# newsfeed-modelwatch configuration (production). Rendered to /etc/newsfeed/modelwatch.toml
# by the deploy workflow.
#
# The ingest token is NOT here — it is a secret, supplied via NEWSFEED_TOKEN in
# /etc/newsfeed/modelwatch.env (created once by infra-setup.sh). That keeps redeploys of
# this file from ever clobbering the token.

ingest_url = "http://127.0.0.1:22672/v1/ingest/candidates"
source_name = "huggingface"

# HF orgs to watch for new open-weight repos.
authors = [
    "tencent", "Qwen", "deepseek-ai", "mistralai", "zai-org", "moonshotai",
    "openbmb", "allenai", "nvidia", "ibm-granite", "google", "meta-llama", "microsoft",
]

# The trending list is the best built-in noise filter; a notable release surfaces fast.
include_trending = true
trending_limit = 25
per_author_limit = 15
# Ignore repos older than this so the first run doesn't backfill old "newest" repos.
max_age_days = 30

http_timeout_secs = 20
user_agent = "newsfeed-modelwatch (+https://git.lair.cafe/grenade/newsfeed)"

# Admission filter: what's worth putting in front of you at all. Ranking is NOT decided
# here — the HF tags ride onto each candidate so your per-interest weights do the ranking.
[predicate]
licenses = ["apache-2.0", "mit"]
# Total safetensors params. NB: this is total, not MoE-active (that needs config.json math).
max_params = 40000000000
require_safetensors = true
skip_gated = true
pipeline_tags = ["text-generation"]