chore: use lance fm index performance branch

2026-09-12 00:02:21 +00:00 · 2026-06-28 22:58:04 -07:00
75 changed files with 401 additions and 1997 deletions
@@ -1,137 +0,0 @@
 ---
 name: lancedb-branch-ops
 description: Branch management for LanceDB tables via the REST API. Use this skill whenever someone wants to create, delete, list, or switch branches on a LanceDB table — or needs to make sure a write (metadata update, index build, etc.) lands on a specific branch instead of main. Invoke it even without the word "branch" if context makes clear they want an experimental copy of a table, want to isolate changes, or want to confirm a mutation didn't touch main. Covers: branches/list, branches/create, branches/delete, and passing "branch" in describe/update_field_metadata/create_index to target a non-main version.
 ---
 ## Goal
 Manage branches on a LanceDB table: list what exists, create new ones, delete stale ones, and direct read/write operations at a specific branch without touching main.
 ## Step 0: Establish the connection
 Use the `lancedb-connect` skill to resolve the base URL and auth headers (`x-api-key`, `x-lancedb-database`). Skip this only if the connection is already known from the current conversation.
 All examples below use `{base_url}` — substitute the resolved endpoint and include the auth headers on every request.
 ## The branch model (important)
 LanceDB branches are named snapshots that diverge from the table's current state at creation time. There is **no checkout command** — you never switch the whole table to a branch. Instead, you **pass `"branch": "<name>"` in the request body** of any operation to target that branch. Omitting the key (or sending an empty body) always targets main.
 `branches/list` returns only non-main branches. Main always exists and is not listed.
 ## List branches
 ```http
 POST {base_url}/v1/table/{table_id}/branches/list
 Content-Type: application/json
 {}
 ```
 Response:
 ```json
 {
  "branches": {
    "experiment-reindex": {"parentVersion": 1, "createAt": 1782506085, "manifestSize": 1029}
  }
 }
 ```
 If `branches` is `{}`, the table has no branches besides main.
 ## Create a branch
 ```http
 POST {base_url}/v1/table/{table_id}/branches/create
 Content-Type: application/json
 {"name": "experiment-reindex"}
 ```
 HTTP 200 with `{}` body = success. The branch is created off the table's current state on main.
 Verify by calling `branches/list` and confirming the new name appears.
 ## Delete a branch
 ```http
 POST {base_url}/v1/table/{table_id}/branches/delete
 Content-Type: application/json
 {"name": "stale-2024"}
 ```
 HTTP 200 with `{}` body = success. Only the branch pointer is removed — main and all row data remain intact.
 Verify by calling `branches/list` (name gone) and `describe` with no branch param (main still responds).
 ## Operate on a specific branch
 Pass `"branch": "<name>"` in the body of any operation to scope it to that branch:
 **Read schema on a branch:**
 ```http
 POST {base_url}/v1/table/{table_id}/describe
 Content-Type: application/json
 {"branch": "wip-branch"}
 ```
 **Write metadata to a branch (not main):**
 ```http
 POST {base_url}/v1/table/{table_id}/update_field_metadata
 Content-Type: application/json
 {
  "branch": "wip-branch",
  "updates": [
    {
      "path": "category",
      "metadata": {"lancedb:description": "Product category label."},
      "replace": false
    }
  ]
 }
 ```
 **Build an index on a branch:**
 ```http
 POST {base_url}/v1/table/{table_id}/create_index
 Content-Type: application/json
 {
  "branch": "wip-branch",
  "column": "category",
  "index_type": "BTREE"
 }
 ```
 ## Verifying isolation
 After writing to a branch, always confirm the change did NOT land on main:
 ```bash
 # Should show the new metadata
 curl -s -X POST {base_url}/v1/table/{table_id}/describe \
  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
  -H "content-type: application/json" \
  -d '{"branch": "wip-branch"}'
 # Should NOT show the new metadata
 curl -s -X POST {base_url}/v1/table/{table_id}/describe \
  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
  -H "content-type: application/json" \
  -d '{}'
 ```
 ## Quick reference
 | Goal | Endpoint | Body |
 |------|----------|------|
 | List all branches | `branches/list` | `{}` |
 | Create a branch | `branches/create` | `{"name": "..."}` |
 | Delete a branch | `branches/delete` | `{"name": "..."}` |
 | Read schema on branch | `describe` | `{"branch": "..."}` |
 | Write metadata on branch | `update_field_metadata` | `{"branch": "...", "updates": [...]}` |
 | Build index on branch | `create_index` | `{"branch": "...", "column": ..., "index_type": ...}` |
 | Target main (default) | any endpoint | omit `"branch"` key |
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.5"
+current_version = "0.31.0-beta.3"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -25,7 +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
@@ -47,7 +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) }}
@@ -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
@@ -30,13 +30,13 @@ jobs:
          echo "tag = ${{ inputs.tag || 'latest' }}"
      - 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
@@ -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
@@ -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'
@@ -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: ${{ toJSON(needs) }}
@@ -36,7 +36,7 @@ jobs:
        working-directory: ./java
    steps:
      - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Set up Java 17
        uses: actions/setup-java@v4
        with:
@@ -19,7 +19,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: Check out code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Install license-header-checker
        working-directory: /tmp
        run: |
@@ -49,7 +49,7 @@ jobs:
    steps:
      - name: Output Inputs
        run: echo "${{ toJSON(github.event.inputs) }}"
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -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
@@ -86,14 +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
@@ -130,7 +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 }}
@@ -166,14 +166,14 @@ 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
      with:
        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
        # in October.
@@ -32,7 +32,7 @@ jobs:
    permissions:
      contents: write
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -170,13 +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.
@@ -190,7 +190,7 @@ jobs:
          toolchain: stable
          targets: ${{ matrix.settings.target }}
      - name: Cache cargo
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: |
            ~/.cargo/registry/index/
@@ -244,7 +244,7 @@ jobs:
        if: ${{ !matrix.settings.docker }}
        shell: bash
      - name: Upload artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v4
        with:
          name: lancedb-${{ matrix.settings.target }}
          path: nodejs/dist/*.node
@@ -256,7 +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: |
@@ -287,13 +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.
@@ -303,18 +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
@@ -339,13 +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
@@ -353,14 +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-*
@@ -398,7 +398,7 @@ 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) }}
@@ -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
@@ -126,7 +126,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -160,7 +160,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -189,7 +189,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -212,7 +212,7 @@ jobs:
        shell: bash
        working-directory: python
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -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
@@ -65,7 +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
@@ -78,7 +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
@@ -113,7 +113,7 @@ 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
@@ -152,7 +152,7 @@ jobs:
        shell: bash
        working-directory: rust
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          lfs: true
@@ -181,7 +181,7 @@ jobs:
      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
@@ -210,7 +210,7 @@ jobs:
      CC: clang-18
      CXX: clang++-18
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
        with:
          submodules: true
      - name: Install dependencies
@@ -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
@@ -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
@@ -157,9 +157,9 @@ dependencies = [
 [[package]]
 name = "anyhow"
-version = "1.0.103"
+version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2a4385e2e34eb35d6b3efe798b9eb88096925d87726c0798709bf56d9ed84af3"
+checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 [[package]]
 name = "approx"
@@ -3177,9 +3177,9 @@ dependencies = [
 [[package]]
 name = "env_filter"
-version = "2.0.0"
+version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "900d271a03799a1ee8d1ca9b19893b48ca674a9284fefcfb85f05e74ed314217"
+checksum = "32e90c2accc4b07a8456ea0debdc2e7587bdd890680d71173a15d4ae604f6eef"
 dependencies = [
 "log",
 "regex",
@@ -3187,9 +3187,9 @@ dependencies = [
 [[package]]
 name = "env_logger"
-version = "0.11.11"
+version = "0.11.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "de671bd27a75a797dc9ae289ba1e77276e75e2026408aab65185384e2d5cd3f6"
+checksum = "0621c04f2196ac3f488dd583365b9c09be011a4ab8b9f37248ffcc8f6198b56a"
 dependencies = [
 "anstream",
 "anstyle",
@@ -3423,8 +3423,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 [[package]]
 name = "fsst"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "rand 0.9.4",
@@ -4726,8 +4726,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
 [[package]]
 name = "lance"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4801,8 +4801,8 @@ dependencies = [
 [[package]]
 name = "lance-arrow"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4823,7 +4823,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4837,7 +4837,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4846,8 +4846,8 @@ dependencies = [
 [[package]]
 name = "lance-bitpacking"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4857,8 +4857,8 @@ dependencies = [
 [[package]]
 name = "lance-core"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4896,8 +4896,8 @@ dependencies = [
 [[package]]
 name = "lance-datafusion"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4927,8 +4927,8 @@ dependencies = [
 [[package]]
 name = "lance-datagen"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4945,8 +4945,8 @@ dependencies = [
 [[package]]
 name = "lance-derive"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -4955,8 +4955,8 @@ dependencies = [
 [[package]]
 name = "lance-encoding"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4991,8 +4991,8 @@ dependencies = [
 [[package]]
 name = "lance-file"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5022,8 +5022,8 @@ dependencies = [
 [[package]]
 name = "lance-index"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5088,8 +5088,8 @@ dependencies = [
 [[package]]
 name = "lance-io"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -5130,8 +5130,8 @@ dependencies = [
 [[package]]
 name = "lance-linalg"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5147,8 +5147,8 @@ dependencies = [
 [[package]]
 name = "lance-namespace"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5160,8 +5160,8 @@ dependencies = [
 [[package]]
 name = "lance-namespace-impls"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5215,8 +5215,8 @@ dependencies = [
 [[package]]
 name = "lance-select"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5231,8 +5231,8 @@ dependencies = [
 [[package]]
 name = "lance-table"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5271,8 +5271,8 @@ dependencies = [
 [[package]]
 name = "lance-testing"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5285,8 +5285,8 @@ dependencies = [
 [[package]]
 name = "lance-tokenizer"
-version = "9.0.0-beta.10"
+version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
+source = "git+https://github.com/jackye1995/lance.git?branch=jack%2Ffix-fmindex-query-performance#0a43448b3d8a15b9f76a87dace50d30cb3e7b797"
 dependencies = [
 "icu_segmenter",
 "jieba-rs",
@@ -5299,13 +5299,12 @@ dependencies = [
 [[package]]
 name = "lancedb"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.3"
 dependencies = [
 "ahash",
 "anyhow",
 "arrow",
 "arrow-array",
 "arrow-buffer",
 "arrow-cast",
 "arrow-data",
 "arrow-ipc",
@@ -5384,7 +5383,7 @@ dependencies = [
 [[package]]
 name = "lancedb-nodejs"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.3"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5409,7 +5408,7 @@ dependencies = [
 [[package]]
 name = "lancedb-python"
-version = "0.34.0-beta.5"
+version = "0.34.0-beta.3"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5642,9 +5641,9 @@ dependencies = [
 [[package]]
 name = "log"
-version = "0.4.33"
+version = "0.4.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
+checksum = "953f07c43838f8e6f9758cab68bf5bed85465e7587ebe0b823f1bcd81978ad3a"
 [[package]]
 name = "loom"
@@ -5952,9 +5951,9 @@ dependencies = [
 [[package]]
 name = "napi"
-version = "3.9.4"
+version = "3.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b41bda2ac390efb5e8d22025d925ccc3f3807d8c1bea6d19b36127247c4b8f83"
+checksum = "fbd9f9295f3ff5921e78a71222c3361a8216f7760b1a99a6ad4e8441de18bbb9"
 dependencies = [
 "bitflags 2.11.1",
 "chrono",
@@ -5977,9 +5976,9 @@ checksum = "c9c366d2c8c60b86fa632df75f745509b52f9128f91a6bad4c796e44abb505e1"
 [[package]]
 name = "napi-derive"
-version = "3.5.7"
+version = "3.5.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "61d66f70256ad5aef58659966064471d0ad90e2897bc36a5a5e0389c85aabc1e"
+checksum = "89b3f766e04667e6da0e181e2da4f85475d5a6513b7cf6a80bea184e224a5b42"
 dependencies = [
 "convert_case",
 "ctor 1.0.5",
@@ -5991,9 +5990,9 @@ dependencies = [
 [[package]]
 name = "napi-derive-backend"
-version = "5.0.5"
+version = "5.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "81b4b08f15eed7a2a20c3f4c6314013fc3ac890a3afa9892b594485299ebdb2d"
+checksum = "0d5af30503edf933ce7377cf6d4c877a62b0f1107ea05585f1b5e430e88d5baf"
 dependencies = [
 "convert_case",
 "proc-macro2",
@@ -10121,9 +10120,9 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 [[package]]
 name = "uuid"
-version = "1.23.4"
+version = "1.23.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf80a72845275afea99e7f2b434723d3bc7e38470fcd1c7ed39a599c73319a53"
+checksum = "144d6b123cef80b301b8f72a9e2ca4370ddec21950d0a103dd22c437006d2db7"
 dependencies = [
 "getrandom 0.4.2",
 "js-sys",
@@ -13,25 +13,24 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 [workspace.dependencies]
-lance = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=9.0.0-beta.8", default-features = false, "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-core = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-datagen = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-file = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-io = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=9.0.0-beta.8", default-features = false, "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-index = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-linalg = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-namespace = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-namespace-impls = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=9.0.0-beta.8", default-features = false, "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-table = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-testing = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-datafusion = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-encoding = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/lance.git" }
-lance-arrow = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=9.0.0-beta.8", "branch" = "jack/fix-fmindex-query-performance", "git" = "https://github.com/jackye1995/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"
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.31.0-beta.5</version>
+    <version>0.31.0-beta.3</version>
 </dependency>
 ```
@@ -518,9 +518,6 @@ 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
@@ -767,9 +767,6 @@ 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
@@ -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).
@@ -12,7 +12,6 @@
 ## Enumerations
 - [FullTextQueryType](enumerations/FullTextQueryType.md)
 - [OAuthFlowType](enumerations/OAuthFlowType.md)
 - [Occur](enumerations/Occur.md)
 - [Operator](enumerations/Operator.md)
@@ -86,8 +85,6 @@
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.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)
@@ -64,19 +64,6 @@ 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
@@ -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"]`
@@ -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"]`
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.31.0-beta.5</version>
+      <version>0.31.0-beta.3</version>
      <relativePath>../pom.xml</relativePath>
    </parent>
@@ -6,7 +6,7 @@
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.31.0-beta.5</version>
+    <version>0.31.0-beta.3</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>9.0.0-beta.10</lance-core.version>
+        <lance-core.version>9.0.0-beta.8</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>
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.3"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -215,20 +215,6 @@ describe("Query orderBy", () => {
    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()
@@ -52,7 +52,6 @@ export {
  SplitHashOptions,
  SplitSequentialOptions,
  ShuffleOptions,
  OAuthConfig as NativeOAuthConfig,
 } from "./native.js";
 export {
@@ -131,8 +130,6 @@ export {
  TokenResponse,
 } from "./header";
 export { OAuthConfig, OAuthFlowType } from "./oauth";
 export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 export * as embedding from "./embedding";
@@ -1,76 +0,0 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 /**
 * OAuth authentication flow types.
 */
 export enum OAuthFlowType {
  /** Client Credentials grant (service-to-service / M2M). */
  ClientCredentials = "client_credentials",
  /** Azure Managed Identity via IMDS. */
  AzureManagedIdentity = "azure_managed_identity",
 }
 /**
 * 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.
 *
 * @example Client Credentials (service-to-service):
 * ```typescript
 * const config: OAuthConfig = {
 *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
 *   clientId: "app-id",
 *   clientSecret: "secret",
 *   scopes: ["api://lancedb-api/.default"],
 * };
 * ```
 *
 * @example Azure Managed Identity:
 * ```typescript
 * const config: OAuthConfig = {
 *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
 *   clientId: "app-id",
 *   scopes: ["api://lancedb-api/.default"],
 *   flow: OAuthFlowType.AzureManagedIdentity,
 * };
 * ```
 */
 export interface OAuthConfig {
  /**
   * OIDC issuer URL or OAuth authority URL.
   * For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
   */
  issuerUrl: string;
  /** Application / Client ID. */
  clientId: string;
  /**
   * OAuth scopes to request.
   * For Azure managed identity, exactly one scope or resource is required.
   * For example: `["api://{app_id}/.default"]`
   */
  scopes: string[];
  /** Authentication flow (default: ClientCredentials). */
  flow?: OAuthFlowType;
  /** Client secret (required for ClientCredentials). */
  clientSecret?: string;
  /** Client ID for user-assigned managed identity (AzureManagedIdentity). */
  managedIdentityClientId?: string;
  /**
   * Seconds before expiry to trigger proactive refresh (default: 300).
   * Keep this well below the token TTL; if it is greater than or equal to
   * the TTL, each request refreshes the token.
   */
  refreshBufferSecs?: number;
 }
@@ -362,9 +362,6 @@ export class StandardQueryBase<
   *
   * 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.
   */
  where(predicate: string): this {
    this.doCall((inner: NativeQueryType) => inner.onlyIf(predicate));
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.3",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.31.0-beta.5",
+  "version": "0.31.0-beta.3",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.31.0-beta.5",
+	"version": "0.31.0-beta.3",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.31.0-beta.5",
+  "version": "0.31.0-beta.3",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.31.0-beta.5",
+      "version": "0.31.0-beta.3",
      "cpu": [
        "x64",
        "arm64"
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.31.0-beta.5",
+  "version": "0.31.0-beta.3",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -112,12 +112,6 @@ impl Connection {
        builder = builder.client_config(rust_config);
        if let Some(oauth_config) = options.oauth_config {
            let config: lancedb::remote::oauth::OAuthConfig =
                oauth_config.try_into().default_error()?;
            builder = builder.oauth_config(config);
        }
        if let Some(api_key) = options.api_key {
            builder = builder.api_key(&api_key);
        }
@@ -65,11 +65,6 @@ pub struct ConnectionOptions {
    /// (For LanceDB cloud only): the host to use for LanceDB cloud. Used
    /// for testing purposes.
    pub host_override: Option<String>,
    /// (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`.
    pub oauth_config: Option<remote::OAuthConfig>,
 }
 #[napi(object)]
@@ -3,7 +3,7 @@
 use std::time::Duration;
-use lancedb::{ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
+use lancedb::{arrow::IntoArrow, ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
@@ -66,9 +66,11 @@ impl NativeMergeInsertBuilder {
    #[napi(catch_unwind)]
    pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
-        let data = ipc_file_to_batches(buf.to_vec()).map_err(|e| {
+        let data = ipc_file_to_batches(buf.to_vec())
-            napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
+            .and_then(IntoArrow::into_arrow)
-        })?;
+            .map_err(|e| {
                napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
            })?;
        let this = self.clone();
@@ -3,7 +3,6 @@
 use std::collections::HashMap;
 use lancedb::error::Error;
 use napi_derive::*;
 /// Timeout configuration for remote HTTP client.
@@ -141,84 +140,6 @@ impl From<TlsConfig> for lancedb::remote::TlsConfig {
    }
 }
 /// 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.
 #[napi(object)]
 #[derive(Clone)]
 pub struct OAuthConfig {
    /// OIDC issuer URL or OAuth authority URL.
    /// For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
    pub issuer_url: String,
    /// Application / Client ID.
    pub client_id: String,
    /// OAuth scopes to request. For Azure managed identity, exactly one scope
    /// or resource is required. For example: `["api://{app_id}/.default"]`
    pub scopes: Vec<String>,
    /// Authentication flow: "client_credentials" or "azure_managed_identity"
    pub flow: Option<String>,
    /// Client secret (required for client_credentials).
    pub client_secret: Option<String>,
    /// Client ID for user-assigned managed identity (azure_managed_identity).
    pub managed_identity_client_id: Option<String>,
    /// Seconds before expiry to trigger proactive refresh (default: 300).
    /// Keep this well below the token TTL; if it is greater than or equal to
    /// the TTL, each request refreshes the token.
    pub refresh_buffer_secs: Option<u32>,
 }
 impl std::fmt::Debug for OAuthConfig {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        f.debug_struct("OAuthConfig")
            .field("issuer_url", &self.issuer_url)
            .field("client_id", &self.client_id)
            .field("scopes", &self.scopes)
            .field("flow", &self.flow)
            .field(
                "client_secret",
                &self.client_secret.as_deref().map(|_| "<redacted>"),
            )
            .field(
                "managed_identity_client_id",
                &self.managed_identity_client_id,
            )
            .field("refresh_buffer_secs", &self.refresh_buffer_secs)
            .finish()
    }
 }
 impl TryFrom<OAuthConfig> for lancedb::remote::oauth::OAuthConfig {
    type Error = Error;
    fn try_from(config: OAuthConfig) -> Result<Self, Self::Error> {
        use lancedb::remote::oauth::OAuthFlow;
        let flow = match config.flow.as_deref().unwrap_or("client_credentials") {
            "client_credentials" => OAuthFlow::ClientCredentials,
            "azure_managed_identity" => OAuthFlow::AzureManagedIdentity {
                client_id: config.managed_identity_client_id,
            },
            other => {
                return Err(Error::InvalidInput {
                    message: format!("Unknown OAuth flow type: {other}"),
                });
            }
        };
        Ok(Self {
            issuer_url: config.issuer_url,
            client_id: config.client_id,
            client_secret: config.client_secret,
            scopes: config.scopes,
            flow,
            refresh_buffer_secs: config.refresh_buffer_secs.map(|v| v as u64),
        })
    }
 }
 impl From<ClientConfig> for lancedb::remote::ClientConfig {
    fn from(config: ClientConfig) -> Self {
        Self {
@@ -235,45 +156,3 @@ impl From<ClientConfig> for lancedb::remote::ClientConfig {
        }
    }
 }
 #[cfg(test)]
 mod tests {
    use super::*;
    #[test]
    fn test_unknown_oauth_flow_returns_invalid_input() {
        let config = OAuthConfig {
            issuer_url: "https://issuer.example.com".to_string(),
            client_id: "client-id".to_string(),
            scopes: vec!["scope".to_string()],
            flow: Some("typo".to_string()),
            client_secret: None,
            managed_identity_client_id: None,
            refresh_buffer_secs: None,
        };
        let err = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap_err();
        assert!(matches!(
            err,
            Error::InvalidInput { message }
                if message == "Unknown OAuth flow type: typo"
        ));
    }
    #[test]
    fn test_oauth_config_debug_redacts_client_secret() {
        let config = OAuthConfig {
            issuer_url: "https://issuer.example.com".to_string(),
            client_id: "client-id".to_string(),
            scopes: vec!["scope".to_string()],
            flow: Some("client_credentials".to_string()),
            client_secret: Some("super-secret".to_string()),
            managed_identity_client_id: None,
            refresh_buffer_secs: None,
        };
        let debug = format!("{config:?}");
        assert!(!debug.contains("super-secret"));
        assert!(debug.contains("client_secret: Some(\"<redacted>\")"));
    }
 }
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.34.0-beta.6"
+current_version = "0.34.0-beta.3"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.34.0-beta.6"
+version = "0.34.0-beta.3"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -89,8 +89,6 @@ def connect(
        If presented, connect to LanceDB cloud.
        Otherwise, connect to a database on file system or cloud storage.
        Can be set via environment variable `LANCEDB_API_KEY`.
        OAuth configuration is currently supported only by ``connect_async``;
        synchronous LanceDB Cloud connections require an API key.
    region: str, default "us-east-1"
        The region to use for LanceDB Cloud.
    host_override: str, optional
@@ -342,7 +340,6 @@ async def connect_async(
    session: Optional[Session] = None,
    manifest_enabled: bool = False,
    namespace_client_properties: Optional[Dict[str, str]] = None,
    oauth_config=None,
 ) -> AsyncConnection:
    """Connect to a LanceDB database.
@@ -392,10 +389,6 @@ async def connect_async(
    namespace_client_properties : dict, optional
        Additional directory namespace client properties to use with
        ``manifest_enabled=True``.
    oauth_config : OAuthConfig, optional
        OAuth configuration for LanceDB Cloud/Enterprise. This is supported by
        ``connect_async`` only; synchronous ``connect`` uses API key
        authentication for ``db://`` URIs.
    Examples
    --------
@@ -442,7 +435,6 @@ async def connect_async(
            session,
            manifest_enabled,
            namespace_client_properties,
            oauth_config,
        )
    )
@@ -280,24 +280,6 @@ async def connect(
    session: Optional[Session],
    manifest_enabled: bool = False,
    namespace_client_properties: Optional[Dict[str, str]] = None,
    oauth_config: Optional[Any] = None,
 ) -> Connection: ...
 def connect_namespace(
    namespace_client_impl: str,
    namespace_client_properties: Dict[str, str],
    read_consistency_interval: Optional[float] = None,
    storage_options: Optional[Dict[str, str]] = None,
    session: Optional[Session] = None,
    namespace_client_pushdown_operations: Optional[List[str]] = None,
 ) -> Connection: ...
 def connect_namespace_client(
    namespace_client: Any,
    read_consistency_interval: Optional[float] = None,
    storage_options: Optional[Dict[str, str]] = None,
    session: Optional[Session] = None,
    namespace_client_pushdown_operations: Optional[List[str]] = None,
    namespace_client_impl: Optional[str] = None,
    namespace_client_properties: Optional[Dict[str, str]] = None,
 ) -> Connection: ...
 class RecordBatchStream:
@@ -51,15 +51,6 @@ class LanceMergeInsertBuilder(object):
        If there are multiple matches then the behavior is undefined.
        Currently this causes multiple copies of the row to be created
        but that behavior is subject to change.
        Parameters
        ----------
        where: Optional[str], default None
            An optional filter to limit which rows are updated. Column
            references in this expression must be prefixed with "target."
            to refer to the existing table data. For example, to only
            update rows where the existing color is red, use:
            ``where="target.color = 'red'"``
        """
        self._when_matched_update_all = True
        self._when_matched_update_all_condition = where
@@ -38,13 +38,15 @@ from lance_namespace_urllib3_client.models.query_table_request_vector import (
    QueryTableRequestVector,
 )
 from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
-from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
+from lance_namespace.errors import TableNotFoundError
-from lancedb._lancedb import (
+from lancedb._lancedb import connect_namespace_client as _connect_namespace_client
    connect_namespace as _connect_namespace,
    connect_namespace_client as _connect_namespace_client,
 )
 from lancedb.background_loop import LOOP
 from lancedb.db import AsyncConnection, DBConnection
 from lancedb.namespace_utils import (
    _normalize_create_namespace_mode,
    _normalize_drop_namespace_mode,
    _normalize_drop_namespace_behavior,
 )
 from lance_namespace import (
    LanceNamespace,
    connect as namespace_connect,
@@ -53,6 +55,13 @@ from lance_namespace import (
    DropNamespaceResponse,
    ListNamespacesResponse,
    ListTablesResponse,
    ListTablesRequest,
    DescribeNamespaceRequest,
    DropTableRequest,
    RenameTableRequest,
    ListNamespacesRequest,
    CreateNamespaceRequest,
    DropNamespaceRequest,
 )
 from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
@@ -377,10 +386,6 @@ def _builds_namespace_natively(
    return namespace_client_impl == "rest" and bool(namespace_client_properties)
 def _supports_native_namespace(namespace_client_impl: str) -> bool:
    return namespace_client_impl in {"dir", "rest"}
 class LanceNamespaceDBConnection(DBConnection):
    """
    A LanceDB connection that uses a namespace for table management.
@@ -391,7 +396,7 @@ class LanceNamespaceDBConnection(DBConnection):
    def __init__(
        self,
-        namespace_client: Optional[LanceNamespace] = None,
+        namespace_client: LanceNamespace,
        *,
        read_consistency_interval: Optional[timedelta] = None,
        storage_options: Optional[Dict[str, str]] = None,
@@ -399,7 +404,6 @@ class LanceNamespaceDBConnection(DBConnection):
        namespace_client_pushdown_operations: Optional[List[str]] = None,
        namespace_client_impl: Optional[str] = None,
        namespace_client_properties: Optional[Dict[str, str]] = None,
        _inner: Optional[AsyncConnection] = None,
    ):
        """
        Initialize a namespace-based LanceDB connection.
@@ -441,36 +445,30 @@ class LanceNamespaceDBConnection(DBConnection):
        )
        self._namespace_client_impl = namespace_client_impl
        self._namespace_client_properties = namespace_client_properties
-        # When the namespace connection or client is built natively in Rust, the
+        # When the namespace client is built natively (see Rust
-        # underlying Rust table performs QueryTable pushdown through the
+        # ``build_namespace_natively``), the underlying Rust table performs
-        # read-freshness context provider, which the pure-Python ``query_table``
+        # QueryTable pushdown through the read-freshness context provider, which
-        # path bypasses.
+        # the pure-Python ``query_table`` path bypasses.
-        self._route_pushdown_to_rust = _inner is not None or _builds_namespace_natively(
+        self._route_pushdown_to_rust = _builds_namespace_natively(
            namespace_client_impl, namespace_client_properties
        )
-        if _inner is not None:
+        self._inner = AsyncConnection(
-            self._inner = _inner
+            _connect_namespace_client(
-        else:
+                namespace_client,
-            if namespace_client is None:
+                read_consistency_interval=(
-                raise ValueError("namespace_client is required without a native _inner")
+                    read_consistency_interval.total_seconds()
-            self._inner = AsyncConnection(
+                    if read_consistency_interval is not None
-                _connect_namespace_client(
+                    else None
-                    namespace_client,
+                ),
-                    read_consistency_interval=(
+                storage_options=self.storage_options or None,
-                        read_consistency_interval.total_seconds()
+                session=session,
-                        if read_consistency_interval is not None
+                namespace_client_pushdown_operations=(
-                        else None
+                    list(self._namespace_client_pushdown_operations)
-                    ),
+                ),
-                    storage_options=self.storage_options or None,
+                namespace_client_impl=namespace_client_impl,
-                    session=session,
+                namespace_client_properties=namespace_client_properties,
                    namespace_client_pushdown_operations=(
                        list(self._namespace_client_pushdown_operations)
                    ),
                    namespace_client_impl=namespace_client_impl,
                    namespace_client_properties=namespace_client_properties,
                )
            )
-        self._uri = self._inner.uri
+        )
    @override
    def serialize(self) -> str:
@@ -516,11 +514,11 @@ class LanceNamespaceDBConnection(DBConnection):
        )
        if namespace_path is None:
            namespace_path = []
-        return LOOP.run(
+        request = ListTablesRequest(
-            self._inner.table_names(
+            id=namespace_path, page_token=page_token, limit=limit
                namespace_path=namespace_path, start_after=page_token, limit=limit
            )
        )
        response = self._namespace_client.list_tables(request)
        return response.tables if response.tables else []
    @override
    def create_table(
@@ -591,8 +589,8 @@ class LanceNamespaceDBConnection(DBConnection):
                    index_cache_size=index_cache_size,
                )
            )
-        except (RuntimeError, ValueError) as e:
+        except RuntimeError as e:
-            if "Table not found" in str(e) or "was not found" in str(e):
+            if "Table not found" in str(e):
                table_id = namespace_path + [name]
                raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
            raise
@@ -614,9 +612,12 @@ class LanceNamespaceDBConnection(DBConnection):
    @override
    def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):
        # Use namespace drop_table directly
        if namespace_path is None:
            namespace_path = []
-        LOOP.run(self._inner.drop_table(name, namespace_path=namespace_path))
+        table_id = namespace_path + [name]
        request = DropTableRequest(id=table_id)
        self._namespace_client.drop_table(request)
    @override
    def rename_table(
@@ -630,19 +631,14 @@ class LanceNamespaceDBConnection(DBConnection):
            cur_namespace_path = []
        if new_namespace_path is None:
            new_namespace_path = []
-        try:
+        cur_table_id = cur_namespace_path + [cur_name]
-            LOOP.run(
+        new_namespace_id = new_namespace_path if new_namespace_path else None
-                self._inner.rename_table(
+        request = RenameTableRequest(
-                    cur_name,
+            id=cur_table_id,
-                    new_name,
+            new_table_name=new_name,
-                    cur_namespace_path=cur_namespace_path,
+            new_namespace_id=new_namespace_id,
-                    new_namespace_path=new_namespace_path,
+        )
-                )
+        self._namespace_client.rename_table(request)
            )
        except RuntimeError as e:
            if "rename_table not implemented" in str(e):
                raise NotImplementedError("rename_table not implemented") from e
            raise
    @override
    def drop_database(self):
@@ -654,7 +650,8 @@ class LanceNamespaceDBConnection(DBConnection):
    def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
        if namespace_path is None:
            namespace_path = []
-        LOOP.run(self._inner.drop_all_tables(namespace_path=namespace_path))
+        for table_name in self.table_names(namespace_path=namespace_path):
            self.drop_table(table_name, namespace_path=namespace_path)
    @override
    def list_namespaces(
@@ -684,10 +681,13 @@ class LanceNamespaceDBConnection(DBConnection):
        """
        if namespace_path is None:
            namespace_path = []
-        return LOOP.run(
+        request = ListNamespacesRequest(
-            self._inner.list_namespaces(
+            id=namespace_path, page_token=page_token, limit=limit
-                namespace_path=namespace_path, page_token=page_token, limit=limit
+        )
-            )
+        response = self._namespace_client.list_namespaces(request)
        return ListNamespacesResponse(
            namespaces=response.namespaces if response.namespaces else [],
            page_token=response.page_token,
        )
    @override
@@ -715,12 +715,14 @@ class LanceNamespaceDBConnection(DBConnection):
        CreateNamespaceResponse
            Response containing the properties of the created namespace.
        """
-        return LOOP.run(
+        request = CreateNamespaceRequest(
-            self._inner.create_namespace(
+            id=namespace_path,
-                namespace_path=namespace_path,
+            mode=_normalize_create_namespace_mode(mode),
-                mode=mode,
+            properties=properties,
-                properties=properties,
+        )
-            )
+        response = self._namespace_client.create_namespace(request)
        return CreateNamespaceResponse(
            properties=response.properties if hasattr(response, "properties") else None
        )
    @override
@@ -748,18 +750,20 @@ class LanceNamespaceDBConnection(DBConnection):
        DropNamespaceResponse
            Response containing properties and transaction_id if applicable.
        """
-        try:
+        request = DropNamespaceRequest(
-            return LOOP.run(
+            id=namespace_path,
-                self._inner.drop_namespace(
+            mode=_normalize_drop_namespace_mode(mode),
-                    namespace_path=namespace_path,
+            behavior=_normalize_drop_namespace_behavior(behavior),
-                    mode=mode,
+        )
-                    behavior=behavior,
+        response = self._namespace_client.drop_namespace(request)
-                )
+        return DropNamespaceResponse(
-            )
+            properties=(
-        except RuntimeError as e:
+                response.properties if hasattr(response, "properties") else None
-            if "Namespace not empty" in str(e):
+            ),
-                raise NamespaceNotEmptyError(str(e)) from e
+            transaction_id=(
-            raise
+                response.transaction_id if hasattr(response, "transaction_id") else None
            ),
        )
    @override
    def describe_namespace(
@@ -778,7 +782,11 @@ class LanceNamespaceDBConnection(DBConnection):
        DescribeNamespaceResponse
            Response containing the namespace properties.
        """
-        return LOOP.run(self._inner.describe_namespace(namespace_path))
+        request = DescribeNamespaceRequest(id=namespace_path)
        response = self._namespace_client.describe_namespace(request)
        return DescribeNamespaceResponse(
            properties=response.properties if hasattr(response, "properties") else None
        )
    @override
    def list_tables(
@@ -808,10 +816,13 @@ class LanceNamespaceDBConnection(DBConnection):
        """
        if namespace_path is None:
            namespace_path = []
-        return LOOP.run(
+        request = ListTablesRequest(
-            self._inner.list_tables(
+            id=namespace_path, page_token=page_token, limit=limit
-                namespace_path=namespace_path, page_token=page_token, limit=limit
+        )
-            )
+        response = self._namespace_client.list_tables(request)
        return ListTablesResponse(
            tables=response.tables if response.tables else [],
            page_token=response.page_token,
        )
    def _lance_table_from_uri(
@@ -867,18 +878,6 @@ class LanceNamespaceDBConnection(DBConnection):
        LanceNamespace
            The namespace client for this connection.
        """
        if self._namespace_client is None:
            if (
                self._namespace_client_impl is None
                or self._namespace_client_properties is None
            ):
                raise ValueError(
                    "Cannot construct a Python namespace client without "
                    "namespace implementation properties"
                )
            self._namespace_client = namespace_connect(
                self._namespace_client_impl, self._namespace_client_properties
            )
        return self._namespace_client
@@ -892,7 +891,7 @@ class AsyncLanceNamespaceDBConnection:
    def __init__(
        self,
-        namespace_client: Optional[LanceNamespace] = None,
+        namespace_client: LanceNamespace,
        *,
        read_consistency_interval: Optional[timedelta] = None,
        storage_options: Optional[Dict[str, str]] = None,
@@ -900,7 +899,6 @@ class AsyncLanceNamespaceDBConnection:
        namespace_client_pushdown_operations: Optional[List[str]] = None,
        namespace_client_impl: Optional[str] = None,
        namespace_client_properties: Optional[Dict[str, str]] = None,
        _inner: Optional[AsyncConnection] = None,
    ):
        """
        Initialize an async namespace-based LanceDB connection.
@@ -942,35 +940,29 @@ class AsyncLanceNamespaceDBConnection:
        )
        self._namespace_client_impl = namespace_client_impl
        self._namespace_client_properties = namespace_client_properties
-        # See LanceNamespaceDBConnection: when Rust owns the namespace
+        # See LanceNamespaceDBConnection: when built natively the Rust table runs
-        # connection/client, its table performs QueryTable pushdown through the
+        # QueryTable pushdown through the read-freshness provider, so defer to it
-        # read-freshness provider, so defer to it rather than the urllib3 client
+        # rather than the urllib3 client (which omits x-lancedb-min-timestamp).
-        # path (which omits x-lancedb-min-timestamp).
+        self._route_pushdown_to_rust = _builds_namespace_natively(
        self._route_pushdown_to_rust = _inner is not None or _builds_namespace_natively(
            namespace_client_impl, namespace_client_properties
        )
-        if _inner is not None:
+        self._inner = AsyncConnection(
-            self._inner = _inner
+            _connect_namespace_client(
-        else:
+                namespace_client,
-            if namespace_client is None:
+                read_consistency_interval=(
-                raise ValueError("namespace_client is required without a native _inner")
+                    read_consistency_interval.total_seconds()
-            self._inner = AsyncConnection(
+                    if read_consistency_interval is not None
-                _connect_namespace_client(
+                    else None
-                    namespace_client,
+                ),
-                    read_consistency_interval=(
+                storage_options=self.storage_options or None,
-                        read_consistency_interval.total_seconds()
+                session=session,
-                        if read_consistency_interval is not None
+                namespace_client_pushdown_operations=(
-                        else None
+                    list(self._namespace_client_pushdown_operations)
-                    ),
+                ),
-                    storage_options=self.storage_options or None,
+                namespace_client_impl=namespace_client_impl,
-                    session=session,
+                namespace_client_properties=namespace_client_properties,
                    namespace_client_pushdown_operations=(
                        list(self._namespace_client_pushdown_operations)
                    ),
                    namespace_client_impl=namespace_client_impl,
                    namespace_client_properties=namespace_client_properties,
                )
            )
        )
    async def table_names(
        self,
@@ -994,9 +986,11 @@ class AsyncLanceNamespaceDBConnection:
        )
        if namespace_path is None:
            namespace_path = []
-        return await self._inner.table_names(
+        request = ListTablesRequest(
-            namespace_path=namespace_path, start_after=page_token, limit=limit
+            id=namespace_path, page_token=page_token, limit=limit
        )
        response = self._namespace_client.list_tables(request)
        return response.tables if response.tables else []
    async def create_table(
        self,
@@ -1059,8 +1053,8 @@ class AsyncLanceNamespaceDBConnection:
                storage_options=storage_options,
                index_cache_size=index_cache_size,
            )
-        except (RuntimeError, ValueError) as e:
+        except RuntimeError as e:
-            if "Table not found" in str(e) or "was not found" in str(e):
+            if "Table not found" in str(e):
                table_id = namespace_path + [name]
                raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
            raise
@@ -1081,7 +1075,9 @@ class AsyncLanceNamespaceDBConnection:
        """Drop a table from the namespace."""
        if namespace_path is None:
            namespace_path = []
-        await self._inner.drop_table(name, namespace_path=namespace_path)
+        table_id = namespace_path + [name]
        request = DropTableRequest(id=table_id)
        self._namespace_client.drop_table(request)
    async def rename_table(
        self,
@@ -1095,17 +1091,14 @@ class AsyncLanceNamespaceDBConnection:
            cur_namespace_path = []
        if new_namespace_path is None:
            new_namespace_path = []
-        try:
+        cur_table_id = cur_namespace_path + [cur_name]
-            await self._inner.rename_table(
+        new_namespace_id = new_namespace_path if new_namespace_path else None
-                cur_name,
+        request = RenameTableRequest(
-                new_name,
+            id=cur_table_id,
-                cur_namespace_path=cur_namespace_path,
+            new_table_name=new_name,
-                new_namespace_path=new_namespace_path,
+            new_namespace_id=new_namespace_id,
-            )
+        )
-        except RuntimeError as e:
+        self._namespace_client.rename_table(request)
            if "rename_table not implemented" in str(e):
                raise NotImplementedError("rename_table not implemented") from e
            raise
    async def drop_database(self):
        """Deprecated method."""
@@ -1117,7 +1110,9 @@ class AsyncLanceNamespaceDBConnection:
        """Drop all tables in the namespace."""
        if namespace_path is None:
            namespace_path = []
-        await self._inner.drop_all_tables(namespace_path=namespace_path)
+        table_names = await self.table_names(namespace_path=namespace_path)
        for table_name in table_names:
            await self.drop_table(table_name, namespace_path=namespace_path)
    async def list_namespaces(
        self,
@@ -1146,8 +1141,13 @@ class AsyncLanceNamespaceDBConnection:
        """
        if namespace_path is None:
            namespace_path = []
-        return await self._inner.list_namespaces(
+        request = ListNamespacesRequest(
-            namespace_path=namespace_path, page_token=page_token, limit=limit
+            id=namespace_path, page_token=page_token, limit=limit
        )
        response = self._namespace_client.list_namespaces(request)
        return ListNamespacesResponse(
            namespaces=response.namespaces if response.namespaces else [],
            page_token=response.page_token,
        )
    async def create_namespace(
@@ -1174,11 +1174,15 @@ class AsyncLanceNamespaceDBConnection:
        CreateNamespaceResponse
            Response containing the properties of the created namespace.
        """
-        return await self._inner.create_namespace(
+        request = CreateNamespaceRequest(
-            namespace_path=namespace_path,
+            id=namespace_path,
-            mode=mode,
+            mode=_normalize_create_namespace_mode(mode),
            properties=properties,
        )
        response = self._namespace_client.create_namespace(request)
        return CreateNamespaceResponse(
            properties=response.properties if hasattr(response, "properties") else None
        )
    async def drop_namespace(
        self,
@@ -1204,16 +1208,20 @@ class AsyncLanceNamespaceDBConnection:
        DropNamespaceResponse
            Response containing properties and transaction_id if applicable.
        """
-        try:
+        request = DropNamespaceRequest(
-            return await self._inner.drop_namespace(
+            id=namespace_path,
-                namespace_path=namespace_path,
+            mode=_normalize_drop_namespace_mode(mode),
-                mode=mode,
+            behavior=_normalize_drop_namespace_behavior(behavior),
-                behavior=behavior,
+        )
-            )
+        response = self._namespace_client.drop_namespace(request)
-        except RuntimeError as e:
+        return DropNamespaceResponse(
-            if "Namespace not empty" in str(e):
+            properties=(
-                raise NamespaceNotEmptyError(str(e)) from e
+                response.properties if hasattr(response, "properties") else None
-            raise
+            ),
            transaction_id=(
                response.transaction_id if hasattr(response, "transaction_id") else None
            ),
        )
    async def describe_namespace(
        self, namespace_path: List[str]
@@ -1231,7 +1239,11 @@ class AsyncLanceNamespaceDBConnection:
        DescribeNamespaceResponse
            Response containing the namespace properties.
        """
-        return await self._inner.describe_namespace(namespace_path)
+        request = DescribeNamespaceRequest(id=namespace_path)
        response = self._namespace_client.describe_namespace(request)
        return DescribeNamespaceResponse(
            properties=response.properties if hasattr(response, "properties") else None
        )
    async def list_tables(
        self,
@@ -1260,8 +1272,13 @@ class AsyncLanceNamespaceDBConnection:
        """
        if namespace_path is None:
            namespace_path = []
-        return await self._inner.list_tables(
+        request = ListTablesRequest(
-            namespace_path=namespace_path, page_token=page_token, limit=limit
+            id=namespace_path, page_token=page_token, limit=limit
        )
        response = self._namespace_client.list_tables(request)
        return ListTablesResponse(
            tables=response.tables if response.tables else [],
            page_token=response.page_token,
        )
    async def namespace_client(self) -> LanceNamespace:
@@ -1275,18 +1292,6 @@ class AsyncLanceNamespaceDBConnection:
        LanceNamespace
            The namespace client for this connection.
        """
        if self._namespace_client is None:
            if (
                self._namespace_client_impl is None
                or self._namespace_client_properties is None
            ):
                raise ValueError(
                    "Cannot construct a Python namespace client without "
                    "namespace implementation properties"
                )
            self._namespace_client = namespace_connect(
                self._namespace_client_impl, self._namespace_client_properties
            )
        return self._namespace_client
@@ -1337,32 +1342,6 @@ def connect_namespace(
    LanceNamespaceDBConnection
        A namespace-based connection to LanceDB
    """
    if _supports_native_namespace(namespace_client_impl):
        inner = AsyncConnection(
            _connect_namespace(
                namespace_client_impl,
                namespace_client_properties,
                read_consistency_interval=(
                    read_consistency_interval.total_seconds()
                    if read_consistency_interval is not None
                    else None
                ),
                storage_options=storage_options,
                session=session,
                namespace_client_pushdown_operations=namespace_client_pushdown_operations,
            )
        )
        return LanceNamespaceDBConnection(
            namespace_client=None,
            read_consistency_interval=read_consistency_interval,
            storage_options=storage_options,
            session=session,
            namespace_client_pushdown_operations=namespace_client_pushdown_operations,
            namespace_client_impl=namespace_client_impl,
            namespace_client_properties=namespace_client_properties,
            _inner=inner,
        )
    namespace_client = namespace_connect(
        namespace_client_impl, namespace_client_properties
    )
@@ -1438,32 +1417,6 @@ def connect_namespace_async(
    ...     tables = await db.table_names()
    ...     table = await db.create_table("my_table", schema=schema)
    """
    if _supports_native_namespace(namespace_client_impl):
        inner = AsyncConnection(
            _connect_namespace(
                namespace_client_impl,
                namespace_client_properties,
                read_consistency_interval=(
                    read_consistency_interval.total_seconds()
                    if read_consistency_interval is not None
                    else None
                ),
                storage_options=storage_options,
                session=session,
                namespace_client_pushdown_operations=namespace_client_pushdown_operations,
            )
        )
        return AsyncLanceNamespaceDBConnection(
            namespace_client=None,
            read_consistency_interval=read_consistency_interval,
            storage_options=storage_options,
            session=session,
            namespace_client_pushdown_operations=namespace_client_pushdown_operations,
            namespace_client_impl=namespace_client_impl,
            namespace_client_properties=namespace_client_properties,
            _inner=inner,
        )
    namespace_client = namespace_connect(
        namespace_client_impl, namespace_client_properties
    )
@@ -48,14 +48,6 @@ class PermutationBuilder:
        By default, the permutation builder will create a single split that contains all
        rows in the same order as the base table.
        """
        if not hasattr(table, "_inner"):
            raise TypeError(
                f"PermutationBuilder requires a local LanceTable, "
                f"got {type(table).__name__}. "
                "The permutation API is not supported on remote tables. "
                "Remote tables connect to LanceDB Cloud or Enterprise and do not have "
                "direct access to the underlying Lance dataset needed for permutations."
            )
        self._async = async_permutation_builder(table)
    def split_random(
@@ -119,27 +119,6 @@ def _filter_to_sql(filter: Optional[Union[str, Expr]]) -> Optional[str]:
    return filter
 def _combine_where(
    existing: Optional[Union[str, Expr]], new: Union[str, Expr]
 ) -> Union[str, Expr]:
    """Combine a new filter with an existing one using a logical AND.
    Calling ``where`` more than once composes the filters with AND instead of
    replacing the previous filter. Two :class:`~lancedb.expr.Expr` filters are
    combined as an expression; otherwise both filters are lowered to SQL strings
    and combined as SQL.
    """
    if existing is None:
        return new
    existing_is_expr = isinstance(existing, Expr)
    new_is_expr = isinstance(new, Expr)
    if existing_is_expr and new_is_expr:
        return existing & new
    existing_sql = existing.to_sql() if existing_is_expr else existing
    new_sql = new.to_sql() if new_is_expr else new
    return f"({existing_sql}) AND ({new_sql})"
 def _projection_to_scanner_kwargs(
    columns: Optional[
        Union[
@@ -1169,13 +1148,8 @@ class LanceQueryBuilder(ABC):
        -------
        LanceQueryBuilder
            The LanceQueryBuilder object.
        Notes
        -----
        Calling this multiple times combines the filters with a logical AND
        rather than replacing the previous filter.
        """
-        self._where = _combine_where(self._where, where)
+        self._where = where
        self._postfilter = not prefilter
        return self
@@ -1719,13 +1693,8 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
        -------
        LanceQueryBuilder
            The LanceQueryBuilder object.
        Notes
        -----
        Calling this multiple times combines the filters with a logical AND
        rather than replacing the previous filter.
        """
-        self._where = _combine_where(self._where, where)
+        self._where = where
        if prefilter is not None:
            self._postfilter = not prefilter
        return self
@@ -2925,9 +2894,6 @@ class AsyncStandardQuery(AsyncQueryBase):
        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.
        """
        if isinstance(predicate, Expr):
            self._inner.where_expr(predicate._inner)
@@ -9,7 +9,6 @@ from typing import List, Optional
 from lancedb import __version__
 from .header import HeaderProvider
 from .oauth import OAuthConfig, OAuthFlowType
 __all__ = [
    "TimeoutConfig",
@@ -17,8 +16,6 @@ __all__ = [
    "TlsConfig",
    "ClientConfig",
    "HeaderProvider",
    "OAuthConfig",
    "OAuthFlowType",
 ]
@@ -1,75 +0,0 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 from dataclasses import dataclass, field
 from enum import Enum
 from typing import List, Optional
 class OAuthFlowType(str, Enum):
    """OAuth authentication flow types."""
    CLIENT_CREDENTIALS = "client_credentials"
    """Client Credentials grant (service-to-service / M2M)."""
    AZURE_MANAGED_IDENTITY = "azure_managed_identity"
    """Azure Managed Identity via IMDS."""
@dataclass
 class OAuthConfig:
    """OAuth configuration for LanceDB authentication.
    All token acquisition and refresh is handled in the Rust layer.
    This config is passed through to Rust via PyO3.
    Parameters
    ----------
    issuer_url : str
        OIDC issuer URL or OAuth authority URL.
        For Azure: ``https://login.microsoftonline.com/{tenant_id}/v2.0``
    client_id : str
        Application / Client ID.
    scopes : List[str]
        OAuth scopes to request.
        For Azure managed identity, exactly one scope or resource is required.
        For example: ``["api://{app_id}/.default"]``
    flow : OAuthFlowType
        Authentication flow to use. Default: CLIENT_CREDENTIALS.
    client_secret : Optional[str]
        Client secret (required for CLIENT_CREDENTIALS).
    managed_identity_client_id : Optional[str]
        Client ID for user-assigned managed identity (AZURE_MANAGED_IDENTITY).
    refresh_buffer_secs : Optional[int]
        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.
    Examples
    --------
    Client Credentials (service-to-service):
    >>> config = OAuthConfig(
    ...     issuer_url="https://login.microsoftonline.com/{tenant}/v2.0",
    ...     client_id="app-id",
    ...     client_secret="secret",
    ...     scopes=["api://lancedb-api/.default"],
    ... )
    Azure Managed Identity:
    >>> config = OAuthConfig(
    ...     issuer_url="https://login.microsoftonline.com/{tenant}/v2.0",
    ...     client_id="app-id",
    ...     scopes=["api://lancedb-api/.default"],
    ...     flow=OAuthFlowType.AZURE_MANAGED_IDENTITY,
    ... )
    """
    issuer_url: str
    client_id: str
    scopes: List[str]
    flow: OAuthFlowType = OAuthFlowType.CLIENT_CREDENTIALS
    client_secret: Optional[str] = field(default=None, repr=False)
    managed_identity_client_id: Optional[str] = None
    refresh_buffer_secs: Optional[int] = None
@@ -156,16 +156,9 @@ class MRRReranker(Reranker):
                reciprocal_rank = 1.0 / rank
                mrr_score_map[result_id].append(reciprocal_rank)
        # MRR averages the reciprocal rank across *all* ranking systems, treating
        # a system in which a document does not appear as a reciprocal rank of 0.
        # We therefore divide by the total number of systems, not by the number of
        # systems the document happens to appear in -- otherwise a document found
        # by a single ranking would outrank one ranked highly by every system,
        # defeating the purpose of fusing the rankings.
        num_systems = len(vector_results)
        final_mrr_scores = {}
        for result_id, reciprocal_ranks in mrr_score_map.items():
-            mean_rr = float(np.sum(reciprocal_ranks)) / num_systems
+            mean_rr = np.mean(reciprocal_ranks)
            final_mrr_scores[result_id] = mean_rr
        combined = pa.concat_tables(vector_results, **self._concat_tables_args)
@@ -2142,19 +2142,12 @@ class LanceTable(Table):
        branch = self.current_branch()
        version = None if branch is not None else self.version
-        namespace_client = self._namespace_client
+        if self._namespace_client is not None:
        if namespace_client is None:
            conn_uri = getattr(self._conn, "uri", "")
            if get_uri_scheme(conn_uri) == "namespace":
                namespace_client = self._conn.namespace_client()
                self._namespace_client = namespace_client
        if namespace_client is not None:
            table_id = self._namespace_path + [self.name]
            ds = lance.dataset(
                version=version,
                storage_options=self._conn.storage_options,
-                namespace_client=namespace_client,
+                namespace_client=self._namespace_client,
                table_id=table_id,
                **kwargs,
            )
@@ -5,7 +5,6 @@
 import tempfile
 import shutil
 import importlib
 import pytest
 import pyarrow as pa
 import lancedb
@@ -104,40 +103,6 @@ class TestNamespaceConnection:
        assert isinstance(db, lancedb.LanceNamespaceDBConnection)
        assert len(list(db.table_names())) == 0
    def test_sync_builtin_namespace_uses_rust_without_python_client(self, monkeypatch):
        """Built-in sync namespace connections should not construct or call the
        Python namespace client for normal namespace/table management."""
        namespace_module = importlib.import_module("lancedb.namespace")
        def fail_namespace_connect(*args, **kwargs):
            raise AssertionError("Python namespace client should not be constructed")
        monkeypatch.setattr(
            namespace_module, "namespace_connect", fail_namespace_connect
        )
        db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
        assert isinstance(db, lancedb.LanceNamespaceDBConnection)
        assert db._namespace_client is None
        assert db._route_pushdown_to_rust is True
        db.create_namespace(["test_ns"])
        assert "test_ns" in db.list_namespaces().namespaces
        schema = pa.schema([pa.field("id", pa.int64())])
        table = db.create_table("test_table", schema=schema, namespace_path=["test_ns"])
        assert table.namespace == ["test_ns"]
        assert "test_table" in db.table_names(namespace_path=["test_ns"])
        assert "test_table" in db.list_tables(namespace_path=["test_ns"]).tables
        opened = db.open_table("test_table", namespace_path=["test_ns"])
        assert opened.namespace == ["test_ns"]
        db.drop_table("test_table", namespace_path=["test_ns"])
        assert db.list_tables(namespace_path=["test_ns"]).tables == []
        db.drop_namespace(["test_ns"])
        assert "test_ns" not in db.list_namespaces().namespaces
    def test_create_table_through_namespace(self):
        """Test creating a table through namespace."""
        db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
@@ -599,61 +564,6 @@ class TestAsyncNamespaceConnection:
        table_names = await db.table_names()
        assert len(list(table_names)) == 0
    async def test_async_builtin_namespace_uses_rust_without_python_client(
        self, monkeypatch
    ):
        """Built-in async namespace connections should not construct or call the
        Python namespace client for normal namespace/table management."""
        namespace_module = importlib.import_module("lancedb.namespace")
        def fail_namespace_connect(*args, **kwargs):
            raise AssertionError("Python namespace client should not be constructed")
        monkeypatch.setattr(
            namespace_module, "namespace_connect", fail_namespace_connect
        )
        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
        assert isinstance(db, lancedb.AsyncLanceNamespaceDBConnection)
        assert db._namespace_client is None
        assert db._route_pushdown_to_rust is True
        await db.create_namespace(["test_ns"])
        assert "test_ns" in (await db.list_namespaces()).namespaces
        schema = pa.schema([pa.field("id", pa.int64())])
        table = await db.create_table(
            "test_table", schema=schema, namespace_path=["test_ns"]
        )
        assert table._namespace_path == ["test_ns"]
        assert table._namespace_client is None
        assert table._route_pushdown_to_rust is True
        assert "test_table" in await db.table_names(namespace_path=["test_ns"])
        assert "test_table" in (await db.list_tables(namespace_path=["test_ns"])).tables
        opened = await db.open_table("test_table", namespace_path=["test_ns"])
        assert opened._namespace_path == ["test_ns"]
        await db.drop_table("test_table", namespace_path=["test_ns"])
        assert (await db.list_tables(namespace_path=["test_ns"])).tables == []
        await db.drop_namespace(["test_ns"])
        assert "test_ns" not in (await db.list_namespaces()).namespaces
    async def test_async_namespace_client_is_lazy(self):
        """namespace_client() should still return the backing client on demand."""
        pytest.importorskip("lance")
        from lance.namespace import DirectoryNamespace
        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
        assert db._namespace_client is None
        ns_client = await db.namespace_client()
        assert isinstance(ns_client, DirectoryNamespace)
        namespace_id = ns_client.namespace_id().replace("\\\\", "\\")
        assert str(self.temp_dir) in namespace_id
        assert db._namespace_client is ns_client
    # Async connect via namespace helper is not enabled yet.
    async def test_create_table_async(self):
@@ -908,11 +818,10 @@ class TestPushdownOperations:
        )
        assert db._route_pushdown_to_rust is True
-    def test_route_pushdown_to_rust_for_native_dir(self):
+    def test_route_pushdown_to_rust_false_for_dir(self):
-        """The sync dir connection is natively built and defers QueryTable
+        """A non-native (dir) connection keeps the Python pushdown path."""
        pushdown to Rust."""
        db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
-        assert db._route_pushdown_to_rust is True
+        assert db._route_pushdown_to_rust is False
    def test_async_route_pushdown_to_rust_for_native_rest(self):
        """The async connection must not silently bypass the read-freshness fix:
@@ -925,11 +834,10 @@ class TestPushdownOperations:
        )
        assert db._route_pushdown_to_rust is True
-    def test_async_route_pushdown_to_rust_for_native_dir(self):
+    def test_async_route_pushdown_to_rust_false_for_dir(self):
-        """The async dir connection is natively built and defers QueryTable
+        """The async non-native (dir) connection keeps the Python pushdown path."""
        pushdown to Rust."""
        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
-        assert db._route_pushdown_to_rust is True
+        assert db._route_pushdown_to_rust is False
    def test_lance_table_to_arrow_uses_query_pushdown(self):
        namespace_client = _NamespaceClient()
@@ -502,61 +502,6 @@ def test_with_row_id(table: lancedb.table.Table):
    assert rs["_rowid"].to_pylist() == [0, 1]
 def test_where_repeated_combines_with_and(table: lancedb.table.Table):
    # Calling where() more than once should AND the filters together instead of
    # silently replacing the previous one (regression test for #2649).
    builder = table.search().where("id >= 1").where("id < 2")
    assert builder._where == "(id >= 1) AND (id < 2)"
    ids = [row["id"] for row in builder.limit(10).to_list()]
    assert ids == [1]
 def test_where_repeated_combines_expr(table: lancedb.table.Table):
    from lancedb.expr import col, lit
    builder = table.search().where(col("id") >= lit(1)).where(col("id") < lit(2))
    ids = [row["id"] for row in builder.limit(10).to_list()]
    assert ids == [1]
 def test_where_mixed_filter_kinds_combines(table: lancedb.table.Table):
    # Mixing a SQL string filter with an expression filter lowers the
    # expression to SQL and combines them as SQL strings.
    from lancedb.expr import col, lit
    builder = table.search().where("id >= 1").where(col("id") < lit(2))
    ids = [row["id"] for row in builder.limit(10).to_list()]
    assert ids == [1]
@pytest.mark.asyncio
 async def test_where_repeated_combines_with_and_async(table_async: AsyncTable):
    ids = [
        row["id"]
        for row in (
            await table_async.query().where("id >= 1").where("id < 2").to_list()
        )
    ]
    assert ids == [1]
@pytest.mark.asyncio
 async def test_where_mixed_filter_kinds_combines_async(table_async: AsyncTable):
    from lancedb.expr import col, lit
    ids = [
        row["id"]
        for row in (
            await table_async.query()
            .where("id >= 1")
            .where(col("id") < lit(2))
            .to_list()
        )
    ]
    assert ids == [1]
 def test_distance_range(table: lancedb.table.Table):
    q = [0, 0]
    rs = table.search(q).to_arrow()
@@ -350,38 +350,6 @@ def test_mrr_reranker_empty_input():
        reranker.rerank_multivector([])
 def test_mrr_multivector_rewards_consensus():
    # Reciprocal ranks must be averaged across *all* ranking systems, treating a
    # missing system as 0. A document ranked first by every system must outrank a
    # document ranked first by only one of them.
    reranker = MRRReranker()
    def ranking(row_ids):
        return pa.table({"_rowid": pa.array(row_ids, type=pa.int64())})
    # Doc 1 is rank 1 in only the first system; doc 2 is rank 1 in two systems
    # and rank 2 in the third (strong cross-system consensus).
    rs1 = ranking([1, 2, 3])
    rs2 = ranking([2, 3, 4])
    rs3 = ranking([2, 5, 6])
    result = reranker.rerank_multivector([rs1, rs2, rs3])
    scores = {
        row_id: score
        for row_id, score in zip(
            result["_rowid"].to_pylist(),
            result["_relevance_score"].to_pylist(),
        )
    }
    # sum of reciprocal ranks / number of systems
    assert scores[1] == pytest.approx(1.0 / 3)
    assert scores[2] == pytest.approx((0.5 + 1.0 + 1.0) / 3)
    assert scores[2] > scores[1]
    # The consensus document ranks first overall.
    assert result["_rowid"].to_pylist()[0] == 2
 def test_rrf_reranker_distance():
    data = pa.table(
        {
@@ -1137,16 +1137,6 @@ def test_namespace_open_table_with_branch_version(tmp_path):
    assert db.open_table("t", namespace_path=["ns1"], branch="exp").count_rows() == 3
 def test_namespace_root_table_to_lance_uses_namespace_client(tmp_path):
    pytest.importorskip("lance")  # "dir" impl is lance.namespace.DirectoryNamespace
    db = lancedb.connect_namespace("dir", {"root": str(tmp_path)})
    table = db.create_table("t", [{"i": 0}])
    assert table._namespace_client is None
    assert table.to_lance().count_rows() == 1
    assert table._namespace_client is not None
@pytest.mark.asyncio
 async def test_async_namespace_open_table_with_branch_version(tmp_path):
    pytest.importorskip("lance")  # "dir" impl is lance.namespace.DirectoryNamespace
@@ -539,7 +539,7 @@ impl Connection {
 }
 #[pyfunction]
-#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None, oauth_config=None))]
+#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect(
    py: Python<'_>,
@@ -553,7 +553,6 @@ pub fn connect(
    session: Option<crate::session::Session>,
    manifest_enabled: bool,
    namespace_client_properties: Option<HashMap<String, String>>,
    oauth_config: Option<crate::oauth::PyOAuthConfig>,
 ) -> PyResult<Bound<'_, PyAny>> {
    future_into_py(py, async move {
        let mut builder = lancedb::connect(&uri);
@@ -583,11 +582,6 @@ pub fn connect(
        if let Some(client_config) = client_config {
            builder = builder.client_config(client_config.into());
        }
        if let Some(oauth_config) = oauth_config {
            let config: lancedb::remote::oauth::OAuthConfig =
                oauth_config.try_into().infer_error()?;
            builder = builder.oauth_config(config);
        }
        if let Some(session) = session {
            builder = builder.session(session.inner.clone());
        }
@@ -655,46 +649,6 @@ pub fn connect_namespace_client(
    )))
 }
 #[pyfunction]
 #[pyo3(signature = (
    namespace_client_impl,
    namespace_client_properties,
    read_consistency_interval=None,
    storage_options=None,
    session=None,
    namespace_client_pushdown_operations=None,
 ))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect_namespace(
    namespace_client_impl: String,
    namespace_client_properties: HashMap<String, String>,
    read_consistency_interval: Option<f64>,
    storage_options: Option<HashMap<String, String>>,
    session: Option<crate::session::Session>,
    namespace_client_pushdown_operations: Option<Vec<String>>,
 ) -> PyResult<Connection> {
    let read_consistency_interval = read_consistency_interval.map(Duration::from_secs_f64);
    let namespace_client_pushdown_operations =
        parse_namespace_client_pushdown_operations(namespace_client_pushdown_operations)?;
    let mut builder =
        lancedb::connect_namespace(&namespace_client_impl, namespace_client_properties)
            .pushdown_operations(namespace_client_pushdown_operations);
    if let Some(storage_options) = storage_options {
        builder = builder.storage_options(storage_options);
    }
    if let Some(read_consistency_interval) = read_consistency_interval {
        builder = builder.read_consistency_interval(read_consistency_interval);
    }
    if let Some(session) = session {
        builder = builder.session(session.inner.clone());
    }
    Ok(Connection::new(
        crate::runtime::block_on(builder.execute()).infer_error()?,
    ))
 }
 /// Whether to build the namespace natively (from impl + properties) instead of
 /// wrapping a pre-built client. Native construction is required for the
 /// read-freshness provider to be installed
@@ -2,7 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 use arrow::RecordBatchStream;
-use connection::{Connection, connect, connect_namespace, connect_namespace_client};
+use connection::{Connection, connect, connect_namespace_client};
 use env_logger::Env;
 use expr::{PyExpr, expr_col, expr_func, expr_lit};
 use index::IndexConfig;
@@ -26,7 +26,6 @@ pub mod expr;
 pub mod header;
 pub mod index;
 pub mod namespace;
 pub mod oauth;
 pub mod permutation;
 pub mod query;
 pub mod runtime;
@@ -62,7 +61,6 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
    m.add_class::<PyPermutationReader>()?;
    m.add_class::<PyExpr>()?;
    m.add_function(wrap_pyfunction!(connect, m)?)?;
    m.add_function(wrap_pyfunction!(connect_namespace, m)?)?;
    m.add_function(wrap_pyfunction!(connect_namespace_client, m)?)?;
    m.add_function(wrap_pyfunction!(permutation::async_permutation_builder, m)?)?;
    m.add_function(wrap_pyfunction!(util::validate_table_name, m)?)?;
@@ -1,72 +0,0 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 use pyo3::FromPyObject;
 use lancedb::error::Error;
 use lancedb::remote::oauth::{OAuthConfig, OAuthFlow};
 /// Python-side OAuth configuration, extracted via FromPyObject.
 /// Maps to `lancedb.remote.oauth.OAuthConfig` Python dataclass.
 #[derive(FromPyObject)]
 pub struct PyOAuthConfig {
    pub issuer_url: String,
    pub client_id: String,
    pub scopes: Vec<String>,
    pub flow: String,
    pub client_secret: Option<String>,
    pub managed_identity_client_id: Option<String>,
    pub refresh_buffer_secs: Option<u64>,
 }
 impl TryFrom<PyOAuthConfig> for OAuthConfig {
    type Error = Error;
    fn try_from(py: PyOAuthConfig) -> Result<Self, Self::Error> {
        let flow = match py.flow.as_str() {
            "client_credentials" => OAuthFlow::ClientCredentials,
            "azure_managed_identity" => OAuthFlow::AzureManagedIdentity {
                client_id: py.managed_identity_client_id,
            },
            other => {
                return Err(Error::InvalidInput {
                    message: format!("Unknown OAuth flow type: {other}"),
                });
            }
        };
        Ok(Self {
            issuer_url: py.issuer_url,
            client_id: py.client_id,
            client_secret: py.client_secret,
            scopes: py.scopes,
            flow,
            refresh_buffer_secs: py.refresh_buffer_secs,
        })
    }
 }
 #[cfg(test)]
 mod tests {
    use super::*;
    #[test]
    fn test_unknown_oauth_flow_returns_invalid_input() {
        let config = PyOAuthConfig {
            issuer_url: "https://issuer.example.com".to_string(),
            client_id: "client-id".to_string(),
            scopes: vec!["scope".to_string()],
            flow: "typo".to_string(),
            client_secret: None,
            managed_identity_client_id: None,
            refresh_buffer_secs: None,
        };
        let err = OAuthConfig::try_from(config).unwrap_err();
        assert!(matches!(
            err,
            Error::InvalidInput { message }
                if message == "Unknown OAuth flow type: typo"
        ));
    }
 }
@@ -1,33 +0,0 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 import importlib.util
 import sys
 from pathlib import Path
 def _load_oauth_module():
    oauth_path = (
        Path(__file__).parents[1] / "python" / "lancedb" / "remote" / "oauth.py"
    )
    spec = importlib.util.spec_from_file_location("lancedb_remote_oauth", oauth_path)
    module = importlib.util.module_from_spec(spec)
    assert spec.loader is not None
    sys.modules[spec.name] = module
    spec.loader.exec_module(module)
    return module
 def test_oauth_config_repr_redacts_client_secret():
    oauth = _load_oauth_module()
    config = oauth.OAuthConfig(
        issuer_url="https://issuer.example.com",
        client_id="client-id",
        scopes=["scope"],
        client_secret="super-secret",
    )
    rendered = repr(config)
    assert "super-secret" not in rendered
    assert "client_secret" not in rendered
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.3"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -14,7 +14,6 @@ rust-version.workspace = true
 ahash = { workspace = true }
 arrow = { workspace = true }
 arrow-array = { workspace = true }
 arrow-buffer = { workspace = true }
 arrow-data = { workspace = true }
 arrow-schema = { workspace = true }
 arrow-select = { workspace = true }
@@ -167,10 +166,6 @@ required-features = ["bedrock"]
 [[example]]
 name = "simple"
 [[example]]
 name = "polars"
 required-features = ["polars"]
 [[example]]
 name = "full_text_search"
@@ -1,47 +0,0 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 //! This example demonstrates ingesting a Polars DataFrame into LanceDB and
 //! reading it back out as a Polars DataFrame.
 use lancedb::arrow::IntoPolars;
 use lancedb::query::ExecutableQuery;
 use lancedb::{Result, connect};
 use polars::prelude::{DataFrame, NamedFrom, Series};
 fn make_dataframe() -> DataFrame {
    let ids = Series::new("id", &[1i32, 2, 3, 4, 5]);
    let names = Series::new("name", &["Alice", "Bob", "Carol", "Dave", "Eve"]);
    let scores = Series::new("score", &[9.5f64, 8.1, 7.3, 9.0, 6.5]);
    DataFrame::new(vec![ids, names, scores]).unwrap()
 }
 #[tokio::main]
 async fn main() -> Result<()> {
    let tmp = tempfile::tempdir().unwrap();
    let db = connect(tmp.path().to_str().unwrap()).execute().await?;
    // Ingest a Polars DataFrame directly — DataFrame now implements Scannable.
    let df = make_dataframe();
    println!("Input DataFrame:\n{df}");
    let table = db.create_table("people", df).execute().await?;
    // Append more rows.
    let more = DataFrame::new(vec![
        Series::new("id", &[6i32, 7]),
        Series::new("name", &["Frank", "Grace"]),
        Series::new("score", &[7.8f64, 8.9]),
    ])
    .unwrap();
    table.add(more).execute().await?;
    // Read back as a Polars DataFrame.
    let result_df = table.query().execute().await?.into_polars().await?;
    println!(
        "\nRound-tripped DataFrame ({} rows):\n{result_df}",
        result_df.height()
    );
    Ok(())
 }
@@ -3,19 +3,7 @@
 use std::{pin::Pin, sync::Arc};
 // Re-export the arrow crates we depend on so downstream consumers can build
 // `RecordBatch`/arrays/builders against the exact same arrow line lancedb was
 // compiled against, instead of declaring their own (potentially mismatched)
 // direct arrow dependencies. See https://github.com/lancedb/lancedb/issues/3575.
 pub use arrow;
 pub use arrow_array;
 pub use arrow_buffer;
 pub use arrow_cast;
 pub use arrow_data;
 pub use arrow_ipc;
 pub use arrow_ord;
 pub use arrow_schema;
 pub use arrow_select;
 use datafusion_common::DataFusionError;
 use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
 use futures::{Stream, StreamExt, TryStreamExt};
@@ -124,14 +112,54 @@ impl<S: Stream<Item = Result<arrow_array::RecordBatch>>> RecordBatchStream
 /// A trait for converting incoming data to Arrow
 ///
 /// Integrations should implement this trait to allow data to be
 /// imported directly from the integration.  For example, implementing
 /// this trait for `Vec<Vec<...>>` would allow the `Vec` to be directly
 /// used in methods like [`crate::connection::Connection::create_table`]
 /// or [`crate::table::Table::add`]
 pub trait IntoArrow {
    /// Convert the data into an iterator of Arrow batches
    fn into_arrow(self) -> Result<Box<dyn arrow_array::RecordBatchReader + Send>>;
 }
 pub type BoxedRecordBatchReader = Box<dyn arrow_array::RecordBatchReader + Send>;
 impl<T: arrow_array::RecordBatchReader + Send + 'static> IntoArrow for T {
    fn into_arrow(self) -> Result<Box<dyn arrow_array::RecordBatchReader + Send>> {
        Ok(Box::new(self))
    }
 }
 /// A trait for converting incoming data to Arrow asynchronously
 ///
 /// Serves the same purpose as [`IntoArrow`], but for asynchronous data.
 ///
 /// Note: Arrow has no async equivalent to RecordBatchReader and so
 pub trait IntoArrowStream {
    /// Convert the data into a stream of Arrow batches
    fn into_arrow(self) -> Result<SendableRecordBatchStream>;
 }
 impl<S: Stream<Item = Result<arrow_array::RecordBatch>>> SimpleRecordBatchStream<S> {
    pub fn new(stream: S, schema: Arc<arrow_schema::Schema>) -> Self {
        Self { schema, stream }
    }
 }
 impl IntoArrowStream for SendableRecordBatchStream {
    fn into_arrow(self) -> Result<SendableRecordBatchStream> {
        Ok(self)
    }
 }
 impl IntoArrowStream for datafusion_physical_plan::SendableRecordBatchStream {
    fn into_arrow(self) -> Result<SendableRecordBatchStream> {
        let schema = self.schema();
        let stream = self.map_err(|df_err| df_err.into());
        Ok(Box::pin(SimpleRecordBatchStream::new(stream, schema)))
    }
 }
 pub trait LanceDbDatagenExt {
    fn into_ldb_stream(
        self,
@@ -236,7 +264,9 @@ impl IntoPolars for SendableRecordBatchStream {
 #[cfg(all(test, feature = "polars"))]
 mod tests {
    use super::SendableRecordBatchStream;
-    use crate::arrow::{IntoPolars, PolarsDataFrameRecordBatchReader, SimpleRecordBatchStream};
+    use crate::arrow::{
        IntoArrow, IntoPolars, PolarsDataFrameRecordBatchReader, SimpleRecordBatchStream,
    };
    use polars::prelude::{DataFrame, NamedFrom, Series};
    fn get_record_batch_reader_from_polars() -> Box<dyn arrow_array::RecordBatchReader + Send> {
@@ -250,7 +280,10 @@ mod tests {
        float_series = Series::new("float", &[2.0]);
        let df2 = DataFrame::new(vec![string_series, int_series, float_series]).unwrap();
-        Box::new(PolarsDataFrameRecordBatchReader::new(df1.vstack(&df2).unwrap()).unwrap())
+        PolarsDataFrameRecordBatchReader::new(df1.vstack(&df2).unwrap())
            .unwrap()
            .into_arrow()
            .unwrap()
    }
    #[test]
@@ -185,43 +185,6 @@ impl Scannable for SendableRecordBatchStream {
    }
 }
 #[cfg(feature = "polars")]
 impl Scannable for polars::frame::DataFrame {
    fn schema(&self) -> SchemaRef {
        crate::polars_arrow_convertors::convert_polars_df_schema_to_arrow_rb_schema(
            self.schema().clone(),
        )
        .expect("failed to convert Polars DataFrame schema to Arrow schema")
    }
    fn scan_as_stream(&mut self) -> SendableRecordBatchStream {
        let schema = Scannable::schema(self);
        let batches: crate::Result<Vec<RecordBatch>> =
            match crate::arrow::PolarsDataFrameRecordBatchReader::new(self.clone()) {
                Err(e) => Err(e),
                Ok(reader) => reader.map(|b| b.map_err(Into::into)).collect(),
            };
        match batches {
            Err(e) => Box::pin(SimpleRecordBatchStream {
                schema,
                stream: once(async move { Err(e) }),
            }),
            Ok(batches) => {
                let stream = futures::stream::iter(batches.into_iter().map(Ok));
                Box::pin(SimpleRecordBatchStream { schema, stream })
            }
        }
    }
    fn num_rows(&self) -> Option<usize> {
        Some(self.height())
    }
    fn rescannable(&self) -> bool {
        true
    }
 }
 #[async_trait]
 impl StreamingWriteSource for Box<dyn Scannable> {
    fn arrow_schema(&self) -> SchemaRef {
@@ -1126,60 +1089,4 @@ mod tests {
            );
        }
    }
    #[cfg(feature = "polars")]
    mod polars_tests {
        use super::*;
        use crate::arrow::IntoPolars;
        use crate::query::ExecutableQuery;
        use polars::prelude::{DataFrame, NamedFrom, Series};
        fn make_df() -> DataFrame {
            DataFrame::new(vec![
                Series::new("id", &[1i32, 2, 3]),
                Series::new("val", &[1.1f64, 2.2, 3.3]),
            ])
            .unwrap()
        }
        #[tokio::test]
        async fn test_dataframe_scannable_round_trip() {
            let tmp = tempfile::tempdir().unwrap();
            let db = crate::connect(tmp.path().to_str().unwrap())
                .execute()
                .await
                .unwrap();
            let df = make_df();
            let table = db.create_table("t", df.clone()).execute().await.unwrap();
            // Append the same rows again.
            table.add(df.clone()).execute().await.unwrap();
            let result = table
                .query()
                .execute()
                .await
                .unwrap()
                .into_polars()
                .await
                .unwrap();
            assert_eq!(result.height(), df.height() * 2);
            assert_eq!(result.schema(), df.schema());
        }
        #[tokio::test]
        async fn test_dataframe_scannable_rescannable() {
            let mut df = make_df();
            assert!(df.rescannable());
            let batches1: Vec<RecordBatch> = df.scan_as_stream().try_collect().await.unwrap();
            assert_eq!(batches1.iter().map(|b| b.num_rows()).sum::<usize>(), 3);
            // Can be scanned again.
            let batches2: Vec<RecordBatch> = df.scan_as_stream().try_collect().await.unwrap();
            assert_eq!(batches2.iter().map(|b| b.num_rows()).sum::<usize>(), 3);
        }
    }
 }
@@ -342,9 +342,3 @@ pub use connection::connect_namespace;
 /// Re-export Lance Session and ObjectStoreRegistry for custom session creation
 pub use lance::session::Session;
 pub use lance_io::object_store::ObjectStoreRegistry;
 /// Re-export DataFusion so consumers can build the `Expr` values that public
 /// query/merge APIs (e.g. [`query::QueryBase::only_if_expr`]) accept without
 /// declaring their own (potentially mismatched) direct `datafusion` dependency.
 /// See <https://github.com/lancedb/lancedb/issues/3575>.
 pub use datafusion;
@@ -401,9 +401,6 @@ pub trait QueryBase {
    ///
    /// 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
    /// (i.e. `(previous) AND (new)`) rather than replacing the previous filter.
    fn only_if(self, filter: impl AsRef<str>) -> Self;
    /// Only return rows which match the filter, using an expression builder.
@@ -426,9 +423,6 @@ pub trait QueryBase {
    ///
    /// Note: Expression filters are not supported for remote/server-side queries.
    /// Use [`QueryBase::only_if`] with SQL strings for remote tables.
    ///
    /// Calling this multiple times combines the expressions with a logical AND
    /// rather than replacing the previous filter.
    fn only_if_expr(self, filter: datafusion_expr::Expr) -> Self;
    /// Perform a full text search on the table.
@@ -541,13 +535,12 @@ impl<T: HasQuery> QueryBase for T {
    }
    fn only_if(mut self, filter: impl AsRef<str>) -> Self {
-        self.mut_query()
+        self.mut_query().filter = Some(QueryFilter::Sql(filter.as_ref().to_string()));
            .add_filter(QueryFilter::Sql(filter.as_ref().to_string()));
        self
    }
    fn only_if_expr(mut self, filter: datafusion_expr::Expr) -> Self {
-        self.mut_query().add_filter(QueryFilter::Datafusion(filter));
+        self.mut_query().filter = Some(QueryFilter::Datafusion(filter));
        self
    }
@@ -723,39 +716,6 @@ pub enum QueryFilter {
    Datafusion(Expr),
 }
 /// Combine two filters with a logical AND.
 ///
 /// This is used when a query receives more than one filter (for example when
 /// `where`/`only_if` is called multiple times) so the filters are composed
 /// with AND rather than the later filter silently replacing the earlier one.
 ///
 /// SQL string and expression filters are combined within their own
 /// representation. When the two representations are mixed, the expression is
 /// lowered to SQL (via [`crate::expr::expr_to_sql_string`]) and the filters are
 /// combined as SQL strings. Substrait filters cannot be combined and return an
 /// error.
 fn and_filters(existing: QueryFilter, new: QueryFilter) -> Result<QueryFilter> {
    match (existing, new) {
        (QueryFilter::Sql(lhs), QueryFilter::Sql(rhs)) => {
            Ok(QueryFilter::Sql(format!("({lhs}) AND ({rhs})")))
        }
        (QueryFilter::Datafusion(lhs), QueryFilter::Datafusion(rhs)) => {
            Ok(QueryFilter::Datafusion(lhs.and(rhs)))
        }
        (QueryFilter::Sql(lhs), QueryFilter::Datafusion(rhs)) => {
            let rhs = crate::expr::expr_to_sql_string(&rhs)?;
            Ok(QueryFilter::Sql(format!("({lhs}) AND ({rhs})")))
        }
        (QueryFilter::Datafusion(lhs), QueryFilter::Sql(rhs)) => {
            let lhs = crate::expr::expr_to_sql_string(&lhs)?;
            Ok(QueryFilter::Sql(format!("({lhs}) AND ({rhs})")))
        }
        _ => Err(Error::InvalidInput {
            message: "cannot combine a Substrait filter with another filter".to_string(),
        }),
    }
 }
 /// A basic query into a table without any kind of search
 ///
 /// This will result in a (potentially filtered) scan if executed
@@ -770,13 +730,6 @@ pub struct QueryRequest {
    /// Apply filter to the returned rows.
    pub filter: Option<QueryFilter>,
    /// An error recorded while combining repeated filters that could not be
    /// composed (see [`QueryRequest::add_filter`]). It is surfaced when the
    /// query is executed via [`QueryRequest::check_filter`]. We defer the error
    /// because the builder methods that set filters return `Self` rather than a
    /// `Result`.
    pub(crate) filter_error: Option<String>,
    /// Perform a full text search on the table.
    pub full_text_search: Option<FullTextSearchQuery>,
@@ -822,7 +775,6 @@ impl Default for QueryRequest {
            limit: None,
            offset: None,
            filter: None,
            filter_error: None,
            full_text_search: None,
            select: Select::All,
            fast_search: false,
@@ -836,41 +788,6 @@ impl Default for QueryRequest {
    }
 }
 impl QueryRequest {
    /// Add a filter, combining it with any existing filter using a logical AND.
    ///
    /// If the new filter cannot be combined with the existing one (because they
    /// use different representations) the error is recorded and surfaced later
    /// by [`Self::check_filter`].
    pub(crate) fn add_filter(&mut self, new: QueryFilter) {
        self.filter = Some(match self.filter.take() {
            None => new,
            Some(existing) => match and_filters(existing, new) {
                Ok(combined) => combined,
                Err(err) => {
                    // The filters were consumed while attempting to combine
                    // them; the recorded error is surfaced by `check_filter`
                    // before the query executes.
                    self.filter_error = Some(err.to_string());
                    return;
                }
            },
        });
    }
    /// Return an error if combining filters failed (see [`Self::add_filter`]).
    ///
    /// This must be called by every backend before executing a query.
    pub(crate) fn check_filter(&self) -> Result<()> {
        if let Some(message) = &self.filter_error {
            return Err(Error::InvalidInput {
                message: message.clone(),
            });
        }
        Ok(())
    }
 }
 /// A builder for LanceDB queries.
 ///
 /// See [`crate::Table::query`] for more details on queries
@@ -1765,70 +1682,6 @@ mod tests {
        }
    }
    #[tokio::test]
    async fn test_repeated_only_if_combines_with_and() {
        use crate::expr::{col, lit};
        let tmp_dir = tempdir().unwrap();
        let dataset_path = tmp_dir.path().join("test.lance");
        let uri = dataset_path.to_str().unwrap();
        let conn = connect(uri).execute().await.unwrap();
        let table = conn
            .create_table("my_table", make_non_empty_batches())
            .execute()
            .await
            .unwrap();
        let query = table.query().only_if("id > 0").only_if("id < 100");
        match &query.request.filter {
            Some(QueryFilter::Sql(sql)) => assert_eq!(sql, "(id > 0) AND (id < 100)"),
            other => panic!("expected combined SQL filter, got {other:?}"),
        }
        // A single filter is left untouched.
        let query = table.query().only_if("id > 0");
        match &query.request.filter {
            Some(QueryFilter::Sql(sql)) => assert_eq!(sql, "id > 0"),
            other => panic!("expected single SQL filter, got {other:?}"),
        }
        // Expression filters are combined with a logical AND as well.
        let query = table
            .query()
            .only_if_expr(col("id").gt(lit(0i32)))
            .only_if_expr(col("id").lt(lit(100i32)));
        match &query.request.filter {
            Some(QueryFilter::Datafusion(expr)) => {
                assert_eq!(
                    expr,
                    &col("id").gt(lit(0i32)).and(col("id").lt(lit(100i32)))
                );
            }
            other => panic!("expected combined Datafusion filter, got {other:?}"),
        }
        // Mixing an SQL string filter with an expression filter lowers the
        // expression to SQL and combines them as SQL strings.
        let query = table
            .query()
            .only_if("id > 0")
            .only_if_expr(col("id").lt(lit(100i32)));
        match &query.request.filter {
            Some(QueryFilter::Sql(sql)) => {
                let expected = format!(
                    "(id > 0) AND ({})",
                    crate::expr::expr_to_sql_string(&col("id").lt(lit(100i32))).unwrap()
                );
                assert_eq!(sql, &expected);
            }
            other => panic!("expected combined SQL filter, got {other:?}"),
        }
        assert!(query.request.check_filter().is_ok());
        // The combined filter executes without error.
        query.execute().await.unwrap();
    }
    #[tokio::test]
    async fn test_select_with_transform() {
        // TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051
@@ -70,29 +70,18 @@ use tokio::sync::RwLock;
 const REQUEST_TIMEOUT_HEADER: HeaderName = HeaderName::from_static("x-request-timeout-ms");
 const MIN_VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-version");
 const MIN_TIMESTAMP_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-timestamp");
 const MIN_READ_VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-read-version");
 const VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-version");
 const METRIC_TYPE_KEY: &str = "metric_type";
 const INDEX_TYPE_KEY: &str = "index_type";
 const SCHEMA_CACHE_TTL: Duration = Duration::from_secs(30);
 const SCHEMA_CACHE_REFRESH_WINDOW: Duration = Duration::from_secs(5);
-/// Per-table state driving the freshness headers (`x-lancedb-min-version`,
+/// Per-table state driving the freshness headers (`x-lancedb-min-version` and
-/// `x-lancedb-min-timestamp`, and `x-lancedb-min-read-version`) sent on read
+/// `x-lancedb-min-timestamp`) sent on read requests.
 /// requests.
 #[derive(Debug, Default, Clone, Copy)]
 struct FreshnessState {
    /// Provides read-your-write within a single handle: writes that return a
    /// version update this, and reads send it as `x-lancedb-min-version`.
    min_version: Option<u64>,
    /// Highest dataset version observed in a *read* response on this handle.
    /// Reads send it as `x-lancedb-min-read-version` so a load-balanced query
    /// node whose cache is behind this version must refresh before serving,
    /// giving monotonic reads across nodes regardless of which one the load
    /// balancer routes to. Sourced only from reads (always committed dataset
    /// versions), never from writes (which may return WAL entry ids), so it is
    /// unaffected by the WAL/version mismatch that retired `min_version`.
    min_read_version: Option<u64>,
    /// Wall-clock time captured at the last [`BaseTable::checkout_latest`]
    /// call. Subsequent reads send
    /// `max(baseline, now - read_consistency_interval)` as
@@ -113,7 +102,6 @@ struct FreshnessState {
 struct FreshnessHeaders {
    min_version: Option<u64>,
    min_timestamp: Option<SystemTime>,
    min_read_version: Option<u64>,
 }
 impl FreshnessHeaders {
@@ -125,9 +113,6 @@ impl FreshnessHeaders {
            let dt: chrono::DateTime<chrono::Utc> = ts.into();
            request = request.header(MIN_TIMESTAMP_HEADER, dt.to_rfc3339());
        }
        if let Some(v) = self.min_read_version {
            request = request.header(MIN_READ_VERSION_HEADER, v.to_string());
        }
        request
    }
 }
@@ -612,7 +597,6 @@ impl<S: HttpSend> RemoteTable<S> {
        body: &mut serde_json::Value,
        params: &QueryRequest,
    ) -> Result<()> {
        params.check_filter()?;
        body["prefilter"] = params.prefilter.into();
        if let Some(offset) = params.offset {
            body["offset"] = serde_json::Value::Number(serde_json::Number::from(offset));
@@ -900,7 +884,6 @@ impl<S: HttpSend> RemoteTable<S> {
                self.client.read_consistency_interval,
                SystemTime::now(),
            ),
            min_read_version: state.min_read_version,
        }
    }
@@ -922,30 +905,6 @@ impl<S: HttpSend> RemoteTable<S> {
        state.min_version = Some(state.min_version.map_or(version, |v| v.max(version)));
    }
    /// Record a dataset version observed in a *read* response so subsequent
    /// reads request at least this version via `x-lancedb-min-read-version`,
    /// giving monotonic reads across load-balanced query nodes. A returned `0`
    /// (or absent header from an old server) is ignored.
    fn track_read_version(&self, version: u64) {
        if version == 0 {
            return;
        }
        let mut state = self.freshness.lock().unwrap();
        state.min_read_version = Some(state.min_read_version.map_or(version, |v| v.max(version)));
    }
    /// Parse the `x-lancedb-version` response header (the dataset version a read
    /// reflects) and fold it into the read-version watermark.
    fn track_read_version_from_headers(&self, headers: &reqwest::header::HeaderMap) {
        if let Some(version) = headers
            .get(&VERSION_HEADER)
            .and_then(|value| value.to_str().ok())
            .and_then(|value| value.parse::<u64>().ok())
        {
            self.track_read_version(version);
        }
    }
    async fn execute_query(
        &self,
        query: &AnyQuery,
@@ -969,7 +928,6 @@ impl<S: HttpSend> RemoteTable<S> {
        let futures = requests.into_iter().map(|req| async move {
            let (request_id, response) = self.send(req, true).await?;
            self.track_read_version_from_headers(response.headers());
            self.read_arrow_stream(&request_id, response).await
        });
        let streams = futures::future::try_join_all(futures);
@@ -1587,12 +1545,11 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
        *write_guard = None;
        drop(write_guard);
-        // Drop any per-handle read/write tracking; subsequent reads use the
+        // Drop any per-handle write tracking; subsequent reads use the
        // baseline timestamp captured now to guarantee freshness.
        *self.freshness.lock().unwrap() = FreshnessState {
            min_version: None,
            checkout_baseline: Some(SystemTime::now()),
            min_read_version: None,
        };
        // Invalidate schema cache since we're switching versions
@@ -1848,7 +1805,6 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
            }
        };
        self.track_read_version_from_headers(response.headers());
        let body = response.text().await.err_to_http(request_id.clone())?;
        serde_json::from_str(&body).map_err(|e| Error::Http {
@@ -7168,7 +7124,6 @@ mod tests {
        let state = FreshnessState {
            min_version: None,
            checkout_baseline: Some(baseline),
            min_read_version: None,
        };
        assert_eq!(compute_min_timestamp(&state, None, now), Some(baseline));
@@ -7193,7 +7148,6 @@ mod tests {
        let state = FreshnessState {
            min_version: None,
            checkout_baseline: Some(baseline),
            min_read_version: None,
        };
        assert_eq!(
            compute_min_timestamp(&state, Some(Duration::from_secs(10)), now),
@@ -7205,7 +7159,6 @@ mod tests {
        let state = FreshnessState {
            min_version: None,
            checkout_baseline: Some(recent_baseline),
            min_read_version: None,
        };
        assert_eq!(
            compute_min_timestamp(&state, Some(Duration::from_secs(60)), now),
@@ -7350,106 +7303,6 @@ mod tests {
        );
    }
    /// A handler that records every request's headers and answers each read with
    /// an `x-lancedb-version` response header taken from `versions` (by call
    /// index, saturating at the last entry). An empty string means "no header".
    fn read_version_handler(
        versions: &'static [&'static str],
    ) -> (
        impl Fn(reqwest::Request) -> http::Response<String> + Clone + Send + Sync + 'static,
        Arc<std::sync::Mutex<Vec<http::HeaderMap>>>,
    ) {
        let requests = Arc::new(std::sync::Mutex::new(Vec::new()));
        let requests_c = requests.clone();
        let call = Arc::new(AtomicUsize::new(0));
        let handler = move |request: reqwest::Request| {
            requests_c.lock().unwrap().push(request.headers().clone());
            let i = call.fetch_add(1, Ordering::SeqCst).min(versions.len() - 1);
            let mut builder = http::Response::builder().status(200);
            if !versions[i].is_empty() {
                builder = builder.header("x-lancedb-version", versions[i]);
            }
            builder.body("42".to_string()).unwrap()
        };
        (handler, requests)
    }
    #[tokio::test]
    async fn test_read_version_watermark_tracked_and_sent() {
        let (handler, requests) = read_version_handler(&["100", "100"]);
        let table = Table::new_with_handler("my_table", handler);
        // First read has no watermark yet; the response advertises version 100,
        // so the second read must floor the server at 100.
        table.count_rows(None).await.unwrap();
        table.count_rows(None).await.unwrap();
        let reqs = requests.lock().unwrap();
        assert!(!reqs[0].contains_key("x-lancedb-min-read-version"));
        assert_eq!(
            reqs[1]
                .get("x-lancedb-min-read-version")
                .unwrap()
                .to_str()
                .unwrap(),
            "100"
        );
    }
    #[tokio::test]
    async fn test_read_version_watermark_keeps_max() {
        // Server reports 100 then a stale 50; the watermark must not regress.
        let (handler, requests) = read_version_handler(&["100", "50", "50"]);
        let table = Table::new_with_handler("my_table", handler);
        table.count_rows(None).await.unwrap();
        table.count_rows(None).await.unwrap();
        table.count_rows(None).await.unwrap();
        let reqs = requests.lock().unwrap();
        assert_eq!(
            reqs[2]
                .get("x-lancedb-min-read-version")
                .unwrap()
                .to_str()
                .unwrap(),
            "100"
        );
    }
    #[tokio::test]
    async fn test_read_version_absent_header_no_watermark() {
        // An old server that doesn't return the version header leaves the
        // watermark unset, preserving backward compatibility.
        let (handler, requests) = read_version_handler(&[""]);
        let table = Table::new_with_handler("my_table", handler);
        table.count_rows(None).await.unwrap();
        table.count_rows(None).await.unwrap();
        let reqs = requests.lock().unwrap();
        assert!(!reqs[1].contains_key("x-lancedb-min-read-version"));
    }
    #[tokio::test]
    async fn test_read_version_watermark_reset_on_checkout_latest() {
        let (handler, requests) = read_version_handler(&["100", "100"]);
        let table = Table::new_with_handler("my_table", handler);
        table.count_rows(None).await.unwrap();
        table.checkout_latest().await.unwrap();
        table.count_rows(None).await.unwrap();
        // The read after checkout_latest starts from a clean slate.
        let reqs = requests.lock().unwrap();
        assert!(
            !reqs
                .last()
                .unwrap()
                .contains_key("x-lancedb-min-read-version")
        );
    }
    /// Like `capturing_handler`, but keeps a per-path snapshot of the headers
    /// from every request so tests can assert on a specific endpoint.
    #[allow(clippy::type_complexity)]
@@ -35,15 +35,6 @@ pub enum AnyQuery {
    VectorQuery(VectorQueryRequest),
 }
 impl AnyQuery {
    pub(crate) fn base(&self) -> &QueryRequest {
        match self {
            Self::Query(query) => query,
            Self::VectorQuery(query) => &query.base,
        }
    }
 }
 //Decide between namespace or local
 pub async fn execute_query(
    table: &NativeTable,
@@ -117,7 +108,6 @@ pub async fn create_plan(
        AnyQuery::VectorQuery(query) => query.clone(),
        AnyQuery::Query(query) => VectorQueryRequest::from_plain_query(query.clone()),
    };
    query.base.check_filter()?;
    let ds_ref = table.dataset.get().await?;
    let schema = ds_ref.schema();
@@ -367,7 +357,6 @@ async fn execute_namespace_query(
 /// Convert an AnyQuery to the namespace QueryTableRequest format.
 fn convert_to_namespace_query(query: &AnyQuery) -> Result<NsQueryTableRequest> {
    query.base().check_filter()?;
    match query {
        AnyQuery::VectorQuery(vq) => {
            // Extract the query vector(s)