# OpenAI-compatible endpoint
# In Docker, use host.docker.internal instead of localhost for a model service on the host.
LLM_BASE_URL=https://api.openai.com/v1/
LLM_API_KEY=sk-your-key

# Default model for inline completions
LLM_MODEL=gpt-4.1-mini

# Pro-tier model (defaults to LLM_MODEL if unset)
PRO_LLM_MODEL=gpt-4.1

# Vision model for OCR
VLM_MODEL=gpt-4.1-mini

# API key for the FastAPI app (change in production)
API_KEY=your-secret-key-here

# Browser origins allowed to send anonymous session cookies
CORS_ALLOW_ORIGINS=https://imageteach.tech,https://www.imageteach.tech,http://localhost:5173,http://127.0.0.1:5173

# Anonymous session cookie
SESSION_COOKIE_NAME=llm_anonymous_session
SESSION_COOKIE_SECURE=true
SESSION_COOKIE_SAMESITE=none
SESSION_COOKIE_DOMAIN=
SESSION_COOKIE_PATH=/
SESSION_COOKIE_MAX_AGE_SECONDS=2592000
SESSION_ROTATION_SECONDS=86400

# Job backend
JOB_BACKEND=redis
REDIS_URL=redis://localhost:6379/0
DATABASE_URL=postgresql://llm_in_text:llm_in_text_change_me@localhost:5432/llm_in_text
DOCS_BACKEND=postgres
JOB_REDIS_PREFIX=llmtext:jobs
JOB_CONSUMER_NAME=
JOB_SHARED_TEMP_DIR=/tmp/llm-in-text-jobs
JOB_STATE_TTL_SECONDS=600
JOB_EVENT_TTL_SECONDS=600
JOB_EVENT_STREAM_MAXLEN=512
JOB_CANCEL_POLL_SECONDS=0.5
JOB_BUSY_NORMAL_THRESHOLD=0.25
JOB_BUSY_HIGH_THRESHOLD=0.75
JOB_BUSY_FULL_THRESHOLD=1.0

# Per-queue concurrency and capacity
JOB_COMPLETION_CONCURRENCY=2
JOB_COMPLETION_MAX_QUEUE=16
JOB_PRO_COMPLETION_CONCURRENCY=1
JOB_PRO_COMPLETION_MAX_QUEUE=8
JOB_COMPRESS_CONCURRENCY=1
JOB_COMPRESS_MAX_QUEUE=8
JOB_OCR_CONCURRENCY=1
JOB_OCR_MAX_QUEUE=8
JOB_CONVERT_CONCURRENCY=1
JOB_CONVERT_MAX_QUEUE=8
JOB_TTS_CONCURRENCY=1
JOB_TTS_MAX_QUEUE=4
JOB_ASR_CONCURRENCY=1
JOB_ASR_MAX_QUEUE=4

# Timeouts (seconds)
LLM_COMPLETION_TIMEOUT=600
LLM_OCR_TIMEOUT=600

# Compression limit
DOC_COMPRESS_CONTEXT_LIMIT=128000

# Risk control
RISK_API_WINDOW_SECONDS=60
RISK_API_SOFT_LIMIT=90
RISK_API_HARD_LIMIT=180
RISK_LLM_WINDOW_SECONDS=600
RISK_LLM_SOFT_LIMIT=8
RISK_LLM_HARD_LIMIT=16
RISK_SESSION_CONCURRENCY_LIMIT=2
RISK_GLOBAL_CONCURRENCY_LIMIT=12
RISK_DAILY_BUDGET_GLOBAL_USD=20
RISK_DAILY_BUDGET_SESSION_USD=2
RISK_DAILY_BUDGET_IP_USD=5
RISK_SINGLE_REQUEST_MAX_COST_USD=0.8
RISK_DELAY_STEP_MS=2500
RISK_DELAY_CAP_MS=30000
RISK_MODEL_CIRCUIT_FAILURES=8
RISK_MODEL_CIRCUIT_TTL_SECONDS=300
RISK_ENFORCE_REDIS_FAIL_CLOSED=false

# Backend-controlled model policy
RISK_COMPLETION_MODEL=gpt-4.1-mini
RISK_PRO_MODEL=gpt-4.1
RISK_VISION_MODEL=gpt-4.1-mini
RISK_COMPLETION_MAX_INPUT_CHARS=24000
RISK_COMPLETION_MAX_OUTPUT_TOKENS=768
RISK_COMPLETION_TEMPERATURE=0.4
RISK_PRO_MAX_INPUT_CHARS=48000
RISK_PRO_MAX_OUTPUT_TOKENS=2048
RISK_PRO_TEMPERATURE=0.6
RISK_COMPRESS_MAX_INPUT_CHARS=128000
RISK_COMPRESS_MAX_OUTPUT_TOKENS=1536
RISK_OCR_MAX_INPUT_BYTES=10485760

# Estimated pricing for budget control
RISK_COMPLETION_INPUT_COST_PER_1K=0.0004
RISK_COMPLETION_OUTPUT_COST_PER_1K=0.0016
RISK_PRO_INPUT_COST_PER_1K=0.003
RISK_PRO_OUTPUT_COST_PER_1K=0.012
RISK_VISION_INPUT_COST_PER_1K=0.0008
RISK_VISION_OUTPUT_COST_PER_1K=0.0024

# Legacy fallback: if LLM_BASE_URL is not set, OLLAMA_HOST will be auto-converted to /v1/ path
#OLLAMA_HOST=http://localhost:11434

# TTS/ASR settings (see README for full list)
TTS_ASR_DEVICE=auto