Files
gitlore/src/cli/commands/who/mod.rs
teernisse a0519a4d0d feat(surgical-sync): add per-IID surgical sync pipeline
Implement lore sync --issue <IID> --mr <IID> -p <project> for on-demand
sync of specific entities without running the full project-wide pipeline.
Completes in seconds by fetching only targeted entities, their discussions,
resource events, and dependent data, then scoping doc regeneration and
embedding to only affected documents.

Pipeline stages: PREFLIGHT -> TOCTOU -> INGEST -> DEPENDENTS -> DOCS -> EMBED

New files:
- src/ingestion/surgical.rs: TOCTOU guard, preflight fetch, per-entity ingest
- src/ingestion/surgical_tests.rs: 17 unit/wiremock tests
- src/cli/commands/sync_surgical.rs: 719-line orchestrator
- src/embedding/pipeline_tests.rs: scoped embedding tests
- src/gitlab/client_tests.rs: get_by_iid wiremock tests
- migrations/027_surgical_sync_runs.sql: 12 surgical columns + indexes

Key changes:
- SyncOptions: issue_iids, mr_iids, project, preflight_only fields
- SyncResult: surgical_mode, surgical_iids, entity_results fields
- SyncRunRecorder: surgical lifecycle methods (set_surgical_metadata, etc)
- GitLabClient: get_issue_by_iid, get_mr_by_iid
- Scoped docs: regenerate_dirty_documents_for_sources
- Scoped embed: embed_documents_by_ids
- run_sync dispatches to run_sync_surgical when is_surgical()
- robot-docs updated with surgical sync schema + workflows
- All 1019 tests pass, clippy clean

Closes: bd-1sc6, bd-tiux, bd-159p, bd-1lja, bd-hs6j, bd-1elx, bd-arka,
        bd-3sez, bd-wcja, bd-kanh, bd-1i4i, bd-3bec
2026-02-18 15:39:14 -05:00

430 lines
15 KiB
Rust

mod active;
mod expert;
mod overlap;
mod reviews;
pub mod types;
mod workload;
pub use types::*;
// Re-export submodule functions for tests (tests use `use super::*`).
#[cfg(test)]
use active::query_active;
#[cfg(test)]
use expert::{build_expert_sql_v2, half_life_decay, query_expert};
#[cfg(test)]
use overlap::{format_overlap_role, query_overlap};
#[cfg(test)]
use reviews::{normalize_review_prefix, query_reviews};
#[cfg(test)]
use workload::query_workload;
use rusqlite::Connection;
use serde::Serialize;
use crate::Config;
use crate::cli::WhoArgs;
use crate::cli::render::Theme;
use crate::cli::robot::RobotMeta;
use crate::core::db::create_connection;
use crate::core::error::{LoreError, Result};
use crate::core::path_resolver::normalize_repo_path;
use crate::core::paths::get_db_path;
use crate::core::project::resolve_project;
use crate::core::time::{ms_to_iso, now_ms, parse_since, parse_since_from};
#[cfg(test)]
use crate::core::config::ScoringConfig;
#[cfg(test)]
use crate::core::path_resolver::{SuffixResult, build_path_query, escape_like, suffix_probe};
// ─── Mode Discrimination ────────────────────────────────────────────────────
/// Determines which query mode to run based on args.
/// Path variants own their strings because path normalization produces new `String`s.
/// Username variants borrow from args since no normalization is needed.
enum WhoMode<'a> {
/// lore who <file-path> OR lore who --path <path>
Expert { path: String },
/// lore who <username>
Workload { username: &'a str },
/// lore who <username> --reviews
Reviews { username: &'a str },
/// lore who --active
Active,
/// lore who --overlap <path>
Overlap { path: String },
}
fn resolve_mode<'a>(args: &'a WhoArgs) -> Result<WhoMode<'a>> {
// Explicit --path flag always wins (handles root files like README.md,
// LICENSE, Makefile -- anything without a / that can't be auto-detected)
if let Some(p) = &args.path {
return Ok(WhoMode::Expert {
path: normalize_repo_path(p),
});
}
if args.active {
return Ok(WhoMode::Active);
}
if let Some(path) = &args.overlap {
return Ok(WhoMode::Overlap {
path: normalize_repo_path(path),
});
}
if let Some(target) = &args.target {
let clean = target.strip_prefix('@').unwrap_or(target);
if args.reviews {
return Ok(WhoMode::Reviews { username: clean });
}
// Disambiguation: if target contains '/', it's a file path.
// GitLab usernames never contain '/'.
// Root files (no '/') require --path.
if clean.contains('/') {
return Ok(WhoMode::Expert {
path: normalize_repo_path(clean),
});
}
return Ok(WhoMode::Workload { username: clean });
}
Err(LoreError::Other(
"Provide a username, file path, --active, or --overlap <path>.\n\n\
Examples:\n \
lore who src/features/auth/\n \
lore who @username\n \
lore who --active\n \
lore who --overlap src/features/\n \
lore who --path README.md\n \
lore who --path Makefile"
.to_string(),
))
}
fn validate_mode_flags(mode: &WhoMode<'_>, args: &WhoArgs) -> Result<()> {
if args.detail && !matches!(mode, WhoMode::Expert { .. }) {
return Err(LoreError::Other(
"--detail is only supported in expert mode (`lore who --path <path>` or `lore who <path/with/slash>`).".to_string(),
));
}
Ok(())
}
// ─── Entry Point ─────────────────────────────────────────────────────────────
/// Main entry point. Resolves mode + resolved inputs once, then dispatches.
pub fn run_who(config: &Config, args: &WhoArgs) -> Result<WhoRun> {
let db_path = get_db_path(config.storage.db_path.as_deref());
let conn = create_connection(&db_path)?;
let project_id = args
.project
.as_deref()
.map(|p| resolve_project(&conn, p))
.transpose()?;
let project_path = project_id
.map(|id| lookup_project_path(&conn, id))
.transpose()?;
let mode = resolve_mode(args)?;
validate_mode_flags(&mode, args)?;
// since_mode semantics:
// - expert/reviews/active/overlap: default window applies if args.since is None -> "default"
// - workload: no default window; args.since None => "none"
let since_mode_for_defaulted = if args.since.is_some() {
"explicit"
} else {
"default"
};
let since_mode_for_workload = if args.since.is_some() {
"explicit"
} else {
"none"
};
let limit = args.limit.map_or(usize::MAX, usize::from);
match mode {
WhoMode::Expert { path } => {
// Compute as_of first so --since durations are relative to it.
let as_of_ms = match &args.as_of {
Some(v) => parse_since(v).ok_or_else(|| {
LoreError::Other(format!(
"Invalid --as-of value: '{v}'. Use a duration (30d, 6m) or date (2024-01-15)"
))
})?,
None => now_ms(),
};
let since_ms = if args.all_history {
0
} else {
resolve_since_from(args.since.as_deref(), "24m", as_of_ms)?
};
let result = expert::query_expert(
&conn,
&path,
project_id,
since_ms,
as_of_ms,
limit,
&config.scoring,
args.detail,
args.explain_score,
args.include_bots,
)?;
Ok(WhoRun {
resolved_input: WhoResolvedInput {
mode: "expert".to_string(),
project_id,
project_path,
since_ms: Some(since_ms),
since_iso: Some(ms_to_iso(since_ms)),
since_mode: since_mode_for_defaulted.to_string(),
limit: args.limit,
},
result: WhoResult::Expert(result),
})
}
WhoMode::Workload { username } => {
let since_ms = args
.since
.as_deref()
.map(resolve_since_required)
.transpose()?;
let result = workload::query_workload(
&conn,
username,
project_id,
since_ms,
limit,
args.include_closed,
)?;
Ok(WhoRun {
resolved_input: WhoResolvedInput {
mode: "workload".to_string(),
project_id,
project_path,
since_ms,
since_iso: since_ms.map(ms_to_iso),
since_mode: since_mode_for_workload.to_string(),
limit: args.limit,
},
result: WhoResult::Workload(result),
})
}
WhoMode::Reviews { username } => {
let since_ms = resolve_since(args.since.as_deref(), "6m")?;
let result = reviews::query_reviews(&conn, username, project_id, since_ms)?;
Ok(WhoRun {
resolved_input: WhoResolvedInput {
mode: "reviews".to_string(),
project_id,
project_path,
since_ms: Some(since_ms),
since_iso: Some(ms_to_iso(since_ms)),
since_mode: since_mode_for_defaulted.to_string(),
limit: args.limit,
},
result: WhoResult::Reviews(result),
})
}
WhoMode::Active => {
let since_ms = resolve_since(args.since.as_deref(), "7d")?;
let result =
active::query_active(&conn, project_id, since_ms, limit, args.include_closed)?;
Ok(WhoRun {
resolved_input: WhoResolvedInput {
mode: "active".to_string(),
project_id,
project_path,
since_ms: Some(since_ms),
since_iso: Some(ms_to_iso(since_ms)),
since_mode: since_mode_for_defaulted.to_string(),
limit: args.limit,
},
result: WhoResult::Active(result),
})
}
WhoMode::Overlap { path } => {
let since_ms = resolve_since(args.since.as_deref(), "30d")?;
let result = overlap::query_overlap(&conn, &path, project_id, since_ms, limit)?;
Ok(WhoRun {
resolved_input: WhoResolvedInput {
mode: "overlap".to_string(),
project_id,
project_path,
since_ms: Some(since_ms),
since_iso: Some(ms_to_iso(since_ms)),
since_mode: since_mode_for_defaulted.to_string(),
limit: args.limit,
},
result: WhoResult::Overlap(result),
})
}
}
}
// ─── Helpers ─────────────────────────────────────────────────────────────────
/// Look up the project path for a resolved project ID.
fn lookup_project_path(conn: &Connection, project_id: i64) -> Result<String> {
conn.query_row(
"SELECT path_with_namespace FROM projects WHERE id = ?1",
rusqlite::params![project_id],
|row| row.get(0),
)
.map_err(|e| LoreError::Other(format!("Failed to look up project path: {e}")))
}
/// Parse --since with a default fallback.
fn resolve_since(input: Option<&str>, default: &str) -> Result<i64> {
let s = input.unwrap_or(default);
parse_since(s).ok_or_else(|| {
LoreError::Other(format!(
"Invalid --since value: '{s}'. Use a duration (7d, 2w, 6m) or date (2024-01-15)"
))
})
}
/// Parse --since with a default fallback, relative to a reference timestamp.
/// Durations (7d, 2w, 6m) are computed from `reference_ms` instead of now.
fn resolve_since_from(input: Option<&str>, default: &str, reference_ms: i64) -> Result<i64> {
let s = input.unwrap_or(default);
parse_since_from(s, reference_ms).ok_or_else(|| {
LoreError::Other(format!(
"Invalid --since value: '{s}'. Use a duration (7d, 2w, 6m) or date (2024-01-15)"
))
})
}
/// Parse --since without a default (returns error if invalid).
fn resolve_since_required(input: &str) -> Result<i64> {
parse_since(input).ok_or_else(|| {
LoreError::Other(format!(
"Invalid --since value: '{input}'. Use a duration (7d, 2w, 6m) or date (2024-01-15)"
))
})
}
// ─── Human Output ────────────────────────────────────────────────────────────
pub fn print_who_human(result: &WhoResult, project_path: Option<&str>) {
match result {
WhoResult::Expert(r) => expert::print_expert_human(r, project_path),
WhoResult::Workload(r) => workload::print_workload_human(r),
WhoResult::Reviews(r) => reviews::print_reviews_human(r),
WhoResult::Active(r) => active::print_active_human(r, project_path),
WhoResult::Overlap(r) => overlap::print_overlap_human(r, project_path),
}
}
/// Print a dim hint when results aggregate across all projects.
pub(super) fn print_scope_hint(project_path: Option<&str>) {
if project_path.is_none() {
println!(
" {}",
Theme::dim().render("(aggregated across all projects; use -p to scope)")
);
}
}
// ─── Robot JSON Output ───────────────────────────────────────────────────────
pub fn print_who_json(run: &WhoRun, args: &WhoArgs, elapsed_ms: u64) {
let (mode, data) = match &run.result {
WhoResult::Expert(r) => ("expert", expert::expert_to_json(r)),
WhoResult::Workload(r) => ("workload", workload::workload_to_json(r)),
WhoResult::Reviews(r) => ("reviews", reviews::reviews_to_json(r)),
WhoResult::Active(r) => ("active", active::active_to_json(r)),
WhoResult::Overlap(r) => ("overlap", overlap::overlap_to_json(r)),
};
// Raw CLI args -- what the user typed
let input = serde_json::json!({
"target": args.target,
"path": args.path,
"project": args.project,
"since": args.since,
"limit": args.limit,
"detail": args.detail,
"as_of": args.as_of,
"explain_score": args.explain_score,
"include_bots": args.include_bots,
"all_history": args.all_history,
});
// Resolved/computed values -- what actually ran
let resolved_input = serde_json::json!({
"mode": run.resolved_input.mode,
"project_id": run.resolved_input.project_id,
"project_path": run.resolved_input.project_path,
"since_ms": run.resolved_input.since_ms,
"since_iso": run.resolved_input.since_iso,
"since_mode": run.resolved_input.since_mode,
"limit": run.resolved_input.limit,
});
let output = WhoJsonEnvelope {
ok: true,
data: WhoJsonData {
mode: mode.to_string(),
input,
resolved_input,
result: data,
},
meta: RobotMeta { elapsed_ms },
};
let mut value = serde_json::to_value(&output).unwrap_or_else(|e| {
serde_json::json!({"ok":false,"error":{"code":"INTERNAL_ERROR","message":format!("JSON serialization failed: {e}")}})
});
if let Some(f) = &args.fields {
let preset_key = format!("who_{mode}");
let expanded = crate::cli::robot::expand_fields_preset(f, &preset_key);
// Each who mode uses a different array key; try all possible keys
for key in &[
"experts",
"assigned_issues",
"authored_mrs",
"review_mrs",
"categories",
"discussions",
"users",
] {
crate::cli::robot::filter_fields(&mut value, key, &expanded);
}
}
match serde_json::to_string(&value) {
Ok(json) => println!("{json}"),
Err(e) => eprintln!("Error serializing to JSON: {e}"),
}
}
#[derive(Serialize)]
struct WhoJsonEnvelope {
ok: bool,
data: WhoJsonData,
meta: RobotMeta,
}
#[derive(Serialize)]
struct WhoJsonData {
mode: String,
input: serde_json::Value,
resolved_input: serde_json::Value,
#[serde(flatten)]
result: serde_json::Value,
}
// ─── Tests ───────────────────────────────────────────────────────────────────
#[cfg(test)]
#[path = "../who_tests.rs"]
mod tests;