chore: update beads state and autocorrect registry for CLI-IMP

Wire hybrid search (FTS5 + vector + RRF) to CLI search command.
Enhance robot-docs with quick_start guide and example_output.
Fill data gaps in issue detail (references, note counts, closed_at).
Add lore drift command for discussion divergence detection.
Rewrite agent skills to mandate lore for reads, glab for writes.

Closes: bd-1ksf, bd-91j1, bd-2g50, bd-1cjx, bd-kvij

.beads/last-touched

@@ -1 +1 @@
-bd-1cjx
+bd-1ksf

AGENTS.md

@@ -16,31 +16,42 @@ If I tell you to do something, even if it goes against what follows below, YOU M
 
 ## Version Control: jj-First (CRITICAL)
 
-**ALWAYS prefer jj (Jujutsu) over git for all VCS operations.** This is a colocated repo with both `.jj/` and `.git/`. When instructed to use git by anything — even later in this file — use the best jj replacement commands instead. Only fall back to raw `git` for things jj cannot do (hooks, LFS, submodules, `gh` CLI interop).
+**ALWAYS prefer jj (Jujutsu) over git for VCS mutations** (commit, describe, rebase, push, bookmark, undo). This is a colocated repo with both `.jj/` and `.git/`. Only fall back to raw `git` for things jj cannot do (hooks, LFS, submodules, `gh` CLI interop).
+
+**Exception — read-only inspection:** Use `git status`, `git diff`, `git log` instead of their jj equivalents. In a colocated repo these see accurate data, and unlike jj, they don't create operations that cause divergences when multiple agents run concurrently. See "Parallel Agent VCS Protocol" below.
 
 See `~/.claude/rules/jj-vcs/` for the full command reference, translation table, revsets, patterns, and recovery recipes.
 
-### Multi-Agent VCS Protocol (CRITICAL)
+### Parallel Agent VCS Protocol (CRITICAL)
 
-**In a multi-agent session, ONLY THE TEAM LEAD performs jj/git operations.** Worker agents MUST NEVER run `jj` or `git` commands.
+Multiple agents often run concurrently in separate terminal panes, sharing the same repo directory. This requires care because jj's auto-snapshot creates operations on EVERY command — even read-only ones like `jj status`. Concurrent jj commands fork from the same parent operation and create **divergent changes**.
 
-**Why:** jj has a single working copy (`@`) per workspace. Every `jj` command — even read-only ones like `jj status` — triggers a working copy snapshot recorded as an operation. When two agents run `jj` commands concurrently, both operations fork from the same parent operation and both rewrite `@`. jj detects this as a **divergent change**: same change ID, two different commits. Resolving divergences requires manual intervention and risks losing work.
+**The rule: use git for reads, jj for writes.**
 
-**Rules for worker agents:**
+In a colocated repo, git reads see accurate data because jj keeps `.git/` in sync.
 
-- Edit files only via Edit/Write tools — NEVER run `jj`, `git`, or any shell command that triggers jj
-- If you need VCS info (status, diff, log), message the team lead
-- Do NOT run "Landing the Plane" — the lead handles all VCS for the team
-- Treat all file changes on disk as your own (other agents' edits are normal)
+| Operation | Use | Why |
+|-----------|-----|-----|
+| Check status | `git status` | No jj operation created |
+| View diff | `git diff` | No jj operation created |
+| Browse history | `git log` | No jj operation created |
+| Commit work | `jj commit -m "msg"` | jj mutation (better UX) |
+| Update description | `jj describe -m "msg"` | jj mutation |
+| Rebase | `jj rebase -d trunk()` | jj mutation |
+| Push | `jj git push -b <name>` | jj mutation |
+| Manage bookmarks | `jj bookmark set ...` | jj mutation |
+| Undo a mistake | `jj undo` | jj mutation |
 
-**Rules for the team lead:**
+**NEVER run `jj status`, `jj diff`, `jj log`, or `jj show` when other agents may be active** — these trigger snapshots that cause divergences.
 
-- You are the sole VCS operator — all commits, pushes, and rebases go through you
-- Run `jj status` / `jj diff` to review all agents' work before committing
-- Use `jj split` to separate different agents' work into distinct commits if needed
-- Follow "Landing the Plane" when ending the session
+**If using Claude Code's built-in agent teams:** Only the team lead runs ANY VCS commands (git or jj). Workers only edit files via Edit/Write tools and do NOT run "Landing the Plane".
 
-**Solo sessions:** When you are the only agent, you handle VCS yourself normally.
+**Resolving divergences if they occur:**
+
+```bash
+jj log -r 'divergent()'              # Find divergent changes
+jj abandon <unwanted-commit-id>      # Keep the version you want
+```
 
 ---
 
@@ -776,6 +787,21 @@ lore -J mrs --fields iid,title,state,draft,labels  # Custom field list
 - Use `lore robot-docs` for response schema discovery
 - The `-p` flag supports fuzzy project matching (suffix and substring)
 
+---
+
+## Read/Write Split: lore vs glab
+
+| Operation | Tool | Why |
+|-----------|------|-----|
+| List issues/MRs | lore | Richer: includes status, discussions, closing MRs |
+| View issue/MR detail | lore | Pre-joined discussions, work-item status |
+| Search across entities | lore | FTS5 + vector hybrid search |
+| Expert/workload analysis | lore | who command — no glab equivalent |
+| Timeline reconstruction | lore | Chronological narrative — no glab equivalent |
+| Create/update/close | glab | Write operations |
+| Approve/merge MR | glab | Write operations |
+| CI/CD pipelines | glab | Not in lore scope |
+
 ````markdown
 ## UBS Quick Reference for AI Agents
 

migrations/023_issue_detail_fields.sql

@@ -0,0 +1,5 @@
+ALTER TABLE issues ADD COLUMN closed_at TEXT;
+ALTER TABLE issues ADD COLUMN confidential INTEGER NOT NULL DEFAULT 0;
+
+INSERT INTO schema_version (version, applied_at, description)
+VALUES (23, strftime('%s', 'now') * 1000, 'Add closed_at and confidential to issues');

src/cli/autocorrect.rs

@@ -185,6 +185,7 @@ const COMMAND_FLAGS: &[(&str, &[&str])] = &[
             "--no-detail",
         ],
     ),
+    ("drift", &["--threshold", "--project"]),
     (
         "init",
         &[

src/cli/commands/drift.rs

@@ -0,0 +1,642 @@
+use std::collections::HashMap;
+use std::sync::LazyLock;
+
+use console::style;
+use regex::Regex;
+use serde::Serialize;
+
+use crate::cli::robot::RobotMeta;
+use crate::core::config::Config;
+use crate::core::db::create_connection;
+use crate::core::error::{LoreError, Result};
+use crate::core::paths::get_db_path;
+use crate::core::project::resolve_project;
+use crate::core::time::ms_to_iso;
+use crate::embedding::ollama::{OllamaClient, OllamaConfig};
+use crate::embedding::similarity::cosine_similarity;
+
+const BATCH_SIZE: usize = 32;
+const WINDOW_SIZE: usize = 3;
+const MIN_DESCRIPTION_LEN: usize = 20;
+const MAX_NOTES: i64 = 200;
+const TOP_TOPICS: usize = 3;
+
+// ---------------------------------------------------------------------------
+// Response types
+// ---------------------------------------------------------------------------
+
+#[derive(Debug, Serialize)]
+pub struct DriftResponse {
+    pub entity: DriftEntity,
+    pub drift_detected: bool,
+    pub threshold: f32,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub drift_point: Option<DriftPoint>,
+    pub drift_topics: Vec<String>,
+    pub similarity_curve: Vec<SimilarityPoint>,
+    pub recommendation: String,
+}
+
+#[derive(Debug, Serialize)]
+pub struct DriftEntity {
+    pub entity_type: String,
+    pub iid: i64,
+    pub title: String,
+}
+
+#[derive(Debug, Serialize)]
+pub struct DriftPoint {
+    pub note_index: usize,
+    pub note_id: i64,
+    pub author: String,
+    pub created_at: String,
+    pub similarity: f32,
+}
+
+#[derive(Debug, Serialize)]
+pub struct SimilarityPoint {
+    pub note_index: usize,
+    pub similarity: f32,
+    pub author: String,
+    pub created_at: String,
+}
+
+// ---------------------------------------------------------------------------
+// Internal row types
+// ---------------------------------------------------------------------------
+
+struct IssueInfo {
+    id: i64,
+    iid: i64,
+    title: String,
+    description: Option<String>,
+}
+
+struct NoteRow {
+    id: i64,
+    body: String,
+    author_username: String,
+    created_at: i64,
+}
+
+// ---------------------------------------------------------------------------
+// Main entry point
+// ---------------------------------------------------------------------------
+
+pub async fn run_drift(
+    config: &Config,
+    entity_type: &str,
+    iid: i64,
+    threshold: f32,
+    project: Option<&str>,
+) -> Result<DriftResponse> {
+    if entity_type != "issues" {
+        return Err(LoreError::Other(
+            "drift currently supports 'issues' only".to_string(),
+        ));
+    }
+
+    let db_path = get_db_path(config.storage.db_path.as_deref());
+    let conn = create_connection(&db_path)?;
+
+    let issue = find_issue(&conn, iid, project)?;
+
+    let description = match &issue.description {
+        Some(d) if d.len() >= MIN_DESCRIPTION_LEN => d.clone(),
+        _ => {
+            return Ok(DriftResponse {
+                entity: DriftEntity {
+                    entity_type: entity_type.to_string(),
+                    iid: issue.iid,
+                    title: issue.title,
+                },
+                drift_detected: false,
+                threshold,
+                drift_point: None,
+                drift_topics: vec![],
+                similarity_curve: vec![],
+                recommendation: "Description too short for drift analysis.".to_string(),
+            });
+        }
+    };
+
+    let notes = fetch_notes(&conn, issue.id)?;
+
+    if notes.len() < WINDOW_SIZE {
+        return Ok(DriftResponse {
+            entity: DriftEntity {
+                entity_type: entity_type.to_string(),
+                iid: issue.iid,
+                title: issue.title,
+            },
+            drift_detected: false,
+            threshold,
+            drift_point: None,
+            drift_topics: vec![],
+            similarity_curve: vec![],
+            recommendation: format!(
+                "Only {} note(s) found; need at least {} for drift detection.",
+                notes.len(),
+                WINDOW_SIZE
+            ),
+        });
+    }
+
+    // Build texts to embed: description first, then each note body.
+    let mut texts: Vec<String> = Vec::with_capacity(1 + notes.len());
+    texts.push(description.clone());
+    for note in &notes {
+        texts.push(note.body.clone());
+    }
+
+    let embeddings = embed_texts(config, &texts).await?;
+
+    let desc_embedding = &embeddings[0];
+    let note_embeddings = &embeddings[1..];
+
+    // Build similarity curve.
+    let similarity_curve: Vec<SimilarityPoint> = note_embeddings
+        .iter()
+        .enumerate()
+        .map(|(i, emb)| SimilarityPoint {
+            note_index: i,
+            similarity: cosine_similarity(desc_embedding, emb),
+            author: notes[i].author_username.clone(),
+            created_at: ms_to_iso(notes[i].created_at),
+        })
+        .collect();
+
+    // Detect drift via sliding window.
+    let (drift_detected, drift_point) = detect_drift(&similarity_curve, &notes, threshold);
+
+    // Extract drift topics.
+    let drift_topics = if drift_detected {
+        let drift_idx = drift_point.as_ref().map_or(0, |dp| dp.note_index);
+        extract_drift_topics(&description, &notes, drift_idx)
+    } else {
+        vec![]
+    };
+
+    let recommendation = if drift_detected {
+        let dp = drift_point.as_ref().unwrap();
+        format!(
+            "Discussion drifted at note {} by @{} (similarity {:.2}). Consider splitting into a new issue.",
+            dp.note_index, dp.author, dp.similarity
+        )
+    } else {
+        "Discussion remains on topic.".to_string()
+    };
+
+    Ok(DriftResponse {
+        entity: DriftEntity {
+            entity_type: entity_type.to_string(),
+            iid: issue.iid,
+            title: issue.title,
+        },
+        drift_detected,
+        threshold,
+        drift_point,
+        drift_topics,
+        similarity_curve,
+        recommendation,
+    })
+}
+
+// ---------------------------------------------------------------------------
+// DB helpers
+// ---------------------------------------------------------------------------
+
+fn find_issue(
+    conn: &rusqlite::Connection,
+    iid: i64,
+    project_filter: Option<&str>,
+) -> Result<IssueInfo> {
+    let (sql, params): (&str, Vec<Box<dyn rusqlite::ToSql>>) = match project_filter {
+        Some(project) => {
+            let project_id = resolve_project(conn, project)?;
+            (
+                "SELECT i.id, i.iid, i.title, i.description
+                 FROM issues i
+                 WHERE i.iid = ? AND i.project_id = ?",
+                vec![Box::new(iid), Box::new(project_id)],
+            )
+        }
+        None => (
+            "SELECT i.id, i.iid, i.title, i.description
+             FROM issues i
+             WHERE i.iid = ?",
+            vec![Box::new(iid)],
+        ),
+    };
+
+    let param_refs: Vec<&dyn rusqlite::ToSql> = params.iter().map(|p| p.as_ref()).collect();
+
+    let mut stmt = conn.prepare(sql)?;
+    let rows: Vec<IssueInfo> = stmt
+        .query_map(param_refs.as_slice(), |row| {
+            Ok(IssueInfo {
+                id: row.get(0)?,
+                iid: row.get(1)?,
+                title: row.get(2)?,
+                description: row.get(3)?,
+            })
+        })?
+        .collect::<std::result::Result<Vec<_>, _>>()?;
+
+    match rows.len() {
+        0 => Err(LoreError::NotFound(format!("Issue #{iid} not found"))),
+        1 => Ok(rows.into_iter().next().unwrap()),
+        _ => Err(LoreError::Ambiguous(format!(
+            "Issue #{iid} exists in multiple projects. Use --project to specify."
+        ))),
+    }
+}
+
+fn fetch_notes(conn: &rusqlite::Connection, issue_id: i64) -> Result<Vec<NoteRow>> {
+    let mut stmt = conn.prepare(
+        "SELECT n.id, n.body, n.author_username, n.created_at
+         FROM notes n
+         JOIN discussions d ON n.discussion_id = d.id
+         WHERE d.issue_id = ?
+           AND n.is_system = 0
+           AND LENGTH(n.body) >= 20
+         ORDER BY n.created_at ASC
+         LIMIT ?",
+    )?;
+
+    let notes: Vec<NoteRow> = stmt
+        .query_map(rusqlite::params![issue_id, MAX_NOTES], |row| {
+            Ok(NoteRow {
+                id: row.get(0)?,
+                body: row.get(1)?,
+                author_username: row.get(2)?,
+                created_at: row.get(3)?,
+            })
+        })?
+        .collect::<std::result::Result<Vec<_>, _>>()?;
+
+    Ok(notes)
+}
+
+// ---------------------------------------------------------------------------
+// Embedding helper
+// ---------------------------------------------------------------------------
+
+async fn embed_texts(config: &Config, texts: &[String]) -> Result<Vec<Vec<f32>>> {
+    let ollama = OllamaClient::new(OllamaConfig {
+        base_url: config.embedding.base_url.clone(),
+        model: config.embedding.model.clone(),
+        timeout_secs: 60,
+    });
+
+    let mut all_embeddings: Vec<Vec<f32>> = Vec::with_capacity(texts.len());
+
+    for chunk in texts.chunks(BATCH_SIZE) {
+        let refs: Vec<&str> = chunk.iter().map(|s| s.as_str()).collect();
+        let batch_result = ollama.embed_batch(&refs).await?;
+        all_embeddings.extend(batch_result);
+    }
+
+    Ok(all_embeddings)
+}
+
+// ---------------------------------------------------------------------------
+// Drift detection
+// ---------------------------------------------------------------------------
+
+fn detect_drift(
+    curve: &[SimilarityPoint],
+    notes: &[NoteRow],
+    threshold: f32,
+) -> (bool, Option<DriftPoint>) {
+    if curve.len() < WINDOW_SIZE {
+        return (false, None);
+    }
+
+    for i in 0..=curve.len() - WINDOW_SIZE {
+        let window_avg: f32 = curve[i..i + WINDOW_SIZE]
+            .iter()
+            .map(|p| p.similarity)
+            .sum::<f32>()
+            / WINDOW_SIZE as f32;
+
+        if window_avg < threshold {
+            return (
+                true,
+                Some(DriftPoint {
+                    note_index: i,
+                    note_id: notes[i].id,
+                    author: notes[i].author_username.clone(),
+                    created_at: ms_to_iso(notes[i].created_at),
+                    similarity: curve[i].similarity,
+                }),
+            );
+        }
+    }
+
+    (false, None)
+}
+
+// ---------------------------------------------------------------------------
+// Topic extraction
+// ---------------------------------------------------------------------------
+
+static STOPWORDS: LazyLock<std::collections::HashSet<&'static str>> = LazyLock::new(|| {
+    [
+        "the", "a", "an", "is", "are", "was", "were", "be", "been", "being", "have", "has", "had",
+        "do", "does", "did", "will", "would", "could", "should", "may", "might", "shall", "can",
+        "need", "dare", "ought", "used", "to", "of", "in", "for", "on", "with", "at", "by", "from",
+        "as", "into", "through", "during", "before", "after", "above", "below", "between", "out",
+        "off", "over", "under", "again", "further", "then", "once", "here", "there", "when",
+        "where", "why", "how", "all", "each", "every", "both", "few", "more", "most", "other",
+        "some", "such", "no", "not", "only", "own", "same", "so", "than", "too", "very", "just",
+        "because", "but", "and", "or", "if", "while", "about", "up", "it", "its", "this", "that",
+        "these", "those", "i", "me", "my", "we", "our", "you", "your", "he", "him", "his", "she",
+        "her", "they", "them", "their", "what", "which", "who", "whom", "also", "like", "get",
+        "got", "think", "know", "see", "make", "go", "one", "two", "new", "way",
+    ]
+    .into_iter()
+    .collect()
+});
+
+fn tokenize(text: &str) -> Vec<String> {
+    let cleaned = strip_markdown(text);
+    cleaned
+        .split(|c: char| !c.is_alphanumeric() && c != '_')
+        .filter(|w| w.len() >= 3)
+        .map(|w| w.to_lowercase())
+        .filter(|w| !STOPWORDS.contains(w.as_str()))
+        .collect()
+}
+
+fn extract_drift_topics(description: &str, notes: &[NoteRow], drift_idx: usize) -> Vec<String> {
+    let desc_terms: std::collections::HashSet<String> = tokenize(description).into_iter().collect();
+
+    let mut freq: HashMap<String, usize> = HashMap::new();
+    for note in notes.iter().skip(drift_idx) {
+        for term in tokenize(&note.body) {
+            if !desc_terms.contains(&term) {
+                *freq.entry(term).or_insert(0) += 1;
+            }
+        }
+    }
+
+    let mut sorted: Vec<(String, usize)> = freq.into_iter().collect();
+    sorted.sort_by(|a, b| b.1.cmp(&a.1));
+
+    sorted
+        .into_iter()
+        .take(TOP_TOPICS)
+        .map(|(t, _)| t)
+        .collect()
+}
+
+// ---------------------------------------------------------------------------
+// Markdown stripping
+// ---------------------------------------------------------------------------
+
+static RE_FENCED_CODE: LazyLock<Regex> =
+    LazyLock::new(|| Regex::new(r"(?s)```[^\n]*\n.*?```").unwrap());
+static RE_INLINE_CODE: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"`[^`]+`").unwrap());
+static RE_LINK: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"\[([^\]]+)\]\([^)]+\)").unwrap());
+static RE_BLOCKQUOTE: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"(?m)^>\s?").unwrap());
+static RE_HTML_TAG: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"<[^>]+>").unwrap());
+
+fn strip_markdown(text: &str) -> String {
+    let text = RE_FENCED_CODE.replace_all(text, "");
+    let text = RE_INLINE_CODE.replace_all(&text, "");
+    let text = RE_LINK.replace_all(&text, "$1");
+    let text = RE_BLOCKQUOTE.replace_all(&text, "");
+    let text = RE_HTML_TAG.replace_all(&text, "");
+    text.into_owned()
+}
+
+// ---------------------------------------------------------------------------
+// Printers
+// ---------------------------------------------------------------------------
+
+pub fn print_drift_human(response: &DriftResponse) {
+    let header = format!(
+        "Drift Analysis: {} #{}",
+        response.entity.entity_type, response.entity.iid
+    );
+    println!("{}", style(&header).bold());
+    println!("{}", "-".repeat(header.len().min(60)));
+    println!("Title:     {}", response.entity.title);
+    println!("Threshold: {:.2}", response.threshold);
+    println!("Notes:     {}", response.similarity_curve.len());
+    println!();
+
+    if response.drift_detected {
+        println!("{}", style("DRIFT DETECTED").red().bold());
+        if let Some(dp) = &response.drift_point {
+            println!(
+                "  At note #{} by @{} ({}) - similarity {:.2}",
+                dp.note_index, dp.author, dp.created_at, dp.similarity
+            );
+        }
+        if !response.drift_topics.is_empty() {
+            println!("  Topics:  {}", response.drift_topics.join(", "));
+        }
+    } else {
+        println!("{}", style("No drift detected").green());
+    }
+
+    println!();
+    println!("{}", response.recommendation);
+
+    if !response.similarity_curve.is_empty() {
+        println!();
+        println!("{}", style("Similarity Curve:").bold());
+        for pt in &response.similarity_curve {
+            let bar_len = ((pt.similarity.max(0.0)) * 30.0) as usize;
+            let bar: String = "#".repeat(bar_len);
+            println!(
+                "  {:>3}  {:.2}  {}  @{}",
+                pt.note_index, pt.similarity, bar, pt.author
+            );
+        }
+    }
+}
+
+pub fn print_drift_json(response: &DriftResponse, elapsed_ms: u64) {
+    let meta = RobotMeta { elapsed_ms };
+    let output = serde_json::json!({
+        "ok": true,
+        "data": response,
+        "meta": meta,
+    });
+    match serde_json::to_string(&output) {
+        Ok(json) => println!("{json}"),
+        Err(e) => eprintln!("Error serializing to JSON: {e}"),
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_detect_drift_when_divergent() {
+        let notes: Vec<NoteRow> = (0..6)
+            .map(|i| NoteRow {
+                id: i as i64,
+                body: format!("note {i}"),
+                author_username: "user".to_string(),
+                created_at: 1000 + i as i64,
+            })
+            .collect();
+
+        let curve: Vec<SimilarityPoint> = [0.9, 0.85, 0.8, 0.25, 0.2, 0.15]
+            .iter()
+            .enumerate()
+            .map(|(i, &sim)| SimilarityPoint {
+                note_index: i,
+                similarity: sim,
+                author: "user".to_string(),
+                created_at: ms_to_iso(1000 + i as i64),
+            })
+            .collect();
+
+        let (detected, point) = detect_drift(&curve, &notes, 0.4);
+        assert!(detected);
+        assert!(point.is_some());
+    }
+
+    #[test]
+    fn test_no_drift_consistent() {
+        let notes: Vec<NoteRow> = (0..5)
+            .map(|i| NoteRow {
+                id: i as i64,
+                body: format!("note {i}"),
+                author_username: "user".to_string(),
+                created_at: 1000 + i as i64,
+            })
+            .collect();
+
+        let curve: Vec<SimilarityPoint> = [0.85, 0.8, 0.75, 0.7, 0.65]
+            .iter()
+            .enumerate()
+            .map(|(i, &sim)| SimilarityPoint {
+                note_index: i,
+                similarity: sim,
+                author: "user".to_string(),
+                created_at: ms_to_iso(1000 + i as i64),
+            })
+            .collect();
+
+        let (detected, _) = detect_drift(&curve, &notes, 0.4);
+        assert!(!detected);
+    }
+
+    #[test]
+    fn test_drift_point_is_first_divergent() {
+        let notes: Vec<NoteRow> = (0..5)
+            .map(|i| NoteRow {
+                id: (i * 10) as i64,
+                body: format!("note {i}"),
+                author_username: format!("user{i}"),
+                created_at: 1000 + i as i64,
+            })
+            .collect();
+
+        // Window of 3: indices [0,1,2] avg=0.83, [1,2,3] avg=0.55, [2,3,4] avg=0.23
+        let curve: Vec<SimilarityPoint> = [0.9, 0.8, 0.8, 0.05, 0.05]
+            .iter()
+            .enumerate()
+            .map(|(i, &sim)| SimilarityPoint {
+                note_index: i,
+                similarity: sim,
+                author: format!("user{i}"),
+                created_at: ms_to_iso(1000 + i as i64),
+            })
+            .collect();
+
+        let (detected, point) = detect_drift(&curve, &notes, 0.4);
+        assert!(detected);
+        let dp = point.unwrap();
+        // Window [2,3,4] avg = (0.8+0.05+0.05)/3 = 0.3 < 0.4
+        // But [1,2,3] avg = (0.8+0.8+0.05)/3 = 0.55 >= 0.4, so first failing is index 2
+        assert_eq!(dp.note_index, 2);
+        assert_eq!(dp.note_id, 20);
+    }
+
+    #[test]
+    fn test_extract_drift_topics_excludes_description_terms() {
+        let description = "We need to fix the authentication flow for login users";
+        let notes = vec![
+            NoteRow {
+                id: 1,
+                body: "The database migration script is broken and needs postgres update"
+                    .to_string(),
+                author_username: "dev".to_string(),
+                created_at: 1000,
+            },
+            NoteRow {
+                id: 2,
+                body: "The database connection pool also has migration issues with postgres"
+                    .to_string(),
+                author_username: "dev".to_string(),
+                created_at: 2000,
+            },
+        ];
+
+        let topics = extract_drift_topics(description, &notes, 0);
+        // "database", "migration", "postgres" should appear; "fix" should not (it's in description)
+        assert!(!topics.is_empty());
+        for t in &topics {
+            assert_ne!(t, "fix");
+            assert_ne!(t, "authentication");
+            assert_ne!(t, "login");
+        }
+    }
+
+    #[test]
+    fn test_strip_markdown_code_blocks() {
+        let input = "Before\n```rust\nfn main() {}\n```\nAfter";
+        let result = strip_markdown(input);
+        assert!(!result.contains("fn main"));
+        assert!(result.contains("Before"));
+        assert!(result.contains("After"));
+    }
+
+    #[test]
+    fn test_strip_markdown_preserves_text() {
+        let input = "Check [this link](https://example.com) and `inline code` for details";
+        let result = strip_markdown(input);
+        assert!(result.contains("this link"));
+        assert!(!result.contains("https://example.com"));
+        assert!(!result.contains("inline code"));
+        assert!(result.contains("details"));
+    }
+
+    #[test]
+    fn test_too_few_notes() {
+        let notes: Vec<NoteRow> = (0..2)
+            .map(|i| NoteRow {
+                id: i as i64,
+                body: format!("note {i}"),
+                author_username: "user".to_string(),
+                created_at: 1000 + i as i64,
+            })
+            .collect();
+
+        let curve: Vec<SimilarityPoint> = [0.1, 0.1]
+            .iter()
+            .enumerate()
+            .map(|(i, &sim)| SimilarityPoint {
+                note_index: i,
+                similarity: sim,
+                author: "user".to_string(),
+                created_at: ms_to_iso(1000 + i as i64),
+            })
+            .collect();
+
+        let (detected, _) = detect_drift(&curve, &notes, 0.4);
+        assert!(!detected);
+    }
+}

src/cli/commands/mod.rs

@@ -1,6 +1,7 @@
 pub mod auth_test;
 pub mod count;
 pub mod doctor;
+pub mod drift;
 pub mod embed;
 pub mod generate_docs;
 pub mod ingest;
@@ -20,6 +21,7 @@ pub use count::{
     run_count_events,
 };
 pub use doctor::{DoctorChecks, print_doctor_results, run_doctor};
+pub use drift::{DriftResponse, print_drift_human, print_drift_json, run_drift};
 pub use embed::{print_embed, print_embed_json, run_embed};
 pub use generate_docs::{print_generate_docs, print_generate_docs_json, run_generate_docs};
 pub use ingest::{

src/cli/commands/search.rs

@@ -1,3 +1,5 @@
+use std::collections::HashMap;
+
 use console::style;
 use serde::Serialize;
 
@@ -8,9 +10,10 @@ use crate::core::paths::get_db_path;
 use crate::core::project::resolve_project;
 use crate::core::time::{ms_to_iso, parse_since};
 use crate::documents::SourceType;
+use crate::embedding::ollama::{OllamaClient, OllamaConfig};
 use crate::search::{
-    FtsQueryMode, PathFilter, SearchFilters, apply_filters, get_result_snippet, rank_rrf,
-    search_fts,
+    FtsQueryMode, HybridResult, PathFilter, SearchFilters, SearchMode, get_result_snippet,
+    search_fts, search_hybrid,
 };
 
 #[derive(Debug, Serialize)]
@@ -58,7 +61,7 @@ pub struct SearchCliFilters {
     pub limit: usize,
 }
 
-pub fn run_search(
+pub async fn run_search(
     config: &Config,
     query: &str,
     cli_filters: SearchCliFilters,
@@ -71,15 +74,18 @@ pub fn run_search(
 
     let mut warnings: Vec<String> = Vec::new();
 
-    // Determine actual mode: vector search requires embeddings, which need async + Ollama.
-    // Until hybrid/semantic are wired up, we run lexical and warn if the user asked for more.
-    let actual_mode = "lexical";
-    if requested_mode != "lexical" {
-        warnings.push(format!(
-            "Requested mode '{}' is not yet available; falling back to lexical search.",
-            requested_mode
-        ));
-    }
+    let actual_mode = SearchMode::parse(requested_mode).unwrap_or(SearchMode::Hybrid);
+
+    let client = if actual_mode != SearchMode::Lexical {
+        let ollama_cfg = &config.embedding;
+        Some(OllamaClient::new(OllamaConfig {
+            base_url: ollama_cfg.base_url.clone(),
+            model: ollama_cfg.model.clone(),
+            ..OllamaConfig::default()
+        }))
+    } else {
+        None
+    };
 
     let doc_count: i64 = conn
         .query_row("SELECT COUNT(*) FROM documents", [], |row| row.get(0))
@@ -89,7 +95,7 @@ pub fn run_search(
         warnings.push("No documents indexed. Run 'lore generate-docs' first.".to_string());
         return Ok(SearchResponse {
             query: query.to_string(),
-            mode: actual_mode.to_string(),
+            mode: actual_mode.as_str().to_string(),
             total_results: 0,
             results: vec![],
             warnings,
@@ -151,52 +157,54 @@ pub fn run_search(
         limit: cli_filters.limit,
     };
 
-    let requested = filters.clamp_limit();
-    let top_k = if filters.has_any_filter() {
-        (requested * 50).clamp(200, 1500)
-    } else {
-        (requested * 10).clamp(50, 1500)
-    };
-
-    let fts_results = search_fts(&conn, query, top_k, fts_mode)?;
-    let fts_tuples: Vec<(i64, f64)> = fts_results
-        .iter()
-        .map(|r| (r.document_id, r.bm25_score))
-        .collect();
-
-    let snippet_map: std::collections::HashMap<i64, String> = fts_results
+    // Run FTS separately for snippet extraction (search_hybrid doesn't return snippets).
+    let snippet_top_k = filters
+        .clamp_limit()
+        .checked_mul(10)
+        .unwrap_or(500)
+        .clamp(50, 1500);
+    let fts_results = search_fts(&conn, query, snippet_top_k, fts_mode)?;
+    let snippet_map: HashMap<i64, String> = fts_results
         .iter()
         .map(|r| (r.document_id, r.snippet.clone()))
         .collect();
 
-    let ranked = rank_rrf(&[], &fts_tuples);
-    let ranked_ids: Vec<i64> = ranked.iter().map(|r| r.document_id).collect();
+    // search_hybrid handles recall sizing, RRF ranking, and filter application internally.
+    let (hybrid_results, mut hybrid_warnings) = search_hybrid(
+        &conn,
+        client.as_ref(),
+        query,
+        actual_mode,
+        &filters,
+        fts_mode,
+    )
+    .await?;
+    warnings.append(&mut hybrid_warnings);
 
-    let filtered_ids = apply_filters(&conn, &ranked_ids, &filters)?;
-
-    if filtered_ids.is_empty() {
+    if hybrid_results.is_empty() {
         return Ok(SearchResponse {
             query: query.to_string(),
-            mode: actual_mode.to_string(),
+            mode: actual_mode.as_str().to_string(),
             total_results: 0,
             results: vec![],
             warnings,
         });
     }
 
-    let hydrated = hydrate_results(&conn, &filtered_ids)?;
+    let ranked_ids: Vec<i64> = hybrid_results.iter().map(|r| r.document_id).collect();
+    let hydrated = hydrate_results(&conn, &ranked_ids)?;
 
-    let rrf_map: std::collections::HashMap<i64, &crate::search::RrfResult> =
-        ranked.iter().map(|r| (r.document_id, r)).collect();
+    let hybrid_map: HashMap<i64, &HybridResult> =
+        hybrid_results.iter().map(|r| (r.document_id, r)).collect();
 
     let mut results: Vec<SearchResultDisplay> = Vec::with_capacity(hydrated.len());
     for row in &hydrated {
-        let rrf = rrf_map.get(&row.document_id);
+        let hr = hybrid_map.get(&row.document_id);
         let fts_snippet = snippet_map.get(&row.document_id).map(|s| s.as_str());
         let snippet = get_result_snippet(fts_snippet, &row.content_text);
 
         let explain_data = if explain {
-            rrf.map(|r| ExplainData {
+            hr.map(|r| ExplainData {
                 vector_rank: r.vector_rank,
                 fts_rank: r.fts_rank,
                 rrf_score: r.rrf_score,
@@ -217,14 +225,14 @@ pub fn run_search(
             labels: row.labels.clone(),
             paths: row.paths.clone(),
             snippet,
-            score: rrf.map(|r| r.normalized_score).unwrap_or(0.0),
+            score: hr.map(|r| r.score).unwrap_or(0.0),
             explain: explain_data,
         });
     }
 
     Ok(SearchResponse {
         query: query.to_string(),
-        mode: actual_mode.to_string(),
+        mode: actual_mode.as_str().to_string(),
         total_results: results.len(),
         results,
         warnings,
@@ -360,8 +368,12 @@ pub fn print_search_results(response: &SearchResponse) {
 
         if let Some(ref explain) = result.explain {
             println!(
-                "    {} fts_rank={} rrf_score={:.6}",
+                "    {} vector_rank={} fts_rank={} rrf_score={:.6}",
                 style("[explain]").magenta(),
+                explain
+                    .vector_rank
+                    .map(|r| r.to_string())
+                    .unwrap_or_else(|| "-".into()),
                 explain
                     .fts_rank
                     .map(|r| r.to_string())

src/cli/commands/show.rs

@@ -75,12 +75,17 @@ pub struct IssueDetail {
     pub author_username: String,
     pub created_at: i64,
     pub updated_at: i64,
+    pub closed_at: Option<String>,
+    pub confidential: bool,
     pub web_url: Option<String>,
     pub project_path: String,
+    pub references_full: String,
     pub labels: Vec<String>,
     pub assignees: Vec<String>,
     pub due_date: Option<String>,
     pub milestone: Option<String>,
+    pub user_notes_count: i64,
+    pub merge_requests_count: usize,
     pub closing_merge_requests: Vec<ClosingMrRef>,
     pub discussions: Vec<DiscussionDetail>,
     pub status_name: Option<String>,
@@ -122,6 +127,9 @@ pub fn run_show_issue(
 
     let discussions = get_issue_discussions(&conn, issue.id)?;
 
+    let references_full = format!("{}#{}", issue.project_path, issue.iid);
+    let merge_requests_count = closing_mrs.len();
+
     Ok(IssueDetail {
         id: issue.id,
         iid: issue.iid,
@@ -131,12 +139,17 @@ pub fn run_show_issue(
         author_username: issue.author_username,
         created_at: issue.created_at,
         updated_at: issue.updated_at,
+        closed_at: issue.closed_at,
+        confidential: issue.confidential,
         web_url: issue.web_url,
         project_path: issue.project_path,
+        references_full,
         labels,
         assignees,
         due_date: issue.due_date,
         milestone: issue.milestone_title,
+        user_notes_count: issue.user_notes_count,
+        merge_requests_count,
         closing_merge_requests: closing_mrs,
         discussions,
         status_name: issue.status_name,
@@ -156,10 +169,13 @@ struct IssueRow {
     author_username: String,
     created_at: i64,
     updated_at: i64,
+    closed_at: Option<String>,
+    confidential: bool,
     web_url: Option<String>,
     project_path: String,
     due_date: Option<String>,
     milestone_title: Option<String>,
+    user_notes_count: i64,
     status_name: Option<String>,
     status_category: Option<String>,
     status_color: Option<String>,
@@ -173,8 +189,12 @@ fn find_issue(conn: &Connection, iid: i64, project_filter: Option<&str>) -> Resu
             let project_id = resolve_project(conn, project)?;
             (
                 "SELECT i.id, i.iid, i.title, i.description, i.state, i.author_username,
-                        i.created_at, i.updated_at, i.web_url, p.path_with_namespace,
+                        i.created_at, i.updated_at, i.closed_at, i.confidential,
+                        i.web_url, p.path_with_namespace,
                         i.due_date, i.milestone_title,
+                        (SELECT COUNT(*) FROM notes n
+                         JOIN discussions d ON n.discussion_id = d.id
+                         WHERE d.noteable_type = 'Issue' AND d.noteable_id = i.id AND n.is_system = 0) AS user_notes_count,
                         i.status_name, i.status_category, i.status_color,
                         i.status_icon_name, i.status_synced_at
                  FROM issues i
@@ -185,8 +205,12 @@ fn find_issue(conn: &Connection, iid: i64, project_filter: Option<&str>) -> Resu
         }
         None => (
             "SELECT i.id, i.iid, i.title, i.description, i.state, i.author_username,
-                    i.created_at, i.updated_at, i.web_url, p.path_with_namespace,
+                    i.created_at, i.updated_at, i.closed_at, i.confidential,
+                    i.web_url, p.path_with_namespace,
                     i.due_date, i.milestone_title,
+                    (SELECT COUNT(*) FROM notes n
+                     JOIN discussions d ON n.discussion_id = d.id
+                     WHERE d.noteable_type = 'Issue' AND d.noteable_id = i.id AND n.is_system = 0) AS user_notes_count,
                     i.status_name, i.status_category, i.status_color,
                     i.status_icon_name, i.status_synced_at
              FROM issues i
@@ -201,6 +225,7 @@ fn find_issue(conn: &Connection, iid: i64, project_filter: Option<&str>) -> Resu
     let mut stmt = conn.prepare(sql)?;
     let issues: Vec<IssueRow> = stmt
         .query_map(param_refs.as_slice(), |row| {
+            let confidential_val: i64 = row.get(9)?;
             Ok(IssueRow {
                 id: row.get(0)?,
                 iid: row.get(1)?,
@@ -210,15 +235,18 @@ fn find_issue(conn: &Connection, iid: i64, project_filter: Option<&str>) -> Resu
                 author_username: row.get(5)?,
                 created_at: row.get(6)?,
                 updated_at: row.get(7)?,
-                web_url: row.get(8)?,
-                project_path: row.get(9)?,
-                due_date: row.get(10)?,
-                milestone_title: row.get(11)?,
-                status_name: row.get(12)?,
-                status_category: row.get(13)?,
-                status_color: row.get(14)?,
-                status_icon_name: row.get(15)?,
-                status_synced_at: row.get(16)?,
+                closed_at: row.get(8)?,
+                confidential: confidential_val != 0,
+                web_url: row.get(10)?,
+                project_path: row.get(11)?,
+                due_date: row.get(12)?,
+                milestone_title: row.get(13)?,
+                user_notes_count: row.get(14)?,
+                status_name: row.get(15)?,
+                status_category: row.get(16)?,
+                status_color: row.get(17)?,
+                status_icon_name: row.get(18)?,
+                status_synced_at: row.get(19)?,
             })
         })?
         .collect::<std::result::Result<Vec<_>, _>>()?;
@@ -618,6 +646,7 @@ pub fn print_show_issue(issue: &IssueDetail) {
     println!("{}", "━".repeat(header.len().min(80)));
     println!();
 
+    println!("Ref:      {}", style(&issue.references_full).dim());
     println!("Project:  {}", style(&issue.project_path).cyan());
 
     let state_styled = if issue.state == "opened" {
@@ -627,6 +656,10 @@ pub fn print_show_issue(issue: &IssueDetail) {
     };
     println!("State:    {}", state_styled);
 
+    if issue.confidential {
+        println!("          {}", style("CONFIDENTIAL").red().bold());
+    }
+
     if let Some(status) = &issue.status_name {
         println!(
             "Status:   {}",
@@ -658,6 +691,10 @@ pub fn print_show_issue(issue: &IssueDetail) {
     println!("Created:  {}", format_date(issue.created_at));
     println!("Updated:  {}", format_date(issue.updated_at));
 
+    if let Some(closed_at) = &issue.closed_at {
+        println!("Closed:   {}", closed_at);
+    }
+
     if let Some(due) = &issue.due_date {
         println!("Due:      {}", due);
     }
@@ -931,12 +968,17 @@ pub struct IssueDetailJson {
     pub author_username: String,
     pub created_at: String,
     pub updated_at: String,
+    pub closed_at: Option<String>,
+    pub confidential: bool,
     pub web_url: Option<String>,
     pub project_path: String,
+    pub references_full: String,
     pub labels: Vec<String>,
     pub assignees: Vec<String>,
     pub due_date: Option<String>,
     pub milestone: Option<String>,
+    pub user_notes_count: i64,
+    pub merge_requests_count: usize,
     pub closing_merge_requests: Vec<ClosingMrRefJson>,
     pub discussions: Vec<DiscussionDetailJson>,
     pub status_name: Option<String>,
@@ -980,12 +1022,17 @@ impl From<&IssueDetail> for IssueDetailJson {
             author_username: issue.author_username.clone(),
             created_at: ms_to_iso(issue.created_at),
             updated_at: ms_to_iso(issue.updated_at),
+            closed_at: issue.closed_at.clone(),
+            confidential: issue.confidential,
             web_url: issue.web_url.clone(),
             project_path: issue.project_path.clone(),
+            references_full: issue.references_full.clone(),
             labels: issue.labels.clone(),
             assignees: issue.assignees.clone(),
             due_date: issue.due_date.clone(),
             milestone: issue.milestone.clone(),
+            user_notes_count: issue.user_notes_count,
+            merge_requests_count: issue.merge_requests_count,
             closing_merge_requests: issue
                 .closing_merge_requests
                 .iter()

src/cli/mod.rs

@@ -215,6 +215,24 @@ pub enum Commands {
     /// People intelligence: experts, workload, active discussions, overlap
     Who(WhoArgs),
 
+    /// Detect discussion divergence from original intent
+    Drift {
+        /// Entity type (currently only "issues" supported)
+        #[arg(value_parser = ["issues"])]
+        entity_type: String,
+
+        /// Entity IID
+        iid: i64,
+
+        /// Similarity threshold for drift detection (0.0-1.0)
+        #[arg(long, default_value = "0.4")]
+        threshold: f32,
+
+        /// Scope to project (fuzzy match)
+        #[arg(short, long)]
+        project: Option<String>,
+    },
+
     #[command(hide = true)]
     List {
         #[arg(value_parser = ["issues", "mrs"])]

src/cli/robot.rs

@@ -77,6 +77,7 @@ pub fn strip_schemas(commands: &mut serde_json::Value) {
         for (_cmd_name, cmd) in map.iter_mut() {
             if let Some(obj) = cmd.as_object_mut() {
                 obj.remove("response_schema");
+                obj.remove("example_output");
             }
         }
     }

src/core/db.rs

@@ -69,6 +69,10 @@ const MIGRATIONS: &[(&str, &str)] = &[
         "021",
         include_str!("../../migrations/021_work_item_status.sql"),
     ),
+    (
+        "023",
+        include_str!("../../migrations/023_issue_detail_fields.sql"),
+    ),
 ];
 
 pub fn create_connection(db_path: &Path) -> Result<Connection> {

src/embedding/mod.rs

@@ -3,7 +3,9 @@ pub mod chunk_ids;
 pub mod chunking;
 pub mod ollama;
 pub mod pipeline;
+pub mod similarity;
 
 pub use change_detector::{PendingDocument, count_pending_documents, find_pending_documents};
 pub use chunking::{CHUNK_MAX_BYTES, CHUNK_OVERLAP_CHARS, split_into_chunks};
 pub use pipeline::{EmbedResult, embed_documents};
+pub use similarity::cosine_similarity;

src/embedding/similarity.rs

@@ -0,0 +1,48 @@
+/// Cosine similarity between two embedding vectors.
+/// Returns value in [-1, 1] range; higher = more similar.
+pub fn cosine_similarity(a: &[f32], b: &[f32]) -> f32 {
+    debug_assert_eq!(a.len(), b.len(), "embedding dimensions must match");
+    let dot: f32 = a.iter().zip(b).map(|(x, y)| x * y).sum();
+    let norm_a: f32 = a.iter().map(|x| x * x).sum::<f32>().sqrt();
+    let norm_b: f32 = b.iter().map(|x| x * x).sum::<f32>().sqrt();
+    if norm_a == 0.0 || norm_b == 0.0 {
+        return 0.0;
+    }
+    dot / (norm_a * norm_b)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_cosine_similarity_identical() {
+        let v = [1.0, 2.0, 3.0];
+        let sim = cosine_similarity(&v, &v);
+        assert!((sim - 1.0).abs() < 1e-6);
+    }
+
+    #[test]
+    fn test_cosine_similarity_orthogonal() {
+        let a = [1.0, 0.0, 0.0];
+        let b = [0.0, 1.0, 0.0];
+        let sim = cosine_similarity(&a, &b);
+        assert!(sim.abs() < 1e-6);
+    }
+
+    #[test]
+    fn test_cosine_similarity_zero_vector() {
+        let a = [1.0, 2.0, 3.0];
+        let b = [0.0, 0.0, 0.0];
+        let sim = cosine_similarity(&a, &b);
+        assert!((sim - 0.0).abs() < 1e-6);
+    }
+
+    #[test]
+    fn test_cosine_similarity_opposite() {
+        let a = [1.0, 2.0, 3.0];
+        let b = [-1.0, -2.0, -3.0];
+        let sim = cosine_similarity(&a, &b);
+        assert!((sim - (-1.0)).abs() < 1e-6);
+    }
+}

src/main.rs

@@ -12,17 +12,17 @@ use lore::cli::autocorrect::{self, CorrectionResult};
 use lore::cli::commands::{
     IngestDisplay, InitInputs, InitOptions, InitResult, ListFilters, MrListFilters,
     SearchCliFilters, SyncOptions, TimelineParams, open_issue_in_browser, open_mr_in_browser,
-    print_count, print_count_json, print_doctor_results, print_dry_run_preview,
-    print_dry_run_preview_json, print_embed, print_embed_json, print_event_count,
-    print_event_count_json, print_generate_docs, print_generate_docs_json, print_ingest_summary,
-    print_ingest_summary_json, print_list_issues, print_list_issues_json, print_list_mrs,
-    print_list_mrs_json, print_search_results, print_search_results_json, print_show_issue,
-    print_show_issue_json, print_show_mr, print_show_mr_json, print_stats, print_stats_json,
-    print_sync, print_sync_json, print_sync_status, print_sync_status_json, print_timeline,
-    print_timeline_json_with_meta, print_who_human, print_who_json, run_auth_test, run_count,
-    run_count_events, run_doctor, run_embed, run_generate_docs, run_ingest, run_ingest_dry_run,
-    run_init, run_list_issues, run_list_mrs, run_search, run_show_issue, run_show_mr, run_stats,
-    run_sync, run_sync_status, run_timeline, run_who,
+    print_count, print_count_json, print_doctor_results, print_drift_human, print_drift_json,
+    print_dry_run_preview, print_dry_run_preview_json, print_embed, print_embed_json,
+    print_event_count, print_event_count_json, print_generate_docs, print_generate_docs_json,
+    print_ingest_summary, print_ingest_summary_json, print_list_issues, print_list_issues_json,
+    print_list_mrs, print_list_mrs_json, print_search_results, print_search_results_json,
+    print_show_issue, print_show_issue_json, print_show_mr, print_show_mr_json, print_stats,
+    print_stats_json, print_sync, print_sync_json, print_sync_status, print_sync_status_json,
+    print_timeline, print_timeline_json_with_meta, print_who_human, print_who_json, run_auth_test,
+    run_count, run_count_events, run_doctor, run_drift, run_embed, run_generate_docs, run_ingest,
+    run_ingest_dry_run, run_init, run_list_issues, run_list_mrs, run_search, run_show_issue,
+    run_show_mr, run_stats, run_sync, run_sync_status, run_timeline, run_who,
 };
 use lore::cli::robot::{RobotMeta, strip_schemas};
 use lore::cli::{
@@ -178,6 +178,22 @@ async fn main() {
         }
         Some(Commands::Timeline(args)) => handle_timeline(cli.config.as_deref(), args, robot_mode),
         Some(Commands::Who(args)) => handle_who(cli.config.as_deref(), args, robot_mode),
+        Some(Commands::Drift {
+            entity_type,
+            iid,
+            threshold,
+            project,
+        }) => {
+            handle_drift(
+                cli.config.as_deref(),
+                &entity_type,
+                iid,
+                threshold,
+                project.as_deref(),
+                robot_mode,
+            )
+            .await
+        }
         Some(Commands::Stats(args)) => handle_stats(cli.config.as_deref(), args, robot_mode).await,
         Some(Commands::Embed(args)) => handle_embed(cli.config.as_deref(), args, robot_mode).await,
         Some(Commands::Sync(args)) => {
@@ -1762,7 +1778,8 @@ async fn handle_search(
         fts_mode,
         &args.mode,
         explain,
-    )?;
+    )
+    .await?;
     let elapsed_ms = start.elapsed().as_millis() as u64;
 
     if robot_mode {
@@ -2048,6 +2065,7 @@ struct RobotDocsData {
     version: String,
     description: String,
     activation: RobotDocsActivation,
+    quick_start: serde_json::Value,
     commands: serde_json::Value,
     /// Deprecated command aliases (old -> new)
     aliases: serde_json::Value,
@@ -2151,6 +2169,7 @@ fn handle_robot_docs(robot_mode: bool, brief: bool) -> Result<(), Box<dyn std::e
                     "meta": {"elapsed_ms": "int"}
                 }
             },
+            "example_output": {"list": {"ok":true,"data":{"issues":[{"iid":3864,"title":"Switch Health Card","state":"opened","status_name":"In progress","labels":["customer:BNSF"],"assignees":["teernisse"],"discussion_count":12,"updated_at_iso":"2026-02-12T..."}],"total_count":1,"showing":1},"meta":{"elapsed_ms":42}}},
             "fields_presets": {"minimal": ["iid", "title", "state", "updated_at_iso"]}
         },
         "mrs": {
@@ -2169,6 +2188,7 @@ fn handle_robot_docs(robot_mode: bool, brief: bool) -> Result<(), Box<dyn std::e
                     "meta": {"elapsed_ms": "int"}
                 }
             },
+            "example_output": {"list": {"ok":true,"data":{"mrs":[{"iid":200,"title":"Add throw time chart","state":"opened","draft":false,"author_username":"teernisse","target_branch":"main","source_branch":"feat/throw-time","reviewers":["cseiber"],"discussion_count":5,"updated_at_iso":"2026-02-11T..."}],"total_count":1,"showing":1},"meta":{"elapsed_ms":38}}},
             "fields_presets": {"minimal": ["iid", "title", "state", "updated_at_iso"]}
         },
         "search": {
@@ -2180,6 +2200,7 @@ fn handle_robot_docs(robot_mode: bool, brief: bool) -> Result<(), Box<dyn std::e
                 "data": {"results": "[{document_id:int, source_type:string, title:string, snippet:string, score:float, url:string?, author:string?, created_at:string?, updated_at:string?, project_path:string, labels:[string], paths:[string]}]", "total_results": "int", "query": "string", "mode": "string", "warnings": "[string]"},
                 "meta": {"elapsed_ms": "int"}
             },
+            "example_output": {"ok":true,"data":{"query":"throw time","mode":"hybrid","total_results":3,"results":[{"document_id":42,"source_type":"issue","title":"Switch Health Card","score":0.92,"snippet":"...throw time data from BNSF...","project_path":"vs/typescript-code"}],"warnings":[]},"meta":{"elapsed_ms":85}},
             "fields_presets": {"minimal": ["document_id", "title", "source_type", "score"]}
         },
         "count": {
@@ -2289,6 +2310,7 @@ fn handle_robot_docs(robot_mode: bool, brief: bool) -> Result<(), Box<dyn std::e
                 },
                 "meta": {"elapsed_ms": "int"}
             },
+            "example_output": {"expert": {"ok":true,"data":{"mode":"expert","result":{"experts":[{"username":"teernisse","score":42,"note_count":15,"diff_note_count":8}]}},"meta":{"elapsed_ms":65}}},
             "fields_presets": {
                 "expert_minimal": ["username", "score"],
                 "workload_minimal": ["entity_type", "iid", "title", "state"],
@@ -2302,7 +2324,28 @@ fn handle_robot_docs(robot_mode: bool, brief: bool) -> Result<(), Box<dyn std::e
         }
     });
 
-    // --brief: strip response_schema from every command (~60% smaller)
+    let quick_start = serde_json::json!({
+        "glab_equivalents": [
+            { "glab": "glab issue list", "lore": "lore -J issues -n 50", "note": "Richer: includes labels, status, closing MRs, discussion counts" },
+            { "glab": "glab issue view 123", "lore": "lore -J issues 123", "note": "Includes full discussions, work-item status, cross-references" },
+            { "glab": "glab issue list -l bug", "lore": "lore -J issues --label bug", "note": "AND logic for multiple --label flags" },
+            { "glab": "glab mr list", "lore": "lore -J mrs", "note": "Includes draft status, reviewers, discussion counts" },
+            { "glab": "glab mr view 456", "lore": "lore -J mrs 456", "note": "Includes discussions, review threads, source/target branches" },
+            { "glab": "glab mr list -s opened", "lore": "lore -J mrs -s opened", "note": "States: opened, merged, closed, locked, all" },
+            { "glab": "glab api '/projects/:id/issues'", "lore": "lore -J issues -p project", "note": "Fuzzy project matching (suffix or substring)" }
+        ],
+        "lore_exclusive": [
+            "search: FTS5 + vector hybrid search across all entities",
+            "who: Expert/workload/reviews analysis per file path or person",
+            "timeline: Chronological event reconstruction across entities",
+            "stats: Database statistics with document/note/discussion counts",
+            "count: Entity counts with state breakdowns",
+            "embed: Generate vector embeddings for semantic search via Ollama"
+        ],
+        "read_write_split": "lore = ALL reads (issues, MRs, search, who, timeline, intelligence). glab = ALL writes (create, update, approve, merge, CI/CD)."
+    });
+
+    // --brief: strip response_schema and example_output from every command (~60% smaller)
     let mut commands = commands;
     if brief {
         strip_schemas(&mut commands);
@@ -2405,6 +2448,7 @@ fn handle_robot_docs(robot_mode: bool, brief: bool) -> Result<(), Box<dyn std::e
                 env: "LORE_ROBOT=1".to_string(),
                 auto: "Non-TTY stdout".to_string(),
             },
+            quick_start,
             commands,
             aliases,
             exit_codes,
@@ -2445,6 +2489,28 @@ fn handle_who(
     Ok(())
 }
 
+async fn handle_drift(
+    config_override: Option<&str>,
+    entity_type: &str,
+    iid: i64,
+    threshold: f32,
+    project: Option<&str>,
+    robot_mode: bool,
+) -> Result<(), Box<dyn std::error::Error>> {
+    let start = std::time::Instant::now();
+    let config = Config::load(config_override)?;
+    let effective_project = config.effective_project(project);
+    let response = run_drift(&config, entity_type, iid, threshold, effective_project).await?;
+    let elapsed_ms = start.elapsed().as_millis() as u64;
+
+    if robot_mode {
+        print_drift_json(&response, elapsed_ms);
+    } else {
+        print_drift_human(&response);
+    }
+    Ok(())
+}
+
 #[allow(clippy::too_many_arguments)]
 async fn handle_list_compat(
     config_override: Option<&str>,