Upgrade spiceai-52 to Vortex 0.68.0

.config/nextest.toml

@@ -0,0 +1,3 @@
+[[profile.default.overrides]]
+filter = 'test(compress_large_int)'
+priority = 100

.github/actions/check-rebuild/action.yml

@@ -0,0 +1,23 @@
+name: "Build and verify rebuild is a no-op"
+description: "Run a cargo command, then re-run it to verify all artifacts are cached"
+inputs:
+  command:
+    description: "The cargo build command to run and verify (--message-format json is appended on the verification run)"
+    required: true
+runs:
+  using: "composite"
+  steps:
+    - name: "Build"
+      shell: bash
+      run: ${{ inputs.command }}
+    - name: "Verify rebuild is a no-op"
+      shell: bash
+      run: |
+        stale=$(${{ inputs.command }} \
+          --message-format json 2>/dev/null \
+          | jq -r 'select(.reason == "compiler-artifact" and .fresh == false) | .target.name')
+        if [ -n "$stale" ]; then
+          echo "ERROR: Rebuild recompiled crates that should have been cached:"
+          echo "$stale"
+          exit 1
+        fi

.github/actions/setup-prebuild/action.yml

@@ -0,0 +1,49 @@
+name: "Setup Prebuild"
+description: "Prebuild AMIs — uses pre-installed tools, falls back to full setup-rust for forks"
+
+inputs:
+  repo-token:
+    description: "GitHub token for accessing the repository (typically secrets.GITHUB_TOKEN)"
+    required: false
+    default: "${{ github.token }}"
+  toolchain:
+    description: "optional override for the toolchain version (e.g. nightly)"
+    required: false
+  components:
+    description: "optional override for the components to install for the step (e.g. clippy, rustfmt, miri)"
+    default: "clippy, rustfmt"
+    required: false
+  targets:
+    description: "optional targets override (e.g. wasm32-unknown-unknown)"
+    required: false
+  enable-sccache:
+    description: "Should sccache be enabled, true by default."
+    required: false
+    default: "true"
+
+runs:
+  using: "composite"
+  steps:
+    # Prebuild path: tools already installed, just configure sccache
+    - name: Configure sccache timeout
+      if: github.repository == 'vortex-data/vortex' && inputs.enable-sccache == 'true'
+      shell: bash
+      run: |
+        mkdir -p ~/.config/sccache
+        echo 'server_startup_timeout_ms = 60000' > ~/.config/sccache/config
+
+    - name: Pre-start sccache server
+      if: github.repository == 'vortex-data/vortex' && inputs.enable-sccache == 'true'
+      shell: bash
+      run: sccache --start-server
+
+    # Fallback path: full setup for forks
+    - name: Full Rust setup
+      if: github.repository != 'vortex-data/vortex'
+      uses: ./.github/actions/setup-rust
+      with:
+        repo-token: ${{ inputs.repo-token }}
+        toolchain: ${{ inputs.toolchain }}
+        components: ${{ inputs.components }}
+        targets: ${{ inputs.targets }}
+        enable-sccache: ${{ inputs.enable-sccache }}

.github/actions/setup-rust/action.yml

@@ -3,9 +3,9 @@ description: "Toolchain setup and Initial compilation"
 
 inputs:
   repo-token:
-    description: "Deprecated: no longer used. Protoc is now downloaded directly from GitHub releases CDN."
+    description: "GitHub token for accessing the repository (typically secrets.GITHUB_TOKEN)"
     required: false
-    default: ""
+    default: "${{ github.token }}"
   toolchain:
     description: "optional override for the toolchain version (e.g. nightly)"
     required: false
@@ -38,21 +38,58 @@ runs:
       if: runner.os == 'Linux'
       uses: rui314/setup-mold@v1
 
+    - name: Check for rustup
+      id: check-rustup
+      shell: bash
+      run: echo "exists=$(command -v rustup &> /dev/null && echo 'true' || echo 'false')" >> $GITHUB_OUTPUT
+
     - name: Rust Toolchain
       id: rust-toolchain
       uses: dtolnay/rust-toolchain@stable
-      if: steps.rustup-cache.outputs.cache-hit != 'true'
+      if: steps.check-rustup.outputs.exists != 'true'
       with:
         toolchain: "${{ steps.toolchain-config.outputs.toolchain }}"
         targets: "${{ inputs.targets }}"
         components: "${{ inputs.components }}"
 
+    - name: Install additional targets and components
+      if: steps.check-rustup.outputs.exists == 'true'
+      shell: bash
+      run: |
+        rustup toolchain install "$TOOLCHAIN"
+        [[ -n "$TARGETS" ]] && rustup target add --toolchain "$TOOLCHAIN" ${TARGETS//,/ }
+        [[ -n "$COMPONENTS" ]] && rustup component add --toolchain "$TOOLCHAIN" ${COMPONENTS//,/ }
+      env:
+        TOOLCHAIN: ${{ steps.toolchain-config.outputs.toolchain }}
+        TARGETS: ${{ inputs.targets }}
+        COMPONENTS: ${{ inputs.components }}
+
+    - name: Configure sccache timeout
+      if: inputs.enable-sccache == 'true'
+      shell: bash
+      run: |
+        mkdir -p ~/.config/sccache
+        echo 'server_startup_timeout_ms = 60000' > ~/.config/sccache/config
+
     - name: Rust Compile Cache
       if: inputs.enable-sccache == 'true'
       uses: mozilla-actions/sccache-action@v0.0.9
-      with:
-        version: "v0.14.0"
+
+    - name: Pre-start sccache server
+      if: inputs.enable-sccache == 'true'
+      shell: bash
+      run: sccache --start-server
 
     - name: Install Protoc (for lance-encoding build step)
       if: runner.os != 'Windows'
       uses: ./.github/actions/setup-protoc
+
+    - name: Install Sweep
+      shell: bash
+      if: ${{ inputs.timestamp == 'true' && github.ref_name == 'develop' }}
+      run: cargo install cargo-sweep
+
+    - name: Timestamp Cache
+      shell: bash
+      if: ${{ inputs.timestamp == 'true' && github.ref_name == 'develop' }}
+      run: cargo sweep --stamp

.github/runs-on.yml

@@ -1,11 +1 @@
-images:
-  vortex-ci-amd64:
-    platform: "linux"
-    arch: "x64"
-    name: "vortex-ci-*"
-    owner: "375504701696"
-  vortex-ci-arm64:
-    platform: "linux"
-    arch: "arm64"
-    name: "vortex-ci-*"
-    owner: "375504701696"
+_extends: .github-private

.github/scripts/fuzz_report/cli.py

@@ -363,8 +363,9 @@ def cmd_report(args: argparse.Namespace) -> int:
         print(f"Commented on #{existing_issue}", file=sys.stderr)
         _write_github_output("issue_number", str(existing_issue))
     else:
-        fuzz_target = variables.get("FUZZ_TARGET", "unknown")
-        title = f"Fuzzing Crash: {crash_info.error_variant} in {fuzz_target}"
+        # Use FUZZ_NAME for the title (descriptive name), fall back to FUZZ_TARGET
+        fuzz_name = variables.get("FUZZ_NAME") or variables.get("FUZZ_TARGET", "unknown")
+        title = f"Fuzzing Crash: {crash_info.error_variant} in {fuzz_name}"
 
         body = render_template(str(TEMPLATES_DIR / "new_issue.md"), variables, use_env=False)
         body_file = Path("issue_body.md")

.github/scripts/fuzz_report/templates/new_issue.md

@@ -5,6 +5,7 @@
 **Crash Location**: `{{CRASH_LOCATION}}`
 
 **Error Message**:
+
 ```
 {{PANIC_MESSAGE}}
 ```
@@ -15,6 +16,7 @@
 ```
 {{STACK_TRACE_RAW}}
 ```
+
 </details>
 {% if CLAUDE_ANALYSIS %}
 
@@ -31,23 +33,66 @@
 - **Commit**: {{COMMIT}}
 - **Crash Artifact**: {{ARTIFACT_URL}}
 
-### Reproduction
+### Reproduce
+
+```bash
+cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+```
+
+<details>
+<summary>Reproduction Steps</summary>
+
+1. Download the crash artifact: {{ARTIFACT_URL}}
 
-1. Download the crash artifact:
-   - **Direct download**: {{ARTIFACT_URL}}
-   - Extract the zip file
+2. Assuming you download the zipfile to `~/Downloads`, and your working directory is the repository root:
 
-2. Reproduce locally:
 ```bash
-cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} {{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+# Create the artifacts directory if you haven't already.
+mkdir -p ./fuzz/artifacts
+
+# Move the zipfile.
+mv ~/Downloads/{{FUZZ_TARGET}}-crash-artifacts.zip ./fuzz/artifacts/
+
+# Unzip the zipfile.
+unzip ./fuzz/artifacts/{{FUZZ_TARGET}}-crash-artifacts.zip -d ./fuzz/artifacts/
+
+# You can remove the zipfile now if you want to.
+rm ./fuzz/artifacts/{{FUZZ_TARGET}}-crash-artifacts.zip
 ```
 
-3. Get full backtrace:
+3. Reproduce the crash:
+
 ```bash
-RUST_BACKTRACE=full cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} {{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
 ```
 
+If you want a backtrace:
+
+```bash
+RUST_BACKTRACE=1 cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+```
+
+```bash
+RUST_BACKTRACE=full cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+```
+
+</details>
+
+<details>
+<summary>Single command to get a backtrace</summary>
+
+```bash
+mkdir -p ./fuzz/artifacts
+mv ~/Downloads/{{FUZZ_TARGET}}-crash-artifacts.zip ./fuzz/artifacts/
+unzip ./fuzz/artifacts/{{FUZZ_TARGET}}-crash-artifacts.zip -d ./fuzz/artifacts/
+rm ./fuzz/artifacts/{{FUZZ_TARGET}}-crash-artifacts.zip
+RUST_BACKTRACE=1 cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+```
+
+</details>
+
 <!-- seed_hash:{{SEED_HASH}} stack_hash:{{STACK_TRACE_HASH}} message_hash:{{MESSAGE_HASH}} -->
 
 ---
-*Auto-created by fuzzing workflow*
+
+_Auto-created by fuzzing workflow_

.github/scripts/run-sql-bench.sh

@@ -15,6 +15,7 @@
 #
 # Options:
 #   --scale-factor <sf>       Scale factor for the benchmark (e.g., 1.0, 10.0)
+#   --iterations <n>          Number of iterations to pass to each benchmark binary
 #   --remote-storage <url>    Remote storage URL (e.g., s3://bucket/path/)
 #                             If provided, runs in remote mode (no lance support).
 #   --benchmark-id <id>       Benchmark ID for error messages (e.g., tpch-s3)
@@ -26,6 +27,7 @@ targets="$2"
 shift 2
 
 scale_factor=""
+iterations=""
 remote_storage=""
 benchmark_id=""
 
@@ -35,6 +37,10 @@ while [[ $# -gt 0 ]]; do
             scale_factor="$2"
             shift 2
             ;;
+        --iterations)
+            iterations="$2"
+            shift 2
+            ;;
         --remote-storage)
             remote_storage="$2"
             shift 2
@@ -91,6 +97,9 @@ if [[ -n "$scale_factor" ]]; then
         opts="--opt scale-factor=$scale_factor"
     fi
 fi
+if [[ -n "$iterations" ]]; then
+    opts="-i $iterations $opts"
+fi
 
 touch results.json
 

.github/workflows/approvals.yml

@@ -0,0 +1,46 @@
+name: PR Approval Check
+
+on:
+  pull_request_review:
+    types: [submitted, dismissed]
+
+jobs:
+  check-approvals:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check required approvals
+        uses: actions/github-script@450193c5abd4cdb17ba9f3ffcfe8f635c4bb6c2a
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+            const reviews = await github.rest.pulls.listReviews({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: pr.number,
+            });
+
+            // Count unique human approvals (latest review per user)
+            const latestByUser = {};
+            for (const review of reviews.data) {
+              if (review.user.type === 'Bot') continue;
+              latestByUser[review.user.login] = review.state;
+            }
+            const approvalCount = Object.values(latestByUser)
+              .filter(state => state === 'APPROVED').length;
+
+            // Determine if PR author is a bot/GitHub Actions
+            const authorType = pr.user.type;        // 'Bot' vs 'User'
+            const authorLogin = pr.user.login;       // e.g. 'github-actions[bot]'
+            const isBot = authorType === 'Bot' || authorLogin.endsWith('[bot]');
+
+            const required = isBot ? 2 : 1;
+
+            console.log(`PR author: ${authorLogin} (${authorType}), isBot: ${isBot}`);
+            console.log(`Approvals: ${approvalCount} / ${required} required`);
+
+            if (approvalCount < required) {
+              core.setFailed(
+                `This PR needs ${required} human approval(s) but has ${approvalCount}. ` +
+                `(Author is ${isBot ? 'a bot' : 'human'})`
+              );
+            }