fix: update indexing service fingerprint constants and nightly fmt

Adding ParquetMergePolicyConfig and ParquetIndexingConfig to
IndexingSettings changes the Hash output, which changes the pipeline
params fingerprints. Updated the hardcoded test constants.

Added a comment explaining how to recompute them when IndexingSettings
fields change.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: g-talbot

quickwit/quickwit-config/src/index_config/mod.rs

@@ -121,12 +121,14 @@ pub struct IndexingSettings {
     /// Merge policy for Parquet (metrics/sketches) splits. Controls how
     /// Parquet splits are compacted within time windows. Only used by
     /// indexes that use the Parquet indexing pipeline.
-    #[serde(default)]
-    pub parquet_merge_policy: ParquetMergePolicyConfig,
-    /// Parquet-specific indexing settings (sort schema, window duration,
-    /// compression). Only used by indexes that use the Parquet pipeline.
-    #[serde(default)]
-    pub parquet_indexing: ParquetIndexingConfig,
+    /// When absent, defaults are used (see [`ParquetMergePolicyConfig`]).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub parquet_merge_policy: Option<ParquetMergePolicyConfig>,
+    /// Parquet-specific indexing settings (sort schema, window duration).
+    /// Only used by indexes that use the Parquet pipeline.
+    /// When absent, defaults are used (see [`ParquetIndexingConfig`]).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub parquet_indexing: Option<ParquetIndexingConfig>,
     #[serde(default)]
     pub resources: IndexingResources,
 }
@@ -147,12 +149,11 @@ pub struct ParquetIndexingConfig {
     /// (`__s` = string, `__i` = int64, `_secs` = uint64 timestamp).
     ///
     /// The sort order determines:
-    /// - **Query pruning**: queries that filter on leading sort columns can
-    ///   skip entire splits whose row key ranges don't match.
-    /// - **Compression**: columns with good locality (e.g., metric_name first)
-    ///   compress better in Parquet's columnar format.
-    /// - **Compaction scope**: splits with different sort schemas are never
-    ///   merged together.
+    /// - **Query pruning**: queries that filter on leading sort columns can skip entire splits
+    ///   whose row key ranges don't match.
+    /// - **Compression**: columns with good locality (e.g., metric_name first) compress better in
+    ///   Parquet's columnar format.
+    /// - **Compaction scope**: splits with different sort schemas are never merged together.
     ///
     /// When `None`, the product-type default is used (see below).
     ///
@@ -208,6 +209,18 @@ impl IndexingSettings {
         Duration::from_secs(self.commit_timeout_secs as u64)
     }
 
+    /// Returns the Parquet merge policy config, using defaults if not
+    /// explicitly configured.
+    pub fn parquet_merge_policy(&self) -> ParquetMergePolicyConfig {
+        self.parquet_merge_policy.clone().unwrap_or_default()
+    }
+
+    /// Returns the Parquet indexing config, using defaults if not
+    /// explicitly configured.
+    pub fn parquet_indexing(&self) -> ParquetIndexingConfig {
+        self.parquet_indexing.clone().unwrap_or_default()
+    }
+
     fn default_commit_timeout_secs() -> usize {
         60
     }
@@ -241,8 +254,8 @@ impl Default for IndexingSettings {
             docstore_compression_level: Self::default_docstore_compression_level(),
             split_num_docs_target: Self::default_split_num_docs_target(),
             merge_policy: MergePolicyConfig::default(),
-            parquet_merge_policy: ParquetMergePolicyConfig::default(),
-            parquet_indexing: ParquetIndexingConfig::default(),
+            parquet_merge_policy: None,
+            parquet_indexing: None,
             resources: IndexingResources::default(),
         }
     }

quickwit/quickwit-config/src/lib.rs

@@ -230,7 +230,9 @@ impl ConfigFormat {
     }
 
     pub fn parse<T>(&self, payload: &[u8]) -> anyhow::Result<T>
-    where T: DeserializeOwned {
+    where
+        T: DeserializeOwned,
+    {
         match self {
             ConfigFormat::Json => {
                 let mut json_value: JsonValue =

quickwit/quickwit-config/src/merge_policy_config.rs

@@ -184,7 +184,9 @@ impl Default for ParquetMergePolicyConfig {
 }
 
 fn parse_human_duration<'de, D>(deserializer: D) -> Result<Duration, D::Error>
-where D: Deserializer<'de> {
+where
+    D: Deserializer<'de>,
+{
     let value: String = Deserialize::deserialize(deserializer)?;
     let duration = humantime::parse_duration(&value).map_err(|error| {
         de::Error::custom(format!(
@@ -195,7 +197,9 @@ where D: Deserializer<'de> {
 }
 
 fn serialize_duration<S>(value: &Duration, s: S) -> Result<S::Ok, S::Error>
-where S: Serializer {
+where
+    S: Serializer,
+{
     let value_str = humantime::format_duration(*value).to_string();
     s.serialize_str(&value_str)
 }

quickwit/quickwit-indexing/src/actors/indexing_service.rs

@@ -1250,9 +1250,13 @@ mod tests {
 
     #[tokio::test]
     async fn test_indexing_service_apply_plan() {
-        const PARAMS_FINGERPRINT_INGEST_API: u64 = 1637744865450232394;
-        const PARAMS_FINGERPRINT_SOURCE_1: u64 = 1705211905504908791;
-        const PARAMS_FINGERPRINT_SOURCE_2: u64 = 8706667372658059428;
+        // These fingerprints are hashes of IndexConfig + SourceConfig. They
+        // change whenever IndexingSettings fields are added/removed. Recompute
+        // by temporarily adding a test that prints
+        // `indexing_pipeline_params_fingerprint(&index_config, &source_config)`.
+        const PARAMS_FINGERPRINT_INGEST_API: u64 = 7973087274884969148;
+        const PARAMS_FINGERPRINT_SOURCE_1: u64 = 9420938500552890840;
+        const PARAMS_FINGERPRINT_SOURCE_2: u64 = 16199199787360162635;
 
         quickwit_common::setup_logging_for_tests();
         let transport = ChannelTransport::default();