.env.example

# =============================================================================
# OpenMAIC Environment Variables
# Copy this file to .env.local and fill in the values you need.
# All variables are optional — only configure the providers you want to use.
# You can also use server-providers.yml for configuration (see docs).
# =============================================================================

# --- LLM Providers -----------------------------------------------------------
# Format: {PROVIDER}_API_KEY, {PROVIDER}_BASE_URL (optional), {PROVIDER}_MODELS (optional, comma-separated)

OPENAI_API_KEY=
OPENAI_BASE_URL=
OPENAI_MODELS=

ANTHROPIC_API_KEY=
ANTHROPIC_BASE_URL=
ANTHROPIC_MODELS=

GOOGLE_API_KEY=
GOOGLE_BASE_URL=
GOOGLE_MODELS=

DEEPSEEK_API_KEY=
DEEPSEEK_BASE_URL=
# Example: deepseek-v4-pro,deepseek-v4-flash
DEEPSEEK_MODELS=

QWEN_API_KEY=
QWEN_BASE_URL=
QWEN_MODELS=

KIMI_API_KEY=
KIMI_BASE_URL=
KIMI_MODELS=

MINIMAX_API_KEY=
# MiniMax Anthropic-compatible endpoint for the built-in Anthropic SDK integration
MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic/v1
# Example: MiniMax-M2.7-highspeed,MiniMax-M2.7,MiniMax-M2.5-highspeed,MiniMax-M2.5
MINIMAX_MODELS=

GLM_API_KEY=
GLM_BASE_URL=
GLM_MODELS=

SILICONFLOW_API_KEY=
SILICONFLOW_BASE_URL=
SILICONFLOW_MODELS=

DOUBAO_API_KEY=
DOUBAO_BASE_URL=
DOUBAO_MODELS=

OPENROUTER_API_KEY=
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
# Example: deepseek/deepseek-v4-pro,deepseek/deepseek-v4-flash
OPENROUTER_MODELS=

GROK_API_KEY=
GROK_BASE_URL=
GROK_MODELS=

TENCENT_API_KEY=
# Tencent TokenHub OpenAI-compatible endpoint. Hy3 is a model ID, not an env prefix.
# TENCENT_HUNYUAN_* is also accepted as an alias.
TENCENT_BASE_URL=https://tokenhub.tencentmaas.com/v1
# Example: hy3-preview,hunyuan-2.0-thinking-20251109,hunyuan-2.0-instruct-20251111
TENCENT_MODELS=

XIAOMI_API_KEY=
# MIMO_* is also accepted as an alias. Use tp-... keys only with Token Plan URLs.
XIAOMI_BASE_URL=https://api.xiaomimimo.com/v1
# Token Plan regional examples:
# XIAOMI_BASE_URL=https://token-plan-cn.xiaomimimo.com/v1
# XIAOMI_BASE_URL=https://token-plan-sgp.xiaomimimo.com/v1
# XIAOMI_BASE_URL=https://token-plan-ams.xiaomimimo.com/v1
# Example: mimo-v2.5-pro,mimo-v2-pro,mimo-v2.5,mimo-v2-omni,mimo-v2-flash
XIAOMI_MODELS=

# --- Ollama (Local Models) ---------------------------------------------------
# No API key needed. Configure BASE_URL here (server-side) so it bypasses SSRF
# protection automatically. Client-supplied localhost URLs are blocked in production.
# OLLAMA_BASE_URL=http://localhost:11434/v1
# OLLAMA_MODELS=llama3.3,llama3.2,qwen2.5,mistral,gemma3

# Lemonade local server (OpenAI-compatible, no API key required)
# LEMONADE_BASE_URL=http://localhost:13305/v1
# LEMONADE_MODELS=Qwen3-0.6B-GGUF,Llama-3.2-1B-Instruct-Hybrid,Qwen2.5-VL-7B-Instruct

# --- TTS (Text-to-Speech) ----------------------------------------------------

TTS_OPENAI_API_KEY=
TTS_OPENAI_BASE_URL=

TTS_AZURE_API_KEY=
TTS_AZURE_BASE_URL=

TTS_GLM_API_KEY=
TTS_GLM_BASE_URL=

TTS_QWEN_API_KEY=
TTS_QWEN_BASE_URL=

TTS_MINIMAX_API_KEY=
# MiniMax TTS endpoint (speech-2.8 / 2.6 / 02 / 01 series)
TTS_MINIMAX_BASE_URL=https://api.minimaxi.com
TTS_ELEVENLABS_API_KEY=
TTS_ELEVENLABS_BASE_URL=

# Lemonade TTS (local, no API key required)
# TTS_LEMONADE_BASE_URL=http://localhost:13305/v1

# --- ASR (Automatic Speech Recognition) --------------------------------------

ASR_OPENAI_API_KEY=
ASR_OPENAI_BASE_URL=

ASR_QWEN_API_KEY=
ASR_QWEN_BASE_URL=

ASR_AZURE_API_KEY=
ASR_AZURE_BASE_URL=https://{region}.api.cognitive.microsoft.com

# Lemonade ASR (local, WAV input only, no API key required)
# ASR_LEMONADE_BASE_URL=http://localhost:13305/v1


# --- PDF Processing -----------------------------------------------------------

PDF_UNPDF_API_KEY=
PDF_UNPDF_BASE_URL=

PDF_MINERU_API_KEY=
PDF_MINERU_BASE_URL=

# --- Image Generation ---------------------------------------------------------

IMAGE_OPENAI_API_KEY=
IMAGE_OPENAI_BASE_URL=https://api.openai.com/v1

IMAGE_SEEDREAM_API_KEY=
IMAGE_SEEDREAM_BASE_URL=

IMAGE_QWEN_IMAGE_API_KEY=
IMAGE_QWEN_IMAGE_BASE_URL=

IMAGE_NANO_BANANA_API_KEY=
IMAGE_NANO_BANANA_BASE_URL=

IMAGE_MINIMAX_API_KEY=
# Example models: image-01, image-01-live
IMAGE_MINIMAX_BASE_URL=https://api.minimaxi.com

IMAGE_GROK_API_KEY=
IMAGE_GROK_BASE_URL=

# Lemonade image generation (local, no API key required)
# IMAGE_LEMONADE_BASE_URL=http://localhost:13305/v1

# --- Video Generation ---------------------------------------------------------

VIDEO_SEEDANCE_API_KEY=
VIDEO_SEEDANCE_BASE_URL=

VIDEO_KLING_API_KEY=
VIDEO_KLING_BASE_URL=

VIDEO_VEO_API_KEY=
VIDEO_VEO_BASE_URL=

VIDEO_SORA_API_KEY=
VIDEO_SORA_BASE_URL=

VIDEO_MINIMAX_API_KEY=
# Example models: MiniMax-Hailuo-2.3, MiniMax-Hailuo-2.3-Fast, MiniMax-Hailuo-02
VIDEO_MINIMAX_BASE_URL=https://api.minimaxi.com

VIDEO_GROK_API_KEY=
VIDEO_GROK_BASE_URL=

VIDEO_HAPPYHORSE_API_KEY=
VIDEO_HAPPYHORSE_BASE_URL=https://dashscope.aliyuncs.com

# --- Web Search ---------------------------------------------------------------
# Note: Grok (xAI) web search is available via chat completions + search tools,
# not as a standalone search API. Use Grok LLM provider with search_parameters
# in chat requests. See: https://docs.x.ai/docs/guides/tools/search-tools

TAVILY_API_KEY=
BOCHA_API_KEY=
BOCHA_BASE_URL=https://api.bocha.cn
BRAVE_API_KEY=
BAIDU_API_KEY=
BAIDU_BASE_URL=https://qianfan.baidubce.com
# Dedicated MiniMax web-search vars avoid conflicting with the LLM MINIMAX_* endpoint.
WEB_SEARCH_MINIMAX_API_KEY=
WEB_SEARCH_MINIMAX_BASE_URL=https://api.minimaxi.com

# --- Proxy (optional) --------------------------------------------------------

# HTTP_PROXY=
# HTTPS_PROXY=

# --- Misc ---------------------------------------------------------------------

# Server-side default model for API routes like /api/generate-classroom.
# Required for server-side stages (those that don't receive a client x-model):
# resolveModel throws if a stage resolves to no model (no MODEL_ROUTES entry, no
# x-model, no DEFAULT_MODEL) — there is intentionally no hardcoded vendor fallback.
# Example: anthropic:claude-3-5-haiku-20241022 or google:gemini-3-flash-preview
# OpenAI example: openai:gpt-5.5
# MiniMax example: minimax:MiniMax-M2.7-highspeed
DEFAULT_MODEL=

# Optional per-stage model routing (#745). A JSON object mapping a generation
# stage to a model string (`provider:model`). Resolution order for a stage:
# stage route > x-model (client) > DEFAULT_MODEL. A configured route is the
# operator's deliberate choice and wins even when the browser sends its saved
# model as x-model. Unset = identical to today (everything uses DEFAULT_MODEL).
# Unlisted stages fall back to x-model then DEFAULT_MODEL, so you can override
# just one or two and leave the rest to the client/default.
# Point a stage only at a server-configured provider (its key resolvable); a
# route to an unconfigured/invalid model fails at request time for that stage,
# the same way a bad DEFAULT_MODEL would (no startup validation).
# Routable stages: scene-outlines-stream, scene-content, scene-actions,
# agent-profiles, quiz-grade, pbl-chat, chat-adapter, generate-classroom,
# web-search-query-rewrite.
# scene-content can also be routed per scene type with composite keys:
# scene-content:slide, scene-content:quiz, scene-content:interactive,
# scene-content:pbl. A type falls back to the base scene-content route when it
# has no key of its own (so scene-content:<type> > scene-content > x-model >
# DEFAULT_MODEL).
# A route value can be a model string, OR an object {"model","thinking"} where
# `thinking` is the full ThinkingConfig: mode (default|disabled|enabled|auto),
# effort (none|minimal|low|medium|high|xhigh|max), level (minimal|low|medium|
# high, Gemini), enabled (bool), budgetTokens (number), excludeReasoningOutput
# (bool). It is normalized per the model's capability. When a stage is routed:
# a set `thinking` wins over the client's thinking; with no `thinking` the routed
# model uses its own default and the client's thinking is dropped. Unrouted
# stages keep the client thinking.
# Example: cheap default, stronger model only for the heavy/conversational stages:
# MODEL_ROUTES='{"scene-content":"openai:gpt-5.4","scene-actions":"openai:gpt-5.4","pbl-chat":"anthropic:claude-sonnet-4","chat-adapter":"anthropic:claude-sonnet-4"}'
# Example: per scene type + pinned thinking (qwen budget, deepseek off):
# MODEL_ROUTES='{"scene-content:interactive":{"model":"qwen:qwen3.7-plus","thinking":{"enabled":true,"budgetTokens":8000}},"scene-content:quiz":{"model":"deepseek:deepseek-v4-pro","thinking":{"enabled":false}}}'
# MODEL_ROUTES=

# LOG_LEVEL=info
# LOG_FORMAT=pretty
# LLM_THINKING_DISABLED=false

# Opt-in parallel scene-content generation (#572). 0/unset = serial (default).
# A value > 1 fetches scene content concurrently (capped at 10); actions + TTS
# stay serial. Leave off if your API key has a low per-key concurrency quota.
# PARALLEL_SCENE_CONCURRENCY=3

# --- Local/Self-hosted Deployment ---------------------------------------------
# Set to "true" to allow private/local network URLs (e.g. localhost, 192.168.x.x).
# Required for self-hosted models like Ollama. Do NOT enable on public deployments.
# ALLOW_LOCAL_NETWORKS=true

# --- Access Control -----------------------------------------------------------
# Set a password to restrict site access. When set, users must enter this code
# before using the app. Leave empty or remove to disable access control.
# ACCESS_CODE=your-secret-code