style(bench): gate the rerank-sweep flag and helper on the embeddings feature

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>

crates/clawhdf5-agent/src/openclaw.rs

@@ -554,6 +554,7 @@ impl MemoryBackend for ClawhdfBackend {
                 timestamp: r.timestamp,
                 source_channel: r.source_channel.clone(),
                 raw_activation: r.activation,
+                relevance: r.score,
             })
             .collect();
 

crates/clawhdf5-agent/src/reranker.rs

@@ -4,8 +4,10 @@
 //! into a single composite score for each retrieved result.
 
 /// Configuration for the multi-factor re-ranker.
-#[derive(Debug, Clone)]
+#[derive(Debug, Clone, Copy)]
 pub struct ReRankConfig {
+    /// Weight applied to the retrieval score the candidate arrived with.
+    pub relevance_weight: f32,
     /// Weight applied to the temporal decay score (0.0–1.0).
     pub temporal_weight: f32,
     /// Weight applied to the source authority score (0.0–1.0).
@@ -20,6 +22,9 @@ pub struct ReRankConfig {
 impl Default for ReRankConfig {
     fn default() -> Self {
         Self {
+            // Relevance leads: the metadata signals break ties and nudge, they
+            // do not decide. See `BENCHMARKS.md`, "Recency discrimination".
+            relevance_weight: 1.0,
             temporal_weight: 0.3,
             authority_weight: 0.2,
             activation_weight: 0.5,
@@ -41,6 +46,8 @@ pub struct ReRankResult {
     pub authority_score: f32,
     /// Normalised Hebbian activation score in [0, 1].
     pub activation_score: f32,
+    /// The retrieval score carried through from the input.
+    pub relevance_score: f32,
 }
 
 /// Compute an exponential decay temporal score.
@@ -105,6 +112,15 @@ pub struct RerankInput {
     pub source_channel: String,
     /// Raw Hebbian activation weight for this entry.
     pub raw_activation: f32,
+    /// The retrieval score that put this entry in the candidate list.
+    ///
+    /// Re-ranking is meant to *adjust* the retriever's ordering with signals
+    /// it does not have, not to replace it. Without this the combined score
+    /// was made of recency, authority and activation alone, so a candidate
+    /// pool came back ordered by age with its relevance ordering discarded.
+    /// Callers with no meaningful score can pass the same value for every
+    /// entry, which reduces to the old behaviour.
+    pub relevance: f32,
 }
 
 /// Re-rank a list of retrieval results using multi-factor scoring.
@@ -138,7 +154,8 @@ pub fn rerank(
             let auth = source_authority_score(&inp.source_channel);
             let act = activation_score(inp.raw_activation);
 
-            let combined = config.temporal_weight * ts
+            let combined = config.relevance_weight * inp.relevance
+                + config.temporal_weight * ts
                 + config.authority_weight * auth
                 + config.activation_weight * act;
 
@@ -148,6 +165,7 @@ pub fn rerank(
                 temporal_score: ts,
                 authority_score: auth,
                 activation_score: act,
+                relevance_score: inp.relevance,
             }
         })
         .collect();
@@ -253,22 +271,51 @@ mod tests {
                 timestamp: 0.0, // very old
                 source_channel: "other".to_string(),
                 raw_activation: 0.1,
+                relevance: 0.0,
             },
             RerankInput {
                 index: 1,
                 timestamp: 86_400.0, // one day ago
                 source_channel: "conversation".to_string(),
                 raw_activation: 0.5,
+                relevance: 0.0,
             },
             RerankInput {
                 index: 2,
                 timestamp: 172_800.0, // "now"
                 source_channel: "user_correction".to_string(),
                 raw_activation: 1.0,
+                relevance: 0.0,
             },
         ]
     }
 
+    #[test]
+    fn relevance_leads_but_recency_breaks_near_ties() {
+        let entry = |index, timestamp, relevance| RerankInput {
+            index,
+            timestamp,
+            source_channel: "conversation".to_string(),
+            raw_activation: 1.0,
+            relevance,
+        };
+        let now = 10.0 * 86_400.0;
+        let config = ReRankConfig::default();
+
+        // A clearly better match wins despite being much older. Before
+        // `relevance` existed the combined score ignored it entirely, so this
+        // returned the newer, irrelevant entry.
+        let ranked = rerank(&[entry(0, 0.0, 1.0), entry(1, now, 0.1)], &config, now);
+        assert_eq!(ranked[0].index, 0, "{ranked:?}");
+
+        // Between near-equal matches, the newer one wins.
+        let ranked = rerank(&[entry(0, 0.0, 0.80), entry(1, now, 0.79)], &config, now);
+        assert_eq!(ranked[0].index, 1, "{ranked:?}");
+
+        // The breakdown carries the relevance through.
+        assert_eq!(ranked[0].relevance_score, 0.79);
+    }
+
     #[test]
     fn rerank_returns_all_entries() {
         let inputs = make_inputs();
@@ -302,6 +349,7 @@ mod tests {
     #[test]
     fn rerank_score_breakdown_matches_manual_calculation() {
         let config = ReRankConfig {
+            relevance_weight: 0.0,
             temporal_weight: 1.0,
             authority_weight: 0.0,
             activation_weight: 0.0,
@@ -312,6 +360,7 @@ mod tests {
             timestamp: 0.0,
             source_channel: "other".to_string(),
             raw_activation: 0.5,
+            relevance: 0.0,
         }];
         let now = 3600.0_f64; // exactly one half-life later
         let results = rerank(&inputs, &config, now);