# supplier/.env.huggingface-chat.example
#
# Preset for a chat supplier that uses the HuggingFace Inference Providers router
# (https://router.huggingface.co) as its COMPUTE BACKEND to fulfil bonded
# inference work commissioned on Vector. It is the OpenAI-compatible on-ramp:
# the router is OpenAI-compatible, so this reuses the existing LLM_BACKEND=openai
# path with NO code changes — it is config only.
#
# Copy to supplier/.env on the host (chmod 600) and fill in real values.
# .env is gitignored — NEVER commit a populated copy.
#
# Runbook: docs/HUGGINGFACE_ROUTER_SETUP.md
#
# To generate a fresh Ed25519 wallet seed:  openssl rand -hex 32
# Lines marked SECRET must never be shared, logged, or committed.

# ─── Required ─────────────────────────────────────────────────────────────

# 64-char hex Ed25519 private key seed for this supplier's wallet. SECRET.
SUPPLIER_PRIV_KEY_HEX=PASTE_64_HEX_CHARS_HERE

# Ogmios WebSocket URL. Testnet shown; use the mainnet URL for NETWORK_ID=1:
#   testnet: wss://ogmios.vector.testnet.apexfusion.org
#   mainnet: wss://ogmios.vector.mainnet.apexfusion.org
OGMIOS_URL=wss://ogmios.vector.testnet.apexfusion.org

# OutputReference of this supplier's on-chain advertisement UTxO.
# Format "<64-hex-tx-hash>#<int>". Post it first (see tx:post-advert below),
# then paste the printed "<txHash>#0" here.
ADVERT_REF=PASTE_TXHASH_HERE#0

# Cardano network ID. "0" = testnet, "1" = mainnet. Keep "0" until you have
# validated the setup end-to-end on testnet.
NETWORK_ID=0

# ─── Backend: HuggingFace router (OpenAI-compatible) ──────────────────────
# Route the chat job runner at the HF Inference Providers router instead of a
# local Ollama. The supplier POSTs to ${OPENAI_BASE_URL}/v1/chat/completions.
LLM_BACKEND=openai

# HF router base URL. The supplier appends /v1/chat/completions itself, so do
# NOT include the /v1 suffix here.
OPENAI_BASE_URL=https://router.huggingface.co

# HuggingFace access token (starts with "hf_"). Create one at
# https://huggingface.co/settings/tokens with "Make calls to Inference
# Providers" permission. Forwarded as `Authorization: Bearer <token>`. SECRET.
OPENAI_API_KEY=PASTE_HF_TOKEN_HERE

# First-token latency across hosted providers can exceed local Ollama — keep a
# generous request timeout.
OPENAI_TIMEOUT_MS=180000

# ─── IMPORTANT: do NOT set OPENAI_REASONING here ──────────────────────────
# `reasoning:{enabled:false}` is an OpenRouter-only param. The HF router
# rejects it with HTTP 400 on every request. The supplier refuses to boot if
# OPENAI_REASONING is disabled while OPENAI_BASE_URL points at the HF router.
# (This is the #1 footgun when copying an OpenRouter env — leave it unset.)
# OPENAI_REASONING=

# Optional hard ceiling forwarded as `max_tokens`. Unset = provider grants the
# max available (context − prompt). Keep below the model's context window.
# OPENAI_MAX_TOKENS=

# ─── Enable real chain submissions ────────────────────────────────────────
# LIVE_CHAIN: only the literal "1" opts in to real Claim/Submit txs. Leave
# unset for a dry run (read-only, no chain writes) while testing.
LIVE_CHAIN=

# HTTP listen port inside the container. Compose maps this to the host.
PORT=8080

# ─── tx:post-advert — run once before first deploy ────────────────────────
# Execute (from repo root):
#   pnpm --filter @marketplace/supplier tx:post-advert \
#     --capability-id llm.text.generate.v1 \
#     --model deepseek-ai/DeepSeek-V3:fastest \
#     --max-output-tokens 512 \
#     --max-processing-ms 60000 \
#     --price-lovelace 2000000 \
#     --endpoint-url https://mp-supplier.vector.testnet.apexfusion.org
# Copy the printed "<txHash>#0" into ADVERT_REF above.
#
# NOTE on --model: HF uses PROVIDER-QUALIFIED model names. The bare id picks a
# default provider; a ":<hint>" suffix pins routing:
#   deepseek-ai/DeepSeek-V3:fastest    # cheapest/fastest provider for the model
#   deepseek-ai/DeepSeek-V3:together   # pin a specific provider
#   openai/gpt-oss-120b                # open-weight, HF-hosted
# Browse models + providers at https://huggingface.co/models?inference_provider=all
# The value lives on-chain in AdvertDatum.model — it is data, not code, so you
# can advertise any router-supported model without touching the supplier.
ADVERT_CAPABILITY_ID=llm.text.generate.v1
ADVERT_MODEL=deepseek-ai/DeepSeek-V3:fastest
ADVERT_MAX_OUTPUT_TOKENS=512
ADVERT_MAX_PROCESSING_MS=60000

# Flat AP3X amount committed in escrow per job (1 AP3X = 1_000_000 lovelace).
# The HF backend meters PER TOKEN while this committed amount is fixed per job,
# so size it for your worst-case prompt length and cap output tightly via
# ADVERT_MAX_OUTPUT_TOKENS. See docs/HUGGINGFACE_ROUTER_SETUP.md §4.
ADVERT_PRICE_LOVELACE=2000000
ADVERT_SUPPLIER_BOND_LOVELACE=1000000
ADVERT_BUYER_BOND_LOVELACE=1000000

# HTTPS endpoint buyers will call (must be publicly reachable).
ADVERT_ENDPOINT_URL=https://mp-supplier.vector.testnet.apexfusion.org

# Optional off-chain detail pointer + its sha256 (leave empty for v1).
ADVERT_DETAIL_URI=
ADVERT_DETAIL_HASH=

# ─── Optional: CIP-33 reference scripts (recommended on mainnet) ──────────
# ESCROW_REF_UTXO=<txhash>#0
# ADVERT_REF_UTXO=<txhash>#1