feat(nodejs): surface skip_auto_cleanup on add and merge insert

.agents/plugins/marketplace.json

@@ -1,20 +0,0 @@
-{
-  "name": "lancedb",
-  "interface": {
-    "displayName": "LanceDB"
-  },
-  "plugins": [
-    {
-      "name": "lancedb",
-      "source": {
-        "source": "local",
-        "path": "./plugins/lancedb"
-      },
-      "policy": {
-        "installation": "AVAILABLE",
-        "authentication": "ON_INSTALL"
-      },
-      "category": "Developer Tools"
-    }
-  ]
-}

.agents/skills/README.md

@@ -1,11 +0,0 @@
-# Agent Skills
-
-This directory contains repo-scoped code agent skills for the LanceDB project.
-
-Each skill is a folder that contains a required `SKILL.md` and optional bundled resources.
-
-Codex discovers skills from `.agents/skills` in the current working directory and parent directories.
-
-The `lancedb` skill lives in the `plugins/lancedb` plugin (see `plugins/lancedb/skills/lancedb`)
-so it can be installed via the plugin marketplaces (`.claude-plugin/marketplace.json` and
-`.agents/plugins/marketplace.json`); the `lancedb` entry here is a symlink into that plugin.

.agents/skills/lancedb

@@ -1 +0,0 @@
-../../plugins/lancedb/skills/lancedb

.agents/skills/lancedb-update-lance-dependency/SKILL.md

@@ -1,98 +0,0 @@
----
-name: lancedb-update-lance-dependency
-description: Update LanceDB to a specific Lance release or tag. Use when bumping Lance dependencies in the lancedb repository, including Rust workspace Lance crates, Java lance-core, validation, branch creation, commit, push, and PR creation when requested.
----
-
-# LanceDB Update Lance Dependency
-
-## Scope
-
-Use this skill in the `lancedb/lancedb` repository when updating the Lance dependency to a specific Lance version or tag.
-
-Inputs can be a version (`7.2.0-beta.1`), a tag (`v7.2.0-beta.1`), a tag ref (`refs/tags/v7.2.0-beta.1`), or `latest`.
-
-## Workflow
-
-1. Confirm the worktree status with `git status --short`.
-2. Resolve the target Lance version:
-
-   - If the input is `latest`, empty, or omitted, run:
-
-     ```bash
-     python3 ci/check_lance_release.py
-     ```
-
-     Parse the JSON output. If `needs_update` is not `true`, stop without creating a PR. Otherwise use `latest_tag`.
-
-   - If the input is explicit, use it directly.
-
-3. Compute update metadata without changing files:
-
-   ```bash
-   python3 ci/update_lance_dependency.py "$TAG_OR_VERSION" --metadata-only
-   ```
-
-   Before making changes, check for an existing open PR with the emitted `pr_title`:
-
-   ```bash
-   gh pr list --search "\"$PR_TITLE\" in:title" --state open --limit 1 --json number,url,title
-   ```
-
-   If a matching open PR exists, stop and report it instead of creating a duplicate.
-
-4. Run the deterministic update entrypoint:
-
-   ```bash
-   python3 ci/update_lance_dependency.py "$TAG_OR_VERSION"
-   ```
-
-   This updates the Rust workspace Lance dependencies through `ci/set_lance_version.py`, updates `java/pom.xml`, refreshes Cargo metadata, and prints JSON metadata containing `branch_name`, `commit_message`, and `pr_title`.
-
-5. Run validation:
-
-   ```bash
-   cargo clippy --quiet --workspace --tests --all-features -- -D warnings
-   cargo fmt --all --quiet
-   ```
-
-   Fix real diagnostics and rerun clippy until it succeeds. Do not skip warnings.
-
-6. Inspect `git status --short` and `git diff` to ensure only the Lance dependency update and required compatibility fixes are present.
-
-7. If the task only asks to prepare local changes, stop here and report the changed files and validation result.
-
-8. If the task asks to publish the update, create a branch using the printed `branch_name`, stage all relevant files, and commit using the printed `commit_message`. Do not amend or rewrite existing commits.
-
-9. Push to `origin`. Before creating the PR, check that the current token has push permission:
-
-   ```bash
-   gh api repos/lancedb/lancedb --jq .permissions.push
-   ```
-
-   If the remote branch already exists for the same generated branch name, delete the remote ref with `gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/$BRANCH_NAME`, then push. Do not force-push.
-
-10. Create a PR targeting `main` with the printed `pr_title`. If there is no PR template, keep the body to two or three concise sentences: state the Lance dependency bump, note any required compatibility fixes, and link the triggering Lance tag or release.
-
-11. Read back the remote PR title after creation. If it is not a Conventional Commit title, fix it immediately.
-
-12. When running in GitHub Actions after creating the LanceDB PR, trigger the Sophon dependency update:
-
-    ```bash
-    gh workflow run codex-bump-lancedb-lance.yml \
-      --repo lancedb/sophon \
-      -f lance_ref="$LANCE_TAG" \
-      -f lancedb_ref="$BRANCH_NAME"
-    gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle
-    ```
-
-    Use the emitted metadata `tag` value as `LANCE_TAG`. Do this only after a new LanceDB PR has been created. If the update was skipped because no update is needed or an open PR already exists, do not trigger Sophon.
-
-## GitHub Actions
-
-When this skill is used from GitHub Actions, `TAG`, `GH_TOKEN`, and `GITHUB_TOKEN` may already be set. Resolve `latest` first when `TAG` is empty. Once an explicit tag or version is known, use:
-
-```bash
-python3 ci/update_lance_dependency.py "$TAG" --github-output "$GITHUB_OUTPUT"
-```
-
-Then use the emitted `branch_name`, `commit_message`, and `pr_title` values for branch, commit, and PR creation.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.37.1-beta.0"
+current_version = "0.28.0-beta.11"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.
@@ -23,8 +23,6 @@ allow_dirty = true
 commit = true
 message = "Bump version: {current_version} → {new_version}"
 commit_args = ""
-# bump-my-version >=1.4.0 rejects pre_commit_hooks containing shell syntax unless opted in.
-allow_shell_hooks = true
 
 # Java maven files
 pre_commit_hooks = [
@@ -75,13 +73,6 @@ filename = "nodejs/Cargo.toml"
 replace = "\nversion = \"{new_version}\""
 search = "\nversion = \"{current_version}\""
 
-# The Python package takes its version from here (pyproject.toml declares
-# `dynamic = ["version"]`, so maturin reads it out of the crate manifest).
-[[tool.bumpversion.files]]
-filename = "python/Cargo.toml"
-replace = "\nversion = \"{new_version}\""
-search = "\nversion = \"{current_version}\""
-
 # Java documentation
 [[tool.bumpversion.files]]
 filename = "docs/src/java/java.md"

.claude-plugin/marketplace.json

@@ -1,19 +0,0 @@
-{
-  "name": "lancedb",
-  "owner": {
-    "name": "LanceDB"
-  },
-  "description": "LanceDB plugins for Claude Code.",
-  "plugins": [
-    {
-      "name": "lancedb",
-      "source": "./plugins/lancedb",
-      "description": "Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables.",
-      "version": "0.1.0",
-      "author": {
-        "name": "LanceDB"
-      },
-      "category": "development"
-    }
-  ]
-}

.github/actions/create-failure-issue/action.yml

@@ -27,31 +27,19 @@ runs:
           # Extract failed job names
           FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')
 
-          TITLE="$WORKFLOW_NAME Failed ($FAILED_JOBS)"
-
-          # This action now also runs on nightly schedules, so a breakage that
-          # persists for a few days would otherwise file one issue per night.
-          # Comment on the open report instead when one already exists.
-          EXISTING=$(gh issue list --state open --label ci --limit 100 --json number,title \
-            | jq -r --arg title "$TITLE" 'map(select(.title == $title)) | .[0].number // empty')
-
-          if [ -n "$EXISTING" ]; then
-            gh issue comment "$EXISTING" --body "Failed again: $RUN_URL"
-            echo "Commented on existing issue #$EXISTING"
-          else
-            gh issue create \
-              --title "$TITLE" \
-              --body "The workflow **$WORKFLOW_NAME** failed during execution.
+          # Create issue with workflow name, failed jobs, and run URL
+          gh issue create \
+            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
+            --body "The workflow **$WORKFLOW_NAME** failed during execution.
 
         **Failed jobs:** $FAILED_JOBS
 
         **Run URL:** $RUN_URL
 
         Please investigate the failed jobs and address any issues." \
-              --label "ci"
+            --label "ci"
 
-            echo "Issue created successfully"
-          fi
+          echo "Issue created successfully"
         else
           echo "No job failures detected, skipping issue creation"
         fi

.github/dependabot.yml

@@ -11,24 +11,8 @@ updates:
     schedule:
       interval: weekly
     open-pull-requests-limit: 10
-    # Only update Cargo.lock, never widen/raise the version requirements in
-    # Cargo.toml. The goal is keeping the lockfile (and the binaries we ship)
-    # current on security fixes, not forcing our library's consumers onto
-    # newer minimum versions.
-    versioning-strategy: lockfile-only
     groups:
       rust-minor-patch:
         update-types:
           - minor
           - patch
-
-  - package-ecosystem: pip
-    directory: /python
-    schedule:
-      interval: weekly
-    # Only update uv.lock, never widen version requirements in pyproject.toml.
-    versioning-strategy: lockfile-only
-    groups:
-      python-deps:
-        patterns:
-          - "*"

.github/workflows/build_linux_wheel/action.yml

@@ -18,14 +18,6 @@ inputs:
     description: "The manylinux version to build for"
     required: false
     default: "2_17"
-  package-name:
-    description: "Override [project] name in python/pyproject.toml (e.g. 'lancedb-compat'). Default keeps 'lancedb'."
-    required: false
-    default: "lancedb"
-  rustflags:
-    description: "RUSTFLAGS for the build container, as a single whitespace-free token (e.g. '-Ctarget-cpu=x86-64-v2'). Empty leaves RUSTFLAGS unset, keeping the defaults from .cargo/config.toml."
-    required: false
-    default: ""
 runs:
   using: "composite"
   steps:
@@ -35,18 +27,6 @@ runs:
         ARM_BUILD: ${{ inputs.arm-build }}
       run: |
         echo "ARM BUILD: $ARM_BUILD"
-    - name: Patch package name for variant build
-      if: ${{ inputs.package-name != 'lancedb' }}
-      shell: bash
-      env:
-        PACKAGE_NAME: ${{ inputs.package-name }}
-      run: |
-        # Swap the [project] name so this build produces e.g. lancedb-compat
-        # wheels. The package still installs files under the lancedb/
-        # namespace -- import lancedb still works after pip install.
-        sed -i.bak 's/^name = "lancedb"$/name = "'"$PACKAGE_NAME"'"/' python/pyproject.toml
-        rm -f python/pyproject.toml.bak
-        grep '^name = ' python/pyproject.toml
     - name: Build x86_64 Manylinux wheel
       if: ${{ inputs.arm-build == 'false' }}
       uses: PyO3/maturin-action@v1
@@ -54,16 +34,15 @@ runs:
         maturin-version: "1.12.4"
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc ${{ inputs.rustflags != '' && format('-e RUSTFLAGS={0}', inputs.rustflags) || '' }}"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         target: x86_64-unknown-linux-gnu
         manylinux: ${{ inputs.manylinux }}
         args: ${{ inputs.args }}
         before-script-linux: |
           set -e
-          curl -fsSL https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-x86_64.zip -o /tmp/protoc.zip
-          unzip /tmp/protoc.zip -d /usr/local
-          rm /tmp/protoc.zip
-          /usr/local/bin/protoc --version
+          curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-$(uname -m).zip > /tmp/protoc.zip \
+            && unzip /tmp/protoc.zip -d /usr/local \
+            && rm /tmp/protoc.zip
     - name: Build Arm Manylinux Wheel
       if: ${{ inputs.arm-build == 'true' }}
       uses: PyO3/maturin-action@v1
@@ -71,14 +50,13 @@ runs:
         maturin-version: "1.12.4"
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc ${{ inputs.rustflags != '' && format('-e RUSTFLAGS={0}', inputs.rustflags) || '' }}"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         target: aarch64-unknown-linux-gnu
         manylinux: ${{ inputs.manylinux }}
         args: ${{ inputs.args }}
         before-script-linux: |
           set -e
-          yum install -y clang
-          curl -fsSL https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-aarch_64.zip -o /tmp/protoc.zip
-          unzip /tmp/protoc.zip -d /usr/local
-          rm /tmp/protoc.zip
-          /usr/local/bin/protoc --version
+          yum install -y clang \
+            && curl -L https://github.com/protocolbuffers/protobuf/releases/download/v24.4/protoc-24.4-linux-aarch_64.zip > /tmp/protoc.zip \
+            && unzip /tmp/protoc.zip -d /usr/local \
+            && rm /tmp/protoc.zip

.github/workflows/build_windows_wheel/action.yml

@@ -29,3 +29,7 @@ runs:
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python
+    - uses: actions/upload-artifact@v4
+      with:
+        name: windows-wheels
+        path: python\target\wheels

.github/workflows/cargo-publish.yml

@@ -6,6 +6,7 @@ on:
       # We don't publish pre-releases for Rust. Crates.io is just a source
       # distribution, so we don't need to publish pre-releases.
       - "v*-beta*"
+      - "*-v*" # for example, python-vX.Y.Z
 
 env:
   # This env var is used by Swatinem/rust-cache@v2 for the cache
@@ -24,7 +25,7 @@ jobs:
     # Only runs on tags that matches the make-release action
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust
@@ -46,7 +47,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/codex-fix-ci.yml

@@ -36,14 +36,14 @@ jobs:
           echo "guidelines = ${{ inputs.guidelines }}"
 
       - name: Checkout Repo
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: ${{ inputs.branch }}
           fetch-depth: 0
           persist-credentials: true
 
       - name: Set up Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           # pnpm 11 (used by the nodejs install step below) requires
           # Node >= 22.13; use 24 since 22 hits EOL in October.
@@ -82,7 +82,7 @@ jobs:
           cache: maven
 
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Install Node.js dependencies for TypeScript bindings

.github/workflows/codex-update-lance-dependency.yml

@@ -4,16 +4,14 @@ on:
   workflow_call:
     inputs:
       tag:
-        description: "Tag name from Lance. If omitted, the skill will use the latest Lance release that needs an update."
-        required: false
-        default: ""
+        description: "Tag name from Lance"
+        required: true
         type: string
   workflow_dispatch:
     inputs:
       tag:
-        description: "Tag name from Lance. Leave empty to use the latest Lance release that needs an update."
-        required: false
-        default: ""
+        description: "Tag name from Lance"
+        required: true
         type: string
 
 permissions:
@@ -27,16 +25,16 @@ jobs:
     steps:
       - name: Show inputs
         run: |
-          echo "tag = ${{ inputs.tag || 'latest' }}"
+          echo "tag = ${{ inputs.tag }}"
 
       - name: Checkout Repo LanceDB
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           persist-credentials: true
 
       - name: Set up Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 20
 
@@ -73,21 +71,65 @@ jobs:
           OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
         run: |
           set -euo pipefail
-          TARGET_TAG="${TAG:-latest}"
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          # Use "chore" for beta/rc versions, "feat" for stable releases
+          if [[ "${VERSION}" == *beta* ]] || [[ "${VERSION}" == *rc* ]]; then
+            COMMIT_TYPE="chore"
+          else
+            COMMIT_TYPE="feat"
+          fi
 
           cat <<EOF >/tmp/codex-prompt.txt
-          You are running inside the lancedb repository on a GitHub Actions runner.
+          You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
 
-          Use \$lancedb-update-lance-dependency with target "${TARGET_TAG}".
+          Follow these steps exactly:
+          1. Use script "ci/set_lance_version.py" to update Lance Rust dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
+          2. Update the Java lance-core dependency version in "java/pom.xml": change the "<lance-core.version>...</lance-core.version>" property to "${VERSION}".
+          3. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
+          4. After clippy succeeds, run "cargo fmt --all" to format the workspace.
+          5. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
+          6. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
+          7. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
+          8. Push the branch to origin. If the remote branch already exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/${BRANCH_NAME}" then push with "git push origin ${BRANCH_NAME}". Do NOT use "git push --force" or "git push -f".
+          9. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
+          10. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
+          11. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
 
           Constraints:
-          - Use env "GH_TOKEN" for GitHub operations.
-          - Do not merge the pull request.
-          - Do not force-push.
-          - Do not create a duplicate pull request if an open PR already exists for the target Lance version.
-          - If any command fails, diagnose and fix the root cause instead of aborting.
-          - After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
+          - Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
+          - Do not merge the PR.
+          - If any command fails, diagnose and fix the issue instead of aborting.
           EOF
 
           printenv OPENAI_API_KEY | codex login --with-api-key
           codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"
+
+      - name: Trigger sophon dependency update
+        env:
+          TAG: ${{ inputs.tag }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          LANCEDB_BRANCH="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          echo "Triggering sophon workflow with:"
+          echo "  lance_ref: ${TAG#refs/tags/}"
+          echo "  lancedb_ref: ${LANCEDB_BRANCH}"
+
+          gh workflow run codex-bump-lancedb-lance.yml \
+            --repo lancedb/sophon \
+            -f lance_ref="${TAG#refs/tags/}" \
+            -f lancedb_ref="${LANCEDB_BRANCH}"
+
+      - name: Show latest sophon workflow run
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          echo "Latest sophon workflow run:"
+          gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/dev.yml

@@ -27,7 +27,7 @@ jobs:
     name: Verify PR title / description conforms to semantic-release
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-node@v6
+      - uses: actions/setup-node@v4
         with:
           node-version: "18"
       # These rules are disabled because Github will always ensure there

.github/workflows/docs.yml

@@ -35,7 +35,7 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Install dependencies needed for ubuntu
         run: |
           sudo apt install -y protobuf-compiler libssl-dev
@@ -53,7 +53,7 @@ jobs:
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
       - name: Set up node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: 'npm'

.github/workflows/gh-release.yml

@@ -1,85 +0,0 @@
-name: GitHub Release
-
-# All SDKs share one version, so a single `vX.Y.Z` tag produces a single GitHub
-# release covering all of them. The per-package publish workflows (PyPI, NPM,
-# Cargo, Maven) trigger off the same tag independently.
-
-on:
-  push:
-    tags:
-      - "v*"
-
-permissions:
-  contents: read
-
-jobs:
-  gh-release:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Extract version
-        id: extract_version
-        env:
-          GITHUB_REF: ${{ github.ref }}
-        run: |
-          set -e
-          echo "Extracting tag and version from $GITHUB_REF"
-          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
-            VERSION=${BASH_REMATCH[1]}
-            TAG=v$VERSION
-            echo "tag=$TAG" >> $GITHUB_OUTPUT
-            echo "version=$VERSION" >> $GITHUB_OUTPUT
-          else
-            echo "Failed to extract version from $GITHUB_REF"
-            exit 1
-          fi
-          echo "Extracted version $VERSION from $GITHUB_REF"
-          if [[ $VERSION =~ beta ]]; then
-            echo "This is a beta release"
-            echo "prerelease=true" >> $GITHUB_OUTPUT
-
-            # Get last release (that is not this one)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          else
-            echo "This is a stable release"
-            echo "prerelease=false" >> $GITHUB_OUTPUT
-            # Get last stable tag (ignore betas)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | grep -v beta \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          fi
-          echo "Found from tag $FROM_TAG"
-          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
-      - name: Create Release Notes
-        id: release_notes
-        uses: mikepenz/release-changelog-builder-action@v4
-        with:
-          configuration: .github/release_notes.json
-          toTag: ${{ steps.extract_version.outputs.tag }}
-          fromTag: ${{ steps.extract_version.outputs.from_tag }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Create GH release
-        uses: softprops/action-gh-release@v2
-        with:
-          # Marking betas as pre-releases keeps them from taking the "Latest"
-          # badge on the releases page.
-          prerelease: ${{ steps.extract_version.outputs.prerelease }}
-          make_latest: ${{ steps.extract_version.outputs.prerelease == 'false' }}
-          tag_name: ${{ steps.extract_version.outputs.tag }}
-          token: ${{ secrets.GITHUB_TOKEN }}
-          generate_release_notes: false
-          name: LanceDB v${{ steps.extract_version.outputs.version }}
-          body: ${{ steps.release_notes.outputs.changelog }}

.github/workflows/java-publish.yml

@@ -32,7 +32,7 @@ jobs:
         working-directory: ./java
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Set up Java 8
         uses: actions/setup-java@v4
         with:
@@ -73,7 +73,7 @@ jobs:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/java.yml

@@ -36,7 +36,7 @@ jobs:
         working-directory: ./java
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Set up Java 17
         uses: actions/setup-java@v4
         with:

.github/workflows/lance-release-timer.yml

@@ -0,0 +1,62 @@
+name: Lance Release Timer
+
+on:
+  schedule:
+    - cron: "*/10 * * * *"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  actions: write
+
+concurrency:
+  group: lance-release-timer
+  cancel-in-progress: false
+
+jobs:
+  trigger-update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Check for new Lance tag
+        id: check
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          python3 ci/check_lance_release.py --github-output "$GITHUB_OUTPUT"
+
+      - name: Look for existing PR
+        if: steps.check.outputs.needs_update == 'true'
+        id: pr
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          TITLE="chore: update lance dependency to v${{ steps.check.outputs.latest_version }}"
+          COUNT=$(gh pr list --search "\"$TITLE\" in:title" --state open --limit 1 --json number --jq 'length')
+          if [ "$COUNT" -gt 0 ]; then
+            echo "Open PR already exists for $TITLE"
+            echo "pr_exists=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "No existing PR for $TITLE"
+            echo "pr_exists=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Trigger codex update workflow
+        if: steps.check.outputs.needs_update == 'true' && steps.pr.outputs.pr_exists != 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          TAG=${{ steps.check.outputs.latest_tag }}
+          gh workflow run codex-update-lance-dependency.yml -f tag=refs/tags/$TAG
+
+      - name: Show latest codex workflow run
+        if: steps.check.outputs.needs_update == 'true' && steps.pr.outputs.pr_exists != 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/license-header-check.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
       - name: Install license-header-checker
         working-directory: /tmp
         run: |

.github/workflows/make-release-commit.yml

@@ -1,14 +1,13 @@
 name: Create release commit
 
-# This workflow increments the version, tags it, and pushes it. All SDKs share
-# a single version, so one tag releases all of them.
+# This workflow increments versions, tags the version, and pushes it.
 # When a tag is pushed, another workflow is triggered that creates a GH release
 # and uploads the binaries. This workflow is only for creating the tag.
 
 # This script will enforce that a minor version is incremented if there are any
-# breaking changes since the last minor increment. A breaking change in any SDK
-# bumps the minor version for all of them. If you wish to bypass this check, you
-# can manually increment the version and push the tag.
+# breaking changes since the last minor increment. However, it isn't able to
+# differentiate between breaking changes in Node versus Python. If you wish to
+# bypass this check, you can manually increment the version and push the tag.
 on:
   workflow_dispatch:
     inputs:
@@ -25,6 +24,16 @@ on:
         options:
           - preview
           - stable
+      python:
+        description: 'Make a Python release'
+        required: true
+        default: true
+        type: boolean
+      other:
+        description: 'Make a Node/Rust/Java release'
+        required: true
+        default: true
+        type: boolean
       bump-minor:
         description: 'Bump minor version'
         required: true
@@ -40,7 +49,7 @@ jobs:
     steps:
       - name: Output Inputs
         run: echo "${{ toJSON(github.event.inputs) }}"
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -56,16 +65,29 @@ jobs:
         run: |
           git config user.name 'Lance Release'
           git config user.email 'lance-dev@lancedb.com'
-      - name: Bump version
+      - name: Bump Python version
+        if: ${{ inputs.python }}
+        working-directory: python
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Need to get the commit before bumping the version, so we can
+          # determine if there are breaking changes in the next step as well.
+          echo "COMMIT_BEFORE_BUMP=$(git rev-parse HEAD)" >> $GITHUB_ENV
+
+          pip install bump-my-version PyGithub packaging
+          bash ../ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} python-v
+      - name: Bump Node/Rust version
+        if: ${{ inputs.other }}
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           pip install bump-my-version PyGithub packaging
-          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }}
+          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
           bash ci/update_lockfiles.sh --amend
       - name: Push new version tag
         if: ${{ !inputs.dry_run }}
-        uses: ad-m/github-push-action@881a6320fdb16eb5318c5054f31c218aec2b324c # v1.3.0
+        uses: ad-m/github-push-action@master
         with:
           # Need to use PAT here too to trigger next workflow. See comment above.
           github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}

.github/workflows/nodejs.yml

@@ -38,14 +38,14 @@ jobs:
       CC: gcc-12
       CXX: g++-12
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       with:
         # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
         # in October. The library itself still supports Node >= 18
@@ -61,11 +61,6 @@ jobs:
         sudo apt update
         sudo apt install -y protobuf-compiler libssl-dev
     - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
     - name: Format Rust
       run: cargo fmt --all -- --check
     - name: Lint Rust
@@ -91,14 +86,14 @@ jobs:
         shell: bash
         working-directory: nodejs
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       name: Setup Node.js 24 for build
       with:
         # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
@@ -108,11 +103,6 @@ jobs:
         cache: 'pnpm'
         cache-dependency-path: nodejs/pnpm-lock.yaml
     - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
     - name: Install dependencies
       run: |
         sudo apt update
@@ -140,7 +130,7 @@ jobs:
           echo "Run 'pnpm run docs', fix any warnings, and commit the changes."
           exit 1
         fi
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       name: Setup Node.js ${{ matrix.node-version }} for test
       with:
         node-version: ${{ matrix.node-version }}
@@ -167,23 +157,20 @@ jobs:
         npx jest --testEnvironment jest-environment-node-single-context --verbose
   macos:
     timeout-minutes: 30
-    # macos-15 ships a newer linker; the older macos-14 linker fails to insert
-    # branch islands when the debug cdylib's __text section exceeds the 128 MB
-    # AArch64 B/BL branch range.
-    runs-on: "macos-15"
+    runs-on: "macos-14"
     defaults:
       run:
         shell: bash
         working-directory: nodejs
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v6
+    - uses: pnpm/action-setup@v4
       with:
         version: 11.1.1
-    - uses: actions/setup-node@v6
+    - uses: actions/setup-node@v4
       with:
         # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
         # in October.
@@ -192,11 +179,6 @@ jobs:
         cache-dependency-path: nodejs/pnpm-lock.yaml
     - uses: dtolnay/rust-toolchain@stable
     - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
     - name: Install dependencies
       run: |
         brew install protobuf

.github/workflows/npm-publish.yml

@@ -10,16 +10,10 @@ permissions:
 
 on:
   push:
+    branches:
+      - main
     tags:
       - "v*"
-  # The cross-compiled targets (musl especially) break from toolchain and
-  # dependency changes that nothing else in CI catches, and discovering that
-  # mid-release is expensive. A nightly run keeps that signal while dropping
-  # the full 8-target release matrix from all ~90 pushes to main each month.
-  # `report-failure` files an issue when a nightly breaks.
-  schedule:
-    - cron: "0 8 * * *"
-  workflow_dispatch:
   pull_request:
     # This should trigger a dry run (we skip the final publish step)
     paths:
@@ -32,6 +26,73 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  gh-release:
+    if: startsWith(github.ref, 'refs/tags/v')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Extract version
+        id: extract_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: |
+          set -e
+          echo "Extracting tag and version from $GITHUB_REF"
+          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
+            VERSION=${BASH_REMATCH[1]}
+            TAG=v$VERSION
+            echo "tag=$TAG" >> $GITHUB_OUTPUT
+            echo "version=$VERSION" >> $GITHUB_OUTPUT
+          else
+            echo "Failed to extract version from $GITHUB_REF"
+            exit 1
+          fi
+          echo "Extracted version $VERSION from $GITHUB_REF"
+          if [[ $VERSION =~ beta ]]; then
+            echo "This is a beta release"
+
+            # Get last release (that is not this one)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^v \
+              | grep -vF "$TAG" \
+              | python ci/semver_sort.py v \
+              | tail -n 1)
+          else
+            echo "This is a stable release"
+            # Get last stable tag (ignore betas)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^v \
+              | grep -vF "$TAG" \
+              | grep -v beta \
+              | python ci/semver_sort.py v \
+              | tail -n 1)
+          fi
+          echo "Found from tag $FROM_TAG"
+          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
+      - name: Create Release Notes
+        id: release_notes
+        uses: mikepenz/release-changelog-builder-action@v4
+        with:
+          configuration: .github/release_notes.json
+          toTag: ${{ steps.extract_version.outputs.tag }}
+          fromTag: ${{ steps.extract_version.outputs.from_tag }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Create GH release
+        uses: softprops/action-gh-release@v2
+        with:
+          prerelease: ${{ contains('beta', github.ref) }}
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          generate_release_notes: false
+          name: Node/Rust LanceDB v${{ steps.extract_version.outputs.version }}
+          body: ${{ steps.release_notes.outputs.changelog }}
+
   build-lancedb:
     strategy:
       fail-fast: false
@@ -40,18 +101,9 @@ jobs:
           - target: aarch64-apple-darwin
             host: macos-latest
             features: fp16kernels
-            pre_build: |-
-              brew install protobuf
-              # Fat LTO (the workspace default in .cargo/config.toml) is
-              # single-threaded and is the peak-memory step of the build. On
-              # this runner it accounted for ~111 of the job's ~113 minutes,
-              # making it the critical path of the entire publish pipeline.
-              # ThinLTO parallelizes it across the runner's cores, for a few
-              # percent of runtime performance.
-              export CARGO_PROFILE_RELEASE_LTO=thin
-              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
+            pre_build: brew install protobuf
           - target: x86_64-pc-windows-msvc
-            host: windows-2025
+            host: windows-latest
             features: ","
             pre_build: |-
               choco install --no-progress protoc ninja nasm
@@ -59,21 +111,12 @@ jobs:
               # There is an issue where choco doesn't add nasm to the path
               export PATH="$PATH:/c/Program Files/NASM"
               nasm -v
-              # See the ThinLTO note on aarch64-apple-darwin above. Keeping
-              # peak memory down is also what lets this run on the standard
-              # 4-core runner: the 8-core larger runner was only needed to
-              # stop fat LTO from OOMing rustc-LLVM.
-              export CARGO_PROFILE_RELEASE_LTO=thin
-              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
           - target: aarch64-pc-windows-msvc
-            host: windows-2025
+            host: windows-latest
             features: ","
             pre_build: |-
                 choco install --no-progress protoc
                 rustup target add aarch64-pc-windows-msvc
-                # See the ThinLTO note on aarch64-apple-darwin above.
-                export CARGO_PROFILE_RELEASE_LTO=thin
-                export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
           - target: x86_64-unknown-linux-gnu
             host: ubuntu-latest
             features: fp16kernels
@@ -127,13 +170,13 @@ jobs:
       run:
         working-directory: nodejs
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Setup node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
           # in October.
@@ -146,49 +189,16 @@ jobs:
         with:
           toolchain: stable
           targets: ${{ matrix.settings.target }}
-      # These builds were entirely uncached: the old key was static, so
-      # `actions/cache` (which only writes on a miss) could never refresh it,
-      # and the multi-GB whole-`target/` copy it tried to store never fit the
-      # repo's cache budget, so no entry was ever saved. rust-cache prunes
-      # `target/` to dependency artifacts and keys on Cargo.lock plus the rustc
-      # version, which both fixes the key and keeps entries a sane size.
-      #
-      # This caches dependency *compilation* only. The LTO link of the cdylib
-      # re-runs regardless, since the local crate changes every time, so the
-      # win is larger on the non-LTO jobs than here.
-      - name: Cache cargo (native builds)
-        uses: Swatinem/rust-cache@v2
-        if: ${{ !matrix.settings.docker }}
+      - name: Cache cargo
+        uses: actions/cache@v4
         with:
-          # The release profile and per-target dirs differ from what the test
-          # workflows cache, so these need to be separate entries.
-          key: release-${{ matrix.settings.target }}
-          # Only the nightly run on main writes, so tag and PR runs restore a
-          # warm entry without every dependabot PR writing its own (which would
-          # be unreadable elsewhere anyway, since GitHub scopes caches to the
-          # creating ref). The nightly cadence also keeps entries inside
-          # GitHub's 7-day eviction window, which a tag-only trigger would not.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
-      # Docker builds can use rust-cache too. `target/` already lives on the
-      # host because the whole workspace is bind-mounted into the container, and
-      # rust-cache's prune and save run host-side, so they can manage it -- which
-      # is what keeps the entry to dependency artifacts rather than a multi-GB
-      # copy of everything.
-      #
-      # Two differences from the native builds. The container's CARGO_HOME is
-      # bind-mounted from `.cargo-cache` rather than the host's ~/.cargo, so that
-      # has to be cached explicitly. And the key is derived from the *host* rustc
-      # version, which is not the compiler that produced these artifacts; that is
-      # safe because cargo fingerprints the real compiler and rebuilds on a
-      # mismatch, it just means a base-image toolchain bump costs one cold build
-      # instead of invalidating the key.
-      - name: Cache cargo (docker builds)
-        uses: Swatinem/rust-cache@v2
-        if: ${{ matrix.settings.docker }}
-        with:
-          key: docker-${{ matrix.settings.target }}
-          cache-directories: .cargo-cache
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            .cargo-cache
+            target/
+          key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
       - name: Install Zig
@@ -206,13 +216,9 @@ jobs:
         if: ${{ matrix.settings.docker }}
         with:
           image: ${{ matrix.settings.docker }}
-          # All three mounts must live under `.cargo-cache`, which is what the
-          # cache step above saves. Previously the registry mounts pointed at
-          # `.cargo/...`, a path nothing cached, so the container re-downloaded
-          # the whole crate registry on every run.
           options: "--user 0:0 -v ${{ github.workspace }}/.cargo-cache/git/db:/usr/local/cargo/git/db \
-                    -v ${{ github.workspace }}/.cargo-cache/registry/cache:/usr/local/cargo/registry/cache \
-                    -v ${{ github.workspace }}/.cargo-cache/registry/index:/usr/local/cargo/registry/index \
+                    -v ${{ github.workspace }}/.cargo/registry/cache:/usr/local/cargo/registry/cache \
+                    -v ${{ github.workspace }}/.cargo/registry/index:/usr/local/cargo/registry/index \
                     -v ${{ github.workspace }}:/build -w /build/nodejs"
           run: |
             set -e
@@ -224,16 +230,6 @@ jobs:
               --js ../lancedb/native.js \
               --strip \
               --output-dir dist/
-      # The container runs as root (`--user 0:0`), so everything it wrote to the
-      # mounted cache dirs is root-owned. rust-cache's post step runs as the
-      # runner user and has to both read these and delete from them while
-      # pruning, so hand them back before it runs.
-      - name: Take ownership of docker build output
-        if: ${{ matrix.settings.docker }}
-        run: |
-          sudo chown -R "$(id -u):$(id -g)" \
-            "${{ github.workspace }}/.cargo-cache" \
-            "${{ github.workspace }}/target"
       - name: Build
         run: |
           ${{ matrix.settings.pre_build }}
@@ -247,17 +243,8 @@ jobs:
               --output-dir dist/
         if: ${{ !matrix.settings.docker }}
         shell: bash
-      # The standard Windows runners have ~14 GB free, and a release `target/`
-      # for this workspace is a large fraction of that. Report the remaining
-      # headroom so a build that only just fits is visible before a dependency
-      # bump turns it into a failed release. `always()` so the numbers are
-      # still there when the build is what ran out of space.
-      - name: Report disk headroom
-        if: always()
-        run: df -h
-        shell: bash
       - name: Upload artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: lancedb-${{ matrix.settings.target }}
           path: nodejs/dist/*.node
@@ -269,7 +256,7 @@ jobs:
         run: pnpm tsc
       - name: Upload Generic Artifacts
         if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
         with:
           name: nodejs-dist
           path: |
@@ -300,13 +287,13 @@ jobs:
         shell: bash
         working-directory: nodejs
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Setup Node.js 24 for install
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
           # in October.
@@ -316,18 +303,18 @@ jobs:
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
       - name: Setup Node.js ${{ matrix.node }} for test
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node }}
       - name: Download artifacts
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v4
         with:
           name: lancedb-${{ matrix.settings.target }}
           path: nodejs/dist/
           # For testing purposes:
           # run-id: 13982782871
           # github-token: ${{ secrets.GITHUB_TOKEN }} # token with actions:read permissions on target repo
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: nodejs-dist
           path: nodejs/dist
@@ -352,13 +339,13 @@ jobs:
     needs:
       - test-lancedb
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Setup pnpm
-        uses: pnpm/action-setup@v6
+        uses: pnpm/action-setup@v4
         with:
           version: 11.1.1
       - name: Setup node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 24
           cache: pnpm
@@ -366,14 +353,14 @@ jobs:
           registry-url: "https://registry.npmjs.org"
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         with:
           name: nodejs-dist
           path: nodejs/dist
           # For testing purposes:
           # run-id: 13982782871
           # github-token: ${{ secrets.GITHUB_TOKEN }} # token with actions:read permissions on target repo
-      - uses: actions/download-artifact@v8
+      - uses: actions/download-artifact@v4
         name: Download arch-specific binaries
         with:
           pattern: lancedb-*
@@ -406,14 +393,12 @@ jobs:
     name: Report Workflow Failure
     runs-on: ubuntu-latest
     needs: [build-lancedb, test-lancedb, publish]
-    # Nightly runs are the only thing watching the cross-compiled targets now,
-    # so they have to report failures too or the signal is silently lost.
-    if: always() && failure() && (startsWith(github.ref, 'refs/tags/v') || github.event_name == 'schedule')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
     permissions:
       contents: read
       issues: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/pypi-publish.yml

@@ -3,14 +3,11 @@ name: PyPI Publish
 on:
   push:
     tags:
-      - 'v*'
+      - 'python-v*'
   pull_request:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/pypi-publish.yml
-      - .github/workflows/build_linux_wheel/action.yml
-      - .github/workflows/build_mac_wheel/action.yml
-      - .github/workflows/build_windows_wheel/action.yml
       - Cargo.toml # Change in dependency frequently breaks builds
       - Cargo.lock
 
@@ -20,48 +17,36 @@ env:
 permissions:
   contents: read
 
-# Without this, a force-push to a PR leaves the previous run going -- including
-# a ~74 minute Windows job and a billed arm64 wheel build.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 jobs:
   linux:
-    name: Python ${{ matrix.config.package_name }} ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
+    name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
     timeout-minutes: 60
+    permissions:
+      id-token: write
+      contents: read
     strategy:
       matrix:
         config:
+          - platform: x86_64
+            manylinux: "2_17"
+            extra_args: ""
+            runner: ubuntu-22.04
           - platform: x86_64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
             runner: ubuntu-22.04
-            package_name: "lancedb"
-            rustflags: ""
-          # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+          - platform: aarch64
+            manylinux: "2_17"
+            extra_args: ""
+            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+            runner: ubuntu-2404-8x-arm64
           - platform: aarch64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
             runner: ubuntu-2404-8x-arm64
-            package_name: "lancedb"
-            rustflags: ""
-          # `lancedb-compat`: pre-Haswell-friendly variant for x86_64 hosts
-          # without AVX2 (Sandy Bridge / Ivy Bridge / Westmere on Intel,
-          # Bulldozer / Piledriver / Steamroller on AMD). Compiled at the
-          # `x86-64-v2` baseline; runtime SIMD dispatch in lance-linalg
-          # picks the appropriate tier (scalar / AVX / AVX+FMA / AVX2+FMA
-          # / AVX-512) at load time. Same import as `lancedb` -- conflicts
-          # at install time, so users pick one.
-          - platform: x86_64
-            manylinux: "2_28"
-            extra_args: ""
-            runner: ubuntu-22.04
-            package_name: "lancedb-compat"
-            rustflags: "-Ctarget-cpu=x86-64-v2"
     runs-on: ${{ matrix.config.runner }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -75,16 +60,15 @@ jobs:
           args: "--release --strip ${{ matrix.config.extra_args }}"
           arm-build: ${{ matrix.config.platform == 'aarch64' }}
           manylinux: ${{ matrix.config.manylinux }}
-          package-name: ${{ matrix.config.package_name }}
-          rustflags: ${{ matrix.config.rustflags }}
-      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+      - uses: ./.github/workflows/upload_wheel
+        if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-linux-${{ matrix.config.package_name }}-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
-          path: target/wheels/*.whl
-          if-no-files-found: error
+          fury_token: ${{ secrets.FURY_TOKEN }}
   mac:
     timeout-minutes: 90
+    permissions:
+      id-token: write
+      contents: read
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
@@ -94,7 +78,7 @@ jobs:
     env:
       MACOSX_DEPLOYMENT_TARGET: 10.15
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -106,21 +90,18 @@ jobs:
         with:
           python-minor-version: 10
           args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
-      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+      - uses: ./.github/workflows/upload_wheel
+        if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-mac-${{ matrix.config.target }}
-          path: target/wheels/lancedb-*.whl
-          if-no-files-found: error
+          fury_token: ${{ secrets.FURY_TOKEN }}
   windows:
-    timeout-minutes: 90
+    timeout-minutes: 60
+    permissions:
+      id-token: write
+      contents: read
     runs-on: windows-latest
-    env:
-      # link.exe is single-threaded and the long pole on Windows builds. Use
-      # rustc's bundled lld-link instead.
-      CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: rust-lld
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -128,84 +109,91 @@ jobs:
         uses: actions/setup-python@v6
         with:
           python-version: "3.13"
-      # NOTE: caching cargo here would be a no-op. This workflow only runs on
-      # tags and PRs, and GitHub only lets a run restore caches from its own ref
-      # or the default branch -- so with no run on main there is nothing that
-      # can populate an entry the release build would be allowed to read. Fixing
-      # this needs a main/nightly trigger (which would also catch wheel-build
-      # breakage before a release); the ~74 minutes here is otherwise dominated
-      # by the fat-LTO link, which no cache avoids.
       - uses: ./.github/workflows/build_windows_wheel
         with:
           python-minor-version: 10
           args: "--release --strip"
-      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+          vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
+      - uses: ./.github/workflows/upload_wheel
+        if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-windows
-          path: target/wheels/lancedb-*.whl
-          if-no-files-found: error
-  publish:
-    name: Publish wheels
-    if: startsWith(github.ref, 'refs/tags/v')
-    needs: [linux, mac, windows]
+          fury_token: ${{ secrets.FURY_TOKEN }}
+  gh-release:
+    if: startsWith(github.ref, 'refs/tags/python-v')
     runs-on: ubuntu-latest
     permissions:
-      id-token: write
-      contents: read
+      contents: write
     steps:
-      - uses: actions/checkout@v6
-      - name: Download wheel artifacts
-        uses: actions/download-artifact@v8
+      - uses: actions/checkout@v4
         with:
-          pattern: wheels-*
-          path: target/wheels
-          merge-multiple: true
-      - name: List wheels
-        run: ls -la target/wheels
-      - name: Choose repo
-        id: choose_repo
-        run: |
-          if [[ ${{ github.ref }} == *beta* ]]; then
-            echo "repo=fury" >> $GITHUB_OUTPUT
-          else
-            echo "repo=pypi" >> $GITHUB_OUTPUT
-          fi
-      - name: Publish to Fury
-        if: steps.choose_repo.outputs.repo == 'fury'
+          fetch-depth: 0
+          lfs: true
+      - name: Extract version
+        id: extract_version
         env:
-          FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
+          GITHUB_REF: ${{ github.ref }}
         run: |
-          shopt -s nullglob
-          WHEELS=(target/wheels/*.whl)
-          if [[ ${#WHEELS[@]} -eq 0 ]]; then
-            echo "No wheels found in target/wheels/" >&2
+          set -e
+          echo "Extracting tag and version from $GITHUB_REF"
+          if [[ $GITHUB_REF =~ refs/tags/python-v(.*) ]]; then
+            VERSION=${BASH_REMATCH[1]}
+            TAG=python-v$VERSION
+            echo "tag=$TAG" >> $GITHUB_OUTPUT
+            echo "version=$VERSION" >> $GITHUB_OUTPUT
+          else
+            echo "Failed to extract version from $GITHUB_REF"
             exit 1
           fi
-          for WHEEL in "${WHEELS[@]}"; do
-            echo "Uploading $WHEEL to Fury"
-            curl -f -F package=@"$WHEEL" "https://$FURY_TOKEN@push.fury.io/lancedb/"
-          done
-      # NOTE: pypa/gh-action-pypi-publish must be invoked directly from a
-      # workflow file, not from inside a composite action. When called from a
-      # composite, `github.action_repository` is empty (actions/runner#2473)
-      # and the action falls back to `github.repository`, producing a bogus
-      # `docker://ghcr.io/<repo>:<ref>` image reference that GHA tries to pull.
-      - name: Publish to PyPI
-        if: steps.choose_repo.outputs.repo == 'pypi'
-        uses: pypa/gh-action-pypi-publish@release/v1
+          echo "Extracted version $VERSION from $GITHUB_REF"
+          if [[ $VERSION =~ beta ]]; then
+            echo "This is a beta release"
+
+            # Get last release (that is not this one)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^python-v \
+              | grep -vF "$TAG" \
+              | python ci/semver_sort.py python-v \
+              | tail -n 1)
+          else
+            echo "This is a stable release"
+            # Get last stable tag (ignore betas)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^python-v \
+              | grep -vF "$TAG" \
+              | grep -v beta \
+              | python ci/semver_sort.py python-v \
+              | tail -n 1)
+          fi
+          echo "Found from tag $FROM_TAG"
+          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
+      - name: Create Python Release Notes
+        id: python_release_notes
+        uses: mikepenz/release-changelog-builder-action@v4
         with:
-          packages-dir: target/wheels/
+          configuration: .github/release_notes.json
+          toTag: ${{ steps.extract_version.outputs.tag }}
+          fromTag: ${{ steps.extract_version.outputs.from_tag }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Create Python GH release
+        uses: softprops/action-gh-release@v2
+        with:
+          prerelease: ${{ contains('beta', github.ref) }}
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          generate_release_notes: false
+          name: Python LanceDB v${{ steps.extract_version.outputs.version }}
+          body: ${{ steps.python_release_notes.outputs.changelog }}
   report-failure:
     name: Report Workflow Failure
     runs-on: ubuntu-latest
-    needs: [linux, mac, windows, publish]
+    needs: [linux, mac, windows]
     permissions:
       contents: read
       issues: write
-    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/python.yml

@@ -41,7 +41,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -66,7 +66,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -95,7 +95,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -108,15 +108,6 @@ jobs:
         run: |
           sudo apt update
           sudo apt install -y protobuf-compiler
-      # `pip install -e .` builds the extension with maturin, which is most of
-      # this job's ~33 minutes. It had no Rust cache, so every dependency was
-      # recompiled from scratch on every run.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install
         run: |
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
@@ -135,7 +126,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -169,7 +160,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -177,14 +168,6 @@ jobs:
         uses: actions/setup-python@v6
         with:
           python-version: "3.13"
-      # maturin runs cargo natively on macOS (docker is Linux-only), so the host
-      # target dir is cacheable. This job had no Rust cache.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - uses: ./.github/workflows/build_mac_wheel
         with:
           args: --profile ci
@@ -206,7 +189,7 @@ jobs:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -214,14 +197,6 @@ jobs:
         uses: actions/setup-python@v6
         with:
           python-version: "3.13"
-      # maturin runs cargo natively on Windows (docker is Linux-only), so the
-      # host target dir is cacheable. This job had no Rust cache at all and so
-      # rebuilt every dependency from scratch on every run.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. The repo sits at
-          # GitHub's cache cap, so per-PR saves just evict main's entries.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - uses: ./.github/workflows/build_windows_wheel
         with:
           args: --profile ci
@@ -230,14 +205,14 @@ jobs:
       - name: Delete wheels
         run: rm -rf target/wheels
   pydantic1x:
-    timeout-minutes: 60
+    timeout-minutes: 30
     runs-on: "ubuntu-24.04"
     defaults:
       run:
         shell: bash
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -249,14 +224,6 @@ jobs:
         uses: actions/setup-python@v6
         with:
           python-version: "3.10"
-      # As with Doctest, `pip install -e .` compiles the extension and this job
-      # had no Rust cache, which is most of its ~37 minutes.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install lancedb
         run: |
           pip install "pydantic<2"

.github/workflows/rust.yml

@@ -40,7 +40,7 @@ jobs:
       CC: clang-18
       CXX: clang++-18
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -48,11 +48,6 @@ jobs:
         with:
           components: rustfmt, clippy
       - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install dependencies
         run: |
           sudo apt update
@@ -70,7 +65,7 @@ jobs:
     timeout-minutes: 10
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: EmbarkStudios/cargo-deny-action@v2
         with:
           command: check advisories bans licenses sources
@@ -83,7 +78,7 @@ jobs:
       CC: clang
       CXX: clang++
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       # Building without a lock file often requires the latest Rust version since downstream
       # dependencies may have updated their minimum Rust version.
       - uses: actions-rust-lang/setup-rust-toolchain@v1
@@ -94,11 +89,6 @@ jobs:
         run: rm -f Cargo.lock
       - uses: rui314/setup-mold@v1
       - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install dependencies
         run: |
           sudo apt update
@@ -108,7 +98,7 @@ jobs:
           cargo build --profile ci --benches --all-features --tests
 
   linux:
-    timeout-minutes: 60
+    timeout-minutes: 30
     # To build all features, we need more disk space than is available
     # on the free OSS github runner. This is mostly due to the the
     # sentence-transformers feature.
@@ -123,16 +113,11 @@ jobs:
       CXX: clang++-18
       GH_TOKEN: ${{ secrets.SOPHON_READ_TOKEN }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
       - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install dependencies
         run: |
           sudo apt update
@@ -140,26 +125,10 @@ jobs:
       - uses: rui314/setup-mold@v1
       - name: Make Swap
         run: |
-          swapfile=/swapfile
-          min_swap_bytes=$((15 * 1024 * 1024 * 1024))
-          active_swap_bytes="$(sudo swapon --show=NAME,SIZE --bytes --noheadings | awk '$1 == "/swapfile" { print $2 }')"
-          if [ -n "$active_swap_bytes" ]; then
-            if [ "$active_swap_bytes" -ge "$min_swap_bytes" ]; then
-              echo "/swapfile is already active with enough space; skipping swap creation"
-              exit 0
-            fi
-            echo "/swapfile is already active but smaller than 16G; using /mnt/lancedb-swapfile"
-            swapfile=/mnt/lancedb-swapfile
-          fi
-          if sudo swapon --show=NAME --noheadings | grep -Fxq "$swapfile"; then
-            echo "$swapfile is already active; skipping swap creation"
-            exit 0
-          fi
-          sudo rm -f "$swapfile"
-          sudo fallocate -l 16G "$swapfile"
-          sudo chmod 600 "$swapfile"
-          sudo mkswap "$swapfile"
-          sudo swapon "$swapfile"
+          sudo fallocate -l 16G /swapfile
+          sudo chmod 600 /swapfile
+          sudo mkswap /swapfile
+          sudo swapon /swapfile
       - name: Build
         run: cargo build --profile ci --all-features --tests --locked --examples
       - name: Run feature tests
@@ -173,7 +142,7 @@ jobs:
         run: CARGO_ARGS="--profile ci" make -C ./lancedb remote-tests
 
   macos:
-    timeout-minutes: 60
+    timeout-minutes: 30
     strategy:
       matrix:
         mac-runner: ["macos-14", "macos-15"]
@@ -183,18 +152,13 @@ jobs:
         shell: bash
         working-directory: rust
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
       - name: CPU features
         run: sysctl -a | grep cpu
       - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install dependencies
         run: brew install protobuf
       - name: Run tests
@@ -207,32 +171,20 @@ jobs:
           cargo test --profile ci --features $ALL_FEATURES --locked
 
   windows:
+    runs-on: windows-2022
     strategy:
-      fail-fast: false
       matrix:
-        include:
-          - target: x86_64-pc-windows-msvc
-            runner: windows-2022
-          # windows-11-arm is a standard runner, so it is free on public repos.
-          # Running natively lets the aarch64 tests actually execute -- this
-          # job used to cross-compile them and then skip the test step, paying
-          # full codegen and link cost for a compile check.
-          - target: aarch64-pc-windows-msvc
-            runner: windows-11-arm
-    runs-on: ${{ matrix.runner }}
+        target:
+          - x86_64-pc-windows-msvc
+          - aarch64-pc-windows-msvc
     defaults:
       run:
         working-directory: rust/lancedb
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - name: Set target
         run: rustup target add ${{ matrix.target }}
       - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Install Protoc v21.12
         run: choco install --no-progress protoc
       - name: Build
@@ -240,12 +192,11 @@ jobs:
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
           cargo build --profile ci --features aws,remote --tests --locked --target ${{ matrix.target }}
       - name: Run tests
+        # Can only run tests when target matches host
+        if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
         run: |
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          # `--target` has to match the build step above. Without it cargo uses
-          # target/ci/ rather than target/<triple>/ci/ and rebuilds the entire
-          # dependency graph a second time.
-          cargo test --profile ci --features aws,remote --locked --target ${{ matrix.target }}
+          cargo test --profile ci --features aws,remote --locked
 
   msrv:
     # Check the minimum supported Rust version
@@ -259,7 +210,7 @@ jobs:
       CC: clang-18
       CXX: clang++-18
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           submodules: true
       - name: Install dependencies
@@ -271,11 +222,6 @@ jobs:
         with:
           toolchain: ${{ matrix.msrv }}
       - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
       - name: Downgrade  dependencies
         # These packages have newer requirements for MSRV
         run: |
@@ -287,26 +233,6 @@ jobs:
           cargo update -p aws-sdk-sso --precise 1.62.0
           cargo update -p aws-sdk-ssooidc --precise 1.63.0
           cargo update -p aws-sdk-sts --precise 1.63.0
-          # aws-runtime/sigv4/credential-types/types and the aws-smithy-*
-          # crates bumped their MSRV to 1.91.1 in late 2026; pin to the last
-          # 1.91.0-compatible versions. The order matters — each downgrade
-          # only succeeds once everything that still pins it at a higher
-          # version has itself been downgraded.
-          cargo update -p aws-runtime --precise 1.5.12
-          cargo update -p aws-types --precise 1.3.9
-          cargo update -p aws-sigv4 --precise 1.3.5
-          cargo update -p aws-credential-types --precise 1.2.8
-          cargo update -p aws-smithy-checksums --precise 0.63.9
-          cargo update -p aws-smithy-runtime --precise 1.9.3
-          cargo update -p aws-smithy-http --precise 0.62.4
-          cargo update -p aws-smithy-eventstream --precise 0.60.12
-          cargo update -p aws-smithy-http-client --precise 1.1.3
-          cargo update -p aws-smithy-observability --precise 0.1.4
-          cargo update -p aws-smithy-query --precise 0.60.8
-          cargo update -p aws-smithy-runtime-api --precise 1.9.1
-          cargo update -p aws-smithy-async --precise 1.2.6
-          cargo update -p aws-smithy-types --precise 1.3.5
-          cargo update -p aws-smithy-xml --precise 0.60.11
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
         env:

.github/workflows/update_package_lock_run.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: main
           persist-credentials: false

.github/workflows/update_package_lock_run_nodejs.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: main
           persist-credentials: false

.github/workflows/upload_wheel/action.yml

@@ -0,0 +1,34 @@
+name: upload-wheel
+
+description: "Upload wheels to Pypi"
+inputs:
+  fury_token:
+    required: true
+    description: "release token for the fury repo"
+
+runs:
+  using: "composite"
+  steps:
+  - name: Choose repo
+    shell: bash
+    id: choose_repo
+    run: |
+      if [[ ${{ github.ref }} == *beta* ]]; then
+        echo "repo=fury" >> $GITHUB_OUTPUT
+      else
+        echo "repo=pypi" >> $GITHUB_OUTPUT
+      fi
+  - name: Publish to Fury
+    if: steps.choose_repo.outputs.repo == 'fury'
+    shell: bash
+    env:
+      FURY_TOKEN: ${{ inputs.fury_token }}
+    run: |
+      WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
+      echo "Uploading $WHEEL to Fury"
+      curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
+  - name: Publish to PyPI
+    if: steps.choose_repo.outputs.repo == 'pypi'
+    uses: pypa/gh-action-pypi-publish@release/v1
+    with:
+      packages-dir: target/wheels/

.gitignore

@@ -27,7 +27,6 @@ python/dist
 *.so
 *.dylib
 *.dll
-*.pdb
 
 ## Javascript
 *.node

AGENTS.md

@@ -17,33 +17,9 @@ Common commands:
 * Run tests: `cargo test --quiet --features remote --tests`
 * Run specific test: `cargo test --quiet --features remote -p <package_name> --test <test_name>`
 * Lint: `cargo clippy --quiet --features remote --tests --examples`
-* Format Rust: `cargo fmt --all`
-* Format Python: `ruff format .`
-* Lint Python: `ruff check .`
-* Bootstrap Python dev env: `cd python && uv run --extra tests --extra dev maturin develop --extras tests,dev`
-* Run Python tests: `cd python && uv run --extra tests pytest python/tests -vv --durations=10 -m "not slow and not s3_test"`
-* Run specific Python test: `cd python && uv run --extra tests pytest python/tests/<test_file>.py::<test_name> -q`
+* Format: `cargo fmt --all`
 
-For Python validation, prefer the uv-managed environment declared by `python/uv.lock`.
-Do not treat system `python`, global `pytest`, or missing editable-install errors as
-final blockers; bootstrap or enter the uv environment instead. If `lancedb._lancedb`
-is missing or stale, or if Rust/PyO3 binding code changed, rebuild the Python
-extension with the bootstrap command above before running tests.
-
-Before committing changes, run formatting for every language you touched. At minimum:
-
-* Rust changes: run `cargo fmt --all`.
-* Python changes: run `ruff format .` and `ruff check .` from the repository root,
-  and run targeted tests through `cd python && uv run ...`.
-* TypeScript changes: run the relevant `npm`/`pnpm` lint, format, build, and docs commands in `nodejs`.
-
-Before creating a PR, the exact value passed to `gh pr create --title` must follow
-Conventional Commits, such as `fix: support nested field paths in native index creation`
-or `feat(python): add dataset multiprocessing support`. Do not use a plain natural
-language summary like `Support nested field paths in native index creation` as the PR
-title. The semantic-release check uses the PR title and body as the merge commit message,
-so a non-conventional PR title will fail CI. After creating a PR, read the remote PR title
-back and fix it immediately if it is not conventional.
+Before committing changes, run formatting.
 
 ## Coding tips
 
@@ -92,8 +68,6 @@ Python bindings changes:
     * Should use `LOOP.run()` to call the corresponding `AsyncTable` method.
 6. Add concrete sync method to `RemoteTable` class in `python/python/lancedb/remote/table.py`.
 7. Add unit test in `python/tests/test_table.py`.
-8. If you added a new public class or module-level function (not just a method on an
-   existing class), expose it in the API reference. See "Python API reference" below.
 
 TypeScript bindings changes:
 
@@ -105,33 +79,6 @@ TypeScript bindings changes:
 5. Add test in `nodejs/__test__/table.test.ts`.
 6. Run `npm run docs` to generate TypeScript documentation.
 
-## Python API reference
-
-`docs/src/python/python.md` is the entire Python API reference. It is maintained by
-hand, and anything not listed there is not rendered at all, so new public classes and
-module-level functions have to be added explicitly. How depends on the module:
-
-* `lancedb.index`, `lancedb.embeddings`, `lancedb.remote`, and `lancedb.rerankers` are
-  rendered by a single directive each, driven by the module's `__all__`. Add the new
-  name to `__all__` and it appears; forget, and it is silently omitted.
-* Everything else (`lancedb`, `lancedb.table`, `lancedb.query`, `lancedb.db`, ...) is
-  listed symbol by symbol. Add a `::: lancedb.<module>.<Name>` line to the matching
-  section, and remember that the page separates synchronous and asynchronous APIs.
-
-Deliberately undocumented: concrete implementations reached through an abstract base
-(`LanceTable`, `LanceDBConnection`, `RemoteDBConnection`), query base classes already
-covered by `inherited_members`, and internal helpers.
-
-Cross-references in docstrings use mkdocstrings syntax, `[text][lancedb.table.Table]`.
-Plain relative links such as `[Table](Table)` do not resolve. To check your work:
-
-```shell
-pip install -r docs/requirements.txt
-cd docs && PYTHONPATH=. mkdocs build
-```
-
-The docs site only builds on pushes to `main`, so this is not covered by PR CI.
-
 ## Review Guidelines
 
 Please consider the following when reviewing code contributions.

Cargo.toml

@@ -13,25 +13,24 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=7.0.0-beta.7", default-features = false, "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=7.0.0-beta.7", default-features = false, "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=7.0.0-beta.7", default-features = false, "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=7.0.0-beta.7", "tag" = "v7.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
 arrow-array = "58.0.0"
-arrow-buffer = "58.0.0"
 arrow-data = "58.0.0"
 arrow-ipc = "58.0.0"
 arrow-ord = "58.0.0"
@@ -39,23 +38,21 @@ arrow-schema = "58.0.0"
 arrow-select = "58.0.0"
 arrow-cast = "58.0.0"
 async-trait = "0"
-datafusion = { version = "54.0.0", default-features = false }
-datafusion-catalog = "54.0.0"
-datafusion-common = { version = "54.0.0", default-features = false }
-datafusion-execution = "54.0.0"
-datafusion-expr = "54.0.0"
-datafusion-functions = "54.0.0"
-datafusion-physical-plan = "54.0.0"
-datafusion-physical-expr = "54.0.0"
-datafusion-sql = "54.0.0"
+datafusion = { version = "53.0.0", default-features = false }
+datafusion-catalog = "53.0.0"
+datafusion-common = { version = "53.0.0", default-features = false }
+datafusion-execution = "53.0.0"
+datafusion-expr = "53.0.0"
+datafusion-functions = "53.0.0"
+datafusion-physical-plan = "53.0.0"
+datafusion-physical-expr = "53.0.0"
+datafusion-sql = "53.0.0"
 env_logger = "0.11"
 half = { "version" = "2.7.1", default-features = false, features = [
     "num-traits",
 ] }
 futures = "0"
 log = "0.4"
-metrics = "0.24"
-metrics-util = "0.19"
 moka = { version = "0.12", features = ["future"] }
 object_store = "0.13.2"
 pin-project = "1.0.7"
@@ -64,6 +61,7 @@ snafu = "0.8"
 url = "2"
 num-traits = "0.2"
 regex = "1.10"
+lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"
 

REVIEW.md

@@ -1,26 +0,0 @@
-# Code review guidelines
-
-Repo-specific guidance for automated PR reviews.
-
-## Cross-SDK parity
-
-LanceDB exposes the same core (`rust/lancedb`) through Python, TypeScript (`nodejs`),
-and Java bindings. Behavioral drift between SDKs is a recurring problem, so watch for
-parity gaps when reviewing — but only flag real ones:
-
-* If the change adds or modifies user-facing API or behavior in the shared core
-  (`rust/lancedb`), check whether each binding that should expose it (`python`,
-  `nodejs`) does. A core change with no corresponding binding update is worth a note.
-* If the change adds or modifies a public API in one SDK but not the other, open the
-  sibling SDK's corresponding module and state whether an equivalent exists. If not,
-  note it as a possible parity gap and suggest a follow-up issue.
-* For bug fixes, first read the sibling SDK's analogous code path to check whether the
-  same bug exists there. Only raise parity if it actually does. Do not ask to "port" a
-  fix for a bug that only ever existed in one binding.
-* Stay silent on internal-only refactors, tests, docs, and changes with no cross-SDK
-  surface.
-* Parity expectations apply to the Python and TypeScript (`nodejs`) SDKs. Java currently
-  implements only the remote table, not the local/embedded backend, so it is expected to
-  be partial — do not flag Java for missing local-only functionality.
-* Keep parity feedback to a short, clearly-labeled note (e.g. "Possible SDK parity
-  gap: …"). It is advisory, not a merge blocker.

ci/bump_version.sh

@@ -2,9 +2,9 @@ set -e
 
 RELEASE_TYPE=${1:-"stable"}
 BUMP_MINOR=${2:-false}
-HEAD_SHA=$(git rev-parse HEAD)
+TAG_PREFIX=${3:-"v"} # Such as "python-v"
+HEAD_SHA=${4:-$(git rev-parse HEAD)}
 
-readonly TAG_PREFIX="v"
 readonly SELF_DIR=$(cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )
 
 PREV_TAG=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
@@ -12,7 +12,7 @@ echo "Found previous tag $PREV_TAG"
 
 # Initially, we don't want to tag if we are doing stable, because we will bump
 # again later. See comment at end for why.
-if [[ "$RELEASE_TYPE" == 'stable' ]]; then
+if [[ "$RELEASE_TYPE" == 'stable' ]]; then 
   BUMP_ARGS="--no-tag"
 fi
 

ci/check_lance_release.py

@@ -112,25 +112,25 @@ def fetch_remote_tags() -> List[TagInfo]:
             "api",
             "-X",
             "GET",
-            f"repos/{LANCE_REPO}/releases",
+            f"repos/{LANCE_REPO}/git/refs/tags",
+            "--paginate",
             "--jq",
-            ".[].tag_name",
-            "-F",
-            "per_page=20",
+            ".[].ref",
         ]
     )
     tags: List[TagInfo] = []
     for line in output.splitlines():
-        tag = line.strip()
-        if not tag.startswith("v"):
+        ref = line.strip()
+        if not ref.startswith("refs/tags/v"):
             continue
+        tag = ref.split("refs/tags/")[-1]
         version = tag.lstrip("v")
         try:
             tags.append(TagInfo(tag=tag, version=version, semver=parse_semver(version)))
         except ValueError:
             continue
     if not tags:
-        raise RuntimeError("No Lance releases could be parsed from GitHub API output")
+        raise RuntimeError("No Lance tags could be parsed from GitHub API output")
     return tags
 
 

ci/update_lance_dependency.py

@@ -1,126 +0,0 @@
-#!/usr/bin/env python3
-"""Prepare a Lance dependency update for LanceDB."""
-
-from __future__ import annotations
-
-import argparse
-import json
-import re
-import subprocess
-import sys
-from pathlib import Path
-from typing import Sequence
-
-try:
-    from check_lance_release import parse_semver
-except ModuleNotFoundError:
-    # Supports importing as ci.update_lance_dependency from tests or ad hoc checks.
-    from ci.check_lance_release import parse_semver  # type: ignore
-
-
-def normalize_version(raw: str) -> str:
-    value = raw.strip()
-    value = value.removeprefix("refs/tags/")
-    value = value.removeprefix("v")
-    try:
-        parse_semver(value)
-    except ValueError:
-        raise ValueError(f"Unsupported Lance version or tag: {raw}")
-    return value
-
-
-def normalized_tag(version: str) -> str:
-    return f"v{version}"
-
-
-def branch_name(version: str) -> str:
-    suffix = re.sub(r"[^a-zA-Z0-9]+", "-", version).strip("-")
-    suffix = re.sub(r"-+", "-", suffix)
-    return f"codex/update-lance-{suffix}"
-
-
-def commit_type(version: str) -> str:
-    prerelease = version.split("-", maxsplit=1)[1] if "-" in version else ""
-    return "chore" if "beta" in prerelease or "rc" in prerelease else "feat"
-
-
-def metadata_for(version: str) -> dict[str, str]:
-    kind = commit_type(version)
-    message = f"{kind}: update lance dependency to v{version}"
-    return {
-        "version": version,
-        "tag": normalized_tag(version),
-        "branch_name": branch_name(version),
-        "commit_type": kind,
-        "commit_message": message,
-        "pr_title": message,
-    }
-
-
-def run_command(cmd: Sequence[str], *, cwd: Path) -> None:
-    subprocess.run(cmd, cwd=cwd, check=True)
-
-
-def update_java_lance_core_version(repo_root: Path, version: str) -> None:
-    pom_path = repo_root / "java" / "pom.xml"
-    contents = pom_path.read_text(encoding="utf-8")
-    updated, count = re.subn(
-        r"(<lance-core\.version>)[^<]+(</lance-core\.version>)",
-        rf"\g<1>{version}\g<2>",
-        contents,
-        count=1,
-    )
-    if count != 1:
-        raise RuntimeError(
-            "Expected exactly one <lance-core.version> entry in java/pom.xml"
-        )
-    pom_path.write_text(updated, encoding="utf-8")
-
-
-def write_github_outputs(path: str | None, payload: dict[str, str]) -> None:
-    if not path:
-        return
-    with open(path, "a", encoding="utf-8") as output:
-        for key, value in payload.items():
-            output.write(f"{key}={value}\n")
-
-
-def main(argv: Sequence[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "tag_or_version",
-        help="Lance tag or version, for example refs/tags/v7.2.0-beta.1 or 7.2.0",
-    )
-    parser.add_argument(
-        "--repo-root",
-        type=Path,
-        default=Path(__file__).resolve().parents[1],
-        help="Path to the lancedb repository root",
-    )
-    parser.add_argument(
-        "--github-output",
-        default=None,
-        help="Optional GitHub Actions output file to receive metadata fields",
-    )
-    parser.add_argument(
-        "--metadata-only",
-        action="store_true",
-        help="Only print derived metadata; do not modify dependency files",
-    )
-    args = parser.parse_args(argv)
-
-    repo_root = args.repo_root.resolve()
-    version = normalize_version(args.tag_or_version)
-    payload = metadata_for(version)
-
-    if not args.metadata_only:
-        run_command([sys.executable, "ci/set_lance_version.py", version], cwd=repo_root)
-        update_java_lance_core_version(repo_root, version)
-
-    write_github_outputs(args.github_output, payload)
-    print(json.dumps(payload, sort_keys=True))
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

deny.toml

@@ -51,6 +51,18 @@ ignore = [
     # https://rustsec.org/advisories/RUSTSEC-2024-0436
     { id = "RUSTSEC-2024-0436", reason = "transitive via datafusion; awaiting ecosystem migration" },
 
+    # encoding: unmaintained. Reached through lindera-dictionary, which is
+    # required by the native Lindera tokenizer path. Lindera has not migrated
+    # off this crate yet.
+    # https://rustsec.org/advisories/RUSTSEC-2021-0153
+    { id = "RUSTSEC-2021-0153", reason = "transitive via lindera-dictionary for native Lindera tokenizer" },
+
+    # fast-float: unsound and unmaintained. Reached only through polars-arrow
+    # from the optional Polars integration; replacement requires a Polars
+    # dependency upgrade.
+    # https://rustsec.org/advisories/RUSTSEC-2024-0379
+    { id = "RUSTSEC-2024-0379", reason = "transitive via polars-arrow; waiting on Polars migration" },
+
     # tantivy: segfault on malformed input due to missing bounds check.
     # Pulled in via lance for full-text search. We only feed tantivy
     # documents we construct ourselves, not attacker-controlled bytes.
@@ -68,6 +80,18 @@ ignore = [
     # https://rustsec.org/advisories/RUSTSEC-2025-0119
     { id = "RUSTSEC-2025-0119", reason = "transitive via hf-hub/indicatif; cosmetic formatting crate" },
 
+    # bincode: unmaintained. Reached through lindera and lindera-dictionary,
+    # which are required by the native Lindera tokenizer path. Lindera has not
+    # migrated to another serialization format yet.
+    # https://rustsec.org/advisories/RUSTSEC-2025-0141
+    { id = "RUSTSEC-2025-0141", reason = "transitive via lindera/lindera-dictionary for native Lindera tokenizer" },
+
+    # lru: soundness issue in IterMut. Reached only through aws-sdk-s3 in
+    # LanceDB's dev-dependency graph; LanceDB does not use that iterator
+    # directly. Clearing this requires the AWS SDK chain to update lru.
+    # https://rustsec.org/advisories/RUSTSEC-2026-0002
+    { id = "RUSTSEC-2026-0002", reason = "transitive via aws-sdk-s3 dev-dependency; waiting on AWS SDK lru upgrade" },
+
     # rustls-webpki 0.101.7 (old major line): name-constraint checks for
     # URI / wildcard names. Pulled in only via the legacy rustls 0.21 chain
     # from aws-smithy-http-client. The 0.103 line we actively use is patched.
@@ -84,23 +108,11 @@ ignore = [
     # https://rustsec.org/advisories/RUSTSEC-2026-0104
     { id = "RUSTSEC-2026-0104", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
 
-    # pyo3 advisories in the Python bindings; tracked pending a patched pyo3 release.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0176
-    # https://rustsec.org/advisories/RUSTSEC-2026-0177
-    { id = "RUSTSEC-2026-0176", reason = "pyo3 in Python bindings; awaiting patched pyo3 release" },
-    { id = "RUSTSEC-2026-0177", reason = "pyo3 in Python bindings; awaiting patched pyo3 release" },
-
-    # quick-xml < 0.41.0: quadratic runtime on duplicate attribute names (DoS).
-    # quick-xml < 0.41.0: unbounded namespace-declaration allocation in NsReader (DoS).
-    # Pulled in transitively by inferno (dev-only flame-graph dep), lance-namespace-impls
-    # (git dep from lance), and opendal/reqsign (cloud storage XML parsing). The XML
-    # parsed by opendal/reqsign comes from trusted cloud-storage endpoints (S3, GCS,
-    # Azure), not attacker-controlled input. Clearing requires upstream crates to migrate
-    # to quick-xml >= 0.41.0.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0194
-    # https://rustsec.org/advisories/RUSTSEC-2026-0195
-    { id = "RUSTSEC-2026-0194", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
-    { id = "RUSTSEC-2026-0195", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
+    # rand 0.8.5: soundness issue only when ThreadRng reseeds inside a custom
+    # logger. Reached through several transitive chains. LanceDB does not use
+    # rand from a custom logger; upgrade once all pinned chains accept 0.8.6+.
+    # https://rustsec.org/advisories/RUSTSEC-2026-0097
+    { id = "RUSTSEC-2026-0097", reason = "transitive rand 0.8.5; LanceDB does not call ThreadRng from custom logging" },
 ]
 
 # ---------------------------------------------------------------------------
@@ -135,14 +147,6 @@ allow = [
     "CDLA-Permissive-2.0",
 ]
 confidence-threshold = 0.8
-# Per-crate license exceptions: allow a license for a specific crate only,
-# rather than globally via the `allow` list above.
-exceptions = [
-    # CDDL-1.0 (copyleft) is pulled in only as a dev/profiling dependency via
-    # `inferno` -> `pprof` -> `lance-testing`; it is a test dependency that we
-    # do not distribute, so scope the allowance to `inferno` alone.
-    { allow = ["CDDL-1.0"], crate = "inferno" },
-]
 # Crates whose license cannot be determined from Cargo metadata but whose
 # license we've manually confirmed from upstream. Keep this list minimal.
 [[licenses.clarify]]

docs/mkdocs.yml

@@ -51,11 +51,6 @@ plugins:
           paths: [../python/python]
           options:
             docstring_style: numpy
-            docstring_options:
-              # Attributes documented in a `Parameters` section, and pydantic
-              # dataclasses whose `__init__` griffe cannot see statically, both
-              # trip this check. It reports nothing actionable here.
-              warn_unknown_params: false
             heading_level: 3
             show_signature_annotations: true
             show_root_heading: true

docs/openapi.yml

@@ -453,16 +453,6 @@ paths:
                     The metric type to use for the index. l2, Cosine, Dot are supported.
                 index_type:
                   type: string
-                custom_stop_words:
-                  type: [array, "null"]
-                  items:
-                    type: string
-                  description: |
-                    The custom stop-word list for an FTS index. A non-null
-                    array replaces the language's built-in stop-word list and is only
-                    applied when remove_stop_words is enabled. Null uses the built-in
-                    language list, while an empty array explicitly replaces it with no
-                    stop words.
       responses:
         "200":
           description: Index successfully created
@@ -520,4 +510,4 @@ paths:
         "401":
           $ref: "#/components/responses/unauthorized"
         "404":
-          $ref: "#/components/responses/not_found"
+          $ref: "#/components/responses/not_found"

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.28.0-beta.11</version>
 </dependency>
 ```
 
@@ -249,57 +249,6 @@ try (BufferAllocator allocator = new RootAllocator();
 }
 ```
 
-### Creating an Empty Table
-
-To create an empty table, send an Arrow IPC stream that contains the table schema and no record batches.
-The schema in the IPC stream becomes the table schema, and rows can be inserted later.
-
-```java
-import org.lance.namespace.model.CreateTableRequest;
-import org.lance.namespace.model.CreateTableResponse;
-import org.apache.arrow.memory.BufferAllocator;
-import org.apache.arrow.memory.RootAllocator;
-import org.apache.arrow.vector.VectorSchemaRoot;
-import org.apache.arrow.vector.ipc.ArrowStreamWriter;
-import org.apache.arrow.vector.types.FloatingPointPrecision;
-import org.apache.arrow.vector.types.pojo.ArrowType;
-import org.apache.arrow.vector.types.pojo.Field;
-import org.apache.arrow.vector.types.pojo.FieldType;
-import org.apache.arrow.vector.types.pojo.Schema;
-
-import java.io.ByteArrayOutputStream;
-import java.nio.channels.Channels;
-import java.util.Arrays;
-
-Schema schema = new Schema(Arrays.asList(
-    new Field("id", FieldType.nullable(new ArrowType.Int(32, true)), null),
-    new Field("name", FieldType.nullable(new ArrowType.Utf8()), null),
-    new Field("embedding",
-        FieldType.nullable(new ArrowType.FixedSizeList(128)),
-        Arrays.asList(new Field("item",
-            FieldType.nullable(new ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE)),
-            null)))
-));
-
-byte[] emptyTableData;
-try (BufferAllocator allocator = new RootAllocator();
-     VectorSchemaRoot root = VectorSchemaRoot.create(schema, allocator)) {
-    root.setRowCount(0);
-
-    ByteArrayOutputStream out = new ByteArrayOutputStream();
-    try (ArrowStreamWriter writer = new ArrowStreamWriter(root, null, Channels.newChannel(out))) {
-        writer.start();
-        writer.end();
-    }
-    emptyTableData = out.toByteArray();
-}
-
-CreateTableRequest request = new CreateTableRequest();
-request.setId(Arrays.asList("my_namespace", "empty_table"));
-
-CreateTableResponse response = namespaceClient.createTable(request, emptyTableData);
-```
-
 ### Insert
 
 ```java
@@ -482,88 +431,9 @@ query.setVector(vector);
 byte[] result = namespaceClient.queryTable(query);
 ```
 
-## Indexing
+### Reading Query Results
 
-The Java SDK exposes the REST namespace index operations through the same `LanceNamespace` client.
-Index creation runs asynchronously, so use `listTableIndices` or `describeTableIndexStats` to check progress.
-
-### Creating a Vector Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("embedding");
-request.setIndexType("IVF_PQ");
-request.setDistanceType("cosine");
-request.setName("embedding_idx");
-
-CreateTableIndexResponse response = namespaceClient.createTableIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Creating a Scalar Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableScalarIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("category");
-request.setIndexType("BTREE");
-request.setName("category_idx");
-
-CreateTableScalarIndexResponse response = namespaceClient.createTableScalarIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Creating a Full Text Search Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableScalarIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("text_column");
-request.setIndexType("FTS");
-request.setName("text_idx");
-request.setBaseTokenizer("simple");
-request.setLowerCase(true);
-request.setWithPosition(true);
-
-CreateTableScalarIndexResponse response = namespaceClient.createTableScalarIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Listing Indexes
-
-```java
-import org.lance.namespace.model.IndexContent;
-import org.lance.namespace.model.ListTableIndicesRequest;
-import org.lance.namespace.model.ListTableIndicesResponse;
-
-ListTableIndicesRequest request = new ListTableIndicesRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-
-ListTableIndicesResponse response = namespaceClient.listTableIndices(request);
-for (IndexContent index : response.getIndexes()) {
-    System.out.println(index.getIndexName() + ": " + index.getStatus());
-}
-```
-
-!!! note
-    The current Java namespace API exposes index type, index name, distance type, and full text search tokenizer options.
-    IVF training parameters such as `num_partitions` are not exposed by `CreateTableIndexRequest` yet.
-    To make those configurable from Java, the namespace API must add those fields first.
-
-## Reading Query Results
-
-Query results are returned as bytes in Apache Arrow IPC file format. Put the byte-channel
-adapter behind a small helper so query code can work with `ArrowFileReader` directly:
+Query results are returned in Apache Arrow IPC file format. Here's how to read them:
 
 ```java
 import org.apache.arrow.vector.ipc.ArrowFileReader;
@@ -571,50 +441,45 @@ import org.apache.arrow.vector.VectorSchemaRoot;
 import org.apache.arrow.memory.BufferAllocator;
 import org.apache.arrow.memory.RootAllocator;
 
-import java.io.IOException;
 import java.nio.ByteBuffer;
 import java.nio.channels.SeekableByteChannel;
 
-final class ArrowIpc {
-    static ArrowFileReader openFileReader(byte[] data, BufferAllocator allocator) throws IOException {
-        return new ArrowFileReader(new ByteArraySeekableByteChannel(data), allocator);
+// Helper class to read Arrow data from byte array
+class ByteArraySeekableByteChannel implements SeekableByteChannel {
+    private final byte[] data;
+    private long position = 0;
+    private boolean isOpen = true;
+
+    public ByteArraySeekableByteChannel(byte[] data) {
+        this.data = data;
     }
 
-    private static final class ByteArraySeekableByteChannel implements SeekableByteChannel {
-        private final byte[] data;
-        private long position = 0;
-        private boolean isOpen = true;
-
-        private ByteArraySeekableByteChannel(byte[] data) {
-            this.data = data;
-        }
-
-        @Override
-        public int read(ByteBuffer dst) {
-            int remaining = dst.remaining();
-            int available = (int) (data.length - position);
-            if (available <= 0) return -1;
-            int toRead = Math.min(remaining, available);
-            dst.put(data, (int) position, toRead);
-            position += toRead;
-            return toRead;
-        }
-
-        @Override public long position() { return position; }
-        @Override public SeekableByteChannel position(long newPosition) { position = newPosition; return this; }
-        @Override public long size() { return data.length; }
-        @Override public boolean isOpen() { return isOpen; }
-        @Override public void close() { isOpen = false; }
-        @Override public int write(ByteBuffer src) { throw new UnsupportedOperationException(); }
-        @Override public SeekableByteChannel truncate(long size) { throw new UnsupportedOperationException(); }
+    @Override
+    public int read(ByteBuffer dst) {
+        int remaining = dst.remaining();
+        int available = (int) (data.length - position);
+        if (available <= 0) return -1;
+        int toRead = Math.min(remaining, available);
+        dst.put(data, (int) position, toRead);
+        position += toRead;
+        return toRead;
     }
+
+    @Override public long position() { return position; }
+    @Override public SeekableByteChannel position(long newPosition) { position = newPosition; return this; }
+    @Override public long size() { return data.length; }
+    @Override public boolean isOpen() { return isOpen; }
+    @Override public void close() { isOpen = false; }
+    @Override public int write(ByteBuffer src) { throw new UnsupportedOperationException(); }
+    @Override public SeekableByteChannel truncate(long size) { throw new UnsupportedOperationException(); }
 }
 
 // Read query results
 byte[] queryResult = namespaceClient.queryTable(query);
 
 try (BufferAllocator allocator = new RootAllocator();
-     ArrowFileReader reader = ArrowIpc.openFileReader(queryResult, allocator)) {
+     ArrowFileReader reader = new ArrowFileReader(
+         new ByteArraySeekableByteChannel(queryResult), allocator)) {
 
     for (int i = 0; i < reader.getRecordBlocks().size(); i++) {
         reader.loadRecordBatch(reader.getRecordBlocks().get(i));

docs/src/js/_media/CONTRIBUTING.md

@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript
 
 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).
 
 ## Project layout
 

docs/src/js/classes/BranchContents.md

@@ -1,43 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchContents
-
-# Class: BranchContents
-
-## Constructors
-
-### new BranchContents()
-
-```ts
-new BranchContents(): BranchContents
-```
-
-#### Returns
-
-[`BranchContents`](BranchContents.md)
-
-## Properties
-
-### manifestSize
-
-```ts
-manifestSize: number;
-```
-
-***
-
-### parentBranch?
-
-```ts
-optional parentBranch: string;
-```
-
-***
-
-### parentVersion
-
-```ts
-parentVersion: number;
-```

docs/src/js/classes/Branches.md

@@ -1,139 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Branches
-
-# Class: Branches
-
-Branch manager for a [Table](Table.md).
-
-Unlike tags, `create` and `checkout` return a new [Table](Table.md) handle scoped
-to the branch; writes on it do not affect `main`.
-
-## Methods
-
-### checkout()
-
-```ts
-checkout(name, version?): Promise<Table>
-```
-
-Check out an existing branch and return a handle scoped to it.
-
-With `version` set, the returned handle is pinned to that version of the
-branch (a read-only, detached view); otherwise it tracks the branch's
-latest and stays writable.
-
-#### Parameters
-
-* **name**: `string`
-
-* **version?**: `number`
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
-### create()
-
-```ts
-create(
-   name,
-   fromRef?,
-   fromVersion?): Promise<Table>
-```
-
-Create a branch and return a handle scoped to it.
-
-#### Parameters
-
-* **name**: `string`
-    Name of the new branch.
-
-* **fromRef?**: `string`
-    Source branch to fork from. Defaults to `main`.
-
-* **fromVersion?**: `number`
-    A specific version on `fromRef`. Defaults to latest.
-
-#### Returns
-
-`Promise`&lt;[`Table`](Table.md)&gt;
-
-***
-
-### delete()
-
-```ts
-delete(name): Promise<void>
-```
-
-Delete a branch.
-
-#### Parameters
-
-* **name**: `string`
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
-### diff()
-
-```ts
-diff(fromBranch): Promise<BranchDiff>
-```
-
-Compare a branch against main without modifying either branch.
-
-#### Parameters
-
-* **fromBranch**: `string`
-
-#### Returns
-
-`Promise`&lt;[`BranchDiff`](../interfaces/BranchDiff.md)&gt;
-
-***
-
-### list()
-
-```ts
-list(): Promise<Record<string, BranchContents>>
-```
-
-List all branches, mapping name to branch metadata.
-
-#### Returns
-
-`Promise`&lt;`Record`&lt;`string`, [`BranchContents`](BranchContents.md)&gt;&gt;
-
-***
-
-### merge()
-
-```ts
-merge(fromBranch, dryRun): Promise<MergeBranchResult>
-```
-
-Merge a branch into main.
-
-Set `dryRun` to `true` to preview the merge. A rejected merge resolves
-with `status: "rejected"` instead of throwing.
-
-#### Parameters
-
-* **fromBranch**: `string`
-    Branch to merge from.
-
-* **dryRun**: `boolean` = `false`
-    When true, only preview the merge. Defaults to false.
-
-#### Returns
-
-`Promise`&lt;[`MergeBranchResult`](../interfaces/MergeBranchResult.md)&gt;

docs/src/js/classes/Connection.md

@@ -437,39 +437,6 @@ Open a table in the database.
 
 ***
 
-### renameTable()
-
-```ts
-abstract renameTable(
-   currentName,
-   newName,
-   options?): Promise<void>
-```
-
-Rename a table.
-
-Currently only supported by LanceDB Cloud. Local OSS connections and
-namespace-backed connections (via [connectNamespace](../functions/connectNamespace.md)) reject with
-a "not supported" error.
-
-#### Parameters
-
-* **currentName**: `string`
-    The current name of the table.
-
-* **newName**: `string`
-    The new name for the table.
-
-* **options?**: [`RenameTableOptions`](../interfaces/RenameTableOptions.md)
-    Optional namespace paths. When
-    `newNamespacePath` is omitted the table stays in `namespacePath`.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### tableNames()
 
 #### tableNames(options)

docs/src/js/classes/Index.md

@@ -57,24 +57,6 @@ block size may be added in the future.
 
 ***
 
-### fm()
-
-```ts
-static fm(): Index
-```
-
-Create an FM-Index.
-
-An FM-Index is a scalar index on string or binary columns that accelerates
-substring search, i.e. `contains(col, 'needle')`. Unlike the tokenized
-full-text-search index, it matches arbitrary substrings of the raw bytes.
-
-#### Returns
-
-[`Index`](Index.md)
-
-***
-
 ### fts()
 
 ```ts

docs/src/js/classes/MergeInsertBuilder.md

@@ -76,56 +76,6 @@ the query optimizer chooses a suboptimal path.
 
 ***
 
-### useLsm()
-
-```ts
-useLsm(enable): MergeInsertBuilder
-```
-
-Control MemWAL routing for this merge.
-
-By default (unset), a `mergeInsert` on a table with an LSM write spec is
-routed through Lance's MemWAL shard writer, and a table without one uses the
-standard path.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces MemWAL routing and errors if the table has no
-    LSM write spec. `false` forces the standard write path even when a spec is set.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
-### validateSingleShard()
-
-```ts
-validateSingleShard(validateSingleShard): MergeInsertBuilder
-```
-
-Controls how an LSM merge checks that its input targets a single shard.
-
-When a table has an LSM write spec, every row in a `mergeInsert` call must
-route to the same shard. When `true` (the default), every row is inspected
-to verify this. When `false`, only the first row is inspected and the
-shard it routes to is used for the whole input — a faster path for callers
-that have already pre-sharded their input. Has no effect on tables without
-an LSM write spec.
-
-#### Parameters
-
-* **validateSingleShard**: `boolean`
-    Whether to check every row routes to one shard. Defaults to `true`.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
 ### whenMatchedUpdateAll()
 
 ```ts

docs/src/js/classes/Query.md

@@ -33,7 +33,7 @@ protected inner: Query | Promise<Query>;
 ### analyzePlan()
 
 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```
 
 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -41,12 +41,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.
 
-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns
 
 `Promise`&lt;`string`&gt;
@@ -349,30 +343,6 @@ This is useful for pagination.
 
 ***
 
-### orderBy()
-
-```ts
-orderBy(ordering): this
-```
-
-Sort the results by the specified column(s).
-
-#### Parameters
-
-* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
-
-#### Returns
-
-`this`
-
-This query builder.
-
-#### Inherited from
-
-`StandardQueryBase.orderBy`
-
-***
-
 ### outputSchema()
 
 ```ts
@@ -497,42 +467,6 @@ ArrowTable.
 
 ***
 
-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
 ### where()
 
 ```ts
@@ -560,9 +494,6 @@ x > 5 OR y = 'test'
 
 Filtering performance can often be improved by creating a scalar index
 on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
 ```
 
 #### Inherited from

docs/src/js/classes/QueryBase.md

@@ -38,7 +38,7 @@ protected inner: NativeQueryType | Promise<NativeQueryType>;
 ### analyzePlan()
 
 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```
 
 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -46,12 +46,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.
 
-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns
 
 `Promise`&lt;`string`&gt;

docs/src/js/classes/Scannable.md

@@ -1,173 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Scannable
-
-# Class: Scannable
-
-A data source that can be scanned as a stream of Arrow `RecordBatch`es.
-
-`Scannable` wraps the schema + optional row count + rescannable flag and
-a callback that yields batches one at a time. It is passed to consumers
-(e.g. `Table.add`, `createTable`, `mergeInsert` — follow-up work) that
-need to pull data without materializing the full dataset in JS memory.
-
-Batches cross the JS↔Rust boundary as Arrow IPC Stream messages; a fresh
-writer serializes each batch, and the Rust side decodes it with
-`arrow_ipc::reader::StreamReader`. One batch is in flight at a time.
-
-## Properties
-
-### numRows
-
-```ts
-readonly numRows: null | number;
-```
-
-***
-
-### rescannable
-
-```ts
-readonly rescannable: boolean;
-```
-
-***
-
-### schema
-
-```ts
-readonly schema: Schema<any>;
-```
-
-## Methods
-
-### fromFactory()
-
-```ts
-static fromFactory(
-   schema,
-   factory,
-   opts): Promise<Scannable>
-```
-
-Build a Scannable from an explicit schema and a factory that returns a
-fresh batch iterator on each call.
-
-The factory is invoked once per scan. Each iterator yields
-`RecordBatch`es matching the declared schema. Use this when you need
-direct control over the pull loop — for example, to wrap a streaming
-source whose batches are produced lazily.
-
-#### Parameters
-
-* **schema**: `Schema`&lt;`any`&gt;
-    The Arrow schema of the produced batches.
-
-* **factory**
-    Called at the start of each scan to produce a batch
-    iterator. Must be idempotent when `rescannable` is true.
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-    Optional hints. `rescannable` defaults to `true`; set to
-    `false` if calling `factory()` twice would not reproduce the same data.
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;
-
-***
-
-### fromIterable()
-
-```ts
-static fromIterable(
-   schema,
-   iter,
-   opts): Promise<Scannable>
-```
-
-Build a Scannable from an iterable of `RecordBatch`es. `rescannable`
-defaults to `false`. Pass an explicit schema so the consumer can
-validate before any batch is pulled.
-
-`opts.rescannable: true` is honest for replayable iterables (Arrays,
-Sets, or custom iterables whose `[Symbol.iterator]()` returns a fresh
-iterator each call). It is rejected for one-shot iterables (generators,
-async generators, or already-an-iterator inputs) because their
-`[Symbol.iterator]()` returns the same exhausted object on the second
-scan. For replayable sources outside this shape, use
-`fromFactory(schema, () => createIter(), { rescannable: true })`.
-
-Note: when `opts.rescannable` is `true`, the constructor calls
-`[Symbol.iterator]()` once on the input to perform the structural check.
-
-#### Parameters
-
-* **schema**: `Schema`&lt;`any`&gt;
-
-* **iter**: `Iterable`&lt;`RecordBatch`&lt;`any`&gt;&gt; \| `AsyncIterable`&lt;`RecordBatch`&lt;`any`&gt;&gt;
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;
-
-***
-
-### fromRecordBatchReader()
-
-```ts
-static fromRecordBatchReader(reader, opts): Promise<Scannable>
-```
-
-Build a Scannable from an Arrow `RecordBatchReader`. A reader can only
-be consumed once; `rescannable` defaults to `false`.
-
-The reader must already be opened (via `.open()`) so its `.schema` is
-populated. `RecordBatchReader.from(...)` returns an unopened reader.
-
-`opts.rescannable: true` is rejected because `RecordBatchReader` is a
-self-iterator (its `[Symbol.iterator]()` returns itself), and this
-constructor does not call `reader.reset()` between scans, so a second
-scan would always see an exhausted reader. For genuinely replayable
-sources, use
-`fromFactory(schema, () => openReader(), { rescannable: true })`,
-which mints a fresh reader on each scan.
-
-#### Parameters
-
-* **reader**: `RecordBatchReader`&lt;`any`&gt;
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;
-
-***
-
-### fromTable()
-
-```ts
-static fromTable(table, opts): Promise<Scannable>
-```
-
-Build a Scannable from an in-memory Arrow `Table`. Always rescannable;
-the table's batches are replayed on each scan.
-
-The table's row count is authoritative: `opts.numRows` must either be
-omitted or equal to `table.numRows`. `opts.rescannable` of `false` is
-rejected because in-memory Tables are always rescannable.
-
-#### Parameters
-
-* **table**: `Table`&lt;`any`&gt;
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;

docs/src/js/classes/Table.md

@@ -110,23 +110,6 @@ containing the new version number of the table after altering the columns.
 
 ***
 
-### branches()
-
-```ts
-abstract branches(): Promise<Branches>
-```
-
-Get the branch manager for this table.
-
-Branches are isolated, writable lines of history forked from another
-branch (or version). Writes on a branch do not affect `main`.
-
-#### Returns
-
-`Promise`&lt;[`Branches`](Branches.md)&gt;
-
-***
-
 ### checkout()
 
 ```ts
@@ -204,25 +187,6 @@ Any attempt to use the table after it is closed will result in an error.
 
 ***
 
-### closeLsmWriters()
-
-```ts
-abstract closeLsmWriters(): Promise<void>
-```
-
-Drain and close any cached MemWAL shard writers held for this table.
-
-When an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) is installed, `mergeInsert` opens MemWAL
-shard writers and caches them for reuse across calls. This closes them,
-flushing pending data; writers reopen lazily on the next `mergeInsert`.
-It is a no-op when no writers are cached.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### countRows()
 
 ```ts
@@ -295,23 +259,6 @@ await table.createIndex("my_float_col");
 
 ***
 
-### currentBranch()
-
-```ts
-abstract currentBranch(): null | string
-```
-
-The branch this table handle is scoped to, or `null` for the main branch.
-
-A handle returned by [Branches.create](Branches.md#create) or [Branches.checkout](Branches.md#checkout)
-reports the branch it targets; a handle opened normally reports `null`.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
 ### delete()
 
 ```ts
@@ -398,26 +345,6 @@ Drop an index from the table.
 
 ***
 
-### getLsmWriteSpec()
-
-```ts
-abstract getLsmWriteSpec(): Promise<undefined | LsmWriteSpec>
-```
-
-Read the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) currently installed on this table.
-
-Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
-spec has been set, or it was removed with [Table#unsetLsmWriteSpec](Table.md#unsetlsmwritespec)).
-The returned spec — including its `maintainedIndexes` and
-`writerConfigDefaults` — mirrors what was passed to
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec).
-
-#### Returns
-
-`Promise`&lt;`undefined` \| [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)&gt;
-
-***
-
 ### indexStats()
 
 ```ts
@@ -763,74 +690,6 @@ of the given query
 
 ***
 
-### setLsmWriteSpec()
-
-```ts
-abstract setLsmWriteSpec(spec): Promise<void>
-```
-
-Install an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) on this table, selecting Lance's MemWAL
-LSM-style write path for future `mergeInsert` calls.
-
-`LsmWriteSpec` chooses one of three sharding strategies via `specType`:
-
-- `"bucket"` — hash-bucket writes by the single-column unenforced primary
-  key (`column` and `numBuckets` required).
-- `"identity"` — shard by the raw value of a scalar `column`.
-- `"unsharded"` — route every write to a single shard.
-
-All variants require the table to have an unenforced primary key
-([Table#setUnenforcedPrimaryKey](Table.md#setunenforcedprimarykey)); bucket sharding additionally
-requires it to be the single column being bucketed.
-
-#### Parameters
-
-* **spec**: [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)
-    The sharding spec to install.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-#### Example
-
-```ts
-await table.setUnenforcedPrimaryKey("id");
-await table.setLsmWriteSpec({
-  specType: "bucket",
-  column: "id",
-  numBuckets: 16,
-  maintainedIndexes: ["id_idx"],
-});
-```
-
-***
-
-### setUnenforcedPrimaryKey()
-
-```ts
-abstract setUnenforcedPrimaryKey(columns): Promise<void>
-```
-
-Set the unenforced primary key for this table to a single column.
-
-"Unenforced" means LanceDB does not check uniqueness on writes; the
-column is recorded in the schema as the primary key for use by features
-such as `merge_insert`. Only single-column primary keys are supported,
-and the key cannot be changed once set.
-
-#### Parameters
-
-* **columns**: `string` \| `string`[]
-    The primary key column. A one-element
-    array is also accepted; passing more than one column is rejected.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### stats()
 
 ```ts
@@ -934,49 +793,6 @@ Return the table as an arrow table
 
 ***
 
-### tokenize()
-
-```ts
-abstract tokenize(query, options): Promise<FtsToken[]>
-```
-
-Tokenize a full-text search query using the tokenizer configured on an FTS index.
-
-Specify exactly one of `column` or `indexName`.
-
-Model-backed tokenizers such as `jieba/*` and `lindera/*` are rebuilt in
-the client process from index metadata. For remote tables, this means the
-same tokenizer model files must also exist locally.
-
-#### Parameters
-
-* **query**: `string`
-
-* **options**: [`TokenizeTableOptions`](../type-aliases/TokenizeTableOptions.md)
-
-#### Returns
-
-`Promise`&lt;[`FtsToken`](../interfaces/FtsToken.md)[]&gt;
-
-***
-
-### unsetLsmWriteSpec()
-
-```ts
-abstract unsetLsmWriteSpec(): Promise<void>
-```
-
-Remove the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) from this table, reverting to the standard
-`mergeInsert` write path.
-
-Errors if no spec is currently set.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### update()
 
 #### update(opts)
@@ -1074,29 +890,6 @@ based on the row being updated (e.g. "my_col + 1")
 
 ***
 
-### updateFieldMetadata()
-
-```ts
-abstract updateFieldMetadata(updates): Promise<UpdateFieldMetadataResult>
-```
-
-Update per-field (column) metadata.
-
-#### Parameters
-
-* **updates**: [`FieldMetadataUpdate`](../interfaces/FieldMetadataUpdate.md)[]
-    One or more per-field updates. Each
-    update's metadata is merged into the field's existing metadata by default;
-    a value of `null` deletes that key, and `replace: true` swaps the whole map.
-
-#### Returns
-
-`Promise`&lt;[`UpdateFieldMetadataResult`](../interfaces/UpdateFieldMetadataResult.md)&gt;
-
-resolves to the new table version.
-
-***
-
 ### vectorSearch()
 
 ```ts

docs/src/js/classes/TakeQuery.md

@@ -29,7 +29,7 @@ protected inner: TakeQuery | Promise<TakeQuery>;
 ### analyzePlan()
 
 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```
 
 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -37,12 +37,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.
 
-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns
 
 `Promise`&lt;`string`&gt;
@@ -273,29 +267,6 @@ ArrowTable.
 
 ***
 
-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this take query.
-
-`false` bypasses the MemWAL and reads the base table only — the escape hatch,
-since take-by-row-id/offset is not supported on the LSM scanner and, on a
-MemWAL table, auto-routes to it and errors otherwise.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `false` reads the base table only.
-
-#### Returns
-
-`this`
-
-***
-
 ### withRowId()
 
 ```ts

docs/src/js/classes/VectorQuery.md

@@ -51,7 +51,7 @@ addQueryVector(vector): VectorQuery
 ### analyzePlan()
 
 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```
 
 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -59,12 +59,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.
 
-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns
 
 `Promise`&lt;`string`&gt;
@@ -504,30 +498,6 @@ This is useful for pagination.
 
 ***
 
-### orderBy()
-
-```ts
-orderBy(ordering): this
-```
-
-Sort the results by the specified column(s).
-
-#### Parameters
-
-* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
-
-#### Returns
-
-`this`
-
-This query builder.
-
-#### Inherited from
-
-`StandardQueryBase.orderBy`
-
-***
-
 ### outputSchema()
 
 ```ts
@@ -746,42 +716,6 @@ ArrowTable.
 
 ***
 
-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
 ### where()
 
 ```ts
@@ -809,9 +743,6 @@ x > 5 OR y = 'test'
 
 Filtering performance can often be improved by creating a scalar index
 on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
 ```
 
 #### Inherited from

docs/src/js/enumerations/OAuthFlowType.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthFlowType
-
-# Enumeration: OAuthFlowType
-
-OAuth authentication flow types.
-
-## Enumeration Members
-
-### AzureManagedIdentity
-
-```ts
-AzureManagedIdentity: "azure_managed_identity";
-```
-
-Azure Managed Identity via IMDS.
-
-***
-
-### ClientCredentials
-
-```ts
-ClientCredentials: "client_credentials";
-```
-
-Client Credentials grant (service-to-service / M2M).

docs/src/js/functions/instrumentLanceDbMetrics.md

@@ -1,42 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / instrumentLanceDbMetrics
-
-# Function: instrumentLanceDbMetrics()
-
-```ts
-function instrumentLanceDbMetrics(meterProvider?): boolean
-```
-
-Register LanceDB metrics as OpenTelemetry observable instruments.
-
-Installs a process-global metrics recorder and creates one observable
-instrument per LanceDB metric (currently object store request counts, bytes,
-latency, errors, and throttles) on the given (or global) `MeterProvider`. The
-configured `MetricReader` then collects them on its own schedule.
-
-Counters and gauges map directly to observable counters/gauges. Because
-OpenTelemetry has no asynchronous histogram instrument, each histogram is
-exported Prometheus-style as cumulative `le` bucket counts (`<name>_bucket`,
-with an `le` attribute) plus `<name>_count` and `<name>_sum`.
-
-Requires `@opentelemetry/api` (a dependency) and, to actually export, an
-OpenTelemetry SDK such as `@opentelemetry/sdk-metrics`.
-
-## Parameters
-
-* **meterProvider?**: `MeterProvider`
-    The provider to register instruments on. Defaults to the
-    global provider from `@opentelemetry/api`.
-
-## Returns
-
-`boolean`
-
-`true` if the recorder is installed and instruments are registered.
-  `false` if a different `metrics` recorder is already installed in this
-  process (only one global recorder is permitted), in which case a warning is
-  emitted and no instruments are created. Calling this more than once is safe;
-  instruments are created only on the first successful call.

docs/src/js/functions/tokenize.md

@@ -1,26 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / tokenize
-
-# Function: tokenize()
-
-```ts
-function tokenize(query, options?): Promise<FtsToken[]>
-```
-
-Tokenize a full-text search query using an explicit tokenizer.
-
-This does not require a table or FTS index. The tokenizer options match
-[Index.fts](../classes/Index.md#fts).
-
-## Parameters
-
-* **query**: `string`
-
-* **options?**: `Partial`&lt;[`TokenizeOptions`](../interfaces/TokenizeOptions.md)&gt;
-
-## Returns
-
-`Promise`&lt;[`FtsToken`](../interfaces/FtsToken.md)[]&gt;

docs/src/js/globals.md

@@ -12,7 +12,6 @@
 ## Enumerations
 
 - [FullTextQueryType](enumerations/FullTextQueryType.md)
-- [OAuthFlowType](enumerations/OAuthFlowType.md)
 - [Occur](enumerations/Occur.md)
 - [Operator](enumerations/Operator.md)
 
@@ -20,8 +19,6 @@
 
 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
-- [BranchContents](classes/BranchContents.md)
-- [Branches](classes/Branches.md)
 - [Connection](classes/Connection.md)
 - [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
@@ -35,7 +32,6 @@
 - [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
-- [Scannable](classes/Scannable.md)
 - [Session](classes/Session.md)
 - [StaticHeaderProvider](classes/StaticHeaderProvider.md)
 - [Table](classes/Table.md)
@@ -52,14 +48,8 @@
 - [AddDataOptions](interfaces/AddDataOptions.md)
 - [AddResult](interfaces/AddResult.md)
 - [AlterColumnsResult](interfaces/AlterColumnsResult.md)
-- [BranchColumnChange](interfaces/BranchColumnChange.md)
-- [BranchColumnSummary](interfaces/BranchColumnSummary.md)
-- [BranchDiff](interfaces/BranchDiff.md)
-- [BranchIndexSummary](interfaces/BranchIndexSummary.md)
-- [BranchRowCountSummary](interfaces/BranchRowCountSummary.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
-- [ColumnOrdering](interfaces/ColumnOrdering.md)
 - [CompactionStats](interfaces/CompactionStats.md)
 - [ConnectNamespaceOptions](interfaces/ConnectNamespaceOptions.md)
 - [ConnectionOptions](interfaces/ConnectionOptions.md)
@@ -73,11 +63,9 @@
 - [DropNamespaceOptions](interfaces/DropNamespaceOptions.md)
 - [DropNamespaceResponse](interfaces/DropNamespaceResponse.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
-- [FieldMetadataUpdate](interfaces/FieldMetadataUpdate.md)
 - [FragmentStatistics](interfaces/FragmentStatistics.md)
 - [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
 - [FtsOptions](interfaces/FtsOptions.md)
-- [FtsToken](interfaces/FtsToken.md)
 - [FullTextQuery](interfaces/FullTextQuery.md)
 - [FullTextSearchOptions](interfaces/FullTextSearchOptions.md)
 - [HnswPqOptions](interfaces/HnswPqOptions.md)
@@ -90,22 +78,14 @@
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
 - [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
-- [LsmWriteSpec](interfaces/LsmWriteSpec.md)
-- [MergeBlocker](interfaces/MergeBlocker.md)
-- [MergeBranchResult](interfaces/MergeBranchResult.md)
-- [MergePreview](interfaces/MergePreview.md)
 - [MergeResult](interfaces/MergeResult.md)
-- [NativeOAuthConfig](interfaces/NativeOAuthConfig.md)
-- [OAuthConfig](interfaces/OAuthConfig.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
 - [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
 - [RemovalStats](interfaces/RemovalStats.md)
-- [RenameTableOptions](interfaces/RenameTableOptions.md)
 - [RestNamespaceConfig](interfaces/RestNamespaceConfig.md)
 - [RetryConfig](interfaces/RetryConfig.md)
-- [ScannableOptions](interfaces/ScannableOptions.md)
 - [ShuffleOptions](interfaces/ShuffleOptions.md)
 - [SplitCalculatedOptions](interfaces/SplitCalculatedOptions.md)
 - [SplitHashOptions](interfaces/SplitHashOptions.md)
@@ -116,18 +96,13 @@
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [TlsConfig](interfaces/TlsConfig.md)
 - [TokenResponse](interfaces/TokenResponse.md)
-- [TokenizeOptions](interfaces/TokenizeOptions.md)
-- [UpdateFieldMetadataResult](interfaces/UpdateFieldMetadataResult.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
 - [WriteExecutionOptions](interfaces/WriteExecutionOptions.md)
-- [WriteProgress](interfaces/WriteProgress.md)
 
 ## Type Aliases
 
-- [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md)
-- [BaseTokenizer](type-aliases/BaseTokenizer.md)
 - [Data](type-aliases/Data.md)
 - [DataLike](type-aliases/DataLike.md)
 - [FieldLike](type-aliases/FieldLike.md)
@@ -137,15 +112,12 @@
 - [RecordBatchLike](type-aliases/RecordBatchLike.md)
 - [SchemaLike](type-aliases/SchemaLike.md)
 - [TableLike](type-aliases/TableLike.md)
-- [TokenizeTableOptions](type-aliases/TokenizeTableOptions.md)
 
 ## Functions
 
 - [RecordBatchIterator](functions/RecordBatchIterator.md)
 - [connect](functions/connect.md)
 - [connectNamespace](functions/connectNamespace.md)
-- [instrumentLanceDbMetrics](functions/instrumentLanceDbMetrics.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
 - [permutationBuilder](functions/permutationBuilder.md)
-- [tokenize](functions/tokenize.md)

docs/src/js/interfaces/AddDataOptions.md

@@ -19,39 +19,3 @@ mode: "append" | "overwrite";
 If "append" (the default) then the new data will be added to the table
 
 If "overwrite" then the new data will replace the existing data in the table.
-
-***
-
-### progress()
-
-```ts
-progress: (progress) => void;
-```
-
-Optional callback invoked periodically with write progress.
-
-The callback is fired once per batch written and once more with
-`done: true` when the write completes. Calls are dispatched
-asynchronously to the JS event loop and never block the write — a slow
-callback will queue events rather than back-pressure the writer.
-
-Errors thrown from the callback are logged with `console.warn` and
-swallowed — they do not abort the write.
-
-#### Parameters
-
-* **progress**: [`WriteProgress`](WriteProgress.md)
-
-#### Returns
-
-`void`
-
-#### Example
-
-```ts
-await table.add(data, {
-  progress: (p) => {
-    console.log(`${p.outputRows}/${p.totalRows ?? "?"} rows`);
-  },
-});
-```

docs/src/js/interfaces/BranchColumnChange.md

@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchColumnChange
-
-# Interface: BranchColumnChange
-
-A column whose definition differs between main and the branch.
-
-## Properties
-
-### branch
-
-```ts
-branch: BranchColumnSummary;
-```
-
-***
-
-### main
-
-```ts
-main: BranchColumnSummary;
-```
-
-***
-
-### name
-
-```ts
-name: string;
-```

docs/src/js/interfaces/BranchColumnSummary.md

@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchColumnSummary
-
-# Interface: BranchColumnSummary
-
-Summary of a column in a branch diff.
-
-## Properties
-
-### dataType
-
-```ts
-dataType: string;
-```
-
-***
-
-### name
-
-```ts
-name: string;
-```
-
-***
-
-### nullable
-
-```ts
-nullable: boolean;
-```

docs/src/js/interfaces/BranchDiff.md

@@ -1,129 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchDiff
-
-# Interface: BranchDiff
-
-Read-only comparison of a branch against main.
-
-## Properties
-
-### addedColumns
-
-```ts
-addedColumns: BranchColumnSummary[];
-```
-
-***
-
-### addedIndexes
-
-```ts
-addedIndexes: BranchIndexSummary[];
-```
-
-***
-
-### baseMoved
-
-```ts
-baseMoved: boolean;
-```
-
-***
-
-### branchVersion
-
-```ts
-branchVersion: number;
-```
-
-***
-
-### changedColumns
-
-```ts
-changedColumns: BranchColumnChange[];
-```
-
-***
-
-### fromBranch
-
-```ts
-fromBranch: string;
-```
-
-***
-
-### mainVersion
-
-```ts
-mainVersion: number;
-```
-
-***
-
-### mergeBlockers
-
-```ts
-mergeBlockers: MergeBlocker[];
-```
-
-***
-
-### mergeable
-
-```ts
-mergeable: boolean;
-```
-
-***
-
-### parentVersion
-
-```ts
-parentVersion: number;
-```
-
-***
-
-### removedColumns
-
-```ts
-removedColumns: BranchColumnSummary[];
-```
-
-***
-
-### removedIndexes
-
-```ts
-removedIndexes: BranchIndexSummary[];
-```
-
-***
-
-### rowCountBranch
-
-```ts
-rowCountBranch: number;
-```
-
-***
-
-### rowCountMain
-
-```ts
-rowCountMain: number;
-```
-
-***
-
-### rowSummary
-
-```ts
-rowSummary: BranchRowCountSummary;
-```

docs/src/js/interfaces/BranchIndexSummary.md

@@ -1,41 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchIndexSummary
-
-# Interface: BranchIndexSummary
-
-Summary of an index in a branch diff.
-
-## Properties
-
-### columns
-
-```ts
-columns: string[];
-```
-
-***
-
-### indexName
-
-```ts
-indexName: string;
-```
-
-***
-
-### indexType?
-
-```ts
-optional indexType: string;
-```
-
-***
-
-### status
-
-```ts
-status: string;
-```

docs/src/js/interfaces/BranchRowCountSummary.md

@@ -1,57 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchRowCountSummary
-
-# Interface: BranchRowCountSummary
-
-Row-level comparison between main and the branch.
-
-## Properties
-
-### deltaAvailable
-
-```ts
-deltaAvailable: boolean;
-```
-
-***
-
-### inputsChanged
-
-```ts
-inputsChanged: number;
-```
-
-***
-
-### newOnBase
-
-```ts
-newOnBase: number;
-```
-
-***
-
-### newOnBranch
-
-```ts
-newOnBranch: number;
-```
-
-***
-
-### staleRecompute
-
-```ts
-staleRecompute: number;
-```
-
-***
-
-### unchanged
-
-```ts
-unchanged: number;
-```

docs/src/js/interfaces/ColumnOrdering.md

@@ -1,31 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ColumnOrdering
-
-# Interface: ColumnOrdering
-
-## Properties
-
-### ascending?
-
-```ts
-optional ascending: boolean;
-```
-
-***
-
-### columnName
-
-```ts
-columnName: string;
-```
-
-***
-
-### nullsFirst?
-
-```ts
-optional nullsFirst: boolean;
-```

docs/src/js/interfaces/ConnectionOptions.md

@@ -64,39 +64,22 @@ client used by manifest-enabled native connections.
 
 ***
 
-### oauthConfig?
-
-```ts
-optional oauthConfig: NativeOAuthConfig;
-```
-
-(For LanceDB cloud only): OAuth configuration for IdP-based
-authentication (e.g., Azure Entra ID). When set, token acquisition
-and refresh are handled entirely in Rust. TypeScript users should pass
-the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-
-***
-
 ### readConsistencyInterval?
 
 ```ts
 optional readConsistencyInterval: number;
 ```
 
-The interval, in seconds, at which to check for updates to the table
-from other processes. If None, then consistency is not checked. For
-performance reasons, this is the default. For strong consistency, set
-this to zero seconds. Then every read will check for updates from other
-processes. As a compromise, you can set this to a non-zero value for
-eventual consistency. If more than that interval has passed since the
-last check, then the table will be checked for updates. Note: this
-consistency only applies to read operations. Write operations are
+(For LanceDB OSS only): The interval, in seconds, at which to check for
+updates to the table from other processes. If None, then consistency is not
+checked. For performance reasons, this is the default. For strong
+consistency, set this to zero seconds. Then every read will check for
+updates from other processes. As a compromise, you can set this to a
+non-zero value for eventual consistency. If more than that interval
+has passed since the last check, then the table will be checked for updates.
+Note: this consistency only applies to read operations. Write operations are
 always consistent.
 
-Stronger consistency is not free. The smaller the interval, the more
-often each read pays the cost of checking for updates against object
-storage, raising per-read latency and cost.
-
 ***
 
 ### region?

docs/src/js/interfaces/FieldMetadataUpdate.md

@@ -1,41 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FieldMetadataUpdate
-
-# Interface: FieldMetadataUpdate
-
-A per-field metadata update, addressed by dot-path.
-
-## Properties
-
-### metadata
-
-```ts
-metadata: Record<string, null | string>;
-```
-
-Metadata key/value pairs. Merged into the field's existing metadata by
-default; a value of `null` deletes that key.
-
-***
-
-### path
-
-```ts
-path: string;
-```
-
-Dot-separated path to the field. For a top-level column this is just its
-name; for a nested field it's the path, e.g. "a.b.c".
-
-***
-
-### replace?
-
-```ts
-optional replace: boolean;
-```
-
-If true, replace the field's entire metadata map instead of merging.

docs/src/js/interfaces/FtsOptions.md

@@ -23,7 +23,7 @@ whether to remove punctuation
 ### baseTokenizer?
 
 ```ts
-optional baseTokenizer: BaseTokenizer;
+optional baseTokenizer: "raw" | "simple" | "whitespace" | "ngram";
 ```
 
 The tokenizer to use when building the index.
@@ -37,38 +37,6 @@ The following tokenizers are available:
 
 "raw" - Raw tokenizer. This tokenizer does not split the text into tokens and indexes the entire text as a single token.
 
-"icu" - ICU dictionary-based word segmentation.
-
-"icu/split" - ICU segmentation with simple-style delimiter splitting.
-
-***
-
-### blockSize?
-
-```ts
-optional blockSize: 128 | 256;
-```
-
-Number of documents per compressed posting block.
-
-The default is 128. Supported values are 128 and 256. A value of 256 uses
-the experimental FTS V3 format and may introduce breaking changes.
-
-***
-
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
 ***
 
 ### language?

docs/src/js/interfaces/FtsToken.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FtsToken
-
-# Interface: FtsToken
-
-Token produced by the tokenizer configured on a full-text search index.
-
-## Properties
-
-### position
-
-```ts
-position: number;
-```
-
-Token position used by full-text query matching.
-
-***
-
-### text
-
-```ts
-text: string;
-```
-
-Token text after tokenizer filters have been applied.

docs/src/js/interfaces/IndexConfig.md

@@ -23,31 +23,6 @@ be more columns to represent composite indices.
 
 ***
 
-### createdAt?
-
-```ts
-optional createdAt: Date;
-```
-
-When the index was created.
-
-`undefined` for remote tables or indices created before timestamps were tracked.
-
-***
-
-### indexDetails?
-
-```ts
-optional indexDetails: any;
-```
-
-Index-type-specific details parsed as a JavaScript object.
-
-Falls back to a raw string if JSON parsing fails. `undefined` for
-remote tables or when details are unavailable.
-
-***
-
 ### indexType
 
 ```ts
@@ -58,30 +33,6 @@ The type of the index
 
 ***
 
-### indexUuid?
-
-```ts
-optional indexUuid: string;
-```
-
-The UUID of the first segment of the index.
-
-`undefined` for remote tables, which do not yet surface this.
-
-***
-
-### indexVersion?
-
-```ts
-optional indexVersion: number;
-```
-
-The on-disk index format version.
-
-`undefined` for remote tables.
-
-***
-
 ### name
 
 ```ts
@@ -89,63 +40,3 @@ name: string;
 ```
 
 The name of the index
-
-***
-
-### numIndexedRows?
-
-```ts
-optional numIndexedRows: number;
-```
-
-The number of rows indexed, across all segments.
-
-`undefined` for remote tables.
-
-***
-
-### numSegments?
-
-```ts
-optional numSegments: number;
-```
-
-The number of segments that make up the index.
-
-`undefined` for remote tables.
-
-***
-
-### numUnindexedRows?
-
-```ts
-optional numUnindexedRows: number;
-```
-
-The number of rows not yet covered by this index.
-
-`undefined` for remote tables.
-
-***
-
-### sizeBytes?
-
-```ts
-optional sizeBytes: number;
-```
-
-The total size in bytes of all index files across all segments.
-
-`undefined` for remote tables or indices without size tracking.
-
-***
-
-### typeUrl?
-
-```ts
-optional typeUrl: string;
-```
-
-The protobuf type URL, a precise type identifier for the index.
-
-`undefined` for remote tables.

docs/src/js/interfaces/IndexStatistics.md

@@ -30,6 +30,17 @@ The type of the index
 
 ***
 
+### loss?
+
+```ts
+optional loss: number;
+```
+
+The KMeans loss value of the index,
+it is only present for vector indices.
+
+***
+
 ### numIndexedRows
 
 ```ts

docs/src/js/interfaces/LsmWriteSpec.md

@@ -1,67 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / LsmWriteSpec
-
-# Interface: LsmWriteSpec
-
-Specification selecting Lance's MemWAL LSM-style write path for
-`mergeInsert`.
-
-`specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
-`column` and `numBuckets` are required; for `"identity"`, `column` is
-required and must be a deterministic function of the unenforced primary
-key (every row with a given primary key must always produce the same
-`column` value, or upserts of that key can land in different shards and a
-stale version can win).
-
-## Properties
-
-### column?
-
-```ts
-optional column: string;
-```
-
-Bucket and identity variants: the sharding column.
-
-***
-
-### maintainedIndexes?
-
-```ts
-optional maintainedIndexes: string[];
-```
-
-Names of indexes the MemWAL should keep up to date during writes.
-
-***
-
-### numBuckets?
-
-```ts
-optional numBuckets: number;
-```
-
-Bucket variant: the number of buckets, in `[1, 1024]`.
-
-***
-
-### specType
-
-```ts
-specType: "bucket" | "identity" | "unsharded";
-```
-
-One of `"bucket"`, `"identity"`, or `"unsharded"`.
-
-***
-
-### writerConfigDefaults?
-
-```ts
-optional writerConfigDefaults: Record<string, string>;
-```
-
-Default `ShardWriter` configuration recorded in the MemWAL index.

docs/src/js/interfaces/MergeBlocker.md

@@ -1,25 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeBlocker
-
-# Interface: MergeBlocker
-
-A reason why a branch cannot currently be merged.
-
-## Properties
-
-### code
-
-```ts
-code: string;
-```
-
-***
-
-### message
-
-```ts
-message: string;
-```

docs/src/js/interfaces/MergeBranchResult.md

@@ -1,46 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeBranchResult
-
-# Interface: MergeBranchResult
-
-Result of previewing or attempting a branch merge.
-
-## Properties
-
-### diff
-
-```ts
-diff: BranchDiff;
-```
-
-***
-
-### mainVersionAfter?
-
-```ts
-optional mainVersionAfter: number;
-```
-
-***
-
-### preview
-
-```ts
-preview: MergePreview;
-```
-
-***
-
-### status
-
-```ts
-status:
-  | "unknown"
-  | "rejected"
-  | "ready"
-  | "notImplemented"
-  | "merged";
-```

docs/src/js/interfaces/MergePreview.md

@@ -1,17 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergePreview
-
-# Interface: MergePreview
-
-Changes that would be, or were, promoted by a branch merge.
-
-## Properties
-
-### promotedColumns
-
-```ts
-promotedColumns: string[];
-```

docs/src/js/interfaces/MergeResult.md

@@ -32,14 +32,6 @@ numInsertedRows: number;
 
 ***
 
-### numRows
-
-```ts
-numRows: number;
-```
-
-***
-
 ### numUpdatedRows
 
 ```ts

docs/src/js/interfaces/NativeOAuthConfig.md

@@ -1,88 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / NativeOAuthConfig
-
-# Interface: NativeOAuthConfig
-
-OAuth configuration for LanceDB authentication.
-
-This is the generated napi-rs binding shape. TypeScript users should prefer
-the public `OAuthConfig` type exported from `@lancedb/lancedb`.
-
-All token acquisition and refresh is handled in the Rust layer.
-
-## Properties
-
-### clientId
-
-```ts
-clientId: string;
-```
-
-Application / Client ID.
-
-***
-
-### clientSecret?
-
-```ts
-optional clientSecret: string;
-```
-
-Client secret (required for client_credentials).
-
-***
-
-### flow?
-
-```ts
-optional flow: string;
-```
-
-Authentication flow: "client_credentials" or "azure_managed_identity"
-
-***
-
-### issuerUrl
-
-```ts
-issuerUrl: string;
-```
-
-OIDC issuer URL or OAuth authority URL.
-For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-
-***
-
-### managedIdentityClientId?
-
-```ts
-optional managedIdentityClientId: string;
-```
-
-Client ID for user-assigned managed identity (azure_managed_identity).
-
-***
-
-### refreshBufferSecs?
-
-```ts
-optional refreshBufferSecs: number;
-```
-
-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.
-
-***
-
-### scopes
-
-```ts
-scopes: string[];
-```
-
-OAuth scopes to request. For Azure managed identity, exactly one scope
-or resource is required. For example: `["api://{app_id}/.default"]`

docs/src/js/interfaces/OAuthConfig.md

@@ -1,111 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / OAuthConfig
-
-# Interface: OAuthConfig
-
-OAuth configuration for LanceDB authentication.
-
-This is the public TypeScript OAuth configuration type. The generated
-`NativeOAuthConfig` type has the same runtime shape but is an implementation
-detail of the napi-rs binding.
-
-All token acquisition and refresh is handled in the Rust layer.
-This config is passed through to Rust via napi-rs.
-
-## Examples
-
-```typescript
-const config: OAuthConfig = {
-  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
-  clientId: "app-id",
-  clientSecret: "secret",
-  scopes: ["api://lancedb-api/.default"],
-};
-```
-
-```typescript
-const config: OAuthConfig = {
-  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
-  clientId: "app-id",
-  scopes: ["api://lancedb-api/.default"],
-  flow: OAuthFlowType.AzureManagedIdentity,
-};
-```
-
-## Properties
-
-### clientId
-
-```ts
-clientId: string;
-```
-
-Application / Client ID.
-
-***
-
-### clientSecret?
-
-```ts
-optional clientSecret: string;
-```
-
-Client secret (required for ClientCredentials).
-
-***
-
-### flow?
-
-```ts
-optional flow: OAuthFlowType;
-```
-
-Authentication flow (default: ClientCredentials).
-
-***
-
-### issuerUrl
-
-```ts
-issuerUrl: string;
-```
-
-OIDC issuer URL or OAuth authority URL.
-For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
-
-***
-
-### managedIdentityClientId?
-
-```ts
-optional managedIdentityClientId: string;
-```
-
-Client ID for user-assigned managed identity (AzureManagedIdentity).
-
-***
-
-### refreshBufferSecs?
-
-```ts
-optional refreshBufferSecs: number;
-```
-
-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.
-
-***
-
-### scopes
-
-```ts
-scopes: string[];
-```
-
-OAuth scopes to request.
-For Azure managed identity, exactly one scope or resource is required.
-For example: `["api://{app_id}/.default"]`

docs/src/js/interfaces/OpenTableOptions.md

@@ -8,18 +8,6 @@
 
 ## Properties
 
-### branch?
-
-```ts
-optional branch: string;
-```
-
-Open the table scoped to this branch instead of the default branch.
-
-Reads and writes on the returned table operate in the branch's context.
-
-***
-
 ### ~~indexCacheSize?~~
 
 ```ts
@@ -55,17 +43,3 @@ Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
 The available options are described at https://docs.lancedb.com/storage/
-
-***
-
-### version?
-
-```ts
-optional version: number;
-```
-
-Open the table pinned to this version, producing a read-only view.
-
-Composes with [OpenTableOptions.branch](OpenTableOptions.md#branch): when both are set, opens
-that branch at the version; otherwise opens `main` at the version. Call
-`checkoutLatest` to return to a writable state.

docs/src/js/interfaces/RenameTableOptions.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / RenameTableOptions
-
-# Interface: RenameTableOptions
-
-## Properties
-
-### namespacePath?
-
-```ts
-optional namespacePath: string[];
-```
-
-The namespace path of the table being renamed. Defaults to the root
-namespace (`[]`) when omitted.
-
-***
-
-### newNamespacePath?
-
-```ts
-optional newNamespacePath: string[];
-```
-
-The namespace path to move the table to as part of the rename. When
-omitted the table stays in `namespacePath`.

docs/src/js/interfaces/ScannableOptions.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ScannableOptions
-
-# Interface: ScannableOptions
-
-## Properties
-
-### numRows?
-
-```ts
-optional numRows: number;
-```
-
-Hint about the number of rows. Not validated against the stream.
-
-***
-
-### rescannable?
-
-```ts
-optional rescannable: boolean;
-```
-
-Whether the source can be scanned more than once. Defaults to `true` for
-`fromTable` / `fromFactory` and `false` for `fromIterable` /
-`fromRecordBatchReader`.

docs/src/js/interfaces/SplitRandomOptions.md

@@ -8,14 +8,6 @@
 
 ## Properties
 
-### clumpSize?
-
-```ts
-optional clumpSize: number;
-```
-
-***
-
 ### counts?
 
 ```ts

docs/src/js/interfaces/TokenizeOptions.md

@@ -1,124 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TokenizeOptions
-
-# Interface: TokenizeOptions
-
-Options for tokenizing a full-text search query without a table index.
-
-## Properties
-
-### asciiFolding?
-
-```ts
-optional asciiFolding: boolean;
-```
-
-Whether to fold ASCII characters.
-
-***
-
-### baseTokenizer?
-
-```ts
-optional baseTokenizer: BaseTokenizer;
-```
-
-The tokenizer to use. The default is "simple".
-
-***
-
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
-***
-
-### language?
-
-```ts
-optional language: string;
-```
-
-Language for stemming and stop words.
-
-***
-
-### lowercase?
-
-```ts
-optional lowercase: boolean;
-```
-
-Whether to lowercase tokens.
-
-***
-
-### maxTokenLength?
-
-```ts
-optional maxTokenLength: number;
-```
-
-Maximum token length; tokens longer than this are ignored.
-
-***
-
-### ngramMaxLength?
-
-```ts
-optional ngramMaxLength: number;
-```
-
-N-gram maximum length.
-
-***
-
-### ngramMinLength?
-
-```ts
-optional ngramMinLength: number;
-```
-
-N-gram minimum length.
-
-***
-
-### prefixOnly?
-
-```ts
-optional prefixOnly: boolean;
-```
-
-Whether to only emit token prefixes for the n-gram tokenizer.
-
-***
-
-### removeStopWords?
-
-```ts
-optional removeStopWords: boolean;
-```
-
-Whether to remove stop words.
-
-***
-
-### stem?
-
-```ts
-optional stem: boolean;
-```
-
-Whether to stem tokens.

docs/src/js/interfaces/UpdateFieldMetadataResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / UpdateFieldMetadataResult
-
-# Interface: UpdateFieldMetadataResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/WriteProgress.md

@@ -1,84 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / WriteProgress
-
-# Interface: WriteProgress
-
-Progress snapshot for a write operation, delivered to the `progress`
-callback passed to [Table.add](../classes/Table.md#add).
-
-## Properties
-
-### activeTasks
-
-```ts
-activeTasks: number;
-```
-
-Number of parallel write tasks currently in flight.
-
-***
-
-### done
-
-```ts
-done: boolean;
-```
-
-`true` for the final callback; `false` otherwise.
-
-***
-
-### elapsedSeconds
-
-```ts
-elapsedSeconds: number;
-```
-
-Wall-clock seconds since the write started.
-
-***
-
-### outputBytes
-
-```ts
-outputBytes: number;
-```
-
-Number of bytes written so far.
-
-***
-
-### outputRows
-
-```ts
-outputRows: number;
-```
-
-Number of rows written so far.
-
-***
-
-### totalRows?
-
-```ts
-optional totalRows: number;
-```
-
-Total rows expected, when the input source reports it.
-
-Always set on the final callback (the one with `done: true`), falling
-back to the actual number of rows written when the source could not
-report a row count up front.
-
-***
-
-### totalTasks
-
-```ts
-totalTasks: number;
-```
-
-Total number of parallel write tasks (the write parallelism).

docs/src/js/type-aliases/AnalyzePlanDistributedMetrics.md

@@ -1,11 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AnalyzePlanDistributedMetrics
-
-# Type Alias: AnalyzePlanDistributedMetrics
-
-```ts
-type AnalyzePlanDistributedMetrics: "aggregate" | "per_worker" | "full";
-```

docs/src/js/type-aliases/BaseTokenizer.md

@@ -1,19 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BaseTokenizer
-
-# Type Alias: BaseTokenizer
-
-```ts
-type BaseTokenizer:
-  | "simple"
-  | "whitespace"
-  | "raw"
-  | "ngram"
-  | "icu"
-  | "icu/split"
-  | `jieba/${string}`
-  | `lindera/${string}`;
-```

docs/src/js/type-aliases/TokenizeTableOptions.md

@@ -1,11 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / TokenizeTableOptions
-
-# Type Alias: TokenizeTableOptions
-
-```ts
-type TokenizeTableOptions: object | object;
-```

docs/src/python/python.md

@@ -26,18 +26,6 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ::: lancedb.db.DBConnection
 
-::: lancedb.Session
-
-## Namespaces (Synchronous)
-
-A namespace-backed connection resolves tables through a
-[Lance namespace](https://lancedb.github.io/lance-namespace/) service instead of
-listing a storage directory.
-
-::: lancedb.connect_namespace
-
-::: lancedb.namespace.LanceNamespaceDBConnection
-
 ## Tables (Synchronous)
 
 ::: lancedb.table.Table
@@ -46,12 +34,8 @@ listing a storage directory.
 
 ::: lancedb.table.FragmentSummaryStats
 
-::: lancedb.table.TableStatistics
-
 ::: lancedb.table.Tags
 
-::: lancedb.table.Branches
-
 ## Expressions
 
 Type-safe expression builder for filters and projections. Use these instead
@@ -78,46 +62,29 @@ of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and
 
 ::: lancedb.query.LanceHybridQueryBuilder
 
-::: lancedb.query.LanceEmptyQueryBuilder
-
-::: lancedb.query.LanceTakeQueryBuilder
-
-## Full text queries
-
-Structured full text queries can be passed to
-[Table.search][lancedb.table.Table.search] or
-[AsyncTable.search][lancedb.table.AsyncTable.search] in place of a query string,
-and combined with [BooleanQuery][lancedb.query.BooleanQuery].
-
-::: lancedb.query.FullTextQuery
-
-::: lancedb.query.MatchQuery
-
-::: lancedb.query.PhraseQuery
-
-::: lancedb.query.BoostQuery
-
-::: lancedb.query.MultiMatchQuery
-
-::: lancedb.query.BooleanQuery
-
-::: lancedb.query.FullTextOperator
-
-::: lancedb.query.Occur
-
 ## Embeddings
 
-::: lancedb.embeddings
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.embeddings.registry.EmbeddingFunctionRegistry
+
+::: lancedb.embeddings.base.EmbeddingFunctionConfig
+
+::: lancedb.embeddings.base.EmbeddingFunction
+
+::: lancedb.embeddings.base.TextEmbeddingFunction
+
+::: lancedb.embeddings.sentence_transformers.SentenceTransformerEmbeddings
+
+::: lancedb.embeddings.openai.OpenAIEmbeddings
+
+::: lancedb.embeddings.open_clip.OpenClipEmbeddings
 
 ## Remote configuration
 
-::: lancedb.remote
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.remote.ClientConfig
+
+::: lancedb.remote.TimeoutConfig
+
+::: lancedb.remote.RetryConfig
 
 ## Context
 
@@ -127,50 +94,11 @@ and combined with [BooleanQuery][lancedb.query.BooleanQuery].
 
 ## Full text search
 
-Pass `custom_stop_words` to [lancedb.index.FTS][]:
+Use [lancedb.table.Table.create_fts_index][] for the synchronous API or
+[lancedb.table.AsyncTable.create_index][] with [lancedb.index.FTS][] for the
+asynchronous API.
 
-```python
-from lancedb.index import FTS
-
-table.create_index(
-    "text",
-    config=FTS(remove_stop_words=True, custom_stop_words=["acme", "internal"]),
-)
-```
-
-The list replaces the built-in stop words and is used only when
-`remove_stop_words=True`:
-
-- `custom_stop_words=None` uses the built-in list for `language`.
-- `custom_stop_words=[]` removes no words.
-- Values are passed through without trimming, lowercasing, or other rewriting.
-
-The same option is available on `lancedb.tokenize(...)` and the deprecated
-[lancedb.table.Table.create_fts_index][] compatibility helper:
-
-```python
-import lancedb
-
-tokens = list(lancedb.tokenize("acme makes searchable data",
-                               custom_stop_words=["acme"]))
-```
-
-::: lancedb.tokenize
-
-::: lancedb.FtsToken
-
-## Blobs
-
-Blob columns store large binary values out of line so they can be read lazily
-instead of being materialized with the rest of the row.
-
-::: lancedb.blob
-
-::: lancedb.BlobType
-
-::: lancedb._blob.BlobFile
-    options:
-      show_root_full_path: false
+::: lancedb.index.FTS
 
 ## Utilities
 
@@ -178,14 +106,6 @@ instead of being materialized with the rest of the row.
 
 ::: lancedb.merge.LanceMergeInsertBuilder
 
-::: lancedb.otel.instrument_lancedb_metrics
-
-## Exceptions
-
-::: lancedb.exceptions.MissingValueError
-
-::: lancedb.exceptions.MissingColumnError
-
 ## Integrations
 
 ## Pydantic
@@ -194,30 +114,19 @@ instead of being materialized with the rest of the row.
 
 ::: lancedb.pydantic.vector
 
-::: lancedb.pydantic.Vector
-
-::: lancedb.pydantic.MultiVector
-
 ::: lancedb.pydantic.LanceModel
 
-## PyTorch
-
-::: lancedb.streaming.StreamingDataset
-
-::: lancedb.permutation.permutation_builder
-
-::: lancedb.permutation.PermutationBuilder
-
-::: lancedb.permutation.Permutation
-
-::: lancedb.permutation.Transforms
-
 ## Reranking
 
-::: lancedb.rerankers
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.rerankers.linear_combination.LinearCombinationReranker
+
+::: lancedb.rerankers.cohere.CohereReranker
+
+::: lancedb.rerankers.colbert.ColbertReranker
+
+::: lancedb.rerankers.cross_encoder.CrossEncoderReranker
+
+::: lancedb.rerankers.openai.OpenaiReranker
 
 ## Connections (Asynchronous)
 
@@ -228,12 +137,6 @@ can be used to create, list, or open tables.
 
 ::: lancedb.db.AsyncConnection
 
-## Namespaces (Asynchronous)
-
-::: lancedb.connect_namespace_async
-
-::: lancedb.namespace.AsyncLanceNamespaceDBConnection
-
 ## Tables (Asynchronous)
 
 Table hold your actual data as a collection of records / rows.
@@ -242,20 +145,26 @@ Table hold your actual data as a collection of records / rows.
 
 ::: lancedb.table.AsyncTags
 
-::: lancedb.table.AsyncBranches
-
 ## Indices (Asynchronous)
 
 Indices can be created on a table to speed up queries. This section
 lists the indices that LanceDb supports.
 
-::: lancedb.index
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
-      # `lang_mapping` is defined in the module rather than imported, so it is
-      # picked up despite not being in `__all__`. It is an internal lookup table.
-      filters: ["!^_", "!^lang_mapping$"]
+::: lancedb.index.BTree
+
+::: lancedb.index.Bitmap
+
+::: lancedb.index.LabelList
+
+::: lancedb.index.FTS
+
+::: lancedb.index.IvfPq
+
+::: lancedb.index.HnswPq
+
+::: lancedb.index.HnswSq
+
+::: lancedb.index.IvfFlat
 
 ::: lancedb.table.IndexStatistics
 
@@ -283,7 +192,3 @@ rows nearest to a query vector and can be created with the
 ::: lancedb.query.AsyncHybridQuery
     options:
       inherited_members: true
-
-::: lancedb.query.AsyncTakeQuery
-    options:
-      inherited_members: true

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.37.1-beta.0</version>
+      <version>0.28.0-beta.11</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.28.0-beta.11</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>10.0.0-beta.5</lance-core.version>
+        <lance-core.version>7.0.0-beta.7</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/CONTRIBUTING.md

@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript
 
 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).
 
 ## Project layout
 

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.37.1-beta.0"
+version = "0.28.0-beta.11"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -25,12 +25,8 @@ lancedb = { path = "../rust/lancedb", default-features = false }
 lance-namespace.workspace = true
 napi = { version = "3.8.3", default-features = false, features = [
     "napi9",
-    "async",
-    "chrono_date",
-    "serde-json",
+    "async"
 ] }
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
-serde_json = "1"
 napi-derive = "3.5.2"
 # Prevent dynamic linking of lzma, which comes from datafusion
 lzma-sys = { version = "0.1", features = ["static"] }
@@ -44,6 +40,6 @@ aws-lc-rs = "=1.16.3"
 napi-build = "2.3.1"
 
 [features]
-default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface", "lancedb/goosefs", "lancedb/metrics-otel"]
+default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]

nodejs/__test__/arrow.test.ts

@@ -52,7 +52,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       Float64,
       Struct,
       List,
-      Map_,
       Int16,
       Int32,
       Int64,
@@ -70,30 +69,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
     type Schema = ApacheArrow["Schema"];
     type Table = ApacheArrow["Table"];
 
-    function expectValidMapField(
-      // biome-ignore lint/suspicious/noExplicitAny: Arrow Field types vary across supported versions
-      field: any,
-    ): void {
-      expect(DataType.isMap(field.type)).toBe(true);
-      expect(field.type.keysSorted).toBe(true);
-      expect(field.type.children).toHaveLength(1);
-
-      const entries = field.type.children[0];
-      expect(entries.name).toBe("entries");
-      expect(entries.nullable).toBe(false);
-      expect(DataType.isStruct(entries.type)).toBe(true);
-      expect(entries.type.children).toHaveLength(2);
-
-      const [key, value] = entries.type.children;
-      expect([key.name, value.name]).toEqual(["key", "value"]);
-      expect(key.nullable).toBe(false);
-      expect(DataType.isUtf8(key.type)).toBe(true);
-      expect(value.nullable).toBe(true);
-      expect(DataType.isInt(value.type)).toBe(true);
-      expect(value.type.bitWidth).toBe(32);
-      expect(value.type.isSigned).toBe(true);
-    }
-
     // Helper method to verify various ways to create a table
     async function checkTableCreation(
       tableCreationMethod: (
@@ -963,65 +938,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
           false,
         );
       });
-
-      it("will make an empty table with a Map field", async function () {
-        const schema = new Schema([
-          new Field(
-            "attributes",
-            new Map_(
-              new Field(
-                "entries",
-                new Struct([
-                  new Field("key", new Utf8(), false),
-                  new Field("value", new Int32(), true),
-                ]),
-                false,
-              ),
-              true,
-            ),
-          ),
-        ]);
-
-        const table = makeEmptyTable(schema);
-
-        expectValidMapField(table.schema.fields[0]);
-
-        const buffer = await fromTableToBuffer(table);
-        const roundTripped = tableFromIPC(buffer);
-
-        expectValidMapField(roundTripped.schema.fields[0]);
-      });
-
-      it("preserves string schema metadata", function () {
-        const metadata = new Map([["source", "fixture"]]);
-        const schema = new Schema(
-          [new Field("value", new Int32(), true)],
-          metadata,
-        );
-
-        expect(makeEmptyTable(schema).schema.metadata.get("source")).toBe(
-          "fixture",
-        );
-      });
-
-      it.each([
-        ["non-string keys", new Map<unknown, unknown>([[42, "fixture"]])],
-        ["non-string values", new Map<unknown, unknown>([["source", 42]])],
-        [
-          "non-string keys and values",
-          new Map<unknown, unknown>([[42, false]]),
-        ],
-      ])("rejects schema metadata with %s", function (_, metadataLike) {
-        const metadata = metadataLike as unknown as Map<string, string>;
-        const schema = new Schema(
-          [new Field("value", new Int32(), true)],
-          metadata,
-        );
-
-        expect(() => makeEmptyTable(schema)).toThrow(
-          "Expected metadata, if present, to be a Map<string, string> but it had non-string keys or values",
-        );
-      });
     });
 
     describe("when using two versions of arrow", function () {

nodejs/__test__/connection.test.ts

@@ -47,14 +47,6 @@ describe("given a connection", () => {
     await db.close();
     expect(db.isOpen()).toBe(false);
     await expect(db.tableNames()).rejects.toThrow("Connection is closed");
-    await expect(db.renameTable("a", "b")).rejects.toThrow(
-      "Connection is closed",
-    );
-  });
-
-  it("should report renameTable as unsupported on an OSS connection", async () => {
-    await db.createTable("a", [{ id: 1 }]);
-    await expect(db.renameTable("a", "b")).rejects.toThrow(/not supported/);
   });
   it("should be able to create a table from an object arg `createTable(options)`, or args `createTable(name, data, options)`", async () => {
     let tbl = await db.createTable("test", [{ id: 1 }, { id: 2 }]);
@@ -171,22 +163,18 @@ describe("given a connection", () => {
 
     let manifestDir =
       tmpDir.name + "/test_manifest_paths_v2_empty.lance/_versions";
-    readdirSync(manifestDir)
-      .filter((f) => f.endsWith(".manifest"))
-      .forEach((file) => {
-        expect(file).toMatch(/^\d{20}\.manifest$/);
-      });
+    readdirSync(manifestDir).forEach((file) => {
+      expect(file).toMatch(/^\d{20}\.manifest$/);
+    });
 
     table = (await db.createTable("test_manifest_paths_v2", [{ id: 1 }], {
       enableV2ManifestPaths: true,
     })) as LocalTable;
     expect(await table.usesV2ManifestPaths()).toBe(true);
     manifestDir = tmpDir.name + "/test_manifest_paths_v2.lance/_versions";
-    readdirSync(manifestDir)
-      .filter((f) => f.endsWith(".manifest"))
-      .forEach((file) => {
-        expect(file).toMatch(/^\d{20}\.manifest$/);
-      });
+    readdirSync(manifestDir).forEach((file) => {
+      expect(file).toMatch(/^\d{20}\.manifest$/);
+    });
   });
 
   it("should be able to migrate tables to the V2 manifest paths", async () => {
@@ -203,20 +191,16 @@ describe("given a connection", () => {
 
     const manifestDir =
       tmpDir.name + "/test_manifest_path_migration.lance/_versions";
-    readdirSync(manifestDir)
-      .filter((f) => f.endsWith(".manifest"))
-      .forEach((file) => {
-        expect(file).toMatch(/^\d\.manifest$/);
-      });
+    readdirSync(manifestDir).forEach((file) => {
+      expect(file).toMatch(/^\d\.manifest$/);
+    });
 
     await table.migrateManifestPathsV2();
     expect(await table.usesV2ManifestPaths()).toBe(true);
 
-    readdirSync(manifestDir)
-      .filter((f) => f.endsWith(".manifest"))
-      .forEach((file) => {
-        expect(file).toMatch(/^\d{20}\.manifest$/);
-      });
+    readdirSync(manifestDir).forEach((file) => {
+      expect(file).toMatch(/^\d{20}\.manifest$/);
+    });
   });
 });
 

nodejs/__test__/otel.test.ts

@@ -1,114 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  MeterProvider,
-  type MetricData,
-  MetricReader,
-} from "@opentelemetry/sdk-metrics";
-import * as tmp from "tmp";
-import { connect, instrumentLanceDbMetrics } from "../lancedb";
-// snapshotLancedbMetrics is internal plumbing (not part of the public API), so
-// it is imported from the native module rather than the package entry point.
-import { snapshotLancedbMetrics } from "../lancedb/native";
-
-// The metrics recorder is process-global and installed once, so the whole
-// bridge is exercised in a single test to avoid cross-test global-state coupling.
-
-// A minimal pull-based reader whose `collect()` we drive directly, invoking the
-// observable-instrument callbacks. `@opentelemetry/sdk-metrics` ships no
-// in-memory reader, so we subclass the abstract base.
-class TestMetricReader extends MetricReader {
-  protected async onForceFlush(): Promise<void> {
-    // no-op: collection is driven directly via collect()
-  }
-  protected async onShutdown(): Promise<void> {
-    // no-op: nothing to release
-  }
-}
-
-async function metricsByName(
-  reader: TestMetricReader,
-): Promise<Map<string, MetricData>> {
-  const collected = await reader.collect();
-  const result = new Map<string, MetricData>();
-  for (const scope of collected.resourceMetrics.scopeMetrics) {
-    for (const metric of scope.metrics) {
-      result.set(metric.descriptor.name, metric);
-    }
-  }
-  return result;
-}
-
-describe("OpenTelemetry metrics bridge", () => {
-  let tmpDir: tmp.DirResult;
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("snapshot is safe to call regardless of install state", () => {
-    expect(Array.isArray(snapshotLancedbMetrics())).toBe(true);
-  });
-
-  it("exports object store metrics via observable instruments", async () => {
-    const reader = new TestMetricReader();
-    const provider = new MeterProvider({ readers: [reader] });
-    expect(instrumentLanceDbMetrics(provider)).toBe(true);
-
-    // Generate object store activity on the local filesystem (scheme "file").
-    const db = await connect(tmpDir.name);
-    const data = Array.from({ length: 256 }, (_, i) => ({ id: i }));
-    const table = await db.createTable("t", data);
-    expect(await table.countRows()).toBe(256);
-
-    const metrics = await metricsByName(reader);
-
-    const requests = metrics.get("lance_object_store_requests_total");
-    expect(requests).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const requestPoints = (requests!.dataPoints as any[]) ?? [];
-    expect(requestPoints.length).toBeGreaterThan(0);
-    for (const p of requestPoints) {
-      // Labelled by `operation` and `base` (the store scheme by default).
-      expect(p.attributes).toHaveProperty("base");
-      expect(p.attributes).toHaveProperty("operation");
-    }
-    const totalRequests = requestPoints.reduce((acc, p) => acc + p.value, 0);
-    expect(totalRequests).toBeGreaterThan(0);
-
-    // Histograms are decomposed into bucket / count / sum observable counters.
-    const bucket = metrics.get(
-      "lance_object_store_request_duration_seconds_bucket",
-    );
-    expect(bucket).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const bucketPoints = (bucket!.dataPoints as any[]) ?? [];
-    expect(bucketPoints.length).toBeGreaterThan(0);
-    expect(bucketPoints.every((p) => "le" in p.attributes)).toBe(true);
-    // The implicit +Inf bucket must be present.
-    expect(bucketPoints.some((p) => p.attributes.le === "+Inf")).toBe(true);
-
-    const count = metrics.get(
-      "lance_object_store_request_duration_seconds_count",
-    );
-    expect(count).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const countPoints = (count!.dataPoints as any[]) ?? [];
-    expect(countPoints.reduce((acc, p) => acc + p.value, 0)).toBeGreaterThan(0);
-
-    const sum = metrics.get("lance_object_store_request_duration_seconds_sum");
-    expect(sum).toBeDefined();
-    // biome-ignore lint/suspicious/noExplicitAny: SDK point shape
-    const sumPoints = (sum!.dataPoints as any[]) ?? [];
-    expect(sumPoints.reduce((acc, p) => acc + p.value, 0)).toBeGreaterThan(0);
-
-    // Unit handling: only `_sum` keeps the histogram's unit (seconds); `_bucket`
-    // and `_count` observe cumulative counts and are unitless.
-    expect(sum!.descriptor.unit).toBe("s");
-    expect(bucket!.descriptor.unit).toBe("");
-    expect(count!.descriptor.unit).toBe("");
-
-    await provider.shutdown();
-  });
-});

nodejs/__test__/query.test.ts

@@ -109,223 +109,3 @@ describe("Query outputSchema", () => {
     expect(schema.fields.length).toBe(3);
   });
 });
-
-describe("Query orderBy", () => {
-  let tmpDir: tmp.DirResult;
-  let table: Table;
-
-  beforeEach(async () => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    const db = await connect(tmpDir.name);
-
-    // Create table with numeric data for sorting
-    const schema = new Schema([
-      new Field("id", new Int64(), true),
-      new Field("score", new Float32(), true),
-      new Field("name", new Utf8(), true),
-    ]);
-
-    const data = makeArrowTable(
-      [
-        { id: 1n, score: 3.5, name: "charlie" },
-        { id: 2n, score: 1.2, name: "alice" },
-        { id: 3n, score: 2.8, name: "bob" },
-        { id: 4n, score: 0.5, name: "david" },
-        { id: 5n, score: 4.1, name: "eve" },
-      ],
-      { schema },
-    );
-    table = await db.createTable("test", data);
-  });
-
-  afterEach(() => {
-    tmpDir.removeCallback();
-  });
-
-  it("should sort by single column ascending", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score", ascending: true, nullsFirst: false })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify ascending order
-    expect(results[0].score).toBeCloseTo(0.5, 0.001);
-    expect(results[1].score).toBeCloseTo(1.2, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(results[3].score).toBeCloseTo(3.5, 0.001);
-    expect(results[4].score).toBeCloseTo(4.1, 0.001);
-  });
-
-  it("should sort by single column descending", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score", ascending: false, nullsFirst: false })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify descending order
-    expect(results[0].score).toBeCloseTo(4.1, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(results[3].score).toBeCloseTo(1.2, 0.001);
-    expect(results[4].score).toBeCloseTo(0.5, 0.001);
-  });
-
-  it("should use ascending as default direction", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score" })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify ascending order (default)
-    expect(results[0].score).toBeCloseTo(0.5, 0.001);
-    expect(results[1].score).toBeCloseTo(1.2, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(results[3].score).toBeCloseTo(3.5, 0.001);
-    expect(results[4].score).toBeCloseTo(4.1, 0.001);
-  });
-
-  it("should sort by string column", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "name" })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify alphabetical order
-    expect(results[0].name).toBe("alice");
-    expect(results[1].name).toBe("bob");
-    expect(results[2].name).toBe("charlie");
-    expect(results[3].name).toBe("david");
-    expect(results[4].name).toBe("eve");
-  });
-
-  it("should support method chaining with where", async () => {
-    const results = await table
-      .query()
-      .where("score > 2.0")
-      .orderBy({ columnName: "score" })
-      .toArray();
-    expect(results.length).toBe(3);
-    // Verify filtered and sorted
-    expect(results[0].score).toBeCloseTo(2.8, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(4.1, 0.001);
-  });
-
-  it("should combine repeated where clauses with AND", async () => {
-    const results = await table
-      .query()
-      .where("score > 1.0")
-      .where("score < 3.0")
-      .orderBy({ columnName: "score" })
-      .toArray();
-    // Only rows matching both predicates should be returned, rather than the
-    // second where() silently replacing the first.
-    expect(results.length).toBe(2);
-    expect(results[0].score).toBeCloseTo(1.2, 0.001);
-    expect(results[1].score).toBeCloseTo(2.8, 0.001);
-  });
-
-  it("should support method chaining with limit", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score", ascending: false })
-      .limit(3)
-      .toArray();
-
-    expect(results.length).toBe(3);
-    // Verify top 3 in descending order
-    expect(results[0].score).toBeCloseTo(4.1, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-  });
-
-  it("should support method chaining with offset", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score" })
-      .offset(2)
-      .limit(2)
-      .toArray();
-
-    expect(results.length).toBe(2);
-    // Verify results skip first 2 and take next 2
-    expect(results[0].score).toBeCloseTo(2.8, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-  });
-
-  it("should support method chaining with select", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "name" })
-      .select(["name", "score"])
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify only selected columns are present
-    expect(Object.keys(results[0])).toEqual(["name", "score"]);
-    expect(Object.keys(results[4])).toEqual(["name", "score"]);
-    // Verify sorted by name
-    expect(results[0].name).toBe("alice");
-    expect(results[4].name).toBe("eve");
-  });
-
-  it("should support complex method chaining", async () => {
-    const results = await table
-      .query()
-      .where("score > 1.0")
-      .orderBy({ columnName: "score", ascending: false })
-      .limit(3)
-      .select(["id", "score", "name"])
-      .toArray();
-
-    expect(results.length).toBe(3);
-    // Verify filtered, sorted, limited, and projected
-    expect(results[0].score).toBeCloseTo(4.1, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(Object.keys(results[0])).toEqual(["id", "score", "name"]);
-  });
-
-  it("should support multi-column ordering and null placement", async () => {
-    const schema = new Schema([
-      new Field("group", new Int64(), true),
-      new Field("score", new Float32(), true),
-      new Field("name", new Utf8(), true),
-    ]);
-
-    const data = makeArrowTable(
-      [
-        { group: 1n, score: null, name: "z" },
-        { group: 1n, score: 1.0, name: "b" },
-        { group: 1n, score: 1.0, name: "a" },
-        { group: 2n, score: 0.5, name: "c" },
-      ],
-      { schema },
-    );
-    const nullTable = await (await connect(tmpDir.name)).createTable(
-      "test_multi_order",
-      data,
-      { mode: "overwrite" },
-    );
-
-    const results = await nullTable
-      .query()
-      .orderBy([
-        { columnName: "group", ascending: true, nullsFirst: false },
-        { columnName: "score", ascending: true, nullsFirst: true },
-        { columnName: "name", ascending: true, nullsFirst: false },
-      ])
-      .toArray();
-
-    expect(results.map((r) => [r.group, r.score, r.name])).toEqual([
-      [1n, null, "z"],
-      [1n, 1.0, "a"],
-      [1n, 1.0, "b"],
-      [2n, 0.5, "c"],
-    ]);
-  });
-});

nodejs/__test__/remote.test.ts

@@ -15,7 +15,6 @@ import {
   OAuthHeaderProvider,
   StaticHeaderProvider,
 } from "../lancedb/header";
-import { Index } from "../lancedb/indices";
 
 // Test-only header providers
 class CustomProvider extends HeaderProvider {
@@ -192,200 +191,6 @@ describe("remote connection", () => {
     );
   });
 
-  it("supports version time-travel and branches on remote", async () => {
-    await withMockDatabase(
-      (req, res) => {
-        const body = req.url?.includes("/branches/list")
-          ? JSON.stringify({
-              branches: {
-                exp: { parentVersion: 1, createAt: 1, manifestSize: 1 },
-              },
-            })
-          : JSON.stringify({ name: "t", version: 2, schema: { fields: [] } });
-        res.writeHead(200, { "Content-Type": "application/json" }).end(body);
-      },
-      async (db) => {
-        // version-only (and "main" + version) time-travel the main chain
-        const v2 = await db.openTable("t", undefined, { version: 2 });
-        expect(v2.currentBranch()).toBeNull();
-        const mainV2 = await db.openTable("t", undefined, {
-          branch: "main",
-          version: 2,
-        });
-        expect(mainV2.currentBranch()).toBeNull();
-
-        // a non-main branch opens a handle scoped to that branch
-        const exp = await db.openTable("t", undefined, { branch: "exp" });
-        expect(exp.currentBranch()).toBe("exp");
-        const expV2 = await db.openTable("t", undefined, {
-          branch: "exp",
-          version: 2,
-        });
-        expect(expV2.currentBranch()).toBe("exp");
-      },
-    );
-  });
-
-  it("sends FTS options to remote tables", async () => {
-    let createIndexBody: Record<string, unknown> | undefined;
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 1,
-              schema: {
-                fields: [
-                  { name: "text", type: { type: "string" }, nullable: false },
-                ],
-              },
-            }),
-          );
-          return;
-        }
-
-        if (path.endsWith("/create_index/")) {
-          let raw = "";
-          req.on("data", (chunk) => {
-            raw += chunk;
-          });
-          req.on("end", () => {
-            createIndexBody = JSON.parse(raw);
-            res.writeHead(200).end();
-          });
-          return;
-        }
-
-        res.writeHead(404).end();
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        await table.createIndex("text", {
-          config: Index.fts({
-            blockSize: 256,
-            removeStopWords: true,
-            customStopWords: ["the"],
-          }),
-        });
-      },
-    );
-
-    expect(createIndexBody?.["column"]).toBe("text");
-    expect(createIndexBody?.["index_type"]).toBe("FTS");
-    expect(createIndexBody?.["block_size"]).toBe(256);
-    expect(createIndexBody?.["custom_stop_words"]).toEqual(["the"]);
-  });
-
-  it("diffs and merges remote branches", async () => {
-    const sampleDiff = {
-      fromBranch: "exp",
-      parentVersion: 1,
-      mainVersion: 2,
-      branchVersion: 3,
-      baseMoved: false,
-      rowCountMain: 3,
-      rowCountBranch: 3,
-      rowSummary: {
-        unchanged: 3,
-        newOnBase: 0,
-        newOnBranch: 0,
-        staleRecompute: 0,
-        inputsChanged: 0,
-        deltaAvailable: false,
-      },
-      addedColumns: [{ name: "tag", dataType: "utf8", nullable: true }],
-      removedColumns: [],
-      changedColumns: [],
-      addedIndexes: [],
-      removedIndexes: [],
-      mergeable: true,
-      mergeBlockers: [],
-    };
-    const mergeBodies: Record<string, unknown>[] = [];
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 2,
-              schema: { fields: [] },
-            }),
-          );
-          return;
-        }
-
-        let raw = "";
-        req.on("data", (chunk) => {
-          raw += chunk;
-        });
-        req.on("end", () => {
-          const body = raw ? JSON.parse(raw) : {};
-          if (path.endsWith("/branches/diff/")) {
-            // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-            expect(body).toEqual({ from_branch: "exp" });
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end(JSON.stringify(sampleDiff));
-            return;
-          }
-          if (path.endsWith("/branches/merge/")) {
-            mergeBodies.push(body);
-            const dryRun = body["dry_run"] === true;
-            const response = {
-              status: dryRun ? "ready" : "rejected",
-              diff: dryRun
-                ? sampleDiff
-                : {
-                    ...sampleDiff,
-                    mergeable: false,
-                    mergeBlockers: [
-                      { code: "baseMoved", message: "main has advanced" },
-                    ],
-                  },
-              preview: { promotedColumns: dryRun ? ["tag"] : [] },
-            };
-            res
-              .writeHead(dryRun ? 200 : 409, {
-                "Content-Type": "application/json",
-              })
-              .end(JSON.stringify(response));
-            return;
-          }
-          res.writeHead(404).end();
-        });
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        const branches = await table.branches();
-
-        await expect(branches.diff("exp")).resolves.toEqual(sampleDiff);
-
-        const rejected = await branches.merge("exp");
-        expect(rejected.status).toBe("rejected");
-        expect(rejected.diff.mergeBlockers).toEqual([
-          { code: "baseMoved", message: "main has advanced" },
-        ]);
-
-        const preview = await branches.merge("exp", true);
-        expect(preview.status).toBe("ready");
-        expect(preview.preview.promotedColumns).toEqual(["tag"]);
-      },
-    );
-
-    expect(mergeBodies).toEqual([
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      { from_branch: "exp", dry_run: false },
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      { from_branch: "exp", dry_run: true },
-    ]);
-  });
-
   describe("TlsConfig", () => {
     it("should create TlsConfig with all fields", () => {
       const tlsConfig: TlsConfig = {
@@ -812,68 +617,4 @@ describe("remote connection", () => {
       );
     });
   });
-
-  describe("renameTable", () => {
-    async function captureRenameRequest(
-      call: (db: Connection) => Promise<void>,
-    ): Promise<{ url: string; body: Record<string, unknown> }> {
-      let captured: { url: string; body: Record<string, unknown> } | undefined;
-      await withMockDatabase((req, res) => {
-        let raw = "";
-        req.on("data", (chunk) => {
-          raw += chunk;
-        });
-        req.on("end", () => {
-          captured = {
-            url: req.url ?? "",
-            body: raw ? JSON.parse(raw) : {},
-          };
-          res.writeHead(200, { "Content-Type": "application/json" }).end("");
-        });
-      }, call);
-      if (!captured) {
-        throw new Error("mock server never saw a request");
-      }
-      return captured;
-    }
-
-    it("sends rename request for a table in the root namespace", async () => {
-      const { url, body } = await captureRenameRequest(async (db) => {
-        await db.renameTable("table1", "table2");
-      });
-      expect(url).toBe("/v1/table/table1/rename/");
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      expect(body).toEqual({ new_table_name: "table2" });
-    });
-
-    it("omits new_namespace when only the current namespace is supplied", async () => {
-      // Safe-default check: passing namespacePath alone must not send
-      // `new_namespace`, so the server keeps the table in its current
-      // namespace instead of silently moving it to root.
-      const { url, body } = await captureRenameRequest(async (db) => {
-        await db.renameTable("table1", "table2", {
-          namespacePath: ["ns1"],
-        });
-      });
-      expect(url).toBe("/v1/table/ns1$table1/rename/");
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      expect(body).toEqual({ new_table_name: "table2" });
-    });
-
-    it("includes new_namespace in the body for a cross-namespace rename", async () => {
-      const { url, body } = await captureRenameRequest(async (db) => {
-        await db.renameTable("table1", "table2", {
-          namespacePath: ["ns1"],
-          newNamespacePath: ["ns2"],
-        });
-      });
-      expect(url).toBe("/v1/table/ns1$table1/rename/");
-      expect(body).toEqual({
-        // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-        new_table_name: "table2",
-        // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-        new_namespace: ["ns2"],
-      });
-    });
-  });
 });

nodejs/__test__/sanitize.test.ts

@@ -2,7 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import * as arrow from "../lancedb/arrow";
-import { sanitizeField, sanitizeMap, sanitizeType } from "../lancedb/sanitize";
+import { sanitizeField, sanitizeType } from "../lancedb/sanitize";
 
 describe("sanitize", function () {
   describe("sanitizeType function", function () {
@@ -181,15 +181,4 @@ describe("sanitize", function () {
       );
     });
   });
-
-  describe("sanitizeMap function", function () {
-    it.each([
-      ["no children", []],
-      ["two children", [{}, {}]],
-    ])("should reject a Map type with %s", function (_, children) {
-      expect(() => sanitizeMap({ children, keysSorted: false })).toThrow(
-        "Expected a Map type to have exactly one child",
-      );
-    });
-  });
 });

nodejs/__test__/scannable.test.ts

@@ -1,438 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  Field,
-  Float16,
-  Int32,
-  type RecordBatch,
-  RecordBatchReader,
-  Schema,
-  tableToIPC,
-} from "apache-arrow";
-import { makeArrowTable, makeEmptyTable } from "../lancedb/arrow";
-import { Scannable } from "../lancedb/scannable";
-
-function makeTable() {
-  return makeArrowTable(
-    [
-      { id: 1, name: "a" },
-      { id: 2, name: "b" },
-      { id: 3, name: "c" },
-    ],
-    { vectorColumns: {} },
-  );
-}
-
-async function makeReader(): Promise<RecordBatchReader> {
-  // `RecordBatchReader.from()` returns an unopened reader; `.schema` is only
-  // populated after `.open()`. Opening sync readers is synchronous.
-  const reader = RecordBatchReader.from(tableToIPC(makeTable()));
-  return reader.open() as RecordBatchReader;
-}
-
-describe("Scannable", () => {
-  describe("fromTable", () => {
-    test("reflects schema, numRows, and defaults rescannable=true", async () => {
-      const table = makeTable();
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBe(table.numRows);
-      expect(scannable.rescannable).toBe(true);
-    });
-
-    test("throws when opts.numRows does not match table.numRows", async () => {
-      await expect(
-        Scannable.fromTable(makeTable(), { numRows: 42 }),
-      ).rejects.toThrow(/does not match table\.numRows/);
-    });
-
-    test("throws when opts.rescannable is false", async () => {
-      await expect(
-        Scannable.fromTable(makeTable(), { rescannable: false }),
-      ).rejects.toThrow(/always rescannable/);
-    });
-  });
-
-  describe("fromRecordBatchReader", () => {
-    test("reflects schema and defaults numRows=null, rescannable=false", async () => {
-      const reader = await makeReader();
-      const scannable = await Scannable.fromRecordBatchReader(reader);
-
-      expect(scannable.schema).toBe(reader.schema);
-      expect(scannable.numRows).toBeNull();
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("honors numRows override", async () => {
-      const scannable = await Scannable.fromRecordBatchReader(
-        await makeReader(),
-        { numRows: 3 },
-      );
-
-      expect(scannable.numRows).toBe(3);
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("rescannable: false explicit does not throw", async () => {
-      const reader = await makeReader();
-      const scannable = await Scannable.fromRecordBatchReader(reader, {
-        rescannable: false,
-      });
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("throws when opts.rescannable is true", async () => {
-      const reader = await makeReader();
-      await expect(
-        Scannable.fromRecordBatchReader(reader, { rescannable: true }),
-      ).rejects.toThrow(/does not accept rescannable/);
-    });
-
-    test("throws when opts.rescannable is true even alongside numRows", async () => {
-      const reader = await makeReader();
-      await expect(
-        Scannable.fromRecordBatchReader(reader, {
-          numRows: 3,
-          rescannable: true,
-        }),
-      ).rejects.toThrow(/does not accept rescannable/);
-    });
-  });
-
-  describe("fromIterable", () => {
-    test("accepts a sync iterable of batches", async () => {
-      const table = makeTable();
-      const scannable = await Scannable.fromIterable(
-        table.schema,
-        table.batches,
-      );
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBeNull();
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("accepts an async iterable of batches", async () => {
-      const table = makeTable();
-      async function* generator(): AsyncGenerator<RecordBatch> {
-        for (const batch of table.batches) {
-          yield batch;
-        }
-      }
-
-      const scannable = await Scannable.fromIterable(table.schema, generator());
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    describe("rescannable: true detection", () => {
-      // Replayable inputs: [Symbol.iterator]() / [Symbol.asyncIterator]()
-      // returns a fresh iterator each call. Must NOT throw.
-
-      test("Array passes (fresh ArrayIterator each call)", async () => {
-        const table = makeTable();
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          table.batches,
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("Set passes (fresh SetIterator each call)", async () => {
-        const table = makeTable();
-        const set = new Set<RecordBatch>(table.batches);
-        const scannable = await Scannable.fromIterable(table.schema, set, {
-          rescannable: true,
-        });
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("custom Iterable returning a fresh iterator passes", async () => {
-        const table = makeTable();
-        const replayable: Iterable<RecordBatch> = {
-          [Symbol.iterator]() {
-            return table.batches[Symbol.iterator]();
-          },
-        };
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          replayable,
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("object with generator method passes (fresh generator each call)", async () => {
-        const table = makeTable();
-        const replayable: Iterable<RecordBatch> = {
-          *[Symbol.iterator]() {
-            for (const batch of table.batches) yield batch;
-          },
-        };
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          replayable,
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("empty Array passes (replayable degenerate case)", async () => {
-        const schema = makeTable().schema;
-        const scannable = await Scannable.fromIterable(
-          schema,
-          [] as RecordBatch[],
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      // One-shot inputs: [Symbol.iterator]() / [Symbol.asyncIterator]()
-      // returns the same object, or the input is already-an-iterator.
-      // Must throw with a /one-shot/ message.
-
-      test("sync generator throws", async () => {
-        const table = makeTable();
-        function* generator(): Generator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        await expect(
-          Scannable.fromIterable(table.schema, generator(), {
-            rescannable: true,
-          }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("async generator throws", async () => {
-        const table = makeTable();
-        async function* generator(): AsyncGenerator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        await expect(
-          Scannable.fromIterable(table.schema, generator(), {
-            rescannable: true,
-          }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("empty generator throws (one-shot degenerate case)", async () => {
-        const schema = makeTable().schema;
-        function* generator(): Generator<RecordBatch> {
-          // intentionally empty; yields nothing.
-        }
-        await expect(
-          Scannable.fromIterable(schema, generator(), { rescannable: true }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("custom self-iterator throws", async () => {
-        const table = makeTable();
-        const batches = table.batches;
-        let i = 0;
-        const oneShot: Iterable<RecordBatch> & Iterator<RecordBatch> = {
-          [Symbol.iterator]() {
-            return this;
-          },
-          next() {
-            if (i >= batches.length) {
-              return { done: true, value: undefined };
-            }
-            return { done: false, value: batches[i++] };
-          },
-        };
-        await expect(
-          Scannable.fromIterable(table.schema, oneShot, { rescannable: true }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("Array.values() (IterableIterator) throws", async () => {
-        const table = makeTable();
-        const iter = table.batches.values();
-        await expect(
-          Scannable.fromIterable(table.schema, iter, { rescannable: true }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("raw iterator (only `.next`) throws", async () => {
-        const table = makeTable();
-        const batches = table.batches;
-        let i = 0;
-        const rawIter = {
-          next(): IteratorResult<RecordBatch> {
-            if (i >= batches.length) {
-              return { done: true, value: undefined };
-            }
-            return { done: false, value: batches[i++] };
-          },
-        };
-        await expect(
-          Scannable.fromIterable(
-            table.schema,
-            rawIter as unknown as Iterable<RecordBatch>,
-            { rescannable: true },
-          ),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      // Edge: null/undefined must not crash the detection helper. The
-      // null check belongs to `normalizeIterator` and only fires when a
-      // scan starts.
-
-      test("null input does not crash detection at construction", async () => {
-        const schema = makeTable().schema;
-        await expect(
-          Scannable.fromIterable(
-            schema,
-            null as unknown as Iterable<RecordBatch>,
-            {
-              rescannable: true,
-            },
-          ),
-        ).resolves.toBeDefined();
-      });
-
-      test("undefined input does not crash detection at construction", async () => {
-        const schema = makeTable().schema;
-        await expect(
-          Scannable.fromIterable(
-            schema,
-            undefined as unknown as Iterable<RecordBatch>,
-            { rescannable: true },
-          ),
-        ).resolves.toBeDefined();
-      });
-
-      // Default (rescannable omitted) skips the check entirely, so even
-      // pathological inputs construct without throwing here.
-
-      test("rescannable omitted skips detection entirely (generator passes)", async () => {
-        const table = makeTable();
-        function* generator(): Generator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          generator(),
-        );
-        expect(scannable.rescannable).toBe(false);
-      });
-
-      test("rescannable: false explicit skips detection entirely (generator passes)", async () => {
-        const table = makeTable();
-        function* generator(): Generator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          generator(),
-          { rescannable: false },
-        );
-        expect(scannable.rescannable).toBe(false);
-      });
-    });
-  });
-
-  describe("fromFactory", () => {
-    test("defaults rescannable=true and does not invoke the factory eagerly", async () => {
-      const table = makeTable();
-      const factory = jest.fn(() => table.batches);
-
-      const scannable = await Scannable.fromFactory(table.schema, factory);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.rescannable).toBe(true);
-      expect(factory).not.toHaveBeenCalled();
-    });
-
-    test("honors rescannable and numRows overrides", async () => {
-      const table = makeTable();
-      const scannable = await Scannable.fromFactory(
-        table.schema,
-        () => table.batches,
-        { numRows: 7, rescannable: false },
-      );
-
-      expect(scannable.numRows).toBe(7);
-      expect(scannable.rescannable).toBe(false);
-    });
-  });
-
-  describe("validation", () => {
-    test("throws when numRows is negative", async () => {
-      await expect(
-        Scannable.fromFactory(makeTable().schema, () => [], { numRows: -1 }),
-      ).rejects.toThrow(/non-negative/);
-    });
-
-    test("throws when numRows is not an integer", async () => {
-      await expect(
-        Scannable.fromFactory(makeTable().schema, () => [], { numRows: 3.5 }),
-      ).rejects.toThrow(/integer/);
-    });
-  });
-
-  describe("native handle", () => {
-    test("exposes a native handle via inner", async () => {
-      const scannable = await Scannable.fromTable(makeTable());
-      expect(scannable.inner).toBeDefined();
-      expect(typeof scannable.inner).toBe("object");
-      expect(scannable.inner).not.toBeNull();
-    });
-  });
-
-  // Schema-variety construction tests. Each asserts that construction
-  // succeeds against a richer Arrow schema, which transitively exercises
-  // schema serialization and the Rust-side `ipc_file_to_schema` for types
-  // beyond flat primitives.
-  describe("schema variety", () => {
-    test("accepts an empty table", async () => {
-      const schema = new Schema([new Field("id", new Int32(), true)]);
-      const table = makeEmptyTable(schema);
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.numRows).toBe(0);
-      expect(scannable.schema).toBe(table.schema);
-    });
-
-    test("accepts nested struct and list columns", async () => {
-      const table = makeArrowTable(
-        [
-          { id: 1, point: { x: 0, y: 0 }, tags: ["a", "b"] },
-          { id: 2, point: { x: 1, y: 2 }, tags: ["c"] },
-        ],
-        { vectorColumns: {} },
-      );
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBe(2);
-    });
-
-    test("accepts a FixedSizeList (vector) column", async () => {
-      const table = makeArrowTable(
-        [
-          { id: 1, vec: [1, 2, 3] },
-          { id: 2, vec: [4, 5, 6] },
-        ],
-        { vectorColumns: { vec: { type: new Float16() } } },
-      );
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBe(2);
-    });
-
-    test("accepts a table with many columns", async () => {
-      const row: Record<string, number> = {};
-      for (let i = 0; i < 50; i++) row[`c${i}`] = i;
-      const table = makeArrowTable([row, row], { vectorColumns: {} });
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema.fields.length).toBe(50);
-      expect(scannable.numRows).toBe(2);
-    });
-  });
-});