
||
# ── Free Proxy Pool (1proxy source) ──
|
||
# Used by: src/lib/freeProxyProviders/oneproxy.ts
|
||
# Set FREE_PROXY_1PROXY_ENABLED=false to disable this source.
|
||
# FREE_PROXY_1PROXY_ENABLED=true
|
||
# FREE_PROXY_1PROXY_API_URL=https://1proxy-api.aitradepulse.com/api/v1/proxies/advanced
|
||
# FREE_PROXY_1PROXY_MAX=500
|
||
# FREE_PROXY_1PROXY_MIN_QUALITY=50
|
||
|
||
# ── Free Proxy Pool (Proxifly source) ──
|
||
# Used by: src/lib/freeProxyProviders/proxifly.ts
|
||
# Enabled by default; set to false to disable.
|
||
# FREE_PROXY_PROXIFLY_ENABLED=true
|
||
# FREE_PROXY_PROXIFLY_QUANTITY=100
|
||
# FREE_PROXY_PROXIFLY_ANONYMITY=elite
|
||
|
||
# ── Free Proxy Pool (IPLocate source) ──
|
||
# Used by: src/lib/freeProxyProviders/iplocate.ts
|
||
# Opt-in only; must set FREE_PROXY_IPLOCATE_ENABLED=true to activate.
|
||
# FREE_PROXY_IPLOCATE_ENABLED=false
|
||
# FREE_PROXY_IPLOCATE_BASE_URL=https://raw.githubusercontent.com/iplocate/free-proxy-list/main/protocols
|
||
|
||
# ── Free Proxy Pool (Webshare source) ──
|
||
# Used by: src/lib/freeProxyProviders/webshare.ts
|
||
# Paid, per-account proxy list — requires FREE_PROXY_WEBSHARE_API_KEY to activate,
|
||
# regardless of FREE_PROXY_WEBSHARE_ENABLED.
|
||
# FREE_PROXY_WEBSHARE_ENABLED=true
|
||
# FREE_PROXY_WEBSHARE_API_KEY=
|
||
# FREE_PROXY_WEBSHARE_API_URL=https://proxy.webshare.io/api/v2/proxy/list/
|
||
# FREE_PROXY_WEBSHARE_MAX=500
|
||
|
||
# ── Vercel Relay ──
|
||
# Used by: src/app/api/settings/proxy/vercel-deploy/route.ts
|
||
# Hides the "Deploy Relay" button when set to false.
|
||
# NEXT_PUBLIC_VERCEL_RELAY_ENABLED=true
|
||
# VERCEL_API_BASE=https://api.vercel.com
|
||
# Default project name pre-filled in the Vercel Relay deploy modal.
|
||
# NEXT_PUBLIC_VERCEL_RELAY_DEFAULT_PROJECT=omniroute-relay
|
||
|
||
# ── Tailscale tunnel binaries ──
|
||
# Optional explicit paths to tailscale/tailscaled binaries used by the
|
||
# dashboard's tunnel manager. Used by: src/lib/tailscaleTunnel.ts.
|
||
# TAILSCALE_BIN=/usr/local/bin/tailscale
|
||
# TAILSCALED_BIN=/usr/local/bin/tailscaled
|
||
# Pre-shared Tailscale auth key for non-interactive / headless `tailscale up`
|
||
# (passed via --auth-key=). When unset, login falls back to the interactive
|
||
# browser auth URL. Used by: src/lib/tailscaleTunnel.ts.
|
||
# TAILSCALE_AUTHKEY=
|
||
|
||
# ── Ngrok tunnel ──
|
||
# Used by: src/lib/ngrokTunnel.ts — authenticates outbound tunnels.
|
||
# NGROK_AUTHTOKEN=
|
||
|
||
# ── Database backups ──
|
||
# Used by: src/lib/db/backup.ts.
|
||
# DB_BACKUP_MAX_FILES=20
|
||
# DB_BACKUP_RETENTION_DAYS=0
|
||
# Tick interval (ms) of the server-side job that executes backup-schedule.json.
|
||
# Must stay well under the 1-minute cron granularity; values below 5000 (or
|
||
# unparseable) fall back to the 30000 default.
|
||
# Used by: src/lib/jobs/backupScheduleJob.ts
|
||
# OMNIROUTE_BACKUP_SCHEDULE_JOB_INTERVAL_MS=30000
|
||
|
||
# ── Skills sandbox (experimental) ──
|
||
# Used by: src/lib/skills/builtins.ts. All values support comma lists where
|
||
# noted in the source.
|
||
# SKILLS_MAX_FILE_BYTES=1048576
|
||
# SKILLS_MAX_HTTP_RESPONSE_BYTES=256000
|
||
# SKILLS_MAX_SANDBOX_OUTPUT_CHARS=100000
|
||
# SKILLS_SANDBOX_TIMEOUT_MS=10000
|
||
# SKILLS_SANDBOX_NETWORK_ENABLED=0
|
||
# SKILLS_ALLOWED_SANDBOX_IMAGES=
|
||
|
||
# Container runtime used by the skill sandbox. Accepted values:
|
||
# auto — pick the best installed runtime per host OS (default)
|
||
# docker — Docker Engine / Docker Desktop
|
||
# apple — Apple Container (macOS native, micro-VM)
|
||
# wsl — WSL Container (Windows native via wslc.exe)
|
||
# orbstack — OrbStack (high-perf Linux VM + docker shim on macOS)
|
||
# podman — Podman (rootless, daemonless)
|
||
# agent-sandbox — remote Kubernetes sandbox (kubernetes-sigs/agent-sandbox warm
|
||
# pools, e.g. gVisor/Kata). Opt-in only, never auto-detected.
|
||
# SKILLS_SANDBOX_RUNTIME=auto
|
||
|
||
# agent-sandbox runtime (only read when SKILLS_SANDBOX_RUNTIME=agent-sandbox).
|
||
# Each run creates one SandboxClaim from a warm pool, runs the command with
|
||
# `kubectl exec`, then deletes the claim. Isolation and limits come from the
|
||
# operator's SandboxTemplate, so SKILLS_SANDBOX_NETWORK_ENABLED does not apply
|
||
# here: network policy, read-only rootfs and CPU/memory limits are set there.
|
||
# The kubeconfig needs, in the namespace:
|
||
# sandboxclaims create/get/list/watch/delete, pods get, pods/exec create.
|
||
# Image -> warm pool mapping (image=pool, comma-separated):
|
||
# SKILLS_AGENT_SANDBOX_POOLS=python:3.12-alpine=py-pool,node:22-alpine=js-pool
|
||
# Fallback warm pool for images not listed above:
|
||
# SKILLS_AGENT_SANDBOX_POOL=
|
||
# SKILLS_AGENT_SANDBOX_NAMESPACE=default
|
||
# SKILLS_AGENT_SANDBOX_KUBECONFIG=
|
||
# SKILLS_AGENT_SANDBOX_KUBECTL=kubectl
|
||
# SKILLS_AGENT_SANDBOX_CONTAINER=main
|
||
# SKILLS_AGENT_SANDBOX_CLAIM_TIMEOUT_S=60
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 25. TEST & E2E
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Used by scripts/dev/run-next-playwright.mjs, scripts/dev/smoke-electron-packaged.mjs,
|
||
# scripts/dev/run-ecosystem-tests.mjs and scripts/build/uninstall.mjs.
|
||
# Production deployments should leave every value below unset.
|
||
|
||
# E2E bootstrap mode for the Playwright runner. Accepted: auth | fresh | reuse.
|
||
# Default (when unset): auth.
|
||
# OMNIROUTE_E2E_BOOTSTRAP_MODE=auth
|
||
|
||
# Admin password injected into the Playwright test environment.
|
||
# Falls back to INITIAL_PASSWORD when unset.
|
||
# OMNIROUTE_E2E_PASSWORD=
|
||
|
||
# Disable the local healthcheck poll during Playwright runs (default: true).
|
||
# OMNIROUTE_DISABLE_LOCAL_HEALTHCHECK=true
|
||
|
||
# Disable the OAuth token healthcheck loop during tests (default: true).
|
||
# OMNIROUTE_DISABLE_TOKEN_HEALTHCHECK=true
|
||
|
||
# Exclude specific providers from the PROACTIVE token-refresh sweep (comma-separated,
|
||
# case-insensitive). Targeted alternative to OMNIROUTE_DISABLE_TOKEN_HEALTHCHECK: keeps
|
||
# rotating-cascade providers (Codex/OpenAI share one Auth0 family) on the reactive 401
|
||
# path only, while short-TTL providers like Kimi-coding keep being refreshed proactively.
|
||
# OMNIROUTE_HEALTHCHECK_SKIP_PROVIDERS=codex,openai
|
||
|
||
# Read synchronized Codex tokens instead of rotating refresh tokens on this instance.
|
||
# Opt-in; empty/unset keeps normal refresh behaviour. Supported ids: codex, cx
|
||
# (comma-separated, case-insensitive). Other ids fail startup validation.
|
||
# Only manual refresh returns a passive error; implicit refreshes reread the DB.
|
||
# Keep one active rotation owner and synchronize its connection tokens yourself.
|
||
# This does not provide distributed locking or prevent new OAuth logins.
|
||
# OMNIROUTE_TOKEN_REFRESH_PASSIVE_PROVIDERS=codex
|
||
|
||
# Silence healthcheck noise in Playwright stdout (default: true).
|
||
# OMNIROUTE_HIDE_HEALTHCHECK_LOGS=true
|
||
|
||
# Skip the Next.js production build before Playwright starts (CI optimization).
|
||
# OMNIROUTE_PLAYWRIGHT_SKIP_BUILD=0
|
||
|
||
# Skip the OmniRoute uninstall hook (used by CI to keep node_modules intact).
|
||
# OMNIROUTE_SKIP_UNINSTALL_HOOK=0
|
||
|
||
# Ecosystem/protocol test orchestrators wait this long (ms) for the server to
|
||
# become healthy. Default: 180000.
|
||
# ECOSYSTEM_SERVER_WAIT_MS=180000
|
||
|
||
# Docs translation pipeline (used by scripts/i18n/run-translation.mjs).
|
||
# OpenAI-compatible base URL, e.g. https://cloud.omniroute.online/v1
|
||
# OMNIROUTE_TRANSLATION_API_URL=
|
||
# Bearer token for the translation backend (NEVER commit a real key here).
|
||
# OMNIROUTE_TRANSLATION_API_KEY=
|
||
# Model id, e.g. gpt-4o-mini or cx/gpt-5.6-sol.
|
||
# OMNIROUTE_TRANSLATION_MODEL=gpt-4o-mini
|
||
# Optional fallback chain, comma-separated, tried in order when the model above fails for a
|
||
# reason another model could fix (429 quota, 401/402, 5xx, timeout, network). A malformed
|
||
# request (400/413/422) is not retried elsewhere. The wave's per-chunk validator still rejects
|
||
# dropped lines or leaked reasoning whichever model answered.
|
||
# OMNIROUTE_TRANSLATION_FALLBACK_MODELS=cmd/deepseek/deepseek-v4.1-flash
|
||
# Per-request timeout in milliseconds (default 60000).
|
||
# OMNIROUTE_TRANSLATION_TIMEOUT_MS=60000
|
||
# Optional reasoning control, sent as-is to the translation backend when set (e.g. none).
|
||
# OMNIROUTE_TRANSLATION_REASONING_EFFORT=
|
||
# Number of parallel translation requests (default 4).
|
||
# OMNIROUTE_TRANSLATION_CONCURRENCY=4
|
||
# Translation engine: llm (default, the backend above) or google (structure-safe Google
|
||
# Translate engine; needs none of the LLM variables).
|
||
# OMNIROUTE_TRANSLATION_ENGINE=llm
|
||
# With the llm engine, translate a chunk the model could not produce through Google instead of
|
||
# failing the locale (default 1; 0 disables).
|
||
# OMNIROUTE_TRANSLATION_GOOGLE_FALLBACK=1
|
||
# Optional Cloud Translation v2 key; unset uses the keyless web endpoint (rate-limited).
|
||
# OMNIROUTE_TRANSLATION_GOOGLE_API_KEY=
|
||
# Parallel Google requests shared by every locale of a run (default 6).
|
||
# OMNIROUTE_TRANSLATION_GOOGLE_CONCURRENCY=6
|
||
# Per-request timeout for the Google engine in milliseconds (default 30000).
|
||
# OMNIROUTE_TRANSLATION_GOOGLE_TIMEOUT_MS=30000
|
||
|
||
# ── UI kit upstream check (CI / maintainers only) ──
|
||
# Read-only token for the private upstream kit repo (keak-ai/cheaper-inference-ui-kit), used by
|
||
# `npm run check:ui-kit-upstream` and the weekly "UI Kit upstream watch" workflow. Locally the
|
||
# check uses your git credentials (gh auth) and this can stay unset.
|
||
# UI_KIT_READ_TOKEN=
|
||
|
||
# ─── Cloud Sync hardening (v3.8.6) ──────────────────────────────────────────
|
||
# Shared secret used to verify the HMAC-SHA256 of the Cloud sync response body
|
||
# (the Cloud endpoint must sign each response with the same secret and place
|
||
# the hex digest in the X-Cloud-Sig header). When unset, v3.8.6 logs a warning
|
||
# but accepts unsigned responses for back-compat. v3.9 will make this required.
|
||
# OMNIROUTE_CLOUD_SYNC_SECRET=
|
||
#
|
||
# Set to "true" to allow the Cloud Sync endpoint to overwrite local OAuth
|
||
# tokens (accessToken / refreshToken / providerSpecificData). Default OFF —
|
||
# only non-credential metadata is synced. See docs/security/SOCKET_DEV_FINDINGS.md §5.
|
||
# OMNIROUTE_CLOUD_SYNC_SECRETS=false
|
||
#
|
||
# Set to "true" to reject an UNSIGNED Cloud sync response when no local secret
|
||
# is configured (#13679). Default OFF keeps v3.8.x back-compat for peers that
|
||
# have not rotated in a shared secret yet; v3.9 flips the default to enforced.
|
||
# A signature that IS present is always verified, and always rejected when
|
||
# OMNIROUTE_CLOUD_SYNC_SECRET is unset, regardless of this flag.
|
||
# OMNIROUTE_CLOUD_SYNC_ENFORCE_SIGNATURE=false
|
||
|
||
# ─── Zed import legacy compat (v3.8.6) ──────────────────────────────────────
|
||
# Set to "true" to fall back to the v3.8.5 one-step "import everything from
|
||
# the keychain" behaviour. Default OFF — the new 2-step confirmation flow
|
||
# requires `confirmedAccounts` in the request body. See SOCKET_DEV_FINDINGS.md §2.
|
||
# OMNIROUTE_ZED_IMPORT_LEGACY_ONE_STEP=false
|
||
|
||
# ─── Build profile (build-time only) ────────────────────────────────────────
|
||
# Set to "minimal" before `npm run build` to physically remove four optional
|
||
# privileged modules (MITM cert install, Zed keychain import, Cloud Sync,
|
||
# 9router installer) from the standalone bundle. The resulting artifact is
|
||
# intended to be published as `omniroute-secure`. See SECURITY.md.
|
||
# OMNIROUTE_BUILD_PROFILE=full
|
||
|
||
# Override the standalone build output directory consumed by the post-build
|
||
# colocation step. Default: the real Next.js standalone output under .build/.
|
||
# Used by: scripts/build/colocate-standalone.mjs (build tooling, not runtime).
|
||
# OMNIROUTE_STANDALONE_DIR=
|
||
# OMNIROUTE_DIST_DIR=
|
||
|
||
# Skip emitting `.tar.gz` tarballs during optional-pack staging for the Electron
|
||
# standalone tree (pack directories + optional-packs.index.json are still produced).
|
||
# Used by the desktop release workflow to trim artifact upload size.
|
||
# Default (when unset): 1 (tarballs emitted). Set to 0 to disable.
|
||
# OMNIROUTE_OPTIONAL_PACK_TAR=1
|
||
|
||
# Electron smoke harness (used by scripts/dev/smoke-electron-packaged.mjs).
|
||
# ELECTRON_SMOKE_URL=http://127.0.0.1:20128/login
|
||
# ELECTRON_SMOKE_TIMEOUT_MS=45000
|
||
# ELECTRON_SMOKE_SETTLE_MS=2000
|
||
# ELECTRON_SMOKE_APP_EXECUTABLE=
|
||
# ELECTRON_SMOKE_DATA_DIR=
|
||
# ELECTRON_SMOKE_KEEP_DATA=0
|
||
# ELECTRON_SMOKE_STREAM_LOGS=0
|
||
# #7592: second launch against the same DATA_DIR must pick the native driver.
|
||
# ELECTRON_SMOKE_COLD_RESTART=0
|
||
# Coverage capture (scripts/quality/coverage-node-register.mjs, coverage-vitest-provider.mjs):
|
||
# repository root the frozen coverage source scope is resolved against. Set by the quality
|
||
# harness only; leave unset in production deployments.
|
||
# OMNI_COVERAGE_ROOT=
|
||
|
||
# Playground Studio
|
||
# Default model used by the improve-prompt route (optional; falls back to model in request body).
|
||
PLAYGROUND_IMPROVE_PROMPT_DEFAULT_MODEL=
|
||
# Maximum number of parallel compare columns in the Compare tab.
|
||
PLAYGROUND_COMPARE_MAX_COLUMNS=4
|
||
# Memory engine (plan 21)
|
||
# MEMORY_EMBEDDING_CACHE_TTL_MS=300000 # default 5 min
|
||
# MEMORY_EMBEDDING_CACHE_MAX=1000 # default 1000 entries
|
||
# MEMORY_TRANSFORMERS_MODEL=Xenova/all-MiniLM-L6-v2
|
||
# MEMORY_STATIC_MODEL=minishlab/potion-base-8M # HF repo id (download once)
|
||
# MEMORY_STATIC_CACHE_DIR= # default <DATA_DIR>/embeddings
|
||
# MEMORY_VEC_TOP_K=20 # default top-K for vector search
|
||
# MEMORY_RRF_K=60 # RRF k constant (sqlite-vec hybrid recipe)
|
||
# HF_HUB_ENDPOINT=https://huggingface.co # override Hugging Face Hub base URL for static potion downloads
|
||
# Test/diagnostic seam (src/lib/memory/vectorStore.ts) — forces getVectorStore() to
|
||
# return null (simulates a cloud/WASM environment without sqlite-vec), degrading
|
||
# memory retrieval to FTS5 keyword search. Default off; leave unset in production.
|
||
# VECTOR_STORE_DISABLE_VEC=false
|
||
# TV6 typed memory decay (OPT-IN, default off — the sweep DELETES decayed memories)
|
||
# MEMORY_TYPED_DECAY_ENABLED=false # master switch for the destructive sweep (default off)
|
||
# MEMORY_TYPED_DECAY_EPISODIC_DAYS=30 # episodic TTL in days; 0 = episodic immune too
|
||
# MEMORY_TYPED_DECAY_ACCESS_IMMUNITY=3 # access_count >= N → immune; 0 disables access immunity
|
||
# MEMORY_TYPED_DECAY_SWEEP_INTERVAL=0 # periodic sweep interval (seconds); 0 = no periodic sweep
|
||
# ─── Memory Backend Connectors (Generic HTTP) ──────────────────────────────
|
||
# NOTION_API_KEY=
|
||
# NOTION_API_URL=
|
||
# OBSIDIAN_API_KEY=
|
||
# OBSIDIAN_API_URL=
|
||
# AgentBridge + Traffic Inspector (Group A)
|
||
|
||
# AgentBridge
|
||
AGENTBRIDGE_UPSTREAM_CA_CERT=
|
||
|
||
# Inspector
|
||
INSPECTOR_BUFFER_SIZE=1000
|
||
INSPECTOR_HTTP_PROXY_PORT=8080
|
||
INSPECTOR_HTTP_PROXY_AUTOSTART=false
|
||
INSPECTOR_SYSTEM_PROXY_GUARD_MINUTES=30
|
||
INSPECTOR_MAX_BODY_KB=1024
|
||
INSPECTOR_MASK_SECRETS=true
|
||
INSPECTOR_LLM_HOSTS_EXTRA=
|
||
INSPECTOR_INTERNAL_INGEST_TOKEN=
|
||
# Shared secret for identity-preserving internal REST hops (#9260): when an
|
||
# OmniRoute component calls another local OmniRoute route, this token (sent as
|
||
# x-omniroute-internal-service-token) marks the request as internal so the
|
||
# original caller identity is preserved. OPT-IN: unset disables the mechanism.
|
||
# Used by: src/lib/api/internalServiceAuth.ts
|
||
# OMNIROUTE_INTERNAL_SERVICE_TOKEN=
|
||
# File-based variant (secret-file pattern; wins only when the inline var is
|
||
# unset): path to a file whose trimmed content is the token.
|
||
# OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE=
|
||
# Quota Sharing (Group B — planos 16+22)
|
||
# sqlite | redis
|
||
QUOTA_STORE_DRIVER=sqlite
|
||
# QUOTA_STORE_REDIS_URL= # ex.: redis://localhost:6379 (apenas quando driver=redis)
|
||
# QUOTA_SATURATION_THRESHOLD=0.5 # 0..1; >= threshold ativa modo strict (sem empréstimo)
|
||
# QUOTA_SOFT_DEPRIORITIZE_FACTOR=0.7 # 0..1; multiplicador do score quando soft policy ativa
|
||
# STATUS_SOFT_DEPRIORITIZE_FACTOR=0.5 # 0..1; multiplicador do score p/ provider esgotado (credits_exhausted/rate_limited) quando preflight cutoff OFF (#4540)
|
||
# QUOTA_CONSUMPTION_RETENTION_DAYS=14 # GC de buckets quota_consumption.updated_at antigos
|
||
# QUOTA_PREFLIGHT_CUTOFF_ENABLED=false # opt-in (default OFF): hard quota cutoff drops low-quota candidates before auto-routing scoring
|
||
|
||
# ─── Auto-Combo tier filter (#4517) ───────────────────────────────────────
|
||
# When an `auto/<category>:free` (or any `:<tier>`) request matches NO connected
|
||
# candidates, OmniRoute returns an EMPTY pool by default — so `:free` really means
|
||
# "free tier only" and a paid model is never picked just because no free provider is
|
||
# connected. Set this to `true`/`1` to restore the legacy behavior of falling back to
|
||
# the full (unfiltered) pool with a warning. Source: open-sse/services/autoCombo/virtualFactory.ts
|
||
# OMNIROUTE_AUTO_FREE_FALLBACK_TO_FULL_POOL=false
|
||
|
||
# ─── Auto-Combo chaos panel (broadcast variant) ────────────────────────────
|
||
# Tuning for the `auto/*:chaos` variant, which fans a single request out to a
|
||
# panel of provider-diverse models. Panel size is clamped to 1..10 (default 5);
|
||
# min-panel and the panel hard-timeout fall back to the engine defaults when
|
||
# unset. Source: open-sse/services/autoCombo/virtualFactory.ts
|
||
# OMNIROUTE_CHAOS_MAX_PANEL=5
|
||
# OMNIROUTE_CHAOS_MIN_PANEL=
|
||
# OMNIROUTE_CHAOS_PANEL_TIMEOUT_MS=
|
||
|
||
# ─── OpenCode config regeneration (scripts/ad-hoc/regen-opencode-config.ts) ───
|
||
# Base URL of the OmniRoute instance to query for /v1/models when regenerating
|
||
# an opencode.json with accurate limit.context values. Used by:
|
||
# scripts/ad-hoc/regen-opencode-config.ts. Default: http://localhost:20128
|
||
# OMNIROUTE_URL=
|
||
# API key to authenticate against the OmniRoute /v1/models endpoint. Falls back
|
||
# to OPENCODE_API_KEY when unset. Used by: scripts/ad-hoc/regen-opencode-config.ts.
|
||
# OMNIROUTE_KEY=
|
||
# OpenCode-style API key (sk-...) for the regenerated opencode.json. Used by:
|
||
# scripts/ad-hoc/regen-opencode-config.ts. Falls back to OMNIROUTE_KEY.
|
||
# OPENCODE_API_KEY=
|
||
|
||
# ─── Bifrost Go sidecar (PR-4 in #3932) ──────────────────────────────────────
|
||
# Master kill switch for the bifrost sidecar proxy. When set to 0, the
|
||
# /api/v1/relay/chat/completions/bifrost route returns 503 with the
|
||
# X-Bifrost-Killswitch header and the operator is bounced to the TS path.
|
||
# Use this to disable the sidecar without redeploying (e.g. during a
|
||
# tier-1 router incident or a key rotation). Default: 1 (sidecar active).
|
||
# BIFROST_ENABLED=1
|
||
# When BIFROST_BASE_URL is set, /api/v1/relay/chat/completions/bifrost routes
|
||
# traffic to the Go gateway instead of the TS relay handler, removing TS from
|
||
# the hot path. Auth/rate-limit/injection-guard stay in the route (security not
|
||
# duplicated). Falls back to TS path via X-Bifrost-Fallback header on
|
||
# timeout/failure. See bin/omniroute for the local-redis companion.
|
||
# BIFROST_BASE_URL=
|
||
# Port the supervised Bifrost embedded service binds to (127.0.0.1:<port>), read by
|
||
# src/lib/services/bootstrap.ts when OmniRoute manages the Bifrost sidecar lifecycle.
|
||
# Default: 8080.
|
||
# BIFROST_PORT=8080
|
||
# Port the supervised sing-box embedded service binds to (127.0.0.1:<port>).
|
||
# Default: 20140.
|
||
# SINGBOX_PORT=20140
|
||
# API key for the Bifrost gateway (sent as Authorization: Bearer ...). If
|
||
# unset, the route expects the request to carry a valid OmniRoute API key;
|
||
# this key is for gateway-side auth only.
|
||
# BIFROST_API_KEY=
|
||
# When true, the Bifrost sidecar route streams responses back via SSE through
|
||
# the gateway rather than the TS streaming executor. Default: true (when
|
||
# BIFROST_BASE_URL is set).
|
||
# BIFROST_STREAMING_ENABLED=
|
||
# Per-request timeout when proxying to the Bifrost gateway. Default: 30000 (30s).
|
||
# BIFROST_TIMEOUT_MS=
|
||
# Alias for BIFROST_API_KEY (used by scripts that read the env via
|
||
# OMNIROUTE_*). BIFROST_API_KEY takes precedence when both are set.
|
||
# OMNIROUTE_BIFROST_KEY=
|
||
# Relay backend selection for the OpenAI-compatible relay endpoint:
|
||
# ts | bifrost | auto. "ts" (default when Bifrost is not configured) uses the
|
||
# TypeScript relay; "auto" selects Bifrost when BIFROST_BASE_URL is set (and
|
||
# BIFROST_ENABLED != 0) and falls back to TS if the sidecar is unreachable;
|
||
# "bifrost" forces Bifrost (strict — no TS fallback). Auth, rate limits,
|
||
# injection guard and model allowlists always run in the Next route first.
|
||
# RELAY_ROUTING_BACKEND is an accepted alias. Responses carry X-Routing-Backend
|
||
# and X-Routing-Fallback.
|
||
# OMNIROUTE_RELAY_BACKEND=
|
||
# RELAY_ROUTING_BACKEND=
|
||
# Cooldown (ms) after a Bifrost sidecar hop fails in "auto" mode before the relay
|
||
# re-attempts the sidecar; it goes straight to the TS path while the cooldown lasts.
|
||
# 0 disables. Default 5000. Only applies when OMNIROUTE_RELAY_BACKEND=auto.
|
||
# OMNIROUTE_BIFROST_FAILURE_COOLDOWN_MS=
|
||
# Opt-in native HTTPS/TLS for `omniroute serve` (equivalent to --tls-cert /
|
||
# --tls-key). Provide BOTH a PEM certificate and its private key and the
|
||
# standalone server terminates TLS on the same listener (wss:// works
|
||
# unchanged). With neither set the server stays plain HTTP; providing only one
|
||
# (or an unreadable path) logs a warning and stays HTTP (never half-enables).
|
||
# OMNIROUTE_TLS_CERT=
|
||
# OMNIROUTE_TLS_KEY=
|
||
|
||
# ─── 1-click local service launchers (PR-3 in #3932) ────────────────────────
|
||
# Master switch for /api/local/* routes. When unset or "0", all /api/local/*
|
||
# routes return 503 in production. Default: 0. Must be "1" in non-loopback
|
||
# deploys to enable the Redis launcher and similar 1-click local service
|
||
# starters. Belt-and-suspenders with the isLocalOnlyPath() route-guard
|
||
# classification (LOCAL_ONLY_API_PREFIXES in src/server/authz/routeGuard.ts).
|
||
# OMNIROUTE_LOCAL_ENDPOINTS_ENABLED=
|
||
# Bearer token for /api/local/* callers that aren't on loopback (e.g. the
|
||
# desktop app). When set, requests from non-loopback IPs must carry
|
||
# Authorization: Bearer <token>. Required when
|
||
# OMNIROUTE_LOCAL_ENDPOINTS_ENABLED=1 in non-loopback deployments. Default:
|
||
# unset (loopback-only).
|
||
# OMNIROUTE_LOCAL_ENDPOINTS_TOKEN=
|
||
# Container name for the 1-click Redis launcher (`omniroute redis up`).
|
||
# Default: omniroute-redis. Used by bin/cli/commands/redis.mjs and the
|
||
# RedisLauncherPanel.
|
||
# OMNIROUTE_REDIS_CONTAINER_NAME=
|
||
# Host port for the 1-click Redis launcher. Default: 6379. Bump if the host
|
||
# already binds 6379. The container's internal port stays 6379.
|
||
# OMNIROUTE_REDIS_HOST_PORT=
|
||
# Host interface the 1-click Redis launcher publishes on. Default: 127.0.0.1
|
||
# (loopback only). The launcher starts Redis WITHOUT a password, so binding
|
||
# 0.0.0.0 hands every host on your LAN an unauthenticated Redis — only widen
|
||
# this if you also set a password on the instance yourself.
|
||
# OMNIROUTE_REDIS_BIND_HOST=
|
||
# Redis image used by the 1-click Redis launcher. Default: redis:7-alpine.
|
||
# Override to redis:8-alpine or a private registry mirror as needed.
|
||
# OMNIROUTE_REDIS_IMAGE=
|
||
|
||
# ── Cluster Profile: Qdrant Vector Memory (opt-in via `docker compose --profile memory up`) ──
|
||
# Qdrant is an OPTIONAL sidecar for deployments that need cosine-distance vector
|
||
# search at >1M embeddings. The default vector store is sqlite-vec
|
||
# (src/lib/memory/vectorStore.ts:108); flip this profile on only if you hit the
|
||
# sqlite-vec ceiling or want persistent cross-replica vector state. See
|
||
# docs/architecture/cluster-decisions.md § "Qdrant (memory profile)".
|
||
# QDRANT_HOST=qdrant
|
||
# QDRANT_PORT=6333
|
||
# QDRANT_GRPC_PORT=6334
|
||
# QDRANT_API_KEY=
|
||
# QDRANT_COLLECTION=omniroute-memory
|
||
# QDRANT_EMBEDDING_MODEL=text-embedding-3-small
|
||
# QDRANT_VECTOR_SIZE=1536
|
||
# QDRANT_HNSW_EF_CONSTRUCT=128
|
||
|
||
# ── Cluster Profile: Bifrost Tier-1 Router (opt-in via `docker compose --profile bifrost up`) ──
|
||
# Bifrost is an OPTIONAL Go-based Tier-1 router that handles the upstream-provider
|
||
# multiplexing layer. Default: OmniRoute's open-sse/executors/bifrost.ts in-process
|
||
# executor handles routing directly. Flip this profile on only if you want the
|
||
# gateway as a separate sidecar (helps in 3+ replica deployments where you want
|
||
# provider rotation centralised). See docs/architecture/cluster-decisions.md §
|
||
# "Bifrost (bifrost profile)".
|
||
# Set OMNIROUTE_RELAY_BACKEND=auto to use this sidecar when healthy, or
|
||
# OMNIROUTE_RELAY_BACKEND=bifrost to require it without TS fallback.
|
||
# BIFROST_BASE_URL=http://bifrost:8080
|
||
# BIFROST_API_KEY=
|
||
# BIFROST_STREAMING_ENABLED=true
|
||
# BIFROST_TIMEOUT_MS=30000
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# Account rotation config (operator-managed; consumed by open-sse/services/rotationConfig.ts)
|
||
# Lets a supervising front-end mirror its rotation rules onto the backend's account-fallback
|
||
# engine. All optional; defaults preserve the historical behavior.
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# OMNIROUTE_ROTATION_ENABLED=true
|
||
# OMNIROUTE_ROTATION_RATE_LIMIT_RESET_SECONDS=0
|
||
# OMNIROUTE_ROTATION_DISABLE_TAG_WITHOUT_RESET=true
|
||
# OMNIROUTE_ROTATE_ON_429=true
|
||
# OMNIROUTE_ROTATE_429_THRESHOLD=1
|
||
# OMNIROUTE_ROTATE_429_WINDOW_SECONDS=120
|
||
# OMNIROUTE_ROTATE_ON_500=true
|
||
# OMNIROUTE_ROTATE_500_THRESHOLD=1
|
||
# OMNIROUTE_ROTATE_500_WINDOW_SECONDS=120
|
||
# OMNIROUTE_ROTATE_ON_502=true
|
||
# OMNIROUTE_ROTATE_502_THRESHOLD=1
|
||
# OMNIROUTE_ROTATE_502_WINDOW_SECONDS=120
|
||
# OMNIROUTE_ROTATE_ON_400=false
|
||
# OMNIROUTE_ROTATE_400_THRESHOLD=1
|
||
# OMNIROUTE_ROTATE_400_WINDOW_SECONDS=120
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# PromptQL playground provider (Unofficial/Experimental — src/shared/constants/providers/web-cookie.ts)
|
||
# Reverse-engineered GraphQL session bridge for prompt.ql.app. All optional —
|
||
# defaults point at the public playground endpoints; override only for a
|
||
# self-hosted/alternate PromptQL deployment.
|
||
# Used by: open-sse/executors/promptql.ts, open-sse/services/usage/promptql.ts
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# PROMPTQL_GRAPHQL_ENDPOINT=https://data.prompt.ql.app/promptql/playground-v2-hge/v1/graphql
|
||
# PROMPTQL_CREDITS_ENDPOINT=https://data.pro.ql.app/v1/graphql
|
||
# PROMPTQL_TOKEN_REFRESH_URL=https://auth.pro.ql.app/ddn/project/token
|
||
# PROMPTQL_POLL_TIMEOUT_MS=180000
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# Kilo Code usage quotas (src/shared/constants/providers/kilocode.ts)
|
||
# Personal USD balance and Kilo Pass usage lookup. Optional — the default
|
||
# points at the public Kilo API; override only for a relay/test fixture.
|
||
# Authentication uses the connection's existing OAuth access token.
|
||
# Used by: open-sse/services/usage/kilocode.ts
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# KILO_API_URL=https://api.kilo.ai
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# MegaBrain plan usage limits (open-sse/config/providers/registry/megabrain)
|
||
# The plan's 5-hour session and weekly limits for Provider Limits. Optional —
|
||
# the default points at the public MegaBrain API; override only for a
|
||
# relay/test fixture. Authentication uses the connection's OAuth token or
|
||
# its mb-v1 API key.
|
||
# Used by: open-sse/services/usage/megabrain.ts
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# MEGABRAIN_API_URL=https://api.getmegabrain.com
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# HyperAgent web provider (Unofficial/Experimental — src/shared/constants/providers/web-cookie.ts)
|
||
# Reverse-engineered session bridge for hyperagent.com. Optional — defaults
|
||
# point at the public billing/usage endpoint; override only for a
|
||
# self-hosted/alternate HyperAgent deployment.
|
||
# Used by: open-sse/services/usage/hyperagent.ts
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# HYPERAGENT_USAGE_URL=https://hyperagent.com/api/settings/billing/usage
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# ChatGPT Web clean-room turn budgets (milliseconds)
|
||
# Used by: open-sse/utils/chatgptWebExecutorAdapter.ts
|
||
# Tool-emulated turns share the 180000ms ceiling with ordinary text turns, because
|
||
# a live Free-account text turn already takes 49-86s; lower it to return control to
|
||
# the client sooner, at the risk of cutting off a slow tool envelope. Values below
|
||
# 1000ms are ignored.
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# CHATGPT_WEB_TOOL_TURN_TIMEOUT_MS=180000
|
||
# CHATGPT_WEB_TURN_TIMEOUT_MS=180000
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# ChatGPT Web clean-room browser (open-sse/utils/chatgptWebExecutorAdapter.ts)
|
||
# Headless is the default: servers have no display, and a headed Chromium either
|
||
# fails to start or puts a window on the operator's desktop. Set to 0 only for
|
||
# accounts whose first-party challenge rejects headless mode.
|
||
# CHATGPT_WEB_HEADLESS=1
|
||
# Ceiling for launching the browser and warming up chatgpt.com. Keeps a dead
|
||
# browser or session from consuming the 600s request-queue execution deadline.
|
||
# CHATGPT_WEB_BROWSER_ACQUIRE_TIMEOUT_MS=45000
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# ChatGPT Web (Codex) headless browser and outbound tool tunnel
|
||
# Used by: open-sse/executors/chatgpt-web-codex.ts
|
||
# Connection values entered in the dashboard override these global defaults.
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# CHATGPT_WEB_CODEX_CHROME_PATH=/usr/bin/chromium
|
||
# CHROME_PATH=/usr/bin/chromium
|
||
# CHATGPT_WEB_CODEX_CDP_URL=http://chatgpt-web-codex-browser:9223
|
||
# CHATGPT_WEB_CODEX_USE_CDP_PROFILE: set to 1 (with a CDP endpoint configured) to reuse the
|
||
# externally managed, signed-in browser profile's existing ChatGPT page instead of creating an
|
||
# isolated context per turn; also caps concurrent ChatGPT tabs at 1. Off by default.
|
||
# See docs/guides/CHATGPT-WEB-PERSISTENT-CDP.md.
|
||
# Used by: open-sse/vendor/codex-chatgpt-web/persistent-cdp-context.ts
|
||
# Default: unset (off)
|
||
# CHATGPT_WEB_CODEX_USE_CDP_PROFILE=1
|
||
# CDP_PROXY_TOKEN: shared secret for docker/chatgpt-web-codex-browser/cdp-proxy.mjs
|
||
# (#13679, #14486). The proxy FAILS CLOSED — every request must present it as an
|
||
# `X-Omni-Cdp-Token` header. Leave empty in docker compose: the browser container
|
||
# then auto-generates a secret into a shared volume (CDP_PROXY_TOKEN_FILE) that the
|
||
# app reads. Set it explicitly only to pin your own value (`openssl rand -hex 32`).
|
||
# CDP_PROXY_TOKEN=
|
||
# CHATGPT_WEB_CODEX_TUNNEL_ID=tunnel_0123456789abcdef0123456789abcdef
|
||
# CHATGPT_WEB_CODEX_RUNTIME_KEY=
|
||
# CHATGPT_WEB_CODEX_CONNECTOR_NAME=OmniRoute Codex v2
|
||
# CODEX_CHATGPT_WEB_HOME=/var/lib/omniroute/chatgpt-web-codex
|
||
# CODEX_CHATGPT_WEB_BROWSER_DIAGNOSTICS=0
|
||
# CODEX_CHATGPT_WEB_LAUNCHER=/absolute/path/to/codex-chatgpt-web
|
||
# CODEX_CHATGPT_WEB_BUN=/absolute/path/to/bun
|
||
# CODEX_WEB_GPT_BUN=/absolute/path/to/bun
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# Browser-login VNC sessions (optional — src/lib/vncSession/manifest.ts)
|
||
# Containerized Chromium+VNC used for interactive browser-login credential
|
||
# capture via /api/vnc-session. All optional — defaults target the bundled
|
||
# `omniroute-vnc-chromium:local` image; override only for a custom image, ports,
|
||
# or lifecycle tuning.
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# OMNIROUTE_VNC_IMAGE=omniroute-vnc-chromium:local
|
||
# OMNIROUTE_DOCKER_BIN=docker
|
||
# OMNIROUTE_VNC_CONTAINER_VNC_PORT=3000
|
||
# OMNIROUTE_VNC_CONTAINER_CDP_PORT=9223
|
||
# OMNIROUTE_VNC_CONTAINER_PROFILE_DIR=/config
|
||
# OMNIROUTE_VNC_PROFILE_DIR=
|
||
# OMNIROUTE_VNC_IDLE_MS=600000
|
||
# OMNIROUTE_VNC_MAX_MS=1800000
|
||
# OMNIROUTE_VNC_MAX_SESSIONS=4
|
||
# OMNIROUTE_VNC_READY_MS=45000
|
||
# OMNIROUTE_VNC_HARVEST_MS=20000
|
||
# OMNIROUTE_VNC_CHROMIUM_ARGS=--remote-debugging-port=9222 --no-first-run --no-default-browser-check
|
||
# OMNIROUTE_VNC_NETWORK=omniroute-vnc-browser-login
|
||
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# Data-dir alias (optional — open-sse/services/notionThreadSessions.ts)
|
||
# Legacy fallback for DATA_DIR, checked only after DATA_DIR and
|
||
# OMNIROUTE_DATA_DIR are both unset. Locates the Notion web-thread session cache.
|
||
# ─────────────────────────────────────────────────────────────────────────────
|
||
# VIBEPROXY_DATA_DIR=
|
||
|
||
# ── Internal service auth (management-plane service-to-service calls) ─────────
|
||
# Inline token for internal service authentication; prefer the _FILE variant in
|
||
# containerized deployments so the secret never lands in the environment table.
|
||
# OMNIROUTE_INTERNAL_SERVICE_TOKEN=
|
||
# Path to a file containing the internal service token (overrides the inline var).
|
||
# OMNIROUTE_INTERNAL_SERVICE_TOKEN_FILE=
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 26. RADAR FEED (SELF-HOSTING)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# Optional add-on (feature flag RADAR_ENABLED, default off — see feature flag
|
||
# settings, not an env var) that overlays a signed, freshly-curated free-model
|
||
# catalog on top of the release baseline. The first four variables below are
|
||
# optional overrides for a self-hosted/forked feed or supporter-key flow. The
|
||
# fifth is an optional, default-free link to the owner's private operations panel. Used by:
|
||
# src/lib/radar/sync.ts, src/lib/radar/pinnedKeys.ts, src/lib/radar/links.ts.
|
||
|
||
# Base URL of the Radar feed service. Overrides the built-in default so forks
|
||
# and self-hosters can point at their own signed feed.
|
||
# RADAR_FEED_URL=https://radar.omniroute.online
|
||
|
||
# Ed25519 public key (base64-DER SPKI or PEM) used to verify the feed
|
||
# signature, replacing the pinned default key. Required when self-hosting a
|
||
# feed signed with a different key pair.
|
||
# RADAR_FEED_PUBKEY=
|
||
|
||
# URL the dashboard's "I'm a contributor" button opens (GitHub OAuth
|
||
# supporter-key claim flow). No pricing/value lives in this repo — only the
|
||
# link.
|
||
# RADAR_CONTRIBUTOR_CLAIM_URL=https://radar.omniroute.online/auth/github
|
||
|
||
# URL the dashboard's "Support the project" button opens (payment/plans
|
||
# page). No pricing/value lives in this repo — only the link.
|
||
# RADAR_SUPPORTER_PLANS_URL=https://radar.omniroute.online/planos
|
||
|
||
# Owner-only link to the private Radar operations panel. There is deliberately
|
||
# no default: when unset or invalid, no "Radar Admin" navigation item exists.
|
||
# Use HTTPS for a tunnel/tailnet URL, or HTTP only for an SSH loopback forward.
|
||
# RADAR_ADMIN_URL=http://127.0.0.1:9351
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# 27. RELEASE v3.8.50 ADDITIONS
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
|
||
# Heavy chat admission queue wait before returning retryable 503. Set 0 for the
|
||
# legacy immediate rejection. Used by: src/shared/middleware/chatBodyAdmission.ts.
|
||
# Documented once above, under the chat admission block — this entry said 5000
|
||
# while the code said 2000, so it is a pointer now rather than a second answer.
|
||
# Default: RATE_LIMIT_MAX_WAIT_MS (see that var elsewhere in this file for its
|
||
# current value)
|
||
|
||
# Timeout for /api/jobs/:id/run-now while it waits for an in-flight run.
|
||
# Used by: src/app/api/jobs/[id]/run-now/route.ts. Default: 30000 (30 seconds)
|
||
# OMNIROUTE_RUNNOW_TIMEOUT_MS=30000
|
||
|
||
# Adobe Firefly browser renewal and durable session cache (enabled by default).
|
||
# Used by: open-sse/services/adobeFireflySession.ts.
|
||
# ADOBE_FIREFLY_BROWSER_REFRESH=1
|
||
# ADOBE_FIREFLY_SESSION_DISK=1
|
||
# Minimum spacing between submissions and the extra pause after every third success.
|
||
# ADOBE_FIREFLY_MIN_SUBMIT_GAP_MS=12000
|
||
# ADOBE_FIREFLY_BATCH_EXTRA_GAP_MS=15000
|
||
# Browser used by Adobe Firefly renewal. True headless is debug-only: Adobe
|
||
# colligo normally rejects risk tokens minted without a headed browser.
|
||
# Used by: open-sse/services/adobeFireflyBrowserLogin.ts
|
||
# ADOBE_FIREFLY_CHROME_HEADLESS=0
|
||
# The CDP-attached Chrome runtime (adobeFireflyChromeRuntime.ts) was removed in
|
||
# #9255 along with its knobs — ADOBE_FIREFLY_CHROME_CDP_PORT, _VISIBLE, _HEADED,
|
||
# _PING, _FORCE_RESTART, ADOBE_FIREFLY_LOGIN_WAIT_MS and _FORTER_WAIT_MS are read
|
||
# nowhere and have no effect.
|
||
|
||
# Telegram Mini App bridge. The update endpoint remains disabled while the bot
|
||
# token is unset. Used by: src/lib/telegram/* and src/app/api/telegram/update/route.ts.
|
||
# TELEGRAM_BOT_TOKEN=
|
||
# Shared secret registered with setWebhook and echoed back by Telegram as the
|
||
# X-Telegram-Bot-Api-Secret-Token header. REQUIRED for the webhook path: without
|
||
# it the webhook is rejected with 503, because an unauthenticated update lets any
|
||
# caller mint API keys and spend upstream quota. The Mini App path does not use it.
|
||
# TELEGRAM_WEBHOOK_SECRET=
|
||
# TELEGRAM_DEFAULT_MODEL=auto/chat
|
||
# TELEGRAM_BOT_API_BASE=https://api.telegram.org
|
||
# TELEGRAM_WEBHOOK_TIMEOUT_MS=60000
|
||
# Who may use the bot. A bot is reachable by anyone who finds its @username, and a
|
||
# valid Telegram signature proves origin, not authorization: with the allowlist off
|
||
# (the default) every Telegram user is served and gets a minted API key that spends
|
||
# upstream quota. Set to true to serve only the users in TELEGRAM_ALLOWED_USER_IDS
|
||
# (others: Mini App 403, webhook message dropped). Recommended for any public bot.
|
||
# TELEGRAM_USER_ALLOWLIST_ENABLED=false
|
||
# Comma-separated numeric Telegram user ids served when the allowlist is enabled.
|
||
# Entries that are not plain positive integers (e.g. @usernames, 0-prefixed ids)
|
||
# are ignored and reported once at startup. Empty with the allowlist enabled =
|
||
# nobody is served.
|
||
# TELEGRAM_ALLOWED_USER_IDS=
|
||
|
||
# ── OmniConductor bridge (Conductor PRD RF1) ──────────────────────────────────
|
||
# Mirrors the OmniConductor hub's tasks into the local A2A TaskManager via SSE.
|
||
# Opt-in: the bridge only starts when CONDUCTOR_HUB_URL is set.
|
||
# Token: emit a `spokesperson`-kind credential on the hub (POST /v1/peers, admin) —
|
||
# server-side only, never exposed to the browser.
|
||
# Used by: src/lib/conductor/boot.ts, src/lib/conductor/bridge.ts
|
||
# CONDUCTOR_HUB_URL=http://127.0.0.1:7910
|
||
# CONDUCTOR_HUB_TOKEN=
|
||
# Inbound A2A→hub delegation credential (falls back to CONDUCTOR_HUB_TOKEN when unset).
|
||
# Used by: src/lib/conductor/hubProxy.ts
|
||
# CONDUCTOR_ORCHESTRATOR_TOKEN=
|
||
# Spokesperson (Faro) base URL for the dashboard chat proxy (/api/conductor/ask).
|
||
# Used by: src/lib/conductor/faroProxy.ts
|
||
# CONDUCTOR_SPOKESPERSON_URL=http://127.0.0.1:7920
|
||
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# QUOTA-AWARE PROVIDER SCHEDULING (opt-in, Phase 2)
|
||
# ═══════════════════════════════════════════════════════════════════════════════
|
||
# When enabled, routing skips connections whose configured per-window token
|
||
# budget (rateLimitOverrides.tpm) cannot afford the estimated request cost —
|
||
# before dispatching — instead of waiting for a 429. Fail-open: connections
|
||
# without a configured budget are always considered affordable. Requires the
|
||
# provider_quota_state table (migration 148).
|
||
# OMNIROUTE_QUOTA_AWARE_ROUTING=0
|
||
|
||
# Feedback calibration of the context-guard token estimator (#14931): learns the
|
||
# provider's real prompt_tokens / estimate ratio per (provider, model, tools) and
|
||
# scales later estimates (clamped 0.15–2.0, in-memory only). On by default; set
|
||
# off, 0 or false to disable. Used by: open-sse/services/estimatorCalibration.ts.
|
||
# OMNIROUTE_ESTIMATOR_CALIBRATION=on
|
||
|
||
# Grok subscription images: registers the xai-oauth (xao) and grok-cli image routes.
|
||
# Dashboard feature flag of the same name; a DB override wins over this value.
|
||
# Default off. Used by: open-sse/config/imageRegistry.ts.
|
||
# GROK_SUBSCRIPTION_IMAGES_ENABLED=false
|
||
|
||
# ─── LOCAL CORPUS (opt-in document index) ───
|
||
# Size of the in-memory LRU index cache for the local document corpus used by
|
||
# corpus-aware retrieval. Higher values keep more index entries hot.
|
||
# Used by: src/lib/localCorpus/configured.ts
|
||
# OMNIROUTE_CORPUS_CACHE_SIZE=5
|
||
|
||
# Service-worker cache-busting id for the PWA shell (#11779). NEXT_PUBLIC_SW_BUILD_ID is
|
||
# derived at build time from OMNIROUTE_SW_BUILD_ID, then SOURCE_VERSION (set by some PaaS
|
||
# builders), then the git SHA — override only when the build cannot see git. Used by:
|
||
# next.config.mjs, scripts/build/assembleStandalone.mjs, src/shared/components/PwaRegister.tsx.
|
||
#OMNIROUTE_SW_BUILD_ID=2026-08-28T12-00-00
|
||
#SOURCE_VERSION=abcdef0123456789
|
||
#NEXT_PUBLIC_SW_BUILD_ID=abcdef0123456789
|
||
|
||
# Optional runtime controls introduced after the previous environment snapshot.
|
||
# Enable the xAI subscription image routes (off by default).
|
||
# Used by: open-sse/config/imageRegistry.ts.
|
||
# GROK_SUBSCRIPTION_IMAGES_ENABLED=0
|
||
# Per-key API-key cooldown when a 429 response has no Retry-After hint (ms).
|
||
# Used by: open-sse/services/apiKeyRotator.ts. Default: 60000.
|
||
# OMNIROUTE_API_KEY_COOLDOWN_MS=60000
|
||
# Disable in-memory estimator calibration with off, 0, or false. Enabled by default.
|
||
# Used by: open-sse/services/estimatorCalibration.ts.
|
||
# OMNIROUTE_ESTIMATOR_CALIBRATION=on
|
||
# Render free-tier keep-alive: the standalone launcher pings its own public URL so the service is
|
||
# not spun down. Inert unless SELF_PING_URL or Render's RENDER_EXTERNAL_URL is set. See ENVIRONMENT.md.
|
||
# Used by: scripts/build/runtime-env.mjs.
|
||
# RENDER_EXTERNAL_URL is set by Render itself; do not set it elsewhere.
|
||
# RENDER_EXTERNAL_URL=
|
||
# SELF_PING_ENABLED=true
|
||
# SELF_PING_URL=
|
||
# SELF_PING_PATH=/api/monitoring/health
|
||
# SELF_PING_INTERVAL_SECONDS=180
|
||
# Internal standalone-server signal override. Normally managed by the launcher.
|
||
# Used by: scripts/dev/standalone-server-ws.mjs.
|
||
# NEXT_MANUAL_SIG_HANDLE=1
|
||
# Path of the private CI UI Kit clone the vendored-snapshot gate diffs packages/ui-kit against.
|
||
# Defaults to _references/cheaper-inference-ui-kit (main checkout); the gate skips with a
|
||
# warning when the clone is absent (public CI / forks). KEA-7886.
|
||
# Used by: scripts/check/check-ui-kit-snapshot.mjs.
|
||
# UI_KIT_CLONE=_references/cheaper-inference-ui-kit
|
||
|
||
# Opt-in model-sync phase timings; disabled unless exactly 1.
|
||
OMNIROUTE_MODEL_SYNC_TIMINGS=0
|
||
|
||
# Opt-in sanitized per-physical-send Antigravity phase timings (no request bodies).
|
||
OMNIROUTE_ANTIGRAVITY_TIMING_TELEMETRY=false
|
||
|
||
# Optional local OpenCode media-analysis tool settings (scripts/cli/omniroute-media-mcp.mjs).
|
||
# These configure the local tool process, not the hosted gateway.
|
||
# OMNIROUTE_MEDIA_CONFIG=
|
||
# OMNIROUTE_MEDIA_PROVIDER=omniroute
|
||
# OMNIROUTE_MEDIA_MODEL=auto
|
||
# OMNIROUTE_MEDIA_API_KEY=
|
||
|
||
# ── Vision image normalization (opt-in) ──
|
||
# Normalizes every inline (base64) image in chat request bodies before
|
||
# dispatch: RGB conversion (alpha flattened onto white), long edge <= 4096px,
|
||
# total pixels <= ~4MP, re-encoded as baseline JPEG/PNG — the comfort zone of
|
||
# Qwen2-VL-style vision pipelines, which reject oversized/exotic images with
|
||
# 400 parse errors or zero-output hangs. Remote http(s) URLs are not
|
||
# downloaded; a missing sharp binary or undecodable image passes through
|
||
# untouched (fail-open). Unset (default) = off, zero change.
|
||
# Used by: open-sse/utils/visionImageNormalization.ts + src/sse/handlers/chat.ts
|
||
# OMNIROUTE_IMAGE_NORMALIZATION=1
|
||
|
||
# Session stickiness/TTL in minutes for in-memory sessions (default 15). Long
|
||
# agent sessions benefit from a higher TTL; unset/blank/invalid keeps 15.
|
||
# Used by: open-sse/services/sessionManager.ts.
|
||
# OMNIROUTE_SESSION_TTL_MIN=15
|