Skip to content

Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

Python

Remove unused environment example (#1815)

Ali Khokhar8ac3c6cd7172
diff --git a/.env.example b/.env.example
deleted file mode 100644
index d4c3d592..00000000
--- a/.env.example
+++ /dev/null
@@ -1,446 +0,0 @@
-# NVIDIA NIM Config
-# NVIDIA_NIM_API_KEY=<your-token>
-
-
-# Azure OpenAI (resource-specific OpenAI v1 Chat Completions endpoint)
-# AZURE_OPENAI_API_KEY=<your-token>
-# AZURE_OPENAI_BASE_URL=<provider-base-url>
-
-
-# OpenRouter Config
-# OPENROUTER_API_KEY=<your-token>
-
-
-# Mistral La Plateforme Config (Experiment plan free tier – rate limits; OpenAI-compatible at api.mistral.ai/v1)
-# MISTRAL_API_KEY=<your-token>
-
-
-# Mistral Codestral (separate key from La Plateforme; OpenAI-compatible at codestral.mistral.ai/v1)
-# CODESTRAL_API_KEY=<your-token>
-
-
-# DeepSeek Config (OpenAI-compatible Chat Completions at api.deepseek.com)
-# DEEPSEEK_API_KEY=<your-token>
-
-
-# Kimi Config (OpenAI-compatible Chat Completions at api.moonshot.ai/v1)
-# KIMI_API_KEY=<your-token>
-
-
-# Kimi Code subscription (OpenAI-compatible Chat Completions at api.kimi.com/coding/v1)
-# KIMI_CODE_API_KEY=<your-token>
-
-
-# Wafer Config (OpenAI-compatible Chat Completions at pass.wafer.ai/v1)
-# WAFER_API_KEY=<your-token>
-
-
-# MiniMax Config (OpenAI-compatible Chat Completions at api.minimax.io/v1)
-# MINIMAX_API_KEY=<your-token>
-
-
-# OpenCode Zen (opencode.ai/zen/v1) and OpenCode Go (opencode.ai/zen/go/v1) share OPENCODE_API_KEY
-# OPENCODE_API_KEY=<your-token>
-
-
-# Vercel AI Gateway Config (OpenAI-compatible Chat Completions at ai-gateway.vercel.sh/v1)
-# AI_GATEWAY_API_KEY=<your-token>
-
-
-# Amazon Bedrock Mantle (region-specific OpenAI-compatible Chat Completions)
-# AWS_BEARER_TOKEN_BEDROCK=<your-token>
-BEDROCK_BASE_URL="https://bedrock-mantle.us-east-1.api.aws/v1"
-
-
-# Hugging Face Inference Providers Config (OpenAI-compatible Chat Completions at router.huggingface.co/v1)
-# HUGGINGFACE_API_KEY=<your-token>
-
-
-# Cohere Config (OpenAI-compatible Chat Completions at api.cohere.ai/compatibility/v1)
-# COHERE_API_KEY=<your-token>
-
-
-# Z.ai Config (one key for Coding Plan zai/... and pay-as-you-go zai_api/...)
-# The model prefix selects api.z.ai/api/coding/paas/v4 or api.z.ai/api/paas/v4.
-# ZAI_API_KEY=<your-token>
-
-
-# TokenRouter Config (OpenAI-compatible Chat Completions gateway at api.tokenrouter.com/v1)
-# TOKENROUTER_API_KEY=<your-token>
-TOKENROUTER_BASE_URL="https://api.tokenrouter.com/v1"
-
-
-# NaraRoute Config (OpenAI-compatible Chat Completions gateway at router.bynara.id/v1)
-# NARAROUTE_API_KEY=<your-token>
-NARAROUTE_BASE_URL="https://router.bynara.id/v1"
-
-
-# Poolside AI (OpenAI-compatible Chat Completions at inference.poolside.ai/v1)
-# POOLSIDE_API_KEY=<your-token>
-
-
-# LLM7.io (OpenAI-compatible Chat Completions at api.llm7.io/v1)
-# LLM7_API_KEY=<your-token>
-
-
-# Lightning AI Model APIs (OpenAI-compatible Chat Completions at lightning.ai/api/v1)
-# LIGHTNING_API_KEY=<your-token>
-# LIGHTNING_BASE_URL="https://lightning.ai/api/v1"
-
-
-# Experiential Labs (OpenAI-compatible Chat Completions at api.experientiallabs.ai/v1)
-# Keys look like xpl_<40 hex>; mint one at https://platform.experientiallabs.ai/settings/api-keys
-# EXPLABS_API_KEY=<your-token>
-# EXPLABS_BASE_URL="https://api.experientiallabs.ai/v1"
-
-
-# Fireworks AI Config (OpenAI-compatible Chat Completions at api.fireworks.ai/inference/v1)
-# FIREWORKS_API_KEY=<your-token>
-
-
-# Novita AI (OpenAI-compatible Chat Completions at api.novita.ai/openai/v1)
-# NOVITA_API_KEY=<your-token>
-
-
-# Cloudflare Workers AI Config (OpenAI-compatible Chat Completions at api.cloudflare.com/client/v4/accounts/<id>/ai/v1)
-# CLOUDFLARE_API_TOKEN=<your-token>
-# CLOUDFLARE_ACCOUNT_ID=<value>
-
-
-# Gemini / Google AI Studio (OpenAI-compatible Chat Completions; see https://ai.google.dev/gemini-api/docs/openai)
-# GEMINI_API_KEY=<your-token>
-
-
-# Google Vertex AI (uses Application Default Credentials; no API key)
-# Local setup: gcloud auth application-default login
-# VERTEX_PROJECT_ID=<value>
-VERTEX_LOCATION="global"
-
-
-# Groq Cloud (OpenAI-compatible Chat Completions; see https://console.groq.com/docs/openai)
-# GROQ_API_KEY=<your-token>
-
-
-# ClinePass subscription (create a programmatic key under Settings > API Keys at app.cline.bot)
-# CLINE_API_KEY=<your-token>
-
-
-# xAI / Grok (OpenAI-compatible Chat Completions at api.x.ai/v1)
-# XAI_API_KEY=<your-token>
-
-
-# QwenCloud Token Plan (dedicated sk-sp- key; OpenAI-compatible Chat Completions)
-# QWENCLOUD_API_KEY=<your-token>
-
-
-# QwenCloud Coding Plan (separate sk-sp- key; personal interactive coding-agent use)
-# QWENCLOUD_CODING_API_KEY=<your-token>
-
-
-# Together AI (OpenAI-compatible Chat Completions at api.together.ai/v1)
-# TOGETHER_API_KEY=<your-token>
-
-
-# DeepInfra (OpenAI-compatible Chat Completions at api.deepinfra.com/v1/openai)
-# DEEPINFRA_API_KEY=<your-token>
-
-
-# SiliconFlow (OpenAI-compatible Chat Completions at api.siliconflow.com/v1)
-# SILICONFLOW_API_KEY=<your-token>
-
-
-# Nebius Token Factory (OpenAI-compatible Chat Completions at api.tokenfactory.nebius.com/v1)
-# NEBIUS_API_KEY=<your-token>
-
-
-# Scaleway (OpenAI-compatible Chat Completions at api.scaleway.ai/v1)
-# SCW_SECRET_KEY=<your-token>
-
-
-# Chutes (OpenAI-compatible Chat Completions at llm.chutes.ai/v1)
-# CHUTES_API_KEY=<your-token>
-
-
-# Featherless AI (OpenAI-compatible Chat Completions at api.featherless.ai/v1)
-# FEATHERLESS_API_KEY=<your-token>
-
-
-# Agnes AI (OpenAI-compatible Chat Completions at apihub.agnes-ai.com/v1)
-# AGNES_API_KEY=<your-token>
-
-
-# ZenMux (OpenAI-compatible Chat Completions gateway at zenmux.ai/api/v1)
-# ZENMUX_API_KEY=<your-token>
-
-
-# W&B Inference (OpenAI-compatible Chat Completions at api.inference.wandb.ai/v1)
-# WANDB_API_KEY=<your-token>
-
-
-# SambaNova Cloud (OpenAI-compatible Chat Completions at api.sambanova.ai/v1)
-# SAMBANOVA_API_KEY=<your-token>
-
-
-# Kilo.ai Config (OpenAI-compatible Chat Completions gateway at api.kilo.ai/api/gateway)
-# KILO_API_KEY=<your-token>
-
-
-# Cerebras Inference (OpenAI-compatible Chat Completions; see https://inference-docs.cerebras.ai/resources/openai)
-# CEREBRAS_API_KEY=<your-token>
-
-
-# Ollama Cloud (direct OpenAI-compatible API at ollama.com/v1)
-# OLLAMA_API_KEY=<your-token>
-
-
-# LM Studio Config (local provider, no API key required)
-LM_STUDIO_BASE_URL="http://localhost:1234/v1"
-
-
-# Llama.cpp Config (local provider, no API key required)
-LLAMACPP_BASE_URL="http://localhost:8080/v1"
-
-
-# Ollama Config (local provider, no API key required)
-OLLAMA_BASE_URL="http://localhost:11434"
-
-
-# Default model and optional Claude tier overrides
-# Format: provider_type/model/name
-# Valid providers: "nvidia_nim" | "openai" | "azure_openai" | "open_router" | "gemini" | "vertex" | "deepseek" | "mistral" | "mistral_codestral" | "opencode_zen" | "opencode_go" | "vercel" | "bedrock" | "huggingface" | "cohere" | "wafer" | "kimi" | "kimi_code" | "minimax" | "cerebras" | "groq" | "cline_pass" | "xai" | "qwencloud" | "qwencloud_coding" | "together" | "deepinfra" | "siliconflow" | "nebius" | "chutes" | "featherless" | "agnes" | "zenmux" | "wandb" | "sambanova" | "kilo" | "fireworks" | "novita" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama" | "tokenrouter" | "nararoute" | "poolside" | "llm7" | "lightning" | "experiential"
-# MODEL_FABLE=<provider/model-id>
-# MODEL_OPUS=<provider/model-id>
-# MODEL_SONNET=<provider/model-id>
-# MODEL_HAIKU=<provider/model-id>
-MODEL="nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
-# Optional ordered cross-client fallbacks when a provider/model fails before output.
-# A request may reach and consume usage from more than one provider.
-# MODEL_FALLBACKS="groq/llama-3.3-70b-versatile,open_router/openrouter/free"
-
-
-# Optional live smoke model overrides. Provider smoke runs once per configured
-# provider even when MODEL/MODEL_* route to a different provider.
-# FCC_SMOKE_MODEL_NVIDIA_NIM=<provider/model-id>
-# FCC_SMOKE_MODEL_NVIDIA_NIM_VISION=<provider/model-id>
-# FCC_SMOKE_MODEL_OPENAI=<provider/model-id>
-# FCC_SMOKE_MODEL_AZURE_OPENAI=<provider/model-id>
-# FCC_SMOKE_MODEL_OPEN_ROUTER=<provider/model-id>
-# FCC_SMOKE_MODEL_MISTRAL=<provider/model-id>
-# FCC_SMOKE_MODEL_MISTRAL_REASONING=<provider/model-id>
-# FCC_SMOKE_MODEL_MISTRAL_CODESTRAL=<provider/model-id>
-# FCC_SMOKE_MODEL_DEEPSEEK=<provider/model-id>
-# FCC_SMOKE_MODEL_OLLAMA_CLOUD=<provider/model-id>
-# FCC_SMOKE_MODEL_LMSTUDIO=<provider/model-id>
-# FCC_SMOKE_MODEL_LLAMACPP=<provider/model-id>
-# FCC_SMOKE_MODEL_OLLAMA=<provider/model-id>
-# FCC_SMOKE_MODEL_KIMI=<provider/model-id>
-# FCC_SMOKE_MODEL_KIMI_CODE=<provider/model-id>
-# FCC_SMOKE_MODEL_WAFER=<provider/model-id>
-# FCC_SMOKE_MODEL_MINIMAX=<provider/model-id>
-# FCC_SMOKE_MODEL_OPENCODE_ZEN=<provider/model-id>
-# FCC_SMOKE_MODEL_OPENCODE_GO=<provider/model-id>
-# FCC_SMOKE_MODEL_VERCEL=<provider/model-id>
-# FCC_SMOKE_MODEL_BEDROCK=<provider/model-id>
-# FCC_SMOKE_MODEL_HUGGINGFACE=<provider/model-id>
-# FCC_SMOKE_MODEL_COHERE=<provider/model-id>
-# FCC_SMOKE_MODEL_ZAI=<provider/model-id>
-# FCC_SMOKE_MODEL_ZAI_API=<provider/model-id>
-# FCC_SMOKE_MODEL_TOKENROUTER=<your-token>
-# FCC_SMOKE_MODEL_NARAROUTE=<provider/model-id>
-# FCC_SMOKE_MODEL_POOLSIDE=<provider/model-id>
-# FCC_SMOKE_MODEL_LLM7=<provider/model-id>
-# FCC_SMOKE_MODEL_LIGHTNING=<provider/model-id>
-# FCC_SMOKE_MODEL_EXPERIENTIAL=<provider/model-id>
-# FCC_SMOKE_MODEL_FIREWORKS=<provider/model-id>
-# FCC_SMOKE_MODEL_NOVITA=<provider/model-id>
-# FCC_SMOKE_MODEL_CLOUDFLARE=<provider/model-id>
-# FCC_SMOKE_MODEL_GEMINI=<provider/model-id>
-# FCC_SMOKE_MODEL_VERTEX=<provider/model-id>
-# FCC_SMOKE_MODEL_GROQ=<provider/model-id>
-# FCC_SMOKE_MODEL_CLINE_PASS=<provider/model-id>
-# FCC_SMOKE_MODEL_QWENCLOUD=<provider/model-id>
-# FCC_SMOKE_MODEL_QWENCLOUD_CODING=<provider/model-id>
-# FCC_SMOKE_MODEL_TOGETHER=<provider/model-id>
-# FCC_SMOKE_MODEL_DEEPINFRA=<provider/model-id>
-# FCC_SMOKE_MODEL_SILICONFLOW=<provider/model-id>
-# FCC_SMOKE_MODEL_NEBIUS=<provider/model-id>
-# FCC_SMOKE_MODEL_SCALEWAY=<provider/model-id>
-# FCC_SMOKE_MODEL_CHUTES=<provider/model-id>
-# FCC_SMOKE_MODEL_FEATHERLESS=<provider/model-id>
-# FCC_SMOKE_MODEL_AGNES=<provider/model-id>
-# FCC_SMOKE_MODEL_ZENMUX=<provider/model-id>
-# FCC_SMOKE_MODEL_WANDB=<provider/model-id>
-# FCC_SMOKE_MODEL_SAMBANOVA=<provider/model-id>
-# FCC_SMOKE_MODEL_KILO=<provider/model-id>
-# FCC_SMOKE_MODEL_CEREBRAS=<provider/model-id>
-# FCC_SMOKE_NIM_MODELS=<provider/model-id>
-# FCC_SMOKE_NIM_EXTRA_MODELS=<provider/model-id>
-# FCC_SMOKE_OPENROUTER_FREE_MODELS=<provider/model-id>
-# FCC_SMOKE_OPENROUTER_FREE_EXTRA_MODELS=<provider/model-id>
-
-
-# Reasoning policy
-# Root: off | client | low | medium | high | xhigh | max
-# Route overrides additionally accept inherit. "client" preserves the CLI's effort;
-# providers translate only controls documented by their API.
-REASONING_POLICY=client
-REASONING_FABLE=inherit
-REASONING_OPUS=inherit
-REASONING_SONNET=inherit
-REASONING_HAIKU=inherit
-
-
-# Provider config
-# Per-provider proxy support: http and socks5, example: "http://username:password@host:port"
-# OPENAI_PROXY=<http-or-socks-url>
-# XAI_PROXY=<http-or-socks-url>
-# QWENCLOUD_PROXY=<http-or-socks-url>
-# QWENCLOUD_CODING_PROXY=<http-or-socks-url>
-# TOGETHER_PROXY=<http-or-socks-url>
-# DEEPINFRA_PROXY=<http-or-socks-url>
-# SILICONFLOW_PROXY=<http-or-socks-url>
-# NEBIUS_PROXY=<http-or-socks-url>
-# SCW_PROXY=<http-or-socks-url>
-# CHUTES_PROXY=<http-or-socks-url>
-# FEATHERLESS_PROXY=<http-or-socks-url>
-# AGNES_PROXY=<http-or-socks-url>
-# ZENMUX_PROXY=<http-or-socks-url>
-# WANDB_PROXY=<http-or-socks-url>
-# AZURE_OPENAI_PROXY=<http-or-socks-url>
-# NVIDIA_NIM_PROXY=<http-or-socks-url>
-# OPENROUTER_PROXY=<http-or-socks-url>
-# MISTRAL_PROXY=<http-or-socks-url>
-# CODESTRAL_PROXY=<http-or-socks-url>
-# LMSTUDIO_PROXY=<http-or-socks-url>
-# LLAMACPP_PROXY=<http-or-socks-url>
-# KIMI_PROXY=<http-or-socks-url>
-# KIMI_CODE_PROXY=<http-or-socks-url>
-# WAFER_PROXY=<http-or-socks-url>
-# MINIMAX_PROXY=<http-or-socks-url>
-# OPENCODE_ZEN_PROXY=<http-or-socks-url>
-# OPENCODE_GO_PROXY=<http-or-socks-url>
-# VERCEL_AI_GATEWAY_PROXY=<http-or-socks-url>
-# BEDROCK_PROXY=<http-or-socks-url>
-# HUGGINGFACE_PROXY=<http-or-socks-url>
-# COHERE_PROXY=<http-or-socks-url>
-# ZAI_PROXY=<http-or-socks-url>
-# ZAI_API_PROXY=<http-or-socks-url>
-# TOKENROUTER_PROXY=<http-or-socks-url>
-# NARAROUTE_PROXY=<http-or-socks-url>
-# POOLSIDE_PROXY=<http-or-socks-url>
-# LLM7_PROXY=<http-or-socks-url>
-# LIGHTNING_PROXY=<http-or-socks-url>
-# EXPLABS_PROXY=<http-or-socks-url>
-# FIREWORKS_PROXY=<http-or-socks-url>
-# NOVITA_PROXY=<http-or-socks-url>
-# CLOUDFLARE_PROXY=<http-or-socks-url>
-# GEMINI_PROXY=<http-or-socks-url>
-# VERTEX_PROXY=<http-or-socks-url>
-# GROQ_PROXY=<http-or-socks-url>
-# CLINE_PASS_PROXY=<http-or-socks-url>
-# SAMBANOVA_PROXY=<http-or-socks-url>
-# KILO_PROXY=<http-or-socks-url>
-# CEREBRAS_PROXY=<http-or-socks-url>
-# OLLAMA_CLOUD_PROXY=<http-or-socks-url>
-
-PROVIDER_RATE_LIMIT=1
-PROVIDER_RATE_WINDOW=2
-PROVIDER_MAX_CONCURRENCY=2
-# Maximum seconds without a non-empty protocol event. Independent of HTTP reads.
-PROVIDER_PROGRESS_TIMEOUT=600
-
-
-# HTTP client timeouts (seconds) for provider API requests
-HTTP_READ_TIMEOUT=120
-HTTP_WRITE_TIMEOUT=10
-HTTP_CONNECT_TIMEOUT=10
-
-
-# Proxy authentication is an explicit switch. Clients always receive the retained
-# non-empty token, even while server-side enforcement is disabled.
-PROXY_AUTH_ENABLED=false
-ANTHROPIC_AUTH_TOKEN="freecc"
-
-
-# Open /admin in the default browser when fcc-server becomes healthy (set 0/false/no to disable)
-FCC_OPEN_BROWSER=true
-
-
-# Messaging Platform: "telegram" | "discord" | "none"
-MESSAGING_PLATFORM="discord"
-MESSAGING_RATE_LIMIT=1
-MESSAGING_RATE_WINDOW=1
-
-
-# Voice Note Transcription
-VOICE_NOTE_ENABLED=true
-# 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="cpu"
-# 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="base"
-
-
-# Telegram Config
-# TELEGRAM_BOT_TOKEN=<your-token>
-# ALLOWED_TELEGRAM_USER_ID=<allowed-id>
-# Optional Telegram-only proxy.
-# Supported schemes: http, https, socks4, socks5, socks5h.
-# Example: "socks5://127.0.0.1:1080" or "https://user:password@host:port"
-# TELEGRAM_PROXY_URL=<http-or-socks-url>
-
-
-# Discord Config
-# DISCORD_BOT_TOKEN=<your-token>
-# ALLOWED_DISCORD_CHANNELS=<allowed-id>
-
-
-# Agent Config
-# ALLOWED_DIR=<workspace-path>
-FAST_PREFIX_DETECTION=true
-ENABLE_NETWORK_PROBE_MOCK=true
-ENABLE_TITLE_GENERATION_SKIP=true
-ENABLE_SUGGESTION_MODE_SKIP=true
-ENABLE_FILEPATH_EXTRACTION_MOCK=true
-
-
-# Claude Code WebSearch and forced local web-tool handling (set false to opt out)
-ENABLE_WEB_SERVER_TOOLS=true
-WEB_FETCH_ALLOWED_SCHEMES=http,https
-WEB_FETCH_ALLOW_PRIVATE_NETWORKS=false
-
-
-# Structured traces: DEBUG lines with `"trace": true` merge
-# ingress/routing/cli/provider/egress stages. Conversation text is logged in those payloads
-# (verbatim). Values under keys named like ``api_key`` / ``authorization`` are redacted.
-# Raw transport payloads still require the LOG_RAW_* toggles below.
-#
-# Minimum log level for the JSON file sink: DEBUG, INFO, WARNING, ERROR, CRITICAL.
-# Defaults to INFO. Use DEBUG temporarily for detailed request traces, or WARNING for quieter logs.
-# The file rotates at 50 MB and retains five rotated files (roughly 300 MB including the active file).
-LOG_LEVEL=INFO
-#
-# 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 only (handler ingress always TRACEs verbatim text separately).
-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
-
-# GitHub Copilot is an Admin connected account; no FCC API-key setting is needed.
-# Install the supported Copilot CLI version documented in README.md on PATH.
-# Connect in Admin, or first sign in with: copilot login --device-code
-# FCC stores enabled state only; the native Copilot profile owns credentials.
diff --git a/smoke/README.md b/smoke/README.md
index d5f1fb8a..d6c7c285 100644
--- a/smoke/README.md
+++ b/smoke/README.md
@@ -177,9 +177,8 @@ for restricted modes and never set up the sandbox or change your Codex config.
- `FCC_SMOKE_TARGETS`: comma-separated targets, or `all`.
- `FCC_SMOKE_PROVIDER_MATRIX`: comma-separated provider prefixes to require.
- `FCC_SMOKE_MODEL_<PROVIDER>`: optional per-provider smoke model override.
- Use the uppercase provider ID, such as `FCC_SMOKE_MODEL_KILO`; the complete
- variable inventory is in [.env.example](../.env.example). Values may include
- the provider prefix or just the model name for that provider.
+ Use the uppercase provider ID, such as `FCC_SMOKE_MODEL_KILO`. Values may
+ include the provider prefix or just the model name for that provider.
- `FCC_SMOKE_MODEL_NVIDIA_NIM_VISION`: required explicit NIM vision model for
the opt-in `nvidia_nim_vision` target; it never falls back to the text model.
- `FCC_SMOKE_MODEL_MISTRAL_REASONING`: optional override for the dedicated
diff --git a/src/free_claude_code/config/constants.py b/src/free_claude_code/config/constants.py
index d96a1617..c68a1900 100644
--- a/src/free_claude_code/config/constants.py
+++ b/src/free_claude_code/config/constants.py
@@ -2,7 +2,7 @@
DEFAULT_MODEL = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
-# HTTP client connect timeout (seconds). Keep aligned with README.md and .env.example.
+# HTTP client connect timeout (seconds).
HTTP_CONNECT_TIMEOUT_DEFAULT = 10.0
# Anthropic Messages API default when the client omits max_tokens.