Curation v2 step 3: Voyage embeddings, cheap signals, candidate telemetry

- embedding.rs: EmbeddingBackend + VoyageBackend, batched bounded-concurrency
  client with its own UsageMeter, f32 BLOB codec, article/interest embedding
  cache keyed by model, dimension and sha256 of the embedded text.
- signals.rs: z-scored interest match, decayed rated-neighbour preference
  with the knn gate, feed affinity with the feed gate, social, text heuristic
  without social terms, mid-rank percentile normalizer, preliminary blend.
- telemetry.rs: candidate_runs writer with §7.5 signals_json, explain and
  near-misses renderers, prune.
- [voyage] and the full [curation.ranking] config with validation.
- CLI: explain, features backfill|prune, generate --skip-embeddings.
- Pipeline: hygiene rows, embed and signals stages before the old prefilter;
  same-date regeneration no longer excludes its own picks.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe

src/curate/mod.rs

@@ -10,11 +10,14 @@
 //! feed excerpts stand in for summaries (notes §6).
 
 pub mod editorial;
+pub mod embedding;
 pub mod llm;
 pub mod prefilter;
 pub mod profile;
 pub mod score;
 pub mod select;
+pub mod signals;
+pub mod telemetry;
 
 use jiff::civil::Date;
 

src/curate/prefilter.rs

@@ -90,7 +90,7 @@ impl PrefilterContext {
         let since = today
             .checked_sub(jiff::Span::new().days(STALE_LOOKBACK_DAYS))
             .unwrap_or(today);
-        let already_published = db.previously_published_ids().await?;
+        let already_published = db.previously_published_ids_before(today).await?;
         let recently_rejected = db.recently_low_scored_ids(STALE_LOW_SCORE, since).await?;
         tracing::debug!(
             published = already_published.len(),
@@ -197,6 +197,29 @@ pub fn social_points(social_score: f64) -> f64 {
     MAX_SOCIAL_POINTS * (social_score / SOCIAL_SATURATION).min(1.0).sqrt()
 }
 
+/// Text-only heuristic used by personalized ranking (§9.3).
+pub fn text_heuristic(article: &Article) -> f64 {
+    longform_points(article.word_count)
+        - excerpt_only_penalty(article)
+        - roundup_penalty(&article.title)
+}
+
+pub fn excerpt_only_penalty(article: &Article) -> f64 {
+    if article.excerpt_only {
+        EXCERPT_ONLY_PENALTY
+    } else {
+        0.0
+    }
+}
+
+pub fn roundup_penalty(title: &str) -> f64 {
+    if looks_like_roundup(title) {
+        ROUNDUP_TITLE_PENALTY
+    } else {
+        0.0
+    }
+}
+
 /// Score one article 0–100 from word count, social proof, source signals,
 /// and the excerpt/roundup/blocklist penalties (§3.5).
 pub fn score_article(article: &Article, _ctx: &PrefilterContext, cfg: &Config) -> f64 {

src/curate/profile/mod.rs

@@ -125,6 +125,16 @@ pub fn load_profile(path: &Path) -> anyhow::Result<ProfileFile> {
     }
 }
 
+/// Load the exact standing-interest union used in the system prompt.
+pub fn load_standing_interests(
+    opml_path: &Path,
+    profile_path: &Path,
+) -> anyhow::Result<Vec<String>> {
+    let opml = parse_interests(opml_path)?;
+    let profile = load_profile(profile_path)?;
+    Ok(union_interests(opml, profile.interests))
+}
+
 fn union_interests(opml: Vec<String>, profile: Vec<String>) -> Vec<String> {
     let mut seen = BTreeSet::new();
     let mut out = Vec::new();

src/curate/signals.rs

@@ -0,0 +1,981 @@
+//! Cheap per-article ranking signals, the mid-rank percentile normalizer and the
+//! preliminary blend (plan §9, §12.2, §12.4).
+//!
+//! Every signal is an `Option<f64>`: `None` means *absent*, which is never a
+//! numeric zero. Absent signals are left out of the percentile computation and
+//! of the blend, whose remaining weights are renormalized (§12.2, §12.4).
+
+use std::collections::{BTreeMap, HashMap, HashSet};
+
+use jiff::Timestamp;
+use serde::{Deserialize, Serialize};
+
+use crate::config::{PreliminaryWeights, RankingConfig, VoyageConfig};
+use crate::curate::embedding::{dot, load_article_embeddings};
+use crate::curate::prefilter;
+use crate::db::Db;
+use crate::types::{Article, ArticleId, FeedId, SourceKind};
+
+/// Below this many embedded eligible articles the z-score is too noisy, so the
+/// interest signal falls back to the raw top-1 cosine (§9.1).
+pub const INTEREST_ZSCORE_MIN_ARTICLES: usize = 30;
+/// Standard-deviation floor for the per-interest z-score (§9.1).
+const ZSCORE_STD_FLOOR: f64 = 1e-3;
+/// How many interests and rated neighbours `signals_json` records (§7.5).
+const RECORDED_TOP: usize = 3;
+
+/// The signal names that go through the percentile normalizer, in the order
+/// they are rendered (§12.2). LLM scores (`triage`, `quality`, `fit`) are
+/// absolute and arrive in steps 4–5.
+pub const PERCENTILE_SIGNALS: [&str; 5] = ["interest", "knn", "feed", "social", "heuristic"];
+
+#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
+pub struct TopInterest {
+    pub name: String,
+    pub z: f64,
+    pub cos: f64,
+}
+
+#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
+pub struct Neighbour {
+    pub article_id: ArticleId,
+    pub label: String,
+    pub cos: f64,
+    pub title: String,
+}
+
+/// Every cheap signal for one article, plus what the normalizer and the blend
+/// derived from them (§9, §12.2, §12.4).
+#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
+pub struct Signals {
+    pub interest: Option<f64>,
+    /// Raw top-1 cosine behind `interest`, recorded for `explain` (§7.5).
+    pub interest_top1_cos: Option<f64>,
+    pub knn: Option<f64>,
+    pub feed: Option<f64>,
+    pub social: Option<f64>,
+    pub heuristic: Option<f64>,
+    /// Mid-rank percentiles of the present signals (§12.2).
+    #[serde(default)]
+    pub norm: BTreeMap<String, f64>,
+    /// Effective preliminary weights after gating and renormalization (§12.4).
+    #[serde(default)]
+    pub weights: BTreeMap<String, f64>,
+    #[serde(default)]
+    pub top_interests: Vec<TopInterest>,
+    #[serde(default)]
+    pub neighbours: Vec<Neighbour>,
+    #[serde(default)]
+    pub notes: Vec<String>,
+    /// Preliminary blend on a 0–100 scale; `None` when nothing is present.
+    pub preliminary: Option<f64>,
+    /// Gate ramps applied to the learned signals' weights (§9.2, §9.3).
+    #[serde(skip)]
+    pub knn_gate: f64,
+    #[serde(skip)]
+    pub feed_gate: f64,
+}
+
+impl Signals {
+    /// The raw value of a named signal, `None` when absent or unknown.
+    pub fn raw(&self, name: &str) -> Option<f64> {
+        match name {
+            "interest" => self.interest,
+            "interest_top1_cos" => self.interest_top1_cos,
+            "knn" => self.knn,
+            "feed" => self.feed,
+            "social" => self.social,
+            "heuristic" => self.heuristic,
+            _ => None,
+        }
+    }
+
+    pub fn present(&self, name: &str) -> bool {
+        self.raw(name).is_some()
+    }
+
+    /// The signals every eligible article gets without embeddings or ratings.
+    pub fn baseline(article: &Article) -> Self {
+        Self {
+            social: (!article.social.is_empty()).then(|| article.social_score()),
+            heuristic: Some(prefilter::text_heuristic(article)),
+            ..Self::default()
+        }
+    }
+}
+
+/// What the run log and the report say about the learned signals (§9.2, §15.4).
+#[derive(Debug, Clone, Copy, Default, PartialEq)]
+pub struct PreferenceSummary {
+    pub rated_with_embeddings: usize,
+    pub attributable_feed_ratings: usize,
+    pub knn_gate: f64,
+    pub feed_gate: f64,
+}
+
+/// One rated article with an embedding: the unit of the preference state (§9.2).
+#[derive(Debug, Clone, PartialEq)]
+pub struct RatedExample {
+    pub article_id: ArticleId,
+    pub label: String,
+    pub title: String,
+    /// The vote's value (`loved` 1.0, `good` 0.35, `not_for_me` −1.0).
+    pub value: f64,
+    /// `0.5 ^ (age_days / half_life_days)` at the time of the run.
+    pub decay: f64,
+    pub embedding: Vec<f32>,
+    /// Distinct direct feeds that carried the rated article (§9.3).
+    pub feeds: Vec<FeedId>,
+}
+
+impl RatedExample {
+    /// `weight_i = value_i × decay_i` (§9.2).
+    pub fn weight(&self) -> f64 {
+        self.value * self.decay
+    }
+}
+
+#[derive(Debug, Clone, Copy, Default, PartialEq)]
+struct FeedRate {
+    up: f64,
+    down: f64,
+}
+
+impl FeedRate {
+    /// Beta-smoothed rate `(up + 1) / (up + down + 2)` (§9.3).
+    fn rate(self) -> f64 {
+        (self.up + 1.0) / (self.up + self.down + 2.0)
+    }
+}
+
+/// Rated-neighbour and feed-affinity state, built once per run (§9.2, §9.3).
+#[derive(Debug, Clone, Default)]
+pub struct PreferenceState {
+    pub examples: Vec<RatedExample>,
+    feed_rates: HashMap<FeedId, FeedRate>,
+    pub attributable_feed_ratings: usize,
+    pub knn_gate: f64,
+    pub feed_gate: f64,
+}
+
+impl PreferenceState {
+    /// Build the state from already-loaded examples (pure; tests use this).
+    pub fn build(examples: Vec<RatedExample>, ranking: &RankingConfig) -> Self {
+        let (feed_rates, attributable_feed_ratings) = feed_rates(&examples);
+        Self {
+            knn_gate: gate(examples.len(), ranking.knn_floor, ranking.knn_full),
+            feed_gate: gate(
+                attributable_feed_ratings,
+                ranking.feed_floor,
+                ranking.feed_full,
+            ),
+            examples,
+            feed_rates,
+            attributable_feed_ratings,
+        }
+    }
+
+    /// Load `db::current_ratings(rating_lookback_days)` joined to
+    /// `article_embeddings`; ratings without an embedding are skipped (§9.2).
+    pub async fn load(
+        db: &Db,
+        voyage: &VoyageConfig,
+        ranking: &RankingConfig,
+        now: Timestamp,
+    ) -> anyhow::Result<Self> {
+        let ratings = db.current_ratings(ranking.rating_lookback_days).await?;
+        let ids = ratings
+            .iter()
+            .map(|rating| rating.article_id)
+            .collect::<Vec<_>>();
+        let embeddings = load_article_embeddings(db, voyage, &ids).await?;
+        let mut examples = Vec::new();
+        for rating in ratings {
+            let Some(embedding) = embeddings.get(&rating.article_id).cloned() else {
+                continue;
+            };
+            let feeds = db
+                .get_article(rating.article_id)
+                .await?
+                .as_ref()
+                .map(direct_feeds)
+                .unwrap_or_default();
+            let age_days = (now.as_second() - rating.event_at.as_second()).max(0) as f64 / 86_400.0;
+            examples.push(RatedExample {
+                article_id: rating.article_id,
+                label: rating.label,
+                title: rating.title,
+                value: rating.value,
+                decay: decay(age_days, ranking.rating_half_life_days),
+                embedding,
+                feeds,
+            });
+        }
+        Ok(Self::build(examples, ranking))
+    }
+
+    pub fn summary(&self) -> PreferenceSummary {
+        PreferenceSummary {
+            rated_with_embeddings: self.examples.len(),
+            attributable_feed_ratings: self.attributable_feed_ratings,
+            knn_gate: self.knn_gate,
+            feed_gate: self.feed_gate,
+        }
+    }
+
+    /// The once-per-run log line of §9.2.
+    pub fn log(&self, ranking: &RankingConfig) {
+        let feed_detail = if self.feed_gate > 0.0 {
+            format!("(n={})", self.attributable_feed_ratings)
+        } else {
+            format!(
+                "(n={} < {})",
+                self.attributable_feed_ratings, ranking.feed_floor
+            )
+        };
+        tracing::info!(
+            rated_with_embeddings = self.examples.len(),
+            knn_gate = self.knn_gate,
+            feed_gate = self.feed_gate,
+            "preference: {} rated articles with embeddings → knn gate {:.2}; feed gate {:.1} {}",
+            self.examples.len(),
+            self.knn_gate,
+            self.feed_gate,
+            feed_detail
+        );
+    }
+
+    /// Signed rated-neighbour preference and the three nearest rated articles
+    /// (§9.2). Absent when the gate is closed or there are no examples.
+    pub fn knn(&self, candidate: &[f32], ranking: &RankingConfig) -> (Option<f64>, Vec<Neighbour>) {
+        if self.knn_gate <= 0.0 || self.examples.is_empty() {
+            return (None, Vec::new());
+        }
+        let mut scored = self
+            .examples
+            .iter()
+            .filter_map(|example| {
+                dot(candidate, &example.embedding)
+                    .ok()
+                    .map(|s| (s, example))
+            })
+            .collect::<Vec<_>>();
+        scored.sort_by(|left, right| right.0.total_cmp(&left.0));
+
+        let side = |positive: bool| -> Option<f64> {
+            let chosen = scored
+                .iter()
+                .filter(|(_, example)| (example.weight() > 0.0) == positive)
+                .take(ranking.neighbour_k.max(1))
+                .collect::<Vec<_>>();
+            let denominator = chosen
+                .iter()
+                .map(|(_, example)| example.weight().abs())
+                .sum::<f64>();
+            (denominator > 0.0).then(|| {
+                chosen
+                    .iter()
+                    .map(|(similarity, example)| example.weight().abs() * similarity)
+                    .sum::<f64>()
+                    / denominator
+            })
+        };
+        let positive = side(true);
+        let negative = side(false);
+        let knn = (positive.is_some() || negative.is_some()).then(|| {
+            positive.unwrap_or(0.0) - ranking.negative_coefficient * negative.unwrap_or(0.0)
+        });
+        let neighbours = scored
+            .iter()
+            .take(RECORDED_TOP)
+            .map(|(cos, example)| Neighbour {
+                article_id: example.article_id,
+                label: example.label.clone(),
+                cos: *cos,
+                title: example.title.clone(),
+            })
+            .collect();
+        (knn, neighbours)
+    }
+
+    /// Mean Beta-smoothed rate over the article's rated direct feeds (§9.3).
+    pub fn feed(&self, article: &Article) -> Option<f64> {
+        if self.feed_gate <= 0.0 {
+            return None;
+        }
+        let rates = direct_feeds(article)
+            .into_iter()
+            .filter_map(|feed| self.feed_rates.get(&feed))
+            .map(|rate| rate.rate())
+            .collect::<Vec<_>>();
+        (!rates.is_empty()).then(|| rates.iter().sum::<f64>() / rates.len() as f64)
+    }
+
+    /// Per-feed `(up, down)` credit, exposed for tests of §9.3.
+    pub fn feed_credit(&self, feed: FeedId) -> Option<(f64, f64)> {
+        self.feed_rates.get(&feed).map(|rate| (rate.up, rate.down))
+    }
+}
+
+/// `0.5 ^ (age_days / half_life_days)` (§9.2).
+pub fn decay(age_days: f64, half_life_days: f64) -> f64 {
+    if half_life_days <= 0.0 {
+        return 1.0;
+    }
+    0.5f64.powf(age_days.max(0.0) / half_life_days)
+}
+
+/// `clamp((n − floor) / (full − floor), 0, 1)` (§9.2).
+pub fn gate(n: usize, floor: usize, full: usize) -> f64 {
+    if n <= floor {
+        0.0
+    } else if n >= full || full <= floor {
+        1.0
+    } else {
+        (n - floor) as f64 / (full - floor) as f64
+    }
+}
+
+/// Distinct `SourceKind::Feed` feeds that carried the article; the best entry's
+/// feed when there are none (§9.3).
+pub fn direct_feeds(article: &Article) -> Vec<FeedId> {
+    let mut feeds = article
+        .sources
+        .iter()
+        .filter(|source| source.kind == SourceKind::Feed)
+        .map(|source| source.feed_id)
+        .collect::<HashSet<_>>()
+        .into_iter()
+        .collect::<Vec<_>>();
+    if feeds.is_empty() && article.feed_id != 0 {
+        feeds.push(article.feed_id);
+    }
+    feeds.sort_unstable();
+    feeds
+}
+
+fn feed_rates(examples: &[RatedExample]) -> (HashMap<FeedId, FeedRate>, usize) {
+    let mut rates: HashMap<FeedId, FeedRate> = HashMap::new();
+    let mut attributable = 0;
+    for example in examples {
+        if example.feeds.is_empty() {
+            continue;
+        }
+        attributable += 1;
+        let credit = example.weight() / example.feeds.len() as f64;
+        for feed in &example.feeds {
+            let rate = rates.entry(*feed).or_default();
+            rate.up += credit.max(0.0);
+            rate.down += (-credit).max(0.0);
+        }
+    }
+    (rates, attributable)
+}
+
+/// The interest match of §9.1 for one article.
+#[derive(Debug, Clone, Default, PartialEq)]
+pub struct InterestMatch {
+    pub score: f64,
+    pub top1_cos: f64,
+    pub top_interests: Vec<TopInterest>,
+}
+
+/// Z-scored standing-interest match for every embedded article (§9.1).
+///
+/// Below [`INTEREST_ZSCORE_MIN_ARTICLES`] embedded articles the score is the raw
+/// top-1 cosine instead, and that is logged.
+pub fn interest_matches(
+    articles: &HashMap<ArticleId, Vec<f32>>,
+    interests: &HashMap<String, Vec<f32>>,
+) -> HashMap<ArticleId, InterestMatch> {
+    if articles.is_empty() || interests.is_empty() {
+        return HashMap::new();
+    }
+    let fallback = articles.len() < INTEREST_ZSCORE_MIN_ARTICLES;
+    if fallback {
+        tracing::info!(
+            embedded = articles.len(),
+            "fewer than {INTEREST_ZSCORE_MIN_ARTICLES} embedded articles; interest uses the raw top-1 cosine"
+        );
+    }
+
+    let mut matches: HashMap<ArticleId, Vec<TopInterest>> = HashMap::new();
+    for (name, interest) in interests {
+        let similarities = articles
+            .iter()
+            .filter_map(|(article_id, article)| {
+                dot(interest, article).ok().map(|cos| (*article_id, cos))
+            })
+            .collect::<Vec<_>>();
+        if similarities.is_empty() {
+            continue;
+        }
+        let n = similarities.len() as f64;
+        let mean = similarities.iter().map(|(_, cos)| cos).sum::<f64>() / n;
+        let variance = similarities
+            .iter()
+            .map(|(_, cos)| (cos - mean).powi(2))
+            .sum::<f64>()
+            / n;
+        let std = variance.sqrt().max(ZSCORE_STD_FLOOR);
+        for (article_id, cos) in similarities {
+            matches.entry(article_id).or_default().push(TopInterest {
+                name: name.clone(),
+                z: (cos - mean) / std,
+                cos,
+            });
+        }
+    }
+
+    matches
+        .into_iter()
+        .map(|(article_id, mut all)| {
+            all.sort_by(|left, right| {
+                right
+                    .z
+                    .total_cmp(&left.z)
+                    .then_with(|| left.name.cmp(&right.name))
+            });
+            let top1_cos = all
+                .iter()
+                .map(|item| item.cos)
+                .fold(f64::NEG_INFINITY, f64::max);
+            all.truncate(RECORDED_TOP);
+            let score = if fallback {
+                top1_cos
+            } else {
+                let top_mean = all.iter().map(|item| item.z).sum::<f64>() / all.len() as f64;
+                0.7 * all[0].z + 0.3 * top_mean
+            };
+            (
+                article_id,
+                InterestMatch {
+                    score,
+                    top1_cos,
+                    top_interests: all,
+                },
+            )
+        })
+        .collect()
+}
+
+/// Every cheap signal for the eligible set, normalized and blended (§9, §12.2,
+/// §12.4). Pure: the preference state is already loaded.
+pub fn compute(
+    articles: &[Article],
+    article_embeddings: &HashMap<ArticleId, Vec<f32>>,
+    interest_embeddings: &HashMap<String, Vec<f32>>,
+    preference: &PreferenceState,
+    ranking: &RankingConfig,
+) -> HashMap<ArticleId, Signals> {
+    let interests = interest_matches(article_embeddings, interest_embeddings);
+    let mut all = articles
+        .iter()
+        .map(|article| {
+            let mut signals = Signals::baseline(article);
+            signals.knn_gate = preference.knn_gate;
+            signals.feed_gate = preference.feed_gate;
+            if let Some(matched) = interests.get(&article.id) {
+                signals.interest = Some(matched.score);
+                signals.interest_top1_cos = Some(matched.top1_cos);
+                signals.top_interests = matched.top_interests.clone();
+            }
+            if let Some(embedding) = article_embeddings.get(&article.id) {
+                let (knn, neighbours) = preference.knn(embedding, ranking);
+                signals.knn = knn;
+                signals.neighbours = neighbours;
+            }
+            signals.feed = preference.feed(article);
+            if preference.knn_gate > 0.0 {
+                signals.notes.push(format!(
+                    "knn gate {:.2} (n={} rated with embeddings)",
+                    preference.knn_gate,
+                    preference.examples.len()
+                ));
+            }
+            signals
+        })
+        .collect::<Vec<_>>();
+
+    normalize(&mut all.iter_mut().collect::<Vec<_>>());
+    for signals in &mut all {
+        preliminary_blend(signals, &ranking.weights.preliminary);
+    }
+    articles.iter().map(|article| article.id).zip(all).collect()
+}
+
+/// [`compute`] with the preference state loaded from the database.
+pub async fn compute_all(
+    db: &Db,
+    articles: &[Article],
+    article_embeddings: &HashMap<ArticleId, Vec<f32>>,
+    interest_embeddings: &HashMap<String, Vec<f32>>,
+    voyage: &VoyageConfig,
+    ranking: &RankingConfig,
+    now: Timestamp,
+) -> anyhow::Result<(HashMap<ArticleId, Signals>, PreferenceSummary)> {
+    let preference = PreferenceState::load(db, voyage, ranking, now).await?;
+    preference.log(ranking);
+    Ok((
+        compute(
+            articles,
+            article_embeddings,
+            interest_embeddings,
+            &preference,
+            ranking,
+        ),
+        preference.summary(),
+    ))
+}
+
+/// Mid-rank percentiles over the present values of each signal (§12.2).
+///
+/// `p(x) = (count_below + (count_equal + 1) / 2) / n_present`; fewer than two
+/// present values or all-equal values give 0.5. Article id never breaks ties.
+pub fn normalize(signals: &mut [&mut Signals]) {
+    for name in PERCENTILE_SIGNALS {
+        let mut values = signals
+            .iter()
+            .filter_map(|signal| signal.raw(name))
+            .collect::<Vec<_>>();
+        if values.is_empty() {
+            continue;
+        }
+        values.sort_by(f64::total_cmp);
+        let n = values.len() as f64;
+        let constant = values.len() < 2 || values.first() == values.last();
+        for signal in signals.iter_mut() {
+            let Some(value) = signal.raw(name) else {
+                continue;
+            };
+            let percentile = if constant {
+                0.5
+            } else {
+                let below = values.partition_point(|other| *other < value);
+                let equal = values.partition_point(|other| *other <= value) - below;
+                (below as f64 + (equal as f64 + 1.0) / 2.0) / n
+            };
+            signal.norm.insert(name.to_string(), percentile);
+        }
+    }
+}
+
+/// The preliminary blend of §12.4 on a 0–100 scale: present-and-active
+/// signals only, learned weights multiplied by their gate, renormalized to 1.
+pub fn preliminary_blend(signals: &mut Signals, configured: &PreliminaryWeights) -> Option<f64> {
+    let candidates = [
+        ("interest", configured.interest, 1.0),
+        ("knn", configured.knn, signals.knn_gate),
+        ("heuristic", configured.heuristic, 1.0),
+        ("feed", configured.feed, signals.feed_gate),
+        ("social", configured.social, 1.0),
+    ];
+    let active = candidates
+        .into_iter()
+        .filter_map(|(name, weight, gate)| {
+            let norm = *signals.norm.get(name)?;
+            let effective = weight * gate;
+            (effective > 0.0).then_some((name, effective, norm))
+        })
+        .collect::<Vec<_>>();
+    let total = active.iter().map(|(_, weight, _)| weight).sum::<f64>();
+    if total <= 0.0 {
+        signals.weights.clear();
+        signals.preliminary = None;
+        return None;
+    }
+    signals.weights = active
+        .iter()
+        .map(|(name, weight, _)| ((*name).to_string(), weight / total))
+        .collect();
+    let blend = active
+        .iter()
+        .map(|(_, weight, norm)| weight / total * norm)
+        .sum::<f64>()
+        * 100.0;
+    signals.preliminary = Some(blend);
+    Some(blend)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::types::{ExtractMethod, SourceRef};
+
+    fn ranking() -> RankingConfig {
+        RankingConfig::default()
+    }
+
+    fn unit(values: &[f32]) -> Vec<f32> {
+        let norm = values.iter().map(|v| v * v).sum::<f32>().sqrt();
+        values.iter().map(|v| v / norm).collect()
+    }
+
+    fn example(id: ArticleId, label: &str, value: f64, embedding: &[f32]) -> RatedExample {
+        RatedExample {
+            article_id: id,
+            label: label.into(),
+            title: format!("rated {id}"),
+            value,
+            decay: 1.0,
+            embedding: unit(embedding),
+            feeds: vec![id],
+        }
+    }
+
+    fn article(id: ArticleId, feeds: &[FeedId]) -> Article {
+        Article {
+            id,
+            canonical_url: format!("https://example.com/{id}"),
+            title: format!("Article {id}"),
+            best_entry_id: id,
+            content_html: String::new(),
+            word_count: 1000,
+            excerpt_only: false,
+            image_count: 0,
+            sources: feeds
+                .iter()
+                .map(|feed| SourceRef {
+                    entry_id: id,
+                    feed_id: *feed,
+                    feed_title: format!("feed {feed}"),
+                    category: None,
+                    kind: SourceKind::Feed,
+                })
+                .collect(),
+            first_seen: "2026-08-15T00:00:00Z".parse().unwrap(),
+            url: format!("https://example.com/{id}"),
+            author: None,
+            feed_id: feeds.first().copied().unwrap_or(0),
+            feed_title: String::new(),
+            category: None,
+            published_at: None,
+            comments_url: None,
+            image_urls: vec![],
+            social: vec![],
+            extract_method: ExtractMethod::Miniflux,
+        }
+    }
+
+    fn with_heuristic(value: Option<f64>) -> Signals {
+        Signals {
+            heuristic: value,
+            ..Signals::default()
+        }
+    }
+
+    // --- §9.1 interest z-scores ---
+
+    fn interest_fixture(n: usize) -> (HashMap<ArticleId, Vec<f32>>, HashMap<String, Vec<f32>>) {
+        // Article 1 sits on axis x; the rest sit near axis y with a tiny spread.
+        let mut articles = HashMap::new();
+        articles.insert(1, unit(&[1.0, 0.0, 0.0]));
+        for id in 2..=n as ArticleId {
+            articles.insert(id, unit(&[0.0, 1.0, 0.001 * id as f32]));
+        }
+        // "Broad" is about equally close to everything; "Specific" matches only article 1.
+        let mut interests = HashMap::new();
+        interests.insert("Broad".to_string(), unit(&[1.0, 1.0, 0.0]));
+        interests.insert("Specific".to_string(), unit(&[1.0, 0.0, 0.0]));
+        (articles, interests)
+    }
+
+    #[test]
+    fn specific_interest_with_one_strong_match_beats_a_broad_one() {
+        let (articles, interests) = interest_fixture(40);
+        let matched = interest_matches(&articles, &interests);
+        let strong = &matched[&1];
+        assert_eq!(strong.top_interests[0].name, "Specific");
+        assert!(
+            strong.top_interests[0].z > 3.0,
+            "z = {}",
+            strong.top_interests[0].z
+        );
+        let others = (2..=40)
+            .map(|id| matched[&id].score)
+            .fold(f64::NEG_INFINITY, f64::max);
+        assert!(strong.score > others + 2.0, "{} vs {others}", strong.score);
+        // Raw cosine would have called Broad a near-tie everywhere (≈0.707).
+        assert!((matched[&2].top1_cos - 0.707).abs() < 0.01);
+    }
+
+    #[test]
+    fn interest_falls_back_to_raw_cosine_under_thirty_articles() {
+        let (articles, interests) = interest_fixture(10);
+        let matched = interest_matches(&articles, &interests);
+        for (id, m) in &matched {
+            assert!(
+                (m.score - m.top1_cos).abs() < 1e-9,
+                "article {id} should use raw top-1"
+            );
+        }
+        assert!((matched[&2].score - 0.707).abs() < 0.01);
+    }
+
+    // --- §9.2 preference ---
+
+    #[test]
+    fn one_loved_article_gives_a_positive_knn_to_a_near_neighbour() {
+        let mut ranking = ranking();
+        ranking.knn_floor = 0;
+        ranking.knn_full = 1;
+        let state = PreferenceState::build(vec![example(1, "loved", 1.0, &[1.0, 0.0])], &ranking);
+        let (knn, neighbours) = state.knn(&unit(&[0.9, 0.1]), &ranking);
+        assert!(knn.unwrap() > 0.9);
+        assert_eq!(neighbours.len(), 1);
+        assert_eq!(neighbours[0].label, "loved");
+        let (far, _) = state.knn(&unit(&[0.0, 1.0]), &ranking);
+        assert!(far.unwrap().abs() < 1e-6);
+    }
+
+    #[test]
+    fn two_unrelated_loved_clusters_both_score_high() {
+        let mut ranking = ranking();
+        ranking.knn_floor = 0;
+        ranking.knn_full = 1;
+        ranking.neighbour_k = 2;
+        let state = PreferenceState::build(
+            vec![
+                example(1, "loved", 1.0, &[1.0, 0.0, 0.0]),
+                example(2, "loved", 1.0, &[0.98, 0.02, 0.0]),
+                example(3, "loved", 1.0, &[0.0, 1.0, 0.0]),
+                example(4, "loved", 1.0, &[0.0, 0.98, 0.02]),
+            ],
+            &ranking,
+        );
+        let (near_a, _) = state.knn(&unit(&[1.0, 0.0, 0.0]), &ranking);
+        let (near_b, _) = state.knn(&unit(&[0.0, 1.0, 0.0]), &ranking);
+        assert!(near_a.unwrap() > 0.95, "{near_a:?}");
+        assert!(near_b.unwrap() > 0.95, "{near_b:?}");
+        // A centroid would have put both at ~0.7.
+    }
+
+    #[test]
+    fn good_carries_a_third_of_loved() {
+        let loved = example(1, "loved", 1.0, &[1.0, 0.0]);
+        let good = example(2, "good", 0.35, &[1.0, 0.0]);
+        assert!((good.weight() / loved.weight() - 0.35).abs() < 1e-9);
+
+        // A mixed neighbourhood: the far example pulls the mean down by 0.35× as
+        // much weight when it is merely "good" as when it is "loved".
+        let mut ranking = ranking();
+        ranking.knn_floor = 0;
+        ranking.knn_full = 1;
+        let near = example(1, "loved", 1.0, &[1.0, 0.0]);
+        let candidate = unit(&[1.0, 0.0]);
+        let both_loved = PreferenceState::build(
+            vec![near.clone(), example(2, "loved", 1.0, &[0.0, 1.0])],
+            &ranking,
+        );
+        let one_good =
+            PreferenceState::build(vec![near, example(2, "good", 0.35, &[0.0, 1.0])], &ranking);
+        let pull_loved = 1.0 - both_loved.knn(&candidate, &ranking).0.unwrap();
+        let pull_good = 1.0 - one_good.knn(&candidate, &ranking).0.unwrap();
+        assert!(pull_good < pull_loved);
+        // Weighted means: 0.5 vs 1/1.35 → pulls 0.5 vs 0.35/1.35.
+        assert!((pull_good / pull_loved - 0.35 / 1.35 / 0.5).abs() < 1e-9);
+    }
+
+    #[test]
+    fn negatives_subtract_with_the_negative_coefficient() {
+        let mut ranking = ranking();
+        ranking.knn_floor = 0;
+        ranking.knn_full = 1;
+        let state =
+            PreferenceState::build(vec![example(1, "not_for_me", -1.0, &[1.0, 0.0])], &ranking);
+        let (knn, _) = state.knn(&unit(&[1.0, 0.0]), &ranking);
+        assert!((knn.unwrap() + ranking.negative_coefficient).abs() < 1e-9);
+    }
+
+    #[test]
+    fn decay_halves_at_the_half_life() {
+        assert!((decay(60.0, 60.0) - 0.5).abs() < 1e-12);
+        assert!((decay(0.0, 60.0) - 1.0).abs() < 1e-12);
+        assert!((decay(120.0, 60.0) - 0.25).abs() < 1e-12);
+    }
+
+    #[test]
+    fn gate_is_zero_below_floor_one_at_full_and_linear_between() {
+        assert_eq!(gate(0, 8, 25), 0.0);
+        assert_eq!(gate(8, 8, 25), 0.0);
+        assert_eq!(gate(25, 8, 25), 1.0);
+        assert_eq!(gate(100, 8, 25), 1.0);
+        assert!((gate(16, 8, 24) - 0.5).abs() < 1e-9);
+        assert!((gate(9, 8, 25) - 1.0 / 17.0).abs() < 1e-9);
+    }
+
+    #[test]
+    fn knn_is_absent_when_the_gate_is_closed() {
+        let ranking = ranking(); // knn_floor 8
+        let state = PreferenceState::build(vec![example(1, "loved", 1.0, &[1.0, 0.0])], &ranking);
+        assert_eq!(state.knn_gate, 0.0);
+        assert_eq!(state.knn(&unit(&[1.0, 0.0]), &ranking), (None, Vec::new()));
+    }
+
+    // --- §9.3 feed affinity ---
+
+    #[test]
+    fn feed_credit_sums_to_one_across_direct_feeds() {
+        let mut rated = example(1, "loved", 1.0, &[1.0, 0.0]);
+        rated.feeds = vec![10, 20, 30];
+        let state = PreferenceState::build(vec![rated], &ranking());
+        let total: f64 = [10, 20, 30]
+            .iter()
+            .map(|feed| state.feed_credit(*feed).unwrap().0)
+            .sum();
+        assert!((total - 1.0).abs() < 1e-9);
+        assert!((state.feed_credit(10).unwrap().0 - 1.0 / 3.0).abs() < 1e-9);
+    }
+
+    #[test]
+    fn feed_affinity_is_the_mean_over_rated_feeds() {
+        let mut ranking = ranking();
+        ranking.feed_floor = 0;
+        ranking.feed_full = 1;
+        let mut loved = example(1, "loved", 1.0, &[1.0, 0.0]);
+        loved.feeds = vec![10];
+        let mut down = example(2, "not_for_me", -1.0, &[1.0, 0.0]);
+        down.feeds = vec![20];
+        let state = PreferenceState::build(vec![loved, down], &ranking);
+        // feed 10: (1+1)/(1+0+2) = 2/3; feed 20: (0+1)/(0+1+2) = 1/3; unrated 99 ignored.
+        let both = state.feed(&article(7, &[10, 20, 99])).unwrap();
+        assert!((both - 0.5).abs() < 1e-9, "{both}");
+        let best = state.feed(&article(8, &[10])).unwrap();
+        assert!((best - 2.0 / 3.0).abs() < 1e-9);
+        assert_eq!(state.feed(&article(9, &[99])), None);
+    }
+
+    #[test]
+    fn feed_is_absent_when_the_gate_is_closed() {
+        let ranking = ranking(); // feed_floor 15
+        let mut loved = example(1, "loved", 1.0, &[1.0, 0.0]);
+        loved.feeds = vec![10];
+        let state = PreferenceState::build(vec![loved], &ranking);
+        assert_eq!(state.feed_gate, 0.0);
+        assert_eq!(state.feed(&article(7, &[10])), None);
+    }
+
+    #[test]
+    fn direct_feeds_fall_back_to_the_best_entry_feed() {
+        let mut a = article(1, &[]);
+        a.feed_id = 42;
+        assert_eq!(direct_feeds(&a), vec![42]);
+        assert_eq!(direct_feeds(&article(2, &[5, 3, 5])), vec![3, 5]);
+    }
+
+    // --- §12.2 normalization, §12.4 blend ---
+
+    #[test]
+    fn constant_signal_normalizes_to_half_for_everyone() {
+        let mut values = [with_heuristic(Some(7.0)), with_heuristic(Some(7.0))];
+        let mut refs = values.iter_mut().collect::<Vec<_>>();
+        normalize(&mut refs);
+        assert!(values.iter().all(|v| v.norm["heuristic"] == 0.5));
+        let mut single = [with_heuristic(Some(3.0))];
+        let mut refs = single.iter_mut().collect::<Vec<_>>();
+        normalize(&mut refs);
+        assert_eq!(single[0].norm["heuristic"], 0.5);
+    }
+
+    #[test]
+    fn ties_get_equal_percentiles_without_an_id_ramp() {
+        let mut values = (0..400)
+            .map(|_| with_heuristic(Some(0.0)))
+            .collect::<Vec<_>>();
+        let mut refs = values.iter_mut().collect::<Vec<_>>();
+        normalize(&mut refs);
+        assert!(values.iter().all(|v| v.norm["heuristic"] == 0.5));
+
+        let mut mixed = [
+            with_heuristic(Some(1.0)),
+            with_heuristic(Some(2.0)),
+            with_heuristic(Some(2.0)),
+            with_heuristic(Some(3.0)),
+        ];
+        let mut refs = mixed.iter_mut().collect::<Vec<_>>();
+        normalize(&mut refs);
+        assert_eq!(mixed[0].norm["heuristic"], 0.25);
+        assert_eq!(mixed[1].norm["heuristic"], 0.625);
+        assert_eq!(mixed[2].norm["heuristic"], 0.625);
+        assert_eq!(mixed[3].norm["heuristic"], 1.0);
+    }
+
+    #[test]
+    fn absent_values_do_not_shift_present_values() {
+        let mut values = [
+            with_heuristic(Some(1.0)),
+            with_heuristic(Some(2.0)),
+            with_heuristic(None),
+        ];
+        let mut refs = values.iter_mut().collect::<Vec<_>>();
+        normalize(&mut refs);
+        assert!(!values[2].norm.contains_key("heuristic"));
+        // n_present = 2: the absent third value does not widen the scale.
+        assert_eq!(values[0].norm["heuristic"], 0.5);
+        assert_eq!(values[1].norm["heuristic"], 1.0);
+    }
+
+    #[test]
+    fn effective_weights_sum_to_one_and_missing_signals_are_skipped() {
+        let mut signals = Signals {
+            interest: Some(1.0),
+            heuristic: Some(2.0),
+            norm: BTreeMap::from([("interest".into(), 0.8), ("heuristic".into(), 0.4)]),
+            ..Signals::default()
+        };
+        let blend = preliminary_blend(&mut signals, &PreliminaryWeights::default()).unwrap();
+        assert!((signals.weights.values().sum::<f64>() - 1.0).abs() < 1e-9);
+        assert!(!signals.weights.contains_key("knn"));
+        assert!(!signals.weights.contains_key("social"));
+        // 0.35/0.55 × 0.8 + 0.20/0.55 × 0.4 = 0.6545…
+        assert!((blend - 65.4545).abs() < 0.01, "{blend}");
+
+        let mut only_heuristic = Signals {
+            heuristic: Some(2.0),
+            norm: BTreeMap::from([("heuristic".into(), 0.4)]),
+            ..Signals::default()
+        };
+        let blend = preliminary_blend(&mut only_heuristic, &PreliminaryWeights::default());
+        assert!((blend.unwrap() - 40.0).abs() < 1e-9);
+        assert_eq!(only_heuristic.weights["heuristic"], 1.0);
+    }
+
+    #[test]
+    fn learned_weights_are_multiplied_by_their_gate() {
+        let mut signals = Signals {
+            knn: Some(0.5),
+            heuristic: Some(2.0),
+            knn_gate: 0.5,
+            norm: BTreeMap::from([("knn".into(), 1.0), ("heuristic".into(), 0.0)]),
+            ..Signals::default()
+        };
+        preliminary_blend(&mut signals, &PreliminaryWeights::default());
+        // knn 0.25 × 0.5 = 0.125 against heuristic 0.20.
+        assert!((signals.weights["knn"] - 0.125 / 0.325).abs() < 1e-9);
+    }
+
+    #[test]
+    fn compute_scores_every_article_and_leaves_ungated_signals_absent() {
+        let articles = vec![article(1, &[10]), article(2, &[20]), article(3, &[30])];
+        let mut embeddings = HashMap::new();
+        embeddings.insert(1, unit(&[1.0, 0.0]));
+        embeddings.insert(2, unit(&[0.0, 1.0]));
+        let mut interests = HashMap::new();
+        interests.insert("Axis".to_string(), unit(&[1.0, 0.0]));
+        let state = PreferenceState::build(vec![example(9, "loved", 1.0, &[1.0, 0.0])], &ranking());
+        let signals = compute(&articles, &embeddings, &interests, &state, &ranking());
+        assert_eq!(signals.len(), 3);
+        assert!(signals[&1].interest.is_some());
+        assert!(signals[&3].interest.is_none(), "no embedding → absent");
+        assert!(
+            signals
+                .values()
+                .all(|s| s.knn.is_none() && s.feed.is_none())
+        );
+        assert!(
+            signals
+                .values()
+                .all(|s| s.heuristic.is_some() && s.preliminary.is_some())
+        );
+    }
+}

src/curate/telemetry.rs

@@ -0,0 +1,962 @@
+//! Per-run candidate telemetry: the `candidate_runs` writer, `signals_json`,
+//! the `explain` command and feature retention (plan §7.4–7.5, §15.2, §16).
+//!
+//! One row per considered article per run says where it stopped and why. Rows
+//! are upserted on every stage transition with every column set (never
+//! `COALESCE`), so the last write for a run is the whole truth.
+
+use std::collections::BTreeMap;
+use std::fmt::Write as _;
+
+use jiff::Timestamp;
+use jiff::civil::Date;
+use serde::{Deserialize, Serialize};
+use sqlx::Row as _;
+
+use crate::curate::signals::{Neighbour, Signals, TopInterest};
+use crate::db::{Db, fmt_ts};
+use crate::types::ArticleId;
+
+/// The stage vocabulary of §7.4, in pipeline order.
+pub const STAGES: [&str; 7] = [
+    "excluded",
+    "eligible",
+    "triaged",
+    "admitted",
+    "assessed",
+    "shortlisted",
+    "selected",
+];
+
+/// Signal names rendered by `explain`, including the LLM ones steps 4–5 add.
+const RENDERED_SIGNALS: [&str; 8] = [
+    "interest",
+    "knn",
+    "feed",
+    "social",
+    "heuristic",
+    "triage",
+    "quality",
+    "fit",
+];
+
+/// One `candidate_runs` row (§7.4).
+#[derive(Debug, Clone)]
+pub struct CandidateRun<'a> {
+    pub run_id: i64,
+    pub article_id: ArticleId,
+    pub stage: &'a str,
+    pub excluded_reason: Option<&'a str>,
+    /// JSON array of retriever names, first = the one that admitted it.
+    pub admitted_by: Option<&'a str>,
+    pub signals_json: &'a str,
+    pub utility: Option<f64>,
+    pub rank_utility: Option<i64>,
+    pub cluster_id: Option<i64>,
+    pub cluster_rank: Option<i64>,
+    pub editor_why: Option<&'a str>,
+}
+
+/// Upsert one row, setting every column (§7.4).
+pub async fn write(db: &Db, row: &CandidateRun<'_>) -> Result<(), sqlx::Error> {
+    sqlx::query(
+        "INSERT INTO candidate_runs
+             (run_id, article_id, stage, excluded_reason, admitted_by, signals_json,
+              utility, rank_utility, cluster_id, cluster_rank, editor_why)
+         VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+         ON CONFLICT(run_id, article_id) DO UPDATE SET
+             stage = excluded.stage,
+             excluded_reason = excluded.excluded_reason,
+             admitted_by = excluded.admitted_by,
+             signals_json = excluded.signals_json,
+             utility = excluded.utility,
+             rank_utility = excluded.rank_utility,
+             cluster_id = excluded.cluster_id,
+             cluster_rank = excluded.cluster_rank,
+             editor_why = excluded.editor_why",
+    )
+    .bind(row.run_id)
+    .bind(row.article_id)
+    .bind(row.stage)
+    .bind(row.excluded_reason)
+    .bind(row.admitted_by)
+    .bind(row.signals_json)
+    .bind(row.utility)
+    .bind(row.rank_utility)
+    .bind(row.cluster_id)
+    .bind(row.cluster_rank)
+    .bind(row.editor_why)
+    .execute(db.pool())
+    .await?;
+    Ok(())
+}
+
+/// The thin row of a hygiene exclusion: keys, `stage = 'excluded'`, the reason
+/// and `signals_json = '{}'` (§8.1).
+pub async fn thin_excluded(
+    db: &Db,
+    run_id: i64,
+    article_id: ArticleId,
+    reason: &str,
+) -> Result<(), sqlx::Error> {
+    write(
+        db,
+        &CandidateRun {
+            run_id,
+            article_id,
+            stage: "excluded",
+            excluded_reason: Some(reason),
+            admitted_by: None,
+            signals_json: "{}",
+            utility: None,
+            rank_utility: None,
+            cluster_id: None,
+            cluster_rank: None,
+            editor_why: None,
+        },
+    )
+    .await
+}
+
+/// `signals_json` (§7.5). Missing signals are absent from `raw`/`norm` and
+/// `false` in `present`; `weights` are the effective weights.
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+pub struct SignalsJson {
+    pub v: i64,
+    #[serde(default)]
+    pub raw: BTreeMap<String, f64>,
+    #[serde(default)]
+    pub norm: BTreeMap<String, f64>,
+    #[serde(default)]
+    pub present: BTreeMap<String, bool>,
+    #[serde(default)]
+    pub weights: BTreeMap<String, f64>,
+    #[serde(default)]
+    pub top_interests: Vec<TopInterest>,
+    #[serde(default)]
+    pub neighbours: Vec<Neighbour>,
+    #[serde(default)]
+    pub exploration: bool,
+    #[serde(default)]
+    pub auto_include: bool,
+    #[serde(default)]
+    pub notes: Vec<String>,
+}
+
+impl SignalsJson {
+    /// The blend implied by the stored effective weights, 0–100.
+    pub fn blend(&self) -> Option<f64> {
+        let mut score = 0.0;
+        let mut any = false;
+        for (name, weight) in &self.weights {
+            if let Some(value) = self.norm.get(name) {
+                score += weight * value;
+                any = true;
+            }
+        }
+        any.then_some(score * 100.0)
+    }
+}
+
+/// Serialize the signals of §7.5 for one article.
+pub fn serialize_signals(signals: &Signals, auto_include: bool) -> String {
+    let mut raw = BTreeMap::new();
+    for name in [
+        "interest",
+        "interest_top1_cos",
+        "knn",
+        "feed",
+        "social",
+        "heuristic",
+    ] {
+        if let Some(value) = signals.raw(name) {
+            raw.insert(name.to_string(), value);
+        }
+    }
+    let present = RENDERED_SIGNALS
+        .into_iter()
+        .map(|name| (name.to_string(), signals.present(name)))
+        .collect();
+    serde_json::to_string(&SignalsJson {
+        v: 1,
+        raw,
+        norm: signals.norm.clone(),
+        present,
+        weights: signals.weights.clone(),
+        top_interests: signals.top_interests.clone(),
+        neighbours: signals.neighbours.clone(),
+        exploration: false,
+        auto_include,
+        notes: signals.notes.clone(),
+    })
+    .unwrap_or_else(|_| "{}".into())
+}
+
+// ---------------------------------------------------------------------------
+// `explain` (§15.2)
+// ---------------------------------------------------------------------------
+
+/// A `candidate_runs` row joined to its article title.
+#[derive(Debug, Clone)]
+pub struct ExplainRow {
+    pub run_id: i64,
+    pub article_id: ArticleId,
+    pub title: String,
+    pub stage: String,
+    pub excluded_reason: Option<String>,
+    pub admitted_by: Option<String>,
+    pub signals_json: String,
+    pub utility: Option<f64>,
+    pub rank_utility: Option<i64>,
+    pub cluster_id: Option<i64>,
+    pub cluster_rank: Option<i64>,
+    pub editor_why: Option<String>,
+}
+
+impl ExplainRow {
+    fn from_row(row: &sqlx::sqlite::SqliteRow) -> Self {
+        Self {
+            run_id: row.get("run_id"),
+            article_id: row.get("article_id"),
+            title: row.get("title"),
+            stage: row.get("stage"),
+            excluded_reason: row.get("excluded_reason"),
+            admitted_by: row.get("admitted_by"),
+            signals_json: row.get("signals_json"),
+            utility: row.get("utility"),
+            rank_utility: row.get("rank_utility"),
+            cluster_id: row.get("cluster_id"),
+            cluster_rank: row.get("cluster_rank"),
+            editor_why: row.get("editor_why"),
+        }
+    }
+
+    pub fn signals(&self) -> Option<SignalsJson> {
+        serde_json::from_str(&self.signals_json).ok()
+    }
+
+    /// Utility when step 5 has written it, else the preliminary blend.
+    pub fn score(&self) -> Option<f64> {
+        self.utility
+            .or_else(|| self.signals().and_then(|signals| signals.blend()))
+    }
+}
+
+/// The run `explain` reads: `--run-id` when given (and of that date), else the
+/// latest non-dry run of the date.
+pub async fn resolve_run(
+    db: &Db,
+    date: Date,
+    requested: Option<i64>,
+) -> Result<Option<i64>, sqlx::Error> {
+    let row = match requested {
+        Some(run_id) => {
+            sqlx::query("SELECT id FROM runs WHERE id = ? AND date = ?")
+                .bind(run_id)
+                .bind(date.to_string())
+                .fetch_optional(db.pool())
+                .await?
+        }
+        None => {
+            sqlx::query(
+                "SELECT id FROM runs WHERE date = ? AND status != 'dry_run'
+                 ORDER BY id DESC LIMIT 1",
+            )
+            .bind(date.to_string())
+            .fetch_optional(db.pool())
+            .await?
+        }
+    };
+    Ok(row.map(|row| row.get("id")))
+}
+
+pub async fn explain_row(
+    db: &Db,
+    run_id: i64,
+    article_id: ArticleId,
+) -> Result<Option<ExplainRow>, sqlx::Error> {
+    let row = sqlx::query(
+        "SELECT cr.run_id, cr.article_id, COALESCE(a.title, '') AS title,
+                cr.stage, cr.excluded_reason, cr.admitted_by, cr.signals_json,
+                cr.utility, cr.rank_utility, cr.cluster_id, cr.cluster_rank, cr.editor_why
+         FROM candidate_runs cr JOIN articles a ON a.id = cr.article_id
+         WHERE cr.run_id = ? AND cr.article_id = ?",
+    )
+    .bind(run_id)
+    .bind(article_id)
+    .fetch_optional(db.pool())
+    .await?;
+    Ok(row.as_ref().map(ExplainRow::from_row))
+}
+
+/// The top `limit` rows by utility-or-blend that were not selected (§15.2).
+pub async fn near_misses(
+    db: &Db,
+    run_id: i64,
+    limit: usize,
+) -> Result<Vec<ExplainRow>, sqlx::Error> {
+    let rows = sqlx::query(
+        "SELECT cr.run_id, cr.article_id, COALESCE(a.title, '') AS title,
+                cr.stage, cr.excluded_reason, cr.admitted_by, cr.signals_json,
+                cr.utility, cr.rank_utility, cr.cluster_id, cr.cluster_rank, cr.editor_why
+         FROM candidate_runs cr JOIN articles a ON a.id = cr.article_id
+         WHERE cr.run_id = ? AND cr.stage != 'selected' AND cr.stage != 'excluded'",
+    )
+    .bind(run_id)
+    .fetch_all(db.pool())
+    .await?;
+    let mut output = rows.iter().map(ExplainRow::from_row).collect::<Vec<_>>();
+    output.sort_by(|left, right| {
+        right
+            .score()
+            .unwrap_or(f64::NEG_INFINITY)
+            .total_cmp(&left.score().unwrap_or(f64::NEG_INFINITY))
+            .then_with(|| left.article_id.cmp(&right.article_id))
+    });
+    output.truncate(limit);
+    Ok(output)
+}
+
+fn fmt_opt(value: Option<f64>) -> String {
+    value
+        .map(|v| format!("{v:.3}"))
+        .unwrap_or_else(|| "—".into())
+}
+
+/// Render one persisted row the way §15.2 lists it.
+pub async fn render_explain(db: &Db, row: &ExplainRow) -> Result<String, sqlx::Error> {
+    let mut out = String::new();
+    let _ = writeln!(out, "article {}: {}", row.article_id, row.title);
+    let _ = write!(out, "run {} · stage: {}", row.run_id, row.stage);
+    if let Some(reason) = &row.excluded_reason {
+        let _ = write!(out, " · reason: {reason}");
+    }
+    let _ = writeln!(out);
+    if let Some(signals) = row.signals() {
+        let _ = writeln!(out, "signals (raw · norm · weight):");
+        for name in RENDERED_SIGNALS {
+            let present = signals.present.get(name).copied().unwrap_or(false);
+            if present {
+                let _ = writeln!(
+                    out,
+                    "  {name:<10} {:>8} · {:>6} · {:>6}",
+                    fmt_opt(signals.raw.get(name).copied()),
+                    fmt_opt(signals.norm.get(name).copied()),
+                    fmt_opt(signals.weights.get(name).copied()),
+                );
+            } else {
+                let _ = writeln!(out, "  {name:<10}   absent");
+            }
+        }
+        if let Some(blend) = signals.blend() {
+            let _ = writeln!(out, "preliminary blend: {blend:.1}");
+        }
+        if let Some(cos) = signals.raw.get("interest_top1_cos") {
+            let _ = writeln!(out, "interest top-1 cosine: {cos:.3}");
+        }
+        if !signals.top_interests.is_empty() {
+            let _ = writeln!(out, "top interests:");
+            for interest in &signals.top_interests {
+                let _ = writeln!(
+                    out,
+                    "  {} · z {:.2} · cos {:.3}",
+                    interest.name, interest.z, interest.cos
+                );
+            }
+        }
+        if !signals.neighbours.is_empty() {
+            let _ = writeln!(out, "nearest rated neighbours:");
+            for neighbour in &signals.neighbours {
+                let _ = writeln!(
+                    out,
+                    "  {} · cos {:.3} · article {} · {}",
+                    neighbour.label, neighbour.cos, neighbour.article_id, neighbour.title
+                );
+            }
+        }
+        if signals.exploration || signals.auto_include {
+            let _ = writeln!(
+                out,
+                "flags: exploration={} auto_include={}",
+                signals.exploration, signals.auto_include
+            );
+        }
+        for note in &signals.notes {
+            let _ = writeln!(out, "note: {note}");
+        }
+    }
+
+    let assessments = sqlx::query(
+        "SELECT stage, model, score, fit, kind, facets_json, rationale, category,
+                paywalled_guess, assessed_at
+         FROM article_assessments WHERE article_id = ? ORDER BY stage",
+    )
+    .bind(row.article_id)
+    .fetch_all(db.pool())
+    .await?;
+    if !assessments.is_empty() {
+        let _ = writeln!(out, "assessments:");
+        for assessment in assessments {
+            let _ = writeln!(
+                out,
+                "  {} · {} · score {} · fit {} · kind {} · category {} · paywalled={} · {}",
+                assessment.get::<String, _>("stage"),
+                assessment.get::<String, _>("model"),
+                fmt_opt(assessment.get::<Option<f64>, _>("score")),
+                fmt_opt(assessment.get::<Option<f64>, _>("fit")),
+                assessment
+                    .get::<Option<String>, _>("kind")
+                    .unwrap_or_else(|| "—".into()),
+                assessment
+                    .get::<Option<String>, _>("category")
+                    .unwrap_or_else(|| "—".into()),
+                assessment.get::<i64, _>("paywalled_guess") != 0,
+                assessment
+                    .get::<Option<String>, _>("rationale")
+                    .unwrap_or_default(),
+            );
+            if let Some(facets) = assessment.get::<Option<String>, _>("facets_json") {
+                let _ = writeln!(out, "    facets: {facets}");
+            }
+        }
+    }
+    if row.utility.is_some() || row.rank_utility.is_some() {
+        let _ = writeln!(
+            out,
+            "utility: {} · rank {}",
+            fmt_opt(row.utility),
+            row.rank_utility
+                .map(|r| r.to_string())
+                .unwrap_or_else(|| "—".into())
+        );
+    }
+    if let Some(cluster) = row.cluster_id {
+        let _ = writeln!(
+            out,
+            "cluster: {cluster} · rank {}",
+            row.cluster_rank
+                .map(|r| r.to_string())
+                .unwrap_or_else(|| "—".into())
+        );
+    }
+    if let Some(admitted_by) = &row.admitted_by {
+        let _ = writeln!(out, "admitted by: {admitted_by}");
+    }
+    if let Some(why) = &row.editor_why {
+        let _ = writeln!(out, "editor: {why}");
+    }
+    Ok(out)
+}
+
+/// What `explain` was asked about.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum ExplainTarget {
+    Article(ArticleId),
+    Url(String),
+}
+
+/// `explain --date D (--article ID | --url URL) [--run-id N]` as text (§15.2).
+pub async fn explain(
+    db: &Db,
+    date: Date,
+    run_id: Option<i64>,
+    target: &ExplainTarget,
+) -> anyhow::Result<String> {
+    let article_id = match target {
+        ExplainTarget::Article(id) => *id,
+        ExplainTarget::Url(url) => {
+            let canonical = crate::dedupe::canonical_url(url)
+                .ok_or_else(|| anyhow::anyhow!("invalid article URL {url:?}"))?;
+            match db.article_id_for_url(&canonical).await? {
+                Some(id) => id,
+                None => {
+                    return Ok(format!(
+                        "{canonical} was never ingested: it is not in `articles`, so this is a feed problem, not a ranking problem."
+                    ));
+                }
+            }
+        }
+    };
+    if db.get_article(article_id).await?.is_none() {
+        return Ok(format!(
+            "article {article_id} was never ingested: it is not in `articles`."
+        ));
+    }
+    let Some(run_id) = resolve_run(db, date, run_id).await? else {
+        return Ok(match run_id {
+            Some(id) => format!("run {id} is not a run for {date}"),
+            None => format!("no non-dry run recorded for {date}"),
+        });
+    };
+    match explain_row(db, run_id, article_id).await? {
+        Some(row) => Ok(render_explain(db, &row).await?),
+        None => Ok(format!(
+            "article {article_id} was not considered by run {run_id} for {date} (outside its ingest window, or telemetry pruned)."
+        )),
+    }
+}
+
+/// `explain --date D --near-misses [N]` as text (§15.2).
+pub async fn explain_near_misses(
+    db: &Db,
+    date: Date,
+    run_id: Option<i64>,
+    limit: usize,
+) -> anyhow::Result<String> {
+    let Some(run_id) = resolve_run(db, date, run_id).await? else {
+        return Ok(format!("no non-dry run recorded for {date}"));
+    };
+    let rows = near_misses(db, run_id, limit).await?;
+    let mut out = String::new();
+    let _ = writeln!(
+        out,
+        "run {run_id} · {date} · top {} not selected, by {}:",
+        rows.len(),
+        if rows.iter().any(|row| row.utility.is_some()) {
+            "utility"
+        } else {
+            "preliminary blend"
+        }
+    );
+    for (index, row) in rows.iter().enumerate() {
+        let reason = row
+            .excluded_reason
+            .as_deref()
+            .map(|reason| format!(", {reason}"))
+            .unwrap_or_default();
+        let _ = writeln!(
+            out,
+            "{:>3}. {:>6} · {} · {}{} · article {}",
+            index + 1,
+            row.score()
+                .map(|score| format!("{score:.1}"))
+                .unwrap_or_else(|| "—".into()),
+            row.title,
+            row.stage,
+            reason,
+            row.article_id
+        );
+    }
+    Ok(out)
+}
+
+// ---------------------------------------------------------------------------
+// `features prune` (§7.1, §7.4)
+// ---------------------------------------------------------------------------
+
+/// Delete `article_embeddings` for articles neither rated nor published that
+/// are older than `embedding_retention_days`, and `candidate_runs` rows whose
+/// run started more than `telemetry_retention_days` ago. Returns the counts.
+pub async fn prune(
+    db: &Db,
+    embedding_retention_days: i64,
+    telemetry_retention_days: i64,
+    now: Timestamp,
+) -> Result<(u64, u64), sqlx::Error> {
+    let cutoff = |days: i64| {
+        now.checked_sub(jiff::Span::new().hours(days.max(0).saturating_mul(24)))
+            .unwrap_or(Timestamp::UNIX_EPOCH)
+    };
+    let embeddings = sqlx::query(
+        "DELETE FROM article_embeddings
+         WHERE article_id IN (
+             SELECT ae.article_id
+             FROM article_embeddings ae JOIN articles a ON a.id = ae.article_id
+             WHERE a.first_seen < ?
+               AND NOT EXISTS (SELECT 1 FROM rating_events re WHERE re.article_id = ae.article_id)
+               AND NOT EXISTS (SELECT 1 FROM issue_articles ia WHERE ia.article_id = ae.article_id)
+         )",
+    )
+    .bind(fmt_ts(cutoff(embedding_retention_days)))
+    .execute(db.pool())
+    .await?
+    .rows_affected();
+
+    let telemetry = sqlx::query(
+        "DELETE FROM candidate_runs
+         WHERE run_id IN (SELECT id FROM runs WHERE started_at < ?)",
+    )
+    .bind(fmt_ts(cutoff(telemetry_retention_days)))
+    .execute(db.pool())
+    .await?
+    .rows_affected();
+    Ok((embeddings, telemetry))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::curate::embedding::encode_blob;
+
+    async fn db_with_articles(ids: &[ArticleId]) -> (tempfile::TempDir, Db) {
+        let dir = tempfile::tempdir().unwrap();
+        let db = Db::open_and_migrate(&dir.path().join("telemetry.db"))
+            .await
+            .unwrap();
+        for id in ids {
+            sqlx::query(
+                "INSERT INTO articles (id, canonical_url, title, first_seen)
+                 VALUES (?, ?, ?, '2026-08-15T00:00:00Z')",
+            )
+            .bind(id)
+            .bind(format!("https://example.com/{id}"))
+            .bind(format!("Article {id}"))
+            .execute(db.pool())
+            .await
+            .unwrap();
+        }
+        (dir, db)
+    }
+
+    fn date() -> Date {
+        "2026-09-02".parse().unwrap()
+    }
+
+    fn signals(heuristic: f64, norm: f64) -> Signals {
+        Signals {
+            interest: Some(1.2),
+            interest_top1_cos: Some(0.61),
+            heuristic: Some(heuristic),
+            norm: BTreeMap::from([("heuristic".into(), norm), ("interest".into(), 0.9)]),
+            weights: BTreeMap::from([
+                ("heuristic".into(), 0.2 / 0.55),
+                ("interest".into(), 0.35 / 0.55),
+            ]),
+            top_interests: vec![TopInterest {
+                name: "Gaussian Splatting".into(),
+                z: 3.4,
+                cos: 0.61,
+            }],
+            neighbours: vec![Neighbour {
+                article_id: 812,
+                label: "loved".into(),
+                cos: 0.71,
+                title: "A rated piece".into(),
+            }],
+            notes: vec!["knn gate 0.60 (n=14 rated with embeddings)".into()],
+            ..Signals::default()
+        }
+    }
+
+    #[test]
+    fn signals_json_follows_the_plan_shape() {
+        let json = serialize_signals(&signals(41.0, 0.55), false);
+        let parsed: serde_json::Value = serde_json::from_str(&json).unwrap();
+        assert_eq!(parsed["v"], 1);
+        assert_eq!(parsed["raw"]["heuristic"], 41.0);
+        assert_eq!(parsed["raw"]["interest_top1_cos"], 0.61);
+        assert_eq!(parsed["present"]["heuristic"], true);
+        assert_eq!(parsed["present"]["knn"], false);
+        assert_eq!(parsed["present"]["quality"], false);
+        assert!(parsed["raw"].get("knn").is_none());
+        assert!(parsed["norm"].get("knn").is_none());
+        assert_eq!(parsed["exploration"], false);
+        assert_eq!(parsed["auto_include"], false);
+        assert_eq!(parsed["top_interests"][0]["name"], "Gaussian Splatting");
+        assert_eq!(parsed["neighbours"][0]["article_id"], 812);
+        assert_eq!(
+            parsed["notes"][0],
+            "knn gate 0.60 (n=14 rated with embeddings)"
+        );
+        let typed: SignalsJson = serde_json::from_str(&json).unwrap();
+        let weights: f64 = typed.weights.values().sum();
+        assert!((weights - 1.0).abs() < 1e-9);
+        assert!(typed.blend().is_some());
+    }
+
+    #[tokio::test]
+    async fn rows_are_upserted_with_every_column_replaced() {
+        let (_dir, db) = db_with_articles(&[1]).await;
+        let run_id = db.start_run(date(), Timestamp::now()).await.unwrap();
+        write(
+            &db,
+            &CandidateRun {
+                run_id,
+                article_id: 1,
+                stage: "eligible",
+                excluded_reason: Some("not_admitted"),
+                admitted_by: None,
+                signals_json: "{}",
+                utility: Some(1.0),
+                rank_utility: None,
+                cluster_id: None,
+                cluster_rank: None,
+                editor_why: None,
+            },
+        )
+        .await
+        .unwrap();
+        write(
+            &db,
+            &CandidateRun {
+                run_id,
+                article_id: 1,
+                stage: "selected",
+                excluded_reason: None,
+                admitted_by: Some("[\"prefilter\"]"),
+                signals_json: "{\"v\":1}",
+                utility: None,
+                rank_utility: None,
+                cluster_id: None,
+                cluster_rank: None,
+                editor_why: Some("because"),
+            },
+        )
+        .await
+        .unwrap();
+        let row = explain_row(&db, run_id, 1).await.unwrap().unwrap();
+        assert_eq!(row.stage, "selected");
+        assert_eq!(row.excluded_reason, None, "no COALESCE");
+        assert_eq!(row.utility, None);
+        assert_eq!(row.admitted_by.as_deref(), Some("[\"prefilter\"]"));
+        assert_eq!(row.editor_why.as_deref(), Some("because"));
+        let count: i64 = sqlx::query_scalar("SELECT COUNT(*) FROM candidate_runs")
+            .fetch_one(db.pool())
+            .await
+            .unwrap();
+        assert_eq!(count, 1);
+    }
+
+    #[tokio::test]
+    async fn explain_renders_persisted_rows_and_reports_never_ingested() {
+        let (_dir, db) = db_with_articles(&[1, 2]).await;
+        let run_id = db.start_run(date(), Timestamp::now()).await.unwrap();
+        thin_excluded(&db, run_id, 2, "blocked").await.unwrap();
+        let json = serialize_signals(&signals(41.0, 0.55), true);
+        write(
+            &db,
+            &CandidateRun {
+                run_id,
+                article_id: 1,
+                stage: "shortlisted",
+                excluded_reason: Some("not_selected"),
+                admitted_by: Some("[\"prefilter\"]"),
+                signals_json: &json,
+                utility: None,
+                rank_utility: None,
+                cluster_id: None,
+                cluster_rank: None,
+                editor_why: None,
+            },
+        )
+        .await
+        .unwrap();
+        // A later dry run must not shadow the real one.
+        let dry = db.start_run(date(), Timestamp::now()).await.unwrap();
+        sqlx::query("UPDATE runs SET status = 'dry_run' WHERE id = ?")
+            .bind(dry)
+            .execute(db.pool())
+            .await
+            .unwrap();
+        assert_eq!(resolve_run(&db, date(), None).await.unwrap(), Some(run_id));
+        assert_eq!(
+            resolve_run(&db, date(), Some(dry)).await.unwrap(),
+            Some(dry)
+        );
+        assert_eq!(
+            resolve_run(&db, "2026-01-01".parse().unwrap(), Some(dry))
+                .await
+                .unwrap(),
+            None
+        );
+
+        let text = explain(&db, date(), None, &ExplainTarget::Article(1))
+            .await
+            .unwrap();
+        assert!(text.contains("article 1: Article 1"), "{text}");
+        assert!(
+            text.contains("stage: shortlisted · reason: not_selected"),
+            "{text}"
+        );
+        let squashed = text.split_whitespace().collect::<Vec<_>>().join(" ");
+        assert!(
+            squashed.contains("heuristic 41.000 · 0.550 · 0.364"),
+            "{text}"
+        );
+        assert!(squashed.contains("knn absent"), "{text}");
+        assert!(squashed.contains("quality absent"), "{text}");
+        assert!(
+            text.contains("Gaussian Splatting · z 3.40 · cos 0.610"),
+            "{text}"
+        );
+        assert!(
+            text.contains("loved · cos 0.710 · article 812 · A rated piece"),
+            "{text}"
+        );
+        assert!(text.contains("admitted by: [\"prefilter\"]"), "{text}");
+        assert!(text.contains("auto_include=true"), "{text}");
+        assert!(text.contains("preliminary blend:"), "{text}");
+        assert!(text.contains("note: knn gate"), "{text}");
+
+        let by_url = explain(
+            &db,
+            date(),
+            None,
+            &ExplainTarget::Url("https://example.com/1?utm_source=x".into()),
+        )
+        .await
+        .unwrap();
+        assert_eq!(by_url, text, "--url canonicalizes and finds the same row");
+
+        let thin = explain(&db, date(), None, &ExplainTarget::Article(2))
+            .await
+            .unwrap();
+        assert!(thin.contains("stage: excluded · reason: blocked"), "{thin}");
+
+        let missing = explain(
+            &db,
+            date(),
+            None,
+            &ExplainTarget::Url("https://nowhere.example/post".into()),
+        )
+        .await
+        .unwrap();
+        assert!(missing.contains("never ingested"), "{missing}");
+        let missing_id = explain(&db, date(), None, &ExplainTarget::Article(99))
+            .await
+            .unwrap();
+        assert!(missing_id.contains("never ingested"), "{missing_id}");
+
+        let no_run = explain(
+            &db,
+            "2026-01-01".parse().unwrap(),
+            None,
+            &ExplainTarget::Article(1),
+        )
+        .await
+        .unwrap();
+        assert!(no_run.contains("no non-dry run"), "{no_run}");
+        let not_considered = explain(&db, date(), Some(dry), &ExplainTarget::Article(1))
+            .await
+            .unwrap();
+        assert!(
+            not_considered.contains("was not considered by run"),
+            "{not_considered}"
+        );
+    }
+
+    #[tokio::test]
+    async fn near_misses_rank_by_blend_and_skip_selected_and_excluded() {
+        let (_dir, db) = db_with_articles(&[1, 2, 3, 4, 5]).await;
+        let run_id = db.start_run(date(), Timestamp::now()).await.unwrap();
+        let rows = [
+            (1, "selected", None, 0.9),
+            (2, "shortlisted", Some("not_selected"), 0.7),
+            (3, "eligible", Some("not_admitted"), 0.95),
+            (4, "shortlisted", Some("not_selected"), 0.1),
+        ];
+        for (id, stage, reason, norm) in rows {
+            let json = serialize_signals(&signals(10.0, norm), false);
+            write(
+                &db,
+                &CandidateRun {
+                    run_id,
+                    article_id: id,
+                    stage,
+                    excluded_reason: reason,
+                    admitted_by: None,
+                    signals_json: &json,
+                    utility: None,
+                    rank_utility: None,
+                    cluster_id: None,
+                    cluster_rank: None,
+                    editor_why: None,
+                },
+            )
+            .await
+            .unwrap();
+        }
+        thin_excluded(&db, run_id, 5, "published_before")
+            .await
+            .unwrap();
+        let misses = near_misses(&db, run_id, 10).await.unwrap();
+        assert_eq!(
+            misses.iter().map(|row| row.article_id).collect::<Vec<_>>(),
+            vec![3, 2, 4]
+        );
+        let text = explain_near_misses(&db, date(), None, 2).await.unwrap();
+        assert!(
+            text.contains("top 2 not selected, by preliminary blend"),
+            "{text}"
+        );
+        assert!(
+            text.contains("Article 3 · eligible, not_admitted"),
+            "{text}"
+        );
+        assert!(!text.contains("Article 4"), "{text}");
+    }
+
+    #[tokio::test]
+    async fn prune_respects_rated_and_published() {
+        let (_dir, db) = db_with_articles(&[1, 2, 3, 4]).await;
+        let now = Timestamp::now();
+        let old = fmt_ts(now - jiff::Span::new().hours(200 * 24));
+        sqlx::query("UPDATE articles SET first_seen = ? WHERE id IN (1, 2, 3)")
+            .bind(&old)
+            .execute(db.pool())
+            .await
+            .unwrap();
+        let blob = encode_blob(&[0.5, 0.5]).unwrap();
+        for id in 1..=4 {
+            sqlx::query(
+                "INSERT INTO article_embeddings
+                     (article_id, model, dimension, input_hash, embedding, created_at)
+                 VALUES (?, 'voyage-4-lite', 2, 'h', ?, ?)",
+            )
+            .bind(id)
+            .bind(&blob)
+            .bind(&old)
+            .execute(db.pool())
+            .await
+            .unwrap();
+        }
+        sqlx::query(
+            "INSERT INTO rating_events (article_id, kind, source, label, value, event_at)
+             VALUES (1, 'explicit', 'cli', 'loved', 1.0, ?)",
+        )
+        .bind(&old)
+        .execute(db.pool())
+        .await
+        .unwrap();
+        sqlx::query(
+            "INSERT INTO issues (date, issue_number, generated_at) VALUES ('2026-02-01', 1, ?);
+             INSERT INTO issue_articles (issue_date, article_id, section) VALUES ('2026-02-01', 2, 'Top Stories');",
+        )
+        .bind(&old)
+        .execute(db.pool())
+        .await
+        .unwrap();
+
+        let old_run = db
+            .start_run("2026-02-01".parse().unwrap(), now)
+            .await
+            .unwrap();
+        sqlx::query("UPDATE runs SET started_at = ? WHERE id = ?")
+            .bind(&old)
+            .bind(old_run)
+            .execute(db.pool())
+            .await
+            .unwrap();
+        let new_run = db.start_run(date(), now).await.unwrap();
+        thin_excluded(&db, old_run, 1, "blocked").await.unwrap();
+        thin_excluded(&db, new_run, 1, "blocked").await.unwrap();
+
+        let (embeddings, telemetry) = prune(&db, 120, 180, now).await.unwrap();
+        assert_eq!(
+            embeddings, 1,
+            "only the old, unrated, unpublished article 3"
+        );
+        assert_eq!(telemetry, 1, "only the old run's rows");
+        let remaining: Vec<i64> =
+            sqlx::query_scalar("SELECT article_id FROM article_embeddings ORDER BY article_id")
+                .fetch_all(db.pool())
+                .await
+                .unwrap();
+        assert_eq!(remaining, vec![1, 2, 4]);
+        let runs: Vec<i64> = sqlx::query_scalar("SELECT run_id FROM candidate_runs")
+            .fetch_all(db.pool())
+            .await
+            .unwrap();
+        assert_eq!(runs, vec![new_run]);
+    }
+}