ci: Auto fix CI if bump failed

fix: add to_lance() and to_polars() stub methods for type-checkers (#2876 )
Adds `Table.to_lance()` and `Table.to_polars()` methods (non-abstract methods, defaulting to `NotImplementedError`) so type checkers like mypy, pyright and ty don’t flag them as unknown attributes on `Table`. Not making these abstract methods should keep existing remote/other `Table` implementations instantiable. This is non-breaking change to existing functionality and is purely for the purpose of pleasing static type-checkers like mypy, ty and pyright. <img width="626" height="134" alt="image" src="https://github.com/user-attachments/assets/f4619bca-a882-432b-bd23-ae8f189ff9e3" />
2025-12-24 22:09:58 +00:00 · 2025-12-24 20:06:36 +08:00 · 2025-12-18 12:55:07 -05:00 · 2025-12-17 06:59:29 +00:00 · 2025-12-17 06:58:52 +00:00 · 2025-12-16 22:58:04 -08:00
23 changed files with 576 additions and 178 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.23.0"
+current_version = "0.23.1-beta.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/.github/workflows/codex-autofix-ci.yml
+++ b/.github/workflows/codex-autofix-ci.yml
@@ -0,0 +1,297 @@
+name: Codex Autofix CI
+
+on:
+  check_suite:
+    types:
+      - completed
+
+permissions:
+  contents: write
+  pull-requests: write
+  actions: read
+
+concurrency:
+  group: codex-autofix-${{ github.event.check_suite.head_branch }}
+  cancel-in-progress: false
+
+jobs:
+  autofix:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Resolve PR and failing required checks
+        id: ctx
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          REPO: ${{ github.repository }}
+          SHA: ${{ github.event.check_suite.head_sha }}
+          HEAD_BRANCH: ${{ github.event.check_suite.head_branch }}
+          MAX_ATTEMPTS: "3"
+        run: |
+          set -euo pipefail
+
+          echo "Repository: $REPO"
+          echo "head_branch: $HEAD_BRANCH"
+          echo "head_sha: $SHA"
+
+          if [[ "$HEAD_BRANCH" != codex/update-lance-* ]]; then
+            echo "Skip: branch '$HEAD_BRANCH' does not match codex/update-lance-*"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          prs_json="$(gh api -H "Accept: application/vnd.github+json" "repos/$REPO/commits/$SHA/pulls")"
+          pr_json="$(echo "$prs_json" | jq -c '[.[] | select(.state=="open")] | .[0]')"
+          if [[ -z "$pr_json" || "$pr_json" == "null" ]]; then
+            echo "Skip: no open PR found for sha $SHA"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          pr_number="$(echo "$pr_json" | jq -r '.number')"
+          head_ref="$(echo "$pr_json" | jq -r '.head.ref')"
+          head_repo="$(echo "$pr_json" | jq -r '.head.repo.full_name')"
+          pr_head_sha="$(echo "$pr_json" | jq -r '.head.sha')"
+
+          if [[ "$head_repo" != "$REPO" ]]; then
+            echo "Skip: cross-repo PR ($head_repo != $REPO)"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          if [[ "$pr_head_sha" != "$SHA" ]]; then
+            echo "Skip: stale check_suite event (pr head sha $pr_head_sha != event sha $SHA)"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          set +e
+          checks_json="$(gh pr checks "$pr_number" --required --repo "$REPO" --json name,state,bucket,link,workflow)"
+          checks_rc=$?
+          set -e
+
+          if [[ "$checks_rc" -eq 8 ]]; then
+            echo "Skip: required checks still pending"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          if [[ "$checks_rc" -ne 0 ]]; then
+            echo "Skip: failed to query required checks (exit=$checks_rc)"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          fail_count="$(echo "$checks_json" | jq '[.[] | select(.bucket=="fail")] | length')"
+          if [[ "$fail_count" -eq 0 ]]; then
+            echo "Skip: no failing required checks"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          comments_json="$(gh api "repos/$REPO/issues/$pr_number/comments" --paginate)"
+          stopped_count="$(echo "$comments_json" | jq '[.[].body | select(test("<!-- codex-autofix stopped -->"))] | length')"
+          if [[ "$stopped_count" -gt 0 ]]; then
+            echo "Skip: codex-autofix already stopped for this PR"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          prior_attempts="$(echo "$comments_json" | jq '[.[].body | select(test("<!-- codex-autofix attempt:"))] | length')"
+          attempt="$((prior_attempts + 1))"
+
+          if [[ "$attempt" -gt "$MAX_ATTEMPTS" ]]; then
+            run_url="${GITHUB_SERVER_URL}/${REPO}/actions/runs/${GITHUB_RUN_ID}"
+            comment_file="$(mktemp /tmp/codex-autofix-comment.XXXXXX.md)"
+            {
+              printf '%s\n' '<!-- codex-autofix stopped -->'
+              printf '<!-- codex-autofix attempt: %s -->\n' "$attempt"
+              printf 'Codex autofix stopped: reached max attempts (%s).\n\n' "$MAX_ATTEMPTS"
+              printf -- '- Run: %s\n' "$run_url"
+              printf -- '- head_sha: `%s`\n' "$SHA"
+              printf -- '- head_ref: `%s`\n' "$head_ref"
+            } >"$comment_file"
+            gh pr comment "$pr_number" --repo "$REPO" --body-file "$comment_file"
+            echo "needs_fix=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          evidence_file="$(mktemp /tmp/codex-autofix-evidence.XXXXXX.txt)"
+          run_url="${GITHUB_SERVER_URL}/${REPO}/actions/runs/${GITHUB_RUN_ID}"
+
+          {
+            echo "PR: #$pr_number"
+            echo "head_ref: $head_ref"
+            echo "head_sha: $SHA"
+            echo "Run: $run_url"
+            echo ""
+            echo "Failing required checks:"
+            echo "$checks_json" | jq -r '.[] | select(.bucket=="fail") | "- \(.name) (\(.workflow // "unknown")): \(.link // "n/a")"'
+            echo ""
+          } > "$evidence_file"
+
+          while IFS= read -r row; do
+            name="$(echo "$row" | jq -r '.name')"
+            link="$(echo "$row" | jq -r '.link // empty')"
+            workflow="$(echo "$row" | jq -r '.workflow // "unknown"')"
+
+            {
+              echo "================================================================================"
+              echo "CHECK: $name"
+              echo "WORKFLOW: $workflow"
+              echo "LINK: ${link:-n/a}"
+            } >> "$evidence_file"
+
+            run_id=""
+            if [[ -n "$link" ]]; then
+              run_id="$(echo "$link" | sed -n 's#.*actions/runs/\\([0-9][0-9]*\\).*#\\1#p' | head -n 1 || true)"
+            fi
+
+            if [[ -z "$run_id" ]]; then
+              echo "LOGS: unavailable (no run id found in link)" >> "$evidence_file"
+              echo "" >> "$evidence_file"
+              continue
+            fi
+
+            echo "LOGS: gh run view $run_id --log-failed (tail -c 20000)" >> "$evidence_file"
+            set +e
+            gh run view "$run_id" --repo "$REPO" --log-failed 2>/dev/null | tail -c 20000 >> "$evidence_file"
+            echo "" >> "$evidence_file"
+            set -e
+          done < <(echo "$checks_json" | jq -c '.[] | select(.bucket=="fail")')
+
+          comment_file="$(mktemp /tmp/codex-autofix-comment.XXXXXX.md)"
+          {
+            printf '<!-- codex-autofix attempt: %s -->\n' "$attempt"
+            printf 'Starting Codex autofix attempt %s.\n\n' "$attempt"
+            printf -- '- Run: %s\n' "$run_url"
+            printf -- '- head_sha: `%s`\n' "$SHA"
+            printf -- '- head_ref: `%s`\n' "$head_ref"
+            printf -- '- Failing required checks: %s\n' "$fail_count"
+          } >"$comment_file"
+          gh pr comment "$pr_number" --repo "$REPO" --body-file "$comment_file"
+
+          {
+            echo "needs_fix=true"
+            echo "pr_number=$pr_number"
+            echo "head_ref=$head_ref"
+            echo "attempt=$attempt"
+            echo "evidence_file=$evidence_file"
+          } >> "$GITHUB_OUTPUT"
+
+      - name: Checkout PR branch
+        if: steps.ctx.outputs.needs_fix == 'true'
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ steps.ctx.outputs.head_ref }}
+          token: ${{ secrets.ROBOT_TOKEN }}
+          persist-credentials: true
+
+      - name: Configure git
+        if: steps.ctx.outputs.needs_fix == 'true'
+        run: |
+          git config user.name "lancedb automation"
+          git config user.email "robot@lancedb.com"
+
+      - name: Set up Node.js
+        if: steps.ctx.outputs.needs_fix == 'true'
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Install Codex CLI
+        if: steps.ctx.outputs.needs_fix == 'true'
+        run: npm install -g @openai/codex
+
+      - name: Install Rust toolchain
+        if: steps.ctx.outputs.needs_fix == 'true'
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          toolchain: stable
+          components: clippy, rustfmt
+
+      - name: Install system dependencies
+        if: steps.ctx.outputs.needs_fix == 'true'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y protobuf-compiler libssl-dev
+
+      - name: Run Codex to fix failing CI
+        if: steps.ctx.outputs.needs_fix == 'true'
+        env:
+          PR_NUMBER: ${{ steps.ctx.outputs.pr_number }}
+          HEAD_REF: ${{ steps.ctx.outputs.head_ref }}
+          ATTEMPT: ${{ steps.ctx.outputs.attempt }}
+          EVIDENCE_FILE: ${{ steps.ctx.outputs.evidence_file }}
+          GITHUB_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
+        run: |
+          set -euo pipefail
+
+          prompt_file="/tmp/codex-prompt.txt"
+          {
+            printf 'You are running inside the lancedb repository on a GitHub Actions runner.\n'
+            printf 'Your task is to fix failing required CI checks for pull request #%s on branch %s.\n\n' "$PR_NUMBER" "$HEAD_REF"
+            printf 'Goal:\n'
+            printf -- '- Make the smallest change necessary so that all required checks pass.\n\n'
+            printf 'Evidence (generated from GitHub checks and logs):\n'
+            printf '---\n'
+            cat "${EVIDENCE_FILE}"
+            printf '\n---\n\n'
+            printf 'Follow these steps exactly:\n'
+            printf '1. Identify the root cause from the evidence and repository state.\n'
+            printf '2. Make changes to fix the failures.\n'
+            printf '3. Run the relevant local commands that correspond to the failing checks until they succeed.\n'
+            printf '   If unsure, start with:\n'
+            printf '   - cargo fmt --all -- --check\n'
+            printf '   - cargo clippy --profile ci --workspace --tests --all-features -- -D warnings\n'
+            printf '4. Ensure the repository is clean except for intentional changes (git status --short, git diff).\n'
+            printf '5. Create a commit with message "fix: codex autofix (attempt %s)".\n' "$ATTEMPT"
+            printf '6. Push to origin branch "%s" (use --force-with-lease only if required).\n' "$HEAD_REF"
+            printf '7. Print the commands you ran and their results, plus git status --short and git log -1 --oneline.\n\n'
+            printf 'Constraints:\n'
+            printf -- '- Do not create a new pull request.\n'
+            printf -- '- Do not merge.\n'
+            printf -- '- Avoid modifying GitHub workflow files unless strictly required to fix CI for this PR.\n'
+          } >"$prompt_file"
+
+          printenv OPENAI_API_KEY | codex login --with-api-key
+          codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat "$prompt_file")"
+
+      - name: Ensure branch is pushed
+        if: steps.ctx.outputs.needs_fix == 'true'
+        env:
+          HEAD_REF: ${{ steps.ctx.outputs.head_ref }}
+        run: |
+          set -euo pipefail
+          if git diff --quiet && git diff --cached --quiet; then
+            echo "Working tree clean."
+          else
+            git add -A
+            git commit -m "fix: codex autofix (post-run)" || true
+          fi
+          git push origin "HEAD:${HEAD_REF}" --force-with-lease
+
+      - name: Comment result
+        if: steps.ctx.outputs.needs_fix == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          REPO: ${{ github.repository }}
+          PR_NUMBER: ${{ steps.ctx.outputs.pr_number }}
+          ATTEMPT: ${{ steps.ctx.outputs.attempt }}
+        run: |
+          set -euo pipefail
+          run_url="${GITHUB_SERVER_URL}/${REPO}/actions/runs/${GITHUB_RUN_ID}"
+          sha="$(git rev-parse HEAD)"
+          summary="$(git log -1 --oneline || true)"
+          status="$(git status --short || true)"
+          comment_file="$(mktemp /tmp/codex-autofix-comment.XXXXXX.md)"
+          {
+            printf 'Codex autofix attempt %s finished.\n\n' "$ATTEMPT"
+            printf -- '- Run: %s\n' "$run_url"
+            printf -- '- head_sha: `%s`\n' "$sha"
+            printf -- '- Last commit: %s\n\n' "$summary"
+            printf '```\n%s\n```\n' "$status"
+          } >"$comment_file"
+          gh pr comment "$PR_NUMBER" --repo "$REPO" --body-file "$comment_file"
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -4970,7 +4970,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.23.0"
+version = "0.23.1-beta.1"
 dependencies = [
 "ahash",
 "anyhow",
@@ -5049,7 +5049,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.23.0"
+version = "0.23.1-beta.1"
 dependencies = [
 "arrow-array",
 "arrow-ipc",
@@ -5069,7 +5069,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.26.0"
+version = "0.26.1-beta.1"
 dependencies = [
 "arrow",
 "async-trait",
--- a/docs/src/java/java.md
+++ b/docs/src/java/java.md
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.23.0</version>
+    <version>0.23.1-beta.1</version>
 </dependency>
 ```

--- a/java/lancedb-core/pom.xml
+++ b/java/lancedb-core/pom.xml
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.23.0-final.0</version>
+      <version>0.23.1-beta.1</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

--- a/java/pom.xml
+++ b/java/pom.xml
@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.23.0-final.0</version>
+    <version>0.23.1-beta.1</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.23.0"
+version = "0.23.1-beta.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
--- a/nodejs/npm/darwin-arm64/package.json
+++ b/nodejs/npm/darwin-arm64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
--- a/nodejs/npm/darwin-x64/package.json
+++ b/nodejs/npm/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
--- a/nodejs/npm/linux-arm64-gnu/package.json
+++ b/nodejs/npm/linux-arm64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
--- a/nodejs/npm/linux-arm64-musl/package.json
+++ b/nodejs/npm/linux-arm64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
--- a/nodejs/npm/linux-x64-gnu/package.json
+++ b/nodejs/npm/linux-x64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
--- a/nodejs/npm/linux-x64-musl/package.json
+++ b/nodejs/npm/linux-x64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
--- a/nodejs/npm/win32-arm64-msvc/package.json
+++ b/nodejs/npm/win32-arm64-msvc/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.23.0",
+  "version": "0.23.1-beta.1",
  "os": [
    "win32"
  ],
--- a/nodejs/npm/win32-x64-msvc/package.json
+++ b/nodejs/npm/win32-x64-msvc/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.23.0",
+	"version": "0.23.1-beta.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
--- a/nodejs/package-lock.json
+++ b/nodejs/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.23.0",
+  "version": "0.23.1-beta.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.23.0",
+      "version": "0.23.1-beta.1",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.23.0",
+  "version": "0.23.1-beta.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/python/.bumpversion.toml
+++ b/python/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.26.1-beta.0"
+current_version = "0.26.1-beta.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.26.1-beta.0"
+version = "0.26.1-beta.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
--- a/python/python/lancedb/table.py
+++ b/python/python/lancedb/table.py
@@ -684,6 +684,24 @@ class Table(ABC):
        """
        raise NotImplementedError

+    def to_lance(self, **kwargs) -> lance.LanceDataset:
+        """Return the table as a lance.LanceDataset.
+
+        Returns
+        -------
+        lance.LanceDataset
+        """
+        raise NotImplementedError
+
+    def to_polars(self, **kwargs) -> "pl.DataFrame":
+        """Return the table as a polars.DataFrame.
+
+        Returns
+        -------
+        polars.DataFrame
+        """
+        raise NotImplementedError
+
    def create_index(
        self,
        metric="l2",
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.23.0"
+version = "0.23.1-beta.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/database/namespace.rs
+++ b/rust/lancedb/src/database/namespace.rs
@@ -7,7 +7,6 @@ use std::collections::HashMap;
 use std::sync::Arc;

 use async_trait::async_trait;
-use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsProvider};
 use lance_namespace::{
    models::{
        CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
@@ -19,13 +18,13 @@ use lance_namespace::{
 };
 use lance_namespace_impls::ConnectBuilder;

-use crate::connection::ConnectRequest;
 use crate::database::ReadConsistency;
 use crate::error::{Error, Result};
+use crate::table::NativeTable;

 use super::{
-    listing::ListingDatabase, BaseTable, CloneTableRequest, CreateTableMode,
-    CreateTableRequest as DbCreateTableRequest, Database, OpenTableRequest, TableNamesRequest,
+    BaseTable, CloneTableRequest, CreateTableMode, CreateTableRequest as DbCreateTableRequest,
+    Database, OpenTableRequest, TableNamesRequest,
 };

 /// A database implementation that uses lance-namespace for table management
@@ -90,51 +89,6 @@ impl std::fmt::Display for LanceNamespaceDatabase {
    }
 }

-impl LanceNamespaceDatabase {
-    /// Create a temporary listing database for the given location
-    ///
-    /// Merges storage options with priority: connection < user < namespace
-    async fn create_listing_database(
-        &self,
-        location: &str,
-        table_id: Vec<String>,
-        user_storage_options: Option<&HashMap<String, String>>,
-        response_storage_options: Option<&HashMap<String, String>>,
-    ) -> Result<ListingDatabase> {
-        // Merge storage options: connection < user < namespace
-        let mut merged_storage_options = self.storage_options.clone();
-        if let Some(opts) = user_storage_options {
-            merged_storage_options.extend(opts.clone());
-        }
-        if let Some(opts) = response_storage_options {
-            merged_storage_options.extend(opts.clone());
-        }
-
-        let request = ConnectRequest {
-            uri: location.to_string(),
-            #[cfg(feature = "remote")]
-            client_config: Default::default(),
-            options: merged_storage_options,
-            read_consistency_interval: self.read_consistency_interval,
-            session: self.session.clone(),
-        };
-
-        let mut listing_db = ListingDatabase::connect_with_options(&request).await?;
-
-        // Create storage options provider only if namespace returned storage options
-        // (not just user-provided options)
-        if response_storage_options.is_some() {
-            let provider = Arc::new(LanceNamespaceStorageOptionsProvider::new(
-                self.namespace.clone(),
-                table_id,
-            )) as Arc<dyn StorageOptionsProvider>;
-            listing_db.storage_options_provider = Some(provider);
-        }
-
-        Ok(listing_db)
-    }
-}
-
 #[async_trait]
 impl Database for LanceNamespaceDatabase {
    fn uri(&self) -> &str {
@@ -195,14 +149,6 @@ impl Database for LanceNamespaceDatabase {
    }

    async fn create_table(&self, request: DbCreateTableRequest) -> Result<Arc<dyn BaseTable>> {
-        // Extract user-provided storage options from request
-        let user_storage_options = request
-            .write_options
-            .lance_write_params
-            .as_ref()
-            .and_then(|lwp| lwp.store_params.as_ref())
-            .and_then(|sp| sp.storage_options.as_ref());
-
        let mut table_id = request.namespace.clone();
        table_id.push(request.name.clone());
        let describe_request = DescribeTableRequest {
@@ -235,34 +181,20 @@ impl Database for LanceNamespaceDatabase {
                }
            }
            CreateTableMode::ExistOk(_) => {
-                if let Ok(response) = describe_result {
-                    let location = response.location.ok_or_else(|| Error::Runtime {
-                        message: "Table location is missing from namespace response".to_string(),
-                    })?;
+                if describe_result.is_ok() {
+                    let native_table = NativeTable::open_from_namespace(
+                        self.namespace.clone(),
+                        &request.name,
+                        request.namespace.clone(),
+                        None,
+                        None,
+                        self.read_consistency_interval,
+                        self.server_side_query_enabled,
+                        self.session.clone(),
+                    )
+                    .await?;

-                    let listing_db = self
-                        .create_listing_database(
-                            &location,
-                            table_id.clone(),
-                            user_storage_options,
-                            response.storage_options.as_ref(),
-                        )
-                        .await?;
-
-                    let namespace_client = self
-                        .server_side_query_enabled
-                        .then(|| self.namespace.clone());
-
-                    return listing_db
-                        .open_table(OpenTableRequest {
-                            name: request.name.clone(),
-                            namespace: request.namespace.clone(),
-                            index_cache_size: None,
-                            lance_read_params: None,
-                            location: Some(location),
-                            namespace_client,
-                        })
-                        .await;
+                    return Ok(Arc::new(native_table));
                }
            }
        }
@@ -294,82 +226,37 @@ impl Database for LanceNamespaceDatabase {
                message: "Table location is missing from create_empty_table response".to_string(),
            })?;

-        let listing_db = self
-            .create_listing_database(
-                &location,
-                table_id.clone(),
-                user_storage_options,
-                create_empty_response.storage_options.as_ref(),
-            )
-            .await?;
+        let native_table = NativeTable::create_from_namespace(
+            self.namespace.clone(),
+            &location,
+            &request.name,
+            request.namespace.clone(),
+            request.data,
+            None, // write_store_wrapper not used for namespace connections
+            request.write_options.lance_write_params,
+            self.read_consistency_interval,
+            self.server_side_query_enabled,
+            self.session.clone(),
+        )
+        .await?;

-        let namespace_client = self
-            .server_side_query_enabled
-            .then(|| self.namespace.clone());
-
-        let create_request = DbCreateTableRequest {
-            name: request.name,
-            namespace: request.namespace,
-            data: request.data,
-            mode: request.mode,
-            write_options: request.write_options,
-            location: Some(location),
-            namespace_client,
-        };
-
-        listing_db.create_table(create_request).await
+        Ok(Arc::new(native_table))
    }

    async fn open_table(&self, request: OpenTableRequest) -> Result<Arc<dyn BaseTable>> {
-        // Extract user-provided storage options from request
-        let user_storage_options = request
-            .lance_read_params
-            .as_ref()
-            .and_then(|lrp| lrp.store_options.as_ref())
-            .and_then(|so| so.storage_options.as_ref());
+        let native_table = NativeTable::open_from_namespace(
+            self.namespace.clone(),
+            &request.name,
+            request.namespace.clone(),
+            None, // write_store_wrapper not used for namespace connections
+            request.lance_read_params,
+            self.read_consistency_interval,
+            self.server_side_query_enabled,
+            self.session.clone(),
+        )
+        .await?;

-        let mut table_id = request.namespace.clone();
-        table_id.push(request.name.clone());
-
-        let describe_request = DescribeTableRequest {
-            id: Some(table_id.clone()),
-            version: None,
-        };
-        let response = self
-            .namespace
-            .describe_table(describe_request)
-            .await
-            .map_err(|e| Error::Runtime {
-                message: format!("Failed to describe table: {}", e),
-            })?;
-
-        let location = response.location.ok_or_else(|| Error::Runtime {
-            message: "Table location is missing from namespace response".to_string(),
-        })?;
-
-        let listing_db = self
-            .create_listing_database(
-                &location,
-                table_id.clone(),
-                user_storage_options,
-                response.storage_options.as_ref(),
-            )
-            .await?;
-
-        let namespace_client = self
-            .server_side_query_enabled
-            .then(|| self.namespace.clone());
-
-        let open_request = OpenTableRequest {
-            name: request.name.clone(),
-            namespace: request.namespace.clone(),
-            index_cache_size: request.index_cache_size,
-            lance_read_params: request.lance_read_params,
-            location: Some(location),
-            namespace_client,
-        };
-
-        listing_db.open_table(open_request).await
+        Ok(Arc::new(native_table))
    }

    async fn clone_table(&self, _request: CloneTableRequest) -> Result<Arc<dyn BaseTable>> {
--- a/rust/lancedb/src/table.rs
+++ b/rust/lancedb/src/table.rs
@@ -29,7 +29,7 @@ use lance::dataset::{
 use lance::dataset::{MergeInsertBuilder as LanceMergeInsertBuilder, WhenNotMatchedBySource};
 use lance::index::vector::utils::infer_vector_dim;
 use lance::index::vector::VectorIndexParams;
-use lance::io::WrappingObjectStore;
+use lance::io::{ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::exec::{analyze_plan as lance_analyze_plan, execute_plan};
 use lance_datafusion::utils::StreamingWriteSource;
 use lance_index::scalar::{BuiltinIndexType, ScalarIndexParams};
@@ -40,6 +40,7 @@ use lance_index::vector::pq::PQBuildParams;
 use lance_index::vector::sq::builder::SQBuildParams;
 use lance_index::DatasetIndexExt;
 use lance_index::IndexType;
+use lance_io::object_store::LanceNamespaceStorageOptionsProvider;
 use lance_namespace::models::{
    QueryTableRequest as NsQueryTableRequest, QueryTableRequestFullTextQuery,
    QueryTableRequestVector, StringFtsQuery,
@@ -1611,6 +1612,105 @@ impl NativeTable {
        self
    }

+    /// Opens an existing Table using a namespace client.
+    ///
+    /// This method uses `DatasetBuilder::from_namespace` to open the table, which
+    /// automatically fetches the table location and storage options from the namespace.
+    /// This eliminates the need to pre-fetch and merge storage options before opening.
+    ///
+    /// # Arguments
+    ///
+    /// * `namespace_client` - The namespace client to use for fetching table metadata
+    /// * `name` - The table name
+    /// * `namespace` - The namespace path (e.g., vec!["parent", "child"])
+    /// * `write_store_wrapper` - Optional wrapper for the object store on write path
+    /// * `params` - Optional read parameters
+    /// * `read_consistency_interval` - Optional interval for read consistency
+    /// * `server_side_query_enabled` - Whether to enable server-side query execution.
+    ///   When true, the namespace_client will be stored and queries will be executed
+    ///   on the namespace server. When false, the namespace is only used for opening
+    ///   the table, and queries are executed locally.
+    /// * `session` - Optional session for object stores and caching
+    ///
+    /// # Returns
+    ///
+    /// * A [NativeTable] object.
+    #[allow(clippy::too_many_arguments)]
+    pub async fn open_from_namespace(
+        namespace_client: Arc<dyn LanceNamespace>,
+        name: &str,
+        namespace: Vec<String>,
+        write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
+        params: Option<ReadParams>,
+        read_consistency_interval: Option<std::time::Duration>,
+        server_side_query_enabled: bool,
+        session: Option<Arc<lance::session::Session>>,
+    ) -> Result<Self> {
+        let mut params = params.unwrap_or_default();
+
+        // Set the session in read params
+        if let Some(sess) = session {
+            params.session(sess);
+        }
+
+        // patch the params if we have a write store wrapper
+        let params = match write_store_wrapper.clone() {
+            Some(wrapper) => params.patch_with_store_wrapper(wrapper)?,
+            None => params,
+        };
+
+        // Build table_id from namespace + name
+        let mut table_id = namespace.clone();
+        table_id.push(name.to_string());
+
+        // Use DatasetBuilder::from_namespace which automatically fetches location
+        // and storage options from the namespace
+        let builder = DatasetBuilder::from_namespace(
+            namespace_client.clone(),
+            table_id,
+            false, // Don't ignore namespace storage options
+        )
+        .await
+        .map_err(|e| match e {
+            lance::Error::Namespace { source, .. } => Error::Runtime {
+                message: format!("Failed to get table info from namespace: {:?}", source),
+            },
+            source => Error::Lance { source },
+        })?;
+
+        let dataset = builder
+            .with_read_params(params)
+            .load()
+            .await
+            .map_err(|e| match e {
+                lance::Error::DatasetNotFound { .. } => Error::TableNotFound {
+                    name: name.to_string(),
+                    source: Box::new(e),
+                },
+                source => Error::Lance { source },
+            })?;
+
+        let uri = dataset.uri().to_string();
+        let dataset = DatasetConsistencyWrapper::new_latest(dataset, read_consistency_interval);
+        let id = Self::build_id(&namespace, name);
+
+        let stored_namespace_client = if server_side_query_enabled {
+            Some(namespace_client)
+        } else {
+            None
+        };
+
+        Ok(Self {
+            name: name.to_string(),
+            namespace,
+            id,
+            uri,
+            dataset,
+            read_consistency_interval,
+            namespace_client: stored_namespace_client,
+        })
+    }
+
    fn get_table_name(uri: &str) -> Result<String> {
        let path = Path::new(uri);
        let name = path
@@ -1722,6 +1822,102 @@ impl NativeTable {
        .await
    }

+    /// Creates a new Table using a namespace client for storage options.
+    ///
+    /// This method sets up a `StorageOptionsProvider` from the namespace client,
+    /// enabling automatic credential refresh for cloud storage. The namespace
+    /// is used for:
+    /// 1. Setting up storage options provider for credential vending
+    /// 2. Optionally enabling server-side query execution
+    ///
+    /// # Arguments
+    ///
+    /// * `namespace_client` - The namespace client to use for storage options
+    /// * `uri` - The URI to the table (obtained from create_empty_table response)
+    /// * `name` - The table name
+    /// * `namespace` - The namespace path (e.g., vec!["parent", "child"])
+    /// * `batches` - RecordBatch to be saved in the database
+    /// * `write_store_wrapper` - Optional wrapper for the object store on write path
+    /// * `params` - Optional write parameters
+    /// * `read_consistency_interval` - Optional interval for read consistency
+    /// * `server_side_query_enabled` - Whether to enable server-side query execution
+    ///
+    /// # Returns
+    ///
+    /// * A [NativeTable] object.
+    #[allow(clippy::too_many_arguments)]
+    pub async fn create_from_namespace(
+        namespace_client: Arc<dyn LanceNamespace>,
+        uri: &str,
+        name: &str,
+        namespace: Vec<String>,
+        batches: impl StreamingWriteSource,
+        write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
+        params: Option<WriteParams>,
+        read_consistency_interval: Option<std::time::Duration>,
+        server_side_query_enabled: bool,
+        session: Option<Arc<lance::session::Session>>,
+    ) -> Result<Self> {
+        // Build table_id from namespace + name for the storage options provider
+        let mut table_id = namespace.clone();
+        table_id.push(name.to_string());
+
+        // Set up storage options provider from namespace
+        let storage_options_provider = Arc::new(LanceNamespaceStorageOptionsProvider::new(
+            namespace_client.clone(),
+            table_id,
+        ));
+
+        // Start with provided params or defaults
+        let mut params = params.unwrap_or_default();
+
+        // Set the session in write params
+        if let Some(sess) = session {
+            params.session = Some(sess);
+        }
+
+        // Ensure store_params exists and set the storage options provider
+        let store_params = params
+            .store_params
+            .get_or_insert_with(ObjectStoreParams::default);
+        store_params.storage_options_provider = Some(storage_options_provider);
+
+        // Patch the params if we have a write store wrapper
+        let params = match write_store_wrapper.clone() {
+            Some(wrapper) => params.patch_with_store_wrapper(wrapper)?,
+            None => params,
+        };
+
+        let insert_builder = InsertBuilder::new(uri).with_params(&params);
+        let dataset = insert_builder
+            .execute_stream(batches)
+            .await
+            .map_err(|e| match e {
+                lance::Error::DatasetAlreadyExists { .. } => Error::TableAlreadyExists {
+                    name: name.to_string(),
+                },
+                source => Error::Lance { source },
+            })?;
+
+        let id = Self::build_id(&namespace, name);
+
+        let stored_namespace_client = if server_side_query_enabled {
+            Some(namespace_client)
+        } else {
+            None
+        };
+
+        Ok(Self {
+            name: name.to_string(),
+            namespace,
+            id,
+            uri: uri.to_string(),
+            dataset: DatasetConsistencyWrapper::new_latest(dataset, read_consistency_interval),
+            read_consistency_interval,
+            namespace_client: stored_namespace_client,
+        })
+    }
+
    async fn optimize_indices(&self, options: &OptimizeOptions) -> Result<()> {
        info!("LanceDB: optimizing indices: {:?}", options);
        self.dataset
Author	SHA1	Message	Date
Xuanwo	523030aa2f	ci: Auto fix CI if bump failed	2025-12-24 20:06:36 +08:00
Prashanth Rao	8ae4f42fbe	fix: add to_lance() and to_polars() stub methods for type-checkers (#2876 ) Adds `Table.to_lance()` and `Table.to_polars()` methods (non-abstract methods, defaulting to `NotImplementedError`) so type checkers like mypy, pyright and ty don’t flag them as unknown attributes on `Table`. Not making these abstract methods should keep existing remote/other `Table` implementations instantiable. This is non-breaking change to existing functionality and is purely for the purpose of pleasing static type-checkers like mypy, ty and pyright. <img width="626" height="134" alt="image" src="https://github.com/user-attachments/assets/f4619bca-a882-432b-bd23-ae8f189ff9e3" />	2025-12-18 12:55:07 -05:00
Lance Release	0667fa38d4	Bump version: 0.23.1-beta.0 → 0.23.1-beta.1	2025-12-17 06:59:29 +00:00
Lance Release	30108c0b1f	Bump version: 0.26.1-beta.0 → 0.26.1-beta.1	2025-12-17 06:58:52 +00:00
Jack Ye	1628f7e3f3	fix: pass namespace storage options provider into native table (#2873 ) Previously the native table is created with static credentials and could not auto-refresh credentials when expired.	2025-12-16 22:58:04 -08:00
Lance Release	2fd712312f	Bump version: 0.23.0 → 0.23.1-beta.0	2025-12-17 03:30:51 +00:00