theirongolddev/gitlore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: Apply cargo fmt and clippy fixes across codebase

Browse Source 
Automated formatting and lint corrections from parallel agent work:

- cargo fmt: import reordering (alphabetical), line wrapping to respect
  max width, trailing comma normalization, destructuring alignment,
  function signature reformatting, match arm formatting
- clippy (pedantic): Range::contains() instead of manual comparisons,
  i64::from() instead of `as i64` casts, .clamp() instead of
  .max().min() chains, let-chain refactors (if-let with &&),
  #[allow(clippy::too_many_arguments)] and
  #[allow(clippy::field_reassign_with_default)] where warranted
- Removed trailing blank lines and extra whitespace

No behavioral changes. All existing tests pass unmodified.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Taylor Eernisse
2026-02-03 13:01:59 -05:00
parent ff94f24702
commit a50fc78823
42 changed files with 1431 additions and 623 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
src/embedding/pipeline.rs
View File

@@ -8,8 +8,8 @@ use tracing::{info, warn};
use crate::core::error::Result;
use crate::embedding::change_detector::{count_pending_documents, find_pending_documents};
use crate::embedding::chunk_ids::{encode_rowid, CHUNK_ROWID_MULTIPLIER};
use crate::embedding::chunking::{split_into_chunks, CHUNK_MAX_BYTES, EXPECTED_DIMS};
use crate::embedding::chunk_ids::{CHUNK_ROWID_MULTIPLIER, encode_rowid};
use crate::embedding::chunking::{CHUNK_MAX_BYTES, EXPECTED_DIMS, split_into_chunks};
use crate::embedding::ollama::OllamaClient;
const BATCH_SIZE: usize = 32;
@@ -211,11 +211,14 @@ pub async fn embed_documents(
|| (err_lower.contains("413") && err_lower.contains("http"));
if is_context_error && batch.len() > 1 {
warn!("Batch failed with context length error, retrying chunks individually");
warn!(
"Batch failed with context length error, retrying chunks individually"
);
for chunk in batch {
match client.embed_batch(vec![chunk.text.clone()]).await {
Ok(embeddings) if !embeddings.is_empty()
&& embeddings[0].len() == EXPECTED_DIMS =>
Ok(embeddings)
if !embeddings.is_empty()
&& embeddings[0].len() == EXPECTED_DIMS =>
{
// Clear old embeddings on first successful chunk
if !cleared_docs.contains(&chunk.doc_id) {
@@ -272,7 +275,6 @@ pub async fn embed_documents(
}
}
}
}
// Fire progress for all normal documents after embedding completes.
@@ -314,6 +316,7 @@ fn clear_document_embeddings(conn: &Connection, document_id: i64) -> Result<()>
}
/// Store an embedding vector and its metadata.
#[allow(clippy::too_many_arguments)]
fn store_embedding(
conn: &Connection,
doc_id: i64,
@@ -347,8 +350,15 @@ fn store_embedding(
created_at, attempt_count, last_error, chunk_max_bytes, chunk_count)
VALUES (?1, ?2, ?3, ?4, ?5, ?6, ?7, 1, NULL, ?8, ?9)",
rusqlite::params![
doc_id, chunk_index as i64, model_name, EXPECTED_DIMS as i64,
doc_hash, chunk_hash, now, CHUNK_MAX_BYTES as i64, chunk_count
doc_id,
chunk_index as i64,
model_name,
EXPECTED_DIMS as i64,
doc_hash,
chunk_hash,
now,
CHUNK_MAX_BYTES as i64,
chunk_count
],
)?;
@@ -377,8 +387,15 @@ fn record_embedding_error(
last_attempt_at = ?7,
chunk_max_bytes = ?9",
rusqlite::params![
doc_id, chunk_index as i64, model_name, EXPECTED_DIMS as i64,
doc_hash, chunk_hash, now, error, CHUNK_MAX_BYTES as i64
doc_id,
chunk_index as i64,
model_name,
EXPECTED_DIMS as i64,
doc_hash,
chunk_hash,
now,
error,
CHUNK_MAX_BYTES as i64
],
)?;
Ok(())