claude-code-proxy / .env.example
Yash030's picture
Deploy claude-code-nvidia proxy to Hugging Face Spaces
0157ac7
# NVIDIA NIM Config
NVIDIA_NIM_API_KEY=""
# All Claude model requests are mapped to these models, plain model is fallback
# Format: provider_type/model/name
# Valid provider: "nvidia_nim"
MODEL_OPUS=
MODEL_SONNET=
MODEL_HAIKU=
MODEL="nvidia_nim/z-ai/glm4.7"
# Optional live smoke model overrides. Smoke runs for NVIDIA NIM.
FCC_SMOKE_MODEL_NVIDIA_NIM=
# Thinking output
# Per-Claude-model switches for provider reasoning requests and Claude thinking blocks.
# Blank per-model switches inherit ENABLE_MODEL_THINKING.
ENABLE_OPUS_THINKING=
ENABLE_SONNET_THINKING=
ENABLE_HAIKU_THINKING=
ENABLE_MODEL_THINKING=true
# Provider config
# Per-provider proxy support: http and socks5, example: "http://username:password@host:port"
NVIDIA_NIM_PROXY=""
PROVIDER_RATE_LIMIT=1
PROVIDER_RATE_WINDOW=3
PROVIDER_MAX_CONCURRENCY=5
# HTTP client timeouts (seconds) for provider API requests
HTTP_READ_TIMEOUT=300
HTTP_WRITE_TIMEOUT=10
HTTP_CONNECT_TIMEOUT=10
# Optional server API key (Anthropic-style)
ANTHROPIC_AUTH_TOKEN="freecc"
# Messaging Platform: "telegram" | "discord" | "none"
MESSAGING_PLATFORM="discord"
MESSAGING_RATE_LIMIT=1
MESSAGING_RATE_WINDOW=1
# Voice Note Transcription
VOICE_NOTE_ENABLED=false
# WHISPER_DEVICE: "cpu" | "cuda" | "nvidia_nim"
# - "cpu"/"cuda": Hugging Face transformers Whisper (offline, free; install with: uv sync --extra voice_local)
# - "nvidia_nim": NVIDIA NIM Whisper via Riva gRPC (requires NVIDIA_NIM_API_KEY; install with: uv sync --extra voice)
# (Independent of MODEL=nvidia_nim/...: that selects the *chat* provider; this selects voice STT only.)
WHISPER_DEVICE="nvidia_nim"
# WHISPER_MODEL:
# - For cpu/cuda: Hugging Face ID or short name (tiny, base, small, medium, large-v2, large-v3, large-v3-turbo)
# - For nvidia_nim: NVIDIA NIM model (e.g., "nvidia/parakeet-ctc-1.1b-asr", "openai/whisper-large-v3")
# - For nvidia_nim, default to "openai/whisper-large-v3" for best performance
WHISPER_MODEL="openai/whisper-large-v3"
HF_TOKEN=""
# Telegram Config
TELEGRAM_BOT_TOKEN=""
ALLOWED_TELEGRAM_USER_ID=""
# Discord Config
DISCORD_BOT_TOKEN=""
ALLOWED_DISCORD_CHANNELS=""
# Agent Config
CLAUDE_WORKSPACE="./agent_workspace"
ALLOWED_DIR=""
CLAUDE_CLI_BIN="claude"
FAST_PREFIX_DETECTION=true
ENABLE_NETWORK_PROBE_MOCK=true
ENABLE_TITLE_GENERATION_SKIP=true
ENABLE_SUGGESTION_MODE_SKIP=true
ENABLE_FILEPATH_EXTRACTION_MOCK=true
# Local Anthropic web_search / web_fetch handling (performs outbound HTTP; on by default)
ENABLE_WEB_SERVER_TOOLS=true
WEB_FETCH_ALLOWED_SCHEMES=http,https
WEB_FETCH_ALLOW_PRIVATE_NETWORKS=false
# Verbose diagnostics (avoid logging raw prompts / SSE bodies in production)
DEBUG_PLATFORM_EDITS=false
DEBUG_SUBAGENT_STACK=false
# When true, also allows DEBUG-level httpx/httpcore/telegram log noise (not just payload logging).
LOG_RAW_API_PAYLOADS=false
LOG_RAW_SSE_EVENTS=false
# When true, log full exception text and tracebacks for unhandled errors (may leak request-derived data).
LOG_API_ERROR_TRACEBACKS=false
# When true, log message/transcription text previews in messaging adapters (may leak user content).
LOG_RAW_MESSAGING_CONTENT=false
# When true, log full Claude CLI stderr, non-JSON stdout lines, and parser error text.
LOG_RAW_CLI_DIAGNOSTICS=false
# When true, log full exception and CLI error message strings in messaging (may leak user content).
LOG_MESSAGING_ERROR_DETAILS=false