diff --git a/.github/workflows/docs-link-check.yml b/.github/workflows/docs-link-check.yml
new file mode 100644
index 000000000..0e22100eb
--- /dev/null
+++ b/.github/workflows/docs-link-check.yml
@@ -0,0 +1,222 @@
+name: Check doc links
+
+# Checking external links is inherently noisy: third-party sites rate-limit
+# automated clients, reject non-browser user agents, and go down temporarily.
+# Blocking pull requests on that trades a lot of false failures for very little
+# signal, so this runs on a schedule and reports findings in a single tracking
+# issue instead of failing anyone's build.
+on:
+  schedule:
+    - cron: "0 7 * * *"
+  workflow_dispatch:
+
+# The report lives in one repository-global issue, so runs must not overlap: a
+# lookup racing a create produces duplicate issues, and a healthy run closing
+# the issue while a failing run only rewrites its body would leave a broken
+# report closed. The group is deliberately ref-independent so that a manual
+# dispatch serializes against the scheduled run.
+concurrency:
+  group: docs-link-check
+  cancel-in-progress: false
+
+permissions: {}
+
+env:
+  REPORT_TITLE: "Docs link checker report"
+
+jobs:
+  scan:
+    name: Scan links
+    runs-on: ubuntu-24.04
+    # lychee-action is pinned by SHA, but its wrapper downloads the lychee
+    # release tarball at run time without verifying a digest, and hands the
+    # resulting binary a GitHub token. Release assets remain replaceable, so
+    # that binary is confined to a job whose token can only read public
+    # content; everything that writes runs in the report job below.
+    permissions:
+      contents: read
+    outputs:
+      exit_code: ${{ steps.lychee.outputs.exit_code }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          # workflow_dispatch can run from any ref, but the report is
+          # repository-global. Always measure the default branch so a manual
+          # run from a topic branch cannot close a report that main warrants,
+          # or overwrite it with branch-only findings.
+          ref: ${{ github.event.repository.default_branch }}
+          persist-credentials: false
+
+      - name: Check links
+        id: lychee
+        uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
+        with:
+          # Restricted to http(s) on purpose. Much of docs/src is generated
+          # API reference (the js/ tree comes from `npm run docs` in nodejs)
+          # and the hand-written pages use mkdocstrings cross-references and
+          # nav-relative paths that only resolve in the site mkdocs builds,
+          # not in this checkout, so relative links would be reported as
+          # broken on every run.
+          args: >-
+            --scheme https
+            --scheme http
+            --no-progress
+            --max-retries 3
+            --timeout 20
+            'docs/src/**/*.md'
+          format: json
+          output: ./lychee/out.json
+          jobSummary: false
+          # The report, not a red build, is the signal for broken links. The
+          # validation step below still fails the run if the check itself
+          # breaks.
+          fail: false
+
+      - name: Validate report
+        # lychee does not reserve exit code 2 for broken links: its CLI
+        # parser also exits 2 on an invalid option, before any link was
+        # checked or any report written. Only a parseable report whose
+        # counts agree with the exit code counts as a link verdict; anything
+        # else fails here, and the report job below is skipped entirely, so
+        # the tracking issue is never touched. Exit 2 covers timeouts as
+        # well as errors, and a timed-out host is exactly the transient
+        # unavailability this report exists to surface, so both count as
+        # findings. Requiring total > 0 also catches a glob that silently
+        # stopped matching any file.
+        if: steps.lychee.outputs.exit_code == 0 || steps.lychee.outputs.exit_code == 2
+        env:
+          EXIT_CODE: ${{ steps.lychee.outputs.exit_code }}
+        run: |
+          jq -e --argjson code "$EXIT_CODE" '
+            (.total > 0) and
+            (if $code == 0
+             then .errors == 0 and .timeouts == 0
+               and (.error_map | length == 0) and (.timeout_map | length == 0)
+             else (.errors + .timeouts) > 0
+               and ((.error_map | length) + (.timeout_map | length)) > 0
+             end)
+          ' ./lychee/out.json
+
+      - name: Upload report
+        if: steps.lychee.outputs.exit_code == 2
+        uses: actions/upload-artifact@v7
+        with:
+          name: link-report
+          path: ./lychee/out.json
+          retention-days: 7
+
+  report:
+    name: Update report issue
+    needs: scan
+    runs-on: ubuntu-24.04
+    # Deliberately no checkout: this job needs the report artifact and the
+    # issues API, not the repository contents.
+    permissions:
+      issues: write
+    env:
+      EXIT_CODE: ${{ needs.scan.outputs.exit_code }}
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - name: Classify checker result
+        # lychee exits 0 when every link resolves and 2 when links fail,
+        # both already cross-checked against the report by the scan job's
+        # validation step. Anything else (1 runtime, 3 bad config) means the
+        # check never produced a link verdict, which must surface as a failed
+        # run rather than be published as "broken documentation links".
+        run: |
+          case "$EXIT_CODE" in
+            0|2)
+              echo "lychee exit code $EXIT_CODE"
+              ;;
+            *)
+              echo "::error::lychee exited with '$EXIT_CODE': the link check did not complete. Leaving the report issue untouched."
+              exit 1
+              ;;
+          esac
+
+      - name: Find existing report issue
+        id: report
+        # Matched on title alone, and through search rather than a listing:
+        # the issue action applies labels in a separate call after creating the
+        # issue, so a label filter misses a half-created report, and this
+        # repository has far more open issues than one listing page holds.
+        # Closed issues are included because a healthy run closes the report:
+        # an open-only lookup would forget that identity and the next failing
+        # run would open a duplicate. The oldest match stays the canonical
+        # report and is reopened below when links break again.
+        run: |
+          match=$(gh issue list --repo "$GITHUB_REPOSITORY" --state all \
+            --search "in:title \"$REPORT_TITLE\" author:app/github-actions" \
+            --limit 50 --json number,title,state \
+            --jq "[.[] | select(.title == \"$REPORT_TITLE\")] | sort_by(.number) | first // empty")
+          echo "number=$(jq -r '.number // empty' <<<"$match")" >> "$GITHUB_OUTPUT"
+          echo "state=$(jq -r '.state // empty' <<<"$match")" >> "$GITHUB_OUTPUT"
+
+      - name: Download report
+        if: env.EXIT_CODE == 2
+        uses: actions/download-artifact@v8
+        with:
+          name: link-report
+          path: ./lychee
+
+      - name: Compose report
+        if: env.EXIT_CODE == 2
+        run: |
+          run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
+          {
+            echo "Broken documentation links found by [\`$GITHUB_WORKFLOW\`]($run_url)."
+            echo
+            echo "This issue is rewritten by every scheduled run and closed automatically once all links resolve."
+            echo
+            echo "Entries can be false positives: some sites rate-limit or block automated clients while working fine in a browser. Confirm before editing the docs, and add persistent offenders to \`--exclude\` in \`.github/workflows/docs-link-check.yml\`."
+            echo
+            # Timeouts are reported alongside errors: entries land in
+            # timeout_map with a status text instead of an HTTP code.
+            jq -r '
+              "\(.errors) of \(.total) links failed, \(.timeouts) timed out.",
+              "",
+              ([(.error_map | to_entries[]), (.timeout_map | to_entries[])]
+               | group_by(.key)[] |
+                "### Errors in \(.[0].key)",
+                "",
+                (map(.value[])[] | "* [\(.status.code // .status.text // "ERR")] <\(.url)> — \(.status.details // .status.text // "unknown error")"),
+                "")
+            ' ./lychee/out.json
+          } > ./lychee/issue.md
+
+      - name: Reopen report issue
+        # A healthy run closes the report, and the issue action below only
+        # rewrites the body of whatever number it is given. Without an
+        # explicit reopen, the 2 -> 0 -> 2 sequence would keep rewriting a
+        # closed issue while links are broken. A CLOSED state implies the
+        # lookup found a canonical issue, so no separate emptiness check.
+        if: env.EXIT_CODE == 2 && steps.report.outputs.state == 'CLOSED'
+        env:
+          ISSUE_NUMBER: ${{ steps.report.outputs.number }}
+        run: |
+          run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
+          gh issue reopen "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \
+            --comment "Broken documentation links found again in [the latest run]($run_url)."
+
+      - name: Report broken links
+        if: env.EXIT_CODE == 2
+        uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v6.0.0
+        with:
+          # Empty on the first failing run, which creates the issue; afterwards
+          # the same issue is updated in place.
+          issue-number: ${{ steps.report.outputs.number }}
+          title: ${{ env.REPORT_TITLE }}
+          content-filepath: ./lychee/issue.md
+          labels: documentation
+
+      - name: Close report issue once links are healthy
+        # An OPEN state implies the lookup found a canonical issue; a report
+        # that is already closed needs nothing.
+        if: env.EXIT_CODE == 0 && steps.report.outputs.state == 'OPEN'
+        env:
+          ISSUE_NUMBER: ${{ steps.report.outputs.number }}
+        run: |
+          run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
+          gh issue close "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \
+            --comment "All documentation links resolved in [the latest run]($run_url)."
diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index 1a0b65c4a..471da43e0 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -296,16 +296,18 @@ jobs:
           cargo update -p aws-types --precise 1.3.9
           cargo update -p aws-sigv4 --precise 1.3.5
           cargo update -p aws-credential-types --precise 1.2.8
-          cargo update -p aws-smithy-checksums --precise 0.63.9
+          # aws-smithy-checksums must stay at or above 0.63.13: OpenDAL's S3
+          # service needs crc-fast ~1.9, and older releases pin it to ~1.3.
+          cargo update -p aws-smithy-checksums --precise 0.63.13
           cargo update -p aws-smithy-runtime --precise 1.9.3
-          cargo update -p aws-smithy-http --precise 0.62.4
-          cargo update -p aws-smithy-eventstream --precise 0.60.12
+          cargo update -p aws-smithy-http --precise 0.62.6
+          cargo update -p aws-smithy-eventstream --precise 0.60.14
           cargo update -p aws-smithy-http-client --precise 1.1.3
           cargo update -p aws-smithy-observability --precise 0.1.4
           cargo update -p aws-smithy-query --precise 0.60.8
-          cargo update -p aws-smithy-runtime-api --precise 1.9.1
-          cargo update -p aws-smithy-async --precise 1.2.6
-          cargo update -p aws-smithy-types --precise 1.3.5
+          cargo update -p aws-smithy-runtime-api --precise 1.9.3
+          cargo update -p aws-smithy-async --precise 1.2.7
+          cargo update -p aws-smithy-types --precise 1.3.6
           cargo update -p aws-smithy-xml --precise 0.60.11
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
diff --git a/Cargo.lock b/Cargo.lock
index 995424b20..93e16c06d 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -775,7 +775,7 @@ dependencies = [
  "http 0.2.12",
  "http 1.5.0",
  "http-body 1.1.0",
- "lru",
+ "lru 0.16.4",
  "percent-encoding",
  "regex-lite",
  "sha2 0.11.0",
@@ -1241,6 +1241,12 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
 
+[[package]]
+name = "base64"
+version = "0.23.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"
+
 [[package]]
 name = "base64-simd"
 version = "0.8.0"
@@ -1964,15 +1970,6 @@ dependencies = [
  "spin 0.10.1",
 ]
 
-[[package]]
-name = "crc32c"
-version = "0.6.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3a47af21622d091a8f0fb295b88bc886ac74efcc613efc19f5d0b21de5c89e47"
-dependencies = [
- "rustc_version",
-]
-
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -2174,9 +2171,9 @@ dependencies = [
 
 [[package]]
 name = "ctor"
-version = "1.0.5"
+version = "1.0.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "378f0974ae2468eaf63aa036dbe9c926b0dc7ea64c156f2ea618bc2f75b934f0"
+checksum = "2d83cb7e7a873830708d6b02a78cd36a592c6fa14bf267b68725103b85c0d77f"
 dependencies = [
  "link-section",
  "linktime-proc-macro",
@@ -2902,6 +2899,37 @@ dependencies = [
  "uuid",
 ]
 
+[[package]]
+name = "defmt"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2953bfe4f93bbd20cc71198842756f77d161884c99ebbabc41d80231ded88d1"
+dependencies = [
+ "bitflags 1.3.2",
+ "defmt-macros",
+]
+
+[[package]]
+name = "defmt-macros"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bad9c72e7ca2137e0dc3813245a0d282fd6daad32fd800af018306a9169b5fe8"
+dependencies = [
+ "defmt-parser",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "defmt-parser"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10d60334b3b2e7c9d91ef8150abfb6fa4c1c39ebbcf4a81c2e346aad939fee3e"
+dependencies = [
+ "thiserror 2.0.18",
+]
+
 [[package]]
 name = "der"
 version = "0.6.1"
@@ -3413,6 +3441,12 @@ dependencies = [
  "percent-encoding",
 ]
 
+[[package]]
+name = "frostem"
+version = "1.20260804.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "82eb03a32a1d50555353c85a7b9d3279a6f1e91af9890b789acdf544ed57c8d7"
+
 [[package]]
 name = "fs_extra"
 version = "1.3.0"
@@ -3421,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "rand 0.9.5",
@@ -3779,14 +3813,23 @@ dependencies = [
 
 [[package]]
 name = "goosefs-sdk"
-version = "0.1.5"
+version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ae079b88ffe7772d12cfc5c40a5a324babb357893d95b5e3a22ae857f236c5f"
+checksum = "e1ea4eee6dcbc31b25ab4fd577adc55b677d2bed3aa3016c44c58fbe1b2298a5"
 dependencies = [
+ "arc-swap",
  "async-trait",
  "bytes",
  "dashmap",
+ "fastrand",
+ "futures",
  "hostname",
+ "io-uring",
+ "itoa",
+ "libc",
+ "lru 0.18.2",
+ "memmap2 0.9.10",
+ "moka",
  "prost",
  "prost-types",
  "rand 0.9.5",
@@ -3799,6 +3842,7 @@ dependencies = [
  "tonic-prost",
  "tracing",
  "uuid",
+ "xxhash-rust",
 ]
 
 [[package]]
@@ -4599,10 +4643,12 @@ dependencies = [
 
 [[package]]
 name = "jiff"
-version = "0.2.24"
+version = "0.2.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f00b5dbd620d61dfdcb6007c9c1f6054ebd75319f163d886a9055cec1155073d"
+checksum = "668b7183bd07af9a4885f5c35b0cc5c83c4607a913c16b7e17291832910d2dcc"
 dependencies = [
+ "defmt",
+ "jiff-core",
  "jiff-static",
  "jiff-tzdb-platform",
  "js-sys",
@@ -4611,15 +4657,25 @@ dependencies = [
  "portable-atomic-util",
  "serde_core",
  "wasm-bindgen",
- "windows-sys 0.61.2",
+ "windows-link",
+]
+
+[[package]]
+name = "jiff-core"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7feca88439efe53da3754500c1851dedf3cb36c524dd5cf8225cc0794de95d09"
+dependencies = [
+ "defmt",
 ]
 
 [[package]]
 name = "jiff-static"
-version = "0.2.24"
+version = "0.2.35"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e000de030ff8022ea1da3f466fbb0f3a809f5e51ed31f6dd931c35181ad8e6d7"
+checksum = "3a69dcb3a21cfb32ce1cd056169337ca284af0766dd766e7878819b251a49204"
 dependencies = [
+ "jiff-core",
  "proc-macro2",
  "quote",
  "syn 2.0.117",
@@ -4731,24 +4787,6 @@ dependencies = [
  "zmij",
 ]
 
-[[package]]
-name = "jsonwebtoken"
-version = "10.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eba32bfb4ffdeaca3e34431072faf01745c9b26d25504aa7a6cf5684334fc4fc"
-dependencies = [
- "aws-lc-rs",
- "base64 0.22.1",
- "getrandom 0.2.17",
- "js-sys",
- "pem",
- "serde",
- "serde_json",
- "signature 2.2.0",
- "simple_asn1",
- "zeroize",
-]
-
 [[package]]
 name = "kanaria"
 version = "0.2.0"
@@ -4777,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
 
 [[package]]
 name = "lance"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -4852,8 +4890,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4875,7 +4913,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4889,7 +4927,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4898,8 +4936,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrayref",
  "crunchy",
@@ -4909,8 +4947,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4950,8 +4988,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4981,8 +5019,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4999,8 +5037,8 @@ dependencies = [
 
 [[package]]
 name = "lance-derive"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5009,8 +5047,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5036,7 +5074,6 @@ dependencies = [
  "prost",
  "prost-build",
  "rand 0.9.5",
- "strum 0.26.3",
  "tokio",
  "tracing",
  "xxhash-rust",
@@ -5045,8 +5082,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5077,8 +5114,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -5145,8 +5182,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index-core"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5168,8 +5205,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5181,7 +5218,6 @@ dependencies = [
  "bytes",
  "chrono",
  "futures",
- "goosefs-sdk",
  "http 1.5.0",
  "io-uring",
  "lance-arrow",
@@ -5206,8 +5242,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5223,8 +5259,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow",
  "async-trait",
@@ -5236,8 +5272,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -5291,8 +5327,8 @@ dependencies = [
 
 [[package]]
 name = "lance-select"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5307,8 +5343,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5347,8 +5383,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5361,13 +5397,13 @@ dependencies = [
 
 [[package]]
 name = "lance-tokenizer"
-version = "10.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.1.0-beta.1#68f4d4c1d0c4871b067557c61fc405078f1ab3b7"
+version = "11.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160"
 dependencies = [
+ "frostem",
  "icu_segmenter",
  "jieba-rs",
  "lindera",
- "rust-stemmers",
  "serde",
  "stop-words",
  "unicode-normalization",
@@ -5645,7 +5681,7 @@ dependencies = [
  "serde",
  "serde_json",
  "serde_yaml_ng",
- "strum 0.28.0",
+ "strum",
  "strum_macros 0.28.0",
  "unicode-blocks",
  "unicode-normalization",
@@ -5675,22 +5711,22 @@ dependencies = [
  "rkyv",
  "serde",
  "serde_json",
- "strum 0.28.0",
+ "strum",
  "strum_macros 0.28.0",
  "thiserror 2.0.18",
 ]
 
 [[package]]
 name = "link-section"
-version = "0.16.1"
+version = "0.19.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c8600ca3dbe044f07955b443ff606c50f45295b863289bbe7d0844d50cf11e4"
+checksum = "5ee1a0d6e252afe82e7bc2db42fba60e02ddf3b1accaf8cb21d96e34ba61f3d4"
 
 [[package]]
 name = "linktime-proc-macro"
-version = "0.1.0"
+version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a44cd706ff0d503ee32b2071166510ca27e281228de10cd3aa8d35ff94560f81"
+checksum = "348d0075b1fc163b26d72a7f75fc5141daf2fd1bdf128d873cbaf6785d495bdf"
 
 [[package]]
 name = "linux-raw-sys"
@@ -5747,6 +5783,15 @@ dependencies = [
  "hashbrown 0.16.1",
 ]
 
+[[package]]
+name = "lru"
+version = "0.18.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d2f2f9b4ba7e6b24d95e7e899329d35be83bcded72c8540cdd5368932d1d90a"
+dependencies = [
+ "hashbrown 0.17.1",
+]
+
 [[package]]
 name = "lru-slab"
 version = "0.1.2"
@@ -6067,7 +6112,7 @@ checksum = "de33522036981030a75c231829566bc63414e08101a6f5ff4ac6cef19c8e0941"
 dependencies = [
  "bitflags 2.11.1",
  "chrono",
- "ctor 1.0.5",
+ "ctor 1.0.12",
  "futures",
  "napi-build",
  "napi-sys",
@@ -6091,7 +6136,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4d5c9c02556ea6dc99dffd36c1ce60141411657438501a125b675776d011ce92"
 dependencies = [
  "convert_case",
- "ctor 1.0.5",
+ "ctor 1.0.12",
  "napi-derive-backend",
  "proc-macro2",
  "quote",
@@ -6384,9 +6429,9 @@ dependencies = [
 
 [[package]]
 name = "object_store_opendal"
-version = "0.57.0"
+version = "0.58.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0eb12a624a41fce745838d0ef3701ff6c47797c13cd18ad3612fd2a3134fdbd8"
+checksum = "88f165780495c17aa3ce86846600504198c3fffd99073521552751c2430fa6ac"
 dependencies = [
  "async-trait",
  "bytes",
@@ -6447,12 +6492,13 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"
 
 [[package]]
 name = "opendal"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96c9c85ce253ff87225e7669979d877a20c98a06604ec9d6dd5f4473e08f1ae1"
+checksum = "4f20562cc7447fcc915fc5c23df305a412ea80a733c9f2fd9e2d267e2815be6d"
 dependencies = [
- "ctor 1.0.5",
+ "ctor 1.0.12",
  "opendal-core",
+ "opendal-http-transport-reqwest",
  "opendal-layer-concurrent-limit",
  "opendal-layer-logging",
  "opendal-layer-retry",
@@ -6469,24 +6515,22 @@ dependencies = [
 
 [[package]]
 name = "opendal-core"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4f8607c90e2c963a91467f50fb49fbc7fb3d573f88cea219ca59ccd3740b309"
+checksum = "ec75551ff4cf3e57da98979f6a937aaa9ddb3915bf68cc17d03df733be6646ed"
 dependencies = [
  "anyhow",
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
  "futures",
  "http 1.5.0",
- "http-body 1.1.0",
  "jiff",
  "log",
  "md-5 0.11.0",
  "mea",
  "percent-encoding",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-core",
- "reqwest 0.13.3",
  "serde",
  "serde_json",
  "tokio",
@@ -6496,10 +6540,24 @@ dependencies = [
 ]
 
 [[package]]
-name = "opendal-layer-concurrent-limit"
-version = "0.57.0"
+name = "opendal-http-transport-reqwest"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d6f81ba6960e3fae1882f253b114b21d7e444e1534f209c7737a79f6243eb6f"
+checksum = "ad4d4f19c3ce01126a30611f8e544eaa217104a278c889ac17c9374fe4f9e4ef"
+dependencies = [
+ "bytes",
+ "futures",
+ "http 1.5.0",
+ "http-body 1.1.0",
+ "opendal-core",
+ "reqwest 0.13.4",
+]
+
+[[package]]
+name = "opendal-layer-concurrent-limit"
+version = "0.58.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "249ac5b0aa5a7a6c3737342d10456067937f9c9a6f3f02544271f7908ab91081"
 dependencies = [
  "futures",
  "http 1.5.0",
@@ -6509,9 +6567,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-layer-logging"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58ada45c6d81d1aa4c9305d0c7d4bc317c59c85866a0908a2d75a7a978aa5ee2"
+checksum = "5c75411ab00f77851ff086b686c1e9ca8175ac18c15afa2cb75b9036436cb06c"
 dependencies = [
  "log",
  "opendal-core",
@@ -6519,9 +6577,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-layer-retry"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b2a25a718afb81fad81cb9a0580a1cb989221fa2317f888c6a37f8dad408eb7"
+checksum = "80b7738bd5f233ad8da39af9b9316b9b7a4eaddd91e8e32a1e19b7030688121d"
 dependencies = [
  "backon",
  "log",
@@ -6530,9 +6588,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-layer-timeout"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e91f731724c213af81e9d03517859c8fc47b4578e64ad61ae4f099f10fe36e3"
+checksum = "a704141924500f3803c05ed871b53305d2a2f11cb5ef20160c3ee688a1857f66"
 dependencies = [
  "opendal-core",
  "tokio",
@@ -6540,17 +6598,17 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-azblob"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0030644366ef5d8cbe3a4a5822bf99a4aafddc1666e9d24b44d158d9062fc76a"
+checksum = "b3310fbbb48f111c6f590473c2cd15e1b7f8e384444b0d4e328f0464c864d767"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
  "http 1.5.0",
  "log",
  "opendal-core",
  "opendal-service-azure-common",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-azure-storage",
  "reqsign-core",
  "reqsign-file-read-tokio",
@@ -6561,17 +6619,18 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-azdls"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6dea4908d490143a9b0b7f7a790e139ff829b06a023f670455ed3d44f664b361"
+checksum = "2e3c406729935fe214ce574d68681a1ff7e0b322548f14094912bdbfe50e5c53"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
  "http 1.5.0",
  "log",
+ "mea",
  "opendal-core",
  "opendal-service-azure-common",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-azure-storage",
  "reqsign-core",
  "reqsign-file-read-tokio",
@@ -6581,9 +6640,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-azure-common"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b489f13c42e69d69bdd72952b634356ec43a7881a20259b38b540fcecdf4051"
+checksum = "7348c88edf15af435b7be930077746b569fac5e738c1bf6a363b675e7317c9df"
 dependencies = [
  "http 1.5.0",
  "opendal-core",
@@ -6591,15 +6650,15 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-cos"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aa8cafe9729213375c7331019b0cb756ad3e1aff7f45cd32c45eae91ebde8901"
+checksum = "d533d4582105d269c8aebeee5f0e8bcf960f41b8aab6197df7012254d9f39bf0"
 dependencies = [
  "bytes",
  "http 1.5.0",
  "log",
  "opendal-core",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-core",
  "reqsign-file-read-tokio",
  "reqsign-tencent-cos",
@@ -6608,9 +6667,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-gcs"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "48de101aac565ed06af4b47903c24eafd249075553ec1fb18256751c45148d47"
+checksum = "007f3fba63c21e516c956b891e96ff9892d8175662bfb781cdada9d3766a11e6"
 dependencies = [
  "async-trait",
  "bytes",
@@ -6618,7 +6677,7 @@ dependencies = [
  "log",
  "opendal-core",
  "percent-encoding",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-core",
  "reqsign-file-read-tokio",
  "reqsign-google",
@@ -6629,9 +6688,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-goosefs"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "69e43048bde419947ba826fbdc2f134d6c03f44ebf48bd33a03b72f9fc45fcb4"
+checksum = "60871e6386f04d831e6a5bdbc032af4a91aeba49963252d0ef456a2cf36a9b78"
 dependencies = [
  "bytes",
  "goosefs-sdk",
@@ -6643,9 +6702,9 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-hf"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4922661976a1d40794a2adfbdb888cc3c23097690f825a92f773af38908a848"
+checksum = "b41fd41eb7ed03c5e66cefda61e8e117808ffd2908f2916737cb020a6beb02c7"
 dependencies = [
  "bytes",
  "hf-xet",
@@ -6653,22 +6712,21 @@ dependencies = [
  "log",
  "opendal-core",
  "percent-encoding",
- "reqwest 0.13.3",
  "serde",
  "serde_json",
 ]
 
 [[package]]
 name = "opendal-service-oss"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "328fa55e8888cbdfe00826bfea2a79042422b720e8369e9e021e46121dea5ace"
+checksum = "cd528ec2d49c5ca69e674ffed7b3e0686fb9cfcfea0596870de381467fda4f1b"
 dependencies = [
  "bytes",
  "http 1.5.0",
  "log",
  "opendal-core",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-aliyun-oss",
  "reqsign-core",
  "reqsign-file-read-tokio",
@@ -6677,18 +6735,18 @@ dependencies = [
 
 [[package]]
 name = "opendal-service-s3"
-version = "0.57.0"
+version = "0.58.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "313d46c9f5ae70bca26b7c3e3fbb9b639292625f28af73aa016f47e788af9deb"
+checksum = "58e80cdf192d7eff05feed747894d64f81905ac4eaf132edf7ea270abdd2d663"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
- "crc32c",
+ "crc-fast",
  "http 1.5.0",
  "log",
  "md-5 0.11.0",
  "opendal-core",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-aws-v4",
  "reqsign-core",
  "reqsign-file-read-tokio",
@@ -7583,7 +7641,7 @@ version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
  "itertools 0.14.0",
  "log",
  "multimap",
@@ -7799,6 +7857,16 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "quick-xml"
+version = "0.41.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e660451e55124f798a69a5af3f49ccfbefbd41910eefd25caf2393e1f3473ec1"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
 [[package]]
 name = "quick_cache"
 version = "0.6.24"
@@ -8220,9 +8288,9 @@ dependencies = [
 
 [[package]]
 name = "reqsign-aliyun-oss"
-version = "3.0.0"
+version = "3.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57ac2757f3140aa2e213b554148ae0b52733e624fc6723f0cc6bb3d440176c95"
+checksum = "a5e6d659fcdbca6fe2d7ef109c2e28499b7be80501f1bb86c10caf5ec8ac1219"
 dependencies = [
  "anyhow",
  "form_urlencoded",
@@ -8236,38 +8304,52 @@ dependencies = [
 ]
 
 [[package]]
-name = "reqsign-aws-v4"
-version = "3.0.0"
+name = "reqsign-aws-core"
+version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44eaca382e94505a49f1a4849658d153aebf79d9c1a58e5dd3b10361511e9f43"
+checksum = "e4af084e1f3cbf3e67e0c972765399bce54ecec804cceba46b39a8331f3c1bff"
 dependencies = [
- "anyhow",
  "bytes",
  "form_urlencoded",
+ "hex",
  "http 1.5.0",
  "log",
  "percent-encoding",
- "quick-xml 0.39.4",
+ "quick-xml 0.41.0",
  "reqsign-core",
  "rust-ini",
  "serde",
  "serde_json",
  "serde_urlencoded",
- "sha1 0.10.6",
+ "sha1 0.11.0",
+]
+
+[[package]]
+name = "reqsign-aws-v4"
+version = "3.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ac5b3b7cefa28933792b439186459f77f19f9b6edbeab41b8b187150361a206"
+dependencies = [
+ "bytes",
+ "http 1.5.0",
+ "log",
+ "quick-xml 0.41.0",
+ "reqsign-aws-core",
+ "reqsign-core",
+ "serde",
 ]
 
 [[package]]
 name = "reqsign-azure-storage"
-version = "3.0.0"
+version = "3.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7a321980405d596bd34aaf95c4722a3de4128a67fd19e74a81a83aa3fdf082e6"
+checksum = "2824e7da3c2cc42ac3406c674eb57c89127fdcd97f3a73c608cfc680505ea134"
 dependencies = [
  "anyhow",
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
  "form_urlencoded",
  "http 1.5.0",
- "jsonwebtoken",
  "log",
  "pem",
  "percent-encoding",
@@ -8275,36 +8357,38 @@ dependencies = [
  "rsa",
  "serde",
  "serde_json",
- "sha1 0.10.6",
+ "sha1 0.11.0",
 ]
 
 [[package]]
 name = "reqsign-core"
-version = "3.0.0"
+version = "3.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b10302cf0a7d7e7352ba211fc92c3c5bebf1286153e49cc5aa87348078a8e102"
+checksum = "c07dd510b1e1b9b241883e483358147fb2ed2d497a7b39b065ba61eb93deceb0"
 dependencies = [
  "anyhow",
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
- "form_urlencoded",
  "futures",
  "hex",
- "hmac 0.12.1",
+ "hmac 0.13.0",
  "http 1.5.0",
  "jiff",
  "log",
  "percent-encoding",
- "sha1 0.10.6",
- "sha2 0.10.9",
+ "rsa",
+ "serde",
+ "serde_json",
+ "sha1 0.11.0",
+ "sha2 0.11.0",
  "windows-sys 0.61.2",
 ]
 
 [[package]]
 name = "reqsign-file-read-tokio"
-version = "3.0.0"
+version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e2d89295b3d17abea31851cc8de55d843d89c52132c864963c38d41920613dc5"
+checksum = "663d9d55abd0df0830ef0ae43708297cc1371cf4e8ca91f3ac813c309cca8c98"
 dependencies = [
  "anyhow",
  "reqsign-core",
@@ -8313,13 +8397,12 @@ dependencies = [
 
 [[package]]
 name = "reqsign-google"
-version = "3.0.0"
+version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35cc609b49c69e76ecaceb775a03f792d1ed3e7755ab3548d4534fd801e3242e"
+checksum = "4080a227f82a09f68540ecd028622065d7ac4c0bcb8727a25bdcfc0526235792"
 dependencies = [
  "form_urlencoded",
  "http 1.5.0",
- "jsonwebtoken",
  "log",
  "percent-encoding",
  "reqsign-aws-v4",
@@ -8327,15 +8410,14 @@ dependencies = [
  "rsa",
  "serde",
  "serde_json",
- "sha2 0.10.9",
  "tokio",
 ]
 
 [[package]]
 name = "reqsign-tencent-cos"
-version = "3.0.0"
+version = "3.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e128f19525861dbded59e1e7c17653a8ed63d573ca04aed708d552dbef5bb32a"
+checksum = "764629c90f7c3566a6d4e4641ebab9acd604ce02e16eda4d37c7d7e79e16ed90"
 dependencies = [
  "anyhow",
  "http 1.5.0",
@@ -8394,9 +8476,9 @@ dependencies = [
 
 [[package]]
 name = "reqwest"
-version = "0.13.3"
+version = "0.13.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "62e0021ea2c22aed41653bc7e1419abb2c97e038ff2c33d0e1309e49a97deec0"
+checksum = "219c5811de6525e5416c7d5d53bb656d3afdbc6c5af816e0802bcfa42dbdc1c3"
 dependencies = [
  "base64 0.22.1",
  "bytes",
@@ -8457,7 +8539,7 @@ dependencies = [
  "anyhow",
  "async-trait",
  "http 1.5.0",
- "reqwest 0.13.3",
+ "reqwest 0.13.4",
  "thiserror 2.0.18",
  "tower-service",
 ]
@@ -8597,16 +8679,6 @@ dependencies = [
  "ordered-multimap",
 ]
 
-[[package]]
-name = "rust-stemmers"
-version = "1.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e46a2036019fdb888131db7a4c847a1063a7493f971ed94ea82c67eada63ca54"
-dependencies = [
- "serde",
- "serde_derive",
-]
-
 [[package]]
 name = "rustc-demangle"
 version = "0.1.27"
@@ -9206,18 +9278,6 @@ version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3a9fe34e3e7a50316060351f37187a3f546bce95496156754b601a5fa71b76e"
 
-[[package]]
-name = "simple_asn1"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d585997b0ac10be3c5ee635f1bab02d512760d14b7c468801ac8a01d9ae5f1d"
-dependencies = [
- "num-bigint",
- "num-traits",
- "thiserror 2.0.18",
- "time",
-]
-
 [[package]]
 name = "siphasher"
 version = "1.0.3"
@@ -9277,7 +9337,7 @@ version = "0.8.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
  "proc-macro2",
  "quote",
  "syn 2.0.117",
@@ -9289,7 +9349,7 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "54254b8531cafa275c5e096f62d48c81435d1015405a91198ddb11e967301d40"
 dependencies = [
- "heck 0.4.1",
+ "heck 0.5.0",
  "proc-macro2",
  "quote",
  "syn 2.0.117",
@@ -9492,15 +9552,6 @@ version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
 
-[[package]]
-name = "strum"
-version = "0.26.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fec0f0aef304996cf250b31b5a10dee7980c85da9d759361292b8bca5a18f06"
-dependencies = [
- "strum_macros 0.26.4",
-]
-
 [[package]]
 name = "strum"
 version = "0.28.0"
@@ -9523,19 +9574,6 @@ dependencies = [
  "syn 2.0.117",
 ]
 
-[[package]]
-name = "strum_macros"
-version = "0.26.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be"
-dependencies = [
- "heck 0.5.0",
- "proc-macro2",
- "quote",
- "rustversion",
- "syn 2.0.117",
-]
-
 [[package]]
 name = "strum_macros"
 version = "0.28.0"
@@ -9730,7 +9768,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
  "fastrand",
- "getrandom 0.3.4",
+ "getrandom 0.4.2",
  "once_cell",
  "rustix",
  "windows-sys 0.61.2",
@@ -11161,7 +11199,7 @@ dependencies = [
  "more-asserts",
  "rand 0.10.1",
  "redb",
- "reqwest 0.13.3",
+ "reqwest 0.13.4",
  "reqwest-middleware",
  "serde",
  "serde_json",
@@ -11274,7 +11312,7 @@ dependencies = [
  "oneshot",
  "pin-project",
  "rand 0.10.1",
- "reqwest 0.13.3",
+ "reqwest 0.13.4",
  "serde",
  "serde_json",
  "shellexpand",
@@ -11370,20 +11408,6 @@ name = "zeroize"
 version = "1.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
-dependencies = [
- "zeroize_derive",
-]
-
-[[package]]
-name = "zeroize_derive"
-version = "1.4.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85a5b4158499876c763cb03bc4e49185d3cccbabb15b33c627f7884f43db852e"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.117",
-]
 
 [[package]]
 name = "zerotrie"
diff --git a/Cargo.toml b/Cargo.toml
index 35370e58f..78474cd16 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
@@ -52,7 +52,7 @@ env_logger = "0.11"
 half = { "version" = "2.7.1", default-features = false, features = [
     "num-traits",
 ] }
-futures = "0"
+futures = "0.3"
 log = "0.4"
 metrics = "0.24"
 metrics-util = "0.19"
diff --git a/docs/src/python/python.md b/docs/src/python/python.md
index 36044d35d..3dd6f59f4 100644
--- a/docs/src/python/python.md
+++ b/docs/src/python/python.md
@@ -31,7 +31,7 @@ is also an [asynchronous API client](#connections-asynchronous).
 ## Namespaces (Synchronous)
 
 A namespace-backed connection resolves tables through a
-[Lance namespace](https://lancedb.github.io/lance-namespace/) service instead of
+[Lance namespace](https://lance-format.github.io/lance-namespace/) service instead of
 listing a storage directory.
 
 ::: lancedb.connect_namespace
diff --git a/java/pom.xml b/java/pom.xml
index 1b96cbcab..e8f030b27 100644
--- a/java/pom.xml
+++ b/java/pom.xml
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>10.1.0-beta.1</lance-core.version>
+        <lance-core.version>11.0.0-beta.2</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>
diff --git a/nodejs/__test__/arrow.test.ts b/nodejs/__test__/arrow.test.ts
index 9e20e3c04..c05849cb9 100644
--- a/nodejs/__test__/arrow.test.ts
+++ b/nodejs/__test__/arrow.test.ts
@@ -197,6 +197,35 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         expect(table.getChild("d")?.toJSON()).toEqual([9n, 10n, null]);
       });
 
+      it("will use a provided FixedSizeList schema with typed array values", function () {
+        const schema = new Schema([
+          new Field("text", new Utf8(), false),
+          new Field(
+            "vector",
+            new FixedSizeList(3, new Field("item", new Float32(), false)),
+            false,
+          ),
+        ]);
+
+        const table = makeArrowTable(
+          [
+            {
+              text: "foo",
+              vector: new Float32Array([1, 2, 3]),
+            },
+          ],
+          { schema },
+        );
+
+        expect(table.getChild("text")?.toJSON()).toEqual(["foo"]);
+        expect(
+          table
+            .getChild("vector")
+            ?.toJSON()
+            .map((value) => value.toJSON()),
+        ).toEqual([[1, 2, 3]]);
+      });
+
       it("will assume the column `vector` is FixedSizeList<Float32> by default", async function () {
         const schema = new Schema([
           new Field("a", new Float(Precision.DOUBLE), true),
diff --git a/nodejs/__test__/embedding.test.ts b/nodejs/__test__/embedding.test.ts
index e56e80631..06184751e 100644
--- a/nodejs/__test__/embedding.test.ts
+++ b/nodejs/__test__/embedding.test.ts
@@ -11,8 +11,11 @@ import {
   Float16,
   Float32,
   Float64,
+  Int32,
   Schema,
   Utf8,
+  fromDataToBuffer,
+  tableFromIPC,
 } from "../lancedb/arrow";
 import { EmbeddingFunction, LanceSchema } from "../lancedb/embedding";
 import { getRegistry, register } from "../lancedb/embedding/registry";
@@ -184,6 +187,63 @@ describe("embedding functions", () => {
     const vector0 = JSON.parse(JSON.stringify(arr[0].vector));
     expect(vector0).toEqual([1, 2, 3]);
   });
+
+  it("should append generated vectors to a non-nullable schema", async () => {
+    @register("non_nullable_schema_test")
+    class MockEmbeddingFunction extends EmbeddingFunction<string> {
+      ndims() {
+        return 3;
+      }
+      embeddingDataType(): Float {
+        return new Float64();
+      }
+      async computeSourceEmbeddings(data: string[]) {
+        return data.map(() => [1, 2, 3]);
+      }
+    }
+
+    const schema = new Schema([
+      new Field("id", new Int32()),
+      new Field("text", new Utf8()),
+      new Field("type", new Utf8()),
+      new Field(
+        "vector",
+        new FixedSizeList(3, new Field("item", new Float64())),
+      ),
+    ]);
+    const func = new MockEmbeddingFunction();
+    const db = await connect(tmpDir.name);
+    const table = await db.createEmptyTable("test_non_nullable", schema, {
+      embeddingFunction: {
+        function: func,
+        sourceColumn: "text",
+      },
+    });
+
+    const data = [
+      { id: 1, text: "Carrot", type: "vegetable" },
+      { id: 2, text: "Apple", type: "fruit" },
+    ];
+    const buffer = await fromDataToBuffer(
+      data,
+      undefined,
+      await table.schema(),
+    );
+    const generatedTable = tableFromIPC(buffer);
+    const vectorField = generatedTable.schema.fields.find(
+      (field) => field.name === "vector",
+    );
+    expect(vectorField?.nullable).toBe(false);
+
+    await table.add(data);
+
+    const rows = await table.query().toArray();
+    expect(rows).toHaveLength(2);
+    for (const row of rows) {
+      expect([...row.vector]).toEqual([1, 2, 3]);
+    }
+  });
+
   it("should error when appending to a table with an unregistered embedding function", async () => {
     @register("mock")
     class MockEmbeddingFunction extends EmbeddingFunction<string> {
diff --git a/nodejs/__test__/package.test.ts b/nodejs/__test__/package.test.ts
new file mode 100644
index 000000000..7743d73d6
--- /dev/null
+++ b/nodejs/__test__/package.test.ts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import packageJson = require("../package.json");
+
+describe("package metadata", () => {
+  it("requires Node.js type declarations compatible with the runtime", () => {
+    expect(packageJson.engines.node).toBe(">= 18");
+    expect(packageJson.peerDependencies["@types/node"]).toBe(">=18");
+    expect(packageJson.peerDependenciesMeta["@types/node"]).toEqual({
+      optional: true,
+    });
+  });
+});
diff --git a/nodejs/__test__/query.test.ts b/nodejs/__test__/query.test.ts
index da001b1eb..5f3e68b16 100644
--- a/nodejs/__test__/query.test.ts
+++ b/nodejs/__test__/query.test.ts
@@ -110,6 +110,81 @@ describe("Query outputSchema", () => {
   });
 });
 
+describe("Search pagination", () => {
+  let tmpDir: tmp.DirResult;
+  let table: Table;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    const db = await connect(tmpDir.name);
+    const schema = new Schema([
+      new Field("id", new Int64(), false),
+      new Field("text", new Utf8(), false),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32())),
+        false,
+      ),
+    ]);
+    const data = makeArrowTable(
+      [
+        { id: 1n, text: "common", vector: [0, 0] },
+        { id: 2n, text: "common common", vector: [1, 1] },
+        { id: 3n, text: "common common common", vector: [2, 2] },
+        { id: 4n, text: "common common common common", vector: [3, 3] },
+      ],
+      { schema },
+    );
+    table = await db.createTable("test", data);
+  });
+
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  it("applies offset after the vector search limit", async () => {
+    const allResults = await table
+      .vectorSearch([0, 0])
+      .select(["id"])
+      .limit(4)
+      .toArray();
+    const secondPage = await table
+      .vectorSearch([0, 0])
+      .select(["id"])
+      .limit(2)
+      .offset(2)
+      .toArray();
+
+    expect(allResults).toHaveLength(4);
+    expect(secondPage).toHaveLength(2);
+    expect(secondPage.map((row) => row.id)).toEqual(
+      allResults.slice(2, 4).map((row) => row.id),
+    );
+  });
+
+  it("applies offset after the full-text search limit", async () => {
+    await table.createIndex("text", { config: Index.fts() });
+
+    const allResults = await table
+      .search("common", "fts")
+      .select(["id"])
+      .limit(4)
+      .toArray();
+    const secondPage = await table
+      .search("common", "fts")
+      .select(["id"])
+      .limit(2)
+      .offset(2)
+      .toArray();
+
+    expect(allResults).toHaveLength(4);
+    expect(secondPage).toHaveLength(2);
+    expect(secondPage.map((row) => row.id)).toEqual(
+      allResults.slice(2, 4).map((row) => row.id),
+    );
+  });
+});
+
 describe("Query orderBy", () => {
   let tmpDir: tmp.DirResult;
   let table: Table;
diff --git a/nodejs/__test__/remote.test.ts b/nodejs/__test__/remote.test.ts
index 89a9e992c..e766b3d2a 100644
--- a/nodejs/__test__/remote.test.ts
+++ b/nodejs/__test__/remote.test.ts
@@ -170,6 +170,38 @@ describe("remote connection", () => {
     );
   });
 
+  it("surfaces JSON server errors from remote table operations", async () => {
+    await withMockDatabase(
+      (req, res) => {
+        const path = req.url ?? "";
+        if (path.endsWith("/describe/")) {
+          res.writeHead(200, { "Content-Type": "application/json" }).end(
+            JSON.stringify({
+              name: "broken_table",
+              version: 1,
+              schema: { fields: [] },
+            }),
+          );
+          return;
+        }
+
+        if (path.endsWith("/count_rows/")) {
+          res
+            .writeHead(400, { "Content-Type": "application/json" })
+            .end(JSON.stringify({ error: "count rows failed" }));
+          return;
+        }
+
+        res.writeHead(404).end();
+      },
+      async (db) => {
+        const table = await db.openTable("broken_table");
+
+        await expect(table.countRows()).rejects.toThrow("count rows failed");
+      },
+    );
+  });
+
   it("should pass on requested extra headers", async () => {
     await withMockDatabase(
       (req, res) => {
diff --git a/nodejs/__test__/table.test.ts b/nodejs/__test__/table.test.ts
index 4cad365af..15d6e0804 100644
--- a/nodejs/__test__/table.test.ts
+++ b/nodejs/__test__/table.test.ts
@@ -86,6 +86,44 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(3);
     });
 
+    it("should support a foreign Float64 vector schema end to end", async () => {
+      const conn = await connect(tmpDir.name);
+      const schema = new arrow.Schema([
+        new arrow.Field("resource_id", new arrow.Int32(), false),
+        new arrow.Field(
+          "vector",
+          new arrow.FixedSizeList(
+            3,
+            new arrow.Field("value", new arrow.Float64(), true),
+          ),
+          false,
+        ),
+      ]);
+      const data = [
+        {
+          // biome-ignore lint/style/useNamingConvention: matches the reported schema
+          resource_id: 0,
+          vector: [0.1, 0.1, 0.1],
+        },
+      ];
+
+      const resources = await conn.createTable("resources", data, { schema });
+
+      const existing = await resources
+        .query()
+        .where("resource_id = 0")
+        .limit(1)
+        .toArray();
+      expect(existing).toHaveLength(1);
+
+      const matched = await resources
+        .search(Float64Array.from(data[0].vector))
+        .limit(1)
+        .toArray();
+      expect(matched).toHaveLength(1);
+      expect(matched[0]["resource_id"]).toBe(0);
+    });
+
     it("should support branches", async () => {
       await table.add([{ id: 1 }]);
       expect(await table.countRows()).toBe(1);
diff --git a/nodejs/package-lock.json b/nodejs/package-lock.json
index 8e30b0fab..bdbd3cf79 100644
--- a/nodejs/package-lock.json
+++ b/nodejs/package-lock.json
@@ -55,7 +55,13 @@
         "openai": "4.29.2"
       },
       "peerDependencies": {
+        "@types/node": ">=18",
         "apache-arrow": ">=15.0.0 <=18.1.0"
+      },
+      "peerDependenciesMeta": {
+        "@types/node": {
+          "optional": true
+        }
       }
     },
     "node_modules/@aws-crypto/crc32": {
diff --git a/nodejs/package.json b/nodejs/package.json
index f3f719af2..671f3f94d 100644
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -101,6 +101,12 @@
     "openai": "4.29.2"
   },
   "peerDependencies": {
+    "@types/node": ">=18",
     "apache-arrow": ">=15.0.0 <=18.1.0"
+  },
+  "peerDependenciesMeta": {
+    "@types/node": {
+      "optional": true
+    }
   }
 }
diff --git a/python/Cargo.toml b/python/Cargo.toml
index cc706e712..5a196e27c 100644
--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -26,7 +26,7 @@ lance-namespace-impls.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
 log.workspace = true
-pyo3 = { version = "0.28", features = ["extension-module", "abi3-py39", "chrono"] }
+pyo3 = { version = "0.28", features = ["extension-module", "abi3-py310", "chrono"] }
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 pyo3-async-runtimes = { version = "0.28", features = [
     "attributes",
@@ -43,7 +43,7 @@ libc = "0.2"
 [build-dependencies]
 pyo3-build-config = { version = "0.28", features = [
     "extension-module",
-    "abi3-py39",
+    "abi3-py310",
 ] }
 
 [features]
diff --git a/python/pyproject.toml b/python/pyproject.toml
index cb175bd6d..ce71484de 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -60,7 +60,7 @@ tests = [
     "pytest-asyncio>=0.21",
     "duckdb>=0.9.0",
     "pytz>=2023.3",
-    "polars>=0.19, <=1.3.0",
+    "polars>=0.19, <=1.32.3",
     "pyarrow<25",
     "pyarrow-stubs>=16.0",
     "pylance==9.0.0rc1",
@@ -140,6 +140,7 @@ include = [
     "python/lancedb/remote/errors.py",
     "python/lancedb/embeddings/__init__.py",
     "python/lancedb/_lancedb.pyi",
+    "python/type_tests/connect.py",
 ]
 exclude = ["python/tests/"]
 pythonVersion = "3.13"
diff --git a/python/python/lancedb/embeddings/instructor.py b/python/python/lancedb/embeddings/instructor.py
index 675a0139c..37ae1c296 100644
--- a/python/python/lancedb/embeddings/instructor.py
+++ b/python/python/lancedb/embeddings/instructor.py
@@ -101,8 +101,7 @@ class InstructorEmbeddingFunction(TextEmbeddingFunction):
 
     @weak_lru(maxsize=1)
     def ndims(self):
-        model = self.get_model()
-        return model.encode("foo").shape[0]
+        return len(self.generate_embeddings([[self.source_instruction, "foo"]])[0])
 
     def compute_query_embeddings(self, query: str, *args, **kwargs) -> List[np.array]:
         return self.generate_embeddings([[self.query_instruction, query]])
diff --git a/python/python/lancedb/py.typed b/python/python/lancedb/py.typed
new file mode 100644
index 000000000..8b1378917
--- /dev/null
+++ b/python/python/lancedb/py.typed
@@ -0,0 +1 @@
+
diff --git a/python/python/lancedb/pydantic.py b/python/python/lancedb/pydantic.py
index c4dedc0e6..1ab6e6fcc 100644
--- a/python/python/lancedb/pydantic.py
+++ b/python/python/lancedb/pydantic.py
@@ -153,6 +153,16 @@ def Vector(
     return FixedSizeList
 
 
+def _raise_bare_vector_error(*_args):
+    raise TypeError("Vector must be parameterized with a dimension, e.g. Vector(128).")
+
+
+# Pydantic v1 and v2 otherwise treat the bare Vector factory as a field validator
+# and inspect its signature, which produces misleading errors about internal types.
+setattr(Vector, "__get_validators__", _raise_bare_vector_error)
+setattr(Vector, "__get_pydantic_core_schema__", _raise_bare_vector_error)
+
+
 def MultiVector(
     dim: int, value_type: pa.DataType = pa.float32(), nullable: bool = True
 ) -> Type:
diff --git a/python/python/lancedb/table.py b/python/python/lancedb/table.py
index ae36bac7a..59e2650eb 100644
--- a/python/python/lancedb/table.py
+++ b/python/python/lancedb/table.py
@@ -108,6 +108,11 @@ def _should_push_down_query_table(
     return namespace_client is not None and "QueryTable" in pushdown_operations
 
 
+def _polars_predicate_pushdown_barrier(frame: Any) -> Any:
+    """Return a Polars frame unchanged while blocking predicate pushdown."""
+    return frame
+
+
 _MODEL_BACKED_TOKENIZER_PREFIXES = ("jieba", "lindera")
 _MODEL_BACKED_TOKENIZER_ERRORS = (
     "unknown base tokenizer",
@@ -864,12 +869,18 @@ class Table(ABC):
         """
         raise NotImplementedError
 
-    def to_polars(self, **kwargs) -> "pl.DataFrame":
-        """Return the table as a polars.DataFrame.
+    def to_polars(self, **kwargs) -> "pl.LazyFrame":
+        """Return the table as a Polars LazyFrame.
+
+        Note
+        ----
+        The Polars streaming engine is not supported because it does not currently
+        implement Python PyArrow dataset scans. Use the default engine when collecting
+        this LazyFrame.
 
         Returns
         -------
-        polars.DataFrame
+        polars.LazyFrame
         """
         raise NotImplementedError
 
@@ -2569,6 +2580,9 @@ class LanceTable(Table):
         2. Currently we've disabled push-down of the filters from polars
            because polars pushdown into pyarrow uses pyarrow compute
            expressions rather than SQl strings (which LanceDB supports)
+        3. The Polars streaming engine is not supported because it does not
+           currently implement Python PyArrow dataset scans. Use the default
+           engine when collecting this LazyFrame.
 
         Returns
         -------
@@ -2577,8 +2591,12 @@ class LanceTable(Table):
         from lancedb.integrations.pyarrow import PyarrowDatasetAdapter
 
         dataset = PyarrowDatasetAdapter(self)
-        return pl.scan_pyarrow_dataset(
-            dataset, allow_pyarrow_filter=False, batch_size=batch_size
+        # Polars 1.32's non-PyArrow callback path passes batch_size twice.  Keep
+        # the compatible PyArrow path, but block predicates because this adapter
+        # cannot translate PyArrow expressions into LanceDB filters.
+        return pl.scan_pyarrow_dataset(dataset, batch_size=batch_size).map_batches(
+            _polars_predicate_pushdown_barrier,
+            predicate_pushdown=False,
         )
 
     # New unified API overload
diff --git a/python/python/lancedb/util.py b/python/python/lancedb/util.py
index f582be7b4..dbc52bff6 100644
--- a/python/python/lancedb/util.py
+++ b/python/python/lancedb/util.py
@@ -395,6 +395,11 @@ def _(value: dict):
     )
 
 
+@value_to_sql.register(pa.Scalar)
+def _(value: pa.Scalar):
+    return value_to_sql(value.as_py())
+
+
 @value_to_sql.register(np.ndarray)
 def _(value: np.ndarray):
     return value_to_sql(value.tolist())
diff --git a/python/python/tests/test_db.py b/python/python/tests/test_db.py
index 93b791650..84e78fd8f 100644
--- a/python/python/tests/test_db.py
+++ b/python/python/tests/test_db.py
@@ -2,9 +2,11 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 
+import inspect
 import re
 import sys
 from datetime import timedelta
+from importlib import resources
 import os
 from types import SimpleNamespace
 
@@ -17,6 +19,10 @@ from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
 from lancedb.pydantic import LanceModel, Vector
 
 
+def test_package_includes_pep_561_marker():
+    assert resources.files(lancedb).joinpath("py.typed").is_file()
+
+
 def test_basic(tmp_path):
     db = lancedb.connect(tmp_path)
 
@@ -62,17 +68,23 @@ def test_basic(tmp_path):
     assert db.open_table("test").name == db["test"].name
 
 
-def test_sync_repr_does_not_use_background_loop(tmp_path, monkeypatch):
+def test_sync_debugger_inspection_does_not_use_background_loop(tmp_path, monkeypatch):
     from lancedb.background_loop import LOOP
 
     db = lancedb.connect(tmp_path)
     table = db.create_table("test", data=[{"id": 1}])
 
     def fail_run(*args, **kwargs):
-        raise AssertionError("repr should not use the Python background loop")
+        raise AssertionError("debugger inspection should not use the background loop")
 
     monkeypatch.setattr(LOOP, "run", fail_run)
 
+    # Debuggers enumerate and evaluate every exposed attribute when expanding a
+    # variable. This must remain safe while their breakpoint suspends LOOP's thread.
+    members = dict(inspect.getmembers(db))
+
+    assert members["uri"] == str(tmp_path)
+    assert members["read_consistency_interval"] is None
     assert repr(db) == f"LanceDBConnection(uri={str(tmp_path)!r})"
     assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
 
diff --git a/python/python/tests/test_embeddings.py b/python/python/tests/test_embeddings.py
index 5efb7d98a..678270f19 100644
--- a/python/python/tests/test_embeddings.py
+++ b/python/python/tests/test_embeddings.py
@@ -64,6 +64,23 @@ def test_embedding_function(tmp_path):
     assert np.allclose(actual, expected)
 
 
+def test_instructor_ndims_uses_instruction():
+    instructor = get_registry().get("instructor").create()
+    model = MagicMock()
+    model.encode.return_value = np.zeros((1, 384))
+
+    with patch.object(type(instructor), "get_model", return_value=model):
+        assert instructor.ndims() == 384
+
+    model.encode.assert_called_once_with(
+        [[instructor.source_instruction, "foo"]],
+        batch_size=instructor.batch_size,
+        show_progress_bar=instructor.show_progress_bar,
+        normalize_embeddings=instructor.normalize_embeddings,
+        device=instructor.device,
+    )
+
+
 def test_embedding_function_variables():
     @register("variable-testing")
     class VariableTestingFunction(TextEmbeddingFunction):
@@ -115,34 +132,16 @@ def test_embedding_function_variables():
     assert func.safe_model_dump()["secret_key"] == "$var:secret"
 
 
-def test_parse_functions_with_variables():
-    @register("variable-parsing-test")
-    class VariableParsingFunction(TextEmbeddingFunction):
-        api_key: str
-        base_url: Optional[str] = None
-
-        @staticmethod
-        def sensitive_keys():
-            return ["api_key"]
-
-        def ndims(self):
-            return 10
-
-        def generate_embeddings(self, texts):
-            # Mock implementation that just returns random embeddings
-            # In real usage, this would use the api_key to call an API
-            return [np.random.rand(self.ndims()).tolist() for _ in texts]
-
+def test_openai_variables_survive_metadata_round_trip():
     registry = EmbeddingFunctionRegistry.get_instance()
 
     registry.set_var("test_api_key", "sk-test-key-12345")
-    registry.set_var("test_base_url", "https://api.example.com")
 
     conf = EmbeddingFunctionConfig(
         source_column="text",
         vector_column="vector",
-        function=registry.get("variable-parsing-test").create(
-            api_key="$var:test_api_key", base_url="$var:test_base_url"
+        function=registry.get("openai").create(
+            api_key="$var:test_api_key", base_url="https://api.example.com"
         ),
     )
 
@@ -150,7 +149,10 @@ def test_parse_functions_with_variables():
 
     # Create a mock arrow table with the metadata
     schema = pa.schema(
-        [pa.field("text", pa.string()), pa.field("vector", pa.list_(pa.float32(), 10))]
+        [
+            pa.field("text", pa.string()),
+            pa.field("vector", pa.list_(pa.float32(), 1536)),
+        ]
     )
     table = pa.table({"text": [], "vector": []}, schema=schema)
     table = table.replace_schema_metadata(metadata)
@@ -164,13 +166,15 @@ def test_parse_functions_with_variables():
 
     assert parsed_func.api_key == "sk-test-key-12345"
     assert parsed_func.base_url == "https://api.example.com"
-
-    embeddings = parsed_func.generate_embeddings(["test text"])
-    assert len(embeddings) == 1
-    assert len(embeddings[0]) == 10
-
     assert parsed_func.safe_model_dump()["api_key"] == "$var:test_api_key"
 
+    with patch("lancedb.embeddings.openai.attempt_import_or_raise") as import_openai:
+        parsed_func._openai_client
+
+    import_openai.return_value.OpenAI.assert_called_once_with(
+        api_key="sk-test-key-12345", base_url="https://api.example.com"
+    )
+
 
 def test_embedding_with_bad_results(tmp_path):
     @register("null-embedding")
diff --git a/python/python/tests/test_hybrid_query.py b/python/python/tests/test_hybrid_query.py
index 65a7890bf..72dcaaa49 100644
--- a/python/python/tests/test_hybrid_query.py
+++ b/python/python/tests/test_hybrid_query.py
@@ -12,7 +12,7 @@ import pyarrow.compute as pc
 import pytest
 import pytest_asyncio
 
-from lancedb.index import FTS
+from lancedb.index import BTree, FTS, IvfPq
 from lancedb.table import AsyncTable, Table
 
 
@@ -99,6 +99,86 @@ async def test_async_hybrid_query_filters(table: AsyncTable):
     assert result["text"].to_pylist() == ["cat", "b"]
 
 
+@pytest.mark.asyncio
+async def test_hybrid_query_with_stale_fixed_size_binary_prefilter(
+    tmpdir_factory,
+):
+    tmp_path = str(tmpdir_factory.mktemp("stale_scalar_prefilter"))
+    db = await lancedb.connect_async(tmp_path)
+
+    def fixed_size_binary(value: int) -> bytes:
+        return value.to_bytes(16, byteorder="big")
+
+    num_rows = 1000
+    data = pa.table(
+        {
+            "space_id": pa.array(
+                [fixed_size_binary(i) for i in range(num_rows)],
+                type=pa.binary(16),
+            ),
+            "text": ["book"] * num_rows,
+            "vector": pa.array(
+                [[float(i), float(i)] for i in range(num_rows)],
+                type=pa.list_(pa.float32(), 2),
+            ),
+        }
+    )
+    table = await db.create_table("test", data)
+    await table.create_index(
+        "vector", config=IvfPq(num_partitions=4, num_sub_vectors=2)
+    )
+    await table.create_index("space_id", config=BTree())
+    await table.create_index("text", config=FTS(with_position=False))
+
+    # Advance the search indices without advancing the scalar index. This is the
+    # state that previously let hybrid search use an incomplete scalar prefilter.
+    await table.add(data)
+    lance_dataset = await table.to_lance()
+    lance_dataset.optimize.optimize_indices(index_names=["vector_idx", "text_idx"])
+    await table.checkout_latest()
+
+    scalar_stats = await table.index_stats("space_id_idx")
+    assert scalar_stats is not None
+    assert scalar_stats.num_indexed_rows == num_rows
+    assert scalar_stats.num_unindexed_rows == num_rows
+
+    for index_name in ["vector_idx", "text_idx"]:
+        search_stats = await table.index_stats(index_name)
+        assert search_stats is not None
+        assert search_stats.num_indexed_rows == num_rows * 2
+        assert search_stats.num_unindexed_rows == 0
+
+    matching_ids = [5, 10, 15, 20, 25, 30]
+    literals = [
+        f"arrow_cast(0x{fixed_size_binary(i).hex()}, 'FixedSizeBinary(16)')"
+        for i in matching_ids
+    ]
+    predicate = f"space_id IN ({', '.join(literals)})"
+    expected_ids = sorted(fixed_size_binary(i) for i in matching_ids for _ in range(2))
+
+    vector_query = (
+        table.query().where(predicate).nearest_to([5.0, 5.0]).limit(num_rows * 2)
+    )
+    vector_results = await vector_query.to_arrow()
+    assert sorted(vector_results["space_id"].to_pylist()) == expected_ids
+
+    fts_query = (
+        table.query().where(predicate).nearest_to_text("book").limit(num_rows * 2)
+    )
+    fts_results = await fts_query.to_arrow()
+    assert sorted(fts_results["space_id"].to_pylist()) == expected_ids
+
+    hybrid_results = await (
+        table.query()
+        .where(predicate)
+        .nearest_to([5.0, 5.0])
+        .nearest_to_text("book")
+        .limit(num_rows * 2)
+        .to_arrow()
+    )
+    assert sorted(hybrid_results["space_id"].to_pylist()) == expected_ids
+
+
 @pytest.mark.asyncio
 async def test_async_hybrid_query_default_limit(table: AsyncTable):
     # add 10 new rows
diff --git a/python/python/tests/test_import.py b/python/python/tests/test_import.py
new file mode 100644
index 000000000..4b87a0ce8
--- /dev/null
+++ b/python/python/tests/test_import.py
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import re
+import shutil
+import subprocess
+import sys
+
+import lancedb._lancedb as _lancedb
+import pytest
+
+
+@pytest.mark.skipif(sys.platform != "linux", reason="ldd is Linux-specific")
+def test_native_extension_does_not_link_openssl():
+    """OpenSSL-linked wheels abort when imported on RHEL hosts in FIPS mode."""
+    ldd = shutil.which("ldd")
+    if ldd is None:
+        pytest.skip("ldd is not installed")
+
+    result = subprocess.run(
+        [ldd, _lancedb.__file__],
+        check=True,
+        capture_output=True,
+        text=True,
+    )
+    openssl_libraries = re.findall(
+        r"^\s*(lib(?:crypto|ssl)\S*)\s+=>", result.stdout, flags=re.MULTILINE
+    )
+
+    assert not openssl_libraries, (
+        "the LanceDB native extension must use rustls instead of linking OpenSSL: "
+        f"{openssl_libraries}"
+    )
diff --git a/python/python/tests/test_index.py b/python/python/tests/test_index.py
index 1cf2c733c..94268a53e 100644
--- a/python/python/tests/test_index.py
+++ b/python/python/tests/test_index.py
@@ -372,6 +372,31 @@ async def test_create_vector_index(some_table: AsyncTable):
     assert stats.num_indices == 1
 
 
+@pytest.mark.asyncio
+async def test_create_ivf_index_reports_unsplittable_partitions(db_async):
+    dim = 8
+    num_partitions = 300  # More than 256 selects hierarchical k-means.
+    base_vectors = [[float(row == column) for column in range(dim)] for row in range(5)]
+    vectors = pa.array(base_vectors * 200, pa.list_(pa.float32(), dim))
+    table = await db_async.create_table(
+        "unsplittable_partitions",
+        pa.table({"vector": vectors}),
+    )
+
+    error_pattern = (
+        rf"Cannot create {num_partitions} IVF partitions: k-means could only form"
+    )
+    with pytest.raises(RuntimeError, match=error_pattern):
+        await table.create_index(
+            "vector",
+            config=IvfFlat(
+                distance_type="dot",
+                num_partitions=num_partitions,
+                max_iterations=10,
+            ),
+        )
+
+
 @pytest.mark.asyncio
 async def test_create_4bit_ivfpq_index(some_table: AsyncTable):
     # Can create
diff --git a/python/python/tests/test_package_metadata.py b/python/python/tests/test_package_metadata.py
new file mode 100644
index 000000000..5792f457b
--- /dev/null
+++ b/python/python/tests/test_package_metadata.py
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import importlib
+import re
+import sys
+from pathlib import Path
+
+import pytest
+
+
+def test_pyo3_abi_matches_minimum_supported_python():
+    project_dir = Path(__file__).parents[2]
+    pyproject = (project_dir / "pyproject.toml").read_text()
+    cargo_manifest = (project_dir / "Cargo.toml").read_text()
+
+    minimum_python = re.search(
+        r'^requires-python\s*=\s*">=(\d+)\.(\d+)"$', pyproject, re.MULTILINE
+    )
+    assert minimum_python is not None
+
+    major, minor = minimum_python.groups()
+    expected_abi = f"abi3-py{major}{minor}"
+    configured_abis = re.findall(r'"(abi3-py\d+)"', cargo_manifest)
+
+    assert configured_abis == [expected_abi, expected_abi], (
+        "the pyo3 runtime and build ABI features must both match requires-python"
+    )
+
+
+@pytest.mark.skipif(sys.platform != "win32", reason="Windows wheel regression test")
+def test_windows_wheel_tag_and_native_import():
+    project_dir = Path(__file__).parents[2]
+    wheels = list((project_dir.parent / "target" / "wheels").glob("lancedb-*.whl"))
+    if not wheels:
+        pytest.skip("no wheel artifact is available in this development environment")
+
+    assert len(wheels) == 1
+    assert wheels[0].name.endswith("-cp310-abi3-win_amd64.whl")
+
+    native_module = importlib.import_module("lancedb._lancedb")
+    assert Path(native_module.__file__).suffix == ".pyd"
diff --git a/python/python/tests/test_pydantic.py b/python/python/tests/test_pydantic.py
index e1d533784..db93d7c64 100644
--- a/python/python/tests/test_pydantic.py
+++ b/python/python/tests/test_pydantic.py
@@ -415,6 +415,17 @@ def test_nullable_vector():
     assert schema == pa.schema([pa.field("vec", pa.list_(pa.float32(), 16), True)])
 
 
+def test_bare_vector_raises_clear_error():
+    namespace = {
+        "__name__": "test_model_without_pyarrow",
+        "LanceModel": LanceModel,
+        "Vector": Vector,
+    }
+
+    with pytest.raises(TypeError, match=r"Vector must be parameterized.*Vector\(128\)"):
+        exec("class TestModel(LanceModel):\n    vector: Vector", namespace)
+
+
 def test_fixed_size_list_field():
     class TestModel(pydantic.BaseModel):
         vec: Vector(16)
diff --git a/python/python/tests/test_query.py b/python/python/tests/test_query.py
index 6840be052..d2629d1a8 100644
--- a/python/python/tests/test_query.py
+++ b/python/python/tests/test_query.py
@@ -570,6 +570,15 @@ def test_query_builder(table):
     assert all(np.array(rs[0]["vector"]) == [1, 2])
 
 
+def test_query_multiple_vectors(table):
+    results = table.search([np.array([1, 2]), np.array([4, 5])]).limit(1).to_list()
+
+    assert len(results) == 2
+    results_by_query = {result["query_index"]: result for result in results}
+    assert results_by_query[0]["id"] == 1
+    assert results_by_query[1]["id"] == 2
+
+
 def test_with_row_id(table: lancedb.table.Table):
     rs = table.search().with_row_id(True).to_arrow()
     assert "_rowid" in rs.column_names
diff --git a/python/python/tests/test_remote_db.py b/python/python/tests/test_remote_db.py
index d5d3569d3..ce8d5bd6e 100644
--- a/python/python/tests/test_remote_db.py
+++ b/python/python/tests/test_remote_db.py
@@ -35,6 +35,12 @@ def make_mock_http_handler(handler):
     return MockLanceDBHandler
 
 
+@pytest.mark.parametrize("db_name", ["a" * 64, "invalid..database"])
+def test_connect_rejects_invalid_cloud_dns_hostname(db_name):
+    with pytest.raises(ValueError, match="DNS labels must contain 1 to 63 bytes"):
+        lancedb.connect(f"db://{db_name}", api_key="fake")
+
+
 @contextlib.contextmanager
 def mock_lancedb_connection(handler):
     with http.server.HTTPServer(
diff --git a/python/python/tests/test_table.py b/python/python/tests/test_table.py
index 069527b21..eb6eaefaa 100644
--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -2,10 +2,13 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 
+import ctypes
+import gc
 import os
 import sys
 import threading
 import warnings
+import weakref
 from concurrent.futures import ThreadPoolExecutor
 from datetime import date, datetime, timedelta
 from time import sleep
@@ -99,6 +102,30 @@ def test_basic(mem_db: DBConnection):
     assert table.to_arrow() == expected_data
 
 
+def test_search_preserves_nulls_from_sliced_arrow_table(mem_db: DBConnection):
+    data = pa.table(
+        {
+            "id": [0, 1, 2, 3, 4],
+            "score_cn": [None, 22, None, 5, 8],
+            "score_mt": [None, 42, None, 5, 8],
+            "vector": [
+                [20, 19, -1, -1],
+                [41, 38, 22, 42],
+                [10, 10, -1, -1],
+                [5, 5, 5, 5],
+                [8, 8, 8, 8],
+            ],
+        }
+    ).slice(1)
+
+    table = mem_db.create_table("sliced_nullable", data=data)
+    result = table.search([41, 38, 22, 42]).limit(1).to_arrow()
+
+    assert result["id"].to_pylist() == [1]
+    assert result["score_cn"].to_pylist() == [22]
+    assert result["score_mt"].to_pylist() == [42]
+
+
 def test_table_to_pandas_default_matches_arrow(tmp_db: DBConnection):
     pd = pytest.importorskip("pandas")
     data = pa.table({"id": [1, 2], "text": ["one", "two"]})
@@ -435,6 +462,38 @@ def test_add(mem_db: DBConnection):
     _add(table, schema)
 
 
+def test_add_releases_arrow_buffers_without_gc(mem_db: DBConnection):
+    """Regression test for https://github.com/lancedb/lancedb/issues/2512."""
+    schema = pa.schema([pa.field("x", pa.int64())])
+    table = mem_db.create_table("test_add_releases_arrow_buffers", schema=schema)
+
+    class BufferOwner:
+        def __init__(self, size: int):
+            self.memory = ctypes.create_string_buffer(size)
+
+    owner_refs = []
+    gc_was_enabled = gc.isenabled()
+    gc.disable()
+    try:
+        for _ in range(3):
+            size = 8 * 1024
+            owner = BufferOwner(size)
+            arrow_buffer = pa.foreign_buffer(
+                ctypes.addressof(owner.memory), size, owner
+            )
+            array = pa.Array.from_buffers(pa.int64(), 1024, [None, arrow_buffer])
+            batch = pa.RecordBatch.from_arrays([array], schema=schema)
+            owner_refs.append(weakref.ref(owner))
+
+            table.add(batch)
+            del batch, array, arrow_buffer, owner
+
+        assert all(owner_ref() is None for owner_ref in owner_refs)
+    finally:
+        if gc_was_enabled:
+            gc.enable()
+
+
 def test_add_write_parallelism(mem_db: DBConnection):
     schema = pa.schema([pa.field("id", pa.int64())])
     table = mem_db.create_table("test", schema=schema)
@@ -870,6 +929,7 @@ def test_polars(mem_db: DBConnection):
 
     # enter table to polars dataframe
     result = table.to_polars()
+    assert isinstance(result, pl.LazyFrame)
     assert np.allclose(result.collect()["vector"].to_list(), data["vector"])
 
     # make sure filtering isn't broken
@@ -1786,6 +1846,27 @@ def test_add_with_empty_fixed_size_list_drops_bad_rows(mem_db: DBConnection):
     assert np.allclose(data["embedding"].to_pylist()[0], np.array([0.1] * 16))
 
 
+def test_add_nullable_fixed_size_list_with_none(mem_db: DBConnection):
+    """Regression test for issue #2340."""
+    table = mem_db.create_table(
+        "test_nullable_fixed_size_list",
+        schema=pa.schema(
+            [
+                pa.field("id", pa.string()),
+                pa.field("feature", pa.list_(pa.float32(), 256)),
+                pa.field("tags", pa.list_(pa.string())),
+            ]
+        ),
+    )
+
+    table.add([{"id": "1", "feature": None, "tags": ["tag1", "tag2"]}])
+
+    result = table.to_arrow()
+    assert result.to_pylist() == [
+        {"id": "1", "feature": None, "tags": ["tag1", "tag2"]}
+    ]
+
+
 def test_add_nullable_struct_with_none(mem_db: DBConnection):
     """Regression test for issue #2654: a nullable struct column whose
     first batch contains only None values must not crash in
@@ -1825,6 +1906,33 @@ def test_add_nullable_struct_with_none(mem_db: DBConnection):
     assert result.column("data").to_pylist() == [{"x": 1.0}, None]
 
 
+def test_read_mostly_null_list_v2_2_page_boundary(tmp_path):
+    # Regression test for #3194. This row/value count crosses a v2.2 structural
+    # encoding page boundary where Lance 3.0.0 sliced repetition/definition
+    # levels by row offset and decoded child arrays at different lengths.
+    num_rows = 64_885
+    num_values = 217
+    list_type = pa.list_(pa.float32())
+    source = pa.table(
+        {
+            "id": np.arange(num_rows, dtype=np.int64),
+            "coords": pa.array(
+                [[1.0, 2.0, 3.0, 4.0]] * num_values + [None] * (num_rows - num_values),
+                type=list_type,
+            ),
+        }
+    )
+    db = lancedb.connect(
+        tmp_path,
+        storage_options={"new_table_data_storage_version": "2.2"},
+    )
+    table = db.create_table("test_sparse_nullable_list", data=source)
+
+    result = table.search().select(["id", "coords"]).limit(num_rows).to_arrow()
+
+    assert result.equals(source)
+
+
 def test_add_with_integer_embeddings_preserves_casting(mem_db: DBConnection):
     class Schema(LanceModel):
         text: str
@@ -2110,6 +2218,45 @@ def test_merge(tmp_db: DBConnection, tmp_path):
     table.merge(other_dataset, left_on="id")
 
 
+@pytest.mark.parametrize("storage_version", ["legacy", "stable"])
+def test_search_after_merge(tmp_path, storage_version):
+    pytest.importorskip("lance")
+    pd = pytest.importorskip("pandas")
+
+    db = lancedb.connect(
+        tmp_path,
+        storage_options={"new_table_data_storage_version": storage_version},
+    )
+    rng = np.random.default_rng(42)
+    row_count = 512
+    vectors = rng.standard_normal((row_count, 8)).astype(np.float32)
+    table = db.create_table(
+        "search_after_merge",
+        data=pd.DataFrame(
+            {
+                "id": [str(i) for i in range(row_count)],
+                "vector": list(vectors),
+            }
+        ),
+    )
+    table.create_index("vector", config=IvfPq(num_partitions=1, num_sub_vectors=2))
+
+    links = pd.DataFrame(
+        {
+            "id": [str(i) for i in range(row_count // 2)],
+            "link": [f"https://example.com/{i}" for i in range(row_count // 2)],
+        }
+    )
+    table.merge(links, left_on="id")
+
+    query = table.search(vectors[-1]).refine_factor(50).limit(10)
+    assert "ANN" in query.explain_plan(verbose=True)
+
+    result = query.to_arrow()
+    links_by_id = dict(zip(result["id"].to_pylist(), result["link"].to_pylist()))
+    assert links_by_id[str(row_count - 1)] is None
+
+
 def test_delete(mem_db: DBConnection):
     table = mem_db.create_table(
         "my_table",
@@ -2196,6 +2343,20 @@ def test_update(mem_db: DBConnection):
     assert np.allclose(v, np.array([[1.2, 1.9], [1.1, 1.1]]))
 
 
+def test_update_with_arrow_scalar(mem_db: DBConnection):
+    schema = pa.schema({"id": pa.int64(), "vector": pa.list_(pa.float32(), 4)})
+    table = mem_db.create_table("my_table", schema=schema)
+    table.add([{"id": 1, "vector": [1.0, 2.0, 3.0, 4.0]}])
+
+    value = table.search().select(["vector"]).limit(1).to_arrow()["vector"][0]
+    assert isinstance(value, pa.FixedSizeListScalar)
+
+    result = table.update(where="id == 1", values={"vector": value})
+
+    assert result.rows_updated == 1
+    assert table.to_arrow()["vector"].to_pylist() == [[1.0, 2.0, 3.0, 4.0]]
+
+
 def test_update_types(mem_db: DBConnection):
     table = mem_db.create_table(
         "my_table",
@@ -2363,6 +2524,55 @@ def test_merge_insert(mem_db: DBConnection):
         )
 
 
+def test_merge_insert_nullable_pandas_into_pydantic_schema(mem_db: DBConnection):
+    # Regression test for https://github.com/lancedb/lancedb/issues/2366
+    pd = pytest.importorskip("pandas")
+
+    class Document(LanceModel):
+        id: int
+        title: str
+        content: str
+
+    table = mem_db.create_table("documents", schema=Document)
+    table.add(
+        pd.DataFrame(
+            {
+                "title": ["Old title", "Unchanged"],
+                "id": [2, 3],
+                "content": ["Old content", "Keep this"],
+            }
+        )
+    )
+
+    # Pandas produces nullable Arrow fields, in an order that differs from the
+    # non-nullable Pydantic schema. This is valid as long as the data has no nulls.
+    new_data = pd.DataFrame(
+        {
+            "title": ["Inserted", "Updated"],
+            "id": [1, 2],
+            "content": ["New row", "New content"],
+        }
+    )
+    result = (
+        table.merge_insert("id")
+        .when_matched_update_all()
+        .when_not_matched_insert_all()
+        .execute(new_data)
+    )
+
+    assert result.num_inserted_rows == 1
+    assert result.num_updated_rows == 1
+    expected = pa.Table.from_pylist(
+        [
+            {"id": 1, "title": "Inserted", "content": "New row"},
+            {"id": 2, "title": "Updated", "content": "New content"},
+            {"id": 3, "title": "Unchanged", "content": "Keep this"},
+        ],
+        schema=Document.to_arrow_schema(),
+    )
+    assert table.to_arrow().sort_by("id") == expected
+
+
 def test_merge_insert_by_source_delete_expr(mem_db: DBConnection):
     table = mem_db.create_table(
         "my_table",
@@ -2463,6 +2673,36 @@ def test_merge_insert_subschema(mem_db: DBConnection, data_format):
     assert table.to_arrow().sort_by("id") == expected
 
 
+def test_repeated_partial_merge_insert_with_scalar_index(mem_db: DBConnection):
+    def make_batch(start: int) -> pa.Table:
+        return pa.table(
+            {
+                "id": [f"id-{i:04}" for i in range(start, start + 100)],
+                "category": ["A"] * 100,
+                "value_a": [float(i) for i in range(start, start + 100)],
+                "value_b": [float(i) / 10 for i in range(100)],
+            }
+        )
+
+    table = mem_db.create_table("my_table", data=make_batch(0))
+    table.add(make_batch(100))
+    table.add(make_batch(200))
+    table.create_index("id", config=BTree())
+
+    ids = [f"id-{i:04}" for i in range(100, 200)]
+    for value in (999.0, 888.0):
+        result = (
+            table.merge_insert("id")
+            .when_matched_update_all()
+            .execute(pa.table({"id": ids, "value_a": [value] * 100}))
+        )
+        assert result.num_updated_rows == 100
+
+    actual = table.to_arrow().sort_by("id")
+    assert actual.num_rows == 300
+    assert actual["value_a"].to_pylist()[100:200] == [888.0] * 100
+
+
 @pytest.mark.asyncio
 async def test_merge_insert_async(mem_db_async: AsyncConnection):
     data = pa.table({"a": [1, 2, 3], "b": ["a", "b", "c"]})
@@ -2559,15 +2799,40 @@ def test_create_with_embedding_function(mem_db: DBConnection):
     assert actual == expected
 
 
+def test_create_f16_table_from_arrow_data(mem_db: DBConnection):
+    dimension = 32
+    num_rows = 512
+    values = pa.array(
+        np.random.default_rng(42)
+        .standard_normal(num_rows * dimension)
+        .astype(np.float16)
+    )
+    df = pa.table(
+        {
+            "text": [f"s-{i}" for i in range(num_rows)],
+            "vector": pa.FixedSizeListArray.from_arrays(values, dimension),
+        }
+    )
+    table = mem_db.create_table("f16_tbl", data=df)
+    assert table.schema.field("vector").type == pa.list_(pa.float16(), dimension)
+    table.create_index(num_partitions=2, num_sub_vectors=2)
+
+    query = df["vector"][2].as_py()
+    expected = table.search(query).limit(2).to_arrow()
+
+    assert "s-2" in expected["text"].to_pylist()
+
+
 def test_create_f16_table(mem_db: DBConnection):
     class MyTable(LanceModel):
         text: str
         vector: Vector(32, value_type=pa.float16())
 
+    rng = np.random.default_rng(42)
     df = pa.table(
         {
             "text": [f"s-{i}" for i in range(512)],
-            "vector": [np.random.randn(32).astype(np.float16) for _ in range(512)],
+            "vector": [rng.standard_normal(32).astype(np.float16) for _ in range(512)],
         }
     )
     table = mem_db.create_table(
@@ -3489,8 +3754,8 @@ def test_create_table_empty_list_no_schema_error(mem_db: DBConnection):
         mem_db.create_table("test_empty_no_schema", data=[])
 
 
-def test_add_table_with_empty_embeddings(tmp_path):
-    """Test exact scenario from issue #1968
+def test_create_table_without_data_with_vector_schema(tmp_path):
+    """Test exact scenario from issue #1968.
 
     Regression test for issue #1968:
     https://github.com/lancedb/lancedb/issues/1968
@@ -3502,6 +3767,9 @@ def test_add_table_with_empty_embeddings(tmp_path):
         embedding: Vector(16)
 
     table = db.create_table("test", schema=MySchema)
+    assert table.count_rows() == 0
+    assert table.schema == MySchema.to_arrow_schema()
+
     table.add(
         [{"text": "bar", "embedding": [0.1] * 16}],
         on_bad_vectors="drop",
diff --git a/python/python/tests/test_voyageai_embeddings.py b/python/python/tests/test_voyageai_embeddings.py
index ac1554cad..040cade1f 100644
--- a/python/python/tests/test_voyageai_embeddings.py
+++ b/python/python/tests/test_voyageai_embeddings.py
@@ -75,6 +75,22 @@ class TestVoyageAIModelRegistration:
         with pytest.raises(ValueError, match="not supported"):
             func.ndims()
 
+    def test_voyage3_source_embeddings_use_text_api(self, mock_voyageai_client):
+        """Regression test for text table data being sent to the multimodal API."""
+        mock_voyageai_client.tokenize.return_value = [["hello", "world"]]
+        mock_voyageai_client.embed.return_value.embeddings = [[0.1] * 1024]
+
+        registry = get_registry()
+        func = registry.get("voyageai").create(name="voyage-3")
+
+        embeddings = func.compute_source_embeddings("hello world")
+
+        assert embeddings == [[0.1] * 1024]
+        mock_voyageai_client.embed.assert_called_once_with(
+            texts=["hello world"], model="voyage-3", input_type="document"
+        )
+        mock_voyageai_client.multimodal_embed.assert_not_called()
+
     @pytest.mark.parametrize(
         "model_name",
         [
diff --git a/python/python/type_tests/connect.py b/python/python/type_tests/connect.py
new file mode 100644
index 000000000..eb2cba37c
--- /dev/null
+++ b/python/python/type_tests/connect.py
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+from typing import assert_type
+
+import lancedb
+from lancedb import AsyncConnection, DBConnection
+
+
+def check_connect_type() -> None:
+    assert_type(lancedb.connect("memory://"), DBConnection)
+
+
+async def check_connect_async_type() -> None:
+    assert_type(await lancedb.connect_async("memory://"), AsyncConnection)
diff --git a/python/uv.lock b/python/uv.lock
index 551dc3f68..2cdcb182e 100644
--- a/python/uv.lock
+++ b/python/uv.lock
@@ -1998,7 +1998,7 @@ requires-dist = [
     { name = "pillow", marker = "extra == 'clip'", specifier = ">=12.1.1" },
     { name = "pillow", marker = "extra == 'embeddings'", specifier = ">=12.1.1" },
     { name = "pillow", marker = "extra == 'siglip'", specifier = ">=12.1.1" },
-    { name = "polars", marker = "extra == 'tests'", specifier = ">=0.19,<=1.3.0" },
+    { name = "polars", marker = "extra == 'tests'", specifier = ">=0.19,<=1.32.3" },
     { name = "pre-commit", marker = "extra == 'dev'", specifier = ">=3.5.0" },
     { name = "pyarrow", specifier = ">=16" },
     { name = "pyarrow", marker = "extra == 'tests'", specifier = "<25" },
diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml
index 66db3cf12..96ea9ec95 100644
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -49,8 +49,8 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, optional = true }
-# Pin the transitive GooseFS SDK until the 0.1.6 compile break is fixed upstream.
-goosefs-sdk = { version = "=0.1.5", optional = true }
+# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency.
+goosefs-sdk = { version = "=0.1.9", optional = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
@@ -75,6 +75,8 @@ reqwest = { version = "0.12.0", default-features = false, features = [
     "http2",
     "json",
     "macos-system-configuration",
+    # Avoid linking OpenSSL into Python wheels, which breaks on FIPS hosts.
+    "rustls-tls-native-roots",
     "stream",
 ], optional = true }
 http = { version = "1", optional = true } # Matching what is in reqwest
diff --git a/rust/lancedb/src/blob.rs b/rust/lancedb/src/blob.rs
index 3448257ab..e1c18dd84 100644
--- a/rust/lancedb/src/blob.rs
+++ b/rust/lancedb/src/blob.rs
@@ -17,7 +17,7 @@ use arrow_array::builder::LargeBinaryBuilder;
 use arrow_schema::{DataType, Field, Schema};
 use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
 use lance_arrow::FieldExt;
-use lance_encoding::version::LanceFileVersion;
+use lance_file::version::LanceFileVersion;
 use lance_io::object_store::ObjectStore;
 use object_store::path::Path;
 
diff --git a/rust/lancedb/src/connection.rs b/rust/lancedb/src/connection.rs
index 89e59e12e..dd53a2d2e 100644
--- a/rust/lancedb/src/connection.rs
+++ b/rust/lancedb/src/connection.rs
@@ -34,7 +34,7 @@ use crate::remote::{
     db::{OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION},
 };
 use lance::io::ObjectStoreParams;
-pub use lance_encoding::version::LanceFileVersion;
+pub use lance_file::version::LanceFileVersion;
 #[cfg(feature = "remote")]
 use lance_io::object_store::StorageOptions;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
diff --git a/rust/lancedb/src/connection/create_table.rs b/rust/lancedb/src/connection/create_table.rs
index 66f6dfa8d..b10141beb 100644
--- a/rust/lancedb/src/connection/create_table.rs
+++ b/rust/lancedb/src/connection/create_table.rs
@@ -202,6 +202,17 @@ mod tests {
         assert_eq!(table.count_rows(None).await.unwrap(), 0);
     }
 
+    #[tokio::test]
+    async fn create_table_in_named_memory_database() {
+        let db = connect("memory://foo").execute().await.unwrap();
+        let batch = record_batch!(("id", Int64, [1, 2, 3])).unwrap();
+
+        let table = db.create_table("my_table", batch).execute().await.unwrap();
+
+        assert_eq!(table.uri().await.unwrap(), "memory://foo/my_table.lance");
+        assert_eq!(table.count_rows(None).await.unwrap(), 3);
+    }
+
     async fn test_create_table_with_data<T>(data: T)
     where
         T: Scannable + 'static,
diff --git a/rust/lancedb/src/database/listing.rs b/rust/lancedb/src/database/listing.rs
index d5cb6b0a4..fb58ed3b9 100644
--- a/rust/lancedb/src/database/listing.rs
+++ b/rust/lancedb/src/database/listing.rs
@@ -12,7 +12,7 @@ use lance::dataset::refs::Ref;
 use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
 use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
-use lance_encoding::version::LanceFileVersion;
+use lance_file::version::LanceFileVersion;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
@@ -1294,9 +1294,11 @@ mod tests {
     use crate::connection::ConnectRequest;
     use crate::data::scannable::Scannable;
     use crate::database::{CreateTableMode, CreateTableRequest};
-    use crate::table::WriteOptions;
+    use crate::query::QueryRequest;
+    use crate::table::{AnyQuery, WriteOptions};
     use arrow_array::{Int32Array, RecordBatch, StringArray};
     use arrow_schema::{DataType, Field, Schema};
+    use futures::TryStreamExt;
     use futures::future::try_join_all;
     use std::path::PathBuf;
     use tempfile::tempdir;
@@ -1430,6 +1432,156 @@ mod tests {
         assert!(!tempdir.path().join("__manifest").exists());
     }
 
+    /// Regression test for https://github.com/lancedb/lancedb/issues/1600.
+    ///
+    /// Opening a table used to create a separate object-store client instead of
+    /// reusing the one that successfully connected to the database.  Repeating
+    /// credential discovery made S3 table opens intermittent, especially in AWS
+    /// Lambda, and the failed open was reported as `TableNotFound`.
+    #[tokio::test]
+    async fn test_open_table_reuses_connection_object_store() {
+        let tempdir = tempdir().unwrap();
+        let uri = tempdir.path().to_str().unwrap();
+        let registry = Arc::new(lance_io::object_store::ObjectStoreRegistry::default());
+        let session = Arc::new(lance::session::Session::new(16, 16, registry.clone()));
+
+        let request = ConnectRequest {
+            uri: uri.to_string(),
+            #[cfg(feature = "remote")]
+            client_config: Default::default(),
+            options: Default::default(),
+            namespace_client_properties: Default::default(),
+            manifest_enabled: false,
+            read_consistency_interval: None,
+            session: Some(session),
+        };
+        let db = ListingDatabase::connect_with_options(&request)
+            .await
+            .unwrap();
+
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+        db.create_table(CreateTableRequest {
+            name: "test".to_string(),
+            namespace_path: vec![],
+            data: Box::new(RecordBatch::new_empty(schema)) as Box<dyn Scannable>,
+            mode: CreateTableMode::Create,
+            write_options: Default::default(),
+            location: None,
+            namespace_client: None,
+        })
+        .await
+        .unwrap();
+
+        let before_open = registry.stats();
+        for _ in 0..3 {
+            let table = db
+                .open_table(OpenTableRequest {
+                    name: "test".to_string(),
+                    namespace_path: vec![],
+                    index_cache_size: None,
+                    lance_read_params: None,
+                    location: None,
+                    namespace_client: None,
+                    managed_versioning: None,
+                })
+                .await
+                .unwrap();
+            assert_eq!(table.count_rows(None).await.unwrap(), 0);
+        }
+
+        let after_open = registry.stats();
+        assert_eq!(after_open.misses, before_open.misses);
+        assert!(after_open.hits >= before_open.hits + 3);
+    }
+
+    /// Regression test for https://github.com/lancedb/lancedb/issues/3197.
+    #[cfg(unix)]
+    #[tokio::test]
+    async fn test_open_table_follows_hugging_face_symlinks() {
+        let (tempdir, db) = setup_database().await;
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+        db.create_table(CreateTableRequest {
+            name: "test".to_string(),
+            namespace_path: vec![],
+            data: Box::new(
+                RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1, 2, 3]))])
+                    .unwrap(),
+            ) as Box<dyn Scannable>,
+            mode: CreateTableMode::Create,
+            write_options: Default::default(),
+            location: None,
+            namespace_client: None,
+        })
+        .await
+        .unwrap();
+
+        let table_dir = tempdir.path().join("test.lance");
+        let versions_dir = table_dir.join("_versions");
+        let manifest_path = std::fs::read_dir(&versions_dir)
+            .unwrap()
+            .map(|entry| entry.unwrap().path())
+            .find(|path| path.extension().is_some_and(|ext| ext == "manifest"))
+            .unwrap();
+        let data_path = std::fs::read_dir(table_dir.join("data"))
+            .unwrap()
+            .map(|entry| entry.unwrap().path())
+            .find(|path| path.extension().is_some_and(|ext| ext == "lance"))
+            .unwrap();
+
+        // Hugging Face snapshots keep dataset objects in a separate blob directory and
+        // expose them through relative symlinks.
+        let blobs_dir = tempdir.path().join("blobs");
+        std::fs::create_dir(&blobs_dir).unwrap();
+        let manifest_blob = "9b603c63d0e692e05d58be25605f2f2064cc781e5ff94fe983a405059547b816";
+        let data_blob = "be64f20e5723bd0a27cfdbdb41cf7d6fad94cd572a71973b717fb8340f4310c5";
+        std::fs::rename(&manifest_path, blobs_dir.join(manifest_blob)).unwrap();
+        std::fs::rename(&data_path, blobs_dir.join(data_blob)).unwrap();
+        std::os::unix::fs::symlink(Path::new("../../blobs").join(manifest_blob), &manifest_path)
+            .unwrap();
+        std::os::unix::fs::symlink(Path::new("../../blobs").join(data_blob), &data_path).unwrap();
+        let symlink_len = std::fs::symlink_metadata(&manifest_path).unwrap().len();
+        let target_len = std::fs::metadata(&manifest_path).unwrap().len();
+        assert_ne!(symlink_len, target_len);
+
+        drop(db);
+        let db = ListingDatabase::connect_with_options(&ConnectRequest {
+            uri: tempdir.path().to_str().unwrap().to_string(),
+            #[cfg(feature = "remote")]
+            client_config: Default::default(),
+            options: Default::default(),
+            namespace_client_properties: Default::default(),
+            manifest_enabled: false,
+            read_consistency_interval: None,
+            session: None,
+        })
+        .await
+        .unwrap();
+
+        let table = db
+            .open_table(OpenTableRequest {
+                name: "test".to_string(),
+                namespace_path: vec![],
+                index_cache_size: None,
+                lance_read_params: None,
+                location: None,
+                namespace_client: None,
+                managed_versioning: None,
+            })
+            .await
+            .unwrap();
+        let batches = table
+            .query(
+                &AnyQuery::Query(QueryRequest::default()),
+                Default::default(),
+            )
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap();
+        assert_eq!(batches.iter().map(RecordBatch::num_rows).sum::<usize>(), 3);
+    }
+
     #[tokio::test]
     async fn test_clone_table_basic() {
         let (_tempdir, db) = setup_database().await;
@@ -2334,7 +2486,7 @@ mod tests {
 
     #[tokio::test]
     async fn test_table_uri() {
-        let (_tempdir, db) = setup_database().await;
+        let (_tempdir, mut db) = setup_database().await;
 
         let mut pb = PathBuf::new();
         pb.push(db.uri.clone());
@@ -2343,6 +2495,18 @@ mod tests {
         let expected = pb.to_str().unwrap();
         let uri = db.table_uri("test").ok().unwrap();
         assert_eq!(uri, expected);
+
+        // URI paths always use forward slashes, even on Windows. Using
+        // `Path::join` here used to produce `az://container/prefix\\test.lance`,
+        // which Azure treated as a different object from the table returned by
+        // `table_names` (https://github.com/lancedb/lancedb/issues/1072).
+        for base_uri in ["az://container/prefix", "az://container/prefix/"] {
+            db.uri = base_uri.to_string();
+            assert_eq!(
+                db.table_uri("test").unwrap(),
+                "az://container/prefix/test.lance"
+            );
+        }
     }
 
     /// Regression: connecting via a URL-style URI (which goes through
diff --git a/rust/lancedb/src/database/namespace.rs b/rust/lancedb/src/database/namespace.rs
index d18c78682..740e11645 100644
--- a/rust/lancedb/src/database/namespace.rs
+++ b/rust/lancedb/src/database/namespace.rs
@@ -201,7 +201,7 @@ impl LanceNamespaceDatabase {
         &self,
         request: &DbCreateTableRequest,
     ) -> Result<(
-        Option<lance_encoding::version::LanceFileVersion>,
+        Option<lance_file::version::LanceFileVersion>,
         Option<bool>,
         Option<bool>,
     )> {
@@ -214,7 +214,7 @@ impl LanceNamespaceDatabase {
 
         let storage_version_override = storage_options
             .and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
-            .map(|s| s.parse::<lance_encoding::version::LanceFileVersion>())
+            .map(|s| s.parse::<lance_file::version::LanceFileVersion>())
             .transpose()?;
 
         let v2_manifest_override = storage_options
diff --git a/rust/lancedb/src/error.rs b/rust/lancedb/src/error.rs
index f6f596f3d..4a6e6d8d9 100644
--- a/rust/lancedb/src/error.rs
+++ b/rust/lancedb/src/error.rs
@@ -169,6 +169,12 @@ impl From<DataFusionError> for Error {
 
 impl From<lance::Error> for Error {
     fn from(source: lance::Error) -> Self {
+        if has_unsupported_local_filesystem_source(&source) {
+            return Self::NotSupported {
+                message: "the filesystem does not support an operation required for safe Lance commits (such as atomic rename). Object-storage mounts such as Mountpoint for Amazon S3 are not supported; use the native object-store URI (for example, s3://bucket/path) instead".to_string(),
+            };
+        }
+
         // Try to unwrap external errors that were wrapped by lance
         match source {
             lance::Error::Wrapped { error, .. } => Self::from_box_error(error),
@@ -181,6 +187,27 @@ impl From<lance::Error> for Error {
     }
 }
 
+fn has_unsupported_local_filesystem_source(error: &(dyn std::error::Error + 'static)) -> bool {
+    let mut current = Some(error);
+    let mut is_local_filesystem = false;
+    let mut is_unsupported = false;
+    while let Some(error) = current {
+        is_local_filesystem |= error
+            .downcast_ref::<object_store::Error>()
+            .is_some_and(|error| {
+                matches!(error, object_store::Error::Generic { store, .. } if *store == "LocalFileSystem")
+            });
+        is_unsupported |= error
+            .downcast_ref::<std::io::Error>()
+            .is_some_and(|error| error.kind() == std::io::ErrorKind::Unsupported);
+        if is_local_filesystem && is_unsupported {
+            return true;
+        }
+        current = error.source();
+    }
+    false
+}
+
 impl Error {
     fn from_box_error(mut source: Box<dyn std::error::Error + Send + Sync>) -> Self {
         source = match source.downcast::<Self>() {
@@ -270,3 +297,46 @@ impl From<candle_core::Error> for Error {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn unsupported_filesystem_operations_have_actionable_error() {
+        let object_store_error = object_store::Error::Generic {
+            store: "LocalFileSystem",
+            source: Box::new(std::io::Error::from(std::io::ErrorKind::Unsupported)),
+        };
+        let lance_error = lance::Error::io_source(Box::new(object_store_error));
+
+        let error = Error::from(lance_error);
+
+        assert!(matches!(
+            error,
+            Error::NotSupported { message }
+                if message.contains("Mountpoint for Amazon S3")
+                    && message.contains("s3://bucket/path")
+        ));
+    }
+
+    #[test]
+    fn other_io_errors_remain_lance_errors() {
+        let object_store_error = object_store::Error::Generic {
+            store: "LocalFileSystem",
+            source: Box::new(std::io::Error::from(std::io::ErrorKind::PermissionDenied)),
+        };
+        let lance_error = lance::Error::io_source(Box::new(object_store_error));
+
+        assert!(matches!(Error::from(lance_error), Error::Lance { .. }));
+    }
+
+    #[test]
+    fn unsupported_non_filesystem_errors_remain_lance_errors() {
+        let lance_error = lance::Error::io_source(Box::new(std::io::Error::from(
+            std::io::ErrorKind::Unsupported,
+        )));
+
+        assert!(matches!(Error::from(lance_error), Error::Lance { .. }));
+    }
+}
diff --git a/rust/lancedb/src/io/object_store.rs b/rust/lancedb/src/io/object_store.rs
index d27357b82..d594bd857 100644
--- a/rust/lancedb/src/io/object_store.rs
+++ b/rust/lancedb/src/io/object_store.rs
@@ -132,9 +132,14 @@ impl ObjectStore for MirroringObjectStore {
         if to.primary_only() {
             self.primary.copy_opts(from, to, options).await
         } else {
-            self.secondary.copy_opts(from, to, options.clone()).await?;
-            self.primary.copy_opts(from, to, options).await?;
-            Ok(())
+            // The secondary store can be process-local and less durable than the
+            // primary, so a source written by another process may not exist here
+            // or may be evicted before the copy begins.
+            match self.secondary.copy_opts(from, to, options.clone()).await {
+                Ok(()) | Err(Error::NotFound { .. }) => {}
+                Err(err) => return Err(err),
+            }
+            self.primary.copy_opts(from, to, options).await
         }
     }
 }
@@ -192,7 +197,8 @@ mod test {
     use futures::TryStreamExt;
     use lance::{dataset::WriteParams, io::ObjectStoreParams};
     use lance_testing::datagen::{BatchGenerator, IncrementingInt32, RandomVector};
-    use object_store::local::LocalFileSystem;
+    use object_store::{local::LocalFileSystem, memory::InMemory};
+    use std::time::Duration;
     use tempfile;
 
     use crate::{
@@ -201,6 +207,139 @@ mod test {
         table::WriteOptions,
     };
 
+    #[derive(Debug)]
+    struct EvictBeforeCopyStore {
+        inner: Arc<dyn ObjectStore>,
+    }
+
+    impl std::fmt::Display for EvictBeforeCopyStore {
+        fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+            write!(f, "EvictBeforeCopyStore")
+        }
+    }
+
+    #[async_trait]
+    impl ObjectStore for EvictBeforeCopyStore {
+        async fn put_opts(
+            &self,
+            location: &Path,
+            payload: PutPayload,
+            options: PutOptions,
+        ) -> Result<PutResult> {
+            self.inner.put_opts(location, payload, options).await
+        }
+
+        async fn put_multipart_opts(
+            &self,
+            location: &Path,
+            options: PutMultipartOptions,
+        ) -> Result<Box<dyn MultipartUpload>> {
+            self.inner.put_multipart_opts(location, options).await
+        }
+
+        async fn get_opts(&self, location: &Path, options: GetOptions) -> Result<GetResult> {
+            self.inner.get_opts(location, options).await
+        }
+
+        fn delete_stream(
+            &self,
+            locations: BoxStream<'static, Result<Path>>,
+        ) -> BoxStream<'static, Result<Path>> {
+            self.inner.delete_stream(locations)
+        }
+
+        fn list(&self, prefix: Option<&Path>) -> BoxStream<'static, Result<ObjectMeta>> {
+            self.inner.list(prefix)
+        }
+
+        async fn list_with_delimiter(&self, prefix: Option<&Path>) -> Result<ListResult> {
+            self.inner.list_with_delimiter(prefix).await
+        }
+
+        async fn copy_opts(&self, from: &Path, to: &Path, options: CopyOptions) -> Result<()> {
+            self.inner.delete(from).await?;
+            self.inner.copy_opts(from, to, options).await
+        }
+    }
+
+    #[tokio::test]
+    async fn test_copy_when_source_is_missing_from_secondary() {
+        let primary_dir = tempfile::tempdir().unwrap();
+        let secondary_dir = tempfile::tempdir().unwrap();
+        let primary: Arc<dyn ObjectStore> =
+            Arc::new(LocalFileSystem::new_with_prefix(primary_dir.path()).unwrap());
+        let secondary: Arc<dyn ObjectStore> =
+            Arc::new(LocalFileSystem::new_with_prefix(secondary_dir.path()).unwrap());
+        let store = MirroringObjectStore {
+            primary: primary.clone(),
+            secondary: secondary.clone(),
+        };
+        let staging = Path::from("_versions/1.manifest-staging");
+        let finalized = Path::from("_versions/1.manifest");
+
+        primary
+            .put(&staging, "manifest contents".into())
+            .await
+            .unwrap();
+
+        tokio::time::timeout(Duration::from_secs(5), store.copy(&staging, &finalized))
+            .await
+            .expect("copy should not hang when the secondary source is missing")
+            .unwrap();
+
+        let copied = primary
+            .get(&finalized)
+            .await
+            .unwrap()
+            .bytes()
+            .await
+            .unwrap();
+        assert_eq!(copied, "manifest contents");
+        assert!(matches!(
+            secondary.head(&finalized).await,
+            Err(Error::NotFound { .. })
+        ));
+    }
+
+    #[tokio::test]
+    async fn test_copy_when_secondary_source_disappears_after_head() {
+        let primary: Arc<dyn ObjectStore> = Arc::new(InMemory::new());
+        let secondary_inner: Arc<dyn ObjectStore> = Arc::new(InMemory::new());
+        let secondary: Arc<dyn ObjectStore> = Arc::new(EvictBeforeCopyStore {
+            inner: secondary_inner.clone(),
+        });
+        let store = MirroringObjectStore {
+            primary: primary.clone(),
+            secondary,
+        };
+        let staging = Path::from("_versions/1.manifest-staging");
+        let finalized = Path::from("_versions/1.manifest");
+
+        primary
+            .put(&staging, "manifest contents".into())
+            .await
+            .unwrap();
+        secondary_inner
+            .put(&staging, "manifest contents".into())
+            .await
+            .unwrap();
+
+        store.copy(&staging, &finalized).await.unwrap();
+
+        let copied = primary
+            .get(&finalized)
+            .await
+            .unwrap()
+            .bytes()
+            .await
+            .unwrap();
+        assert_eq!(copied, "manifest contents");
+        assert!(matches!(
+            secondary_inner.head(&finalized).await,
+            Err(Error::NotFound { .. })
+        ));
+    }
+
     // This test is ignored because lance 3.0 introduced LocalWriter optimization
     // that bypasses the object store wrapper for local writes. The mirroring feature
     // still works for remote/cloud storage, but can't be tested with local storage.
diff --git a/rust/lancedb/src/query.rs b/rust/lancedb/src/query.rs
index b76865043..b2c5fefbe 100644
--- a/rust/lancedb/src/query.rs
+++ b/rust/lancedb/src/query.rs
@@ -1661,14 +1661,8 @@ mod tests {
 
     #[tokio::test]
     async fn test_setters_getters() {
-        // TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051
-        // is fixed
-        let tmp_dir = tempdir().unwrap();
-        let dataset_path = tmp_dir.path().join("test.lance");
-        let uri = dataset_path.to_str().unwrap();
-
         let batches = make_test_batches();
-        let conn = connect(uri).execute().await.unwrap();
+        let conn = connect("memory://foo").execute().await.unwrap();
         let table = conn
             .create_table("my_table", batches)
             .execute()
@@ -1763,14 +1757,8 @@ mod tests {
 
     #[tokio::test]
     async fn test_execute() {
-        // TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051
-        // is fixed
-        let tmp_dir = tempdir().unwrap();
-        let dataset_path = tmp_dir.path().join("test.lance");
-        let uri = dataset_path.to_str().unwrap();
-
         let batches = make_non_empty_batches();
-        let conn = connect(uri).execute().await.unwrap();
+        let conn = connect("memory://foo").execute().await.unwrap();
         let table = conn
             .create_table("my_table", batches)
             .execute()
@@ -1889,14 +1877,8 @@ mod tests {
 
     #[tokio::test]
     async fn test_select_with_transform() {
-        // TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051
-        // is fixed
-        let tmp_dir = tempdir().unwrap();
-        let dataset_path = tmp_dir.path().join("test.lance");
-        let uri = dataset_path.to_str().unwrap();
-
         let batches = make_non_empty_batches();
-        let conn = connect(uri).execute().await.unwrap();
+        let conn = connect("memory://foo").execute().await.unwrap();
         let table = conn
             .create_table("my_table", batches)
             .execute()
@@ -1993,15 +1975,9 @@ mod tests {
 
     #[tokio::test]
     async fn test_execute_no_vector() {
-        // TODO: Switch back to memory://foo after https://github.com/lancedb/lancedb/issues/1051
-        // is fixed
-        let tmp_dir = tempdir().unwrap();
-        let dataset_path = tmp_dir.path().join("test.lance");
-        let uri = dataset_path.to_str().unwrap();
-
         // test that it's ok to not specify a query vector (just filter / limit)
         let batches = make_non_empty_batches();
-        let conn = connect(uri).execute().await.unwrap();
+        let conn = connect("memory://foo").execute().await.unwrap();
         let table = conn
             .create_table("my_table", batches)
             .execute()
diff --git a/rust/lancedb/src/remote/client.rs b/rust/lancedb/src/remote/client.rs
index 9e34fca9f..57dd89890 100644
--- a/rust/lancedb/src/remote/client.rs
+++ b/rust/lancedb/src/remote/client.rs
@@ -373,6 +373,37 @@ pub fn parse_db_url(db_url: &str) -> Result<ParsedDbUrl> {
     Ok(ParsedDbUrl { db_name, db_prefix })
 }
 
+fn validate_dns_hostname(hostname: &str) -> Result<()> {
+    let ascii_hostname = match url::Host::parse(hostname) {
+        Ok(url::Host::Domain(hostname)) => hostname,
+        Ok(_) => {
+            return Err(Error::InvalidInput {
+                message: "LanceDB Cloud database URI or region produced a non-DNS hostname"
+                    .to_string(),
+            });
+        }
+        Err(err) => {
+            return Err(Error::InvalidInput {
+                message: format!(
+                    "LanceDB Cloud database URI or region produced an invalid hostname: {err}"
+                ),
+            });
+        }
+    };
+
+    if ascii_hostname.len() > 253
+        || ascii_hostname
+            .split('.')
+            .any(|label| label.is_empty() || label.len() > 63)
+    {
+        return Err(Error::InvalidInput {
+            message: "LanceDB Cloud database URI or region produced an invalid hostname: DNS labels must contain 1 to 63 bytes and the full hostname must not exceed 253 bytes".to_string(),
+        });
+    }
+
+    Ok(())
+}
+
 impl RestfulLanceDbClient<Sender> {
     fn get_timeout(passed: Option<Duration>, env_var: &str) -> Result<Option<Duration>> {
         if let Some(passed) = passed {
@@ -480,7 +511,11 @@ impl RestfulLanceDbClient<Sender> {
 
         let host = match host_override {
             Some(host_override) => host_override,
-            None => format!("https://{}.{}.api.lancedb.com", parsed_url.db_name, region),
+            None => {
+                let hostname = format!("{}.{}.api.lancedb.com", parsed_url.db_name, region);
+                validate_dns_hostname(&hostname)?;
+                format!("https://{hostname}")
+            }
         };
         debug!("Created client for host: {}", host);
         let retry_config = client_config.retry_config.clone().try_into()?;
@@ -1157,6 +1192,29 @@ mod tests {
         assert_eq!(headers.get("x-api-key").unwrap(), "api-key");
     }
 
+    #[test]
+    fn test_rejects_invalid_cloud_dns_hostname() {
+        let invalid_database_names = ["a".repeat(64), "invalid..database".to_string()];
+
+        for db_name in invalid_database_names {
+            let parsed_url = parse_db_url(&format!("db://{db_name}")).unwrap();
+            let error = RestfulLanceDbClient::<Sender>::try_new(
+                &parsed_url,
+                "us-east-1",
+                None,
+                HeaderMap::new(),
+                ClientConfig::default(),
+                None,
+            )
+            .unwrap_err();
+
+            assert!(
+                matches!(error, Error::InvalidInput { ref message } if message.contains("DNS labels must contain 1 to 63 bytes")),
+                "unexpected error: {error}"
+            );
+        }
+    }
+
     // Test implementation of HeaderProvider
     #[derive(Debug, Clone)]
     struct TestHeaderProvider {
diff --git a/rust/lancedb/src/remote/table.rs b/rust/lancedb/src/remote/table.rs
index 5fefabeb2..388bed0f7 100644
--- a/rust/lancedb/src/remote/table.rs
+++ b/rust/lancedb/src/remote/table.rs
@@ -2791,9 +2791,10 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
     }
 
     async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>> {
+        let encoded_name = urlencoding::encode(index_name);
         let mut request = self.post_read(&format!(
-            "/v1/table/{}/index/{}/stats/",
-            self.identifier, index_name
+            "/v1/table/{}/index/{encoded_name}/stats/",
+            self.identifier
         ));
         let version = self.current_version().await;
         let mut body = serde_json::json!({ "version": version });
@@ -2820,9 +2821,10 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
     }
 
     async fn drop_index(&self, index_name: &str) -> Result<()> {
+        let encoded_name = urlencoding::encode(index_name);
         let request = self.apply_branch_query(self.client.post(&format!(
-            "/v1/table/{}/index/{}/drop/",
-            self.identifier, index_name
+            "/v1/table/{}/index/{encoded_name}/drop/",
+            self.identifier
         )));
         let (request_id, response) = self.send(request, true).await?;
         if response.status() == StatusCode::NOT_FOUND {
@@ -2835,9 +2837,10 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
     }
 
     async fn prewarm_index(&self, index_name: &str) -> Result<()> {
+        let encoded_name = urlencoding::encode(index_name);
         let request = self.client.post(&format!(
-            "/v1/table/{}/index/{}/prewarm/",
-            self.identifier, index_name
+            "/v1/table/{}/index/{encoded_name}/prewarm/",
+            self.identifier
         ));
         let (request_id, response) = self.send(request, true).await?;
         if response.status() == StatusCode::NOT_FOUND {
@@ -2939,7 +2942,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
 }
 
 #[derive(Serialize, Clone, Debug)]
-pub(crate) struct MergeInsertRequest {
+pub struct MergeInsertRequest {
     on: String,
     when_matched_update_all: bool,
     when_matched_update_all_filt: Option<String>,
@@ -5904,16 +5907,18 @@ mod tests {
             .await
             .unwrap();
 
+        // Positions are relative to the first retained token, so dropping the
+        // leading "hello" stop word does not shift the remaining tokens.
         assert_eq!(
             tokens,
             vec![
                 FtsToken {
                     text: "こんにちは".to_string(),
-                    position: 1,
+                    position: 0,
                 },
                 FtsToken {
                     text: "世界".to_string(),
-                    position: 2,
+                    position: 1,
                 },
             ]
         );
@@ -6489,6 +6494,41 @@ mod tests {
         assert!(matches!(e, Error::IndexNotFound { .. }));
     }
 
+    /// Index names are unvalidated, so reserved characters must be
+    /// percent-encoded or they restructure the request path.
+    #[tokio::test]
+    async fn test_per_index_paths_encode_reserved_characters() {
+        const NAME: &str = "my/index?a#b c";
+        const PREFIX: &str = "/v1/table/my_table/index/my%2Findex%3Fa%23b%20c";
+
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.url().path(), format!("{PREFIX}/stats/"));
+            let body = serde_json::json!({
+              "num_indexed_rows": 1,
+              "num_unindexed_rows": 0,
+              "index_type": "IVF_PQ",
+              "distance_type": "l2"
+            });
+            http::Response::builder()
+                .status(200)
+                .body(serde_json::to_string(&body).unwrap())
+                .unwrap()
+        });
+        assert!(table.index_stats(NAME).await.unwrap().is_some());
+
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.url().path(), format!("{PREFIX}/drop/"));
+            http::Response::builder().status(200).body("{}").unwrap()
+        });
+        table.drop_index(NAME).await.unwrap();
+
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.url().path(), format!("{PREFIX}/prewarm/"));
+            http::Response::builder().status(200).body("{}").unwrap()
+        });
+        table.prewarm_index(NAME).await.unwrap();
+    }
+
     #[tokio::test]
     async fn test_set_lsm_write_spec_unsharded() {
         let table = Table::new_with_handler("my_table", |request| {
diff --git a/rust/lancedb/src/remote/table/blobs.rs b/rust/lancedb/src/remote/table/blobs.rs
index bb8a5d103..387d3c6dc 100644
--- a/rust/lancedb/src/remote/table/blobs.rs
+++ b/rust/lancedb/src/remote/table/blobs.rs
@@ -90,7 +90,7 @@ struct RemoteBlobState {
 
 /// Seekable Cloud blob handle over HTTP Range.
 #[derive(Debug)]
-pub(crate) struct RemoteBlobFile {
+pub struct RemoteBlobFile {
     requester: Arc<dyn BlobRangeRequester>,
     state: Mutex<RemoteBlobState>,
     closed: AtomicBool,
diff --git a/rust/lancedb/src/remote/table/insert.rs b/rust/lancedb/src/remote/table/insert.rs
index 67ea7765d..a4a28a9c6 100644
--- a/rust/lancedb/src/remote/table/insert.rs
+++ b/rust/lancedb/src/remote/table/insert.rs
@@ -33,7 +33,7 @@ use crate::table::{AddResult, MergeResult};
 /// same Arrow-IPC streaming body and error side-channel; only the target
 /// endpoint, query parameters, and parsed result type differ.
 #[derive(Debug, Clone)]
-pub(crate) enum WriteOp {
+pub enum WriteOp {
     /// `add`: stream to `/v1/table/{id}/insert/`, optionally overwriting.
     Insert { overwrite: bool },
     /// `merge_insert`: stream to `/v1/table/{id}/merge_insert/` with the merge
@@ -49,7 +49,7 @@ pub(crate) enum WriteOp {
 /// The parsed server response for a completed write, discriminated by the
 /// operation that produced it.
 #[derive(Debug, Clone)]
-pub(crate) enum WriteResult {
+pub enum WriteResult {
     Add(AddResult),
     Merge(MergeResult),
 }
diff --git a/rust/lancedb/src/table/merge.rs b/rust/lancedb/src/table/merge.rs
index 13a633c67..82a1d1473 100644
--- a/rust/lancedb/src/table/merge.rs
+++ b/rust/lancedb/src/table/merge.rs
@@ -315,7 +315,10 @@ pub(crate) async fn execute_merge_insert(
 
 #[cfg(test)]
 mod tests {
-    use arrow_array::{Int32Array, RecordBatch, RecordBatchIterator, RecordBatchReader};
+    use arrow_array::builder::FixedSizeBinaryBuilder;
+    use arrow_array::{
+        Int32Array, RecordBatch, RecordBatchIterator, RecordBatchReader, StringArray, UInt64Array,
+    };
     use arrow_schema::{DataType, Field, Schema};
     use std::sync::Arc;
 
@@ -337,6 +340,42 @@ mod tests {
         Box::new(RecordBatchIterator::new(vec![Ok(batch)], schema))
     }
 
+    fn fixed_size_binary_merge_batch(
+        id_range: std::ops::Range<u64>,
+        price: u64,
+    ) -> Box<dyn RecordBatchReader + Send> {
+        let ids = id_range.collect::<Vec<_>>();
+        let mut id_builder = FixedSizeBinaryBuilder::new(16);
+        for id in &ids {
+            let mut bytes = [0; 16];
+            bytes[..8].copy_from_slice(&id.to_le_bytes());
+            id_builder.append_value(bytes).unwrap();
+        }
+
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("id", DataType::FixedSizeBinary(16), false),
+            Field::new("id_as_int", DataType::UInt64, false),
+            Field::new("name", DataType::Utf8, false),
+            Field::new("market", DataType::Utf8, false),
+        ]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![
+                Arc::new(id_builder.finish()),
+                Arc::new(UInt64Array::from_iter_values(ids.iter().copied())),
+                Arc::new(StringArray::from_iter_values(
+                    ids.iter().map(|id| format!("name{id}")),
+                )),
+                Arc::new(StringArray::from_iter_values(std::iter::repeat_n(
+                    format!("market_{price}"),
+                    ids.len(),
+                ))),
+            ],
+        )
+        .unwrap();
+        Box::new(RecordBatchIterator::new(vec![Ok(batch)], schema))
+    }
+
     #[tokio::test]
     async fn test_merge_insert() {
         let conn = connect("memory://").execute().await.unwrap();
@@ -388,6 +427,36 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn test_merge_insert_fixed_size_binary_non_nullable() {
+        // Regression test for #2869: an unrelated FixedSizeBinary column used to corrupt the
+        // outer join that implements when_not_matched_by_source_delete.
+        let conn = connect("memory://").execute().await.unwrap();
+        let table = conn
+            .create_table(
+                "fixed_size_binary_merge",
+                fixed_size_binary_merge_batch(0..256, 100),
+            )
+            .execute()
+            .await
+            .unwrap();
+
+        let mut merge_insert = table.merge_insert(&["id_as_int"]);
+        merge_insert
+            .when_matched_update_all(None)
+            .when_not_matched_insert_all()
+            .when_not_matched_by_source_delete(None);
+        let result = merge_insert
+            .execute(fixed_size_binary_merge_batch(100..356, 200))
+            .await
+            .unwrap();
+
+        assert_eq!(result.num_updated_rows, 156);
+        assert_eq!(result.num_inserted_rows, 100);
+        assert_eq!(result.num_deleted_rows, 100);
+        assert_eq!(table.count_rows(None).await.unwrap(), 256);
+    }
+
     #[tokio::test]
     async fn test_merge_insert_use_index() {
         let conn = connect("memory://").execute().await.unwrap();
diff --git a/rust/lancedb/src/table/optimize.rs b/rust/lancedb/src/table/optimize.rs
index e29445b2d..4ad58cffb 100644
--- a/rust/lancedb/src/table/optimize.rs
+++ b/rust/lancedb/src/table/optimize.rs
@@ -214,12 +214,17 @@ pub(crate) async fn execute_optimize(
 
 #[cfg(test)]
 mod tests {
-    use arrow_array::{Int32Array, RecordBatch, StringArray};
+    use arrow_array::{
+        Array, FixedSizeListArray, Float32Array, Int32Array, RecordBatch, StringArray,
+    };
     use arrow_schema::{DataType, Field, Schema};
+    use lance_arrow::FixedSizeListArrayExt;
     use rstest::rstest;
     use std::sync::Arc;
 
     use crate::connect;
+    use crate::database::listing::OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS;
+    use crate::index::vector::IvfRqIndexBuilder;
     use crate::index::{Index, scalar::BTreeIndexBuilder};
     use crate::query::ExecutableQuery;
     use crate::table::{CompactionOptions, OptimizeAction, OptimizeStats};
@@ -304,6 +309,96 @@ mod tests {
         assert_eq!(all_values, expected);
     }
 
+    #[tokio::test]
+    async fn test_compact_with_concurrent_add() {
+        const NUM_FRAGMENTS: usize = 5;
+        const ROWS_PER_FRAGMENT: i32 = 300;
+
+        let tmpdir = tempfile::tempdir().unwrap();
+        let conn = connect(tmpdir.path().to_str().unwrap())
+            .execute()
+            .await
+            .unwrap();
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+        let batch = RecordBatch::try_new(
+            schema,
+            vec![Arc::new(Int32Array::from_iter_values(0..ROWS_PER_FRAGMENT))],
+        )
+        .unwrap();
+
+        let table = conn
+            .create_table("test_concurrent_compact", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        table
+            .create_index(&["id"], Index::BTree(BTreeIndexBuilder::default()))
+            .execute()
+            .await
+            .unwrap();
+        for _ in 0..NUM_FRAGMENTS {
+            table.add(batch.clone()).execute().await.unwrap();
+        }
+
+        // Use separate handles so the two writes actually overlap, as they can
+        // when different Node connections operate on the same S3 table.
+        let compact_table = conn
+            .open_table("test_concurrent_compact")
+            .execute()
+            .await
+            .unwrap();
+        let append_table = conn
+            .open_table("test_concurrent_compact")
+            .execute()
+            .await
+            .unwrap();
+        let compact_task = tokio::spawn(async move {
+            compact_table
+                .optimize(OptimizeAction::Compact {
+                    options: CompactionOptions {
+                        target_rows_per_fragment: 1_000,
+                        ..Default::default()
+                    },
+                    remap_options: None,
+                })
+                .await
+        });
+        tokio::task::yield_now().await;
+        for _ in 0..NUM_FRAGMENTS {
+            append_table.add(batch.clone()).execute().await.unwrap();
+        }
+        compact_task.await.unwrap().unwrap();
+
+        let table = conn
+            .open_table("test_concurrent_compact")
+            .execute()
+            .await
+            .unwrap();
+        let dataset = table.dataset().unwrap().get().await.unwrap();
+        let fragment_ids = dataset
+            .get_fragments()
+            .iter()
+            .map(|fragment| fragment.id())
+            .collect::<Vec<_>>();
+        assert!(fragment_ids.windows(2).all(|ids| ids[0] < ids[1]));
+
+        // A second compaction exposed the original out-of-order row-id bug.
+        table
+            .optimize(OptimizeAction::Compact {
+                options: CompactionOptions {
+                    target_rows_per_fragment: 1_000,
+                    ..Default::default()
+                },
+                remap_options: None,
+            })
+            .await
+            .unwrap();
+        assert_eq!(
+            table.count_rows(None).await.unwrap(),
+            ROWS_PER_FRAGMENT as usize * (NUM_FRAGMENTS * 2 + 1)
+        );
+    }
+
     #[tokio::test]
     async fn test_optimize_prune_versions() {
         let conn = connect("memory://").execute().await.unwrap();
@@ -442,6 +537,58 @@ mod tests {
         assert_eq!(final_row_count, 200);
     }
 
+    #[tokio::test]
+    async fn test_optimize_vector_index_after_delete_with_stable_row_ids() {
+        const NUM_ROWS: i32 = 400;
+        const DIMENSION: i32 = 32;
+
+        let conn = connect("memory://").execute().await.unwrap();
+        let vectors = FixedSizeListArray::try_new_from_values(
+            Float32Array::from_iter_values((0..NUM_ROWS).flat_map(|id| {
+                (0..DIMENSION).map(move |offset| ((id as f32 * 0.1) + (offset as f32 * 0.3)).sin())
+            })),
+            DIMENSION,
+        )
+        .unwrap();
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("id", DataType::Int32, false),
+            Field::new("vector", vectors.data_type().clone(), false),
+        ]));
+        let batch = RecordBatch::try_new(
+            schema,
+            vec![
+                Arc::new(Int32Array::from_iter_values(0..NUM_ROWS)),
+                Arc::new(vectors),
+            ],
+        )
+        .unwrap();
+        let table = conn
+            .create_table("test_vector_index_optimize_after_delete", batch)
+            .storage_option(OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS, "true")
+            .execute()
+            .await
+            .unwrap();
+
+        table
+            .create_index(
+                &["vector"],
+                Index::IvfRq(IvfRqIndexBuilder::default().num_partitions(4)),
+            )
+            .execute()
+            .await
+            .unwrap();
+        table.delete("id % 3 = 0").await.unwrap();
+
+        // Regression test for #3330: deleted stable row IDs used to become
+        // misaligned with row addresses while joining small IVF partitions.
+        table
+            .optimize(OptimizeAction::Index(Default::default()))
+            .await
+            .unwrap();
+
+        assert_eq!(table.count_rows(None).await.unwrap(), 266);
+    }
+
     #[tokio::test]
     async fn test_optimize_all() {
         let conn = connect("memory://").execute().await.unwrap();
diff --git a/rust/lancedb/tests/blob_integration.rs b/rust/lancedb/tests/blob_integration.rs
index 3d327766e..77d49abd9 100644
--- a/rust/lancedb/tests/blob_integration.rs
+++ b/rust/lancedb/tests/blob_integration.rs
@@ -10,7 +10,7 @@ use arrow_array::{
 use arrow_schema::{DataType, Field, Fields, Schema};
 use futures::TryStreamExt;
 use lance::Dataset;
-use lance_encoding::version::LanceFileVersion;
+use lance_file::version::LanceFileVersion;
 use lancedb::{
     Connection, Error, Result, Table,
     blob::{BlobRangeRequest, blob},