feat: Implement Gate 3 timeline pipeline and Gate 4 migration scaffolding

Complete 5 beads for the Phase B temporal intelligence feature:

- bd-1oo: Register migration 015 (commit SHAs, closes watermark) and
  create migration 016 (mr_file_changes table with 4 indexes for
  Gate 4 file-history)

- bd-20e: Define TimelineEvent model with 9 event type variants,
  EntityRef, ExpandedEntityRef, UnresolvedRef, and TimelineResult
  types. Ord impl for chronological sorting with stable tiebreak.

- bd-32q: Implement timeline seed phase - FTS5 keyword search to
  entity IDs with discussion-to-parent resolution, entity dedup,
  and evidence note extraction with snippet truncation.

- bd-ypa: Implement timeline expand phase - BFS cross-reference
  expansion over entity_references with bidirectional traversal,
  depth limiting, mention filtering, provenance tracking, and
  unresolved reference collection.

- bd-3as: Implement timeline event collection - gathers Created,
  StateChanged, LabelAdded/Removed, MilestoneSet/Removed, Merged,
  and NoteEvidence events. Merged dedup (state=merged -> Merged
  variant only). NULL label/milestone fallbacks. Chronological
  interleaving with since filter and limit.

38 new tests, all 445 tests pass. All quality gates clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Taylor Eernisse
2026-02-05 16:54:28 -05:00
parent d1b2b5fa7d
commit 3767c33c28
9 changed files with 2143 additions and 6 deletions

View File

@@ -0,0 +1,687 @@
use rusqlite::Connection;
use crate::core::error::Result;
use crate::core::timeline::{EntityRef, ExpandedEntityRef, TimelineEvent, TimelineEventType};
/// Collect all events for seed and expanded entities, interleave chronologically.
///
/// Steps 4-5 of the timeline pipeline:
/// 1. For each entity, collect Created, StateChanged, Label, Milestone, Merged events
/// 2. Merge in evidence notes from the seed phase
/// 3. Sort chronologically with stable tiebreak
/// 4. Apply --since filter and --limit
pub fn collect_events(
conn: &Connection,
seed_entities: &[EntityRef],
expanded_entities: &[ExpandedEntityRef],
evidence_notes: &[TimelineEvent],
since_ms: Option<i64>,
limit: usize,
) -> Result<Vec<TimelineEvent>> {
let mut all_events: Vec<TimelineEvent> = Vec::new();
// Collect events for seed entities
for entity in seed_entities {
collect_entity_events(conn, entity, true, &mut all_events)?;
}
// Collect events for expanded entities
for expanded in expanded_entities {
collect_entity_events(conn, &expanded.entity_ref, false, &mut all_events)?;
}
// Add evidence notes from seed phase
all_events.extend(evidence_notes.iter().cloned());
// Sort chronologically (uses Ord impl from timeline.rs)
all_events.sort();
// Apply --since filter
if let Some(since) = since_ms {
all_events.retain(|e| e.timestamp >= since);
}
// Apply limit
all_events.truncate(limit);
Ok(all_events)
}
/// Collect all events for a single entity.
fn collect_entity_events(
conn: &Connection,
entity: &EntityRef,
is_seed: bool,
events: &mut Vec<TimelineEvent>,
) -> Result<()> {
collect_creation_event(conn, entity, is_seed, events)?;
collect_state_events(conn, entity, is_seed, events)?;
collect_label_events(conn, entity, is_seed, events)?;
collect_milestone_events(conn, entity, is_seed, events)?;
collect_merged_event(conn, entity, is_seed, events)?;
Ok(())
}
/// Collect the Created event from the entity's own table.
fn collect_creation_event(
conn: &Connection,
entity: &EntityRef,
is_seed: bool,
events: &mut Vec<TimelineEvent>,
) -> Result<()> {
let table = match entity.entity_type.as_str() {
"issue" => "issues",
"merge_request" => "merge_requests",
_ => return Ok(()),
};
let sql =
format!("SELECT created_at, author_username, title, web_url FROM {table} WHERE id = ?1");
let result = conn.query_row(&sql, rusqlite::params![entity.entity_id], |row| {
Ok((
row.get::<_, Option<i64>>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, Option<String>>(2)?,
row.get::<_, Option<String>>(3)?,
))
});
if let Ok((Some(created_at), author, title, url)) = result {
let type_label = if entity.entity_type == "issue" {
"Issue"
} else {
"MR"
};
let title_str = title.as_deref().unwrap_or("(untitled)");
events.push(TimelineEvent {
timestamp: created_at,
entity_type: entity.entity_type.clone(),
entity_id: entity.entity_id,
entity_iid: entity.entity_iid,
project_path: entity.project_path.clone(),
event_type: TimelineEventType::Created,
summary: format!("{type_label} #{} created: {title_str}", entity.entity_iid),
actor: author,
url,
is_seed,
});
}
Ok(())
}
/// Collect state change events. State='merged' produces Merged, not StateChanged.
fn collect_state_events(
conn: &Connection,
entity: &EntityRef,
is_seed: bool,
events: &mut Vec<TimelineEvent>,
) -> Result<()> {
let (id_col, id_val) = entity_id_column(entity);
let sql = format!(
"SELECT state, actor_username, created_at FROM resource_state_events
WHERE {id_col} = ?1
ORDER BY created_at ASC"
);
let mut stmt = conn.prepare(&sql)?;
let rows = stmt.query_map(rusqlite::params![id_val], |row| {
Ok((
row.get::<_, String>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, i64>(2)?,
))
})?;
for row_result in rows {
let (state, actor, created_at) = row_result?;
// state='merged' is handled by collect_merged_event — skip here
if state == "merged" {
continue;
}
events.push(TimelineEvent {
timestamp: created_at,
entity_type: entity.entity_type.clone(),
entity_id: entity.entity_id,
entity_iid: entity.entity_iid,
project_path: entity.project_path.clone(),
event_type: TimelineEventType::StateChanged {
state: state.clone(),
},
summary: format!("State changed to {state}"),
actor,
url: None,
is_seed,
});
}
Ok(())
}
/// Collect label add/remove events.
fn collect_label_events(
conn: &Connection,
entity: &EntityRef,
is_seed: bool,
events: &mut Vec<TimelineEvent>,
) -> Result<()> {
let (id_col, id_val) = entity_id_column(entity);
let sql = format!(
"SELECT action, label_name, actor_username, created_at FROM resource_label_events
WHERE {id_col} = ?1
ORDER BY created_at ASC"
);
let mut stmt = conn.prepare(&sql)?;
let rows = stmt.query_map(rusqlite::params![id_val], |row| {
Ok((
row.get::<_, String>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, Option<String>>(2)?,
row.get::<_, i64>(3)?,
))
})?;
for row_result in rows {
let (action, label_name, actor, created_at) = row_result?;
let label = label_name.unwrap_or_else(|| "[deleted label]".to_owned());
let (event_type, summary) = match action.as_str() {
"add" => (
TimelineEventType::LabelAdded {
label: label.clone(),
},
format!("Label added: {label}"),
),
"remove" => (
TimelineEventType::LabelRemoved {
label: label.clone(),
},
format!("Label removed: {label}"),
),
_ => continue,
};
events.push(TimelineEvent {
timestamp: created_at,
entity_type: entity.entity_type.clone(),
entity_id: entity.entity_id,
entity_iid: entity.entity_iid,
project_path: entity.project_path.clone(),
event_type,
summary,
actor,
url: None,
is_seed,
});
}
Ok(())
}
/// Collect milestone add/remove events.
fn collect_milestone_events(
conn: &Connection,
entity: &EntityRef,
is_seed: bool,
events: &mut Vec<TimelineEvent>,
) -> Result<()> {
let (id_col, id_val) = entity_id_column(entity);
let sql = format!(
"SELECT action, milestone_title, actor_username, created_at FROM resource_milestone_events
WHERE {id_col} = ?1
ORDER BY created_at ASC"
);
let mut stmt = conn.prepare(&sql)?;
let rows = stmt.query_map(rusqlite::params![id_val], |row| {
Ok((
row.get::<_, String>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, Option<String>>(2)?,
row.get::<_, i64>(3)?,
))
})?;
for row_result in rows {
let (action, milestone_title, actor, created_at) = row_result?;
let milestone = milestone_title.unwrap_or_else(|| "[deleted milestone]".to_owned());
let (event_type, summary) = match action.as_str() {
"add" => (
TimelineEventType::MilestoneSet {
milestone: milestone.clone(),
},
format!("Milestone set: {milestone}"),
),
"remove" => (
TimelineEventType::MilestoneRemoved {
milestone: milestone.clone(),
},
format!("Milestone removed: {milestone}"),
),
_ => continue,
};
events.push(TimelineEvent {
timestamp: created_at,
entity_type: entity.entity_type.clone(),
entity_id: entity.entity_id,
entity_iid: entity.entity_iid,
project_path: entity.project_path.clone(),
event_type,
summary,
actor,
url: None,
is_seed,
});
}
Ok(())
}
/// Collect Merged event for MRs. Prefers merged_at from the MR table.
/// Falls back to resource_state_events WHERE state='merged' if merged_at is NULL.
fn collect_merged_event(
conn: &Connection,
entity: &EntityRef,
is_seed: bool,
events: &mut Vec<TimelineEvent>,
) -> Result<()> {
if entity.entity_type != "merge_request" {
return Ok(());
}
// Try merged_at from merge_requests table first
let mr_result = conn.query_row(
"SELECT merged_at, merge_user_username, web_url FROM merge_requests WHERE id = ?1",
rusqlite::params![entity.entity_id],
|row| {
Ok((
row.get::<_, Option<i64>>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, Option<String>>(2)?,
))
},
);
if let Ok((Some(merged_at), merge_user, url)) = mr_result {
events.push(TimelineEvent {
timestamp: merged_at,
entity_type: entity.entity_type.clone(),
entity_id: entity.entity_id,
entity_iid: entity.entity_iid,
project_path: entity.project_path.clone(),
event_type: TimelineEventType::Merged,
summary: format!("MR !{} merged", entity.entity_iid),
actor: merge_user,
url,
is_seed,
});
return Ok(());
}
// Fallback: check resource_state_events for state='merged'
let fallback_result = conn.query_row(
"SELECT actor_username, created_at FROM resource_state_events
WHERE merge_request_id = ?1 AND state = 'merged'
ORDER BY created_at DESC LIMIT 1",
rusqlite::params![entity.entity_id],
|row| Ok((row.get::<_, Option<String>>(0)?, row.get::<_, i64>(1)?)),
);
if let Ok((actor, created_at)) = fallback_result {
events.push(TimelineEvent {
timestamp: created_at,
entity_type: entity.entity_type.clone(),
entity_id: entity.entity_id,
entity_iid: entity.entity_iid,
project_path: entity.project_path.clone(),
event_type: TimelineEventType::Merged,
summary: format!("MR !{} merged", entity.entity_iid),
actor,
url: None,
is_seed,
});
}
Ok(())
}
/// Return the correct column name and value for querying resource event tables.
fn entity_id_column(entity: &EntityRef) -> (&'static str, i64) {
match entity.entity_type.as_str() {
"issue" => ("issue_id", entity.entity_id),
"merge_request" => ("merge_request_id", entity.entity_id),
_ => ("issue_id", entity.entity_id), // shouldn't happen
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::core::db::{create_connection, run_migrations};
use std::path::Path;
fn setup_test_db() -> Connection {
let conn = create_connection(Path::new(":memory:")).unwrap();
run_migrations(&conn).unwrap();
conn
}
fn insert_project(conn: &Connection) -> i64 {
conn.execute(
"INSERT INTO projects (gitlab_project_id, path_with_namespace, web_url) VALUES (1, 'group/project', 'https://gitlab.com/group/project')",
[],
)
.unwrap();
conn.last_insert_rowid()
}
fn insert_issue(conn: &Connection, project_id: i64, iid: i64) -> i64 {
conn.execute(
"INSERT INTO issues (gitlab_id, project_id, iid, title, state, author_username, created_at, updated_at, last_seen_at, web_url) VALUES (?1, ?2, ?3, 'Auth bug', 'opened', 'alice', 1000, 2000, 3000, 'https://gitlab.com/group/project/-/issues/1')",
rusqlite::params![iid * 100, project_id, iid],
)
.unwrap();
conn.last_insert_rowid()
}
fn insert_mr(conn: &Connection, project_id: i64, iid: i64, merged_at: Option<i64>) -> i64 {
conn.execute(
"INSERT INTO merge_requests (gitlab_id, project_id, iid, title, state, author_username, created_at, updated_at, last_seen_at, merged_at, merge_user_username, web_url) VALUES (?1, ?2, ?3, 'Fix auth', 'merged', 'bob', 1000, 5000, 6000, ?4, 'charlie', 'https://gitlab.com/group/project/-/merge_requests/10')",
rusqlite::params![iid * 100, project_id, iid, merged_at],
)
.unwrap();
conn.last_insert_rowid()
}
fn make_entity_ref(entity_type: &str, entity_id: i64, iid: i64) -> EntityRef {
EntityRef {
entity_type: entity_type.to_owned(),
entity_id,
entity_iid: iid,
project_path: "group/project".to_owned(),
}
}
fn insert_state_event(
conn: &Connection,
project_id: i64,
issue_id: Option<i64>,
mr_id: Option<i64>,
state: &str,
created_at: i64,
) {
let gitlab_id: i64 = rand::random::<u32>().into();
conn.execute(
"INSERT INTO resource_state_events (gitlab_id, project_id, issue_id, merge_request_id, state, actor_username, created_at) VALUES (?1, ?2, ?3, ?4, ?5, 'alice', ?6)",
rusqlite::params![gitlab_id, project_id, issue_id, mr_id, state, created_at],
)
.unwrap();
}
fn insert_label_event(
conn: &Connection,
project_id: i64,
issue_id: Option<i64>,
mr_id: Option<i64>,
action: &str,
label_name: Option<&str>,
created_at: i64,
) {
let gitlab_id: i64 = rand::random::<u32>().into();
conn.execute(
"INSERT INTO resource_label_events (gitlab_id, project_id, issue_id, merge_request_id, action, label_name, actor_username, created_at) VALUES (?1, ?2, ?3, ?4, ?5, ?6, 'alice', ?7)",
rusqlite::params![gitlab_id, project_id, issue_id, mr_id, action, label_name, created_at],
)
.unwrap();
}
fn insert_milestone_event(
conn: &Connection,
project_id: i64,
issue_id: Option<i64>,
mr_id: Option<i64>,
action: &str,
milestone_title: Option<&str>,
created_at: i64,
) {
let gitlab_id: i64 = rand::random::<u32>().into();
conn.execute(
"INSERT INTO resource_milestone_events (gitlab_id, project_id, issue_id, merge_request_id, action, milestone_title, actor_username, created_at) VALUES (?1, ?2, ?3, ?4, ?5, ?6, 'alice', ?7)",
rusqlite::params![gitlab_id, project_id, issue_id, mr_id, action, milestone_title, created_at],
)
.unwrap();
}
#[test]
fn test_collect_creation_event() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
assert_eq!(events.len(), 1);
assert!(matches!(events[0].event_type, TimelineEventType::Created));
assert_eq!(events[0].timestamp, 1000);
assert_eq!(events[0].actor, Some("alice".to_owned()));
assert!(events[0].is_seed);
}
#[test]
fn test_collect_state_events() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
insert_state_event(&conn, project_id, Some(issue_id), None, "closed", 3000);
insert_state_event(&conn, project_id, Some(issue_id), None, "reopened", 4000);
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
// Created + 2 state changes = 3
assert_eq!(events.len(), 3);
assert!(matches!(events[0].event_type, TimelineEventType::Created));
assert!(matches!(
events[1].event_type,
TimelineEventType::StateChanged { ref state } if state == "closed"
));
assert!(matches!(
events[2].event_type,
TimelineEventType::StateChanged { ref state } if state == "reopened"
));
}
#[test]
fn test_collect_merged_dedup() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let mr_id = insert_mr(&conn, project_id, 10, Some(5000));
// Also add a state event for 'merged' — this should NOT produce a StateChanged
insert_state_event(&conn, project_id, None, Some(mr_id), "merged", 5000);
let seeds = vec![make_entity_ref("merge_request", mr_id, 10)];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
// Should have Created + Merged (not Created + StateChanged{merged} + Merged)
let merged_count = events
.iter()
.filter(|e| matches!(e.event_type, TimelineEventType::Merged))
.count();
let state_merged_count = events
.iter()
.filter(|e| matches!(&e.event_type, TimelineEventType::StateChanged { state } if state == "merged"))
.count();
assert_eq!(merged_count, 1);
assert_eq!(state_merged_count, 0);
}
#[test]
fn test_collect_null_label_fallback() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
insert_label_event(&conn, project_id, Some(issue_id), None, "add", None, 2000);
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
let label_event = events.iter().find(|e| {
matches!(&e.event_type, TimelineEventType::LabelAdded { label } if label == "[deleted label]")
});
assert!(label_event.is_some());
}
#[test]
fn test_collect_null_milestone_fallback() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
insert_milestone_event(&conn, project_id, Some(issue_id), None, "add", None, 2000);
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
let ms_event = events.iter().find(|e| {
matches!(&e.event_type, TimelineEventType::MilestoneSet { milestone } if milestone == "[deleted milestone]")
});
assert!(ms_event.is_some());
}
#[test]
fn test_collect_since_filter() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
insert_state_event(&conn, project_id, Some(issue_id), None, "closed", 3000);
insert_state_event(&conn, project_id, Some(issue_id), None, "reopened", 5000);
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
// Since 4000: should exclude Created (1000) and closed (3000)
let events = collect_events(&conn, &seeds, &[], &[], Some(4000), 100).unwrap();
assert_eq!(events.len(), 1);
assert_eq!(events[0].timestamp, 5000);
}
#[test]
fn test_collect_chronological_sort() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
let mr_id = insert_mr(&conn, project_id, 10, Some(4000));
insert_state_event(&conn, project_id, Some(issue_id), None, "closed", 3000);
insert_label_event(
&conn,
project_id,
None,
Some(mr_id),
"add",
Some("bug"),
2000,
);
let seeds = vec![
make_entity_ref("issue", issue_id, 1),
make_entity_ref("merge_request", mr_id, 10),
];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
// Verify chronological order
for window in events.windows(2) {
assert!(window[0].timestamp <= window[1].timestamp);
}
}
#[test]
fn test_collect_respects_limit() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
for i in 0..20 {
insert_state_event(
&conn,
project_id,
Some(issue_id),
None,
"closed",
3000 + i * 100,
);
}
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
let events = collect_events(&conn, &seeds, &[], &[], None, 5).unwrap();
assert_eq!(events.len(), 5);
}
#[test]
fn test_collect_evidence_notes_included() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
let issue_id = insert_issue(&conn, project_id, 1);
let evidence = vec![TimelineEvent {
timestamp: 2500,
entity_type: "issue".to_owned(),
entity_id: issue_id,
entity_iid: 1,
project_path: "group/project".to_owned(),
event_type: TimelineEventType::NoteEvidence {
note_id: 42,
snippet: "relevant note".to_owned(),
discussion_id: Some(1),
},
summary: "Note by alice".to_owned(),
actor: Some("alice".to_owned()),
url: None,
is_seed: true,
}];
let seeds = vec![make_entity_ref("issue", issue_id, 1)];
let events = collect_events(&conn, &seeds, &[], &evidence, None, 100).unwrap();
let note_event = events.iter().find(|e| {
matches!(
&e.event_type,
TimelineEventType::NoteEvidence { note_id, .. } if *note_id == 42
)
});
assert!(note_event.is_some());
}
#[test]
fn test_collect_merged_fallback_to_state_event() {
let conn = setup_test_db();
let project_id = insert_project(&conn);
// MR with merged_at = NULL
let mr_id = insert_mr(&conn, project_id, 10, None);
// But has a state event for 'merged'
insert_state_event(&conn, project_id, None, Some(mr_id), "merged", 5000);
let seeds = vec![make_entity_ref("merge_request", mr_id, 10)];
let events = collect_events(&conn, &seeds, &[], &[], None, 100).unwrap();
let merged = events
.iter()
.find(|e| matches!(e.event_type, TimelineEventType::Merged));
assert!(merged.is_some());
assert_eq!(merged.unwrap().timestamp, 5000);
}
}