feat(decide): memory rerank and paper triage on the decision tier

mission_memory::recall is two stages when a key is set: BM25 proposes 8
candidates, one Noul per candidate ('this earlier verdict is relevant to
the task') reorders them and drops those under 0.3, three are kept. BM25
measures keyword overlap, and a verdict about MICROVM.md shares words
with every task that names a file. Without a key the BM25 order stands.

continuous_research: topic_tags was written as [] on every manifest line
since the manifest existed. triage_papers asks, per harvested paper, a
Choice over the mission's topics (readable names, the arXiv query as the
description, 'none' offered) and a four-level relevance Score; the tags
(every topic ≥ 0.3) and {score, confidence} land on the line the agents
already read. Probe on PORTICO's abstract: relevance 3.0 at 1.0; topic
'none' 0.59 / verification 0.41 — true, the topic list has no
authority/sandboxing entry. Untriaged papers write the old empty line.

Co-Authored-By: Claude Opus 5 <[email protected]>

crates/cm-api/src/continuous_research.rs

@@ -128,32 +128,161 @@ pub fn write_manifest(
     checkout: &std::path::Path,
     papers: &[crate::papers::Paper],
     date: &str,
+    triage: &[PaperTriage],
 ) -> Result<std::path::PathBuf, String> {
     let rel = manifest_path(date);
     let abs = checkout.join(&rel);
     if let Some(parent) = abs.parent() {
         std::fs::create_dir_all(parent).map_err(|e| format!("create {}: {e}", parent.display()))?;
     }
-    let body = manifest_lines(papers, date);
+    let body = manifest_lines(papers, date, triage);
     std::fs::write(&abs, format!("{body}\n")).map_err(|e| format!("write {}: {e}", abs.display()))?;
     Ok(abs)
 }
 
+/// What the decision model said about one harvested paper. `topic_tags`
+/// was written as `[]` on every manifest line from the day the manifest
+/// existed — a slot the agents were told to read and nothing filled. This
+/// fills it: which of the mission's topics the paper belongs to (a Choice,
+/// every topic ≥ 0.3 kept, `none` when it fits none), and how much it
+/// matters to an agent platform (a four-level Score), so the ranking phase
+/// starts from a calibrated number rather than from the title alone.
+#[derive(Debug, Clone, serde::Serialize, Default)]
+pub struct PaperTriage {
+    pub topic_tags: Vec<String>,
+    /// 0 = unrelated … 3 = directly about what the platform does. `None`
+    /// when no triage ran (no key, or the call failed).
+    pub relevance: Option<f64>,
+    pub relevance_confidence: Option<f64>,
+}
+
+const RELEVANCE_LEVELS: [&str; 4] = [
+    "Unrelated to LLM agents, agent platforms, or their evaluation",
+    "Adjacent: language models or systems work an agent platform might one day draw on",
+    "Relevant: about agents, tools, memory, skills, judging, sandboxing, or multi-agent orchestration",
+    "Directly applicable: a method, measurement, or failure mode a platform running autonomous coding and research agents should act on",
+];
+
+/// Triage every harvested paper in one call each. Best-effort: a missing key
+/// or a failed call leaves that paper's tags empty and relevance `None`, the
+/// state the manifest has always been in.
+pub async fn triage_papers(
+    papers: &[crate::papers::Paper],
+    topics: &[String],
+) -> Vec<PaperTriage> {
+    use cm_decide::{Answer, Decider as _, Question};
+    let Some(jev) = cm_decide::jev::Jev::from_env() else {
+        return vec![PaperTriage::default(); papers.len()];
+    };
+    // Topics are arXiv query strings; the option NAME the model sees is the
+    // readable form (`all:"agent memory" AND all:"long-term"` → `agent memory
+    // long-term`), the value the query itself for precision.
+    let mut criteria: std::collections::BTreeMap<String, Option<String>> = topics
+        .iter()
+        .map(|t| (readable_topic(t), Some(t.clone())))
+        .collect();
+    criteria.insert("none".into(), Some("Fits none of the listed topics".into()));
+    let questions: std::collections::BTreeMap<String, Question> = [
+        (
+            "topic".to_string(),
+            Question::Choice {
+                instructions: "Which of these research topics is this paper about?".into(),
+                criteria,
+            },
+        ),
+        (
+            "relevance".to_string(),
+            Question::score(
+                "How relevant is this paper to a platform that runs autonomous LLM coding and research agents?",
+                RELEVANCE_LEVELS,
+            ),
+        ),
+    ]
+    .into_iter()
+    .collect();
+
+    let mut out = Vec::with_capacity(papers.len());
+    for p in papers {
+        let state = format!("Title: {}\n\nAbstract: {}", p.title, p.summary);
+        let decided = tokio::time::timeout(
+            std::time::Duration::from_secs(10),
+            jev.decide(&state, &questions),
+        )
+        .await;
+        let mut t = PaperTriage::default();
+        match decided {
+            Ok(Ok(d)) => {
+                if let Some(Answer::Choice { probabilities, .. }) = d.answers.get("topic") {
+                    let mut tags: Vec<(String, f64)> = probabilities
+                        .iter()
+                        .filter(|(k, p)| k.as_str() != "none" && **p >= 0.3)
+                        .map(|(k, p)| (k.clone(), *p))
+                        .collect();
+                    tags.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap_or(std::cmp::Ordering::Equal));
+                    t.topic_tags = tags.into_iter().map(|(k, _)| k).collect();
+                }
+                if let Some(Answer::Score { score, confidence, .. }) = d.answers.get("relevance") {
+                    t.relevance = Some((*score * 100.0).round() / 100.0);
+                    t.relevance_confidence = Some((*confidence * 100.0).round() / 100.0);
+                }
+            }
+            Ok(Err(e)) => eprintln!("continuous_research: triage of {} failed: {e}", p.arxiv_id),
+            Err(_) => eprintln!("continuous_research: triage of {} timed out", p.arxiv_id),
+        }
+        out.push(t);
+    }
+    let tagged = out.iter().filter(|t| !t.topic_tags.is_empty()).count();
+    eprintln!(
+        "continuous_research: triaged {} paper(s) with {}: {tagged} tagged, {} scored",
+        papers.len(),
+        jev.name(),
+        out.iter().filter(|t| t.relevance.is_some()).count()
+    );
+    out
+}
+
+/// `all:"agent memory" AND all:"long-term"` → `agent memory long-term`.
+fn readable_topic(query: &str) -> String {
+    let words: Vec<&str> = query
+        .split(|c: char| c == '"' || c.is_whitespace() || c == '(' || c == ')')
+        .filter(|w| !w.is_empty())
+        .filter(|w| !matches!(*w, "AND" | "OR" | "NOT"))
+        .map(|w| w.strip_prefix("all:").unwrap_or(w))
+        .map(|w| w.strip_prefix("ti:").unwrap_or(w))
+        .map(|w| w.strip_prefix("abs:").unwrap_or(w))
+        .filter(|w| !w.is_empty())
+        .collect();
+    words.join(" ")
+}
+
 /// The manifest lines for a set of freshly shelved papers.
 ///
 /// Shape matches what `templates/teams/continuous_research.toml` documents:
-/// `{ source, url, title, snippet, first_seen, topic_tags }`.
-pub fn manifest_lines(papers: &[crate::papers::Paper], first_seen: &str) -> String {
+/// `{ source, url, title, snippet, first_seen, topic_tags }`, plus
+/// `relevance` since 2026-09-21 (see [`PaperTriage`]). `triage` is
+/// positional with `papers`; shorter means the rest are untriaged.
+pub fn manifest_lines(
+    papers: &[crate::papers::Paper],
+    first_seen: &str,
+    triage: &[PaperTriage],
+) -> String {
     papers
         .iter()
-        .map(|p| {
+        .enumerate()
+        .map(|(i, p)| {
+            let t = triage.get(i).cloned().unwrap_or_default();
             json!({
                 "source": p.source_id(),
                 "url": format!("https://arxiv.org/abs/{}", p.arxiv_id),
                 "title": p.title,
                 "snippet": p.summary.chars().take(400).collect::<String>(),
                 "first_seen": first_seen,
-                "topic_tags": [],
+                "topic_tags": t.topic_tags,
+                "relevance": t.relevance.map(|r| json!({
+                    "score": r,
+                    "confidence": t.relevance_confidence,
+                    "scale": "0 unrelated … 3 directly applicable",
+                })),
             })
             .to_string()
         })
@@ -198,6 +327,18 @@ mod tests {
         }
     }
 
+    #[test]
+    fn arxiv_queries_become_readable_option_names() {
+        assert_eq!(
+            readable_topic(r#"all:"agent memory" AND all:"long-term""#),
+            "agent memory long-term"
+        );
+        assert_eq!(
+            readable_topic(r#"all:"agentic topology" OR all:"multi-agent topology""#),
+            "agentic topology multi-agent topology"
+        );
+    }
+
     #[test]
     fn the_date_stamp_is_zero_padded() {
         let d = today();
@@ -217,12 +358,25 @@ mod tests {
             published: "2026-08-17".into(),
             pdf_url: "https://arxiv.org/pdf/2401.12345".into(),
         };
-        let out = manifest_lines(std::slice::from_ref(&p), "2026-08-17");
+        let out = manifest_lines(std::slice::from_ref(&p), "2026-08-17", &[]);
         assert_eq!(out.lines().count(), 1);
         let v: serde_json::Value = serde_json::from_str(&out).expect("each line is JSON");
-        for key in ["source", "url", "title", "snippet", "first_seen", "topic_tags"] {
+        for key in ["source", "url", "title", "snippet", "first_seen", "topic_tags", "relevance"] {
             assert!(v.get(key).is_some(), "missing {key} in {v}");
         }
+        // Untriaged: the slot is there and empty, as it always was.
+        assert_eq!(v["topic_tags"], serde_json::json!([]));
+        assert!(v["relevance"].is_null());
+        // Triaged: the tags and the score land on the line.
+        let t = PaperTriage {
+            topic_tags: vec!["agent memory long-term".into()],
+            relevance: Some(2.4),
+            relevance_confidence: Some(0.7),
+        };
+        let out = manifest_lines(std::slice::from_ref(&p), "2026-08-17", std::slice::from_ref(&t));
+        let v: serde_json::Value = serde_json::from_str(&out).unwrap();
+        assert_eq!(v["topic_tags"][0], "agent memory long-term");
+        assert_eq!(v["relevance"]["score"], 2.4);
         assert_eq!(v["source"], "arxiv:2401.12345");
         assert!(
             v["snippet"].as_str().unwrap().chars().count() <= 400,

crates/cm-api/src/mission_memory.rs

@@ -27,6 +27,15 @@ use uuid::Uuid;
 /// tried" without becoming the prompt.
 pub const RECALL_K: usize = 3;
 
+/// How many BM25 candidates the reranker sees. Wider than `RECALL_K` so a
+/// relevant verdict that keyword overlap ranked fourth can still make the
+/// brief; narrow enough that one call stays one call.
+pub const CANDIDATES: usize = 8;
+
+/// Below this a candidate is dropped even if fewer than `RECALL_K` remain:
+/// a brief that carries an irrelevant verdict is worse than a shorter one.
+pub const RELEVANT_AT: f64 = 0.3;
+
 /// The heading the recalled lines go under. Named here because the scorer and
 /// the prompt-order tests read it back.
 pub const SECTION_HEADING: &str = "# What past missions on this repository learned";
@@ -112,18 +121,88 @@ fn remember_in(
 
 /// The past verdicts most relevant to `query` (the phase's task text).
 /// Empty when the repo has no brain yet, which is every repo's first mission.
-pub fn recall(repo_id: Uuid, query: &str) -> Vec<String> {
-    recall_in(&cm_runtime::brain::brain_dir(), repo_id, query)
+///
+/// Two stages when a decision model is configured: BM25 proposes
+/// `CANDIDATES`, one Noul per candidate — "is this past verdict relevant
+/// to the task?" — reorders them and drops the ones below `RELEVANT_AT`.
+/// Keyword overlap is what BM25 measures, and a verdict about MICROVM.md
+/// shares words with every task that mentions a file; the rerank is the
+/// vendor's own pattern and costs one ~200 ms call. Without a key the
+/// BM25 order stands, as before.
+pub async fn recall(repo_id: Uuid, query: &str) -> Vec<String> {
+    let candidates = recall_in(&cm_runtime::brain::brain_dir(), repo_id, query, CANDIDATES);
+    match cm_decide::jev::Jev::from_env() {
+        Some(jev) if candidates.len() > 1 => rerank(&jev, query, candidates).await,
+        _ => candidates.into_iter().take(RECALL_K).collect(),
+    }
 }
 
-fn recall_in(dir: &Path, repo_id: Uuid, query: &str) -> Vec<String> {
+async fn rerank(jev: &cm_decide::jev::Jev, query: &str, candidates: Vec<String>) -> Vec<String> {
+    use cm_decide::{Answer, Decider as _, Question};
+    let questions: std::collections::BTreeMap<String, Question> = candidates
+        .iter()
+        .enumerate()
+        .map(|(i, c)| {
+            (
+                format!("c{i}"),
+                Question::noul(format!(
+                    "This earlier judge verdict is relevant to the task and would help an \
+                     agent doing it: {c}"
+                )),
+            )
+        })
+        .collect();
+    let decided = tokio::time::timeout(
+        std::time::Duration::from_secs(10),
+        jev.decide(query, &questions),
+    )
+    .await;
+    let decision = match decided {
+        Ok(Ok(d)) => d,
+        Ok(Err(e)) => {
+            eprintln!("mission_memory: rerank failed ({e}); keeping the BM25 order");
+            return candidates.into_iter().take(RECALL_K).collect();
+        }
+        Err(_) => {
+            eprintln!("mission_memory: rerank timed out; keeping the BM25 order");
+            return candidates.into_iter().take(RECALL_K).collect();
+        }
+    };
+    let scored: Vec<(String, f64)> = candidates
+        .into_iter()
+        .enumerate()
+        .map(|(i, c)| {
+            let p = match decision.answers.get(&format!("c{i}")) {
+                Some(Answer::Noul { noul }) => *noul,
+                _ => 0.0,
+            };
+            (c, p)
+        })
+        .collect();
+    let kept: Vec<String> = cm_decide::patterns::rerank(scored)
+        .into_iter()
+        .filter(|(_, p)| *p >= RELEVANT_AT)
+        .take(RECALL_K)
+        .map(|(c, _)| c)
+        .collect();
+    eprintln!(
+        "mission_memory: reranked {} candidate(s) with {}, kept {} ({} ms)",
+        questions.len(),
+        decision.model,
+        kept.len(),
+        decision.latency.as_millis()
+    );
+    kept
+}
+
+fn recall_in(dir: &Path, repo_id: Uuid, query: &str, k: usize) -> Vec<String> {
     let path = brain_path(dir, repo_id);
     if !path.exists() {
         return Vec::new();
     }
     match ClawBrain::open_or_create(&path, &format!("repo_{repo_id}")) {
         Ok(brain) => brain
-            .recall(query, RECALL_K)
+            .recall(query, k)
             .into_iter()
             // `remember` stores "role: text"; the role is ours and not a lesson.
             .map(|m| m.strip_prefix("judge: ").map(str::to_string).unwrap_or(m))
@@ -227,13 +306,13 @@ mod tests {
             None,
         );
         remember_in(&dir, repo, Uuid::now_v7(), "benchmark", "a baseline is recorded", &v);
-        let got = recall_in(&dir, repo, "record a performance baseline for the hot path");
+        let got = recall_in(&dir, repo, "record a performance baseline for the hot path", RECALL_K);
         assert_eq!(got.len(), 1, "{got:?}");
         assert!(got[0].starts_with("MET — benchmark phase"), "{}", got[0]);
         assert!(!got[0].starts_with("judge: "));
         // A repo with no history recalls nothing and creates no file.
         let other = Uuid::now_v7();
-        assert!(recall_in(&dir, other, "anything").is_empty());
+        assert!(recall_in(&dir, other, "anything", RECALL_K).is_empty());
         assert!(!brain_path(&dir, other).exists());
         let _ = std::fs::remove_dir_all(&dir);
     }

crates/cm-api/src/mission_orchestrator.rs

@@ -129,7 +129,12 @@ pub async fn on_launch(
             // rightly refuses the branch. See `write_manifest`.
             if mission.template_kind == crate::continuous_research::TEMPLATE_KIND {
                 let date = crate::continuous_research::today();
-                match crate::continuous_research::write_manifest(&path, &harvested, &date) {
+                // Tag and score each paper before the agents see the list;
+                // an untriaged manifest (no key) is the old, empty-tags one.
+                let topics = crate::continuous_research::topics_for(&mission.config);
+                let triage =
+                    crate::continuous_research::triage_papers(&harvested, &topics).await;
+                match crate::continuous_research::write_manifest(&path, &harvested, &date, &triage) {
                     Ok(at) => eprintln!(
                         "mission_orchestrator: wrote {} paper(s) to {}",
                         harvested.len(),

crates/cm-api/src/phase_runner.rs

@@ -1254,9 +1254,9 @@ async fn launch_phase(
     // Appended to the task rather than the identity so all three executors
     // carry it: the task text is the one thing they share.
     let task = match p.repo_id {
-        Some(repo) => match crate::mission_memory::section(&crate::mission_memory::recall(
-            repo, &task,
-        )) {
+        Some(repo) => match crate::mission_memory::section(
+            &crate::mission_memory::recall(repo, &task).await,
+        ) {
             Some(memory) => {
                 eprintln!(
                     "phase_runner: phase {phase_id} brief carries project memory for repo {repo}"