Merge branch 'main' into refactor/wal-naming

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

nodejs/src/blob.rs

@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use std::future::Future;
+use std::ops::Range;
+use std::sync::Arc;
+use std::sync::atomic::{AtomicBool, Ordering};
+
+use arrow_array::{Array, LargeBinaryArray};
+use futures::future::abortable;
+use lancedb::blob::BlobFile as LanceBlobFile;
+use napi::Env;
+use napi::bindgen_prelude::*;
+use napi_derive::napi;
+
+use crate::error::convert_error;
+
+#[napi(object)]
+pub struct BlobRange {
+    pub start: BigInt,
+    pub end: BigInt,
+}
+
+#[napi]
+pub struct BlobFile {
+    inner: Arc<LanceBlobFile>,
+    closed: AtomicBool,
+}
+
+impl BlobFile {
+    pub(crate) fn new(inner: LanceBlobFile) -> Self {
+        Self {
+            inner: Arc::new(inner),
+            closed: AtomicBool::new(false),
+        }
+    }
+
+    fn ensure_open(&self) -> napi::Result<()> {
+        if self.closed.load(Ordering::Acquire) {
+            Err(napi::Error::from_reason("blob file is already closed"))
+        } else {
+            Ok(())
+        }
+    }
+}
+
+#[napi]
+impl BlobFile {
+    #[napi]
+    pub fn size(&self) -> BigInt {
+        BigInt::from(self.inner.size())
+    }
+
+    #[napi]
+    pub fn read<'env>(
+        &self,
+        env: &'env Env,
+        max_bytes: Option<BigInt>,
+        signal: Option<AbortSignal>,
+    ) -> napi::Result<PromiseRaw<'env, Buffer>> {
+        self.ensure_open()?;
+        let max_bytes = max_bytes
+            .map(|max_bytes| {
+                usize::try_from(parse_u64(max_bytes, "maxBytes")?)
+                    .map_err(|_| napi::Error::from_reason("maxBytes is too large"))
+            })
+            .transpose()?;
+        let inner = self.inner.clone();
+        spawn_abortable(env, signal, async move {
+            let bytes = match max_bytes {
+                None => inner.read().await,
+                Some(max_bytes) => inner.read_up_to(max_bytes).await,
+            }
+            .map_err(|err| convert_error(&err))?;
+            Ok(Buffer::from(bytes.as_ref()))
+        })
+    }
+
+    #[napi]
+    pub fn read_range<'env>(
+        &self,
+        env: &'env Env,
+        start: BigInt,
+        end: BigInt,
+        signal: Option<AbortSignal>,
+    ) -> napi::Result<PromiseRaw<'env, Buffer>> {
+        self.ensure_open()?;
+        let range = bigint_range(start, end)?;
+        let inner = self.inner.clone();
+        spawn_abortable(env, signal, async move {
+            let bytes = inner
+                .read_range(range)
+                .await
+                .map_err(|err| convert_error(&err))?;
+            Ok(Buffer::from(bytes.as_ref()))
+        })
+    }
+
+    #[napi]
+    pub fn read_ranges<'env>(
+        &self,
+        env: &'env Env,
+        ranges: Vec<BlobRange>,
+        signal: Option<AbortSignal>,
+    ) -> napi::Result<PromiseRaw<'env, Vec<Buffer>>> {
+        self.ensure_open()?;
+        let ranges = ranges
+            .into_iter()
+            .map(|range| bigint_range(range.start, range.end))
+            .collect::<napi::Result<Vec<_>>>()?;
+        let inner = self.inner.clone();
+        spawn_abortable(env, signal, async move {
+            let buffers = inner
+                .read_ranges(&ranges)
+                .await
+                .map_err(|err| convert_error(&err))?;
+            Ok(buffers
+                .iter()
+                .map(|bytes| Buffer::from(bytes.as_ref()))
+                .collect())
+        })
+    }
+
+    #[napi]
+    pub async fn seek(&self, position: BigInt) -> napi::Result<()> {
+        self.ensure_open()?;
+        let position = parse_u64(position, "position")?;
+        self.inner
+            .seek(position)
+            .await
+            .map_err(|err| convert_error(&err))
+    }
+
+    #[napi]
+    pub async fn tell(&self) -> napi::Result<BigInt> {
+        self.ensure_open()?;
+        let position = self.inner.tell().await.map_err(|err| convert_error(&err))?;
+        Ok(BigInt::from(position))
+    }
+
+    #[napi]
+    pub async fn close(&self) -> napi::Result<()> {
+        if self.closed.swap(true, Ordering::AcqRel) {
+            return Ok(());
+        }
+        self.inner.close().await.map_err(|err| convert_error(&err))
+    }
+
+    #[napi]
+    pub fn is_closed(&self) -> bool {
+        self.closed.load(Ordering::Acquire)
+    }
+}
+
+/// Runs `fut` on the napi runtime. Aborting `signal` drops the future, which
+/// cancels in-flight reads.
+pub fn spawn_abortable<'env, T>(
+    env: &'env Env,
+    signal: Option<AbortSignal>,
+    fut: impl Future<Output = napi::Result<T>> + Send + 'static,
+) -> napi::Result<PromiseRaw<'env, T>>
+where
+    T: ToNapiValue + Send + 'static,
+{
+    let (fut, handle) = abortable(fut);
+    if let Some(signal) = signal {
+        signal.on_abort(move || handle.abort());
+    }
+    env.spawn_future(async move {
+        fut.await
+            .unwrap_or_else(|_| Err(napi::Error::from_reason("blob read aborted")))
+    })
+}
+
+fn bigint_range(start: BigInt, end: BigInt) -> napi::Result<Range<u64>> {
+    let start = parse_u64(start, "start")?;
+    let end = parse_u64(end, "end")?;
+    if start > end {
+        return Err(napi::Error::from_reason(format!(
+            "invalid blob range: start ({start}) > end ({end})"
+        )));
+    }
+    Ok(start..end)
+}
+
+fn parse_u64(value: BigInt, name: &str) -> napi::Result<u64> {
+    let (negative, value, lossless) = value.get_u64();
+    if negative {
+        return Err(napi::Error::from_reason(format!(
+            "{name} cannot be negative"
+        )));
+    }
+    if !lossless {
+        return Err(napi::Error::from_reason(format!(
+            "{name} is too large to fit in u64"
+        )));
+    }
+    Ok(value)
+}
+
+pub fn parse_row_ids(row_ids: Vec<BigInt>) -> napi::Result<Vec<u64>> {
+    row_ids
+        .into_iter()
+        .map(|id| parse_u64(id, "row id"))
+        .collect()
+}
+
+pub fn copy_blob_buffers(array: LargeBinaryArray) -> Vec<Option<Buffer>> {
+    (0..array.len())
+        .map(|i| {
+            if array.is_null(i) {
+                None
+            } else {
+                Some(Buffer::from(array.value(i).to_vec()))
+            }
+        })
+        .collect()
+}

nodejs/src/catalog.rs

@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use std::sync::{Arc, Mutex};
+use std::time::Duration;
+
+use futures::{StreamExt, future::poll_fn};
+
+use lancedb::catalog::{CatalogConnection, CreateDatabaseRequest, DropDatabaseRequest};
+use napi::bindgen_prelude::*;
+use napi_derive::napi;
+
+use crate::connection::Connection;
+use crate::error::NapiErrorExt;
+use crate::header::JsHeaderProvider;
+use crate::remote::{ClientConfig, OAuthConfig};
+
+#[napi(object)]
+pub struct CatalogOptions {
+    pub api_key: Option<String>,
+    pub client_config: Option<ClientConfig>,
+    /// SQL service endpoint inherited by database connections.
+    pub sql_host_override: Option<String>,
+    pub read_consistency_interval: Option<f64>,
+    pub oauth_config: Option<OAuthConfig>,
+}
+
+/// A lazy iterator over database names with inspectable pagination state.
+#[napi]
+pub struct DatabaseNames {
+    inner: Mutex<lancedb::catalog::DatabaseNames>,
+    next_lock: futures::lock::Mutex<()>,
+}
+
+#[napi]
+impl DatabaseNames {
+    /// Number of names cached without another REST request.
+    #[napi]
+    pub fn num_page_results(&self) -> u32 {
+        self.inner.lock().unwrap().num_page_results() as u32
+    }
+
+    /// Continuation token for the next REST request.
+    #[napi]
+    pub fn page_token(&self) -> Option<String> {
+        self.inner.lock().unwrap().page_token().map(str::to_owned)
+    }
+
+    /// Fetch the next name, returning None when exhausted.
+    #[napi]
+    pub async fn next(&self) -> Result<Option<String>> {
+        // Serialize advances but allow synchronous inspection between polls.
+        let _guard = self.next_lock.lock().await;
+        poll_fn(|cx| self.inner.lock().unwrap().poll_next_unpin(cx))
+            .await
+            .transpose()
+            .default_error()
+    }
+}
+
+#[napi]
+pub struct Catalog {
+    inner: CatalogConnection,
+}
+
+#[napi]
+impl Catalog {
+    #[napi(factory)]
+    pub async fn new(
+        endpoint: String,
+        options: CatalogOptions,
+        header_provider: Option<&JsHeaderProvider>,
+    ) -> Result<Self> {
+        let mut builder = lancedb::connect_catalog(endpoint);
+        if let Some(key) = options.api_key {
+            builder = builder.api_key(key);
+        }
+        let mut config: lancedb::remote::ClientConfig =
+            options.client_config.unwrap_or_default().into();
+        if let Some(provider) = header_provider {
+            config.header_provider = Some(Arc::new(provider.clone()));
+        }
+        builder = builder.client_config(config);
+        if let Some(endpoint) = options.sql_host_override {
+            builder = builder.sql_host_override(endpoint);
+        }
+        if let Some(interval) = options.read_consistency_interval {
+            let interval = Duration::try_from_secs_f64(interval).map_err(|err| {
+                Error::from_reason(format!("Invalid read consistency interval: {err}"))
+            })?;
+            builder = builder.read_consistency_interval(interval);
+        }
+        if let Some(oauth) = options.oauth_config {
+            builder = builder.oauth_config(oauth.try_into().default_error()?);
+        }
+        Ok(Self {
+            inner: builder.execute().await.default_error()?,
+        })
+    }
+
+    #[napi(getter)]
+    pub fn uri(&self) -> String {
+        self.inner.uri().to_string()
+    }
+
+    #[napi]
+    pub async fn create_database(
+        &self,
+        name: String,
+        exist_ok: Option<bool>,
+    ) -> Result<Connection> {
+        self.inner
+            .create_database(CreateDatabaseRequest::new(name).exist_ok(exist_ok.unwrap_or(false)))
+            .await
+            .map(Connection::inner_new)
+            .default_error()
+    }
+    #[napi]
+    pub async fn connect_database(&self, name: String) -> Result<Connection> {
+        self.inner
+            .connect_database(name)
+            .await
+            .map(Connection::inner_new)
+            .default_error()
+    }
+    #[napi]
+    pub async fn drop_database(&self, name: String, ignore_missing: Option<bool>) -> Result<()> {
+        self.inner
+            .drop_database(
+                DropDatabaseRequest::new(name).ignore_missing(ignore_missing.unwrap_or(false)),
+            )
+            .await
+            .default_error()
+    }
+    #[napi]
+    pub fn list_databases(
+        &self,
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> DatabaseNames {
+        DatabaseNames {
+            inner: Mutex::new(self.inner.list_databases(page_token, page_limit)),
+            next_lock: futures::lock::Mutex::new(()),
+        }
+    }
+}

nodejs/src/connection.rs

@@ -55,6 +55,32 @@ pub struct DropNamespaceResponse {
     pub transaction_id: Option<Vec<String>>,
 }
 
+/// What a database records about one view.
+#[napi(object)]
+pub struct ViewDescription {
+    pub name: String,
+    pub namespace_path: Vec<String>,
+    pub query: String,
+    pub default_database: String,
+    pub default_namespace_path: Vec<String>,
+    /// The view's schema as an empty Arrow IPC file, the way a table reports
+    /// its own.
+    pub schema: Buffer,
+}
+
+impl ViewDescription {
+    fn from_inner(view: lancedb::view::ViewDescription) -> napi::Result<Self> {
+        Ok(Self {
+            name: view.name,
+            namespace_path: view.namespace_path,
+            query: view.query,
+            default_database: view.default_database,
+            default_namespace_path: view.default_namespace_path,
+            schema: crate::util::schema_to_buffer(&view.schema)?,
+        })
+    }
+}
+
 impl Connection {
     pub(crate) fn inner_new(inner: LanceDBConnection) -> Self {
         Self { inner: Some(inner) }
@@ -308,6 +334,7 @@ impl Connection {
         projections: Option<Vec<Vec<String>>>,
         filter: Option<String>,
         limit: Option<i64>,
+        with_no_data: bool,
     ) -> napi::Result<Table> {
         let mut builder = self.get_inner()?.create_materialized_view(name, source);
         if let Some(projections) = projections {
@@ -328,6 +355,7 @@ impl Connection {
                 .map_err(|_| napi::Error::from_reason("limit must be a non-negative integer"))?;
             builder = builder.limit(limit);
         }
+        builder = builder.with_no_data(with_no_data);
         let view = builder.execute().await.default_error()?;
         Ok(Table::new(view.table().clone()))
     }
@@ -343,13 +371,125 @@ impl Connection {
     }
 
     #[napi(catch_unwind)]
-    pub async fn list_materialized_views(&self) -> napi::Result<Vec<String>> {
-        let views = self
+    pub fn list_materialized_views(
+        &self,
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> napi::Result<crate::listing::NameListing> {
+        Ok(crate::listing::NameListing::new(
+            self.get_inner()?
+                .list_materialized_views(crate::listing::options(page_token, page_limit)),
+        ))
+    }
+
+    /// Drop a materialized view.
+    #[napi(catch_unwind)]
+    pub async fn drop_materialized_view(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<()> {
+        let ns = namespace_path.unwrap_or_default();
+        self.get_inner()?
+            .drop_materialized_view(&name, &ns)
+            .await
+            .default_error()
+    }
+
+    /// Create a view: a named query planned on every read.
+    #[napi(catch_unwind)]
+    pub async fn create_view(
+        &self,
+        name: String,
+        query: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<ViewDescription> {
+        let ns = namespace_path.unwrap_or_default();
+        let view = self
             .get_inner()?
-            .list_materialized_views()
+            .create_view(&name, &query, &ns)
             .await
             .default_error()?;
-        Ok(views.into_iter().map(|v| v.name).collect())
+        ViewDescription::from_inner(view)
+    }
+
+    /// What the database records about one view.
+    #[napi(catch_unwind)]
+    pub async fn describe_view(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<ViewDescription> {
+        let ns = namespace_path.unwrap_or_default();
+        let view = self
+            .get_inner()?
+            .describe_view(&name, &ns)
+            .await
+            .default_error()?;
+        ViewDescription::from_inner(view)
+    }
+
+    /// Drop a view and wait for its definition to be deleted. The tables it
+    /// reads are untouched.
+    #[napi(catch_unwind)]
+    pub async fn drop_view(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<()> {
+        let ns = namespace_path.unwrap_or_default();
+        self.get_inner()?
+            .drop_view(&name, &ns)
+            .await
+            .default_error()
+    }
+
+    /// Start dropping a view and return the job deleting its definition.
+    #[napi(catch_unwind)]
+    pub async fn drop_view_async(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<crate::job::Job> {
+        let ns = namespace_path.unwrap_or_default();
+        let job = self
+            .get_inner()?
+            .drop_view_async(&name, &ns)
+            .await
+            .default_error()?;
+        Ok(crate::job::Job::new(job))
+    }
+
+    /// The names of the views in one namespace.
+    #[napi(catch_unwind)]
+    pub fn list_views(
+        &self,
+        namespace_path: Option<Vec<String>>,
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> napi::Result<crate::listing::NameListing> {
+        Ok(crate::listing::NameListing::new(
+            self.get_inner()?.list_views(
+                &namespace_path.unwrap_or_default(),
+                crate::listing::options(page_token, page_limit),
+            ),
+        ))
+    }
+
+    /// Start dropping a materialized view and return its cleanup job.
+    #[napi(catch_unwind)]
+    pub async fn drop_materialized_view_async(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<crate::job::Job> {
+        let ns = namespace_path.unwrap_or_default();
+        let job = self
+            .get_inner()?
+            .drop_materialized_view_async(&name, &ns)
+            .await
+            .default_error()?;
+        Ok(crate::job::Job::new(job))
     }
 
     #[napi(catch_unwind)]
@@ -442,32 +582,29 @@ impl Connection {
         self.get_inner()?.drop_all_tables(&ns).await.default_error()
     }
 
-    /// A `Job` handle for a server-side job by id.
+    /// Open a server-side job by id, returning a handle with its record
+    /// already populated. Rejects when the server has no such job.
     ///
-    /// The handle is constructed without a server round trip; an unknown id
-    /// surfaces when the handle is used.
-    #[napi]
-    pub fn job(&self, job_id: String) -> napi::Result<crate::job::Job> {
-        let job = self.get_inner()?.job(job_id).default_error()?;
+    /// The returned handle answers for its own state, specification, result,
+    /// failure and event history, so there is no separate connection-level
+    /// call for any of them.
+    #[napi(catch_unwind)]
+    pub async fn open_job(&self, job_id: String) -> napi::Result<crate::job::Job> {
+        let job = self.get_inner()?.open_job(&job_id).await.default_error()?;
         Ok(crate::job::Job::new(job))
     }
 
     /// List server-side jobs across the database's tables.
     #[napi(catch_unwind)]
-    pub async fn list_jobs(&self) -> napi::Result<Vec<crate::job::JobInfo>> {
-        let jobs = self.get_inner()?.list_jobs().await.default_error()?;
-        Ok(jobs.into_iter().map(Into::into).collect())
-    }
-
-    /// Describe a single server-side job by id. `null` when the server has
-    /// no such job.
-    #[napi(catch_unwind)]
-    pub async fn get_job(
+    pub fn list_jobs(
         &self,
-        job_id: String,
-    ) -> napi::Result<Option<crate::job::JobDescription>> {
-        let description = self.get_inner()?.get_job(&job_id).await.default_error()?;
-        Ok(description.map(Into::into))
+        page_token: Option<String>,
+        page_limit: Option<u32>,
+    ) -> napi::Result<crate::listing::JobListing> {
+        Ok(crate::listing::JobListing::new(
+            self.get_inner()?
+                .list_jobs(crate::listing::options(page_token, page_limit)),
+        ))
     }
 
     /// Request cancellation of a server-side job by id. Returns true if the
@@ -477,32 +614,32 @@ impl Connection {
         self.get_inner()?.cancel_job(&job_id).await.default_error()
     }
 
-    /// The lifecycle event history of a server-side job (all jobs when
-    /// `job_id` is null), as an Arrow IPC stream buffer. Empty when there is
-    /// no history.
+    /// Pause a server-side job by id: its workers drain and it stays parked
+    /// until resumed. Returns "pausing", "already_paused", or "committing".
     #[napi(catch_unwind)]
-    pub async fn job_history(&self, job_id: Option<String>) -> napi::Result<Buffer> {
-        let batches = self
+    pub async fn pause_job(&self, job_id: String) -> napi::Result<String> {
+        let status = self.get_inner()?.pause_job(&job_id).await.default_error()?;
+        Ok(match status {
+            lancedb::database::PauseJobStatus::Pausing => "pausing".to_string(),
+            lancedb::database::PauseJobStatus::AlreadyPaused => "already_paused".to_string(),
+            lancedb::database::PauseJobStatus::Committing => "committing".to_string(),
+        })
+    }
+
+    /// Resume a paused server-side job by id. Returns "resumed",
+    /// "still_pausing", or "not_paused".
+    #[napi(catch_unwind)]
+    pub async fn resume_job(&self, job_id: String) -> napi::Result<String> {
+        let status = self
             .get_inner()?
-            .job_history(job_id.as_deref())
+            .resume_job(&job_id)
             .await
             .default_error()?;
-        let Some(first) = batches.first() else {
-            return Ok(Buffer::from(Vec::<u8>::new()));
-        };
-        let mut out = Vec::new();
-        let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
-            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-        for batch in &batches {
-            writer
-                .write(batch)
-                .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-        }
-        writer
-            .finish()
-            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-        drop(writer);
-        Ok(Buffer::from(out))
+        Ok(match status {
+            lancedb::database::ResumeJobStatus::Resumed => "resumed".to_string(),
+            lancedb::database::ResumeJobStatus::StillPausing => "still_pausing".to_string(),
+            lancedb::database::ResumeJobStatus::NotPaused => "not_paused".to_string(),
+        })
     }
 
     #[napi(catch_unwind)]

nodejs/src/index.rs

@@ -239,7 +239,12 @@ impl Index {
             opts = opts.base_tokenizer(base_tokenizer);
         }
         if let Some(language) = language {
-            opts = opts.language(&language).unwrap();
+            opts = opts.language(&language).map_err(|_| {
+                napi::Error::from_reason(format!(
+                    "LanceDB does not support the requested language: '{}'",
+                    language
+                ))
+            })?;
         }
         if let Some(max_token_length) = max_token_length {
             opts = opts.max_token_length(Some(max_token_length as usize));

nodejs/src/iterator.rs

@@ -7,6 +7,8 @@ use lancedb::ipc::batches_to_ipc_file;
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
 
+use crate::util::schema_to_buffer;
+
 /** Typescript-style Async Iterator over RecordBatches */
 #[napi]
 pub struct RecordBatchIterator {
@@ -19,6 +21,12 @@ impl RecordBatchIterator {
         Self { inner }
     }
 
+    /// Return the executed stream's output schema as an Arrow IPC file.
+    #[napi]
+    pub fn schema(&self) -> napi::Result<Buffer> {
+        schema_to_buffer(&self.inner.schema())
+    }
+
     #[napi(catch_unwind)]
     pub async unsafe fn next(&mut self) -> napi::Result<Option<Buffer>> {
         if let Some(rst) = self.inner.next().await {

nodejs/src/job.rs

@@ -3,6 +3,9 @@
 
 use std::sync::Arc;
 
+use arrow_array::RecordBatch;
+use lancedb::job::JobEventsRequest;
+use napi::bindgen_prelude::Buffer;
 use napi_derive::napi;
 
 use crate::error::NapiErrorExt;
@@ -55,12 +58,98 @@ impl Job {
     pub async fn cancel(&self) -> napi::Result<()> {
         self.inner.cancel().await.default_error()
     }
+
+    /// Ask the backend for this job's current state, and for a server-side job
+    /// its full record, then cache it for the getters below.
+    ///
+    /// They are all null until this runs, because submitting an operation
+    /// returns only a job id. {@link Job.status} fetches the whole record too;
+    /// {@link Job.wait} records only the terminal state it establishes.
+    #[napi(catch_unwind)]
+    pub async fn refresh(&self) -> napi::Result<()> {
+        self.inner.refresh().await.default_error()
+    }
+
+    /// The last observed lifecycle state, without contacting the backend.
+    #[napi(getter)]
+    pub fn state(&self) -> Option<String> {
+        self.inner.state()
+    }
+
+    /// The job's type, as the server names it. Null for an in-process job,
+    /// which has no server-side record.
+    #[napi(getter)]
+    pub fn job_type(&self) -> Option<String> {
+        self.inner.job_type()
+    }
+
+    /// When the job was created, in milliseconds since the epoch.
+    #[napi(getter)]
+    pub fn creation_ms(&self) -> Option<i64> {
+        self.inner.creation_ms()
+    }
+
+    /// The job-type-specific specification as a JSON string, when present.
+    #[napi(getter)]
+    pub fn spec_json(&self) -> Option<String> {
+        self.inner.spec().map(|spec| spec.to_string())
+    }
+
+    /// The job-type-specific terminal result as a JSON string. Null until the
+    /// job succeeds, so a job that never terminates reports its progress
+    /// through {@link Job.events} instead.
+    #[napi(getter)]
+    pub fn result_json(&self) -> Option<String> {
+        self.inner.result().map(|result| result.to_string())
+    }
+
+    /// Why the job failed, when it failed and the server reports a reason.
+    #[napi(getter)]
+    pub fn failure(&self) -> Option<JobFailureInfo> {
+        self.inner.failure().map(|failure| JobFailureInfo {
+            phase: failure.phase,
+            message: failure.message,
+            retryable: failure.retryable,
+        })
+    }
+
+    /// This job's recorded lifecycle events, as an Arrow IPC stream buffer.
+    /// The TypeScript wrapper turns it into an Arrow table.
+    #[napi(catch_unwind)]
+    pub async fn events(&self, limit: Option<u32>, filter: Option<String>) -> napi::Result<Buffer> {
+        let batches = self
+            .inner
+            .events(JobEventsRequest { limit, filter })
+            .await
+            .default_error()?;
+        batches_to_ipc_buffer(&batches)
+    }
+}
+
+/// Serialise Arrow batches as a single IPC stream for the TypeScript layer.
+fn batches_to_ipc_buffer(batches: &[RecordBatch]) -> napi::Result<Buffer> {
+    let Some(first) = batches.first() else {
+        return Ok(Buffer::from(Vec::<u8>::new()));
+    };
+    let mut out = Vec::new();
+    let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
+        .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+    for batch in batches {
+        writer
+            .write(batch)
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+    }
+    writer
+        .finish()
+        .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+    drop(writer);
+    Ok(Buffer::from(out))
 }
 
 /// A row from `Connection.listJobs`: one server-side job.
 #[napi(object)]
 pub struct JobInfo {
-    /// The job id -- what `Connection.getJob` and `Connection.cancelJob`
+    /// The job id -- what `Connection.openJob` and `Connection.cancelJob`
     /// accept.
     pub job_id: String,
     /// The table the job runs against, without URI or namespace.
@@ -91,36 +180,3 @@ pub struct JobFailureInfo {
     pub message: Option<String>,
     pub retryable: Option<bool>,
 }
-
-/// A described job from `Connection.getJob`.
-#[napi(object)]
-pub struct JobDescription {
-    pub job_id: String,
-    pub job_type: String,
-    /// Lifecycle state: "running", "finished", "failed", or "cancelled".
-    pub state: String,
-    /// When the job was created, in milliseconds since the epoch.
-    pub creation_ms: i64,
-    /// The job-type-specific specification as a JSON string, when present.
-    pub spec_json: Option<String>,
-    /// Why the job failed, when the job is failed and the server reports a
-    /// reason.
-    pub failure: Option<JobFailureInfo>,
-}
-
-impl From<lancedb::database::JobDescription> for JobDescription {
-    fn from(description: lancedb::database::JobDescription) -> Self {
-        Self {
-            job_id: description.job_id,
-            job_type: description.job_type,
-            state: description.state,
-            creation_ms: description.creation_ms,
-            spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
-            failure: description.failure.map(|failure| JobFailureInfo {
-                phase: failure.phase,
-                message: failure.message,
-                retryable: failure.retryable,
-            }),
-        }
-    }
-}

nodejs/src/lib.rs

@@ -10,12 +10,15 @@ use std::collections::HashMap;
 use env_logger::Env;
 use napi_derive::*;
 
+mod blob;
+mod catalog;
 mod connection;
 mod error;
 mod header;
 mod index;
 mod iterator;
 mod job;
+mod listing;
 pub mod merge;
 pub mod otel;
 pub mod permutation;

nodejs/src/listing.rs

@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use crate::error::NapiErrorExt;
+use futures::{StreamExt, future::poll_fn};
+use lancedb::listing::{Listing, ListingOptions};
+use napi_derive::napi;
+use std::sync::Mutex;
+
+pub fn options(page_token: Option<String>, page_limit: Option<u32>) -> ListingOptions {
+    let mut options = ListingOptions::default();
+    options.page_token = page_token;
+    options.page_limit = page_limit;
+    options
+}
+
+#[napi]
+pub struct NameListing {
+    inner: Mutex<Listing<String>>,
+    next_lock: futures::lock::Mutex<()>,
+}
+impl NameListing {
+    pub fn new(inner: Listing<String>) -> Self {
+        Self {
+            inner: Mutex::new(inner),
+            next_lock: futures::lock::Mutex::new(()),
+        }
+    }
+}
+#[napi]
+impl NameListing {
+    #[napi]
+    pub fn num_page_results(&self) -> u32 {
+        self.inner.lock().unwrap().num_page_results() as u32
+    }
+    #[napi]
+    pub fn page_token(&self) -> Option<String> {
+        self.inner.lock().unwrap().page_token().map(str::to_owned)
+    }
+    #[napi]
+    pub async fn next(&self) -> napi::Result<Option<String>> {
+        let _guard = self.next_lock.lock().await;
+        let value = poll_fn(|cx| self.inner.lock().unwrap().poll_next_unpin(cx))
+            .await
+            .transpose()
+            .default_error()?;
+        Ok(value)
+    }
+}
+
+#[napi]
+pub struct JobListing {
+    inner: Mutex<Listing<lancedb::database::JobInfo>>,
+    next_lock: futures::lock::Mutex<()>,
+}
+impl JobListing {
+    pub fn new(inner: Listing<lancedb::database::JobInfo>) -> Self {
+        Self {
+            inner: Mutex::new(inner),
+            next_lock: futures::lock::Mutex::new(()),
+        }
+    }
+}
+#[napi]
+impl JobListing {
+    #[napi]
+    pub fn num_page_results(&self) -> u32 {
+        self.inner.lock().unwrap().num_page_results() as u32
+    }
+    #[napi]
+    pub fn page_token(&self) -> Option<String> {
+        self.inner.lock().unwrap().page_token().map(str::to_owned)
+    }
+    #[napi]
+    pub async fn next(&self) -> napi::Result<Option<crate::job::JobInfo>> {
+        let _guard = self.next_lock.lock().await;
+        let value = poll_fn(|cx| self.inner.lock().unwrap().poll_next_unpin(cx))
+            .await
+            .transpose()
+            .default_error()?;
+        Ok(value.map(|value| value.into()))
+    }
+}

nodejs/src/query.rs

@@ -289,8 +289,23 @@ impl VectorQuery {
     }
 
     #[napi]
-    pub fn nprobes(&mut self, nprobe: u32) {
-        self.inner = self.inner.clone().nprobes(nprobe as usize);
+    pub fn nprobes(&mut self, nprobe: u32) -> napi::Result<()> {
+        self.inner = self
+            .inner
+            .clone()
+            .nprobes(nprobe as usize)
+            .default_error()?;
+        Ok(())
+    }
+
+    #[napi]
+    pub fn search_effort(&mut self, search_effort: Option<f64>) -> napi::Result<()> {
+        self.inner = self
+            .inner
+            .clone()
+            .search_effort(search_effort)
+            .default_error()?;
+        Ok(())
     }
 
     #[napi]
@@ -658,13 +673,18 @@ impl JsFullTextQuery {
             FtsQuery::Phrase(_) => "phrase".to_string(),
             FtsQuery::Boost(_) => "boost".to_string(),
             FtsQuery::MultiMatch(_) => "multi_match".to_string(),
+            FtsQuery::CombinedFields(_) => "combined_fields".to_string(),
             FtsQuery::Boolean(_) => "boolean".to_string(),
         }
     }
 }
 
 fn parse_fts_query(query: Object) -> napi::Result<FullTextSearchQuery> {
-    if let Ok(Some(query)) = query.get::<&JsFullTextQuery>("query") {
+    // `&JsFullTextQuery` recovers a native class reference through napi's borrow-tracked
+    // path, which is only usable from generated `#[napi]` argument conversion. This is a
+    // manual lookup on a nested `Object` property instead, so use `ClassInstance`, which
+    // unwraps the class without requiring a borrow scope.
+    if let Ok(Some(query)) = query.get::<ClassInstance<JsFullTextQuery>>("query") {
         Ok(FullTextSearchQuery::new_query(query.inner.clone()))
     } else if let Ok(Some(query_text)) = query.get::<String>("query") {
         let mut query_text = query_text;

nodejs/src/remote.rs

@@ -6,6 +6,8 @@ use std::collections::HashMap;
 use lancedb::error::Error;
 use napi_derive::*;
 
+use crate::error::NapiErrorExt;
+
 /// Timeout configuration for remote HTTP client.
 #[napi(object)]
 #[derive(Debug)]
@@ -91,6 +93,9 @@ pub struct ClientConfig {
     pub retry_config: Option<RetryConfig>,
     pub timeout_config: Option<TimeoutConfig>,
     pub extra_headers: Option<HashMap<String, String>>,
+    /// The delimiter joining a namespace path and a name into one object
+    /// identifier. `"$"` is the only supported value, and leaving this unset is
+    /// how to get it; anything else is rejected when the connection is created.
     pub id_delimiter: Option<String>,
     pub tls_config: Option<TlsConfig>,
     /// User identifier for tracking purposes.
@@ -141,6 +146,34 @@ impl From<TlsConfig> for lancedb::remote::TlsConfig {
     }
 }
 
+/// Options for the persistent OAuth token cache.
+///
+/// The cache is opt-in: it is only used when set as `tokenCache` on
+/// `OAuthConfig`. Only refresh tokens are persisted, in a private directory
+/// with owner-only permissions, so short-lived processes can reuse an
+/// authenticated session instead of re-prompting on every start.
+#[napi(object)]
+#[derive(Clone, Debug, Default)]
+pub struct TokenCacheOptions {
+    /// Directory that holds cached credentials. Defaults to
+    /// `$XDG_CACHE_HOME/lancedb/oauth`, `$HOME/.cache/lancedb/oauth` on Unix,
+    /// or `%LOCALAPPDATA%\lancedb\oauth` on Windows. The directory is created
+    /// with owner-only permissions (`0700`) when missing.
+    pub cache_dir: Option<String>,
+    /// How long to wait for the cross-process refresh lock before failing,
+    /// in seconds (default: 30).
+    pub lock_timeout_secs: Option<u32>,
+}
+
+impl From<TokenCacheOptions> for lancedb::remote::TokenCacheOptions {
+    fn from(options: TokenCacheOptions) -> Self {
+        Self {
+            cache_dir: options.cache_dir.map(std::path::PathBuf::from),
+            lock_timeout_secs: options.lock_timeout_secs.map(|secs| secs as u64),
+        }
+    }
+}
+
 /// OAuth configuration for LanceDB authentication.
 ///
 /// This is the generated napi-rs binding shape. TypeScript users should prefer
@@ -158,16 +191,35 @@ pub struct OAuthConfig {
     /// OAuth scopes to request. For Azure managed identity, exactly one scope
     /// or resource is required. For example: `["api://{app_id}/.default"]`
     pub scopes: Vec<String>,
-    /// Authentication flow: "client_credentials" or "azure_managed_identity"
+    /// Optional resource indicator for authorization and token requests.
+    pub resource: Option<String>,
+    /// Optional provider-specific audience for authorization and token requests.
+    pub audience: Option<String>,
+    /// Authentication flow: "client_credentials", "authorization_code",
+    /// "device_code", or "azure_managed_identity"
     pub flow: Option<String>,
     /// Client secret (required for client_credentials).
     pub client_secret: Option<String>,
+    /// How the client authenticates to the token endpoint: "none",
+    /// "client_secret_basic", or "client_secret_post". Defaults to
+    /// "client_secret_basic" when a client secret is set, and "none" for
+    /// public clients.
+    pub client_auth_method: Option<String>,
+    /// Loopback redirect URI for authorization_code.
+    pub redirect_uri: Option<String>,
+    /// Port for the authorization_code loopback callback server.
+    pub callback_port: Option<u16>,
+    /// Whether authorization_code uses S256 PKCE (default: true).
+    pub use_pkce: Option<bool>,
     /// Client ID for user-assigned managed identity (azure_managed_identity).
     pub managed_identity_client_id: Option<String>,
     /// Seconds before expiry to trigger proactive refresh (default: 300).
     /// Keep this well below the token TTL; if it is greater than or equal to
     /// the TTL, each request refreshes the token.
     pub refresh_buffer_secs: Option<u32>,
+    /// Opt in to the persistent token cache so short-lived processes reuse
+    /// one session. Only refresh tokens are persisted.
+    pub token_cache: Option<TokenCacheOptions>,
 }
 
 impl std::fmt::Debug for OAuthConfig {
@@ -176,16 +228,23 @@ impl std::fmt::Debug for OAuthConfig {
             .field("issuer_url", &self.issuer_url)
             .field("client_id", &self.client_id)
             .field("scopes", &self.scopes)
+            .field("resource", &self.resource)
+            .field("audience", &self.audience)
             .field("flow", &self.flow)
             .field(
                 "client_secret",
                 &self.client_secret.as_deref().map(|_| "<redacted>"),
             )
+            .field("client_auth_method", &self.client_auth_method)
+            .field("redirect_uri", &self.redirect_uri)
+            .field("callback_port", &self.callback_port)
+            .field("use_pkce", &self.use_pkce)
             .field(
                 "managed_identity_client_id",
                 &self.managed_identity_client_id,
             )
             .field("refresh_buffer_secs", &self.refresh_buffer_secs)
+            .field("token_cache", &self.token_cache)
             .finish()
     }
 }
@@ -194,10 +253,22 @@ impl TryFrom<OAuthConfig> for lancedb::remote::oauth::OAuthConfig {
     type Error = Error;
 
     fn try_from(config: OAuthConfig) -> Result<Self, Self::Error> {
-        use lancedb::remote::oauth::OAuthFlow;
+        use lancedb::remote::oauth::{AuthorizationCodeOptions, OAuthFlow};
 
         let flow = match config.flow.as_deref().unwrap_or("client_credentials") {
             "client_credentials" => OAuthFlow::ClientCredentials,
+            "authorization_code" => {
+                let mut options =
+                    AuthorizationCodeOptions::new().use_pkce(config.use_pkce.unwrap_or(true));
+                if let Some(redirect_uri) = config.redirect_uri {
+                    options = options.redirect_uri(redirect_uri);
+                }
+                if let Some(callback_port) = config.callback_port {
+                    options = options.callback_port(callback_port);
+                }
+                OAuthFlow::AuthorizationCode(options)
+            }
+            "device_code" => OAuthFlow::DeviceCode,
             "azure_managed_identity" => OAuthFlow::AzureManagedIdentity {
                 client_id: config.managed_identity_client_id,
             },
@@ -208,17 +279,147 @@ impl TryFrom<OAuthConfig> for lancedb::remote::oauth::OAuthConfig {
             }
         };
 
+        let client_auth_method = match config.client_auth_method.as_deref() {
+            Some("none") => Some(lancedb::remote::oauth::ClientAuthMethod::None),
+            Some("client_secret_basic") => {
+                Some(lancedb::remote::oauth::ClientAuthMethod::ClientSecretBasic)
+            }
+            Some("client_secret_post") => {
+                Some(lancedb::remote::oauth::ClientAuthMethod::ClientSecretPost)
+            }
+            None => None,
+            Some(other) => {
+                return Err(Error::InvalidInput {
+                    message: format!("Unknown OAuth client auth method: {other}"),
+                });
+            }
+        };
+
         Ok(Self {
             issuer_url: config.issuer_url,
             client_id: config.client_id,
             client_secret: config.client_secret,
+            client_auth_method,
             scopes: config.scopes,
+            resource: config.resource,
+            audience: config.audience,
             flow,
             refresh_buffer_secs: config.refresh_buffer_secs.map(|v| v as u64),
+            token_cache: config.token_cache.map(Into::into),
         })
     }
 }
 
+/// Safe, non-secret view of a cached OAuth session, returned by
+/// `OAuthSession.status()` and `OAuthSession.login()`.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct SessionStatus {
+    /// Whether a cached session exists that can obtain tokens without
+    /// interactive authentication.
+    pub refreshable: bool,
+    /// Canonical issuer URL of the cached session.
+    pub issuer_url: String,
+    /// Client ID of the cached session.
+    pub client_id: String,
+    /// Canonical (sorted, de-duplicated) scopes of the cached session.
+    pub scopes: Vec<String>,
+    /// Optional resource indicator for authorization and token requests.
+    pub resource: Option<String>,
+    /// Optional provider-specific audience for authorization and token requests.
+    pub audience: Option<String>,
+    /// Flow that produced the cached session.
+    pub flow: String,
+    /// When the cached session was obtained, as Unix seconds.
+    pub obtained_at: Option<f64>,
+}
+
+/// Result of `OAuthSession.logout()`.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct SessionLogout {
+    /// Whether a cached credential was removed. `false` means no matching
+    /// session was cached; logout is idempotent.
+    pub removed: bool,
+}
+
+/// Explicit OAuth session lifecycle for the persistent token cache: eager
+/// `login`, non-secret `status`, and local `logout`.
+///
+/// A session is built from the same `OAuthConfig` used to connect (including
+/// its `tokenCache` options). A connection created with the same
+/// configuration shares the cache, so logging in here prepares tokens for
+/// later processes without any database request.
+#[napi]
+pub struct OAuthSession {
+    inner: lancedb::remote::OAuthSession,
+}
+
+#[napi]
+impl OAuthSession {
+    /// Create a session manager for the given OAuth configuration.
+    ///
+    /// The configuration must enable `tokenCache` options and use a flow that
+    /// supports persistent sessions (authorization code or device code).
+    #[napi(constructor)]
+    pub fn new(config: OAuthConfig) -> napi::Result<Self> {
+        let config: lancedb::remote::oauth::OAuthConfig = config.try_into().default_error()?;
+        let inner = lancedb::remote::OAuthSession::new(config).default_error()?;
+        Ok(Self { inner })
+    }
+
+    /// Eagerly run the configured authentication flow and store the session.
+    ///
+    /// A successful login always replaces any prior cached session for this
+    /// identity; if the provider does not issue a refresh token (for example
+    /// without `offline_access`), the previous record is removed and the
+    /// status reports `refreshable == false`.
+    #[napi(catch_unwind)]
+    pub async fn login(&self) -> napi::Result<SessionStatus> {
+        let status = self.inner.login().await.default_error()?;
+        Ok(SessionStatus::from(status))
+    }
+
+    /// Report whether a matching cached session exists, with safe metadata.
+    ///
+    /// This never contacts the identity provider and never exposes token
+    /// values.
+    #[napi(catch_unwind)]
+    pub async fn status(&self) -> napi::Result<SessionStatus> {
+        let status = self.inner.status().await.default_error()?;
+        Ok(SessionStatus::from(status))
+    }
+
+    /// Remove the matching local cached credential.
+    ///
+    /// This only deletes the local cache entry. It does not revoke the
+    /// refresh token with the provider and does not sign out of a browser
+    /// SSO session. Repeated calls succeed; `removed` reports whether a
+    /// credential existed.
+    #[napi(catch_unwind)]
+    pub async fn logout(&self) -> napi::Result<SessionLogout> {
+        let logout = self.inner.logout().await.default_error()?;
+        Ok(SessionLogout {
+            removed: logout.removed,
+        })
+    }
+}
+
+impl From<lancedb::remote::SessionStatus> for SessionStatus {
+    fn from(status: lancedb::remote::SessionStatus) -> Self {
+        Self {
+            refreshable: status.refreshable,
+            issuer_url: status.issuer_url,
+            client_id: status.client_id,
+            scopes: status.scopes,
+            resource: status.resource,
+            audience: status.audience,
+            flow: status.flow,
+            obtained_at: status.obtained_at.map(|secs| secs as f64),
+        }
+    }
+}
+
 impl From<ClientConfig> for lancedb::remote::ClientConfig {
     fn from(config: ClientConfig) -> Self {
         Self {
@@ -252,8 +453,15 @@ mod tests {
             scopes: vec!["scope".to_string()],
             flow: Some("typo".to_string()),
             client_secret: None,
+            client_auth_method: None,
+            redirect_uri: None,
+            callback_port: None,
+            use_pkce: None,
             managed_identity_client_id: None,
             refresh_buffer_secs: None,
+            resource: None,
+            audience: None,
+            token_cache: None,
         };
 
         let err = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap_err();
@@ -272,12 +480,136 @@ mod tests {
             scopes: vec!["scope".to_string()],
             flow: Some("client_credentials".to_string()),
             client_secret: Some("super-secret".to_string()),
+            client_auth_method: None,
+            redirect_uri: None,
+            callback_port: None,
+            use_pkce: None,
             managed_identity_client_id: None,
             refresh_buffer_secs: None,
+            resource: None,
+            audience: None,
+            token_cache: None,
         };
 
         let debug = format!("{config:?}");
         assert!(!debug.contains("super-secret"));
         assert!(debug.contains("client_secret: Some(\"<redacted>\")"));
     }
+
+    #[test]
+    fn test_authorization_code_conversion_preserves_options() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            scopes: vec!["openid".to_string()],
+            flow: Some("authorization_code".to_string()),
+            client_secret: Some("secret".to_string()),
+            client_auth_method: None,
+            redirect_uri: Some("http://127.0.0.1:9000/callback".to_string()),
+            callback_port: Some(9000),
+            use_pkce: Some(false),
+            managed_identity_client_id: None,
+            refresh_buffer_secs: None,
+            resource: Some("urn:resource".into()),
+            audience: Some("audience".into()),
+            token_cache: None,
+        };
+
+        let converted = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap();
+        let lancedb::remote::oauth::OAuthFlow::AuthorizationCode(options) = converted.flow else {
+            panic!("expected authorization code flow");
+        };
+        assert_eq!(
+            options.redirect_uri.as_deref(),
+            Some("http://127.0.0.1:9000/callback")
+        );
+        assert_eq!(options.callback_port, Some(9000));
+        assert!(!options.use_pkce);
+        assert_eq!(converted.resource.as_deref(), Some("urn:resource"));
+        assert_eq!(converted.audience.as_deref(), Some("audience"));
+    }
+
+    #[test]
+    fn test_device_code_conversion() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            scopes: vec!["openid".to_string()],
+            flow: Some("device_code".to_string()),
+            client_secret: None,
+            client_auth_method: None,
+            redirect_uri: None,
+            callback_port: None,
+            use_pkce: None,
+            managed_identity_client_id: None,
+            refresh_buffer_secs: None,
+            resource: None,
+            audience: None,
+            token_cache: None,
+        };
+
+        let converted = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap();
+        assert!(matches!(
+            converted.flow,
+            lancedb::remote::oauth::OAuthFlow::DeviceCode
+        ));
+    }
+
+    #[test]
+    fn test_client_auth_method_conversion() {
+        use lancedb::remote::oauth::ClientAuthMethod;
+
+        for (value, expected) in [
+            ("none", ClientAuthMethod::None),
+            ("client_secret_basic", ClientAuthMethod::ClientSecretBasic),
+            ("client_secret_post", ClientAuthMethod::ClientSecretPost),
+        ] {
+            let config = OAuthConfig {
+                issuer_url: "https://issuer.example.com".to_string(),
+                client_id: "client-id".to_string(),
+                scopes: vec!["openid".to_string()],
+                flow: Some("device_code".to_string()),
+                client_secret: None,
+                client_auth_method: Some(value.to_string()),
+                resource: None,
+                audience: None,
+                redirect_uri: None,
+                callback_port: None,
+                use_pkce: None,
+                managed_identity_client_id: None,
+                refresh_buffer_secs: None,
+                token_cache: None,
+            };
+
+            let converted = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap();
+            assert_eq!(converted.client_auth_method, Some(expected));
+        }
+    }
+
+    #[test]
+    fn test_unknown_client_auth_method_returns_invalid_input() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            scopes: vec!["openid".to_string()],
+            flow: Some("device_code".to_string()),
+            client_secret: None,
+            client_auth_method: Some("typo".to_string()),
+            resource: None,
+            audience: None,
+            redirect_uri: None,
+            callback_port: None,
+            use_pkce: None,
+            managed_identity_client_id: None,
+            refresh_buffer_secs: None,
+            token_cache: None,
+        };
+
+        let err = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap_err();
+        assert!(matches!(
+            err,
+            Error::InvalidInput { message }
+                if message == "Unknown OAuth client auth method: typo"
+        ));
+    }
 }

nodejs/src/table.rs

@@ -7,14 +7,16 @@ use chrono::{DateTime, Utc};
 
 use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
 use lancedb::table::{
-    AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration,
+    AddDataMode, ColumnAlteration as LanceColumnAlteration,
     FieldMetadataUpdate as LanceFieldMetadataUpdate, FtsToken as LanceDbFtsToken,
     NewColumnTransform, OptimizeAction, OptimizeOptions, Ref, Table as LanceDbTable,
 };
+use napi::Env;
 use napi::bindgen_prelude::*;
 use napi::threadsafe_function::{ThreadsafeFunction, ThreadsafeFunctionCallMode};
 use napi_derive::napi;
 
+use crate::blob::{BlobFile, copy_blob_buffers, parse_row_ids, spawn_abortable};
 use crate::error::NapiErrorExt;
 use crate::index::Index;
 use crate::merge::NativeMergeInsertBuilder;
@@ -73,13 +75,14 @@ impl Table {
 
     #[napi(
         catch_unwind,
-        ts_args_type = "buf: Buffer, mode: string, progressCallback?: (progress: WriteProgressInfo) => void"
+        ts_args_type = "buf: Buffer, mode: string, progressCallback?: (progress: WriteProgressInfo) => void, allowExternalBlobOutsideBases?: boolean"
     )]
     pub async fn add(
         &self,
         buf: Buffer,
         mode: String,
         progress_callback: Option<ProgressFn>,
+        allow_external_blob_outside_bases: Option<bool>,
     ) -> napi::Result<AddResult> {
         let batches = ipc_file_to_batches(buf.to_vec())
             .map_err(|e| napi::Error::from_reason(format!("Failed to read IPC file: {}", e)))?;
@@ -104,6 +107,9 @@ impl Table {
             return Err(napi::Error::from_reason(format!("Invalid mode: {}", mode)));
         };
 
+        op = op
+            .allow_external_blob_outside_bases(allow_external_blob_outside_bases.unwrap_or(false));
+
         if let Some(tsfn) = progress_callback {
             op = op.progress(move |p| {
                 // NonBlocking: dispatch onto the JS event loop without
@@ -329,6 +335,52 @@ impl Table {
         ))
     }
 
+    #[napi(catch_unwind)]
+    pub async fn blob_columns(&self) -> napi::Result<Vec<String>> {
+        self.inner_ref()?.blob_columns().await.default_error()
+    }
+
+    #[napi(catch_unwind)]
+    pub fn fetch_blobs<'env>(
+        &self,
+        env: &'env Env,
+        column: String,
+        row_ids: Vec<BigInt>,
+        signal: Option<AbortSignal>,
+    ) -> napi::Result<PromiseRaw<'env, Vec<Option<Buffer>>>> {
+        let row_ids = parse_row_ids(row_ids)?;
+        let table = self.inner_ref()?.clone();
+        spawn_abortable(env, signal, async move {
+            let array = table
+                .fetch_blobs(column.as_str(), &row_ids)
+                .await
+                .default_error()?;
+            Ok(copy_blob_buffers(array))
+        })
+    }
+
+    #[napi(catch_unwind)]
+    pub fn fetch_blob_files<'env>(
+        &self,
+        env: &'env Env,
+        column: String,
+        row_ids: Vec<BigInt>,
+        signal: Option<AbortSignal>,
+    ) -> napi::Result<PromiseRaw<'env, Vec<Option<BlobFile>>>> {
+        let row_ids = parse_row_ids(row_ids)?;
+        let table = self.inner_ref()?.clone();
+        spawn_abortable(env, signal, async move {
+            let files = table
+                .fetch_blob_files(column.as_str(), &row_ids)
+                .await
+                .default_error()?;
+            Ok(files
+                .into_iter()
+                .map(|file| file.map(BlobFile::new))
+                .collect())
+        })
+    }
+
     #[napi(catch_unwind)]
     pub fn vector_search(&self, vector: Float32Array) -> napi::Result<VectorQuery> {
         self.query()?.nearest_to(vector)
@@ -388,16 +440,41 @@ impl Table {
         Ok(crate::job::Job::new(job))
     }
 
+    #[napi(catch_unwind)]
+    pub async fn function_errors(
+        &self,
+        options: Option<FunctionErrorsOptions>,
+    ) -> napi::Result<FunctionErrors> {
+        let options = options.unwrap_or_default();
+        let limit = options
+            .limit
+            .map(|limit| {
+                usize::try_from(limit)
+                    .map_err(|_| napi::Error::from_reason("limit must be a non-negative integer"))
+            })
+            .transpose()?;
+        let request = lancedb::function::FunctionErrorsRequest {
+            job_id: options.job_id,
+            column: options.column,
+            limit,
+        };
+        let errors = self
+            .inner_ref()?
+            .function_errors(request)
+            .await
+            .default_error()?;
+        Ok(errors.into())
+    }
+
     #[napi(catch_unwind)]
     pub async fn refresh_materialized_view(
         &self,
-        full: Option<bool>,
         source_version: Option<i64>,
     ) -> napi::Result<RefreshMaterializedViewResult> {
         let view = lancedb::MaterializedView::from_table(self.inner_ref()?.clone())
             .await
             .default_error()?;
-        let mut builder = view.refresh().full(full.unwrap_or(false));
+        let mut builder = view.refresh();
         if let Some(version) = source_version {
             let version = u64::try_from(version).map_err(|_| {
                 napi::Error::from_reason("sourceVersion must be a non-negative integer")
@@ -408,6 +485,17 @@ impl Table {
         Ok(result.into())
     }
 
+    #[napi(catch_unwind)]
+    pub async fn materialized_view_definition(&self) -> napi::Result<String> {
+        let inner = self.inner_ref()?.clone();
+        let view = lancedb::MaterializedView::from_table(inner)
+            .await
+            .default_error()?;
+        Ok(lancedb::materialized_view::definition_metadata_from_sql(
+            view.definition_sql(),
+        ))
+    }
+
     #[napi(catch_unwind)]
     pub async fn add_columns_with_schema(
         &self,
@@ -638,22 +726,20 @@ impl Table {
     #[napi(catch_unwind)]
     pub async fn optimize(
         &self,
-        older_than_ms: Option<i64>,
+        before_timestamp_ms: Option<i64>,
         delete_unverified: Option<bool>,
     ) -> napi::Result<OptimizeStats> {
         let inner = self.inner_ref()?;
 
-        let older_than = if let Some(ms) = older_than_ms {
-            if ms == i64::MIN {
-                return Err(napi::Error::from_reason(format!(
-                    "older_than_ms can not be {}",
-                    i32::MIN,
-                )));
-            }
-            Duration::try_milliseconds(ms)
-        } else {
-            None
-        };
+        let before_timestamp = before_timestamp_ms
+            .map(|ms| {
+                DateTime::from_timestamp_millis(ms).ok_or_else(|| {
+                    napi::Error::from_reason(format!(
+                        "cleanupOlderThan timestamp is out of range: {ms}"
+                    ))
+                })
+            })
+            .transpose()?;
 
         let compaction_stats = inner
             .optimize(OptimizeAction::Compact {
@@ -664,16 +750,22 @@ impl Table {
             .default_error()?
             .compaction
             .unwrap();
-        let prune_stats = inner
-            .optimize(OptimizeAction::Prune {
-                older_than,
-                delete_unverified,
-                error_if_tagged_old_versions: None,
-            })
-            .await
-            .default_error()?
-            .prune
-            .unwrap();
+        let prune_stats = if let Some(before_timestamp) = before_timestamp {
+            inner
+                .optimize_prune_before(before_timestamp, delete_unverified, None)
+                .await
+        } else {
+            inner
+                .optimize(OptimizeAction::Prune {
+                    older_than: None,
+                    delete_unverified,
+                    error_if_tagged_old_versions: None,
+                })
+                .await
+        }
+        .default_error()?
+        .prune
+        .unwrap();
         inner
             .optimize(lancedb::table::OptimizeAction::Index(
                 OptimizeOptions::default(),
@@ -744,7 +836,10 @@ impl Table {
     pub async fn uses_v2_manifest_paths(&self) -> napi::Result<bool> {
         self.inner_ref()?
             .as_native()
-            .ok_or_else(|| napi::Error::from_reason("This cannot be run on a remote table"))?
+            .ok_or_else(|| lancedb::Error::NotSupported {
+                message: "uses_v2_manifest_paths is not supported for remote tables.".into(),
+            })
+            .default_error()?
             .uses_v2_manifest_paths()
             .await
             .default_error()
@@ -754,7 +849,10 @@ impl Table {
     pub async fn migrate_manifest_paths_v2(&self) -> napi::Result<()> {
         self.inner_ref()?
             .as_native()
-            .ok_or_else(|| napi::Error::from_reason("This cannot be run on a remote table"))?
+            .ok_or_else(|| lancedb::Error::NotSupported {
+                message: "migrate_manifest_paths_v2 is not supported for remote tables.".into(),
+            })
+            .default_error()?
             .migrate_manifest_paths_v2()
             .await
             .default_error()
@@ -1270,6 +1368,16 @@ pub struct TableStatistics {
     /// The number of rows in the table
     pub num_rows: i64,
 
+    /// The number of rows marked as deleted across all fragments of the table
+    ///
+    /// These rows are not included in `numRows`, but still occupy space on disk
+    /// until the table is compacted, so a large value here indicates that the
+    /// table should be optimized. Fragments in which every row was deleted are
+    /// dropped outright, so their rows are not counted here.
+    ///
+    /// Absent (`undefined`) when the backend does not report deletion counts.
+    pub num_deleted_rows: Option<i64>,
+
     /// The number of indices in the table
     pub num_indices: i64,
 
@@ -1318,6 +1426,7 @@ impl From<lancedb::table::TableStatistics> for TableStatistics {
         Self {
             total_bytes: v.total_bytes as i64,
             num_rows: v.num_rows as i64,
+            num_deleted_rows: v.num_deleted_rows.map(|n| n as i64),
             num_indices: v.num_indices as i64,
             fragment_stats: FragmentStatistics {
                 num_fragments: v.fragment_stats.num_fragments as i64,
@@ -1420,9 +1529,100 @@ pub struct RefreshColumnResult {
     pub version: i64,
 }
 
+/// Which per-row Function errors to list; every filter is optional.
+#[napi(object)]
+#[derive(Clone, Debug, Default)]
+pub struct FunctionErrorsOptions {
+    /// Only errors recorded by this job.
+    pub job_id: Option<String>,
+    /// Only errors on this column.
+    pub column: Option<String>,
+    /// At most this many records (server default 10000, cap 100000).
+    pub limit: Option<i64>,
+}
+
+/// One row a Function refresh skipped, as the server recorded it.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct FunctionErrorRecord {
+    pub job_id: String,
+    pub fragment_id: i64,
+    /// The row's offset within the fragment; absent when the fragment's
+    /// detail was capped.
+    pub row_offset: Option<i64>,
+    pub column: String,
+    pub function: String,
+    pub function_version: String,
+    pub table_version: i64,
+    pub error_type: String,
+    pub error_message: String,
+    pub created_at_millis: i64,
+}
+
+impl From<lancedb::function::FunctionErrorRecord> for FunctionErrorRecord {
+    fn from(record: lancedb::function::FunctionErrorRecord) -> Self {
+        Self {
+            job_id: record.job_id,
+            fragment_id: record.fragment_id as i64,
+            row_offset: record.row_offset.map(i64::from),
+            column: record.column,
+            function: record.function,
+            function_version: record.function_version,
+            table_version: record.table_version as i64,
+            error_type: record.error_type,
+            error_message: record.error_message,
+            created_at_millis: record.created_at_millis,
+        }
+    }
+}
+
+/// A fragment whose per-row error detail was capped: `rowsSkipped` rows
+/// failed, of which only `rowsRecorded` have a record of their own.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct FunctionErrorFragment {
+    pub job_id: String,
+    pub fragment_id: i64,
+    pub rows_skipped: i64,
+    pub rows_recorded: i64,
+}
+
+impl From<lancedb::function::FunctionErrorFragment> for FunctionErrorFragment {
+    fn from(fragment: lancedb::function::FunctionErrorFragment) -> Self {
+        Self {
+            job_id: fragment.job_id,
+            fragment_id: fragment.fragment_id as i64,
+            rows_skipped: fragment.rows_skipped as i64,
+            rows_recorded: fragment.rows_recorded as i64,
+        }
+    }
+}
+
+/// A table's per-row Function errors.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct FunctionErrors {
+    /// The recorded rows, newest job first.
+    pub records: Vec<FunctionErrorRecord>,
+    /// Fragments whose detail was capped.
+    pub fragments: Vec<FunctionErrorFragment>,
+    /// Whether the listing stopped at its limit.
+    pub truncated: bool,
+}
+
+impl From<lancedb::function::FunctionErrors> for FunctionErrors {
+    fn from(errors: lancedb::function::FunctionErrors) -> Self {
+        Self {
+            records: errors.records.into_iter().map(Into::into).collect(),
+            fragments: errors.fragments.into_iter().map(Into::into).collect(),
+            truncated: errors.truncated,
+        }
+    }
+}
+
 #[napi(object)]
 pub struct RefreshMaterializedViewResult {
-    /// How the view was brought up to date: "rebuild", "incremental" or "no_op".
+    /// How the view was brought up to date: "rebuild".
     pub mode: String,
     pub rows_written: i64,
     pub source_version: i64,
@@ -1433,8 +1633,6 @@ impl From<lancedb::RefreshMaterializedViewResult> for RefreshMaterializedViewRes
     fn from(value: lancedb::RefreshMaterializedViewResult) -> Self {
         let mode = match value.mode {
             lancedb::RefreshMode::Rebuild => "rebuild",
-            lancedb::RefreshMode::Incremental => "incremental",
-            lancedb::RefreshMode::NoOp => "no_op",
         };
         Self {
             mode: mode.to_string(),