# Runtime configuration and tuning knobs.
#
# Three-file split, so a new user knows what to touch:
#   config.toml   this file -- machinery. Sane defaults; rarely edited.
#   profile.toml  who you are: interests, vetoes, importance, delivery.
#   sources.toml  what to read.
#
# Nothing here is specific to any person. Everything personal lives in the
# other two files.

[http]
# Sent on every outbound request. Feed operators use it to identify traffic and
# some will block a generic or absent agent, so put a real contact here.
# CHANGE THIS if you are not Connor -- it is the contact address feed operators
# see, and pointing them at someone else's domain is rude and unhelpful.
user_agent = "news/0.1 (+https://news.rcjohnstone.com; personal feed reader; one user)"
timeout_secs = 30
connect_timeout_secs = 10
concurrency = 8
max_body_bytes = 10485760

[embedding]
# Any model fastembed can serve. `dim` must match the model.
#
# The default is English-only. For native-language sources use a multilingual
# model -- "intfloat/multilingual-e5-small" (384 dim) is the usual choice.
# Be aware that changing the model INVALIDATES the calibrated constants below
# and in [scoring]: they are cosine thresholds, and a different model puts
# similarity on a different scale. Re-run the calibration before trusting them.
model = "BAAI/bge-small-en-v1.5"
dim = 384

[clustering]
# Calibrated by inspection on a 3,885-item corpus; see CALIBRATION.md.
# 0.70 merged "Solheim Cup capsules" with "FIBA Women's World Cup Glance";
# 0.86 under-merged. Over-merging is the worse failure because it inflates the
# corroboration signal that feeds importance.
#
# Re-tune if your sources differ substantially in style or language.
threshold = 0.82
window_hours = 48

[scoring]
# Compare blocks by z-score WITHIN each block, never by raw cosine: cosine
# magnitude is not comparable across blocks, and a plain max let one block win
# 78% of all items. See CALIBRATION.md.
normalize = "zscore-per-block"

# Veto is not a plain similarity threshold. A story can be genuinely adjacent to
# a vetoed topic and still be wanted, so an item is vetoed on unambiguous
# similarity OR when the veto signal beats the best interest signal by a margin.
veto_absolute = 0.60
veto_margin_over_interest = 0.3