Bump version: 0.31.0-beta.4 → 0.31.0-beta.5

Summary:
- Route built-in sync namespace connections through the Rust namespace
connector.
- Keep custom namespace clients on the existing Python fallback.
- Preserve namespace-backed to_lance compatibility with lazy Python
client construction and add regressions.

.agents/skills/lancedb-branch-ops/SKILL.md

@@ -0,0 +1,137 @@
+---
+name: lancedb-branch-ops
+description: Branch management for LanceDB tables via the REST API. Use this skill whenever someone wants to create, delete, list, or switch branches on a LanceDB table — or needs to make sure a write (metadata update, index build, etc.) lands on a specific branch instead of main. Invoke it even without the word "branch" if context makes clear they want an experimental copy of a table, want to isolate changes, or want to confirm a mutation didn't touch main. Covers: branches/list, branches/create, branches/delete, and passing "branch" in describe/update_field_metadata/create_index to target a non-main version.
+---
+
+## Goal
+
+Manage branches on a LanceDB table: list what exists, create new ones, delete stale ones, and direct read/write operations at a specific branch without touching main.
+
+## Step 0: Establish the connection
+
+Use the `lancedb-connect` skill to resolve the base URL and auth headers (`x-api-key`, `x-lancedb-database`). Skip this only if the connection is already known from the current conversation.
+
+All examples below use `{base_url}` — substitute the resolved endpoint and include the auth headers on every request.
+
+## The branch model (important)
+
+LanceDB branches are named snapshots that diverge from the table's current state at creation time. There is **no checkout command** — you never switch the whole table to a branch. Instead, you **pass `"branch": "<name>"` in the request body** of any operation to target that branch. Omitting the key (or sending an empty body) always targets main.
+
+`branches/list` returns only non-main branches. Main always exists and is not listed.
+
+## List branches
+
+```http
+POST {base_url}/v1/table/{table_id}/branches/list
+Content-Type: application/json
+
+{}
+```
+
+Response:
+```json
+{
+  "branches": {
+    "experiment-reindex": {"parentVersion": 1, "createAt": 1782506085, "manifestSize": 1029}
+  }
+}
+```
+
+If `branches` is `{}`, the table has no branches besides main.
+
+## Create a branch
+
+```http
+POST {base_url}/v1/table/{table_id}/branches/create
+Content-Type: application/json
+
+{"name": "experiment-reindex"}
+```
+
+HTTP 200 with `{}` body = success. The branch is created off the table's current state on main.
+
+Verify by calling `branches/list` and confirming the new name appears.
+
+## Delete a branch
+
+```http
+POST {base_url}/v1/table/{table_id}/branches/delete
+Content-Type: application/json
+
+{"name": "stale-2024"}
+```
+
+HTTP 200 with `{}` body = success. Only the branch pointer is removed — main and all row data remain intact.
+
+Verify by calling `branches/list` (name gone) and `describe` with no branch param (main still responds).
+
+## Operate on a specific branch
+
+Pass `"branch": "<name>"` in the body of any operation to scope it to that branch:
+
+**Read schema on a branch:**
+```http
+POST {base_url}/v1/table/{table_id}/describe
+Content-Type: application/json
+
+{"branch": "wip-branch"}
+```
+
+**Write metadata to a branch (not main):**
+```http
+POST {base_url}/v1/table/{table_id}/update_field_metadata
+Content-Type: application/json
+
+{
+  "branch": "wip-branch",
+  "updates": [
+    {
+      "path": "category",
+      "metadata": {"lancedb:description": "Product category label."},
+      "replace": false
+    }
+  ]
+}
+```
+
+**Build an index on a branch:**
+```http
+POST {base_url}/v1/table/{table_id}/create_index
+Content-Type: application/json
+
+{
+  "branch": "wip-branch",
+  "column": "category",
+  "index_type": "BTREE"
+}
+```
+
+## Verifying isolation
+
+After writing to a branch, always confirm the change did NOT land on main:
+
+```bash
+# Should show the new metadata
+curl -s -X POST {base_url}/v1/table/{table_id}/describe \
+  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
+  -H "content-type: application/json" \
+  -d '{"branch": "wip-branch"}'
+
+# Should NOT show the new metadata
+curl -s -X POST {base_url}/v1/table/{table_id}/describe \
+  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
+  -H "content-type: application/json" \
+  -d '{}'
+```
+
+## Quick reference
+
+| Goal | Endpoint | Body |
+|------|----------|------|
+| List all branches | `branches/list` | `{}` |
+| Create a branch | `branches/create` | `{"name": "..."}` |
+| Delete a branch | `branches/delete` | `{"name": "..."}` |
+| Read schema on branch | `describe` | `{"branch": "..."}` |
+| Write metadata on branch | `update_field_metadata` | `{"branch": "...", "updates": [...]}` |
+| Build index on branch | `create_index` | `{"branch": "...", "column": ..., "index_type": ...}` |
+| Target main (default) | any endpoint | omit `"branch"` key |

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.2"
+current_version = "0.31.0-beta.5"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

Cargo.lock

@@ -157,9 +157,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.102"
+version = "1.0.103"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
+checksum = "2a4385e2e34eb35d6b3efe798b9eb88096925d87726c0798709bf56d9ed84af3"
 
 [[package]]
 name = "approx"
@@ -1297,15 +1297,6 @@ version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
 
-[[package]]
-name = "bitpacking"
-version = "0.9.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96a7139abd3d9cebf8cd6f920a389cf3dc9576172e32f4563f188cae3c3eb019"
-dependencies = [
- "crunchy",
-]
-
 [[package]]
 name = "bitvec"
 version = "1.0.1"
@@ -3186,9 +3177,9 @@ dependencies = [
 
 [[package]]
 name = "env_filter"
-version = "1.0.1"
+version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32e90c2accc4b07a8456ea0debdc2e7587bdd890680d71173a15d4ae604f6eef"
+checksum = "900d271a03799a1ee8d1ca9b19893b48ca674a9284fefcfb85f05e74ed314217"
 dependencies = [
  "log",
  "regex",
@@ -3196,9 +3187,9 @@ dependencies = [
 
 [[package]]
 name = "env_logger"
-version = "0.11.10"
+version = "0.11.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0621c04f2196ac3f488dd583365b9c09be011a4ab8b9f37248ffcc8f6198b56a"
+checksum = "de671bd27a75a797dc9ae289ba1e77276e75e2026408aab65185384e2d5cd3f6"
 dependencies = [
  "anstream",
  "anstyle",
@@ -3432,8 +3423,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "rand 0.9.4",
@@ -4735,8 +4726,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
 
 [[package]]
 name = "lance"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -4754,7 +4745,6 @@ dependencies = [
  "async_cell",
  "aws-credential-types",
  "aws-sdk-dynamodb",
- "bitpacking",
  "byteorder",
  "bytes",
  "chrono",
@@ -4773,6 +4763,7 @@ dependencies = [
  "humantime",
  "itertools 0.14.0",
  "lance-arrow",
+ "lance-bitpacking",
  "lance-core",
  "lance-datafusion",
  "lance-encoding",
@@ -4810,8 +4801,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4832,7 +4823,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4846,7 +4837,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4855,18 +4846,19 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrayref",
+ "crunchy",
  "paste",
  "seq-macro",
 ]
 
 [[package]]
 name = "lance-core"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4904,8 +4896,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4935,8 +4927,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4953,8 +4945,8 @@ dependencies = [
 
 [[package]]
 name = "lance-derive"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -4963,8 +4955,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4999,8 +4991,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5030,8 +5022,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -5043,7 +5035,6 @@ dependencies = [
  "async-channel",
  "async-recursion",
  "async-trait",
- "bitpacking",
  "bitvec",
  "bytes",
  "chrono",
@@ -5061,6 +5052,7 @@ dependencies = [
  "jsonb",
  "lance-arrow",
  "lance-arrow-stats",
+ "lance-bitpacking",
  "lance-core",
  "lance-datafusion",
  "lance-datagen",
@@ -5096,8 +5088,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -5138,8 +5130,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5155,8 +5147,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow",
  "async-trait",
@@ -5168,8 +5160,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -5223,8 +5215,8 @@ dependencies = [
 
 [[package]]
 name = "lance-select"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5239,8 +5231,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5279,8 +5271,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5293,8 +5285,8 @@ dependencies = [
 
 [[package]]
 name = "lance-tokenizer"
-version = "9.0.0-beta.8"
-source = "git+https://github.com/lance-format/lance.git?rev=4acefffd5d38f88003fce681ae1d0871077ce5e7#4acefffd5d38f88003fce681ae1d0871077ce5e7"
+version = "9.0.0-beta.10"
+source = "git+https://github.com/lance-format/lance.git?tag=v9.0.0-beta.10#e25b71e74b89d10c57b412d111bde087117383f3"
 dependencies = [
  "icu_segmenter",
  "jieba-rs",
@@ -5307,7 +5299,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.31.0-beta.2"
+version = "0.31.0-beta.4"
 dependencies = [
  "ahash",
  "anyhow",
@@ -5384,13 +5376,14 @@ dependencies = [
  "tokenizers",
  "tokio",
  "url",
+ "urlencoding",
  "uuid",
  "walkdir",
 ]
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.31.0-beta.2"
+version = "0.31.0-beta.4"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5415,7 +5408,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.34.0-beta.2"
+version = "0.34.0-beta.4"
 dependencies = [
  "arrow",
  "async-trait",
@@ -5648,9 +5641,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.32"
+version = "0.4.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "953f07c43838f8e6f9758cab68bf5bed85465e7587ebe0b823f1bcd81978ad3a"
+checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
 
 [[package]]
 name = "loom"
@@ -5958,9 +5951,9 @@ dependencies = [
 
 [[package]]
 name = "napi"
-version = "3.9.3"
+version = "3.9.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fbd9f9295f3ff5921e78a71222c3361a8216f7760b1a99a6ad4e8441de18bbb9"
+checksum = "b41bda2ac390efb5e8d22025d925ccc3f3807d8c1bea6d19b36127247c4b8f83"
 dependencies = [
  "bitflags 2.11.1",
  "chrono",
@@ -5983,9 +5976,9 @@ checksum = "c9c366d2c8c60b86fa632df75f745509b52f9128f91a6bad4c796e44abb505e1"
 
 [[package]]
 name = "napi-derive"
-version = "3.5.6"
+version = "3.5.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "89b3f766e04667e6da0e181e2da4f85475d5a6513b7cf6a80bea184e224a5b42"
+checksum = "61d66f70256ad5aef58659966064471d0ad90e2897bc36a5a5e0389c85aabc1e"
 dependencies = [
  "convert_case",
  "ctor 1.0.5",
@@ -5997,9 +5990,9 @@ dependencies = [
 
 [[package]]
 name = "napi-derive-backend"
-version = "5.0.4"
+version = "5.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d5af30503edf933ce7377cf6d4c877a62b0f1107ea05585f1b5e430e88d5baf"
+checksum = "81b4b08f15eed7a2a20c3f4c6314013fc3ac890a3afa9892b594485299ebdb2d"
 dependencies = [
  "convert_case",
  "proc-macro2",
@@ -10127,9 +10120,9 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 
 [[package]]
 name = "uuid"
-version = "1.23.3"
+version = "1.23.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "144d6b123cef80b301b8f72a9e2ca4370ddec21950d0a103dd22c437006d2db7"
+checksum = "bf80a72845275afea99e7f2b434723d3bc7e38470fcd1c7ed39a599c73319a53"
 dependencies = [
  "getrandom 0.4.2",
  "js-sys",

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=9.0.0-beta.8", default-features = false, "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=9.0.0-beta.8", default-features = false, "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=9.0.0-beta.8", default-features = false, "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=9.0.0-beta.8", "rev" = "4acefffd5d38f88003fce681ae1d0871077ce5e7", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=9.0.0-beta.10", default-features = false, "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=9.0.0-beta.10", "tag" = "v9.0.0-beta.10", "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 }

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.31.0-beta.2</version>
+    <version>0.31.0-beta.5</version>
 </dependency>
 ```
 

docs/src/js/enumerations/OAuthFlowType.md

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

docs/src/js/globals.md

@@ -12,6 +12,7 @@
 ## Enumerations
 
 - [FullTextQueryType](enumerations/FullTextQueryType.md)
+- [OAuthFlowType](enumerations/OAuthFlowType.md)
 - [Occur](enumerations/Occur.md)
 - [Operator](enumerations/Operator.md)
 
@@ -85,6 +86,8 @@
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.md)
 - [MergeResult](interfaces/MergeResult.md)
+- [NativeOAuthConfig](interfaces/NativeOAuthConfig.md)
+- [OAuthConfig](interfaces/OAuthConfig.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)

docs/src/js/interfaces/ConnectionOptions.md

@@ -64,6 +64,19 @@ client used by manifest-enabled native connections.
 
 ***
 
+### oauthConfig?
+
+```ts
+optional oauthConfig: NativeOAuthConfig;
+```
+
+(For LanceDB cloud only): OAuth configuration for IdP-based
+authentication (e.g., Azure Entra ID). When set, token acquisition
+and refresh are handled entirely in Rust. TypeScript users should pass
+the public `OAuthConfig` type exported from `@lancedb/lancedb`.
+
+***
+
 ### readConsistencyInterval?
 
 ```ts

docs/src/js/interfaces/NativeOAuthConfig.md

@@ -0,0 +1,88 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / NativeOAuthConfig
+
+# Interface: NativeOAuthConfig
+
+OAuth configuration for LanceDB authentication.
+
+This is the generated napi-rs binding shape. TypeScript users should prefer
+the public `OAuthConfig` type exported from `@lancedb/lancedb`.
+
+All token acquisition and refresh is handled in the Rust layer.
+
+## Properties
+
+### clientId
+
+```ts
+clientId: string;
+```
+
+Application / Client ID.
+
+***
+
+### clientSecret?
+
+```ts
+optional clientSecret: string;
+```
+
+Client secret (required for client_credentials).
+
+***
+
+### flow?
+
+```ts
+optional flow: string;
+```
+
+Authentication flow: "client_credentials" or "azure_managed_identity"
+
+***
+
+### issuerUrl
+
+```ts
+issuerUrl: string;
+```
+
+OIDC issuer URL or OAuth authority URL.
+For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
+
+***
+
+### managedIdentityClientId?
+
+```ts
+optional managedIdentityClientId: string;
+```
+
+Client ID for user-assigned managed identity (azure_managed_identity).
+
+***
+
+### refreshBufferSecs?
+
+```ts
+optional refreshBufferSecs: number;
+```
+
+Seconds before expiry to trigger proactive refresh (default: 300).
+Keep this well below the token TTL; if it is greater than or equal to
+the TTL, each request refreshes the token.
+
+***
+
+### scopes
+
+```ts
+scopes: string[];
+```
+
+OAuth scopes to request. For Azure managed identity, exactly one scope
+or resource is required. For example: `["api://{app_id}/.default"]`

docs/src/js/interfaces/OAuthConfig.md

@@ -0,0 +1,111 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / OAuthConfig
+
+# Interface: OAuthConfig
+
+OAuth configuration for LanceDB authentication.
+
+This is the public TypeScript OAuth configuration type. The generated
+`NativeOAuthConfig` type has the same runtime shape but is an implementation
+detail of the napi-rs binding.
+
+All token acquisition and refresh is handled in the Rust layer.
+This config is passed through to Rust via napi-rs.
+
+## Examples
+
+```typescript
+const config: OAuthConfig = {
+  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
+  clientId: "app-id",
+  clientSecret: "secret",
+  scopes: ["api://lancedb-api/.default"],
+};
+```
+
+```typescript
+const config: OAuthConfig = {
+  issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
+  clientId: "app-id",
+  scopes: ["api://lancedb-api/.default"],
+  flow: OAuthFlowType.AzureManagedIdentity,
+};
+```
+
+## Properties
+
+### clientId
+
+```ts
+clientId: string;
+```
+
+Application / Client ID.
+
+***
+
+### clientSecret?
+
+```ts
+optional clientSecret: string;
+```
+
+Client secret (required for ClientCredentials).
+
+***
+
+### flow?
+
+```ts
+optional flow: OAuthFlowType;
+```
+
+Authentication flow (default: ClientCredentials).
+
+***
+
+### issuerUrl
+
+```ts
+issuerUrl: string;
+```
+
+OIDC issuer URL or OAuth authority URL.
+For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
+
+***
+
+### managedIdentityClientId?
+
+```ts
+optional managedIdentityClientId: string;
+```
+
+Client ID for user-assigned managed identity (AzureManagedIdentity).
+
+***
+
+### refreshBufferSecs?
+
+```ts
+optional refreshBufferSecs: number;
+```
+
+Seconds before expiry to trigger proactive refresh (default: 300).
+Keep this well below the token TTL; if it is greater than or equal to
+the TTL, each request refreshes the token.
+
+***
+
+### scopes
+
+```ts
+scopes: string[];
+```
+
+OAuth scopes to request.
+For Azure managed identity, exactly one scope or resource is required.
+For example: `["api://{app_id}/.default"]`

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.31.0-beta.2</version>
+      <version>0.31.0-beta.5</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.31.0-beta.2</version>
+    <version>0.31.0-beta.5</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>9.0.0-beta.8</lance-core.version>
+        <lance-core.version>9.0.0-beta.10</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.31.0-beta.2"
+version = "0.31.0-beta.5"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/lancedb/index.ts

@@ -52,6 +52,7 @@ export {
   SplitHashOptions,
   SplitSequentialOptions,
   ShuffleOptions,
+  OAuthConfig as NativeOAuthConfig,
 } from "./native.js";
 
 export {
@@ -130,6 +131,8 @@ export {
   TokenResponse,
 } from "./header";
 
+export { OAuthConfig, OAuthFlowType } from "./oauth";
+
 export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";

nodejs/lancedb/oauth.ts

@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+/**
+ * OAuth authentication flow types.
+ */
+export enum OAuthFlowType {
+  /** Client Credentials grant (service-to-service / M2M). */
+  ClientCredentials = "client_credentials",
+  /** Azure Managed Identity via IMDS. */
+  AzureManagedIdentity = "azure_managed_identity",
+}
+
+/**
+ * OAuth configuration for LanceDB authentication.
+ *
+ * This is the public TypeScript OAuth configuration type. The generated
+ * `NativeOAuthConfig` type has the same runtime shape but is an implementation
+ * detail of the napi-rs binding.
+ *
+ * All token acquisition and refresh is handled in the Rust layer.
+ * This config is passed through to Rust via napi-rs.
+ *
+ * @example Client Credentials (service-to-service):
+ * ```typescript
+ * const config: OAuthConfig = {
+ *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
+ *   clientId: "app-id",
+ *   clientSecret: "secret",
+ *   scopes: ["api://lancedb-api/.default"],
+ * };
+ * ```
+ *
+ * @example Azure Managed Identity:
+ * ```typescript
+ * const config: OAuthConfig = {
+ *   issuerUrl: "https://login.microsoftonline.com/{tenant}/v2.0",
+ *   clientId: "app-id",
+ *   scopes: ["api://lancedb-api/.default"],
+ *   flow: OAuthFlowType.AzureManagedIdentity,
+ * };
+ * ```
+ */
+export interface OAuthConfig {
+  /**
+   * OIDC issuer URL or OAuth authority URL.
+   * For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
+   */
+  issuerUrl: string;
+
+  /** Application / Client ID. */
+  clientId: string;
+
+  /**
+   * OAuth scopes to request.
+   * For Azure managed identity, exactly one scope or resource is required.
+   * For example: `["api://{app_id}/.default"]`
+   */
+  scopes: string[];
+
+  /** Authentication flow (default: ClientCredentials). */
+  flow?: OAuthFlowType;
+
+  /** Client secret (required for ClientCredentials). */
+  clientSecret?: string;
+
+  /** Client ID for user-assigned managed identity (AzureManagedIdentity). */
+  managedIdentityClientId?: string;
+
+  /**
+   * Seconds before expiry to trigger proactive refresh (default: 300).
+   * Keep this well below the token TTL; if it is greater than or equal to
+   * the TTL, each request refreshes the token.
+   */
+  refreshBufferSecs?: number;
+}

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.31.0-beta.2",
+	"version": "0.31.0-beta.5",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.31.0-beta.2",
+	"version": "0.31.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.31.0-beta.2",
+	"version": "0.31.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.31.0-beta.2",
+	"version": "0.31.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.31.0-beta.2",
+	"version": "0.31.0-beta.5",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.31.0-beta.2",
+  "version": "0.31.0-beta.5",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.31.0-beta.2",
+	"version": "0.31.0-beta.5",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.31.0-beta.2",
+  "version": "0.31.0-beta.4",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.31.0-beta.2",
+      "version": "0.31.0-beta.4",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.31.0-beta.2",
+  "version": "0.31.0-beta.5",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/connection.rs

@@ -112,6 +112,12 @@ impl Connection {
 
         builder = builder.client_config(rust_config);
 
+        if let Some(oauth_config) = options.oauth_config {
+            let config: lancedb::remote::oauth::OAuthConfig =
+                oauth_config.try_into().default_error()?;
+            builder = builder.oauth_config(config);
+        }
+
         if let Some(api_key) = options.api_key {
             builder = builder.api_key(&api_key);
         }

nodejs/src/lib.rs

@@ -65,6 +65,11 @@ pub struct ConnectionOptions {
     /// (For LanceDB cloud only): the host to use for LanceDB cloud. Used
     /// for testing purposes.
     pub host_override: Option<String>,
+    /// (For LanceDB cloud only): OAuth configuration for IdP-based
+    /// authentication (e.g., Azure Entra ID). When set, token acquisition
+    /// and refresh are handled entirely in Rust. TypeScript users should pass
+    /// the public `OAuthConfig` type exported from `@lancedb/lancedb`.
+    pub oauth_config: Option<remote::OAuthConfig>,
 }
 
 #[napi(object)]

nodejs/src/merge.rs

@@ -3,7 +3,7 @@
 
 use std::time::Duration;
 
-use lancedb::{arrow::IntoArrow, ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
+use lancedb::{ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
 
@@ -66,11 +66,9 @@ impl NativeMergeInsertBuilder {
 
     #[napi(catch_unwind)]
     pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
-        let data = ipc_file_to_batches(buf.to_vec())
-            .and_then(IntoArrow::into_arrow)
-            .map_err(|e| {
-                napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
-            })?;
+        let data = ipc_file_to_batches(buf.to_vec()).map_err(|e| {
+            napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
+        })?;
 
         let this = self.clone();
 

nodejs/src/remote.rs

@@ -3,6 +3,7 @@
 
 use std::collections::HashMap;
 
+use lancedb::error::Error;
 use napi_derive::*;
 
 /// Timeout configuration for remote HTTP client.
@@ -140,6 +141,84 @@ impl From<TlsConfig> for lancedb::remote::TlsConfig {
     }
 }
 
+/// OAuth configuration for LanceDB authentication.
+///
+/// This is the generated napi-rs binding shape. TypeScript users should prefer
+/// the public `OAuthConfig` type exported from `@lancedb/lancedb`.
+///
+/// All token acquisition and refresh is handled in the Rust layer.
+#[napi(object)]
+#[derive(Clone)]
+pub struct OAuthConfig {
+    /// OIDC issuer URL or OAuth authority URL.
+    /// For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
+    pub issuer_url: String,
+    /// Application / Client ID.
+    pub client_id: String,
+    /// OAuth scopes to request. For Azure managed identity, exactly one scope
+    /// or resource is required. For example: `["api://{app_id}/.default"]`
+    pub scopes: Vec<String>,
+    /// Authentication flow: "client_credentials" or "azure_managed_identity"
+    pub flow: Option<String>,
+    /// Client secret (required for client_credentials).
+    pub client_secret: Option<String>,
+    /// Client ID for user-assigned managed identity (azure_managed_identity).
+    pub managed_identity_client_id: Option<String>,
+    /// Seconds before expiry to trigger proactive refresh (default: 300).
+    /// Keep this well below the token TTL; if it is greater than or equal to
+    /// the TTL, each request refreshes the token.
+    pub refresh_buffer_secs: Option<u32>,
+}
+
+impl std::fmt::Debug for OAuthConfig {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("OAuthConfig")
+            .field("issuer_url", &self.issuer_url)
+            .field("client_id", &self.client_id)
+            .field("scopes", &self.scopes)
+            .field("flow", &self.flow)
+            .field(
+                "client_secret",
+                &self.client_secret.as_deref().map(|_| "<redacted>"),
+            )
+            .field(
+                "managed_identity_client_id",
+                &self.managed_identity_client_id,
+            )
+            .field("refresh_buffer_secs", &self.refresh_buffer_secs)
+            .finish()
+    }
+}
+
+impl TryFrom<OAuthConfig> for lancedb::remote::oauth::OAuthConfig {
+    type Error = Error;
+
+    fn try_from(config: OAuthConfig) -> Result<Self, Self::Error> {
+        use lancedb::remote::oauth::OAuthFlow;
+
+        let flow = match config.flow.as_deref().unwrap_or("client_credentials") {
+            "client_credentials" => OAuthFlow::ClientCredentials,
+            "azure_managed_identity" => OAuthFlow::AzureManagedIdentity {
+                client_id: config.managed_identity_client_id,
+            },
+            other => {
+                return Err(Error::InvalidInput {
+                    message: format!("Unknown OAuth flow type: {other}"),
+                });
+            }
+        };
+
+        Ok(Self {
+            issuer_url: config.issuer_url,
+            client_id: config.client_id,
+            client_secret: config.client_secret,
+            scopes: config.scopes,
+            flow,
+            refresh_buffer_secs: config.refresh_buffer_secs.map(|v| v as u64),
+        })
+    }
+}
+
 impl From<ClientConfig> for lancedb::remote::ClientConfig {
     fn from(config: ClientConfig) -> Self {
         Self {
@@ -156,3 +235,45 @@ impl From<ClientConfig> for lancedb::remote::ClientConfig {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_unknown_oauth_flow_returns_invalid_input() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            scopes: vec!["scope".to_string()],
+            flow: Some("typo".to_string()),
+            client_secret: None,
+            managed_identity_client_id: None,
+            refresh_buffer_secs: None,
+        };
+
+        let err = lancedb::remote::oauth::OAuthConfig::try_from(config).unwrap_err();
+        assert!(matches!(
+            err,
+            Error::InvalidInput { message }
+                if message == "Unknown OAuth flow type: typo"
+        ));
+    }
+
+    #[test]
+    fn test_oauth_config_debug_redacts_client_secret() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            scopes: vec!["scope".to_string()],
+            flow: Some("client_credentials".to_string()),
+            client_secret: Some("super-secret".to_string()),
+            managed_identity_client_id: None,
+            refresh_buffer_secs: None,
+        };
+
+        let debug = format!("{config:?}");
+        assert!(!debug.contains("super-secret"));
+        assert!(debug.contains("client_secret: Some(\"<redacted>\")"));
+    }
+}

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.34.0-beta.2"
+current_version = "0.34.0-beta.5"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.34.0-beta.2"
+version = "0.34.0-beta.5"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"

python/python/lancedb/__init__.py

@@ -89,6 +89,8 @@ def connect(
         If presented, connect to LanceDB cloud.
         Otherwise, connect to a database on file system or cloud storage.
         Can be set via environment variable `LANCEDB_API_KEY`.
+        OAuth configuration is currently supported only by ``connect_async``;
+        synchronous LanceDB Cloud connections require an API key.
     region: str, default "us-east-1"
         The region to use for LanceDB Cloud.
     host_override: str, optional
@@ -340,6 +342,7 @@ async def connect_async(
     session: Optional[Session] = None,
     manifest_enabled: bool = False,
     namespace_client_properties: Optional[Dict[str, str]] = None,
+    oauth_config=None,
 ) -> AsyncConnection:
     """Connect to a LanceDB database.
 
@@ -389,6 +392,10 @@ async def connect_async(
     namespace_client_properties : dict, optional
         Additional directory namespace client properties to use with
         ``manifest_enabled=True``.
+    oauth_config : OAuthConfig, optional
+        OAuth configuration for LanceDB Cloud/Enterprise. This is supported by
+        ``connect_async`` only; synchronous ``connect`` uses API key
+        authentication for ``db://`` URIs.
 
     Examples
     --------
@@ -435,6 +442,7 @@ async def connect_async(
             session,
             manifest_enabled,
             namespace_client_properties,
+            oauth_config,
         )
     )
 

python/python/lancedb/_lancedb.pyi

@@ -280,6 +280,24 @@ async def connect(
     session: Optional[Session],
     manifest_enabled: bool = False,
     namespace_client_properties: Optional[Dict[str, str]] = None,
+    oauth_config: Optional[Any] = None,
+) -> Connection: ...
+def connect_namespace(
+    namespace_client_impl: str,
+    namespace_client_properties: Dict[str, str],
+    read_consistency_interval: Optional[float] = None,
+    storage_options: Optional[Dict[str, str]] = None,
+    session: Optional[Session] = None,
+    namespace_client_pushdown_operations: Optional[List[str]] = None,
+) -> Connection: ...
+def connect_namespace_client(
+    namespace_client: Any,
+    read_consistency_interval: Optional[float] = None,
+    storage_options: Optional[Dict[str, str]] = None,
+    session: Optional[Session] = None,
+    namespace_client_pushdown_operations: Optional[List[str]] = None,
+    namespace_client_impl: Optional[str] = None,
+    namespace_client_properties: Optional[Dict[str, str]] = None,
 ) -> Connection: ...
 
 class RecordBatchStream:

python/python/lancedb/namespace.py

@@ -38,8 +38,11 @@ from lance_namespace_urllib3_client.models.query_table_request_vector import (
     QueryTableRequestVector,
 )
 from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
-from lance_namespace.errors import TableNotFoundError
-from lancedb._lancedb import connect_namespace_client as _connect_namespace_client
+from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
+from lancedb._lancedb import (
+    connect_namespace as _connect_namespace,
+    connect_namespace_client as _connect_namespace_client,
+)
 from lancedb.background_loop import LOOP
 from lancedb.db import AsyncConnection, DBConnection
 from lancedb.namespace_utils import (
@@ -373,6 +376,23 @@ def _convert_pyarrow_schema_to_json(schema: pa.Schema) -> JsonArrowSchema:
     return JsonArrowSchema(fields=fields, metadata=meta)
 
 
+def _builds_namespace_natively(
+    namespace_client_impl: Optional[str],
+    namespace_client_properties: Optional[Dict[str, str]],
+) -> bool:
+    """Whether ``connect_namespace_client`` builds the namespace client natively
+    in Rust (installing the read-freshness context provider) rather than wrapping
+    the pre-built Python client.
+
+    Must mirror Rust ``build_namespace_natively`` in ``python/src/connection.rs``.
+    """
+    return namespace_client_impl == "rest" and bool(namespace_client_properties)
+
+
+def _supports_native_sync_namespace(namespace_client_impl: str) -> bool:
+    return namespace_client_impl in {"dir", "rest"}
+
+
 class LanceNamespaceDBConnection(DBConnection):
     """
     A LanceDB connection that uses a namespace for table management.
@@ -383,7 +403,7 @@ class LanceNamespaceDBConnection(DBConnection):
 
     def __init__(
         self,
-        namespace_client: LanceNamespace,
+        namespace_client: Optional[LanceNamespace] = None,
         *,
         read_consistency_interval: Optional[timedelta] = None,
         storage_options: Optional[Dict[str, str]] = None,
@@ -391,6 +411,8 @@ class LanceNamespaceDBConnection(DBConnection):
         namespace_client_pushdown_operations: Optional[List[str]] = None,
         namespace_client_impl: Optional[str] = None,
         namespace_client_properties: Optional[Dict[str, str]] = None,
+        _inner: Optional[AsyncConnection] = None,
+        _route_pushdown_to_rust: Optional[bool] = None,
     ):
         """
         Initialize a namespace-based LanceDB connection.
@@ -432,23 +454,40 @@ class LanceNamespaceDBConnection(DBConnection):
         )
         self._namespace_client_impl = namespace_client_impl
         self._namespace_client_properties = namespace_client_properties
-        self._inner = AsyncConnection(
-            _connect_namespace_client(
-                namespace_client,
-                read_consistency_interval=(
-                    read_consistency_interval.total_seconds()
-                    if read_consistency_interval is not None
-                    else None
-                ),
-                storage_options=self.storage_options or None,
-                session=session,
-                namespace_client_pushdown_operations=(
-                    list(self._namespace_client_pushdown_operations)
-                ),
-                namespace_client_impl=namespace_client_impl,
-                namespace_client_properties=namespace_client_properties,
+        # When the namespace client is built natively (see Rust
+        # ``build_namespace_natively``), the underlying Rust table performs
+        # QueryTable pushdown through the read-freshness context provider, which
+        # the pure-Python ``query_table`` path bypasses.
+        self._route_pushdown_to_rust = (
+            _route_pushdown_to_rust
+            if _route_pushdown_to_rust is not None
+            else _builds_namespace_natively(
+                namespace_client_impl, namespace_client_properties
             )
         )
+        if _inner is not None:
+            self._inner = _inner
+        else:
+            if namespace_client is None:
+                raise ValueError("namespace_client is required without a native _inner")
+            self._inner = AsyncConnection(
+                _connect_namespace_client(
+                    namespace_client,
+                    read_consistency_interval=(
+                        read_consistency_interval.total_seconds()
+                        if read_consistency_interval is not None
+                        else None
+                    ),
+                    storage_options=self.storage_options or None,
+                    session=session,
+                    namespace_client_pushdown_operations=(
+                        list(self._namespace_client_pushdown_operations)
+                    ),
+                    namespace_client_impl=namespace_client_impl,
+                    namespace_client_properties=namespace_client_properties,
+                )
+            )
+        self._uri = self._inner.uri
 
     @override
     def serialize(self) -> str:
@@ -494,11 +533,11 @@ class LanceNamespaceDBConnection(DBConnection):
         )
         if namespace_path is None:
             namespace_path = []
-        request = ListTablesRequest(
-            id=namespace_path, page_token=page_token, limit=limit
+        return LOOP.run(
+            self._inner.table_names(
+                namespace_path=namespace_path, start_after=page_token, limit=limit
+            )
         )
-        response = self._namespace_client.list_tables(request)
-        return response.tables if response.tables else []
 
     @override
     def create_table(
@@ -543,6 +582,7 @@ class LanceNamespaceDBConnection(DBConnection):
             namespace_path=namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._namespace_client_pushdown_operations,
+            route_pushdown_to_rust=self._route_pushdown_to_rust,
             _async=async_table,
         )
 
@@ -568,8 +608,8 @@ class LanceNamespaceDBConnection(DBConnection):
                     index_cache_size=index_cache_size,
                 )
             )
-        except RuntimeError as e:
-            if "Table not found" in str(e):
+        except (RuntimeError, ValueError) as e:
+            if "Table not found" in str(e) or "was not found" in str(e):
                 table_id = namespace_path + [name]
                 raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
             raise
@@ -580,6 +620,7 @@ class LanceNamespaceDBConnection(DBConnection):
             namespace_path=namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._namespace_client_pushdown_operations,
+            route_pushdown_to_rust=self._route_pushdown_to_rust,
             _async=async_table,
         )
         if branch is not None:
@@ -590,12 +631,9 @@ class LanceNamespaceDBConnection(DBConnection):
 
     @override
     def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):
-        # Use namespace drop_table directly
         if namespace_path is None:
             namespace_path = []
-        table_id = namespace_path + [name]
-        request = DropTableRequest(id=table_id)
-        self._namespace_client.drop_table(request)
+        LOOP.run(self._inner.drop_table(name, namespace_path=namespace_path))
 
     @override
     def rename_table(
@@ -609,14 +647,19 @@ class LanceNamespaceDBConnection(DBConnection):
             cur_namespace_path = []
         if new_namespace_path is None:
             new_namespace_path = []
-        cur_table_id = cur_namespace_path + [cur_name]
-        new_namespace_id = new_namespace_path if new_namespace_path else None
-        request = RenameTableRequest(
-            id=cur_table_id,
-            new_table_name=new_name,
-            new_namespace_id=new_namespace_id,
-        )
-        self._namespace_client.rename_table(request)
+        try:
+            LOOP.run(
+                self._inner.rename_table(
+                    cur_name,
+                    new_name,
+                    cur_namespace_path=cur_namespace_path,
+                    new_namespace_path=new_namespace_path,
+                )
+            )
+        except RuntimeError as e:
+            if "rename_table not implemented" in str(e):
+                raise NotImplementedError("rename_table not implemented") from e
+            raise
 
     @override
     def drop_database(self):
@@ -628,8 +671,7 @@ class LanceNamespaceDBConnection(DBConnection):
     def drop_all_tables(self, namespace_path: Optional[List[str]] = None):
         if namespace_path is None:
             namespace_path = []
-        for table_name in self.table_names(namespace_path=namespace_path):
-            self.drop_table(table_name, namespace_path=namespace_path)
+        LOOP.run(self._inner.drop_all_tables(namespace_path=namespace_path))
 
     @override
     def list_namespaces(
@@ -659,13 +701,10 @@ class LanceNamespaceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        request = ListNamespacesRequest(
-            id=namespace_path, page_token=page_token, limit=limit
-        )
-        response = self._namespace_client.list_namespaces(request)
-        return ListNamespacesResponse(
-            namespaces=response.namespaces if response.namespaces else [],
-            page_token=response.page_token,
+        return LOOP.run(
+            self._inner.list_namespaces(
+                namespace_path=namespace_path, page_token=page_token, limit=limit
+            )
         )
 
     @override
@@ -693,14 +732,12 @@ class LanceNamespaceDBConnection(DBConnection):
         CreateNamespaceResponse
             Response containing the properties of the created namespace.
         """
-        request = CreateNamespaceRequest(
-            id=namespace_path,
-            mode=_normalize_create_namespace_mode(mode),
-            properties=properties,
-        )
-        response = self._namespace_client.create_namespace(request)
-        return CreateNamespaceResponse(
-            properties=response.properties if hasattr(response, "properties") else None
+        return LOOP.run(
+            self._inner.create_namespace(
+                namespace_path=namespace_path,
+                mode=mode,
+                properties=properties,
+            )
         )
 
     @override
@@ -728,20 +765,18 @@ class LanceNamespaceDBConnection(DBConnection):
         DropNamespaceResponse
             Response containing properties and transaction_id if applicable.
         """
-        request = DropNamespaceRequest(
-            id=namespace_path,
-            mode=_normalize_drop_namespace_mode(mode),
-            behavior=_normalize_drop_namespace_behavior(behavior),
-        )
-        response = self._namespace_client.drop_namespace(request)
-        return DropNamespaceResponse(
-            properties=(
-                response.properties if hasattr(response, "properties") else None
-            ),
-            transaction_id=(
-                response.transaction_id if hasattr(response, "transaction_id") else None
-            ),
-        )
+        try:
+            return LOOP.run(
+                self._inner.drop_namespace(
+                    namespace_path=namespace_path,
+                    mode=mode,
+                    behavior=behavior,
+                )
+            )
+        except RuntimeError as e:
+            if "Namespace not empty" in str(e):
+                raise NamespaceNotEmptyError(str(e)) from e
+            raise
 
     @override
     def describe_namespace(
@@ -760,11 +795,7 @@ class LanceNamespaceDBConnection(DBConnection):
         DescribeNamespaceResponse
             Response containing the namespace properties.
         """
-        request = DescribeNamespaceRequest(id=namespace_path)
-        response = self._namespace_client.describe_namespace(request)
-        return DescribeNamespaceResponse(
-            properties=response.properties if hasattr(response, "properties") else None
-        )
+        return LOOP.run(self._inner.describe_namespace(namespace_path))
 
     @override
     def list_tables(
@@ -794,13 +825,10 @@ class LanceNamespaceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        request = ListTablesRequest(
-            id=namespace_path, page_token=page_token, limit=limit
-        )
-        response = self._namespace_client.list_tables(request)
-        return ListTablesResponse(
-            tables=response.tables if response.tables else [],
-            page_token=response.page_token,
+        return LOOP.run(
+            self._inner.list_tables(
+                namespace_path=namespace_path, page_token=page_token, limit=limit
+            )
         )
 
     def _lance_table_from_uri(
@@ -856,6 +884,18 @@ class LanceNamespaceDBConnection(DBConnection):
         LanceNamespace
             The namespace client for this connection.
         """
+        if self._namespace_client is None:
+            if (
+                self._namespace_client_impl is None
+                or self._namespace_client_properties is None
+            ):
+                raise ValueError(
+                    "Cannot construct a Python namespace client without "
+                    "namespace implementation properties"
+                )
+            self._namespace_client = namespace_connect(
+                self._namespace_client_impl, self._namespace_client_properties
+            )
         return self._namespace_client
 
 
@@ -875,6 +915,8 @@ class AsyncLanceNamespaceDBConnection:
         storage_options: Optional[Dict[str, str]] = None,
         session: Optional[Session] = None,
         namespace_client_pushdown_operations: Optional[List[str]] = None,
+        namespace_client_impl: Optional[str] = None,
+        namespace_client_properties: Optional[Dict[str, str]] = None,
     ):
         """
         Initialize an async namespace-based LanceDB connection.
@@ -900,6 +942,12 @@ class AsyncLanceNamespaceDBConnection:
               namespace.create_table() instead of using declare_table + local write.
 
             Default is None (no pushdown, all operations run locally).
+        namespace_client_impl : Optional[str]
+            The namespace implementation name used to create this connection.
+            Required (with ``namespace_client_properties``) for the Rust client to
+            be built natively and install the read-freshness provider.
+        namespace_client_properties : Optional[Dict[str, str]]
+            The namespace properties used to create this connection.
         """
         self._namespace_client = namespace_client
         self.read_consistency_interval = read_consistency_interval
@@ -908,6 +956,14 @@ class AsyncLanceNamespaceDBConnection:
         self._namespace_client_pushdown_operations = set(
             namespace_client_pushdown_operations or []
         )
+        self._namespace_client_impl = namespace_client_impl
+        self._namespace_client_properties = namespace_client_properties
+        # See LanceNamespaceDBConnection: when built natively the Rust table runs
+        # QueryTable pushdown through the read-freshness provider, so defer to it
+        # rather than the urllib3 client (which omits x-lancedb-min-timestamp).
+        self._route_pushdown_to_rust = _builds_namespace_natively(
+            namespace_client_impl, namespace_client_properties
+        )
         self._inner = AsyncConnection(
             _connect_namespace_client(
                 namespace_client,
@@ -921,8 +977,8 @@ class AsyncLanceNamespaceDBConnection:
                 namespace_client_pushdown_operations=(
                     list(self._namespace_client_pushdown_operations)
                 ),
-                namespace_client_impl=None,
-                namespace_client_properties=None,
+                namespace_client_impl=namespace_client_impl,
+                namespace_client_properties=namespace_client_properties,
             )
         )
 
@@ -992,6 +1048,7 @@ class AsyncLanceNamespaceDBConnection:
             namespace_path=namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._namespace_client_pushdown_operations,
+            route_pushdown_to_rust=self._route_pushdown_to_rust,
         )
 
     async def open_table(
@@ -1029,6 +1086,7 @@ class AsyncLanceNamespaceDBConnection:
             namespace_path=namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._namespace_client_pushdown_operations,
+            route_pushdown_to_rust=self._route_pushdown_to_rust,
         )
 
     async def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):
@@ -1302,6 +1360,33 @@ def connect_namespace(
     LanceNamespaceDBConnection
         A namespace-based connection to LanceDB
     """
+    if _supports_native_sync_namespace(namespace_client_impl):
+        inner = AsyncConnection(
+            _connect_namespace(
+                namespace_client_impl,
+                namespace_client_properties,
+                read_consistency_interval=(
+                    read_consistency_interval.total_seconds()
+                    if read_consistency_interval is not None
+                    else None
+                ),
+                storage_options=storage_options,
+                session=session,
+                namespace_client_pushdown_operations=namespace_client_pushdown_operations,
+            )
+        )
+        return LanceNamespaceDBConnection(
+            namespace_client=None,
+            read_consistency_interval=read_consistency_interval,
+            storage_options=storage_options,
+            session=session,
+            namespace_client_pushdown_operations=namespace_client_pushdown_operations,
+            namespace_client_impl=namespace_client_impl,
+            namespace_client_properties=namespace_client_properties,
+            _inner=inner,
+            _route_pushdown_to_rust=True,
+        )
+
     namespace_client = namespace_connect(
         namespace_client_impl, namespace_client_properties
     )
@@ -1387,4 +1472,6 @@ def connect_namespace_async(
         storage_options=storage_options,
         session=session,
         namespace_client_pushdown_operations=namespace_client_pushdown_operations,
+        namespace_client_impl=namespace_client_impl,
+        namespace_client_properties=namespace_client_properties,
     )

python/python/lancedb/permutation.py

@@ -48,6 +48,14 @@ class PermutationBuilder:
         By default, the permutation builder will create a single split that contains all
         rows in the same order as the base table.
         """
+        if not hasattr(table, "_inner"):
+            raise TypeError(
+                f"PermutationBuilder requires a local LanceTable, "
+                f"got {type(table).__name__}. "
+                "The permutation API is not supported on remote tables. "
+                "Remote tables connect to LanceDB Cloud or Enterprise and do not have "
+                "direct access to the underlying Lance dataset needed for permutations."
+            )
         self._async = async_permutation_builder(table)
 
     def split_random(

python/python/lancedb/remote/__init__.py

@@ -9,6 +9,7 @@ from typing import List, Optional
 from lancedb import __version__
 
 from .header import HeaderProvider
+from .oauth import OAuthConfig, OAuthFlowType
 
 __all__ = [
     "TimeoutConfig",
@@ -16,6 +17,8 @@ __all__ = [
     "TlsConfig",
     "ClientConfig",
     "HeaderProvider",
+    "OAuthConfig",
+    "OAuthFlowType",
 ]
 
 

python/python/lancedb/remote/oauth.py

@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import List, Optional
+
+
+class OAuthFlowType(str, Enum):
+    """OAuth authentication flow types."""
+
+    CLIENT_CREDENTIALS = "client_credentials"
+    """Client Credentials grant (service-to-service / M2M)."""
+
+    AZURE_MANAGED_IDENTITY = "azure_managed_identity"
+    """Azure Managed Identity via IMDS."""
+
+
+@dataclass
+class OAuthConfig:
+    """OAuth configuration for LanceDB authentication.
+
+    All token acquisition and refresh is handled in the Rust layer.
+    This config is passed through to Rust via PyO3.
+
+    Parameters
+    ----------
+    issuer_url : str
+        OIDC issuer URL or OAuth authority URL.
+        For Azure: ``https://login.microsoftonline.com/{tenant_id}/v2.0``
+    client_id : str
+        Application / Client ID.
+    scopes : List[str]
+        OAuth scopes to request.
+        For Azure managed identity, exactly one scope or resource is required.
+        For example: ``["api://{app_id}/.default"]``
+    flow : OAuthFlowType
+        Authentication flow to use. Default: CLIENT_CREDENTIALS.
+    client_secret : Optional[str]
+        Client secret (required for CLIENT_CREDENTIALS).
+    managed_identity_client_id : Optional[str]
+        Client ID for user-assigned managed identity (AZURE_MANAGED_IDENTITY).
+    refresh_buffer_secs : Optional[int]
+        Seconds before expiry to trigger proactive refresh (default: 300).
+        Keep this well below the token TTL; if it is greater than or equal to
+        the TTL, each request refreshes the token.
+
+    Examples
+    --------
+    Client Credentials (service-to-service):
+
+    >>> config = OAuthConfig(
+    ...     issuer_url="https://login.microsoftonline.com/{tenant}/v2.0",
+    ...     client_id="app-id",
+    ...     client_secret="secret",
+    ...     scopes=["api://lancedb-api/.default"],
+    ... )
+
+    Azure Managed Identity:
+
+    >>> config = OAuthConfig(
+    ...     issuer_url="https://login.microsoftonline.com/{tenant}/v2.0",
+    ...     client_id="app-id",
+    ...     scopes=["api://lancedb-api/.default"],
+    ...     flow=OAuthFlowType.AZURE_MANAGED_IDENTITY,
+    ... )
+    """
+
+    issuer_url: str
+    client_id: str
+    scopes: List[str]
+    flow: OAuthFlowType = OAuthFlowType.CLIENT_CREDENTIALS
+    client_secret: Optional[str] = field(default=None, repr=False)
+    managed_identity_client_id: Optional[str] = None
+    refresh_buffer_secs: Optional[int] = None

python/python/lancedb/table.py

@@ -2022,6 +2022,7 @@ class LanceTable(Table):
         namespace_client: Optional[Any] = None,
         managed_versioning: Optional[bool] = None,
         pushdown_operations: Optional[set] = None,
+        route_pushdown_to_rust: bool = False,
         _async: AsyncTable = None,
     ):
         if namespace_path is None:
@@ -2031,6 +2032,14 @@ class LanceTable(Table):
         self._location = location  # Store location for use in _dataset_path
         self._namespace_client = namespace_client
         self._pushdown_operations = pushdown_operations or set()
+        # When the connection built the namespace client natively (e.g. an
+        # enterprise "rest" connection), the underlying Rust table already
+        # executes QueryTable pushdown itself -- and, unlike this Python urllib3
+        # path, it routes through the read-freshness context provider that emits
+        # the ``x-lancedb-min-timestamp`` header. So we must defer pushdown to
+        # Rust instead of calling the Python ``namespace_client.query_table``
+        # directly, or reads silently bypass read-freshness (stale results).
+        self._route_pushdown_to_rust = route_pushdown_to_rust
         if _async is not None:
             self._table = _async
         else:
@@ -2133,12 +2142,19 @@ class LanceTable(Table):
 
         branch = self.current_branch()
         version = None if branch is not None else self.version
-        if self._namespace_client is not None:
+        namespace_client = self._namespace_client
+        if namespace_client is None:
+            conn_uri = getattr(self._conn, "uri", "")
+            if get_uri_scheme(conn_uri) == "namespace":
+                namespace_client = self._conn.namespace_client()
+                self._namespace_client = namespace_client
+
+        if namespace_client is not None:
             table_id = self._namespace_path + [self.name]
             ds = lance.dataset(
                 version=version,
                 storage_options=self._conn.storage_options,
-                namespace_client=self._namespace_client,
+                namespace_client=namespace_client,
                 table_id=table_id,
                 **kwargs,
             )
@@ -2241,6 +2257,7 @@ class LanceTable(Table):
             namespace_path=self._namespace_path,
             namespace_client=self._namespace_client,
             pushdown_operations=self._pushdown_operations,
+            route_pushdown_to_rust=self._route_pushdown_to_rust,
             location=self._location,
             _async=async_table,
         )
@@ -2391,8 +2408,11 @@ class LanceTable(Table):
         Returns
         -------
         pa.Table"""
-        if _should_push_down_query_table(
-            self._namespace_client, self._pushdown_operations
+        if (
+            _should_push_down_query_table(
+                self._namespace_client, self._pushdown_operations
+            )
+            and not self._route_pushdown_to_rust
         ):
             return self._execute_query(Query()).read_all()
 
@@ -3344,6 +3364,7 @@ class LanceTable(Table):
         location: Optional[str] = None,
         namespace_client: Optional[Any] = None,
         pushdown_operations: Optional[set] = None,
+        route_pushdown_to_rust: bool = False,
     ):
         """
         Create a new table.
@@ -3406,6 +3427,7 @@ class LanceTable(Table):
         self._location = location
         self._namespace_client = namespace_client
         self._pushdown_operations = pushdown_operations or set()
+        self._route_pushdown_to_rust = route_pushdown_to_rust
 
         if data_storage_version is not None:
             warnings.warn(
@@ -3519,6 +3541,7 @@ class LanceTable(Table):
             _should_push_down_query_table(
                 self._namespace_client, self._pushdown_operations
             )
+            and not self._route_pushdown_to_rust
             and self.current_branch() is None
         ):
             from lancedb.namespace import _execute_server_side_query
@@ -4260,6 +4283,7 @@ class AsyncTable:
         namespace_path: Optional[List[str]] = None,
         namespace_client: Optional[Any] = None,
         pushdown_operations: Optional[set] = None,
+        route_pushdown_to_rust: bool = False,
     ):
         """Create a new AsyncTable object.
 
@@ -4272,6 +4296,9 @@ class AsyncTable:
         self._namespace_path = namespace_path or []
         self._namespace_client = namespace_client
         self._pushdown_operations = pushdown_operations or set()
+        # See LanceTable.__init__: defer QueryTable pushdown to Rust (which emits
+        # the read-freshness header) for natively-built namespace clients.
+        self._route_pushdown_to_rust = route_pushdown_to_rust
 
     def _set_namespace_context(
         self,
@@ -4279,10 +4306,12 @@ class AsyncTable:
         namespace_path: Optional[List[str]] = None,
         namespace_client: Optional[Any] = None,
         pushdown_operations: Optional[set] = None,
+        route_pushdown_to_rust: bool = False,
     ) -> "AsyncTable":
         self._namespace_path = namespace_path or []
         self._namespace_client = namespace_client
         self._pushdown_operations = pushdown_operations or set()
+        self._route_pushdown_to_rust = route_pushdown_to_rust
         return self
 
     def __repr__(self):
@@ -4492,8 +4521,11 @@ class AsyncTable:
         -------
         pa.Table
         """
-        if _should_push_down_query_table(
-            self._namespace_client, self._pushdown_operations
+        if (
+            _should_push_down_query_table(
+                self._namespace_client, self._pushdown_operations
+            )
+            and not self._route_pushdown_to_rust
         ):
             return (await self._execute_query(Query())).read_all()
 
@@ -5177,8 +5209,11 @@ class AsyncTable:
         batch_size: Optional[int] = None,
         timeout: Optional[timedelta] = None,
     ) -> pa.RecordBatchReader:
-        if _should_push_down_query_table(
-            self._namespace_client, self._pushdown_operations
+        if (
+            _should_push_down_query_table(
+                self._namespace_client, self._pushdown_operations
+            )
+            and not self._route_pushdown_to_rust
         ):
             from lancedb.namespace import _execute_server_side_query
 

python/python/tests/test_namespace.py

@@ -5,6 +5,7 @@
 
 import tempfile
 import shutil
+import importlib
 import pytest
 import pyarrow as pa
 import lancedb
@@ -65,6 +66,9 @@ def _namespace_lance_table(namespace_client: _NamespaceClient) -> LanceTable:
     table._namespace_path = ["geneva"]
     table._namespace_client = namespace_client
     table._pushdown_operations = {"QueryTable"}
+    # This test exercises the Python-side pushdown path (non-native client), so
+    # pushdown is not routed to Rust.
+    table._route_pushdown_to_rust = False
     return table
 
 
@@ -100,6 +104,40 @@ class TestNamespaceConnection:
         assert isinstance(db, lancedb.LanceNamespaceDBConnection)
         assert len(list(db.table_names())) == 0
 
+    def test_sync_builtin_namespace_uses_rust_without_python_client(self, monkeypatch):
+        """Built-in sync namespace connections should not construct or call the
+        Python namespace client for normal namespace/table management."""
+        namespace_module = importlib.import_module("lancedb.namespace")
+
+        def fail_namespace_connect(*args, **kwargs):
+            raise AssertionError("Python namespace client should not be constructed")
+
+        monkeypatch.setattr(
+            namespace_module, "namespace_connect", fail_namespace_connect
+        )
+
+        db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
+        assert isinstance(db, lancedb.LanceNamespaceDBConnection)
+        assert db._namespace_client is None
+        assert db._route_pushdown_to_rust is True
+
+        db.create_namespace(["test_ns"])
+        assert "test_ns" in db.list_namespaces().namespaces
+
+        schema = pa.schema([pa.field("id", pa.int64())])
+        table = db.create_table("test_table", schema=schema, namespace_path=["test_ns"])
+        assert table.namespace == ["test_ns"]
+        assert "test_table" in db.table_names(namespace_path=["test_ns"])
+        assert "test_table" in db.list_tables(namespace_path=["test_ns"]).tables
+
+        opened = db.open_table("test_table", namespace_path=["test_ns"])
+        assert opened.namespace == ["test_ns"]
+
+        db.drop_table("test_table", namespace_path=["test_ns"])
+        assert db.list_tables(namespace_path=["test_ns"]).tables == []
+        db.drop_namespace(["test_ns"])
+        assert "test_ns" not in db.list_namespaces().namespaces
+
     def test_create_table_through_namespace(self):
         """Test creating a table through namespace."""
         db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
@@ -805,6 +843,38 @@ class TestPushdownOperations:
         db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
         assert len(db._namespace_client_pushdown_operations) == 0
 
+    def test_route_pushdown_to_rust_for_native_rest(self):
+        """A natively-built rest connection must defer QueryTable pushdown to
+        Rust so reads carry the x-lancedb-min-timestamp read-freshness header."""
+        db = lancedb.connect_namespace(
+            "rest",
+            {"uri": "http://localhost:12345"},
+            namespace_client_pushdown_operations=["QueryTable"],
+        )
+        assert db._route_pushdown_to_rust is True
+
+    def test_route_pushdown_to_rust_for_native_dir(self):
+        """The sync dir connection is natively built and defers QueryTable
+        pushdown to Rust."""
+        db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
+        assert db._route_pushdown_to_rust is True
+
+    def test_async_route_pushdown_to_rust_for_native_rest(self):
+        """The async connection must not silently bypass the read-freshness fix:
+        a natively-built rest connection defers pushdown to Rust (regression test
+        for the async path omitting the freshness header)."""
+        db = lancedb.connect_namespace_async(
+            "rest",
+            {"uri": "http://localhost:12345"},
+            namespace_client_pushdown_operations=["QueryTable"],
+        )
+        assert db._route_pushdown_to_rust is True
+
+    def test_async_route_pushdown_to_rust_false_for_dir(self):
+        """The async non-native (dir) connection keeps the Python pushdown path."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+        assert db._route_pushdown_to_rust is False
+
     def test_lance_table_to_arrow_uses_query_pushdown(self):
         namespace_client = _NamespaceClient()
         table = _namespace_lance_table(namespace_client)

python/python/tests/test_table.py

@@ -1137,6 +1137,16 @@ def test_namespace_open_table_with_branch_version(tmp_path):
     assert db.open_table("t", namespace_path=["ns1"], branch="exp").count_rows() == 3
 
 
+def test_namespace_root_table_to_lance_uses_namespace_client(tmp_path):
+    pytest.importorskip("lance")  # "dir" impl is lance.namespace.DirectoryNamespace
+    db = lancedb.connect_namespace("dir", {"root": str(tmp_path)})
+    table = db.create_table("t", [{"i": 0}])
+
+    assert table._namespace_client is None
+    assert table.to_lance().count_rows() == 1
+    assert table._namespace_client is not None
+
+
 @pytest.mark.asyncio
 async def test_async_namespace_open_table_with_branch_version(tmp_path):
     pytest.importorskip("lance")  # "dir" impl is lance.namespace.DirectoryNamespace

python/src/connection.rs

@@ -539,7 +539,7 @@ impl Connection {
 }
 
 #[pyfunction]
-#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None))]
+#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None, oauth_config=None))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect(
     py: Python<'_>,
@@ -553,6 +553,7 @@ pub fn connect(
     session: Option<crate::session::Session>,
     manifest_enabled: bool,
     namespace_client_properties: Option<HashMap<String, String>>,
+    oauth_config: Option<crate::oauth::PyOAuthConfig>,
 ) -> PyResult<Bound<'_, PyAny>> {
     future_into_py(py, async move {
         let mut builder = lancedb::connect(&uri);
@@ -582,6 +583,11 @@ pub fn connect(
         if let Some(client_config) = client_config {
             builder = builder.client_config(client_config.into());
         }
+        if let Some(oauth_config) = oauth_config {
+            let config: lancedb::remote::oauth::OAuthConfig =
+                oauth_config.try_into().infer_error()?;
+            builder = builder.oauth_config(config);
+        }
         if let Some(session) = session {
             builder = builder.session(session.inner.clone());
         }
@@ -610,24 +616,38 @@ pub fn connect_namespace_client(
     namespace_client_impl: Option<String>,
     namespace_client_properties: Option<HashMap<String, String>>,
 ) -> PyResult<Connection> {
-    let namespace_client = extract_namespace_arc(py, namespace_client)?;
     let read_consistency_interval = read_consistency_interval.map(Duration::from_secs_f64);
     let namespace_client_pushdown_operations =
         parse_namespace_client_pushdown_operations(namespace_client_pushdown_operations)?;
-    let ns_impl = namespace_client_impl.unwrap_or_else(|| "python".to_string());
     let ns_properties = namespace_client_properties.unwrap_or_default();
     let storage_options = storage_options.unwrap_or_default();
     let session = session.map(|s| s.inner.clone());
 
-    let database = LanceNamespaceDatabase::from_namespace_client(
-        namespace_client,
-        ns_impl,
-        ns_properties,
-        storage_options,
-        read_consistency_interval,
-        session,
-        namespace_client_pushdown_operations,
-    );
+    // Prefer building the namespace natively from (impl, properties) so the
+    // read-freshness provider installed
+    let database = if build_namespace_natively(namespace_client_impl.as_deref(), &ns_properties) {
+        let ns_impl = namespace_client_impl.expect("impl present per build_namespace_natively");
+        crate::runtime::block_on(LanceNamespaceDatabase::connect(
+            &ns_impl,
+            ns_properties,
+            storage_options,
+            read_consistency_interval,
+            session,
+            namespace_client_pushdown_operations,
+        ))
+        .infer_error()?
+    } else {
+        let namespace_client = extract_namespace_arc(py, namespace_client)?;
+        LanceNamespaceDatabase::from_namespace_client(
+            namespace_client,
+            namespace_client_impl.unwrap_or_else(|| "python".to_string()),
+            ns_properties,
+            storage_options,
+            read_consistency_interval,
+            session,
+            namespace_client_pushdown_operations,
+        )
+    };
 
     Ok(Connection::new(LanceConnection::new(
         Arc::new(database),
@@ -635,6 +655,56 @@ pub fn connect_namespace_client(
     )))
 }
 
+#[pyfunction]
+#[pyo3(signature = (
+    namespace_client_impl,
+    namespace_client_properties,
+    read_consistency_interval=None,
+    storage_options=None,
+    session=None,
+    namespace_client_pushdown_operations=None,
+))]
+#[allow(clippy::too_many_arguments)]
+pub fn connect_namespace(
+    namespace_client_impl: String,
+    namespace_client_properties: HashMap<String, String>,
+    read_consistency_interval: Option<f64>,
+    storage_options: Option<HashMap<String, String>>,
+    session: Option<crate::session::Session>,
+    namespace_client_pushdown_operations: Option<Vec<String>>,
+) -> PyResult<Connection> {
+    let read_consistency_interval = read_consistency_interval.map(Duration::from_secs_f64);
+    let namespace_client_pushdown_operations =
+        parse_namespace_client_pushdown_operations(namespace_client_pushdown_operations)?;
+
+    let mut builder =
+        lancedb::connect_namespace(&namespace_client_impl, namespace_client_properties)
+            .pushdown_operations(namespace_client_pushdown_operations);
+    if let Some(storage_options) = storage_options {
+        builder = builder.storage_options(storage_options);
+    }
+    if let Some(read_consistency_interval) = read_consistency_interval {
+        builder = builder.read_consistency_interval(read_consistency_interval);
+    }
+    if let Some(session) = session {
+        builder = builder.session(session.inner.clone());
+    }
+
+    Ok(Connection::new(
+        crate::runtime::block_on(builder.execute()).infer_error()?,
+    ))
+}
+
+/// Whether to build the namespace natively (from impl + properties) instead of
+/// wrapping a pre-built client. Native construction is required for the
+/// read-freshness provider to be installed
+fn build_namespace_natively(
+    namespace_client_impl: Option<&str>,
+    namespace_client_properties: &HashMap<String, String>,
+) -> bool {
+    matches!(namespace_client_impl, Some("rest")) && !namespace_client_properties.is_empty()
+}
+
 #[derive(FromPyObject)]
 pub struct PyClientConfig {
     user_agent: String,
@@ -733,3 +803,36 @@ impl From<PyClientConfig> for lancedb::remote::ClientConfig {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn props(pairs: &[(&str, &str)]) -> HashMap<String, String> {
+        pairs
+            .iter()
+            .map(|(k, v)| (k.to_string(), v.to_string()))
+            .collect()
+    }
+
+    #[test]
+    fn native_build_only_for_rest_with_properties() {
+        let rest = props(&[("uri", "http://localhost:10024")]);
+
+        // rest + non-empty properties -> build natively (installs the
+        // read-freshness provider so checkout_latest() busts the server cache).
+        assert!(build_namespace_natively(Some("rest"), &rest));
+
+        // dir is local (no server cache) -> wrap the pre-built client unchanged.
+        assert!(!build_namespace_natively(
+            Some("dir"),
+            &props(&[("root", "/tmp")])
+        ));
+
+        // No impl: only a pre-built client was handed in -> wrap it as-is.
+        assert!(!build_namespace_natively(None, &rest));
+
+        // rest but no properties: nothing to build a connection from -> wrap.
+        assert!(!build_namespace_natively(Some("rest"), &HashMap::new()));
+    }
+}

python/src/lib.rs

@@ -2,7 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use arrow::RecordBatchStream;
-use connection::{Connection, connect, connect_namespace_client};
+use connection::{Connection, connect, connect_namespace, connect_namespace_client};
 use env_logger::Env;
 use expr::{PyExpr, expr_col, expr_func, expr_lit};
 use index::IndexConfig;
@@ -26,6 +26,7 @@ pub mod expr;
 pub mod header;
 pub mod index;
 pub mod namespace;
+pub mod oauth;
 pub mod permutation;
 pub mod query;
 pub mod runtime;
@@ -61,6 +62,7 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<PyPermutationReader>()?;
     m.add_class::<PyExpr>()?;
     m.add_function(wrap_pyfunction!(connect, m)?)?;
+    m.add_function(wrap_pyfunction!(connect_namespace, m)?)?;
     m.add_function(wrap_pyfunction!(connect_namespace_client, m)?)?;
     m.add_function(wrap_pyfunction!(permutation::async_permutation_builder, m)?)?;
     m.add_function(wrap_pyfunction!(util::validate_table_name, m)?)?;

python/src/oauth.rs

@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use pyo3::FromPyObject;
+
+use lancedb::error::Error;
+use lancedb::remote::oauth::{OAuthConfig, OAuthFlow};
+
+/// Python-side OAuth configuration, extracted via FromPyObject.
+/// Maps to `lancedb.remote.oauth.OAuthConfig` Python dataclass.
+#[derive(FromPyObject)]
+pub struct PyOAuthConfig {
+    pub issuer_url: String,
+    pub client_id: String,
+    pub scopes: Vec<String>,
+    pub flow: String,
+    pub client_secret: Option<String>,
+    pub managed_identity_client_id: Option<String>,
+    pub refresh_buffer_secs: Option<u64>,
+}
+
+impl TryFrom<PyOAuthConfig> for OAuthConfig {
+    type Error = Error;
+
+    fn try_from(py: PyOAuthConfig) -> Result<Self, Self::Error> {
+        let flow = match py.flow.as_str() {
+            "client_credentials" => OAuthFlow::ClientCredentials,
+            "azure_managed_identity" => OAuthFlow::AzureManagedIdentity {
+                client_id: py.managed_identity_client_id,
+            },
+            other => {
+                return Err(Error::InvalidInput {
+                    message: format!("Unknown OAuth flow type: {other}"),
+                });
+            }
+        };
+
+        Ok(Self {
+            issuer_url: py.issuer_url,
+            client_id: py.client_id,
+            client_secret: py.client_secret,
+            scopes: py.scopes,
+            flow,
+            refresh_buffer_secs: py.refresh_buffer_secs,
+        })
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_unknown_oauth_flow_returns_invalid_input() {
+        let config = PyOAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            scopes: vec!["scope".to_string()],
+            flow: "typo".to_string(),
+            client_secret: None,
+            managed_identity_client_id: None,
+            refresh_buffer_secs: None,
+        };
+
+        let err = OAuthConfig::try_from(config).unwrap_err();
+        assert!(matches!(
+            err,
+            Error::InvalidInput { message }
+                if message == "Unknown OAuth flow type: typo"
+        ));
+    }
+}

python/src/runtime.rs

@@ -56,6 +56,15 @@ fn get_runtime() -> &'static runtime::Runtime {
     unsafe { &*new_ptr }
 }
 
+/// Block the current thread on a future using the shared runtime.
+///
+/// For sync `#[pyfunction]`s that need to drive an async operation (e.g.
+/// building a namespace client). Must not be called from within the runtime's
+/// own worker threads.
+pub fn block_on<F: std::future::Future>(fut: F) -> F::Output {
+    get_runtime().block_on(fut)
+}
+
 /// Runs in async-signal context after `fork()` in the child.  We can only
 /// touch atomics here; we deliberately leak the previous runtime because
 /// dropping a tokio `Runtime` would try to join its (now-dead) worker

python/tests/test_oauth.py

@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import importlib.util
+import sys
+from pathlib import Path
+
+
+def _load_oauth_module():
+    oauth_path = (
+        Path(__file__).parents[1] / "python" / "lancedb" / "remote" / "oauth.py"
+    )
+    spec = importlib.util.spec_from_file_location("lancedb_remote_oauth", oauth_path)
+    module = importlib.util.module_from_spec(spec)
+    assert spec.loader is not None
+    sys.modules[spec.name] = module
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_oauth_config_repr_redacts_client_secret():
+    oauth = _load_oauth_module()
+
+    config = oauth.OAuthConfig(
+        issuer_url="https://issuer.example.com",
+        client_id="client-id",
+        scopes=["scope"],
+        client_secret="super-secret",
+    )
+
+    rendered = repr(config)
+    assert "super-secret" not in rendered
+    assert "client_secret" not in rendered

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.31.0-beta.2"
+version = "0.31.0-beta.5"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -50,7 +50,7 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
-tokio = { version = "1.23", features = ["rt-multi-thread"] }
+tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
 log.workspace = true
 async-trait = "0"
 bytes = "1"
@@ -75,6 +75,7 @@ reqwest = { version = "0.12.0", default-features = false, features = [
     "stream",
 ], optional = true }
 http = { version = "1", optional = true } # Matching what is in reqwest
+urlencoding = { version = "2", optional = true }
 uuid = { version = "1.7.0", features = ["v4", "v5"] }
 polars-arrow = { version = ">=0.37,<0.40.0", optional = true }
 polars = { version = ">=0.37,<0.40.0", optional = true }
@@ -93,6 +94,7 @@ semver = { workspace = true }
 anyhow = "1"
 tempfile = "3.5.0"
 random_word = { version = "0.4.3", features = ["en"] }
+tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync"] }
 uuid = { version = "1.7.0", features = ["v4"] }
 walkdir = "2"
 aws-sdk-dynamodb = { version = "1.55.0" }
@@ -129,7 +131,13 @@ huggingface = [
     "lance-namespace-impls/dir-huggingface",
 ]
 dynamodb = ["lance/dynamodb", "aws"]
-remote = ["dep:reqwest", "dep:http", "lance-namespace-impls/rest", "lance-namespace-impls/rest-adapter"]
+remote = [
+    "dep:reqwest",
+    "dep:http",
+    "dep:urlencoding",
+    "lance-namespace-impls/rest",
+    "lance-namespace-impls/rest-adapter",
+]
 fp16kernels = ["lance-linalg/fp16kernels"]
 s3-test = []
 bedrock = ["dep:aws-sdk-bedrockruntime"]
@@ -158,6 +166,10 @@ required-features = ["bedrock"]
 [[example]]
 name = "simple"
 
+[[example]]
+name = "polars"
+required-features = ["polars"]
+
 [[example]]
 name = "full_text_search"
 

rust/lancedb/examples/polars.rs

@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+//! This example demonstrates ingesting a Polars DataFrame into LanceDB and
+//! reading it back out as a Polars DataFrame.
+
+use lancedb::arrow::IntoPolars;
+use lancedb::query::ExecutableQuery;
+use lancedb::{Result, connect};
+use polars::prelude::{DataFrame, NamedFrom, Series};
+
+fn make_dataframe() -> DataFrame {
+    let ids = Series::new("id", &[1i32, 2, 3, 4, 5]);
+    let names = Series::new("name", &["Alice", "Bob", "Carol", "Dave", "Eve"]);
+    let scores = Series::new("score", &[9.5f64, 8.1, 7.3, 9.0, 6.5]);
+    DataFrame::new(vec![ids, names, scores]).unwrap()
+}
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    let tmp = tempfile::tempdir().unwrap();
+    let db = connect(tmp.path().to_str().unwrap()).execute().await?;
+
+    // Ingest a Polars DataFrame directly — DataFrame now implements Scannable.
+    let df = make_dataframe();
+    println!("Input DataFrame:\n{df}");
+
+    let table = db.create_table("people", df).execute().await?;
+
+    // Append more rows.
+    let more = DataFrame::new(vec![
+        Series::new("id", &[6i32, 7]),
+        Series::new("name", &["Frank", "Grace"]),
+        Series::new("score", &[7.8f64, 8.9]),
+    ])
+    .unwrap();
+    table.add(more).execute().await?;
+
+    // Read back as a Polars DataFrame.
+    let result_df = table.query().execute().await?.into_polars().await?;
+
+    println!(
+        "\nRound-tripped DataFrame ({} rows):\n{result_df}",
+        result_df.height()
+    );
+    Ok(())
+}

rust/lancedb/src/arrow.rs

@@ -112,54 +112,14 @@ impl<S: Stream<Item = Result<arrow_array::RecordBatch>>> RecordBatchStream
 
 /// A trait for converting incoming data to Arrow
 ///
-/// Integrations should implement this trait to allow data to be
-/// imported directly from the integration.  For example, implementing
-/// this trait for `Vec<Vec<...>>` would allow the `Vec` to be directly
-/// used in methods like [`crate::connection::Connection::create_table`]
-/// or [`crate::table::Table::add`]
-pub trait IntoArrow {
-    /// Convert the data into an iterator of Arrow batches
-    fn into_arrow(self) -> Result<Box<dyn arrow_array::RecordBatchReader + Send>>;
-}
-
 pub type BoxedRecordBatchReader = Box<dyn arrow_array::RecordBatchReader + Send>;
 
-impl<T: arrow_array::RecordBatchReader + Send + 'static> IntoArrow for T {
-    fn into_arrow(self) -> Result<Box<dyn arrow_array::RecordBatchReader + Send>> {
-        Ok(Box::new(self))
-    }
-}
-
-/// A trait for converting incoming data to Arrow asynchronously
-///
-/// Serves the same purpose as [`IntoArrow`], but for asynchronous data.
-///
-/// Note: Arrow has no async equivalent to RecordBatchReader and so
-pub trait IntoArrowStream {
-    /// Convert the data into a stream of Arrow batches
-    fn into_arrow(self) -> Result<SendableRecordBatchStream>;
-}
-
 impl<S: Stream<Item = Result<arrow_array::RecordBatch>>> SimpleRecordBatchStream<S> {
     pub fn new(stream: S, schema: Arc<arrow_schema::Schema>) -> Self {
         Self { schema, stream }
     }
 }
 
-impl IntoArrowStream for SendableRecordBatchStream {
-    fn into_arrow(self) -> Result<SendableRecordBatchStream> {
-        Ok(self)
-    }
-}
-
-impl IntoArrowStream for datafusion_physical_plan::SendableRecordBatchStream {
-    fn into_arrow(self) -> Result<SendableRecordBatchStream> {
-        let schema = self.schema();
-        let stream = self.map_err(|df_err| df_err.into());
-        Ok(Box::pin(SimpleRecordBatchStream::new(stream, schema)))
-    }
-}
-
 pub trait LanceDbDatagenExt {
     fn into_ldb_stream(
         self,
@@ -264,9 +224,7 @@ impl IntoPolars for SendableRecordBatchStream {
 #[cfg(all(test, feature = "polars"))]
 mod tests {
     use super::SendableRecordBatchStream;
-    use crate::arrow::{
-        IntoArrow, IntoPolars, PolarsDataFrameRecordBatchReader, SimpleRecordBatchStream,
-    };
+    use crate::arrow::{IntoPolars, PolarsDataFrameRecordBatchReader, SimpleRecordBatchStream};
     use polars::prelude::{DataFrame, NamedFrom, Series};
 
     fn get_record_batch_reader_from_polars() -> Box<dyn arrow_array::RecordBatchReader + Send> {
@@ -280,10 +238,7 @@ mod tests {
         float_series = Series::new("float", &[2.0]);
         let df2 = DataFrame::new(vec![string_series, int_series, float_series]).unwrap();
 
-        PolarsDataFrameRecordBatchReader::new(df1.vstack(&df2).unwrap())
-            .unwrap()
-            .into_arrow()
-            .unwrap()
+        Box::new(PolarsDataFrameRecordBatchReader::new(df1.vstack(&df2).unwrap()).unwrap())
     }
 
     #[test]

rust/lancedb/src/connection.rs

@@ -667,6 +667,8 @@ pub struct ConnectRequest {
 pub struct ConnectBuilder {
     request: ConnectRequest,
     embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
+    #[cfg(feature = "remote")]
+    oauth_config: Option<crate::remote::OAuthConfig>,
 }
 
 #[cfg(feature = "remote")]
@@ -688,6 +690,8 @@ impl ConnectBuilder {
                 session: None,
             },
             embedding_registry: None,
+            #[cfg(feature = "remote")]
+            oauth_config: None,
         }
     }
 
@@ -776,6 +780,19 @@ impl ConnectBuilder {
         self
     }
 
+    /// Configure OAuth authentication for LanceDB Cloud/Enterprise.
+    ///
+    /// This creates an [`OAuthHeaderProvider`](crate::remote::OAuthHeaderProvider)
+    /// from the given config and sets it as the header provider. OAuth cannot
+    /// be combined with an API key or another header provider.
+    ///
+    /// Token acquisition and refresh are handled in Rust.
+    #[cfg(feature = "remote")]
+    pub fn oauth_config(mut self, config: crate::remote::OAuthConfig) -> Self {
+        self.oauth_config = Some(config);
+        self
+    }
+
     /// Provide a custom [`EmbeddingRegistry`] to use for this connection.
     pub fn embedding_registry(mut self, registry: Arc<dyn EmbeddingRegistry>) -> Self {
         self.embedding_registry = Some(registry);
@@ -921,9 +938,40 @@ impl ConnectBuilder {
         let region = options.region.ok_or_else(|| Error::InvalidInput {
             message: "A region is required when connecting to LanceDb Cloud".to_string(),
         })?;
-        let api_key = options.api_key.ok_or_else(|| Error::InvalidInput {
-            message: "An api_key is required when connecting to LanceDb Cloud".to_string(),
-        })?;
+        let api_key = match (&self.oauth_config, &options.api_key) {
+            (Some(_), None) => String::new(),
+            (Some(_), Some(_)) => {
+                return Err(Error::InvalidInput {
+                    message:
+                        "api_key and oauth_config cannot both be set when connecting to LanceDb Cloud"
+                            .to_string(),
+                });
+            }
+            (None, Some(key)) => key.clone(),
+            (None, None) => {
+                return Err(Error::InvalidInput {
+                    message:
+                        "An api_key or oauth_config is required when connecting to LanceDb Cloud"
+                            .to_string(),
+                });
+            }
+        };
+
+        if self.oauth_config.is_some() && self.request.client_config.header_provider.is_some() {
+            return Err(Error::InvalidInput {
+                message:
+                    "oauth_config and client_config.header_provider cannot both be set when connecting to LanceDb Cloud"
+                        .to_string(),
+            });
+        }
+
+        let mut client_config = self.request.client_config;
+
+        if let Some(oauth_config) = self.oauth_config {
+            let provider = crate::remote::OAuthHeaderProvider::new(oauth_config)?;
+            client_config.header_provider =
+                Some(Arc::new(provider) as Arc<dyn crate::remote::HeaderProvider>);
+        }
 
         let storage_options = StorageOptions(options.storage_options.clone());
         let internal = Arc::new(crate::remote::db::RemoteDatabase::try_new(
@@ -931,7 +979,7 @@ impl ConnectBuilder {
             &api_key,
             &region,
             options.host_override,
-            self.request.client_config,
+            client_config,
             storage_options.into(),
             self.request.read_consistency_interval,
         )?);
@@ -1240,6 +1288,83 @@ mod tests {
         assert_eq!(Some(&"EXPLICIT-VALUE".to_string()), options.get(opts_key));
     }
 
+    #[cfg(feature = "remote")]
+    #[tokio::test]
+    async fn test_connect_rejects_api_key_with_oauth_config() {
+        let oauth_config = crate::remote::OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            client_secret: Some("secret".to_string()),
+            scopes: vec!["scope".to_string()],
+            flow: crate::remote::OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: None,
+        };
+
+        let result = ConnectBuilder::new("db://my-container/my-prefix")
+            .region("us-east-1")
+            .api_key("my-api-key")
+            .oauth_config(oauth_config)
+            .execute()
+            .await;
+
+        match result {
+            Err(Error::InvalidInput { message })
+                if message
+                    == "api_key and oauth_config cannot both be set when connecting to LanceDb Cloud" =>
+                {}
+            Err(err) => panic!("expected InvalidInput, got {err:?}"),
+            Ok(_) => panic!("expected api_key and oauth_config to be rejected"),
+        }
+    }
+
+    #[cfg(feature = "remote")]
+    #[tokio::test]
+    async fn test_connect_rejects_header_provider_with_oauth_config() {
+        #[derive(Debug)]
+        struct TestHeaderProvider;
+
+        #[async_trait::async_trait]
+        impl crate::remote::HeaderProvider for TestHeaderProvider {
+            async fn get_headers(&self) -> Result<HashMap<String, String>> {
+                Ok(HashMap::from([(
+                    "authorization".to_string(),
+                    "Bearer token".to_string(),
+                )]))
+            }
+        }
+
+        let oauth_config = crate::remote::OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            client_secret: Some("secret".to_string()),
+            scopes: vec!["scope".to_string()],
+            flow: crate::remote::OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: None,
+        };
+        let client_config = crate::remote::ClientConfig {
+            header_provider: Some(
+                Arc::new(TestHeaderProvider) as Arc<dyn crate::remote::HeaderProvider>
+            ),
+            ..Default::default()
+        };
+
+        let result = ConnectBuilder::new("db://my-container/my-prefix")
+            .region("us-east-1")
+            .client_config(client_config)
+            .oauth_config(oauth_config)
+            .execute()
+            .await;
+
+        match result {
+            Err(Error::InvalidInput { message })
+                if message
+                    == "oauth_config and client_config.header_provider cannot both be set when connecting to LanceDb Cloud" =>
+                {}
+            Err(err) => panic!("expected InvalidInput, got {err:?}"),
+            Ok(_) => panic!("expected header_provider and oauth_config to be rejected"),
+        }
+    }
+
     #[cfg(not(windows))]
     #[tokio::test]
     async fn test_connect_relative() {

rust/lancedb/src/data/scannable.rs

@@ -185,6 +185,43 @@ impl Scannable for SendableRecordBatchStream {
     }
 }
 
+#[cfg(feature = "polars")]
+impl Scannable for polars::frame::DataFrame {
+    fn schema(&self) -> SchemaRef {
+        crate::polars_arrow_convertors::convert_polars_df_schema_to_arrow_rb_schema(
+            self.schema().clone(),
+        )
+        .expect("failed to convert Polars DataFrame schema to Arrow schema")
+    }
+
+    fn scan_as_stream(&mut self) -> SendableRecordBatchStream {
+        let schema = Scannable::schema(self);
+        let batches: crate::Result<Vec<RecordBatch>> =
+            match crate::arrow::PolarsDataFrameRecordBatchReader::new(self.clone()) {
+                Err(e) => Err(e),
+                Ok(reader) => reader.map(|b| b.map_err(Into::into)).collect(),
+            };
+        match batches {
+            Err(e) => Box::pin(SimpleRecordBatchStream {
+                schema,
+                stream: once(async move { Err(e) }),
+            }),
+            Ok(batches) => {
+                let stream = futures::stream::iter(batches.into_iter().map(Ok));
+                Box::pin(SimpleRecordBatchStream { schema, stream })
+            }
+        }
+    }
+
+    fn num_rows(&self) -> Option<usize> {
+        Some(self.height())
+    }
+
+    fn rescannable(&self) -> bool {
+        true
+    }
+}
+
 #[async_trait]
 impl StreamingWriteSource for Box<dyn Scannable> {
     fn arrow_schema(&self) -> SchemaRef {
@@ -1089,4 +1126,60 @@ mod tests {
             );
         }
     }
+
+    #[cfg(feature = "polars")]
+    mod polars_tests {
+        use super::*;
+        use crate::arrow::IntoPolars;
+        use crate::query::ExecutableQuery;
+        use polars::prelude::{DataFrame, NamedFrom, Series};
+
+        fn make_df() -> DataFrame {
+            DataFrame::new(vec![
+                Series::new("id", &[1i32, 2, 3]),
+                Series::new("val", &[1.1f64, 2.2, 3.3]),
+            ])
+            .unwrap()
+        }
+
+        #[tokio::test]
+        async fn test_dataframe_scannable_round_trip() {
+            let tmp = tempfile::tempdir().unwrap();
+            let db = crate::connect(tmp.path().to_str().unwrap())
+                .execute()
+                .await
+                .unwrap();
+
+            let df = make_df();
+            let table = db.create_table("t", df.clone()).execute().await.unwrap();
+
+            // Append the same rows again.
+            table.add(df.clone()).execute().await.unwrap();
+
+            let result = table
+                .query()
+                .execute()
+                .await
+                .unwrap()
+                .into_polars()
+                .await
+                .unwrap();
+
+            assert_eq!(result.height(), df.height() * 2);
+            assert_eq!(result.schema(), df.schema());
+        }
+
+        #[tokio::test]
+        async fn test_dataframe_scannable_rescannable() {
+            let mut df = make_df();
+            assert!(df.rescannable());
+
+            let batches1: Vec<RecordBatch> = df.scan_as_stream().try_collect().await.unwrap();
+            assert_eq!(batches1.iter().map(|b| b.num_rows()).sum::<usize>(), 3);
+
+            // Can be scanned again.
+            let batches2: Vec<RecordBatch> = df.scan_as_stream().try_collect().await.unwrap();
+            assert_eq!(batches2.iter().map(|b| b.num_rows()).sum::<usize>(), 3);
+        }
+    }
 }

rust/lancedb/src/database/listing.rs

@@ -14,6 +14,7 @@ use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
 use lance_encoding::version::LanceFileVersion;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
+use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
 use snafu::ResultExt;
 
@@ -234,9 +235,11 @@ impl ListingDatabaseOptionsBuilder {
 /// We will have two tables named `table1` and `table2`.
 #[derive(Debug)]
 pub struct ListingDatabase {
+    object_store: Arc<ObjectStore>,
     query_string: Option<String>,
 
     pub(crate) uri: String,
+    pub(crate) base_path: object_store::path::Path,
 
     // the object store wrapper to use on write path
     pub(crate) store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
@@ -255,13 +258,8 @@ pub struct ListingDatabase {
     // Session for object stores and caching
     session: Arc<lance::session::Session>,
 
-    // Namespace-backed database for child namespace operations (manifest mode).
+    // Namespace-backed database for child namespace operations
     namespace_database: Arc<LanceNamespaceDatabase>,
-
-    // V1 (manifest-disabled) directory namespace for root table lifecycle, so root
-    // drops are soft-deletes and purge/table_status are available. Shares the same root
-    // as `namespace_database` but in directory mode.
-    root_namespace_database: Arc<LanceNamespaceDatabase>,
 }
 
 impl std::fmt::Display for ListingDatabase {
@@ -282,6 +280,7 @@ impl std::fmt::Display for ListingDatabase {
     }
 }
 
+const LANCE_EXTENSION: &str = "lance";
 const ENGINE: &str = "engine";
 const MIRRORED_STORE: &str = "mirroredStore";
 
@@ -343,39 +342,6 @@ impl ListingDatabase {
         ))
     }
 
-    /// Build the V1 (manifest-disabled) directory namespace used for *root* table
-    /// lifecycle ops.
-    ///
-    /// Root tables in a listing database are flat `<name>.lance` directories; soft-delete
-    /// (drop/purge/TTL) is a V1-only mechanism, so root ops go through this namespace.
-    /// Child namespaces are manifest-backed and handled by the separate
-    /// (manifest-enabled) `namespace_database`.
-    async fn connect_root_namespace_database(
-        uri: &str,
-        storage_options: HashMap<String, String>,
-        namespace_client_properties: HashMap<String, String>,
-        read_consistency_interval: Option<std::time::Duration>,
-        session: Arc<lance::session::Session>,
-    ) -> Result<Arc<LanceNamespaceDatabase>> {
-        let mut ns_properties = Self::build_namespace_client_properties(
-            uri,
-            &storage_options,
-            namespace_client_properties,
-        );
-        ns_properties.insert("manifest_enabled".to_string(), "false".to_string());
-        Ok(Arc::new(
-            LanceNamespaceDatabase::connect(
-                "dir",
-                ns_properties,
-                storage_options,
-                read_consistency_interval,
-                Some(session),
-                HashSet::new(),
-            )
-            .await?,
-        ))
-    }
-
     async fn prepare_namespace_root(
         uri: &str,
         storage_options: &HashMap<String, String>,
@@ -582,7 +548,7 @@ impl ListingDatabase {
                     },
                     ..Default::default()
                 };
-                let (object_store, _base_path) = ObjectStore::from_uri_and_params(
+                let (object_store, base_path) = ObjectStore::from_uri_and_params(
                     session.store_registry(),
                     &plain_uri,
                     &os_params,
@@ -611,18 +577,12 @@ impl ListingDatabase {
                     session.clone(),
                 )
                 .await?;
-                let root_namespace_database = Self::connect_root_namespace_database(
-                    &table_base_uri,
-                    options.storage_options.clone(),
-                    request.namespace_client_properties.clone(),
-                    request.read_consistency_interval,
-                    session.clone(),
-                )
-                .await?;
 
                 Ok(Self {
                     uri: table_base_uri,
                     query_string,
+                    base_path,
+                    object_store,
                     store_wrapper: write_store_wrapper,
                     read_consistency_interval: request.read_consistency_interval,
                     storage_options: options.storage_options,
@@ -630,7 +590,6 @@ impl ListingDatabase {
                     new_table_config: options.new_table_config,
                     session,
                     namespace_database,
-                    root_namespace_database,
                 })
             }
             Err(_) => {
@@ -654,7 +613,7 @@ impl ListingDatabase {
         session: Option<Arc<lance::session::Session>>,
     ) -> Result<Self> {
         let session = session.unwrap_or_else(|| Arc::new(lance::session::Session::default()));
-        let (object_store, _base_path) = ObjectStore::from_uri_and_params(
+        let (object_store, base_path) = ObjectStore::from_uri_and_params(
             session.store_registry(),
             path,
             &ObjectStoreParams::default(),
@@ -665,14 +624,6 @@ impl ListingDatabase {
         }
 
         let namespace_database = Self::connect_namespace_database(
-            path,
-            HashMap::new(),
-            namespace_client_properties.clone(),
-            read_consistency_interval,
-            session.clone(),
-        )
-        .await?;
-        let root_namespace_database = Self::connect_root_namespace_database(
             path,
             HashMap::new(),
             namespace_client_properties,
@@ -684,6 +635,8 @@ impl ListingDatabase {
         Ok(Self {
             uri: path.to_string(),
             query_string: None,
+            base_path,
+            object_store,
             store_wrapper: None,
             read_consistency_interval,
             storage_options: HashMap::new(),
@@ -691,7 +644,6 @@ impl ListingDatabase {
             new_table_config,
             session,
             namespace_database,
-            root_namespace_database,
         })
     }
 
@@ -753,10 +705,42 @@ impl ListingDatabase {
         self.namespace_database.clone()
     }
 
-    /// The V1 directory namespace used for root table lifecycle (soft-delete drop, purge,
-    /// table_status, O(1) listing).
-    fn root_namespace_database(&self) -> Arc<LanceNamespaceDatabase> {
-        self.root_namespace_database.clone()
+    async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
+        let object_store_params = ObjectStoreParams {
+            storage_options_accessor: if self.storage_options.is_empty() {
+                None
+            } else {
+                Some(Arc::new(StorageOptionsAccessor::with_static_options(
+                    self.storage_options.clone(),
+                )))
+            },
+            ..Default::default()
+        };
+        let mut uri = self.uri.clone();
+        if let Some(query_string) = &self.query_string {
+            uri.push_str(&format!("?{}", query_string));
+        }
+        let commit_handler = commit_handler_from_url(&uri, &Some(object_store_params)).await?;
+        for name in names {
+            let dir_name = format!("{}.{}", name, LANCE_EXTENSION);
+            let full_path = self.base_path.clone().join(dir_name.clone());
+
+            commit_handler.delete(&full_path).await?;
+
+            self.object_store
+                .remove_dir_all(full_path.clone())
+                .await
+                .map_err(|err| match err {
+                    // this error is not lance::Error::DatasetNotFound, as the method
+                    // `remove_dir_all` may be used to remove something not be a dataset
+                    lance::Error::NotFound { .. } => Error::TableNotFound {
+                        name: name.clone(),
+                        source: Box::new(err),
+                    },
+                    _ => Error::from(err),
+                })?;
+        }
+        Ok(())
     }
 
     /// Inherit storage options from the connection into the target map
@@ -962,43 +946,88 @@ impl Database for ListingDatabase {
         if !request.namespace_path.is_empty() {
             return self.namespace_database().table_names(request).await;
         }
-        // Root tables: the V1 namespace lists them in a single read_dir (O(1) requests)
-        // and excludes soft-deleted tables, instead of a per-table probe here.
-        self.root_namespace_database().table_names(request).await
+        let mut f = self
+            .object_store
+            .read_dir(self.base_path.clone())
+            .await?
+            .iter()
+            .map(Path::new)
+            .filter(|path| {
+                let is_lance = path
+                    .extension()
+                    .and_then(|e| e.to_str())
+                    .map(|e| e == LANCE_EXTENSION);
+                is_lance.unwrap_or(false)
+            })
+            .filter_map(|p| p.file_stem().and_then(|s| s.to_str().map(String::from)))
+            .collect::<Vec<String>>();
+        f.sort();
+        if let Some(start_after) = request.start_after {
+            let index = f
+                .iter()
+                .position(|name| name.as_str() > start_after.as_str())
+                .unwrap_or(f.len());
+            f.drain(0..index);
+        }
+        if let Some(limit) = request.limit {
+            f.truncate(limit as usize);
+        }
+        Ok(f)
     }
 
     async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
         if request.id.as_ref().map(|v| !v.is_empty()).unwrap_or(false) {
             return self.namespace_database().list_tables(request).await;
         }
-        self.root_namespace_database().list_tables(request).await
+        let mut f = self
+            .object_store
+            .read_dir(self.base_path.clone())
+            .await?
+            .iter()
+            .map(Path::new)
+            .filter(|path| {
+                let is_lance = path
+                    .extension()
+                    .and_then(|e| e.to_str())
+                    .map(|e| e == LANCE_EXTENSION);
+                is_lance.unwrap_or(false)
+            })
+            .filter_map(|p| p.file_stem().and_then(|s| s.to_str().map(String::from)))
+            .collect::<Vec<String>>();
+        f.sort();
+
+        // Handle pagination with page_token
+        if let Some(ref page_token) = request.page_token {
+            let index = f
+                .iter()
+                .position(|name| name.as_str() > page_token.as_str())
+                .unwrap_or(f.len());
+            f.drain(0..index);
+        }
+
+        // Determine if there's a next page
+        let next_page_token = if let Some(limit) = request.limit {
+            if f.len() > limit as usize {
+                let token = f[limit as usize].clone();
+                f.truncate(limit as usize);
+                Some(token)
+            } else {
+                None
+            }
+        } else {
+            None
+        };
+
+        Ok(ListTablesResponse {
+            tables: f,
+            page_token: next_page_token,
+        })
     }
 
     async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>> {
         if !request.namespace_path.is_empty() {
             return self.namespace_database().create_table(request).await;
         }
-        let mut request = request;
-        // Re-creating a soft-deleted table is a revive: clear the delete marker (via the
-        // V1 root namespace, under its lifecycle lock so a concurrent purge can't race),
-        // making the table live again, then overwrite its data through the native create
-        // path below (preserving lineage as a new version). A plain native create would
-        // leave the marker in place, keeping the table hidden.
-        if matches!(
-            self.root_namespace_database()
-                .namespace_client()
-                .await?
-                .table_status(Some(vec![request.name.clone()]))
-                .await?,
-            lance_namespace::TableLifecycle::SoftDeleted { .. }
-        ) {
-            self.root_namespace_database()
-                .namespace_client()
-                .await?
-                .undelete_table(Some(vec![request.name.clone()]))
-                .await?;
-            request.mode = CreateTableMode::Overwrite;
-        }
         // Use provided location if available, otherwise derive from table name
         let table_uri = request
             .location
@@ -1117,19 +1146,6 @@ impl Database for ListingDatabase {
         if !request.namespace_path.is_empty() {
             return self.namespace_database().open_table(request).await;
         }
-        // A soft-deleted (dropped-but-not-purged) table must read as absent even though
-        // its data still exists on disk. Consult the V1 root namespace (which owns the
-        // marker); if soft-deleted, route to it so the open surfaces TableNotFound.
-        if matches!(
-            self.root_namespace_database()
-                .namespace_client()
-                .await?
-                .table_status(Some(vec![request.name.clone()]))
-                .await?,
-            lance_namespace::TableLifecycle::SoftDeleted { .. }
-        ) {
-            return self.root_namespace_database().open_table(request).await;
-        }
         // Use provided location if available, otherwise derive from table name
         let table_uri = request
             .location
@@ -1229,23 +1245,20 @@ impl Database for ListingDatabase {
                 .drop_table(name, namespace_path)
                 .await;
         }
-        // Root table: route through the V1 namespace so the drop is a soft-delete (writes
-        // a marker, leaves data for later purge) rather than an immediate remove_dir_all.
-        self.root_namespace_database()
-            .drop_table(name, namespace_path)
-            .await
+        self.drop_tables(vec![name.to_string()]).await
     }
 
+    #[allow(deprecated)]
     async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()> {
+        // Check if namespace parameter is provided
         if !namespace_path.is_empty() {
             return self
                 .namespace_database()
                 .drop_all_tables(namespace_path)
                 .await;
         }
-        self.root_namespace_database()
-            .drop_all_tables(namespace_path)
-            .await
+        let tables = self.table_names(TableNamesRequest::default()).await?;
+        self.drop_tables(tables).await
     }
 
     fn as_any(&self) -> &dyn std::any::Any {
@@ -1253,9 +1266,6 @@ impl Database for ListingDatabase {
     }
 
     async fn namespace_client(&self) -> Result<Arc<dyn lance_namespace::LanceNamespace>> {
-        // Returns the manifest-backed namespace so callers can operate on child
-        // namespaces (multi-level table ids) through the client. Root-table soft-delete
-        // lifecycle (table_status/purge) is reached via the V1 root namespace internally.
         self.namespace_database.namespace_client().await
     }
 
@@ -2605,67 +2615,4 @@ mod tests {
             .unwrap();
         assert!(post_drop.tables.is_empty());
     }
-
-    /// Root-table drop is a soft-delete routed through the V1 namespace: the table is
-    /// hidden from listing/open but its data survives until purged, and re-creating it
-    /// revives it. Verifies the consolidation end-to-end at the ListingDatabase level.
-    #[tokio::test]
-    async fn test_root_table_soft_delete_lifecycle() {
-        let (_tempdir, db) = setup_database().await;
-        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
-        let create = |name: &str| CreateTableRequest {
-            name: name.to_string(),
-            namespace_path: vec![],
-            data: Box::new(RecordBatch::new_empty(schema.clone())) as Box<dyn Scannable>,
-            mode: CreateTableMode::Create,
-            write_options: Default::default(),
-            location: None,
-            namespace_client: None,
-        };
-        let open = |name: &str| OpenTableRequest {
-            name: name.to_string(),
-            namespace_path: vec![],
-            index_cache_size: None,
-            lance_read_params: None,
-            location: None,
-            namespace_client: None,
-            managed_versioning: None,
-        };
-
-        db.create_table(create("t")).await.unwrap();
-        db.drop_table("t", &[]).await.unwrap();
-
-        // Hidden from listing and not openable...
-        #[allow(deprecated)]
-        let names = db.table_names(TableNamesRequest::default()).await.unwrap();
-        assert!(!names.contains(&"t".to_string()));
-        assert!(matches!(
-            db.open_table(open("t")).await,
-            Err(Error::TableNotFound { .. })
-        ));
-
-        // ...but data survives: it shows up as purgable via the V1 root namespace.
-        let root_ns = db
-            .root_namespace_database()
-            .namespace_client()
-            .await
-            .unwrap();
-        let purgable = root_ns.list_purgable_tables(None).await.unwrap();
-        assert_eq!(purgable.len(), 1);
-        assert_eq!(purgable[0].id, vec!["t".to_string()]);
-
-        // Re-creating revives it.
-        db.create_table(create("t")).await.unwrap();
-        db.open_table(open("t")).await.unwrap();
-        #[allow(deprecated)]
-        let names = db.table_names(TableNamesRequest::default()).await.unwrap();
-        assert!(names.contains(&"t".to_string()));
-        assert!(root_ns.list_purgable_tables(None).await.unwrap().is_empty());
-
-        // Drop then purge reclaims it for good.
-        db.drop_table("t", &[]).await.unwrap();
-        let purged = root_ns.purge_tables(None).await.unwrap();
-        assert_eq!(purged, vec![vec!["t".to_string()]]);
-        assert!(root_ns.list_purgable_tables(None).await.unwrap().is_empty());
-    }
 }

rust/lancedb/src/database/namespace.rs

@@ -583,9 +583,9 @@ impl Database for LanceNamespaceDatabase {
         self.namespace
             .drop_table(drop_request)
             .await
-            // Preserve TableNotFound (e.g. dropping a non-existent table) rather than
-            // flattening every failure to a generic Runtime error.
-            .map_err(|e| map_namespace_lance_error(e, name))?;
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to drop table: {}", e),
+            })?;
 
         Ok(())
     }

rust/lancedb/src/remote.rs

@@ -8,6 +8,7 @@
 
 pub(crate) mod client;
 pub(crate) mod db;
+pub mod oauth;
 mod retry;
 pub(crate) mod table;
 pub(crate) mod util;
@@ -20,3 +21,4 @@ const JSON_CONTENT_TYPE: &str = "application/json";
 
 pub use client::{ClientConfig, HeaderProvider, RetryConfig, TimeoutConfig, TlsConfig};
 pub use db::{RemoteDatabaseOptions, RemoteDatabaseOptionsBuilder};
+pub use oauth::{OAuthConfig, OAuthFlow, OAuthHeaderProvider};

rust/lancedb/src/remote/oauth.rs

@@ -0,0 +1,907 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use std::collections::HashMap;
+use std::net::IpAddr;
+use std::sync::Arc;
+use std::time::{Duration, Instant};
+
+use async_trait::async_trait;
+use log::debug;
+use reqwest::Client;
+use serde::Deserialize;
+use tokio::sync::RwLock;
+
+use crate::error::{Error, Result};
+use crate::remote::client::HeaderProvider;
+
+const DEFAULT_REFRESH_BUFFER_SECS: u64 = 300;
+const DEFAULT_TOKEN_TTL_SECS: u64 = 3600;
+const AZURE_IMDS_ENDPOINT: &str = "http://169.254.169.254/metadata/identity/oauth2/token";
+const AZURE_IMDS_API_VERSION: &str = "2018-02-01";
+
+/// OAuth authentication flow configuration.
+#[derive(Debug, Clone)]
+pub enum OAuthFlow {
+    /// Client Credentials grant (service-to-service / M2M).
+    /// Requires `client_secret` in [`OAuthConfig`].
+    ClientCredentials,
+
+    /// Azure Managed Identity via IMDS.
+    /// Works on Azure VMs, AKS, App Service, and Azure Functions.
+    /// IMDS requests bypass proxy settings because the endpoint is link-local.
+    AzureManagedIdentity {
+        /// Client ID for user-assigned managed identity.
+        /// Omit for system-assigned managed identity.
+        client_id: Option<String>,
+    },
+}
+
+/// OAuth configuration for LanceDB authentication.
+///
+/// All token acquisition and refresh is handled in the Rust layer.
+/// Python and TypeScript bindings expose this as a plain config object.
+#[derive(Clone)]
+pub struct OAuthConfig {
+    /// OIDC issuer URL or OAuth authority URL.
+    /// For Azure: `https://login.microsoftonline.com/{tenant_id}/v2.0`
+    pub issuer_url: String,
+
+    /// Application / Client ID.
+    pub client_id: String,
+
+    /// Client secret (required for `ClientCredentials`, optional for others).
+    pub client_secret: Option<String>,
+
+    /// OAuth scopes to request.
+    /// For Azure managed identity, exactly one scope or resource is required.
+    /// For example: `["api://{app_id}/.default"]`
+    pub scopes: Vec<String>,
+
+    /// Authentication flow to use.
+    pub flow: OAuthFlow,
+
+    /// Seconds before token expiry to trigger proactive refresh (default: 300).
+    /// Keep this well below the token TTL; if it is greater than or equal to
+    /// the TTL, each request refreshes the token.
+    pub refresh_buffer_secs: Option<u64>,
+}
+
+impl std::fmt::Debug for OAuthConfig {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("OAuthConfig")
+            .field("issuer_url", &self.issuer_url)
+            .field("client_id", &self.client_id)
+            .field(
+                "client_secret",
+                &self.client_secret.as_deref().map(|_| "<redacted>"),
+            )
+            .field("scopes", &self.scopes)
+            .field("flow", &self.flow)
+            .field("refresh_buffer_secs", &self.refresh_buffer_secs)
+            .finish()
+    }
+}
+
+// -- OIDC Discovery --
+
+#[derive(Clone, Debug, Deserialize)]
+struct OidcDiscovery {
+    token_endpoint: String,
+}
+
+// -- Token Response --
+
+#[derive(Deserialize)]
+struct TokenResponse {
+    access_token: String,
+    /// Token lifetime in seconds.
+    /// Some providers (Azure IMDS) return this as a string, so we accept both.
+    #[serde(default, deserialize_with = "deserialize_optional_u64_or_string")]
+    expires_in: Option<u64>,
+    #[serde(default)]
+    #[allow(dead_code)]
+    token_type: Option<String>,
+}
+
+impl std::fmt::Debug for TokenResponse {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("TokenResponse")
+            .field("access_token", &"<redacted>")
+            .field("expires_in", &self.expires_in)
+            .field("token_type", &self.token_type)
+            .finish()
+    }
+}
+
+fn deserialize_optional_u64_or_string<'de, D>(
+    deserializer: D,
+) -> std::result::Result<Option<u64>, D::Error>
+where
+    D: serde::Deserializer<'de>,
+{
+    use serde::de;
+
+    struct U64OrString;
+    impl<'de> de::Visitor<'de> for U64OrString {
+        type Value = Option<u64>;
+
+        fn expecting(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
+            formatter.write_str("an integer, an integer-valued float, a numeric string, or null")
+        }
+
+        fn visit_u64<E: de::Error>(self, v: u64) -> std::result::Result<Self::Value, E> {
+            Ok(Some(v))
+        }
+
+        fn visit_i64<E: de::Error>(self, v: i64) -> std::result::Result<Self::Value, E> {
+            if v < 0 {
+                return Err(E::custom(format!("invalid expires_in value: {v}")));
+            }
+            Ok(Some(v as u64))
+        }
+
+        fn visit_f64<E: de::Error>(self, v: f64) -> std::result::Result<Self::Value, E> {
+            if !v.is_finite() || v < 0.0 || v.fract() != 0.0 || v > u64::MAX as f64 {
+                return Err(E::custom(format!("invalid expires_in value: {v}")));
+            }
+            Ok(Some(v as u64))
+        }
+
+        fn visit_str<E: de::Error>(self, v: &str) -> std::result::Result<Self::Value, E> {
+            v.parse::<u64>().map(Some).map_err(de::Error::custom)
+        }
+
+        fn visit_none<E: de::Error>(self) -> std::result::Result<Self::Value, E> {
+            Ok(None)
+        }
+
+        fn visit_unit<E: de::Error>(self) -> std::result::Result<Self::Value, E> {
+            Ok(None)
+        }
+    }
+
+    deserializer.deserialize_any(U64OrString)
+}
+
+// -- Internal Token State --
+
+struct TokenState {
+    access_token: Option<String>,
+    expires_at: Option<Instant>,
+}
+
+impl TokenState {
+    fn new() -> Self {
+        Self {
+            access_token: None,
+            expires_at: None,
+        }
+    }
+
+    fn is_expired(&self, buffer: Duration) -> bool {
+        match (self.access_token.as_ref(), self.expires_at) {
+            (Some(_), Some(expires_at)) => Instant::now() + buffer >= expires_at,
+            (None, _) => true,
+            (Some(_), None) => true,
+        }
+    }
+
+    fn update(&mut self, resp: &TokenResponse) {
+        self.access_token = Some(resp.access_token.clone());
+        let expires_in = resp.expires_in.unwrap_or(DEFAULT_TOKEN_TTL_SECS);
+        self.expires_at = Some(Instant::now() + Duration::from_secs(expires_in));
+    }
+}
+
+#[async_trait]
+trait TokenSource: Send + Sync + std::fmt::Debug {
+    async fn fetch_token(&self) -> Result<TokenResponse>;
+}
+
+struct ClientCredentialsSource {
+    issuer_url: String,
+    client_id: String,
+    client_secret: String,
+    scopes: Vec<String>,
+    http_client: Client,
+    discovery: RwLock<Option<OidcDiscovery>>,
+}
+
+impl std::fmt::Debug for ClientCredentialsSource {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("ClientCredentialsSource")
+            .field("issuer_url", &self.issuer_url)
+            .field("client_id", &self.client_id)
+            .field("client_secret", &"<redacted>")
+            .field("scopes", &self.scopes)
+            .finish()
+    }
+}
+
+impl ClientCredentialsSource {
+    fn new(
+        issuer_url: String,
+        client_id: String,
+        client_secret: Option<String>,
+        scopes: Vec<String>,
+    ) -> Result<Self> {
+        let client_secret = client_secret.ok_or(Error::InvalidInput {
+            message: "client_secret is required for ClientCredentials flow".to_string(),
+        })?;
+        Self::validate_issuer_transport(&issuer_url)?;
+
+        let http_client = Client::builder()
+            .timeout(Duration::from_secs(30))
+            .build()
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to create HTTP client for OAuth: {e}"),
+            })?;
+
+        Ok(Self {
+            issuer_url,
+            client_id,
+            client_secret,
+            scopes,
+            http_client,
+            discovery: RwLock::new(None),
+        })
+    }
+
+    fn validate_issuer_transport(issuer_url: &str) -> Result<()> {
+        let issuer = url::Url::parse(issuer_url).map_err(|e| Error::InvalidInput {
+            message: format!("Invalid OAuth issuer_url: {e}"),
+        })?;
+
+        match issuer.scheme() {
+            "https" => Ok(()),
+            "http" if Self::is_loopback_issuer(&issuer) => Ok(()),
+            _ => Err(Error::InvalidInput {
+                message:
+                    "ClientCredentials OAuth issuer_url must use https, except for loopback hosts"
+                        .to_string(),
+            }),
+        }
+    }
+
+    fn is_loopback_issuer(issuer: &url::Url) -> bool {
+        let Some(host) = issuer.host_str() else {
+            return false;
+        };
+
+        host.eq_ignore_ascii_case("localhost")
+            || host
+                .parse::<IpAddr>()
+                .map(|addr| addr.is_loopback())
+                .unwrap_or(false)
+    }
+
+    async fn get_discovery(&self) -> Result<OidcDiscovery> {
+        {
+            let cached = self.discovery.read().await;
+            if let Some(ref disc) = *cached {
+                return Ok(disc.clone());
+            }
+        }
+
+        let mut cache = self.discovery.write().await;
+        // Double-check
+        if let Some(ref disc) = *cache {
+            return Ok(disc.clone());
+        }
+
+        let discovery_url = format!(
+            "{}/.well-known/openid-configuration",
+            self.issuer_url.trim_end_matches('/')
+        );
+
+        debug!("Fetching OIDC discovery from {}", discovery_url);
+
+        let resp = self
+            .http_client
+            .get(&discovery_url)
+            .send()
+            .await
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to fetch OIDC discovery document: {e}"),
+            })?;
+
+        if !resp.status().is_success() {
+            return Err(Error::Runtime {
+                message: format!(
+                    "OIDC discovery failed with status {}: {}",
+                    resp.status(),
+                    resp.text().await.unwrap_or_default()
+                ),
+            });
+        }
+
+        let disc: OidcDiscovery = resp.json().await.map_err(|e| Error::Runtime {
+            message: format!("Failed to parse OIDC discovery document: {e}"),
+        })?;
+
+        let result = disc.clone();
+
+        *cache = Some(disc);
+        Ok(result)
+    }
+
+    async fn get_token_endpoint(&self) -> Result<String> {
+        self.get_discovery().await.map(|disc| disc.token_endpoint)
+    }
+
+    fn scopes_string(&self) -> String {
+        self.scopes.join(" ")
+    }
+
+    async fn post_token_request(
+        &self,
+        endpoint: &str,
+        params: &[(&str, &str)],
+    ) -> Result<TokenResponse> {
+        let resp = self
+            .http_client
+            .post(endpoint)
+            .form(params)
+            .send()
+            .await
+            .map_err(|e| Error::Runtime {
+                message: format!("Token request to {endpoint} failed: {e}"),
+            })?;
+
+        if !resp.status().is_success() {
+            return Err(Error::Runtime {
+                message: format!(
+                    "Token request failed with status {}: {}",
+                    resp.status(),
+                    resp.text().await.unwrap_or_default()
+                ),
+            });
+        }
+
+        resp.json().await.map_err(|e| Error::Runtime {
+            message: format!("Failed to parse token response: {e}"),
+        })
+    }
+}
+
+#[async_trait]
+impl TokenSource for ClientCredentialsSource {
+    async fn fetch_token(&self) -> Result<TokenResponse> {
+        let token_endpoint = self.get_token_endpoint().await?;
+        let scope = self.scopes_string();
+        let params = [
+            ("grant_type", "client_credentials"),
+            ("client_id", self.client_id.as_str()),
+            ("client_secret", self.client_secret.as_str()),
+            ("scope", scope.as_str()),
+        ];
+
+        self.post_token_request(&token_endpoint, &params).await
+    }
+}
+
+struct AzureImdsSource {
+    client_id: Option<String>,
+    resource: String,
+    http_client: Client,
+}
+
+impl std::fmt::Debug for AzureImdsSource {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("AzureImdsSource")
+            .field("client_id", &self.client_id)
+            .field("resource", &self.resource)
+            .finish()
+    }
+}
+
+impl AzureImdsSource {
+    fn new(scopes: Vec<String>, client_id: Option<String>) -> Result<Self> {
+        let resource = Self::resource_from_scopes(&scopes)?;
+        let http_client = Client::builder()
+            .timeout(Duration::from_secs(30))
+            .no_proxy()
+            .build()
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to create HTTP client for Azure IMDS OAuth: {e}"),
+            })?;
+
+        Ok(Self {
+            client_id,
+            resource,
+            http_client,
+        })
+    }
+
+    fn resource_from_scopes(scopes: &[String]) -> Result<String> {
+        let [scope] = scopes else {
+            return Err(Error::InvalidInput {
+                message: "AzureManagedIdentity flow requires exactly one OAuth scope or resource"
+                    .to_string(),
+            });
+        };
+
+        Ok(scope.strip_suffix("/.default").unwrap_or(scope).to_string())
+    }
+}
+
+#[async_trait]
+impl TokenSource for AzureImdsSource {
+    async fn fetch_token(&self) -> Result<TokenResponse> {
+        let mut url = format!(
+            "{AZURE_IMDS_ENDPOINT}?api-version={AZURE_IMDS_API_VERSION}&resource={}",
+            urlencoding::encode(&self.resource),
+        );
+        if let Some(cid) = self.client_id.as_deref() {
+            url.push_str(&format!("&client_id={}", urlencoding::encode(cid)));
+        }
+
+        let resp = self
+            .http_client
+            .get(&url)
+            .header("Metadata", "true")
+            .send()
+            .await
+            .map_err(|e| Error::Runtime {
+                message: format!("Azure IMDS request failed: {e}"),
+            })?;
+
+        if !resp.status().is_success() {
+            return Err(Error::Runtime {
+                message: format!(
+                    "Azure IMDS returned status {}: {}",
+                    resp.status(),
+                    resp.text().await.unwrap_or_default()
+                ),
+            });
+        }
+
+        resp.json().await.map_err(|e| Error::Runtime {
+            message: format!("Failed to parse IMDS token response: {e}"),
+        })
+    }
+}
+
+/// OAuth header provider that manages the full token lifecycle.
+///
+/// Implements [`HeaderProvider`] to inject `Authorization: Bearer <token>`
+/// headers into every LanceDB request, with automatic token refresh.
+pub struct OAuthHeaderProvider {
+    token_source: Box<dyn TokenSource>,
+    token_state: Arc<RwLock<TokenState>>,
+    refresh_buffer: Duration,
+}
+
+impl std::fmt::Debug for OAuthHeaderProvider {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("OAuthHeaderProvider")
+            .field("token_source", &self.token_source)
+            .finish()
+    }
+}
+
+impl OAuthHeaderProvider {
+    /// Create a new OAuth header provider from configuration.
+    pub fn new(config: OAuthConfig) -> Result<Self> {
+        let OAuthConfig {
+            issuer_url,
+            client_id,
+            client_secret,
+            scopes,
+            flow,
+            refresh_buffer_secs,
+        } = config;
+
+        if scopes.is_empty() {
+            return Err(Error::InvalidInput {
+                message: "At least one OAuth scope is required".to_string(),
+            });
+        }
+
+        let refresh_buffer =
+            Duration::from_secs(refresh_buffer_secs.unwrap_or(DEFAULT_REFRESH_BUFFER_SECS));
+        let token_source: Box<dyn TokenSource> = match flow {
+            OAuthFlow::ClientCredentials => Box::new(ClientCredentialsSource::new(
+                issuer_url,
+                client_id,
+                client_secret,
+                scopes,
+            )?),
+            OAuthFlow::AzureManagedIdentity { client_id } => {
+                Box::new(AzureImdsSource::new(scopes, client_id)?)
+            }
+        };
+
+        Ok(Self {
+            token_source,
+            token_state: Arc::new(RwLock::new(TokenState::new())),
+            refresh_buffer,
+        })
+    }
+
+    /// Get a valid access token, refreshing if necessary.
+    async fn get_valid_token(&self) -> Result<String> {
+        // Fast path: check if current token is still valid
+        {
+            let state = self.token_state.read().await;
+            if !state.is_expired(self.refresh_buffer)
+                && let Some(ref token) = state.access_token
+            {
+                return Ok(token.clone());
+            }
+        }
+
+        // Slow path: acquire or refresh token
+        let mut state = self.token_state.write().await;
+
+        // Double-check after acquiring write lock
+        if !state.is_expired(self.refresh_buffer)
+            && let Some(ref token) = state.access_token
+        {
+            return Ok(token.clone());
+        }
+
+        debug!("Acquiring new OAuth token via {:?}", self.token_source);
+        let resp = self.token_source.fetch_token().await?;
+
+        state.update(&resp);
+        Ok(resp.access_token)
+    }
+}
+
+#[async_trait]
+impl HeaderProvider for OAuthHeaderProvider {
+    async fn get_headers(&self) -> Result<HashMap<String, String>> {
+        let token = self.get_valid_token().await?;
+        Ok(HashMap::from([(
+            "authorization".to_string(),
+            format!("Bearer {token}"),
+        )]))
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::sync::atomic::{AtomicUsize, Ordering};
+
+    use tokio::io::{AsyncReadExt, AsyncWriteExt};
+    use tokio::net::{TcpListener, TcpStream};
+    use tokio::task::JoinHandle;
+
+    #[test]
+    fn test_token_state_expiry() {
+        let mut state = TokenState::new();
+        assert!(state.is_expired(Duration::from_secs(0)));
+
+        state.access_token = Some("tok".to_string());
+        state.expires_at = Some(Instant::now() + Duration::from_secs(600));
+        assert!(!state.is_expired(Duration::from_secs(300)));
+        assert!(state.is_expired(Duration::from_secs(601)));
+
+        state.expires_at = None;
+        assert!(state.is_expired(Duration::from_secs(0)));
+    }
+
+    #[test]
+    fn test_token_state_uses_default_expiry() {
+        let mut state = TokenState::new();
+        let response = TokenResponse {
+            access_token: "tok".to_string(),
+            expires_in: None,
+            token_type: None,
+        };
+
+        state.update(&response);
+
+        assert!(!state.is_expired(Duration::from_secs(DEFAULT_TOKEN_TTL_SECS - 1)));
+        assert!(state.is_expired(Duration::from_secs(DEFAULT_TOKEN_TTL_SECS + 1)));
+    }
+
+    #[test]
+    fn test_token_response_accepts_float_expires_in() {
+        let response: TokenResponse =
+            serde_json::from_str(r#"{"access_token":"tok","expires_in":3600.0}"#).unwrap();
+
+        assert_eq!(response.expires_in, Some(3600));
+    }
+
+    #[test]
+    fn test_token_response_rejects_negative_expires_in() {
+        let err =
+            serde_json::from_str::<TokenResponse>(r#"{"access_token":"tok","expires_in":-1}"#)
+                .unwrap_err();
+
+        assert!(err.to_string().contains("invalid expires_in value: -1"));
+    }
+
+    #[test]
+    fn test_token_response_debug_redacts_access_token() {
+        let response = TokenResponse {
+            access_token: "secret-token".to_string(),
+            expires_in: Some(3600),
+            token_type: Some("Bearer".to_string()),
+        };
+
+        let debug = format!("{response:?}");
+        assert!(!debug.contains("secret-token"));
+        assert!(debug.contains("access_token: \"<redacted>\""));
+    }
+
+    #[test]
+    fn test_scopes_string() {
+        let source = ClientCredentialsSource::new(
+            "https://login.microsoftonline.com/tenant/v2.0".to_string(),
+            "app-id".to_string(),
+            Some("secret".to_string()),
+            vec!["scope1".to_string(), "scope2".to_string()],
+        )
+        .unwrap();
+
+        assert_eq!(source.scopes_string(), "scope1 scope2");
+    }
+
+    #[test]
+    fn test_oauth_config_debug_redacts_client_secret() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            client_secret: Some("super-secret".to_string()),
+            scopes: vec!["scope".to_string()],
+            flow: OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: None,
+        };
+
+        let debug = format!("{config:?}");
+        assert!(!debug.contains("super-secret"));
+        assert!(debug.contains("client_secret: Some(\"<redacted>\")"));
+    }
+
+    #[test]
+    fn test_oauth_header_provider_debug_redacts_client_secret() {
+        let config = OAuthConfig {
+            issuer_url: "https://issuer.example.com".to_string(),
+            client_id: "client-id".to_string(),
+            client_secret: Some("super-secret".to_string()),
+            scopes: vec!["scope".to_string()],
+            flow: OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: None,
+        };
+
+        let provider = OAuthHeaderProvider::new(config).unwrap();
+        let debug = format!("{provider:?}");
+        assert!(!debug.contains("super-secret"));
+        assert!(debug.contains("client_secret: \"<redacted>\""));
+    }
+
+    #[test]
+    fn test_managed_identity_resource_from_default_scope() {
+        assert_eq!(
+            AzureImdsSource::resource_from_scopes(&["api://test/.default".to_string()]).unwrap(),
+            "api://test"
+        );
+    }
+
+    #[test]
+    fn test_managed_identity_resource_without_default_suffix() {
+        assert_eq!(
+            AzureImdsSource::resource_from_scopes(&["api://test".to_string()]).unwrap(),
+            "api://test"
+        );
+    }
+
+    #[test]
+    fn test_managed_identity_rejects_multiple_scopes() {
+        let config = OAuthConfig {
+            issuer_url: "https://login.microsoftonline.com/tenant/v2.0".to_string(),
+            client_id: "app-id".to_string(),
+            client_secret: None,
+            scopes: vec![
+                "api://test-a/.default".to_string(),
+                "api://test-b/.default".to_string(),
+            ],
+            flow: OAuthFlow::AzureManagedIdentity { client_id: None },
+            refresh_buffer_secs: None,
+        };
+        assert!(OAuthHeaderProvider::new(config).is_err());
+    }
+
+    #[tokio::test]
+    async fn test_token_endpoint_requires_discovery_success() {
+        let (issuer_url, server) = spawn_discovery_error_server().await;
+        let source = ClientCredentialsSource::new(
+            issuer_url,
+            "client-id".to_string(),
+            Some("secret".to_string()),
+            vec!["scope".to_string()],
+        )
+        .unwrap();
+
+        let err = source.get_token_endpoint().await.unwrap_err();
+        assert!(matches!(
+            err,
+            Error::Runtime { message }
+                if message.contains("OIDC discovery failed with status 503")
+        ));
+        server.await.unwrap();
+    }
+
+    #[test]
+    fn test_client_credentials_requires_secret() {
+        let config = OAuthConfig {
+            issuer_url: "https://login.microsoftonline.com/tenant/v2.0".to_string(),
+            client_id: "app-id".to_string(),
+            client_secret: None,
+            scopes: vec!["scope".to_string()],
+            flow: OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: None,
+        };
+        assert!(OAuthHeaderProvider::new(config).is_err());
+    }
+
+    #[test]
+    fn test_client_credentials_rejects_insecure_non_loopback_issuer() {
+        let config = OAuthConfig {
+            issuer_url: "http://issuer.example.com".to_string(),
+            client_id: "app-id".to_string(),
+            client_secret: Some("secret".to_string()),
+            scopes: vec!["scope".to_string()],
+            flow: OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: None,
+        };
+
+        let err = OAuthHeaderProvider::new(config).unwrap_err();
+        assert!(matches!(
+            err,
+            Error::InvalidInput { message }
+                if message == "ClientCredentials OAuth issuer_url must use https, except for loopback hosts"
+        ));
+    }
+
+    #[test]
+    fn test_empty_scopes_rejected() {
+        let config = OAuthConfig {
+            issuer_url: "https://login.microsoftonline.com/tenant/v2.0".to_string(),
+            client_id: "app-id".to_string(),
+            client_secret: None,
+            scopes: vec![],
+            flow: OAuthFlow::AzureManagedIdentity { client_id: None },
+            refresh_buffer_secs: None,
+        };
+        assert!(OAuthHeaderProvider::new(config).is_err());
+    }
+
+    #[tokio::test]
+    async fn test_client_credentials_token_lifecycle() {
+        let (issuer_url, token_requests, server) = spawn_oauth_server().await;
+        let config = OAuthConfig {
+            issuer_url,
+            client_id: "client-id".to_string(),
+            client_secret: Some("secret".to_string()),
+            scopes: vec!["scope".to_string()],
+            flow: OAuthFlow::ClientCredentials,
+            refresh_buffer_secs: Some(0),
+        };
+        let provider = OAuthHeaderProvider::new(config).unwrap();
+
+        let headers = provider.get_headers().await.unwrap();
+        assert_eq!(headers.get("authorization").unwrap(), "Bearer token-1");
+        assert_eq!(token_requests.load(Ordering::SeqCst), 1);
+
+        let headers = provider.get_headers().await.unwrap();
+        assert_eq!(headers.get("authorization").unwrap(), "Bearer token-1");
+        assert_eq!(token_requests.load(Ordering::SeqCst), 1);
+
+        provider.token_state.write().await.expires_at =
+            Some(Instant::now() - Duration::from_secs(1));
+
+        let headers = provider.get_headers().await.unwrap();
+        assert_eq!(headers.get("authorization").unwrap(), "Bearer token-2");
+        assert_eq!(token_requests.load(Ordering::SeqCst), 2);
+
+        server.await.unwrap();
+    }
+
+    async fn spawn_oauth_server() -> (String, Arc<AtomicUsize>, JoinHandle<()>) {
+        let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+        let addr = listener.local_addr().unwrap();
+        let issuer_url = format!("http://{addr}");
+        let token_requests = Arc::new(AtomicUsize::new(0));
+        let server_token_requests = Arc::clone(&token_requests);
+
+        let server = tokio::spawn(async move {
+            for _ in 0..3 {
+                let (mut stream, _) = listener.accept().await.unwrap();
+                let (request_line, body) = read_http_request(&mut stream).await;
+
+                if request_line.starts_with("GET /.well-known/openid-configuration ") {
+                    let discovery = format!(r#"{{"token_endpoint":"http://{addr}/token"}}"#);
+                    write_json_response(&mut stream, "200 OK", &discovery).await;
+                } else if request_line.starts_with("POST /token ") {
+                    assert!(body.contains("grant_type=client_credentials"));
+                    assert!(body.contains("client_id=client-id"));
+                    assert!(body.contains("client_secret=secret"));
+                    assert!(body.contains("scope=scope"));
+
+                    let token_num = server_token_requests.fetch_add(1, Ordering::SeqCst) + 1;
+                    let token = format!(
+                        r#"{{"access_token":"token-{token_num}","expires_in":3600,"token_type":"Bearer"}}"#
+                    );
+                    write_json_response(&mut stream, "200 OK", &token).await;
+                } else {
+                    write_json_response(&mut stream, "404 Not Found", "{}").await;
+                }
+            }
+        });
+
+        (issuer_url, token_requests, server)
+    }
+
+    async fn spawn_discovery_error_server() -> (String, JoinHandle<()>) {
+        let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+        let addr = listener.local_addr().unwrap();
+        let issuer_url = format!("http://{addr}");
+
+        let server = tokio::spawn(async move {
+            let (mut stream, _) = listener.accept().await.unwrap();
+            let (request_line, _) = read_http_request(&mut stream).await;
+            assert!(request_line.starts_with("GET /.well-known/openid-configuration "));
+            write_json_response(&mut stream, "503 Service Unavailable", "{}").await;
+        });
+
+        (issuer_url, server)
+    }
+
+    async fn read_http_request(stream: &mut TcpStream) -> (String, String) {
+        let mut buffer = Vec::new();
+        let mut header_end = None;
+
+        while header_end.is_none() {
+            let mut chunk = [0; 1024];
+            let read = stream.read(&mut chunk).await.unwrap();
+            assert_ne!(read, 0, "connection closed before request headers");
+            buffer.extend_from_slice(&chunk[..read]);
+            header_end = find_subsequence(&buffer, b"\r\n\r\n").map(|pos| pos + 4);
+        }
+
+        let header_end = header_end.unwrap();
+        let headers = String::from_utf8_lossy(&buffer[..header_end]).to_string();
+        let request_line = headers.lines().next().unwrap_or_default().to_string();
+        let content_length = headers
+            .lines()
+            .find_map(|line| {
+                let (name, value) = line.split_once(':')?;
+                name.eq_ignore_ascii_case("content-length")
+                    .then(|| value.trim().parse::<usize>().ok())
+                    .flatten()
+            })
+            .unwrap_or(0);
+
+        while buffer.len() < header_end + content_length {
+            let mut chunk = [0; 1024];
+            let read = stream.read(&mut chunk).await.unwrap();
+            assert_ne!(read, 0, "connection closed before request body");
+            buffer.extend_from_slice(&chunk[..read]);
+        }
+
+        let body =
+            String::from_utf8_lossy(&buffer[header_end..header_end + content_length]).to_string();
+
+        (request_line, body)
+    }
+
+    fn find_subsequence(haystack: &[u8], needle: &[u8]) -> Option<usize> {
+        haystack
+            .windows(needle.len())
+            .position(|window| window == needle)
+    }
+
+    async fn write_json_response(stream: &mut TcpStream, status: &str, body: &str) {
+        let response = format!(
+            "HTTP/1.1 {status}\r\ncontent-type: application/json\r\ncontent-length: {}\r\nconnection: close\r\n\r\n{body}",
+            body.len()
+        );
+        stream.write_all(response.as_bytes()).await.unwrap();
+    }
+}

rust/lancedb/src/remote/table.rs

@@ -70,18 +70,29 @@ use tokio::sync::RwLock;
 const REQUEST_TIMEOUT_HEADER: HeaderName = HeaderName::from_static("x-request-timeout-ms");
 const MIN_VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-version");
 const MIN_TIMESTAMP_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-timestamp");
+const MIN_READ_VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-min-read-version");
+const VERSION_HEADER: HeaderName = HeaderName::from_static("x-lancedb-version");
 const METRIC_TYPE_KEY: &str = "metric_type";
 const INDEX_TYPE_KEY: &str = "index_type";
 const SCHEMA_CACHE_TTL: Duration = Duration::from_secs(30);
 const SCHEMA_CACHE_REFRESH_WINDOW: Duration = Duration::from_secs(5);
 
-/// Per-table state driving the freshness headers (`x-lancedb-min-version` and
-/// `x-lancedb-min-timestamp`) sent on read requests.
+/// Per-table state driving the freshness headers (`x-lancedb-min-version`,
+/// `x-lancedb-min-timestamp`, and `x-lancedb-min-read-version`) sent on read
+/// requests.
 #[derive(Debug, Default, Clone, Copy)]
 struct FreshnessState {
     /// Provides read-your-write within a single handle: writes that return a
     /// version update this, and reads send it as `x-lancedb-min-version`.
     min_version: Option<u64>,
+    /// Highest dataset version observed in a *read* response on this handle.
+    /// Reads send it as `x-lancedb-min-read-version` so a load-balanced query
+    /// node whose cache is behind this version must refresh before serving,
+    /// giving monotonic reads across nodes regardless of which one the load
+    /// balancer routes to. Sourced only from reads (always committed dataset
+    /// versions), never from writes (which may return WAL entry ids), so it is
+    /// unaffected by the WAL/version mismatch that retired `min_version`.
+    min_read_version: Option<u64>,
     /// Wall-clock time captured at the last [`BaseTable::checkout_latest`]
     /// call. Subsequent reads send
     /// `max(baseline, now - read_consistency_interval)` as
@@ -102,6 +113,7 @@ struct FreshnessState {
 struct FreshnessHeaders {
     min_version: Option<u64>,
     min_timestamp: Option<SystemTime>,
+    min_read_version: Option<u64>,
 }
 
 impl FreshnessHeaders {
@@ -113,6 +125,9 @@ impl FreshnessHeaders {
             let dt: chrono::DateTime<chrono::Utc> = ts.into();
             request = request.header(MIN_TIMESTAMP_HEADER, dt.to_rfc3339());
         }
+        if let Some(v) = self.min_read_version {
+            request = request.header(MIN_READ_VERSION_HEADER, v.to_string());
+        }
         request
     }
 }
@@ -884,6 +899,7 @@ impl<S: HttpSend> RemoteTable<S> {
                 self.client.read_consistency_interval,
                 SystemTime::now(),
             ),
+            min_read_version: state.min_read_version,
         }
     }
 
@@ -905,6 +921,30 @@ impl<S: HttpSend> RemoteTable<S> {
         state.min_version = Some(state.min_version.map_or(version, |v| v.max(version)));
     }
 
+    /// Record a dataset version observed in a *read* response so subsequent
+    /// reads request at least this version via `x-lancedb-min-read-version`,
+    /// giving monotonic reads across load-balanced query nodes. A returned `0`
+    /// (or absent header from an old server) is ignored.
+    fn track_read_version(&self, version: u64) {
+        if version == 0 {
+            return;
+        }
+        let mut state = self.freshness.lock().unwrap();
+        state.min_read_version = Some(state.min_read_version.map_or(version, |v| v.max(version)));
+    }
+
+    /// Parse the `x-lancedb-version` response header (the dataset version a read
+    /// reflects) and fold it into the read-version watermark.
+    fn track_read_version_from_headers(&self, headers: &reqwest::header::HeaderMap) {
+        if let Some(version) = headers
+            .get(&VERSION_HEADER)
+            .and_then(|value| value.to_str().ok())
+            .and_then(|value| value.parse::<u64>().ok())
+        {
+            self.track_read_version(version);
+        }
+    }
+
     async fn execute_query(
         &self,
         query: &AnyQuery,
@@ -928,6 +968,7 @@ impl<S: HttpSend> RemoteTable<S> {
 
         let futures = requests.into_iter().map(|req| async move {
             let (request_id, response) = self.send(req, true).await?;
+            self.track_read_version_from_headers(response.headers());
             self.read_arrow_stream(&request_id, response).await
         });
         let streams = futures::future::try_join_all(futures);
@@ -1545,11 +1586,12 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         *write_guard = None;
         drop(write_guard);
 
-        // Drop any per-handle write tracking; subsequent reads use the
+        // Drop any per-handle read/write tracking; subsequent reads use the
         // baseline timestamp captured now to guarantee freshness.
         *self.freshness.lock().unwrap() = FreshnessState {
             min_version: None,
             checkout_baseline: Some(SystemTime::now()),
+            min_read_version: None,
         };
 
         // Invalidate schema cache since we're switching versions
@@ -1805,6 +1847,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
             }
         };
 
+        self.track_read_version_from_headers(response.headers());
         let body = response.text().await.err_to_http(request_id.clone())?;
 
         serde_json::from_str(&body).map_err(|e| Error::Http {
@@ -7124,6 +7167,7 @@ mod tests {
         let state = FreshnessState {
             min_version: None,
             checkout_baseline: Some(baseline),
+            min_read_version: None,
         };
         assert_eq!(compute_min_timestamp(&state, None, now), Some(baseline));
 
@@ -7148,6 +7192,7 @@ mod tests {
         let state = FreshnessState {
             min_version: None,
             checkout_baseline: Some(baseline),
+            min_read_version: None,
         };
         assert_eq!(
             compute_min_timestamp(&state, Some(Duration::from_secs(10)), now),
@@ -7159,6 +7204,7 @@ mod tests {
         let state = FreshnessState {
             min_version: None,
             checkout_baseline: Some(recent_baseline),
+            min_read_version: None,
         };
         assert_eq!(
             compute_min_timestamp(&state, Some(Duration::from_secs(60)), now),
@@ -7303,6 +7349,106 @@ mod tests {
         );
     }
 
+    /// A handler that records every request's headers and answers each read with
+    /// an `x-lancedb-version` response header taken from `versions` (by call
+    /// index, saturating at the last entry). An empty string means "no header".
+    fn read_version_handler(
+        versions: &'static [&'static str],
+    ) -> (
+        impl Fn(reqwest::Request) -> http::Response<String> + Clone + Send + Sync + 'static,
+        Arc<std::sync::Mutex<Vec<http::HeaderMap>>>,
+    ) {
+        let requests = Arc::new(std::sync::Mutex::new(Vec::new()));
+        let requests_c = requests.clone();
+        let call = Arc::new(AtomicUsize::new(0));
+        let handler = move |request: reqwest::Request| {
+            requests_c.lock().unwrap().push(request.headers().clone());
+            let i = call.fetch_add(1, Ordering::SeqCst).min(versions.len() - 1);
+            let mut builder = http::Response::builder().status(200);
+            if !versions[i].is_empty() {
+                builder = builder.header("x-lancedb-version", versions[i]);
+            }
+            builder.body("42".to_string()).unwrap()
+        };
+        (handler, requests)
+    }
+
+    #[tokio::test]
+    async fn test_read_version_watermark_tracked_and_sent() {
+        let (handler, requests) = read_version_handler(&["100", "100"]);
+        let table = Table::new_with_handler("my_table", handler);
+
+        // First read has no watermark yet; the response advertises version 100,
+        // so the second read must floor the server at 100.
+        table.count_rows(None).await.unwrap();
+        table.count_rows(None).await.unwrap();
+
+        let reqs = requests.lock().unwrap();
+        assert!(!reqs[0].contains_key("x-lancedb-min-read-version"));
+        assert_eq!(
+            reqs[1]
+                .get("x-lancedb-min-read-version")
+                .unwrap()
+                .to_str()
+                .unwrap(),
+            "100"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_read_version_watermark_keeps_max() {
+        // Server reports 100 then a stale 50; the watermark must not regress.
+        let (handler, requests) = read_version_handler(&["100", "50", "50"]);
+        let table = Table::new_with_handler("my_table", handler);
+
+        table.count_rows(None).await.unwrap();
+        table.count_rows(None).await.unwrap();
+        table.count_rows(None).await.unwrap();
+
+        let reqs = requests.lock().unwrap();
+        assert_eq!(
+            reqs[2]
+                .get("x-lancedb-min-read-version")
+                .unwrap()
+                .to_str()
+                .unwrap(),
+            "100"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_read_version_absent_header_no_watermark() {
+        // An old server that doesn't return the version header leaves the
+        // watermark unset, preserving backward compatibility.
+        let (handler, requests) = read_version_handler(&[""]);
+        let table = Table::new_with_handler("my_table", handler);
+
+        table.count_rows(None).await.unwrap();
+        table.count_rows(None).await.unwrap();
+
+        let reqs = requests.lock().unwrap();
+        assert!(!reqs[1].contains_key("x-lancedb-min-read-version"));
+    }
+
+    #[tokio::test]
+    async fn test_read_version_watermark_reset_on_checkout_latest() {
+        let (handler, requests) = read_version_handler(&["100", "100"]);
+        let table = Table::new_with_handler("my_table", handler);
+
+        table.count_rows(None).await.unwrap();
+        table.checkout_latest().await.unwrap();
+        table.count_rows(None).await.unwrap();
+
+        // The read after checkout_latest starts from a clean slate.
+        let reqs = requests.lock().unwrap();
+        assert!(
+            !reqs
+                .last()
+                .unwrap()
+                .contains_key("x-lancedb-min-read-version")
+        );
+    }
+
     /// Like `capturing_handler`, but keeps a per-path snapshot of the headers
     /// from every request so tests can assert on a specific endpoint.
     #[allow(clippy::type_complexity)]

rust/lancedb/src/table/query.rs

@@ -579,24 +579,45 @@ fn array_to_f32_vec(arr: &Arc<dyn arrow_array::Array>) -> Result<Vec<f32>> {
     })
 }
 
+/// Magic bytes that prefix (and suffix) the Arrow IPC *file* format.
+const ARROW_IPC_FILE_MAGIC: &[u8] = b"ARROW1";
+
 /// Parse Arrow IPC response from the namespace server.
+///
+/// The server may return either the Arrow IPC *file* format or the *stream*
+/// format. REST/phalanx returns the file format (it begins with the `ARROW1`
+/// magic); reading that with a `StreamReader` fails with "failed to fill whole
+/// buffer". Detect the magic and pick the matching reader so both are handled.
 async fn parse_arrow_ipc_response(bytes: bytes::Bytes) -> Result<DatasetRecordBatchStream> {
-    use arrow_ipc::reader::StreamReader;
+    use arrow_ipc::reader::{FileReader, StreamReader};
     use std::io::Cursor;
 
-    let cursor = Cursor::new(bytes);
-    let reader = StreamReader::try_new(cursor, None).map_err(|e| Error::Runtime {
-        message: format!("Failed to parse Arrow IPC response: {}", e),
-    })?;
-
-    // Collect all record batches
-    let schema = reader.schema();
-    let batches: Vec<_> = reader
-        .into_iter()
-        .collect::<std::result::Result<Vec<_>, _>>()
-        .map_err(|e| Error::Runtime {
-            message: format!("Failed to read Arrow IPC batches: {}", e),
+    let (schema, batches) = if bytes.starts_with(ARROW_IPC_FILE_MAGIC) {
+        let reader = FileReader::try_new(Cursor::new(bytes), None).map_err(|e| Error::Runtime {
+            message: format!("Failed to parse Arrow IPC file response: {}", e),
         })?;
+        let schema = reader.schema();
+        let batches = reader
+            .into_iter()
+            .collect::<std::result::Result<Vec<_>, _>>()
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to read Arrow IPC file batches: {}", e),
+            })?;
+        (schema, batches)
+    } else {
+        let reader =
+            StreamReader::try_new(Cursor::new(bytes), None).map_err(|e| Error::Runtime {
+                message: format!("Failed to parse Arrow IPC response: {}", e),
+            })?;
+        let schema = reader.schema();
+        let batches = reader
+            .into_iter()
+            .collect::<std::result::Result<Vec<_>, _>>()
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to read Arrow IPC batches: {}", e),
+            })?;
+        (schema, batches)
+    };
 
     // Create a stream from the batches
     let stream = futures::stream::iter(batches.into_iter().map(Ok));
@@ -624,6 +645,59 @@ mod tests {
         FixedSizeListArray::try_new_from_values(Float32Array::from(values), dimension).unwrap()
     }
 
+    #[tokio::test]
+    async fn test_parse_arrow_ipc_response_handles_file_and_stream() {
+        use arrow_array::{Int32Array, RecordBatch};
+        use arrow_ipc::writer::{FileWriter, StreamWriter};
+        use arrow_schema::{DataType, Field, Schema};
+
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from(vec![1, 2, 3])) as ArrayRef],
+        )
+        .unwrap();
+
+        // Arrow IPC *file* format -- what REST/phalanx returns. Previously this
+        // failed with "failed to fill whole buffer" because we used a StreamReader.
+        let mut file_buf = Vec::new();
+        {
+            let mut writer = FileWriter::try_new(&mut file_buf, &schema).unwrap();
+            writer.write(&batch).unwrap();
+            writer.finish().unwrap();
+        }
+        assert!(file_buf.starts_with(ARROW_IPC_FILE_MAGIC));
+        let rows: usize = parse_arrow_ipc_response(bytes::Bytes::from(file_buf))
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap()
+            .iter()
+            .map(|b| b.num_rows())
+            .sum();
+        assert_eq!(rows, 3);
+
+        // Arrow IPC *stream* format must still parse.
+        let mut stream_buf = Vec::new();
+        {
+            let mut writer = StreamWriter::try_new(&mut stream_buf, &schema).unwrap();
+            writer.write(&batch).unwrap();
+            writer.finish().unwrap();
+        }
+        assert!(!stream_buf.starts_with(ARROW_IPC_FILE_MAGIC));
+        let rows: usize = parse_arrow_ipc_response(bytes::Bytes::from(stream_buf))
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap()
+            .iter()
+            .map(|b| b.num_rows())
+            .sum();
+        assert_eq!(rows, 3);
+    }
+
     #[test]
     fn test_convert_to_namespace_query_vector() {
         let query_vector = Arc::new(Float32Array::from(vec![1.0, 2.0, 3.0, 4.0]));