.env.example

# ┌─────────────────────────────────────────────────────────────────────────────┐
# │                          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: bootstrap only — sets the initial dashboard password on first boot.
# After first login you can change it from Dashboard → Settings → Security.
# Default: CHANGEME (insecure, for local dev only)
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

# 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

# Automatic SQLite backup on startup.
# Used by: src/lib/db/backup.ts — creates a timestamped backup before migrations.
# Default: false (backups enabled)  |  Set true to skip backup on every restart.
DISABLE_SQLITE_AUTO_BACKUP=false

# ── 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

# ═══════════════════════════════════════════════════════════════════════════════
# 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

# 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

# Port for the real-time WebSocket live monitoring server.
# Used by: src/server/ws/liveServer.ts, src/app/api/v1/ws/route.ts
# Default: 20129
# LIVE_WS_PORT=20129

# 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).
# LIVE_WS_ALLOWED_ORIGINS=https://omni.local,https://dashboard.example.com

# Disable the standalone live WebSocket helper used by scripts/start-ws-server.mjs.
# Used by: scripts/start-ws-server.mjs (CI/embedded harness toggle).
# OMNIROUTE_DISABLE_LIVE_WS=0

# 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`. 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 still uses webpack (build pipeline is
# unaffected by this dev-only flag).
OMNIROUTE_USE_TURBOPACK=1

# 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: 300000 (5 minutes). Minimum: 10000 (10 seconds).
# Used by: open-sse/config/constants.ts, src/lib/credentialHealth/scheduler.ts
# CREDENTIAL_HEALTH_CHECK_INTERVAL=300000

# 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

# 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

# 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).
#HOST=0.0.0.0
#HOSTNAME=127.0.0.1

# 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" when running under rootless Podman so the entrypoint
# gives the correct fix instructions (podman unshare chown vs sudo chown).
CONTAINER_HOST=docker

# ═══════════════════════════════════════════════════════════════════════════════
# 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.
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/malformed) preserves the legacy
# 1000/day, 5000/week, 20000/month windows so existing deployments do not
# silently lose rate limiting on upgrade.
# 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).
# Used by: src/shared/middleware/bodySizeGuard.ts — prevents oversized uploads.
# Default: 10485760 (10 MB)
# MAX_BODY_SIZE_BYTES=10485760

# CORS configuration — controls which origins can call the API.
# Used by: Next.js middleware — sets Access-Control-Allow-Origin header.
# Default: * (all origins)  |  Restrict for production security.
# CORS_ORIGIN=https://your-domain.com

# Allow provider URLs pointing to private/local networks (localhost, 192.168.x.x, etc.).
# REQUIRED for self-hosted providers: LM Studio, Ollama, vLLM, Llamafile, Triton, etc.
# Used by: src/shared/network/outboundUrlGuard.ts — disables SSRF guard for provider calls.
# Default: false (blocked)  |  Set true to enable local providers.
# OMNIROUTE_ALLOW_PRIVATE_PROVIDER_URLS=true

# Allow adding/validating providers on local/private addresses (127.0.0.1, localhost, LAN).
# Used by: src/shared/network/outboundUrlGuard.ts — scopes to the provider validation path and
# still blocks cloud-metadata (169.254.169.254, metadata.google.internal). Default: true
# (OmniRoute is local-first). Set false to enforce strict public-only blocking.
# OMNIROUTE_ALLOW_LOCAL_PROVIDER_URLS=false

# Legacy alias toggling the SSRF guard. Used by: src/shared/network/outboundUrlGuard.ts
# When unset, OmniRoute uses the per-feature defaults. Set to "false"/"0" to disable.
# OUTBOUND_SSRF_GUARD_ENABLED=true

# ═══════════════════════════════════════════════════════════════════════════════
# 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
# INPUT_SANITIZER_ENABLED=true
# INPUT_SANITIZER_MODE=warn    # warn = log only | block = reject request | redact = strip patterns

# Legacy alias for INPUT_SANITIZER_MODE (same effect).
# INJECTION_GUARD_MODE=warn

# PII detection in incoming requests (emails, phone numbers, SSNs, etc.).
# Used by: src/middleware/promptInjectionGuard.ts — extends injection guard.
# PII_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

# ═══════════════════════════════════════════════════════════════════════════════
# 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.
# 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 — CRITICAL for reverse proxy / OAuth callback setups.
# Used by: OAuth redirect_uri computation, Dashboard UI links, cloud/model sync.
# Set to your public URL when 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 must point to a
# canonical URL.
#
# Default: http://localhost:20128
NEXT_PUBLIC_BASE_URL=http://localhost:20128

# Browser-facing OmniRoute origin for generated assets in API responses.
# Used by: chatgpt-web image generation cache URLs (/v1/chatgpt-web/image/<id>).
# Set this when OpenWebUI or another relay reaches OmniRoute by an internal URL
# but the user's browser must fetch images from a LAN, tunnel, or public origin.
# Do not include /v1; if included accidentally it will be normalized away.
# OMNIROUTE_PUBLIC_BASE_URL=http://192.168.0.15:20128

# Max wait time for an async chatgpt-web image to land via the celsius
# WebSocket, in milliseconds. Default 180000 (3 minutes). Increase during
# upstream queue-deep windows ("Lots of people are creating images right now").
# OMNIROUTE_CGPT_WEB_IMAGE_TIMEOUT_MS=180000

# Total in-memory byte budget for the chatgpt-web image cache (used to serve
# /v1/chatgpt-web/image/<id>), in megabytes. Default 256. Lower this if you
# run OmniRoute on a memory-constrained host; raise it if image generation
# is heavy and clients are racing the 30-minute TTL.
# OMNIROUTE_CGPT_WEB_IMAGE_CACHE_MAX_MB=256

# 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

# 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/
#OMNIROUTE_GEMINI_CLI_USAGE_URL=https://cloudcode-pa.googleapis.com/v1internal:loadCodeAssist
#OMNIROUTE_CODEWHISPERER_BASE_URL=https://codewhisperer.us-east-1.amazonaws.com
#OMNIROUTE_OPENCODE_QUOTA_URL=https://opencode.ai/zen/go/v1/quota
#OMNIROUTE_OPENCODE_GO_QUOTA_URL=https://api.z.ai/api/monitor/usage/quota/limit
#OMNIROUTE_OPENCODE_GO_DASHBOARD_URL=https://opencode.ai/workspace
#OMNIROUTE_OLLAMA_CLOUD_USAGE_URL=https://ollama.com/settings

# OpenCode Go dashboard quota scraping. Prefer configuring these per connection
# in Dashboard → Providers → OpenCode Go. Env vars are useful for headless
# deployments or shared server defaults. The cookie is sensitive.
#OPENCODE_GO_WORKSPACE_ID=wrk_...
#OMNIROUTE_OPENCODE_GO_WORKSPACE_ID=wrk_...
#OPENCODE_GO_AUTH_COOKIE=auth=...
#OMNIROUTE_OPENCODE_GO_AUTH_COOKIE=auth=...

# 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

# 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

# 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

# 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

# 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

# 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=qoder
# CLI_QWEN_BIN=qwen

# 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

# ═══════════════════════════════════════════════════════════════════════════════
# 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=

# 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=

# 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

# 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

# Model catalog sync interval in hours.
# Used by: src/shared/services/modelSyncScheduler.ts — periodic model refresh.
# Default: 24
# MODEL_SYNC_INTERVAL_HOURS=24

# Provider limits sync interval in minutes (rate limit windows, quotas).
# Used by: src/server-init.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

# 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).
# Used by: src/instrumentation-node.ts, src/lib/initCloudSync.ts
# Useful for: CI builds, test environments, or resource-constrained containers.
# OMNIROUTE_DISABLE_BACKGROUND_SERVICES=false

# 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

# 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

# Emergency budget-exhaustion fallback (set false or 0 to disable the reroute to
# nvidia/openai/gpt-oss-120b 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

# 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=

# 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

# 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

# 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

# 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

# Adjust how Antigravity advertises remaining credits.  Used by:
# open-sse/services/antigravityCredits.ts — accepts forced override strings.
# Default: empty (use upstream-reported credits).
#ANTIGRAVITY_CREDITS=

# 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=

# ── The Old LLM (theoldllm) ──
# Playwright navigation timeout (ms) for the browser-backed token capture.
# Used by: open-sse/executors/theoldllm.ts. Default: 30000 (30s).
# THEOLDLLM_NAV_TIMEOUT_MS=30000

# ── Gemini / Gemini CLI / Antigravity / Windsurf (all Google-based) ──
# These providers ship public OAuth client_id/secret values (or Firebase Web
# keys) embedded in their public CLIs/binaries. 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=
# GEMINI_CLI_OAUTH_CLIENT_ID=
# GEMINI_CLI_OAUTH_CLIENT_SECRET=
# ANTIGRAVITY_OAUTH_CLIENT_ID=
# ANTIGRAVITY_OAUTH_CLIENT_SECRET=
# WINDSURF_FIREBASE_API_KEY=

# ── Qwen (Alibaba) ──
QWEN_OAUTH_CLIENT_ID=f0304373b74a44d2b584a3fb70ca9e56

# ── Kimi Coding (Moonshot) ──
KIMI_CODING_OAUTH_CLIENT_ID=17e5f671-d194-4dfb-9706-5516cb48c098

# ── GitHub Copilot ──
GITHUB_OAUTH_CLIENT_ID=Iv1.b507a08c87ecfe98

# ── 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: api, read_user, openid, profile, email
# 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=

# ── 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=

# ─────────────────────────────────────────────────────────────────────────────
# ⚠️  GOOGLE OAUTH (Antigravity, Gemini CLI) & 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.

CLAUDE_USER_AGENT="claude-cli/2.1.187 (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
CODEX_USER_AGENT="codex-cli/0.142.0 (Windows 10.0.26200; x64)"
GITHUB_USER_AGENT="GitHubCopilotChat/0.45.1"
ANTIGRAVITY_USER_AGENT="antigravity/2.0.1 linux/arm64 google-api-nodejs-client/10.3.0"
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
QODER_USER_AGENT="Qoder-Cli"
QWEN_USER_AGENT="QwenCode/0.15.11 (linux; x64)"
CURSOR_USER_AGENT="Cursor/3.4"
GEMINI_CLI_USER_AGENT="google-api-nodejs-client/10.3.0"

# Override Codex client version sent in headers independently of the
# CODEX_USER_AGENT string. Used by: open-sse/config/codexClient.ts.
# CODEX_CLIENT_VERSION=0.142.0

# 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

# ═══════════════════════════════════════════════════════════════════════════════
# 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
# CLI_COMPAT_QWEN=1

# Or enable for all providers at once:
# CLI_COMPAT_ALL=1

# ── 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=

# 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.
# 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
# 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)

# 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

# ── ChatGPT TLS sidecar (Firefox-fingerprinted client) ──
# Used by: open-sse/services/chatgptTlsClient.ts — wire-level timeout for
# the bogdanfinn/tls-client koffi binding and the JS-side grace window
# layered on top of it when the native library is wedged.
# OMNIROUTE_CHATGPT_TLS_TIMEOUT_MS=60000
# OMNIROUTE_CHATGPT_TLS_GRACE_MS=10000

# ── Claude TLS sidecar (Chromium-fingerprinted client) ──
# Used by: open-sse/services/claudeTlsClient.ts — wire-level timeout for
# the bogdanfinn/tls-client koffi binding and the JS-side grace window
# layered on top of it when the native library is wedged.
# OMNIROUTE_CLAUDE_TLS_TIMEOUT_MS=60000
# OMNIROUTE_CLAUDE_TLS_GRACE_MS=10000

# ── Perplexity TLS sidecar (Firefox-fingerprinted client) ──
# Used by: open-sse/services/perplexityTlsClient.ts — wire-level timeout for
# the bogdanfinn/tls-client koffi binding and the JS-side grace window
# layered on top of it when the native library is wedged.
# OMNIROUTE_PPLX_TLS_TIMEOUT_MS=30000
# OMNIROUTE_PPLX_TLS_GRACE_MS=10000

# ── Grok web TLS sidecar (Chrome-fingerprinted client) ──
# Used by: open-sse/services/grokTlsClient.ts — wire-level timeout for the
# bogdanfinn/tls-client koffi binding and the JS-side grace window layered on
# top of it when the native library is wedged.
# OMNIROUTE_GROK_TLS_TIMEOUT_MS=60000
# OMNIROUTE_GROK_TLS_GRACE_MS=10000

# ── 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

# ── 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

# ── 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

# ── Stream idle detection ──
# STREAM_IDLE_TIMEOUT_MS=600000      # Max silence between SSE chunks (default: 600000)
#                                     # Extended-thinking models rarely pause >90s.
# STREAM_READINESS_TIMEOUT_MS=80000  # Time to receive the first non-ping SSE event

# ── TLS client (wreq-js fingerprint proxy) ──
# TLS_CLIENT_TIMEOUT_MS=600000       # Inherits from FETCH_TIMEOUT_MS by default

# ── 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: logs/application/app.log (relative to project root / DATA_DIR)
# 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

# 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

# Whether call log pipeline capture stores stream chunks when enabled in settings.
# Only applies when call_log_pipeline_enabled=true.
# Default: true
# 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

# 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=24               # Number of array items retained from tail (default: 24)
# CHAT_LOG_MAX_DEPTH=6                       # Max nesting depth before truncation (default: 6)
# CHAT_LOG_MAX_OBJECT_KEYS=80                # Max object keys retained (default: 80, 0 = no limit)

# Maximum rows in the proxy_logs SQLite table.
# Default: 100000
# PROXY_LOGS_TABLE_MAX_ROWS=100000

# ═══════════════════════════════════════════════════════════════════════════════
# 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

# 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=

# ── 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=

# Per-attempt HTTP timeout for CLI → server calls (milliseconds). Default: 30000.
# OMNIROUTE_HTTP_TIMEOUT_MS=30000

# 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.
# OMNIROUTE_PLUGIN_PATH=

# Allow plugins to request the 'exec' permission (spawn child processes from the
# plugin worker sandbox). Disabled by default; set to 1 to enable (local operator only).
# OMNIROUTE_PLUGINS_ALLOW_EXEC=0

# ── 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_TTL_MS=1800000          # Cache entry TTL (default: 30 minutes)

# ── In-memory log buffers ──
# Maximum recent stream events kept in memory for the Dashboard live view.
# STREAM_HISTORY_MAX=50

# ── Context length default ──
# Global fallback max context length for models without explicit config.
# 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

# Sync interval in seconds.  Default: 86400 (24 hours).
# ARENA_ELO_SYNC_INTERVAL=86400

# ═══════════════════════════════════════════════════════════════════════════════
# 19. MODEL SYNC (Dev)
# ═══════════════════════════════════════════════════════════════════════════════
# Development-time model catalog sync interval in seconds.
# Used by: src/lib/modelsDevSync.ts
# Default: 86400 (24 hours)
# MODELS_DEV_SYNC_INTERVAL=86400

# ═══════════════════════════════════════════════════════════════════════════════
# 20. PROVIDER-SPECIFIC SETTINGS
# ═══════════════════════════════════════════════════════════════════════════════

# ── OpenRouter ──
# OpenRouter model catalog cache TTL in ms.
# Used by: src/lib/catalog/openrouterCatalog.ts
# Default: 86400000 (24 hours)
# OPENROUTER_CATALOG_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

# ── 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)

# ── 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=

# ── 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

# ── 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

# ── OpenAI-compatible multi-connection ──
# Allow multiple simultaneous connections per OpenAI-compatible provider node.
# Used by: src/app/api/providers/route.ts
# ALLOW_MULTI_CONNECTIONS_PER_COMPAT_NODE=false

# ── 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

# ── 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

# ── 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

# Health check result cache TTL (ms).  Default: 30000 (30s)
# PROXY_HEALTH_CACHE_TTL_MS=30000

# 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: 120000 (2 min)
# Used by: open-sse/services/rateLimitManager.ts
# RATE_LIMIT_MAX_WAIT_MS=120000

# 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

# Stagger interval (ms) between provider token healthchecks at startup.
# Used by: src/lib/tokenHealthCheck.ts.  Default: 3000.
# HEALTHCHECK_STAGGER_MS=3000

# ═══════════════════════════════════════════════════════════════════════════════
# 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

# 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

# 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 cursor version detection).
# Used by: open-sse/utils/cursorVersionDetector.ts. Default: probed automatically.
# CURSOR_STATE_DB_PATH=

# 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: enabled.
# 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

# 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=

# ── 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

# ── 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

# ── 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

# ── 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

# ── 1Proxy egress pool ──
# Used by: src/lib/oneproxySync.ts — fetches proxy nodes from the OmniRoute
# CrofAI 1Proxy service. Disable, override URL, or tune the import quality.
# ONEPROXY_ENABLED=true
# ONEPROXY_API_URL=https://1proxy-api.aitradepulse.com
# ONEPROXY_MAX_PROXIES=500
# ONEPROXY_MIN_QUALITY_THRESHOLD=50

# ── 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

# ── 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

# ── TLS sidecar override ──
# Used by: open-sse/services/chatgptTlsClient.ts tests. Production deployments
# should leave this unset; the sidecar is auto-managed.
# OMNIROUTE_TLS_PROXY_URL=

# ── 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=

# ═══════════════════════════════════════════════════════════════════════════════
# 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

# 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-5.4-mini.
# OMNIROUTE_TRANSLATION_MODEL=gpt-4o-mini
# Per-request timeout in milliseconds (default 60000).
# OMNIROUTE_TRANSLATION_TIMEOUT_MS=60000
# Number of parallel translation requests (default 4).
# OMNIROUTE_TRANSLATION_CONCURRENCY=4

# ─── 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

# ─── 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

# 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

# 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
# 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_TLS_INTERCEPT=false
INSPECTOR_SYSTEM_PROXY_GUARD_MINUTES=30
INSPECTOR_MAX_BODY_KB=1024
INSPECTOR_MASK_SECRETS=true
INSPECTOR_LLM_HOSTS_EXTRA=
INSPECTOR_INTERNAL_INGEST_TOKEN=
# Quota Sharing (Group B — planos 16+22)
QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
# 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

# ─── 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=
# 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_*). Falls back to BIFROST_API_KEY when unset.
# OMNIROUTE_BIFROST_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=
# 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)".
# BIFROST_BASE_URL=http://bifrost:8080
# BIFROST_API_KEY=
# BIFROST_STREAMING_ENABLED=true
# BIFROST_TIMEOUT_MS=30000