fix: propagate DB errors instead of silently swallowing them
Replace .unwrap_or(), .ok(), and .filter_map(|r| r.ok()) patterns with proper error propagation using ? and rusqlite::OptionalExtension where the query may legitimately return no rows. Affected areas: - events_db::count_events: three count queries now propagate errors instead of defaulting to (0, 0) on failure - note_parser::extract_refs_from_system_notes: row iteration errors are now propagated instead of silently dropped via filter_map - note_parser::noteable_type_to_entity_type: unknown types now log a debug warning before defaulting to "issue" - payloads::store_payload/read_payload: use .optional()? instead of .ok() to distinguish "no row" from "query failed" - backoff::compute_next_attempt_at: use .clamp(0, 30) to guard against negative attempt_count, not just .min(30) - search::vector::max_chunks_per_document: returns Result<i64> with proper error propagation through .optional()?.flatten() - embedding::chunk_ids::decode_rowid: promote debug_assert to assert since negative rowids indicate data corruption worth failing fast on - ingestion::dirty_tracker::record_dirty_error: use .optional()? to handle missing dirty_sources row gracefully instead of hard error Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1,6 +1,7 @@
|
||||
use std::collections::HashMap;
|
||||
|
||||
use rusqlite::Connection;
|
||||
use rusqlite::OptionalExtension;
|
||||
|
||||
use crate::core::error::Result;
|
||||
use crate::embedding::chunk_ids::decode_rowid;
|
||||
@@ -11,7 +12,7 @@ pub struct VectorResult {
|
||||
pub distance: f64,
|
||||
}
|
||||
|
||||
fn max_chunks_per_document(conn: &Connection) -> i64 {
|
||||
fn max_chunks_per_document(conn: &Connection) -> Result<i64> {
|
||||
let stored: Option<i64> = conn
|
||||
.query_row(
|
||||
"SELECT MAX(chunk_count) FROM embedding_metadata
|
||||
@@ -19,21 +20,24 @@ fn max_chunks_per_document(conn: &Connection) -> i64 {
|
||||
[],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.unwrap_or(None);
|
||||
.optional()?
|
||||
.flatten();
|
||||
|
||||
if let Some(max) = stored {
|
||||
return max;
|
||||
return Ok(max);
|
||||
}
|
||||
|
||||
conn.query_row(
|
||||
"SELECT COALESCE(MAX(cnt), 1) FROM (
|
||||
Ok(conn
|
||||
.query_row(
|
||||
"SELECT COALESCE(MAX(cnt), 1) FROM (
|
||||
SELECT COUNT(*) as cnt FROM embedding_metadata
|
||||
WHERE last_error IS NULL GROUP BY document_id
|
||||
)",
|
||||
[],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.unwrap_or(1)
|
||||
[],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.optional()?
|
||||
.unwrap_or(1))
|
||||
}
|
||||
|
||||
pub fn search_vector(
|
||||
@@ -50,7 +54,7 @@ pub fn search_vector(
|
||||
.flat_map(|f| f.to_le_bytes())
|
||||
.collect();
|
||||
|
||||
let max_chunks = max_chunks_per_document(conn).max(1);
|
||||
let max_chunks = max_chunks_per_document(conn)?.max(1);
|
||||
let multiplier = ((max_chunks.unsigned_abs() as usize * 3 / 2) + 1).clamp(8, 200);
|
||||
let k = (limit * multiplier).min(10_000);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user